mirror of
https://github.com/xen-project/xen.git
synced 2026-10-29 18:50:05 +01:00
Anthony Perard
a6aa655723
This will save the acpi_ioport_location hvm_param in the checkpoint file and set the parameter in Xen at restore. Signed-off-by: Anthony PERARD <anthony.perard@citrix.com> Acked-by: Ian Jackson <ian.jackson@eu.citrix.com> Signed-off-by: Ian Jackson <ian.jackson@eu.citrix.com>
280 lines
10 KiB
C
280 lines
10 KiB
C
/*
|
|
* Definitions and utilities for save / restore.
|
|
*
|
|
* This library is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU Lesser General Public
|
|
* License as published by the Free Software Foundation;
|
|
* version 2.1 of the License.
|
|
*
|
|
* This library is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
* 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
|
|
*/
|
|
|
|
#include "xc_private.h"
|
|
|
|
#include <xen/foreign/x86_32.h>
|
|
#include <xen/foreign/x86_64.h>
|
|
|
|
/*
|
|
* SAVE/RESTORE/MIGRATE PROTOCOL
|
|
* =============================
|
|
*
|
|
* The general form of a stream of chunks is a header followed by a
|
|
* body consisting of a variable number of chunks (terminated by a
|
|
* chunk with type 0) followed by a trailer.
|
|
*
|
|
* For a rolling/checkpoint (e.g. remus) migration then the body and
|
|
* trailer phases can be repeated until an external event
|
|
* (e.g. failure) causes the process to terminate and commit to the
|
|
* most recent complete checkpoint.
|
|
*
|
|
* HEADER
|
|
* ------
|
|
*
|
|
* unsigned long : p2m_size
|
|
*
|
|
* extended-info (PV-only, optional):
|
|
*
|
|
* If first unsigned long == ~0UL then extended info is present,
|
|
* otherwise unsigned long is part of p2m. Note that p2m_size above
|
|
* does not include the length of the extended info.
|
|
*
|
|
* extended-info:
|
|
*
|
|
* unsigned long : signature == ~0UL
|
|
* uint32_t : number of bytes remaining in extended-info
|
|
*
|
|
* 1 or more extended-info blocks of form:
|
|
* char[4] : block identifier
|
|
* uint32_t : block data size
|
|
* bytes : block data
|
|
*
|
|
* defined extended-info blocks:
|
|
* "vcpu" : VCPU context info containing vcpu_guest_context_t.
|
|
* The precise variant of the context structure
|
|
* (e.g. 32 vs 64 bit) is distinguished by
|
|
* the block size.
|
|
* "extv" : Presence indicates use of extended VCPU context in
|
|
* tail, data size is 0.
|
|
*
|
|
* p2m (PV-only):
|
|
*
|
|
* consists of p2m_size bytes comprising an array of xen_pfn_t sized entries.
|
|
*
|
|
* BODY PHASE
|
|
* ----------
|
|
*
|
|
* A series of chunks with a common header:
|
|
* int : chunk type
|
|
*
|
|
* If the chunk type is +ve then chunk contains guest memory data, and the
|
|
* type contains the number of pages in the batch:
|
|
*
|
|
* unsigned long[] : PFN array, length == number of pages in batch
|
|
* Each entry consists of XEN_DOMCTL_PFINFO_*
|
|
* in bits 31-28 and the PFN number in bits 27-0.
|
|
* page data : PAGE_SIZE bytes for each page marked present in PFN
|
|
* array
|
|
*
|
|
* If the chunk type is -ve then chunk consists of one of a number of
|
|
* metadata types. See definitions of XC_SAVE_ID_* below.
|
|
*
|
|
* If chunk type is 0 then body phase is complete.
|
|
*
|
|
* TAIL PHASE
|
|
* ----------
|
|
*
|
|
* Content differs for PV and HVM guests.
|
|
*
|
|
* HVM TAIL:
|
|
*
|
|
* "Magic" pages:
|
|
* uint64_t : I/O req PFN
|
|
* uint64_t : Buffered I/O req PFN
|
|
* uint64_t : Store PFN
|
|
* Xen HVM Context:
|
|
* uint32_t : Length of context in bytes
|
|
* bytes : Context data
|
|
* Qemu context:
|
|
* char[21] : Signature:
|
|
* "QemuDeviceModelRecord" : Read Qemu save data until EOF
|
|
* "DeviceModelRecord0002" : uint32_t length field followed by that many
|
|
* bytes of Qemu save data
|
|
* "RemusDeviceModelState" : Currently the same as "DeviceModelRecord0002".
