Sign Up
Log In
Log In
or
Sign Up
Places
All Projects
Status Monitor
Collapse sidebar
SUSE:SLE-12-SP5:GA
grub2.14589
0001-Import-xen-headers-directly-into-GRUB.patch
Overview
Repositories
Revisions
Requests
Users
Attributes
Meta
File 0001-Import-xen-headers-directly-into-GRUB.patch of Package grub2.14589
From e07badcc31babb24ace4f96444bc484502427d3a Mon Sep 17 00:00:00 2001 From: Vladimir Serbinenko <phcoder@gmail.com> Date: Sun, 8 Nov 2015 21:23:52 +0100 Subject: [PATCH] Import xen headers directly into GRUB --- include/xen/arch-x86/xen-x86_32.h | 171 ++++++++ include/xen/arch-x86/xen-x86_64.h | 202 +++++++++ include/xen/arch-x86/xen.h | 273 ++++++++++++ include/xen/event_channel.h | 381 ++++++++++++++++ include/xen/grant_table.h | 662 ++++++++++++++++++++++++++++ include/xen/io/blkif.h | 608 ++++++++++++++++++++++++++ include/xen/io/console.h | 51 +++ include/xen/io/protocols.h | 40 ++ include/xen/io/ring.h | 312 +++++++++++++ include/xen/io/xenbus.h | 80 ++++ include/xen/io/xs_wire.h | 138 ++++++ include/xen/sched.h | 174 ++++++++ include/xen/xen-compat.h | 44 ++ include/xen/xen.h | 899 ++++++++++++++++++++++++++++++++++++++ 14 files changed, 4035 insertions(+) create mode 100644 include/xen/arch-x86/xen-x86_32.h create mode 100644 include/xen/arch-x86/xen-x86_64.h create mode 100644 include/xen/arch-x86/xen.h create mode 100644 include/xen/event_channel.h create mode 100644 include/xen/grant_table.h create mode 100644 include/xen/io/blkif.h create mode 100644 include/xen/io/console.h create mode 100644 include/xen/io/protocols.h create mode 100644 include/xen/io/ring.h create mode 100644 include/xen/io/xenbus.h create mode 100644 include/xen/io/xs_wire.h create mode 100644 include/xen/sched.h create mode 100644 include/xen/xen-compat.h create mode 100644 include/xen/xen.h diff --git a/include/xen/arch-x86/xen-x86_32.h b/include/xen/arch-x86/xen-x86_32.h new file mode 100644 index 0000000..1504191 --- /dev/null +++ b/include/xen/arch-x86/xen-x86_32.h @@ -0,0 +1,171 @@ +/****************************************************************************** + * xen-x86_32.h + * + * Guest OS interface to x86 32-bit Xen. + * + * 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) 2004-2007, K A Fraser + */ + +#ifndef __XEN_PUBLIC_ARCH_X86_XEN_X86_32_H__ +#define __XEN_PUBLIC_ARCH_X86_XEN_X86_32_H__ + +/* + * Hypercall interface: + * Input: %ebx, %ecx, %edx, %esi, %edi, %ebp (arguments 1-6) + * Output: %eax + * Access is via hypercall page (set up by guest loader or via a Xen MSR): + * call hypercall_page + hypercall-number * 32 + * Clobbered: Argument registers (e.g., 2-arg hypercall clobbers %ebx,%ecx) + */ + +/* + * 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 + +#define __HYPERVISOR_VIRT_START_PAE 0xF5800000 +#define __MACH2PHYS_VIRT_START_PAE 0xF5800000 +#define __MACH2PHYS_VIRT_END_PAE 0xF6800000 +#define HYPERVISOR_VIRT_START_PAE \ + mk_unsigned_long(__HYPERVISOR_VIRT_START_PAE) +#define MACH2PHYS_VIRT_START_PAE \ + mk_unsigned_long(__MACH2PHYS_VIRT_START_PAE) +#define MACH2PHYS_VIRT_END_PAE \ + mk_unsigned_long(__MACH2PHYS_VIRT_END_PAE) + +/* Non-PAE bounds are obsolete. */ +#define __HYPERVISOR_VIRT_START_NONPAE 0xFC000000 +#define __MACH2PHYS_VIRT_START_NONPAE 0xFC000000 +#define __MACH2PHYS_VIRT_END_NONPAE 0xFC400000 +#define HYPERVISOR_VIRT_START_NONPAE \ + mk_unsigned_long(__HYPERVISOR_VIRT_START_NONPAE) +#define MACH2PHYS_VIRT_START_NONPAE \ + mk_unsigned_long(__MACH2PHYS_VIRT_START_NONPAE) +#define MACH2PHYS_VIRT_END_NONPAE \ + mk_unsigned_long(__MACH2PHYS_VIRT_END_NONPAE) + +#define __HYPERVISOR_VIRT_START __HYPERVISOR_VIRT_START_PAE +#define __MACH2PHYS_VIRT_START __MACH2PHYS_VIRT_START_PAE +#define __MACH2PHYS_VIRT_END __MACH2PHYS_VIRT_END_PAE + +#ifndef HYPERVISOR_VIRT_START +#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START) +#endif + +#define MACH2PHYS_VIRT_START mk_unsigned_long(__MACH2PHYS_VIRT_START) +#define MACH2PHYS_VIRT_END mk_unsigned_long(__MACH2PHYS_VIRT_END) +#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>2) +#ifndef machine_to_phys_mapping +#define machine_to_phys_mapping ((unsigned long *)MACH2PHYS_VIRT_START) +#endif + +/* 32-/64-bit invariability for control interfaces (domctl/sysctl). */ +#if defined(__XEN__) || defined(__XEN_TOOLS__) +#undef ___DEFINE_XEN_GUEST_HANDLE +#define ___DEFINE_XEN_GUEST_HANDLE(name, type) \ + typedef struct { type *p; } \ + __guest_handle_ ## name; \ + typedef struct { union { type *p; uint64_aligned_t q; }; } \ + __guest_handle_64_ ## name +#undef set_xen_guest_handle_raw +#define set_xen_guest_handle_raw(hnd, val) \ + do { if ( sizeof(hnd) == 8 ) *(uint64_t *)&(hnd) = 0; \ + (hnd).p = val; \ + } while ( 0 ) +#define uint64_aligned_t uint64_t __attribute__((aligned(8))) +#define __XEN_GUEST_HANDLE_64(name) __guest_handle_64_ ## name +#define XEN_GUEST_HANDLE_64(name) __XEN_GUEST_HANDLE_64(name) +#endif + +#ifndef __ASSEMBLY__ + +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; +}; +typedef struct cpu_user_regs cpu_user_regs_t; +DEFINE_XEN_GUEST_HANDLE(cpu_user_regs_t); + +/* + * Page-directory addresses above 4GB do not fit into architectural %cr3. + * When accessing %cr3, or equivalent field in vcpu_guest_context, guests + * must use the following accessor macros to pack/unpack valid MFNs. + */ +#define xen_pfn_to_cr3(pfn) (((unsigned)(pfn) << 12) | ((unsigned)(pfn) >> 20)) +#define xen_cr3_to_pfn(cr3) (((unsigned)(cr3) >> 12) | ((unsigned)(cr3) << 20)) + +struct arch_vcpu_info { + unsigned long cr2; + unsigned long pad[5]; /* sizeof(vcpu_info_t) == 64 */ +}; +typedef struct arch_vcpu_info arch_vcpu_info_t; + +struct xen_callback { + unsigned long cs; + unsigned long eip; +}; +typedef struct xen_callback xen_callback_t; + +#endif /* !__ASSEMBLY__ */ + +#endif /* __XEN_PUBLIC_ARCH_X86_XEN_X86_32_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/arch-x86/xen-x86_64.h b/include/xen/arch-x86/xen-x86_64.h new file mode 100644 index 0000000..1c4e159 --- /dev/null +++ b/include/xen/arch-x86/xen-x86_64.h @@ -0,0 +1,202 @@ +/****************************************************************************** + * xen-x86_64.h + * + * Guest OS interface to x86 64-bit Xen. + * + * 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) 2004-2006, K A Fraser + */ + +#ifndef __XEN_PUBLIC_ARCH_X86_XEN_X86_64_H__ +#define __XEN_PUBLIC_ARCH_X86_XEN_X86_64_H__ + +/* + * Hypercall interface: + * Input: %rdi, %rsi, %rdx, %r10, %r8, %r9 (arguments 1-6) + * Output: %rax + * Access is via hypercall page (set up by guest loader or via a Xen MSR): + * call hypercall_page + hypercall-number * 32 + * Clobbered: argument registers (e.g., 2-arg hypercall clobbers %rdi,%rsi) + */ + +/* + * 64-bit segment selectors + * 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_RING3_CS32 0xe023 /* GDT index 260 */ +#define FLAT_RING3_CS64 0xe033 /* GDT index 261 */ +#define FLAT_RING3_DS32 0xe02b /* GDT index 262 */ +#define FLAT_RING3_DS64 0x0000 /* NULL selector */ +#define FLAT_RING3_SS32 0xe02b /* GDT index 262 */ +#define FLAT_RING3_SS64 0xe02b /* GDT index 262 */ + +#define FLAT_KERNEL_DS64 FLAT_RING3_DS64 +#define FLAT_KERNEL_DS32 FLAT_RING3_DS32 +#define FLAT_KERNEL_DS FLAT_KERNEL_DS64 +#define FLAT_KERNEL_CS64 FLAT_RING3_CS64 +#define FLAT_KERNEL_CS32 FLAT_RING3_CS32 +#define FLAT_KERNEL_CS FLAT_KERNEL_CS64 +#define FLAT_KERNEL_SS64 FLAT_RING3_SS64 +#define FLAT_KERNEL_SS32 FLAT_RING3_SS32 +#define FLAT_KERNEL_SS FLAT_KERNEL_SS64 + +#define FLAT_USER_DS64 FLAT_RING3_DS64 +#define FLAT_USER_DS32 FLAT_RING3_DS32 +#define FLAT_USER_DS FLAT_USER_DS64 +#define FLAT_USER_CS64 FLAT_RING3_CS64 +#define FLAT_USER_CS32 FLAT_RING3_CS32 +#define FLAT_USER_CS FLAT_USER_CS64 +#define FLAT_USER_SS64 FLAT_RING3_SS64 +#define FLAT_USER_SS32 FLAT_RING3_SS32 +#define FLAT_USER_SS FLAT_USER_SS64 + +#define __HYPERVISOR_VIRT_START 0xFFFF800000000000 +#define __HYPERVISOR_VIRT_END 0xFFFF880000000000 +#define __MACH2PHYS_VIRT_START 0xFFFF800000000000 +#define __MACH2PHYS_VIRT_END 0xFFFF804000000000 + +#ifndef HYPERVISOR_VIRT_START +#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START) +#define HYPERVISOR_VIRT_END mk_unsigned_long(__HYPERVISOR_VIRT_END) +#endif + +#define MACH2PHYS_VIRT_START mk_unsigned_long(__MACH2PHYS_VIRT_START) +#define MACH2PHYS_VIRT_END mk_unsigned_long(__MACH2PHYS_VIRT_END) +#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>3) +#ifndef machine_to_phys_mapping +#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START) +#endif + +/* + * int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base) + * @which == SEGBASE_* ; @base == 64-bit base address + * Returns 0 on success. + */ +#define SEGBASE_FS 0 +#define SEGBASE_GS_USER 1 +#define SEGBASE_GS_KERNEL 2 +#define SEGBASE_GS_USER_SEL 3 /* Set user %gs specified in base[15:0] */ + +/* + * int HYPERVISOR_iret(void) + * All arguments are on the kernel stack, in the following format. + * Never returns if successful. Current kernel context is lost. + * The saved CS is mapped as follows: + * RING0 -> RING3 kernel mode. + * RING1 -> RING3 kernel mode. + * RING2 -> RING3 kernel mode. + * RING3 -> RING3 user mode. + * However RING0 indicates that the guest kernel should return to iteself + * directly with + * orb $3,1*8(%rsp) + * iretq + * If flags contains VGCF_in_syscall: + * Restore RAX, RIP, RFLAGS, RSP. + * Discard R11, RCX, CS, SS. + * Otherwise: + * Restore RAX, R11, RCX, CS:RIP, RFLAGS, SS:RSP. + * All other registers are saved on hypercall entry and restored to user. + */ +/* Guest exited in SYSCALL context? Return to guest with SYSRET? */ +#define _VGCF_in_syscall 8 +#define VGCF_in_syscall (1<<_VGCF_in_syscall) +#define VGCF_IN_SYSCALL VGCF_in_syscall + +#ifndef __ASSEMBLY__ + +struct iret_context { + /* Top of stack (%rsp at point of hypercall). */ + uint64_t rax, r11, rcx, flags, rip, cs, rflags, rsp, ss; + /* Bottom of iret stack frame. */ +}; + +#if defined(__GNUC__) && !defined(__STRICT_ANSI__) +/* Anonymous union includes both 32- and 64-bit names (e.g., eax/rax). */ +#define __DECL_REG(name) union { \ + uint64_t r ## name, e ## name; \ + uint32_t _e ## name; \ +} +#else +/* Non-gcc sources must always use the proper 64-bit name (e.g., rax). */ +#define __DECL_REG(name) uint64_t r ## name +#endif + +struct cpu_user_regs { + uint64_t r15; + uint64_t r14; + uint64_t r13; + uint64_t r12; + __DECL_REG(bp); + __DECL_REG(bx); + uint64_t r11; + uint64_t r10; + uint64_t r9; + uint64_t r8; + __DECL_REG(ax); + __DECL_REG(cx); + __DECL_REG(dx); + __DECL_REG(si); + __DECL_REG(di); + uint32_t error_code; /* private */ + uint32_t entry_vector; /* private */ + __DECL_REG(ip); + uint16_t cs, _pad0[1]; + uint8_t saved_upcall_mask; + uint8_t _pad1[3]; + __DECL_REG(flags); /* rflags.IF == !saved_upcall_mask */ + __DECL_REG(sp); + uint16_t ss, _pad2[3]; + uint16_t es, _pad3[3]; + uint16_t ds, _pad4[3]; + uint16_t fs, _pad5[3]; /* Non-zero => takes precedence over fs_base. */ + uint16_t gs, _pad6[3]; /* Non-zero => takes precedence over gs_base_usr. */ +}; +typedef struct cpu_user_regs cpu_user_regs_t; +DEFINE_XEN_GUEST_HANDLE(cpu_user_regs_t); + +#undef __DECL_REG + +#define xen_pfn_to_cr3(pfn) ((unsigned long)(pfn) << 12) +#define xen_cr3_to_pfn(cr3) ((unsigned long)(cr3) >> 12) + +struct arch_vcpu_info { + unsigned long cr2; + unsigned long pad; /* sizeof(vcpu_info_t) == 64 */ +}; +typedef struct arch_vcpu_info arch_vcpu_info_t; + +typedef unsigned long xen_callback_t; + +#endif /* !