diff options
Diffstat (limited to 'include')
61 files changed, 4091 insertions, 111 deletions
diff --git a/include/asm-i386/irq.h b/include/asm-i386/irq.h index 9e15ce0006e..36f310632c4 100644 --- a/include/asm-i386/irq.h +++ b/include/asm-i386/irq.h @@ -41,6 +41,7 @@ extern int irqbalance_disable(char *str); extern void fixup_irqs(cpumask_t map); #endif +unsigned int do_IRQ(struct pt_regs *regs); void init_IRQ(void); void __init native_init_IRQ(void); diff --git a/include/asm-i386/mach-default/irq_vectors_limits.h b/include/asm-i386/mach-default/irq_vectors_limits.h index 7f161e760be..a90c7a60109 100644 --- a/include/asm-i386/mach-default/irq_vectors_limits.h +++ b/include/asm-i386/mach-default/irq_vectors_limits.h @@ -1,7 +1,7 @@ #ifndef _ASM_IRQ_VECTORS_LIMITS_H #define _ASM_IRQ_VECTORS_LIMITS_H -#ifdef CONFIG_X86_IO_APIC +#if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT) #define NR_IRQS 224 # if (224 >= 32 * NR_CPUS) # define NR_IRQ_VECTORS NR_IRQS diff --git a/include/asm-i386/mmu_context.h b/include/asm-i386/mmu_context.h index 8198d1cca1f..7eb0b0b1fb3 100644 --- a/include/asm-i386/mmu_context.h +++ b/include/asm-i386/mmu_context.h @@ -32,6 +32,8 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) #endif } +void leave_mm(unsigned long cpu); + static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) diff --git a/include/asm-i386/paravirt.h b/include/asm-i386/paravirt.h index 7f846a7d6bc..7df88be2dd9 100644 --- a/include/asm-i386/paravirt.h +++ b/include/asm-i386/paravirt.h @@ -52,6 +52,8 @@ struct paravirt_ops /* Basic arch-specific setup */ void (*arch_setup)(void); char *(*memory_setup)(void); + void (*post_allocator_init)(void); + void (*init_IRQ)(void); void (*time_init)(void); @@ -116,7 +118,7 @@ struct paravirt_ops u64 (*read_tsc)(void); u64 (*read_pmc)(void); - u64 (*get_scheduled_cycles)(void); + unsigned long long (*sched_clock)(void); unsigned long (*get_cpu_khz)(void); /* Segment descriptor handling */ @@ -173,7 +175,7 @@ struct paravirt_ops unsigned long va); /* Hooks for allocating/releasing pagetable pages */ - void (*alloc_pt)(u32 pfn); + void (*alloc_pt)(struct mm_struct *mm, u32 pfn); void (*alloc_pd)(u32 pfn); void (*alloc_pd_clone)(u32 pfn, u32 clonepfn, u32 start, u32 count); void (*release_pt)(u32 pfn); @@ -260,6 +262,7 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *site, unsigned len) unsigned paravirt_patch_insns(void *site, unsigned len, const char *start, const char *end); +int paravirt_disable_iospace(void); /* * This generates an indirect call based on the operation type number. @@ -563,7 +566,10 @@ static inline u64 paravirt_read_tsc(void) #define rdtscll(val) (val = paravirt_read_tsc()) -#define get_scheduled_cycles(val) (val = paravirt_ops.get_scheduled_cycles()) +static inline unsigned long long paravirt_sched_clock(void) +{ + return PVOP_CALL0(unsigned long long, sched_clock); +} #define calculate_cpu_khz() (paravirt_ops.get_cpu_khz()) #define write_tsc(val1,val2) wrmsr(0x10, val1, val2) @@ -669,6 +675,12 @@ static inline void setup_secondary_clock(void) } #endif +static inline void paravirt_post_allocator_init(void) +{ + if (paravirt_ops.post_allocator_init) + (*paravirt_ops.post_allocator_init)(); +} + static inline void paravirt_pagetable_setup_start(pgd_t *base) { if (paravirt_ops.pagetable_setup_start) @@ -725,9 +737,9 @@ static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm, PVOP_VCALL3(flush_tlb_others, &cpumask, mm, va); } -static inline void paravirt_alloc_pt(unsigned pfn) +static inline void paravirt_alloc_pt(struct mm_struct *mm, unsigned pfn) { - PVOP_VCALL1(alloc_pt, pfn); + PVOP_VCALL2(alloc_pt, mm, pfn); } static inline void paravirt_release_pt(unsigned pfn) { diff --git a/include/asm-i386/pgalloc.h b/include/asm-i386/pgalloc.h index d07b7afc269..f2fc33ceb9f 100644 --- a/include/asm-i386/pgalloc.h +++ b/include/asm-i386/pgalloc.h @@ -7,7 +7,7 @@ #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else -#define paravirt_alloc_pt(pfn) do { } while (0) +#define paravirt_alloc_pt(mm, pfn) do { } while (0) #define paravirt_alloc_pd(pfn) do { } while (0) #define paravirt_alloc_pd(pfn) do { } while (0) #define paravirt_alloc_pd_clone(pfn, clonepfn, start, count) do { } while (0) @@ -17,13 +17,13 @@ #define pmd_populate_kernel(mm, pmd, pte) \ do { \ - paravirt_alloc_pt(__pa(pte) >> PAGE_SHIFT); \ + paravirt_alloc_pt(mm, __pa(pte) >> PAGE_SHIFT); \ set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte))); \ } while (0) #define pmd_populate(mm, pmd, pte) \ do { \ - paravirt_alloc_pt(page_to_pfn(pte)); \ + paravirt_alloc_pt(mm, page_to_pfn(pte)); \ set_pmd(pmd, __pmd(_PAGE_TABLE + \ ((unsigned long long)page_to_pfn(pte) << \ (unsigned long long) PAGE_SHIFT))); \ diff --git a/include/asm-i386/setup.h b/include/asm-i386/setup.h index 0d5bff9dc4a..7862fe858a9 100644 --- a/include/asm-i386/setup.h +++ b/include/asm-i386/setup.h @@ -81,6 +81,10 @@ void __init add_memory_region(unsigned long long start, extern unsigned long init_pg_tables_end; +#ifndef CONFIG_PARAVIRT +#define paravirt_post_allocator_init() do {} while (0) +#endif + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/include/asm-i386/smp.h b/include/asm-i386/smp.h index 0c713278706..1f73bde165b 100644 --- a/include/asm-i386/smp.h +++ b/include/asm-i386/smp.h @@ -43,9 +43,12 @@ extern u8 x86_cpu_to_apicid[]; #define cpu_physical_id(cpu) x86_cpu_to_apicid[cpu] +extern void set_cpu_sibling_map(int cpu); + #ifdef CONFIG_HOTPLUG_CPU extern void cpu_exit_clear(void); extern void cpu_uninit(void); +extern void remove_siblinginfo(int cpu); #endif struct smp_ops @@ -129,6 +132,8 @@ extern int __cpu_disable(void); extern void __cpu_die(unsigned int cpu); extern unsigned int num_processors; +void __cpuinit smp_store_cpu_info(int id); + #endif /* !__ASSEMBLY__ */ #else /* CONFIG_SMP */ diff --git a/include/asm-i386/timer.h b/include/asm-i386/timer.h index 153770e25fa..51a713e33a9 100644 --- a/include/asm-i386/timer.h +++ b/include/asm-i386/timer.h @@ -15,8 +15,38 @@ extern int no_sync_cmos_clock; extern int recalibrate_cpu_khz(void); #ifndef CONFIG_PARAVIRT -#define get_scheduled_cycles(val) rdtscll(val) #define calculate_cpu_khz() native_calculate_cpu_khz() #endif +/* Accellerators for sched_clock() + * convert from cycles(64bits) => nanoseconds (64bits) + * basic equation: + * ns = cycles / (freq / ns_per_sec) + * ns = cycles * (ns_per_sec / freq) + * ns = cycles * (10^9 / (cpu_khz * 10^3)) + * ns = cycles * (10^6 / cpu_khz) + * + * Then we use scaling math (suggested by george@mvista.com) to get: + * ns = cycles * (10^6 * SC / cpu_khz) / SC + * ns = cycles * cyc2ns_scale / SC + * + * And since SC is a constant power of two, we can convert the div + * into a shift. + * + * We can use khz divisor instead of mhz to keep a better percision, since + * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. + * (mathieu.desnoyers@polymtl.ca) + * + * -johnstul@us.ibm.com "math is hard, lets go shopping!" + */ +extern unsigned long cyc2ns_scale __read_mostly; + +#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */ + +static inline unsigned long long cycles_2_ns(unsigned long long cyc) +{ + return (cyc * cyc2ns_scale) >> CYC2NS_SCALE_FACTOR; +} + + #endif diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h index e84ace1ec8b..9b15545eb9b 100644 --- a/include/asm-i386/unistd.h +++ b/include/asm-i386/unistd.h @@ -329,10 +329,11 @@ #define __NR_signalfd 321 #define __NR_timerfd 322 #define __NR_eventfd 323 +#define __NR_fallocate 324 #ifdef __KERNEL__ -#define NR_syscalls 324 +#define NR_syscalls 325 #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR diff --git a/include/asm-i386/vmi_time.h b/include/asm-i386/vmi_time.h index 213930b995c..47818813032 100644 --- a/include/asm-i386/vmi_time.h +++ b/include/asm-i386/vmi_time.h @@ -49,7 +49,7 @@ extern struct vmi_timer_ops { extern void __init vmi_time_init(void); extern unsigned long vmi_get_wallclock(void); extern int vmi_set_wallclock(unsigned long now); -extern unsigned long long vmi_get_sched_cycles(void); +extern unsigned long long vmi_sched_clock(void); extern unsigned long vmi_cpu_khz(void); #ifdef CONFIG_X86_LOCAL_APIC diff --git a/include/asm-i386/xen/hypercall.h b/include/asm-i386/xen/hypercall.h new file mode 100644 index 00000000000..bc0ee7d961c --- /dev/null +++ b/include/asm-i386/xen/hypercall.h @@ -0,0 +1,413 @@ +/****************************************************************************** + * hypercall.h + * + * Linux-specific hypervisor handling. + * + * Copyright (c) 2002-2004, K A Fraser + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __HYPERCALL_H__ +#define __HYPERCALL_H__ + +#include <linux/errno.h> +#include <linux/string.h> + +#include <xen/interface/xen.h> +#include <xen/interface/sched.h> +#include <xen/interface/physdev.h> + +extern struct { char _entry[32]; } hypercall_page[]; + +#define _hypercall0(type, name) \ +({ \ + long __res; \ + asm volatile ( \ + "call %[call]" \ + : "=a" (__res) \ + : [call] "m" (hypercall_page[__HYPERVISOR_##name]) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall1(type, name, a1) \ +({ \ + long __res, __ign1; \ + asm volatile ( \ + "call %[call]" \ + : "=a" (__res), "=b" (__ign1) \ + : "1" ((long)(a1)), \ + [call] "m" (hypercall_page[__HYPERVISOR_##name]) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall2(type, name, a1, a2) \ +({ \ + long __res, __ign1, __ign2; \ + asm volatile ( \ + "call %[call]" \ + : "=a" (__res), "=b" (__ign1), "=c" (__ign2) \ + : "1" ((long)(a1)), "2" ((long)(a2)), \ + [call] "m" (hypercall_page[__HYPERVISOR_##name]) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall3(type, name, a1, a2, a3) \ +({ \ + long __res, __ign1, __ign2, __ign3; \ + asm volatile ( \ + "call %[call]" \ + : "=a" (__res), "=b" (__ign1), "=c" (__ign2), \ + "=d" (__ign3) \ + : "1" ((long)(a1)), "2" ((long)(a2)), \ + "3" ((long)(a3)), \ + [call] "m" (hypercall_page[__HYPERVISOR_##name]) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall4(type, name, a1, a2, a3, a4) \ +({ \ + long __res, __ign1, __ign2, __ign3, __ign4; \ + asm volatile ( \ + "call %[call]" \ + : "=a" (__res), "=b" (__ign1), "=c" (__ign2), \ + "=d" (__ign3), "=S" (__ign4) \ + : "1" ((long)(a1)), "2" ((long)(a2)), \ + "3" ((long)(a3)), "4" ((long)(a4)), \ + [call] "m" (hypercall_page[__HYPERVISOR_##name]) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall5(type, name, a1, a2, a3, a4, a5) \ +({ \ + long __res, __ign1, __ign2, __ign3, __ign4, __ign5; \ + asm volatile ( \ + "call %[call]" \ + : "=a" (__res), "=b" (__ign1), "=c" (__ign2), \ + "=d" (__ign3), "=S" (__ign4), "=D" (__ign5) \ + : "1" ((long)(a1)), "2" ((long)(a2)), \ + "3" ((long)(a3)), "4" ((long)(a4)), \ + "5" ((long)(a5)), \ + [call] "m" (hypercall_page[__HYPERVISOR_##name]) \ + : "memory" ); \ + (type)__res; \ +}) + +static inline int +HYPERVISOR_set_trap_table(struct trap_info *table) +{ + return _hypercall1(int, set_trap_table, table); +} + +static inline int +HYPERVISOR_mmu_update(struct mmu_update *req, int count, + int *success_count, domid_t domid) +{ + return _hypercall4(int, mmu_update, req, count, success_count, domid); +} + +static inline int +HYPERVISOR_mmuext_op(struct mmuext_op *op, int count, + int *success_count, domid_t domid) +{ + return _hypercall4(int, mmuext_op, op, count, success_count, domid); +} + +static inline int +HYPERVISOR_set_gdt(unsigned long *frame_list, int entries) +{ + return _hypercall2(int, set_gdt, frame_list, entries); +} + +static inline int +HYPERVISOR_stack_switch(unsigned long ss, unsigned long esp) +{ + return _hypercall2(int, stack_switch, ss, esp); +} + +static inline int +HYPERVISOR_set_callbacks(unsigned long event_selector, + unsigned long event_address, + unsigned long failsafe_selector, + unsigned long failsafe_address) +{ + return _hypercall4(int, set_callbacks, + event_selector, event_address, + failsafe_selector, failsafe_address); +} + +static inline int +HYPERVISOR_fpu_taskswitch(int set) +{ + return _hypercall1(int, fpu_taskswitch, set); +} + +static inline int +HYPERVISOR_sched_op(int cmd, unsigned long arg) +{ + return _hypercall2(int, sched_op, cmd, arg); +} + +static inline long +HYPERVISOR_set_timer_op(u64 timeout) +{ + unsigned long timeout_hi = (unsigned long)(timeout>>32); + unsigned long timeout_lo = (unsigned long)timeout; + return _hypercall2(long, set_timer_op, timeout_lo, timeout_hi); +} + +static inline int +HYPERVISOR_set_debugreg(int reg, unsigned long value) +{ + return _hypercall2(int, set_debugreg, reg, value); +} + +static inline unsigned long +HYPERVISOR_get_debugreg(int reg) +{ + return _hypercall1(unsigned long, get_debugreg, reg); +} + +static inline int +HYPERVISOR_update_descriptor(u64 ma, u64 desc) +{ + return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32); +} + +static inline int +HYPERVISOR_memory_op(unsigned int cmd, void *arg) +{ + return _hypercall2(int, memory_op, cmd, arg); +} + +static inline int +HYPERVISOR_multicall(void *call_list, int nr_calls) +{ + return _hypercall2(int, multicall, call_list, nr_calls); +} + +static inline int +HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val, + unsigned long flags) +{ + unsigned long pte_hi = 0; +#ifdef CONFIG_X86_PAE + pte_hi = new_val.pte_high; +#endif + return _hypercall4(int, update_va_mapping, va, + new_val.pte_low, pte_hi, flags); +} + +static inline int +HYPERVISOR_event_channel_op(int cmd, void *arg) +{ + int rc = _hypercall2(int, event_channel_op, cmd, arg); + if (unlikely(rc == -ENOSYS)) { + struct evtchn_op op; + op.cmd = cmd; + memcpy(&op.u, arg, sizeof(op.u)); + rc = _hypercall1(int, event_channel_op_compat, &op); + memcpy(arg, &op.u, sizeof(op.u)); + } + return rc; +} + +static inline int +HYPERVISOR_xen_version(int cmd, void *arg) +{ + return _hypercall2(int, xen_version, cmd, arg); +} + +static inline int +HYPERVISOR_console_io(int cmd, int count, char *str) +{ + return _hypercall3(int, console_io, cmd, count, str); +} + +static inline int +HYPERVISOR_physdev_op(int cmd, void *arg) +{ + int rc = _hypercall2(int, physdev_op, cmd, arg); + if (unlikely(rc == -ENOSYS)) { + struct physdev_op op; + op.cmd = cmd; + memcpy(&op.u, arg, sizeof(op.u)); + rc = _hypercall1(int, physdev_op_compat, &op); + memcpy(arg, &op.u, sizeof(op.u)); + } + return rc; +} + +static inline int +HYPERVISOR_grant_table_op(unsigned int cmd, void *uop, unsigned int count) +{ + return _hypercall3(int, grant_table_op, cmd, uop, count); +} + +static inline int +HYPERVISOR_update_va_mapping_otherdomain(unsigned long va, pte_t new_val, + unsigned long flags, domid_t domid) +{ + unsigned long pte_hi = 0; +#ifdef CONFIG_X86_PAE + pte_hi = new_val.pte_high; +#endif + return _hypercall5(int, update_va_mapping_otherdomain, va, + new_val.pte_low, pte_hi, flags, domid); +} + +static inline int +HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type) +{ + return _hypercall2(int, vm_assist, cmd, type); +} + +static inline int +HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args) +{ + return _hypercall3(int, vcpu_op, cmd, vcpuid, extra_args); +} + +static inline int +HYPERVISOR_suspend(unsigned long srec) +{ + return _hypercall3(int, sched_op, SCHEDOP_shutdown, + SHUTDOWN_suspend, srec); +} + +static inline int +HYPERVISOR_nmi_op(unsigned long op, unsigned long arg) +{ + return _hypercall2(int, nmi_op, op, arg); +} + +static inline void +MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va, + pte_t new_val, unsigned long flags) +{ + mcl->op = __HYPERVISOR_update_va_mapping; + mcl->args[0] = va; +#ifdef CONFIG_X86_PAE + mcl->args[1] = new_val.pte_low; + mcl->args[2] = new_val.pte_high; +#else + mcl->args[1] = new_val.pte_low; + mcl->args[2] = 0; +#endif + mcl->args[3] = flags; +} + +static inline void +MULTI_grant_table_op(struct multicall_entry *mcl, unsigned int cmd, + void *uop, unsigned int count) +{ + mcl->op = __HYPERVISOR_grant_table_op; + mcl->args[0] = cmd; + mcl->args[1] = (unsigned long)uop; + mcl->args[2] = count; +} + +static inline void +MULTI_update_va_mapping_otherdomain(struct multicall_entry *mcl, unsigned long va, + pte_t new_val, unsigned long flags, + domid_t domid) +{ + mcl->op = __HYPERVISOR_update_va_mapping_otherdomain; + mcl->args[0] = va; +#ifdef CONFIG_X86_PAE + mcl->args[1] = new_val.pte_low; + mcl->args[2] = new_val.pte_high; +#else + mcl->args[1] = new_val.pte_low; + mcl->args[2] = 0; +#endif + mcl->args[3] = flags; + mcl->args[4] = domid; +} + +static inline void +MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, + struct desc_struct desc) +{ + mcl->op = __HYPERVISOR_update_descriptor; + mcl->args[0] = maddr; + mcl->args[1] = maddr >> 32; + mcl->args[2] = desc.a; + mcl->args[3] = desc.b; +} + +static inline void +MULTI_memory_op(struct multicall_entry *mcl, unsigned int cmd, void *arg) +{ + mcl->op = __HYPERVISOR_memory_op; + mcl->args[0] = cmd; + mcl->args[1] = (unsigned long)arg; +} + +static inline void +MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req, + int count, int *success_count, domid_t domid) +{ + mcl->op = __HYPERVISOR_mmu_update; + mcl->args[0] = (unsigned long)req; + mcl->args[1] = count; + mcl->args[2] = (unsigned long)success_count; + mcl->args[3] = domid; +} + +static inline void +MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count, + int *success_count, domid_t domid) +{ + mcl->op = __HYPERVISOR_mmuext_op; + mcl->args[0] = (unsigned long)op; + mcl->args[1] = count; + mcl->args[2] = (unsigned long)success_count; + mcl->args[3] = domid; +} + +static inline void +MULTI_set_gdt(struct multicall_entry *mcl, unsigned long *frames, int entries) +{ + mcl->op = __HYPERVISOR_set_gdt; + mcl->args[0] = (unsigned long)frames; + mcl->args[1] = entries; +} + +static inline void +MULTI_stack_switch(struct multicall_entry *mcl, + unsigned long ss, unsigned long esp) +{ + mcl->op = __HYPERVISOR_stack_switch; + mcl->args[0] = ss; + mcl->args[1] = esp; +} + +#endif /* __HYPERCALL_H__ */ diff --git a/include/asm-i386/xen/hypervisor.h b/include/asm-i386/xen/hypervisor.h new file mode 100644 index 00000000000..8e15dd28c91 --- /dev/null +++ b/include/asm-i386/xen/hypervisor.h @@ -0,0 +1,73 @@ +/****************************************************************************** + * hypervisor.h + * + * Linux-specific hypervisor handling. + * + * Copyright (c) 2002-2004, K A Fraser + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __HYPERVISOR_H__ +#define __HYPERVISOR_H__ + +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/version.h> + +#include <xen/interface/xen.h> +#include <xen/interface/version.h> + +#include <asm/ptrace.h> +#include <asm/page.h> +#include <asm/desc.h> +#if defined(__i386__) +# ifdef CONFIG_X86_PAE +# include <asm-generic/pgtable-nopud.h> +# else +# include <asm-generic/pgtable-nopmd.h> +# endif +#endif +#include <asm/xen/hypercall.h> + +/* arch/i386/kernel/setup.c */ +extern struct shared_info *HYPERVISOR_shared_info; +extern struct start_info *xen_start_info; +#define is_initial_xendomain() (xen_start_info->flags & SIF_INITDOMAIN) + +/* arch/i386/mach-xen/evtchn.c */ +/* Force a proper event-channel callback from Xen. */ +extern void force_evtchn_callback(void); + +/* Turn jiffies into Xen system time. */ +u64 jiffies_to_st(unsigned long jiffies); + + +#define MULTI_UVMFLAGS_INDEX 3 +#define MULTI_UVMDOMID_INDEX 4 + +#define is_running_on_xen() (xen_start_info ? 