Hi all, this patch series allows tools/ to compile on ARM, mostly providing an empty implementation for all the arch specific functions that are needed. Changes in v5: - libxc: return -1 and set errno on error; - add few missing emacs runes in new files. Changes in v4: - rebased on 55a36564fb4f85722c67f16fe508f3ecbd204549; - minor compile fixes. Changes in v3: - move libxl_cpuid_policy_list_gen_json to libxl_(no)cpuid.c; - rename xc_hvm_build.c to xc_hvm_build_x86.c; - remove xc_nohvm, introduce xc_hvm_build_arm.c instead; - remove "libxl: do not allocate e820 for non x86 guests."; - introduce libxl__arch_domain_create. Changes in v2: - rebased on a22587ae517170a7755d3a88611ae0e2d5bb555e; - dropped "arm: arch_dump_shared_mem_info as a no-op" that is already in xen-unstable; - define xen_callback_t as uint64_t; - define guest_word_t as uint64_t. Ian Campbell (1): arm: add stub hvm/save.h Stefano Stabellini (6): arm: compile libxc arm: compile libxenguest arm: compile memshr arm: compile xentrace arm: compile libxl libxl: Introduce libxl__arch_domain_create tools/libxc/Makefile | 13 +- tools/libxc/xc_core.h | 2 + tools/libxc/xc_core_arm.c | 107 +++++++ tools/libxc/xc_core_arm.h | 60 ++++ tools/libxc/xc_dom_arm.c | 50 +++ tools/libxc/xc_hvm_build.c | 511 -------------------------------- tools/libxc/xc_hvm_build_arm.c | 61 ++++ tools/libxc/xc_hvm_build_x86.c | 511 ++++++++++++++++++++++++++++++++ tools/libxc/xc_nomigrate.c | 53 ++++ tools/libxc/xenctrl.h | 4 + tools/libxl/Makefile | 5 +- tools/libxl/libxl_arch.h | 22 ++ tools/libxl/libxl_cpuid.c | 60 ++++ tools/libxl/libxl_create.c | 12 +- tools/libxl/libxl_internal.h | 2 - tools/libxl/libxl_json.c | 60 ---- tools/libxl/libxl_noarch.c | 8 + tools/libxl/libxl_nocpuid.c | 8 +- tools/libxl/libxl_pci.c | 242 --------------- tools/libxl/libxl_x86.c | 259 ++++++++++++++++ tools/memshr/bidir-hash.c | 31 ++ tools/xentrace/xenctx.c | 12 + xen/include/public/arch-arm/hvm/save.h | 39 +++ xen/include/public/hvm/save.h | 2 + 24 files changed, 1303 insertions(+), 831 deletions(-) A git tree based on 6c69c04ed2b1d5fd0cbebb61e649c03d9d2e8d9a, is available here: git://xenbits.xen.org/people/sstabellini/xen-unstable.git arm-tools-5 Cheers, Stefano
From: Ian Campbell <ian.campbell@citrix.com> Signed-off-by: Ian Campbell <ian.campbell@citrix.com> Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> --- xen/include/public/arch-arm/hvm/save.h | 39 ++++++++++++++++++++++++++++++++ xen/include/public/hvm/save.h | 2 + 2 files changed, 41 insertions(+), 0 deletions(-) create mode 100644 xen/include/public/arch-arm/hvm/save.h diff --git a/xen/include/public/arch-arm/hvm/save.h b/xen/include/public/arch-arm/hvm/save.h new file mode 100644 index 0000000..ec61298 --- /dev/null +++ b/xen/include/public/arch-arm/hvm/save.h @@ -0,0 +1,39 @@ +/* + * Structure definitions for HVM state that is held by Xen and must + * be saved along with the domain''s memory and device-model state. + * + * Copyright (c) 2012 Citrix Systems Ltd. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +#ifndef __XEN_PUBLIC_HVM_SAVE_ARM_H__ +#define __XEN_PUBLIC_HVM_SAVE_ARM_H__ + +#endif + +/* + * Local variables: + * mode: C + * c-set-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/xen/include/public/hvm/save.h b/xen/include/public/hvm/save.h index d0f2661..58f8433 100644 --- a/xen/include/public/hvm/save.h +++ b/xen/include/public/hvm/save.h @@ -104,6 +104,8 @@ DECLARE_HVM_SAVE_TYPE(END, 0, struct hvm_save_end); #include "../arch-x86/hvm/save.h" #elif defined(__ia64__) #include "../arch-ia64/hvm/save.h" +#elif defined(__arm__) +#include "../arch-arm/hvm/save.h" #else #error "unsupported architecture" #endif -- 1.7.2.5