__ASSEMBLY__ */ + +#endif /* __XEN_PUBLIC_ARCH_X86_XEN_X86_64_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/arch-x86/xen.h b/include/xen/arch-x86/xen.h new file mode 100644 index 0000000..f35804b --- /dev/null +++ b/include/xen/arch-x86/xen.h @@ -0,0 +1,273 @@ +/****************************************************************************** + * arch-x86/xen.h + * + * Guest OS interface to x86 Xen. + * + * 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) 2004-2006, K A Fraser + */ + +#include "../xen.h" + +#ifndef __XEN_PUBLIC_ARCH_X86_XEN_H__ +#define __XEN_PUBLIC_ARCH_X86_XEN_H__ + +/* Structural guest handles introduced in 0x00030201. */ +#if __XEN_INTERFACE_VERSION__ >= 0x00030201 +#define ___DEFINE_XEN_GUEST_HANDLE(name, type) \ + typedef struct { type *p; } __guest_handle_ ## name +#else +#define ___DEFINE_XEN_GUEST_HANDLE(name, type) \ + typedef type * __guest_handle_ ## name +#endif + +/* + * XEN_GUEST_HANDLE represents a guest pointer, when passed as a field + * in a struct in memory. + * XEN_GUEST_HANDLE_PARAM represent a guest pointer, when passed as an + * hypercall argument. + * XEN_GUEST_HANDLE_PARAM and XEN_GUEST_HANDLE are the same on X86 but + * they might not be on other architectures. + */ +#define __DEFINE_XEN_GUEST_HANDLE(name, type) \ + ___DEFINE_XEN_GUEST_HANDLE(name, type); \ + ___DEFINE_XEN_GUEST_HANDLE(const_##name, const type) +#define DEFINE_XEN_GUEST_HANDLE(name) __DEFINE_XEN_GUEST_HANDLE(name, name) +#define __XEN_GUEST_HANDLE(name) __guest_handle_ ## name +#define XEN_GUEST_HANDLE(name) __XEN_GUEST_HANDLE(name) +#define XEN_GUEST_HANDLE_PARAM(name) XEN_GUEST_HANDLE(name) +#define set_xen_guest_handle_raw(hnd, val) do { (hnd).p = val; } while (0) +#ifdef __XEN_TOOLS__ +#define get_xen_guest_handle(val, hnd) do { val = (hnd).p; } while (0) +#endif +#define set_xen_guest_handle(hnd, val) set_xen_guest_handle_raw(hnd, val) + +#if defined(__i386__) +#include "xen-x86_32.h" +#elif defined(__x86_64__) +#include "xen-x86_64.h" +#endif + +#ifndef __ASSEMBLY__ +typedef unsigned long xen_pfn_t; +#define PRI_xen_pfn "lx" +#endif + +#define XEN_HAVE_PV_GUEST_ENTRY 1 + +#define XEN_HAVE_PV_UPCALL_MASK 1 + +/* + * `incontents 200 segdesc Segment Descriptor Tables + */ +/* + * ` enum neg_errnoval + * ` HYPERVISOR_set_gdt(const xen_pfn_t frames[], unsigned int entries); + * ` + */ +/* + * 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. + * + * NB The LDT is set using the MMUEXT_SET_LDT op of HYPERVISOR_mmuext_op + */ +#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) + + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_update_descriptor(u64 pa, u64 desc); + * ` + * ` @pa The machine physical address of the descriptor to + * ` update. Must be either a descriptor page or writable. + * ` @desc The descriptor value to update, in the same format as a + * ` native descriptor table entry. + */ + +/* Maximum number of virtual CPUs in legacy multi-processor guests. */ +#define XEN_LEGACY_MAX_VCPUS 32 + +#ifndef __ASSEMBLY__ + +typedef unsigned long xen_ulong_t; +#define PRI_xen_ulong "lx" + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_stack_switch(unsigned long ss, unsigned long esp); + * ` + * Sets the stack segment and pointer for the current vcpu. + */ + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_set_trap_table(const struct trap_info traps[]); + * ` + */ +/* + * Send an array of these to HYPERVISOR_set_trap_table(). + * Terminate the array with a sentinel entry, with traps[].address==0. + * The privilege level specifies which modes may enter a trap via a software + * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate + * privilege levels as follows: + * Level == 0: Noone may enter + * Level == 1: Kernel may enter + * Level == 2: Kernel may enter + * Level == 3: Everyone may enter + */ +#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 */ +}; +typedef struct trap_info trap_info_t; +DEFINE_XEN_GUEST_HANDLE(trap_info_t); + +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. + * + * Also note that when calling DOMCTL_setvcpucontext and VCPU_initialise + * for HVM and PVH guests, not all information in this structure is updated: + * + * - For HVM guests, the structures read include: fpu_ctxt (if + * VGCT_I387_VALID is set), flags, user_regs, debugreg[*] + * + * - PVH guests are the same as HVM guests, but additionally use ctrlreg[3] to + * set cr3. All other fields not used should be set to 0. + */ +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_IN_KERNEL (1<<2) +#define _VGCF_i387_valid 0 +#define VGCF_i387_valid (1<<_VGCF_i387_valid) +#define _VGCF_in_kernel 2 +#define VGCF_in_kernel (1<<_VGCF_in_kernel) +#define _VGCF_failsafe_disables_events 3 +#define VGCF_failsafe_disables_events (1<<_VGCF_failsafe_disables_events) +#define _VGCF_syscall_disables_events 4 +#define VGCF_syscall_disables_events (1<<_VGCF_syscall_disables_events) +#define _VGCF_online 5 +#define VGCF_online (1<<_VGCF_online) + 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) */ + /* NB. User pagetable on x86/64 is placed in ctrlreg[1]. */ + unsigned long ctrlreg[8]; /* CR0-CR7 (control registers) */ + unsigned long debugreg[8]; /* DB0-DB7 (debug registers) */ +#ifdef __i386__ + 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; +#else + unsigned long event_callback_eip; + unsigned long failsafe_callback_eip; +#ifdef __XEN__ + union { + unsigned long syscall_callback_eip; + struct { + unsigned int event_callback_cs; /* compat CS of event cb */ + unsigned int failsafe_callback_cs; /* compat CS of failsafe cb */ + }; + }; +#else + unsigned long syscall_callback_eip; +#endif +#endif + unsigned long vm_assist; /* VMASST_TYPE_* bitmap */ +#ifdef __x86_64__ + /* Segment base addresses. */ + uint64_t fs_base; + uint64_t gs_base_kernel; + uint64_t gs_base_user; +#endif +}; +typedef struct vcpu_guest_context vcpu_guest_context_t; +DEFINE_XEN_GUEST_HANDLE(vcpu_guest_context_t); + +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. */ + xen_pfn_t pfn_to_mfn_frame_list_list; + unsigned long nmi_reason; + uint64_t pad[32]; +}; +typedef struct arch_shared_info arch_shared_info_t; + +#endif /* !__ASSEMBLY__ */ + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_fpu_taskswitch(int set); + * ` + * Sets (if set!=0) or clears (if set==0) CR0.TS. + */ + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_set_debugreg(int regno, unsigned long value); + * + * ` unsigned long + * ` HYPERVISOR_get_debugreg(int regno); + * For 0<=reg<=7, returns the debug register value. + * For other values of reg, returns ((unsigned long)-EINVAL). + * (Unfortunately, this interface is defective.) + */ + +/* + * 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 /* __XEN_PUBLIC_ARCH_X86_XEN_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/event_channel.h b/include/xen/event_channel.h new file mode 100644 index 0000000..49ac8cc --- /dev/null +++ b/include/xen/event_channel.h @@ -0,0 +1,381 @@ +/****************************************************************************** + * event_channel.h + * + * Event channels between domains. + * + * 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) 2003-2004, K A Fraser. + */ + +#ifndef __XEN_PUBLIC_EVENT_CHANNEL_H__ +#define __XEN_PUBLIC_EVENT_CHANNEL_H__ + +#include "xen.h" + +/* + * `incontents 150 evtchn Event Channels + * + * Event channels are the basic primitive provided by Xen for event + * notifications. An event is the Xen equivalent of a hardware + * interrupt. They essentially store one bit of information, the event + * of interest is signalled by transitioning this bit from 0 to 1. + * + * Notifications are received by a guest via an upcall from Xen, + * indicating when an event arrives (setting the bit). Further + * notifications are masked until the bit is cleared again (therefore, + * guests must check the value of the bit after re-enabling event + * delivery to ensure no missed notifications). + * + * Event notifications can be masked by setting a flag; this is + * equivalent to disabling interrupts and can be used to ensure + * atomicity of certain operations in the guest kernel. + * + * Event channels are represented by the evtchn_* fields in + * struct shared_info and struct vcpu_info. + */ + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_event_channel_op(enum event_channel_op cmd, void *args) + * ` + * @cmd == EVTCHNOP_* (event-channel operation). + * @args == struct evtchn_* Operation-specific extra arguments (NULL if none). + */ + +/* ` enum event_channel_op { // EVTCHNOP_* => struct evtchn_* */ +#define EVTCHNOP_bind_interdomain 0 +#define EVTCHNOP_bind_virq 1 +#define EVTCHNOP_bind_pirq 2 +#define EVTCHNOP_close 3 +#define EVTCHNOP_send 4 +#define EVTCHNOP_status 5 +#define EVTCHNOP_alloc_unbound 6 +#define EVTCHNOP_bind_ipi 7 +#define EVTCHNOP_bind_vcpu 8 +#define EVTCHNOP_unmask 9 +#define EVTCHNOP_reset 10 +#define EVTCHNOP_init_control 11 +#define EVTCHNOP_expand_array 12 +#define EVTCHNOP_set_priority 13 +/* ` } */ + +typedef uint32_t evtchn_port_t; +DEFINE_XEN_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. + */ +struct evtchn_alloc_unbound { + /* IN parameters */ + domid_t dom, remote_dom; + /* OUT parameters */ + evtchn_port_t port; +}; +typedef struct evtchn_alloc_unbound evtchn_alloc_unbound_t; + +/* + * 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>. + * + * In case the peer domain has already tried to set our event channel + * pending, before it was bound, EVTCHNOP_bind_interdomain always sets + * the local event channel pending. + * + * The usual pattern of use, in the guest's upcall (or subsequent + * handler) is as follows: (Re-enable the event channel for subsequent + * signalling and then) check for the existence of whatever condition + * is being waited for by other means, and take whatever action is + * needed (if any). + * + * NOTES: + * 1. <remote_dom> may be DOMID_SELF, allowing loopback connections. + */ +struct evtchn_bind_interdomain { + /* IN parameters. */ + domid_t remote_dom; + evtchn_port_t remote_port; + /* OUT parameters. */ + evtchn_port_t local_port; +}; +typedef struct evtchn_bind_interdomain evtchn_bind_interdomain_t; + +/* + * EVTCHNOP_bind_virq: Bind a local event channel to VIRQ <irq> on specified + * vcpu. + * NOTES: + * 1. Virtual IRQs are classified as per-vcpu or global. See the VIRQ list + * in xen.h for the classification of each VIRQ. + * 2. Global VIRQs must be allocated on VCPU0 but can subsequently be + * re-bound via EVTCHNOP_bind_vcpu. + * 3. Per-vcpu VIRQs may be bound to at most one event channel per vcpu. + * The allocated event channel is bound to the specified vcpu and the + * binding cannot be changed. + */ +struct evtchn_bind_virq { + /* IN parameters. */ + uint32_t virq; /* enum virq */ + uint32_t vcpu; + /* OUT parameters. */ + evtchn_port_t port; +}; +typedef struct evtchn_bind_virq evtchn_bind_virq_t; + +/* + * EVTCHNOP_bind_pirq: Bind a local event channel to a real IRQ (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. + */ +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; +}; +typedef struct evtchn_bind_pirq evtchn_bind_pirq_t; + +/* + * 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. + */ +struct evtchn_bind_ipi { + uint32_t vcpu; + /* OUT parameters. */ + evtchn_port_t port; +}; +typedef struct evtchn_bind_ipi evtchn_bind_ipi_t; + +/* + * 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. + */ +struct evtchn_close { + /* IN parameters. */ + evtchn_port_t port; +}; +typedef struct evtchn_close evtchn_close_t; + +/* + * EVTCHNOP_send: Send an event to the remote end of the channel whose local + * endpoint is <port>. + */ +struct evtchn_send { + /* IN parameters. */ + evtchn_port_t port; +}; +typedef struct evtchn_send evtchn_send_t; + +/* + * 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. + */ +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; +}; +typedef struct evtchn_status evtchn_status_t; + +/* + * EVTCHNOP_bind_vcpu: Specify which vcpu a channel should notify when an + * event is pending. + * NOTES: + * 1. IPI-bound channels always notify the vcpu specified at bind time. + * This binding cannot be changed. + * 2. Per-VCPU VIRQ channels always notify the vcpu specified at bind time. + * This binding cannot be changed. + * 3. 