1 : 0) + +#endif /* __HYPERVISOR_H__ */ diff --git a/include/asm-i386/xen/interface.h b/include/asm-i386/xen/interface.h new file mode 100644 index 00000000000..165c3968e13 --- /dev/null +++ b/include/asm-i386/xen/interface.h @@ -0,0 +1,188 @@ +/****************************************************************************** + * arch-x86_32.h + * + * Guest OS interface to x86 32-bit Xen. + * + * Copyright (c) 2004, K A Fraser + */ + +#ifndef __XEN_PUBLIC_ARCH_X86_32_H__ +#define __XEN_PUBLIC_ARCH_X86_32_H__ + +#ifdef __XEN__ +#define __DEFINE_GUEST_HANDLE(name, type) \ + typedef struct { type *p; } __guest_handle_ ## name +#else +#define __DEFINE_GUEST_HANDLE(name, type) \ + typedef type * __guest_handle_ ## name +#endif + +#define DEFINE_GUEST_HANDLE_STRUCT(name) \ + __DEFINE_GUEST_HANDLE(name, struct name) +#define DEFINE_GUEST_HANDLE(name) __DEFINE_GUEST_HANDLE(name, name) +#define GUEST_HANDLE(name) __guest_handle_ ## name + +#ifndef __ASSEMBLY__ +/* Guest handles for primitive C types. */ +__DEFINE_GUEST_HANDLE(uchar, unsigned char); +__DEFINE_GUEST_HANDLE(uint, unsigned int); +__DEFINE_GUEST_HANDLE(ulong, unsigned long); +DEFINE_GUEST_HANDLE(char); +DEFINE_GUEST_HANDLE(int); +DEFINE_GUEST_HANDLE(long); +DEFINE_GUEST_HANDLE(void); +#endif + +/* + * SEGMENT DESCRIPTOR TABLES + */ +/* + * A number of GDT entries are reserved by Xen. These are not situated at the + * start of the GDT because some stupid OSes export hard-coded selector values + * in their ABI. These hard-coded values are always near the start of the GDT, + * so Xen places itself out of the way, at the far end of the GDT. + */ +#define FIRST_RESERVED_GDT_PAGE 14 +#define FIRST_RESERVED_GDT_BYTE (FIRST_RESERVED_GDT_PAGE * 4096) +#define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8) + +/* + * These flat segments are in the Xen-private section of every GDT. Since these + * are also present in the initial GDT, many OSes will be able to avoid + * installing their own GDT. + */ +#define FLAT_RING1_CS 0xe019 /* GDT index 259 */ +#define FLAT_RING1_DS 0xe021 /* GDT index 260 */ +#define FLAT_RING1_SS 0xe021 /* GDT index 260 */ +#define FLAT_RING3_CS 0xe02b /* GDT index 261 */ +#define FLAT_RING3_DS 0xe033 /* GDT index 262 */ +#define FLAT_RING3_SS 0xe033 /* GDT index 262 */ + +#define FLAT_KERNEL_CS FLAT_RING1_CS +#define FLAT_KERNEL_DS FLAT_RING1_DS +#define FLAT_KERNEL_SS FLAT_RING1_SS +#define FLAT_USER_CS FLAT_RING3_CS +#define FLAT_USER_DS FLAT_RING3_DS +#define FLAT_USER_SS FLAT_RING3_SS + +/* And the trap vector is... */ +#define TRAP_INSTR "int $0x82" + +/* + * Virtual addresses beyond this are not modifiable by guest OSes. The + * machine->physical mapping table starts at this address, read-only. + */ +#ifdef CONFIG_X86_PAE +#define __HYPERVISOR_VIRT_START 0xF5800000 +#else +#define __HYPERVISOR_VIRT_START 0xFC000000 +#endif + +#ifndef HYPERVISOR_VIRT_START +#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START) +#endif + +#ifndef machine_to_phys_mapping +#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START) +#endif + +/* Maximum number of virtual CPUs in multi-processor guests. */ +#define MAX_VIRT_CPUS 32 + +#ifndef __ASSEMBLY__ + +/* + * Send an array of these to HYPERVISOR_set_trap_table() + */ +#define TI_GET_DPL(_ti) ((_ti)->flags & 3) +#define TI_GET_IF(_ti) ((_ti)->flags & 4) +#define TI_SET_DPL(_ti, _dpl) ((_ti)->flags |= (_dpl)) +#define TI_SET_IF(_ti, _if) ((_ti)->flags |= ((!!(_if))<<2)) + +struct trap_info { + uint8_t vector; /* exception vector */ + uint8_t flags; /* 0-3: privilege level; 4: clear event enable? */ + uint16_t cs; /* code selector */ + unsigned long address; /* code offset */ +}; +DEFINE_GUEST_HANDLE_STRUCT(trap_info); + +struct cpu_user_regs { + uint32_t ebx; + uint32_t ecx; + uint32_t edx; + uint32_t esi; + uint32_t edi; + uint32_t ebp; + uint32_t eax; + uint16_t error_code; /* private */ + uint16_t entry_vector; /* private */ + uint32_t eip; + uint16_t cs; + uint8_t saved_upcall_mask; + uint8_t _pad0; + uint32_t eflags; /* eflags.IF == !saved_upcall_mask */ + uint32_t esp; + uint16_t ss, _pad1; + uint16_t es, _pad2; + uint16_t ds, _pad3; + uint16_t fs, _pad4; + uint16_t gs, _pad5; +}; +DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs); + +typedef uint64_t tsc_timestamp_t; /* RDTSC timestamp */ + +/* + * The following is all CPU context. Note that the fpu_ctxt block is filled + * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used. + */ +struct vcpu_guest_context { + /* FPU registers come first so they can be aligned for FXSAVE/FXRSTOR. */ + struct { char x[512]; } fpu_ctxt; /* User-level FPU registers */ +#define VGCF_I387_VALID (1<<0) +#define VGCF_HVM_GUEST (1<<1) +#define VGCF_IN_KERNEL (1<<2) + unsigned long flags; /* VGCF_* flags */ + struct cpu_user_regs user_regs; /* User-level CPU registers */ + struct trap_info trap_ctxt[256]; /* Virtual IDT */ + unsigned long ldt_base, ldt_ents; /* LDT (linear address, # ents) */ + unsigned long gdt_frames[16], gdt_ents; /* GDT (machine frames, # ents) */ + unsigned long kernel_ss, kernel_sp; /* Virtual TSS (only SS1/SP1) */ + unsigned long ctrlreg[8]; /* CR0-CR7 (control registers) */ + unsigned long debugreg[8]; /* DB0-DB7 (debug registers) */ + unsigned long event_callback_cs; /* CS:EIP of event callback */ + unsigned long event_callback_eip; + unsigned long failsafe_callback_cs; /* CS:EIP of failsafe callback */ + unsigned long failsafe_callback_eip; + unsigned long vm_assist; /* VMASST_TYPE_* bitmap */ +}; +DEFINE_GUEST_HANDLE_STRUCT(vcpu_guest_context); + +struct arch_shared_info { + unsigned long max_pfn; /* max pfn that appears in table */ + /* Frame containing list of mfns containing list of mfns containing p2m. */ + unsigned long pfn_to_mfn_frame_list_list; + unsigned long nmi_reason; +}; + +struct arch_vcpu_info { + unsigned long cr2; + unsigned long pad[5]; /* sizeof(struct vcpu_info) == 64 */ +}; + +#endif /* !__ASSEMBLY__ */ + +/* + * Prefix forces emulation of some non-trapping instructions. + * Currently only CPUID. + */ +#ifdef __ASSEMBLY__ +#define XEN_EMULATE_PREFIX .byte 0x0f,0x0b,0x78,0x65,0x6e ; +#define XEN_CPUID XEN_EMULATE_PREFIX cpuid +#else +#define XEN_EMULATE_PREFIX ".byte 0x0f,0x0b,0x78,0x65,0x6e ; " +#define XEN_CPUID XEN_EMULATE_PREFIX "cpuid" +#endif + +#endif diff --git a/include/asm-powerpc/systbl.h b/include/asm-powerpc/systbl.h index 1cc3f9cb6f4..cc6d8722825 100644 --- a/include/asm-powerpc/systbl.h +++ b/include/asm-powerpc/systbl.h @@ -308,6 +308,7 @@ COMPAT_SYS_SPU(move_pages) SYSCALL_SPU(getcpu) COMPAT_SYS(epoll_pwait) COMPAT_SYS_SPU(utimensat) +COMPAT_SYS(fallocate) COMPAT_SYS_SPU(signalfd) COMPAT_SYS_SPU(timerfd) SYSCALL_SPU(eventfd) diff --git a/include/asm-powerpc/unistd.h b/include/asm-powerpc/unistd.h index f71c6061f1e..97d82b6a940 100644 --- a/include/asm-powerpc/unistd.h +++ b/include/asm-powerpc/unistd.h @@ -331,10 +331,11 @@ #define __NR_timerfd 306 #define __NR_eventfd 307 #define __NR_sync_file_range2 308 +#define __NR_fallocate 309 #ifdef __KERNEL__ -#define __NR_syscalls 309 +#define __NR_syscalls 310 #define __NR__exit __NR_exit #define NR_syscalls __NR_syscalls diff --git a/include/asm-sparc64/io.h b/include/asm-sparc64/io.h index ad595b67984..9565a892801 100644 --- a/include/asm-sparc64/io.h +++ b/include/asm-sparc64/io.h @@ -14,11 +14,6 @@ #define __SLOW_DOWN_IO do { } while (0) #define SLOW_DOWN_IO do { } while (0) -extern unsigned long virt_to_bus_not_defined_use_pci_map(volatile void *addr); -#define virt_to_bus virt_to_bus_not_defined_use_pci_map -extern unsigned long bus_to_virt_not_defined_use_pci_map(volatile void *addr); -#define bus_to_virt bus_to_virt_not_defined_use_pci_map - /* BIO layer definitions. */ extern unsigned long kern_base, kern_size; #define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT) diff --git a/include/asm-sparc64/mdesc.h b/include/asm-sparc64/mdesc.h index e97c4313375..1acc7272e53 100644 --- a/include/asm-sparc64/mdesc.h +++ b/include/asm-sparc64/mdesc.h @@ -61,6 +61,16 @@ extern u64 mdesc_arc_target(struct mdesc_handle *hp, u64 arc); extern void mdesc_update(void); +struct mdesc_notifier_client { + void (*add)(struct mdesc_handle *handle, u64 node); + void (*remove)(struct mdesc_handle *handle, u64 node); + + const char *node_name; + struct mdesc_notifier_client *next; +}; + +extern void mdesc_register_notifier(struct mdesc_notifier_client *client); + extern void mdesc_fill_in_cpu_data(cpumask_t mask); extern void sun4v_mdesc_init(void); diff --git a/include/asm-sparc64/vio.h b/include/asm-sparc64/vio.h index 83c96422e9d..c0a8d4ed5bc 100644 --- a/include/asm-sparc64/vio.h +++ b/include/asm-sparc64/vio.h @@ -264,7 +264,7 @@ static inline u32 vio_dring_avail(struct vio_dring_state *dr, ((dr->prod - dr->cons) & (ring_size - 1))); } -#define VIO_MAX_TYPE_LEN 64 +#define VIO_MAX_TYPE_LEN 32 #define VIO_MAX_COMPAT_LEN 64 struct vio_dev { diff --git a/include/asm-x86_64/unistd.h b/include/asm-x86_64/unistd.h index 8696f8ad401..fc4e73f5f1f 100644 --- a/include/asm-x86_64/unistd.h +++ b/include/asm-x86_64/unistd.h @@ -630,6 +630,8 @@ __SYSCALL(__NR_signalfd, sys_signalfd) __SYSCALL(__NR_timerfd, sys_timerfd) #define __NR_eventfd 284 __SYSCALL(__NR_eventfd, sys_eventfd) +#define __NR_fallocate 285 +__SYSCALL(__NR_fallocate, sys_fallocate) #ifndef __NO_STUBS #define __ARCH_WANT_OLD_READDIR diff --git a/include/linux/elfnote.h b/include/linux/elfnote.h index 9a1e0674e56..e831759b2fb 100644 --- a/include/linux/elfnote.h +++ b/include/linux/elfnote.h @@ -38,17 +38,25 @@ * e.g. ELFNOTE(XYZCo, 42, .asciz, "forty-two") * ELFNOTE(XYZCo, 12, .long, 0xdeadbeef) */ -#define ELFNOTE(name, type, desctype, descdata) \ -.pushsection .note.name, "",@note ; \ - .align 4 ; \ +#define ELFNOTE_START(name, type, flags) \ +.pushsection .note.name, flags,@note ; \ + .balign 4 ; \ .long 2f - 1f /* namesz */ ; \ - .long 4f - 3f /* descsz */ ; \ + .long 4484f - 3f /* descsz */ ; \ .long type ; \ 1:.asciz #name ; \ -2:.align 4 ; \ -3:desctype descdata ; \ -4:.align 4 ; \ +2:.balign 4 ; \ +3: + +#define ELFNOTE_END \ +4484:.balign 4 ; \ .popsection ; + +#define ELFNOTE(name, type, desc) \ + ELFNOTE_START(name, type, "") \ + desc ; \ + ELFNOTE_END + #else /* !__ASSEMBLER__ */ #include <linux/elf.h> /* diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index de1f9f78625..cdee7aaa57a 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -71,7 +71,7 @@ /* * Maximal count of links to a file */ -#define EXT4_LINK_MAX 32000 +#define EXT4_LINK_MAX 65000 /* * Macro-instructions used to manage several block sizes @@ -102,6 +102,7 @@ EXT4_GOOD_OLD_FIRST_INO : \ (s)->s_first_ino) #endif +#define EXT4_BLOCK_ALIGN(size, blkbits) ALIGN((size), (1 << (blkbits))) /* * Macro-instructions used to manage fragments @@ -201,6 +202,7 @@ struct ext4_group_desc #define EXT4_STATE_JDATA 0x00000001 /* journaled data exists */ #define EXT4_STATE_NEW 0x00000002 /* inode is newly created */ #define EXT4_STATE_XATTR 0x00000004 /* has in-inode xattrs */ +#define EXT4_STATE_NO_EXPAND 0x00000008 /* No space for expansion */ /* Used to pass group descriptor data when online resize is done */ struct ext4_new_group_input { @@ -225,6 +227,11 @@ struct ext4_new_group_data { __u32 free_blocks_count; }; +/* + * Following is used by preallocation code to tell get_blocks() that we + * want uninitialzed extents. + */ +#define EXT4_CREATE_UNINITIALIZED_EXT 2 /* * ioctl commands @@ -237,7 +244,7 @@ struct ext4_new_group_data { #define EXT4_IOC_GROUP_ADD _IOW('f', 8,struct ext4_new_group_input) #define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION #define EXT4_IOC_SETVERSION_OLD FS_IOC_SETVERSION -#ifdef CONFIG_JBD_DEBUG +#ifdef CONFIG_JBD2_DEBUG #define EXT4_IOC_WAIT_FOR_READONLY _IOR('f', 99, long) #endif #define EXT4_IOC_GETRSVSZ _IOR('f', 5, long) @@ -253,7 +260,7 @@ struct ext4_new_group_data { #define EXT4_IOC32_GETRSVSZ _IOR('f', 5, int) #define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int) #define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int) -#ifdef CONFIG_JBD_DEBUG +#ifdef CONFIG_JBD2_DEBUG #define EXT4_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int) #endif #define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION @@ -282,7 +289,7 @@ struct ext4_inode { __le16 i_uid; /* Low 16 bits of Owner Uid */ __le32 i_size; /* Size in bytes */ __le32 i_atime; /* Access time */ - __le32 i_ctime; /* Creation time */ + __le32 i_ctime; /* Inode Change time */ __le32 i_mtime; /* Modification time */ __le32 i_dtime; /* Deletion Time */ __le16 i_gid; /* Low 16 bits of Group Id */ @@ -331,10 +338,85 @@ struct ext4_inode { } osd2; /* OS dependent 2 */ __le16 i_extra_isize; __le16 i_pad1; + __le32 i_ctime_extra; /* extra Change time (nsec << 2 | epoch) */ + __le32 i_mtime_extra; /* extra Modification time(nsec << 2 | epoch) */ + __le32 i_atime_extra; /* extra Access time (nsec << 2 | epoch) */ + __le32 i_crtime; /* File Creation time */ + __le32 i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */ }; #define i_size_high i_dir_acl +#define EXT4_EPOCH_BITS 2 +#define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1) +#define EXT4_NSEC_MASK (~0UL << EXT4_EPOCH_BITS) + +/* + * Extended fields will fit into an inode if the filesystem was formatted + * with large inodes (-I 256 or larger) and there are not currently any EAs + * consuming all of the available space. For new inodes we always reserve + * enough space for the kernel's known extended fields, but for inodes + * created with an old kernel this might not have been the case. None of + * the extended inode fields is critical for correct filesystem operation. + * This macro checks if a certain field fits in the inode. Note that + * inode-size = GOOD_OLD_INODE_SIZE + i_extra_isize + */ +#define EXT4_FITS_IN_INODE(ext4_inode, einode, field) \ + ((offsetof(typeof(*ext4_inode), field) + \ + sizeof((ext4_inode)->field)) \ + <= (EXT4_GOOD_OLD_INODE_SIZE + \ + (einode)->i_extra_isize)) \ + +static inline __le32 ext4_encode_extra_time(struct timespec *time) +{ + return cpu_to_le32((sizeof(time->tv_sec) > 4 ? + time->tv_sec >> 32 : 0) | + ((time->tv_nsec << 2) & EXT4_NSEC_MASK)); +} + +static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra) +{ + if (sizeof(time->tv_sec) > 4) + time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) + << 32; + time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> 2; +} + +#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \ +do { \ + (raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec); \ + if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) \ + (raw_inode)->xtime ## _extra = \ + ext4_encode_extra_time(&(inode)->xtime); \ +} while (0) + +#define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode) \ +do { \ + if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \ + (raw_inode)->xtime = cpu_to_le32((einode)->xtime.tv_sec); \ + if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \ + (raw_inode)->xtime ## _extra = \ + ext4_encode_extra_time(&(einode)->xtime); \ +} while (0) + +#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode) \ +do { \ + (inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime); \ + if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) \ + ext4_decode_extra_time(&(inode)->xtime, \ + raw_inode->xtime ## _extra); \ +} while (0) + +#define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode) \ +do { \ + if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \ + (einode)->xtime.tv_sec = \ + (signed)le32_to_cpu((raw_inode)->xtime); \ + if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \ + ext4_decode_extra_time(&(einode)->xtime, \ + raw_inode->xtime ## _extra); \ +} while (0) + #if defined(__KERNEL__) || defined(__linux__) #define i_reserved1 osd1.linux1.l_i_reserved1 #define i_frag osd2.linux2.l_i_frag @@ -533,6 +615,13 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode) return container_of(inode, struct ext4_inode_info, vfs_inode); } +static inline struct timespec ext4_current_time(struct inode *inode) +{ + return (inode->i_sb->s_time_gran < NSEC_PER_SEC) ? + current_fs_time(inode->i_sb) : CURRENT_TIME_SEC; +} + + static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || @@ -603,6 +692,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) #define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001 #define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002 #define EXT4_FEATURE_RO_COMPAT_BTREE_DIR 0x0004 +#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020 +#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040 #define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001 #define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002 @@ -620,6 +711,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) EXT4_FEATURE_INCOMPAT_64BIT) #define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ + EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \ + EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR) /* @@ -862,6 +955,7 @@ extern int ext4_change_inode_journal_flag(struct inode *, int); extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *); extern void ext4_truncate (struct inode *); extern void ext4_set_inode_flags(struct inode *); +extern void ext4_get_inode_flags(struct ext4_inode_info *); extern void ext4_set_aops(struct inode *inode); extern int ext4_writepage_trans_blocks(struct inode *); extern int ext4_block_truncate_page(handle_t *handle, struct page *page, @@ -983,6 +1077,8 @@ extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, extern void ext4_ext_truncate(struct inode *, struct page *); extern void ext4_ext_init(struct super_block *); extern void ext4_ext_release(struct super_block *); +extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset, + loff_t len); static inline int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, unsigned long max_blocks, struct buffer_head *bh, diff --git a/include/linux/ext4_fs_extents.h b/include/linux/ext4_fs_extents.h index acfe59740b0..81406f3655d 100644 --- a/include/linux/ext4_fs_extents.h +++ b/include/linux/ext4_fs_extents.h @@ -141,7 +141,25 @@ typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *, #define EXT_MAX_BLOCK 0xffffffff -#define EXT_MAX_LEN ((1UL << 15) - 1) +/* + * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an + * initialized extent. This is 2^15 and not (2^16 - 1), since we use the + * MSB of ee_len field in the extent datastructure to signify if this + * particular extent is an initialized extent or an uninitialized (i.e. + * preallocated). + * EXT_UNINIT_MAX_LEN is the maximum number of blocks we can have in an + * uninitialized extent. + * If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an + * uninitialized one. In other words, if MSB of ee_len is set, it is an + * uninitialized extent with only one special scenario when ee_len = 0x8000. + * In this case we can not have an uninitialized extent of zero length and + * thus we make it as a special case of initialized extent with 0x8000 length. + * This way we get better extent-to-group alignment for initialized extents. + * Hence, the maximum number of blocks we can have in an *initialized* + * extent is 2^15 (32768) and in an *uninitialized* extent