Introduce an empty implementation of the arch specific ARM functions in xc_core_arm.c and xc_core_arm.h; define barriers on ARM. Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Acked-by: Ian Campbell <ian.campbell@citrix.com> Acked-by: Ian Jackson <ian.jackson@eu.citrix.com> --- tools/libxc/Makefile | 1 + tools/libxc/xc_core.h | 2 + tools/libxc/xc_core_arm.c | 107 +++++++++++++++++++++++++++++++++++++++++++++ tools/libxc/xc_core_arm.h | 60 +++++++++++++++++++++++++ tools/libxc/xenctrl.h | 4 ++ 5 files changed, 174 insertions(+), 0 deletions(-) create mode 100644 tools/libxc/xc_core_arm.c create mode 100644 tools/libxc/xc_core_arm.h diff --git a/tools/libxc/Makefile b/tools/libxc/Makefile index b5e7022..f2e1ba7 100644 --- a/tools/libxc/Makefile +++ b/tools/libxc/Makefile @@ -8,6 +8,7 @@ CTRL_SRCS-y : CTRL_SRCS-y += xc_core.c CTRL_SRCS-$(CONFIG_X86) += xc_core_x86.c CTRL_SRCS-$(CONFIG_IA64) += xc_core_ia64.c +CTRL_SRCS-$(CONFIG_ARM) += xc_core_arm.c CTRL_SRCS-y += xc_cpupool.c CTRL_SRCS-y += xc_domain.c CTRL_SRCS-y += xc_evtchn.c diff --git a/tools/libxc/xc_core.h b/tools/libxc/xc_core.h index 1e88a75..358a8c1 100644 --- a/tools/libxc/xc_core.h +++ b/tools/libxc/xc_core.h @@ -155,6 +155,8 @@ int xc_core_arch_map_p2m_writable(xc_interface *xch, unsigned int guest_width, # include "xc_core_x86.h" #elif defined (__ia64__) # include "xc_core_ia64.h" +#elif defined (__arm__) +# include "xc_core_arm.h" #else # error "unsupported architecture" #endif diff --git a/tools/libxc/xc_core_arm.c b/tools/libxc/xc_core_arm.c new file mode 100644 index 0000000..e6716e4 --- /dev/null +++ b/tools/libxc/xc_core_arm.c @@ -0,0 +1,107 @@ +/* + * 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; either + * version 2.1 of the License, or (at your option) any later version. + * + * 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 + * + * Copyright (c) 2011 Citrix Systems + * + */ + +#include "xg_private.h" +#include "xc_core.h" + +int +xc_core_arch_gpfn_may_present(struct xc_core_arch_context *arch_ctxt, + unsigned long pfn) +{ + /* TODO: memory from DT */ + if (pfn >= 0x80000 && pfn < 0x88000) + return 1; + return 0; +} + + +static int nr_gpfns(xc_interface *xch, domid_t domid) +{ + return xc_domain_maximum_gpfn(xch, domid) + 1; +} + +int +xc_core_arch_auto_translated_physmap(const xc_dominfo_t *info) +{ + return 1; +} + +int +xc_core_arch_memory_map_get(xc_interface *xch, struct xc_core_arch_context *unused, + xc_dominfo_t *info, shared_info_any_t *live_shinfo, + xc_core_memory_map_t **mapp, + unsigned int *nr_entries) +{ + unsigned long p2m_size = nr_gpfns(xch, info->domid); + xc_core_memory_map_t *map; + + map = malloc(sizeof(*map)); + if ( map == NULL ) + { + PERROR("Could not allocate memory"); + return -1; + } + + map->addr = 0; + map->size = ((uint64_t)p2m_size) << PAGE_SHIFT; + + *mapp = map; + *nr_entries = 1; + return 0; +} + +static int +xc_core_arch_map_p2m_rw(xc_interface *xch, struct domain_info_context *dinfo, xc_dominfo_t *info, + shared_info_any_t *live_shinfo, xen_pfn_t **live_p2m, + unsigned long *pfnp, int rw) +{ + errno = ENOSYS; + return -1; +} + +int +xc_core_arch_map_p2m(xc_interface *xch, unsigned int guest_width, xc_dominfo_t *info, + shared_info_any_t *live_shinfo, xen_pfn_t **live_p2m, + unsigned long *pfnp) +{ + struct domain_info_context _dinfo = { .guest_width = guest_width }; + struct domain_info_context *dinfo = &_dinfo; + return