diff options
| author | royger <royger@FreeBSD.org> | 2015-10-06 11:29:44 +0000 |
|---|---|---|
| committer | royger <royger@FreeBSD.org> | 2015-10-06 11:29:44 +0000 |
| commit | c1bb2e3246dc6cf235535737449549cc16265dda (patch) | |
| tree | 2676d5622b3a36ed986be512a7cda0d369b42c51 /sys/xen | |
| parent | 94c16d891ee59ecdc9436e9a5ce921af7f873910 (diff) | |
| download | FreeBSD-src-c1bb2e3246dc6cf235535737449549cc16265dda.zip FreeBSD-src-c1bb2e3246dc6cf235535737449549cc16265dda.tar.gz | |
Update Xen headers from 4.2 to 4.6
Pull the latest headers for Xen which allow us to add support for ARM and
use new features in FreeBSD.
This is a verbatim copy of the xen/include/public so every headers which
don't exits anymore in the Xen repositories have been dropped.
Note the interface version hasn't been bumped, it will be done in a
follow-up. Although, it requires fix in the code to get it compiled:
- sys/xen/xen_intr.h: evtchn_port_t is already defined in the headers so
drop it.
- {amd64,i386}/include/intr_machdep.h: NR_EVENT_CHANNELS now depends on
xen/interface/event_channel.h, so include it.
- {amd64,i386}/{amd64,i386}/support.S: It's not neccessary to include
machine/intr_machdep.h. This is also fixing build compilation with the
new headers.
- dev/xen/blkfront/blkfront.c: The typedef for blkif_request_segmenthas
been dropped. So directly use struct blkif_request_segment
Finally, modify xen/interface/xen-compat.h to throw a preprocessing error if
__XEN_INTERFACE_VERSION__ is not set. This is allow us to catch any file
where xen/xen-os.h is not correctly included.
Submitted by: Julien Grall <julien.grall@citrix.com>
Reviewed by: royger
Differential Revision: https://reviews.freebsd.org/D3805
Sponsored by: Citrix Systems R&D
Diffstat (limited to 'sys/xen')
69 files changed, 4059 insertions, 2494 deletions
diff --git a/sys/xen/interface/acm.h b/sys/xen/interface/acm.h deleted file mode 100644 index ef62da0..0000000 --- a/sys/xen/interface/acm.h +++ /dev/null @@ -1,228 +0,0 @@ -/* - * acm.h: Xen access control module interface defintions - * - * 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. - * - * Reiner Sailer <sailer@watson.ibm.com> - * Copyright (c) 2005, International Business Machines Corporation. - */ - -#ifndef _XEN_PUBLIC_ACM_H -#define _XEN_PUBLIC_ACM_H - -#include "xen.h" - -/* if ACM_DEBUG defined, all hooks should - * print a short trace message (comment it out - * when not in testing mode ) - */ -/* #define ACM_DEBUG */ - -#ifdef ACM_DEBUG -# define printkd(fmt, args...) printk(fmt,## args) -#else -# define printkd(fmt, args...) -#endif - -/* default ssid reference value if not supplied */ -#define ACM_DEFAULT_SSID 0x0 -#define ACM_DEFAULT_LOCAL_SSID 0x0 - -/* Internal ACM ERROR types */ -#define ACM_OK 0 -#define ACM_UNDEF -1 -#define ACM_INIT_SSID_ERROR -2 -#define ACM_INIT_SOID_ERROR -3 -#define ACM_ERROR -4 - -/* External ACCESS DECISIONS */ -#define ACM_ACCESS_PERMITTED 0 -#define ACM_ACCESS_DENIED -111 -#define ACM_NULL_POINTER_ERROR -200 - -/* - Error codes reported in when trying to test for a new policy - These error codes are reported in an array of tuples where - each error code is followed by a parameter describing the error - more closely, such as a domain id. -*/ -#define ACM_EVTCHN_SHARING_VIOLATION 0x100 -#define ACM_GNTTAB_SHARING_VIOLATION 0x101 -#define ACM_DOMAIN_LOOKUP 0x102 -#define ACM_CHWALL_CONFLICT 0x103 -#define ACM_SSIDREF_IN_USE 0x104 - - -/* primary policy in lower 4 bits */ -#define ACM_NULL_POLICY 0 -#define ACM_CHINESE_WALL_POLICY 1 -#define ACM_SIMPLE_TYPE_ENFORCEMENT_POLICY 2 -#define ACM_POLICY_UNDEFINED 15 - -/* combinations have secondary policy component in higher 4bit */ -#define ACM_CHINESE_WALL_AND_SIMPLE_TYPE_ENFORCEMENT_POLICY \ - ((ACM_SIMPLE_TYPE_ENFORCEMENT_POLICY << 4) | ACM_CHINESE_WALL_POLICY) - -/* policy: */ -#define ACM_POLICY_NAME(X) \ - ((X) == (ACM_NULL_POLICY)) ? "NULL" : \ - ((X) == (ACM_CHINESE_WALL_POLICY)) ? "CHINESE WALL" : \ - ((X) == (ACM_SIMPLE_TYPE_ENFORCEMENT_POLICY)) ? "SIMPLE TYPE ENFORCEMENT" : \ - ((X) == (ACM_CHINESE_WALL_AND_SIMPLE_TYPE_ENFORCEMENT_POLICY)) ? "CHINESE WALL AND SIMPLE TYPE ENFORCEMENT" : \ - "UNDEFINED" - -/* the following policy versions must be increased - * whenever the interpretation of the related - * policy's data structure changes - */ -#define ACM_POLICY_VERSION 3 -#define ACM_CHWALL_VERSION 1 -#define ACM_STE_VERSION 1 - -/* defines a ssid reference used by xen */ -typedef uint32_t ssidref_t; - -/* hooks that are known to domains */ -#define ACMHOOK_none 0 -#define ACMHOOK_sharing 1 - -/* -------security policy relevant type definitions-------- */ - -/* type identifier; compares to "equal" or "not equal" */ -typedef uint16_t domaintype_t; - -/* CHINESE WALL POLICY DATA STRUCTURES - * - * current accumulated conflict type set: - * When a domain is started and has a type that is in - * a conflict set, the conflicting types are incremented in - * the aggregate set. When a domain is destroyed, the - * conflicting types to its type are decremented. - * If a domain has multiple types, this procedure works over - * all those types. - * - * conflict_aggregate_set[i] holds the number of - * running domains that have a conflict with type i. - * - * running_types[i] holds the number of running domains - * that include type i in their ssidref-referenced type set - * - * conflict_sets[i][j] is "0" if type j has no conflict - * with type i and is "1" otherwise. - */ -/* high-16 = version, low-16 = check magic */ -#define ACM_MAGIC 0x0001debc - -/* each offset in bytes from start of the struct they - * are part of */ - -/* V3 of the policy buffer aded a version structure */ -struct acm_policy_version -{ - uint32_t major; - uint32_t minor; -}; - - -/* each buffer consists of all policy information for - * the respective policy given in the policy code - * - * acm_policy_buffer, acm_chwall_policy_buffer, - * and acm_ste_policy_buffer need to stay 32-bit aligned - * because we create binary policies also with external - * tools that assume packed representations (e.g. the java tool) - */ -struct acm_policy_buffer { - uint32_t policy_version; /* ACM_POLICY_VERSION */ - uint32_t magic; - uint32_t len; - uint32_t policy_reference_offset; - uint32_t primary_policy_code; - uint32_t primary_buffer_offset; - uint32_t secondary_policy_code; - uint32_t secondary_buffer_offset; - struct acm_policy_version xml_pol_version; /* add in V3 */ -}; - - -struct acm_policy_reference_buffer { - uint32_t len; -}; - -struct acm_chwall_policy_buffer { - uint32_t policy_version; /* ACM_CHWALL_VERSION */ - uint32_t policy_code; - uint32_t chwall_max_types; - uint32_t chwall_max_ssidrefs; - uint32_t chwall_max_conflictsets; - uint32_t chwall_ssid_offset; - uint32_t chwall_conflict_sets_offset; - uint32_t chwall_running_types_offset; - uint32_t chwall_conflict_aggregate_offset; -}; - -struct acm_ste_policy_buffer { - uint32_t policy_version; /* ACM_STE_VERSION */ - uint32_t policy_code; - uint32_t ste_max_types; - uint32_t ste_max_ssidrefs; - uint32_t ste_ssid_offset; -}; - -struct acm_stats_buffer { - uint32_t magic; - uint32_t len; - uint32_t primary_policy_code; - uint32_t primary_stats_offset; - uint32_t secondary_policy_code; - uint32_t secondary_stats_offset; -}; - -struct acm_ste_stats_buffer { - uint32_t ec_eval_count; - uint32_t gt_eval_count; - uint32_t ec_denied_count; - uint32_t gt_denied_count; - uint32_t ec_cachehit_count; - uint32_t gt_cachehit_count; -}; - -struct acm_ssid_buffer { - uint32_t len; - ssidref_t ssidref; - uint32_t policy_reference_offset; - uint32_t primary_policy_code; - uint32_t primary_max_types; - uint32_t primary_types_offset; - uint32_t secondary_policy_code; - uint32_t secondary_max_types; - uint32_t secondary_types_offset; -}; - -#endif - -/* - * Local variables: - * mode: C - * c-set-style: "BSD" - * c-basic-offset: 4 - * tab-width: 4 - * indent-tabs-mode: nil - * End: - */ diff --git a/sys/xen/interface/acm_ops.h b/sys/xen/interface/acm_ops.h deleted file mode 100644 index 27a8872..0000000 --- a/sys/xen/interface/acm_ops.h +++ /dev/null @@ -1,159 +0,0 @@ -/* - * acm_ops.h: Xen access control module hypervisor commands - * - * 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. - * - * Reiner Sailer <sailer@watson.ibm.com> - * Copyright (c) 2005,2006 International Business Machines Corporation. - */ - -#ifndef __XEN_PUBLIC_ACM_OPS_H__ -#define __XEN_PUBLIC_ACM_OPS_H__ - -#include "xen.h" -#include "acm.h" - -/* - * Make sure you increment the interface version whenever you modify this file! - * This makes sure that old versions of acm tools will stop working in a - * well-defined way (rather than crashing the machine, for instance). - */ -#define ACM_INTERFACE_VERSION 0xAAAA000A - -/************************************************************************/ - -/* - * Prototype for this hypercall is: - * int acm_op(int cmd, void *args) - * @cmd == ACMOP_??? (access control module operation). - * @args == Operation-specific extra arguments (NULL if none). - */ - - -#define ACMOP_setpolicy 1 -struct acm_setpolicy { - /* IN */ - XEN_GUEST_HANDLE_64(void) pushcache; - uint32_t pushcache_size; -}; - - -#define ACMOP_getpolicy 2 -struct acm_getpolicy { - /* IN */ - XEN_GUEST_HANDLE_64(void) pullcache; - uint32_t pullcache_size; -}; - - -#define ACMOP_dumpstats 3 -struct acm_dumpstats { - /* IN */ - XEN_GUEST_HANDLE_64(void) pullcache; - uint32_t pullcache_size; -}; - - -#define ACMOP_getssid 4 -#define ACM_GETBY_ssidref 1 -#define ACM_GETBY_domainid 2 -struct acm_getssid { - /* IN */ - uint32_t get_ssid_by; /* ACM_GETBY_* */ - union { - domaintype_t domainid; - ssidref_t ssidref; - } id; - XEN_GUEST_HANDLE_64(void) ssidbuf; - uint32_t ssidbuf_size; -}; - -#define ACMOP_getdecision 5 -struct acm_getdecision { - /* IN */ - uint32_t get_decision_by1; /* ACM_GETBY_* */ - uint32_t get_decision_by2; /* ACM_GETBY_* */ - union { - domaintype_t domainid; - ssidref_t ssidref; - } id1; - union { - domaintype_t domainid; - ssidref_t ssidref; - } id2; - uint32_t hook; - /* OUT */ - uint32_t acm_decision; -}; - - -#define ACMOP_chgpolicy 6 -struct acm_change_policy { - /* IN */ - XEN_GUEST_HANDLE_64(void) policy_pushcache; - uint32_t policy_pushcache_size; - XEN_GUEST_HANDLE_64(void) del_array; - uint32_t delarray_size; - XEN_GUEST_HANDLE_64(void) chg_array; - uint32_t chgarray_size; - /* OUT */ - /* array with error code */ - XEN_GUEST_HANDLE_64(void) err_array; - uint32_t errarray_size; -}; - -#define ACMOP_relabeldoms 7 -struct acm_relabel_doms { - /* IN */ - XEN_GUEST_HANDLE_64(void) relabel_map; - uint32_t relabel_map_size; - /* OUT */ - XEN_GUEST_HANDLE_64(void) err_array; - uint32_t errarray_size; -}; - -/* future interface to Xen */ -struct xen_acmctl { - uint32_t cmd; - uint32_t interface_version; - union { - struct acm_setpolicy setpolicy; - struct acm_getpolicy getpolicy; - struct acm_dumpstats dumpstats; - struct acm_getssid getssid; - struct acm_getdecision getdecision; - struct acm_change_policy change_policy; - struct acm_relabel_doms relabel_doms; - } u; -}; - -typedef struct xen_acmctl xen_acmctl_t; -DEFINE_XEN_GUEST_HANDLE(xen_acmctl_t); - -#endif /* __XEN_PUBLIC_ACM_OPS_H__ */ - -/* - * Local variables: - * mode: C - * c-set-style: "BSD" - * c-basic-offset: 4 - * tab-width: 4 - * indent-tabs-mode: nil - * End: - */ diff --git a/sys/xen/interface/arch-arm.h b/sys/xen/interface/arch-arm.h index f18bafa..9a96401 100644 --- a/sys/xen/interface/arch-arm.h +++ b/sys/xen/interface/arch-arm.h @@ -27,93 +27,253 @@ #ifndef __XEN_PUBLIC_ARCH_ARM_H__ #define __XEN_PUBLIC_ARCH_ARM_H__ -/* hypercall calling convention - * ---------------------------- +/* + * `incontents 50 arm_abi Hypercall Calling Convention * * A hypercall is issued using the ARM HVC instruction. * * A hypercall can take up to 5 arguments. These are passed in - * registers, the first argument in r0, the second argument in r1, the - * third in r2, the forth in r3 and the fifth in r4. + * registers, the first argument in x0/r0 (for arm64/arm32 guests + * respectively irrespective of whether the underlying hypervisor is + * 32- or 64-bit), the second argument in x1/r1, the third in x2/r2, + * the forth in x3/r3 and the fifth in x4/r4. * - * The hypercall number is passed in r12. + * The hypercall number is passed in r12 (arm) or x16 (arm64). In both + * cases the relevant ARM procedure calling convention specifies this + * is an inter-procedure-call scratch register (e.g. for use in linker + * stubs). This use does not conflict with use during a hypercall. * * The HVC ISS must contain a Xen specific TAG: XEN_HYPERCALL_TAG. * - * The return value is in r0. + * The return value is in x0/r0. + * + * The hypercall will clobber x16/r12 and the argument registers used + * by that hypercall (except r0 which is the return value) i.e. in + * addition to x16/r12 a 2 argument hypercall will clobber x1/r1 and a + * 4 argument hypercall will clobber x1/r1, x2/r2 and x3/r3. + * + * Parameter structs passed to hypercalls are laid out according to + * the Procedure Call Standard for the ARM Architecture (AAPCS, AKA + * EABI) and Procedure Call Standard for the ARM 64-bit Architecture + * (AAPCS64). Where there is a conflict the 64-bit standard should be + * used regardless of guest type. Structures which are passed as + * hypercall arguments are always little endian. * - * The hypercall will clobber r12 and the argument registers used by - * that hypercall (except r0 which is the return value) i.e. a 2 - * argument hypercall will clobber r1 and a 4 argument hypercall will - * clobber r1, r2 and r3. + * All memory which is shared with other entities in the system + * (including the hypervisor and other guests) must reside in memory + * which is mapped as Normal Inner-cacheable. This applies to: + * - hypercall arguments passed via a pointer to guest memory. + * - memory shared via the grant table mechanism (including PV I/O + * rings etc). + * - memory shared with the hypervisor (struct shared_info, struct + * vcpu_info, the grant table, etc). * + * Any Inner cache allocation strategy (Write-Back, Write-Through etc) + * is acceptable. There is no restriction on the Outer-cacheability. + */ + +/* + * `incontents 55 arm_hcall Supported Hypercalls + * + * Xen on ARM makes extensive use of hardware facilities and therefore + * only a subset of the potential hypercalls are required. + * + * Since ARM uses second stage paging any machine/physical addresses + * passed to hypercalls are Guest Physical Addresses (Intermediate + * Physical Addresses) unless otherwise noted. + * + * The following hypercalls (and sub operations) are supported on the + * ARM platform. Other hypercalls should be considered + * unavailable/unsupported. + * + * HYPERVISOR_memory_op + * All generic sub-operations + * + * HYPERVISOR_domctl + * All generic sub-operations, with the exception of: + * * XEN_DOMCTL_irq_permission (not yet implemented) + * + * HYPERVISOR_sched_op + * All generic sub-operations, with the exception of: + * * SCHEDOP_block -- prefer wfi hardware instruction + * + * HYPERVISOR_console_io + * All generic sub-operations + * + * HYPERVISOR_xen_version + * All generic sub-operations + * + * HYPERVISOR_event_channel_op + * All generic sub-operations + * + * HYPERVISOR_physdev_op + * No sub-operations are currenty supported + * + * HYPERVISOR_sysctl + * All generic sub-operations, with the exception of: + * * XEN_SYSCTL_page_offline_op + * * XEN_SYSCTL_get_pmstat + * * XEN_SYSCTL_pm_op + * + * HYPERVISOR_hvm_op + * Exactly these sub-operations are supported: + * * HVMOP_set_param + * * HVMOP_get_param + * + * HYPERVISOR_grant_table_op + * All generic sub-operations + * + * HYPERVISOR_vcpu_op + * Exactly these sub-operations are supported: + * * VCPUOP_register_vcpu_info + * * VCPUOP_register_runstate_memory_area + * + * + * Other notes on the ARM ABI: + * + * - struct start_info is not exported to ARM guests. + * + * - struct shared_info is mapped by ARM guests using the + * HYPERVISOR_memory_op sub-op XENMEM_add_to_physmap, passing + * XENMAPSPACE_shared_info as space parameter. + * + * - All the per-cpu struct vcpu_info are mapped by ARM guests using the + * HYPERVISOR_vcpu_op sub-op VCPUOP_register_vcpu_info, including cpu0 + * struct vcpu_info. + * + * - The grant table is mapped using the HYPERVISOR_memory_op sub-op + * XENMEM_add_to_physmap, passing XENMAPSPACE_grant_table as space + * parameter. The memory range specified under the Xen compatible + * hypervisor node on device tree can be used as target gpfn for the + * mapping. + * + * - Xenstore is initialized by using the two hvm_params + * HVM_PARAM_STORE_PFN and HVM_PARAM_STORE_EVTCHN. They can be read + * with the HYPERVISOR_hvm_op sub-op HVMOP_get_param. + * + * - The paravirtualized console is initialized by using the two + * hvm_params HVM_PARAM_CONSOLE_PFN and HVM_PARAM_CONSOLE_EVTCHN. They + * can be read with the HYPERVISOR_hvm_op sub-op HVMOP_get_param. + * + * - Event channel notifications are delivered using the percpu GIC + * interrupt specified under the Xen compatible hypervisor node on + * device tree. + * + * - The device tree Xen compatible node is fully described under Linux + * at Documentation/devicetree/bindings/arm/xen.txt. */ #define XEN_HYPERCALL_TAG 0XEA1 +#define int64_aligned_t int64_t __attribute__((aligned(8))) +#define uint64_aligned_t uint64_t __attribute__((aligned(8))) #ifndef __ASSEMBLY__ -#define ___DEFINE_XEN_GUEST_HANDLE(name, type) \ - typedef struct { type *p; } __guest_handle_ ## name +#define ___DEFINE_XEN_GUEST_HANDLE(name, type) \ + typedef union { type *p; unsigned long q; } \ + __guest_handle_ ## name; \ + typedef union { type *p; uint64_aligned_t q; } \ + __guest_handle_64_ ## name; +/* + * XEN_GUEST_HANDLE represents a guest pointer, when passed as a field + * in a struct in memory. On ARM is always 8 bytes sizes and 8 bytes + * aligned. + * XEN_GUEST_HANDLE_PARAM represents a guest pointer, when passed as an + * hypercall argument. It is 4 bytes on aarch32 and 8 bytes on aarch64. + */ #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) __guest_handle_64_ ## name #define XEN_GUEST_HANDLE(name) __XEN_GUEST_HANDLE(name) -#define set_xen_guest_handle_raw(hnd, val) do { (hnd).p = val; } while (0) +#define XEN_GUEST_HANDLE_PARAM(name) __guest_handle_ ## name +#define set_xen_guest_handle_raw(hnd, val) \ + do { \ + typeof(&(hnd)) _sxghr_tmp = &(hnd); \ + _sxghr_tmp->q = 0; \ + _sxghr_tmp->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) -struct cpu_user_regs +#if defined(__GNUC__) && !defined(__STRICT_ANSI__) +/* Anonymous union includes both 32- and 64-bit names (e.g., r0/x0). */ +# define __DECL_REG(n64, n32) union { \ + uint64_t n64; \ + uint32_t n32; \ + } +#else +/* Non-gcc sources must always use the proper 64-bit name (e.g., x0). */ +#define __DECL_REG(n64, n32) uint64_t n64 +#endif + +struct vcpu_guest_core_regs { - uint32_t r0; - uint32_t r1; - uint32_t r2; - uint32_t r3; - uint32_t r4; - uint32_t r5; - uint32_t r6; - uint32_t r7; - uint32_t r8; - uint32_t r9; - uint32_t r10; - union { - uint32_t r11; - uint32_t fp; - }; - uint32_t r12; + /* Aarch64 Aarch32 */ + __DECL_REG(x0, r0_usr); + __DECL_REG(x1, r1_usr); + __DECL_REG(x2, r2_usr); + __DECL_REG(x3, r3_usr); + __DECL_REG(x4, r4_usr); + __DECL_REG(x5, r5_usr); + __DECL_REG(x6, r6_usr); + __DECL_REG(x7, r7_usr); + __DECL_REG(x8, r8_usr); + __DECL_REG(x9, r9_usr); + __DECL_REG(x10, r10_usr); + __DECL_REG(x11, r11_usr); + __DECL_REG(x12, r12_usr); - uint32_t sp; /* r13 - SP: Valid for Hyp. frames only, o/w banked (see below) */ + __DECL_REG(x13, sp_usr); + __DECL_REG(x14, lr_usr); - /* r14 - LR: is the same physical register as LR_usr */ - union { - uint32_t lr; /* r14 - LR: Valid for Hyp. Same physical register as lr_usr. */ - uint32_t lr_usr; - }; + __DECL_REG(x15, __unused_sp_hyp); + + __DECL_REG(x16, lr_irq); + __DECL_REG(x17, sp_irq); - uint32_t pc; /* Return IP */ - uint32_t cpsr; /* Return mode */ - uint32_t pad0; /* Doubleword-align the kernel half of the frame */ + __DECL_REG(x18, lr_svc); + __DECL_REG(x19, sp_svc); - /* Outer guest frame only from here on... */ + __DECL_REG(x20, lr_abt); + __DECL_REG(x21, sp_abt); - uint32_t r8_fiq, r9_fiq, r10_fiq, r11_fiq, r12_fiq; + __DECL_REG(x22, lr_und); + __DECL_REG(x23, sp_und); - uint32_t sp_usr; /* LR_usr is the same register as LR, see above */ + __DECL_REG(x24, r8_fiq); + __DECL_REG(x25, r9_fiq); + __DECL_REG(x26, r10_fiq); + __DECL_REG(x27, r11_fiq); + __DECL_REG(x28, r12_fiq); - uint32_t sp_svc, sp_abt, sp_und, sp_irq, sp_fiq; - uint32_t lr_svc, lr_abt, lr_und, lr_irq, lr_fiq; + __DECL_REG(x29, sp_fiq); + __DECL_REG(x30, lr_fiq); - uint32_t spsr_svc, spsr_abt, spsr_und, spsr_irq, spsr_fiq; + /* Return address and mode */ + __DECL_REG(pc64, pc32); /* ELR_EL2 */ + uint32_t cpsr; /* SPSR_EL2 */ + + union { + uint32_t spsr_el1; /* AArch64 */ + uint32_t spsr_svc; /* AArch32 */ + }; - uint32_t pad1; /* Doubleword-align the user half of the frame */ + /* AArch32 guests only */ + uint32_t spsr_fiq, spsr_irq, spsr_und, spsr_abt; + + /* AArch64 guests only */ + uint64_t sp_el0; + uint64_t sp_el1, elr_el1; }; -typedef struct cpu_user_regs cpu_user_regs_t; -DEFINE_XEN_GUEST_HANDLE(cpu_user_regs_t); +typedef struct vcpu_guest_core_regs vcpu_guest_core_regs_t; +DEFINE_XEN_GUEST_HANDLE(vcpu_guest_core_regs_t); + +#undef __DECL_REG typedef uint64_t xen_pfn_t; #define PRI_xen_pfn PRIx64 @@ -122,30 +282,77 @@ typedef uint64_t xen_pfn_t; /* Only one. All other VCPUS must use VCPUOP_register_vcpu_info */ #define XEN_LEGACY_MAX_VCPUS 1 -typedef uint32_t xen_ulong_t; +typedef uint64_t xen_ulong_t; +#define PRI_xen_ulong PRIx64 +#if defined(__XEN__) || defined(__XEN_TOOLS__) struct vcpu_guest_context { - struct cpu_user_regs user_regs; /* User-level CPU registers */ +#define _VGCF_online 0 +#define VGCF_online (1<<_VGCF_online) + uint32_t flags; /* VGCF_* */ + + struct vcpu_guest_core_regs user_regs; /* Core CPU registers */ uint32_t sctlr; - uint32_t ttbr0, ttbr1, ttbcr; + uint64_t ttbcr, ttbr0, ttbr1; }; typedef struct vcpu_guest_context vcpu_guest_context_t; DEFINE_XEN_GUEST_HANDLE(vcpu_guest_context_t); -struct arch_vcpu_info { }; +/* + * struct xen_arch_domainconfig's ABI is covered by + * XEN_DOMCTL_INTERFACE_VERSION. + */ +#define XEN_DOMCTL_CONFIG_GIC_NATIVE 0 +#define XEN_DOMCTL_CONFIG_GIC_V2 1 +#define XEN_DOMCTL_CONFIG_GIC_V3 2 +struct xen_arch_domainconfig { + /* IN/OUT */ + uint8_t gic_version; + /* IN */ + uint32_t nr_spis; + /* + * OUT + * Based on the property clock-frequency in the DT timer node. + * The property may be present when the bootloader/firmware doesn't + * set correctly CNTFRQ which hold the timer frequency. + * + * As it's not possible to trap this register, we have to replicate + * the value in the guest DT. + * + * = 0 => property not present + * > 0 => Value of the property + * + */ + uint32_t clock_frequency; +}; +#endif /* __XEN__ || __XEN_TOOLS__ */ + +struct arch_vcpu_info { +}; typedef struct arch_vcpu_info arch_vcpu_info_t; -struct arch_shared_info { }; +struct arch_shared_info { +}; typedef struct arch_shared_info arch_shared_info_t; typedef uint64_t xen_callback_t; -#endif /* ifndef __ASSEMBLY __ */ +#endif + +#if defined(__XEN__) || defined(__XEN_TOOLS__) -/* PSR bits (CPSR, SPSR)*/ +/* PSR bits (CPSR, SPSR) */ + +#define PSR_THUMB (1<<5) /* Thumb Mode enable */ +#define PSR_FIQ_MASK (1<<6) /* Fast Interrupt mask */ +#define PSR_IRQ_MASK (1<<7) /* Interrupt mask */ +#define PSR_ABT_MASK (1<<8) /* Asynchronous Abort mask */ +#define PSR_BIG_ENDIAN (1<<9) /* arm32: Big Endian Mode */ +#define PSR_DBG_MASK (1<<9) /* arm64: Debug Exception mask */ +#define PSR_IT_MASK (0x0600fc00) /* Thumb If-Then Mask */ +#define PSR_JAZELLE (1<<24) /* Jazelle Mode */ -/* 0-4: Mode */ -#define PSR_MODE_MASK 0x1f +/* 32 bit modes */ #define PSR_MODE_USR 0x10 #define PSR_MODE_FIQ 0x11 #define PSR_MODE_IRQ 0x12 @@ -156,19 +363,102 @@ typedef uint64_t xen_callback_t; #define PSR_MODE_UND 0x1b #define PSR_MODE_SYS 0x1f -#define PSR_THUMB (1<<5) /* Thumb Mode enable */ -#define PSR_FIQ_MASK (1<<6) /* Fast Interrupt mask */ -#define PSR_IRQ_MASK (1<<7) /* Interrupt mask */ -#define PSR_ABT_MASK (1<<8) /* Asynchronous Abort mask */ -#define PSR_BIG_ENDIAN (1<<9) /* Big Endian Mode */ -#define PSR_JAZELLE (1<<24) /* Jazelle Mode */ +/* 64 bit modes */ +#define PSR_MODE_BIT 0x10 /* Set iff AArch32 */ +#define PSR_MODE_EL3h 0x0d +#define PSR_MODE_EL3t 0x0c +#define PSR_MODE_EL2h 0x09 +#define PSR_MODE_EL2t 0x08 +#define PSR_MODE_EL1h 0x05 +#define PSR_MODE_EL1t 0x04 +#define PSR_MODE_EL0t 0x00 + +#define PSR_GUEST32_INIT (PSR_ABT_MASK|PSR_FIQ_MASK|PSR_IRQ_MASK|PSR_MODE_SVC) +#define PSR_GUEST64_INIT (PSR_ABT_MASK|PSR_FIQ_MASK|PSR_IRQ_MASK|PSR_MODE_EL1h) + +#define SCTLR_GUEST_INIT 0x00c50078 + +/* + * Virtual machine platform (memory layout, interrupts) + * + * These are defined for consistency between the tools and the + * hypervisor. Guests must not rely on these hardcoded values but + * should instead use the FDT. + */ + +/* Physical Address Space */ + +/* + * vGIC mappings: Only one set of mapping is used by the guest. + * Therefore they can overlap. + */ + +/* vGIC v2 mappings */ +#define GUEST_GICD_BASE 0x03001000ULL +#define GUEST_GICD_SIZE 0x00001000ULL +#define GUEST_GICC_BASE 0x03002000ULL +#define GUEST_GICC_SIZE 0x00000100ULL + +/* vGIC v3 mappings */ +#define GUEST_GICV3_GICD_BASE 0x03001000ULL +#define GUEST_GICV3_GICD_SIZE 0x00010000ULL + +#define GUEST_GICV3_RDIST_STRIDE 0x20000ULL +#define GUEST_GICV3_RDIST_REGIONS 1 + +#define GUEST_GICV3_GICR0_BASE 0x03020000ULL /* vCPU0 - vCPU127 */ +#define GUEST_GICV3_GICR0_SIZE 0x01000000ULL + +/* + * 16MB == 4096 pages reserved for guest to use as a region to map its + * grant table in. + */ +#define GUEST_GNTTAB_BASE 0x38000000ULL +#define GUEST_GNTTAB_SIZE 0x01000000ULL + +#define GUEST_MAGIC_BASE 0x39000000ULL +#define GUEST_MAGIC_SIZE 0x01000000ULL + +#define GUEST_RAM_BANKS 2 + +#define GUEST_RAM0_BASE 0x40000000ULL /* 3GB of low RAM @ 1GB */ +#define GUEST_RAM0_SIZE 0xc0000000ULL + +#define GUEST_RAM1_BASE 0x0200000000ULL /* 1016GB of RAM @ 8GB */ +#define GUEST_RAM1_SIZE 0xfe00000000ULL + +#define GUEST_RAM_BASE GUEST_RAM0_BASE /* Lowest RAM address */ +/* Largest amount of actual RAM, not including holes */ +#define GUEST_RAM_MAX (GUEST_RAM0_SIZE + GUEST_RAM1_SIZE) +/* Suitable for e.g. const uint64_t ramfoo[] = GUEST_RAM_BANK_FOOS; */ +#define GUEST_RAM_BANK_BASES { GUEST_RAM0_BASE, GUEST_RAM1_BASE } +#define GUEST_RAM_BANK_SIZES { GUEST_RAM0_SIZE, GUEST_RAM1_SIZE } + +/* Interrupts */ +#define GUEST_TIMER_VIRT_PPI 27 +#define GUEST_TIMER_PHYS_S_PPI 29 +#define GUEST_TIMER_PHYS_NS_PPI 30 +#define GUEST_EVTCHN_PPI 31 + +/* PSCI functions */ +#define PSCI_cpu_suspend 0 +#define PSCI_cpu_off 1 +#define PSCI_cpu_on 2 +#define PSCI_migrate 3 + +#endif + +#ifndef __ASSEMBLY__ +/* Stub definition of PMU structure */ +typedef struct xen_pmu_arch { uint8_t dummy; } xen_pmu_arch_t; +#endif #endif /* __XEN_PUBLIC_ARCH_ARM_H__ */ /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/arch-arm/hvm/save.h b/sys/xen/interface/arch-arm/hvm/save.h index ec61298..75b8e65 100644 --- a/sys/xen/interface/arch-arm/hvm/save.h +++ b/sys/xen/interface/arch-arm/hvm/save.h @@ -31,7 +31,7 @@ /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/arch-powerpc.h b/sys/xen/interface/arch-powerpc.h deleted file mode 100644 index d92532f..0000000 --- a/sys/xen/interface/arch-powerpc.h +++ /dev/null @@ -1,120 +0,0 @@ -/* - * 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) IBM Corp. 2005, 2006 - * - * Authors: Hollis Blanchard <hollisb@us.ibm.com> - */ - -#include "xen.h" - -#ifndef __XEN_PUBLIC_ARCH_PPC_64_H__ -#define __XEN_PUBLIC_ARCH_PPC_64_H__ - -#define ___DEFINE_XEN_GUEST_HANDLE(name, type) \ - typedef struct { \ - int __pad[(sizeof (long long) - sizeof (void *)) / sizeof (int)]; \ - type *p; \ - } __attribute__((__aligned__(8))) __guest_handle_ ## name - -#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 set_xen_guest_handle(hnd, val) \ - do { \ - if (sizeof ((hnd).__pad)) \ - (hnd).