is 2^15-1 (32767). + */ +#define EXT_INIT_MAX_LEN (1UL << 15) +#define EXT_UNINIT_MAX_LEN (EXT_INIT_MAX_LEN - 1) #define EXT_FIRST_EXTENT(__hdr__) \ @@ -188,8 +206,31 @@ ext4_ext_invalidate_cache(struct inode *inode) EXT4_I(inode)->i_cached_extent.ec_type = EXT4_EXT_CACHE_NO; } +static inline void ext4_ext_mark_uninitialized(struct ext4_extent *ext) +{ + /* We can not have an uninitialized extent of zero length! */ + BUG_ON((le16_to_cpu(ext->ee_len) & ~EXT_INIT_MAX_LEN) == 0); + ext->ee_len |= cpu_to_le16(EXT_INIT_MAX_LEN); +} + +static inline int ext4_ext_is_uninitialized(struct ext4_extent *ext) +{ + /* Extent with ee_len of 0x8000 is treated as an initialized extent */ + return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN); +} + +static inline int ext4_ext_get_actual_len(struct ext4_extent *ext) +{ + return (le16_to_cpu(ext->ee_len) <= EXT_INIT_MAX_LEN ? + le16_to_cpu(ext->ee_len) : + (le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN)); +} + extern int ext4_extent_tree_init(handle_t *, struct inode *); extern int ext4_ext_calc_credits_for_insert(struct inode *, struct ext4_ext_path *); +extern int ext4_ext_try_to_merge(struct inode *inode, + struct ext4_ext_path *path, + struct ext4_extent *); extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, struct ext4_ext_path *); extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *); extern int ext4_ext_walk_space(struct inode *, unsigned long, unsigned long, ext_prepare_callback, void *); diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h index 9de49440699..1a511e9905a 100644 --- a/include/linux/ext4_fs_i.h +++ b/include/linux/ext4_fs_i.h @@ -153,6 +153,11 @@ struct ext4_inode_info { unsigned long i_ext_generation; struct ext4_ext_cache i_cached_extent; + /* + * File creation time. Its function is same as that of + * struct timespec i_{a,c,m}time in the generic inode. + */ + struct timespec i_crtime; }; #endif /* _LINUX_EXT4_FS_I */ diff --git a/include/linux/ext4_fs_sb.h b/include/linux/ext4_fs_sb.h index 2347557a327..1b2ffee12be 100644 --- a/include/linux/ext4_fs_sb.h +++ b/include/linux/ext4_fs_sb.h @@ -73,7 +73,7 @@ struct ext4_sb_info { struct list_head s_orphan; unsigned long s_commit_interval; struct block_device *journal_bdev; -#ifdef CONFIG_JBD_DEBUG +#ifdef CONFIG_JBD2_DEBUG struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */ wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */ #endif @@ -81,6 +81,7 @@ struct ext4_sb_info { char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */ int s_jquota_fmt; /* Format of quota to use */ #endif + unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */ #ifdef EXTENTS_STATS /* ext4 extents stats */ diff --git a/include/linux/falloc.h b/include/linux/falloc.h new file mode 100644 index 00000000000..8e912ab6a07 --- /dev/null +++ b/include/linux/falloc.h @@ -0,0 +1,6 @@ +#ifndef _FALLOC_H_ +#define _FALLOC_H_ + +#define FALLOC_FL_KEEP_SIZE 0x01 /* default is extend size */ + +#endif /* _FALLOC_H_ */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 98205f68047..0b806c5e32e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1147,6 +1147,8 @@ struct inode_operations { ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*removexattr) (struct dentry *, const char *); void (*truncate_range)(struct inode *, loff_t, loff_t); + long (*fallocate)(struct inode *inode, int mode, loff_t offset, + loff_t len); }; struct seq_file; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 0e0fedd2039..260d6d76c5f 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -50,14 +50,14 @@ */ #define JBD_DEFAULT_MAX_COMMIT_AGE 5 -#ifdef CONFIG_JBD_DEBUG +#ifdef CONFIG_JBD2_DEBUG /* * Define JBD_EXPENSIVE_CHECKING to enable more expensive internal * consistency checks. By default we don't do this unless - * CONFIG_JBD_DEBUG is on. + * CONFIG_JBD2_DEBUG is on. */ #define JBD_EXPENSIVE_CHECKING -extern int jbd2_journal_enable_debug; +extern u8 jbd2_journal_enable_debug; #define jbd_debug(n, f, a...) \ do { \ diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 10f505c8431..5dc13848891 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -36,13 +36,57 @@ static inline int request_module(const char * name, ...) { return -ENOSYS; } #define try_then_request_module(x, mod...) ((x) ?: (request_module(mod), (x))) struct key; -extern int call_usermodehelper_keys(char *path, char *argv[], char *envp[], - struct key *session_keyring, int wait); +struct file; +struct subprocess_info; + +/* Allocate a subprocess_info structure */ +struct subprocess_info *call_usermodehelper_setup(char *path, + char **argv, char **envp); + +/* Set various pieces of state into the subprocess_info structure */ +void call_usermodehelper_setkeys(struct subprocess_info *info, + struct key *session_keyring); +int call_usermodehelper_stdinpipe(struct subprocess_info *sub_info, + struct file **filp); +void call_usermodehelper_setcleanup(struct subprocess_info *info, + void (*cleanup)(char **argv, char **envp)); + +enum umh_wait { + UMH_NO_WAIT = -1, /* don't wait at all */ + UMH_WAIT_EXEC = 0, /* wait for the exec, but not the process */ + UMH_WAIT_PROC = 1, /* wait for the process to complete */ +}; + +/* Actually execute the sub-process */ +int call_usermodehelper_exec(struct subprocess_info *info, enum umh_wait wait); + +/* Free the subprocess_info. This is only needed if you're not going + to call call_usermodehelper_exec */ +void call_usermodehelper_freeinfo(struct subprocess_info *info); static inline int -call_usermodehelper(char *path, char **argv, char **envp, int wait) +call_usermodehelper(char *path, char **argv, char **envp, enum umh_wait wait) { - return call_usermodehelper_keys(path, argv, envp, NULL, wait); + struct subprocess_info *info; + + info = call_usermodehelper_setup(path, argv, envp); + if (info == NULL) + return -ENOMEM; + return call_usermodehelper_exec(info, wait); +} + +static inline int +call_usermodehelper_keys(char *path, char **argv, char **envp, + struct key *session_keyring, enum umh_wait wait) +{ + struct subprocess_info *info; + + info = call_usermodehelper_setup(path, argv, envp); + if (info == NULL) + return -ENOMEM; + + call_usermodehelper_setkeys(info, session_keyring); + return call_usermodehelper_exec(info, wait); } extern void usermodehelper_init(void); diff --git a/include/linux/major.h b/include/linux/major.h index 7e7c9093919..0cb98053537 100644 --- a/include/linux/major.h +++ b/include/linux/major.h @@ -158,6 +158,8 @@ #define VXSPEC_MAJOR 200 /* VERITAS volume config driver */ #define VXDMP_MAJOR 201 /* VERITAS volume multipath driver */ +#define XENVBD_MAJOR 202 /* Xen virtual block device */ + #define MSR_MAJOR 202 #define CPUID_MAJOR 203 diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index da7a13c97eb..9820ca1e45e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1098,10 +1098,8 @@ extern int dev_mc_delete(struct net_device *dev, void *addr, int alen, int all extern int dev_mc_add(struct net_device *dev, void *addr, int alen, int newonly); extern int dev_mc_sync(struct net_device *to, struct net_device *from); extern void dev_mc_unsync(struct net_device *to, struct net_device *from); -extern void dev_mc_discard(struct net_device *dev); extern int __dev_addr_delete(struct dev_addr_list **list, int *count, void *addr, int alen, int all); extern int __dev_addr_add(struct dev_addr_list **list, int *count, void *addr, int alen, int newonly); -extern void __dev_addr_discard(struct dev_addr_list **list); extern void dev_set_promiscuity(struct net_device *dev, int inc); extern void dev_set_allmulti(struct net_device *dev, int inc); extern void netdev_state_change(struct net_device *dev); diff --git a/include/linux/netfilter_ipv4/ipt_iprange.h b/include/linux/netfilter_ipv4/ipt_iprange.h index 34ab0fb736e..a92fefc3c7e 100644 --- a/include/linux/netfilter_ipv4/ipt_iprange.h +++ b/include/linux/netfilter_ipv4/ipt_iprange.h @@ -1,6 +1,8 @@ #ifndef _IPT_IPRANGE_H #define _IPT_IPRANGE_H +#include <linux/types.h> + #define IPRANGE_SRC 0x01 /* Match source IP address */ #define IPRANGE_DST 0x02 /* Match destination IP address */ #define IPRANGE_SRC_INV 0x10 /* Negate the condition */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index ae2d79f2107..731cd2ac322 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -92,6 +92,7 @@ /* PG_owner_priv_1 users should have descriptive aliases */ #define PG_checked PG_owner_priv_1 /* Used by some filesystems */ +#define PG_pinned PG_owner_priv_1 /* Xen pinned pagetable */ #if (BITS_PER_LONG > 32) /* @@ -170,6 +171,10 @@ static inline void SetPageUptodate(struct page *page) #define SetPageChecked(page) set_bit(PG_checked, &(page)->flags) #define ClearPageChecked(page) clear_bit(PG_checked, &(page)->flags) +#define PagePinned(page) test_bit(PG_pinned, &(page)->flags) +#define SetPagePinned(page) set_bit(PG_pinned, &(page)->flags) +#define ClearPagePinned(page) clear_bit(PG_pinned, &(page)->flags) + #define PageReserved(page) test_bit(PG_reserved, &(page)->flags) #define SetPageReserved(page) set_bit(PG_reserved, &(page)->flags) #define ClearPageReserved(page) clear_bit(PG_reserved, &(page)->flags) diff --git a/include/linux/reboot.h b/include/linux/reboot.h index 1dd1c707311..85ea63f462a 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -67,6 +67,11 @@ extern void kernel_power_off(void); void ctrl_alt_del(void); +#define POWEROFF_CMD_PATH_LEN 256 +extern char poweroff_cmd[POWEROFF_CMD_PATH_LEN]; + +extern int orderly_poweroff(bool force); + /* * Emergency restart, callable from an interrupt handler. */ diff --git a/include/linux/string.h b/include/linux/string.h index 7f2eb6a477f..836062b7582 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -105,8 +105,12 @@ extern void * memchr(const void *,int,__kernel_size_t); #endif extern char *kstrdup(const char *s, gfp_t gfp); +extern char *kstrndup(const char *s, size_t len, gfp_t gfp); extern void *kmemdup(const void *src, size_t len, gfp_t gfp); +extern char **argv_split(gfp_t gfp, const char *str, int *argcp); +extern void argv_free(char **argv); + #ifdef __cplusplus } #endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 83d0ec11235..7a8b1e3322e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -610,6 +610,7 @@ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemas asmlinkage long sys_timerfd(int ufd, int clockid, int flags, const struct itimerspec __user *utmr); asmlinkage long sys_eventfd(unsigned int count); +asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len); int kernel_execve(const char *filename, char *const argv[], char *const envp[]); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 132b260aef1..c2b10cae5da 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -70,6 +70,10 @@ extern int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages); extern void unmap_kernel_range(unsigned long addr, unsigned long size); +/* Allocate/destroy a 'vmalloc' VM area. */ +extern struct vm_struct *alloc_vm_area(size_t size); +extern void free_vm_area(struct vm_struct *area); + /* * Internals. Dont't use.. */ diff --git a/include/mtd/ubi-header.h b/include/mtd/ubi-header.h index fa479c71aa3..74efa776347 100644 --- a/include/mtd/ubi-header.h +++ b/include/mtd/ubi-header.h @@ -74,42 +74,13 @@ enum { UBI_COMPAT_REJECT = 5 }; -/* - * ubi16_t/ubi32_t/ubi64_t - 16, 32, and 64-bit integers used in UBI on-flash - * data structures. - */ -typedef struct { - uint16_t int16; -} __attribute__ ((packed)) ubi16_t; - -typedef struct { - uint32_t int32; -} __attribute__ ((packed)) ubi32_t; - -typedef struct { - uint64_t int64; -} __attribute__ ((packed)) ubi64_t; - -/* - * In this implementation of UBI uses the big-endian format for on-flash - * integers. The below are the corresponding conversion macros. - */ -#define cpu_to_ubi16(x) ((ubi16_t){__cpu_to_be16(x)}) -#define ubi16_to_cpu(x) ((uint16_t)__be16_to_cpu((x).int16)) - -#define cpu_to_ubi32(x) ((ubi32_t){__cpu_to_be32(x)}) -#define ubi32_to_cpu(x) ((uint32_t)__be32_to_cpu((x).int32)) - -#define cpu_to_ubi64(x) ((ubi64_t){__cpu_to_be64(x)}) -#define ubi64_to_cpu(x) ((uint64_t)__be64_to_cpu((x).int64)) - /* Sizes of UBI headers */ #define UBI_EC_HDR_SIZE sizeof(struct ubi_ec_hdr) #define UBI_VID_HDR_SIZE sizeof(struct ubi_vid_hdr) /* Sizes of UBI headers without the ending CRC */ -#define UBI_EC_HDR_SIZE_CRC (UBI_EC_HDR_SIZE - sizeof(ubi32_t)) -#define UBI_VID_HDR_SIZE_CRC (UBI_VID_HDR_SIZE - sizeof(ubi32_t)) +#define UBI_EC_HDR_SIZE_CRC (UBI_EC_HDR_SIZE - sizeof(__be32)) +#define UBI_VID_HDR_SIZE_CRC (UBI_VID_HDR_SIZE - sizeof(__be32)) /** * struct ubi_ec_hdr - UBI erase counter header. @@ -137,14 +108,14 @@ typedef struct { * eraseblocks. */ struct ubi_ec_hdr { - ubi32_t magic; - uint8_t version; - uint8_t padding1[3]; - ubi64_t ec; /* Warning: the current limit is 31-bit anyway! */ - ubi32_t vid_hdr_offset; - ubi32_t data_offset; - uint8_t padding2[36]; - ubi32_t hdr_crc; + __be32 magic; + __u8 version; + __u8 padding1[3]; + __be64 ec; /* Warning: the current limit is 31-bit anyway! */ + __be32 vid_hdr_offset; + __be32 data_offset; + __u8 padding2[36]; + __be32 hdr_crc; } __attribute__ ((packed)); /** @@ -262,22 +233,22 @@ struct ubi_ec_hdr { * software (say, cramfs) on top of the UBI volume. */ struct ubi_vid_hdr { - ubi32_t magic; - uint8_t version; - uint8_t vol_type; - uint8_t copy_flag; - uint8_t compat; - ubi32_t vol_id; - ubi32_t lnum; - ubi32_t leb_ver; /* obsolete, to be removed, don't use */ - ubi32_t data_size; - ubi32_t used_ebs; - ubi32_t data_pad; - ubi32_t data_crc; - uint8_t padding1[4]; - ubi64_t sqnum; - uint8_t padding2[12]; - ubi32_t hdr_crc; + __be32 magic; + __u8 version; + __u8 vol_type; + __u8 copy_flag; + __u8 compat; + __be32 vol_id; + __be32 lnum; + __be32 leb_ver; /* obsolete, to be removed, don't use */ + __be32 data_size; + __be32 used_ebs; + __be32 data_pad; + __be32 data_crc; + __u8 padding1[4]; + __be64 sqnum; + __u8 padding2[12]; + __be32 hdr_crc; } __attribute__ ((packed)); /* Internal UBI volumes count */ @@ -306,7 +277,7 @@ struct ubi_vid_hdr { #define UBI_VTBL_RECORD_SIZE sizeof(struct ubi_vtbl_record) /* Size of the volume table record without the ending CRC */ -#define UBI_VTBL_RECORD_SIZE_CRC (UBI_VTBL_RECORD_SIZE - sizeof(ubi32_t)) +#define UBI_VTBL_RECORD_SIZE_CRC (UBI_VTBL_RECORD_SIZE - sizeof(__be32)) /** * struct ubi_vtbl_record - a record in the volume table. @@ -346,15 +317,15 @@ struct ubi_vid_hdr { * Empty records contain all zeroes and the CRC checksum of those zeroes. */ struct ubi_vtbl_record { - ubi32_t reserved_pebs; - ubi32_t alignment; - ubi32_t data_pad; - uint8_t vol_type; - uint8_t upd_marker; - ubi16_t name_len; - uint8_t name[UBI_VOL_NAME_MAX+1]; - uint8_t padding2[24]; - ubi32_t crc; + __be32 reserved_pebs; + __be32 alignment; + __be32 data_pad; + __u8 vol_type; + __u8 upd_marker; + __be16 name_len; + __u8 name[UBI_VOL_NAME_MAX+1]; + __u8 padding2[24]; + __be32 crc; } __attribute__ ((packed)); #endif /* !__UBI_HEADER_H__ */ diff --git a/include/net/tcp.h b/include/net/tcp.h index a8af9ae0017..8b404b1ef7c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -652,8 +652,7 @@ struct tcp_congestion_ops { /* lower bound for congestion window (optional) */ u32 (*min_cwnd)(const struct sock *sk); /* do new cwnd calculation (required) */ - void (*cong_avoid)(struct sock *sk, u32 ack, - u32 rtt, u32 in_flight, int good_ack); + void (*cong_avoid)(struct sock *sk, u32 ack, u32 in_flight, int good_ack); /* call before changing ca_state (optional) */ void (*set_state)(struct sock *sk, u8 new_state); /* call when cwnd event occurs (optional) */ @@ -684,8 +683,7 @@ extern void tcp_slow_start(struct tcp_sock *tp); extern struct tcp_congestion_ops tcp_init_congestion_ops; extern u32 tcp_reno_ssthresh(struct sock *sk); -extern void tcp_reno_cong_avoid(struct sock *sk, u32 ack, - u32 rtt, u32 in_flight, int flag); +extern void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight, int flag); extern u32 tcp_reno_min_cwnd(const struct sock *sk); extern struct tcp_congestion_ops tcp_reno; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index ae959e95017..a5f80bfbaaa 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -585,7 +585,6 @@ static inline int xfrm_sec_ctx_match(struct xfrm_sec_ctx *s1, struct xfrm_sec_ct struct xfrm_dst { union { - struct xfrm_dst *next; struct dst_entry dst; struct rtable rt; struct rt6_info rt6; diff --git a/include/xen/events.h b/include/xen/events.h new file mode 100644 index 00000000000..2bde54d29be --- /dev/null +++ b/include/xen/events.h @@ -0,0 +1,48 @@ +#ifndef _XEN_EVENTS_H +#define _XEN_EVENTS_H + +#include <linux/interrupt.h> + +#include <xen/interface/event_channel.h> +#include <asm/xen/hypercall.h> + +enum ipi_vector { + XEN_RESCHEDULE_VECTOR, + XEN_CALL_FUNCTION_VECTOR, + + XEN_NR_IPIS, +}; + +int bind_evtchn_to_irq(unsigned int evtchn); +int bind_evtchn_to_irqhandler(unsigned int evtchn, + irq_handler_t handler, + unsigned long irqflags, const char *devname, + void *dev_id); +int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu, + irq_handler_t handler, + unsigned long irqflags, const char *devname, + void *dev_id); +int bind_ipi_to_irqhandler(enum ipi_vector ipi, + unsigned int cpu, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, + void *dev_id); + +/* + * Common unbind function for all event sources. Takes IRQ to unbind from. + * Automatically closes the underlying event channel (even for bindings + * made with bind_evtchn_to_irqhandler()). + */ +void unbind_from_irqhandler(unsigned int irq, void *dev_id); + +void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector); + +static inline void notify_remote_via_evtchn(int port) +{ + struct evtchn_send send = { .port = port }; + (void)HYPERVISOR_event_channel_op(EVTCHNOP_send, &send); +} + +extern void notify_remote_via_irq(int irq); +#endif /* _XEN_EVENTS_H */ diff --git a/include/xen/features.h b/include/xen/features.h new file mode 100644 index 00000000000..27292d4d2a6 --- /dev/null +++ b/include/xen/features.h @@ -0,0 +1,23 @@ +/****************************************************************************** + * features.h + * + * Query the features reported by Xen. + * + * Copyright (c) 2006, Ian Campbell + */ + +#ifndef __XEN_FEATURES_H__ +#define __XEN_FEATURES_H__ + +#include <xen/interface/features.h> + +void xen_setup_features(void); + +extern u8 xen_features[XENFEAT_NR_SUBMAPS * 32]; + +static inline int xen_feature(int flag) +{ + return xen_features[flag]; +} + +#endif /* __ASM_XEN_FEATURES_H__ */ diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h new file mode 100644 index 00000000000..761c83498e0 --- /dev/null +++ b/include/xen/grant_table.h @@ -0,0 +1,107 @@ +/****************************************************************************** + * grant_table.h + * + * Two sets of functionality: + * 1. Granting foreign access to our memory reservation. + * 2. Accessing others' memory reservations via grant references. + * (i.e., mechanisms for both sender and recipient of grant references) + * + * Copyright (c) 2004-2005, K A Fraser + * Copyright (c) 2005, Christopher Clark + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __ASM_GNTTAB_H__ +#define __ASM_GNTTAB_H__ + +#include <asm/xen/hypervisor.h> +#include <xen/interface/grant_table.h> + +/* NR_GRANT_FRAMES must be less than or equal to that configured in Xen */ +#define NR_GRANT_FRAMES 4 + +struct gnttab_free_callback { + struct gnttab_free_callback *next; + void (*fn)(void *); + void *arg; + u16 count; +}; + +int gnttab_grant_foreign_access(domid_t domid, unsigned long frame, + int readonly); + +/* + * End access through the given grant reference, iff the grant entry is no + * longer in use. Return 1 if the grant entry was freed, 0 if it is still in + * use. + */ +int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly); + +/* + * Eventually end access through the given grant reference, and once that + * access has been ended, free the given page too. Access will be ended + * immediately iff the grant entry is not in use, otherwise it will happen + * some time later. page may be 0, in which case no freeing will occur. + */ +void gnttab_end_foreign_access(grant_ref_t ref, int readonly, + unsigned long page); + +int gnttab_grant_foreign_transfer(domid_t domid, unsigned long pfn); + +unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref); +unsigned long gnttab_end_foreign_transfer(grant_ref_t ref); + +int gnttab_query_foreign_access(grant_ref_t ref); + +/* + * operations on reserved batches of grant references + */ +int gnttab_alloc_grant_references(u16 count, grant_ref_t *pprivate_head); + +void gnttab_free_grant_reference(grant_ref_t ref); + +void gnttab_free_grant_references(grant_ref_t head); + +int gnttab_empty_grant_references(const grant_ref_t *pprivate_head); + +int gnttab_claim_grant_reference(grant_ref_t *pprivate_head); + +void gnttab_release_grant_reference(grant_ref_t *private_head, + grant_ref_t release); + +void gnttab_request_free_callback(struct gnttab_free_callback *callback, + void (*fn)(void *), void *arg, u16 count); +void gnttab_cancel_free_callback(struct gnttab_free_callback *callback); + +void gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid, + unsigned long frame, int readonly); + +void gnttab_grant_foreign_transfer_ref(grant_ref_t, domid_t domid, + unsigned long pfn); + +#define gnttab_map_vaddr(map) ((void *)(map.host_virt_addr)) + +#endif /* __ASM_GNTTAB_H__ */ diff --git a/include/xen/hvc-console.h b/include/xen/hvc-console.h new file mode 100644 index 00000000000..21c0ecfd786 --- /dev/null +++ b/include/xen/hvc-console.h @@ -0,0 +1,6 @@ +#ifndef XEN_HVC_CONSOLE_H +#define XEN_HVC_CONSOLE_H + +extern struct console xenboot_console; + +#endif /* XEN_HVC_CONSOLE_H */ diff --git a/include/xen/interface/elfnote.h b/include/xen/interface/elfnote.h new file mode 100644 index 00000000000..a64d3df5bd9 --- /dev/null +++ b/include/xen/interface/elfnote.h @@ -0,0 +1,133 @@ +/****************************************************************************** + * elfnote.h + * + * Definitions used for the Xen ELF notes. + * + * Copyright (c) 2006, Ian Campbell, XenSource Ltd. + */ + +#ifndef __XEN_PUBLIC_ELFNOTE_H__ +#define __XEN_PUBLIC_ELFNOTE_H__ + +/* + * The notes should live in a SHT_NOTE segment and have "Xen" in the + * name field. + * + * Numeric types are either 4 or 8 bytes depending on the content of + * the desc field. + * + * LEGACY indicated the fields in the legacy __xen_guest string which + * this a note type replaces. + */ + +/* + * NAME=VALUE pair (string). + * + * LEGACY: FEATURES and PAE + */ +#define XEN_ELFNOTE_INFO 0 + +/* + * The virtual address of the entry point (numeric). + * + * LEGACY: VIRT_ENTRY + */ +#define XEN_ELFNOTE_ENTRY 1 + +/* The virtual address of the hypercall transfer page (numeric). + * + * LEGACY: HYPERCALL_PAGE. (n.b. legacy value is a physical page + * number not a virtual address) + */ +#define XEN_ELFNOTE_HYPERCALL_PAGE 2 + +/* The virtual address where the kernel image should be mapped (numeric). + * + * Defaults to 0. + * + * LEGACY: VIRT_BASE + */ +#define XEN_ELFNOTE_VIRT_BASE 3 + +/* + * The offset of the ELF paddr field from the acutal required + * psuedo-physical address (numeric). + * + * This is used to maintain backwards compatibility with older kernels + * which wrote __PAGE_OFFSET into that field. This field defaults to 0 + * if not present. + * + * LEGACY: ELF_PADDR_OFFSET. (n.b. legacy default is VIRT_BASE) + */ +#define XEN_ELFNOTE_PADDR_OFFSET 4 + +/* + * The version of Xen that we work with (string). + * + * LEGACY: XEN_VER + */ +#define XEN_ELFNOTE_XEN_VERSION 5 + +/* + * The name of the guest operating system (string). + * + * LEGACY: GUEST_OS + */ +#define XEN_ELFNOTE_GUEST_OS 6 + +/* + * The version of the guest operating system (string). + * + * LEGACY: GUEST_VER + */ +#define XEN_ELFNOTE_GUEST_VERSION 7 + +/* + * The loader type (string). + * + * LEGACY: LOADER + */ +#define XEN_ELFNOTE_LOADER 8 + +/* + * The kernel supports PAE (x86/32 only, string = "yes" or "no"). + * + * LEGACY: PAE (n.b. The legacy interface included a provision to + * indicate 'extended-cr3' support allowing L3 page tables to be + * placed above 4G. It is assumed that any kernel new enough to use + * these ELF notes will include this and therefore "yes" here is + * equivalent to "yes[entended-cr3]" in the __xen_guest interface. + */ +#define XEN_ELFNOTE_PAE_MODE 9 + +/* + * The features supported/required by this kernel (string). + * + * The string must consist of a list of feature names (as given in + * features.h, without the "XENFEAT_" prefix) separated by '|' + * characters. If a feature is required for the kernel to function + * then the feature name must be preceded by a '!' character. + * + * LEGACY: FEATURES + */ +#define XEN_ELFNOTE_FEATURES 10 + +/* + * The kernel requires the symbol table to be loaded (string = "yes" or "no") + * LEGACY: BSD_SYMTAB (n.b. The legacy treated the presence or absence + * of this string as a boolean flag rather than requiring "yes" or + * "no". + */ +#define XEN_ELFNOTE_BSD_SYMTAB 11 + +#endif /* __XEN_PUBLIC_ELFNOTE_H__ */ + +/* + * Local variables: + * mode: C + * c-set-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/interface/event_channel.h b/include/xen/interface/event_channel.h new file mode 100644 index 00000000000..919b5bdcb2b --- /dev/null +++ b/include/xen/interface/event_channel.h @@ -0,0 +1,195 @@ +/****************************************************************************** + * event_channel.h + * + * Event channels between domains. + * + * Copyright (c) 2003-2004, K A Fraser. + */ + +#ifndef __XEN_PUBLIC_EVENT_CHANNEL_H__ +#define __XEN_PUBLIC_EVENT_CHANNEL_H__ + +typedef uint32_t evtchn_port_t; +DEFINE_GUEST_HANDLE(evtchn_port_t); + +/* + * EVTCHNOP_alloc_unbound: Allocate a port in domain <dom> and mark as + * accepting interdomain bindings from domain <remote_dom>. A fresh port + * is allocated in <dom> and returned as <port>. + * NOTES: + * 1. If the caller is unprivileged then <dom> must be DOMID_SELF. + * 2. <rdom> may be DOMID_SELF, allowing loopback connections. + */ +#define EVTCHNOP_alloc_unbound 6 +struct evtchn_alloc_unbound { + /* IN parameters */ + domid_t dom, remote_dom; + /* OUT parameters */ + evtchn_port_t port; +}; + +/* + * EVTCHNOP_bind_interdomain: Construct an interdomain event channel between + * the calling domain and <remote_dom>. <remote_dom,remote_port> must identify + * a port that is unbound and marked as accepting bindings from the calling + * domain. A fresh port is allocated in the calling domain and returned as + * <local_port>. + * NOTES: + * 2. <remote_dom> may be DOMID_SELF, allowing loopback connections. + */ +#define EVTCHNOP_bind_interdomain 0 +struct evtchn_bind_interdomain { + /* IN parameters. */ + domid_t remote_dom; + evtchn_port_t remote_port; + /* OUT parameters. */ + evtchn_port_t local_port; +}; + +/* + * EVTCHNOP_bind_virq: Bind a local event channel to VIRQ <irq> on specified + * vcpu. + * NOTES: + * 1. A virtual IRQ may be bound to at most one event channel per vcpu. + * 2. The allocated event channel is bound to the specified vcpu. The binding + * may not be changed. + */ +#define EVTCHNOP_bind_virq 1 +struct evtchn_bind_virq { + /* IN parameters. */ + uint32_t virq; + uint32_t vcpu; + /* OUT parameters. */ + evtchn_port_t port; +}; + +/* + * EVTCHNOP_bind_pirq: Bind a local event channel to PIRQ <irq>. + * NOTES: + * 1. A physical IRQ may be bound to at most one event channel per domain. + * 2. Only a sufficiently-privileged domain may bind to a physical IRQ. + */ +#define EVTCHNOP_bind_pirq 2 +struct evtchn_bind_pirq { + /* IN parameters. */ + uint32_t pirq; +#define BIND_PIRQ__WILL_SHARE 1 + uint32_t flags; /* BIND_PIRQ__* */ + /* OUT parameters. */ + evtchn_port_t port; +}; + +/* + * EVTCHNOP_bind_ipi: Bind a local event channel to receive events. + * NOTES: + * 1. The allocated event channel is bound to the specified vcpu. The binding + * may not be changed. + */ +#define EVTCHNOP_bind_ipi 7 +struct evtchn_bind_ipi { + uint32_t vcpu; + /* OUT parameters. */ + evtchn_port_t port; +}; + +/* + * EVTCHNOP_close: Close a local event channel <port>. If the channel is + * interdomain then the remote end is placed in the unbound state + * (EVTCHNSTAT_unbound), awaiting a new connection. + */ +#define EVTCHNOP_close 3 +struct evtchn_close { + /* IN parameters. */ + evtchn_port_t port; +}; + +/* + * EVTCHNOP_send: Send an event to the remote end of the channel whose local + * endpoint is <port>. + */ +#define EVTCHNOP_send 4 +struct evtchn_send { + /* IN parameters. */ + evtchn_port_t port; +}; + +/* + * EVTCHNOP_status: Get the current status of the communication channel which + * has an endpoint at <dom, port>. + * NOTES: + * 1. <dom> may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may obtain the status of an event + * channel for which <dom> is not DOMID_SELF. + */ +#define EVTCHNOP_status 5 +struct evtchn_status { + /* IN parameters */ + domid_t dom; + evtchn_port_t port; + /* OUT parameters */ +#define EVTCHNSTAT_closed 0 /* Channel is not in use. */ +#define EVTCHNSTAT_unbound 1 /* Channel is waiting interdom connection.*/ +#define EVTCHNSTAT_interdomain 2 /* Channel is connected to remote domain. */ +#define EVTCHNSTAT_pirq 3 /* Channel is bound to a phys IRQ line. */ +#define EVTCHNSTAT_virq 4 /* Channel is bound to a virtual IRQ line */ +#define EVTCHNSTAT_ipi 5 /* Channel is bound to a virtual IPI line */ + uint32_t status; + uint32_t vcpu; /* VCPU to which this channel is bound. */ + union { + struct { + domid_t dom; + } unbound; /* EVTCHNSTAT_unbound */ + struct { + domid_t dom; + evtchn_port_t port; + } interdomain; /* EVTCHNSTAT_interdomain */ + uint32_t pirq; /* EVTCHNSTAT_pirq */ + uint32_t virq; /* EVTCHNSTAT_virq */ + } u; +}; + +/* + * EVTCHNOP_bind_vcpu: Specify which vcpu a channel should notify when an + * event is pending. + * NOTES: + * 1. IPI- and VIRQ-bound channels always notify the vcpu that initialised + * the binding. This binding cannot be changed. + * 2. All other channels notify vcpu0 by default. This default is set when + * the channel is allocated (a port that is freed and subsequently reused + * has its binding reset to vcpu0). + */ +#define EVTCHNOP_bind_vcpu 8 +struct evtchn_bind_vcpu { + /* IN parameters. */ + evtchn_port_t port; + uint32_t vcpu; +}; + +/* + * EVTCHNOP_unmask: Unmask the specified local event-channel port and deliver + * a notification to the appropriate VCPU if an event is pending. + */ +#define EVTCHNOP_unmask 9 +struct evtchn_unmask { + /* IN parameters. */ + evtchn_port_t port; +}; + +struct evtchn_op { + uint32_t cmd; /* EVTCHNOP_* */ + union { + struct evtchn_alloc_unbound alloc_unbound; + struct evtchn_bind_interdomain bind_interdomain; + struct evtchn_bind_virq bind_virq; + struct evtchn_bind_pirq bind_pirq; + struct evtchn_bind_ipi bind_ipi; + struct evtchn_close close; + struct evtchn_send send; + struct evtchn_status status; + struct evtchn_bind_vcpu bind_vcpu; + struct evtchn_unmask unmask; + } u; +}; +DEFINE_GUEST_HANDLE_STRUCT(evtchn_op); + +#endif /* __XEN_PUBLIC_EVENT_CHANNEL_H__ */ diff --git a/include/xen/interface/features.h b/include/xen/interface/features.h new file mode 100644 index 00000000000..d73228d1648 --- /dev/null +++ b/include/xen/interface/features.h @@ -0,0 +1,43 @@ +/****************************************************************************** + * features.h + * + * Feature flags, reported by XENVER_get_features. + * + * Copyright (c) 2006, Keir Fraser <keir@xensource.com> + */ + +#ifndef __XEN_PUBLIC_FEATURES_H__ +#define __XEN_PUBLIC_FEATURES_H__ + +/* + * If set, the guest does not need to write-protect its pagetables, and can + * update them via direct writes. + */ +#define XENFEAT_writable_page_tables 0 + +/* + * If set, the guest does not need to write-protect its segment descriptor + * tables, and can update them via direct writes. + */ +#define XENFEAT_writable_descriptor_tables 1 + +/* + * If set, translation between the guest's 'pseudo-physical' address space + * and the host's machine address space are handled by the hypervisor. In this + * mode the guest does not need to perform phys-to/from-machine translations + * when performing page table operations. + */ +#define XENFEAT_auto_translated_physmap 2 + +/* If set, the guest is running in supervisor mode (e.g., x86 ring 0). */ +#define XENFEAT_supervisor_mode_kernel 3 + +/* + * If set, the guest does not need to allocate x86 PAE page directories + * below 4GB. This flag is usually implied by auto_translated_physmap. + */ +#define XENFEAT_pae_pgdir_above_4gb 4 + +#define XENFEAT_NR_SUBMAPS 1 + +#endif /* __XEN_PUBLIC_FEATURES_H__ */ diff --git a/include/xen/interface/grant_table.h b/include/xen/interface/grant_table.h new file mode 100644 index 00000000000..219049802cf --- /dev/null +++ b/include/xen/interface/grant_table.h @@ -0,0 +1,375 @@ +/****************************************************************************** + * grant_table.h + * + * Interface for granting foreign access to page frames, and receiving + * page-ownership transfers. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2004, K A Fraser + */ + +#ifndef __XEN_PUBLIC_GRANT_TABLE_H__ +#define __XEN_PUBLIC_GRANT_TABLE_H__ + + +/*********************************** + * GRANT TABLE REPRESENTATION + */ + +/* Some rough guidelines on accessing and updating grant-table entries + * in a concurrency-safe manner. For more information, Linux contains a + * reference implementation for guest OSes (arch/xen/kernel/grant_table.c). + * + * NB. WMB is a no-op on current-generation x86 processors. However, a + * compiler barrier will still be required. + * + * Introducing a valid entry into the grant table: + * 1. Write ent->domid. + * 2. Write ent->frame: + * GTF_permit_access: Frame to which access is permitted. + * GTF_accept_transfer: Pseudo-phys frame slot being filled by new + * frame, or zero if none. + * 3. Write memory barrier (WMB). + * 4. Write ent->flags, inc. valid type. + * + * Invalidating an unused GTF_permit_access entry: + * 1. flags = ent->flags. + * 2. Observe that !(flags & (GTF_reading|GTF_writing)). + * 3. Check result of SMP-safe CMPXCHG(&ent->flags, flags, 0). + * NB. No need for WMB as reuse of entry is control-dependent on success of + * step 3, and all architectures guarantee ordering of ctrl-dep writes. + * + * Invalidating an in-use GTF_permit_access entry: + * This cannot be done directly. Request assistance from the domain controller + * which can set a timeout on the use of a grant entry and take necessary + * action. (NB. This is not yet implemented!). + * + * Invalidating an unused GTF_accept_transfer entry: + * 1. flags = ent->flags. + * 2. Observe that !(flags & GTF_transfer_committed). [*] + * 3. Check result of SMP-safe CMPXCHG(&ent->flags, flags, 0). + * NB. No need for WMB as reuse of entry is control-dependent on success of + * step 3, and all architectures guarantee ordering of ctrl-dep writes. + * [*] If GTF_transfer_committed is set then the grant entry is 'committed'. + * The guest must /not/ modify the grant entry until the address of the + * transferred frame is written. It is safe for the guest to spin waiting + * for this to occur (detect by observing GTF_transfer_completed in + * ent->flags). + * + * Invalidating a committed GTF_accept_transfer entry: + * 1. Wait for (ent->flags & GTF_transfer_completed). + * + * Changing a GTF_permit_access from writable to read-only: + * Use SMP-safe CMPXCHG to set GTF_readonly, while checking !GTF_writing. + * + * Changing a GTF_permit_access from read-only to writable: + * Use SMP-safe bit-setting instruction. + */ + +/* + * A grant table comprises a packed array of grant entries in one or more + * page frames shared between Xen and a guest. + * [XEN]: This field is written by Xen and read by the sharing guest. + * [GST]: This field is written by the guest and read by Xen. + */ +struct grant_entry { + /* GTF_xxx: various type and flag information. [XEN,GST] */ + uint16_t flags; + /* The domain being granted foreign privileges. [GST] */ + domid_t domid; + /* + * GTF_permit_access: Frame that @domid is allowed to map and access. [GST] + * GTF_accept_transfer: Frame whose ownership transferred by @domid. [XEN] + */ + uint32_t frame; +}; + +/* + * Type of grant entry. + * GTF_invalid: This grant entry grants no privileges. + * GTF_permit_access: Allow @domid to map/access @frame. + * GTF_accept_transfer: Allow @domid to transfer ownership of one page frame + * to this guest. Xen writes the page number to @frame. + */ +#define GTF_invalid (0U<<0) +#define GTF_permit_access (1U<<0) +#define GTF_accept_transfer (2U<<0) +#define GTF_type_mask (3U<<0) + +/* + * Subflags for GTF_permit_access. + * GTF_readonly: Restrict @domid to read-only mappings and accesses. [GST] + * GTF_reading: Grant entry is currently mapped for reading by @domid. [XEN] + * GTF_writing: Grant entry is currently mapped for writing by @domid. [XEN] + */ +#define _GTF_readonly (2) +#define GTF_readonly (1U<<_GTF_readonly) +#define _GTF_reading (3) +#define GTF_reading (1U<<_GTF_reading) +#define _GTF_writing (4) +#define GTF_writing (1U<<_GTF_writing) + +/* + * Subflags for GTF_accept_transfer: + * GTF_transfer_committed: Xen sets this flag to indicate that it is committed + * to transferring ownership of a page frame. When a guest sees this flag + * it must /not/ modify the grant entry until GTF_transfer_completed is + * set by Xen. + * GTF_transfer_completed: It is safe for the guest to spin-wait on this flag + * after reading GTF_transfer_committed. Xen will always write the frame + * address, followed by ORing this flag, in a timely manner. + */ +#define _GTF_transfer_committed (2) +#define GTF_transfer_committed (1U<<_GTF_transfer_committed) +#define _GTF_transfer_completed (3) +#define GTF_transfer_completed (1U<<_GTF_transfer_completed) + + +/*********************************** + * GRANT TABLE QUERIES AND USES + */ + +/* + * Reference to a grant entry in a specified domain's grant table. + */ +typedef uint32_t grant_ref_t; + +/* + * Handle to track a mapping created via a grant reference. + */ +typedef uint32_t grant_handle_t; + +/* + * GNTTABOP_map_grant_ref: Map the grant entry (<dom>,<ref>) for access + * by devices and/or host CPUs. If successful, <handle> is a tracking number + * that must be presented later to destroy the mapping(s). On error, <handle> + * is a negative status code. + * NOTES: + * 