From: Paul Durrant Date: Wed, 25 Sep 2013 10:18:42 +0000 (+0100) Subject: Switch to Xen 3.4 headers for backwards compatibility X-Git-Url: http://xenbits.xensource.com/gitweb?a=commitdiff_plain;h=c2a60d437b42f2349361629f15275e4fabdcc22e;p=people%2Fpauldu%2Fxenbus.git Switch to Xen 3.4 headers for backwards compatibility Signed-off-by: Paul Durrant --- diff --git a/get_xen_headers.py b/get_xen_headers.py new file mode 100644 index 0000000..ba3b44e --- /dev/null +++ b/get_xen_headers.py @@ -0,0 +1,72 @@ +#!python -u + +import os, sys +import shutil +import subprocess +import re + +def shell(command): + print(command) + sys.stdout.flush() + + pipe = os.popen(' '.join(command), 'r', 1) + + for line in pipe: + print(line.rstrip()) + + return pipe.close() + +def get_repo(url): + shell(['rm', '-rf', 'working']) + shell(['git', 'clone', '--no-checkout', url, 'working']) + +def get_branch(tag): + cwd = os.getcwd() + os.chdir('working') + shell(['git', 'checkout', '-b', tag]) + os.chdir(cwd) + +def copy_file(src_dir, dst_dir, name): + try: + os.makedirs('include\\xen\\%s' % dst_dir) + except OSError: + None + + src = open('working\\xen\\include\\%s\\%s' % (src_dir, name), 'r') + dst = open('include\\xen\\%s\\%s' % (dst_dir, name), 'w') + + print(name) + + for line in src: + line = re.sub(' unsigned long', ' ULONG_PTR', line) + line = re.sub('\(unsigned long', '(ULONG_PTR', line) + line = re.sub(' long', ' LONG_PTR', line) + line = re.sub('\(long', '(LONG_PTR', line) + dst.write(line) + + dst.close() + src.close() + +if __name__ == '__main__': + get_repo('git://xenbits.xen.org/xen.git') + get_branch(sys.argv[1]) + + copy_file('public', '.', 'xen.h') + + copy_file('public', '.', 'xen-compat.h') + copy_file('public', '.', 'trace.h') + copy_file('public', '.', 'memory.h') + copy_file('public', '.', 'sched.h') + copy_file('public', '.', 'event_channel.h') + copy_file('public', '.', 'grant_table.h') + + copy_file('xen', '.', 'errno.h') + + copy_file('public\\arch-x86', 'arch-x86', 'xen.h') + copy_file('public\\arch-x86', 'arch-x86', 'xen-x86_32.h') + copy_file('public\\arch-x86', 'arch-x86', 'xen-x86_64.h') + + copy_file('public\\hvm', 'hvm', 'hvm_op.h') + copy_file('public\\hvm', 'hvm', 'params.h') + + copy_file('public\\io', 'io', 'xs_wire.h') diff --git a/include/xen/arch-x86/xen-x86_32.h b/include/xen/arch-x86/xen-x86_32.h index 5c125fb..c6ba3b9 100644 --- a/include/xen/arch-x86/xen-x86_32.h +++ b/include/xen/arch-x86/xen-x86_32.h @@ -1,180 +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 (arguments 1-5) - * 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) - */ - -#if __XEN_INTERFACE_VERSION__ < 0x00030203 -/* - * Legacy hypercall interface: - * As above, except the entry sequence to the hypervisor is: - * mov $hypercall-number*32,%eax ; int $0x82 - */ -#define TRAP_INSTR "int $0x82" -#endif - -/* - * 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 ((ULONG_PTR *)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 { - ULONG_PTR cr2; - ULONG_PTR pad[5]; /* sizeof(vcpu_info_t) == 64 */ -}; -typedef struct arch_vcpu_info arch_vcpu_info_t; - -struct xen_callback { - ULONG_PTR cs; - ULONG_PTR eip; -}; -typedef struct xen_callback xen_callback_t; - -#endif /* !__ASSEMBLY__ */ - -#endif /* __XEN_PUBLIC_ARCH_X86_XEN_X86_32_H__ */ - -/* - * Local variables: - * mode: C - * c-set-style: "BSD" - * c-basic-offset: 4 - * tab-width: 4 - * indent-tabs-mode: nil - * End: - */ +/****************************************************************************** + * 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 ((ULONG_PTR *)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 { + ULONG_PTR cr2; + ULONG_PTR pad[5]; /* sizeof(vcpu_info_t) == 64 */ +}; +typedef struct arch_vcpu_info arch_vcpu_info_t; + +struct xen_callback { + ULONG_PTR cs; + ULONG_PTR 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 index 1821e3a..76e1273 100644 --- a/include/xen/arch-x86/xen-x86_64.h +++ b/include/xen/arch-x86/xen-x86_64.h @@ -1,212 +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 (arguments 1-5) - * 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) - */ - -#if __XEN_INTERFACE_VERSION__ < 0x00030203 -/* - * Legacy hypercall interface: - * As above, except the entry sequence to the hypervisor is: - * mov $hypercall-number*32,%eax ; syscall - * Clobbered: %rcx, %r11, argument registers (as above) - */ -#define TRAP_INSTR "syscall" -#endif - -/* - * 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 ((ULONG_PTR *)HYPERVISOR_VIRT_START) -#endif - -/* - * int HYPERVISOR_set_segment_base(unsigned int which, ULONG_PTR 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) ((ULONG_PTR)(pfn) << 12) -#define xen_cr3_to_pfn(cr3) ((ULONG_PTR)(cr3) >> 12) - -struct arch_vcpu_info { - ULONG_PTR cr2; - ULONG_PTR pad; /* sizeof(vcpu_info_t) == 64 */ -}; -typedef struct arch_vcpu_info arch_vcpu_info_t; - -typedef ULONG_PTR xen_callback_t; - -#endif /* !__ASSEMBLY__ */ - -#endif /* __XEN_PUBLIC_ARCH_X86_XEN_X86_64_H__ */ - -/* - * Local variables: - * mode: C - * c-set-style: "BSD" - * c-basic-offset: 4 - * tab-width: 4 - * indent-tabs-mode: nil - * End: - */ +/****************************************************************************** + * 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 ((ULONG_PTR *)HYPERVISOR_VIRT_START) +#endif + +/* + * int HYPERVISOR_set_segment_base(unsigned int which, ULONG_PTR 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) ((ULONG_PTR)(pfn) << 12) +#define xen_cr3_to_pfn(cr3) ((ULONG_PTR)(cr3) >> 12) + +struct arch_vcpu_info { + ULONG_PTR cr2; + ULONG_PTR pad; /* sizeof(vcpu_info_t) == 64 */ +}; +typedef struct arch_vcpu_info arch_vcpu_info_t; + +typedef ULONG_PTR 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 index 72eb853..2da04b8 100644 --- a/include/xen/arch-x86/xen.h +++ b/include/xen/arch-x86/xen.h @@ -1,201 +1,264 @@ -/****************************************************************************** - * 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 - -#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 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 ULONG_PTR xen_pfn_t; -#define PRI_xen_pfn "lx" -#endif - -/* - * SEGMENT DESCRIPTOR TABLES - */ -/* - * A number of GDT entries are reserved by Xen. These are not situated at the - * start of the GDT because some stupid OSes export hard-coded selector values - * in their ABI. These hard-coded values are always near the start of the GDT, - * so Xen places itself out of the way, at the far end of the GDT. - */ -#define FIRST_RESERVED_GDT_PAGE 14 -#define FIRST_RESERVED_GDT_BYTE (FIRST_RESERVED_GDT_PAGE * 4096) -#define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8) - -/* Maximum number of virtual CPUs in legacy multi-processor guests. */ -#define XEN_LEGACY_MAX_VCPUS 32 - -#ifndef __ASSEMBLY__ - -typedef ULONG_PTR xen_ulong_t; - -/* - * Send an array of these to HYPERVISOR_set_trap_table(). - * 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 */ - ULONG_PTR 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. - */ -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) - ULONG_PTR flags; /* VGCF_* flags */ - struct cpu_user_regs user_regs; /* User-level CPU registers */ - struct trap_info trap_ctxt[256]; /* Virtual IDT */ - ULONG_PTR ldt_base, ldt_ents; /* LDT (linear address, # ents) */ - ULONG_PTR gdt_frames[16], gdt_ents; /* GDT (machine frames, # ents) */ - ULONG_PTR kernel_ss, kernel_sp; /* Virtual TSS (only SS1/SP1) */ - /* NB. User pagetable on x86/64 is placed in ctrlreg[1]. */ - ULONG_PTR ctrlreg[8]; /* CR0-CR7 (control registers) */ - ULONG_PTR debugreg[8]; /* DB0-DB7 (debug registers) */ -#ifdef __i386__ - ULONG_PTR event_callback_cs; /* CS:EIP of event callback */ - ULONG_PTR event_callback_eip; - ULONG_PTR failsafe_callback_cs; /* CS:EIP of failsafe callback */ - ULONG_PTR failsafe_callback_eip; -#else - ULONG_PTR event_callback_eip; - ULONG_PTR failsafe_callback_eip; -#ifdef __XEN__ - union { - ULONG_PTR 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 - ULONG_PTR syscall_callback_eip; -#endif -#endif - ULONG_PTR 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 { - ULONG_PTR 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; - ULONG_PTR nmi_reason; - uint64_t pad[32]; -}; -typedef struct arch_shared_info arch_shared_info_t; - -#endif /* !__ASSEMBLY__ */ - -/* - * Prefix forces emulation of some non-trapping instructions. - * Currently only CPUID. - */ -#ifdef __ASSEMBLY__ -#define XEN_EMULATE_PREFIX .byte 0x0f,0x0b,0x78,0x65,0x6e ; -#define XEN_CPUID XEN_EMULATE_PREFIX cpuid -#else -#define XEN_EMULATE_PREFIX ".byte 0x0f,0x0b,0x78,0x65,0x6e ; " -#define XEN_CPUID XEN_EMULATE_PREFIX "cpuid" -#endif - -#endif /* __XEN_PUBLIC_ARCH_X86_XEN_H__ */ - -/* - * Local variables: - * mode: C - * c-set-style: "BSD" - * c-basic-offset: 4 - * tab-width: 4 - * indent-tabs-mode: nil - * End: - */ +/****************************************************************************** + * 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 ULONG_PTR 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 ULONG_PTR xen_ulong_t; +#define PRI_xen_ulong "lx" + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_stack_switch(ULONG_PTR ss, ULONG_PTR 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 */ + ULONG_PTR 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. + */ +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) + ULONG_PTR flags; /* VGCF_* flags */ + struct cpu_user_regs user_regs; /* User-level CPU registers */ + struct trap_info trap_ctxt[256]; /* Virtual IDT */ + ULONG_PTR ldt_base, ldt_ents; /* LDT (linear address, # ents) */ + ULONG_PTR gdt_frames[16], gdt_ents; /* GDT (machine frames, # ents) */ + ULONG_PTR kernel_ss, kernel_sp; /* Virtual TSS (only SS1/SP1) */ + /* NB. User pagetable on x86/64 is placed in ctrlreg[1]. */ + ULONG_PTR ctrlreg[8]; /* CR0-CR7 (control registers) */ + ULONG_PTR debugreg[8]; /* DB0-DB7 (debug registers) */ +#ifdef __i386__ + ULONG_PTR event_callback_cs; /* CS:EIP of event callback */ + ULONG_PTR event_callback_eip; + ULONG_PTR failsafe_callback_cs; /* CS:EIP of failsafe callback */ + ULONG_PTR failsafe_callback_eip; +#else + ULONG_PTR event_callback_eip; + ULONG_PTR failsafe_callback_eip; +#ifdef __XEN__ + union { + ULONG_PTR 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 + ULONG_PTR syscall_callback_eip; +#endif +#endif + ULONG_PTR 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 { + ULONG_PTR 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; + ULONG_PTR 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, ULONG_PTR value); + * + * ` ULONG_PTR + * ` HYPERVISOR_get_debugreg(int regno); + * For 0<=reg<=7, returns the debug register value. + * For other values of reg, returns ((ULONG_PTR)-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/errno.h b/include/xen/errno.h index 3dccad0..a38b85e 100644 --- a/include/xen/errno.h +++ b/include/xen/errno.h @@ -1,132 +1,137 @@ -#ifndef _I386_ERRNO_H -#define _I386_ERRNO_H - -#define EPERM 1 /* Operation not permitted */ -#define ENOENT 2 /* No such file or directory */ -#define ESRCH 3 /* No such process */ -#define EINTR 4 /* Interrupted system call */ -#define EIO 5 /* I/O error */ -#define ENXIO 6 /* No such device or address */ -#define E2BIG 7 /* Arg list too LONG_PTR */ -#define ENOEXEC 8 /* Exec format error */ -#define EBADF 9 /* Bad file number */ -#define ECHILD 10 /* No child processes */ -#define EAGAIN 11 /* Try again */ -#define ENOMEM 12 /* Out of memory */ -#define EACCES 13 /* Permission denied */ -#define EFAULT 14 /* Bad address */ -#define ENOTBLK 15 /* Block device required */ -#define EBUSY 16 /* Device or resource busy */ -#define EEXIST 17 /* File exists */ -#define EXDEV 18 /* Cross-device link */ -#define ENODEV 19 /* No such device */ -#define ENOTDIR 20 /* Not a directory */ -#define EISDIR 21 /* Is a directory */ -#define EINVAL 22 /* Invalid argument */ -#define ENFILE 23 /* File table overflow */ -#define EMFILE 24 /* Too many open files */ -#define ENOTTY 25 /* Not a typewriter */ -#define ETXTBSY 26 /* Text file busy */ -#define EFBIG 27 /* File too large */ -#define ENOSPC 28 /* No space left on device */ -#define ESPIPE 29 /* Illegal seek */ -#define EROFS 30 /* Read-only file system */ -#define EMLINK 31 /* Too many links */ -#define EPIPE 32 /* Broken pipe */ -#define EDOM 33 /* Math argument out of domain of func */ -#define ERANGE 34 /* Math result not representable */ -#define EDEADLK 35 /* Resource deadlock would occur */ -#define ENAMETOOLONG 36 /* File name too LONG_PTR */ -#define ENOLCK 37 /* No record locks available */ -#define ENOSYS 38 /* Function not implemented */ -#define ENOTEMPTY 39 /* Directory not empty */ -#define ELOOP 40 /* Too many symbolic links encountered */ -#define EWOULDBLOCK EAGAIN /* Operation would block */ -#define ENOMSG 42 /* No message of desired type */ -#define EIDRM 43 /* Identifier removed */ -#define ECHRNG 44 /* Channel number out of range */ -#define EL2NSYNC 45 /* Level 2 not synchronized */ -#define EL3HLT 46 /* Level 3 halted */ -#define EL3RST 47 /* Level 3 reset */ -#define ELNRNG 48 /* Link number out of range */ -#define EUNATCH 49 /* Protocol driver not attached */ -#define ENOCSI 50 /* No CSI structure available */ -#define EL2HLT 51 /* Level 2 halted */ -#define EBADE 52 /* Invalid exchange */ -#define EBADR 53 /* Invalid request descriptor */ -#define EXFULL 54 /* Exchange full */ -#define ENOANO 55 /* No anode */ -#define EBADRQC 56 /* Invalid request code */ -#define EBADSLT 57 /* Invalid slot */ - -#define EDEADLOCK EDEADLK - -#define EBFONT 59 /* Bad font file format */ -#define ENOSTR 60 /* Device not a stream */ -#define ENODATA 61 /* No data available */ -#define ETIME 62 /* Timer expired */ -#define ENOSR 63 /* Out of streams resources */ -#define ENONET 64 /* Machine is not on the network */ -#define ENOPKG 65 /* Package not installed */ -#define EREMOTE 66 /* Object is remote */ -#define ENOLINK 67 /* Link has been severed */ -#define EADV 68 /* Advertise error */ -#define ESRMNT 69 /* Srmount error */ -#define ECOMM 70 /* Communication error