__pad[0] = 0; \ - (hnd).p = val; \ - } while (0) - -#ifdef __XEN_TOOLS__ -#define get_xen_guest_handle(val, hnd) do { val = (hnd).p; } while (0) -#endif - -#ifndef __ASSEMBLY__ -typedef unsigned long long xen_pfn_t; -#define PRI_xen_pfn "llx" -#endif - -/* - * Pointers and other address fields inside interface structures are padded to - * 64 bits. This means that field alignments aren't different between 32- and - * 64-bit architectures. - */ -/* NB. Multi-level macro ensures __LINE__ is expanded before concatenation. */ -#define __MEMORY_PADDING(_X) -#define _MEMORY_PADDING(_X) __MEMORY_PADDING(_X) -#define MEMORY_PADDING _MEMORY_PADDING(__LINE__) - -/* And the trap vector is... */ -#define TRAP_INSTR "li 0,-1; sc" /* XXX just "sc"? */ - -#ifndef __ASSEMBLY__ - -#define XENCOMM_INLINE_FLAG (1UL << 63) - -typedef uint64_t xen_ulong_t; - -/* User-accessible registers: nost of these need to be saved/restored - * for every nested Xen invocation. */ -struct cpu_user_regs -{ - uint64_t gprs[32]; - uint64_t lr; - uint64_t ctr; - uint64_t srr0; - uint64_t srr1; - uint64_t pc; - uint64_t msr; - uint64_t fpscr; /* XXX Is this necessary */ - uint64_t xer; - uint64_t hid4; /* debug only */ - uint64_t dar; /* debug only */ - uint32_t dsisr; /* debug only */ - uint32_t cr; - uint32_t __pad; /* good spot for another 32bit reg */ - uint32_t entry_vector; -}; -typedef struct cpu_user_regs cpu_user_regs_t; - -typedef uint64_t tsc_timestamp_t; /* RDTSC timestamp */ /* XXX timebase */ - -/* ONLY used to communicate with dom0! See also struct exec_domain. */ -struct vcpu_guest_context { - cpu_user_regs_t user_regs; /* User-level CPU registers */ - uint64_t sdr1; /* Pagetable base */ - /* XXX etc */ -}; -typedef struct vcpu_guest_context vcpu_guest_context_t; -DEFINE_XEN_GUEST_HANDLE(vcpu_guest_context_t); - -struct arch_shared_info { - uint64_t boot_timebase; -}; - -struct arch_vcpu_info { -}; - -/* Support for multi-processor guests. */ -#define MAX_VIRT_CPUS 32 -#endif - -#endif diff --git a/sys/xen/interface/arch-x86/cpuid.h b/sys/xen/interface/arch-x86/cpuid.h index d9bd627..d709340 100644 --- a/sys/xen/interface/arch-x86/cpuid.h +++ b/sys/xen/interface/arch-x86/cpuid.h @@ -30,12 +30,20 @@ #ifndef __XEN_PUBLIC_ARCH_X86_CPUID_H__ #define __XEN_PUBLIC_ARCH_X86_CPUID_H__ -/* Xen identification leaves start at 0x40000000. */ +/* + * For compatibility with other hypervisor interfaces, the Xen cpuid leaves + * can be found at the first otherwise unused 0x100 aligned boundary starting + * from 0x40000000. + * + * e.g If viridian extensions are enabled for an HVM domain, the Xen cpuid + * leaves will start at 0x40000100 + */ + #define XEN_CPUID_FIRST_LEAF 0x40000000 #define XEN_CPUID_LEAF(i) (XEN_CPUID_FIRST_LEAF + (i)) /* - * Leaf 1 (0x40000000) + * Leaf 1 (0x40000x00) * EAX: Largest Xen-information leaf. All leaves up to an including @EAX * are supported by the Xen host. * EBX-EDX: "XenVMMXenVMM" signature, allowing positive identification @@ -46,14 +54,14 @@ #define XEN_CPUID_SIGNATURE_EDX 0x4d4d566e /* "nVMM" */ /* - * Leaf 2 (0x40000001) + * Leaf 2 (0x40000x01) * EAX[31:16]: Xen major version. * EAX[15: 0]: Xen minor version. * EBX-EDX: Reserved (currently all zeroes). */ /* - * Leaf 3 (0x40000002) + * Leaf 3 (0x40000x02) * EAX: Number of hypercall transfer pages. This register is always guaranteed * to specify one hypercall page. * EBX: Base address of Xen-specific MSRs. @@ -65,4 +73,18 @@ #define _XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD 0 #define XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD (1u<<0) +/* + * Leaf 5 (0x40000x04) + * HVM-specific features + * EAX: Features + * EBX: vcpu id (iff EAX has XEN_HVM_CPUID_VCPU_ID_PRESENT flag) + */ +#define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0) /* Virtualized APIC registers */ +#define XEN_HVM_CPUID_X2APIC_VIRT (1u << 1) /* Virtualized x2APIC accesses */ +/* Memory mapped from other domains has valid IOMMU entries */ +#define XEN_HVM_CPUID_IOMMU_MAPPINGS (1u << 2) +#define XEN_HVM_CPUID_VCPU_ID_PRESENT (1u << 3) /* vcpu id is present in EBX */ + +#define XEN_CPUID_MAX_NUM_LEAVES 4 + #endif /* __XEN_PUBLIC_ARCH_X86_CPUID_H__ */ diff --git a/sys/xen/interface/arch-x86/hvm/save.h b/sys/xen/interface/arch-x86/hvm/save.h index 9ae645d..efb0b62 100644 --- a/sys/xen/interface/arch-x86/hvm/save.h +++ b/sys/xen/interface/arch-x86/hvm/save.h @@ -269,15 +269,18 @@ struct hvm_hw_cpu_compat { }; static inline int _hvm_hw_fix_cpu(void *h) { - struct hvm_hw_cpu *new=h; - struct hvm_hw_cpu_compat *old=h; + + union hvm_hw_cpu_union { + struct hvm_hw_cpu nat; + struct hvm_hw_cpu_compat cmp; + } *ucpu = (union hvm_hw_cpu_union *)h; /* If we copy from the end backwards, we should * be able to do the modification in-place */ - new->error_code=old->error_code; - new->pending_event=old->pending_event; - new->tsc=old->tsc; - new->msr_tsc_aux=0; + ucpu->nat.error_code = ucpu->cmp.error_code; + ucpu->nat.pending_event = ucpu->cmp.pending_event; + ucpu->nat.tsc = ucpu->cmp.tsc; + ucpu->nat.msr_tsc_aux = 0; return 0; } @@ -541,7 +544,7 @@ DECLARE_HVM_SAVE_TYPE(MTRR, 14, struct hvm_hw_mtrr); */ struct hvm_hw_cpu_xsave { - uint64_t xfeature_mask; + uint64_t xfeature_mask; /* Ignored */ uint64_t xcr0; /* Updated by XSETBV */ uint64_t xcr0_accum; /* Updated by XSETBV */ struct { @@ -565,6 +568,8 @@ struct hvm_hw_cpu_xsave { struct hvm_viridian_domain_context { uint64_t hypercall_gpa; uint64_t guest_os_id; + uint64_t time_ref_count; + uint64_t reference_tsc; }; DECLARE_HVM_SAVE_TYPE(VIRIDIAN_DOMAIN, 15, struct hvm_viridian_domain_context); @@ -577,13 +582,49 @@ DECLARE_HVM_SAVE_TYPE(VIRIDIAN_VCPU, 17, struct hvm_viridian_vcpu_context); struct hvm_vmce_vcpu { uint64_t caps; + uint64_t mci_ctl2_bank0; + uint64_t mci_ctl2_bank1; }; DECLARE_HVM_SAVE_TYPE(VMCE_VCPU, 18, struct hvm_vmce_vcpu); +struct hvm_tsc_adjust { + uint64_t tsc_adjust; +}; + +DECLARE_HVM_SAVE_TYPE(TSC_ADJUST, 19, struct hvm_tsc_adjust); + + +struct hvm_msr { + uint32_t count; + struct hvm_one_msr { + uint32_t index; + uint32_t _rsvd; + uint64_t val; +#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + } msr[]; +#elif defined(__GNUC__) + } msr[0]; +#else + } msr[1 /* variable size */]; +#endif +}; + +#define CPU_MSR_CODE 20 + /* * Largest type-code in use */ -#define HVM_SAVE_CODE_MAX 18 +#define HVM_SAVE_CODE_MAX 20 #endif /* __XEN_PUBLIC_HVM_SAVE_X86_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/sys/xen/interface/arch-x86/pmu.h b/sys/xen/interface/arch-x86/pmu.h new file mode 100644 index 0000000..68ebf12 --- /dev/null +++ b/sys/xen/interface/arch-x86/pmu.h @@ -0,0 +1,167 @@ +/* + * 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) 2015 Oracle and/or its affiliates. All rights reserved. + */ + +#ifndef __XEN_PUBLIC_ARCH_X86_PMU_H__ +#define __XEN_PUBLIC_ARCH_X86_PMU_H__ + +/* x86-specific PMU definitions */ + +/* AMD PMU registers and structures */ +struct xen_pmu_amd_ctxt { + /* + * Offsets to counter and control MSRs (relative to xen_pmu_arch.c.amd). + * For PV(H) guests these fields are RO. + */ + uint32_t counters; + uint32_t ctrls; + + /* Counter MSRs */ +#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + uint64_t regs[]; +#elif defined(__GNUC__) + uint64_t regs[0]; +#endif +}; +typedef struct xen_pmu_amd_ctxt xen_pmu_amd_ctxt_t; +DEFINE_XEN_GUEST_HANDLE(xen_pmu_amd_ctxt_t); + +/* Intel PMU registers and structures */ +struct xen_pmu_cntr_pair { + uint64_t counter; + uint64_t control; +}; +typedef struct xen_pmu_cntr_pair xen_pmu_cntr_pair_t; +DEFINE_XEN_GUEST_HANDLE(xen_pmu_cntr_pair_t); + +struct xen_pmu_intel_ctxt { + /* + * Offsets to fixed and architectural counter MSRs (relative to + * xen_pmu_arch.c.intel). + * For PV(H) guests these fields are RO. + */ + uint32_t fixed_counters; + uint32_t arch_counters; + + /* PMU registers */ + uint64_t global_ctrl; + uint64_t global_ovf_ctrl; + uint64_t global_status; + uint64_t fixed_ctrl; + uint64_t ds_area; + uint64_t pebs_enable; + uint64_t debugctl; + + /* Fixed and architectural counter MSRs */ +#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + uint64_t regs[]; +#elif defined(__GNUC__) + uint64_t regs[0]; +#endif +}; +typedef struct xen_pmu_intel_ctxt xen_pmu_intel_ctxt_t; +DEFINE_XEN_GUEST_HANDLE(xen_pmu_intel_ctxt_t); + +/* Sampled domain's registers */ +struct xen_pmu_regs { + uint64_t ip; + uint64_t sp; + uint64_t flags; + uint16_t cs; + uint16_t ss; + uint8_t cpl; + uint8_t pad[3]; +}; +typedef struct xen_pmu_regs xen_pmu_regs_t; +DEFINE_XEN_GUEST_HANDLE(xen_pmu_regs_t); + +/* PMU flags */ +#define PMU_CACHED (1<<0) /* PMU MSRs are cached in the context */ +#define PMU_SAMPLE_USER (1<<1) /* Sample is from user or kernel mode */ +#define PMU_SAMPLE_REAL (1<<2) /* Sample is from realmode */ +#define PMU_SAMPLE_PV (1<<3) /* Sample from a PV guest */ + +/* + * Architecture-specific information describing state of the processor at + * the time of PMU interrupt. + * Fields of this structure marked as RW for guest should only be written by + * the guest when PMU_CACHED bit in pmu_flags is set (which is done by the + * hypervisor during PMU interrupt). Hypervisor will read updated data in + * XENPMU_flush hypercall and clear PMU_CACHED bit. + */ +struct xen_pmu_arch { + union { + /* + * Processor's registers at the time of interrupt. + * WO for hypervisor, RO for guests. + */ + struct xen_pmu_regs regs; + /* Padding for adding new registers to xen_pmu_regs in the future */ +#define XENPMU_REGS_PAD_SZ 64 + uint8_t pad[XENPMU_REGS_PAD_SZ]; + } r; + + /* WO for hypervisor, RO for guest */ + uint64_t pmu_flags; + + /* + * APIC LVTPC register. + * RW for both hypervisor and guest. + * Only APIC_LVT_MASKED bit is loaded by the hypervisor into hardware + * during XENPMU_flush or XENPMU_lvtpc_set. + */ + union { + uint32_t lapic_lvtpc; + uint64_t pad; + } l; + + /* + * Vendor-specific PMU registers. + * RW for both hypervisor and guest (see exceptions above). + * Guest's updates to this field are verified and then loaded by the + * hypervisor into hardware during XENPMU_flush + */ + union { + struct xen_pmu_amd_ctxt amd; + struct xen_pmu_intel_ctxt intel; + + /* + * Padding for contexts (fixed parts only, does not include MSR banks + * that are specified by offsets) + */ +#define XENPMU_CTXT_PAD_SZ 128 + uint8_t pad[XENPMU_CTXT_PAD_SZ]; + } c; +}; +typedef struct xen_pmu_arch xen_pmu_arch_t; +DEFINE_XEN_GUEST_HANDLE(xen_pmu_arch_t); + +#endif /* __XEN_PUBLIC_ARCH_X86_PMU_H__ */ +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ + diff --git a/sys/xen/interface/arch-x86/xen-mca.h b/sys/xen/interface/arch-x86/xen-mca.h index dca6b3e..04382ed 100644 --- a/sys/xen/interface/arch-x86/xen-mca.h +++ b/sys/xen/interface/arch-x86/xen-mca.h @@ -414,7 +414,7 @@ struct xen_mc_mceinject { struct xen_mc_inject_v2 { uint32_t flags; - struct xenctl_cpumap cpumap; + struct xenctl_bitmap cpumap; }; #endif diff --git a/sys/xen/interface/arch-x86/xen-x86_32.h b/sys/xen/interface/arch-x86/xen-x86_32.h index 906e74a..be9a6c6 100644 --- a/sys/xen/interface/arch-x86/xen-x86_32.h +++ b/sys/xen/interface/arch-x86/xen-x86_32.h @@ -104,6 +104,7 @@ do { if ( sizeof(hnd) == 8 ) *(uint64_t *)&(hnd) = 0; \ (hnd).p = val; \ } while ( 0 ) +#define int64_aligned_t int64_t __attribute__((aligned(8))) #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) @@ -163,7 +164,7 @@ typedef struct xen_callback xen_callback_t; /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/arch-x86/xen-x86_64.h b/sys/xen/interface/arch-x86/xen-x86_64.h index 2654d24..1c4e159 100644 --- a/sys/xen/interface/arch-x86/xen-x86_64.h +++ b/sys/xen/interface/arch-x86/xen-x86_64.h @@ -194,7 +194,7 @@ typedef unsigned long xen_callback_t; /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/arch-x86/xen.h b/sys/xen/interface/arch-x86/xen.h index 1c186d7..2ecc9c9 100644 --- a/sys/xen/interface/arch-x86/xen.h +++ b/sys/xen/interface/arch-x86/xen.h @@ -38,12 +38,21 @@ 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) @@ -61,8 +70,12 @@ typedef unsigned long xen_pfn_t; #define PRI_xen_pfn "lx" #endif +#define XEN_HAVE_PV_GUEST_ENTRY 1 + +#define XEN_HAVE_PV_UPCALL_MASK 1 + /* - * SEGMENT DESCRIPTOR TABLES + * `incontents 200 segdesc Segment Descriptor Tables */ /* * ` enum neg_errnoval @@ -74,17 +87,31 @@ typedef unsigned long xen_pfn_t; * start of the GDT because some stupid OSes export hard-coded selector values * in their ABI. These hard-coded values are always near the start of the GDT, * so Xen places itself out of the way, at the far end of the GDT. + * + * NB The LDT is set using the MMUEXT_SET_LDT op of HYPERVISOR_mmuext_op */ #define FIRST_RESERVED_GDT_PAGE 14 #define FIRST_RESERVED_GDT_BYTE (FIRST_RESERVED_GDT_PAGE * 4096) #define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8) + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_update_descriptor(u64 pa, u64 desc); + * ` + * ` @pa The machine physical address of the descriptor to + * ` update. Must be either a descriptor page or writable. + * ` @desc The descriptor value to update, in the same format as a + * ` native descriptor table entry. + */ + /* Maximum number of virtual CPUs in legacy multi-processor guests. */ #define XEN_LEGACY_MAX_VCPUS 32 #ifndef __ASSEMBLY__ typedef unsigned long xen_ulong_t; +#define PRI_xen_ulong "lx" /* * ` enum neg_errnoval @@ -127,6 +154,15 @@ typedef uint64_t tsc_timestamp_t; /* RDTSC timestamp */ /* * The following is all CPU context. Note that the fpu_ctxt block is filled * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used. + * + * Also note that when calling DOMCTL_setvcpucontext and VCPU_initialise + * for HVM and PVH guests, not all information in this structure is updated: + * + * - For HVM guests, the structures read include: fpu_ctxt (if + * VGCT_I387_VALID is set), flags, user_regs, debugreg[*] + * + * - PVH guests are the same as HVM guests, but additionally use ctrlreg[3] to + * set cr3. All other fields not used should be set to 0. */ struct vcpu_guest_context { /* FPU registers come first so they can be aligned for FXSAVE/FXRSTOR. */ @@ -184,14 +220,58 @@ typedef struct vcpu_guest_context vcpu_guest_context_t; DEFINE_XEN_GUEST_HANDLE(vcpu_guest_context_t); struct arch_shared_info { - unsigned long max_pfn; /* max pfn that appears in table */ - /* Frame containing list of mfns containing list of mfns containing p2m. */ + /* + * Number of valid entries in the p2m table(s) anchored at + * pfn_to_mfn_frame_list_list and/or p2m_vaddr. + */ + unsigned long max_pfn; + /* + * Frame containing list of mfns containing list of mfns containing p2m. + * A value of 0 indicates it has not yet been set up, ~0 indicates it has + * been set to invalid e.g. due to the p2m being too large for the 3-level + * p2m tree. In this case the linear mapper p2m list anchored at p2m_vaddr + * is to be used. + */ xen_pfn_t pfn_to_mfn_frame_list_list; unsigned long nmi_reason; - uint64_t pad[32]; + /* + * Following three fields are valid if p2m_cr3 contains a value different + * from 0. + * p2m_cr3 is the root of the address space where p2m_vaddr is valid. + * p2m_cr3 is in the same format as a cr3 value in the vcpu register state + * and holds the folded machine frame number (via xen_pfn_to_cr3) of a + * L3 or L4 page table. + * p2m_vaddr holds the virtual address of the linear p2m list. All entries + * in the range [0...max_pfn[ are accessible via this pointer. + * p2m_generation will be incremented by the guest before and after each + * change of the mappings of the p2m list. p2m_generation starts at 0 and + * a value with the least significant bit set indicates that a mapping + * update is in progress. This allows guest external software (e.g. in Dom0) + * to verify that read mappings are consistent and whether they have changed + * since the last check. + * Modifying a p2m element in the linear p2m list is allowed via an atomic + * write only. + */ + unsigned long p2m_cr3; /* cr3 value of the p2m address space */ + unsigned long p2m_vaddr; /* virtual address of the p2m list */ + unsigned long p2m_generation; /* generation count of p2m mapping */ +#ifdef __i386__ + /* There's no room for this field in the generic structure. */ + uint32_t wc_sec_hi; +#endif }; typedef struct arch_shared_info arch_shared_info_t; +#if defined(__XEN__) || defined(__XEN_TOOLS__) +/* + * struct xen_arch_domainconfig's ABI is covered by + * XEN_DOMCTL_INTERFACE_VERSION. + */ +struct xen_arch_domainconfig { + char dummy; +}; +#endif + #endif /* !__ASSEMBLY__ */ /* @@ -229,7 +309,7 @@ typedef struct arch_shared_info arch_shared_info_t; /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/callback.h b/sys/xen/interface/callback.h index f4962f6..8f93788 100644 --- a/sys/xen/interface/callback.h +++ b/sys/xen/interface/callback.h @@ -36,7 +36,7 @@ * @extra_args == Operation-specific extra arguments (NULL if none). */ -/* ia64, x86: Callback for event delivery. */ +/* x86: Callback for event delivery. */ #define CALLBACKTYPE_event 0 /* x86: Failsafe callback when guest state cannot be restored by Xen. */ @@ -113,7 +113,7 @@ DEFINE_XEN_GUEST_HANDLE(callback_unregister_t); /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/dom0_ops.h b/sys/xen/interface/dom0_ops.h index 5d2b324..c8d764e 100644 --- a/sys/xen/interface/dom0_ops.h +++ b/sys/xen/interface/dom0_ops.h @@ -112,7 +112,7 @@ DEFINE_XEN_GUEST_HANDLE(dom0_op_t); /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/domctl.h b/sys/xen/interface/domctl.h index 240ceb9..675f021 100644 --- a/sys/xen/interface/domctl.h +++ b/sys/xen/interface/domctl.h @@ -34,8 +34,10 @@ #include "xen.h" #include "grant_table.h" +#include "hvm/save.h" +#include "memory.h" -#define XEN_DOMCTL_INTERFACE_VERSION 0x00000008 +#define XEN_DOMCTL_INTERFACE_VERSION 0x0000000b /* * NB. xen_domctl.domain is an IN/OUT parameter for this operation. @@ -46,7 +48,7 @@ struct xen_domctl_createdomain { /* IN parameters */ uint32_t ssidref; xen_domain_handle_t handle; - /* Is this an HVM guest (as opposed to a PV guest)? */ + /* Is this an HVM guest (as opposed to a PVH or PV guest)? */ #define _XEN_DOMCTL_CDF_hvm_guest 0 #define XEN_DOMCTL_CDF_hvm_guest (1U<<_XEN_DOMCTL_CDF_hvm_guest) /* Use hardware-assisted paging if available? */ @@ -58,7 +60,11 @@ struct xen_domctl_createdomain { /* Disable out-of-sync shadow page tables? */ #define _XEN_DOMCTL_CDF_oos_off 3 #define XEN_DOMCTL_CDF_oos_off (1U<<_XEN_DOMCTL_CDF_oos_off) + /* Is this a PVH guest (as opposed to an HVM or PV guest)? */ +#define _XEN_DOMCTL_CDF_pvh_guest 4 +#define XEN_DOMCTL_CDF_pvh_guest (1U<<_XEN_DOMCTL_CDF_pvh_guest) uint32_t flags; + struct xen_arch_domainconfig config; }; typedef struct xen_domctl_createdomain xen_domctl_createdomain_t; DEFINE_XEN_GUEST_HANDLE(xen_domctl_createdomain_t); @@ -88,17 +94,22 @@ struct xen_domctl_getdomaininfo { /* Being debugged. */ #define _XEN_DOMINF_debugged 6 #define XEN_DOMINF_debugged (1U<<_XEN_DOMINF_debugged) +/* domain is PVH */ +#define _XEN_DOMINF_pvh_guest 7 +#define XEN_DOMINF_pvh_guest (1U<<_XEN_DOMINF_pvh_guest) /* XEN_DOMINF_shutdown guest-supplied code. */ #define XEN_DOMINF_shutdownmask 255 #define XEN_DOMINF_shutdownshift 16 uint32_t flags; /* XEN_DOMINF_* */ uint64_aligned_t tot_pages; uint64_aligned_t max_pages; + uint64_aligned_t outstanding_pages; uint64_aligned_t shr_pages; uint64_aligned_t paged_pages; uint64_aligned_t shared_info_frame; /* GMFN of shared_info struct */ uint64_aligned_t cpu_time; uint32_t nr_online_vcpus; /* Number of VCPUs currently online. */ +#define XEN_INVALID_MAX_VCPU_ID (~0U) /* Domain has no vcpus? */ uint32_t max_vcpu_id; /* Maximum VCPUID in use by this domain. */ uint32_t ssidref; xen_domain_handle_t handle; @@ -135,30 +146,9 @@ DEFINE_XEN_GUEST_HANDLE(xen_domctl_getmemlist_t); #define XEN_DOMCTL_PFINFO_LPINTAB (0x1U<<31) #define XEN_DOMCTL_PFINFO_XTAB (0xfU<<28) /* invalid page */ #define XEN_DOMCTL_PFINFO_XALLOC (0xeU<<28) /* allocate-only page */ -#define XEN_DOMCTL_PFINFO_PAGEDTAB (0x8U<<28) +#define XEN_DOMCTL_PFINFO_BROKEN (0xdU<<28) /* broken page */ #define XEN_DOMCTL_PFINFO_LTAB_MASK (0xfU<<28) -struct xen_domctl_getpageframeinfo { - /* IN variables. */ - uint64_aligned_t gmfn; /* GMFN to query */ - /* OUT variables. */ - /* Is the page PINNED to a type? */ - uint32_t type; /* see above type defs */ -}; -typedef struct xen_domctl_getpageframeinfo xen_domctl_getpageframeinfo_t; -DEFINE_XEN_GUEST_HANDLE(xen_domctl_getpageframeinfo_t); - - -/* XEN_DOMCTL_getpageframeinfo2 */ -struct xen_domctl_getpageframeinfo2 { - /* IN variables. */ - uint64_aligned_t num; - /* IN/OUT variables. */ - XEN_GUEST_HANDLE_64(uint32) array; -}; -typedef struct xen_domctl_getpageframeinfo2 xen_domctl_getpageframeinfo2_t; -DEFINE_XEN_GUEST_HANDLE(xen_domctl_getpageframeinfo2_t); - /* XEN_DOMCTL_getpageframeinfo3 */ struct xen_domctl_getpageframeinfo3 { /* IN variables. */ @@ -278,12 +268,47 @@ typedef struct xen_domctl_getvcpuinfo xen_domctl_getvcpuinfo_t; DEFINE_XEN_GUEST_HANDLE(xen_domctl_getvcpuinfo_t); +/* Get/set the NUMA node(s) with which the guest has affinity with. */ +/* XEN_DOMCTL_setnodeaffinity */ +/* XEN_DOMCTL_getnodeaffinity */ +struct xen_domctl_nodeaffinity { + struct xenctl_bitmap nodemap;/* IN */ +}; +typedef struct xen_domctl_nodeaffinity xen_domctl_nodeaffinity_t; +DEFINE_XEN_GUEST_HANDLE(xen_domctl_nodeaffinity_t); + + /* Get/set which physical cpus a vcpu can execute on. */ /* XEN_DOMCTL_setvcpuaffinity */ /* XEN_DOMCTL_getvcpuaffinity */ struct xen_domctl_vcpuaffinity { - uint32_t vcpu; /* IN */ - struct xenctl_cpumap cpumap; /* IN/OUT */ + /* IN variables. */ + uint32_t vcpu; + /* Set/get the hard affinity for vcpu */ +#define _XEN_VCPUAFFINITY_HARD 0 +#define XEN_VCPUAFFINITY_HARD (1U<<_XEN_VCPUAFFINITY_HARD) + /* Set/get the soft affinity for vcpu */ +#define _XEN_VCPUAFFINITY_SOFT 1 +#define XEN_VCPUAFFINITY_SOFT (1U<<_XEN_VCPUAFFINITY_SOFT) + uint32_t flags; + /* + * IN/OUT variables. + * + * Both are IN/OUT for XEN_DOMCTL_setvcpuaffinity, in which case they + * contain effective hard or/and soft affinity. That is, upon successful + * return, cpumap_soft, contains the intersection of the soft affinity, + * hard affinity and the cpupool's online CPUs for the domain (if + * XEN_VCPUAFFINITY_SOFT was set in flags). cpumap_hard contains the + * intersection between hard affinity and the cpupool's online CPUs (if + * XEN_VCPUAFFINITY_HARD was set in flags). + * + * Both are OUT-only for XEN_DOMCTL_getvcpuaffinity, in which case they + * contain the plain hard and/or soft affinity masks that were set during + * previous successful calls to XEN_DOMCTL_setvcpuaffinity (or the + * default values), without intersecting or altering them in any way. + */ + struct xenctl_bitmap cpumap_hard; + struct xenctl_bitmap cpumap_soft; }; typedef struct xen_domctl_vcpuaffinity xen_domctl_vcpuaffinity_t; DEFINE_XEN_GUEST_HANDLE(xen_domctl_vcpuaffinity_t); @@ -299,10 +324,12 @@ DEFINE_XEN_GUEST_HANDLE(xen_domctl_max_vcpus_t); /* XEN_DOMCTL_scheduler_op */ /* Scheduler types. */ -#define XEN_SCHEDULER_SEDF 4 +/* #define XEN_SCHEDULER_SEDF 4 (Removed) */ #define XEN_SCHEDULER_CREDIT 5 #define XEN_SCHEDULER_CREDIT2 6 #define XEN_SCHEDULER_ARINC653 7 +#define XEN_SCHEDULER_RTDS 8 + /* Set or get info? */ #define XEN_DOMCTL_SCHEDOP_putinfo 0 #define XEN_DOMCTL_SCHEDOP_getinfo 1 @@ -310,13 +337,6 @@ struct xen_domctl_scheduler_op { uint32_t sched_id; /* XEN_SCHEDULER_* */ uint32_t cmd; /* XEN_DOMCTL_SCHEDOP_* */ union { - struct xen_domctl_sched_sedf { - uint64_aligned_t period; - uint64_aligned_t slice; - uint64_aligned_t latency; - uint32_t extratime; - uint32_t weight; - } sedf; struct xen_domctl_sched_credit { uint16_t weight; uint16_t cap; @@ -324,6 +344,10 @@ struct xen_domctl_scheduler_op { struct xen_domctl_sched_credit2 { uint16_t weight; } credit2; + struct xen_domctl_sched_rtds { + uint32_t period; + uint32_t budget; + } rtds; } u; }; typedef struct xen_domctl_scheduler_op xen_domctl_scheduler_op_t; @@ -383,29 +407,9 @@ typedef struct xen_domctl_hypercall_init xen_domctl_hypercall_init_t; DEFINE_XEN_GUEST_HANDLE(xen_domctl_hypercall_init_t); -/* XEN_DOMCTL_arch_setup */ -#define _XEN_DOMAINSETUP_hvm_guest 0 -#define XEN_DOMAINSETUP_hvm_guest (1UL<<_XEN_DOMAINSETUP_hvm_guest) -#define _XEN_DOMAINSETUP_query 1 /* Get parameters (for save) */ -#define XEN_DOMAINSETUP_query (1UL<<_XEN_DOMAINSETUP_query) -#define _XEN_DOMAINSETUP_sioemu_guest 2 -#define XEN_DOMAINSETUP_sioemu_guest (1UL<<_XEN_DOMAINSETUP_sioemu_guest) -typedef struct xen_domctl_arch_setup { - uint64_aligned_t flags; /* XEN_DOMAINSETUP_* */ -#ifdef __ia64__ - uint64_aligned_t bp; /* mpaddr of boot param area */ - uint64_aligned_t maxmem; /* Highest memory address for MDT. */ - uint64_aligned_t xsi_va; /* Xen shared_info area virtual address. */ - uint32_t hypercall_imm; /* Break imm for Xen hypercalls. */ - int8_t vhpt_size_log2; /* Log2 of VHPT size. */ -#endif -} xen_domctl_arch_setup_t; -DEFINE_XEN_GUEST_HANDLE(xen_domctl_arch_setup_t); - - /* XEN_DOMCTL_settimeoffset */ struct xen_domctl_settimeoffset { - int32_t time_offset_seconds; /* applied to domain wallclock time */ + int64_aligned_t time_offset_seconds; /* applied to domain wallclock time */ }; typedef struct xen_domctl_settimeoffset xen_domctl_settimeoffset_t; DEFINE_XEN_GUEST_HANDLE(xen_domctl_settimeoffset_t); @@ -429,14 +433,6 @@ typedef struct xen_domctl_address_size { DEFINE_XEN_GUEST_HANDLE(xen_domctl_address_size_t); -/* XEN_DOMCTL_real_mode_area */ -struct xen_domctl_real_mode_area { - uint32_t log; /* log2 of Real Mode Area size */ -}; -typedef struct xen_domctl_real_mode_area xen_domctl_real_mode_area_t; -DEFINE_XEN_GUEST_HANDLE(xen_domctl_real_mode_area_t); - - /* XEN_DOMCTL_sendtrigger */ #define XEN_DOMCTL_SENDTRIGGER_NMI 0 #define XEN_DOMCTL_SENDTRIGGER_RESET 1 @@ -451,12 +447,33 @@ typedef struct xen_domctl_sendtrigger xen_domctl_sendtrigger_t; DEFINE_XEN_GUEST_HANDLE(xen_domctl_sendtrigger_t); -/* Assign PCI device to HVM guest. Sets up IOMMU structures. */ +/* Assign a device to a guest. Sets up IOMMU structures. */ /* XEN_DOMCTL_assign_device */ /* XEN_DOMCTL_test_assign_device */ -/* XEN_DOMCTL_deassign_device */ +/* + * XEN_DOMCTL_deassign_device: The behavior of this DOMCTL differs + * between the different type of device: + * - PCI device (XEN_DOMCTL_DEV_PCI) will be reassigned to DOM0 + * - DT device (XEN_DOMCTL_DT_PCI) will left unassigned. DOM0 + * will have to call XEN_DOMCTL_assign_device in order to use the + * device. + */ +#define XEN_DOMCTL_DEV_PCI 0 +#define XEN_DOMCTL_DEV_DT 1 struct xen_domctl_assign_device { - uint32_t machine_sbdf; /* machine PCI ID of assigned device */ + uint32_t dev; /* XEN_DOMCTL_DEV_* */ + union { + struct { + uint32_t machine_sbdf; /* machine PCI ID of assigned device */ + } pci; + struct { + uint32_t size; /* Length of the path */ + XEN_GUEST_HANDLE_64(char) path; /* path to the device tree node */ + } dt; + } u; + /* IN */ +#define XEN_DOMCTL_DEV_RDM_RELAXED 1 + uint32_t flag; /* flag of assigned device */ }; typedef struct xen_domctl_assign_device xen_domctl_assign_device_t; DEFINE_XEN_GUEST_HANDLE(xen_domctl_assign_device_t); @@ -480,6 +497,7 @@ typedef enum pt_irq_type_e { PT_IRQ_TYPE_ISA, PT_IRQ_TYPE_MSI, PT_IRQ_TYPE_MSI_TRANSLATE, + PT_IRQ_TYPE_SPI, /* ARM: valid range 32-1019 */ } pt_irq_type_t; struct xen_domctl_bind_pt_irq { uint32_t machine_irq; @@ -500,6 +518,9 @@ struct xen_domctl_bind_pt_irq { uint32_t gflags; uint64_aligned_t gtable; } msi; + struct { + uint16_t spi; + } spi; } u; }; typedef struct xen_domctl_bind_pt_irq xen_domctl_bind_pt_irq_t; @@ -507,6 +528,7 @@ DEFINE_XEN_GUEST_HANDLE(xen_domctl_bind_pt_irq_t); /* Bind machine I/O address range -> HVM address range. */ +/* If this returns -E2BIG lower nr_mfns value. */ /* XEN_DOMCTL_memory_mapping */ #define DPCI_ADD_MAPPING 1 #define DPCI_REMOVE_MAPPING 0 @@ -544,6 +566,7 @@ DEFINE_XEN_GUEST_HANDLE(xen_domctl_ioport_mapping_t); #define XEN_DOMCTL_MEM_CACHEATTR_WP 5 #define XEN_DOMCTL_MEM_CACHEATTR_WB 6 #define XEN_DOMCTL_MEM_CACHEATTR_UCM 7 +#define XEN_DOMCTL_DELETE_MEM_CACHEATTR (~(uint32_t)0) struct xen_domctl_pin_mem_cacheattr { uint64_aligned_t start, end; uint32_t type; /* XEN_DOMCTL_MEM_CACHEATTR_* */ @@ -571,28 +594,20 @@ struct xen_domctl_ext_vcpucontext { uint16_t sysenter_callback_cs; uint8_t syscall32_disables_events; uint8_t sysenter_disables_events; - uint64_aligned_t mcg_cap; +#if defined(__GNUC__) + union { + uint64_aligned_t mcg_cap; + struct hvm_vmce_vcpu vmce; + }; +#else + struct hvm_vmce_vcpu vmce; +#endif #endif }; typedef struct xen_domctl_ext_vcpucontext xen_domctl_ext_vcpucontext_t; DEFINE_XEN_GUEST_HANDLE(xen_domctl_ext_vcpucontext_t); /* - * Set optimizaton features for a domain - */ -/* XEN_DOMCTL_set_opt_feature */ -struct xen_domctl_set_opt_feature { -#if defined(__ia64__) - struct xen_ia64_opt_feature optf; -#else - /* Make struct non-empty: do not depend on this field name! */ - uint64_t dummy; -#endif -}; -typedef struct xen_domctl_set_opt_feature xen_domctl_set_opt_feature_t; -DEFINE_XEN_GUEST_HANDLE(xen_domctl_set_opt_feature_t); - -/* * Set the target domain for a domain */ /* XEN_DOMCTL_set_target */ @@ -616,6 +631,22 @@ typedef struct xen_domctl_cpuid xen_domctl_cpuid_t; DEFINE_XEN_GUEST_HANDLE(xen_domctl_cpuid_t); #endif +/* + * Arranges that if the domain suspends (specifically, if it shuts + * down with code SHUTDOWN_suspend), this event channel will be + * notified. + * + * This is _instead of_ the usual notification to the global + * VIRQ_DOM_EXC. (In most systems that pirq is owned by xenstored.) + * + * Only one subscription per domain is possible. Last subscriber + * wins; others are silently displaced. + * + * NB that contrary to the rather general name, it only applies to + * domain shutdown with code suspend. Shutdown for other reasons + * (including crash), and domain death, are notified to VIRQ_DOM_EXC + * regardless. + */ /* XEN_DOMCTL_subscribe */ struct xen_domctl_subscribe { uint32_t port; /* IN */ @@ -664,18 +695,13 @@ typedef struct xen_domctl_disable_migrate { /* XEN_DOMCTL_gettscinfo */ /* XEN_DOMCTL_settscinfo */ -struct xen_guest_tsc_info { +typedef struct xen_domctl_tsc_info { + /* IN/OUT */ uint32_t tsc_mode; uint32_t gtsc_khz; uint32_t incarnation; uint32_t pad; uint64_aligned_t elapsed_nsec; -}; -typedef struct xen_guest_tsc_info xen_guest_tsc_info_t; -DEFINE_XEN_GUEST_HANDLE(xen_guest_tsc_info_t); -typedef struct xen_domctl_tsc_info { - XEN_GUEST_HANDLE_64(xen_guest_tsc_info_t) out_info; /* OUT */ - xen_guest_tsc_info_t info; /* IN */ } xen_domctl_tsc_info_t; /* XEN_DOMCTL_gdbsx_guestmemio guest mem io */ @@ -705,10 +731,21 @@ struct xen_domctl_gdbsx_domstatus { }; /* - * Memory event operations + * VM event operations */ -/* XEN_DOMCTL_mem_event_op */ +/* XEN_DOMCTL_vm_event_op */ + +/* + * There are currently three rings available for VM events: + * sharing, monitor and paging. This hypercall allows one to + * control these rings (enable/disable), as well as to signal + * to the hypervisor to pull responses (resume) from the given + * ring. + */ +#define XEN_VM_EVENT_ENABLE 0 +#define XEN_VM_EVENT_DISABLE 1 +#define XEN_VM_EVENT_RESUME 2 /* * Domain memory paging @@ -717,41 +754,38 @@ struct xen_domctl_gdbsx_domstatus { * pager<->hypervisor interface. Use XENMEM_paging_op* * to perform per-page operations. * - * The XEN_DOMCTL_MEM_EVENT_OP_PAGING_ENABLE domctl returns several + * The XEN_VM_EVENT_PAGING_ENABLE domctl returns several * non-standard error codes to indicate why paging could not be enabled: * ENODEV - host lacks HAP support (EPT/NPT) or HAP is disabled in guest * EMLINK - guest has iommu passthrough enabled * EXDEV - guest has PoD enabled * EBUSY - guest has or had paging enabled, ring buffer still active */ -#define XEN_DOMCTL_MEM_EVENT_OP_PAGING 1 - -#define XEN_DOMCTL_MEM_EVENT_OP_PAGING_ENABLE 0 -#define XEN_DOMCTL_MEM_EVENT_OP_PAGING_DISABLE 1 +#define XEN_DOMCTL_VM_EVENT_OP_PAGING 1 /* - * Access permissions. + * Monitor helper. * * As with paging, use the domctl for teardown/setup of the * helper<->hypervisor interface. * - * There are HVM hypercalls to set the per-page access permissions of every - * page in a domain. When one of these permissions--independent, read, - * write, and execute--is violated, the VCPU is paused and a memory event - * is sent with what happened. (See public/mem_event.h) . + * The monitor interface can be used to register for various VM events. For + * example, there are HVM hypercalls to set the per-page access permissions + * of every page in a domain. When one of these permissions--independent, + * read, write, and execute--is violated, the VCPU is paused and a memory event + * is sent with what happened. The memory event handler can then resume the + * VCPU and redo the access with a XEN_VM_EVENT_RESUME option. * - * The memory event handler can then resume the VCPU and redo the access - * with a XENMEM_access_op_resume hypercall. + * See public/vm_event.h for the list of available events that can be + * subscribed to via the monitor interface. * - * The XEN_DOMCTL_MEM_EVENT_OP_ACCESS_ENABLE domctl returns several + * The XEN_VM_EVENT_MONITOR_* domctls returns * non-standard error codes to indicate why access could not be enabled: * ENODEV - host lacks HAP support (EPT/NPT) or HAP is disabled in guest * EBUSY - guest has or had access enabled, ring buffer still active + * */ -#define XEN_DOMCTL_MEM_EVENT_OP_ACCESS 2 - -#define XEN_DOMCTL_MEM_EVENT_OP_ACCESS_ENABLE 0 -#define XEN_DOMCTL_MEM_EVENT_OP_ACCESS_DISABLE 1 +#define XEN_DOMCTL_VM_EVENT_OP_MONITOR 2 /* * Sharing ENOMEM helper. @@ -766,21 +800,18 @@ struct xen_domctl_gdbsx_domstatus { * Note that shring can be turned on (as per the domctl below) * *without* this ring being setup. */ -#define XEN_DOMCTL_MEM_EVENT_OP_SHARING 3 - -#define XEN_DOMCTL_MEM_EVENT_OP_SHARING_ENABLE 0 -#define XEN_DOMCTL_MEM_EVENT_OP_SHARING_DISABLE 1 +#define XEN_DOMCTL_VM_EVENT_OP_SHARING 3 /* Use for teardown/setup of helper<->hypervisor interface for paging, * access and sharing.