1. If GNTMAP_device_map is specified then <dev_bus_addr> is the address + * via which I/O devices may access the granted frame. + * 2. If GNTMAP_host_map is specified then a mapping will be added at + * either a host virtual address in the current address space, or at + * a PTE at the specified machine address. The type of mapping to + * perform is selected through the GNTMAP_contains_pte flag, and the + * address is specified in <host_addr>. + * 3. Mappings should only be destroyed via GNTTABOP_unmap_grant_ref. If a + * host mapping is destroyed by other means then it is *NOT* guaranteed + * to be accounted to the correct grant reference! + */ +#define GNTTABOP_map_grant_ref 0 +struct gnttab_map_grant_ref { + /* IN parameters. */ + uint64_t host_addr; + uint32_t flags; /* GNTMAP_* */ + grant_ref_t ref; + domid_t dom; + /* OUT parameters. */ + int16_t status; /* GNTST_* */ + grant_handle_t handle; + uint64_t dev_bus_addr; +}; + +/* + * GNTTABOP_unmap_grant_ref: Destroy one or more grant-reference mappings + * tracked by <handle>. If <host_addr> or <dev_bus_addr> is zero, that + * field is ignored. If non-zero, they must refer to a device/host mapping + * that is tracked by <handle> + * NOTES: + * 1. The call may fail in an undefined manner if either mapping is not + * tracked by <handle>. + * 3. After executing a batch of unmaps, it is guaranteed that no stale + * mappings will remain in the device or host TLBs. + */ +#define GNTTABOP_unmap_grant_ref 1 +struct gnttab_unmap_grant_ref { + /* IN parameters. */ + uint64_t host_addr; + uint64_t dev_bus_addr; + grant_handle_t handle; + /* OUT parameters. */ + int16_t status; /* GNTST_* */ +}; + +/* + * GNTTABOP_setup_table: Set up a grant table for <dom> comprising at least + * <nr_frames> pages. The frame addresses are written to the <frame_list>. + * Only <nr_frames> addresses are written, even if the table is larger. + * NOTES: + * 1. <dom> may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF. + * 3. Xen may not support more than a single grant-table page per domain. + */ +#define GNTTABOP_setup_table 2 +struct gnttab_setup_table { + /* IN parameters. */ + domid_t dom; + uint32_t nr_frames; + /* OUT parameters. */ + int16_t status; /* GNTST_* */ + ulong *frame_list; +}; + +/* + * GNTTABOP_dump_table: Dump the contents of the grant table to the + * xen console. Debugging use only. + */ +#define GNTTABOP_dump_table 3 +struct gnttab_dump_table { + /* IN parameters. */ + domid_t dom; + /* OUT parameters. */ + int16_t status; /* GNTST_* */ +}; + +/* + * GNTTABOP_transfer_grant_ref: Transfer <frame> to a foreign domain. The + * foreign domain has previously registered its interest in the transfer via + * <domid, ref>. + * + * Note that, even if the transfer fails, the specified page no longer belongs + * to the calling domain *unless* the error is GNTST_bad_page. + */ +#define GNTTABOP_transfer 4 +struct gnttab_transfer { + /* IN parameters. */ + unsigned long mfn; + domid_t domid; + grant_ref_t ref; + /* OUT parameters. */ + int16_t status; +}; + + +/* + * GNTTABOP_copy: Hypervisor based copy + * source and destinations can be eithers MFNs or, for foreign domains, + * grant references. the foreign domain has to grant read/write access + * in its grant table. + * + * The flags specify what type source and destinations are (either MFN + * or grant reference). + * + * Note that this can also be used to copy data between two domains + * via a third party if the source and destination domains had previously + * grant appropriate access to their pages to the third party. + * + * source_offset specifies an offset in the source frame, dest_offset + * the offset in the target frame and len specifies the number of + * bytes to be copied. + */ + +#define _GNTCOPY_source_gref (0) +#define GNTCOPY_source_gref (1<<_GNTCOPY_source_gref) +#define _GNTCOPY_dest_gref (1) +#define GNTCOPY_dest_gref (1<<_GNTCOPY_dest_gref) + +#define GNTTABOP_copy 5 +struct gnttab_copy { + /* IN parameters. */ + struct { + union { + grant_ref_t ref; + unsigned long gmfn; + } u; + domid_t domid; + uint16_t offset; + } source, dest; + uint16_t len; + uint16_t flags; /* GNTCOPY_* */ + /* OUT parameters. */ + int16_t status; +}; + +/* + * GNTTABOP_query_size: Query the current and maximum sizes of the shared + * grant table. + * NOTES: + * 1. <dom> may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF. + */ +#define GNTTABOP_query_size 6 +struct gnttab_query_size { + /* IN parameters. */ + domid_t dom; + /* OUT parameters. */ + uint32_t nr_frames; + uint32_t max_nr_frames; + int16_t status; /* GNTST_* */ +}; + + +/* + * Bitfield values for update_pin_status.flags. + */ + /* Map the grant entry for access by I/O devices. */ +#define _GNTMAP_device_map (0) +#define GNTMAP_device_map (1<<_GNTMAP_device_map) + /* Map the grant entry for access by host CPUs. */ +#define _GNTMAP_host_map (1) +#define GNTMAP_host_map (1<<_GNTMAP_host_map) + /* Accesses to the granted frame will be restricted to read-only access. */ +#define _GNTMAP_readonly (2) +#define GNTMAP_readonly (1<<_GNTMAP_readonly) + /* + * GNTMAP_host_map subflag: + * 0 => The host mapping is usable only by the guest OS. + * 1 => The host mapping is usable by guest OS + current application. + */ +#define _GNTMAP_application_map (3) +#define GNTMAP_application_map (1<<_GNTMAP_application_map) + + /* + * GNTMAP_contains_pte subflag: + * 0 => This map request contains a host virtual address. + * 1 => This map request contains the machine addess of the PTE to update. + */ +#define _GNTMAP_contains_pte (4) +#define GNTMAP_contains_pte (1<<_GNTMAP_contains_pte) + +/* + * Values for error status returns. All errors are -ve. + */ +#define GNTST_okay (0) /* Normal return. */ +#define GNTST_general_error (-1) /* General undefined error. */ +#define GNTST_bad_domain (-2) /* Unrecognsed domain id. */ +#define GNTST_bad_gntref (-3) /* Unrecognised or inappropriate gntref. */ +#define GNTST_bad_handle (-4) /* Unrecognised or inappropriate handle. */ +#define GNTST_bad_virt_addr (-5) /* Inappropriate virtual address to map. */ +#define GNTST_bad_dev_addr (-6) /* Inappropriate device address to unmap.*/ +#define GNTST_no_device_space (-7) /* Out of space in I/O MMU. */ +#define GNTST_permission_denied (-8) /* Not enough privilege for operation. */ +#define GNTST_bad_page (-9) /* Specified page was invalid for op. */ +#define GNTST_bad_copy_arg (-10) /* copy arguments cross page boundary */ + +#define GNTTABOP_error_msgs { \ + "okay", \ + "undefined error", \ + "unrecognised domain id", \ + "invalid grant reference", \ + "invalid mapping handle", \ + "invalid virtual address", \ + "invalid device address", \ + "no spare translation slot in the I/O MMU", \ + "permission denied", \ + "bad page", \ + "copy arguments cross page boundary" \ +} + +#endif /* __XEN_PUBLIC_GRANT_TABLE_H__ */ diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h new file mode 100644 index 00000000000..c2d1fa4dc1e --- /dev/null +++ b/include/xen/interface/io/blkif.h @@ -0,0 +1,94 @@ +/****************************************************************************** + * blkif.h + * + * Unified block-device I/O interface for Xen guest OSes. + * + * Copyright (c) 2003-2004, Keir Fraser + */ + +#ifndef __XEN_PUBLIC_IO_BLKIF_H__ +#define __XEN_PUBLIC_IO_BLKIF_H__ + +#include "ring.h" +#include "../grant_table.h" + +/* + * Front->back notifications: When enqueuing a new request, sending a + * notification can be made conditional on req_event (i.e., the generic + * hold-off mechanism provided by the ring macros). Backends must set + * req_event appropriately (e.g., using RING_FINAL_CHECK_FOR_REQUESTS()). + * + * Back->front notifications: When enqueuing a new response, sending a + * notification can be made conditional on rsp_event (i.e., the generic + * hold-off mechanism provided by the ring macros). Frontends must set + * rsp_event appropriately (e.g., using RING_FINAL_CHECK_FOR_RESPONSES()). + */ + +typedef uint16_t blkif_vdev_t; +typedef uint64_t blkif_sector_t; + +/* + * REQUEST CODES. + */ +#define BLKIF_OP_READ 0 +#define BLKIF_OP_WRITE 1 +/* + * Recognised only if "feature-barrier" is present in backend xenbus info. + * The "feature_barrier" node contains a boolean indicating whether barrier + * requests are likely to succeed or fail. Either way, a barrier request + * may fail at any time with BLKIF_RSP_EOPNOTSUPP if it is unsupported by + * the underlying block-device hardware. The boolean simply indicates whether + * or not it is worthwhile for the frontend to attempt barrier requests. + * If a backend does not recognise BLKIF_OP_WRITE_BARRIER, it should *not* + * create the "feature-barrier" node! + */ +#define BLKIF_OP_WRITE_BARRIER 2 + +/* + * Maximum scatter/gather segments per request. + * This is carefully chosen so that sizeof(struct blkif_ring) <= PAGE_SIZE. + * NB. This could be 12 if the ring indexes weren't stored in the same page. + */ +#define BLKIF_MAX_SEGMENTS_PER_REQUEST 11 + +struct blkif_request { + uint8_t operation; /* BLKIF_OP_??? */ + uint8_t nr_segments; /* number of segments */ + blkif_vdev_t handle; /* only for read/write requests */ + uint64_t id; /* private guest value, echoed in resp */ + blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */ + struct blkif_request_segment { + grant_ref_t gref; /* reference to I/O buffer frame */ + /* @first_sect: first sector in frame to transfer (inclusive). */ + /* @last_sect: last sector in frame to transfer (inclusive). */ + uint8_t first_sect, last_sect; + } seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; +}; + +struct blkif_response { + uint64_t id; /* copied from request */ + uint8_t operation; /* copied from request */ + int16_t status; /* BLKIF_RSP_??? */ +}; + +/* + * STATUS RETURN CODES. + */ + /* Operation not supported (only happens on barrier writes). */ +#define BLKIF_RSP_EOPNOTSUPP -2 + /* Operation failed for some unspecified reason (-EIO). */ +#define BLKIF_RSP_ERROR -1 + /* Operation completed successfully. */ +#define BLKIF_RSP_OKAY 0 + +/* + * Generate blkif ring structures and types. + */ + +DEFINE_RING_TYPES(blkif, struct blkif_request, struct blkif_response); + +#define VDISK_CDROM 0x1 +#define VDISK_REMOVABLE 0x2 +#define VDISK_READONLY 0x4 + +#endif /* __XEN_PUBLIC_IO_BLKIF_H__ */ diff --git a/include/xen/interface/io/console.h b/include/xen/interface/io/console.h new file mode 100644 index 00000000000..e563de70f78 --- /dev/null +++ b/include/xen/interface/io/console.h @@ -0,0 +1,23 @@ +/****************************************************************************** + * console.h + * + * Console I/O interface for Xen guest OSes. + * + * Copyright (c) 2005, Keir Fraser + */ + +#ifndef __XEN_PUBLIC_IO_CONSOLE_H__ +#define __XEN_PUBLIC_IO_CONSOLE_H__ + +typedef uint32_t XENCONS_RING_IDX; + +#define MASK_XENCONS_IDX(idx, ring) ((idx) & (sizeof(ring)-1)) + +struct xencons_interface { + char in[1024]; + char out[2048]; + XENCONS_RING_IDX in_cons, in_prod; + XENCONS_RING_IDX out_cons, out_prod; +}; + +#endif /* __XEN_PUBLIC_IO_CONSOLE_H__ */ diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h new file mode 100644 index 00000000000..518481c95f1 --- /dev/null +++ b/include/xen/interface/io/netif.h @@ -0,0 +1,158 @@ +/****************************************************************************** + * netif.h + * + * Unified network-device I/O interface for Xen guest OSes. + * + * Copyright (c) 2003-2004, Keir Fraser + */ + +#ifndef __XEN_PUBLIC_IO_NETIF_H__ +#define __XEN_PUBLIC_IO_NETIF_H__ + +#include "ring.h" +#include "../grant_table.h" + +/* + * Notifications after enqueuing any type of message should be conditional on + * the appropriate req_event or rsp_event field in the shared ring. + * If the client sends notification for rx requests then it should specify + * feature 'feature-rx-notify' via xenbus. Otherwise the backend will assume + * that it cannot safely queue packets (as it may not be kicked to send them). + */ + +/* + * This is the 'wire' format for packets: + * Request 1: netif_tx_request -- NETTXF_* (any flags) + * [Request 2: netif_tx_extra] (only if request 1 has NETTXF_extra_info) + * [Request 3: netif_tx_extra] (only if request 2 has XEN_NETIF_EXTRA_MORE) + * Request 4: netif_tx_request -- NETTXF_more_data + * Request 5: netif_tx_request -- NETTXF_more_data + * ... + * Request N: netif_tx_request -- 0 + */ + +/* Protocol checksum field is blank in the packet (hardware offload)? */ +#define _NETTXF_csum_blank (0) +#define NETTXF_csum_blank (1U<<_NETTXF_csum_blank) + +/* Packet data has been validated against protocol checksum. */ +#define _NETTXF_data_validated (1) +#define NETTXF_data_validated (1U<<_NETTXF_data_validated) + +/* Packet continues in the next request descriptor. */ +#define _NETTXF_more_data (2) +#define NETTXF_more_data (1U<<_NETTXF_more_data) + +/* Packet to be followed by extra descriptor(s). */ +#define _NETTXF_extra_info (3) +#define NETTXF_extra_info (1U<<_NETTXF_extra_info) + +struct xen_netif_tx_request { + grant_ref_t gref; /* Reference to buffer page */ + uint16_t offset; /* Offset within buffer page */ + uint16_t flags; /* NETTXF_* */ + uint16_t id; /* Echoed in response message. */ + uint16_t size; /* Packet size in bytes. */ +}; + +/* Types of netif_extra_info descriptors. */ +#define XEN_NETIF_EXTRA_TYPE_NONE (0) /* Never used - invalid */ +#define XEN_NETIF_EXTRA_TYPE_GSO (1) /* u.gso */ +#define XEN_NETIF_EXTRA_TYPE_MAX (2) + +/* netif_extra_info flags. */ +#define _XEN_NETIF_EXTRA_FLAG_MORE (0) +#define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE) + +/* GSO types - only TCPv4 currently supported. */ +#define XEN_NETIF_GSO_TYPE_TCPV4 (1) + +/* + * This structure needs to fit within both netif_tx_request and + * netif_rx_response for compatibility. + */ +struct xen_netif_extra_info { + uint8_t type; /* XEN_NETIF_EXTRA_TYPE_* */ + uint8_t flags; /* XEN_NETIF_EXTRA_FLAG_* */ + + union { + struct { + /* + * Maximum payload size of each segment. For + * example, for TCP this is just the path MSS. + */ + uint16_t size; + + /* + * GSO type. This determines the protocol of + * the packet and any extra features required + * to segment the packet properly. + */ + uint8_t type; /* XEN_NETIF_GSO_TYPE_* */ + + /* Future expansion. */ + uint8_t pad; + + /* + * GSO features. This specifies any extra GSO + * features required to process this packet, + * such as ECN support for TCPv4. + */ + uint16_t features; /* XEN_NETIF_GSO_FEAT_* */ + } gso; + + uint16_t pad[3]; + } u; +}; + +struct xen_netif_tx_response { + uint16_t id; + int16_t status; /* NETIF_RSP_* */ +}; + +struct xen_netif_rx_request { + uint16_t id; /* Echoed in response message. */ + grant_ref_t gref; /* Reference to incoming granted frame */ +}; + +/* Packet data has been validated against protocol checksum. */ +#define _NETRXF_data_validated (0) +#define NETRXF_data_validated (1U<<_NETRXF_data_validated) + +/* Protocol checksum field is blank in the packet (hardware offload)? */ +#define _NETRXF_csum_blank (1) +#define NETRXF_csum_blank (1U<<_NETRXF_csum_blank) + +/* Packet continues in the next request descriptor. */ +#define _NETRXF_more_data (2) +#define NETRXF_more_data (1U<<_NETRXF_more_data) + +/* Packet to be followed by extra descriptor(s). */ +#define _NETRXF_extra_info (3) +#define NETRXF_extra_info (1U<<_NETRXF_extra_info) + +struct xen_netif_rx_response { + uint16_t id; + uint16_t offset; /* Offset in page of start of received packet */ + uint16_t flags; /* NETRXF_* */ + int16_t status; /* -ve: BLKIF_RSP_* ; +ve: Rx'ed pkt size. */ +}; + +/* + * Generate netif ring structures and types. + */ + +DEFINE_RING_TYPES(xen_netif_tx, + struct xen_netif_tx_request, + struct xen_netif_tx_response); +DEFINE_RING_TYPES(xen_netif_rx, + struct xen_netif_rx_request, + struct xen_netif_rx_response); + +#define NETIF_RSP_DROPPED -2 +#define NETIF_RSP_ERROR -1 +#define NETIF_RSP_OKAY 0 +/* No response: used for auxiliary requests (e.g., netif_tx_extra). */ +#define NETIF_RSP_NULL 1 + +#endif diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h new file mode 100644 index 00000000000..e8cbf431c8c --- /dev/null +++ b/include/xen/interface/io/ring.h @@ -0,0 +1,260 @@ +/****************************************************************************** + * ring.h + * + * Shared producer-consumer ring macros. + * + * Tim Deegan and Andrew Warfield November 2004. + */ + +#ifndef __XEN_PUBLIC_IO_RING_H__ +#define __XEN_PUBLIC_IO_RING_H__ + +typedef unsigned int RING_IDX; + +/* Round a 32-bit unsigned constant down to the nearest power of two. */ +#define __RD2(_x) (((_x) & 0x00000002) ? 