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). + */ +struct evtchn_bind_vcpu { + /* IN parameters. */ + evtchn_port_t port; + uint32_t vcpu; +}; +typedef struct evtchn_bind_vcpu evtchn_bind_vcpu_t; + +/* + * EVTCHNOP_unmask: Unmask the specified local event-channel port and deliver + * a notification to the appropriate VCPU if an event is pending. + */ +struct evtchn_unmask { + /* IN parameters. */ + evtchn_port_t port; +}; +typedef struct evtchn_unmask evtchn_unmask_t; + +/* + * EVTCHNOP_reset: Close all event channels associated with specified domain. + * NOTES: + * 1. <dom> may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may specify other than DOMID_SELF. + */ +struct evtchn_reset { + /* IN parameters. */ + domid_t dom; +}; +typedef struct evtchn_reset evtchn_reset_t; + +/* + * EVTCHNOP_init_control: initialize the control block for the FIFO ABI. + * + * Note: any events that are currently pending will not be resent and + * will be lost. Guests should call this before binding any event to + * avoid losing any events. + */ +struct evtchn_init_control { + /* IN parameters. */ + uint64_t control_gfn; + uint32_t offset; + uint32_t vcpu; + /* OUT parameters. */ + uint8_t link_bits; + uint8_t _pad[7]; +}; +typedef struct evtchn_init_control evtchn_init_control_t; + +/* + * EVTCHNOP_expand_array: add an additional page to the event array. + */ +struct evtchn_expand_array { + /* IN parameters. */ + uint64_t array_gfn; +}; +typedef struct evtchn_expand_array evtchn_expand_array_t; + +/* + * EVTCHNOP_set_priority: set the priority for an event channel. + */ +struct evtchn_set_priority { + /* IN parameters. */ + uint32_t port; + uint32_t priority; +}; +typedef struct evtchn_set_priority evtchn_set_priority_t; + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_event_channel_op_compat(struct evtchn_op *op) + * ` + * Superceded by new event_channel_op() hypercall since 0x00030202. + */ +struct evtchn_op { + uint32_t cmd; /* enum event_channel_op */ + 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; +}; +typedef struct evtchn_op evtchn_op_t; +DEFINE_XEN_GUEST_HANDLE(evtchn_op_t); + +/* + * 2-level ABI + */ + +#define EVTCHN_2L_NR_CHANNELS (sizeof(xen_ulong_t) * sizeof(xen_ulong_t) * 64) + +/* + * FIFO ABI + */ + +/* Events may have priorities from 0 (highest) to 15 (lowest). */ +#define EVTCHN_FIFO_PRIORITY_MAX 0 +#define EVTCHN_FIFO_PRIORITY_DEFAULT 7 +#define EVTCHN_FIFO_PRIORITY_MIN 15 + +#define EVTCHN_FIFO_MAX_QUEUES (EVTCHN_FIFO_PRIORITY_MIN + 1) + +typedef uint32_t event_word_t; + +#define EVTCHN_FIFO_PENDING 31 +#define EVTCHN_FIFO_MASKED 30 +#define EVTCHN_FIFO_LINKED 29 +#define EVTCHN_FIFO_BUSY 28 + +#define EVTCHN_FIFO_LINK_BITS 17 +#define EVTCHN_FIFO_LINK_MASK ((1 << EVTCHN_FIFO_LINK_BITS) - 1) + +#define EVTCHN_FIFO_NR_CHANNELS (1 << EVTCHN_FIFO_LINK_BITS) + +struct evtchn_fifo_control_block { + uint32_t ready; + uint32_t _rsvd; + uint32_t head[EVTCHN_FIFO_MAX_QUEUES]; +}; +typedef struct evtchn_fifo_control_block evtchn_fifo_control_block_t; + +#endif /* __XEN_PUBLIC_EVENT_CHANNEL_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h new file mode 100644 index 0000000..b8a3d6c --- /dev/null +++ b/include/xen/grant_table.h @@ -0,0 +1,662 @@ +/****************************************************************************** + * 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__ + +#include "xen.h" + +/* + * `incontents 150 gnttab Grant Tables + * + * Xen's grant tables provide a generic mechanism to memory sharing + * between domains. This shared memory interface underpins the split + * device drivers for block and network IO. + * + * Each domain has its own grant table. This is a data structure that + * is shared with Xen; it allows the domain to tell Xen what kind of + * permissions other domains have on its pages. Entries in the grant + * table are identified by grant references. A grant reference is an + * integer, which indexes into the grant table. It acts as a + * capability which the grantee can use to perform operations on the + * granter’s memory. + * + * This capability-based system allows shared-memory communications + * between unprivileged domains. A grant reference also encapsulates + * the details of a shared page, removing the need for a domain to + * know the real machine address of a page it is sharing. This makes + * it possible to share memory correctly with domains running in + * fully virtualised memory. + */ + +/*********************************** + * 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 (drivers/xen/grant_table.c, see + * http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git;a=blob;f=drivers/xen/grant-table.c;hb=HEAD + * + * 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. + */ + +/* + * Reference to a grant entry in a specified domain's grant table. + */ +typedef uint32_t grant_ref_t; + +/* + * 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. + */ + +/* + * Version 1 of the grant table entry structure is maintained purely + * for backwards compatibility. New guests should use version 2. + */ +#if __XEN_INTERFACE_VERSION__ < 0x0003020a +#define grant_entry_v1 grant_entry +#define grant_entry_v1_t grant_entry_t +#endif +struct grant_entry_v1 { + /* 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; +}; +typedef struct grant_entry_v1 grant_entry_v1_t; + +/* The first few grant table entries will be preserved across grant table + * version changes and may be pre-populated at domain creation by tools. + */ +#define GNTTAB_NR_RESERVED_ENTRIES 8 +#define GNTTAB_RESERVED_CONSOLE 0 +#define GNTTAB_RESERVED_XENSTORE 1 + +/* + * 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. + * GTF_transitive: Allow @domid to transitively access a subrange of + * @trans_grant in @trans_domid. No mappings are allowed. + */ +#define GTF_invalid (0U<<0) +#define GTF_permit_access (1U<<0) +#define GTF_accept_transfer (2U<<0) +#define GTF_transitive (3U<<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] + * GTF_PAT, GTF_PWT, GTF_PCD: (x86) cache attribute flags for the grant [GST] + * GTF_sub_page: Grant access to only a subrange of the page. @domid + * will only be allowed to copy from the grant, and not + * map it. [GST] + */ +#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) +#define _GTF_PWT (5) +#define GTF_PWT (1U<<_GTF_PWT) +#define _GTF_PCD (6) +#define GTF_PCD (1U<<_GTF_PCD) +#define _GTF_PAT (7) +#define GTF_PAT (1U<<_GTF_PAT) +#define _GTF_sub_page (8) +#define GTF_sub_page (1U<<_GTF_sub_page) + +/* + * 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) + +/* + * Version 2 grant table entries. These fulfil the same role as + * version 1 entries, but can represent more complicated operations. + * Any given domain will have either a version 1 or a version 2 table, + * and every entry in the table will be the same version. + * + * The interface by which domains use grant references does not depend + * on the grant table version in use by the other domain. + */ +#if __XEN_INTERFACE_VERSION__ >= 0x0003020a +/* + * Version 1 and version 2 grant entries share a common prefix. The + * fields of the prefix are documented as part of struct + * grant_entry_v1. + */ +struct grant_entry_header { + uint16_t flags; + domid_t domid; +}; +typedef struct grant_entry_header grant_entry_header_t; + +/* + * Version 2 of the grant entry structure. + */ +union grant_entry_v2 { + grant_entry_header_t hdr; + + /* + * This member is used for V1-style full page grants, where either: + * + * -- hdr.type is GTF_accept_transfer, or + * -- hdr.type is GTF_permit_access and GTF_sub_page is not set. + * + * In that case, the frame field has the same semantics as the + * field of the same name in the V1 entry structure. + */ + struct { + grant_entry_header_t hdr; + uint32_t pad0; + uint64_t frame; + } full_page; + + /* + * If the grant type is GTF_grant_access and GTF_sub_page is set, + * @domid is allowed to access bytes [@page_off,@page_off+@length) + * in frame @frame. + */ + struct { + grant_entry_header_t hdr; + uint16_t page_off; + uint16_t length; + uint64_t frame; + } sub_page; + + /* + * If the grant is GTF_transitive, @domid is allowed to use the + * grant @gref in domain @trans_domid, as if it was the local + * domain. Obviously, the transitive access must be compatible + * with the original grant. + * + * The current version of Xen does not allow transitive grants + * to be mapped. + */ + struct { + grant_entry_header_t hdr; + domid_t trans_domid; + uint16_t pad0; + grant_ref_t gref; + } transitive; + + uint32_t __spacer[4]; /* Pad to a power of two */ +}; +typedef union grant_entry_v2 grant_entry_v2_t; + +typedef uint16_t grant_status_t; + +#endif /* __XEN_INTERFACE_VERSION__ */ + +/*********************************** + * GRANT TABLE QUERIES AND USES + */ + +/* ` enum neg_errnoval + * ` HYPERVISOR_grant_table_op(enum grant_table_op cmd, + * ` void *args, + * ` unsigned int count) + * ` + * + * @args points to an array of a per-command data structure. The array + * has @count members + */ + +/* ` enum grant_table_op { // GNTTABOP_* => struct gnttab_* */ +#define GNTTABOP_map_grant_ref 0 +#define GNTTABOP_unmap_grant_ref 1 +#define GNTTABOP_setup_table 2 +#define GNTTABOP_dump_table 3 +#define GNTTABOP_transfer 4 +#define GNTTABOP_copy 5 +#define GNTTABOP_query_size 6 +#define GNTTABOP_unmap_and_replace 7 +#if __XEN_INTERFACE_VERSION__ >= 0x0003020a +#define GNTTABOP_set_version 8 +#define GNTTABOP_get_status_frames 9 +#define GNTTABOP_get_version 10 +#define GNTTABOP_swap_grant_ref 11 +#endif /* __XEN_INTERFACE_VERSION__ */ +/* ` } */ + +/* + * 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! + */ +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; /* => enum grant_status */ + grant_handle_t handle; + uint64_t dev_bus_addr; +}; +typedef struct gnttab_map_grant_ref gnttab_map_grant_ref_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_map_grant_ref_t); + +/* + * 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. + */ +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; /* => enum grant_status */ +}; +typedef struct gnttab_unmap_grant_ref gnttab_unmap_grant_ref_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_unmap_grant_ref_t); + +/* + * 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. + */ +struct gnttab_setup_table { + /* IN parameters. */ + domid_t dom; + uint32_t nr_frames; + /* OUT parameters. */ + int16_t status; /* => enum grant_status */ +#if __XEN_INTERFACE_VERSION__ < 0x00040300 + XEN_GUEST_HANDLE(ulong) frame_list; +#else + XEN_GUEST_HANDLE(xen_pfn_t) frame_list; +#endif +}; +typedef struct gnttab_setup_table gnttab_setup_table_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_setup_table_t); + +/* + * GNTTABOP_dump_table: Dump the contents of the grant table to the + * xen console. Debugging use only. + */ +struct gnttab_dump_table { + /* IN parameters. */ + domid_t dom; + /* OUT parameters. */ + int16_t status; /* => enum grant_status */ +}; +typedef struct gnttab_dump_table gnttab_dump_table_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_dump_table_t); + +/* + * 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. + */ +struct gnttab_transfer { + /* IN parameters. */ + xen_pfn_t mfn; + domid_t domid; + grant_ref_t ref; + /* OUT parameters. */ + int16_t status; +}; +typedef struct gnttab_transfer gnttab_transfer_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_transfer_t); + + +/* + * 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) + +struct gnttab_copy { + /* IN parameters. */ + struct { + union { + grant_ref_t ref; + xen_pfn_t gmfn; + } u; + domid_t domid; + uint16_t offset; + } source, dest; + uint16_t len; + uint16_t flags; /* GNTCOPY_* */ + /* OUT parameters. */ + int16_t status; +}; +typedef struct gnttab_copy gnttab_copy_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_copy_t); + +/* + * 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. + */ +struct gnttab_query_size { + /* IN parameters. */ + domid_t dom; + /* OUT parameters. */ + uint32_t nr_frames; + uint32_t max_nr_frames; + int16_t status; /* => enum grant_status */ +}; +typedef struct gnttab_query_size gnttab_query_size_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_query_size_t); + +/* + * GNTTABOP_unmap_and_replace: Destroy one or more grant-reference mappings + * tracked by <handle> but atomically replace the page table entry with one + * pointing to the machine address under <new_addr>. <new_addr> will be + * redirected