*/ -struct xen_domctl_mem_event_op { - uint32_t op; /* XEN_DOMCTL_MEM_EVENT_OP_*_* */ - uint32_t mode; /* XEN_DOMCTL_MEM_EVENT_OP_* */ +struct xen_domctl_vm_event_op { + uint32_t op; /* XEN_VM_EVENT_* */ + uint32_t mode; /* XEN_DOMCTL_VM_EVENT_OP_* */ uint32_t port; /* OUT: event channel for ring */ }; -typedef struct xen_domctl_mem_event_op xen_domctl_mem_event_op_t; -DEFINE_XEN_GUEST_HANDLE(xen_domctl_mem_event_op_t); +typedef struct xen_domctl_vm_event_op xen_domctl_vm_event_op_t; +DEFINE_XEN_GUEST_HANDLE(xen_domctl_vm_event_op_t); /* * Memory sharing operations @@ -821,7 +852,7 @@ struct xen_domctl_vcpuextstate { /* IN: VCPU that this call applies to. */ uint32_t vcpu; /* - * SET: xfeature support mask of struct (IN) + * SET: Ignored. * GET: xfeature support mask of struct (IN/OUT) * xfeature mask is served as identifications of the saving format * so that compatible CPUs can have a check on format to decide @@ -849,6 +880,189 @@ struct xen_domctl_set_access_required { typedef struct xen_domctl_set_access_required xen_domctl_set_access_required_t; DEFINE_XEN_GUEST_HANDLE(xen_domctl_set_access_required_t); +struct xen_domctl_set_broken_page_p2m { + uint64_aligned_t pfn; +}; +typedef struct xen_domctl_set_broken_page_p2m xen_domctl_set_broken_page_p2m_t; +DEFINE_XEN_GUEST_HANDLE(xen_domctl_set_broken_page_p2m_t); + +/* + * XEN_DOMCTL_set_max_evtchn: sets the maximum event channel port + * number the guest may use. Use this limit the amount of resources + * (global mapping space, xenheap) a guest may use for event channels. + */ +struct xen_domctl_set_max_evtchn { + uint32_t max_port; +}; +typedef struct xen_domctl_set_max_evtchn xen_domctl_set_max_evtchn_t; +DEFINE_XEN_GUEST_HANDLE(xen_domctl_set_max_evtchn_t); + +/* + * ARM: Clean and invalidate caches associated with given region of + * guest memory. + */ +struct xen_domctl_cacheflush { + /* IN: page range to flush. */ + xen_pfn_t start_pfn, nr_pfns; +}; +typedef struct xen_domctl_cacheflush xen_domctl_cacheflush_t; +DEFINE_XEN_GUEST_HANDLE(xen_domctl_cacheflush_t); + +#if defined(__i386__) || defined(__x86_64__) +struct xen_domctl_vcpu_msr { + uint32_t index; + uint32_t reserved; + uint64_aligned_t value; +}; +typedef struct xen_domctl_vcpu_msr xen_domctl_vcpu_msr_t; +DEFINE_XEN_GUEST_HANDLE(xen_domctl_vcpu_msr_t); + +/* + * XEN_DOMCTL_set_vcpu_msrs / XEN_DOMCTL_get_vcpu_msrs. + * + * Input: + * - A NULL 'msrs' guest handle is a request for the maximum 'msr_count'. + * - Otherwise, 'msr_count' is the number of entries in 'msrs'. + * + * Output for get: + * - If 'msr_count' is less than the number Xen needs to write, -ENOBUFS shall + * be returned and 'msr_count' updated to reflect the intended number. + * - On success, 'msr_count' shall indicate the number of MSRs written, which + * may be less than the maximum if some are not currently used by the vcpu. + * + * Output for set: + * - If Xen encounters an error with a specific MSR, -EINVAL shall be returned + * and 'msr_count' shall be set to the offending index, to aid debugging. + */ +struct xen_domctl_vcpu_msrs { + uint32_t vcpu; /* IN */ + uint32_t msr_count; /* IN/OUT */ + XEN_GUEST_HANDLE_64(xen_domctl_vcpu_msr_t) msrs; /* IN/OUT */ +}; +typedef struct xen_domctl_vcpu_msrs xen_domctl_vcpu_msrs_t; +DEFINE_XEN_GUEST_HANDLE(xen_domctl_vcpu_msrs_t); +#endif + +/* XEN_DOMCTL_setvnumainfo: specifies a virtual NUMA topology for the guest */ +struct xen_domctl_vnuma { + /* IN: number of vNUMA nodes to setup. Shall be greater than 0 */ + uint32_t nr_vnodes; + /* IN: number of memory ranges to setup */ + uint32_t nr_vmemranges; + /* + * IN: number of vCPUs of the domain (used as size of the vcpu_to_vnode + * array declared below). Shall be equal to the domain's max_vcpus. + */ + uint32_t nr_vcpus; + uint32_t pad; /* must be zero */ + + /* + * IN: array for specifying the distances of the vNUMA nodes + * between each others. Shall have nr_vnodes*nr_vnodes elements. + */ + XEN_GUEST_HANDLE_64(uint) vdistance; + /* + * IN: array for specifying to what vNUMA node each vCPU belongs. + * Shall have nr_vcpus elements. + */ + XEN_GUEST_HANDLE_64(uint) vcpu_to_vnode; + /* + * IN: array for specifying on what physical NUMA node each vNUMA + * node is placed. Shall have nr_vnodes elements. + */ + XEN_GUEST_HANDLE_64(uint) vnode_to_pnode; + /* + * IN: array for specifying the memory ranges. Shall have + * nr_vmemranges elements. + */ + XEN_GUEST_HANDLE_64(xen_vmemrange_t) vmemrange; +}; +typedef struct xen_domctl_vnuma xen_domctl_vnuma_t; +DEFINE_XEN_GUEST_HANDLE(xen_domctl_vnuma_t); + +struct xen_domctl_psr_cmt_op { +#define XEN_DOMCTL_PSR_CMT_OP_DETACH 0 +#define XEN_DOMCTL_PSR_CMT_OP_ATTACH 1 +#define XEN_DOMCTL_PSR_CMT_OP_QUERY_RMID 2 + uint32_t cmd; + uint32_t data; +}; +typedef struct xen_domctl_psr_cmt_op xen_domctl_psr_cmt_op_t; +DEFINE_XEN_GUEST_HANDLE(xen_domctl_psr_cmt_op_t); + +/* XEN_DOMCTL_MONITOR_* + * + * Enable/disable monitoring various VM events. + * This domctl configures what events will be reported to helper apps + * via the ring buffer "MONITOR". The ring has to be first enabled + * with the domctl XEN_DOMCTL_VM_EVENT_OP_MONITOR. + * + * GET_CAPABILITIES can be used to determine which of these features is + * available on a given platform. + * + * NOTICE: mem_access events are also delivered via the "MONITOR" ring buffer; + * however, enabling/disabling those events is performed with the use of + * memory_op hypercalls! + */ +#define XEN_DOMCTL_MONITOR_OP_ENABLE 0 +#define XEN_DOMCTL_MONITOR_OP_DISABLE 1 +#define XEN_DOMCTL_MONITOR_OP_GET_CAPABILITIES 2 + +#define XEN_DOMCTL_MONITOR_EVENT_WRITE_CTRLREG 0 +#define XEN_DOMCTL_MONITOR_EVENT_MOV_TO_MSR 1 +#define XEN_DOMCTL_MONITOR_EVENT_SINGLESTEP 2 +#define XEN_DOMCTL_MONITOR_EVENT_SOFTWARE_BREAKPOINT 3 +#define XEN_DOMCTL_MONITOR_EVENT_GUEST_REQUEST 4 + +struct xen_domctl_monitor_op { + uint32_t op; /* XEN_DOMCTL_MONITOR_OP_* */ + + /* + * When used with ENABLE/DISABLE this has to be set to + * the requested XEN_DOMCTL_MONITOR_EVENT_* value. + * With GET_CAPABILITIES this field returns a bitmap of + * events supported by the platform, in the format + * (1 << XEN_DOMCTL_MONITOR_EVENT_*). + */ + uint32_t event; + + /* + * Further options when issuing XEN_DOMCTL_MONITOR_OP_ENABLE. + */ + union { + struct { + /* Which control register */ + uint8_t index; + /* Pause vCPU until response */ + uint8_t sync; + /* Send event only on a change of value */ + uint8_t onchangeonly; + } mov_to_cr; + + struct { + /* Enable the capture of an extended set of MSRs */ + uint8_t extended_capture; + } mov_to_msr; + + struct { + /* Pause vCPU until response */ + uint8_t sync; + } guest_request; + } u; +}; +typedef struct xen_domctl_monitor_op xen_domctl_monitor_op_t; +DEFINE_XEN_GUEST_HANDLE(xen_domctl_monitor_op_t); + +struct xen_domctl_psr_cat_op { +#define XEN_DOMCTL_PSR_CAT_OP_SET_L3_CBM 0 +#define XEN_DOMCTL_PSR_CAT_OP_GET_L3_CBM 1 + uint32_t cmd; /* IN: XEN_DOMCTL_PSR_CAT_OP_* */ + uint32_t target; /* IN */ + uint64_t data; /* IN/OUT */ +}; +typedef struct xen_domctl_psr_cat_op xen_domctl_psr_cat_op_t; +DEFINE_XEN_GUEST_HANDLE(xen_domctl_psr_cat_op_t); + struct xen_domctl { uint32_t cmd; #define XEN_DOMCTL_createdomain 1 @@ -857,8 +1071,8 @@ struct xen_domctl { #define XEN_DOMCTL_unpausedomain 4 #define XEN_DOMCTL_getdomaininfo 5 #define XEN_DOMCTL_getmemlist 6 -#define XEN_DOMCTL_getpageframeinfo 7 -#define XEN_DOMCTL_getpageframeinfo2 8 +/* #define XEN_DOMCTL_getpageframeinfo 7 Obsolete - use getpageframeinfo3 */ +/* #define XEN_DOMCTL_getpageframeinfo2 8 Obsolete - use getpageframeinfo3 */ #define XEN_DOMCTL_setvcpuaffinity 9 #define XEN_DOMCTL_shadow_op 10 #define XEN_DOMCTL_max_mem 11 @@ -873,10 +1087,10 @@ struct xen_domctl { #define XEN_DOMCTL_iomem_permission 20 #define XEN_DOMCTL_ioport_permission 21 #define XEN_DOMCTL_hypercall_init 22 -#define XEN_DOMCTL_arch_setup 23 +#define XEN_DOMCTL_arch_setup 23 /* Obsolete IA64 only */ #define XEN_DOMCTL_settimeoffset 24 #define XEN_DOMCTL_getvcpuaffinity 25 -#define XEN_DOMCTL_real_mode_area 26 +#define XEN_DOMCTL_real_mode_area 26 /* Obsolete PPC only */ #define XEN_DOMCTL_resumedomain 27 #define XEN_DOMCTL_sendtrigger 28 #define XEN_DOMCTL_subscribe 29 @@ -891,7 +1105,7 @@ struct xen_domctl { #define XEN_DOMCTL_pin_mem_cacheattr 41 #define XEN_DOMCTL_set_ext_vcpucontext 42 #define XEN_DOMCTL_get_ext_vcpucontext 43 -#define XEN_DOMCTL_set_opt_feature 44 +#define XEN_DOMCTL_set_opt_feature 44 /* Obsolete IA64 only */ #define XEN_DOMCTL_test_assign_device 45 #define XEN_DOMCTL_set_target 46 #define XEN_DOMCTL_deassign_device 47 @@ -903,7 +1117,7 @@ struct xen_domctl { #define XEN_DOMCTL_suppress_spurious_page_faults 53 #define XEN_DOMCTL_debug_op 54 #define XEN_DOMCTL_gethvmcontext_partial 55 -#define XEN_DOMCTL_mem_event_op 56 +#define XEN_DOMCTL_vm_event_op 56 #define XEN_DOMCTL_mem_sharing_op 57 #define XEN_DOMCTL_disable_migrate 58 #define XEN_DOMCTL_gettscinfo 59 @@ -914,6 +1128,17 @@ struct xen_domctl { #define XEN_DOMCTL_set_access_required 64 #define XEN_DOMCTL_audit_p2m 65 #define XEN_DOMCTL_set_virq_handler 66 +#define XEN_DOMCTL_set_broken_page_p2m 67 +#define XEN_DOMCTL_setnodeaffinity 68 +#define XEN_DOMCTL_getnodeaffinity 69 +#define XEN_DOMCTL_set_max_evtchn 70 +#define XEN_DOMCTL_cacheflush 71 +#define XEN_DOMCTL_get_vcpu_msrs 72 +#define XEN_DOMCTL_set_vcpu_msrs 73 +#define XEN_DOMCTL_setvnumainfo 74 +#define XEN_DOMCTL_psr_cmt_op 75 +#define XEN_DOMCTL_monitor_op 77 +#define XEN_DOMCTL_psr_cat_op 78 #define XEN_DOMCTL_gdbsx_guestmemio 1000 #define XEN_DOMCTL_gdbsx_pausevcpu 1001 #define XEN_DOMCTL_gdbsx_unpausevcpu 1002 @@ -924,9 +1149,8 @@ struct xen_domctl { struct xen_domctl_createdomain createdomain; struct xen_domctl_getdomaininfo getdomaininfo; struct xen_domctl_getmemlist getmemlist; - struct xen_domctl_getpageframeinfo getpageframeinfo; - struct xen_domctl_getpageframeinfo2 getpageframeinfo2; struct xen_domctl_getpageframeinfo3 getpageframeinfo3; + struct xen_domctl_nodeaffinity nodeaffinity; struct xen_domctl_vcpuaffinity vcpuaffinity; struct xen_domctl_shadow_op shadow_op; struct xen_domctl_max_mem max_mem; @@ -940,11 +1164,9 @@ struct xen_domctl { struct xen_domctl_iomem_permission iomem_permission; struct xen_domctl_ioport_permission ioport_permission; struct xen_domctl_hypercall_init hypercall_init; - struct xen_domctl_arch_setup arch_setup; struct xen_domctl_settimeoffset settimeoffset; struct xen_domctl_disable_migrate disable_migrate; struct xen_domctl_tsc_info tsc_info; - struct xen_domctl_real_mode_area real_mode_area; struct xen_domctl_hvmcontext hvmcontext; struct xen_domctl_hvmcontext_partial hvmcontext_partial; struct xen_domctl_address_size address_size; @@ -956,22 +1178,29 @@ struct xen_domctl { struct xen_domctl_ioport_mapping ioport_mapping; struct xen_domctl_pin_mem_cacheattr pin_mem_cacheattr; struct xen_domctl_ext_vcpucontext ext_vcpucontext; - struct xen_domctl_set_opt_feature set_opt_feature; struct xen_domctl_set_target set_target; struct xen_domctl_subscribe subscribe; struct xen_domctl_debug_op debug_op; - struct xen_domctl_mem_event_op mem_event_op; + struct xen_domctl_vm_event_op vm_event_op; struct xen_domctl_mem_sharing_op mem_sharing_op; #if defined(__i386__) || defined(__x86_64__) struct xen_domctl_cpuid cpuid; struct xen_domctl_vcpuextstate vcpuextstate; + struct xen_domctl_vcpu_msrs vcpu_msrs; #endif struct xen_domctl_set_access_required access_required; struct xen_domctl_audit_p2m audit_p2m; struct xen_domctl_set_virq_handler set_virq_handler; + struct xen_domctl_set_max_evtchn set_max_evtchn; struct xen_domctl_gdbsx_memio gdbsx_guest_memio; + struct xen_domctl_set_broken_page_p2m set_broken_page_p2m; + struct xen_domctl_cacheflush cacheflush; struct xen_domctl_gdbsx_pauseunp_vcpu gdbsx_pauseunp_vcpu; struct xen_domctl_gdbsx_domstatus gdbsx_domstatus; + struct xen_domctl_vnuma vnuma; + struct xen_domctl_psr_cmt_op psr_cmt_op; + struct xen_domctl_monitor_op monitor_op; + struct xen_domctl_psr_cat_op psr_cat_op; uint8_t pad[128]; } u; }; @@ -983,7 +1212,7 @@ DEFINE_XEN_GUEST_HANDLE(xen_domctl_t); /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/elfnote.h b/sys/xen/interface/elfnote.h index 42d76da..3824a94 100644 --- a/sys/xen/interface/elfnote.h +++ b/sys/xen/interface/elfnote.h @@ -28,6 +28,8 @@ #define __XEN_PUBLIC_ELFNOTE_H__ /* + * `incontents 200 elfnotes ELF notes + * * The notes should live in a PT_NOTE segment and have "Xen" in the * name field. * @@ -36,6 +38,9 @@ * * LEGACY indicated the fields in the legacy __xen_guest string which * this a note type replaces. + * + * String values (for non-legacy) are NULL terminated ASCII, also known + * as ASCIZ type. */ /* @@ -66,8 +71,8 @@ #define XEN_ELFNOTE_VIRT_BASE 3 /* - * The offset of the ELF paddr field from the acutal required - * psuedo-physical address (numeric). + * The offset of the ELF paddr field from the actual required + * pseudo-physical address (numeric). * * This is used to maintain backwards compatibility with older kernels * which wrote __PAGE_OFFSET into that field. This field defaults to 0 @@ -158,6 +163,9 @@ /* * Whether or not the guest supports cooperative suspend cancellation. + * This is a numeric value. + * + * Default is 0 */ #define XEN_ELFNOTE_SUSPEND_CANCEL 14 @@ -255,7 +263,7 @@ /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/elfstructs.h b/sys/xen/interface/elfstructs.h deleted file mode 100644 index 77362f3..0000000 --- a/sys/xen/interface/elfstructs.h +++ /dev/null @@ -1,527 +0,0 @@ -#ifndef __XEN_PUBLIC_ELFSTRUCTS_H__ -#define __XEN_PUBLIC_ELFSTRUCTS_H__ 1 -/* - * Copyright (c) 1995, 1996 Erik Theisen. All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. The name of the author may not be used to endorse or promote products - * derived from this software without specific prior written permission - * - * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR - * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES - * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. - * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, - * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT - * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF - * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -typedef uint8_t Elf_Byte; - -typedef uint32_t Elf32_Addr; /* Unsigned program address */ -typedef uint32_t Elf32_Off; /* Unsigned file offset */ -typedef int32_t Elf32_Sword; /* Signed large integer */ -typedef uint32_t Elf32_Word; /* Unsigned large integer */ -typedef uint16_t Elf32_Half; /* Unsigned medium integer */ - -typedef uint64_t Elf64_Addr; -typedef uint64_t Elf64_Off; -typedef int32_t Elf64_Shalf; - -typedef int32_t Elf64_Sword; -typedef uint32_t Elf64_Word; - -typedef int64_t Elf64_Sxword; -typedef uint64_t Elf64_Xword; - -typedef uint32_t Elf64_Half; -typedef uint16_t Elf64_Quarter; - -/* - * e_ident[] identification indexes - * See http://www.caldera.com/developers/gabi/2000-07-17/ch4.eheader.html - */ -#define EI_MAG0 0 /* file ID */ -#define EI_MAG1 1 /* file ID */ -#define EI_MAG2 2 /* file ID */ -#define EI_MAG3 3 /* file ID */ -#define EI_CLASS 4 /* file class */ -#define EI_DATA 5 /* data encoding */ -#define EI_VERSION 6 /* ELF header version */ -#define EI_OSABI 7 /* OS/ABI ID */ -#define EI_ABIVERSION 8 /* ABI version */ -#define EI_PAD 9 /* start of pad bytes */ -#define EI_NIDENT 16 /* Size of e_ident[] */ - -/* e_ident[] magic number */ -#define ELFMAG0 0x7f /* e_ident[EI_MAG0] */ -#define ELFMAG1 'E' /* e_ident[EI_MAG1] */ -#define ELFMAG2 'L' /* e_ident[EI_MAG2] */ -#define ELFMAG3 'F' /* e_ident[EI_MAG3] */ -#define ELFMAG "\177ELF" /* magic */ -#define SELFMAG 4 /* size of magic */ - -/* e_ident[] file class */ -#define ELFCLASSNONE 0 /* invalid */ -#define ELFCLASS32 1 /* 32-bit objs */ -#define ELFCLASS64 2 /* 64-bit objs */ -#define ELFCLASSNUM 3 /* number of classes */ - -/* e_ident[] data encoding */ -#define ELFDATANONE 0 /* invalid */ -#define ELFDATA2LSB 1 /* Little-Endian */ -#define ELFDATA2MSB 2 /* Big-Endian */ -#define ELFDATANUM 3 /* number of data encode defines */ - -/* e_ident[] Operating System/ABI */ -#define ELFOSABI_SYSV 0 /* UNIX System V ABI */ -#define ELFOSABI_HPUX 1 /* HP-UX operating system */ -#define ELFOSABI_NETBSD 2 /* NetBSD */ -#define ELFOSABI_LINUX 3 /* GNU/Linux */ -#define ELFOSABI_HURD 4 /* GNU/Hurd */ -#define ELFOSABI_86OPEN 5 /* 86Open common IA32 ABI */ -#define ELFOSABI_SOLARIS 6 /* Solaris */ -#define ELFOSABI_MONTEREY 7 /* Monterey */ -#define ELFOSABI_IRIX 8 /* IRIX */ -#define ELFOSABI_FREEBSD 9 /* FreeBSD */ -#define ELFOSABI_TRU64 10 /* TRU64 UNIX */ -#define ELFOSABI_MODESTO 11 /* Novell Modesto */ -#define ELFOSABI_OPENBSD 12 /* OpenBSD */ -#define ELFOSABI_ARM 97 /* ARM */ -#define ELFOSABI_STANDALONE 255 /* Standalone (embedded) application */ - -/* e_ident */ -#define IS_ELF(ehdr) ((ehdr).e_ident[EI_MAG0] == ELFMAG0 && \ - (ehdr).e_ident[EI_MAG1] == ELFMAG1 && \ - (ehdr).e_ident[EI_MAG2] == ELFMAG2 && \ - (ehdr).e_ident[EI_MAG3] == ELFMAG3) - -/* ELF Header */ -typedef struct elfhdr { - unsigned char e_ident[EI_NIDENT]; /* ELF Identification */ - Elf32_Half e_type; /* object file type */ - Elf32_Half e_machine; /* machine */ - Elf32_Word e_version; /* object file version */ - Elf32_Addr e_entry; /* virtual entry point */ - Elf32_Off e_phoff; /* program header table offset */ - Elf32_Off e_shoff; /* section header table offset */ - Elf32_Word e_flags; /* processor-specific flags */ - Elf32_Half e_ehsize; /* ELF header size */ - Elf32_Half e_phentsize; /* program header entry size */ - Elf32_Half e_phnum; /* number of program header entries */ - Elf32_Half e_shentsize; /* section header entry size */ - Elf32_Half e_shnum; /* number of section header entries */ - Elf32_Half e_shstrndx; /* section header table's "section - header string table" entry offset */ -} Elf32_Ehdr; - -typedef struct { - unsigned char e_ident[EI_NIDENT]; /* Id bytes */ - Elf64_Quarter e_type; /* file type */ - Elf64_Quarter e_machine; /* machine type */ - Elf64_Half e_version; /* version number */ - Elf64_Addr e_entry; /* entry point */ - Elf64_Off e_phoff; /* Program hdr offset */ - Elf64_Off e_shoff; /* Section hdr offset */ - Elf64_Half e_flags; /* Processor flags */ - Elf64_Quarter e_ehsize; /* sizeof ehdr */ - Elf64_Quarter e_phentsize; /* Program header entry size */ - Elf64_Quarter e_phnum; /* Number of program headers */ - Elf64_Quarter e_shentsize; /* Section header entry size */ - Elf64_Quarter e_shnum; /* Number of section headers */ - Elf64_Quarter e_shstrndx; /* String table index */ -} Elf64_Ehdr; - -/* e_type */ -#define ET_NONE 0 /* No file type */ -#define ET_REL 1 /* relocatable file */ -#define ET_EXEC 2 /* executable file */ -#define ET_DYN 3 /* shared object file */ -#define ET_CORE 4 /* core file */ -#define ET_NUM 5 /* number of types */ -#define ET_LOPROC 0xff00 /* reserved range for processor */ -#define ET_HIPROC 0xffff /* specific e_type */ - -/* e_machine */ -#define EM_NONE 0 /* No Machine */ -#define EM_M32 1 /* AT&T WE 32100 */ -#define EM_SPARC 2 /* SPARC */ -#define EM_386 3 /* Intel 80386 */ -#define EM_68K 4 /* Motorola 68000 */ -#define EM_88K 5 /* Motorola 88000 */ -#define EM_486 6 /* Intel 80486 - unused? */ -#define EM_860 7 /* Intel 80860 */ -#define EM_MIPS 8 /* MIPS R3000 Big-Endian only */ -/* - * Don't know if EM_MIPS_RS4_BE, - * EM_SPARC64, EM_PARISC, - * or EM_PPC are ABI compliant - */ -#define EM_MIPS_RS4_BE 10 /* MIPS R4000 Big-Endian */ -#define EM_SPARC64 11 /* SPARC v9 64-bit unoffical */ -#define EM_PARISC 15 /* HPPA */ -#define EM_SPARC32PLUS 18 /* Enhanced instruction set SPARC */ -#define EM_PPC 20 /* PowerPC */ -#define EM_PPC64 21 /* PowerPC 64-bit */ -#define EM_ARM 40 /* Advanced RISC Machines ARM */ -#define EM_ALPHA 41 /* DEC ALPHA */ -#define EM_SPARCV9 43 /* SPARC version 9 */ -#define EM_ALPHA_EXP 0x9026 /* DEC ALPHA */ -#define EM_IA_64 50 /* Intel Merced */ -#define EM_X86_64 62 /* AMD x86-64 architecture */ -#define EM_VAX 75 /* DEC VAX */ - -/* Version */ -#define EV_NONE 0 /* Invalid */ -#define EV_CURRENT 1 /* Current */ -#define EV_NUM 2 /* number of versions */ - -/* Section Header */ -typedef struct { - Elf32_Word sh_name; /* name - index into section header - string table section */ - Elf32_Word sh_type; /* type */ - Elf32_Word sh_flags; /* flags */ - Elf32_Addr sh_addr; /* address */ - Elf32_Off sh_offset; /* file offset */ - Elf32_Word sh_size; /* section size */ - Elf32_Word sh_link; /* section header table index link */ - Elf32_Word sh_info; /* extra information */ - Elf32_Word sh_addralign; /* address alignment */ - Elf32_Word sh_entsize; /* section entry size */ -} Elf32_Shdr; - -typedef struct { - Elf64_Half sh_name; /* section name */ - Elf64_Half sh_type; /* section type */ - Elf64_Xword sh_flags; /* section flags */ - Elf64_Addr sh_addr; /* virtual address */ - Elf64_Off sh_offset; /* file offset */ - Elf64_Xword sh_size; /* section size */ - Elf64_Half sh_link; /* link to another */ - Elf64_Half sh_info; /* misc info */ - Elf64_Xword sh_addralign; /* memory alignment */ - Elf64_Xword sh_entsize; /* table entry size */ -} Elf64_Shdr; - -/* Special Section Indexes */ -#define SHN_UNDEF 0 /* undefined */ -#define SHN_LORESERVE 0xff00 /* lower bounds of reserved indexes */ -#define SHN_LOPROC 0xff00 /* reserved range for processor */ -#define SHN_HIPROC 0xff1f /* specific section indexes */ -#define SHN_ABS 0xfff1 /* absolute value */ -#define SHN_COMMON 0xfff2 /* common symbol */ -#define SHN_HIRESERVE 0xffff /* upper bounds of reserved indexes */ - -/* sh_type */ -#define SHT_NULL 0 /* inactive */ -#define SHT_PROGBITS 1 /* program defined information */ -#define SHT_SYMTAB 2 /* symbol table section */ -#define SHT_STRTAB 3 /* string table section */ -#define SHT_RELA 4 /* relocation section with addends*/ -#define SHT_HASH 5 /* symbol hash table section */ -#define SHT_DYNAMIC 6 /* dynamic section */ -#define SHT_NOTE 7 /* note section */ -#define SHT_NOBITS 8 /* no space section */ -#define SHT_REL 9 /* relation section without addends */ -#define SHT_SHLIB 10 /* reserved - purpose unknown */ -#define SHT_DYNSYM 11 /* dynamic symbol table section */ -#define SHT_NUM 12 /* number of section types */ -#define SHT_LOPROC 0x70000000 /* reserved range for processor */ -#define SHT_HIPROC 0x7fffffff /* specific section header types */ -#define SHT_LOUSER 0x80000000 /* reserved range for application */ -#define SHT_HIUSER 0xffffffff /* specific indexes */ - -/* Section names */ -#define ELF_BSS ".bss" /* uninitialized data */ -#define ELF_DATA ".data" /* initialized data */ -#define ELF_DEBUG ".debug" /* debug */ -#define ELF_DYNAMIC ".dynamic" /* dynamic linking information */ -#define ELF_DYNSTR ".dynstr" /* dynamic string table */ -#define ELF_DYNSYM ".dynsym" /* dynamic symbol table */ -#define ELF_FINI ".fini" /* termination code */ -#define ELF_GOT ".got" /* global offset table */ -#define ELF_HASH ".hash" /* symbol hash table */ -#define ELF_INIT ".init" /* initialization code */ -#define ELF_REL_DATA ".rel.data" /* relocation data */ -#define ELF_REL_FINI ".rel.fini" /* relocation termination code */ -#define ELF_REL_INIT ".rel.init" /* relocation initialization code */ -#define ELF_REL_DYN ".rel.dyn" /* relocaltion dynamic link info */ -#define ELF_REL_RODATA ".rel.rodata" /* relocation read-only data */ -#define ELF_REL_TEXT ".rel.text" /* relocation code */ -#define ELF_RODATA ".rodata" /* read-only data */ -#define ELF_SHSTRTAB ".shstrtab" /* section header string table */ -#define ELF_STRTAB ".strtab" /* string table */ -#define ELF_SYMTAB ".symtab" /* symbol table */ -#define ELF_TEXT ".text" /* code */ - - -/* Section Attribute Flags - sh_flags */ -#define SHF_WRITE 0x1 /* Writable */ -#define SHF_ALLOC 0x2 /* occupies memory */ -#define SHF_EXECINSTR 0x4 /* executable */ -#define SHF_MASKPROC 0xf0000000 /* reserved bits for processor */ - /* specific section attributes */ - -/* Symbol Table Entry */ -typedef struct elf32_sym { - Elf32_Word st_name; /* name - index into string table */ - Elf32_Addr st_value; /* symbol value */ - Elf32_Word st_size; /* symbol size */ - unsigned char st_info; /* type and binding */ - unsigned char st_other; /* 0 - no defined meaning */ - Elf32_Half st_shndx; /* section header index */ -} Elf32_Sym; - -typedef struct { - Elf64_Half st_name; /* Symbol name index in str table */ - Elf_Byte st_info; /* type / binding attrs */ - Elf_Byte st_other; /* unused */ - Elf64_Quarter st_shndx; /* section index of symbol */ - Elf64_Xword st_value; /* value of symbol */ - Elf64_Xword st_size; /* size of symbol */ -} Elf64_Sym; - -/* Symbol table index */ -#define STN_UNDEF 0 /* undefined */ - -/* Extract symbol info - st_info */ -#define ELF32_ST_BIND(x) ((x) >> 4) -#define ELF32_ST_TYPE(x) (((unsigned int) x) & 0xf) -#define ELF32_ST_INFO(b,t) (((b) << 4) + ((t) & 0xf)) - -#define ELF64_ST_BIND(x) ((x) >> 4) -#define ELF64_ST_TYPE(x) (((unsigned int) x) & 0xf) -#define ELF64_ST_INFO(b,t) (((b) << 4) + ((t) & 0xf)) - -/* Symbol Binding - ELF32_ST_BIND - st_info */ -#define STB_LOCAL 0 /* Local symbol */ -#define STB_GLOBAL 1 /* Global symbol */ -#define STB_WEAK 2 /* like global - lower precedence */ -#define STB_NUM 3 /* number of symbol bindings */ -#define STB_LOPROC 13 /* reserved range for processor */ -#define STB_HIPROC 15 /* specific symbol bindings */ - -/* Symbol type - ELF32_ST_TYPE - st_info */ -#define STT_NOTYPE 0 /* not specified */ -#define STT_OBJECT 1 /* data object */ -#define STT_FUNC 2 /* function */ -#define STT_SECTION 3 /* section */ -#define STT_FILE 4 /* file */ -#define STT_NUM 5 /* number of symbol types */ -#define STT_LOPROC 13 /* reserved range for processor */ -#define STT_HIPROC 15 /* specific symbol types */ - -/* Relocation entry with implicit addend */ -typedef struct { - Elf32_Addr r_offset; /* offset of relocation */ - Elf32_Word r_info; /* symbol table index and type */ -} Elf32_Rel; - -/* Relocation entry with explicit addend */ -typedef struct { - Elf32_Addr r_offset; /* offset of relocation */ - Elf32_Word r_info; /* symbol table index and type */ - Elf32_Sword r_addend; -} Elf32_Rela; - -/* Extract relocation info - r_info */ -#define ELF32_R_SYM(i) ((i) >> 8) -#define ELF32_R_TYPE(i) ((unsigned char) (i)) -#define ELF32_R_INFO(s,t) (((s) << 8) + (unsigned char)(t)) - -typedef struct { - Elf64_Xword r_offset; /* where to do it */ - Elf64_Xword r_info; /* index & type of relocation */ -} Elf64_Rel; - -typedef struct { - Elf64_Xword r_offset; /* where to do it */ - Elf64_Xword r_info; /* index & type of relocation */ - Elf64_Sxword r_addend; /* adjustment value */ -} Elf64_Rela; - -#define ELF64_R_SYM(info) ((info) >> 32) -#define ELF64_R_TYPE(info) ((info) & 0xFFFFFFFF) -#define ELF64_R_INFO(s,t) (((s) << 32) + (u_int32_t)(t)) - -/* Program Header */ -typedef struct { - Elf32_Word p_type; /* segment type */ - Elf32_Off p_offset; /* segment offset */ - Elf32_Addr p_vaddr; /* virtual address of segment */ - Elf32_Addr p_paddr; /* physical address - ignored? */ - Elf32_Word p_filesz; /* number of bytes in file for seg. */ - Elf32_Word p_memsz; /* number of bytes in mem. for seg. */ - Elf32_Word p_flags; /* flags */ - Elf32_Word p_align; /* memory alignment */ -} Elf32_Phdr; - -typedef struct { - Elf64_Half p_type; /* entry type */ - Elf64_Half p_flags; /* flags */ - Elf64_Off p_offset; /* offset */ - Elf64_Addr p_vaddr; /* virtual address */ - Elf64_Addr p_paddr; /* physical address */ - Elf64_Xword p_filesz; /* file size */ - Elf64_Xword p_memsz; /* memory size */ - Elf64_Xword p_align; /* memory & file alignment */ -} Elf64_Phdr; - -/* Segment types - p_type */ -#define PT_NULL 0 /* unused */ -#define PT_LOAD 1 /* loadable segment */ -#define PT_DYNAMIC 2 /* dynamic linking section */ -#define PT_INTERP 3 /* the RTLD */ -#define PT_NOTE 4 /* auxiliary information */ -#define PT_SHLIB 5 /* reserved - purpose undefined */ -#define PT_PHDR 6 /* program header */ -#define PT_NUM 7 /* Number of segment types */ -#define PT_LOPROC 0x70000000 /* reserved range for processor */ -#define PT_HIPROC 0x7fffffff /* specific segment types */ - -/* Segment flags - p_flags */ -#define PF_X 0x1 /* Executable */ -#define PF_W 0x2 /* Writable */ -#define PF_R 0x4 /* Readable */ -#define PF_MASKPROC 0xf0000000 /* reserved bits for processor */ - /* specific segment flags */ - -/* Dynamic structure */ -typedef struct { - Elf32_Sword d_tag; /* controls meaning of d_val */ - union { - Elf32_Word d_val; /* Multiple meanings - see d_tag */ - Elf32_Addr d_ptr; /* program virtual address */ - } d_un; -} Elf32_Dyn; - -typedef struct { - Elf64_Xword d_tag; /* controls meaning of d_val */ - union { - Elf64_Addr d_ptr; - Elf64_Xword d_val; - } d_un; -} Elf64_Dyn; - -/* Dynamic Array Tags - d_tag */ -#define DT_NULL 0 /* marks end of _DYNAMIC array */ -#define DT_NEEDED 1 /* string table offset of needed lib */ -#define DT_PLTRELSZ 2 /* size of relocation entries in PLT */ -#define DT_PLTGOT 3 /* address PLT/GOT */ -#define DT_HASH 4 /* address of symbol hash table */ -#define DT_STRTAB 5 /* address of string table */ -#define DT_SYMTAB 6 /* address of symbol table */ -#define DT_RELA 7 /* address of relocation table */ -#define DT_RELASZ 8 /* size of relocation table */ -#define DT_RELAENT 9 /* size of relocation entry */ -#define DT_STRSZ 10 /* size of string table */ -#define DT_SYMENT 11 /* size of symbol table entry */ -#define DT_INIT 12 /* address of initialization func. */ -#define DT_FINI 13 /* address of termination function */ -#define DT_SONAME 14 /* string table offset of shared obj */ -#define DT_RPATH 15 /* string table offset of library - search path */ -#define DT_SYMBOLIC 16 /* start sym search in shared obj. */ -#define DT_REL 17 /* address of rel. tbl. w addends */ -#define DT_RELSZ 18 /* size of DT_REL relocation table */ -#define DT_RELENT 19 /* size of DT_REL relocation entry */ -#define DT_PLTREL 20 /* PLT referenced relocation entry */ -#define DT_DEBUG 21 /* bugger */ -#define DT_TEXTREL 22 /* Allow rel. mod. to unwritable seg */ -#define DT_JMPREL 23 /* add. of PLT's relocation entries */ -#define DT_BIND_NOW 24 /* Bind now regardless of env setting */ -#define DT_NUM 25 /* Number used. */ -#define DT_LOPROC 0x70000000 /* reserved range for processor */ -#define DT_HIPROC 0x7fffffff /* specific dynamic array tags */ - -/* Standard ELF hashing function */ -unsigned int elf_hash(const unsigned char *name); - -/* - * Note Definitions - */ -typedef struct { - Elf32_Word namesz; - Elf32_Word descsz; - Elf32_Word type; -} Elf32_Note; - -typedef struct { - Elf64_Half namesz; - Elf64_Half descsz; - Elf64_Half type; -} Elf64_Note; - - -#if defined(ELFSIZE) -#define CONCAT(x,y) __CONCAT(x,y) -#define ELFNAME(x) CONCAT(elf,CONCAT(ELFSIZE,CONCAT(_,x))) -#define ELFNAME2(x,y) CONCAT(x,CONCAT(_elf,CONCAT(ELFSIZE,CONCAT(_,y)))) -#define ELFNAMEEND(x) CONCAT(x,CONCAT(_elf,ELFSIZE)) -#define ELFDEFNNAME(x) CONCAT(ELF,CONCAT(ELFSIZE,CONCAT(_,x))) -#endif - -#if defined(ELFSIZE) && (ELFSIZE == 32) -#define Elf_Ehdr Elf32_Ehdr -#define Elf_Phdr Elf32_Phdr -#define Elf_Shdr Elf32_Shdr -#define Elf_Sym Elf32_Sym -#define Elf_Rel Elf32_Rel -#define Elf_RelA Elf32_Rela -#define Elf_Dyn Elf32_Dyn -#define Elf_Word Elf32_Word -#define Elf_Sword Elf32_Sword -#define Elf_Addr Elf32_Addr -#define Elf_Off Elf32_Off -#define Elf_Nhdr Elf32_Nhdr -#define Elf_Note Elf32_Note - -#define ELF_R_SYM ELF32_R_SYM -#define ELF_R_TYPE ELF32_R_TYPE -#define ELF_R_INFO ELF32_R_INFO -#define ELFCLASS ELFCLASS32 - -#define ELF_ST_BIND ELF32_ST_BIND -#define ELF_ST_TYPE ELF32_ST_TYPE -#define ELF_ST_INFO ELF32_ST_INFO - -#define AuxInfo Aux32Info -#elif defined(ELFSIZE) && (ELFSIZE == 64) -#define Elf_Ehdr Elf64_Ehdr -#define Elf_Phdr Elf64_Phdr -#define Elf_Shdr Elf64_Shdr -#define Elf_Sym Elf64_Sym -#define Elf_Rel Elf64_Rel -#define Elf_RelA Elf64_Rela -#define Elf_Dyn Elf64_Dyn -#define Elf_Word Elf64_Word -#define Elf_Sword Elf64_Sword -#define Elf_Addr Elf64_Addr -#define Elf_Off Elf64_Off -#define Elf_Nhdr Elf64_Nhdr -#define Elf_Note Elf64_Note - -#define ELF_R_SYM ELF64_R_SYM -#define ELF_R_TYPE ELF64_R_TYPE -#define ELF_R_INFO ELF64_R_INFO -#define ELFCLASS ELFCLASS64 - -#define ELF_ST_BIND ELF64_ST_BIND -#define ELF_ST_TYPE ELF64_ST_TYPE -#define ELF_ST_INFO ELF64_ST_INFO - -#define AuxInfo Aux64Info -#endif - -#endif /* __XEN_PUBLIC_ELFSTRUCTS_H__ */ diff --git a/sys/xen/interface/errno.h b/sys/xen/interface/errno.h new file mode 100644 index 0000000..8c88bb1 --- /dev/null +++ b/sys/xen/interface/errno.h @@ -0,0 +1,95 @@ +#ifndef __XEN_PUBLIC_ERRNO_H__ + +#ifndef __ASSEMBLY__ + +#define XEN_ERRNO(name, value) XEN_##name = value, +enum xen_errno { + +#else /* !