0x2 : ((_x) & 0x1)) +#define __RD4(_x) (((_x) & 0x0000000c) ? __RD2((_x)>>2)<<2 : __RD2(_x)) +#define __RD8(_x) (((_x) & 0x000000f0) ? __RD4((_x)>>4)<<4 : __RD4(_x)) +#define __RD16(_x) (((_x) & 0x0000ff00) ? __RD8((_x)>>8)<<8 : __RD8(_x)) +#define __RD32(_x) (((_x) & 0xffff0000) ? __RD16((_x)>>16)<<16 : __RD16(_x)) + +/* + * Calculate size of a shared ring, given the total available space for the + * ring and indexes (_sz), and the name tag of the request/response structure. + * A ring contains as many entries as will fit, rounded down to the nearest + * power of two (so we can mask with (size-1) to loop around). + */ +#define __RING_SIZE(_s, _sz) \ + (__RD32(((_sz) - (long)&(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0]))) + +/* + * Macros to make the correct C datatypes for a new kind of ring. + * + * To make a new ring datatype, you need to have two message structures, + * let's say struct request, and struct response already defined. + * + * In a header where you want the ring datatype declared, you then do: + * + * DEFINE_RING_TYPES(mytag, struct request, struct response); + * + * These expand out to give you a set of types, as you can see below. + * The most important of these are: + * + * struct mytag_sring - The shared ring. + * struct mytag_front_ring - The 'front' half of the ring. + * struct mytag_back_ring - The 'back' half of the ring. + * + * To initialize a ring in your code you need to know the location and size + * of the shared memory area (PAGE_SIZE, for instance). To initialise + * the front half: + * + * struct mytag_front_ring front_ring; + * SHARED_RING_INIT((struct mytag_sring *)shared_page); + * FRONT_RING_INIT(&front_ring, (struct mytag_sring *)shared_page, + * PAGE_SIZE); + * + * Initializing the back follows similarly (note that only the front + * initializes the shared ring): + * + * struct mytag_back_ring back_ring; + * BACK_RING_INIT(&back_ring, (struct mytag_sring *)shared_page, + * PAGE_SIZE); + */ + +#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t) \ + \ +/* Shared ring entry */ \ +union __name##_sring_entry { \ + __req_t req; \ + __rsp_t rsp; \ +}; \ + \ +/* Shared ring page */ \ +struct __name##_sring { \ + RING_IDX req_prod, req_event; \ + RING_IDX rsp_prod, rsp_event; \ + uint8_t pad[48]; \ + union __name##_sring_entry ring[1]; /* variable-length */ \ +}; \ + \ +/* "Front" end's private variables */ \ +struct __name##_front_ring { \ + RING_IDX req_prod_pvt; \ + RING_IDX rsp_cons; \ + unsigned int nr_ents; \ + struct __name##_sring *sring; \ +}; \ + \ +/* "Back" end's private variables */ \ +struct __name##_back_ring { \ + RING_IDX rsp_prod_pvt; \ + RING_IDX req_cons; \ + unsigned int nr_ents; \ + struct __name##_sring *sring; \ +}; + +/* + * Macros for manipulating rings. + * + * FRONT_RING_whatever works on the "front end" of a ring: here + * requests are pushed on to the ring and responses taken off it. + * + * BACK_RING_whatever works on the "back end" of a ring: here + * requests are taken off the ring and responses put on. + * + * N.B. these macros do NO INTERLOCKS OR FLOW CONTROL. + * This is OK in 1-for-1 request-response situations where the + * requestor (front end) never has more than RING_SIZE()-1 + * outstanding requests. + */ + +/* Initialising empty rings */ +#define SHARED_RING_INIT(_s) do { \ + (_s)->req_prod = (_s)->rsp_prod = 0; \ + (_s)->req_event = (_s)->rsp_event = 1; \ + memset((_s)->pad, 0, sizeof((_s)->pad)); \ +} while(0) + +#define FRONT_RING_INIT(_r, _s, __size) do { \ + (_r)->req_prod_pvt = 0; \ + (_r)->rsp_cons = 0; \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ + (_r)->sring = (_s); \ +} while (0) + +#define BACK_RING_INIT(_r, _s, __size) do { \ + (_r)->rsp_prod_pvt = 0; \ + (_r)->req_cons = 0; \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ + (_r)->sring = (_s); \ +} while (0) + +/* Initialize to existing shared indexes -- for recovery */ +#define FRONT_RING_ATTACH(_r, _s, __size) do { \ + (_r)->sring = (_s); \ + (_r)->req_prod_pvt = (_s)->req_prod; \ + (_r)->rsp_cons = (_s)->rsp_prod; \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ +} while (0) + +#define BACK_RING_ATTACH(_r, _s, __size) do { \ + (_r)->sring = (_s); \ + (_r)->rsp_prod_pvt = (_s)->rsp_prod; \ + (_r)->req_cons = (_s)->req_prod; \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ +} while (0) + +/* How big is this ring? */ +#define RING_SIZE(_r) \ + ((_r)->nr_ents) + +/* Number of free requests (for use on front side only). */ +#define RING_FREE_REQUESTS(_r) \ + (RING_SIZE(_r) - ((_r)->req_prod_pvt - (_r)->rsp_cons)) + +/* Test if there is an empty slot available on the front ring. + * (This is only meaningful from the front. ) + */ +#define RING_FULL(_r) \ + (RING_FREE_REQUESTS(_r) == 0) + +/* Test if there are outstanding messages to be processed on a ring. */ +#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ + ((_r)->sring->rsp_prod - (_r)->rsp_cons) + +#define RING_HAS_UNCONSUMED_REQUESTS(_r) \ + ({ \ + unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \ + unsigned int rsp = RING_SIZE(_r) - \ + ((_r)->req_cons - (_r)->rsp_prod_pvt); \ + req < rsp ? req : rsp; \ + }) + +/* Direct access to individual ring elements, by index. */ +#define RING_GET_REQUEST(_r, _idx) \ + (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req)) + +#define RING_GET_RESPONSE(_r, _idx) \ + (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp)) + +/* Loop termination condition: Would the specified index overflow the ring? */ +#define RING_REQUEST_CONS_OVERFLOW(_r, _cons) \ + (((_cons) - (_r)->rsp_prod_pvt) >= RING_SIZE(_r)) + +#define RING_PUSH_REQUESTS(_r) do { \ + wmb(); /* back sees requests /before/ updated producer index */ \ + (_r)->sring->req_prod = (_r)->req_prod_pvt; \ +} while (0) + +#define RING_PUSH_RESPONSES(_r) do { \ + wmb(); /* front sees responses /before/ updated producer index */ \ + (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt; \ +} while (0) + +/* + * Notification hold-off (req_event and rsp_event): + * + * When queueing requests or responses on a shared ring, it may not always be + * necessary to notify the remote end. For example, if requests are in flight + * in a backend, the front may be able to queue further requests without + * notifying the back (if the back checks for new requests when it queues + * responses). + * + * When enqueuing requests or responses: + * + * Use RING_PUSH_{REQUESTS,RESPONSES}_AND_CHECK_NOTIFY(). The second argument + * is a boolean return value. True indicates that the receiver requires an + * asynchronous notification. + * + * After dequeuing requests or responses (before sleeping the connection): + * + * Use RING_FINAL_CHECK_FOR_REQUESTS() or RING_FINAL_CHECK_FOR_RESPONSES(). + * The second argument is a boolean return value. True indicates that there + * are pending messages on the ring (i.e., the connection should not be put + * to sleep). + * + * These macros will set the req_event/rsp_event field to trigger a + * notification on the very next message that is enqueued. If you want to + * create batches of work (i.e., only receive a notification after several + * messages have been enqueued) then you will need to create a customised + * version of the FINAL_CHECK macro in your own code, which sets the event + * field appropriately. + */ + +#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do { \ + RING_IDX __old = (_r)->sring->req_prod; \ + RING_IDX __new = (_r)->req_prod_pvt; \ + wmb(); /* back sees requests /before/ updated producer index */ \ + (_r)->sring->req_prod = __new; \ + mb(); /* back sees new requests /before/ we check req_event */ \ + (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) < \ + (RING_IDX)(__new - __old)); \ +} while (0) + +#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do { \ + RING_IDX __old = (_r)->sring->rsp_prod; \ + RING_IDX __new = (_r)->rsp_prod_pvt; \ + wmb(); /* front sees responses /before/ updated producer index */ \ + (_r)->sring->rsp_prod = __new; \ + mb(); /* front sees new responses /before/ we check rsp_event */ \ + (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) < \ + (RING_IDX)(__new - __old)); \ +} while (0) + +#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do { \ + (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ + if (_work_to_do) break; \ + (_r)->sring->req_event = (_r)->req_cons + 1; \ + mb(); \ + (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ +} while (0) + +#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do { \ + (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ + if (_work_to_do) break; \ + (_r)->sring->rsp_event = (_r)->rsp_cons + 1; \ + mb(); \ + (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ +} while (0) + +#endif /* __XEN_PUBLIC_IO_RING_H__ */ diff --git a/include/xen/interface/io/xenbus.h b/include/xen/interface/io/xenbus.h new file mode 100644 index 00000000000..46508c7fa39 --- /dev/null +++ b/include/xen/interface/io/xenbus.h @@ -0,0 +1,44 @@ +/***************************************************************************** + * xenbus.h + * + * Xenbus protocol details. + * + * Copyright (C) 2005 XenSource Ltd. + */ + +#ifndef _XEN_PUBLIC_IO_XENBUS_H +#define _XEN_PUBLIC_IO_XENBUS_H + +/* The state of either end of the Xenbus, i.e. the current communication + status of initialisation across the bus. States here imply nothing about + the state of the connection between the driver and the kernel's device + layers. */ +enum xenbus_state +{ + XenbusStateUnknown = 0, + XenbusStateInitialising = 1, + XenbusStateInitWait = 2, /* Finished early + initialisation, but waiting + for information from the peer + or hotplug scripts. */ + XenbusStateInitialised = 3, /* Initialised and waiting for a + connection from the peer. */ + XenbusStateConnected = 4, + XenbusStateClosing = 5, /* The device is being closed + due to an error or an unplug + event. */ + XenbusStateClosed = 6 + +}; + +#endif /* _XEN_PUBLIC_IO_XENBUS_H */ + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff --git a/include/xen/interface/io/xs_wire.h b/include/xen/interface/io/xs_wire.h new file mode 100644 index 00000000000..99fcffb372d --- /dev/null +++ b/include/xen/interface/io/xs_wire.h @@ -0,0 +1,87 @@ +/* + * Details of the "wire" protocol between Xen Store Daemon and client + * library or guest kernel. + * Copyright (C) 2005 Rusty Russell IBM Corporation + */ + +#ifndef _XS_WIRE_H +#define _XS_WIRE_H + +enum xsd_sockmsg_type +{ + XS_DEBUG, + XS_DIRECTORY, + XS_READ, + XS_GET_PERMS, + XS_WATCH, + XS_UNWATCH, + XS_TRANSACTION_START, + XS_TRANSACTION_END, + XS_INTRODUCE, + XS_RELEASE, + XS_GET_DOMAIN_PATH, + XS_WRITE, + XS_MKDIR, + XS_RM, + XS_SET_PERMS, + XS_WATCH_EVENT, + XS_ERROR, + XS_IS_DOMAIN_INTRODUCED +}; + +#define XS_WRITE_NONE "NONE" +#define XS_WRITE_CREATE "CREATE" +#define XS_WRITE_CREATE_EXCL "CREATE|EXCL" + +/* We hand errors as strings, for portability. */ +struct xsd_errors +{ + int errnum; + const char *errstring; +}; +#define XSD_ERROR(x) { x, #x } +static struct xsd_errors xsd_errors[] __attribute__((unused)) = { + XSD_ERROR(EINVAL), + XSD_ERROR(EACCES), + XSD_ERROR(EEXIST), + XSD_ERROR(EISDIR), + XSD_ERROR(ENOENT), + XSD_ERROR(ENOMEM), + XSD_ERROR(ENOSPC), + XSD_ERROR(EIO), + XSD_ERROR(ENOTEMPTY), + XSD_ERROR(ENOSYS), + XSD_ERROR(EROFS), + XSD_ERROR(EBUSY), + XSD_ERROR(EAGAIN), + XSD_ERROR(EISCONN) +}; + +struct xsd_sockmsg +{ + uint32_t type; /* XS_??? */ + uint32_t req_id;/* Request identifier, echoed in daemon's response. */ + uint32_t tx_id; /* Transaction id (0 if not related to a transaction). */ + uint32_t len; /* Length of data following this. */ + + /* Generally followed by nul-terminated string(s). */ +}; + +enum xs_watch_type +{ + XS_WATCH_PATH = 0, + XS_WATCH_TOKEN +}; + +/* Inter-domain shared memory communications. */ +#define XENSTORE_RING_SIZE 1024 +typedef uint32_t XENSTORE_RING_IDX; +#define MASK_XENSTORE_IDX(idx) ((idx) & (XENSTORE_RING_SIZE-1)) +struct xenstore_domain_interface { + char req[XENSTORE_RING_SIZE]; /* Requests to xenstore daemon. */ + char rsp[XENSTORE_RING_SIZE]; /* Replies and async watch events. */ + XENSTORE_RING_IDX req_cons, req_prod; + XENSTORE_RING_IDX rsp_cons, rsp_prod; +}; + +#endif /* _XS_WIRE_H */ diff --git a/include/xen/interface/memory.h b/include/xen/interface/memory.h new file mode 100644 index 00000000000..af36ead1681 --- /dev/null +++ b/include/xen/interface/memory.h @@ -0,0 +1,145 @@ +/****************************************************************************** + * memory.h + * + * Memory reservation and information. + * + * Copyright (c) 2005, Keir Fraser <keir@xensource.com> + */ + +#ifndef __XEN_PUBLIC_MEMORY_H__ +#define __XEN_PUBLIC_MEMORY_H__ + +/* + * Increase or decrease the specified domain's memory reservation. Returns a + * -ve errcode on failure, or the # extents successfully allocated or freed. + * arg == addr of struct xen_memory_reservation. + */ +#define XENMEM_increase_reservation 0 +#define XENMEM_decrease_reservation 1 +#define XENMEM_populate_physmap 6 +struct xen_memory_reservation { + + /* + * XENMEM_increase_reservation: + * OUT: MFN (*not* GMFN) bases of extents that were allocated + * XENMEM_decrease_reservation: + * IN: GMFN bases of extents to free + * XENMEM_populate_physmap: + * IN: GPFN bases of extents to populate with memory + * OUT: GMFN bases of extents that were allocated + * (NB. This command also updates the mach_to_phys translation table) + */ + GUEST_HANDLE(ulong) extent_start; + + /* Number of extents, and size/alignment of each (2^extent_order pages). */ + unsigned long nr_extents; + unsigned int extent_order; + + /* + * Maximum # bits addressable by the user of the allocated region (e.g., + * I/O devices often have a 32-bit limitation even in 64-bit systems). If + * zero then the user has no addressing restriction. + * This field is not used by XENMEM_decrease_reservation. + */ + unsigned int address_bits; + + /* + * Domain whose reservation is being changed. + * Unprivileged domains can specify only DOMID_SELF. + */ + domid_t domid; + +}; +DEFINE_GUEST_HANDLE_STRUCT(xen_memory_reservation); + +/* + * Returns the maximum machine frame number of mapped RAM in this system. + * This command always succeeds (it never returns an error code). + * arg == NULL. + */ +#define XENMEM_maximum_ram_page 2 + +/* + * Returns the current or maximum memory reservation, in pages, of the + * specified domain (may be DOMID_SELF). Returns -ve errcode on failure. + * arg == addr of domid_t. + */ +#define XENMEM_current_reservation 3 +#define XENMEM_maximum_reservation 4 + +/* + * Returns a list of MFN bases of 2MB extents comprising the machine_to_phys + * mapping table. Architectures which do not have a m2p table do not implement + * this command. + * arg == addr of xen_machphys_mfn_list_t. + */ +#define XENMEM_machphys_mfn_list 5 +struct xen_machphys_mfn_list { + /* + * Size of the 'extent_start' array. Fewer entries will be filled if the + * machphys table is smaller than max_extents * 2MB. + */ + unsigned int max_extents; + + /* + * Pointer to buffer to fill with list of extent starts. If there are + * any large discontiguities in the machine address space, 2MB gaps in + * the machphys table will be represented by an MFN base of zero. + */ + GUEST_HANDLE(ulong) extent_start; + + /* + * Number of extents written to the above array. This will be smaller + * than 'max_extents' if the machphys table is smaller than max_e * 2MB. + */ + unsigned int nr_extents; +}; +DEFINE_GUEST_HANDLE_STRUCT(xen_machphys_mfn_list); + +/* + * Sets the GPFN at which a particular page appears in the specified guest's + * pseudophysical address space. + * arg == addr of xen_add_to_physmap_t. + */ +#define XENMEM_add_to_physmap 7 +struct xen_add_to_physmap { + /* Which domain to change the mapping for. */ + domid_t domid; + + /* Source mapping space. */ +#define XENMAPSPACE_shared_info 0 /* shared info page */ +#define XENMAPSPACE_grant_table 1 /* grant table page */ + unsigned int space; + + /* Index into source mapping space. */ + unsigned long idx; + + /* GPFN where the source mapping page should appear. */ + unsigned long gpfn; +}; +DEFINE_GUEST_HANDLE_STRUCT(xen_add_to_physmap); + +/* + * Translates a list of domain-specific GPFNs into MFNs. Returns a -ve error + * code on failure. This call only works for auto-translated guests. + */ +#define XENMEM_translate_gpfn_list 8 +struct xen_translate_gpfn_list { + /* Which domain to translate for? */ + domid_t domid; + + /* Length of list. */ + unsigned long nr_gpfns; + + /* List of GPFNs to translate. */ + GUEST_HANDLE(ulong) gpfn_list; + + /* + * Output list to contain MFN translations. May be the same as the input + * list (in which case each input GPFN is overwritten with the output MFN). + */ + GUEST_HANDLE(ulong) mfn_list; +}; +DEFINE_GUEST_HANDLE_STRUCT(xen_translate_gpfn_list); + +#endif /* __XEN_PUBLIC_MEMORY_H__ */ diff --git a/include/xen/interface/physdev.h b/include/xen/interface/physdev.h new file mode 100644 index 00000000000..cd6939147cb --- /dev/null +++ b/include/xen/interface/physdev.h @@ -0,0 +1,145 @@ +/* + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +#ifndef __XEN_PUBLIC_PHYSDEV_H__ +#define __XEN_PUBLIC_PHYSDEV_H__ + +/* + * Prototype for this hypercall is: + * int physdev_op(int cmd, void *args) + * @cmd == PHYSDEVOP_??? (physdev operation). + * @args == Operation-specific extra arguments (NULL if none). + */ + +/* + * Notify end-of-interrupt (EOI) for the specified IRQ. + * @arg == pointer to physdev_eoi structure. + */ +#define PHYSDEVOP_eoi 12 +struct physdev_eoi { + /* IN */ + uint32_t irq; +}; + +/* + * Query the status of an IRQ line. + * @arg == pointer to physdev_irq_status_query structure. + */ +#define PHYSDEVOP_irq_status_query 5 +struct physdev_irq_status_query { + /* IN */ + uint32_t irq; + /* OUT */ + uint32_t flags; /* XENIRQSTAT_* */ +}; + +/* Need to call PHYSDEVOP_eoi when the IRQ has been serviced? */ +#define _XENIRQSTAT_needs_eoi (0) +#define XENIRQSTAT_needs_eoi (1U<<_XENIRQSTAT_needs_eoi) + +/* IRQ shared by multiple guests? */ +#define _XENIRQSTAT_shared (1) +#define XENIRQSTAT_shared (1U<<_XENIRQSTAT_shared) + +/* + * Set the current VCPU's I/O privilege level. + * @arg == pointer to physdev_set_iopl structure. + */ +#define PHYSDEVOP_set_iopl 6 +struct physdev_set_iopl { + /* IN */ + uint32_t iopl; +}; + +/* + * Set the current VCPU's I/O-port permissions bitmap. + * @arg == pointer to physdev_set_iobitmap structure. + */ +#define PHYSDEVOP_set_iobitmap 7 +struct physdev_set_iobitmap { + /* IN */ + uint8_t * bitmap; + uint32_t nr_ports; +}; + +/* + * Read or write an IO-APIC register. + * @arg == pointer to physdev_apic structure. + */ +#define PHYSDEVOP_apic_read 8 +#define PHYSDEVOP_apic_write 9 +struct physdev_apic { + /* IN */ + unsigned long apic_physbase; + uint32_t reg; + /* IN or OUT */ + uint32_t value; +}; + +/* + * Allocate or free a physical upcall vector for the specified IRQ line. + * @arg == pointer to physdev_irq structure. + */ +#define PHYSDEVOP_alloc_irq_vector 10 +#define PHYSDEVOP_free_irq_vector 11 +struct physdev_irq { + /* IN */ + uint32_t irq; + /* IN or OUT */ + uint32_t vector; +}; + +/* + * Argument to physdev_op_compat() hypercall. Superceded by new physdev_op() + * hypercall since 0x00030202. + */ +struct physdev_op { + uint32_t cmd; + union { + struct physdev_irq_status_query irq_status_query; + struct physdev_set_iopl set_iopl; + struct physdev_set_iobitmap set_iobitmap; + struct physdev_apic apic_op; + struct physdev_irq irq_op; + } u; +}; + +/* + * Notify that some PIRQ-bound event channels have been unmasked. + * ** This command is obsolete since interface version 0x00030202 and is ** + * ** unsupported by newer versions of Xen. ** + */ +#define PHYSDEVOP_IRQ_UNMASK_NOTIFY 4 + +/* + * These all-capitals physdev operation names are superceded by the new names + * (defined above) since interface version 0x00030202. + */ +#define PHYSDEVOP_IRQ_STATUS_QUERY PHYSDEVOP_irq_status_query +#define PHYSDEVOP_SET_IOPL PHYSDEVOP_set_iopl +#define PHYSDEVOP_SET_IOBITMAP PHYSDEVOP_set_iobitmap +#define PHYSDEVOP_APIC_READ PHYSDEVOP_apic_read +#define PHYSDEVOP_APIC_WRITE PHYSDEVOP_apic_write +#define PHYSDEVOP_ASSIGN_VECTOR PHYSDEVOP_alloc_irq_vector +#define PHYSDEVOP_FREE_VECTOR PHYSDEVOP_free_irq_vector +#define PHYSDEVOP_IRQ_NEEDS_UNMASK_NOTIFY XENIRQSTAT_needs_eoi +#define PHYSDEVOP_IRQ_SHARED XENIRQSTAT_shared + +#endif /* __XEN_PUBLIC_PHYSDEV_H__ */ diff --git a/include/xen/interface/sched.h b/include/xen/interface/sched.h new file mode 100644 index 00000000000..5fec575a800 --- /dev/null +++ b/include/xen/interface/sched.h @@ -0,0 +1,77 @@ +/****************************************************************************** + * sched.h + * + * Scheduler state interactions + * + * Copyright (c) 2005, Keir Fraser <keir@xensource.com> + */ + +#ifndef __XEN_PUBLIC_SCHED_H__ +#define __XEN_PUBLIC_SCHED_H__ + +#include "event_channel.h" + +/* + * The prototype for this hypercall is: + * long sched_op_new(int cmd, void *arg) + * @cmd == SCHEDOP_??? (scheduler operation). + * @arg == Operation-specific extra argument(s), as described below. + * + * **NOTE**: + * Versions of Xen prior to 3.0.2 provide only the following legacy version + * of this hypercall, supporting only the commands yield, block and shutdown: + * long sched_op(int cmd, unsigned long arg) + * @cmd == SCHEDOP_??? (scheduler operation). + * @arg == 0 (SCHEDOP_yield and SCHEDOP_block) + * == SHUTDOWN_* code (SCHEDOP_shutdown) + */ + +/* + * Voluntarily yield the CPU. + * @arg == NULL. + */ +#define SCHEDOP_yield 0 + +/* + * Block execution of this VCPU until an event is received for processing. + * If called with event upcalls masked, this operation will atomically + * reenable event delivery and check for pending events before blocking the + * VCPU. This avoids a "wakeup waiting" race. + * @arg == NULL. + */ +#define SCHEDOP_block 1 + +/* + * Halt execution of this domain (all VCPUs) and notify the system controller. + * @arg == pointer to sched_shutdown structure. + */ +#define SCHEDOP_shutdown 2 +struct sched_shutdown { + unsigned int reason; /* SHUTDOWN_* */ +}; +DEFINE_GUEST_HANDLE_STRUCT(sched_shutdown); + +/* + * Poll a set of event-channel ports. Return when one or more are pending. An + * optional timeout may be specified. + * @arg == pointer to sched_poll structure. + */ +#define SCHEDOP_poll 3 +struct sched_poll { + GUEST_HANDLE(evtchn_port_t) ports; + unsigned int nr_ports; + uint64_t timeout; +}; +DEFINE_GUEST_HANDLE_STRUCT(sched_poll); + +/* + * Reason codes for SCHEDOP_shutdown. These may be interpreted by control + * software to determine the appropriate action. For the most part, Xen does + * not care about the shutdown code. + */ +#define SHUTDOWN_poweroff 0 /* Domain exited normally. Clean up and kill. */ +#define SHUTDOWN_reboot 1 /* Clean up, kill, and then restart. */ +#define SHUTDOWN_suspend 2 /* Clean up, save suspend info, kill. */ +#define SHUTDOWN_crash 3 /* Tell controller we've crashed. */ + +#endif /* __XEN_PUBLIC_SCHED_H__ */ diff --git a/include/xen/interface/vcpu.h b/include/xen/interface/vcpu.h new file mode 100644 index 00000000000..ff61ea36599 --- /dev/null +++ b/include/xen/interface/vcpu.h @@ -0,0 +1,167 @@ +/****************************************************************************** + * vcpu.h + * + * VCPU initialisation, query, and hotplug. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2005, Keir Fraser <keir@xensource.com> + */ + +#ifndef __XEN_PUBLIC_VCPU_H__ +#define __XEN_PUBLIC_VCPU_H__ + +/* + * Prototype for this hypercall is: + * int vcpu_op(int cmd, int vcpuid, void *extra_args) + * @cmd == VCPUOP_??? (VCPU operation). + * @vcpuid == VCPU to operate on. + * @extra_args == Operation-specific extra arguments (NULL if none). + */ + +/* + * Initialise a VCPU. Each VCPU can be initialised only once. A + * newly-initialised VCPU will not run until it is brought up by VCPUOP_up. + * + * @extra_arg == pointer to vcpu_guest_context structure containing initial + * state for the VCPU. + */ +#define VCPUOP_initialise 0 + +/* + * Bring up a VCPU. This makes the VCPU runnable. This operation will fail + * if the VCPU has not been initialised (VCPUOP_initialise). + */ +#define VCPUOP_up 1 + +/* + * Bring down a VCPU (i.e., make it non-runnable). + * There are a few caveats that callers should observe: + * 1. This operation may return, and VCPU_is_up may return false, before the + * VCPU stops running (i.e., the command is asynchronous). It is a good + * idea to ensure that the VCPU has entered a non-critical loop before + * bringing it down. Alternatively, this operation is guaranteed + * synchronous if invoked by the VCPU itself. + * 2. After a VCPU is initialised, there is currently no way to drop all its + * references to domain memory. Even a VCPU that is down still holds + * memory references via its pagetable base pointer and GDT. It is good + * practise to move a VCPU onto an 'idle' or default page table, LDT and + * GDT before bringing it down. + */ +#define VCPUOP_down 2 + +/* Returns 1 if the given VCPU is up. */ +#define VCPUOP_is_up 3 + +/* + * Return information about the state and running time of a VCPU. + * @extra_arg == pointer to vcpu_runstate_info structure. + */ +#define VCPUOP_get_runstate_info 4 +struct vcpu_runstate_info { + /* VCPU's current state (RUNSTATE_*). */ + int state; + /* When was current state entered (system time, ns)? */ + uint64_t state_entry_time; + /* + * Time spent in each RUNSTATE_* (ns). The sum of these times is + * guaranteed not to drift from system time. + */ + uint64_t time[4]; +}; + +/* VCPU is currently running on a physical CPU. */ +#define RUNSTATE_running 0 + +/* VCPU is runnable, but not currently scheduled on any physical CPU. */ +#define RUNSTATE_runnable 1 + +/* VCPU is blocked (a.k.a. idle). It is therefore not runnable. */ +#define RUNSTATE_blocked 2 + +/* + * VCPU is not runnable, but it is not blocked. + * This is a 'catch all' state for things like hotplug and pauses by the + * system administrator (or for critical sections in the hypervisor). + * RUNSTATE_blocked dominates this state (it is the preferred state). + */ +#define RUNSTATE_offline 3 + +/* + * Register a shared memory area from which the guest may obtain its own + * runstate information without needing to execute a hypercall. + * Notes: + * 1. The registered address may be virtual or physical, depending on the + * platform. The virtual address should be registered on x86 systems. + * 2. Only one shared area may be registered per VCPU. The shared area is + * updated by the hypervisor each time the VCPU is scheduled. Thus + * runstate.state will always be RUNSTATE_running and + * runstate.state_entry_time will indicate the system time at which the + * VCPU was last scheduled to run. + * @extra_arg == pointer to vcpu_register_runstate_memory_area structure. + */ +#define VCPUOP_register_runstate_memory_area 5 +struct vcpu_register_runstate_memory_area { + union { + struct vcpu_runstate_info *v; + uint64_t p; + } addr; +}; + +/* + * Set or stop a VCPU's periodic timer. Every VCPU has one periodic timer + * which can be set via these commands. Periods smaller than one millisecond + * may not be supported. + */ +#define VCPUOP_set_periodic_timer 6 /* arg == vcpu_set_periodic_timer_t */ +#define VCPUOP_stop_periodic_timer 7 /* arg == NULL */ +struct vcpu_set_periodic_timer { + uint64_t period_ns; +}; + +/* + * Set or stop a VCPU's single-shot timer. Every VCPU has one single-shot + * timer which can be set via these commands. + */ +#define VCPUOP_set_singleshot_timer 8 /* arg == vcpu_set_singleshot_timer_t */ +#define VCPUOP_stop_singleshot_timer 9 /* arg == NULL */ +struct vcpu_set_singleshot_timer { + uint64_t timeout_abs_ns; + uint32_t flags; /* VCPU_SSHOTTMR_??? */ +}; + +/* Flags to VCPUOP_set_singleshot_timer. */ + /* Require the timeout to be in the future (return -ETIME if it's passed). */ +#define _VCPU_SSHOTTMR_future (0) +#define VCPU_SSHOTTMR_future (1U << _VCPU_SSHOTTMR_future) + +/* + * Register a memory location in the guest address space for the + * vcpu_info structure. This allows the guest to place the vcpu_info + * structure in a convenient place, such as in a per-cpu data area. + * The pointer need not be page aligned, but the structure must not + * cross a page boundary. + */ +#define VCPUOP_register_vcpu_info 10 /* arg == struct vcpu_info */ +struct vcpu_register_vcpu_info { + uint32_t mfn; /* mfn of page to place vcpu_info */ + uint32_t offset; /* offset within page */ +}; + +#endif /* __XEN_PUBLIC_VCPU_H__ */ diff --git a/include/xen/interface/version.h b/include/xen/interface/version.h new file mode 100644 index 00000000000..453235e923f --- /dev/null +++ b/include/xen/interface/version.h @@ -0,0 +1,60 @@ +/****************************************************************************** + * version.h + * + * Xen version, type, and compile information. + * + * Copyright (c) 2005, Nguyen Anh Quynh <aquynh@gmail.com> + * Copyright (c) 2005, Keir Fraser <keir@xensource.com> + */ + +#ifndef __XEN_PUBLIC_VERSION_H__ +#define __XEN_PUBLIC_VERSION_H__ + +/* NB. All ops return zero on success, except XENVER_version. */ + +/* arg == NULL; returns major:minor (16:16). */ +#define XENVER_version 0 + +/* arg == xen_extraversion_t. */ +#define XENVER_extraversion 1 +struct xen_extraversion { + char extraversion[16]; +}; +#define XEN_EXTRAVERSION_LEN (sizeof(struct xen_extraversion)) + +/* arg == xen_compile_info_t. */ +#define XENVER_compile_info 2 +struct xen_compile_info { + char compiler[64]; + char compile_by[16]; + char compile_domain[32]; + char compile_date[32]; +}; + +#define XENVER_capabilities 3 +struct xen_capabilities_info { + char info[1024]; +}; +#define XEN_CAPABILITIES_INFO_LEN (sizeof(struct xen_capabilities_info)) + +#define XENVER_changeset 4 +struct xen_changeset_info { + char info[64]; +}; +#define XEN_CHANGESET_INFO_LEN (sizeof(struct xen_changeset_info)) + +#define XENVER_platform_parameters 5 +struct xen_platform_parameters { + unsigned long virt_start; +}; + +#define XENVER_get_features 6 +struct xen_feature_info { + unsigned int submap_idx; /* IN: which 32-bit submap to return */ + uint32_t submap; /* OUT: 32-bit submap */ +}; + +/* Declares the features reported by XENVER_get_features. */ +#include "features.h" + +#endif /* __XEN_PUBLIC_VERSION_H__ */ diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h new file mode 100644 index 00000000000..518a5bf79ed --- /dev/null +++ b/include/xen/interface/xen.h @@ -0,0 +1,447 @@ +/****************************************************************************** + * xen.h + * + * Guest OS interface to Xen. + * + * Copyright (c) 2004, K A Fraser + */ + +#ifndef __XEN_PUBLIC_XEN_H__ +#define __XEN_PUBLIC_XEN_H__ + +#include <asm/xen/interface.h> + +/* + * XEN "SYSTEM CALLS" (a.k.a. HYPERCALLS). + */ + +/* + * x86_32: EAX = vector; EBX, ECX, EDX, ESI, EDI = args 1, 2, 3, 4, 5. + * EAX = return value + * (argument registers may be clobbered on return) + * x86_64: RAX = vector; RDI, RSI, RDX, R10, R8, R9 = args 1, 2, 3, 4, 5, 6. + * RAX = return value + * (argument registers not clobbered on return; RCX, R11 are) + */ +#define __HYPERVISOR_set_trap_table 0 +#define __HYPERVISOR_mmu_update 1 +#define __HYPERVISOR_set_gdt 2 +#define __HYPERVISOR_stack_switch 3 +#define __HYPERVISOR_set_callbacks 4 +#define __HYPERVISOR_fpu_taskswitch 5 +#define __HYPERVISOR_sched_op 6 +#define __HYPERVISOR_dom0_op 7 +#define __HYPERVISOR_set_debugreg 8 +#define __HYPERVISOR_get_debugreg 9 +#define __HYPERVISOR_update_descriptor 10 +#define __HYPERVISOR_memory_op 12 +#define __HYPERVISOR_multicall 13 +#define __HYPERVISOR_update_va_mapping 14 +#define __HYPERVISOR_set_timer_op 15 +#define __HYPERVISOR_event_channel_op_compat 16 +#define __HYPERVISOR_xen_version 17 +#define __HYPERVISOR_console_io 18 +#define __HYPERVISOR_physdev_op_compat 19 +#define __HYPERVISOR_grant_table_op 20 +#define __HYPERVISOR_vm_assist 21 +#define __HYPERVISOR_update_va_mapping_otherdomain 22 +#define __HYPERVISOR_iret 23 /* x86 only */ +#define __HYPERVISOR_vcpu_op 24 +#define __HYPERVISOR_set_segment_base 25 /* x86/64 only */ +#define __HYPERVISOR_mmuext_op 26 +#define __HYPERVISOR_acm_op 27 +#define __HYPERVISOR_nmi_op 28 +#define __HYPERVISOR_sched_op_new 29 +#define __HYPERVISOR_callback_op 30 +#define __HYPERVISOR_xenoprof_op 31 +#define __HYPERVISOR_event_channel_op 32 +#define __HYPERVISOR_physdev_op 33 +#define __HYPERVISOR_hvm_op 34 + +/* + * VIRTUAL INTERRUPTS + * + * Virtual interrupts that a guest OS may receive from Xen. + */ +#define VIRQ_TIMER 0 /* Timebase update, and/or requested timeout. */ +#define VIRQ_DEBUG 1 /* Request guest to dump debug info. */ +#define VIRQ_CONSOLE 2 /* (DOM0) Bytes received on emergency console. */ +#define VIRQ_DOM_EXC 3 /* (DOM0) Exceptional event for some domain. */ +#define VIRQ_DEBUGGER 6 /* (DOM0) A domain has paused for debugging. */ +#define NR_VIRQS 8 + +/* + * MMU-UPDATE REQUESTS + * + * HYPERVISOR_mmu_update() accepts a list of (ptr, val) pairs. + * A foreigndom (FD) can be specified (or DOMID_SELF for none). + * Where the FD has some effect, it is described below. + * ptr[1:0] specifies the appropriate MMU_* command. + * + * ptr[1:0] == MMU_NORMAL_PT_UPDATE: + * Updates an entry in a page table. If updating an L1 table, and the new + * table entry is valid/present, the mapped frame must belong to the FD, if + * an FD has been specified. If attempting to map an I/O page then the + * caller assumes the privilege of the FD. + * FD == DOMID_IO: Permit /only/ I/O mappings, at the priv level of the caller. + * FD == DOMID_XEN: Map restricted areas of Xen's heap space. + * ptr[:2] -- Machine address of the page-table entry to modify. + * val -- Value to write. + * + * ptr[1:0] == MMU_MACHPHYS_UPDATE: + * Updates an entry in the machine->pseudo-physical mapping table. + * ptr[:2] -- Machine address within the frame whose mapping to modify. + * The frame must belong to the FD, if one is specified. + * val -- Value to write into the mapping entry. + */ +#define MMU_NORMAL_PT_UPDATE 0 /* checked '*ptr = val'. ptr is MA. */ +#define MMU_MACHPHYS_UPDATE 1 /* ptr = MA of frame to modify entry for */ + +/* + * MMU EXTENDED OPERATIONS + * + * HYPERVISOR_mmuext_op() accepts a list of mmuext_op structures. + * A foreigndom (FD) can be specified (or DOMID_SELF for none). + * Where the FD has some effect, it is described below. + * + * cmd: MMUEXT_(UN)PIN_*_TABLE + * mfn: Machine frame number to be (un)pinned as a p.t. page. + * The frame must belong to the FD, if one is specified. + * + * cmd: MMUEXT_NEW_BASEPTR + * mfn: Machine frame number of new page-table base to install in MMU. + * + * cmd: MMUEXT_NEW_USER_BASEPTR [x86/64 only] + * mfn: Machine frame number of new page-table base to install in MMU + * when in user space. + * + * cmd: MMUEXT_TLB_FLUSH_LOCAL + * No additional arguments. Flushes local TLB. + * + * cmd: MMUEXT_INVLPG_LOCAL + * linear_addr: Linear address to be flushed from the local TLB. + * + * cmd: MMUEXT_TLB_FLUSH_MULTI + * vcpumask: Pointer to bitmap of VCPUs to be flushed. + * + * cmd: MMUEXT_INVLPG_MULTI + * linear_addr: Linear address to be flushed. + * vcpumask: Pointer to bitmap of VCPUs to be flushed. + * + * cmd: MMUEXT_TLB_FLUSH_ALL + * No additional arguments. Flushes all VCPUs' TLBs. + * + * cmd: MMUEXT_INVLPG_ALL + * linear_addr: Linear address to be flushed from all VCPUs' TLBs. + * + * cmd: MMUEXT_FLUSH_CACHE + * No additional arguments. Writes back and flushes cache contents. + * + * cmd: MMUEXT_SET_LDT + * linear_addr: Linear address of LDT base (NB. must be page-aligned). + * nr_ents: Number of entries in LDT. + */ +#define MMUEXT_PIN_L1_TABLE 0 +#define MMUEXT_PIN_L2_TABLE 1 +#define MMUEXT_PIN_L3_TABLE 2 +#define MMUEXT_PIN_L4_TABLE 3 +#define MMUEXT_UNPIN_TABLE 4 +#define MMUEXT_NEW_BASEPTR 5 +#define MMUEXT_TLB_FLUSH_LOCAL 6 +#define MMUEXT_INVLPG_LOCAL 7 +#define MMUEXT_TLB_FLUSH_MULTI 8 +#define MMUEXT_INVLPG_MULTI 9 +#define MMUEXT_TLB_FLUSH_ALL 10 +#define MMUEXT_INVLPG_ALL 11 +#define MMUEXT_FLUSH_CACHE 12 +#define MMUEXT_SET_LDT 13 +#define MMUEXT_NEW_USER_BASEPTR 15 + +#ifndef __ASSEMBLY__ +struct mmuext_op { + unsigned int cmd; + union { + /* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR */ + unsigned long mfn; + /* INVLPG_LOCAL, INVLPG_ALL, SET_LDT */ + unsigned long linear_addr; + } arg1; + union { + /* SET_LDT */ + unsigned int nr_ents; + /* TLB_FLUSH_MULTI, INVLPG_MULTI */ + void *vcpumask; + } arg2; +}; +DEFINE_GUEST_HANDLE_STRUCT(mmuext_op); +#endif + +/* These are passed as 'flags' to update_va_mapping. They can be ORed. */ +/* When specifying UVMF_MULTI, also OR in a pointer to a CPU bitmap. */ +/* UVMF_LOCAL is merely UVMF_MULTI with a NULL bitmap pointer. */ +#define UVMF_NONE (0UL<<0) /* No flushing at all. */ +#define UVMF_TLB_FLUSH (1UL<<0) /* Flush entire TLB(s). */ +#define UVMF_INVLPG (2UL<<0) /* Flush only one entry. */ +#define UVMF_FLUSHTYPE_MASK (3UL<<0) +#define UVMF_MULTI (0UL<<2) /* Flush subset of TLBs. */ +#define UVMF_LOCAL (0UL<<2) /* Flush local TLB. */ +#define UVMF_ALL (1UL<<2) /* Flush all TLBs. */ + +/* + * Commands to HYPERVISOR_console_io(). + */ +#define CONSOLEIO_write 0 +#define CONSOLEIO_read 1 + +/* + * Commands to HYPERVISOR_vm_assist(). + */ +#define VMASST_CMD_enable 0 +#define VMASST_CMD_disable 1 +#define VMASST_TYPE_4gb_segments 0 +#define VMASST_TYPE_4gb_segments_notify 1 +#define VMASST_TYPE_writable_pagetables 2 +#define VMASST_TYPE_pae_extended_cr3 3 +#define MAX_VMASST_TYPE 3 + +#ifndef __ASSEMBLY__ + +typedef uint16_t domid_t; + +/* Domain ids >= DOMID_FIRST_RESERVED cannot be used for ordinary domains. */ +#define DOMID_FIRST_RESERVED (0x7FF0U) + +/* DOMID_SELF is used in certain contexts to refer to oneself. */ +#define DOMID_SELF (0x7FF0U) + +/* + * DOMID_IO is used to restrict page-table updates to mapping I/O memory. + * Although no Foreign Domain need be specified to map I/O pages, DOMID_IO + * is useful to ensure that no mappings to the OS's own heap are accidentally + * installed. (e.g., in Linux this could cause havoc as reference counts + * aren't adjusted on the I/O-mapping code path). + * This only makes sense in MMUEXT_SET_FOREIGNDOM, but in that context can + * be specified by any calling domain. + */ +#define DOMID_IO (0x7FF1U) + +/* + * DOMID_XEN is used to allow privileged domains to map restricted parts of + * Xen's heap space (e.g., the machine_to_phys table). + * This only makes sense in MMUEXT_SET_FOREIGNDOM, and is only permitted if + * the caller is privileged. + */ +#define DOMID_XEN (0x7FF2U) + +/* + * Send an array of these to HYPERVISOR_mmu_update(). + * NB. The fields are natural pointer/address size for this architecture. + */ +struct mmu_update { + uint64_t ptr; /* Machine address of PTE. */ + uint64_t val; /* New contents of PTE. */ +}; +DEFINE_GUEST_HANDLE_STRUCT(mmu_update); + +/* + * Send an array of these to HYPERVISOR_multicall(). + * NB. The fields are natural register size for this architecture. + */ +struct multicall_entry { + unsigned long op; + long result; + unsigned long args[6]; +}; +DEFINE_GUEST_HANDLE_STRUCT(multicall_entry); + +/* + * Event channel endpoints per domain: + * 1024 if a long is 32 bits; 4096 if a long is 64 bits. + */ +#define NR_EVENT_CHANNELS (sizeof(unsigned long) * sizeof(unsigned long) * 64) + +struct vcpu_time_info { + /* + * Updates to the following values are preceded and followed + * by an increment of 'version'. The guest can therefore + * detect updates by looking for changes to 'version'. If the + * least-significant bit of the version number is set then an + * update is in progress and the guest must wait to read a + * consistent set of values. The correct way to interact with + * the version number is similar to Linux's seqlock: see the + * implementations of read_seqbegin/read_seqretry. + */ + uint32_t version; + uint32_t pad0; + uint64_t tsc_timestamp; /* TSC at last update of time vals. */ + uint64_t system_time; /* Time, in nanosecs, since boot. */ + /* + * Current system time: + * system_time + ((tsc - tsc_timestamp) << tsc_shift) * tsc_to_system_mul + * CPU frequency (Hz): + * ((10^9 << 32) / tsc_to_system_mul) >> tsc_shift + */ + uint32_t tsc_to_system_mul; + int8_t tsc_shift; + int8_t pad1[3]; +}; /* 32 bytes */ + +struct vcpu_info { + /* + * 'evtchn_upcall_pending' is written non-zero by Xen to indicate + * a pending notification for a particular VCPU. It is then cleared + * by the guest OS /before/ checking for pending work, thus avoiding + * a set-and-check race. Note that the mask is only accessed by Xen + * on the CPU that is currently hosting the VCPU. This means that the + * pending and mask flags can be updated by the guest without special + * synchronisation (i.e., no need for the x86 LOCK prefix). + * This may seem suboptimal because if the pending flag is set by + * a different CPU then an IPI may be scheduled even when the mask + * is set. However, note: + * 1. The task of 'interrupt holdoff' is covered by the per-event- + * channel