on send */ -#define EPROTO 71 /* Protocol error */ -#define EMULTIHOP 72 /* Multihop attempted */ -#define EDOTDOT 73 /* RFS specific error */ -#define EBADMSG 74 /* Not a data message */ -#define EOVERFLOW 75 /* Value too large for defined data type */ -#define ENOTUNIQ 76 /* Name not unique on network */ -#define EBADFD 77 /* File descriptor in bad state */ -#define EREMCHG 78 /* Remote address changed */ -#define ELIBACC 79 /* Can not access a needed shared library */ -#define ELIBBAD 80 /* Accessing a corrupted shared library */ -#define ELIBSCN 81 /* .lib section in a.out corrupted */ -#define ELIBMAX 82 /* Attempting to link in too many shared libraries */ -#define ELIBEXEC 83 /* Cannot exec a shared library directly */ -#define EILSEQ 84 /* Illegal byte sequence */ -#define ERESTART 85 /* Interrupted system call should be restarted */ -#define ESTRPIPE 86 /* Streams pipe error */ -#define EUSERS 87 /* Too many users */ -#define ENOTSOCK 88 /* Socket operation on non-socket */ -#define EDESTADDRREQ 89 /* Destination address required */ -#define EMSGSIZE 90 /* Message too LONG_PTR */ -#define EPROTOTYPE 91 /* Protocol wrong type for socket */ -#define ENOPROTOOPT 92 /* Protocol not available */ -#define EPROTONOSUPPORT 93 /* Protocol not supported */ -#define ESOCKTNOSUPPORT 94 /* Socket type not supported */ -#define EOPNOTSUPP 95 /* Operation not supported on transport endpoint */ -#define EPFNOSUPPORT 96 /* Protocol family not supported */ -#define EAFNOSUPPORT 97 /* Address family not supported by protocol */ -#define EADDRINUSE 98 /* Address already in use */ -#define EADDRNOTAVAIL 99 /* Cannot assign requested address */ -#define ENETDOWN 100 /* Network is down */ -#define ENETUNREACH 101 /* Network is unreachable */ -#define ENETRESET 102 /* Network dropped connection because of reset */ -#define ECONNABORTED 103 /* Software caused connection abort */ -#define ECONNRESET 104 /* Connection reset by peer */ -#define ENOBUFS 105 /* No buffer space available */ -#define EISCONN 106 /* Transport endpoint is already connected */ -#define ENOTCONN 107 /* Transport endpoint is not connected */ -#define ESHUTDOWN 108 /* Cannot send after transport endpoint shutdown */ -#define ETOOMANYREFS 109 /* Too many references: cannot splice */ -#define ETIMEDOUT 110 /* Connection timed out */ -#define ECONNREFUSED 111 /* Connection refused */ -#define EHOSTDOWN 112 /* Host is down */ -#define EHOSTUNREACH 113 /* No route to host */ -#define EALREADY 114 /* Operation already in progress */ -#define EINPROGRESS 115 /* Operation now in progress */ -#define ESTALE 116 /* Stale NFS file handle */ -#define EUCLEAN 117 /* Structure needs cleaning */ -#define ENOTNAM 118 /* Not a XENIX named type file */ -#define ENAVAIL 119 /* No XENIX semaphores available */ -#define EISNAM 120 /* Is a named type file */ -#define EREMOTEIO 121 /* Remote I/O error */ -#define EDQUOT 122 /* Quota exceeded */ - -#define ENOMEDIUM 123 /* No medium found */ -#define EMEDIUMTYPE 124 /* Wrong medium type */ - -#endif +#ifndef _I386_ERRNO_H +#define _I386_ERRNO_H + +/* ` enum neg_errnoval { [ -Efoo for each Efoo in the list below ] } */ +/* ` enum errnoval { */ + +#define EPERM 1 /* Operation not permitted */ +#define ENOENT 2 /* No such file or directory */ +#define ESRCH 3 /* No such process */ +#define EINTR 4 /* Interrupted system call */ +#define EIO 5 /* I/O error */ +#define ENXIO 6 /* No such device or address */ +#define E2BIG 7 /* Arg list too LONG_PTR */ +#define ENOEXEC 8 /* Exec format error */ +#define EBADF 9 /* Bad file number */ +#define ECHILD 10 /* No child processes */ +#define EAGAIN 11 /* Try again */ +#define ENOMEM 12 /* Out of memory */ +#define EACCES 13 /* Permission denied */ +#define EFAULT 14 /* Bad address */ +#define ENOTBLK 15 /* Block device required */ +#define EBUSY 16 /* Device or resource busy */ +#define EEXIST 17 /* File exists */ +#define EXDEV 18 /* Cross-device link */ +#define ENODEV 19 /* No such device */ +#define ENOTDIR 20 /* Not a directory */ +#define EISDIR 21 /* Is a directory */ +#define EINVAL 22 /* Invalid argument */ +#define ENFILE 23 /* File table overflow */ +#define EMFILE 24 /* Too many open files */ +#define ENOTTY 25 /* Not a typewriter */ +#define ETXTBSY 26 /* Text file busy */ +#define EFBIG 27 /* File too large */ +#define ENOSPC 28 /* No space left on device */ +#define ESPIPE 29 /* Illegal seek */ +#define EROFS 30 /* Read-only file system */ +#define EMLINK 31 /* Too many links */ +#define EPIPE 32 /* Broken pipe */ +#define EDOM 33 /* Math argument out of domain of func */ +#define ERANGE 34 /* Math result not representable */ +#define EDEADLK 35 /* Resource deadlock would occur */ +#define ENAMETOOLONG 36 /* File name too LONG_PTR */ +#define ENOLCK 37 /* No record locks available */ +#define ENOSYS 38 /* Function not implemented */ +#define ENOTEMPTY 39 /* Directory not empty */ +#define ELOOP 40 /* Too many symbolic links encountered */ +#define EWOULDBLOCK EAGAIN /* Operation would block */ +#define ENOMSG 42 /* No message of desired type */ +#define EIDRM 43 /* Identifier removed */ +#define ECHRNG 44 /* Channel number out of range */ +#define EL2NSYNC 45 /* Level 2 not synchronized */ +#define EL3HLT 46 /* Level 3 halted */ +#define EL3RST 47 /* Level 3 reset */ +#define ELNRNG 48 /* Link number out of range */ +#define EUNATCH 49 /* Protocol driver not attached */ +#define ENOCSI 50 /* No CSI structure available */ +#define EL2HLT 51 /* Level 2 halted */ +#define EBADE 52 /* Invalid exchange */ +#define EBADR 53 /* Invalid request descriptor */ +#define EXFULL 54 /* Exchange full */ +#define ENOANO 55 /* No anode */ +#define EBADRQC 56 /* Invalid request code */ +#define EBADSLT 57 /* Invalid slot */ + +#define EDEADLOCK EDEADLK + +#define EBFONT 59 /* Bad font file format */ +#define ENOSTR 60 /* Device not a stream */ +#define ENODATA 61 /* No data available */ +#define ETIME 62 /* Timer expired */ +#define ENOSR 63 /* Out of streams resources */ +#define ENONET 64 /* Machine is not on the network */ +#define ENOPKG 65 /* Package not installed */ +#define EREMOTE 66 /* Object is remote */ +#define ENOLINK 67 /* Link has been severed */ +#define EADV 68 /* Advertise error */ +#define ESRMNT 69 /* Srmount error */ +#define ECOMM 70 /* Communication error on send */ +#define EPROTO 71 /* Protocol error */ +#define EMULTIHOP 72 /* Multihop attempted */ +#define EDOTDOT 73 /* RFS specific error */ +#define EBADMSG 74 /* Not a data message */ +#define EOVERFLOW 75 /* Value too large for defined data type */ +#define ENOTUNIQ 76 /* Name not unique on network */ +#define EBADFD 77 /* File descriptor in bad state */ +#define EREMCHG 78 /* Remote address changed */ +#define ELIBACC 79 /* Can not access a needed shared library */ +#define ELIBBAD 80 /* Accessing a corrupted shared library */ +#define ELIBSCN 81 /* .lib section in a.out corrupted */ +#define ELIBMAX 82 /* Attempting to link in too many shared libraries */ +#define ELIBEXEC 83 /* Cannot exec a shared library directly */ +#define EILSEQ 84 /* Illegal byte sequence */ +#define ERESTART 85 /* Interrupted system call should be restarted */ +#define ESTRPIPE 86 /* Streams pipe error */ +#define EUSERS 87 /* Too many users */ +#define ENOTSOCK 88 /* Socket operation on non-socket */ +#define EDESTADDRREQ 89 /* Destination address required */ +#define EMSGSIZE 90 /* Message too LONG_PTR */ +#define EPROTOTYPE 91 /* Protocol wrong type for socket */ +#define ENOPROTOOPT 92 /* Protocol not available */ +#define EPROTONOSUPPORT 93 /* Protocol not supported */ +#define ESOCKTNOSUPPORT 94 /* Socket type not supported */ +#define EOPNOTSUPP 95 /* Operation not supported on transport endpoint */ +#define EPFNOSUPPORT 96 /* Protocol family not supported */ +#define EAFNOSUPPORT 97 /* Address family not supported by protocol */ +#define EADDRINUSE 98 /* Address already in use */ +#define EADDRNOTAVAIL 99 /* Cannot assign requested address */ +#define ENETDOWN 100 /* Network is down */ +#define ENETUNREACH 101 /* Network is unreachable */ +#define ENETRESET 102 /* Network dropped connection because of reset */ +#define ECONNABORTED 103 /* Software caused connection abort */ +#define ECONNRESET 104 /* Connection reset by peer */ +#define ENOBUFS 105 /* No buffer space available */ +#define EISCONN 106 /* Transport endpoint is already connected */ +#define ENOTCONN 107 /* Transport endpoint is not connected */ +#define ESHUTDOWN 108 /* Cannot send after transport endpoint shutdown */ +#define ETOOMANYREFS 109 /* Too many references: cannot splice */ +#define ETIMEDOUT 110 /* Connection timed out */ +#define ECONNREFUSED 111 /* Connection refused */ +#define EHOSTDOWN 112 /* Host is down */ +#define EHOSTUNREACH 113 /* No route to host */ +#define EALREADY 114 /* Operation already in progress */ +#define EINPROGRESS 115 /* Operation now in progress */ +#define ESTALE 116 /* Stale NFS file handle */ +#define EUCLEAN 117 /* Structure needs cleaning */ +#define ENOTNAM 118 /* Not a XENIX named type file */ +#define ENAVAIL 119 /* No XENIX semaphores available */ +#define EISNAM 120 /* Is a named type file */ +#define EREMOTEIO 121 /* Remote I/O error */ +#define EDQUOT 122 /* Quota exceeded */ + +#define ENOMEDIUM 123 /* No medium found */ +#define EMEDIUMTYPE 124 /* Wrong medium type */ + +/* ` } */ + +#endif diff --git a/include/xen/event_channel.h b/include/xen/event_channel.h index 03d4ce7..388f40b 100644 --- a/include/xen/event_channel.h +++ b/include/xen/event_channel.h @@ -1,266 +1,294 @@ -/****************************************************************************** - * 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" - -/* - * Prototype for this hypercall is: - * int event_channel_op(int cmd, void *args) - * @cmd == EVTCHNOP_??? (event-channel operation). - * @args == Operation-specific extra arguments (NULL if none). - */ - -typedef uint32_t evtchn_port_t; -DEFINE_XEN_GUEST_HANDLE(evtchn_port_t); - -/* - * EVTCHNOP_alloc_unbound: Allocate a port in domain and mark as - * accepting interdomain bindings from domain . A fresh port - * is allocated in and returned as . - * NOTES: - * 1. If the caller is unprivileged then must be DOMID_SELF. - * 2. may be DOMID_SELF, allowing loopback connections. - */ -#define EVTCHNOP_alloc_unbound 6 -struct evtchn_alloc_unbound { - /* IN parameters */ - domid_t dom, remote_dom; - /* OUT parameters */ - evtchn_port_t port; -}; -typedef struct evtchn_alloc_unbound evtchn_alloc_unbound_t; - -/* - * EVTCHNOP_bind_interdomain: Construct an interdomain event channel between - * the calling domain and . 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 - * . - * NOTES: - * 2. may be DOMID_SELF, allowing loopback connections. - */ -#define EVTCHNOP_bind_interdomain 0 -struct evtchn_bind_interdomain { - /* IN parameters. */ - domid_t remote_dom; - evtchn_port_t remote_port; - /* OUT parameters. */ - evtchn_port_t local_port; -}; -typedef struct evtchn_bind_interdomain evtchn_bind_interdomain_t; - -/* - * EVTCHNOP_bind_virq: Bind a local event channel to VIRQ 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. - */ -#define EVTCHNOP_bind_virq 1 -struct evtchn_bind_virq { - /* IN parameters. */ - uint32_t 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 PIRQ . - * NOTES: - * 1. A physical IRQ may be bound to at most one event channel per domain. - * 2. Only a sufficiently-privileged domain may bind to a physical IRQ. - */ -#define EVTCHNOP_bind_pirq 2 -struct evtchn_bind_pirq { - /* IN parameters. */ - uint32_t pirq; -#define BIND_PIRQ__WILL_SHARE 1 - uint32_t flags; /* BIND_PIRQ__* */ - /* OUT parameters. */ - evtchn_port_t port; -}; -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. - */ -#define EVTCHNOP_bind_ipi 7 -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 . If the channel is - * interdomain then the remote end is placed in the unbound state - * (EVTCHNSTAT_unbound), awaiting a new connection. - */ -#define EVTCHNOP_close 3 -struct evtchn_close { - /* IN parameters. */ - evtchn_port_t port; -}; -typedef struct evtchn_close evtchn_close_t; - -/* - * EVTCHNOP_send: Send an event to the remote end of the channel whose local - * endpoint is . - */ -#define EVTCHNOP_send 4 -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 . - * NOTES: - * 1. may be specified as DOMID_SELF. - * 2. Only a sufficiently-privileged domain may obtain the status of an event - * channel for which is not DOMID_SELF. - */ -#define EVTCHNOP_status 5 -struct evtchn_status { - /* IN parameters */ - domid_t dom; - evtchn_port_t port; - /* OUT parameters */ -#define EVTCHNSTAT_closed 0 /* Channel is not in use. */ -#define EVTCHNSTAT_unbound 1 /* Channel is waiting interdom connection.*/ -#define EVTCHNSTAT_interdomain 2 /* Channel is connected to remote domain. */ -#define EVTCHNSTAT_pirq 3 /* Channel is bound to a phys IRQ line. */ -#define EVTCHNSTAT_virq 4 /* Channel is bound to a virtual IRQ line */ -#define EVTCHNSTAT_ipi 5 /* Channel is bound to a virtual IPI line */ - uint32_t status; - uint32_t vcpu; /* VCPU to which this channel is bound. */ - union { - struct { - domid_t dom; - } unbound; /* EVTCHNSTAT_unbound */ - struct { - domid_t dom; - evtchn_port_t port; - } interdomain; /* EVTCHNSTAT_interdomain */ - uint32_t pirq; /* EVTCHNSTAT_pirq */ - uint32_t virq; /* EVTCHNSTAT_virq */ - } u; -}; -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). - */ -#define EVTCHNOP_bind_vcpu 8 -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. - */ -#define EVTCHNOP_unmask 9 -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. may be specified as DOMID_SELF. - * 2. Only a sufficiently-privileged domain may specify other than DOMID_SELF. - */ -#define EVTCHNOP_reset 10 -struct evtchn_reset { - /* IN parameters. */ - domid_t dom; -}; -typedef struct evtchn_reset evtchn_reset_t; - -/* - * Argument to event_channel_op_compat() hypercall. Superceded by new - * event_channel_op() hypercall since 0x00030202. - */ -struct evtchn_op { - uint32_t cmd; /* EVTCHNOP_* */ - union { - struct evtchn_alloc_unbound alloc_unbound; - struct evtchn_bind_interdomain bind_interdomain; - struct evtchn_bind_virq bind_virq; - struct evtchn_bind_pirq bind_pirq; - struct evtchn_bind_ipi bind_ipi; - struct evtchn_close close; - struct evtchn_send send; - struct evtchn_status status; - struct evtchn_bind_vcpu bind_vcpu; - struct evtchn_unmask unmask; - } u; -}; -typedef struct evtchn_op evtchn_op_t; -DEFINE_XEN_GUEST_HANDLE(evtchn_op_t); - -#endif /* __XEN_PUBLIC_EVENT_CHANNEL_H__ */ - -/* - * Local variables: - * mode: C - * c-set-style: "BSD" - * c-basic-offset: 4 - * tab-width: 4 - * indent-tabs-mode: nil - * End: - */ +/****************************************************************************** + * 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 +/* ` } */ + +typedef uint32_t evtchn_port_t; +DEFINE_XEN_GUEST_HANDLE(evtchn_port_t); + +/* + * EVTCHNOP_alloc_unbound: Allocate a port in domain and mark as + * accepting interdomain bindings from domain . A fresh port + * is allocated in and returned as . + * NOTES: + * 1. If the caller is unprivileged then must be DOMID_SELF. + * 2. 