__ASSEMBLY__ */ + +#define XEN_ERRNO(name, value) .equ XEN_##name, value + +#endif /* __ASSEMBLY__ */ + +/* ` enum neg_errnoval { [ -Efoo for each Efoo in the list below ] } */ +/* ` enum errnoval { */ + +#endif /* __XEN_PUBLIC_ERRNO_H__ */ + +#ifdef XEN_ERRNO + +/* + * Values originating from x86 Linux. Please consider using respective + * values when adding new definitions here. + * + * The set of identifiers to be added here shouldn't extend beyond what + * POSIX mandates (see e.g. + * http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html) + * with the exception that we support some optional (XSR) values + * specified there (but no new ones should be added). + */ + +XEN_ERRNO(EPERM, 1) /* Operation not permitted */ +XEN_ERRNO(ENOENT, 2) /* No such file or directory */ +XEN_ERRNO(ESRCH, 3) /* No such process */ +#ifdef __XEN__ /* Internal only, should never be exposed to the guest. */ +XEN_ERRNO(EINTR, 4) /* Interrupted system call */ +#endif +XEN_ERRNO(EIO, 5) /* I/O error */ +XEN_ERRNO(ENXIO, 6) /* No such device or address */ +XEN_ERRNO(E2BIG, 7) /* Arg list too long */ +XEN_ERRNO(ENOEXEC, 8) /* Exec format error */ +XEN_ERRNO(EBADF, 9) /* Bad file number */ +XEN_ERRNO(ECHILD, 10) /* No child processes */ +XEN_ERRNO(EAGAIN, 11) /* Try again */ +XEN_ERRNO(ENOMEM, 12) /* Out of memory */ +XEN_ERRNO(EACCES, 13) /* Permission denied */ +XEN_ERRNO(EFAULT, 14) /* Bad address */ +XEN_ERRNO(EBUSY, 16) /* Device or resource busy */ +XEN_ERRNO(EEXIST, 17) /* File exists */ +XEN_ERRNO(EXDEV, 18) /* Cross-device link */ +XEN_ERRNO(ENODEV, 19) /* No such device */ +XEN_ERRNO(EINVAL, 22) /* Invalid argument */ +XEN_ERRNO(ENFILE, 23) /* File table overflow */ +XEN_ERRNO(EMFILE, 24) /* Too many open files */ +XEN_ERRNO(ENOSPC, 28) /* No space left on device */ +XEN_ERRNO(EMLINK, 31) /* Too many links */ +XEN_ERRNO(EDOM, 33) /* Math argument out of domain of func */ +XEN_ERRNO(ERANGE, 34) /* Math result not representable */ +XEN_ERRNO(EDEADLK, 35) /* Resource deadlock would occur */ +XEN_ERRNO(ENAMETOOLONG, 36) /* File name too long */ +XEN_ERRNO(ENOLCK, 37) /* No record locks available */ +XEN_ERRNO(ENOSYS, 38) /* Function not implemented */ +XEN_ERRNO(ENODATA, 61) /* No data available */ +XEN_ERRNO(ETIME, 62) /* Timer expired */ +XEN_ERRNO(EBADMSG, 74) /* Not a data message */ +XEN_ERRNO(EOVERFLOW, 75) /* Value too large for defined data type */ +XEN_ERRNO(EILSEQ, 84) /* Illegal byte sequence */ +#ifdef __XEN__ /* Internal only, should never be exposed to the guest. */ +XEN_ERRNO(ERESTART, 85) /* Interrupted system call should be restarted */ +#endif +XEN_ERRNO(ENOTSOCK, 88) /* Socket operation on non-socket */ +XEN_ERRNO(EOPNOTSUPP, 95) /* Operation not supported on transport endpoint */ +XEN_ERRNO(EADDRINUSE, 98) /* Address already in use */ +XEN_ERRNO(EADDRNOTAVAIL, 99) /* Cannot assign requested address */ +XEN_ERRNO(ENOBUFS, 105) /* No buffer space available */ +XEN_ERRNO(EISCONN, 106) /* Transport endpoint is already connected */ +XEN_ERRNO(ENOTCONN, 107) /* Transport endpoint is not connected */ +XEN_ERRNO(ETIMEDOUT, 110) /* Connection timed out */ + +#undef XEN_ERRNO +#endif /* XEN_ERRNO */ + +#ifndef __XEN_PUBLIC_ERRNO_H__ +#define __XEN_PUBLIC_ERRNO_H__ + +/* ` } */ + +#ifndef __ASSEMBLY__ +}; +#endif + +#define XEN_EWOULDBLOCK XEN_EAGAIN /* Operation would block */ +#define XEN_EDEADLOCK XEN_EDEADLK /* Resource deadlock would occur */ + +#endif /* __XEN_PUBLIC_ERRNO_H__ */ diff --git a/sys/xen/interface/event_channel.h b/sys/xen/interface/event_channel.h index 65d1911..05e531d 100644 --- a/sys/xen/interface/event_channel.h +++ b/sys/xen/interface/event_channel.h @@ -71,13 +71,13 @@ #define EVTCHNOP_bind_vcpu 8 #define EVTCHNOP_unmask 9 #define EVTCHNOP_reset 10 +#define EVTCHNOP_init_control 11 +#define EVTCHNOP_expand_array 12 +#define EVTCHNOP_set_priority 13 /* ` } */ -#ifndef __XEN_EVTCHN_PORT_DEFINED__ typedef uint32_t evtchn_port_t; DEFINE_XEN_GUEST_HANDLE(evtchn_port_t); -#define __XEN_EVTCHN_PORT_DEFINED__ 1 -#endif /* * EVTCHNOP_alloc_unbound: Allocate a port in domain <dom> and mark as @@ -101,6 +101,17 @@ typedef struct evtchn_alloc_unbound evtchn_alloc_unbound_t; * a port that is unbound and marked as accepting bindings from the calling * domain. A fresh port is allocated in the calling domain and returned as * <local_port>. + * + * In case the peer domain has already tried to set our event channel + * pending, before it was bound, EVTCHNOP_bind_interdomain always sets + * the local event channel pending. + * + * The usual pattern of use, in the guest's upcall (or subsequent + * handler) is as follows: (Re-enable the event channel for subsequent + * signalling and then) check for the existence of whatever condition + * is being waited for by other means, and take whatever action is + * needed (if any). + * * NOTES: * 1. <remote_dom> may be DOMID_SELF, allowing loopback connections. */ @@ -253,6 +264,10 @@ typedef struct evtchn_unmask evtchn_unmask_t; * NOTES: * 1. <dom> may be specified as DOMID_SELF. * 2. Only a sufficiently-privileged domain may specify other than DOMID_SELF. + * 3. Destroys all control blocks and event array, resets event channel + * operations to 2-level ABI if called with <dom> == DOMID_SELF and FIFO + * ABI was used. Guests should not bind events during EVTCHNOP_reset call + * as these events are likely to be lost. */ struct evtchn_reset { /* IN parameters. */ @@ -261,6 +276,43 @@ struct evtchn_reset { typedef struct evtchn_reset evtchn_reset_t; /* + * EVTCHNOP_init_control: initialize the control block for the FIFO ABI. + * + * Note: any events that are currently pending will not be resent and + * will be lost. Guests should call this before binding any event to + * avoid losing any events. + */ +struct evtchn_init_control { + /* IN parameters. */ + uint64_t control_gfn; + uint32_t offset; + uint32_t vcpu; + /* OUT parameters. */ + uint8_t link_bits; + uint8_t _pad[7]; +}; +typedef struct evtchn_init_control evtchn_init_control_t; + +/* + * EVTCHNOP_expand_array: add an additional page to the event array. + */ +struct evtchn_expand_array { + /* IN parameters. */ + uint64_t array_gfn; +}; +typedef struct evtchn_expand_array evtchn_expand_array_t; + +/* + * EVTCHNOP_set_priority: set the priority for an event channel. + */ +struct evtchn_set_priority { + /* IN parameters. */ + uint32_t port; + uint32_t priority; +}; +typedef struct evtchn_set_priority evtchn_set_priority_t; + +/* * ` enum neg_errnoval * ` HYPERVISOR_event_channel_op_compat(struct evtchn_op *op) * ` @@ -284,12 +336,48 @@ struct evtchn_op { typedef struct evtchn_op evtchn_op_t; DEFINE_XEN_GUEST_HANDLE(evtchn_op_t); +/* + * 2-level ABI + */ + +#define EVTCHN_2L_NR_CHANNELS (sizeof(xen_ulong_t) * sizeof(xen_ulong_t) * 64) + +/* + * FIFO ABI + */ + +/* Events may have priorities from 0 (highest) to 15 (lowest). */ +#define EVTCHN_FIFO_PRIORITY_MAX 0 +#define EVTCHN_FIFO_PRIORITY_DEFAULT 7 +#define EVTCHN_FIFO_PRIORITY_MIN 15 + +#define EVTCHN_FIFO_MAX_QUEUES (EVTCHN_FIFO_PRIORITY_MIN + 1) + +typedef uint32_t event_word_t; + +#define EVTCHN_FIFO_PENDING 31 +#define EVTCHN_FIFO_MASKED 30 +#define EVTCHN_FIFO_LINKED 29 +#define EVTCHN_FIFO_BUSY 28 + +#define EVTCHN_FIFO_LINK_BITS 17 +#define EVTCHN_FIFO_LINK_MASK ((1 << EVTCHN_FIFO_LINK_BITS) - 1) + +#define EVTCHN_FIFO_NR_CHANNELS (1 << EVTCHN_FIFO_LINK_BITS) + +struct evtchn_fifo_control_block { + uint32_t ready; + uint32_t _rsvd; + uint32_t head[EVTCHN_FIFO_MAX_QUEUES]; +}; +typedef struct evtchn_fifo_control_block evtchn_fifo_control_block_t; + #endif /* __XEN_PUBLIC_EVENT_CHANNEL_H__ */ /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/features.h b/sys/xen/interface/features.h index b4533cc..2110b04 100644 --- a/sys/xen/interface/features.h +++ b/sys/xen/interface/features.h @@ -28,6 +28,20 @@ #define __XEN_PUBLIC_FEATURES_H__ /* + * `incontents 200 elfnotes_features XEN_ELFNOTE_FEATURES + * + * The list of all the features the guest supports. They are set by + * parsing the XEN_ELFNOTE_FEATURES and XEN_ELFNOTE_SUPPORTED_FEATURES + * string. The format is the feature names (as given here without the + * "XENFEAT_" prefix) separated by '|' characters. + * If a feature is required for the kernel to function then the feature name + * must be preceded by a '!' character. + * + * Note that if XEN_ELFNOTE_SUPPORTED_FEATURES is used, then in the + * XENFEAT_dom0 MUST be set if the guest is to be booted as dom0, + */ + +/* * If set, the guest does not need to write-protect its pagetables, and can * update them via direct writes. */ @@ -80,6 +94,14 @@ /* operation as Dom0 is supported */ #define XENFEAT_dom0 11 +/* Xen also maps grant references at pfn = mfn. + * This feature flag is deprecated and should not be used. +#define XENFEAT_grant_map_identity 12 + */ + +/* Guest can use XENMEMF_vnode to specify virtual node for memory op. */ +#define XENFEAT_memory_op_vnode_supported 13 + #define XENFEAT_NR_SUBMAPS 1 #endif /* __XEN_PUBLIC_FEATURES_H__ */ @@ -87,7 +109,7 @@ /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/foreign/Makefile b/sys/xen/interface/foreign/Makefile deleted file mode 100644 index 7bde873..0000000 --- a/sys/xen/interface/foreign/Makefile +++ /dev/null @@ -1,37 +0,0 @@ -XEN_ROOT=../../../.. -include $(XEN_ROOT)/Config.mk - -architectures := x86_32 x86_64 ia64 -headers := $(patsubst %, %.h, $(architectures)) -scripts := $(wildcard *.py) - -.PHONY: all clean check-headers -all: $(headers) check-headers - -clean: - rm -f $(headers) - rm -f checker checker.c $(XEN_TARGET_ARCH).size - rm -f *.pyc *.o *~ - -ifeq ($(CROSS_COMPILE)$(XEN_TARGET_ARCH),$(XEN_COMPILE_ARCH)) -check-headers: checker - ./checker > $(XEN_TARGET_ARCH).size - diff -u reference.size $(XEN_TARGET_ARCH).size -checker: checker.c $(headers) - $(HOSTCC) $(HOSTCFLAGS) -o $@ $< -else -check-headers: - @echo "cross build: skipping check" -endif - -x86_32.h: ../arch-x86/xen-x86_32.h ../arch-x86/xen.h ../xen.h $(scripts) - python mkheader.py $* $@ $(filter %.h,$^) - -x86_64.h: ../arch-x86/xen-x86_64.h ../arch-x86/xen.h ../xen.h $(scripts) - python mkheader.py $* $@ $(filter %.h,$^) - -ia64.h: ../arch-ia64.h ../xen.h $(scripts) - python mkheader.py $* $@ $(filter %.h,$^) - -checker.c: $(scripts) - python mkchecker.py $(XEN_TARGET_ARCH) $@ $(architectures) diff --git a/sys/xen/interface/foreign/mkchecker.py b/sys/xen/interface/foreign/mkchecker.py deleted file mode 100644 index 9da1e2b..0000000 --- a/sys/xen/interface/foreign/mkchecker.py +++ /dev/null @@ -1,58 +0,0 @@ -#!/usr/bin/python - -import sys; -from structs import structs; - -# command line arguments -arch = sys.argv[1]; -outfile = sys.argv[2]; -archs = sys.argv[3:]; - -f = open(outfile, "w"); -f.write(''' -/* - * sanity checks for generated foreign headers: - * - verify struct sizes - * - * generated by %s -- DO NOT EDIT - */ -#include <stdio.h> -#include <stdlib.h> -#include <stddef.h> -#include <inttypes.h> -#include "../xen.h" -'''); - -for a in archs: - f.write('#include "%s.h"\n' % a); - -f.write('int main(int argc, char *argv[])\n{\n'); - -f.write('\tprintf("\\n");'); -f.write('printf("%-25s |", "structs");\n'); -for a in archs: - f.write('\tprintf("%%8s", "%s");\n' % a); -f.write('\tprintf("\\n");'); - -f.write('\tprintf("\\n");'); -for struct in structs: - f.write('\tprintf("%%-25s |", "%s");\n' % struct); - for a in archs: - if a == arch: - s = struct; # native - else: - s = struct + "_" + a; - f.write('#ifdef %s_has_no_%s\n' % (a, struct)); - f.write('\tprintf("%8s", "-");\n'); - f.write("#else\n"); - f.write('\tprintf("%%8zd", sizeof(struct %s));\n' % s); - f.write("#endif\n"); - - f.write('\tprintf("\\n");\n\n'); - -f.write('\tprintf("\\n");\n'); -f.write('\texit(0);\n'); -f.write('}\n'); - -f.close(); - diff --git a/sys/xen/interface/foreign/mkheader.py b/sys/xen/interface/foreign/mkheader.py deleted file mode 100644 index d833c7e..0000000 --- a/sys/xen/interface/foreign/mkheader.py +++ /dev/null @@ -1,167 +0,0 @@ -#!/usr/bin/python - -import sys, re; -from structs import unions, structs, defines; - -# command line arguments -arch = sys.argv[1]; -outfile = sys.argv[2]; -infiles = sys.argv[3:]; - - -########################################################################### -# configuration #2: architecture information - -inttypes = {}; -header = {}; -footer = {}; - -# x86_32 -inttypes["x86_32"] = { - "unsigned long" : "uint32_t", - "long" : "uint32_t", - "xen_pfn_t" : "uint32_t", -}; -header["x86_32"] = """ -#define __i386___X86_32 1 -#pragma pack(4) -"""; -footer["x86_32"] = """ -#pragma pack() -"""; - -# x86_64 -inttypes["x86_64"] = { - "unsigned long" : "__align8__ uint64_t", - "long" : "__align8__ uint64_t", - "xen_pfn_t" : "__align8__ uint64_t", -}; -header["x86_64"] = """ -#ifdef __GNUC__ -# define __DECL_REG(name) union { uint64_t r ## name, e ## name; } -# define __align8__ __attribute__((aligned (8))) -#else -# define __DECL_REG(name) uint64_t r ## name -# define __align8__ FIXME -#endif -#define __x86_64___X86_64 1 -"""; - -# ia64 -inttypes["ia64"] = { - "unsigned long" : "__align8__ uint64_t", - "long" : "__align8__ uint64_t", - "xen_pfn_t" : "__align8__ uint64_t", - "long double" : "__align16__ ldouble_t", -}; -header["ia64"] = """ -#define __align8__ __attribute__((aligned (8))) -#define __align16__ __attribute__((aligned (16))) -typedef unsigned char ldouble_t[16]; -"""; - - -########################################################################### -# main - -input = ""; -output = ""; -fileid = re.sub("[-.]", "_", "__FOREIGN_%s__" % outfile.upper()); - -# read input header files -for name in infiles: - f = open(name, "r"); - input += f.read(); - f.close(); - -# add header -output += """ -/* - * public xen defines and struct for %s - * generated by %s -- DO NOT EDIT - */ - -#ifndef %s -#define %s 1 - -""" % (arch, sys.argv[0], fileid, fileid) - -if arch in header: - output += header[arch]; - output += "\n"; - -# add defines to output -for line in re.findall("#define[^\n]+", input): - for define in defines: - regex = "#define\s+%s\\b" % define; - match = re.search(regex, line); - if None == match: - continue; - if define.upper()[0] == define[0]: - replace = define + "_" + arch.upper(); - else: - replace = define + "_" + arch; - regex = "\\b%s\\b" % define; - output += re.sub(regex, replace, line) + "\n"; -output += "\n"; - -# delete defines, comments, empty lines -input = re.sub("#define[^\n]+\n", "", input); -input = re.compile("/\*(.*?)\*/", re.S).sub("", input) -input = re.compile("\n\s*\n", re.S).sub("\n", input); - -# add unions to output -for union in unions: - regex = "union\s+%s\s*\{(.*?)\n\};" % union; - match = re.search(regex, input, re.S) - if None == match: - output += "#define %s_has_no_%s 1\n" % (arch, union); - else: - output += "union %s_%s {%s\n};\n" % (union, arch, match.group(1)); - output += "\n"; - -# add structs to output -for struct in structs: - regex = "struct\s+%s\s*\{(.*?)\n\};" % struct; - match = re.search(regex, input, re.S) - if None == match: - output += "#define %s_has_no_%s 1\n" % (arch, struct); - else: - output += "struct %s_%s {%s\n};\n" % (struct, arch, match.group(1)); - output += "typedef struct %s_%s %s_%s_t;\n" % (struct, arch, struct, arch); - output += "\n"; - -# add footer -if arch in footer: - output += footer[arch]; - output += "\n"; -output += "#endif /* %s */\n" % fileid; - -# replace: defines -for define in defines: - if define.upper()[0] == define[0]: - replace = define + "_" + arch.upper(); - else: - replace = define + "_" + arch; - output = re.sub("\\b%s\\b" % define, replace, output); - -# replace: unions -for union in unions: - output = re.sub("\\b(union\s+%s)\\b" % union, "\\1_%s" % arch, output); - -# replace: structs + struct typedefs -for struct in structs: - output = re.sub("\\b(struct\s+%s)\\b" % struct, "\\1_%s" % arch, output); - output = re.sub("\\b(%s)_t\\b" % struct, "\\1_%s_t" % arch, output); - -# replace: integer types -integers = list(inttypes[arch].keys()); -integers.sort(lambda a, b: cmp(len(b),len(a))); -for type in integers: - output = re.sub("\\b%s\\b" % type, inttypes[arch][type], output); - -# print results -f = open(outfile, "w"); -f.write(output); -f.close; - diff --git a/sys/xen/interface/foreign/reference.size b/sys/xen/interface/foreign/reference.size deleted file mode 100644 index f35d281..0000000 --- a/sys/xen/interface/foreign/reference.size +++ /dev/null @@ -1,17 +0,0 @@ - -structs | x86_32 x86_64 ia64 - -start_info | 1104 1152 1152 -trap_info | 8 16 - -pt_fpreg | - - 16 -cpu_user_regs | 68 200 496 -xen_ia64_boot_param | - - 96 -ia64_tr_entry | - - 32 -vcpu_extra_regs | - - 536 -vcpu_guest_context | 2800 5168 1056 -arch_vcpu_info | 24 16 0 -vcpu_time_info | 32 32 32 -vcpu_info | 64 64 48 -arch_shared_info | 268 280 272 -shared_info | 2584 3368 4384 - diff --git a/sys/xen/interface/foreign/structs.py b/sys/xen/interface/foreign/structs.py deleted file mode 100644 index a1bc055..0000000 --- a/sys/xen/interface/foreign/structs.py +++ /dev/null @@ -1,58 +0,0 @@ -# configuration: what needs translation - -unions = [ "vcpu_cr_regs", - "vcpu_ar_regs" ]; - -structs = [ "start_info", - "trap_info", - "pt_fpreg", - "cpu_user_regs", - "xen_ia64_boot_param", - "ia64_tr_entry", - "vcpu_tr_regs", - "vcpu_guest_context_regs", - "vcpu_guest_context", - "arch_vcpu_info", - "vcpu_time_info", - "vcpu_info", - "arch_shared_info", - "shared_info" ]; - -defines = [ "__i386__", - "__x86_64__", - - "FLAT_RING1_CS", - "FLAT_RING1_DS", - "FLAT_RING1_SS", - - "FLAT_RING3_CS64", - "FLAT_RING3_DS64", - "FLAT_RING3_SS64", - "FLAT_KERNEL_CS64", - "FLAT_KERNEL_DS64", - "FLAT_KERNEL_SS64", - - "FLAT_KERNEL_CS", - "FLAT_KERNEL_DS", - "FLAT_KERNEL_SS", - - # x86_{32,64} - "_VGCF_i387_valid", - "VGCF_i387_valid", - "_VGCF_in_kernel", - "VGCF_in_kernel", - "_VGCF_failsafe_disables_events", - "VGCF_failsafe_disables_events", - "_VGCF_syscall_disables_events", - "VGCF_syscall_disables_events", - "_VGCF_online", - "VGCF_online", - - # ia64 - "VGCF_EXTRA_REGS", - - # all archs - "xen_pfn_to_cr3", - "XEN_LEGACY_MAX_VCPUS", - "MAX_GUEST_CMDLINE" ]; - diff --git a/sys/xen/interface/gcov.h b/sys/xen/interface/gcov.h new file mode 100644 index 0000000..1b29b48 --- /dev/null +++ b/sys/xen/interface/gcov.h @@ -0,0 +1,115 @@ +/****************************************************************************** + * gcov.h + * + * Coverage structures exported by Xen. + * Structure is different from Gcc one. + * + * 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) 2013, Citrix Systems R&D Ltd. + */ + +#ifndef __XEN_PUBLIC_GCOV_H__ +#define __XEN_PUBLIC_GCOV_H__ __XEN_PUBLIC_GCOV_H__ + +#define XENCOV_COUNTERS 5 +#define XENCOV_TAG_BASE 0x58544300u +#define XENCOV_TAG_FILE (XENCOV_TAG_BASE+0x46u) +#define XENCOV_TAG_FUNC (XENCOV_TAG_BASE+0x66u) +#define XENCOV_TAG_COUNTER(n) (XENCOV_TAG_BASE+0x30u+((n)&0xfu)) +#define XENCOV_TAG_END (XENCOV_TAG_BASE+0x2eu) +#define XENCOV_IS_TAG_COUNTER(n) \ + ((n) >= XENCOV_TAG_COUNTER(0) && (n) < XENCOV_TAG_COUNTER(XENCOV_COUNTERS)) +#define XENCOV_COUNTER_NUM(n) ((n)-XENCOV_TAG_COUNTER(0)) + +/* + * The main structure for the blob is + * BLOB := FILE.. END + * FILE := TAG_FILE VERSION STAMP FILENAME COUNTERS FUNCTIONS + * FILENAME := LEN characters + * characters are padded to 32 bit + * LEN := 32 bit value + * COUNTERS := TAG_COUNTER(n) NUM COUNTER.. + * NUM := 32 bit valie + * COUNTER := 64 bit value + * FUNCTIONS := TAG_FUNC NUM FUNCTION.. + * FUNCTION := IDENT CHECKSUM NUM_COUNTERS + * + * All tagged structures are aligned to 8 bytes + */ + +/** + * File information + * Prefixed with XENCOV_TAG_FILE and a string with filename + * Aligned to 8 bytes + */ +struct xencov_file +{ + uint32_t tag; /* XENCOV_TAG_FILE */ + uint32_t version; + uint32_t stamp; + uint32_t fn_len; + char filename[1]; +}; + + +/** + * Counters information + * Prefixed with XENCOV_TAG_COUNTER(n) where n is 0..(XENCOV_COUNTERS-1) + * Aligned to 8 bytes + */ +struct xencov_counter +{ + uint32_t tag; /* XENCOV_TAG_COUNTER(n) */ + uint32_t num; + uint64_t values[1]; +}; + +/** + * Information for each function + * Number of counter is equal to the number of counter structures got before + */ +struct xencov_function +{ + uint32_t ident; + uint32_t checksum; + uint32_t num_counters[1]; +}; + +/** + * Information for all functions + * Aligned to 8 bytes + */ +struct xencov_functions +{ + uint32_t tag; /* XENCOV_TAG_FUNC */ + uint32_t num; + struct xencov_function xencov_function[1]; +}; + +/** + * Terminator + */ +struct xencov_end +{ + uint32_t tag; /* XENCOV_TAG_END */ +}; + +#endif /* __XEN_PUBLIC_GCOV_H__ */ + diff --git a/sys/xen/interface/grant_table.h b/sys/xen/interface/grant_table.h index 28d9476..e9393fd 100644 --- a/sys/xen/interface/grant_table.h +++ b/sys/xen/interface/grant_table.h @@ -134,8 +134,10 @@ struct grant_entry_v1 { /* 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] + * GTF_permit_access: GFN that @domid is allowed to map and access. [GST] + * GTF_accept_transfer: GFN that @domid is allowed to transfer into. [GST] + * GTF_transfer_completed: MFN whose ownership transferred by @domid + * (non-translated guests only). [XEN] */ uint32_t frame; }; @@ -309,6 +311,7 @@ typedef uint16_t grant_status_t; #define GNTTABOP_get_status_frames 9 #define GNTTABOP_get_version 10 #define GNTTABOP_swap_grant_ref 11 +#define GNTTABOP_cache_flush 12 #endif /* __XEN_INTERFACE_VERSION__ */ /* ` } */ @@ -320,7 +323,7 @@ typedef uint32_t grant_handle_t; /* * GNTTABOP_map_grant_ref: Map the grant entry (<dom>,<ref>) for access * by devices and/or host CPUs. If successful, <handle> is a tracking number - * that must be presented later to destroy the mapping(s). On error, <handle> + * that must be presented later to destroy the mapping(s). On error, <status> * is a negative status code. * NOTES: * 1. If GNTMAP_device_map is specified then <dev_bus_addr> is the address @@ -385,7 +388,11 @@ struct gnttab_setup_table { 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); @@ -445,12 +452,10 @@ DEFINE_XEN_GUEST_HANDLE(gnttab_transfer_t); #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) struct gnttab_copy { /* IN parameters. */ - struct { + struct gnttab_copy_ptr { union { grant_ref_t ref; xen_pfn_t gmfn; @@ -572,6 +577,25 @@ struct gnttab_swap_grant_ref { typedef struct gnttab_swap_grant_ref gnttab_swap_grant_ref_t; DEFINE_XEN_GUEST_HANDLE(gnttab_swap_grant_ref_t); +/* + * Issue one or more cache maintenance operations on a portion of a + * page granted to the calling domain by a foreign domain. + */ +struct gnttab_cache_flush { + union { + uint64_t dev_bus_addr; + grant_ref_t ref; + } a; + uint16_t offset; /* offset from start of grant */ + uint16_t length; /* size within the grant */ +#define GNTTAB_CACHE_CLEAN (1<<0) +#define GNTTAB_CACHE_INVAL (1<<1) +#define GNTTAB_CACHE_SOURCE_GREF (1<<31) + uint32_t op; +}; +typedef struct gnttab_cache_flush gnttab_cache_flush_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_cache_flush_t); + #endif /* __XEN_INTERFACE_VERSION__ */ /* @@ -652,7 +676,7 @@ DEFINE_XEN_GUEST_HANDLE(gnttab_swap_grant_ref_t); /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/hvm/e820.h b/sys/xen/interface/hvm/e820.h index 5bdc227..6c58a37 100644 --- a/sys/xen/interface/hvm/e820.h +++ b/sys/xen/interface/hvm/e820.h @@ -1,4 +1,3 @@ - /* * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to @@ -17,6 +16,8 @@ * 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, Keir Fraser */ #ifndef __XEN_PUBLIC_HVM_E820_H__ diff --git a/sys/xen/interface/hvm/hvm_info_table.h b/sys/xen/interface/hvm/hvm_info_table.h index 36085fa..9e3f807 100644 --- a/sys/xen/interface/hvm/hvm_info_table.h +++ b/sys/xen/interface/hvm/hvm_info_table.h @@ -20,6 +20,8 @@ * 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, Keir Fraser */ #ifndef __XEN_PUBLIC_HVM_HVM_INFO_TABLE_H__ diff --git a/sys/xen/interface/hvm/hvm_op.h b/sys/xen/interface/hvm/hvm_op.h index a9aab4b..1606185 100644 --- a/sys/xen/interface/hvm/hvm_op.h +++ b/sys/xen/interface/hvm/hvm_op.h @@ -16,6 +16,8 @@ * 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) 2007, Keir Fraser */ #ifndef __XEN_PUBLIC_HVM_HVM_OP_H__ @@ -23,6 +25,7 @@ #include "../xen.h" #include "../trace.h" +#include "../event_channel.h" /* Get/set subcommands: extra argument == pointer to xen_hvm_param struct. */ #define HVMOP_set_param 0 @@ -80,6 +83,7 @@ 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_mmio_write_dm /* Read-only; writes go to the device model */ } hvmmem_type_t; /* Following tools-only interfaces may change in future. */ @@ -90,10 +94,10 @@ typedef enum { struct xen_hvm_track_dirty_vram { /* Domain to be tracked. */ domid_t domid; + /* Number of pages to track. */ + uint32_t nr; /* 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; @@ -106,10 +110,10 @@ DEFINE_XEN_GUEST_HANDLE(xen_hvm_track_dirty_vram_t); struct xen_hvm_modified_memory { /* Domain to be updated. */ domid_t domid; + /* Number of pages. */ + uint32_t nr; /* 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); @@ -162,49 +166,11 @@ DEFINE_XEN_GUEST_HANDLE(xen_hvm_xentrace_t); /* Following tools-only interfaces may change in future. */ #if defined(__XEN__) || defined(__XEN_TOOLS__) +/* Deprecated by XENMEM_access_op_set_access */ #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); +/* Deprecated by XENMEM_access_op_get_access */ #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 @@ -270,6 +236,267 @@ struct xen_hvm_inject_msi { typedef struct xen_hvm_inject_msi xen_hvm_inject_msi_t; DEFINE_XEN_GUEST_HANDLE(xen_hvm_inject_msi_t); +/* + * IOREQ Servers + * + * The interface between an I/O emulator an Xen is called an IOREQ Server. + * A domain supports a single 'legacy' IOREQ Server which is instantiated if + * parameter... + * + * HVM_PARAM_IOREQ_PFN is read (to get the gmfn containing the synchronous + * ioreq structures), or... + * HVM_PARAM_BUFIOREQ_PFN is read (to get the gmfn containing the buffered + * ioreq ring), or... + * HVM_PARAM_BUFIOREQ_EVTCHN is read (to get the event channel that Xen uses + * to request buffered I/O emulation). + * + * The following hypercalls facilitate the creation of IOREQ Servers for + * 'secondary' emulators which are invoked to implement port I/O, memory, or + * PCI config space ranges which they explicitly register. + */ + +typedef uint16_t ioservid_t; + +/* + * HVMOP_create_ioreq_server: Instantiate a new IOREQ Server for a secondary + * emulator servicing domain <domid>. + * + * The <id> handed back is unique for <domid>. If <handle_bufioreq> is zero + * the buffered ioreq ring will not be allocated and hence all emulation + * requestes to this server will be synchronous. + */ +#define HVMOP_create_ioreq_server 17 +struct xen_hvm_create_ioreq_server { + domid_t domid; /* IN - domain to be serviced */ +#define HVM_IOREQSRV_BUFIOREQ_OFF 0 +#define HVM_IOREQSRV_BUFIOREQ_LEGACY 1 +/* + * Use this when read_pointer gets updated atomically and + * the pointer pair gets read atomically: + */ +#define HVM_IOREQSRV_BUFIOREQ_ATOMIC 2 + uint8_t handle_bufioreq; /* IN - should server handle buffered ioreqs */ + ioservid_t id; /* OUT - server id */ +}; +typedef struct xen_hvm_create_ioreq_server xen_hvm_create_ioreq_server_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_create_ioreq_server_t); + +/* + * HVMOP_get_ioreq_server_info: Get all the information necessary to access + * IOREQ Server <id>. + * + * The emulator needs to map the synchronous ioreq structures and buffered + * ioreq ring (if it exists) that Xen uses to request emulation. These are + * hosted in domain <domid>'s gmfns <ioreq_pfn> and <bufioreq_pfn> + * respectively. In addition, if the IOREQ Server is handling buffered + * emulation requests, the emulator needs to bind to event channel + * <bufioreq_port> to listen for them. (The event channels used for + * synchronous emulation requests are specified in the per-CPU ioreq + * structures in <ioreq_pfn>). + * If the IOREQ Server is not handling buffered emulation requests then the + * values handed back in <bufioreq_pfn> and <bufioreq_port> will both be 0. + */ +#define HVMOP_get_ioreq_server_info 18 +struct xen_hvm_get_ioreq_server_info { + domid_t domid; /* IN - domain to be serviced */ + ioservid_t id; /* IN - server id */ + evtchn_port_t bufioreq_port; /* OUT - buffered ioreq port */ + uint64_aligned_t ioreq_pfn; /* OUT - sync ioreq pfn */ + uint64_aligned_t bufioreq_pfn; /* OUT - buffered ioreq pfn */ +}; +typedef struct xen_hvm_get_ioreq_server_info xen_hvm_get_ioreq_server_info_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_get_ioreq_server_info_t); + +/* + * HVM_map_io_range_to_ioreq_server: Register an I/O range of domain <domid> + * for emulation by the client of IOREQ + * Server <id> + * HVM_unmap_io_range_from_ioreq_server: Deregister an I/O range of <domid> + * for emulation by the client of IOREQ + * Server <id> + * + * There are three types of I/O that can be emulated: port I/O, memory accesses + * and PCI config space accesses. The <type> field denotes which type of range + * the <start> and <end> (inclusive) fields are specifying. + * PCI config space ranges are specified by segment/bus/device/function values + * which should be encoded using the HVMOP_PCI_SBDF helper macro below. + * + * NOTE: unless an emulation request falls entirely within a range mapped + * by a secondary emulator, it will not be passed to that emulator. + */ +#define HVMOP_map_io_range_to_ioreq_server 19 +#define HVMOP_unmap_io_range_from_ioreq_server 20 +struct xen_hvm_io_range { + domid_t domid; /* IN - domain to be serviced */ + ioservid_t id; /* IN - server id */ + uint32_t type; /* IN - type of range */ +# define HVMOP_IO_RANGE_PORT 0 /* I/O port range */ +# define HVMOP_IO_RANGE_MEMORY 1 /* MMIO range */ +# define HVMOP_IO_RANGE_PCI 2 /* PCI segment/bus/dev/func range */ + uint64_aligned_t start, end; /* IN - inclusive start and end of range */ +}; +typedef struct xen_hvm_io_range xen_hvm_io_range_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_io_range_t); + +#define HVMOP_PCI_SBDF(s,b,d,f) \ + ((((s) & 0xffff) << 16) | \ + (((b) & 0xff) << 8) | \ + (((d) & 0x1f) << 3) | \ + ((f) & 0x07)) + +/* + * HVMOP_destroy_ioreq_server: Destroy the IOREQ Server <id> servicing domain + * <domid>. + * + * Any registered I/O ranges will be automatically deregistered. + */ +#define HVMOP_destroy_ioreq_server 21 +struct xen_hvm_destroy_ioreq_server { + domid_t domid; /* IN - domain to be serviced */ + ioservid_t id; /* IN - server id */ +}; +typedef struct xen_hvm_destroy_ioreq_server xen_hvm_destroy_ioreq_server_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_destroy_ioreq_server_t); + +/* + * HVMOP_set_ioreq_server_state: Enable or disable the IOREQ Server <id> servicing + * domain <domid>. + * + * The IOREQ Server will not be passed any emulation requests until it is in the + * enabled state. + * Note that the contents of the ioreq_pfn and bufioreq_fn (see + * HVMOP_get_ioreq_server_info) are not meaningful until the IOREQ Server is in + * the enabled state. + */ +#define HVMOP_set_ioreq_server_state 22 +struct xen_hvm_set_ioreq_server_state { + domid_t domid; /* IN - domain to be serviced */ + ioservid_t id; /* IN - server id */ + uint8_t enabled; /* IN - enabled? */ +}; +typedef struct xen_hvm_set_ioreq_server_state xen_hvm_set_ioreq_server_state_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_set_ioreq_server_state_t); + #endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */ +#if defined(__i386__) || defined(__x86_64__) + +/* + * HVMOP_set_evtchn_upcall_vector: Set a <vector> that should be used for event + * channel upcalls on the specified <vcpu>. If set, + * this vector will be used in preference to the + * domain global callback via (see + * HVM_PARAM_CALLBACK_IRQ). + */ +#define HVMOP_set_evtchn_upcall_vector 23 +struct xen_hvm_evtchn_upcall_vector { + uint32_t vcpu; + uint8_t vector; +}; +typedef struct xen_hvm_evtchn_upcall_vector xen_hvm_evtchn_upcall_vector_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_evtchn_upcall_vector_t); + +#endif /* defined(__i386__) || defined(__x86_64__) */ + +#define HVMOP_guest_request_vm_event 24 + +/* HVMOP_altp2m: perform altp2m state operations */ +#define HVMOP_altp2m 25 + +#define HVMOP_ALTP2M_INTERFACE_VERSION 0x00000001 + +struct xen_hvm_altp2m_domain_state { + /* IN or OUT variable on/off */ + uint8_t state; +}; +typedef struct xen_hvm_altp2m_domain_state xen_hvm_altp2m_domain_state_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_altp2m_domain_state_t); + +struct xen_hvm_altp2m_vcpu_enable_notify { + uint32_t vcpu_id; + uint32_t pad; + /* #VE info area gfn */ + uint64_t gfn; +}; +typedef struct xen_hvm_altp2m_vcpu_enable_notify xen_hvm_altp2m_vcpu_enable_notify_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_altp2m_vcpu_enable_notify_t); + +struct xen_hvm_altp2m_view { + /* IN/OUT variable */ + uint16_t view; + /* Create view only: default access type + * NOTE: currently ignored */ + uint16_t hvmmem_default_access; /* xenmem_access_t */ +}; +typedef struct xen_hvm_altp2m_view xen_hvm_altp2m_view_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_altp2m_view_t); + +struct xen_hvm_altp2m_set_mem_access { + /* view */ + uint16_t view; + /* Memory type */ + uint16_t hvmmem_access; /* xenmem_access_t */ + uint32_t pad; + /* gfn */ + uint64_t gfn; +}; +typedef struct xen_hvm_altp2m_set_mem_access xen_hvm_altp2m_set_mem_access_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_altp2m_set_mem_access_t); + +struct xen_hvm_altp2m_change_gfn { + /* view */ + uint16_t view; + uint16_t pad1; + uint32_t pad2; + /* old gfn */ + uint64_t old_gfn; + /* new gfn, INVALID_GFN (~0UL) means revert */ + uint64_t new_gfn; +}; +typedef struct xen_hvm_altp2m_change_gfn xen_hvm_altp2m_change_gfn_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_altp2m_change_gfn_t); + +struct xen_hvm_altp2m_op { + uint32_t version; /* HVMOP_ALTP2M_INTERFACE_VERSION */ + uint32_t cmd; +/* Get/set the altp2m state for a domain */ +#define HVMOP_altp2m_get_domain_state 1 +#define HVMOP_altp2m_set_domain_state 2 +/* Set the current VCPU to receive altp2m event notifications */ +#define HVMOP_altp2m_vcpu_enable_notify 3 +/* Create a new view */ +#define HVMOP_altp2m_create_p2m 4 +/* Destroy a view */ +#define HVMOP_altp2m_destroy_p2m 5 +/* Switch view for an entire domain */ +#define HVMOP_altp2m_switch_p2m 6 +/* Notify that a page of memory is to have specific access types */ +#define HVMOP_altp2m_set_mem_access 7 +/* Change a p2m entry to have a different gfn->mfn mapping */ +#define HVMOP_altp2m_change_gfn 8 + domid_t domain; + uint16_t pad1; + uint32_t pad2; + union { + struct xen_hvm_altp2m_domain_state domain_state; + struct xen_hvm_altp2m_vcpu_enable_notify enable_notify; + struct xen_hvm_altp2m_view view; + struct xen_hvm_altp2m_set_mem_access set_mem_access; + struct xen_hvm_altp2m_change_gfn change_gfn; + uint8_t pad[64]; + } u; +}; +typedef struct xen_hvm_altp2m_op xen_hvm_altp2m_op_t; +DEFINE_XEN_GUEST_HANDLE(xen_hvm_altp2m_op_t); + #endif /* __XEN_PUBLIC_HVM_HVM_OP_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/sys/xen/interface/hvm/hvm_xs_strings.h b/sys/xen/interface/hvm/hvm_xs_strings.h new file mode 100644 index 0000000..146b0b0 --- /dev/null +++ b/sys/xen/interface/hvm/hvm_xs_strings.h @@ -0,0 +1,82 @@ +/****************************************************************************** + * hvm/hvm_xs_strings.h + * + * HVM xenstore strings used in HVMLOADER. + * + * 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) 2013, Citrix Systems + */ + +#ifndef __XEN_PUBLIC_HVM_HVM_XS_STRINGS_H__ +#define __XEN_PUBLIC_HVM_HVM_XS_STRINGS_H__ + +#define HVM_XS_HVMLOADER "hvmloader" +#define HVM_XS_BIOS "hvmloader/bios" +#define HVM_XS_GENERATION_ID_ADDRESS "hvmloader/generation-id-address" +#define HVM_XS_ALLOW_MEMORY_RELOCATE "hvmloader/allow-memory-relocate" + +/* The following values allow additional ACPI tables to be added to the + * virtual ACPI BIOS that hvmloader constructs. The values specify the guest + * physical address and length of a block of ACPI tables to add. The format of + * the block is simply concatenated raw tables (which specify their own length + * in the ACPI header). + */ +#define HVM_XS_ACPI_PT_ADDRESS "hvmloader/acpi/address" +#define HVM_XS_ACPI_PT_LENGTH "hvmloader/acpi/length" + +/* Any number of SMBIOS