mask bits. A 'noisy' event that is continually being + * triggered can be masked at source at this very precise + * granularity. + * 2. The main purpose of the per-VCPU mask is therefore to restrict + * reentrant execution: whether for concurrency control, or to + * prevent unbounded stack usage. Whatever the purpose, we expect + * that the mask will be asserted only for short periods at a time, + * and so the likelihood of a 'spurious' IPI is suitably small. + * The mask is read before making an event upcall to the guest: a + * non-zero mask therefore guarantees that the VCPU will not receive + * an upcall activation. The mask is cleared when the VCPU requests + * to block: this avoids wakeup-waiting races. + */ + uint8_t evtchn_upcall_pending; + uint8_t evtchn_upcall_mask; + unsigned long evtchn_pending_sel; + struct arch_vcpu_info arch; + struct vcpu_time_info time; +}; /* 64 bytes (x86) */ + +/* + * Xen/kernel shared data -- pointer provided in start_info. + * NB. We expect that this struct is smaller than a page. + */ +struct shared_info { + struct vcpu_info vcpu_info[MAX_VIRT_CPUS]; + + /* + * A domain can create "event channels" on which it can send and receive + * asynchronous event notifications. There are three classes of event that + * are delivered by this mechanism: + * 1. Bi-directional inter- and intra-domain connections. Domains must + * arrange out-of-band to set up a connection (usually by allocating + * an unbound 'listener' port and avertising that via a storage service + * such as xenstore). + * 2. Physical interrupts. A domain with suitable hardware-access + * privileges can bind an event-channel port to a physical interrupt + * source. + * 3. Virtual interrupts ('events'). A domain can bind an event-channel + * port to a virtual interrupt source, such as the virtual-timer + * device or the emergency console. + * + * Event channels are addressed by a "port index". Each channel is + * associated with two bits of information: + * 1. PENDING -- notifies the domain that there is a pending notification + * to be processed. This bit is cleared by the guest. + * 2. MASK -- if this bit is clear then a 0->1 transition of PENDING + * will cause an asynchronous upcall to be scheduled. This bit is only + * updated by the guest. It is read-only within Xen. If a channel + * becomes pending while the channel is masked then the 'edge' is lost + * (i.e., when the channel is unmasked, the guest must manually handle + * pending notifications as no upcall will be scheduled by Xen). + * + * To expedite scanning of pending notifications, any 0->1 pending + * transition on an unmasked channel causes a corresponding bit in a + * per-vcpu selector word to be set. Each bit in the selector covers a + * 'C long' in the PENDING bitfield array. + */ + unsigned long evtchn_pending[sizeof(unsigned long) * 8]; + unsigned long evtchn_mask[sizeof(unsigned long) * 8]; + + /* + * Wallclock time: updated only by control software. Guests should base + * their gettimeofday() syscall on this wallclock-base value. + */ + uint32_t wc_version; /* Version counter: see vcpu_time_info_t. */ + uint32_t wc_sec; /* Secs 00:00:00 UTC, Jan 1, 1970. */ + uint32_t wc_nsec; /* Nsecs 00:00:00 UTC, Jan 1, 1970. */ + + struct arch_shared_info arch; + +}; + +/* + * Start-of-day memory layout for the initial domain (DOM0): + * 1. The domain is started within contiguous virtual-memory region. + * 2. The contiguous region begins and ends on an aligned 4MB boundary. + * 3. The region start corresponds to the load address of the OS image. + * If the load address is not 4MB aligned then the address is rounded down. + * 4. This the order of bootstrap elements in the initial virtual region: + * a. relocated kernel image + * b. initial ram disk [mod_start, mod_len] + * c. list of allocated page frames [mfn_list, nr_pages] + * d. start_info_t structure [register ESI (x86)] + * e. bootstrap page tables [pt_base, CR3 (x86)] + * f. bootstrap stack [register ESP (x86)] + * 5. Bootstrap elements are packed together, but each is 4kB-aligned. + * 6. The initial ram disk may be omitted. + * 7. The list of page frames forms a contiguous 'pseudo-physical' memory + * layout for the domain. In particular, the bootstrap virtual-memory + * region is a 1:1 mapping to the first section of the pseudo-physical map. + * 8. All bootstrap elements are mapped read-writable for the guest OS. The + * only exception is the bootstrap page table, which is mapped read-only. + * 9. There is guaranteed to be at least 512kB padding after the final + * bootstrap element. If necessary, the bootstrap virtual region is + * extended by an extra 4MB to ensure this. + */ + +#define MAX_GUEST_CMDLINE 1024 +struct start_info { + /* THE FOLLOWING ARE FILLED IN BOTH ON INITIAL BOOT AND ON RESUME. */ + char magic[32]; /* "xen-<version>-<platform>". */ + unsigned long nr_pages; /* Total pages allocated to this domain. */ + unsigned long shared_info; /* MACHINE address of shared info struct. */ + uint32_t flags; /* SIF_xxx flags. */ + unsigned long store_mfn; /* MACHINE page number of shared page. */ + uint32_t store_evtchn; /* Event channel for store communication. */ + union { + struct { + unsigned long mfn; /* MACHINE page number of console page. */ + uint32_t evtchn; /* Event channel for console page. */ + } domU; + struct { + uint32_t info_off; /* Offset of console_info struct. */ + uint32_t info_size; /* Size of console_info struct from start.*/ + } dom0; + } console; + /* THE FOLLOWING ARE ONLY FILLED IN ON INITIAL BOOT (NOT RESUME). */ + unsigned long pt_base; /* VIRTUAL address of page directory. */ + unsigned long nr_pt_frames; /* Number of bootstrap p.t. frames. */ + unsigned long mfn_list; /* VIRTUAL address of page-frame list. */ + unsigned long mod_start; /* VIRTUAL address of pre-loaded module. */ + unsigned long mod_len; /* Size (bytes) of pre-loaded module. */ + int8_t cmd_line[MAX_GUEST_CMDLINE]; +}; + +/* These flags are passed in the 'flags' field of start_info_t. */ +#define SIF_PRIVILEGED (1<<0) /* Is the domain privileged? */ +#define SIF_INITDOMAIN (1<<1) /* Is this the initial control domain? */ + +typedef uint64_t cpumap_t; + +typedef uint8_t xen_domain_handle_t[16]; + +/* Turn a plain number into a C unsigned long constant. */ +#define __mk_unsigned_long(x) x ## UL +#define mk_unsigned_long(x) __mk_unsigned_long(x) + +#else /* __ASSEMBLY__ */ + +/* In assembly code we cannot use C numeric constant suffixes. */ +#define mk_unsigned_long(x) x + +#endif /* !__ASSEMBLY__ */ + +#endif /* __XEN_PUBLIC_XEN_H__ */ diff --git a/include/xen/page.h b/include/xen/page.h new file mode 100644 index 00000000000..1df6c193057 --- /dev/null +++ b/include/xen/page.h @@ -0,0 +1,179 @@ +#ifndef __XEN_PAGE_H +#define __XEN_PAGE_H + +#include <linux/pfn.h> + +#include <asm/uaccess.h> + +#include <xen/features.h> + +#ifdef CONFIG_X86_PAE +/* Xen machine address */ +typedef struct xmaddr { + unsigned long long maddr; +} xmaddr_t; + +/* Xen pseudo-physical address */ +typedef struct xpaddr { + unsigned long long paddr; +} xpaddr_t; +#else +/* Xen machine address */ +typedef struct xmaddr { + unsigned long maddr; +} xmaddr_t; + +/* Xen pseudo-physical address */ +typedef struct xpaddr { + unsigned long paddr; +} xpaddr_t; +#endif + +#define XMADDR(x) ((xmaddr_t) { .maddr = (x) }) +#define XPADDR(x) ((xpaddr_t) { .paddr = (x) }) + +/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/ +#define INVALID_P2M_ENTRY (~0UL) +#define FOREIGN_FRAME_BIT (1UL<<31) +#define FOREIGN_FRAME(m) ((m) | FOREIGN_FRAME_BIT) + +extern unsigned long *phys_to_machine_mapping; + +static inline unsigned long pfn_to_mfn(unsigned long pfn) +{ + if (xen_feature(XENFEAT_auto_translated_physmap)) + return pfn; + + return phys_to_machine_mapping[(unsigned int)(pfn)] & + ~FOREIGN_FRAME_BIT; +} + +static inline int phys_to_machine_mapping_valid(unsigned long pfn) +{ + if (xen_feature(XENFEAT_auto_translated_physmap)) + return 1; + + return (phys_to_machine_mapping[pfn] != INVALID_P2M_ENTRY); +} + +static inline unsigned long mfn_to_pfn(unsigned long mfn) +{ + unsigned long pfn; + + if (xen_feature(XENFEAT_auto_translated_physmap)) + return mfn; + +#if 0 + if (unlikely((mfn >> machine_to_phys_order) != 0)) + return max_mapnr; +#endif + + pfn = 0; + /* + * The array access can fail (e.g., device space beyond end of RAM). + * In such cases it doesn't matter what we return (we return garbage), + * but we must handle the fault without crashing! + */ + __get_user(pfn, &machine_to_phys_mapping[mfn]); + + return pfn; +} + +static inline xmaddr_t phys_to_machine(xpaddr_t phys) +{ + unsigned offset = phys.paddr & ~PAGE_MASK; + return XMADDR(PFN_PHYS((u64)pfn_to_mfn(PFN_DOWN(phys.paddr))) | offset); +} + +static inline xpaddr_t machine_to_phys(xmaddr_t machine) +{ + unsigned offset = machine.maddr & ~PAGE_MASK; + return XPADDR(PFN_PHYS((u64)mfn_to_pfn(PFN_DOWN(machine.maddr))) | offset); +} + +/* + * We detect special mappings in one of two ways: + * 1. If the MFN is an I/O page then Xen will set the m2p entry + * to be outside our maximum possible pseudophys range. + * 2. If the MFN belongs to a different domain then we will certainly + * not have MFN in our p2m table. Conversely, if the page is ours, + * then we'll have p2m(m2p(MFN))==MFN. + * If we detect a special mapping then it doesn't have a 'struct page'. + * We force !pfn_valid() by returning an out-of-range pointer. + * + * NB. These checks require that, for any MFN that is not in our reservation, + * there is no PFN such that p2m(PFN) == MFN. Otherwise we can get confused if + * we are foreign-mapping the MFN, and the other domain as m2p(MFN) == PFN. + * Yikes! Various places must poke in INVALID_P2M_ENTRY for safety. + * + * NB2. When deliberately mapping foreign pages into the p2m table, you *must* + * use FOREIGN_FRAME(). This will cause pte_pfn() to choke on it, as we + * require. In all the cases we care about, the FOREIGN_FRAME bit is + * masked (e.g., pfn_to_mfn()) so behaviour there is correct. + */ +static inline unsigned long mfn_to_local_pfn(unsigned long mfn) +{ + extern unsigned long max_mapnr; + unsigned long pfn = mfn_to_pfn(mfn); + if ((pfn < max_mapnr) + && !xen_feature(XENFEAT_auto_translated_physmap) + && (phys_to_machine_mapping[pfn] != mfn)) + return max_mapnr; /* force !pfn_valid() */ + return pfn; +} + +static inline void set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + if (xen_feature(XENFEAT_auto_translated_physmap)) { + BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); + return; + } + phys_to_machine_mapping[pfn] = mfn; +} + +/* VIRT <-> MACHINE conversion */ +#define virt_to_machine(v) (phys_to_machine(XPADDR(__pa(v)))) +#define virt_to_mfn(v) (pfn_to_mfn(PFN_DOWN(__pa(v)))) +#define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) + +#ifdef CONFIG_X86_PAE +#define pte_mfn(_pte) (((_pte).pte_low >> PAGE_SHIFT) | \ + (((_pte).pte_high & 0xfff) << (32-PAGE_SHIFT))) + +static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot) +{ + pte_t pte; + + pte.pte_high = (page_nr >> (32 - PAGE_SHIFT)) | + (pgprot_val(pgprot) >> 32); + pte.pte_high &= (__supported_pte_mask >> 32); + pte.pte_low = ((page_nr << PAGE_SHIFT) | pgprot_val(pgprot)); + pte.pte_low &= __supported_pte_mask; + + return pte; +} + +static inline unsigned long long pte_val_ma(pte_t x) +{ + return ((unsigned long long)x.pte_high << 32) | x.pte_low; +} +#define pmd_val_ma(v) ((v).pmd) +#define pud_val_ma(v) ((v).pgd.pgd) +#define __pte_ma(x) ((pte_t) { .pte_low = (x), .pte_high = (x)>>32 } ) +#define __pmd_ma(x) ((pmd_t) { (x) } ) +#else /* !X86_PAE */ +#define pte_mfn(_pte) ((_pte).pte_low >> PAGE_SHIFT) +#define mfn_pte(pfn, prot) __pte_ma(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) +#define pte_val_ma(x) ((x).pte_low) +#define pmd_val_ma(v) ((v).pud.pgd.pgd) +#define __pte_ma(x) ((pte_t) { (x) } ) +#endif /* CONFIG_X86_PAE */ + +#define pgd_val_ma(x) ((x).pgd) + + +xmaddr_t arbitrary_virt_to_machine(unsigned long address); +void make_lowmem_page_readonly(void *vaddr); +void make_lowmem_page_readwrite(void *vaddr); + +#endif /* __XEN_PAGE_H */ diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h new file mode 100644 index 00000000000..6f7c290651a --- /dev/null +++ b/include/xen/xenbus.h @@ -0,0 +1,234 @@ +/****************************************************************************** + * xenbus.h + * + * Talks to Xen Store to figure out what devices we have. + * + * Copyright (C) 2005 Rusty Russell, IBM Corporation + * Copyright (C) 2005 XenSource Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef _XEN_XENBUS_H +#define _XEN_XENBUS_H + +#include <linux/device.h> +#include <linux/notifier.h> +#include <linux/mutex.h> +#include <linux/completion.h> +#include <linux/init.h> +#include <xen/interface/xen.h> +#include <xen/interface/grant_table.h> +#include <xen/interface/io/xenbus.h> +#include <xen/interface/io/xs_wire.h> + +/* Register callback to watch this node. */ +struct xenbus_watch +{ + struct list_head list; + + /* Path being watched. */ + const char *node; + + /* Callback (executed in a process context with no locks held). */ + void (*callback)(struct xenbus_watch *, + const char **vec, unsigned int len); +}; + + +/* A xenbus device. */ +struct xenbus_device { + const char *devicetype; + const char *nodename; + const char *otherend; + int otherend_id; + struct xenbus_watch otherend_watch; + struct device dev; + enum xenbus_state state; + struct completion down; +}; + +static inline struct xenbus_device *to_xenbus_device(struct device *dev) +{ + return container_of(dev, struct xenbus_device, dev); +} + +struct xenbus_device_id +{ + /* .../device/<device_type>/<identifier> */ + char devicetype[32]; /* General class of device. */ +}; + +/* A xenbus driver. */ +struct xenbus_driver { + char *name; + struct module *owner; + const struct xenbus_device_id *ids; + int (*probe)(struct xenbus_device *dev, + const struct xenbus_device_id *id); + void (*otherend_changed)(struct xenbus_device *dev, + enum xenbus_state backend_state); + int (*remove)(struct xenbus_device *dev); + int (*suspend)(struct xenbus_device *dev); + int (*suspend_cancel)(struct xenbus_device *dev); + int (*resume)(struct xenbus_device *dev); + int (*uevent)(struct xenbus_device *, char **, int, char *, int); + struct device_driver driver; + int (*read_otherend_details)(struct xenbus_device *dev); +}; + +static inline struct xenbus_driver *to_xenbus_driver(struct device_driver *drv) +{ + return container_of(drv, struct xenbus_driver, driver); +} + +int __must_check __xenbus_register_frontend(struct xenbus_driver *drv, + struct module *owner, + const char *mod_name); + +static inline int __must_check +xenbus_register_frontend(struct xenbus_driver *drv) +{ + WARN_ON(drv->owner != THIS_MODULE); + return __xenbus_register_frontend(drv, THIS_MODULE, KBUILD_MODNAME); +} + +int __must_check __xenbus_register_backend(struct xenbus_driver *drv, + struct module *owner, + const char *mod_name); +static inline int __must_check +xenbus_register_backend(struct xenbus_driver *drv) +{ + WARN_ON(drv->owner != THIS_MODULE); + return __xenbus_register_backend(drv, THIS_MODULE, KBUILD_MODNAME); +} + +void xenbus_unregister_driver(struct xenbus_driver *drv); + +struct xenbus_transaction +{ + u32 id; +}; + +/* Nil transaction ID. */ +#define XBT_NIL ((struct xenbus_transaction) { 0 }) + +int __init xenbus_dev_init(void); + +char **xenbus_directory(struct xenbus_transaction t, + const char *dir, const char *node, unsigned int *num); +void *xenbus_read(struct xenbus_transaction t, + const char *dir, const char *node, unsigned int *len); +int xenbus_write(struct xenbus_transaction t, + const char *dir, const char *node, const char *string); +int xenbus_mkdir(struct xenbus_transaction t, + const char *dir, const char *node); +int xenbus_exists(struct xenbus_transaction t, + const char *dir, const char *node); +int xenbus_rm(struct xenbus_transaction t, const char *dir, const char *node); +int xenbus_transaction_start(struct xenbus_transaction *t); +int xenbus_transaction_end(struct xenbus_transaction t, int abort); + +/* Single read and scanf: returns -errno or num scanned if > 0. */ +int xenbus_scanf(struct xenbus_transaction t, + const char *dir, const char *node, const char *fmt, ...) + __attribute__((format(scanf, 4, 5))); + +/* Single printf and write: returns -errno or 0. */ +int xenbus_printf(struct xenbus_transaction t, + const char *dir, const char *node, const char *fmt, ...) + __attribute__((format(printf, 4, 5))); + +/* Generic read function: NULL-terminated triples of name, + * sprintf-style type string, and pointer. Returns 0 or errno.*/ +int xenbus_gather(struct xenbus_transaction t, const char *dir, ...); + +/* notifer routines for when the xenstore comes up */ +extern int xenstored_ready; +int register_xenstore_notifier(struct notifier_block *nb); +void unregister_xenstore_notifier(struct notifier_block *nb); + +int register_xenbus_watch(struct xenbus_watch *watch); +void unregister_xenbus_watch(struct xenbus_watch *watch); +void xs_suspend(void); +void xs_resume(void); +void xs_suspend_cancel(void); + +/* Used by xenbus_dev to borrow kernel's store connection. */ +void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg); + +struct work_struct; + +/* Prepare for domain suspend: then resume or cancel the suspend. */ +void xenbus_suspend(void); +void xenbus_resume(void); +void xenbus_probe(struct work_struct *); +void xenbus_suspend_cancel(void); + +#define XENBUS_IS_ERR_READ(str) ({ \ + if (!IS_ERR(str) && strlen(str) == 0) { \ + kfree(str); \ + str = ERR_PTR(-ERANGE); \ + } \ + IS_ERR(str); \ +}) + +#define XENBUS_EXIST_ERR(err) ((err) == -ENOENT || (err) == -ERANGE) + +int xenbus_watch_path(struct xenbus_device *dev, const char *path, + struct xenbus_watch *watch, + void (*callback)(struct xenbus_watch *, + const char **, unsigned int)); +int xenbus_watch_pathfmt(struct xenbus_device *dev, struct xenbus_watch *watch, + void (*callback)(struct xenbus_watch *, + const char **, unsigned int), + const char *pathfmt, ...) + __attribute__ ((format (printf, 4, 5))); + +int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state new_state); +int xenbus_grant_ring(struct xenbus_device *dev, unsigned long ring_mfn); +int xenbus_map_ring_valloc(struct xenbus_device *dev, + int gnt_ref, void **vaddr); +int xenbus_map_ring(struct xenbus_device *dev, int gnt_ref, + grant_handle_t *handle, void *vaddr); + +int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr); +int xenbus_unmap_ring(struct xenbus_device *dev, + grant_handle_t handle, void *vaddr); + +int xenbus_alloc_evtchn(struct xenbus_device *dev, int *port); +int xenbus_bind_evtchn(struct xenbus_device *dev, int remote_port, int *port); +int xenbus_free_evtchn(struct xenbus_device *dev, int port); + +enum xenbus_state xenbus_read_driver_state(const char *path); + +void xenbus_dev_error(struct xenbus_device *dev, int err, const char *fmt, ...); +void xenbus_dev_fatal(struct xenbus_device *dev, int err, const char *fmt, ...); + +const char *xenbus_strstate(enum xenbus_state state); +int xenbus_dev_is_online(struct xenbus_device *dev); +int xenbus_frontend_closed(struct xenbus_device *dev); + +#endif /* _XEN_XENBUS_H */ |