to the null entry. + * NOTES: + * 1. The call may fail in an undefined manner if either mapping is not + * tracked by <handle>. + * 2. After executing a batch of unmaps, it is guaranteed that no stale + * mappings will remain in the device or host TLBs. + */ +struct gnttab_unmap_and_replace { + /* IN parameters. */ + uint64_t host_addr; + uint64_t new_addr; + grant_handle_t handle; + /* OUT parameters. */ + int16_t status; /* => enum grant_status */ +}; +typedef struct gnttab_unmap_and_replace gnttab_unmap_and_replace_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_unmap_and_replace_t); + +#if __XEN_INTERFACE_VERSION__ >= 0x0003020a +/* + * GNTTABOP_set_version: Request a particular version of the grant + * table shared table structure. This operation can only be performed + * once in any given domain. It must be performed before any grants + * are activated; otherwise, the domain will be stuck with version 1. + * The only defined versions are 1 and 2. + */ +struct gnttab_set_version { + /* IN/OUT parameters */ + uint32_t version; +}; +typedef struct gnttab_set_version gnttab_set_version_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_set_version_t); + + +/* + * GNTTABOP_get_status_frames: Get the list of frames used to store grant + * status for <dom>. In grant format version 2, the status is separated + * from the other shared grant fields to allow more efficient synchronization + * using barriers instead of atomic cmpexch operations. + * <nr_frames> specify the size of vector <frame_list>. + * The frame addresses are returned in the <frame_list>. + * Only <nr_frames> addresses are returned, 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. + */ +struct gnttab_get_status_frames { + /* IN parameters. */ + uint32_t nr_frames; + domid_t dom; + /* OUT parameters. */ + int16_t status; /* => enum grant_status */ + XEN_GUEST_HANDLE(uint64_t) frame_list; +}; +typedef struct gnttab_get_status_frames gnttab_get_status_frames_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_get_status_frames_t); + +/* + * GNTTABOP_get_version: Get the grant table version which is in + * effect for domain <dom>. + */ +struct gnttab_get_version { + /* IN parameters */ + domid_t dom; + uint16_t pad; + /* OUT parameters */ + uint32_t version; +}; +typedef struct gnttab_get_version gnttab_get_version_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_get_version_t); + +/* + * GNTTABOP_swap_grant_ref: Swap the contents of two grant entries. + */ +struct gnttab_swap_grant_ref { + /* IN parameters */ + grant_ref_t ref_a; + grant_ref_t ref_b; + /* OUT parameters */ + int16_t status; /* => enum grant_status */ +}; +typedef struct gnttab_swap_grant_ref gnttab_swap_grant_ref_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_swap_grant_ref_t); + +#endif /* __XEN_INTERFACE_VERSION__ */ + +/* + * Bitfield values for gnttab_map_grant_ref.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) + +#define _GNTMAP_can_fail (5) +#define GNTMAP_can_fail (1<<_GNTMAP_can_fail) + +/* + * Bits to be placed in guest kernel available PTE bits (architecture + * dependent; only supported when XENFEAT_gnttab_map_avail_bits is set). + */ +#define _GNTMAP_guest_avail0 (16) +#define GNTMAP_guest_avail_mask ((uint32_t)~0 << _GNTMAP_guest_avail0) + +/* + * Values for error status returns. All errors are -ve. + */ +/* ` enum grant_status { */ +#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 GNTST_address_too_big (-11) /* transfer page address too large. */ +#define GNTST_eagain (-12) /* Operation not done; try again. */ +/* ` } */ + +#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", \ + "page address size too large", \ + "operation not done; try again" \ +} + +#endif /* __XEN_PUBLIC_GRANT_TABLE_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/io/blkif.h b/include/xen/io/blkif.h new file mode 100644 index 0000000..c3e169c --- /dev/null +++ b/include/xen/io/blkif.h @@ -0,0 +1,608 @@ +/****************************************************************************** + * blkif.h + * + * Unified block-device I/O interface for Xen guest OSes. + * + * 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) 2003-2004, Keir Fraser + * Copyright (c) 2012, Spectra Logic Corporation + */ + +#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()). + */ + +#ifndef blkif_vdev_t +#define blkif_vdev_t uint16_t +#endif +#define blkif_sector_t uint64_t + +/* + * Feature and Parameter Negotiation + * ================================= + * The two halves of a Xen block driver utilize nodes within the XenStore to + * communicate capabilities and to negotiate operating parameters. This + * section enumerates these nodes which reside in the respective front and + * backend portions of the XenStore, following the XenBus convention. + * + * All data in the XenStore is stored as strings. Nodes specifying numeric + * values are encoded in decimal. Integer value ranges listed below are + * expressed as fixed sized integer types capable of storing the conversion + * of a properly formated node string, without loss of information. + * + * Any specified default value is in effect if the corresponding XenBus node + * is not present in the XenStore. + * + * XenStore nodes in sections marked "PRIVATE" are solely for use by the + * driver side whose XenBus tree contains them. + * + * XenStore nodes marked "DEPRECATED" in their notes section should only be + * used to provide interoperability with legacy implementations. + * + * See the XenBus state transition diagram below for details on when XenBus + * nodes must be published and when they can be queried. + * + ***************************************************************************** + * Backend XenBus Nodes + ***************************************************************************** + * + *------------------ Backend Device Identification (PRIVATE) ------------------ + * + * mode + * Values: "r" (read only), "w" (writable) + * + * The read or write access permissions to the backing store to be + * granted to the frontend. + * + * params + * Values: string + * + * A free formatted string providing sufficient information for the + * backend driver to open the backing device. (e.g. the path to the + * file or block device representing the backing store.) + * + * type + * Values: "file", "phy", "tap" + * + * The type of the backing device/object. + * + *--------------------------------- Features --------------------------------- + * + * feature-barrier + * Values: 0/1 (boolean) + * Default Value: 0 + * + * A value of "1" indicates that the backend can process requests + * containing the BLKIF_OP_WRITE_BARRIER request opcode. Requests + * of this type may still be returned at any time with the + * BLKIF_RSP_EOPNOTSUPP result code. + * + * feature-flush-cache + * Values: 0/1 (boolean) + * Default Value: 0 + * + * A value of "1" indicates that the backend can process requests + * containing the BLKIF_OP_FLUSH_DISKCACHE request opcode. Requests + * of this type may still be returned at any time with the + * BLKIF_RSP_EOPNOTSUPP result code. + * + * feature-discard + * Values: 0/1 (boolean) + * Default Value: 0 + * + * A value of "1" indicates that the backend can process requests + * containing the BLKIF_OP_DISCARD request opcode. Requests + * of this type may still be returned at any time with the + * BLKIF_RSP_EOPNOTSUPP result code. + * + * feature-persistent + * Values: 0/1 (boolean) + * Default Value: 0 + * Notes: 7 + * + * A value of "1" indicates that the backend can keep the grants used + * by the frontend driver mapped, so the same set of grants should be + * used in all transactions. The maximum number of grants the backend + * can map persistently depends on the implementation, but ideally it + * should be RING_SIZE * BLKIF_MAX_SEGMENTS_PER_REQUEST. Using this + * feature the backend doesn't need to unmap each grant, preventing + * costly TLB flushes. The backend driver should only map grants + * persistently if the frontend supports it. If a backend driver chooses + * to use the persistent protocol when the frontend doesn't support it, + * it will probably hit the maximum number of persistently mapped grants + * (due to the fact that the frontend won't be reusing the same grants), + * and fall back to non-persistent mode. Backend implementations may + * shrink or expand the number of persistently mapped grants without + * notifying the frontend depending on memory constraints (this might + * cause a performance degradation). + * + * If a backend driver wants to limit the maximum number of persistently + * mapped grants to a value less than RING_SIZE * + * BLKIF_MAX_SEGMENTS_PER_REQUEST a LRU strategy should be used to + * discard the grants that are less commonly used. Using a LRU in the + * backend driver paired with a LIFO queue in the frontend will + * allow us to have better performance in this scenario. + * + *----------------------- Request Transport Parameters ------------------------ + * + * max-ring-page-order + * Values: <uint32_t> + * Default Value: 0 + * Notes: 1, 3 + * + * The maximum supported size of the request ring buffer in units of + * lb(machine pages). (e.g. 0 == 1 page, 1 = 2 pages, 2 == 4 pages, + * etc.). + * + * max-ring-pages + * Values: <uint32_t> + * Default Value: 1 + * Notes: DEPRECATED, 2, 3 + * + * The maximum supported size of the request ring buffer in units of + * machine pages. The value must be a power of 2. + * + *------------------------- Backend Device Properties ------------------------- + * + * discard-alignment + * Values: <uint32_t> + * Default Value: 0 + * Notes: 4, 5 + * + * The offset, in bytes from the beginning of the virtual block device, + * to the first, addressable, discard extent on the underlying device. + * + * discard-granularity + * Values: <uint32_t> + * Default Value: <"sector-size"> + * Notes: 4 + * + * The size, in bytes, of the individually addressable discard extents + * of the underlying device. + * + * discard-secure + * Values: 0/1 (boolean) + * Default Value: 0 + * Notes: 10 + * + * A value of "1" indicates that the backend can process BLKIF_OP_DISCARD + * requests with the BLKIF_DISCARD_SECURE flag set. + * + * info + * Values: <uint32_t> (bitmap) + * + * A collection of bit flags describing attributes of the backing + * device. The VDISK_* macros define the meaning of each bit + * location. + * + * sector-size + * Values: <uint32_t> + * + * The logical sector size, in bytes, of the backend device. + * + * physical-sector-size + * Values: <uint32_t> + * + * The physical sector size, in bytes, of the backend device. + * + * sectors + * Values: <uint64_t> + * + * The size of the backend device, expressed in units of its logical + * sector size ("sector-size"). + * + ***************************************************************************** + * Frontend XenBus Nodes + ***************************************************************************** + * + *----------------------- Request Transport Parameters ----------------------- + * + * event-channel + * Values: <uint32_t> + * + * The identifier of the Xen event channel used to signal activity + * in the ring buffer. + * + * ring-ref + * Values: <uint32_t> + * Notes: 6 + * + * The Xen grant reference granting permission for the backend to map + * the sole page in a single page sized ring buffer. + * + * ring-ref%u + * Values: <uint32_t> + * Notes: 6 + * + * For a frontend providing a multi-page ring, a "number of ring pages" + * sized list of nodes, each containing a Xen grant reference granting + * permission for the backend to map the page of the ring located + * at page index "%u". Page indexes are zero based. + * + * protocol + * Values: string (XEN_IO_PROTO_ABI_*) + * Default Value: XEN_IO_PROTO_ABI_NATIVE + * + * The machine ABI rules governing the format of all ring request and + * response structures. + * + * ring-page-order + * Values: <uint32_t> + * Default Value: 0 + * Maximum Value: MAX(ffs(max-ring-pages) - 1, max-ring-page-order) + * Notes: 1, 3 + * + * The size of the frontend allocated