types can be passed through to an HVM guest using + * the following xenstore values. The values specify the guest physical + * address and length of a block of SMBIOS structures for hvmloader to use. + * The block is formatted in the following way: + * + * <length><struct><length><struct>... + * + * Each length separator is a 32b integer indicating the length of the next + * SMBIOS structure. For DMTF defined types (0 - 121), the passed in struct + * will replace the default structure in hvmloader. In addition, any + * OEM/vendortypes (128 - 255) will all be added. + */ +#define HVM_XS_SMBIOS_PT_ADDRESS "hvmloader/smbios/address" +#define HVM_XS_SMBIOS_PT_LENGTH "hvmloader/smbios/length" + +/* Set to 1 to enable SMBIOS default portable battery (type 22) values. */ +#define HVM_XS_SMBIOS_DEFAULT_BATTERY "hvmloader/smbios/default_battery" + +/* The following xenstore values are used to override some of the default + * string values in the SMBIOS table constructed in hvmloader. + */ +#define HVM_XS_BIOS_STRINGS "bios-strings" +#define HVM_XS_BIOS_VENDOR "bios-strings/bios-vendor" +#define HVM_XS_BIOS_VERSION "bios-strings/bios-version" +#define HVM_XS_SYSTEM_MANUFACTURER "bios-strings/system-manufacturer" +#define HVM_XS_SYSTEM_PRODUCT_NAME "bios-strings/system-product-name" +#define HVM_XS_SYSTEM_VERSION "bios-strings/system-version" +#define HVM_XS_SYSTEM_SERIAL_NUMBER "bios-strings/system-serial-number" +#define HVM_XS_ENCLOSURE_MANUFACTURER "bios-strings/enclosure-manufacturer" +#define HVM_XS_ENCLOSURE_SERIAL_NUMBER "bios-strings/enclosure-serial-number" +#define HVM_XS_BATTERY_MANUFACTURER "bios-strings/battery-manufacturer" +#define HVM_XS_BATTERY_DEVICE_NAME "bios-strings/battery-device-name" + +/* 1 to 99 OEM strings can be set in xenstore using values of the form + * below. These strings will be loaded into the SMBIOS type 11 structure. + */ +#define HVM_XS_OEM_STRINGS "bios-strings/oem-%d" + +#endif /* __XEN_PUBLIC_HVM_HVM_XS_STRINGS_H__ */ diff --git a/sys/xen/interface/hvm/ioreq.h b/sys/xen/interface/hvm/ioreq.h index 4022a1d..2e5809b 100644 --- a/sys/xen/interface/hvm/ioreq.h +++ b/sys/xen/interface/hvm/ioreq.h @@ -34,13 +34,20 @@ #define IOREQ_TYPE_PIO 0 /* pio */ #define IOREQ_TYPE_COPY 1 /* mmio ops */ +#define IOREQ_TYPE_PCI_CONFIG 2 #define IOREQ_TYPE_TIMEOFFSET 7 #define IOREQ_TYPE_INVALIDATE 8 /* mapcache */ /* * VMExit dispatcher should cooperate with instruction decoder to * prepare this structure and notify service OS and DM by sending - * virq + * virq. + * + * For I/O type IOREQ_TYPE_PCI_CONFIG, the physical address is formatted + * as follows: + * + * 63....48|47..40|39..35|34..32|31........0 + * SEGMENT |BUS |DEV |FN |OFFSET */ struct ioreq { uint64_t addr; /* physical address */ @@ -76,30 +83,21 @@ typedef struct buf_ioreq buf_ioreq_t; #define IOREQ_BUFFER_SLOT_NUM 511 /* 8 bytes each, plus 2 4-byte indexes */ struct buffered_iopage { - unsigned int read_pointer; - unsigned int write_pointer; +#ifdef __XEN__ + union bufioreq_pointers { + struct { +#endif + uint32_t read_pointer; + uint32_t write_pointer; +#ifdef __XEN__ + }; + uint64_t full; + } ptrs; +#endif buf_ioreq_t buf_ioreq[IOREQ_BUFFER_SLOT_NUM]; }; /* NB. Size of this structure must be no greater than one page. */ typedef struct buffered_iopage buffered_iopage_t; -#if defined(__ia64__) -struct pio_buffer { - uint32_t page_offset; - uint32_t pointer; - uint32_t data_end; - uint32_t buf_size; - void *opaque; -}; - -#define PIO_BUFFER_IDE_PRIMARY 0 /* I/O port = 0x1F0 */ -#define PIO_BUFFER_IDE_SECONDARY 1 /* I/O port = 0x170 */ -#define PIO_BUFFER_ENTRY_NUM 2 -struct buffered_piopage { - struct pio_buffer pio[PIO_BUFFER_ENTRY_NUM]; - uint8_t buffer[1]; -}; -#endif /* defined(__ia64__) */ - /* * ACPI Control/Event register locations. Location is controlled by a * version number in HVM_PARAM_ACPI_IOPORTS_LOCATION. @@ -132,7 +130,7 @@ struct buffered_piopage { /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/hvm/params.h b/sys/xen/interface/hvm/params.h index 55c1b57..356dfd3 100644 --- a/sys/xen/interface/hvm/params.h +++ b/sys/xen/interface/hvm/params.h @@ -16,6 +16,8 @@ * 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) 2007, Keir Fraser */ #ifndef __XEN_PUBLIC_HVM_PARAMS_H__ @@ -54,16 +56,53 @@ #define HVM_PARAM_BUFIOREQ_PFN 6 #define HVM_PARAM_BUFIOREQ_EVTCHN 26 -#ifdef __ia64__ +#if defined(__i386__) || defined(__x86_64__) -#define HVM_PARAM_NVRAM_FD 7 -#define HVM_PARAM_VHPT_SIZE 8 -#define HVM_PARAM_BUFPIOREQ_PFN 9 +/* + * Viridian enlightenments + * + * (See http://download.microsoft.com/download/A/B/4/AB43A34E-BDD0-4FA6-BDEF-79EEF16E880B/Hypervisor%20Top%20Level%20Functional%20Specification%20v4.0.docx) + * + * To expose viridian enlightenments to the guest set this parameter + * to the desired feature mask. The base feature set must be present + * in any valid feature mask. + */ +#define HVM_PARAM_VIRIDIAN 9 -#elif defined(__i386__) || defined(__x86_64__) +/* Base+Freq viridian feature sets: + * + * - Hypercall MSRs (HV_X64_MSR_GUEST_OS_ID and HV_X64_MSR_HYPERCALL) + * - APIC access MSRs (HV_X64_MSR_EOI, HV_X64_MSR_ICR and HV_X64_MSR_TPR) + * - Virtual Processor index MSR (HV_X64_MSR_VP_INDEX) + * - Timer frequency MSRs (HV_X64_MSR_TSC_FREQUENCY and + * HV_X64_MSR_APIC_FREQUENCY) + */ +#define _HVMPV_base_freq 0 +#define HVMPV_base_freq (1 << _HVMPV_base_freq) -/* Expose Viridian interfaces to this HVM guest? */ -#define HVM_PARAM_VIRIDIAN 9 +/* Feature set modifications */ + +/* Disable timer frequency MSRs (HV_X64_MSR_TSC_FREQUENCY and + * HV_X64_MSR_APIC_FREQUENCY). + * This modification restores the viridian feature set to the + * original 'base' set exposed in releases prior to Xen 4.4. + */ +#define _HVMPV_no_freq 1 +#define HVMPV_no_freq (1 << _HVMPV_no_freq) + +/* Enable Partition Time Reference Counter (HV_X64_MSR_TIME_REF_COUNT) */ +#define _HVMPV_time_ref_count 2 +#define HVMPV_time_ref_count (1 << _HVMPV_time_ref_count) + +/* Enable Reference TSC Page (HV_X64_MSR_REFERENCE_TSC) */ +#define _HVMPV_reference_tsc 3 +#define HVMPV_reference_tsc (1 << _HVMPV_reference_tsc) + +#define HVMPV_feature_mask \ + (HVMPV_base_freq | \ + HVMPV_no_freq | \ + HVMPV_time_ref_count | \ + HVMPV_reference_tsc) #endif @@ -125,28 +164,34 @@ */ #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 */ +/* Deprecated */ #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_PARAM_MEMORY_EVENT_MSR 30 /* 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_MONITOR_RING_PFN 28 #define HVM_PARAM_SHARING_RING_PFN 29 -#define HVM_NR_PARAMS 30 +/* SHUTDOWN_* action in case of a triple fault */ +#define HVM_PARAM_TRIPLE_FAULT_REASON 31 + +#define HVM_PARAM_IOREQ_SERVER_PFN 32 +#define HVM_PARAM_NR_IOREQ_SERVER_PAGES 33 + +/* Location of the VM Generation ID in guest physical address space. */ +#define HVM_PARAM_VM_GENERATION_ID_ADDR 34 + +/* Boolean: Enable altp2m */ +#define HVM_PARAM_ALTP2M 35 + +#define HVM_NR_PARAMS 36 #endif /* __XEN_PUBLIC_HVM_PARAMS_H__ */ diff --git a/sys/xen/interface/hvm/pvdrivers.h b/sys/xen/interface/hvm/pvdrivers.h new file mode 100644 index 0000000..77994d2 --- /dev/null +++ b/sys/xen/interface/hvm/pvdrivers.h @@ -0,0 +1,49 @@ +/* + * pvdrivers.h: Register of PV drivers product numbers. + * Copyright (c) 2012, Citrix Systems Inc. + * + * 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_PVDRIVERS_H_ +#define _XEN_PUBLIC_PVDRIVERS_H_ + +/* + * This is the master registry of product numbers for + * PV drivers. + * If you need a new product number allocating, please + * post to xen-devel@lists.xensource.com. You should NOT use + * a product number without allocating one. + * If you maintain a separate versioning and distribution path + * for PV drivers you should have a separate product number so + * that your drivers can be separated from others. + * + * During development, you may use the product ID to + * indicate a driver which is yet to be released. + */ + +#define PVDRIVERS_PRODUCT_LIST(EACH) \ + EACH("xensource-windows", 0x0001) /* Citrix */ \ + EACH("gplpv-windows", 0x0002) /* James Harper */ \ + EACH("linux", 0x0003) \ + EACH("xenserver-windows-v7.0+", 0x0004) /* Citrix */ \ + EACH("xenserver-windows-v7.2+", 0x0005) /* Citrix */ \ + EACH("experimental", 0xffff) + +#endif /* _XEN_PUBLIC_PVDRIVERS_H_ */ diff --git a/sys/xen/interface/hvm/save.h b/sys/xen/interface/hvm/save.h index 58f8433..cc8b5fd 100644 --- a/sys/xen/interface/hvm/save.h +++ b/sys/xen/interface/hvm/save.h @@ -102,9 +102,7 @@ DECLARE_HVM_SAVE_TYPE(END, 0, struct hvm_save_end); #if defined(__i386__) || defined(__x86_64__) #include "../arch-x86/hvm/save.h" -#elif defined(__ia64__) -#include "../arch-ia64/hvm/save.h" -#elif defined(__arm__) +#elif defined(__arm__) || defined(__aarch64__) #include "../arch-arm/hvm/save.h" #else #error "unsupported architecture" diff --git a/sys/xen/interface/io/blkif.h b/sys/xen/interface/io/blkif.h index 9c73ae7..8f0f9a6 100644 --- a/sys/xen/interface/io/blkif.h +++ b/sys/xen/interface/io/blkif.h @@ -59,7 +59,7 @@ * All data in the XenStore is stored as strings. Nodes specifying numeric * values are encoded in decimal. Integer value ranges listed below are * expressed as fixed sized integer types capable of storing the conversion - * of a properly formatted node string, without loss of information. + * of a properly formated node string, without loss of information. * * Any specified default value is in effect if the corresponding XenBus node * is not present in the XenStore. @@ -88,9 +88,15 @@ * params * Values: string * - * Data used by the backend driver to locate and configure the backing - * device. The format and semantics of this data vary according to the - * backing device in use and are outside the scope of this specification. + * A free formatted string providing sufficient information for the + * backend driver to open the backing device. (e.g. the path to the + * file or block device representing the backing store.) + * + * physical-device + * Values: "MAJOR:MINOR" + * + * MAJOR and MINOR are the major number and minor number of the + * backing device respectively. * * type * Values: "file", "phy", "tap" @@ -493,7 +499,7 @@ * discarded region on the device must be rendered unrecoverable before the * command returns. * - * This operation is analogous to performing a trim (ATA) or unmap (SCSI), + * This operation is analogous to performing a trim (ATA) or unamp (SCSI), * command on a native device. * * More information about trim/unmap operations can be found at: @@ -558,7 +564,6 @@ struct blkif_request_segment { /* @last_sect: last sector in frame to transfer (inclusive). */ uint8_t first_sect, last_sect; }; -typedef struct blkif_request_segment blkif_request_segment_t; /* * Starting ring element for any I/O request. @@ -569,7 +574,7 @@ struct blkif_request { blkif_vdev_t handle; /* only for read/write requests */ uint64_t id; /* private guest value, echoed in resp */ blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */ - blkif_request_segment_t seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; }; typedef struct blkif_request blkif_request_t; diff --git a/sys/xen/interface/io/console.h b/sys/xen/interface/io/console.h index 4b8c01a..e2cd97f 100644 --- a/sys/xen/interface/io/console.h +++ b/sys/xen/interface/io/console.h @@ -43,7 +43,7 @@ struct xencons_interface { /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/io/fbif.h b/sys/xen/interface/io/fbif.h index 95377a0..cc25aab 100644 --- a/sys/xen/interface/io/fbif.h +++ b/sys/xen/interface/io/fbif.h @@ -168,7 +168,7 @@ struct xenfb_page /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/io/kbdif.h b/sys/xen/interface/io/kbdif.h index e1d66a5..2d2aebd 100644 --- a/sys/xen/interface/io/kbdif.h +++ b/sys/xen/interface/io/kbdif.h @@ -124,7 +124,7 @@ struct xenkbd_page /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/io/libxenvchan.h b/sys/xen/interface/io/libxenvchan.h index 5c3d3d4..a62869a 100644 --- a/sys/xen/interface/io/libxenvchan.h +++ b/sys/xen/interface/io/libxenvchan.h @@ -21,8 +21,7 @@ * Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + * License along with this library; If not, see <http://www.gnu.org/licenses/>. * * @section DESCRIPTION * diff --git a/sys/xen/interface/io/netif.h b/sys/xen/interface/io/netif.h index aca5df4..5c31ae3 100644 --- a/sys/xen/interface/io/netif.h +++ b/sys/xen/interface/io/netif.h @@ -31,6 +31,24 @@ #include "../grant_table.h" /* + * Older implementation of Xen network frontend / backend has an + * implicit dependency on the MAX_SKB_FRAGS as the maximum number of + * ring slots a skb can use. Netfront / netback may not work as + * expected when frontend and backend have different MAX_SKB_FRAGS. + * + * A better approach is to add mechanism for netfront / netback to + * negotiate this value. However we cannot fix all possible + * frontends, so we need to define a value which states the minimum + * slots backend must support. + * + * The minimum value derives from older Linux kernel's MAX_SKB_FRAGS + * (18), which is proved to work with most frontends. Any new backend + * which doesn't negotiate with frontend should expect frontend to + * send a valid packet using slots up to this value. + */ +#define XEN_NETIF_NR_SLOTS_MIN 18 + +/* * Notifications after enqueuing any type of message should be conditional on * the appropriate req_event or rsp_event field in the shared ring. * If the client sends notification for rx requests then it should specify @@ -39,14 +57,224 @@ */ /* + * "feature-split-event-channels" is introduced to separate guest TX + * and RX notification. Backend either doesn't support this feature or + * advertises it via xenstore as 0 (disabled) or 1 (enabled). + * + * To make use of this feature, frontend should allocate two event + * channels for TX and RX, advertise them to backend as + * "event-channel-tx" and "event-channel-rx" respectively. If frontend + * doesn't want to use this feature, it just writes "event-channel" + * node as before. + */ + +/* + * Multiple transmit and receive queues: + * If supported, the backend will write the key "multi-queue-max-queues" to + * the directory for that vif, and set its value to the maximum supported + * number of queues. + * Frontends that are aware of this feature and wish to use it can write the + * key "multi-queue-num-queues", set to the number they wish to use, which + * must be greater than zero, and no more than the value reported by the backend + * in "multi-queue-max-queues". + * + * Queues replicate the shared rings and event channels. + * "feature-split-event-channels" may optionally be used when using + * multiple queues, but is not mandatory. + * + * Each queue consists of one shared ring pair, i.e. there must be the same + * number of tx and rx rings. + * + * For frontends requesting just one queue, the usual event-channel and + * ring-ref keys are written as before, simplifying the backend processing + * to avoid distinguishing between a frontend that doesn't understand the + * multi-queue feature, and one that does, but requested only one queue. + * + * Frontends requesting two or more queues must not write the toplevel + * event-channel (or event-channel-{tx,rx}) and {tx,rx}-ring-ref keys, + * instead writing those keys under sub-keys having the name "queue-N" where + * N is the integer ID of the queue for which those keys belong. Queues + * are indexed from zero. For example, a frontend with two queues and split + * event channels must write the following set of queue-related keys: + * + * /local/domain/1/device/vif/0/multi-queue-num-queues = "2" + * /local/domain/1/device/vif/0/queue-0 = "" + * /local/domain/1/device/vif/0/queue-0/tx-ring-ref = "<ring-ref-tx0>" + * /local/domain/1/device/vif/0/queue-0/rx-ring-ref = "<ring-ref-rx0>" + * /local/domain/1/device/vif/0/queue-0/event-channel-tx = "<evtchn-tx0>" + * /local/domain/1/device/vif/0/queue-0/event-channel-rx = "<evtchn-rx0>" + * /local/domain/1/device/vif/0/queue-1 = "" + * /local/domain/1/device/vif/0/queue-1/tx-ring-ref = "<ring-ref-tx1>" + * /local/domain/1/device/vif/0/queue-1/rx-ring-ref = "<ring-ref-rx1" + * /local/domain/1/device/vif/0/queue-1/event-channel-tx = "<evtchn-tx1>" + * /local/domain/1/device/vif/0/queue-1/event-channel-rx = "<evtchn-rx1>" + * + * If there is any inconsistency in the XenStore data, the backend may + * choose not to connect any queues, instead treating the request as an + * error. This includes scenarios where more (or fewer) queues were + * requested than the frontend provided details for. + * + * Mapping of packets to queues is considered to be a function of the + * transmitting system (backend or frontend) and is not negotiated + * between the two. Guests are free to transmit packets on any queue + * they choose, provided it has been set up correctly. Guests must be + * prepared to receive packets on any queue they have requested be set up. + */ + +/* + * "feature-no-csum-offload" should be used to turn IPv4 TCP/UDP checksum + * offload off or on. If it is missing then the feature is assumed to be on. + * "feature-ipv6-csum-offload" should be used to turn IPv6 TCP/UDP checksum + * offload on or off. If it is missing then the feature is assumed to be off. + */ + +/* + * "feature-gso-tcpv4" and "feature-gso-tcpv6" advertise the capability to + * handle large TCP packets (in IPv4 or IPv6 form respectively). Neither + * frontends nor backends are assumed to be capable unless the flags are + * present. + */ + +/* + * "feature-multicast-control" advertises the capability to filter ethernet + * multicast packets in the backend. To enable use of this capability the + * frontend must set "request-multicast-control" before moving into the + * connected state. + * + * If "request-multicast-control" is set then the backend transmit side should + * no longer flood multicast packets to the frontend, it should instead drop any + * multicast packet that does not match in a filter list. The list is + * amended by the frontend by sending dummy transmit requests containing + * XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL} extra-info fragments as specified below. + * Once enabled by the frontend, the feature cannot be disabled except by + * closing and re-connecting to the backend. + */ + +/* * This is the 'wire' format for packets: - * Request 1: netif_tx_request -- NETTXF_* (any flags) - * [Request 2: netif_tx_extra] (only if request 1 has NETTXF_extra_info) - * [Request 3: netif_tx_extra] (only if request 2 has XEN_NETIF_EXTRA_FLAG_MORE) - * Request 4: netif_tx_request -- NETTXF_more_data - * Request 5: netif_tx_request -- NETTXF_more_data + * Request 1: netif_tx_request_t -- NETTXF_* (any flags) + * [Request 2: netif_extra_info_t] (only if request 1 has NETTXF_extra_info) + * [Request 3: netif_extra_info_t] (only if request 2 has XEN_NETIF_EXTRA_MORE) + * Request 4: netif_tx_request_t -- NETTXF_more_data + * Request 5: netif_tx_request_t -- NETTXF_more_data * ... - * Request N: netif_tx_request -- 0 + * Request N: netif_tx_request_t -- 0 + */ + +/* + * Guest transmit + * ============== + * + * Ring slot size is 12 octets, however not all request/response + * structs use the full size. + * + * tx request data (netif_tx_request_t) + * ------------------------------------ + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | grant ref | offset | flags | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | id | size | + * +-----+-----+-----+-----+ + * + * grant ref: Reference to buffer page. + * offset: Offset within buffer page. + * flags: NETTXF_*. + * id: request identifier, echoed in response. + * size: packet size in bytes. + * + * tx response (netif_tx_response_t) + * --------------------------------- + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | id | status | unused | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | unused | + * +-----+-----+-----+-----+ + * + * id: reflects id in transmit request + * status: NETIF_RSP_* + * + * Guest receive + * ============= + * + * Ring slot size is 8 octets. + * + * rx request (netif_rx_request_t) + * ------------------------------- + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | id | pad | gref | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * + * id: request identifier, echoed in response. + * gref: reference to incoming granted frame. + * + * rx response (netif_rx_response_t) + * --------------------------------- + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | id | offset | flags | status | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * + * id: reflects id in receive request + * offset: offset in page of start of received packet + * flags: NETRXF_* + * status: -ve: NETIF_RSP_*; +ve: Rx'ed pkt size. + * + * Extra Info + * ========== + * + * Can be present if initial request has NET{T,R}XF_extra_info, or + * previous extra request has XEN_NETIF_EXTRA_MORE. + * + * The struct therefore needs to fit into either a tx or rx slot and + * is therefore limited to 8 octets. + * + * extra info (netif_extra_info_t) + * ------------------------------- + * + * General format: + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * |type |flags| type specfic data | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * | padding for tx | + * +-----+-----+-----+-----+ + * + * type: XEN_NETIF_EXTRA_TYPE_* + * flags: XEN_NETIF_EXTRA_FLAG_* + * padding for tx: present only in the tx case due to 8 octet limit + * from rx case. Not shown in type specific entries below. + * + * XEN_NETIF_EXTRA_TYPE_GSO: + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * |type |flags| size |type | pad | features | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * + * type: Must be XEN_NETIF_EXTRA_TYPE_GSO + * flags: XEN_NETIF_EXTRA_FLAG_* + * size: Maximum payload size of each segment. + * type: XEN_NETIF_GSO_TYPE_* + * features: EN_NETIF_GSO_FEAT_* + * + * XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL}: + * + * 0 1 2 3 4 5 6 7 octet + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * |type |flags| addr | + * +-----+-----+-----+-----+-----+-----+-----+-----+ + * + * type: Must be XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL} + * flags: XEN_NETIF_EXTRA_FLAG_* + * addr: address to add/remove */ /* Protocol checksum field is blank in the packet (hardware offload)? */ @@ -65,14 +293,13 @@ #define _NETTXF_extra_info (3) #define NETTXF_extra_info (1U<<_NETTXF_extra_info) +#define XEN_NETIF_MAX_TX_SIZE 0xFFFF struct netif_tx_request { grant_ref_t gref; /* Reference to buffer page */ uint16_t offset; /* Offset within buffer page */ uint16_t flags; /* NETTXF_* */ uint16_t id; /* Echoed in response message. */ - uint16_t size; /* For the first request in a packet, the packet - size in bytes. For subsequent requests, the - size of that request's associated data in bytes*/ + uint16_t size; /* Packet size in bytes. */ }; typedef struct netif_tx_request netif_tx_request_t; @@ -83,16 +310,18 @@ typedef struct netif_tx_request netif_tx_request_t; #define XEN_NETIF_EXTRA_TYPE_MCAST_DEL (3) /* u.mcast */ #define XEN_NETIF_EXTRA_TYPE_MAX (4) -/* netif_extra_info flags. */ +/* netif_extra_info_t flags. */ #define _XEN_NETIF_EXTRA_FLAG_MORE (0) #define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE) -/* GSO types - only TCPv4 currently supported. */ +/* GSO types */ +#define XEN_NETIF_GSO_TYPE_NONE (0) #define XEN_NETIF_GSO_TYPE_TCPV4 (1) +#define XEN_NETIF_GSO_TYPE_TCPV6 (2) /* - * This structure needs to fit within both netif_tx_request and - * netif_rx_response for compatibility. + * This structure needs to fit within both netif_tx_request_t and + * netif_rx_response_t for compatibility. */ struct netif_extra_info { uint8_t type; /* XEN_NETIF_EXTRA_TYPE_* */ @@ -127,14 +356,6 @@ struct netif_extra_info { /* * XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL}: - * Backend advertises availability via 'feature-multicast-control' - * xenbus node containing value '1'. - * Frontend requests this feature by advertising - * 'request-multicast-control' xenbus node containing value '1'. - * If multicast control is requested then multicast flooding is - * disabled and the frontend must explicitly register its interest - * in multicast groups using dummy transmit requests containing - * MCAST_{ADD,DEL} extra-info fragments. */ struct { uint8_t addr[6]; /* Address to add/remove. */ @@ -153,6 +374,7 @@ typedef struct netif_tx_response netif_tx_response_t; struct netif_rx_request { uint16_t id; /* Echoed in response message. */ + uint16_t pad; grant_ref_t gref; /* Reference to incoming granted frame */ }; typedef struct netif_rx_request netif_rx_request_t; @@ -173,15 +395,11 @@ typedef struct netif_rx_request netif_rx_request_t; #define _NETRXF_extra_info (3) #define NETRXF_extra_info (1U<<_NETRXF_extra_info) -/* GSO Prefix descriptor. */ -#define _NETRXF_gso_prefix (4) -#define NETRXF_gso_prefix (1U<<_NETRXF_gso_prefix) - struct netif_rx_response { uint16_t id; uint16_t offset; /* Offset in page of start of received packet */ uint16_t flags; /* NETRXF_* */ - int16_t status; /* -ve: NETIF_RSP_* ; +ve: Rx'ed response size. */ + int16_t status; /* -ve: NETIF_RSP_* ; +ve: Rx'ed pkt size. */ }; typedef struct netif_rx_response netif_rx_response_t; @@ -195,7 +413,7 @@ DEFINE_RING_TYPES(netif_rx, struct netif_rx_request, struct netif_rx_response); #define NETIF_RSP_DROPPED -2 #define NETIF_RSP_ERROR -1 #define NETIF_RSP_OKAY 0 -/* No response: used for auxiliary requests (e.g., netif_tx_extra). */ +/* No response: used for auxiliary requests (e.g., netif_extra_info_t). */ #define NETIF_RSP_NULL 1 #endif @@ -203,7 +421,7 @@ DEFINE_RING_TYPES(netif_rx, struct netif_rx_request, struct netif_rx_response); /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/io/pciif.h b/sys/xen/interface/io/pciif.h index c4177f3..a4ba13c 100644 --- a/sys/xen/interface/io/pciif.h +++ b/sys/xen/interface/io/pciif.h @@ -46,6 +46,7 @@ #define XEN_PCI_OP_aer_resume (7) #define XEN_PCI_OP_aer_mmio (8) #define XEN_PCI_OP_aer_slotreset (9) +#define XEN_PCI_OP_enable_multi_msi (10) /* xen_pci_op error numbers */ #define XEN_PCI_ERR_success (0) @@ -116,7 +117,7 @@ struct xen_pci_sharedinfo { /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/io/protocols.h b/sys/xen/interface/io/protocols.h index 0b7a2ea..40a9b30 100644 --- a/sys/xen/interface/io/protocols.h +++ b/sys/xen/interface/io/protocols.h @@ -18,6 +18,8 @@ * 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) 2008, Keir Fraser */ #ifndef __XEN_PROTOCOLS_H__ @@ -25,16 +27,13 @@ #define XEN_IO_PROTO_ABI_X86_32 "x86_32-abi" #define XEN_IO_PROTO_ABI_X86_64 "x86_64-abi" -#define XEN_IO_PROTO_ABI_IA64 "ia64-abi" #define XEN_IO_PROTO_ABI_ARM "arm-abi" #if defined(__i386__) # define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_X86_32 #elif defined(__x86_64__) # define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_X86_64 -#elif defined(__ia64__) -# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_IA64 -#elif defined(__arm__) +#elif defined(__arm__) || defined(__aarch64__) # define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_ARM #else # error arch fixup needed here diff --git a/sys/xen/interface/io/ring.h b/sys/xen/interface/io/ring.h index 1d668c4..ba9401b 100644 --- a/sys/xen/interface/io/ring.h +++ b/sys/xen/interface/io/ring.h @@ -45,15 +45,9 @@ typedef unsigned int RING_IDX; #define __RD32(_x) (((_x) & 0xffff0000) ? __RD16((_x)>>16)<<16 : __RD16(_x)) /* - * The amount of space reserved in the shared ring for accounting information. - */ -#define __RING_HEADER_SIZE(_s) \ - ((intptr_t)(_s)->ring - (intptr_t)(_s)) - -/* * Calculate size of a shared ring, given the total available space for the * ring and indexes (_sz), and the name tag of the request/response structure. - * A ring contains as many entries as will fit, rounded down to the nearest + * A ring contains as many entries as will fit, rounded down to the nearest * power of two (so we can mask with (size-1) to loop around). */ #define __CONST_RING_SIZE(_s, _sz) \ @@ -63,17 +57,7 @@ typedef unsigned int RING_IDX; * The same for passing in an actual pointer instead of a name tag. */ #define __RING_SIZE(_s, _sz) \ - (__RD32(((_sz) - __RING_HEADER_SIZE(_s)) / sizeof((_s)->ring[0]))) - -/* - * The number of pages needed to support a given number of request/reponse - * entries. The entry count is rounded down to the nearest power of two - * as required by the ring macros. - */ -#define __RING_PAGES(_s, _entries) \ - ((__RING_HEADER_SIZE(_s) \ - + (__RD32(_entries) * sizeof((_s)->ring[0])) \ - + PAGE_SIZE - 1) / PAGE_SIZE) + (__RD32(((_sz) - (long)(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0]))) /* * Macros to make the correct C datatypes for a new kind of ring. @@ -127,7 +111,7 @@ struct __name##_sring { \ uint8_t msg; \ } tapif_user; \ uint8_t pvt_pad[4]; \ - } private; \ + } pvt; \ uint8_t __pad[44]; \ union __name##_sring_entry ring[1]; /* variable-length */ \ }; \ @@ -172,7 +156,7 @@ typedef struct __name##_back_ring __name##_back_ring_t #define SHARED_RING_INIT(_s) do { \ (_s)->req_prod = (_s)->rsp_prod = 0; \ (_s)->req_event = (_s)->rsp_event = 1; \ - (void)memset((_s)->private.pvt_pad, 0, sizeof((_s)->private.pvt_pad)); \ + (void)memset((_s)->pvt.pvt_pad, 0, sizeof((_s)->pvt.pvt_pad)); \ (void)memset((_s)->__pad, 0, sizeof((_s)->__pad)); \ } while(0) @@ -190,21 +174,6 @@ typedef struct __name##_back_ring __name##_back_ring_t (_r)->sring = (_s); \ } while (0) -/* Initialize to existing shared indexes -- for recovery */ -#define FRONT_RING_ATTACH(_r, _s, __size) do { \ - (_r)->sring = (_s); \ - (_r)->req_prod_pvt = (_s)->req_prod; \ - (_r)->rsp_cons = (_s)->rsp_prod; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ -} while (0) - -#define BACK_RING_ATTACH(_r, _s, __size) do { \ - (_r)->sring = (_s); \ - (_r)->rsp_prod_pvt = (_s)->rsp_prod; \ - (_r)->req_cons = (_s)->req_prod; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ -} while (0) - /* How big is this ring? */ #define RING_SIZE(_r) \ ((_r)->nr_ents) @@ -250,6 +219,10 @@ typedef struct __name##_back_ring __name##_back_ring_t #define RING_REQUEST_CONS_OVERFLOW(_r, _cons) \ (((_cons) - (_r)->rsp_prod_pvt) >= RING_SIZE(_r)) +/* Ill-behaved frontend determination: Can there be this many requests? */ +#define RING_REQUEST_PROD_OVERFLOW(_r, _prod) \ + (((_prod) - (_r)->rsp_prod_pvt) > RING_SIZE(_r)) + #define RING_PUSH_REQUESTS(_r) do { \ xen_wmb(); /* back sees requests /before/ updated producer index */ \ (_r)->sring->req_prod = (_r)->req_prod_pvt; \ @@ -331,7 +304,7 @@ typedef struct __name##_back_ring __name##_back_ring_t /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/io/tpmif.h b/sys/xen/interface/io/tpmif.h index 02ccdab..9743dc9 100644 --- a/sys/xen/interface/io/tpmif.h +++ b/sys/xen/interface/io/tpmif.h @@ -64,12 +64,78 @@ struct tpmif_tx_interface { }; typedef struct tpmif_tx_interface tpmif_tx_interface_t; +/****************************************************************************** + * TPM I/O interface for Xen guest OSes, v2 + * + * Author: Daniel De Graaf <dgdegra@tycho.nsa.gov> + * + * This protocol emulates the request/response behavior of a TPM using a Xen + * shared memory interface. All interaction with the TPM is at the direction + * of the frontend, since a TPM (hardware or virtual) is a passive device - + * the backend only processes commands as requested by the frontend. + * + * The frontend sends a request to the TPM by populating the shared page with + * the request packet, changing the state to TPMIF_STATE_SUBMIT, and sending + * and event channel notification. When the backend is finished, it will set + * the state to TPMIF_STATE_FINISH and send an event channel notification. + * + * In order to allow long-running commands to be canceled, the frontend can + * at any time change the state to TPMIF_STATE_CANCEL and send a notification. + * The TPM can either finish the command (changing state to TPMIF_STATE_FINISH) + * or can cancel the command and change the state to TPMIF_STATE_IDLE. The TPM + * can also change the state to TPMIF_STATE_IDLE instead of TPMIF_STATE_FINISH + * if another reason for cancellation is required - for example, a physical + * TPM may cancel a command if the interface is seized by another locality. + * + * The TPM command format is defined by the TCG, and is available at + * http://www.trustedcomputinggroup.org/resources/tpm_main_specification + */ + +enum tpmif_state { + TPMIF_STATE_IDLE, /* no contents / vTPM idle / cancel complete */ + TPMIF_STATE_SUBMIT, /* request ready / vTPM working */ + TPMIF_STATE_FINISH, /* response ready / vTPM idle */ + TPMIF_STATE_CANCEL, /* cancel requested / vTPM working */ +}; +/* Note: The backend should only change state to IDLE or FINISH, while the + * frontend should only change to SUBMIT or CANCEL. Status