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 . 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 + * . + * NOTES: + * 1. 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 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 ). + * 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 . 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 . + */ +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 . + * NOTES: + * 1. may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may obtain the status of an event + * channel for which 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. 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; + +/* + * ` 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); + +#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 index c003d5c..75ce949 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -1,597 +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" - -/*********************************** - * GRANT TABLE REPRESENTATION - */ - -/* Some rough guidelines on accessing and updating grant-table entries - * in a concurrency-safe manner. For more information, Linux contains a - * reference implementation for guest OSes (arch/xen/kernel/grant_table.c). - * - * NB. WMB is a no-op on current-generation x86 processors. However, a - * compiler barrier will still be required. - * - * Introducing a valid entry into the grant table: - * 1. Write ent->domid. - * 2. Write ent->frame: - * GTF_permit_access: Frame to which access is permitted. - * GTF_accept_transfer: Pseudo-phys frame slot being filled by new - * frame, or zero if none. - * 3. Write memory barrier (WMB). - * 4. Write ent->flags, inc. valid type. - * - * Invalidating an unused GTF_permit_access entry: - * 1. flags = ent->flags. - * 2. Observe that !(flags & (GTF_reading|GTF_writing)). - * 3. Check result of SMP-safe CMPXCHG(&ent->flags, flags, 0). - * NB. No need for WMB as reuse of entry is control-dependent on success of - * step 3, and all architectures guarantee ordering of ctrl-dep writes. - * - * Invalidating an in-use GTF_permit_access entry: - * This cannot be done directly. Request assistance from the domain controller - * which can set a timeout on the use of a grant entry and take necessary - * action. (NB. This is not yet implemented!). - * - * Invalidating an unused GTF_accept_transfer entry: - * 1. flags = ent->flags. - * 2. Observe that !(flags & GTF_transfer_committed). [*] - * 3. Check result of SMP-safe CMPXCHG(&ent->flags, flags, 0). - * NB. No need for WMB as reuse of entry is control-dependent on success of - * step 3, and all architectures guarantee ordering of ctrl-dep writes. - * [*] If GTF_transfer_committed is set then the grant entry is 'committed'. - * The guest must /not/ modify the grant entry until the address of the - * transferred frame is written. It is safe for the guest to spin waiting - * for this to occur (detect by observing GTF_transfer_completed in - * ent->flags). - * - * Invalidating a committed GTF_accept_transfer entry: - * 1. Wait for (ent->flags & GTF_transfer_completed). - * - * Changing a GTF_permit_access from writable to read-only: - * Use SMP-safe CMPXCHG to set GTF_readonly, while checking !GTF_writing. - * - * Changing a GTF_permit_access from read-only to writable: - * Use SMP-safe bit-setting instruction. - */ - -/* - * 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; - -/* - * 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 - */ - -/* - * Handle to track a mapping created via a grant reference. - */ -typedef uint32_t grant_handle_t; - -/* - * GNTTABOP_map_grant_ref: Map the grant entry (,) for access - * by devices and/or host CPUs. If successful, is a tracking number - * that must be presented later to destroy the mapping(s). On error, - * is a negative status code. - * NOTES: - * 1. If GNTMAP_device_map is specified then 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 . - * 3. Mappings should only be destroyed via GNTTABOP_unmap_grant_ref. If a - * host mapping is destroyed by other means then it is *NOT* guaranteed - * to be accounted to the correct grant reference! - */ -#define GNTTABOP_map_grant_ref 0 -struct gnttab_map_grant_ref { - /* IN parameters. */ - uint64_t host_addr; - uint32_t flags; /* GNTMAP_* */ - grant_ref_t ref; - domid_t dom; - /* OUT parameters. */ - int16_t status; /* GNTST_* */ - grant_handle_t handle; - uint64_t dev_bus_addr; -}; -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 . If or is zero, that - * field is ignored. If non-zero, they must refer to a device/host mapping - * that is tracked by - * NOTES: - * 1. The call may fail in an undefined manner if either mapping is not - * tracked by . - * 3. After executing a batch of unmaps, it is guaranteed that no stale - * mappings will remain in the device or host TLBs. - */ -#define GNTTABOP_unmap_grant_ref 1 -struct gnttab_unmap_grant_ref { - /* IN parameters. */ - uint64_t host_addr; - uint64_t dev_bus_addr; - grant_handle_t handle; - /* OUT parameters. */ - int16_t status; /* GNTST_* */ -}; -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 comprising at least - * pages. The frame addresses are written to the . - * Only addresses are written, even if the table is larger. - * NOTES: - * 1. may be specified as DOMID_SELF. - * 2. Only a sufficiently-privileged domain may specify != DOMID_SELF. - * 3. Xen may not support more than a single grant-table page per domain. - */ -#define GNTTABOP_setup_table 2 -struct gnttab_setup_table { - /* IN parameters. */ - domid_t dom; - uint32_t nr_frames; - /* OUT parameters. */ - int16_t status; /* GNTST_* */ - XEN_GUEST_HANDLE(ulong) frame_list; -}; -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. - */ -#define GNTTABOP_dump_table 3 -struct gnttab_dump_table { - /* IN parameters. */ - domid_t dom; - /* OUT parameters. */ - int16_t status; /* GNTST_* */ -}; -typedef struct gnttab_dump_table gnttab_dump_table_t; -DEFINE_XEN_GUEST_HANDLE(gnttab_dump_table_t); - -/* - * GNTTABOP_transfer_grant_ref: Transfer to a foreign domain. The - * foreign domain has previously registered its interest in the transfer via - * . - * - * Note that, even if the transfer fails, the specified page no LONG_PTRer belongs - * to the calling domain *unless* the error is GNTST_bad_page. - */ -#define GNTTABOP_transfer 4 -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) -#define _GNTCOPY_can_fail (2) -#define GNTCOPY_can_fail (1<<_GNTCOPY_can_fail) - -#define GNTTABOP_copy 5 -typedef 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; -} 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. may be specified as DOMID_SELF. - * 2. Only a sufficiently-privileged domain may specify != DOMID_SELF. - */ -#define GNTTABOP_query_size 6 -struct gnttab_query_size { - /* IN parameters. */ - domid_t dom; - /* OUT parameters. */ - uint32_t nr_frames; - uint32_t max_nr_frames; - int16_t status; /* GNTST_* */ -}; -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 but atomically replace the page table entry with one - * pointing to the machine address under . will be - * redirected to the null entry. - * NOTES: - * 1. The call may fail in an undefined manner if either mapping is not - * tracked by . - * 2. After executing a batch of unmaps, it is guaranteed that no stale - * mappings will remain in the device or host TLBs. - */ -#define GNTTABOP_unmap_and_replace 7 -struct gnttab_unmap_and_replace { - /* IN parameters. */ - uint64_t host_addr; - uint64_t new_addr; - grant_handle_t handle; - /* OUT parameters. */ - int16_t status; /* GNTST_* */ -}; -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. - */ -#define GNTTABOP_set_version 8 -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 . 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. - * specify the size of vector . - * The frame addresses are returned in the . - * Only addresses are returned, even if the table is larger. - * NOTES: - * 1. may be specified as DOMID_SELF. - * 2. Only a sufficiently-privileged domain may specify != DOMID_SELF. - */ -#define GNTTABOP_get_status_frames 9 -struct gnttab_get_status_frames { - /* IN parameters. */ - uint32_t nr_frames; - domid_t dom; - /* OUT parameters. */ - int16_t status; /* GNTST_* */ - 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 . - */ -#define GNTTABOP_get_version 10 -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); - -#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. - */ -#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) /* Could not map at the moment. Retry. */ - -#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", \ - "could not map at the moment, retry" \ -} - -#endif /* __XEN_PUBLIC_GRANT_TABLE_H__ */ - -/* - * Local variables: - * mode: C - * c-set-style: "BSD" - * c-basic-offset: 4 - * tab-width: 4 - * indent-tabs-mode: nil - * End: - */ +/****************************************************************************** + * 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 (,) for access + * by devices and/or host CPUs. If successful, is a tracking number + * that must be presented later to destroy the mapping(s). On error, + * is a negative status code. + * NOTES: + * 1. If GNTMAP_device_map is specified then 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 . + * 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 . If or is zero, that + * field is ignored. If non-zero, they must refer to a device/host mapping + * that is tracked by + * NOTES: + * 1. The call may fail in an undefined manner if either mapping is not + * tracked by . + * 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 comprising at least + * pages. The frame addresses are written to the . + * Only addresses are written, even if the table is larger. + * NOTES: + * 1. may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may specify != 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 to a foreign domain. The + * foreign domain has previously registered its interest in the transfer via + * . + * + * Note that, even if the transfer fails, the specified page no LONG_PTRer 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. may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may specify != 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 but atomically replace the page table entry with one + * pointing to the machine address under . will be + * redirected to the null entry. + * NOTES: + * 1. The call may fail in an undefined manner if either mapping is not + * tracked by . + * 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 . 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. + * specify the size of vector . + * The frame addresses are returned in the . + * Only addresses are returned, even if the table is larger. + * NOTES: + * 1. may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may specify != 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 . + */ +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/hvm/hvm_op.h b/include/xen/hvm/hvm_op.h index 2a597da..7beb701 100644 --- a/include/xen/hvm/hvm_op.h +++ b/include/xen/hvm/hvm_op.h @@ -1,243 +1,275 @@ -/* - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - */ - -#ifndef __XEN_PUBLIC_HVM_HVM_OP_H__ -#define __XEN_PUBLIC_HVM_HVM_OP_H__ - -#include "../xen.h" -#include "../trace.h" - -/* Get/set subcommands: extra argument == pointer to xen_hvm_param struct. */ -#define HVMOP_set_param 0 -#define HVMOP_get_param 1 -struct xen_hvm_param { - domid_t domid; /* IN */ - uint32_t index; /* IN */ - uint64_t value; /* IN/OUT */ -}; -typedef struct xen_hvm_param xen_hvm_param_t; -DEFINE_XEN_GUEST_HANDLE(xen_hvm_param_t); - -/* Set the logical level of one of a domain's PCI INTx wires. */ -#define HVMOP_set_pci_intx_level 2 -struct xen_hvm_set_pci_intx_level { - /* Domain to be updated. */ - domid_t domid; - /* PCI INTx identification in PCI topology (domain:bus:device:intx). */ - uint8_t domain, bus, device, intx; - /* Assertion level (0 = unasserted, 1 = asserted). */ - uint8_t level; -}; -typedef struct xen_hvm_set_pci_intx_level xen_hvm_set_pci_intx_level_t; -DEFINE_XEN_GUEST_HANDLE(xen_hvm_set_pci_intx_level_t); - -/* Set the logical level of one of a domain's ISA IRQ wires. */ -#define HVMOP_set_isa_irq_level 3 -struct xen_hvm_set_isa_irq_level { - /* Domain to be updated. */ - domid_t domid; - /* ISA device identification, by ISA IRQ (0-15). */ - uint8_t isa_irq; - /* Assertion level (0 = unasserted, 1 = asserted). */ - uint8_t level; -}; -typedef struct xen_hvm_set_isa_irq_level xen_hvm_set_isa_irq_level_t; -DEFINE_XEN_GUEST_HANDLE(xen_hvm_set_isa_irq_level_t); - -#define HVMOP_set_pci_link_route 4 -struct xen_hvm_set_pci_link_route { - /* Domain to be updated. */ - domid_t domid; - /* PCI link identifier (0-3). */ - uint8_t link; - /* ISA IRQ (1-15), or 0 (disable link). */ - uint8_t isa_irq; -}; -typedef struct xen_hvm_set_pci_link_route xen_hvm_set_pci_link_route_t; -DEFINE_XEN_GUEST_HANDLE(xen_hvm_set_pci_link_route_t); - -/* Flushes all VCPU TLBs: @arg must be NULL. */ -#define HVMOP_flush_tlbs 5 - -typedef enum { - HVMMEM_ram_rw, /* Normal read/write guest RAM */ - HVMMEM_ram_ro, /* Read-only; writes are discarded */ - HVMMEM_mmio_dm, /* Reads and write go to the device model */ -} hvmmem_type_t; - -/* Following tools-only interfaces may change in future. */ -#if defined(__XEN__) || defined(__XEN_TOOLS__) - -/* Track dirty VRAM. */ -#define HVMOP_track_dirty_vram 6 -struct xen_hvm_track_dirty_vram { - /* Domain to be tracked. */ - domid_t domid; - /* First pfn to track. */ - uint64_aligned_t first_pfn; - /* Number of pages to track. */ - uint64_aligned_t nr; - /* OUT variable. */ - /* Dirty bitmap buffer. */ - XEN_GUEST_HANDLE_64(uint8) dirty_bitmap; -}; -typedef struct xen_hvm_track_dirty_vram xen_hvm_track_dirty_vram_t; -DEFINE_XEN_GUEST_HANDLE(xen_hvm_track_dirty_vram_t); - -/* Notify that some pages got modified by the Device Model. */ -#define HVMOP_modified_memory 7 -struct xen_hvm_modified_memory { - /* Domain to be updated. */ - domid_t domid; - /* First pfn. */ - uint64_aligned_t first_pfn; - /* Number of pages. */ - uint64_aligned_t nr; -}; -typedef struct xen_hvm_modified_memory xen_hvm_modified_memory_t; -DEFINE_XEN_GUEST_HANDLE(xen_hvm_modified_memory_t); - -#define HVMOP_set_mem_type 8 -/* Notify that a region of memory is to be treated in a specific way. */ -struct xen_hvm_set_mem_type { - /* Domain to be updated. */ - domid_t domid; - /* Memory type */ - uint16_t hvmmem_type; - /* Number of pages. */ - uint32_t nr; - /* First pfn. */ - uint64_aligned_t first_pfn; -}; -typedef struct xen_hvm_set_mem_type xen_hvm_set_mem_type_t; -DEFINE_XEN_GUEST_HANDLE(xen_hvm_set_mem_type_t); - -#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */ - -/* Hint from PV drivers for pagetable destruction. */ -#define HVMOP_pagetable_dying 9 -struct xen_hvm_pagetable_dying { - /* Domain with a pagetable about to be destroyed. */ - domid_t domid; - uint16_t pad[3]; /* align next field on 8-byte boundary */ - /* guest physical address of the toplevel pagetable dying */ - uint64_t gpa; -}; -typedef struct xen_hvm_pagetable_dying xen_hvm_pagetable_dying_t; -DEFINE_XEN_GUEST_HANDLE(xen_hvm_pagetable_dying_t); - -/* Get the current Xen time, in nanoseconds since system boot. */ -#define HVMOP_get_time 10 -struct xen_hvm_get_time { - uint64_t now; /* OUT */ -}; -typedef struct xen_hvm_get_time xen_hvm_get_time_t; -DEFINE_XEN_GUEST_HANDLE(xen_hvm_get_time_t); - -#define HVMOP_xentrace 11 -struct xen_hvm_xentrace { - uint16_t event, extra_bytes; - uint8_t extra[TRACE_EXTRA_MAX * sizeof(uint32_t)]; -}; -typedef struct xen_hvm_xentrace xen_hvm_xentrace_t; -DEFINE_XEN_GUEST_HANDLE(xen_hvm_xentrace_t); - -/* Following tools-only interfaces may change in future. */ -#if defined(__XEN__) || defined(__XEN_TOOLS__) - -#define HVMOP_set_mem_access 12 -typedef enum { - HVMMEM_access_n, - HVMMEM_access_r, - HVMMEM_access_w, - HVMMEM_access_rw, - HVMMEM_access_x, - HVMMEM_access_rx, - HVMMEM_access_wx, - HVMMEM_access_rwx, - HVMMEM_access_rx2rw, /* Page starts off as r-x, but automatically - * change to r-w on a write */ - HVMMEM_access_default /* Take the domain default */ -} hvmmem_access_t; -/* Notify that a region of memory is to have specific access types */ -struct xen_hvm_set_mem_access { - /* Domain to be updated. */ - domid_t domid; - /* Memory type */ - uint16_t hvmmem_access; /* hvm_access_t */ - /* Number of pages, ignored on setting default access */ - uint32_t nr; - /* First pfn, or ~0ull to set the default access for new pages */ - uint64_aligned_t first_pfn; -}; -typedef struct xen_hvm_set_mem_access xen_hvm_set_mem_access_t; -DEFINE_XEN_GUEST_HANDLE(xen_hvm_set_mem_access_t); - -#define HVMOP_get_mem_access 13 -/* Get the specific access type for that region of memory */ -struct xen_hvm_get_mem_access { - /* Domain to be queried. */ - domid_t domid; - /* Memory type: OUT */ - uint16_t hvmmem_access; /* hvm_access_t */ - /* pfn, or ~0ull for default access for new pages. IN */ - uint64_aligned_t pfn; -}; -typedef struct xen_hvm_get_mem_access xen_hvm_get_mem_access_t; -DEFINE_XEN_GUEST_HANDLE(xen_hvm_get_mem_access_t); - -#define HVMOP_inject_trap 14 -/* Inject a trap into a VCPU, which will get taken up on the next - * scheduling of it. Note that the caller should know enough of the - * state of the CPU before injecting, to know what the effect of - * injecting the trap will be. - */ -struct xen_hvm_inject_trap { - /* Domain to be queried. */ - domid_t domid; - /* VCPU */ - uint32_t vcpuid; - /* Trap number */ - uint32_t trap; - /* Error code, or -1 to skip */ - uint32_t error_code; - /* CR2 for page faults */ - uint64_aligned_t cr2; -}; -typedef struct xen_hvm_inject_trap xen_hvm_inject_trap_t; -DEFINE_XEN_GUEST_HANDLE(xen_hvm_inject_trap_t); - -#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */ - -#define HVMOP_get_mem_type 15 -/* Return hvmmem_type_t for the specified pfn. */ -struct xen_hvm_get_mem_type { - /* Domain to be queried. */ - domid_t domid; - /* OUT variable. */ - uint16_t mem_type; - uint16_t pad[2]; /* align next field on 8-byte boundary */ - /* IN variable. */ - uint64_t pfn; -}; -typedef struct xen_hvm_get_mem_type xen_hvm_get_mem_type_t; -DEFINE_XEN_GUEST_HANDLE(xen_hvm_get_mem_type_t); - -#endif /* __XEN_PUBLIC_HVM_HVM_OP_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_PUBLIC_HVM_HVM_OP_H__ +#define __XEN_PUBLIC_HVM_HVM_OP_H__ + +#include "../xen.h" +#include "../trace.h" + +/* Get/set subcommands: extra argument == pointer to xen_hvm_param struct. */ +#define HVMOP_set_param 0 +#define HVMOP_get_param 1 +struct xen_hvm_param { + domid_t domid; /* IN */ + uint32_t index; /* IN */ + uint64_t value; /* IN/OUT */ +}; +typedef struct xen_hvm_param xen_hvm_param_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_param_t); + +/* Set the logical level of one of a domain's PCI INTx wires. */ +#define HVMOP_set_pci_intx_level 2 +struct xen_hvm_set_pci_intx_level { + /* Domain to be updated. */ + domid_t domid; + /* PCI INTx identification in PCI topology (domain:bus:device:intx). */ + uint8_t domain, bus, device, intx; + /* Assertion level (0 = unasserted, 1 = asserted). */ + uint8_t level; +}; +typedef struct xen_hvm_set_pci_intx_level xen_hvm_set_pci_intx_level_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_set_pci_intx_level_t); + +/* Set the logical level of one of a domain's ISA IRQ wires. */ +#define HVMOP_set_isa_irq_level 3 +struct xen_hvm_set_isa_irq_level { + /* Domain to be updated. */ + domid_t domid; + /* ISA device identification, by ISA IRQ (0-15). */ + uint8_t isa_irq; + /* Assertion level (0 = unasserted, 1 = asserted). */ + uint8_t level; +}; +typedef struct xen_hvm_set_isa_irq_level xen_hvm_set_isa_irq_level_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_set_isa_irq_level_t); + +#define HVMOP_set_pci_link_route 4 +struct xen_hvm_set_pci_link_route { + /* Domain to be updated. */ + domid_t domid; + /* PCI link identifier (0-3). */ + uint8_t link; + /* ISA IRQ (1-15), or 0 (disable link). */ + uint8_t isa_irq; +}; +typedef struct xen_hvm_set_pci_link_route xen_hvm_set_pci_link_route_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_set_pci_link_route_t); + +/* Flushes all VCPU TLBs: @arg must be NULL. */ +#define HVMOP_flush_tlbs 5 + +typedef enum { + HVMMEM_ram_rw, /* Normal read/write guest RAM */ + HVMMEM_ram_ro, /* Read-only; writes are discarded */ + HVMMEM_mmio_dm, /* Reads and write go to the device model */ +} hvmmem_type_t; + +/* Following tools-only interfaces may change in future. */ +#if defined(__XEN__) || defined(__XEN_TOOLS__) + +/* Track dirty VRAM. */ +#define HVMOP_track_dirty_vram 6 +struct xen_hvm_track_dirty_vram { + /* Domain to be tracked. */ + domid_t domid; + /* First pfn to track. */ + uint64_aligned_t first_pfn; + /* Number of pages to track. */ + uint64_aligned_t nr; + /* OUT variable. */ + /* Dirty bitmap buffer. */ + XEN_GUEST_HANDLE_64(uint8) dirty_bitmap; +}; +typedef struct xen_hvm_track_dirty_vram xen_hvm_track_dirty_vram_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_track_dirty_vram_t); + +/* Notify that some pages got modified by the Device Model. */ +#define HVMOP_modified_memory 7 +struct xen_hvm_modified_memory { + /* Domain to be updated. */ + domid_t domid; + /* First pfn. */ + uint64_aligned_t first_pfn; + /* Number of pages. */ + uint64_aligned_t nr; +}; +typedef struct xen_hvm_modified_memory xen_hvm_modified_memory_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_modified_memory_t); + +#define HVMOP_set_mem_type 8 +/* Notify that a region of memory is to be treated in a specific way. */ +struct xen_hvm_set_mem_type { + /* Domain to be updated. */ + domid_t domid; + /* Memory type */ + uint16_t hvmmem_type; + /* Number of pages. */ + uint32_t nr; + /* First pfn. */ + uint64_aligned_t first_pfn; +}; +typedef struct xen_hvm_set_mem_type xen_hvm_set_mem_type_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_set_mem_type_t); + +#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */ + +/* Hint from PV drivers for pagetable destruction. */ +#define HVMOP_pagetable_dying 9 +struct xen_hvm_pagetable_dying { + /* Domain with a pagetable about to be destroyed. */ + domid_t domid; + uint16_t pad[3]; /* align next field on 8-byte boundary */ + /* guest physical address of the toplevel pagetable dying */ + uint64_t gpa; +}; +typedef struct xen_hvm_pagetable_dying xen_hvm_pagetable_dying_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_pagetable_dying_t); + +/* Get the current Xen time, in nanoseconds since system boot. */ +#define HVMOP_get_time 10 +struct xen_hvm_get_time { + uint64_t now; /* OUT */ +}; +typedef struct xen_hvm_get_time xen_hvm_get_time_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_get_time_t); + +#define HVMOP_xentrace 11 +struct xen_hvm_xentrace { + uint16_t event, extra_bytes; + uint8_t extra[TRACE_EXTRA_MAX * sizeof(uint32_t)]; +}; +typedef struct xen_hvm_xentrace xen_hvm_xentrace_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_xentrace_t); + +/* Following tools-only interfaces may change in future. */ +#if defined(__XEN__) || defined(__XEN_TOOLS__) + +#define HVMOP_set_mem_access 12 +typedef enum { + HVMMEM_access_n, + HVMMEM_access_r, + HVMMEM_access_w, + HVMMEM_access_rw, + HVMMEM_access_x, + HVMMEM_access_rx, + HVMMEM_access_wx, + HVMMEM_access_rwx, + HVMMEM_access_rx2rw, /* Page starts off as r-x, but automatically + * change to r-w on a write */ + HVMMEM_access_n2rwx, /* Log access: starts off as n, automatically + * goes to rwx, generating an event without + * pausing the vcpu */ + HVMMEM_access_default /* Take the domain default */ +} hvmmem_access_t; +/* Notify that a region of memory is to have specific access types */ +struct xen_hvm_set_mem_access { + /* Domain to be updated. */ + domid_t domid; + /* Memory type */ + uint16_t hvmmem_access; /* hvm_access_t */ + /* Number of pages, ignored on setting default access */ + uint32_t nr; + /* First pfn, or ~0ull to set the default access for new pages */ + uint64_aligned_t first_pfn; +}; +typedef struct xen_hvm_set_mem_access xen_hvm_set_mem_access_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_set_mem_access_t); + +#define HVMOP_get_mem_access 13 +/* Get the specific access type for that region of memory */ +struct xen_hvm_get_mem_access { + /* Domain to be queried. */ + domid_t domid; + /* Memory type: OUT */ + uint16_t hvmmem_access; /* hvm_access_t */ + /* pfn, or ~0ull for default access for new pages. IN */ + uint64_aligned_t pfn; +}; +typedef struct xen_hvm_get_mem_access xen_hvm_get_mem_access_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_get_mem_access_t); + +#define HVMOP_inject_trap 14 +/* Inject a trap into a VCPU, which will get taken up on the next + * scheduling of it. Note that the caller should know enough of the + * state of the CPU before injecting, to know what the effect of + * injecting the trap will be. + */ +struct xen_hvm_inject_trap { + /* Domain to be queried. */ + domid_t domid; + /* VCPU */ + uint32_t vcpuid; + /* Vector number */ + uint32_t vector; + /* Trap type (HVMOP_TRAP_*) */ + uint32_t type; +/* NB. This enumeration precisely matches hvm.h:X86_EVENTTYPE_* */ +# define HVMOP_TRAP_ext_int 0 /* external interrupt */ +# define HVMOP_TRAP_nmi 2 /* nmi */ +# define HVMOP_TRAP_hw_exc 3 /* hardware exception */ +# define HVMOP_TRAP_sw_int 4 /* software interrupt (CD nn) */ +# define HVMOP_TRAP_pri_sw_exc 5 /* ICEBP (F1) */ +# define HVMOP_TRAP_sw_exc 6 /* INT3 (CC), INTO (CE) */ + /* Error code, or ~0u to skip */ + uint32_t error_code; + /* Intruction length */ + uint32_t insn_len; + /* CR2 for page faults */ + uint64_aligned_t cr2; +}; +typedef struct xen_hvm_inject_trap xen_hvm_inject_trap_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_inject_trap_t); + +#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */ + +#define HVMOP_get_mem_type 15 +/* Return hvmmem_type_t for the specified pfn. */ +struct xen_hvm_get_mem_type { + /* Domain to be queried. */ + domid_t domid; + /* OUT variable. */ + uint16_t mem_type; + uint16_t pad[2]; /* align next field on 8-byte boundary */ + /* IN variable. */ + uint64_t pfn; +}; +typedef struct xen_hvm_get_mem_type xen_hvm_get_mem_type_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_get_mem_type_t); + +/* Following tools-only interfaces may change in future. */ +#if defined(__XEN__) || defined(__XEN_TOOLS__) + +/* MSI injection for emulated devices */ +#define HVMOP_inject_msi 16 +struct xen_hvm_inject_msi { + /* Domain to be injected */ + domid_t domid; + /* Data -- lower 32 bits */ + uint32_t data; + /* Address (0xfeexxxxx) */ + uint64_t addr; +}; +typedef struct xen_hvm_inject_msi xen_hvm_inject_msi_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_inject_msi_t); + +#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */ + +#endif /* __XEN_PUBLIC_HVM_HVM_OP_H__ */ diff --git a/include/xen/hvm/params.h b/include/xen/hvm/params.h index 1c98277..9646b9b 100644 --- a/include/xen/hvm/params.h +++ b/include/xen/hvm/params.h @@ -1,143 +1,150 @@ -/* - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - */ - -#ifndef __XEN_PUBLIC_HVM_PARAMS_H__ -#define __XEN_PUBLIC_HVM_PARAMS_H__ - -#include "hvm_op.h" - -/* - * Parameter space for HVMOP_{set,get}_param. - */ - -/* - * How should CPU0 event-channel notifications be delivered? - * val[63:56] == 0: val[55:0] is a delivery GSI (Global System Interrupt). - * val[63:56] == 1: val[55:0] is a delivery PCI INTx line, as follows: - * Domain = val[47:32], Bus = val[31:16], - * DevFn = val[15: 8], IntX = val[ 1: 0] - * val[63:56] == 2: val[7:0] is a vector number, check for - * XENFEAT_hvm_callback_vector to know if this delivery - * method is available. - * If val == 0 then CPU0 event-channel notifications are not delivered. - */ -#define HVM_PARAM_CALLBACK_IRQ 0 - -/* - * These are not used by Xen. They are here for convenience of HVM-guest - * xenbus implementations. - */ -#define HVM_PARAM_STORE_PFN 1 -#define HVM_PARAM_STORE_EVTCHN 2 - -#define HVM_PARAM_PAE_ENABLED 4 - -#define HVM_PARAM_IOREQ_PFN 5 - -#define HVM_PARAM_BUFIOREQ_PFN 6 - -#ifdef __ia64__ - -#define HVM_PARAM_NVRAM_FD 7 -#define HVM_PARAM_VHPT_SIZE 8 -#define HVM_PARAM_BUFPIOREQ_PFN 9 - -#elif defined(__i386__) || defined(__x86_64__) - -/* Expose Viridian interfaces to this HVM guest? */ -#define HVM_PARAM_VIRIDIAN 9 - -#endif - -/* - * Set mode for virtual timers (currently x86 only): - * delay_for_missed_ticks (default): - * Do not advance a vcpu's time beyond the correct delivery time for - * interrupts that have been missed due to preemption. Deliver missed - * interrupts when the vcpu is rescheduled and advance the vcpu's virtual - * time stepwise for each one. - * no_delay_for_missed_ticks: - * As above, missed interrupts are delivered, but guest time always tracks - * wallclock (i.e., real) time while doing so. - * no_missed_ticks_pending: - * No missed interrupts are held pending. Instead, to ensure ticks are - * delivered at some non-zero rate, if we detect missed ticks then the - * internal tick alarm is not disabled if the VCPU is preempted during the - * next tick period. - * one_missed_tick_pending: - * Missed interrupts are collapsed together and delivered as one 'late tick'. - * Guest time always tracks wallclock (i.e., real) time. - */ -#define HVM_PARAM_TIMER_MODE 10 -#define HVMPTM_delay_for_missed_ticks 0 -#define HVMPTM_no_delay_for_missed_ticks 1 -#define HVMPTM_no_missed_ticks_pending 2 -#define HVMPTM_one_missed_tick_pending 3 - -/* Boolean: Enable virtual HPET (high-precision event timer)? (x86-only) */ -#define HVM_PARAM_HPET_ENABLED 11 - -/* Identity-map page directory used by Intel EPT when CR0.PG=0. */ -#define HVM_PARAM_IDENT_PT 12 - -/* Device Model domain, defaults to 0. */ -#define HVM_PARAM_DM_DOMAIN 13 - -/* ACPI S state: currently support S0 and S3 on x86. */ -#define HVM_PARAM_ACPI_S_STATE 14 - -/* TSS used on Intel when CR0.PE=0. */ -#define HVM_PARAM_VM86_TSS 15 - -/* Boolean: Enable aligning all periodic vpts to reduce interrupts */ -#define HVM_PARAM_VPT_ALIGN 16 - -/* Console debug shared memory ring and event channel */ -#define HVM_PARAM_CONSOLE_PFN 17 -#define HVM_PARAM_CONSOLE_EVTCHN 18 - -/* - * Select location of ACPI PM1a and TMR control blocks. Currently two locations - * are supported, specified by version 0 or 1 in this parameter: - * - 0: default, use the old addresses - * PM1A_EVT == 0x1f40; PM1A_CNT == 0x1f44; PM_TMR == 0x1f48 - * - 1: use the new default qemu addresses - * PM1A_EVT == 0xb000; PM1A_CNT == 0xb004; PM_TMR == 0xb008 - * You can find these address definitions in - */ -#define HVM_PARAM_ACPI_IOPORTS_LOCATION 19 - -/* Enable blocking memory events, async or sync (pause vcpu until response) - * onchangeonly indicates messages only on a change of value */ -#define HVM_PARAM_MEMORY_EVENT_CR0 20 -#define HVM_PARAM_MEMORY_EVENT_CR3 21 -#define HVM_PARAM_MEMORY_EVENT_CR4 22 -#define HVM_PARAM_MEMORY_EVENT_INT3 23 -#define HVM_PARAM_MEMORY_EVENT_SINGLE_STEP 25 - -#define HVMPME_MODE_MASK (3 << 0) -#define HVMPME_mode_disabled 0 -#define HVMPME_mode_async 1 -#define HVMPME_mode_sync 2 -#define HVMPME_onchangeonly (1 << 2) - -#define HVM_NR_PARAMS 26 - -#endif /* __XEN_PUBLIC_HVM_PARAMS_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_PUBLIC_HVM_PARAMS_H__ +#define __XEN_PUBLIC_HVM_PARAMS_H__ + +#include "hvm_op.h" + +/* + * Parameter space for HVMOP_{set,get}_param. + */ + +/* + * How should CPU0 event-channel notifications be delivered? + * val[63:56] == 0: val[55:0] is a delivery GSI (Global System Interrupt). + * val[63:56] == 1: val[55:0] is a delivery PCI INTx line, as follows: + * Domain = val[47:32], Bus = val[31:16], + * DevFn = val[15: 8], IntX = val[ 1: 0] + * val[63:56] == 2: val[7:0] is a vector number, check for + * XENFEAT_hvm_callback_vector to know if this delivery + * method is available. + * If val == 0 then CPU0 event-channel notifications are not delivered. + */ +#define HVM_PARAM_CALLBACK_IRQ 0 + +/* + * These are not used by Xen. They are here for convenience of HVM-guest + * xenbus implementations. + */ +#define HVM_PARAM_STORE_PFN 1 +#define HVM_PARAM_STORE_EVTCHN 2 + +#define HVM_PARAM_PAE_ENABLED 4 + +#define HVM_PARAM_IOREQ_PFN 5 + +#define HVM_PARAM_BUFIOREQ_PFN 6 +#define HVM_PARAM_BUFIOREQ_EVTCHN 26 + +#if defined(__i386__) || defined(__x86_64__) + +/* Expose Viridian interfaces to this HVM guest? */ +#define HVM_PARAM_VIRIDIAN 9 + +#endif + +/* + * Set mode for virtual timers (currently x86 only): + * delay_for_missed_ticks (default): + * Do not advance a vcpu's time beyond the correct delivery time for + * interrupts that have been missed due to preemption. Deliver missed + * interrupts when the vcpu is rescheduled and advance the vcpu's virtual + * time stepwise for each one. + * no_delay_for_missed_ticks: + * As above, missed interrupts are delivered, but guest time always tracks + * wallclock (i.e., real) time while doing so. + * no_missed_ticks_pending: + * No missed interrupts are held pending. Instead, to ensure ticks are + * delivered at some non-zero rate, if we detect missed ticks then the + * internal tick alarm is not disabled if the VCPU is preempted during the + * next tick period. + * one_missed_tick_pending: + * Missed interrupts are collapsed together and delivered as one 'late tick'. + * Guest time always tracks wallclock (i.e., real) time. + */ +#define HVM_PARAM_TIMER_MODE 10 +#define HVMPTM_delay_for_missed_ticks 0 +#define HVMPTM_no_delay_for_missed_ticks 1 +#define HVMPTM_no_missed_ticks_pending 2 +#define HVMPTM_one_missed_tick_pending 3 + +/* Boolean: Enable virtual HPET (high-precision event timer)? (x86-only) */ +#define HVM_PARAM_HPET_ENABLED 11 + +/* Identity-map page directory used by Intel EPT when CR0.PG=0. */ +#define HVM_PARAM_IDENT_PT 12 + +/* Device Model domain, defaults to 0. */ +#define HVM_PARAM_DM_DOMAIN 13 + +/* ACPI S state: currently support S0 and S3 on x86. */ +#define HVM_PARAM_ACPI_S_STATE 14 + +/* TSS used on Intel when CR0.PE=0. */ +#define HVM_PARAM_VM86_TSS 15 + +/* Boolean: Enable aligning all periodic vpts to reduce interrupts */ +#define HVM_PARAM_VPT_ALIGN 16 + +/* Console debug shared memory ring and event channel */ +#define HVM_PARAM_CONSOLE_PFN 17 +#define HVM_PARAM_CONSOLE_EVTCHN 18 + +/* + * Select location of ACPI PM1a and TMR control blocks. Currently two locations + * are supported, specified by version 0 or 1 in this parameter: + * - 0: default, use the old addresses + * PM1A_EVT == 0x1f40; PM1A_CNT == 0x1f44; PM_TMR == 0x1f48 + * - 1: use the new default qemu addresses + * PM1A_EVT == 0xb000; PM1A_CNT == 0xb004; PM_TMR == 0xb008 + * You can find these address definitions in + */ +#define HVM_PARAM_ACPI_IOPORTS_LOCATION 19 + +/* Enable blocking memory events, async or sync (pause vcpu until response) + * onchangeonly indicates messages only on a change of value */ +#define HVM_PARAM_MEMORY_EVENT_CR0 20 +#define HVM_PARAM_MEMORY_EVENT_CR3 21 +#define HVM_PARAM_MEMORY_EVENT_CR4 22 +#define HVM_PARAM_MEMORY_EVENT_INT3 23 +#define HVM_PARAM_MEMORY_EVENT_SINGLE_STEP 25 +#define HVM_PARAM_MEMORY_EVENT_MSR 30 + +#define HVMPME_MODE_MASK (3 << 0) +#define HVMPME_mode_disabled 0 +#define HVMPME_mode_async 1 +#define HVMPME_mode_sync 2 +#define HVMPME_onchangeonly (1 << 2) + +/* Boolean: Enable nestedhvm (hvm only) */ +#define HVM_PARAM_NESTEDHVM 24 + +/* Params for the mem event rings */ +#define HVM_PARAM_PAGING_RING_PFN 27 +#define HVM_PARAM_ACCESS_RING_PFN 28 +#define HVM_PARAM_SHARING_RING_PFN 29 + +/* SHUTDOWN_* action in case of a triple fault */ +#define HVM_PARAM_TRIPLE_FAULT_REASON 31 + +#define HVM_NR_PARAMS 32 + +#endif /* __XEN_PUBLIC_HVM_PARAMS_H__ */ diff --git a/include/xen/io/xs_wire.h b/include/xen/io/xs_wire.h index e1debce..5042323 100644 --- a/include/xen/io/xs_wire.h +++ b/include/xen/io/xs_wire.h @@ -1,133 +1,137 @@ -/* - * 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 -}; - -#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) -}; -#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 -}; - -/* 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-set-style: "BSD" - * c-basic-offset: 4 - * tab-width: 4 - * indent-tabs-mode: nil - * End: - */ +/* + * 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) +}; +#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/memory.h b/include/xen/memory.h index 08355e3..e086f37 100644 --- a/include/xen/memory.h +++ b/include/xen/memory.h @@ -1,304 +1,474 @@ -/****************************************************************************** - * memory.h - * - * Memory reservation and information. - * - * 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_MEMORY_H__ -#define __XEN_PUBLIC_MEMORY_H__ - -#include "xen.h" - -/* - * Increase or decrease the specified domain's memory reservation. Returns the - * number of extents successfully allocated or freed. - * arg == addr of struct xen_memory_reservation. - */ -#define XENMEM_increase_reservation 0 -#define XENMEM_decrease_reservation 1 -#define XENMEM_populate_physmap 6 - -#if __XEN_INTERFACE_VERSION__ >= 0x00030209 -/* - * Maximum # bits addressable by the user of the allocated region (e.g., I/O - * devices often have a 32-bit limitation even in 64-bit systems). If zero - * then the user has no addressing restriction. This field is not used by - * XENMEM_decrease_reservation. - */ -#define XENMEMF_address_bits(x) (x) -#define XENMEMF_get_address_bits(x) ((x) & 0xffu) -/* NUMA node to allocate from. */ -#define XENMEMF_node(x) (((x) + 1) << 8) -#define XENMEMF_get_node(x) ((((x) >> 8) - 1) & 0xffu) -/* Flag to populate physmap with populate-on-demand entries */ -#define XENMEMF_populate_on_demand (1<<16) -/* Flag to request allocation only from the node specified */ -#define XENMEMF_exact_node_request (1<<17) -#define XENMEMF_exact_node(n) (XENMEMF_node(n) | XENMEMF_exact_node_request) -#endif - -struct xen_memory_reservation { - - /* - * XENMEM_increase_reservation: - * OUT: MFN (*not* GMFN) bases of extents that were allocated - * XENMEM_decrease_reservation: - * IN: GMFN bases of extents to free - * XENMEM_populate_physmap: - * IN: GPFN bases of extents to populate with memory - * OUT: GMFN bases of extents that were allocated - * (NB. This command also updates the mach_to_phys translation table) - */ - XEN_GUEST_HANDLE(xen_pfn_t) extent_start; - - /* Number of extents, and size/alignment of each (2^extent_order pages). */ - xen_ulong_t nr_extents; - unsigned int extent_order; - -#if __XEN_INTERFACE_VERSION__ >= 0x00030209 - /* XENMEMF flags. */ - unsigned int mem_flags; -#else - unsigned int address_bits; -#endif - - /* - * Domain whose reservation is being changed. - * Unprivileged domains can specify only DOMID_SELF. - */ - domid_t domid; -}; -typedef struct xen_memory_reservation xen_memory_reservation_t; -DEFINE_XEN_GUEST_HANDLE(xen_memory_reservation_t); - -/* - * An atomic exchange of memory pages. If return code is zero then - * @out.extent_list provides GMFNs of the newly-allocated memory. - * Returns zero on complete success, otherwise a negative error code. - * On complete success then always @nr_exchanged == @in.nr_extents. - * On partial success @nr_exchanged indicates how much work was done. - */ -#define XENMEM_exchange 11 -struct xen_memory_exchange { - /* - * [IN] Details of memory extents to be exchanged (GMFN bases). - * Note that @in.address_bits is ignored and unused. - */ - struct xen_memory_reservation in; - - /* - * [IN/OUT] Details of new memory extents. - * We require that: - * 1. @in.domid == @out.domid - * 2. @in.nr_extents << @in.extent_order == - * @out.nr_extents << @out.extent_order - * 3. @in.extent_start and @out.extent_start lists must not overlap - * 4. @out.extent_start lists GPFN bases to be populated - * 5. @out.extent_start is overwritten with allocated GMFN bases - */ - struct xen_memory_reservation out; - - /* - * [OUT] Number of input extents that were successfully exchanged: - * 1. The first @nr_exchanged input extents were successfully - * deallocated. - * 2. The corresponding first entries in the output extent list correctly - * indicate the GMFNs that were successfully exchanged. - * 3. All other input and output extents are untouched. - * 4. If not all input exents are exchanged then the return code of this - * command will be non-zero. - * 5. THIS FIELD MUST BE INITIALISED TO ZERO BY THE CALLER! - */ - xen_ulong_t nr_exchanged; -}; -typedef struct xen_memory_exchange xen_memory_exchange_t; -DEFINE_XEN_GUEST_HANDLE(xen_memory_exchange_t); - -/* - * Returns the maximum machine frame number of mapped RAM in this system. - * This command always succeeds (it never returns an error code). - * arg == NULL. - */ -#define XENMEM_maximum_ram_page 2 - -/* - * Returns the current or maximum memory reservation, in pages, of the - * specified domain (may be DOMID_SELF). Returns -ve errcode on failure. - * arg == addr of domid_t. - */ -#define XENMEM_current_reservation 3 -#define XENMEM_maximum_reservation 4 - -/* - * Returns the maximum GPFN in use by the guest, or -ve errcode on failure. - */ -#define XENMEM_maximum_gpfn 14 - -/* - * Returns a list of MFN bases of 2MB extents comprising the machine_to_phys - * mapping table. Architectures which do not have a m2p table do not implement - * this command. - * arg == addr of