request ring buffer in units + * of lb(machine pages). (e.g. 0 == 1 page, 1 = 2 pages, 2 == 4 pages, + * etc.). + * + * num-ring-pages + * Values: <uint32_t> + * Default Value: 1 + * Maximum Value: MAX(max-ring-pages,(0x1 << max-ring-page-order)) + * Notes: DEPRECATED, 2, 3 + * + * The size of the frontend allocated request ring buffer in units of + * machine pages. The value must be a power of 2. + * + * feature-persistent + * Values: 0/1 (boolean) + * Default Value: 0 + * Notes: 7, 8, 9 + * + * A value of "1" indicates that the frontend will reuse the same grants + * for all transactions, allowing the backend to map them with write + * access (even when it should be read-only). If the frontend hits the + * maximum number of allowed persistently mapped grants, it can fallback + * to non persistent mode. This will cause a performance degradation, + * since the the backend driver will still try to map those grants + * persistently. Since the persistent grants protocol is compatible with + * the previous protocol, a frontend driver can choose to work in + * persistent mode even when the backend doesn't support it. + * + * It is recommended that the frontend driver stores the persistently + * mapped grants in a LIFO queue, so a subset of all persistently mapped + * grants gets used commonly. This is done in case the backend driver + * decides to limit the maximum number of persistently mapped grants + * to a value less than RING_SIZE * BLKIF_MAX_SEGMENTS_PER_REQUEST. + * + *------------------------- Virtual Device Properties ------------------------- + * + * device-type + * Values: "disk", "cdrom", "floppy", etc. + * + * virtual-device + * Values: <uint32_t> + * + * A value indicating the physical device to virtualize within the + * frontend's domain. (e.g. "The first ATA disk", "The third SCSI + * disk", etc.) + * + * See docs/misc/vbd-interface.txt for details on the format of this + * value. + * + * Notes + * ----- + * (1) Multi-page ring buffer scheme first developed in the Citrix XenServer + * PV drivers. + * (2) Multi-page ring buffer scheme first used in some RedHat distributions + * including a distribution deployed on certain nodes of the Amazon + * EC2 cluster. + * (3) Support for multi-page ring buffers was implemented independently, + * in slightly different forms, by both Citrix and RedHat/Amazon. + * For full interoperability, block front and backends should publish + * identical ring parameters, adjusted for unit differences, to the + * XenStore nodes used in both schemes. + * (4) Devices that support discard functionality may internally allocate space + * (discardable extents) in units that are larger than the exported logical + * block size. If the backing device has such discardable extents the + * backend should provide both discard-granularity and discard-alignment. + * Providing just one of the two may be considered an error by the frontend. + * Backends supporting discard should include discard-granularity and + * discard-alignment even if it supports discarding individual sectors. + * Frontends should assume discard-alignment == 0 and discard-granularity + * == sector size if these keys are missing. + * (5) The discard-alignment parameter allows a physical device to be + * partitioned into virtual devices that do not necessarily begin or + * end on a discardable extent boundary. + * (6) When there is only a single page allocated to the request ring, + * 'ring-ref' is used to communicate the grant reference for this + * page to the backend. When using a multi-page ring, the 'ring-ref' + * node is not created. Instead 'ring-ref0' - 'ring-refN' are used. + * (7) When using persistent grants data has to be copied from/to the page + * where the grant is currently mapped. The overhead of doing this copy + * however doesn't suppress the speed improvement of not having to unmap + * the grants. + * (8) The frontend driver has to allow the backend driver to map all grants + * with write access, even when they should be mapped read-only, since + * further requests may reuse these grants and require write permissions. + * (9) Linux implementation doesn't have a limit on the maximum number of + * grants that can be persistently mapped in the frontend driver, but + * due to the frontent driver implementation it should never be bigger + * than RING_SIZE * BLKIF_MAX_SEGMENTS_PER_REQUEST. + *(10) The discard-secure property may be present and will be set to 1 if the + * backing device supports secure discard. + */ + +/* + * STATE DIAGRAMS + * + ***************************************************************************** + * Startup * + ***************************************************************************** + * + * Tool stack creates front and back nodes with state XenbusStateInitialising. + * + * Front Back + * ================================= ===================================== + * XenbusStateInitialising XenbusStateInitialising + * o Query virtual device o Query backend device identification + * properties. data. + * o Setup OS device instance. o Open and validate backend device. + * o Publish backend features and + * transport parameters. + * | + * | + * V + * XenbusStateInitWait + * + * o Query backend features and + * transport parameters. + * o Allocate and initialize the + * request ring. + * o Publish transport parameters + * that will be in effect during + * this connection. + * | + * | + * V + * XenbusStateInitialised + * + * o Query frontend transport parameters. + * o Connect to the request ring and + * event channel. + * o Publish backend device properties. + * | + * | + * V + * XenbusStateConnected + * + * o Query backend device properties. + * o Finalize OS virtual device + * instance. + * | + * | + * V + * XenbusStateConnected + * + * Note: Drivers that do not support any optional features, or the negotiation + * of transport parameters, can skip certain states in the state machine: + * + * o A frontend may transition to XenbusStateInitialised without + * waiting for the backend to enter XenbusStateInitWait. In this + * case, default transport parameters are in effect and any + * transport parameters published by the frontend must contain + * their default values. + * + * o A backend may transition to XenbusStateInitialised, bypassing + * XenbusStateInitWait, without waiting for the frontend to first + * enter the XenbusStateInitialised state. In this case, default + * transport parameters are in effect and any transport parameters + * published by the backend must contain their default values. + * + * Drivers that support optional features and/or transport parameter + * negotiation must tolerate these additional state transition paths. + * In general this means performing the work of any skipped state + * transition, if it has not already been performed, in addition to the + * work associated with entry into the current state. + */ + +/* + * REQUEST CODES. + */ +#define BLKIF_OP_READ 0 +#define BLKIF_OP_WRITE 1 +/* + * All writes issued prior to a request with the BLKIF_OP_WRITE_BARRIER + * operation code ("barrier request") must be completed prior to the + * execution of the barrier request. All writes issued after the barrier + * request must not execute until after the completion of the barrier request. + * + * Optional. See "feature-barrier" XenBus node documentation above. + */ +#define BLKIF_OP_WRITE_BARRIER 2 +/* + * Commit any uncommitted contents of the backing device's volatile cache + * to stable storage. + * + * Optional. See "feature-flush-cache" XenBus node documentation above. + */ +#define BLKIF_OP_FLUSH_DISKCACHE 3 +/* + * Used in SLES sources for device specific command packet + * contained within the request. Reserved for that purpose. + */ +#define BLKIF_OP_RESERVED_1 4 +/* + * Indicate to the backend device that a region of storage is no longer in + * use, and may be discarded at any time without impact to the client. If + * the BLKIF_DISCARD_SECURE flag is set on the request, all copies of the + * discarded region on the device must be rendered unrecoverable before the + * command returns. + * + * This operation is analogous to performing a trim (ATA) or unamp (SCSI), + * command on a native device. + * + * More information about trim/unmap operations can be found at: + * http://t13.org/Documents/UploadedDocuments/docs2008/ + * e07154r6-Data_Set_Management_Proposal_for_ATA-ACS2.doc + * http://www.seagate.com/staticfiles/support/disc/manuals/ + * Interface%20manuals/100293068c.pdf + * + * Optional. See "feature-discard", "discard-alignment", + * "discard-granularity", and "discard-secure" in the XenBus node + * documentation above. + */ +#define BLKIF_OP_DISCARD 5 + +/* + * Recognized if "feature-max-indirect-segments" in present in the backend + * xenbus info. The "feature-max-indirect-segments" node contains the maximum + * number of segments allowed by the backend per request. If the node is + * present, the frontend might use blkif_request_indirect structs in order to + * issue requests with more than BLKIF_MAX_SEGMENTS_PER_REQUEST (11). The + * maximum number of indirect segments is fixed by the backend, but the + * frontend can issue requests with any number of indirect segments as long as + * it's less than the number provided by the backend. The indirect_grefs field + * in blkif_request_indirect should be filled by the frontend with the + * grant references of the pages that are holding the indirect segments. + * These pages are filled with an array of blkif_request_segment that hold the + * information about the segments. The number of indirect pages to use is + * determined by the number of segments an indirect request contains. Every + * indirect page can contain a maximum of + * (PAGE_SIZE / sizeof(struct blkif_request_segment)) segments, so to + * calculate the number of indirect pages to use we have to do + * ceil(indirect_segments / (PAGE_SIZE / sizeof(struct blkif_request_segment))). + * + * If a backend does not recognize BLKIF_OP_INDIRECT, it should *not* + * create the "feature-max-indirect-segments" node! + */ +#define BLKIF_OP_INDIRECT 6 + +/* + * Maximum scatter/gather segments per request. + * This is carefully chosen so that sizeof(blkif_ring_t) <= 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 + +/* + * Maximum number of indirect pages to use per request. + */ +#define BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST 8 + +/* + * NB. first_sect and last_sect in blkif_request_segment, as well as + * sector_number in blkif_request, are always expressed in 512-byte units. + * However they must be properly aligned to the real sector size of the + * physical disk, which is reported in the "physical-sector-size" node in + * the backend xenbus info. Also the xenbus "sectors" node is expressed in + * 512-byte units. + */ +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; +}; + +/* + * Starting ring element for any I/O request. + */ +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 seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; +}; +typedef struct blkif_request blkif_request_t; + +/* + * Cast to this structure when blkif_request.operation == BLKIF_OP_DISCARD + * sizeof(struct blkif_request_discard) <= sizeof(struct blkif_request) + */ +struct blkif_request_discard { + uint8_t operation; /* BLKIF_OP_DISCARD */ + uint8_t flag; /* BLKIF_DISCARD_SECURE or zero */ +#define BLKIF_DISCARD_SECURE (1<<0) /* ignored if discard-secure=0 */ + blkif_vdev_t handle; /* same as for read/write requests */ + uint64_t id; /* private guest value, echoed in resp */ + blkif_sector_t sector_number;/* start sector idx on disk */ + uint64_t nr_sectors; /* number of contiguous sectors to discard*/ +}; +typedef struct blkif_request_discard blkif_request_discard_t; + +struct blkif_request_indirect { + uint8_t operation; /* BLKIF_OP_INDIRECT */ + uint8_t indirect_op; /* BLKIF_OP_{READ/WRITE} */ + uint16_t nr_segments; /* number of segments */ + uint64_t id; /* private guest value, echoed in resp */ + blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */ + blkif_vdev_t handle; /* same as for read/write requests */ + grant_ref_t indirect_grefs[BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST]; +#ifdef __i386__ + uint64_t pad; /* Make it 64 byte aligned on i386 */ +#endif +}; +typedef struct blkif_request_indirect blkif_request_indirect_t; + +struct blkif_response { + uint64_t id; /* copied from request */ + uint8_t operation; /* copied from request */ + int16_t status; /* BLKIF_RSP_??? */ +}; +typedef struct blkif_response blkif_response_t; + +/* + * 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__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/io/console.h b/include/xen/io/console.h new file mode 100644 index 0000000..e2cd97f --- /dev/null +++ b/include/xen/io/console.h @@ -0,0 +1,51 @@ +/****************************************************************************** + * console.h + * + * Console I/O interface for Xen guest OSes. + * + * 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 + */ + +#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__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/io/protocols.h b/include/xen/io/protocols.h new file mode 100644 index 0000000..80b196b --- /dev/null +++ b/include/xen/io/protocols.h @@ -0,0 +1,40 @@ +/****************************************************************************** + * protocols.h + * + * 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_PROTOCOLS_H__ +#define __XEN_PROTOCOLS_H__ + +#define XEN_IO_PROTO_ABI_X86_32 "x86_32-abi" +#define XEN_IO_PROTO_ABI_X86_64 "x86_64-abi" +#define XEN_IO_PROTO_ABI_ARM "arm-abi" + +#if defined(__i386__) +# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_X86_32 +#elif defined(__x86_64__) +# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_X86_64 +#elif defined(__arm__) || defined(__aarch64__) +# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_ARM +#else +# error arch fixup needed here +#endif + +#endif diff --git a/include/xen/io/ring.h b/include/xen/io/ring.h new file mode 100644 index 0000000..73e13d7 --- /dev/null +++ b/include/xen/io/ring.h @@ -0,0 +1,312 @@ +/****************************************************************************** + * ring.h + * + * Shared producer-consumer ring macros. + * + * 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. + * + * Tim Deegan and Andrew Warfield November 2004. + */ + +#ifndef __XEN_PUBLIC_IO_RING_H__ +#define __XEN_PUBLIC_IO_RING_H__ + +#include "../xen-compat.h" + +#if __XEN_INTERFACE_VERSION__ < 0x00030208 +#define xen_mb() mb() +#define xen_rmb() rmb() +#define xen_wmb() wmb() +#endif + +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 __CONST_RING_SIZE(_s, _sz) \ + (__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \ + sizeof(((struct _s##_sring *)0)->ring[0]))) +/* + * The same for passing in an actual pointer instead of a name tag. + */ +#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 request_t, and response_t already defined. + * + * In a header where you want the ring datatype declared, you then do: + * + * DEFINE_RING_TYPES(mytag, request_t, response_t); + * + * These expand out to give you a set of types, as you can see below. + * The most important of these are: + * + * mytag_sring_t - The shared ring. + * mytag_front_ring_t - The 'front' half of the ring. + * mytag_back_ring_t - 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: + * + * mytag_front_ring_t front_ring; + * SHARED_RING_INIT((mytag_sring_t *)shared_page); + * FRONT_RING_INIT(&front_ring, (mytag_sring_t *)shared_page, PAGE_SIZE); + * + * Initializing the back follows similarly (note that only the front + * initializes the shared ring): + * + * mytag_back_ring_t back_ring; + * BACK_RING_INIT(&back_ring, (mytag_sring_t *)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; \ + union { \ + struct { \ + uint8_t smartpoll_active; \ + } netif; \ + struct { \ + uint8_t msg; \ + } tapif_user; \ + uint8_t pvt_pad[4]; \ + } private; \ + uint8_t __pad[44]; \ + 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; \ +}; \ + \ +/* Syntactic sugar */ \ +typedef struct __name##_sring __name##_sring_t; \ +typedef struct __name##_front_ring __name##_front_ring_t; \ +typedef struct __name##_back_ring __name##_back_ring_t + +/* + * 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; \ + (void)memset((_s)->private.pvt_pad, 0, sizeof((_s)->private.pvt_pad)); \ + (void)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) + +/* 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) + +#ifdef __GNUC__ +#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; \ +}) +#else +/* Same as above, but without the nice GCC ({ ... }) syntax. */ +#define RING_HAS_UNCONSUMED_REQUESTS(_r) \ + ((((_r)->sring->req_prod - (_r)->req_cons) < \ + (RING_SIZE(_r) - ((_r)->req_cons - (_r)->rsp_prod_pvt))) ? \ + ((_r)->sring->req_prod - (_r)->req_cons) : \ + (RING_SIZE(_r) - ((_r)->req_cons - (_r)->rsp_prod_pvt))) +#endif + +/* 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)) + +/* Ill-behaved frontend determination: Can there be this many requests? */ +#define RING_REQUEST_PROD_OVERFLOW(_r, _prod) \ + (((_prod) - (_r)->rsp_prod_pvt) > RING_SIZE(_r)) + +#define RING_PUSH_REQUESTS(_r) do { \ + xen_wmb(); /* back sees requests /before/ updated producer index */ \ + (_r)->sring->req_prod = (_r)->req_prod_pvt; \ +} while (0) + +#define RING_PUSH_RESPONSES(_r) do { \ + xen_wmb(); /* front sees resps /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; \ + xen_wmb(); /* back sees requests /before/ updated producer index */ \ + (_r)->sring->req_prod = __new; \ + xen_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; \ + xen_wmb(); /* front sees resps /before/ updated producer index */ \ + (_r)->sring->rsp_prod = __new; \ + xen_mb(); /* front sees new resps /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; \ + xen_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; \ + xen_mb(); \ + (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ +} while (0) + +#endif /* __XEN_PUBLIC_IO_RING_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/io/xenbus.h b/include/xen/io/xenbus.h new file mode 100644 index 0000000..927f9db --- /dev/null +++ b/include/xen/io/xenbus.h @@ -0,0 +1,80 @@ +/***************************************************************************** + * xenbus.h + * + * Xenbus protocol details. + * + * 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 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, + + /* + * InitWait: Finished early initialisation but waiting for information + * from the peer or hotplug scripts. + */ + XenbusStateInitWait = 2, + + /* + * Initialised: Waiting for a connection from the peer. + */ + XenbusStateInitialised = 3, + + XenbusStateConnected = 4, + + /* + * Closing: The device is being closed due to an error or an unplug event. + */ + XenbusStateClosing = 5, + + XenbusStateClosed = 6, + + /* + * Reconfiguring: The device is being reconfigured. + */ + XenbusStateReconfiguring = 7, + + XenbusStateReconfigured = 8 +}; +typedef enum xenbus_state XenbusState; + +#endif /* _XEN_PUBLIC_IO_XENBUS_H */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/io/xs_wire.h b/include/xen/io/xs_wire.h new file mode 100644 index 0000000..585f0c8 --- /dev/null +++ b/include/xen/io/xs_wire.h @@ -0,0 +1,138 @@ +/* + * Details of the "wire" protocol between Xen Store Daemon and client + * library or guest kernel. + * + * 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 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, + XS_RESUME, + XS_SET_TARGET, + XS_RESTRICT, + XS_RESET_WATCHES +}; + +#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; +}; +#ifdef EINVAL +#define XSD_ERROR(x) { x, #x } +/* LINTED: static unused */ +static struct xsd_errors xsd_errors[] +#if defined(__GNUC__) +__attribute__((unused)) +#endif + = { + 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), + XSD_ERROR(E2BIG) +}; +#endif + +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 +}; + +/* + * `incontents 150 xenstore_struct XenStore wire protocol. + * + * 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; +}; + +/* Violating this is very bad. See docs/misc/xenstore.txt. */ +#define XENSTORE_PAYLOAD_MAX 4096 + +/* Violating these just gets you an error back */ +#define XENSTORE_ABS_PATH_MAX 3072 +#define XENSTORE_REL_PATH_MAX 2048 + +#endif /* _XS_WIRE_H */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/sched.h b/include/xen/sched.h new file mode 100644 index 0000000..a30b11d --- /dev/null +++ b/include/xen/sched.h @@ -0,0 +1,174 @@ +/****************************************************************************** + * sched.h + * + * Scheduler state interactions + * + * 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_SCHED_H__ +#define __XEN_PUBLIC_SCHED_H__ + +#include "event_channel.h" + +/* + * `incontents 150 sched Guest Scheduler Operations + * + * The SCHEDOP interface provides mechanisms for a guest to interact + * with the scheduler, including yield, blocking and shutting itself + * down. + */ + +/* + * The prototype for this hypercall is: + * ` long HYPERVISOR_sched_op(enum sched_op cmd, void *arg, ...) + * + * @cmd == SCHEDOP_??? (scheduler operation). + * @arg == Operation-specific extra argument(s), as described below. + * ... == Additional Operation-specific extra arguments, described below. + * + * Versions of Xen prior to 3.0.2 provided 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) + * + * This legacy version is available to new guests as: + * ` long HYPERVISOR_sched_op_compat(enum sched_op cmd, unsigned long arg) + */ + +/* ` enum sched_op { // SCHEDOP_* => struct sched_* */ +/* + * 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_t structure. + * + * If the sched_shutdown_t reason is SHUTDOWN_suspend then this + * hypercall takes an additional extra argument which should be the + * MFN of the guest's start_info_t. + * + * In addition, which reason is SHUTDOWN_suspend this hypercall + * returns 1 if suspend was cancelled or the domain was merely + * checkpointed, and 0 if it is resuming in a new domain. + */ +#define SCHEDOP_shutdown 2 + +/* + * 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_t structure. + */ +#define SCHEDOP_poll 3 + +/* + * Declare a shutdown for another domain. The main use of this function is + * in interpreting shutdown requests and reasons for fully-virtualized + * domains. A para-virtualized domain may use SCHEDOP_shutdown directly. + * @arg == pointer to sched_remote_shutdown_t structure. + */ +#define SCHEDOP_remote_shutdown 4 + +/* + * Latch a shutdown code, so that when the domain later shuts down it + * reports this code to the control tools. + * @arg == sched_shutdown_t, as for SCHEDOP_shutdown. + */ +#define SCHEDOP_shutdown_code 5 + +/* + * Setup, poke and destroy a domain watchdog timer. + * @arg == pointer to sched_watchdog_t structure. + * With id == 0, setup a domain watchdog timer to cause domain shutdown + * after timeout, returns watchdog id. + * With id != 0 and timeout == 0, destroy domain watchdog timer. + * With id != 0 and timeout != 0, poke watchdog timer and set new timeout. + */ +#define SCHEDOP_watchdog 6 +/* ` } */ + +struct sched_shutdown { + unsigned int reason; /* SHUTDOWN_* => enum sched_shutdown_reason */ +}; +typedef struct sched_shutdown sched_shutdown_t; +DEFINE_XEN_GUEST_HANDLE(sched_shutdown_t); + +struct sched_poll { + XEN_GUEST_HANDLE(evtchn_port_t) ports; + unsigned int nr_ports; + uint64_t timeout; +}; +typedef struct sched_poll sched_poll_t; +DEFINE_XEN_GUEST_HANDLE(sched_poll_t); + +struct sched_remote_shutdown { + domid_t domain_id; /* Remote domain ID */ + unsigned int reason; /* SHUTDOWN_* => enum sched_shutdown_reason */ +}; +typedef struct sched_remote_shutdown sched_remote_shutdown_t; +DEFINE_XEN_GUEST_HANDLE(sched_remote_shutdown_t); + +struct sched_watchdog { + uint32_t id; /* watchdog ID */ + uint32_t timeout; /* timeout */ +}; +typedef struct sched_watchdog sched_watchdog_t; +DEFINE_XEN_GUEST_HANDLE(sched_watchdog_t); + +/* + * 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. + */ +/* ` enum sched_shutdown_reason { */ +#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. */ +#define SHUTDOWN_watchdog 4 /* Restart because watchdog time expired. */ +#define SHUTDOWN_MAX 4 /* Maximum valid shutdown reason. */ +/* ` } */ + +#endif /* __XEN_PUBLIC_SCHED_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/xen-compat.h b/include/xen/xen-compat.h new file mode 100644 index 0000000..3eb80a0 --- /dev/null +++ b/include/xen/xen-compat.h @@ -0,0 +1,44 @@ +/****************************************************************************** + * xen-compat.h + * + * Guest OS interface to Xen. Compatibility layer. + * + * 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) 2006, Christian Limpach + */ + +#ifndef __XEN_PUBLIC_XEN_COMPAT_H__ +#define __XEN_PUBLIC_XEN_COMPAT_H__ + +#define __XEN_LATEST_INTERFACE_VERSION__ 0x00040400 + +#if defined(__XEN__) || defined(__XEN_TOOLS__) +/* Xen is built with matching headers and implements the latest interface. */ +#define __XEN_INTERFACE_VERSION__ __XEN_LATEST_INTERFACE_VERSION__ +#elif !defined(__XEN_INTERFACE_VERSION__) +/* Guests which do not specify a version get the legacy interface. */ +#define __XEN_INTERFACE_VERSION__ 0x00000000 +#endif + +#if __XEN_INTERFACE_VERSION__ > __XEN_LATEST_INTERFACE_VERSION__ +#error "These header files do not support the requested interface version." +#endif + +#endif /* __XEN_PUBLIC_XEN_COMPAT_H__ */ diff --git a/include/xen/xen.h b/include/xen/xen.h new file mode 100644 index 0000000..a6a2092 --- /dev/null +++ b/include/xen/xen.h @@ -0,0 +1,899 @@ +/****************************************************************************** + * xen.h + * + * Guest OS interface to Xen. + * + * 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_XEN_H__ +#define __XEN_PUBLIC_XEN_H__ + +#include "xen-compat.h" + +#if defined(__i386__) || defined(__x86_64__) +#include "arch-x86/xen.h" +#elif defined(__arm__) || defined (__aarch64__) +#include "arch-arm.h" +#else +#error "Unsupported architecture" +#endif + +#ifndef __ASSEMBLY__ +/* Guest handles for primitive C types. */ +DEFINE_XEN_GUEST_HANDLE(char); +__DEFINE_XEN_GUEST_HANDLE(uchar, unsigned char); +DEFINE_XEN_GUEST_HANDLE(int); +__DEFINE_XEN_GUEST_HANDLE(uint, unsigned int); +#if __XEN_INTERFACE_VERSION__ < 0x00040300 +DEFINE_XEN_GUEST_HANDLE(long); +__DEFINE_XEN_GUEST_HANDLE(ulong, unsigned long); +#endif +DEFINE_XEN_GUEST_HANDLE(void); + +DEFINE_XEN_GUEST_HANDLE(uint64_t); +DEFINE_XEN_GUEST_HANDLE(xen_pfn_t); +DEFINE_XEN_GUEST_HANDLE(xen_ulong_t); +#endif + +/* + * HYPERCALLS + */ + +/* `incontents 100 hcalls List of hypercalls + * ` enum hypercall_num { // __HYPERVISOR_* => HYPERVISOR_*() + */ + +#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_compat 6 /* compat since 0x00030101 */ +#define __HYPERVISOR_platform_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 /* compat since 0x00030202 */ +#define __HYPERVISOR_xen_version 17 +#define __HYPERVISOR_console_io 18 +#define __HYPERVISOR_physdev_op_compat 19 /* compat since 0x00030202 */ +#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_xsm_op 27 +#define __HYPERVISOR_nmi_op 28 +#define __HYPERVISOR_sched_op 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 +#define __HYPERVISOR_sysctl 35 +#define __HYPERVISOR_domctl 36 +#define __HYPERVISOR_kexec_op 37 +#define __HYPERVISOR_tmem_op 38 +#define __HYPERVISOR_xc_reserved_op 39 /* reserved for XenClient */ + +/* Architecture-specific hypercall definitions. */ +#define __HYPERVISOR_arch_0 48 +#define __HYPERVISOR_arch_1 49 +#define __HYPERVISOR_arch_2 50 +#define __HYPERVISOR_arch_3 51 +#define __HYPERVISOR_arch_4 52 +#define __HYPERVISOR_arch_5 53 +#define __HYPERVISOR_arch_6 54 +#define __HYPERVISOR_arch_7 55 + +/* ` } */ + +/* + * HYPERCALL COMPATIBILITY. + */ + +/* New sched_op hypercall introduced in 0x00030101. */ +#if __XEN_INTERFACE_VERSION__ < 0x00030101 +#undef __HYPERVISOR_sched_op +#define __HYPERVISOR_sched_op __HYPERVISOR_sched_op_compat +#endif + +/* New event-channel and physdev hypercalls introduced in 0x00030202. */ +#if __XEN_INTERFACE_VERSION__ < 0x00030202 +#undef __HYPERVISOR_event_channel_op +#define __HYPERVISOR_event_channel_op __HYPERVISOR_event_channel_op_compat +#undef __HYPERVISOR_physdev_op +#define __HYPERVISOR_physdev_op __HYPERVISOR_physdev_op_compat +#endif + +/* New platform_op hypercall introduced in 0x00030204. */ +#if __XEN_INTERFACE_VERSION__ < 0x00030204 +#define __HYPERVISOR_dom0_op __HYPERVISOR_platform_op +#endif + +/* + * VIRTUAL INTERRUPTS + * + * Virtual interrupts that a guest OS may receive from Xen. + * + * In the side comments, 'V.' denotes a per-VCPU VIRQ while 'G.' denotes a + * global VIRQ. The former can be bound once per VCPU and cannot be re-bound. + * The latter can be allocated only once per guest: they must initially be + * allocated to VCPU0 but can subsequently be re-bound. + */ +/* ` enum virq { */ +#define VIRQ_TIMER 0 /* V. Timebase update, and/or requested timeout. */ +#define VIRQ_DEBUG 1 /* V. Request guest to dump debug info. */ +#define VIRQ_CONSOLE 2 /* G. (DOM0) Bytes received on emergency console. */ +#define VIRQ_DOM_EXC 3 /* G. (DOM0) Exceptional event for some domain. */ +#define VIRQ_TBUF 4 /* G. (DOM0) Trace buffer has records available. */ +#define VIRQ_DEBUGGER 6 /* G. (DOM0) A domain has paused for debugging. */ +#define VIRQ_XENOPROF 7 /* V. XenOprofile interrupt: new sample available */ +#define VIRQ_CON_RING 8 /* G. (DOM0) Bytes received on console */ +#define VIRQ_PCPU_STATE 9 /* G. (DOM0) PCPU state changed */ +#define VIRQ_MEM_EVENT 10 /* G. (DOM0) A memory event has occured */ +#define VIRQ_XC_RESERVED 11 /* G. Reserved for XenClient */ +#define VIRQ_ENOMEM 12 /* G. (DOM0) Low on heap memory */ + +/* Architecture-specific VIRQ definitions. */ +#define VIRQ_ARCH_0 16 +#define VIRQ_ARCH_1 17 +#define VIRQ_ARCH_2 18 +#define VIRQ_ARCH_3 19 +#define VIRQ_ARCH_4 20 +#define VIRQ_ARCH_5 21 +#define VIRQ_ARCH_6 22 +#define VIRQ_ARCH_7 23 +/* ` } */ + +#define NR_VIRQS 24 + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_mmu_update(const struct mmu_update reqs[], + * ` unsigned count, unsigned *done_out, + * ` unsigned foreigndom) + * ` + * @reqs is an array of mmu_update_t structures ((ptr, val) pairs). + * @count is the length of the above array. + * @pdone is an output parameter indicating number of completed operations + * @foreigndom[15:0]: FD, the expected owner of data pages referenced in this + * hypercall invocation. Can be DOMID_SELF. + * @foreigndom[31:16]: PFD, the expected owner of pagetable pages referenced + * in this hypercall invocation. The value of this field + * (x) encodes the PFD as follows: + * x == 0 => PFD == DOMID_SELF + * x != 0 => PFD == x - 1 + * + * Sub-commands: ptr[1:0] specifies the appropriate MMU_* command. + * ------------- + * ptr[1:0] == MMU_NORMAL_PT_UPDATE: + * Updates an entry in a page table belonging to PFD. If updating an L1 table, + * and the new table entry is valid/present, the mapped frame must belong to + * FD. 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. + * + * There also certain implicit requirements when using this hypercall. The + * pages that make up a pagetable must be mapped read-only in the guest. + * This prevents uncontrolled guest updates to the pagetable. Xen strictly + * enforces this, and will disallow any pagetable update which will end up + * mapping pagetable page RW, and will disallow using any writable page as a + * pagetable. In practice it means that when constructing a page table for a + * process, thread, etc, we MUST be very dilligient in following these rules: + * 1). Start with top-level page (PGD or in Xen language: L4). Fill out + * the entries. + * 2). Keep on going, filling out the upper (PUD or L3), and middle (PMD + * or L2). + * 3). Start filling out the PTE table (L1) with the PTE entries. Once + * done, make sure to set each of those entries to RO (so writeable bit + * is unset). Once that has been completed, set the PMD (L2) for this + * PTE table as RO. + * 4). When completed with all of the PMD (L2) entries, and all of them have + * been set to RO, make sure to set RO the PUD (L3). Do the same + * operation on PGD (L4) pagetable entries that have a PUD (L3) entry. + * 5). Now before you can use those pages (so setting the cr3), you MUST also + * pin them so that the hypervisor can verify the entries. This is done + * via the HYPERVISOR_mmuext_op(MMUEXT_PIN_L4_TABLE, guest physical frame + * number of the PGD (L4)). And this point the HYPERVISOR_mmuext_op( + * MMUEXT_NEW_BASEPTR, guest physical frame number of the PGD (L4)) can be + * issued. + * For 32-bit guests, the L4 is not used (as there is less pagetables), so + * instead use L3. + * At this point the pagetables can be modified using the MMU_NORMAL_PT_UPDATE + * hypercall. Also if so desired the OS can also try to write to the PTE + * and be trapped by the hypervisor (as the PTE entry is RO). + * + * To deallocate the pages, the operations are the reverse of the steps + * mentioned above. The argument is MMUEXT_UNPIN_TABLE for all levels and the + * pagetable MUST not be in use (meaning that the cr3 is not set to it). + * + * 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. + * + * ptr[1:0] == MMU_PT_UPDATE_PRESERVE_AD: + * As MMU_NORMAL_PT_UPDATE above, but A/D bits currently in the PTE are ORed + * with those in @val. + * + * @val is usually the machine frame number along with some attributes. + * The attributes by default follow the architecture defined bits. Meaning that + * if this is a X86_64 machine and four page table layout is used, the layout + * of val is: + * - 63 if set means No execute (NX) + * - 46-13 the machine frame number + * - 12 available for guest + * - 11 available for guest + * - 10 available for guest + * - 9 available for guest + * - 8 global + * - 7 PAT (PSE is disabled, must use hypercall to make 4MB or 2MB pages) + * - 6 dirty + * - 5 accessed + * - 4 page cached disabled + * - 3 page write through + * - 2 userspace accessible + * - 1 writeable + * - 0 present + * + * The one bits that does not fit with the default layout is the PAGE_PSE + * also called PAGE_PAT). The MMUEXT_[UN]MARK_SUPER arguments to the + * HYPERVISOR_mmuext_op serve as mechanism to set a pagetable to be 4MB + * (or 2MB) instead of using the PAGE_PSE bit. + * + * The reason that the PAGE_PSE (bit 7) is not being utilized is due to Xen + * using it as the Page Attribute Table (PAT) bit - for details on it please + * refer to Intel SDM 10.12. The PAT allows to set the caching attributes of + * pages instead of using MTRRs. + * + * The PAT MSR is as follows (it is a 64-bit value, each entry is 8 bits): + * PAT4 PAT0 + * +-----+-----+----+----+----+-----+----+----+ + * | UC | UC- | WC | WB | UC | UC- | WC | WB | <= Linux + * +-----+-----+----+----+----+-----+----+----+ + * | UC | UC- | WT | WB | UC | UC- | WT | WB | <= BIOS (default when machine boots) + * +-----+-----+----+----+----+-----+----+----+ + * | rsv | rsv | WP | WC | UC | UC- | WT | WB | <= Xen + * +-----+-----+----+----+----+-----+----+----+ + * + * The lookup of this index table translates to looking up + * Bit 7, Bit 4, and Bit 3 of val entry: + * + * PAT/PSE (bit 7) ... PCD (bit 4) .. PWT (bit 3). + * + * If all bits are off, then we are using PAT0. If bit 3 turned on, + * then we are using PAT1, if bit 3 and bit 4, then PAT2.. + * + * As you can see, the Linux PAT1 translates to PAT4 under Xen. Which means + * that if a guest that follows Linux's PAT setup and would like to set Write + * Combined on pages it MUST use PAT4 entry. Meaning that Bit 7 (PAGE_PAT) is + * set. For example, under Linux it only uses PAT0, PAT1, and PAT2 for the + * caching as: + * + * WB = none (so PAT0) + * WC = PWT (bit 3 on) + * UC = PWT | PCD (bit 3 and 4 are on). + * + * To make it work with Xen, it needs to translate the WC bit as so: + * + * PWT (so bit 3 on) --> PAT (so bit 7 is on) and clear bit 3 + * + * And to translate back it would: + * + * PAT (bit 7 on) --> PWT (bit 3 on) and clear bit 