changes do not need + * to use atomic operations. + */ + + +/* The shared page for vTPM request/response packets looks like: + * + * Offset Contents + * ================================================= + * 0 struct tpmif_shared_page + * 16 [optional] List of grant IDs + * 16+4*nr_extra_pages TPM packet data + * + * If the TPM packet data extends beyond the end of a single page, the grant IDs + * defined in extra_pages are used as if they were mapped immediately following + * the primary shared page. The grants are allocated by the frontend and mapped + * by the backend. Before sending a request spanning multiple pages, the + * frontend should verify that the TPM supports such large requests by querying + * the TPM_CAP_PROP_INPUT_BUFFER property from the TPM. + */ +struct tpmif_shared_page { + uint32_t length; /* request/response length in bytes */ + + uint8_t state; /* enum tpmif_state */ + uint8_t locality; /* for the current request */ + uint8_t pad; /* should be zero */ + + uint8_t nr_extra_pages; /* extra pages for long packets; may be zero */ + uint32_t extra_pages[0]; /* grant IDs; length is actually nr_extra_pages */ +}; +typedef struct tpmif_shared_page tpmif_shared_page_t; + #endif /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/io/usbif.h b/sys/xen/interface/io/usbif.h index 6099c29..9ef0cdc 100644 --- a/sys/xen/interface/io/usbif.h +++ b/sys/xen/interface/io/usbif.h @@ -31,6 +31,76 @@ #include "ring.h" #include "../grant_table.h" +/* + * Feature and Parameter Negotiation + * ================================= + * The two halves of a Xen pvUSB driver utilize nodes within the XenStore to + * communicate capabilities and to negotiate operating parameters. This + * section enumerates these nodes which reside in the respective front and + * backend portions of the XenStore, following the XenBus convention. + * + * Any specified default value is in effect if the corresponding XenBus node + * is not present in the XenStore. + * + * XenStore nodes in sections marked "PRIVATE" are solely for use by the + * driver side whose XenBus tree contains them. + * + ***************************************************************************** + * Backend XenBus Nodes + ***************************************************************************** + * + *------------------ Backend Device Identification (PRIVATE) ------------------ + * + * num-ports + * Values: unsigned [1...31] + * + * Number of ports for this (virtual) USB host connector. + * + * usb-ver + * Values: unsigned [1...2] + * + * USB version of this host connector: 1 = USB 1.1, 2 = USB 2.0. + * + * port/[1...31] + * Values: string + * + * Physical USB device connected to the given port, e.g. "3-1.5". + * + ***************************************************************************** + * Frontend XenBus Nodes + ***************************************************************************** + * + *----------------------- Request Transport Parameters ----------------------- + * + * event-channel + * Values: unsigned + * + * The identifier of the Xen event channel used to signal activity + * in the ring buffer. + * + * urb-ring-ref + * Values: unsigned + * + * The Xen grant reference granting permission for the backend to map + * the sole page in a single page sized ring buffer. This is the ring + * buffer for urb requests. + * + * conn-ring-ref + * Values: unsigned + * + * The Xen grant reference granting permission for the backend to map + * the sole page in a single page sized ring buffer. This is the ring + * buffer for connection/disconnection requests. + * + * protocol + * Values: string (XEN_IO_PROTO_ABI_*) + * Default Value: XEN_IO_PROTO_ABI_NATIVE + * + * The machine ABI rules governing the format of all ring request and + * response structures. + * + */ + enum usb_spec_version { USB_VER_UNKNOWN = 0, USB_VER_USB11, @@ -41,38 +111,65 @@ enum usb_spec_version { /* * USB pipe in usbif_request * - * bits 0-5 are specific bits for virtual USB driver. - * bits 7-31 are standard urb pipe. - * - * - port number(NEW): bits 0-4 - * (USB_MAXCHILDREN is 31) + * - port number: bits 0-4 + * (USB_MAXCHILDREN is 31) * - * - operation flag(NEW): bit 5 - * (0 = submit urb, - * 1 = unlink urb) + * - operation flag: bit 5 + * (0 = submit urb, + * 1 = unlink urb) * * - direction: bit 7 - * (0 = Host-to-Device [Out] - * 1 = Device-to-Host [In]) + * (0 = Host-to-Device [Out] + * 1 = Device-to-Host [In]) * * - device address: bits 8-14 * * - endpoint: bits 15-18 * - * - pipe type: bits 30-31 - * (00 = isochronous, 01 = interrupt, - * 10 = control, 11 = bulk) + * - pipe type: bits 30-31 + * (00 = isochronous, 01 = interrupt, + * 10 = control, 11 = bulk) */ -#define usbif_pipeportnum(pipe) ((pipe) & 0x1f) -#define usbif_setportnum_pipe(pipe, portnum) \ - ((pipe)|(portnum)) -#define usbif_pipeunlink(pipe) ((pipe) & 0x20) -#define usbif_pipesubmit(pipe) (!usbif_pipeunlink(pipe)) -#define usbif_setunlink_pipe(pipe) ((pipe)|(0x20)) +#define USBIF_PIPE_PORT_MASK 0x0000001f +#define USBIF_PIPE_UNLINK 0x00000020 +#define USBIF_PIPE_DIR 0x00000080 +#define USBIF_PIPE_DEV_MASK 0x0000007f +#define USBIF_PIPE_DEV_SHIFT 8 +#define USBIF_PIPE_EP_MASK 0x0000000f +#define USBIF_PIPE_EP_SHIFT 15 +#define USBIF_PIPE_TYPE_MASK 0x00000003 +#define USBIF_PIPE_TYPE_SHIFT 30 +#define USBIF_PIPE_TYPE_ISOC 0 +#define USBIF_PIPE_TYPE_INT 1 +#define USBIF_PIPE_TYPE_CTRL 2 +#define USBIF_PIPE_TYPE_BULK 3 + +#define usbif_pipeportnum(pipe) ((pipe) & USBIF_PIPE_PORT_MASK) +#define usbif_setportnum_pipe(pipe, portnum) ((pipe) | (portnum)) + +#define usbif_pipeunlink(pipe) ((pipe) & USBIF_PIPE_UNLINK) +#define usbif_pipesubmit(pipe) (!usbif_pipeunlink(pipe)) +#define usbif_setunlink_pipe(pipe) ((pipe) | USBIF_PIPE_UNLINK) + +#define usbif_pipein(pipe) ((pipe) & USBIF_PIPE_DIR) +#define usbif_pipeout(pipe) (!usbif_pipein(pipe)) + +#define usbif_pipedevice(pipe) \ + (((pipe) >> USBIF_PIPE_DEV_SHIFT) & USBIF_PIPE_DEV_MASK) + +#define usbif_pipeendpoint(pipe) \ + (((pipe) >> USBIF_PIPE_EP_SHIFT) & USBIF_PIPE_EP_MASK) + +#define usbif_pipetype(pipe) \ + (((pipe) >> USBIF_PIPE_TYPE_SHIFT) & USBIF_PIPE_TYPE_MASK) +#define usbif_pipeisoc(pipe) (usbif_pipetype(pipe) == USBIF_PIPE_TYPE_ISOC) +#define usbif_pipeint(pipe) (usbif_pipetype(pipe) == USBIF_PIPE_TYPE_INT) +#define usbif_pipectrl(pipe) (usbif_pipetype(pipe) == USBIF_PIPE_TYPE_CTRL) +#define usbif_pipebulk(pipe) (usbif_pipetype(pipe) == USBIF_PIPE_TYPE_BULK) -#define USBIF_BACK_MAX_PENDING_REQS (128) #define USBIF_MAX_SEGMENTS_PER_REQUEST (16) +#define USBIF_MAX_PORTNR 31 /* * RING for transferring urbs. @@ -142,6 +239,10 @@ struct usbif_conn_response { uint16_t id; /* request id */ uint8_t portnum; /* port number */ uint8_t speed; /* usb_device_speed */ +#define USBIF_SPEED_NONE 0 +#define USBIF_SPEED_LOW 1 +#define USBIF_SPEED_FULL 2 +#define USBIF_SPEED_HIGH 3 }; typedef struct usbif_conn_response usbif_conn_response_t; diff --git a/sys/xen/interface/io/vscsiif.h b/sys/xen/interface/io/vscsiif.h index 3ce2914..7a1db05 100644 --- a/sys/xen/interface/io/vscsiif.h +++ b/sys/xen/interface/io/vscsiif.h @@ -1,8 +1,8 @@ /****************************************************************************** * vscsiif.h - * + * * Based on the blkif.h code. - * + * * 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 @@ -30,57 +30,212 @@ #include "ring.h" #include "../grant_table.h" -/* command between backend and frontend */ -#define VSCSIIF_ACT_SCSI_CDB 1 /* SCSI CDB command */ -#define VSCSIIF_ACT_SCSI_ABORT 2 /* SCSI Device(Lun) Abort*/ -#define VSCSIIF_ACT_SCSI_RESET 3 /* SCSI Device(Lun) Reset*/ +/* + * Feature and Parameter Negotiation + * ================================= + * The two halves of a Xen pvSCSI driver utilize nodes within the XenStore to + * communicate capabilities and to negotiate operating parameters. This + * section enumerates these nodes which reside in the respective front and + * backend portions of the XenStore, following the XenBus convention. + * + * Any specified default value is in effect if the corresponding XenBus node + * is not present in the XenStore. + * + * XenStore nodes in sections marked "PRIVATE" are solely for use by the + * driver side whose XenBus tree contains them. + * + ***************************************************************************** + * Backend XenBus Nodes + ***************************************************************************** + * + *------------------ Backend Device Identification (PRIVATE) ------------------ + * + * p-devname + * Values: string + * + * A free string used to identify the physical device (e.g. a disk name). + * + * p-dev + * Values: string + * + * A string specifying the backend device: either a 4-tuple "h:c:t:l" + * (host, controller, target, lun, all integers), or a WWN (e.g. + * "naa.60014054ac780582"). + * + * v-dev + * Values: string + * + * A string specifying the frontend device in form of a 4-tuple "h:c:t:l" + * (host, controller, target, lun, all integers). + * + *--------------------------------- Features --------------------------------- + * + * feature-sg-grant + * Values: unsigned [VSCSIIF_SG_TABLESIZE...65535] + * Default Value: 0 + * + * Specifies the maximum number of scatter/gather elements in grant pages + * supported. If not set, the backend supports up to VSCSIIF_SG_TABLESIZE + * SG elements specified directly in the request. + * + ***************************************************************************** + * Frontend XenBus Nodes + ***************************************************************************** + * + *----------------------- Request Transport Parameters ----------------------- + * + * event-channel + * Values: unsigned + * + * The identifier of the Xen event channel used to signal activity + * in the ring buffer. + * + * ring-ref + * Values: unsigned + * + * The Xen grant reference granting permission for the backend to map + * the sole page in a single page sized ring buffer. + * + * protocol + * Values: string (XEN_IO_PROTO_ABI_*) + * Default Value: XEN_IO_PROTO_ABI_NATIVE + * + * The machine ABI rules governing the format of all ring request and + * response structures. + */ +/* Requests from the frontend to the backend */ -#define VSCSIIF_BACK_MAX_PENDING_REQS 128 +/* + * Request a SCSI operation specified via a CDB in vscsiif_request.cmnd. + * The target is specified via channel, id and lun. + * + * The operation to be performed is specified via a CDB in cmnd[], the length + * of the CDB is in cmd_len. sc_data_direction specifies the direction of data + * (to the device, from the device, or none at all). + * + * If data is to be transferred to or from the device the buffer(s) in the + * guest memory is/are specified via one or multiple scsiif_request_segment + * descriptors each specifying a memory page via a grant_ref_t, a offset into + * the page and the length of the area in that page. All scsiif_request_segment + * areas concatenated form the resulting data buffer used by the operation. + * If the number of scsiif_request_segment areas is not too large (less than + * or equal VSCSIIF_SG_TABLESIZE) the areas can be specified directly in the + * seg[] array and the number of valid scsiif_request_segment elements is to be + * set in nr_segments. + * + * If "feature-sg-grant" in the Xenstore is set it is possible to specify more + * than VSCSIIF_SG_TABLESIZE scsiif_request_segment elements via indirection. + * The maximum number of allowed scsiif_request_segment elements is the value + * of the "feature-sg-grant" entry from Xenstore. When using indirection the + * seg[] array doesn't contain specifications of the data buffers, but + * references to scsiif_request_segment arrays, which in turn reference the + * data buffers. While nr_segments holds the number of populated seg[] entries + * (plus the set VSCSIIF_SG_GRANT bit), the number of scsiif_request_segment + * elements referencing the target data buffers is calculated from the lengths + * of the seg[] elements (the sum of all valid seg[].length divided by the + * size of one scsiif_request_segment structure). The frontend may use a mix of + * direct and indirect requests. + */ +#define VSCSIIF_ACT_SCSI_CDB 1 + +/* + * Request abort of a running operation for the specified target given by + * channel, id, lun and the operation's rqid in ref_rqid. + */ +#define VSCSIIF_ACT_SCSI_ABORT 2 + +/* + * Request a device reset of the specified target (channel and id). + */ +#define VSCSIIF_ACT_SCSI_RESET 3 + +/* + * Preset scatter/gather elements for a following request. Deprecated. + * Keeping the define only to avoid usage of the value "4" for other actions. + */ +#define VSCSIIF_ACT_SCSI_SG_PRESET 4 /* * Maximum scatter/gather segments per request. * - * Considering balance between allocating al least 16 "vscsiif_request" - * structures on one page (4096bytes) and number of scatter gather - * needed, we decided to use 26 as a magic number. + * Considering balance between allocating at least 16 "vscsiif_request" + * structures on one page (4096 bytes) and the number of scatter/gather + * elements needed, we decided to use 26 as a magic number. + * + * If "feature-sg-grant" is set, more scatter/gather elements can be specified + * by placing them in one or more (up to VSCSIIF_SG_TABLESIZE) granted pages. + * In this case the vscsiif_request seg elements don't contain references to + * the user data, but to the SG elements referencing the user data. */ #define VSCSIIF_SG_TABLESIZE 26 /* - * base on linux kernel 2.6.18 + * based on Linux kernel 2.6.18, still valid + * + * Changing these values requires support of multiple protocols via the rings + * as "old clients" will blindly use these values and the resulting structure + * sizes. */ #define VSCSIIF_MAX_COMMAND_SIZE 16 #define VSCSIIF_SENSE_BUFFERSIZE 96 +struct scsiif_request_segment { + grant_ref_t gref; + uint16_t offset; + uint16_t length; +}; +typedef struct scsiif_request_segment vscsiif_segment_t; + +#define VSCSIIF_SG_PER_PAGE (PAGE_SIZE / sizeof(struct scsiif_request_segment)) +/* Size of one request is 252 bytes */ struct vscsiif_request { uint16_t rqid; /* private guest value, echoed in resp */ uint8_t act; /* command between backend and frontend */ - uint8_t cmd_len; - - uint8_t cmnd[VSCSIIF_MAX_COMMAND_SIZE]; - uint16_t timeout_per_command; /* The command is issued by twice - the value in Backend. */ - uint16_t channel, id, lun; - uint16_t padding; - uint8_t sc_data_direction; /* for DMA_TO_DEVICE(1) - DMA_FROM_DEVICE(2) - DMA_NONE(3) requests */ - uint8_t nr_segments; /* Number of pieces of scatter-gather */ - - struct scsiif_request_segment { - grant_ref_t gref; - uint16_t offset; - uint16_t length; - } seg[VSCSIIF_SG_TABLESIZE]; + uint8_t cmd_len; /* valid CDB bytes */ + + uint8_t cmnd[VSCSIIF_MAX_COMMAND_SIZE]; /* the CDB */ + uint16_t timeout_per_command; /* deprecated: timeout in secs, 0=default */ + uint16_t channel, id, lun; /* (virtual) device specification */ + uint16_t ref_rqid; /* command abort reference */ + uint8_t sc_data_direction; /* for DMA_TO_DEVICE(1) + DMA_FROM_DEVICE(2) + DMA_NONE(3) requests */ + uint8_t nr_segments; /* Number of pieces of scatter-gather */ +/* + * flag in nr_segments: SG elements via grant page + * + * If VSCSIIF_SG_GRANT is set, the low 7 bits of nr_segments specify the number + * of grant pages containing SG elements. Usable if "feature-sg-grant" set. + */ +#define VSCSIIF_SG_GRANT 0x80 + + vscsiif_segment_t seg[VSCSIIF_SG_TABLESIZE]; uint32_t reserved[3]; }; typedef struct vscsiif_request vscsiif_request_t; +/* + * The following interface is deprecated! + */ +#define VSCSIIF_SG_LIST_SIZE ((sizeof(vscsiif_request_t) - 4) \ + / sizeof(vscsiif_segment_t)) + +struct vscsiif_sg_list { + /* First two fields must match struct vscsiif_request! */ + uint16_t rqid; /* private guest value, must match main req */ + uint8_t act; /* VSCSIIF_ACT_SCSI_SG_PRESET */ + uint8_t nr_segments; /* Number of pieces of scatter-gather */ + vscsiif_segment_t seg[VSCSIIF_SG_LIST_SIZE]; +}; +typedef struct vscsiif_sg_list vscsiif_sg_list_t; +/* End of deprecated interface */ + +/* Size of one response is 252 bytes */ struct vscsiif_response { - uint16_t rqid; - uint8_t padding; + uint16_t rqid; /* identifies request */ + uint8_t act; /* deprecated: valid only if SG_PRESET supported */ uint8_t sense_len; uint8_t sense_buffer[VSCSIIF_SENSE_BUFFERSIZE]; int32_t rslt; @@ -97,7 +252,7 @@ DEFINE_RING_TYPES(vscsiif, struct vscsiif_request, struct vscsiif_response); /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/io/xenbus.h b/sys/xen/interface/io/xenbus.h index 672c7d4..927f9db 100644 --- a/sys/xen/interface/io/xenbus.h +++ b/sys/xen/interface/io/xenbus.h @@ -36,9 +36,6 @@ enum xenbus_state { XenbusStateUnknown = 0, - /* - * Initializing: Back-end is initializing. - */ XenbusStateInitialising = 1, /* @@ -52,9 +49,6 @@ enum xenbus_state { */ XenbusStateInitialised = 3, - /* - * Connected: The normal state for a front to backend connection. - */ XenbusStateConnected = 4, /* @@ -62,18 +56,6 @@ enum xenbus_state { */ XenbusStateClosing = 5, - /* - * Closed: No connection exists between front and back end. - * - * For backend devices with the "online" attribute, the front can - * request a reconnect at any time. To handle this transition - * gracefully, backend devices must reinitialize any XenStore data - * used to negotiate features with a peer before transitioning to - * the closed state. When a reconnect request occurs, the - * XenBus backend support code will automatically transition the - * backend device from Closed to InitWait, kicking off the ring - * and feature negotiation process. - */ XenbusStateClosed = 6, /* @@ -90,7 +72,7 @@ typedef enum xenbus_state XenbusState; /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/io/xs_wire.h b/sys/xen/interface/io/xs_wire.h index 7e454c4..0a0cdbc 100644 --- a/sys/xen/interface/io/xs_wire.h +++ b/sys/xen/interface/io/xs_wire.h @@ -49,7 +49,9 @@ enum xsd_sockmsg_type XS_RESUME, XS_SET_TARGET, XS_RESTRICT, - XS_RESET_WATCHES + XS_RESET_WATCHES, + + XS_INVALID = 0xffff /* Guaranteed to remain an invalid type */ }; #define XS_WRITE_NONE "NONE" @@ -83,7 +85,8 @@ __attribute__((unused)) XSD_ERROR(EROFS), XSD_ERROR(EBUSY), XSD_ERROR(EAGAIN), - XSD_ERROR(EISCONN) + XSD_ERROR(EISCONN), + XSD_ERROR(E2BIG) }; #endif @@ -103,7 +106,10 @@ enum xs_watch_type XS_WATCH_TOKEN }; -/* Inter-domain shared memory communications. */ +/* + * `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)) @@ -112,6 +118,8 @@ struct xenstore_domain_interface { char rsp[XENSTORE_RING_SIZE]; /* Replies and async watch events. */ XENSTORE_RING_IDX req_cons, req_prod; XENSTORE_RING_IDX rsp_cons, rsp_prod; + uint32_t server_features; /* Bitmap of features supported by the server */ + uint32_t connection; }; /* Violating this is very bad. See docs/misc/xenstore.txt. */ @@ -121,12 +129,19 @@ struct xenstore_domain_interface { #define XENSTORE_ABS_PATH_MAX 3072 #define XENSTORE_REL_PATH_MAX 2048 +/* The ability to reconnect a ring */ +#define XENSTORE_SERVER_FEATURE_RECONNECTION 1 + +/* Valid values for the connection field */ +#define XENSTORE_CONNECTED 0 /* the steady-state */ +#define XENSTORE_RECONNECT 1 /* guest has initiated a reconnect */ + #endif /* _XS_WIRE_H */ /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/kexec.h b/sys/xen/interface/kexec.h index 0425222..a6a0a88 100644 --- a/sys/xen/interface/kexec.h +++ b/sys/xen/interface/kexec.h @@ -97,9 +97,6 @@ typedef struct xen_kexec_image { #if defined(__i386__) || defined(__x86_64__) unsigned long page_list[KEXEC_XEN_NO_PAGES]; #endif -#if defined(__ia64__) - unsigned long reboot_code_buffer; -#endif unsigned long indirection_page; unsigned long start_address; } xen_kexec_image_t; @@ -108,6 +105,20 @@ typedef struct xen_kexec_image { * Perform kexec having previously loaded a kexec or kdump kernel * as appropriate. * type == KEXEC_TYPE_DEFAULT or KEXEC_TYPE_CRASH [in] + * + * Control is transferred to the image entry point with the host in + * the following state. + * + * - The image may be executed on any PCPU and all other PCPUs are + * stopped. + * + * - Local interrupts are disabled. + * + * - Register values are undefined. + * + * - The image segments have writeable 1:1 virtual to machine + * mappings. The location of any page tables is undefined and these + * page table frames are not be mapped. */ #define KEXEC_CMD_kexec 0 typedef struct xen_kexec_exec { @@ -119,12 +130,12 @@ typedef struct xen_kexec_exec { * type == KEXEC_TYPE_DEFAULT or KEXEC_TYPE_CRASH [in] * image == relocation information for kexec (ignored for unload) [in] */ -#define KEXEC_CMD_kexec_load 1 -#define KEXEC_CMD_kexec_unload 2 -typedef struct xen_kexec_load { +#define KEXEC_CMD_kexec_load_v1 1 /* obsolete since 0x00040400 */ +#define KEXEC_CMD_kexec_unload_v1 2 /* obsolete since 0x00040400 */ +typedef struct xen_kexec_load_v1 { int type; xen_kexec_image_t image; -} xen_kexec_load_t; +} xen_kexec_load_v1_t; #define KEXEC_RANGE_MA_CRASH 0 /* machine address and size of crash area */ #define KEXEC_RANGE_MA_XEN 1 /* machine address and size of Xen itself */ @@ -134,7 +145,7 @@ typedef struct xen_kexec_load { * to Xen it exists in a separate EFI * region on ia64, and thus needs to be * inserted into iomem_machine separately */ -#define KEXEC_RANGE_MA_BOOT_PARAM 4 /* machine address and size of +#define KEXEC_RANGE_MA_BOOT_PARAM 4 /* Obsolete: machine address and size of * the ia64_boot_param */ #define KEXEC_RANGE_MA_EFI_MEMMAP 5 /* machine address and size of * of the EFI Memory Map */ @@ -155,12 +166,82 @@ typedef struct xen_kexec_range { unsigned long start; } xen_kexec_range_t; +#if __XEN_INTERFACE_VERSION__ >= 0x00040400 +/* + * A contiguous chunk of a kexec image and it's destination machine + * address. + */ +typedef struct xen_kexec_segment { + union { + XEN_GUEST_HANDLE(const_void) h; + uint64_t _pad; + } buf; + uint64_t buf_size; + uint64_t dest_maddr; + uint64_t dest_size; +} xen_kexec_segment_t; +DEFINE_XEN_GUEST_HANDLE(xen_kexec_segment_t); + +/* + * Load a kexec image into memory. + * + * For KEXEC_TYPE_DEFAULT images, the segments may be anywhere in RAM. + * The image is relocated prior to being executed. + * + * For KEXEC_TYPE_CRASH images, each segment of the image must reside + * in the memory region reserved for kexec (KEXEC_RANGE_MA_CRASH) and + * the entry point must be within the image. The caller is responsible + * for ensuring that multiple images do not overlap. + * + * All image segments will be loaded to their destination machine + * addresses prior to being executed. The trailing portion of any + * segments with a source buffer (from dest_maddr + buf_size to + * dest_maddr + dest_size) will be zeroed. + * + * Segments with no source buffer will be accessible to the image when + * it is executed. + */ + +#define KEXEC_CMD_kexec_load 4 +typedef struct xen_kexec_load { + uint8_t type; /* One of KEXEC_TYPE_* */ + uint8_t _pad; + uint16_t arch; /* ELF machine type (EM_*). */ + uint32_t nr_segments; + union { + XEN_GUEST_HANDLE(xen_kexec_segment_t) h; + uint64_t _pad; + } segments; + uint64_t entry_maddr; /* image entry point machine address. */ +} xen_kexec_load_t; +DEFINE_XEN_GUEST_HANDLE(xen_kexec_load_t); + +/* + * Unload a kexec image. + * + * Type must be one of KEXEC_TYPE_DEFAULT or KEXEC_TYPE_CRASH. + */ +#define KEXEC_CMD_kexec_unload 5 +typedef struct xen_kexec_unload { + uint8_t type; +} xen_kexec_unload_t; +DEFINE_XEN_GUEST_HANDLE(xen_kexec_unload_t); + +#else /* __XEN_INTERFACE_VERSION__ < 0x00040400 */ + +#define KEXEC_CMD_kexec_load KEXEC_CMD_kexec_load_v1 +#define KEXEC_CMD_kexec_unload KEXEC_CMD_kexec_unload_v1 +#define xen_kexec_load xen_kexec_load_v1 +#define xen_kexec_load_t xen_kexec_load_v1_t + +#endif + #endif /* _XEN_PUBLIC_KEXEC_H */ /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/libelf.h b/sys/xen/interface/libelf.h deleted file mode 100644 index d238330..0000000 --- a/sys/xen/interface/libelf.h +++ /dev/null @@ -1,265 +0,0 @@ -/****************************************************************************** - * libelf.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 __XC_LIBELF__ -#define __XC_LIBELF__ 1 - -#if defined(__i386__) || defined(__x86_64__) || defined(__ia64__) -#define XEN_ELF_LITTLE_ENDIAN -#else -#error define architectural endianness -#endif - -#undef ELFSIZE -#include "elfnote.h" -#include "elfstructs.h" -#include "features.h" - -/* ------------------------------------------------------------------------ */ - -typedef union { - Elf32_Ehdr e32; - Elf64_Ehdr e64; -} elf_ehdr; - -typedef union { - Elf32_Phdr e32; - Elf64_Phdr e64; -} elf_phdr; - -typedef union { - Elf32_Shdr e32; - Elf64_Shdr e64; -} elf_shdr; - -typedef union { - Elf32_Sym e32; - Elf64_Sym e64; -} elf_sym; - -typedef union { - Elf32_Rel e32; - Elf64_Rel e64; -} elf_rel; - -typedef union { - Elf32_Rela e32; - Elf64_Rela e64; -} elf_rela; - -typedef union { - Elf32_Note e32; - Elf64_Note e64; -} elf_note; - -struct elf_binary { - /* elf binary */ - const char *image; - size_t size; - char class; - char data; - - const elf_ehdr *ehdr; - const char *sec_strtab; - const elf_shdr *sym_tab; - const char *sym_strtab; - - /* loaded to */ - char *dest; - uint64_t pstart; - uint64_t pend; - uint64_t reloc_offset; - - uint64_t bsd_symtab_pstart; - uint64_t bsd_symtab_pend; - -#ifndef __XEN__ - /* misc */ - FILE *log; -#endif - int verbose; -}; - -/* ------------------------------------------------------------------------ */ -/* accessing elf header fields */ - -#ifdef XEN_ELF_BIG_ENDIAN -# define NATIVE_ELFDATA ELFDATA2MSB -#else -# define NATIVE_ELFDATA ELFDATA2LSB -#endif - -#define elf_32bit(elf) (ELFCLASS32 == (elf)->class) -#define elf_64bit(elf) (ELFCLASS64 == (elf)->class) -#define elf_msb(elf) (ELFDATA2MSB == (elf)->data) -#define elf_lsb(elf) (ELFDATA2LSB == (elf)->data) -#define elf_swap(elf) (NATIVE_ELFDATA != (elf)->data) - -#define elf_uval(elf, str, elem) \ - ((ELFCLASS64 == (elf)->class) \ - ? elf_access_unsigned((elf), (str), \ - offsetof(typeof(*(str)),e64.elem), \ - sizeof((str)->e64.elem)) \ - : elf_access_unsigned((elf), (str), \ - offsetof(typeof(*(str)),e32.elem), \ - sizeof((str)->e32.elem))) - -#define elf_sval(elf, str, elem) \ - ((ELFCLASS64 == (elf)->class) \ - ? elf_access_signed((elf), (str), \ - offsetof(typeof(*(str)),e64.elem), \ - sizeof((str)->e64.elem)) \ - : elf_access_signed((elf), (str), \ - offsetof(typeof(*(str)),e32.elem), \ - sizeof((str)->e32.elem))) - -#define elf_size(elf, str) \ - ((ELFCLASS64 == (elf)->class) \ - ? sizeof((str)->e64) : sizeof((str)->e32)) - -uint64_t elf_access_unsigned(struct elf_binary *elf, const void *ptr, - uint64_t offset, size_t size); -int64_t elf_access_signed(struct elf_binary *elf, const void *ptr, - uint64_t offset, size_t size); - -uint64_t elf_round_up(struct elf_binary *elf, uint64_t addr); - -/* ------------------------------------------------------------------------ */ -/* xc_libelf_tools.c */ - -int elf_shdr_count(struct elf_binary *elf); -int elf_phdr_count(struct elf_binary *elf); - -const elf_shdr *elf_shdr_by_name(struct elf_binary *elf, const char *name); -const elf_shdr *elf_shdr_by_index(struct elf_binary *elf, int index); -const elf_phdr *elf_phdr_by_index(struct elf_binary *elf, int index); - -const char *elf_section_name(struct elf_binary *elf, const elf_shdr * shdr); -const void *elf_section_start(struct elf_binary *elf, const elf_shdr * shdr); -const void *elf_section_end(struct elf_binary *elf, const elf_shdr * shdr); - -const void *elf_segment_start(struct elf_binary *elf, const elf_phdr * phdr); -const void *elf_segment_end(struct elf_binary *elf, const elf_phdr * phdr); - -const elf_sym *elf_sym_by_name(struct elf_binary *elf, const char *symbol); -const elf_sym *elf_sym_by_index(struct elf_binary *elf, int index); - -const char *elf_note_name(struct elf_binary *elf, const elf_note * note); -const void *elf_note_desc(struct elf_binary *elf, const elf_note * note); -uint64_t elf_note_numeric(struct elf_binary *elf, const elf_note * note); -const elf_note *elf_note_next(struct elf_binary *elf, const elf_note * note); - -int elf_is_elfbinary(const void *image); -int elf_phdr_is_loadable(struct elf_binary *elf, const elf_phdr * phdr); - -/* ------------------------------------------------------------------------ */ -/* xc_libelf_loader.c */ - -int elf_init(struct elf_binary *elf, const char *image, size_t size); -#ifdef __XEN__ -void elf_set_verbose(struct elf_binary *elf); -#else -void elf_set_logfile(struct elf_binary *elf, FILE * log, int verbose); -#endif - -void elf_parse_binary(struct elf_binary *elf); -void elf_load_binary(struct elf_binary *elf); - -void *elf_get_ptr(struct elf_binary *elf, unsigned long addr); -uint64_t elf_lookup_addr(struct elf_binary *elf, const char *symbol); - -void elf_parse_bsdsyms(struct elf_binary *elf, uint64_t pstart); /* private */ - -/* ------------------------------------------------------------------------ */ -/* xc_libelf_relocate.c */ - -int elf_reloc(struct elf_binary *elf); - -/* ------------------------------------------------------------------------ */ -/* xc_libelf_dominfo.c */ - -#define UNSET_ADDR ((uint64_t)-1) - -enum xen_elfnote_type { - XEN_ENT_NONE = 0, - XEN_ENT_LONG = 1, - XEN_ENT_STR = 2 -}; - -struct xen_elfnote { - enum xen_elfnote_type type; - const char *name; - union { - const char *str; - uint64_t num; - } data; -}; - -struct elf_dom_parms { - /* raw */ - const char *guest_info; - const void *elf_note_start; - const void *elf_note_end; - struct xen_elfnote elf_notes[XEN_ELFNOTE_MAX + 1]; - - /* parsed */ - char guest_os[16]; - char guest_ver[16]; - char xen_ver[16]; - char loader[16]; - int pae; - int bsd_symtab; - uint64_t virt_base; - uint64_t virt_entry; - uint64_t virt_hypercall; - uint64_t virt_hv_start_low; - uint64_t elf_paddr_offset; - uint32_t f_supported[XENFEAT_NR_SUBMAPS]; - uint32_t f_required[XENFEAT_NR_SUBMAPS]; - - /* calculated */ - uint64_t virt_offset; - uint64_t virt_kstart; - uint64_t virt_kend; -}; - -static inline void elf_xen_feature_set(int nr, uint32_t * addr) -{ - addr[nr >> 5] |= 1 << (nr & 31); -} -static inline int elf_xen_feature_get(int nr, uint32_t * addr) -{ - return !!