|
|
*
|
|
* PV TAIL:
|
|
*
|
|
* Unmapped PFN list : list of all the PFNs that were not in map at the close
|
|
* unsigned int : Number of unmapped pages
|
|
* unsigned long[] : PFNs of unmapped pages
|
|
*
|
|
* VCPU context data : A series of VCPU records, one per present VCPU
|
|
* Maximum and present map supplied in XC_SAVE_ID_VCPUINFO
|
|
* bytes: : VCPU context structure. Size is determined by size
|
|
* provided in extended-info header
|
|
* bytes[128] : Extended VCPU context (present IFF "extv" block
|
|
* present in extended-info header)
|
|
*
|
|
* Shared Info Page : 4096 bytes of shared info page
|
|
*/
|
|
|
|
#define XC_SAVE_ID_ENABLE_VERIFY_MODE -1 /* Switch to validation phase. */
|
|
#define XC_SAVE_ID_VCPU_INFO -2 /* Additional VCPU info */
|
|
#define XC_SAVE_ID_HVM_IDENT_PT -3 /* (HVM-only) */
|
|
#define XC_SAVE_ID_HVM_VM86_TSS -4 /* (HVM-only) */
|
|
#define XC_SAVE_ID_TMEM -5
|
|
#define XC_SAVE_ID_TMEM_EXTRA -6
|
|
#define XC_SAVE_ID_TSC_INFO -7
|
|
#define XC_SAVE_ID_HVM_CONSOLE_PFN -8 /* (HVM-only) */
|
|
#define XC_SAVE_ID_LAST_CHECKPOINT -9 /* Commit to restoring after completion of current iteration. */
|
|
#define XC_SAVE_ID_HVM_ACPI_IOPORTS_LOCATION -10
|
|
|
|
/*
|
|
** We process save/restore/migrate in batches of pages; the below
|
|
** determines how many pages we (at maximum) deal with in each batch.
|
|
*/
|
|
#define MAX_BATCH_SIZE 1024 /* up to 1024 pages (4MB) at a time */
|
|
|
|
/* When pinning page tables at the end of restore, we also use batching. */
|
|
#define MAX_PIN_BATCH 1024
|
|
|
|
|
|
|
|
/*
|
|
** Determine various platform information required for save/restore, in
|
|
** particular:
|
|
**
|
|
** - the maximum MFN on this machine, used to compute the size of
|
|
** the M2P table;
|
|
**
|
|
** - the starting virtual address of the the hypervisor; we use this
|
|
** to determine which parts of guest address space(s) do and don't
|
|
** require canonicalization during save/restore; and
|
|
**
|
|
** - the number of page-table levels for save/ restore. This should
|
|
** be a property of the domain, but for the moment we just read it
|
|
** from the hypervisor.
|
|
**
|
|
** - The width of a guest word (unsigned long), in bytes.
|
|
**
|
|
** Returns 1 on success, 0 on failure.
|
|
*/
|
|
static inline int get_platform_info(xc_interface *xch, uint32_t dom,
|
|
/* OUT */ unsigned long *max_mfn,
|
|
/* OUT */ unsigned long *hvirt_start,
|
|
/* OUT */ unsigned int *pt_levels,
|
|
/* OUT */ unsigned int *guest_width)
|
|
{
|
|
xen_capabilities_info_t xen_caps = "";
|
|
xen_platform_parameters_t xen_params;
|
|
DECLARE_DOMCTL;
|
|
|
|
if (xc_version(xch, XENVER_platform_parameters, &xen_params) != 0)
|
|
return 0;
|
|
|
|
if (xc_version(xch, XENVER_capabilities, &xen_caps) != 0)
|
|
return 0;
|
|
|
|
*max_mfn = xc_maximum_ram_page(xch);
|
|
|
|
*hvirt_start = xen_params.virt_start;
|
|
|
|
memset(&domctl, 0, sizeof(domctl));
|
|
domctl.domain = dom;
|
|
domctl.cmd = XEN_DOMCTL_get_address_size;
|
|
|
|
if ( do_domctl(xch, &domctl) != 0 )
|
|
return 0;
|
|
|
|
*guest_width = domctl.u.address_size.size / 8;
|
|
|
|
/* 64-bit tools will see the 64-bit hvirt_start, but 32-bit guests
|
|
* will be using the compat one. */
|
|
if ( *guest_width < sizeof (unsigned long) )
|
|
/* XXX need to fix up a way of extracting this value from Xen if
|
|
* XXX it becomes variable for domU */
|
|
*hvirt_start = 0xf5800000;
|
|
|
|
if (strstr(xen_caps, "xen-3.0-x86_64"))
|
|
/* Depends on whether it's a compat 32-on-64 guest */
|
|
*pt_levels = ( (*guest_width == 8) ? 4 : 3 );
|
|
else if (strstr(xen_caps, "xen-3.0-x86_32p"))
|
|
*pt_levels = 3;
|
|
else if (strstr(xen_caps, "xen-3.0-x86_32"))
|
|
*pt_levels = 2;
|
|
else
|
|
return 0;
|
|
|
|
return 1;