7. + */ +#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 */ +#define MMU_PT_UPDATE_PRESERVE_AD 2 /* atomically: *ptr = val | (*ptr&(A|D)) */ + +/* + * MMU EXTENDED OPERATIONS + * + * ` enum neg_errnoval + * ` HYPERVISOR_mmuext_op(mmuext_op_t uops[], + * ` unsigned int count, + * ` unsigned int *pdone, + * ` unsigned int foreigndom) + */ +/* 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_FLUSH_CACHE_GLOBAL + * No additional arguments. Writes back and flushes cache contents + * on all CPUs in the system. + * + * cmd: MMUEXT_SET_LDT + * linear_addr: Linear address of LDT base (NB. must be page-aligned). + * nr_ents: Number of entries in LDT. + * + * cmd: MMUEXT_CLEAR_PAGE + * mfn: Machine frame number to be cleared. + * + * cmd: MMUEXT_COPY_PAGE + * mfn: Machine frame number of the destination page. + * src_mfn: Machine frame number of the source page. + * + * cmd: MMUEXT_[UN]MARK_SUPER + * mfn: Machine frame number of head of superpage to be [un]marked. + */ +/* ` enum mmuext_cmd { */ +#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 +#define MMUEXT_CLEAR_PAGE 16 +#define MMUEXT_COPY_PAGE 17 +#define MMUEXT_FLUSH_CACHE_GLOBAL 18 +#define MMUEXT_MARK_SUPER 19 +#define MMUEXT_UNMARK_SUPER 20 +/* ` } */ + +#ifndef __ASSEMBLY__ +struct mmuext_op { + unsigned int cmd; /* => enum mmuext_cmd */ + union { + /* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR + * CLEAR_PAGE, COPY_PAGE, [UN]MARK_SUPER */ + xen_pfn_t mfn; + /* INVLPG_LOCAL, INVLPG_ALL, SET_LDT */ + unsigned long linear_addr; + } arg1; + union { + /* SET_LDT */ + unsigned int nr_ents; + /* TLB_FLUSH_MULTI, INVLPG_MULTI */ +#if __XEN_INTERFACE_VERSION__ >= 0x00030205 + XEN_GUEST_HANDLE(const_void) vcpumask; +#else + const void *vcpumask; +#endif + /* COPY_PAGE */ + xen_pfn_t src_mfn; + } arg2; +}; +typedef struct mmuext_op mmuext_op_t; +DEFINE_XEN_GUEST_HANDLE(mmuext_op_t); +#endif + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_update_va_mapping(unsigned long va, u64 val, + * ` enum uvm_flags flags) + * ` + * ` enum neg_errnoval + * ` HYPERVISOR_update_va_mapping_otherdomain(unsigned long va, u64 val, + * ` enum uvm_flags flags, + * ` domid_t domid) + * ` + * ` @va: The virtual address whose mapping we want to change + * ` @val: The new page table entry, must contain a machine address + * ` @flags: Control TLB flushes + */ +/* 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. */ +/* ` enum uvm_flags { */ +#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 + +/* x86/32 guests: simulate full 4GB segment limits. */ +#define VMASST_TYPE_4gb_segments 0 + +/* x86/32 guests: trap (vector 15) whenever above vmassist is used. */ +#define VMASST_TYPE_4gb_segments_notify 1 + +/* + * x86 guests: support writes to bottom-level PTEs. + * NB1. Page-directory entries cannot be written. + * NB2. Guest must continue to remove all writable mappings of PTEs. + */ +#define VMASST_TYPE_writable_pagetables 2 + +/* x86/PAE guests: support PDPTs above 4GB. */ +#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) + +/* + * DOMID_COW is used as the owner of sharable pages */ +#define DOMID_COW (0x7FF3U) + +/* DOMID_INVALID is used to identify pages with unknown owner. */ +#define DOMID_INVALID (0x7FF4U) + +/* Idle domain. */ +#define DOMID_IDLE (0x7FFFU) + +/* + * 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. */ +}; +typedef struct mmu_update mmu_update_t; +DEFINE_XEN_GUEST_HANDLE(mmu_update_t); + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_multicall(multicall_entry_t call_list[], + * ` uint32_t nr_calls); + * + * NB. The fields are logically the natural register size for this + * architecture. In cases where xen_ulong_t is larger than this then + * any unused bits in the upper portion must be zero. + */ +struct multicall_entry { + xen_ulong_t op, result; + xen_ulong_t args[6]; +}; +typedef struct multicall_entry multicall_entry_t; +DEFINE_XEN_GUEST_HANDLE(multicall_entry_t); + +#if __XEN_INTERFACE_VERSION__ < 0x00040400 +/* + * Event channel endpoints per domain (when using the 2-level ABI): + * 1024 if a long is 32 bits; 4096 if a long is 64 bits. + */ +#define NR_EVENT_CHANNELS EVTCHN_2L_NR_CHANNELS +#endif + +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) >> 32) + * 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 */ +typedef struct vcpu_time_info vcpu_time_info_t; + +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; +#ifdef XEN_HAVE_PV_UPCALL_MASK + uint8_t evtchn_upcall_mask; +#else /* XEN_HAVE_PV_UPCALL_MASK */ + uint8_t pad0; +#endif /* XEN_HAVE_PV_UPCALL_MASK */ + xen_ulong_t evtchn_pending_sel; + struct arch_vcpu_info arch; + struct vcpu_time_info time; +}; /* 64 bytes (x86) */ +#ifndef __XEN__ +typedef struct vcpu_info vcpu_info_t; +#endif + +/* + * `incontents 200 startofday_shared Start-of-day shared data structure + * Xen/kernel shared data -- pointer provided in start_info. + * + * This structure is defined to be both smaller than a page, and the + * only data on the shared page, but may vary in actual size even within + * compatible Xen versions; guests should not rely on the size + * of this structure remaining constant. + */ +struct shared_info { + struct vcpu_info vcpu_info[XEN_LEGACY_MAX_VCPUS]; + + /* + * 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. + */ + xen_ulong_t evtchn_pending[sizeof(xen_ulong_t) * 8]; + xen_ulong_t evtchn_mask[sizeof(xen_ulong_t) * 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; + +}; +#ifndef __XEN__ +typedef struct shared_info shared_info_t; +#endif + +/* + * `incontents 200 startofday Start-of-day memory layout + * + * 1. The domain is started within contiguous virtual-memory region. + * 2. The contiguous region ends on an aligned 4MB boundary. + * 3. 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] + * (unless relocated due to XEN_ELFNOTE_INIT_P2M) + * d. start_info_t structure [register ESI (x86)] + * e. bootstrap page tables [pt_base and CR3 (x86)] + * f. bootstrap stack [register ESP (x86)] + * 4. Bootstrap elements are packed together, but each is 4kB-aligned. + * 5. The initial ram disk may be omitted. + * 6. 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. + * 7. All bootstrap elements are mapped read-writable for the guest OS. The + * only exception is the bootstrap page table, which is mapped read-only. + * 8. 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. + * + * Note: Prior to 25833:bb85bbccb1c9. ("x86/32-on-64 adjust Dom0 initial page + * table layout") a bug caused the pt_base (3.e above) and cr3 to not point + * to the start of the guest page tables (it was offset by two pages). + * This only manifested itself on 32-on-64 dom0 kernels and not 32-on-64 domU + * or 64-bit kernels of any colour. The page tables for a 32-on-64 dom0 got + * allocated in the order: 'first L1','first L2', 'first L3', so the offset + * to the page table base is by two pages back. The initial domain if it is + * 32-bit and runs under a 64-bit hypervisor should _NOT_ use two of the + * pages preceding pt_base and mark them as reserved/unused. + */ +#ifdef XEN_HAVE_PV_GUEST_ENTRY +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. */ + xen_pfn_t store_mfn; /* MACHINE page number of shared page. */ + uint32_t store_evtchn; /* Event channel for store communication. */ + union { + struct { + xen_pfn_t 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 */ + /* (PFN of pre-loaded module if */ + /* SIF_MOD_START_PFN set in flags). */ + unsigned long mod_len; /* Size (bytes) of pre-loaded module. */ +#define MAX_GUEST_CMDLINE 1024 + int8_t cmd_line[MAX_GUEST_CMDLINE]; + /* The pfn range here covers both page table and p->m table frames. */ + unsigned long first_p2m_pfn;/* 1st pfn forming initial P->M table. */ + unsigned long nr_p2m_frames;/* # of pfns forming initial P->M table. */ +}; +typedef struct start_info start_info_t; + +/* New console union for dom0 introduced in 0x00030203. */ +#if __XEN_INTERFACE_VERSION__ < 0x00030203 +#define console_mfn console.domU.mfn +#define console_evtchn console.domU.evtchn +#endif +#endif /* XEN_HAVE_PV_GUEST_ENTRY */ + +/* 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? */ +#define SIF_MULTIBOOT_MOD (1<<2) /* Is mod_start a multiboot module? */ +#define SIF_MOD_START_PFN (1<<3) /* Is mod_start a PFN? */ +#define SIF_PM_MASK (0xFF<<8) /* reserve 1 byte for xen-pm options */ + +/* + * A multiboot module is a package containing modules very similar to a + * multiboot module array. The only differences are: + * - the array of module descriptors is by convention simply at the beginning + * of the multiboot module, + * - addresses in the module descriptors are based on the beginning of the + * multiboot module, + * - the number of modules is determined by a termination descriptor that has + * mod_start == 0. + * + * This permits to both build it statically and reference it in a configuration + * file, and let the PV guest easily rebase the addresses to virtual addresses + * and at the same time count the number of modules. + */ +struct xen_multiboot_mod_list +{ + /* Address of first byte of the module */ + uint32_t mod_start; + /* Address of last byte of the module (inclusive) */ + uint32_t mod_end; + /* Address of zero-terminated command line */ + uint32_t cmdline; + /* Unused, must be zero */ + uint32_t pad; +}; +/* + * `incontents 200 startofday_dom0_console Dom0_console + * + * The console structure in start_info.console.dom0 + * + * This structure includes a variety of information required to + * have a working VGA/VESA console. + */ +typedef struct dom0_vga_console_info { + uint8_t video_type; /* DOM0_VGA_CONSOLE_??? */ +#define XEN_VGATYPE_TEXT_MODE_3 0x03 +#define XEN_VGATYPE_VESA_LFB 0x23 +#define XEN_VGATYPE_EFI_LFB 0x70 + + union { + struct { + /* Font height, in pixels. */ + uint16_t font_height; + /* Cursor location (column, row). */ + uint16_t cursor_x, cursor_y; + /* Number of rows and columns (dimensions in characters). */ + uint16_t rows, columns; + } text_mode_3; + + struct { + /* Width and height, in pixels. */ + uint16_t width, height; + /* Bytes per scan line. */ + uint16_t bytes_per_line; + /* Bits per pixel. */ + uint16_t bits_per_pixel; + /* LFB physical address, and size (in units of 64kB). */ + uint32_t lfb_base; + uint32_t lfb_size; + /* RGB mask offsets and sizes, as defined by VBE 1.2+ */ + uint8_t red_pos, red_size; + uint8_t green_pos, green_size; + uint8_t blue_pos, blue_size; + uint8_t rsvd_pos, rsvd_size; +#if __XEN_INTERFACE_VERSION__ >= 0x00030206 + /* VESA capabilities (offset 0xa, VESA command 0x4f00). */ + uint32_t gbl_caps; + /* Mode attributes (offset 0x0, VESA command 0x4f01). */ + uint16_t mode_attrs; +#endif + } vesa_lfb; + } u; +} dom0_vga_console_info_t; +#define xen_vga_console_info dom0_vga_console_info +#define xen_vga_console_info_t dom0_vga_console_info_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) + +__DEFINE_XEN_GUEST_HANDLE(uint8, uint8_t); +__DEFINE_XEN_GUEST_HANDLE(uint16, uint16_t); +__DEFINE_XEN_GUEST_HANDLE(uint32, uint32_t); +__DEFINE_XEN_GUEST_HANDLE(uint64, uint64_t); + +#else /* __ASSEMBLY__ */ + +/* In assembly code we cannot use C numeric constant suffixes. */ +#define mk_unsigned_long(x) x + +#endif /* !__ASSEMBLY__ */ + +/* Default definitions for macros used by domctl/sysctl. */ +#if defined(__XEN__) || defined(__XEN_TOOLS__) + +#ifndef uint64_aligned_t +#define uint64_aligned_t uint64_t +#endif +#ifndef XEN_GUEST_HANDLE_64 +#define XEN_GUEST_HANDLE_64(name) XEN_GUEST_HANDLE(name) +#endif + +#ifndef __ASSEMBLY__ +struct xenctl_bitmap { + XEN_GUEST_HANDLE_64(uint8) bitmap; + uint32_t nr_bits; +}; +#endif + +#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */ + +#endif /* __XEN_PUBLIC_XEN_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ -- 2.6.6
Locations
Projects
Search
Status Monitor
Help
OpenBuildService.org
Documentation
API Documentation
Code of Conduct
Contact
Support
@OBShq
Terms
openSUSE Build Service is sponsored by
The Open Build Service is an
openSUSE project
.
Sign Up
Log In
Places
Places
All Projects
Status Monitor