(addr[nr >> 5] & (1 << (nr & 31))); -} - -int elf_xen_parse_features(const char *features, - uint32_t *supported, - uint32_t *required); -int elf_xen_parse_note(struct elf_binary *elf, - struct elf_dom_parms *parms, - const elf_note *note); -int elf_xen_parse_guest_info(struct elf_binary *elf, - struct elf_dom_parms *parms); -int elf_xen_parse(struct elf_binary *elf, - struct elf_dom_parms *parms); - -#endif /* __XC_LIBELF__ */ diff --git a/sys/xen/interface/mem_event.h b/sys/xen/interface/mem_event.h deleted file mode 100644 index 5d0bd4c..0000000 --- a/sys/xen/interface/mem_event.h +++ /dev/null @@ -1,80 +0,0 @@ -/****************************************************************************** - * mem_event.h - * - * Memory event common structures. - * - * Copyright (c) 2009 by Citrix Systems, Inc. (Patrick Colp) - * - * 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_MEM_EVENT_H -#define _XEN_PUBLIC_MEM_EVENT_H - -#include "xen.h" -#include "io/ring.h" - -/* Memory event flags */ -#define MEM_EVENT_FLAG_VCPU_PAUSED (1 << 0) -#define MEM_EVENT_FLAG_DROP_PAGE (1 << 1) -#define MEM_EVENT_FLAG_EVICT_FAIL (1 << 2) -#define MEM_EVENT_FLAG_FOREIGN (1 << 3) -#define MEM_EVENT_FLAG_DUMMY (1 << 4) - -/* Reasons for the memory event request */ -#define MEM_EVENT_REASON_UNKNOWN 0 /* typical reason */ -#define MEM_EVENT_REASON_VIOLATION 1 /* access violation, GFN is address */ -#define MEM_EVENT_REASON_CR0 2 /* CR0 was hit: gfn is CR0 value */ -#define MEM_EVENT_REASON_CR3 3 /* CR3 was hit: gfn is CR3 value */ -#define MEM_EVENT_REASON_CR4 4 /* CR4 was hit: gfn is CR4 value */ -#define MEM_EVENT_REASON_INT3 5 /* int3 was hit: gla/gfn are RIP */ -#define MEM_EVENT_REASON_SINGLESTEP 6 /* single step was invoked: gla/gfn are RIP */ - -typedef struct mem_event_st { - uint32_t flags; - uint32_t vcpu_id; - - uint64_t gfn; - uint64_t offset; - uint64_t gla; /* if gla_valid */ - - uint32_t p2mt; - - uint16_t access_r:1; - uint16_t access_w:1; - uint16_t access_x:1; - uint16_t gla_valid:1; - uint16_t available:12; - - uint16_t reason; -} mem_event_request_t, mem_event_response_t; - -DEFINE_RING_TYPES(mem_event, mem_event_request_t, mem_event_response_t); - -#endif - -/* - * Local variables: - * mode: C - * c-set-style: "BSD" - * c-basic-offset: 4 - * tab-width: 4 - * indent-tabs-mode: nil - * End: - */ diff --git a/sys/xen/interface/memory.h b/sys/xen/interface/memory.h index cdb7a58..320de91 100644 --- a/sys/xen/interface/memory.h +++ b/sys/xen/interface/memory.h @@ -28,6 +28,7 @@ #define __XEN_PUBLIC_MEMORY_H__ #include "xen.h" +#include "physdev.h" /* * Increase or decrease the specified domain's memory reservation. Returns the @@ -55,6 +56,8 @@ /* 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) +/* Flag to indicate the node specified is virtual node */ +#define XENMEMF_vnode (1<<18) #endif struct xen_memory_reservation { @@ -68,6 +71,8 @@ struct xen_memory_reservation { * 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; @@ -185,6 +190,15 @@ typedef struct xen_machphys_mfn_list xen_machphys_mfn_list_t; DEFINE_XEN_GUEST_HANDLE(xen_machphys_mfn_list_t); /* + * For a compat caller, this is identical to XENMEM_machphys_mfn_list. + * + * For a non compat caller, this functions similarly to + * XENMEM_machphys_mfn_list, but returns the mfns making up the compatibility + * m2p table. + */ +#define XENMEM_machphys_compat_mfn_list 25 + +/* * 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. @@ -198,13 +212,15 @@ struct xen_machphys_mapping { 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. - */ + * XENMEM_add_to_physmap_batch only. */ +/* ` } */ /* * Sets the GPFN at which a particular page appears in the specified guest's @@ -219,45 +235,22 @@ struct xen_add_to_physmap { /* Number of pages to go through for gmfn_range */ uint16_t size; - /* Source mapping 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 */ - unsigned int space; + unsigned int space; /* => enum phys_map_space */ #define XENMAPIDX_grant_table_status 0x80000000 - /* Index into source mapping space. */ + /* Index into space being mapped. */ xen_ulong_t idx; - /* GPFN where the source mapping page should appear. */ + /* 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); -/* - * 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*/ - -#define XENMEM_add_to_physmap_range 23 -struct xen_add_to_physmap_range { +/* A batched version of add_to_physmap. */ +#define XENMEM_add_to_physmap_batch 23 +struct xen_add_to_physmap_batch { /* IN */ /* Which domain to change the mapping for. */ domid_t domid; @@ -278,8 +271,34 @@ struct xen_add_to_physmap_range { /* Per index error code. */ XEN_GUEST_HANDLE(int) errs; }; -typedef struct xen_add_to_physmap_range xen_add_to_physmap_range_t; +typedef struct xen_add_to_physmap_batch xen_add_to_physmap_batch_t; +DEFINE_XEN_GUEST_HANDLE(xen_add_to_physmap_batch_t); + +#if __XEN_INTERFACE_VERSION__ < 0x00040400 +#define XENMEM_add_to_physmap_range XENMEM_add_to_physmap_batch +#define xen_add_to_physmap_range xen_add_to_physmap_batch +typedef struct xen_add_to_physmap_batch xen_add_to_physmap_range_t; DEFINE_XEN_GUEST_HANDLE(xen_add_to_physmap_range_t); +#endif + +/* + * 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 @@ -356,32 +375,78 @@ typedef struct xen_pod_target xen_pod_target_t; #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_* */ +struct xen_mem_paging_op { + uint8_t op; /* XENMEM_paging_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); +typedef struct xen_mem_paging_op xen_mem_paging_op_t; +DEFINE_XEN_GUEST_HANDLE(xen_mem_paging_op_t); + +#define XENMEM_access_op 21 +#define XENMEM_access_op_set_access 0 +#define XENMEM_access_op_get_access 1 +#define XENMEM_access_op_enable_emulate 2 +#define XENMEM_access_op_disable_emulate 3 + +typedef enum { + XENMEM_access_n, + XENMEM_access_r, + XENMEM_access_w, + XENMEM_access_rw, + XENMEM_access_x, + XENMEM_access_rx, + XENMEM_access_wx, + XENMEM_access_rwx, + /* + * Page starts off as r-x, but automatically + * change to r-w on a write + */ + XENMEM_access_rx2rw, + /* + * Log access: starts off as n, automatically + * goes to rwx, generating an event without + * pausing the vcpu + */ + XENMEM_access_n2rwx, + /* Take the domain default */ + XENMEM_access_default +} xenmem_access_t; + +struct xen_mem_access_op { + /* XENMEM_access_op_* */ + uint8_t op; + /* xenmem_access_t */ + uint8_t access; + domid_t domid; + /* + * Number of pages for set op + * Ignored on setting default access and other ops + */ + uint32_t nr; + /* + * First pfn for set op + * pfn for get op + * ~0ull is used to set and get the default access for pages + */ + uint64_aligned_t pfn; +}; +typedef struct xen_mem_access_op xen_mem_access_op_t; +DEFINE_XEN_GUEST_HANDLE(xen_mem_access_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_debug_gfn 3 +#define XENMEM_sharing_op_debug_mfn 4 +#define XENMEM_sharing_op_debug_gref 5 +#define XENMEM_sharing_op_add_physmap 6 +#define XENMEM_sharing_op_audit 7 #define XENMEM_SHARING_OP_S_HANDLE_INVALID (-10) #define XENMEM_SHARING_OP_C_HANDLE_INVALID (-9) @@ -430,14 +495,127 @@ struct xen_mem_sharing_op { 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. + */ + +/* + * With some legacy devices, certain guest-physical addresses cannot safely + * be used for other purposes, e.g. to map guest RAM. This hypercall + * enumerates those regions so the toolstack can avoid using them. + */ +#define XENMEM_reserved_device_memory_map 27 +struct xen_reserved_device_memory { + xen_pfn_t start_pfn; + xen_ulong_t nr_pages; +}; +typedef struct xen_reserved_device_memory xen_reserved_device_memory_t; +DEFINE_XEN_GUEST_HANDLE(xen_reserved_device_memory_t); + +struct xen_reserved_device_memory_map { +#define XENMEM_RDM_ALL 1 /* Request all regions (ignore dev union). */ + /* IN */ + uint32_t flags; + /* + * IN/OUT + * + * Gets set to the required number of entries when too low, + * signaled by error code -ERANGE. + */ + unsigned int nr_entries; + /* OUT */ + XEN_GUEST_HANDLE(xen_reserved_device_memory_t) buffer; + /* IN */ + union { + struct physdev_pci_device pci; + } dev; +}; +typedef struct xen_reserved_device_memory_map xen_reserved_device_memory_map_t; +DEFINE_XEN_GUEST_HANDLE(xen_reserved_device_memory_map_t); + #endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */ +/* + * XENMEM_get_vnumainfo used by guest to get + * vNUMA topology from hypervisor. + */ +#define XENMEM_get_vnumainfo 26 + +/* vNUMA node memory ranges */ +struct xen_vmemrange { + uint64_t start, end; + unsigned int flags; + unsigned int nid; +}; +typedef struct xen_vmemrange xen_vmemrange_t; +DEFINE_XEN_GUEST_HANDLE(xen_vmemrange_t); + +/* + * vNUMA topology specifies vNUMA node number, distance table, + * memory ranges and vcpu mapping provided for guests. + * XENMEM_get_vnumainfo hypercall expects to see from guest + * nr_vnodes, nr_vmemranges and nr_vcpus to indicate available memory. + * After filling guests structures, nr_vnodes, nr_vmemranges and nr_vcpus + * copied back to guest. Domain returns expected values of nr_vnodes, + * nr_vmemranges and nr_vcpus to guest if the values where incorrect. + */ +struct xen_vnuma_topology_info { + /* IN */ + domid_t domid; + uint16_t pad; + /* IN/OUT */ + unsigned int nr_vnodes; + unsigned int nr_vcpus; + unsigned int nr_vmemranges; + /* OUT */ + union { + XEN_GUEST_HANDLE(uint) h; + uint64_t pad; + } vdistance; + union { + XEN_GUEST_HANDLE(uint) h; + uint64_t pad; + } vcpu_to_vnode; + union { + XEN_GUEST_HANDLE(xen_vmemrange_t) h; + uint64_t pad; + } vmemrange; +}; +typedef struct xen_vnuma_topology_info xen_vnuma_topology_info_t; +DEFINE_XEN_GUEST_HANDLE(xen_vnuma_topology_info_t); + +/* Next available subop number is 28 */ + #endif /* __XEN_PUBLIC_MEMORY_H__ */ /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/nmi.h b/sys/xen/interface/nmi.h index 2fd21d2..604b293 100644 --- a/sys/xen/interface/nmi.h +++ b/sys/xen/interface/nmi.h @@ -36,9 +36,14 @@ /* I/O-check error reported via ISA port 0x61, bit 6. */ #define _XEN_NMIREASON_io_error 0 #define XEN_NMIREASON_io_error (1UL << _XEN_NMIREASON_io_error) + /* PCI SERR reported via ISA port 0x61, bit 7. */ +#define _XEN_NMIREASON_pci_serr 1 +#define XEN_NMIREASON_pci_serr (1UL << _XEN_NMIREASON_pci_serr) +#if __XEN_INTERFACE_VERSION__ < 0x00040300 /* legacy alias of the above */ /* Parity error reported via ISA port 0x61, bit 7. */ #define _XEN_NMIREASON_parity_error 1 #define XEN_NMIREASON_parity_error (1UL << _XEN_NMIREASON_parity_error) +#endif /* Unknown hardware-generated NMI. */ #define _XEN_NMIREASON_unknown 2 #define XEN_NMIREASON_unknown (1UL << _XEN_NMIREASON_unknown) @@ -72,7 +77,7 @@ DEFINE_XEN_GUEST_HANDLE(xennmi_callback_t); /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/physdev.h b/sys/xen/interface/physdev.h index 56b8be0..0e54635 100644 --- a/sys/xen/interface/physdev.h +++ b/sys/xen/interface/physdev.h @@ -16,6 +16,8 @@ * 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, Keir Fraser */ #ifndef __XEN_PUBLIC_PHYSDEV_H__ @@ -158,15 +160,15 @@ struct physdev_map_pirq { domid_t domid; /* IN */ int type; - /* IN */ + /* IN (ignored for ..._MULTI_MSI) */ int index; /* IN or OUT */ int pirq; - /* IN - high 16 bits hold segment for MAP_PIRQ_TYPE_MSI_SEG */ + /* IN - high 16 bits hold segment for ..._MSI_SEG and ..._MULTI_MSI */ int bus; /* IN */ int devfn; - /* IN */ + /* IN (also OUT for ..._MULTI_MSI) */ int entry_nr; /* IN */ uint64_t table_base; @@ -293,6 +295,11 @@ struct physdev_pci_device_add { uint8_t bus; uint8_t devfn; } physfn; + /* + * Optional parameters array. + * First element ([0]) is PXM domain associated with the device (if + * XEN_PCI_DEV_PXM is set) + */ #if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L uint32_t optarr[]; #elif defined(__GNUC__) @@ -304,6 +311,12 @@ DEFINE_XEN_GUEST_HANDLE(physdev_pci_device_add_t); #define PHYSDEVOP_pci_device_remove 26 #define PHYSDEVOP_restore_msi_ext 27 +/* + * Dom0 should use these two to announce MMIO resources assigned to + * MSI-X capable devices won't (prepare) or may (release) change. + */ +#define PHYSDEVOP_prepare_msix 30 +#define PHYSDEVOP_release_msix 31 struct physdev_pci_device { /* IN */ uint16_t seg; @@ -313,6 +326,24 @@ struct physdev_pci_device { typedef struct physdev_pci_device physdev_pci_device_t; DEFINE_XEN_GUEST_HANDLE(physdev_pci_device_t); +#define PHYSDEVOP_DBGP_RESET_PREPARE 1 +#define PHYSDEVOP_DBGP_RESET_DONE 2 + +#define PHYSDEVOP_DBGP_BUS_UNKNOWN 0 +#define PHYSDEVOP_DBGP_BUS_PCI 1 + +#define PHYSDEVOP_dbgp_op 29 +struct physdev_dbgp_op { + /* IN */ + uint8_t op; + uint8_t bus; + union { + struct physdev_pci_device pci; + } u; +}; +typedef struct physdev_dbgp_op physdev_dbgp_op_t; +DEFINE_XEN_GUEST_HANDLE(physdev_dbgp_op_t); + /* * Notify that some PIRQ-bound event channels have been unmasked. * ** This command is obsolete since interface version 0x00030202 and is ** @@ -320,9 +351,11 @@ DEFINE_XEN_GUEST_HANDLE(physdev_pci_device_t); */ #define PHYSDEVOP_IRQ_UNMASK_NOTIFY 4 +#if __XEN_INTERFACE_VERSION__ < 0x00040600 /* * These all-capitals physdev operation names are superceded by the new names - * (defined above) since interface version 0x00030202. + * (defined above) since interface version 0x00030202. The guard above was + * added post-4.5 only though and hence shouldn't check for 0x00030202. */ #define PHYSDEVOP_IRQ_STATUS_QUERY PHYSDEVOP_irq_status_query #define PHYSDEVOP_SET_IOPL PHYSDEVOP_set_iopl @@ -333,6 +366,7 @@ DEFINE_XEN_GUEST_HANDLE(physdev_pci_device_t); #define PHYSDEVOP_FREE_VECTOR PHYSDEVOP_free_irq_vector #define PHYSDEVOP_IRQ_NEEDS_UNMASK_NOTIFY XENIRQSTAT_needs_eoi #define PHYSDEVOP_IRQ_SHARED XENIRQSTAT_shared +#endif #if __XEN_INTERFACE_VERSION__ < 0x00040200 #define PHYSDEVOP_pirq_eoi_gmfn PHYSDEVOP_pirq_eoi_gmfn_v1 @@ -345,7 +379,7 @@ DEFINE_XEN_GUEST_HANDLE(physdev_pci_device_t); /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/platform.h b/sys/xen/interface/platform.h index ad51634..1e6a6ce 100644 --- a/sys/xen/interface/platform.h +++ b/sys/xen/interface/platform.h @@ -35,13 +35,28 @@ * Set clock such that it would read <secs,nsecs> after 00:00:00 UTC, * 1 January, 1970 if the current system time was <system_time>. */ -#define XENPF_settime 17 -struct xenpf_settime { +#define XENPF_settime32 17 +struct xenpf_settime32 { /* IN variables. */ uint32_t secs; uint32_t nsecs; uint64_t system_time; }; +#define XENPF_settime64 62 +struct xenpf_settime64 { + /* IN variables. */ + uint64_t secs; + uint32_t nsecs; + uint32_t mbz; + uint64_t system_time; +}; +#if __XEN_INTERFACE_VERSION__ < 0x00040600 +#define XENPF_settime XENPF_settime32 +#define xenpf_settime xenpf_settime32 +#else +#define XENPF_settime XENPF_settime64 +#define xenpf_settime xenpf_settime64 +#endif typedef struct xenpf_settime xenpf_settime_t; DEFINE_XEN_GUEST_HANDLE(xenpf_settime_t); @@ -126,6 +141,26 @@ DEFINE_XEN_GUEST_HANDLE(xenpf_platform_quirk_t); #define XEN_EFI_query_variable_info 9 #define XEN_EFI_query_capsule_capabilities 10 #define XEN_EFI_update_capsule 11 + +struct xenpf_efi_time { + uint16_t year; + uint8_t month; + uint8_t day; + uint8_t hour; + uint8_t min; + uint8_t sec; + uint32_t ns; + int16_t tz; + uint8_t daylight; +}; + +struct xenpf_efi_guid { + uint32_t data1; + uint16_t data2; + uint16_t data3; + uint8_t data4[8]; +}; + struct xenpf_efi_runtime_call { uint32_t function; /* @@ -134,21 +169,11 @@ struct xenpf_efi_runtime_call { * where it holds the single returned value. */ uint32_t misc; - unsigned long status; + xen_ulong_t status; union { #define XEN_EFI_GET_TIME_SET_CLEARS_NS 0x00000001 struct { - struct xenpf_efi_time { - uint16_t year; - uint8_t month; - uint8_t day; - uint8_t hour; - uint8_t min; - uint8_t sec; - uint32_t ns; - int16_t tz; - uint8_t daylight; - } time; + struct xenpf_efi_time time; uint32_t resolution; uint32_t accuracy; } get_time; @@ -168,22 +193,18 @@ struct xenpf_efi_runtime_call { #define XEN_EFI_VARIABLE_RUNTIME_ACCESS 0x00000004 struct { XEN_GUEST_HANDLE(void) name; /* UCS-2/UTF-16 string */ - unsigned long size; + xen_ulong_t size; XEN_GUEST_HANDLE(void) data; - struct xenpf_efi_guid { - uint32_t data1; - uint16_t data2; - uint16_t data3; - uint8_t data4[8]; - } vendor_guid; + struct xenpf_efi_guid vendor_guid; } get_variable, set_variable; struct { - unsigned long size; + xen_ulong_t size; XEN_GUEST_HANDLE(void) name; /* UCS-2/UTF-16 string */ struct xenpf_efi_guid vendor_guid; } get_next_variable_name; +#define XEN_EFI_VARINFO_BOOT_SNAPSHOT 0x00000001 struct { uint32_t attr; uint64_t max_store_size; @@ -193,14 +214,14 @@ struct xenpf_efi_runtime_call { struct { XEN_GUEST_HANDLE(void) capsule_header_array; - unsigned long capsule_count; + xen_ulong_t capsule_count; uint64_t max_capsule_size; - unsigned int reset_type; + uint32_t reset_type; } query_capsule_capabilities; struct { XEN_GUEST_HANDLE(void) capsule_header_array; - unsigned long capsule_count; + xen_ulong_t capsule_count; uint64_t sg_list; /* machine address */ } update_capsule; } u; @@ -218,6 +239,8 @@ DEFINE_XEN_GUEST_HANDLE(xenpf_efi_runtime_call_t); #define XEN_FW_EFI_VENDOR 2 #define XEN_FW_EFI_MEM_INFO 3 #define XEN_FW_EFI_RT_VERSION 4 +#define XEN_FW_EFI_PCI_ROM 5 +#define XEN_FW_KBD_SHIFT_FLAGS 5 struct xenpf_firmware_info { /* IN variables. */ uint32_t type; @@ -265,7 +288,21 @@ struct xenpf_firmware_info { uint64_t attr; uint32_t type; } mem; + struct { + /* IN variables */ + uint16_t segment; + uint8_t bus; + uint8_t devfn; + uint16_t vendor; + uint16_t devid; + /* OUT variables */ + uint64_t address; + xen_ulong_t size; + } pci_rom; } efi_info; /* XEN_FW_EFI_INFO */ + + /* Int16, Fn02: Get keyboard shift flags. */ + uint8_t kbd_shift_flags; /* XEN_FW_KBD_SHIFT_FLAGS */ } u; }; typedef struct xenpf_firmware_info xenpf_firmware_info_t; @@ -274,10 +311,16 @@ DEFINE_XEN_GUEST_HANDLE(xenpf_firmware_info_t); #define XENPF_enter_acpi_sleep 51 struct xenpf_enter_acpi_sleep { /* IN variables */ +#if __XEN_INTERFACE_VERSION__ < 0x00040300 uint16_t pm1a_cnt_val; /* PM1a control value. */ uint16_t pm1b_cnt_val; /* PM1b control value. */ +#else + uint16_t val_a; /* PM1a control / sleep type A. */ + uint16_t val_b; /* PM1b control / sleep type B. */ +#endif uint32_t sleep_state; /* Which state to enter (Sn). */ - uint32_t flags; /* Must be zero. */ +#define XENPF_ACPI_SLEEP_EXTENDED 0x00000001 + uint32_t flags; /* XENPF_ACPI_SLEEP_*. */ }; typedef struct xenpf_enter_acpi_sleep xenpf_enter_acpi_sleep_t; DEFINE_XEN_GUEST_HANDLE(xenpf_enter_acpi_sleep_t); @@ -505,6 +548,67 @@ typedef struct xenpf_core_parking xenpf_core_parking_t; DEFINE_XEN_GUEST_HANDLE(xenpf_core_parking_t); /* + * Access generic platform resources(e.g., accessing MSR, port I/O, etc) + * in unified way. Batch resource operations in one call are supported and + * they are always non-preemptible and executed in their original order. + * The batch itself returns a negative integer for general errors, or a + * non-negative integer for the number of successful operations. For the latter + * case, the @ret in the failed entry (if any) indicates the exact error. + */ +#define XENPF_resource_op 61 + +#define XEN_RESOURCE_OP_MSR_READ 0 +#define XEN_RESOURCE_OP_MSR_WRITE 1 + +/* + * Specially handled MSRs: + * - MSR_IA32_TSC + * READ: Returns the scaled system time(ns) instead of raw timestamp. In + * multiple entry case, if other MSR read is followed by a MSR_IA32_TSC + * read, then both reads are guaranteed to be performed atomically (with + * IRQ disabled). The return time indicates the point of reading that MSR. + * WRITE: Not supported. + */ + +struct xenpf_resource_entry { + union { + uint32_t cmd; /* IN: XEN_RESOURCE_OP_* */ + int32_t ret; /* OUT: return value for failed entry */ + } u; + uint32_t rsvd; /* IN: padding and must be zero */ + uint64_t idx; /* IN: resource address to access */ + uint64_t val; /* IN/OUT: resource value to set/get */ +}; +typedef struct xenpf_resource_entry xenpf_resource_entry_t; +DEFINE_XEN_GUEST_HANDLE(xenpf_resource_entry_t); + +struct xenpf_resource_op { + uint32_t nr_entries; /* number of resource entry */ + uint32_t cpu; /* which cpu to run */ + XEN_GUEST_HANDLE(xenpf_resource_entry_t) entries; +}; +typedef struct xenpf_resource_op xenpf_resource_op_t; +DEFINE_XEN_GUEST_HANDLE(xenpf_resource_op_t); + +#define XENPF_get_symbol 63 +struct xenpf_symdata { + /* IN/OUT variables */ + uint32_t namelen; /* IN: size of name buffer */ + /* OUT: strlen(name) of hypervisor symbol (may be */ + /* larger than what's been copied to guest) */ + uint32_t symnum; /* IN: Symbol to read */ + /* OUT: Next available symbol. If same as IN then */ + /* we reached the end */ + + /* OUT variables */ + XEN_GUEST_HANDLE(char) name; + uint64_t address; + char type; +}; +typedef struct xenpf_symdata xenpf_symdata_t; +DEFINE_XEN_GUEST_HANDLE(xenpf_symdata_t); + +/* * ` enum neg_errnoval * ` HYPERVISOR_platform_op(const struct xen_platform_op*); */ @@ -513,6 +617,8 @@ struct xen_platform_op { uint32_t interface_version; /* XENPF_INTERFACE_VERSION */ union { struct xenpf_settime settime; + struct xenpf_settime32 settime32; + struct xenpf_settime64 settime64; struct xenpf_add_memtype add_memtype; struct xenpf_del_memtype del_memtype; struct xenpf_read_memtype read_memtype; @@ -530,6 +636,8 @@ struct xen_platform_op { struct xenpf_cpu_hotadd cpu_add; struct xenpf_mem_hotadd mem_add; struct xenpf_core_parking core_parking; + struct xenpf_resource_op resource_op; + struct xenpf_symdata symdata; uint8_t pad[128]; } u; }; @@ -541,7 +649,7 @@ DEFINE_XEN_GUEST_HANDLE(xen_platform_op_t); /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/pmu.h b/sys/xen/interface/pmu.h new file mode 100644 index 0000000..7753df0 --- /dev/null +++ b/sys/xen/interface/pmu.h @@ -0,0 +1,133 @@ +/* + * 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) 2015 Oracle and/or its affiliates. All rights reserved. + */ + +#ifndef __XEN_PUBLIC_PMU_H__ +#define __XEN_PUBLIC_PMU_H__ + +#include "xen.h" +#if defined(__i386__) || defined(__x86_64__) +#include "arch-x86/pmu.h" +#elif defined (__arm__) || defined (__aarch64__) +#include "arch-arm.h" +#else +#error "Unsupported architecture" +#endif + +#define XENPMU_VER_MAJ 0 +#define XENPMU_VER_MIN 1 + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_xenpmu_op(enum xenpmu_op cmd, struct xenpmu_params *args); + * + * @cmd == XENPMU_* (PMU operation) + * @args == struct xenpmu_params + */ +/* ` enum xenpmu_op { */ +#define XENPMU_mode_get 0 /* Also used for getting PMU version */ +#define XENPMU_mode_set 1 +#define XENPMU_feature_get 2 +#define XENPMU_feature_set 3 +#define XENPMU_init 4 +#define XENPMU_finish 5 +#define XENPMU_lvtpc_set 6 +#define XENPMU_flush 7 /* Write cached MSR values to HW */ +/* ` } */ + +/* Parameters structure for HYPERVISOR_xenpmu_op call */ +struct xen_pmu_params { + /* IN/OUT parameters */ + struct { + uint32_t maj; + uint32_t min; + } version; + uint64_t val; + + /* IN parameters */ + uint32_t vcpu; + uint32_t pad; +}; +typedef struct xen_pmu_params xen_pmu_params_t; +DEFINE_XEN_GUEST_HANDLE(xen_pmu_params_t); + +/* PMU modes: + * - XENPMU_MODE_OFF: No PMU virtualization + * - XENPMU_MODE_SELF: Guests can profile themselves + * - XENPMU_MODE_HV: Guests can profile themselves, dom0 profiles + * itself and Xen + * - XENPMU_MODE_ALL: Only dom0 has access to VPMU and it profiles + * everyone: itself, the hypervisor and the guests. + */ +#define XENPMU_MODE_OFF 0 +#define XENPMU_MODE_SELF (1<<0) +#define XENPMU_MODE_HV (1<<1) +#define XENPMU_MODE_ALL (1<<2) + +/* + * PMU features: + * - XENPMU_FEATURE_INTEL_BTS: Intel BTS support (ignored on AMD) + */ +#define XENPMU_FEATURE_INTEL_BTS 1 + +/* + * Shared PMU data between hypervisor and PV(H) domains. + * + * The hypervisor fills out this structure during PMU interrupt and sends an + * interrupt to appropriate VCPU. + * Architecture-independent fields of xen_pmu_data are WO for the hypervisor + * and RO for the guest but some fields in xen_pmu_arch can be writable + * by both the hypervisor and the guest (see arch-$arch/pmu.h). + */ +struct xen_pmu_data { + /* Interrupted VCPU */ + uint32_t vcpu_id; + + /* + * Physical processor on which the interrupt occurred. On non-privileged + * guests set to vcpu_id; + */ + uint32_t pcpu_id; + + /* + * Domain that was interrupted. On non-privileged guests set to DOMID_SELF. + * On privileged guests can be DOMID_SELF, DOMID_XEN, or, when in + * XENPMU_MODE_ALL mode, domain ID of another domain. + */ + domid_t domain_id; + + uint8_t pad[6]; + + /* Architecture-specific information */ + struct xen_pmu_arch pmu; +}; + +#endif /* __XEN_PUBLIC_PMU_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/sys/xen/interface/sched.h b/sys/xen/interface/sched.h index 7f87420..4000ac9 100644 --- a/sys/xen/interface/sched.h +++ b/sys/xen/interface/sched.h @@ -1,8 +1,8 @@ /****************************************************************************** * 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 @@ -30,20 +30,33 @@ #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 sched_op(int cmd, void *arg) + * ` long HYPERVISOR_sched_op(enum sched_op cmd, void *arg, ...) + * * @cmd == SCHEDOP_??? (scheduler operation). * @arg == Operation-specific extra argument(s), as described below. - * + * ... == Additional Operation-specific extra arguments, described below. + * * Versions of Xen prior to 3.0.2 provided only the following legacy version * of this hypercall, supporting only the commands yield, block and shutdown: * long sched_op(int cmd, unsigned long arg) * @cmd == SCHEDOP_??? (scheduler operation). * @arg == 0 (SCHEDOP_yield and SCHEDOP_block) * == SHUTDOWN_* code (SCHEDOP_shutdown) - * This legacy version is available to new guests as sched_op_compat(). + * + * This legacy version is available to new guests as: + * ` long HYPERVISOR_sched_op_compat(enum sched_op cmd, unsigned long arg) */ +/* ` enum sched_op { // SCHEDOP_* => struct sched_* */ /* * Voluntarily yield the CPU. * @arg == NULL. @@ -61,59 +74,73 @@ /* * Halt execution of this domain (all VCPUs) and notify the system controller. - * @arg == pointer to sched_shutdown structure. + * @arg == pointer to sched_shutdown_t structure. + * + * If the sched_shutdown_t reason is SHUTDOWN_suspend then + * x86 PV guests must also set RDX (EDX for 32-bit guests) to the MFN + * of the guest's start info page. RDX/EDX is the third hypercall + * argument. + * + * 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 -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. + * @arg == pointer to sched_poll_t 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. + * @arg == pointer to sched_remote_shutdown_t 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. + * @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 structure. + * @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 */ @@ -126,18 +153,21 @@ DEFINE_XEN_GUEST_HANDLE(sched_watchdog_t); * 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-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/sysctl.h b/sys/xen/interface/sysctl.h index 3225b2a..0cacacc 100644 --- a/sys/xen/interface/sysctl.h +++ b/sys/xen/interface/sysctl.h @@ -33,8 +33,10 @@ #include "xen.h" #include "domctl.h" +#include "physdev.h" +#include "tmem.h" -#define XEN_SYSCTL_INTERFACE_VERSION 0x00000009 +#define XEN_SYSCTL_INTERFACE_VERSION 0x0000000C /* * Read console content from Xen buffer ring. @@ -71,7 +73,7 @@ struct xen_sysctl_tbuf_op { #define XEN_SYSCTL_TBUFOP_disable 5 uint32_t cmd; /* IN/OUT variables */ - struct xenctl_cpumap cpu_mask; + struct xenctl_bitmap cpu_mask; uint32_t evt_mask; /* OUT variables */ uint64_aligned_t buffer_mfn; @@ -101,6 +103,7 @@ struct xen_sysctl_physinfo { uint64_aligned_t total_pages; uint64_aligned_t free_pages; uint64_aligned_t scrub_pages; + uint64_aligned_t outstanding_pages; uint32_t hw_cap[8]; /* XEN_SYSCTL_PHYSCAP_??? */ @@ -225,13 +228,17 @@ struct pm_cx_stat { uint64_aligned_t idle_time; /* idle time from boot */ XEN_GUEST_HANDLE_64(uint64) triggers; /* Cx trigger counts */ XEN_GUEST_HANDLE_64(uint64) residencies; /* Cx residencies */ - uint64_aligned_t pc2; - uint64_aligned_t pc3; - uint64_aligned_t pc6; - uint64_aligned_t pc7; - uint64_aligned_t cc3; - uint64_aligned_t cc6; - uint64_aligned_t cc7; + uint32_t nr_pc; /* entry nr in pc[] */ + uint32_t nr_cc; /* entry nr in cc[] */ + /* + * These two arrays may (and generally will) have unused slots; slots not + * having a corresponding hardware register will not be written by the + * hypervisor. It is therefore up to the caller to put a suitable sentinel + * into all slots before invoking the function. + * Indexing is 1-biased (PC1/CC1 being at index 0). + */ + XEN_GUEST_HANDLE_64(uint64) pc; + XEN_GUEST_HANDLE_64(uint64) cc; }; struct xen_sysctl_get_pmstat { @@ -457,61 +464,76 @@ struct xen_sysctl_lockprof_op { typedef struct xen_sysctl_lockprof_op xen_sysctl_lockprof_op_t; DEFINE_XEN_GUEST_HANDLE(xen_sysctl_lockprof_op_t); -/* XEN_SYSCTL_topologyinfo */ -#define INVALID_TOPOLOGY_ID (~0U) -struct xen_sysctl_topologyinfo { - /* - * IN: maximum addressable entry in the caller-provided arrays. - * OUT: largest cpu identifier in the system. - * If OUT is greater than IN then the arrays are truncated! - * If OUT is leass than IN then the array tails are not written by sysctl. - */ - uint32_t max_cpu_index; +/* XEN_SYSCTL_cputopoinfo */ +#define XEN_INVALID_CORE_ID (~0U) +#define XEN_INVALID_SOCKET_ID (~0U) +#define XEN_INVALID_NODE_ID (~0U) - /* - * If not NULL, these arrays are filled with core/socket/node identifier - * for each cpu. - * If a cpu has no core/socket/node information (e.g., cpu not present) - * then the sentinel value ~0u is written to each array. - * The number of array elements written by the sysctl is: - * min(@max_cpu_index_IN,@max_cpu_index_OUT)+1 - */ - XEN_GUEST_HANDLE_64(uint32) cpu_to_core; - XEN_GUEST_HANDLE_64(uint32) cpu_to_socket; - XEN_GUEST_HANDLE_64(uint32) cpu_to_node; +struct xen_sysctl_cputopo { + uint32_t core; + uint32_t socket; + uint32_t node; }; -typedef struct xen_sysctl_topologyinfo xen_sysctl_topologyinfo_t; -DEFINE_XEN_GUEST_HANDLE(xen_sysctl_topologyinfo_t); +typedef struct xen_sysctl_cputopo xen_sysctl_cputopo_t; +DEFINE_XEN_GUEST_HANDLE(xen_sysctl_cputopo_t); + +/* + * IN: + * - a NULL 'cputopo' handle is a request for maximun 'num_cpus'. + * - otherwise it's the number of entries in 'cputopo' + * + * OUT: + * - If 'num_cpus' is less than the number Xen wants to write but the handle + * handle is not a NULL one, partial data gets returned and 'num_cpus' gets + * updated to reflect the intended number. + * - Otherwise, 'num_cpus' shall indicate the number of entries written, which + * may be less than the input value. + */ +struct xen_sysctl_cputopoinfo { + uint32_t num_cpus; + XEN_GUEST_HANDLE_64(xen_sysctl_cputopo_t) cputopo; +}; +typedef struct xen_sysctl_cputopoinfo xen_sysctl_cputopoinfo_t; +DEFINE_XEN_GUEST_HANDLE(xen_sysctl_cputopoinfo_t); /* XEN_SYSCTL_numainfo */ -#define INVALID_NUMAINFO_ID (~0U) +#define XEN_INVALID_MEM_SZ (~0U) +#define XEN_INVALID_NODE_DIST (~0U) + +struct xen_sysctl_meminfo { + uint64_t memsize; + uint64_t memfree; +}; +typedef struct xen_sysctl_meminfo xen_sysctl_meminfo_t; +DEFINE_XEN_GUEST_HANDLE(xen_sysctl_meminfo_t); + +/* + * IN: + * - Both 'meminfo' and 'distance' handles being null is a request + * for maximum value of 'num_nodes'. + * - Otherwise it's the number of entries in 'meminfo' and square root + * of number of entries in 'distance' (when corresponding handle is + * non-null) + * + * OUT: + * - If 'num_nodes' is less than the number Xen wants to write but either + * handle is not a NULL one, partial data gets returned and 'num_nodes' + * gets updated to reflect the intended number. + * - Otherwise, 'num_nodes' shall indicate the number of entries written, which + * may be less than the input value. + */ + struct xen_sysctl_numainfo { - /* - * IN: maximum addressable entry in the caller-provided arrays. - * OUT: largest node identifier in the system. - * If OUT is greater than IN then the arrays are truncated! - */ - uint32_t max_node_index; + uint32_t num_nodes; - /* NB. Entries are 0 if node is not present. */ - XEN_GUEST_HANDLE_64(uint64) node_to_memsize; - XEN_GUEST_HANDLE_64(uint64) node_to_memfree; + XEN_GUEST_HANDLE_64(xen_sysctl_meminfo_t) meminfo; /* - * Array, of size (max_node_index+1)^2, listing memory access distances - * between nodes. If an entry has no node distance information (e.g., node - * not present) then the value ~0u is written. - * - * Note that the array rows must be indexed by multiplying by the minimum - * of the caller-provided max_node_index and the returned value of - * max_node_index. That is, if the largest node index in the system is - * smaller than the caller can handle, a smaller 2-d array is constructed - * within the space provided by the caller. When this occurs, trailing - * space provided by the caller is not modified. If the largest node index - * in the system is larger than the caller can handle, then a 2-d array of - * the maximum size handleable by the caller is constructed. + * Distance between nodes 'i' and 'j' is stored in index 'i*N + j', + * where N is the number of nodes that will be returned in 'num_nodes' + * (i.e. not 'num_nodes' provided by the caller) */ - XEN_GUEST_HANDLE_64(uint32) node_to_node_distance; + XEN_GUEST_HANDLE_64(uint32) distance; }; typedef struct xen_sysctl_numainfo xen_sysctl_numainfo_t; DEFINE_XEN_GUEST_HANDLE(xen_sysctl_numainfo_t); @@ -532,7 +554,7 @@ struct xen_sysctl_cpupool_op { uint32_t domid; /* IN: M */ uint32_t cpu; /* IN: AR */ uint32_t n_dom; /* OUT: I */ - struct xenctl_cpumap cpumap; /* OUT: IF */ + struct xenctl_bitmap cpumap; /* OUT: IF */ }; typedef struct xen_sysctl_cpupool_op xen_sysctl_cpupool_op_t; DEFINE_XEN_GUEST_HANDLE(xen_sysctl_cpupool_op_t); @@ -596,6 +618,152 @@ struct xen_sysctl_scheduler_op { typedef struct xen_sysctl_scheduler_op xen_sysctl_scheduler_op_t; DEFINE_XEN_GUEST_HANDLE(xen_sysctl_scheduler_op_t); +/* XEN_SYSCTL_coverage_op */ +/* + * Get total size of information, to help allocate + * the buffer. The pointer points to a 32 bit value. + */ +#define XEN_SYSCTL_COVERAGE_get_total_size 0 + +/* + * Read coverage information in a single run + * You must use a tool to split them. + */ +#define XEN_SYSCTL_COVERAGE_read 1 + +/* + * Reset all the coverage counters to 0 + * No parameters. + */ +#define XEN_SYSCTL_COVERAGE_reset 2 + +/* + * Like XEN_SYSCTL_COVERAGE_read but reset also + * counters to 0 in a single call. + */ +#define XEN_SYSCTL_COVERAGE_read_and_reset 3 + +struct xen_sysctl_coverage_op { + uint32_t cmd; /* XEN_SYSCTL_COVERAGE_* */ + union { + uint32_t total_size; /* OUT */ + XEN_GUEST_HANDLE_64(uint8) raw_info; /* OUT */ + } u; +}; +typedef struct xen_sysctl_coverage_op xen_sysctl_coverage_op_t; +DEFINE_XEN_GUEST_HANDLE(xen_sysctl_coverage_op_t); + +#define XEN_SYSCTL_PSR_CMT_get_total_rmid 0 +#define XEN_SYSCTL_PSR_CMT_get_l3_upscaling_factor 1 +/* The L3 cache size is returned in KB unit */ +#define XEN_SYSCTL_PSR_CMT_get_l3_cache_size 2 +#define XEN_SYSCTL_PSR_CMT_enabled 3 +#define XEN_SYSCTL_PSR_CMT_get_l3_event_mask 4 +struct xen_sysctl_psr_cmt_op { + uint32_t cmd; /* IN: XEN_SYSCTL_PSR_CMT_* */ + uint32_t flags; /* padding variable, may be extended for future use */ + union { + uint64_t data; /* OUT */ + struct { + uint32_t cpu; /* IN */ + uint32_t rsvd; + } l3_cache; + } u; +}; +typedef struct xen_sysctl_psr_cmt_op xen_sysctl_psr_cmt_op_t; +DEFINE_XEN_GUEST_HANDLE(xen_sysctl_psr_cmt_op_t); + +/* XEN_SYSCTL_pcitopoinfo */ +#define XEN_INVALID_DEV (XEN_INVALID_NODE_ID - 1) +struct xen_sysctl_pcitopoinfo { + /* + * IN: Number of elements in 'pcitopo' and 'nodes' arrays. + * OUT: Number of processed elements of those arrays. + */ + uint32_t num_devs; + + /* IN: list of devices for which node IDs are requested. */ + XEN_GUEST_HANDLE_64(physdev_pci_device_t) devs; + + /* + * OUT: node identifier for each device. + * If information for a particular device is not available then + * corresponding entry will be set to XEN_INVALID_NODE_ID. If + * device is not known to the hypervisor then XEN_INVALID_DEV + * will be provided. + */ + XEN_GUEST_HANDLE_64(uint32) nodes; +}; +typedef struct xen_sysctl_pcitopoinfo xen_sysctl_pcitopoinfo_t; +DEFINE_XEN_GUEST_HANDLE(xen_sysctl_pcitopoinfo_t); + +#define XEN_SYSCTL_PSR_CAT_get_l3_info 0 +struct xen_sysctl_psr_cat_op { + uint32_t cmd; /* IN: XEN_SYSCTL_PSR_CAT_* */ + uint32_t target; /* IN */ + union { + struct { + uint32_t cbm_len; /* OUT: CBM length */ + uint32_t cos_max; /* OUT: Maximum COS */ + } l3_info; + } u; +}; +typedef struct xen_sysctl_psr_cat_op xen_sysctl_psr_cat_op_t; +DEFINE_XEN_GUEST_HANDLE(xen_sysctl_psr_cat_op_t); + +#define XEN_SYSCTL_TMEM_OP_ALL_CLIENTS 0xFFFFU + +#define XEN_SYSCTL_TMEM_OP_THAW 0 +#define XEN_SYSCTL_TMEM_OP_FREEZE 1 +#define XEN_SYSCTL_TMEM_OP_FLUSH 2 +#define XEN_SYSCTL_TMEM_OP_DESTROY 3 +#define XEN_SYSCTL_TMEM_OP_LIST 4 +#define XEN_SYSCTL_TMEM_OP_SET_WEIGHT 5 +#define XEN_SYSCTL_TMEM_OP_SET_CAP 6 +#define XEN_SYSCTL_TMEM_OP_SET_COMPRESS 7 +#define XEN_SYSCTL_TMEM_OP_QUERY_FREEABLE_MB 8 +#define XEN_SYSCTL_TMEM_OP_SAVE_BEGIN 10 +#define XEN_SYSCTL_TMEM_OP_SAVE_GET_VERSION 11 +#define XEN_SYSCTL_TMEM_OP_SAVE_GET_MAXPOOLS 12 +#define XEN_SYSCTL_TMEM_OP_SAVE_GET_CLIENT_WEIGHT 13 +#define XEN_SYSCTL_TMEM_OP_SAVE_GET_CLIENT_CAP 14 +#define XEN_SYSCTL_TMEM_OP_SAVE_GET_CLIENT_FLAGS 15 +#define XEN_SYSCTL_TMEM_OP_SAVE_GET_POOL_FLAGS 16 +#define XEN_SYSCTL_TMEM_OP_SAVE_GET_POOL_NPAGES 17 +#define XEN_SYSCTL_TMEM_OP_SAVE_GET_POOL_UUID 18 +#define XEN_SYSCTL_TMEM_OP_SAVE_GET_NEXT_PAGE 19 +#define XEN_SYSCTL_TMEM_OP_SAVE_GET_NEXT_INV 20 +#define XEN_SYSCTL_TMEM_OP_SAVE_END 21 +#define XEN_SYSCTL_TMEM_OP_RESTORE_BEGIN 30 +#define XEN_SYSCTL_TMEM_OP_RESTORE_PUT_PAGE 32 +#define XEN_SYSCTL_TMEM_OP_RESTORE_FLUSH_PAGE 33 + +/* + * XEN_SYSCTL_TMEM_OP_SAVE_GET_NEXT_[PAGE|INV] override the 'buf' in + * xen_sysctl_tmem_op with this structure - sometimes with an extra + * page tackled on. + */ +struct tmem_handle { + uint32_t pool_id; + uint32_t index; + xen_tmem_oid_t oid; +}; + +struct xen_sysctl_tmem_op { + uint32_t cmd; /* IN: XEN_SYSCTL_TMEM_OP_* . */ + int32_t pool_id; /* IN: 0 by default unless _SAVE_*, RESTORE_* .