|
|
}
|
|
|
|
|
|
/*
|
|
** Save/restore deal with the mfn_to_pfn (M2P) and pfn_to_mfn (P2M) tables.
|
|
** The M2P simply holds the corresponding PFN, while the top bit of a P2M
|
|
** entry tell us whether or not the the PFN is currently mapped.
|
|
*/
|
|
|
|
#define PFN_TO_KB(_pfn) ((_pfn) << (PAGE_SHIFT - 10))
|
|
|
|
|
|
/*
|
|
** The M2P is made up of some number of 'chunks' of at least 2MB in size.
|
|
** The below definitions and utility function(s) deal with mapping the M2P
|
|
** regarldess of the underlying machine memory size or architecture.
|
|
*/
|
|
#define M2P_SHIFT L2_PAGETABLE_SHIFT_PAE
|
|
#define M2P_CHUNK_SIZE (1 << M2P_SHIFT)
|
|
#define M2P_SIZE(_m) ROUNDUP(((_m) * sizeof(xen_pfn_t)), M2P_SHIFT)
|
|
#define M2P_CHUNKS(_m) (M2P_SIZE((_m)) >> M2P_SHIFT)
|
|
|
|
/* Returns TRUE if the PFN is currently mapped */
|
|
#define is_mapped(pfn_type) (!((pfn_type) & 0x80000000UL))
|
|
|
|
|
|
#define GET_FIELD(_p, _f) ((dinfo->guest_width==8) ? ((_p)->x64._f) : ((_p)->x32._f))
|
|
|
|
#define SET_FIELD(_p, _f, _v) do { \
|
|
if (dinfo->guest_width == 8) \
|
|
(_p)->x64._f = (_v); \
|
|
else \
|
|
(_p)->x32._f = (_v); \
|
|
} while (0)
|
|
|
|
#define UNFOLD_CR3(_c) \
|
|
((uint64_t)((dinfo->guest_width == 8) \
|
|
? ((_c) >> 12) \
|
|
: (((uint32_t)(_c) >> 12) | ((uint32_t)(_c) << 20))))
|
|
|
|
#define FOLD_CR3(_c) \
|
|
((uint64_t)((dinfo->guest_width == 8) \
|
|
? ((uint64_t)(_c)) << 12 \
|
|
: (((uint32_t)(_c) << 12) | ((uint32_t)(_c) >> 20))))
|
|
|
|
#define MEMCPY_FIELD(_d, _s, _f) do { \
|
|
if (dinfo->guest_width == 8) \
|
|
memcpy(&(_d)->x64._f, &(_s)->x64._f,sizeof((_d)->x64._f)); \
|
|
else \
|
|
memcpy(&(_d)->x32._f, &(_s)->x32._f,sizeof((_d)->x32._f)); \
|
|
} while (0)
|
|
|
|
#define MEMSET_ARRAY_FIELD(_p, _f, _v) do { \
|
|
if (dinfo->guest_width == 8) \
|
|
memset(&(_p)->x64._f[0], (_v), sizeof((_p)->x64._f)); \
|
|
else \
|
|
memset(&(_p)->x32._f[0], (_v), sizeof((_p)->x32._f)); \
|
|
} while (0)
|
|
|
|
#ifndef MAX
|
|
#define MAX(_a, _b) ((_a) >= (_b) ? (_a) : (_b))
|
|
#endif
|
|
#ifndef MIN
|
|
#define MIN(_a, _b) ((_a) <= (_b) ? (_a) : (_b))
|
|
#endif
|