xen_machphys_mfn_list_t. - */ -#define XENMEM_machphys_mfn_list 5 -struct xen_machphys_mfn_list { - /* - * Size of the 'extent_start' array. Fewer entries will be filled if the - * machphys table is smaller than max_extents * 2MB. - */ - unsigned int max_extents; - - /* - * Pointer to buffer to fill with list of extent starts. If there are - * any large discontiguities in the machine address space, 2MB gaps in - * the machphys table will be represented by an MFN base of zero. - */ - XEN_GUEST_HANDLE(xen_pfn_t) extent_start; - - /* - * Number of extents written to the above array. This will be smaller - * than 'max_extents' if the machphys table is smaller than max_e * 2MB. - */ - unsigned int nr_extents; -}; -typedef struct xen_machphys_mfn_list xen_machphys_mfn_list_t; -DEFINE_XEN_GUEST_HANDLE(xen_machphys_mfn_list_t); - -/* - * Returns the location in virtual address space of the machine_to_phys - * mapping table. Architectures which do not have a m2p table, or which do not - * map it by default into guest address space, do not implement this command. - * arg == addr of xen_machphys_mapping_t. - */ -#define XENMEM_machphys_mapping 12 -struct xen_machphys_mapping { - xen_ulong_t v_start, v_end; /* Start and end virtual addresses. */ - xen_ulong_t max_mfn; /* Maximum MFN that can be looked up. */ -}; -typedef struct xen_machphys_mapping xen_machphys_mapping_t; -DEFINE_XEN_GUEST_HANDLE(xen_machphys_mapping_t); - -/* - * Sets the GPFN at which a particular page appears in the specified guest's - * pseudophysical address space. - * arg == addr of xen_add_to_physmap_t. - */ -#define XENMEM_add_to_physmap 7 -struct xen_add_to_physmap { - /* Which domain to change the mapping for. */ - domid_t domid; - - /* Source mapping space. */ -#define XENMAPSPACE_shared_info 0 /* shared info page */ -#define XENMAPSPACE_grant_table 1 /* grant table page */ -#define XENMAPSPACE_gmfn 2 /* GMFN */ - unsigned int space; - -#define XENMAPIDX_grant_table_status 0x80000000 - - /* Index into source mapping space. */ - xen_ulong_t idx; - - /* GPFN where the source mapping page should appear. */ - xen_pfn_t gpfn; -}; -typedef struct xen_add_to_physmap xen_add_to_physmap_t; -DEFINE_XEN_GUEST_HANDLE(xen_add_to_physmap_t); - -/*** REMOVED ***/ -/*#define XENMEM_translate_gpfn_list 8*/ - -/* - * Returns the pseudo-physical memory map as it was when the domain - * was started (specified by XENMEM_set_memory_map). - * arg == addr of xen_memory_map_t. - */ -#define XENMEM_memory_map 9 -struct xen_memory_map { - /* - * On call the number of entries which can be stored in buffer. On - * return the number of entries which have been stored in - * buffer. - */ - unsigned int nr_entries; - - /* - * Entries in the buffer are in the same format as returned by the - * BIOS INT 0x15 EAX=0xE820 call. - */ - XEN_GUEST_HANDLE(void) buffer; -}; -typedef struct xen_memory_map xen_memory_map_t; -DEFINE_XEN_GUEST_HANDLE(xen_memory_map_t); - -/* - * Returns the real physical memory map. Passes the same structure as - * XENMEM_memory_map. - * arg == addr of xen_memory_map_t. - */ -#define XENMEM_machine_memory_map 10 - -/* - * Set the pseudo-physical memory map of a domain, as returned by - * XENMEM_memory_map. - * arg == addr of xen_foreign_memory_map_t. - */ -#define XENMEM_set_memory_map 13 -struct xen_foreign_memory_map { - domid_t domid; - struct xen_memory_map map; -}; -typedef struct xen_foreign_memory_map xen_foreign_memory_map_t; -DEFINE_XEN_GUEST_HANDLE(xen_foreign_memory_map_t); - -#define XENMEM_set_pod_target 16 -#define XENMEM_get_pod_target 17 -struct xen_pod_target { - /* IN */ - uint64_t target_pages; - /* OUT */ - uint64_t tot_pages; - uint64_t pod_cache_pages; - uint64_t pod_entries; - /* IN */ - domid_t domid; -}; -typedef struct xen_pod_target xen_pod_target_t; - -/* - * Get the number of MFNs saved through memory sharing. - * The call never fails. - */ -#define XENMEM_get_sharing_freed_pages 18 - -#endif /* __XEN_PUBLIC_MEMORY_H__ */ - -/* - * Local variables: - * mode: C - * c-set-style: "BSD" - * c-basic-offset: 4 - * tab-width: 4 - * indent-tabs-mode: nil - * End: - */ +/****************************************************************************** + * memory.h + * + * Memory reservation and information. + * + * 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_MEMORY_H__ +#define __XEN_PUBLIC_MEMORY_H__ + +#include "xen.h" + +/* + * Increase or decrease the specified domain's memory reservation. Returns the + * number of extents successfully allocated or freed. + * arg == addr of struct xen_memory_reservation. + */ +#define XENMEM_increase_reservation 0 +#define XENMEM_decrease_reservation 1 +#define XENMEM_populate_physmap 6 + +#if __XEN_INTERFACE_VERSION__ >= 0x00030209 +/* + * Maximum # bits addressable by the user of the allocated region (e.g., I/O + * devices often have a 32-bit limitation even in 64-bit systems). If zero + * then the user has no addressing restriction. This field is not used by + * XENMEM_decrease_reservation. + */ +#define XENMEMF_address_bits(x) (x) +#define XENMEMF_get_address_bits(x) ((x) & 0xffu) +/* NUMA node to allocate from. */ +#define XENMEMF_node(x) (((x) + 1) << 8) +#define XENMEMF_get_node(x) ((((x) >> 8) - 1) & 0xffu) +/* Flag to populate physmap with populate-on-demand entries */ +#define XENMEMF_populate_on_demand (1<<16) +/* Flag to request allocation only from the node specified */ +#define XENMEMF_exact_node_request (1<<17) +#define XENMEMF_exact_node(n) (XENMEMF_node(n) | XENMEMF_exact_node_request) +#endif + +struct xen_memory_reservation { + + /* + * XENMEM_increase_reservation: + * OUT: MFN (*not* GMFN) bases of extents that were allocated + * XENMEM_decrease_reservation: + * IN: GMFN bases of extents to free + * XENMEM_populate_physmap: + * IN: GPFN bases of extents to populate with memory + * OUT: GMFN bases of extents that were allocated + * (NB. This command also updates the mach_to_phys translation table) + * XENMEM_claim_pages: + * IN: must be zero + */ + XEN_GUEST_HANDLE(xen_pfn_t) extent_start; + + /* Number of extents, and size/alignment of each (2^extent_order pages). */ + xen_ulong_t nr_extents; + unsigned int extent_order; + +#if __XEN_INTERFACE_VERSION__ >= 0x00030209 + /* XENMEMF flags. */ + unsigned int mem_flags; +#else + unsigned int address_bits; +#endif + + /* + * Domain whose reservation is being changed. + * Unprivileged domains can specify only DOMID_SELF. + */ + domid_t domid; +}; +typedef struct xen_memory_reservation xen_memory_reservation_t; +DEFINE_XEN_GUEST_HANDLE(xen_memory_reservation_t); + +/* + * An atomic exchange of memory pages. If return code is zero then + * @out.extent_list provides GMFNs of the newly-allocated memory. + * Returns zero on complete success, otherwise a negative error code. + * On complete success then always @nr_exchanged == @in.nr_extents. + * On partial success @nr_exchanged indicates how much work was done. + */ +#define XENMEM_exchange 11 +struct xen_memory_exchange { + /* + * [IN] Details of memory extents to be exchanged (GMFN bases). + * Note that @in.address_bits is ignored and unused. + */ + struct xen_memory_reservation in; + + /* + * [IN/OUT] Details of new memory extents. + * We require that: + * 1. @in.domid == @out.domid + * 2. @in.nr_extents << @in.extent_order == + * @out.nr_extents << @out.extent_order + * 3. @in.extent_start and @out.extent_start lists must not overlap + * 4. @out.extent_start lists GPFN bases to be populated + * 5. @out.extent_start is overwritten with allocated GMFN bases + */ + struct xen_memory_reservation out; + + /* + * [OUT] Number of input extents that were successfully exchanged: + * 1. The first @nr_exchanged input extents were successfully + * deallocated. + * 2. The corresponding first entries in the output extent list correctly + * indicate the GMFNs that were successfully exchanged. + * 3. All other input and output extents are untouched. + * 4. If not all input exents are exchanged then the return code of this + * command will be non-zero. + * 5. THIS FIELD MUST BE INITIALISED TO ZERO BY THE CALLER! + */ + xen_ulong_t nr_exchanged; +}; +typedef struct xen_memory_exchange xen_memory_exchange_t; +DEFINE_XEN_GUEST_HANDLE(xen_memory_exchange_t); + +/* + * Returns the maximum machine frame number of mapped RAM in this system. + * This command always succeeds (it never returns an error code). + * arg == NULL. + */ +#define XENMEM_maximum_ram_page 2 + +/* + * Returns the current or maximum memory reservation, in pages, of the + * specified domain (may be DOMID_SELF). Returns -ve errcode on failure. + * arg == addr of domid_t. + */ +#define XENMEM_current_reservation 3 +#define XENMEM_maximum_reservation 4 + +/* + * Returns the maximum GPFN in use by the guest, or -ve errcode on failure. + */ +#define XENMEM_maximum_gpfn 14 + +/* + * Returns a list of MFN bases of 2MB extents comprising the machine_to_phys + * mapping table. Architectures which do not have a m2p table do not implement + * this command. + * arg == addr of xen_machphys_mfn_list_t. + */ +#define XENMEM_machphys_mfn_list 5 +struct xen_machphys_mfn_list { + /* + * Size of the 'extent_start' array. Fewer entries will be filled if the + * machphys table is smaller than max_extents * 2MB. + */ + unsigned int max_extents; + + /* + * Pointer to buffer to fill with list of extent starts. If there are + * any large discontiguities in the machine address space, 2MB gaps in + * the machphys table will be represented by an MFN base of zero. + */ + XEN_GUEST_HANDLE(xen_pfn_t) extent_start; + + /* + * Number of extents written to the above array. This will be smaller + * than 'max_extents' if the machphys table is smaller than max_e * 2MB. + */ + unsigned int nr_extents; +}; +typedef struct xen_machphys_mfn_list xen_machphys_mfn_list_t; +DEFINE_XEN_GUEST_HANDLE(xen_machphys_mfn_list_t); + +/* + * Returns the location in virtual address space of the machine_to_phys + * mapping table. Architectures which do not have a m2p table, or which do not + * map it by default into guest address space, do not implement this command. + * arg == addr of xen_machphys_mapping_t. + */ +#define XENMEM_machphys_mapping 12 +struct xen_machphys_mapping { + xen_ulong_t v_start, v_end; /* Start and end virtual addresses. */ + xen_ulong_t max_mfn; /* Maximum MFN that can be looked up. */ +}; +typedef struct xen_machphys_mapping xen_machphys_mapping_t; +DEFINE_XEN_GUEST_HANDLE(xen_machphys_mapping_t); + +/* Source mapping space. */ +/* ` enum phys_map_space { */ +#define XENMAPSPACE_shared_info 0 /* shared info page */ +#define XENMAPSPACE_grant_table 1 /* grant table page */ +#define XENMAPSPACE_gmfn 2 /* GMFN */ +#define XENMAPSPACE_gmfn_range 3 /* GMFN range, XENMEM_add_to_physmap only. */ +#define XENMAPSPACE_gmfn_foreign 4 /* GMFN from another dom, + * XENMEM_add_to_physmap_range only. + */ +/* ` } */ + +/* + * Sets the GPFN at which a particular page appears in the specified guest's + * pseudophysical address space. + * arg == addr of xen_add_to_physmap_t. + */ +#define XENMEM_add_to_physmap 7 +struct xen_add_to_physmap { + /* Which domain to change the mapping for. */ + domid_t domid; + + /* Number of pages to go through for gmfn_range */ + uint16_t size; + + unsigned int space; /* => enum phys_map_space */ + +#define XENMAPIDX_grant_table_status 0x80000000 + + /* Index into space being mapped. */ + xen_ulong_t idx; + + /* GPFN in domid where the source mapping page should appear. */ + xen_pfn_t gpfn; +}; +typedef struct xen_add_to_physmap xen_add_to_physmap_t; +DEFINE_XEN_GUEST_HANDLE(xen_add_to_physmap_t); + +/* A batched version of add_to_physmap. */ +#define XENMEM_add_to_physmap_range 23 +struct xen_add_to_physmap_range { + /* IN */ + /* Which domain to change the mapping for. */ + domid_t domid; + uint16_t space; /* => enum phys_map_space */ + + /* Number of pages to go through */ + uint16_t size; + domid_t foreign_domid; /* IFF gmfn_foreign */ + + /* Indexes into space being mapped. */ + XEN_GUEST_HANDLE(xen_ulong_t) idxs; + + /* GPFN in domid where the source mapping page should appear. */ + XEN_GUEST_HANDLE(xen_pfn_t) gpfns; + + /* OUT */ + + /* Per index error code. */ + XEN_GUEST_HANDLE(int) errs; +}; +typedef struct xen_add_to_physmap_range xen_add_to_physmap_range_t; +DEFINE_XEN_GUEST_HANDLE(xen_add_to_physmap_range_t); + +/* + * Unmaps the page appearing at a particular GPFN from the specified guest's + * pseudophysical address space. + * arg == addr of xen_remove_from_physmap_t. + */ +#define XENMEM_remove_from_physmap 15 +struct xen_remove_from_physmap { + /* Which domain to change the mapping for. */ + domid_t domid; + + /* GPFN of the current mapping of the page. */ + xen_pfn_t gpfn; +}; +typedef struct xen_remove_from_physmap xen_remove_from_physmap_t; +DEFINE_XEN_GUEST_HANDLE(xen_remove_from_physmap_t); + +/*** REMOVED ***/ +/*#define XENMEM_translate_gpfn_list 8*/ + +/* + * Returns the pseudo-physical memory map as it was when the domain + * was started (specified by XENMEM_set_memory_map). + * arg == addr of xen_memory_map_t. + */ +#define XENMEM_memory_map 9 +struct xen_memory_map { + /* + * On call the number of entries which can be stored in buffer. On + * return the number of entries which have been stored in + * buffer. + */ + unsigned int nr_entries; + + /* + * Entries in the buffer are in the same format as returned by the + * BIOS INT 0x15 EAX=0xE820 call. + */ + XEN_GUEST_HANDLE(void) buffer; +}; +typedef struct xen_memory_map xen_memory_map_t; +DEFINE_XEN_GUEST_HANDLE(xen_memory_map_t); + +/* + * Returns the real physical memory map. Passes the same structure as + * XENMEM_memory_map. + * arg == addr of xen_memory_map_t. + */ +#define XENMEM_machine_memory_map 10 + +/* + * Set the pseudo-physical memory map of a domain, as returned by + * XENMEM_memory_map. + * arg == addr of xen_foreign_memory_map_t. + */ +#define XENMEM_set_memory_map 13 +struct xen_foreign_memory_map { + domid_t domid; + struct xen_memory_map map; +}; +typedef struct xen_foreign_memory_map xen_foreign_memory_map_t; +DEFINE_XEN_GUEST_HANDLE(xen_foreign_memory_map_t); + +#define XENMEM_set_pod_target 16 +#define