*/ + uint32_t cli_id; /* IN: client id, 0 for XEN_SYSCTL_TMEM_QUERY_FREEABLE_MB + for all others can be the domain id or + XEN_SYSCTL_TMEM_OP_ALL_CLIENTS for all. */ + uint32_t arg1; /* IN: If not applicable to command use 0. */ + uint32_t arg2; /* IN: If not applicable to command use 0. */ + uint32_t pad; /* Padding so structure is the same under 32 and 64. */ + xen_tmem_oid_t oid; /* IN: If not applicable to command use 0s. */ + XEN_GUEST_HANDLE_64(char) buf; /* IN/OUT: Buffer to save and restore ops. */ +}; +typedef struct xen_sysctl_tmem_op xen_sysctl_tmem_op_t; +DEFINE_XEN_GUEST_HANDLE(xen_sysctl_tmem_op_t); + struct xen_sysctl { uint32_t cmd; #define XEN_SYSCTL_readconsole 1 @@ -612,16 +780,22 @@ struct xen_sysctl { #define XEN_SYSCTL_pm_op 12 #define XEN_SYSCTL_page_offline_op 14 #define XEN_SYSCTL_lockprof_op 15 -#define XEN_SYSCTL_topologyinfo 16 +#define XEN_SYSCTL_cputopoinfo 16 #define XEN_SYSCTL_numainfo 17 #define XEN_SYSCTL_cpupool_op 18 #define XEN_SYSCTL_scheduler_op 19 +#define XEN_SYSCTL_coverage_op 20 +#define XEN_SYSCTL_psr_cmt_op 21 +#define XEN_SYSCTL_pcitopoinfo 22 +#define XEN_SYSCTL_psr_cat_op 23 +#define XEN_SYSCTL_tmem_op 24 uint32_t interface_version; /* XEN_SYSCTL_INTERFACE_VERSION */ union { struct xen_sysctl_readconsole readconsole; struct xen_sysctl_tbuf_op tbuf_op; struct xen_sysctl_physinfo physinfo; - struct xen_sysctl_topologyinfo topologyinfo; + struct xen_sysctl_cputopoinfo cputopoinfo; + struct xen_sysctl_pcitopoinfo pcitopoinfo; struct xen_sysctl_numainfo numainfo; struct xen_sysctl_sched_id sched_id; struct xen_sysctl_perfc_op perfc_op; @@ -636,6 +810,10 @@ struct xen_sysctl { struct xen_sysctl_lockprof_op lockprof_op; struct xen_sysctl_cpupool_op cpupool_op; struct xen_sysctl_scheduler_op scheduler_op; + struct xen_sysctl_coverage_op coverage_op; + struct xen_sysctl_psr_cmt_op psr_cmt_op; + struct xen_sysctl_psr_cat_op psr_cat_op; + struct xen_sysctl_tmem_op tmem_op; uint8_t pad[128]; } u; }; @@ -647,7 +825,7 @@ DEFINE_XEN_GUEST_HANDLE(xen_sysctl_t); /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/tmem.h b/sys/xen/interface/tmem.h index 74bd1c6..2d805fb 100644 --- a/sys/xen/interface/tmem.h +++ b/sys/xen/interface/tmem.h @@ -33,48 +33,28 @@ #define TMEM_SPEC_VERSION 1 /* Commands to HYPERVISOR_tmem_op() */ -#define TMEM_CONTROL 0 +#ifdef __XEN__ +#define TMEM_CONTROL 0 /* Now called XEN_SYSCTL_tmem_op */ +#else +#undef TMEM_CONTROL +#endif #define TMEM_NEW_POOL 1 #define TMEM_DESTROY_POOL 2 -#define TMEM_NEW_PAGE 3 #define TMEM_PUT_PAGE 4 #define TMEM_GET_PAGE 5 #define TMEM_FLUSH_PAGE 6 #define TMEM_FLUSH_OBJECT 7 +#if __XEN_INTERFACE_VERSION__ < 0x00040400 +#define TMEM_NEW_PAGE 3 #define TMEM_READ 8 #define TMEM_WRITE 9 #define TMEM_XCHG 10 +#endif /* Privileged commands to HYPERVISOR_tmem_op() */ -#define TMEM_AUTH 101 +#define TMEM_AUTH 101 #define TMEM_RESTORE_NEW 102 -/* Subops for HYPERVISOR_tmem_op(TMEM_CONTROL) */ -#define TMEMC_THAW 0 -#define TMEMC_FREEZE 1 -#define TMEMC_FLUSH 2 -#define TMEMC_DESTROY 3 -#define TMEMC_LIST 4 -#define TMEMC_SET_WEIGHT 5 -#define TMEMC_SET_CAP 6 -#define TMEMC_SET_COMPRESS 7 -#define TMEMC_QUERY_FREEABLE_MB 8 -#define TMEMC_SAVE_BEGIN 10 -#define TMEMC_SAVE_GET_VERSION 11 -#define TMEMC_SAVE_GET_MAXPOOLS 12 -#define TMEMC_SAVE_GET_CLIENT_WEIGHT 13 -#define TMEMC_SAVE_GET_CLIENT_CAP 14 -#define TMEMC_SAVE_GET_CLIENT_FLAGS 15 -#define TMEMC_SAVE_GET_POOL_FLAGS 16 -#define TMEMC_SAVE_GET_POOL_NPAGES 17 -#define TMEMC_SAVE_GET_POOL_UUID 18 -#define TMEMC_SAVE_GET_NEXT_PAGE 19 -#define TMEMC_SAVE_GET_NEXT_INV 20 -#define TMEMC_SAVE_END 21 -#define TMEMC_RESTORE_BEGIN 30 -#define TMEMC_RESTORE_PUT_PAGE 32 -#define TMEMC_RESTORE_FLUSH_PAGE 33 - /* Bits for HYPERVISOR_tmem_op(TMEM_NEW_POOL) */ #define TMEM_POOL_PERSIST 1 #define TMEM_POOL_SHARED 2 @@ -93,9 +73,16 @@ #define EFROZEN 1000 #define EEMPTY 1001 +struct xen_tmem_oid { + uint64_t oid[3]; +}; +typedef struct xen_tmem_oid xen_tmem_oid_t; +DEFINE_XEN_GUEST_HANDLE(xen_tmem_oid_t); #ifndef __ASSEMBLY__ +#if __XEN_INTERFACE_VERSION__ < 0x00040400 typedef xen_pfn_t tmem_cli_mfn_t; +#endif typedef XEN_GUEST_HANDLE(char) tmem_cli_va_t; struct tmem_op { uint32_t cmd; @@ -106,33 +93,22 @@ struct tmem_op { uint32_t flags; uint32_t arg1; } creat; /* for cmd == TMEM_NEW_POOL, TMEM_AUTH, TMEM_RESTORE_NEW */ - struct { - uint32_t subop; - uint32_t cli_id; - uint32_t arg1; - uint32_t arg2; - uint64_t oid[3]; - tmem_cli_va_t buf; - } ctrl; /* for cmd == TMEM_CONTROL */ struct { - +#if __XEN_INTERFACE_VERSION__ < 0x00040600 uint64_t oid[3]; +#else + xen_tmem_oid_t oid; +#endif uint32_t index; uint32_t tmem_offset; uint32_t pfn_offset; uint32_t len; - tmem_cli_mfn_t cmfn; /* client machine page frame */ + xen_pfn_t cmfn; /* client machine page frame */ } gen; /* for all other cmd ("generic") */ } u; }; typedef struct tmem_op tmem_op_t; DEFINE_XEN_GUEST_HANDLE(tmem_op_t); - -struct tmem_handle { - uint32_t pool_id; - uint32_t index; - uint64_t oid[3]; -}; #endif #endif /* __XEN_PUBLIC_TMEM_H__ */ @@ -140,7 +116,7 @@ struct tmem_handle { /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/trace.h b/sys/xen/interface/trace.h index 0dfabe9..274f8f6 100644 --- a/sys/xen/interface/trace.h +++ b/sys/xen/interface/trace.h @@ -50,13 +50,41 @@ #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_HVM_ENTRYEXIT 0x00081000 /* VMENTRY and #VMEXIT */ +#define TRC_HVM_HANDLER 0x00082000 /* various HVM handlers */ +#define TRC_HVM_EMUL 0x00084000 /* emulated devices */ #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<<TRC_SCHED_ID_BITS) - 1) << TRC_SCHED_ID_SHIFT) +#define TRC_SCHED_EVT_MASK (~(TRC_SCHED_ID_MASK)) + +/* Per-scheduler IDs, to identify scheduler specific events */ +#define TRC_SCHED_CSCHED 0 +#define TRC_SCHED_CSCHED2 1 +/* #define XEN_SCHEDULER_SEDF 2 (Removed) */ +#define TRC_SCHED_ARINC653 3 +#define TRC_SCHED_RTDS 4 + +/* Per-scheduler tracing */ +#define TRC_SCHED_CLASS_EVT(_c, _e) \ + ( ( TRC_SCHED_CLASS | \ + ((TRC_SCHED_##_c << TRC_SCHED_ID_SHIFT) & TRC_SCHED_ID_MASK) ) + \ + (_e & TRC_SCHED_EVT_MASK) ) + /* Trace classes for Hardware */ #define TRC_HW_PM 0x00801000 /* Power management traces */ #define TRC_HW_IRQ 0x00802000 /* Traces relating to the handling of IRQs */ @@ -94,20 +122,51 @@ #define TRC_MEM_POD_ZERO_RECLAIM (TRC_MEM + 17) #define TRC_MEM_POD_SUPERPAGE_SPLINTER (TRC_MEM + 18) +#define TRC_PV_ENTRY 0x00201000 /* Hypervisor entry points for PV guests. */ +#define TRC_PV_SUBCALL 0x00202000 /* Sub-call in a multicall hypercall */ + +#define TRC_PV_HYPERCALL (TRC_PV_ENTRY + 1) +#define TRC_PV_TRAP (TRC_PV_ENTRY + 3) +#define TRC_PV_PAGE_FAULT (TRC_PV_ENTRY + 4) +#define TRC_PV_FORCED_INVALID_OP (TRC_PV_ENTRY + 5) +#define TRC_PV_EMULATE_PRIVOP (TRC_PV_ENTRY + 6) +#define TRC_PV_EMULATE_4GB (TRC_PV_ENTRY + 7) +#define TRC_PV_MATH_STATE_RESTORE (TRC_PV_ENTRY + 8) +#define TRC_PV_PAGING_FIXUP (TRC_PV_ENTRY + 9) +#define TRC_PV_GDT_LDT_MAPPING_FAULT (TRC_PV_ENTRY + 10) +#define TRC_PV_PTWR_EMULATION (TRC_PV_ENTRY + 11) +#define TRC_PV_PTWR_EMULATION_PAE (TRC_PV_ENTRY + 12) +#define TRC_PV_HYPERCALL_V2 (TRC_PV_ENTRY + 13) +#define TRC_PV_HYPERCALL_SUBCALL (TRC_PV_SUBCALL + 14) -#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) +/* + * TRC_PV_HYPERCALL_V2 format + * + * Only some of the hypercall argument are recorded. Bit fields A0 to + * A5 in the first extra word are set if the argument is present and + * the arguments themselves are packed sequentially in the following + * words. + * + * The TRC_64_FLAG bit is not set for these events (even if there are + * 64-bit arguments in the record). + * + * Word + * 0 bit 31 30|29 28|27 26|25 24|23 22|21 20|19 ... 0 + * A5 |A4 |A3 |A2 |A1 |A0 |Hypercall op + * 1 First 32 bit (or low word of first 64 bit) arg in record + * 2 Second 32 bit (or high word of first 64 bit) arg in record + * ... + * + * A0-A5 bitfield values: + * + * 00b Argument not present + * 01b 32-bit argument present + * 10b 64-bit argument present + * 11b Reserved + */ +#define TRC_PV_HYPERCALL_V2_ARG_32(i) (0x1 << (20 + 2*(i))) +#define TRC_PV_HYPERCALL_V2_ARG_64(i) (0x2 << (20 + 2*(i))) +#define TRC_PV_HYPERCALL_V2_ARG_MASK (0xfff00000) #define TRC_SHADOW_NOT_SHADOW (TRC_SHADOW + 1) #define TRC_SHADOW_FAST_PROPAGATE (TRC_SHADOW + 2) @@ -172,6 +231,25 @@ #define TRC_HVM_IOPORT_WRITE (TRC_HVM_HANDLER + 0x216) #define TRC_HVM_IOMEM_WRITE (TRC_HVM_HANDLER + 0x217) +/* Trace events for emulated devices */ +#define TRC_HVM_EMUL_HPET_START_TIMER (TRC_HVM_EMUL + 0x1) +#define TRC_HVM_EMUL_PIT_START_TIMER (TRC_HVM_EMUL + 0x2) +#define TRC_HVM_EMUL_RTC_START_TIMER (TRC_HVM_EMUL + 0x3) +#define TRC_HVM_EMUL_LAPIC_START_TIMER (TRC_HVM_EMUL + 0x4) +#define TRC_HVM_EMUL_HPET_STOP_TIMER (TRC_HVM_EMUL + 0x5) +#define TRC_HVM_EMUL_PIT_STOP_TIMER (TRC_HVM_EMUL + 0x6) +#define TRC_HVM_EMUL_RTC_STOP_TIMER (TRC_HVM_EMUL + 0x7) +#define TRC_HVM_EMUL_LAPIC_STOP_TIMER (TRC_HVM_EMUL + 0x8) +#define TRC_HVM_EMUL_PIT_TIMER_CB (TRC_HVM_EMUL + 0x9) +#define TRC_HVM_EMUL_LAPIC_TIMER_CB (TRC_HVM_EMUL + 0xA) +#define TRC_HVM_EMUL_PIC_INT_OUTPUT (TRC_HVM_EMUL + 0xB) +#define TRC_HVM_EMUL_PIC_KICK (TRC_HVM_EMUL + 0xC) +#define TRC_HVM_EMUL_PIC_INTACK (TRC_HVM_EMUL + 0xD) +#define TRC_HVM_EMUL_PIC_POSEDGE (TRC_HVM_EMUL + 0xE) +#define TRC_HVM_EMUL_PIC_NEGEDGE (TRC_HVM_EMUL + 0xF) +#define TRC_HVM_EMUL_PIC_PEND_IRQ_CALL (TRC_HVM_EMUL + 0x10) +#define TRC_HVM_EMUL_LAPIC_PIC_INTR (TRC_HVM_EMUL + 0x11) + /* trace events for per class */ #define TRC_PM_FREQ_CHANGE (TRC_HW_PM + 0x01) #define TRC_PM_IDLE_ENTRY (TRC_HW_PM + 0x02) @@ -187,6 +265,14 @@ #define TRC_HW_IRQ_UNMAPPED_VECTOR (TRC_HW_IRQ + 0x7) #define TRC_HW_IRQ_HANDLED (TRC_HW_IRQ + 0x8) +/* + * Event Flags + * + * Some events (e.g, TRC_PV_TRAP and TRC_HVM_IOMEM_READ) have multiple + * record formats. These event flags distinguish between the + * different formats. + */ +#define TRC_64_FLAG 0x100 /* Addresses are 64 bits (instead of 32 bits) */ /* This structure represents a single trace buffer record. */ struct t_rec { @@ -237,7 +323,7 @@ struct t_info { /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/vcpu.h b/sys/xen/interface/vcpu.h index d52f121..898b89f 100644 --- a/sys/xen/interface/vcpu.h +++ b/sys/xen/interface/vcpu.h @@ -31,7 +31,7 @@ /* * Prototype for this hypercall is: - * int vcpu_op(int cmd, int vcpuid, void *extra_args) + * long vcpu_op(int cmd, unsigned int vcpuid, void *extra_args) * @cmd == VCPUOP_??? (VCPU operation). * @vcpuid == VCPU to operate on. * @extra_args == Operation-specific extra arguments (NULL if none). @@ -232,7 +232,7 @@ DEFINE_XEN_GUEST_HANDLE(vcpu_register_time_memory_area_t); /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/version.h b/sys/xen/interface/version.h index 8742c2b..44f26b0 100644 --- a/sys/xen/interface/version.h +++ b/sys/xen/interface/version.h @@ -28,6 +28,8 @@ #ifndef __XEN_PUBLIC_VERSION_H__ #define __XEN_PUBLIC_VERSION_H__ +#include "xen.h" + /* NB. All ops return zero on success, except XENVER_{version,pagesize} */ /* arg == NULL; returns major:minor (16:16). */ @@ -58,7 +60,7 @@ typedef char xen_changeset_info_t[64]; #define XENVER_platform_parameters 5 struct xen_platform_parameters { - unsigned long virt_start; + xen_ulong_t virt_start; }; typedef struct xen_platform_parameters xen_platform_parameters_t; @@ -86,7 +88,7 @@ typedef char xen_commandline_t[1024]; /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/vm_event.h b/sys/xen/interface/vm_event.h new file mode 100644 index 0000000..ff2f217 --- /dev/null +++ b/sys/xen/interface/vm_event.h @@ -0,0 +1,269 @@ +/****************************************************************************** + * vm_event.h + * + * Memory event common structures. + * + * Copyright (c) 2009 by Citrix Systems, Inc. (Patrick Colp) + * + * 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_VM_EVENT_H +#define _XEN_PUBLIC_VM_EVENT_H + +#include "xen.h" + +#define VM_EVENT_INTERFACE_VERSION 0x00000001 + +#if defined(__XEN__) || defined(__XEN_TOOLS__) + +#include "io/ring.h" + +/* + * Memory event flags + */ + +/* + * VCPU_PAUSED in a request signals that the vCPU triggering the event has been + * paused + * VCPU_PAUSED in a response signals to unpause the vCPU + */ +#define VM_EVENT_FLAG_VCPU_PAUSED (1 << 0) +/* Flags to aid debugging vm_event */ +#define VM_EVENT_FLAG_FOREIGN (1 << 1) +/* + * The following flags can be set in response to a mem_access event. + * + * Emulate the fault-causing instruction (if set in the event response flags). + * This will allow the guest to continue execution without lifting the page + * access restrictions. + */ +#define VM_EVENT_FLAG_EMULATE (1 << 2) +/* + * Same as VM_EVENT_FLAG_EMULATE, but with write operations or operations + * potentially having side effects (like memory mapped or port I/O) disabled. + */ +#define VM_EVENT_FLAG_EMULATE_NOWRITE (1 << 3) +/* + * Toggle singlestepping on vm_event response. + * Requires the vCPU to be paused already (synchronous events only). + */ +#define VM_EVENT_FLAG_TOGGLE_SINGLESTEP (1 << 4) +/* + * Data is being sent back to the hypervisor in the event response, to be + * returned by the read function when emulating an instruction. + * This flag is only useful when combined with VM_EVENT_FLAG_EMULATE + * and takes precedence if combined with VM_EVENT_FLAG_EMULATE_NOWRITE + * (i.e. if both VM_EVENT_FLAG_EMULATE_NOWRITE and + * VM_EVENT_FLAG_SET_EMUL_READ_DATA are set, only the latter will be honored). + */ +#define VM_EVENT_FLAG_SET_EMUL_READ_DATA (1 << 5) + /* + * Deny completion of the operation that triggered the event. + * Currently only useful for MSR, CR0, CR3 and CR4 write events. + */ +#define VM_EVENT_FLAG_DENY (1 << 6) +/* + * This flag can be set in a request or a response + * + * On a request, indicates that the event occurred in the alternate p2m specified by + * the altp2m_idx request field. + * + * On a response, indicates that the VCPU should resume in the alternate p2m specified + * by the altp2m_idx response field if possible. + */ +#define VM_EVENT_FLAG_ALTERNATE_P2M (1 << 7) + +/* + * Reasons for the vm event request + */ + +/* Default case */ +#define VM_EVENT_REASON_UNKNOWN 0 +/* Memory access violation */ +#define VM_EVENT_REASON_MEM_ACCESS 1 +/* Memory sharing event */ +#define VM_EVENT_REASON_MEM_SHARING 2 +/* Memory paging event */ +#define VM_EVENT_REASON_MEM_PAGING 3 +/* A control register was updated */ +#define VM_EVENT_REASON_WRITE_CTRLREG 4 +/* An MSR was updated. */ +#define VM_EVENT_REASON_MOV_TO_MSR 5 +/* Debug operation executed (e.g. int3) */ +#define VM_EVENT_REASON_SOFTWARE_BREAKPOINT 6 +/* Single-step (e.g. MTF) */ +#define VM_EVENT_REASON_SINGLESTEP 7 +/* An event has been requested via HVMOP_guest_request_vm_event. */ +#define VM_EVENT_REASON_GUEST_REQUEST 8 + +/* Supported values for the vm_event_write_ctrlreg index. */ +#define VM_EVENT_X86_CR0 0 +#define VM_EVENT_X86_CR3 1 +#define VM_EVENT_X86_CR4 2 +#define VM_EVENT_X86_XCR0 3 + +/* + * Using a custom struct (not hvm_hw_cpu) so as to not fill + * the vm_event ring buffer too quickly. + */ +struct vm_event_regs_x86 { + uint64_t rax; + uint64_t rcx; + uint64_t rdx; + uint64_t rbx; + uint64_t rsp; + uint64_t rbp; + uint64_t rsi; + uint64_t rdi; + uint64_t r8; + uint64_t r9; + uint64_t r10; + uint64_t r11; + uint64_t r12; + uint64_t r13; + uint64_t r14; + uint64_t r15; + uint64_t rflags; + uint64_t dr7; + uint64_t rip; + uint64_t cr0; + uint64_t cr2; + uint64_t cr3; + uint64_t cr4; + uint64_t sysenter_cs; + uint64_t sysenter_esp; + uint64_t sysenter_eip; + uint64_t msr_efer; + uint64_t msr_star; + uint64_t msr_lstar; + uint64_t fs_base; + uint64_t gs_base; + uint32_t cs_arbytes; + uint32_t _pad; +}; + +/* + * mem_access flag definitions + * + * These flags are set only as part of a mem_event request. + * + * R/W/X: Defines the type of violation that has triggered the event + * Multiple types can be set in a single violation! + * GLA_VALID: If the gla field holds a guest VA associated with the event + * FAULT_WITH_GLA: If the violation was triggered by accessing gla + * FAULT_IN_GPT: If the violation was triggered during translating gla + */ +#define MEM_ACCESS_R (1 << 0) +#define MEM_ACCESS_W (1 << 1) +#define MEM_ACCESS_X (1 << 2) +#define MEM_ACCESS_RWX (MEM_ACCESS_R | MEM_ACCESS_W | MEM_ACCESS_X) +#define MEM_ACCESS_RW (MEM_ACCESS_R | MEM_ACCESS_W) +#define MEM_ACCESS_RX (MEM_ACCESS_R | MEM_ACCESS_X) +#define MEM_ACCESS_WX (MEM_ACCESS_W | MEM_ACCESS_X) +#define MEM_ACCESS_GLA_VALID (1 << 3) +#define MEM_ACCESS_FAULT_WITH_GLA (1 << 4) +#define MEM_ACCESS_FAULT_IN_GPT (1 << 5) + +struct vm_event_mem_access { + uint64_t gfn; + uint64_t offset; + uint64_t gla; /* if flags has MEM_ACCESS_GLA_VALID set */ + uint32_t flags; /* MEM_ACCESS_* */ + uint32_t _pad; +}; + +struct vm_event_write_ctrlreg { + uint32_t index; + uint32_t _pad; + uint64_t new_value; + uint64_t old_value; +}; + +struct vm_event_debug { + uint64_t gfn; +}; + +struct vm_event_mov_to_msr { + uint64_t msr; + uint64_t value; +}; + +#define MEM_PAGING_DROP_PAGE (1 << 0) +#define MEM_PAGING_EVICT_FAIL (1 << 1) + +struct vm_event_paging { + uint64_t gfn; + uint32_t p2mt; + uint32_t flags; +}; + +struct vm_event_sharing { + uint64_t gfn; + uint32_t p2mt; + uint32_t _pad; +}; + +struct vm_event_emul_read_data { + uint32_t size; + /* The struct is used in a union with vm_event_regs_x86. */ + uint8_t data[sizeof(struct vm_event_regs_x86) - sizeof(uint32_t)]; +}; + +typedef struct vm_event_st { + uint32_t version; /* VM_EVENT_INTERFACE_VERSION */ + uint32_t flags; /* VM_EVENT_FLAG_* */ + uint32_t reason; /* VM_EVENT_REASON_* */ + uint32_t vcpu_id; + uint16_t altp2m_idx; /* may be used during request and response */ + uint16_t _pad[3]; + + union { + struct vm_event_paging mem_paging; + struct vm_event_sharing mem_sharing; + struct vm_event_mem_access mem_access; + struct vm_event_write_ctrlreg write_ctrlreg; + struct vm_event_mov_to_msr mov_to_msr; + struct vm_event_debug software_breakpoint; + struct vm_event_debug singlestep; + } u; + + union { + union { + struct vm_event_regs_x86 x86; + } regs; + + struct vm_event_emul_read_data emul_read_data; + } data; +} vm_event_request_t, vm_event_response_t; + +DEFINE_RING_TYPES(vm_event, vm_event_request_t, vm_event_response_t); + +#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */ +#endif /* _XEN_PUBLIC_VM_EVENT_H */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/sys/xen/interface/xen-compat.h b/sys/xen/interface/xen-compat.h index d8c55bf..74714de 100644 --- a/sys/xen/interface/xen-compat.h +++ b/sys/xen/interface/xen-compat.h @@ -27,14 +27,17 @@ #ifndef __XEN_PUBLIC_XEN_COMPAT_H__ #define __XEN_PUBLIC_XEN_COMPAT_H__ -#define __XEN_LATEST_INTERFACE_VERSION__ 0x00040200 +#define __XEN_LATEST_INTERFACE_VERSION__ 0x00040600 #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 +/* + * The interface version is not set if and only if xen/xen-os.h is not + * included. + */ +#error "Please include xen/xen-os.h" #endif #if __XEN_INTERFACE_VERSION__ > __XEN_LATEST_INTERFACE_VERSION__ diff --git a/sys/xen/interface/xen.h b/sys/xen/interface/xen.h index 9425520..ff5547e 100644 --- a/sys/xen/interface/xen.h +++ b/sys/xen/interface/xen.h @@ -31,9 +31,7 @@ #if defined(__i386__) || defined(__x86_64__) #include "arch-x86/xen.h" -#elif defined(__ia64__) -#include "arch-ia64.h" -#elif defined(__arm__) +#elif defined(__arm__) || defined (__aarch64__) #include "arch-arm.h" #else #error "Unsupported architecture" @@ -45,8 +43,10 @@ DEFINE_XEN_GUEST_HANDLE(char); __DEFINE_XEN_GUEST_HANDLE(uchar, unsigned char); DEFINE_XEN_GUEST_HANDLE(int); __DEFINE_XEN_GUEST_HANDLE(uint, unsigned int); +#if __XEN_INTERFACE_VERSION__ < 0x00040300 DEFINE_XEN_GUEST_HANDLE(long); __DEFINE_XEN_GUEST_HANDLE(ulong, unsigned long); +#endif DEFINE_XEN_GUEST_HANDLE(void); DEFINE_XEN_GUEST_HANDLE(uint64_t); @@ -101,6 +101,7 @@ DEFINE_XEN_GUEST_HANDLE(xen_ulong_t); #define __HYPERVISOR_kexec_op 37 #define __HYPERVISOR_tmem_op 38 #define __HYPERVISOR_xc_reserved_op 39 /* reserved for XenClient */ +#define __HYPERVISOR_xenpmu_op 40 /* Architecture-specific hypercall definitions. */ #define __HYPERVISOR_arch_0 48 @@ -160,6 +161,7 @@ DEFINE_XEN_GUEST_HANDLE(xen_ulong_t); #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 */ +#define VIRQ_XENPMU 13 /* V. PMC interrupt */ /* Architecture-specific VIRQ definitions. */ #define VIRQ_ARCH_0 16 @@ -277,15 +279,15 @@ DEFINE_XEN_GUEST_HANDLE(xen_ulong_t); * 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 follow (it is a 64-bit value, each entry is 8 bits): - * PAT4 PAT0 - * +---+----+----+----+-----+----+----+ - * WC | WC | WB | UC | UC- | WC | WB | <= Linux - * +---+----+----+----+-----+----+----+ - * WC | WT | WB | UC | UC- | WT | WB | <= BIOS (default when machine boots) - * +---+----+----+----+-----+----+----+ - * WC | WP | WC | UC | UC- | WT | WB | <= Xen - * +---+----+----+----+-----+----+----+ + * 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: @@ -319,48 +321,54 @@ DEFINE_XEN_GUEST_HANDLE(xen_ulong_t); /* * MMU EXTENDED OPERATIONS - * - * HYPERVISOR_mmuext_op() accepts a list of mmuext_op structures. + * + * ` 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. @@ -375,6 +383,7 @@ DEFINE_XEN_GUEST_HANDLE(xen_ulong_t); * 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 @@ -395,10 +404,11 @@ DEFINE_XEN_GUEST_HANDLE(xen_ulong_t); #define MMUEXT_FLUSH_CACHE_GLOBAL 18 #define MMUEXT_MARK_SUPER 19 #define MMUEXT_UNMARK_SUPER 20 +/* ` } */ #ifndef __ASSEMBLY__ struct mmuext_op { - unsigned int cmd; + unsigned int cmd; /* => enum mmuext_cmd */ union { /* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR * CLEAR_PAGE, COPY_PAGE, [UN]MARK_SUPER */ @@ -423,9 +433,24 @@ typedef struct mmuext_op mmuext_op_t; DEFINE_XEN_GUEST_HANDLE(mmuext_op_t); #endif +/* + * ` enum neg_errnoval + * ` HYPERVISOR_update_va_mapping(unsigned long va, u64 val, + * ` enum uvm_flags flags) + * ` + * ` enum neg_errnoval + * ` HYPERVISOR_update_va_mapping_otherdomain(unsigned long va, u64 val, + * ` enum uvm_flags flags, + * ` domid_t domid) + * ` + * ` @va: The virtual address whose mapping we want to change + * ` @val: The new page table entry, must contain a machine address + * ` @flags: Control TLB flushes + */ /* These are passed as 'flags' to update_va_mapping. They can be ORed. */ /* When specifying UVMF_MULTI, also OR in a pointer to a CPU bitmap. */ /* UVMF_LOCAL is merely UVMF_MULTI with a NULL bitmap pointer. */ +/* ` enum uvm_flags { */ #define UVMF_NONE (0UL<<0) /* No flushing at all. */ #define UVMF_TLB_FLUSH (1UL<<0) /* Flush entire TLB(s). */ #define UVMF_INVLPG (2UL<<0) /* Flush only one entry. */ @@ -433,6 +458,7 @@ DEFINE_XEN_GUEST_HANDLE(mmuext_op_t); #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(). @@ -462,7 +488,21 @@ DEFINE_XEN_GUEST_HANDLE(mmuext_op_t); /* x86/PAE guests: support PDPTs above 4GB. */ #define VMASST_TYPE_pae_extended_cr3 3 +/* + * x86/64 guests: strictly hide M2P from user mode. + * This allows the guest to control respective hypervisor behavior: + * - when not set, L4 tables get created with the respective slot blank, + * and whenever the L4 table gets used as a kernel one the missing + * mapping gets inserted, + * - when set, L4 tables get created with the respective slot initialized + * as before, and whenever the L4 table gets used as a user one the + * mapping gets zapped. + */ +#define VMASST_TYPE_m2p_strict 32 + +#if __XEN_INTERFACE_VERSION__ < 0x00040600 #define MAX_VMASST_TYPE 3 +#endif #ifndef __ASSEMBLY__ @@ -515,21 +555,28 @@ 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. + * ` enum neg_errnoval + * ` HYPERVISOR_multicall(multicall_entry_t call_list[], + * ` uint32_t nr_calls); + * + * NB. The fields are logically the natural register size for this + * architecture. In cases where xen_ulong_t is larger than this then + * any unused bits in the upper portion must be zero. */ struct multicall_entry { - unsigned long op, result; - unsigned long args[6]; + xen_ulong_t op, result; + xen_ulong_t args[6]; }; typedef struct multicall_entry multicall_entry_t; DEFINE_XEN_GUEST_HANDLE(multicall_entry_t); +#if __XEN_INTERFACE_VERSION__ < 0x00040400 /* - * Event channel endpoints per domain: + * Event channel endpoints per domain (when using the 2-level ABI): * 1024 if a long is 32 bits; 4096 if a long is 64 bits. */ -#define NR_EVENT_CHANNELS (sizeof(unsigned long) * sizeof(unsigned long) * 64) +#define NR_EVENT_CHANNELS EVTCHN_2L_NR_CHANNELS +#endif struct vcpu_time_info { /* @@ -585,8 +632,12 @@ struct vcpu_info { * to block: this avoids wakeup-waiting races. */ uint8_t evtchn_upcall_pending; +#ifdef XEN_HAVE_PV_UPCALL_MASK uint8_t evtchn_upcall_mask; - unsigned long evtchn_pending_sel; +#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) */ @@ -595,6 +646,7 @@ 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 @@ -636,8 +688,8 @@ struct shared_info { * per-vcpu selector word to be set. Each bit in the selector covers a * 'C long' in the PENDING bitfield array. */ - unsigned long evtchn_pending[sizeof(unsigned long) * 8]; - unsigned long evtchn_mask[sizeof(unsigned long) * 8]; + 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 @@ -646,6 +698,12 @@ struct shared_info { 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. */ +#if !defined(__i386__) + uint32_t wc_sec_hi; +# define xen_wc_sec_hi wc_sec_hi +#elif !defined(__XEN__) && !defined(__XEN_TOOLS__) +# define xen_wc_sec_hi arch.wc_sec_hi +#endif struct arch_shared_info arch; @@ -655,30 +713,43 @@ typedef struct shared_info shared_info_t; #endif /* - * Start-of-day memory layout: + * `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] + * (may be omitted) * 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)] + * in case of dom0 this page contains the console info, too + * e. unless dom0: xenstore ring page + * f. unless dom0: console ring page + * g. bootstrap page tables [pt_base and CR3 (x86)] + * h. 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 + * 5. 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 + * 6. 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 + * 7. 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.g 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. */ - -#define MAX_GUEST_CMDLINE 1024 +#ifdef XEN_HAVE_PV_GUEST_ENTRY struct start_info { /* THE FOLLOWING ARE FILLED IN BOTH ON INITIAL BOOT AND ON RESUME. */ char magic[32]; /* "xen-<version>-<platform>". */ @@ -705,6 +776,7 @@ struct start_info { /* (PFN of pre-loaded module if */ /* SIF_MOD_START_PFN set in flags). */ unsigned long mod_len; /* Size (bytes) of pre-loaded module. */ +#define MAX_GUEST_CMDLINE 1024 int8_t cmd_line[MAX_GUEST_CMDLINE]; /* The pfn range here covers both page table and p->m table frames. */ unsigned long first_p2m_pfn;/* 1st pfn forming initial P->M table. */ @@ -717,12 +789,15 @@ typedef struct start_info start_info_t; #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_VIRT_P2M_4TOOLS (1<<4) /* Do Xen tools understand a virt. mapped */ + /* P->M making the 3 level tree obsolete? */ #define SIF_PM_MASK (0xFF<<8) /* reserve 1 byte for xen-pm options */ /* @@ -750,7 +825,14 @@ struct xen_multiboot_mod_list /* 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 @@ -815,6 +897,9 @@ __DEFINE_XEN_GUEST_HANDLE(uint64, uint64_t); /* Default definitions for macros used by domctl/sysctl. */ #if defined(__XEN__) || defined(__XEN_TOOLS__) +#ifndef int64_aligned_t +#define int64_aligned_t int64_t +#endif #ifndef uint64_aligned_t #define uint64_aligned_t uint64_t #endif @@ -823,9 +908,9 @@ __DEFINE_XEN_GUEST_HANDLE(uint64, uint64_t); #endif #ifndef __ASSEMBLY__ -struct xenctl_cpumap { +struct xenctl_bitmap { XEN_GUEST_HANDLE_64(uint8) bitmap; - uint32_t nr_cpus; + uint32_t nr_bits; }; #endif @@ -836,7 +921,7 @@ struct xenctl_cpumap { /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/xenoprof.h b/sys/xen/interface/xenoprof.h index a0c6987..1c305c4 100644 --- a/sys/xen/interface/xenoprof.h +++ b/sys/xen/interface/xenoprof.h @@ -144,7 +144,7 @@ DEFINE_XEN_GUEST_HANDLE(xenoprof_ibs_counter_t); /* * Local variables: * mode: C - * c-set-style: "BSD" + * c-file-style: "BSD" * c-basic-offset: 4 * tab-width: 4 * indent-tabs-mode: nil diff --git a/sys/xen/interface/xsm/flask_op.h b/sys/xen/interface/xsm/flask_op.h index 1a251c9..c76359c 100644 --- a/sys/xen/interface/xsm/flask_op.h +++ b/sys/xen/interface/xsm/flask_op.h @@ -25,6 +25,8 @@ #ifndef __FLASK_OP_H__ #define __FLASK_OP_H__ +#include "../event_channel.h" + #define XEN_FLASK_INTERFACE_VERSION 1 struct xen_flask_load { @@ -142,6 +144,19 @@ struct xen_flask_peersid { uint32_t sid; }; +struct xen_flask_relabel { + /* IN */ + uint32_t domid; + uint32_t sid; +}; + +struct xen_flask_devicetree_label { + /* IN */ + uint32_t sid; + uint32_t length; + XEN_GUEST_HANDLE(char) path; +}; + struct xen_flask_op { uint32_t cmd; #define FLASK_LOAD 1 @@ -167,6 +182,8 @@ struct xen_flask_op { #define FLASK_ADD_OCONTEXT 21 #define FLASK_DEL_OCONTEXT 22 #define FLASK_GET_PEER_SID 23 +#define FLASK_RELABEL_DOMAIN 24 +#define FLASK_DEVICETREE_LABEL 25 uint32_t interface_version; /* XEN_FLASK_INTERFACE_VERSION */ union { struct xen_flask_load load; @@ -185,6 +202,8 @@ struct xen_flask_op { /* FLASK_ADD_OCONTEXT, FLASK_DEL_OCONTEXT */ struct xen_flask_ocontext ocontext; struct xen_flask_peersid peersid; + struct xen_flask_relabel relabel; + struct xen_flask_devicetree_label devicetree_label; } u; }; typedef struct xen_flask_op xen_flask_op_t; diff --git a/sys/xen/xen_intr.h b/sys/xen/xen_intr.h index d2d6470..b86f94a 100644 --- a/sys/xen/xen_intr.h +++ b/sys/xen/xen_intr.h @@ -33,11 +33,7 @@ #ifndef _XEN_INTR_H_ #define _XEN_INTR_H_ -#ifndef __XEN_EVTCHN_PORT_DEFINED__ -typedef uint32_t evtchn_port_t; -DEFINE_XEN_GUEST_HANDLE(evtchn_port_t); -#define __XEN_EVTCHN_PORT_DEFINED__ 1 -#endif +#include <xen/interface/event_channel.h> /** Registered Xen interrupt callback handle. */ typedef void * xen_intr_handle_t; |