XENMEM_get_pod_target 17 +struct xen_pod_target { + /* IN */ + uint64_t target_pages; + /* OUT */ + uint64_t tot_pages; + uint64_t pod_cache_pages; + uint64_t pod_entries; + /* IN */ + domid_t domid; +}; +typedef struct xen_pod_target xen_pod_target_t; + +#if defined(__XEN__) || defined(__XEN_TOOLS__) + +#ifndef uint64_aligned_t +#define uint64_aligned_t uint64_t +#endif + +/* + * Get the number of MFNs saved through memory sharing. + * The call never fails. + */ +#define XENMEM_get_sharing_freed_pages 18 +#define XENMEM_get_sharing_shared_pages 19 + +#define XENMEM_paging_op 20 +#define XENMEM_paging_op_nominate 0 +#define XENMEM_paging_op_evict 1 +#define XENMEM_paging_op_prep 2 + +#define XENMEM_access_op 21 +#define XENMEM_access_op_resume 0 + +struct xen_mem_event_op { + uint8_t op; /* XENMEM_*_op_* */ + domid_t domain; + + + /* PAGING_PREP IN: buffer to immediately fill page in */ + uint64_aligned_t buffer; + /* Other OPs */ + uint64_aligned_t gfn; /* IN: gfn of page being operated on */ +}; +typedef struct xen_mem_event_op xen_mem_event_op_t; +DEFINE_XEN_GUEST_HANDLE(xen_mem_event_op_t); + +#define XENMEM_sharing_op 22 +#define XENMEM_sharing_op_nominate_gfn 0 +#define XENMEM_sharing_op_nominate_gref 1 +#define XENMEM_sharing_op_share 2 +#define XENMEM_sharing_op_resume 3 +#define XENMEM_sharing_op_debug_gfn 4 +#define XENMEM_sharing_op_debug_mfn 5 +#define XENMEM_sharing_op_debug_gref 6 +#define XENMEM_sharing_op_add_physmap 7 +#define XENMEM_sharing_op_audit 8 + +#define XENMEM_SHARING_OP_S_HANDLE_INVALID (-10) +#define XENMEM_SHARING_OP_C_HANDLE_INVALID (-9) + +/* The following allows sharing of grant refs. This is useful + * for sharing utilities sitting as "filters" in IO backends + * (e.g. memshr + blktap(2)). The IO backend is only exposed + * to grant references, and this allows sharing of the grefs */ +#define XENMEM_SHARING_OP_FIELD_IS_GREF_FLAG (1ULL << 62) + +#define XENMEM_SHARING_OP_FIELD_MAKE_GREF(field, val) \ + (field) = (XENMEM_SHARING_OP_FIELD_IS_GREF_FLAG | val) +#define XENMEM_SHARING_OP_FIELD_IS_GREF(field) \ + ((field) & XENMEM_SHARING_OP_FIELD_IS_GREF_FLAG) +#define XENMEM_SHARING_OP_FIELD_GET_GREF(field) \ + ((field) & (~XENMEM_SHARING_OP_FIELD_IS_GREF_FLAG)) + +struct xen_mem_sharing_op { + uint8_t op; /* XENMEM_sharing_op_* */ + domid_t domain; + + union { + struct mem_sharing_op_nominate { /* OP_NOMINATE_xxx */ + union { + uint64_aligned_t gfn; /* IN: gfn to nominate */ + uint32_t grant_ref; /* IN: grant ref to nominate */ + } u; + uint64_aligned_t handle; /* OUT: the handle */ + } nominate; + struct mem_sharing_op_share { /* OP_SHARE/ADD_PHYSMAP */ + uint64_aligned_t source_gfn; /* IN: the gfn of the source page */ + uint64_aligned_t source_handle; /* IN: handle to the source page */ + uint64_aligned_t client_gfn; /* IN: the client gfn */ + uint64_aligned_t client_handle; /* IN: handle to the client page */ + domid_t client_domain; /* IN: the client domain id */ + } share; + struct mem_sharing_op_debug { /* OP_DEBUG_xxx */ + union { + uint64_aligned_t gfn; /* IN: gfn to debug */ + uint64_aligned_t mfn; /* IN: mfn to debug */ + uint32_t gref; /* IN: gref to debug */ + } u; + } debug; + } u; +}; +typedef struct xen_mem_sharing_op xen_mem_sharing_op_t; +DEFINE_XEN_GUEST_HANDLE(xen_mem_sharing_op_t); + +/* + * Attempt to stake a claim for a domain on a quantity of pages + * of system RAM, but _not_ assign specific pageframes. Only + * arithmetic is performed so the hypercall is very fast and need + * not be preemptible, thus sidestepping time-of-check-time-of-use + * races for memory allocation. Returns 0 if the hypervisor page + * allocator has atomically and successfully claimed the requested + * number of pages, else non-zero. + * + * Any domain may have only one active claim. When sufficient memory + * has been allocated to resolve the claim, the claim silently expires. + * Claiming zero pages effectively resets any outstanding claim and + * is always successful. + * + * Note that a valid claim may be staked even after memory has been + * allocated for a domain. In this case, the claim is not incremental, + * i.e. if the domain's tot_pages is 3, and a claim is staked for 10, + * only 7 additional pages are claimed. + * + * Caller must be privileged or the hypercall fails. + */ +#define XENMEM_claim_pages 24 + +/* + * XENMEM_claim_pages flags - the are no flags at this time. + * The zero value is appropiate. + */ + +#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */ + +#endif /* __XEN_PUBLIC_MEMORY_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 index 8041ef4..8600d48 100644 --- a/include/xen/sched.h +++ b/include/xen/sched.h @@ -1,145 +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 - */ - -#ifndef __XEN_PUBLIC_SCHED_H__ -#define __XEN_PUBLIC_SCHED_H__ - -#include "event_channel.h" - -/* - * The prototype for this hypercall is: - * LONG_PTR sched_op(int cmd, void *arg) - * @cmd == SCHEDOP_??? (scheduler operation). - * @arg == Operation-specific extra argument(s), as 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_PTR sched_op(int cmd, ULONG_PTR 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 sched_op_compat(). - */ - -/* - * Voluntarily yield the CPU. - * @arg == NULL. - */ -#define SCHEDOP_yield 0 - -/* - * Block execution of this VCPU until an event is received for processing. - * If called with event upcalls masked, this operation will atomically - * reenable event delivery and check for pending events before blocking the - * VCPU. This avoids a "wakeup waiting" race. - * @arg == NULL. - */ -#define SCHEDOP_block 1 - -/* - * Halt execution of this domain (all VCPUs) and notify the system controller. - * @arg == pointer to sched_shutdown structure. - */ -#define SCHEDOP_shutdown 2 -struct sched_shutdown { - unsigned int reason; /* SHUTDOWN_* */ -}; -typedef struct sched_shutdown sched_shutdown_t; -DEFINE_XEN_GUEST_HANDLE(sched_shutdown_t); - -/* - * Poll a set of event-channel ports. Return when one or more are pending. An - * optional timeout may be specified. - * @arg == pointer to sched_poll structure. - */ -#define SCHEDOP_poll 3 -struct sched_poll { - 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); - -/* - * 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 structure. - */ -#define SCHEDOP_remote_shutdown 4 -struct sched_remote_shutdown { - domid_t domain_id; /* Remote domain ID */ - unsigned int reason; /* SHUTDOWN_xxx reason */ -}; -typedef struct sched_remote_shutdown sched_remote_shutdown_t; -DEFINE_XEN_GUEST_HANDLE(sched_remote_shutdown_t); - -/* - * Latch a shutdown code, so that when the domain later shuts down it - * reports this code to the control tools. - * @arg == as for SCHEDOP_shutdown. - */ -#define SCHEDOP_shutdown_code 5 - -/* - * Setup, poke and destroy a domain watchdog timer. - * @arg == pointer to sched_watchdog 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_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. - */ -#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. */ - -#endif /* __XEN_PUBLIC_SCHED_H__ */ - -/* - * Local variables: - * mode: C - * c-set-style: "BSD" - * c-basic-offset: 4 - * tab-width: 4 - * indent-tabs-mode: nil - * End: - */ +/****************************************************************************** + * 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 + */ + +#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_PTR 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_PTR sched_op(int cmd, ULONG_PTR 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_PTR HYPERVISOR_sched_op_compat(enum sched_op cmd, ULONG_PTR 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/trace.h b/include/xen/trace.h index 52289e5..caf0318 100644 --- a/include/xen/trace.h +++ b/include/xen/trace.h @@ -1,230 +1,310 @@ -/****************************************************************************** - * include/public/trace.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. - * - * Mark Williamson, (C) 2004 Intel Research Cambridge - * Copyright (C) 2005 Bin Ren - */ - -#ifndef __XEN_PUBLIC_TRACE_H__ -#define __XEN_PUBLIC_TRACE_H__ - -#define TRACE_EXTRA_MAX 7 -#define TRACE_EXTRA_SHIFT 28 - -/* Trace classes */ -#define TRC_CLS_SHIFT 16 -#define TRC_GEN 0x0001f000 /* General trace */ -#define TRC_SCHED 0x0002f000 /* Xen Scheduler trace */ -#define TRC_DOM0OP 0x0004f000 /* Xen DOM0 operation trace */ -#define TRC_HVM 0x0008f000 /* Xen HVM trace */ -#define TRC_MEM 0x0010f000 /* Xen memory trace */ -#define TRC_PV 0x0020f000 /* Xen PV traces */ -#define TRC_SHADOW 0x0040f000 /* Xen shadow tracing */ -#define TRC_PM 0x0080f000 /* Xen power management trace */ -#define TRC_GUEST 0x0800f000 /* Guest-generated traces */ -#define TRC_ALL 0x0ffff000 -#define TRC_HD_TO_EVENT(x) ((x)&0x0fffffff) -#define TRC_HD_CYCLE_FLAG (1UL<<31) -#define TRC_HD_INCLUDES_CYCLE_COUNT(x) ( !!( (x) & TRC_HD_CYCLE_FLAG ) ) -#define TRC_HD_EXTRA(x) (((x)>>TRACE_EXTRA_SHIFT)&TRACE_EXTRA_MAX) - -/* Trace subclasses */ -#define TRC_SUBCLS_SHIFT 12 - -/* trace subclasses for SVM */ -#define TRC_HVM_ENTRYEXIT 0x00081000 /* VMENTRY and #VMEXIT */ -#define TRC_HVM_HANDLER 0x00082000 /* various HVM handlers */ - -#define TRC_SCHED_MIN 0x00021000 /* Just runstate changes */ -#define TRC_SCHED_CLASS 0x00022000 /* Scheduler-specific */ -#define TRC_SCHED_VERBOSE 0x00028000 /* More inclusive scheduling */ - -/* Trace events per class */ -#define TRC_LOST_RECORDS (TRC_GEN + 1) -#define TRC_TRACE_WRAP_BUFFER (TRC_GEN + 2) -#define TRC_TRACE_CPU_CHANGE (TRC_GEN + 3) -#define TRC_TRACE_IRQ (TRC_GEN + 4) - -#define TRC_SCHED_RUNSTATE_CHANGE (TRC_SCHED_MIN + 1) -#define TRC_SCHED_CONTINUE_RUNNING (TRC_SCHED_MIN + 2) -#define TRC_SCHED_DOM_ADD (TRC_SCHED_VERBOSE + 1) -#define TRC_SCHED_DOM_REM (TRC_SCHED_VERBOSE + 2) -#define TRC_SCHED_SLEEP (TRC_SCHED_VERBOSE + 3) -#define TRC_SCHED_WAKE (TRC_SCHED_VERBOSE + 4) -#define TRC_SCHED_YIELD (TRC_SCHED_VERBOSE + 5) -#define TRC_SCHED_BLOCK (TRC_SCHED_VERBOSE + 6) -#define TRC_SCHED_SHUTDOWN (TRC_SCHED_VERBOSE + 7) -#define TRC_SCHED_CTL (TRC_SCHED_VERBOSE + 8) -#define TRC_SCHED_ADJDOM (TRC_SCHED_VERBOSE + 9) -#define TRC_SCHED_SWITCH (TRC_SCHED_VERBOSE + 10) -#define TRC_SCHED_S_TIMER_FN (TRC_SCHED_VERBOSE + 11) -#define TRC_SCHED_T_TIMER_FN (TRC_SCHED_VERBOSE + 12) -#define TRC_SCHED_DOM_TIMER_FN (TRC_SCHED_VERBOSE + 13) -#define TRC_SCHED_SWITCH_INFPREV (TRC_SCHED_VERBOSE + 14) -#define TRC_SCHED_SWITCH_INFNEXT (TRC_SCHED_VERBOSE + 15) -#define TRC_SCHED_SHUTDOWN_CODE (TRC_SCHED_VERBOSE + 16) - -#define TRC_MEM_PAGE_GRANT_MAP (TRC_MEM + 1) -#define TRC_MEM_PAGE_GRANT_UNMAP (TRC_MEM + 2) -#define TRC_MEM_PAGE_GRANT_TRANSFER (TRC_MEM + 3) -#define TRC_MEM_SET_P2M_ENTRY (TRC_MEM + 4) -#define TRC_MEM_DECREASE_RESERVATION (TRC_MEM + 5) -#define TRC_MEM_POD_POPULATE (TRC_MEM + 16) -#define TRC_MEM_POD_ZERO_RECLAIM (TRC_MEM + 17) -#define TRC_MEM_POD_SUPERPAGE_SPLINTER (TRC_MEM + 18) - - -#define TRC_PV_HYPERCALL (TRC_PV + 1) -#define TRC_PV_TRAP (TRC_PV + 3) -#define TRC_PV_PAGE_FAULT (TRC_PV + 4) -#define TRC_PV_FORCED_INVALID_OP (TRC_PV + 5) -#define TRC_PV_EMULATE_PRIVOP (TRC_PV + 6) -#define TRC_PV_EMULATE_4GB (TRC_PV + 7) -#define TRC_PV_MATH_STATE_RESTORE (TRC_PV + 8) -#define TRC_PV_PAGING_FIXUP (TRC_PV + 9) -#define TRC_PV_GDT_LDT_MAPPING_FAULT (TRC_PV + 10) -#define TRC_PV_PTWR_EMULATION (TRC_PV + 11) -#define TRC_PV_PTWR_EMULATION_PAE (TRC_PV + 12) - /* Indicates that addresses in trace record are 64 bits */ -#define TRC_64_FLAG (0x100) - -#define TRC_SHADOW_NOT_SHADOW (TRC_SHADOW + 1) -#define TRC_SHADOW_FAST_PROPAGATE (TRC_SHADOW + 2) -#define TRC_SHADOW_FAST_MMIO (TRC_SHADOW + 3) -#define TRC_SHADOW_FALSE_FAST_PATH (TRC_SHADOW + 4) -#define TRC_SHADOW_MMIO (TRC_SHADOW + 5) -#define TRC_SHADOW_FIXUP (TRC_SHADOW + 6) -#define TRC_SHADOW_DOMF_DYING (TRC_SHADOW + 7) -#define TRC_SHADOW_EMULATE (TRC_SHADOW + 8) -#define TRC_SHADOW_EMULATE_UNSHADOW_USER (TRC_SHADOW + 9) -#define TRC_SHADOW_EMULATE_UNSHADOW_EVTINJ (TRC_SHADOW + 10) -#define TRC_SHADOW_EMULATE_UNSHADOW_UNHANDLED (TRC_SHADOW + 11) -#define TRC_SHADOW_WRMAP_BF (TRC_SHADOW + 12) -#define TRC_SHADOW_PREALLOC_UNPIN (TRC_SHADOW + 13) -#define TRC_SHADOW_RESYNC_FULL (TRC_SHADOW + 14) -#define TRC_SHADOW_RESYNC_ONLY (TRC_SHADOW + 15) - -/* trace events per subclass */ -#define TRC_HVM_VMENTRY (TRC_HVM_ENTRYEXIT + 0x01) -#define TRC_HVM_VMEXIT (TRC_HVM_ENTRYEXIT + 0x02) -#define TRC_HVM_VMEXIT64 (TRC_HVM_ENTRYEXIT + TRC_64_FLAG + 0x02) -#define TRC_HVM_PF_XEN (TRC_HVM_HANDLER + 0x01) -#define TRC_HVM_PF_XEN64 (TRC_HVM_HANDLER + TRC_64_FLAG + 0x01) -#define TRC_HVM_PF_INJECT (TRC_HVM_HANDLER + 0x02) -#define TRC_HVM_PF_INJECT64 (TRC_HVM_HANDLER + TRC_64_FLAG + 0x02) -#define TRC_HVM_INJ_EXC (TRC_HVM_HANDLER + 0x03) -#define TRC_HVM_INJ_VIRQ (TRC_HVM_HANDLER + 0x04) -#define TRC_HVM_REINJ_VIRQ (TRC_HVM_HANDLER + 0x05) -#define TRC_HVM_IO_READ (TRC_HVM_HANDLER + 0x06) -#define TRC_HVM_IO_WRITE (TRC_HVM_HANDLER + 0x07) -#define TRC_HVM_CR_READ (TRC_HVM_HANDLER + 0x08) -#define TRC_HVM_CR_READ64 (TRC_HVM_HANDLER + TRC_64_FLAG + 0x08) -#define TRC_HVM_CR_WRITE (TRC_HVM_HANDLER + 0x09) -#define TRC_HVM_CR_WRITE64 (TRC_HVM_HANDLER + TRC_64_FLAG + 0x09) -#define TRC_HVM_DR_READ (TRC_HVM_HANDLER + 0x0A) -#define TRC_HVM_DR_WRITE (TRC_HVM_HANDLER + 0x0B) -#define TRC_HVM_MSR_READ (TRC_HVM_HANDLER + 0x0C) -#define TRC_HVM_MSR_WRITE (TRC_HVM_HANDLER + 0x0D) -#define TRC_HVM_CPUID (TRC_HVM_HANDLER + 0x0E) -#define TRC_HVM_INTR (TRC_HVM_HANDLER + 0x0F) -#define TRC_HVM_NMI (TRC_HVM_HANDLER + 0x10) -#define TRC_HVM_SMI (TRC_HVM_HANDLER + 0x11) -#define TRC_HVM_VMMCALL (TRC_HVM_HANDLER + 0x12) -#define TRC_HVM_HLT (TRC_HVM_HANDLER + 0x13) -#define TRC_HVM_INVLPG (TRC_HVM_HANDLER + 0x14) -#define TRC_HVM_INVLPG64 (TRC_HVM_HANDLER + TRC_64_FLAG + 0x14) -#define TRC_HVM_MCE (TRC_HVM_HANDLER + 0x15) -#define TRC_HVM_IOPORT_READ (TRC_HVM_HANDLER + 0x16) -#define TRC_HVM_IOMEM_READ (TRC_HVM_HANDLER + 0x17) -#define TRC_HVM_CLTS (TRC_HVM_HANDLER + 0x18) -#define TRC_HVM_LMSW (TRC_HVM_HANDLER + 0x19) -#define TRC_HVM_LMSW64 (TRC_HVM_HANDLER + TRC_64_FLAG + 0x19) -#define TRC_HVM_RDTSC (TRC_HVM_HANDLER + 0x1a) -#define TRC_HVM_INTR_WINDOW (TRC_HVM_HANDLER + 0x20) -#define TRC_HVM_NPF (TRC_HVM_HANDLER + 0x21) - -#define TRC_HVM_IOPORT_WRITE (TRC_HVM_HANDLER + 0x216) -#define TRC_HVM_IOMEM_WRITE (TRC_HVM_HANDLER + 0x217) - -/* trace subclasses for power management */ -#define TRC_PM_FREQ 0x00801000 /* xen cpu freq events */ -#define TRC_PM_IDLE 0x00802000 /* xen cpu idle events */ - -/* trace events for per class */ -#define TRC_PM_FREQ_CHANGE (TRC_PM_FREQ + 0x01) -#define TRC_PM_IDLE_ENTRY (TRC_PM_IDLE + 0x01) -#define TRC_PM_IDLE_EXIT (TRC_PM_IDLE + 0x02) - -/* This structure represents a single trace buffer record. */ -struct t_rec { - uint32_t event:28; - uint32_t extra_u32:3; /* # entries in trailing extra_u32[] array */ - uint32_t cycles_included:1; /* u.cycles or u.no_cycles? */ - union { - struct { - uint32_t cycles_lo, cycles_hi; /* cycle counter timestamp */ - uint32_t extra_u32[7]; /* event data items */ - } cycles; - struct { - uint32_t extra_u32[7]; /* event data items */ - } nocycles; - } u; -}; - -/* - * This structure contains the metadata for a single trace buffer. The head - * field, indexes into an array of struct t_rec's. - */ -struct t_buf { - /* Assume the data buffer size is X. X is generally not a power of 2. - * CONS and PROD are incremented modulo (2*X): - * 0 <= cons < 2*X - * 0 <= prod < 2*X - * This is done because addition modulo X breaks at 2^32 when X is not a - * power of 2: - * (((2^32 - 1) % X) + 1) % X != (2^32) % X - */ - uint32_t cons; /* Offset of next item to be consumed by control tools. */ - uint32_t prod; /* Offset of next item to be produced by Xen. */ - /* Records follow immediately after the meta-data header. */ -}; - -/* Structure used to pass MFNs to the trace buffers back to trace consumers. - * Offset is an offset into the mapped structure where the mfn list will be held. - * MFNs will be at ((ULONG_PTR *)(t_info))+(t_info->cpu_offset[cpu]). - */ -struct t_info { - uint16_t tbuf_size; /* Size in pages of each trace buffer */ - uint16_t mfn_offset[]; /* Offset within t_info structure of the page list per cpu */ - /* MFN lists immediately after the header */ -}; - -#endif /* __XEN_PUBLIC_TRACE_H__ */ - -/* - * Local variables: - * mode: C - * c-set-style: "BSD" - * c-basic-offset: 4 - * tab-width: 4 - * indent-tabs-mode: nil - * End: - */ +/****************************************************************************** + * include/public/trace.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. + * + * Mark Williamson, (C) 2004 Intel Research Cambridge + * Copyright (C) 2005 Bin Ren + */ + +#ifndef __XEN_PUBLIC_TRACE_H__ +#define __XEN_PUBLIC_TRACE_H__ + +#define TRACE_EXTRA_MAX 7 +#define TRACE_EXTRA_SHIFT 28 + +/* Trace classes */ +#define TRC_CLS_SHIFT 16 +#define TRC_GEN 0x0001f000 /* General trace */ +#define TRC_SCHED 0x0002f000 /* Xen Scheduler trace */ +#define TRC_DOM0OP 0x0004f000 /* Xen DOM0 operation trace */ +#define TRC_HVM 0x0008f000 /* Xen HVM trace */ +#define TRC_MEM 0x0010f000 /* Xen memory trace */ +#define TRC_PV 0x0020f000 /* Xen PV traces */ +#define TRC_SHADOW 0x0040f000 /* Xen shadow tracing */ +#define TRC_HW 0x0080f000 /* Xen hardware-related traces */ +#define TRC_GUEST 0x0800f000 /* Guest-generated traces */ +#define TRC_ALL 0x0ffff000 +#define TRC_HD_TO_EVENT(x) ((x)&0x0fffffff) +#define TRC_HD_CYCLE_FLAG (1UL<<31) +#define TRC_HD_INCLUDES_CYCLE_COUNT(x) ( !!( (x) & TRC_HD_CYCLE_FLAG ) ) +#define TRC_HD_EXTRA(x) (((x)>>TRACE_EXTRA_SHIFT)&TRACE_EXTRA_MAX) + +/* Trace subclasses */ +#define TRC_SUBCLS_SHIFT 12 + +/* trace subclasses for SVM */ +#define TRC_HVM_ENTRYEXIT 0x00081000 /* VMENTRY and #VMEXIT */ +#define TRC_HVM_HANDLER 0x00082000 /* various HVM handlers */ + +#define TRC_SCHED_MIN 0x00021000 /* Just runstate changes */ +#define TRC_SCHED_CLASS 0x00022000 /* Scheduler-specific */ +#define TRC_SCHED_VERBOSE 0x00028000 /* More inclusive scheduling */ + +/* + * The highest 3 bits of the last 12 bits of TRC_SCHED_CLASS above are + * reserved for encoding what scheduler produced the information. The + * actual event is encoded in the last 9 bits. + * + * This means we have 8 scheduling IDs available (which means at most 8 + * schedulers generating events) and, in each scheduler, up to 512 + * different events. + */ +#define TRC_SCHED_ID_BITS 3 +#define TRC_SCHED_ID_SHIFT (TRC_SUBCLS_SHIFT - TRC_SCHED_ID_BITS) +#define TRC_SCHED_ID_MASK (((1UL<cpu_offset[cpu]). + */ +struct t_info { + uint16_t tbuf_size; /* Size in pages of each trace buffer */ + uint16_t mfn_offset[]; /* Offset within t_info structure of the page list per cpu */ + /* MFN lists immediately after the header */ +}; + +#endif /* __XEN_PUBLIC_TRACE_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 index 2e38003..8b3c703 100644 --- a/include/xen/xen-compat.h +++ b/include/xen/xen-compat.h @@ -1,44 +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__ 0x0003020a - -#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__ */ +/****************************************************************************** + * 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__ 0x00040300 + +#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 index d673be1..1d2b940 100644 --- a/include/xen/xen.h +++ b/include/xen/xen.h @@ -1,726 +1,895 @@ -/****************************************************************************** - * 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(__ia64__) -#include "arch-ia64.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); -DEFINE_XEN_GUEST_HANDLE(LONG_PTR); -__DEFINE_XEN_GUEST_HANDLE(ulong, ULONG_PTR); -DEFINE_XEN_GUEST_HANDLE(void); - -DEFINE_XEN_GUEST_HANDLE(uint64_t); -DEFINE_XEN_GUEST_HANDLE(xen_pfn_t); -#endif - -/* - * HYPERCALLS - */ - -#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 - -/* 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. - */ -#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 */ - -/* 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 - -/* - * HYPERVISOR_mmu_update(reqs, count, pdone, 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. - * - * 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. - */ -#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 - * - * 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. - */ -#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; - 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 */ - ULONG_PTR 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 - -/* These are passed as 'flags' to update_va_mapping. They can be ORed. */ -/* When specifying UVMF_MULTI, also OR in a pointer to a CPU bitmap. */ -/* UVMF_LOCAL is merely UVMF_MULTI with a NULL bitmap pointer. */ -#define UVMF_NONE (0UL<<0) /* No flushing at all. */ -#define UVMF_TLB_FLUSH (1UL<<0) /* Flush entire TLB(s). */ -#define UVMF_INVLPG (2UL<<0) /* Flush only one entry. */ -#define UVMF_FLUSHTYPE_MASK (3UL<<0) -#define UVMF_MULTI (0UL<<2) /* Flush subset of TLBs. */ -#define UVMF_LOCAL (0UL<<2) /* Flush local TLB. */ -#define UVMF_ALL (1UL<<2) /* Flush all TLBs. */ - -/* - * Commands to HYPERVISOR_console_io(). - */ -#define CONSOLEIO_write 0 -#define CONSOLEIO_read 1 - -/* - * Commands to HYPERVISOR_vm_assist(). - */ -#define VMASST_CMD_enable 0 -#define VMASST_CMD_disable 1 - -/* 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); - -/* - * Send an array of these to HYPERVISOR_multicall(). - * NB. The fields are natural register size for this architecture. - */ -struct multicall_entry { - ULONG_PTR op, result; - ULONG_PTR args[6]; -}; -typedef struct multicall_entry multicall_entry_t; -DEFINE_XEN_GUEST_HANDLE(multicall_entry_t); - -/* - * Event channel endpoints per domain: - * 1024 if a LONG_PTR is 32 bits; 4096 if a LONG_PTR is 64 bits. - */ -#define NR_EVENT_CHANNELS (sizeof(ULONG_PTR) * sizeof(ULONG_PTR) * 64) - -struct vcpu_time_info { - /* - * Updates to the following values are preceded and followed by an - * increment of 'version'. The guest can therefore detect updates by - * looking for changes to 'version'. If the least-significant bit of - * the version number is set then an update is in progress and the guest - * must wait to read a consistent set of values. - * The correct way to interact with the version number is similar to - * Linux's seqlock: see the implementations of read_seqbegin/read_seqretry. - */ - uint32_t version; - uint32_t pad0; - uint64_t tsc_timestamp; /* TSC at last update of time vals. */ - uint64_t system_time; /* Time, in nanosecs, since boot. */ - /* - * Current system time: - * system_time + - * ((((tsc - tsc_timestamp) << tsc_shift) * tsc_to_system_mul) >> 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; - uint8_t evtchn_upcall_mask; - ULONG_PTR 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 - -/* - * 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_PTR' in the PENDING bitfield array. - */ - ULONG_PTR evtchn_pending[sizeof(ULONG_PTR) * 8]; - ULONG_PTR evtchn_mask[sizeof(ULONG_PTR) * 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 - -/* - * 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, 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. - */ - -#define MAX_GUEST_CMDLINE 1024 -struct start_info { - /* THE FOLLOWING ARE FILLED IN BOTH ON INITIAL BOOT AND ON RESUME. */ - char magic[32]; /* "xen--". */ - ULONG_PTR nr_pages; /* Total pages allocated to this domain. */ - ULONG_PTR 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). */ - ULONG_PTR pt_base; /* VIRTUAL address of page directory. */ - ULONG_PTR nr_pt_frames; /* Number of bootstrap p.t. frames. */ - ULONG_PTR mfn_list; /* VIRTUAL address of page-frame list. */ - ULONG_PTR mod_start; /* VIRTUAL address of pre-loaded module */ - /* (PFN of pre-loaded module if */ - /* SIF_MOD_START_PFN set in flags). */ - ULONG_PTR mod_len; /* Size (bytes) of pre-loaded module. */ - int8_t cmd_line[MAX_GUEST_CMDLINE]; - /* The pfn range here covers both page table and p->m table frames. */ - ULONG_PTR first_p2m_pfn;/* 1st pfn forming initial P->M table. */ - ULONG_PTR 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 - -/* 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; -}; - -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 - - 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 ULONG_PTR 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_cpumap { - XEN_GUEST_HANDLE_64(uint8) bitmap; - uint32_t nr_cpus; -}; -#endif - -#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */ - -#endif /* __XEN_PUBLIC_XEN_H__ */ - -/* - * Local variables: - * mode: C - * c-set-style: "BSD" - * c-basic-offset: 4 - * tab-width: 4 - * indent-tabs-mode: nil - * End: - */ +/****************************************************************************** + * 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_PTR); +__DEFINE_XEN_GUEST_HANDLE(ulong, ULONG_PTR); +#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 */ + ULONG_PTR 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(ULONG_PTR va, u64 val, + * ` enum uvm_flags flags) + * ` + * ` enum neg_errnoval + * ` HYPERVISOR_update_va_mapping_otherdomain(ULONG_PTR 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[], + * ` unsigned int nr_calls); + * + * NB. The fields are natural register size for this architecture. + */ +struct multicall_entry { + ULONG_PTR op, result; + ULONG_PTR args[6]; +}; +typedef struct multicall_entry multicall_entry_t; +DEFINE_XEN_GUEST_HANDLE(multicall_entry_t); + +/* + * Event channel endpoints per domain: + * 1024 if a LONG_PTR is 32 bits; 4096 if a LONG_PTR is 64 bits. + */ +#define NR_EVENT_CHANNELS (sizeof(xen_ulong_t) * sizeof(xen_ulong_t) * 64) + +struct vcpu_time_info { + /* + * Updates to the following values are preceded and followed by an + * increment of 'version'. The guest can therefore detect updates by + * looking for changes to 'version'. If the least-significant bit of + * the version number is set then an update is in progress and the guest + * must wait to read a consistent set of values. + * The correct way to interact with the version number is similar to + * Linux's seqlock: see the implementations of read_seqbegin/read_seqretry. + */ + uint32_t version; + uint32_t pad0; + uint64_t tsc_timestamp; /* TSC at last update of time vals. */ + uint64_t system_time; /* Time, in nanosecs, since boot. */ + /* + * Current system time: + * system_time + + * ((((tsc - tsc_timestamp) << tsc_shift) * tsc_to_system_mul) >> 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_PTR' 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--". */ + ULONG_PTR nr_pages; /* Total pages allocated to this domain. */ + ULONG_PTR 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). */ + ULONG_PTR pt_base; /* VIRTUAL address of page directory. */ + ULONG_PTR nr_pt_frames; /* Number of bootstrap p.t. frames. */ + ULONG_PTR mfn_list; /* VIRTUAL address of page-frame list. */ + ULONG_PTR mod_start; /* VIRTUAL address of pre-loaded module */ + /* (PFN of pre-loaded module if */ + /* SIF_MOD_START_PFN set in flags). */ + ULONG_PTR 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. */ + ULONG_PTR first_p2m_pfn;/* 1st pfn forming initial P->M table. */ + ULONG_PTR 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 ULONG_PTR 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: + */ diff --git a/src/xenbus/shared_info.c b/src/xenbus/shared_info.c index ae5bd6a..b047796 100644 --- a/src/xenbus/shared_info.c +++ b/src/xenbus/shared_info.c @@ -393,19 +393,17 @@ __SharedInfoMap( NTSTATUS status; // This, unfortunately, seems to be a necessary hack to - // get the domain wallclock updated correctly. - // The HVM parameter in question is defined in Xen kernel - // patch 32-on-64-geneva-drivers.patch. + // get the domain wallclock updated correctly on older + // versions of XenServer. #define HVM_PARAM_32BIT 8 #if defined(__i386__) - status = HvmSetParam(HVM_PARAM_32BIT, 1); + (VOID) HvmSetParam(HVM_PARAM_32BIT, 1); #elif defined(__x86_64__) - status = HvmSetParam(HVM_PARAM_32BIT, 0); + (VOID) HvmSetParam(HVM_PARAM_32BIT, 0); #else #error 'Unrecognised architecture' #endif - ASSERT(NT_SUCCESS(status)); #undef HVM_PARAM_32BIT