xc_core_arch_map_p2m_rw(xch, dinfo, info, + live_shinfo, live_p2m, pfnp, 0); +} + +int +xc_core_arch_map_p2m_writable(xc_interface *xch, unsigned int guest_width, xc_dominfo_t *info, + shared_info_any_t *live_shinfo, xen_pfn_t **live_p2m, + unsigned long *pfnp) +{ + struct domain_info_context _dinfo = { .guest_width = guest_width }; + struct domain_info_context *dinfo = &_dinfo; + return xc_core_arch_map_p2m_rw(xch, dinfo, info, + live_shinfo, live_p2m, pfnp, 1); +} +/* + * Local variables: + * mode: C + * c-set-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/tools/libxc/xc_core_arm.h b/tools/libxc/xc_core_arm.h new file mode 100644 index 0000000..3a6be2a --- /dev/null +++ b/tools/libxc/xc_core_arm.h @@ -0,0 +1,60 @@ +/* + * 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; either + * version 2.1 of the License, or (at your option) any later version. + * + * 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 + * + * Copyright (c) 2012 Citrix Systems + * + */ + +#ifndef XC_CORE_ARM_H +#define XC_CORE_ARM_H + +#define ELF_ARCH_DATA ELFDATA2LSB +#define ELF_ARCH_MACHINE EM_ARM + +struct xc_core_arch_context { + /* nothing */ +}; + +#define xc_core_arch_context_init(arch_ctxt) do {} while (0) +#define xc_core_arch_context_free(arch_ctxt) do {} while (0) +#define xc_core_arch_context_get(arch_ctxt, ctxt, xch, domid) \ + (0) +#define xc_core_arch_context_dump(xch, arch_ctxt, args, dump_rtn) (0) + +int +xc_core_arch_gpfn_may_present(struct xc_core_arch_context *arch_ctxt, + unsigned long pfn); +static inline int +xc_core_arch_context_get_shdr(xc_interface *xch, + struct xc_core_arch_context *arch_ctxt, + struct xc_core_section_headers *sheaders, + struct xc_core_strtab *strtab, + uint64_t *filesz, uint64_t offset) +{ + *filesz = 0; + return 0; +} + +#endif /* XC_CORE_ARM_H */ + +/* + * Local variables: + * mode: C + * c-set-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/tools/libxc/xenctrl.h b/tools/libxc/xenctrl.h index 73d24e5..29c13a7 100644 --- a/tools/libxc/xenctrl.h +++ b/tools/libxc/xenctrl.h @@ -83,6 +83,10 @@ #define xen_mb() asm volatile ("mf" ::: "memory") #define xen_rmb() asm volatile ("mf" ::: "memory") #define xen_wmb() asm volatile ("mf" ::: "memory") +#elif defined(__arm__) +#define xen_mb() asm volatile ("dmb" : : : "memory") +#define xen_rmb() asm volatile ("dmb" : : : "memory") +#define xen_wmb() asm volatile ("dmb" : : : "memory") #else #error "Define barriers" #endif -- 1.7.2.5
Introduce an empty implementation of the arch specific ARM functions in xc_dom_arm.c. Provide empty implementations of xc_domain_save and xc_domain_restore when CONFIG_MIGRATE is not set. Move xc_hvm_build.c to xc_hvm_build_x86.c because the implementation is x86 specific, introduce xc_hvm_build_arm.c with empty stubs. Changes in v3: - rename xc_hvm_build.c to xc_hvm_build_x86.c; - remove xc_nohvm, introduce xc_hvm_build_arm.c instead; Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> --- tools/libxc/Makefile | 12 +- tools/libxc/xc_dom_arm.c | 50 ++++ tools/libxc/xc_hvm_build.c | 511 ---------------------------------------- tools/libxc/xc_hvm_build_arm.c | 61 +++++ tools/libxc/xc_hvm_build_x86.c | 511 ++++++++++++++++++++++++++++++++++++++++ tools/libxc/xc_nomigrate.c | 53 ++++ 6 files changed, 684 insertions(+), 514 deletions(-) create mode 100644 tools/libxc/xc_dom_arm.c delete mode 100644 tools/libxc/xc_hvm_build.c create mode 100644 tools/libxc/xc_hvm_build_arm.c create mode 100644 tools/libxc/xc_hvm_build_x86.c create mode 100644 tools/libxc/xc_nomigrate.c diff --git a/tools/libxc/Makefile b/tools/libxc/Makefile index f2e1ba7..02d39a3 100644 --- a/tools/libxc/Makefile +++ b/tools/libxc/Makefile @@ -42,9 +42,12 @@ CTRL_SRCS-$(CONFIG_MiniOS) += xc_minios.c GUEST_SRCS-y : GUEST_SRCS-y += xg_private.c xc_suspend.c -GUEST_SRCS-$(CONFIG_MIGRATE) += xc_domain_restore.c xc_domain_save.c -GUEST_SRCS-$(CONFIG_MIGRATE) += xc_offline_page.c xc_compression.c -GUEST_SRCS-$(CONFIG_HVM) += xc_hvm_build.c +ifeq ($(CONFIG_MIGRATE),y) +GUEST_SRCS-y += xc_domain_restore.c xc_domain_save.c +GUEST_SRCS-y += xc_offline_page.c xc_compression.c +else +GUEST_SRCS-y += xc_nomigrate.c +endif vpath %.c ../../xen/common/libelf CFLAGS += -I../../xen/common/libelf @@ -61,7 +64,10 @@ GUEST_SRCS-y += xc_dom_compat_linux.c GUEST_SRCS-$(CONFIG_X86) += xc_dom_x86.c GUEST_SRCS-$(CONFIG_X86) += xc_cpuid_x86.c +GUEST_SRCS-$(CONFIG_X86) += xc_hvm_build_x86.c GUEST_SRCS-$(CONFIG_IA64) += xc_dom_ia64.c +GUEST_SRCS-$(CONFIG_ARM) += xc_dom_arm.c +GUEST_SRCS-$(CONFIG_ARM) += xc_hvm_build_arm.c OSDEP_SRCS-y += xenctrl_osdep_ENOSYS.c diff --git a/tools/libxc/xc_dom_arm.c b/tools/libxc/xc_dom_arm.c new file mode 100644 index 0000000..122d0e8 --- /dev/null +++ b/tools/libxc/xc_dom_arm.c @@ -0,0 +1,50 @@ +/* + * Xen domain builder -- ARM + * + * 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 + * + * Copyright (c) 2011, Citrix Systems + */ +#include <inttypes.h> +#include <xen/xen.h> +#include "xg_private.h" +#include "xc_dom.h" + +int arch_setup_meminit(struct xc_dom_image *dom) +{ + errno = ENOSYS; + return -1; +} + +int arch_setup_bootearly(struct xc_dom_image *dom) +{ + DOMPRINTF("%s: doing nothing", __FUNCTION__); + return 0; +} + +int arch_setup_bootlate(struct xc_dom_image *dom) +{ + DOMPRINTF("%s: doing nothing", __FUNCTION__); + return 0; +} +/* + * Local variables: + * mode: C + * c-set-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/tools/libxc/xc_hvm_build.c b/tools/libxc/xc_hvm_build.c deleted file mode 100644 index 1fa5658..0000000 --- a/tools/libxc/xc_hvm_build.c +++ /dev/null @@ -1,511 +0,0 @@ -/****************************************************************************** - * xc_hvm_build.c - * - * 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 <stddef.h> -#include <inttypes.h> -#include <stdlib.h> -#include <unistd.h> -#include <zlib.h> - -#include "xg_private.h" -#include "xc_private.h" - -#include <xen/foreign/x86_32.h> -#include <xen/foreign/x86_64.h> -#include <xen/hvm/hvm_info_table.h> -#include <xen/hvm/params.h> -#include <xen/hvm/e820.h> - -#include <xen/libelf/libelf.h> - -#define SUPERPAGE_2MB_SHIFT 9 -#define SUPERPAGE_2MB_NR_PFNS (1UL << SUPERPAGE_2MB_SHIFT) -#define SUPERPAGE_1GB_SHIFT 18 -#define SUPERPAGE_1GB_NR_PFNS (1UL << SUPERPAGE_1GB_SHIFT) - -#define SPECIALPAGE_BUFIOREQ 0 -#define SPECIALPAGE_XENSTORE 1 -#define SPECIALPAGE_IOREQ 2 -#define SPECIALPAGE_IDENT_PT 3 -#define SPECIALPAGE_CONSOLE 4 -#define NR_SPECIAL_PAGES 5 -#define special_pfn(x) (0xff000u - NR_SPECIAL_PAGES + (x)) - -static void build_hvm_info(void *hvm_info_page, uint64_t mem_size) -{ - struct hvm_info_table *hvm_info = (struct hvm_info_table *) - (((unsigned char *)hvm_info_page) + HVM_INFO_OFFSET); - uint64_t lowmem_end = mem_size, highmem_end = 0; - uint8_t sum; - int i; - - if ( lowmem_end > HVM_BELOW_4G_RAM_END ) - { - highmem_end = lowmem_end + (1ull<<32) - HVM_BELOW_4G_RAM_END; - lowmem_end = HVM_BELOW_4G_RAM_END; - } - - memset(hvm_info_page, 0, PAGE_SIZE); - - /* Fill in the header. */ - strncpy(hvm_info->signature, "HVM INFO", 8); - hvm_info->length = sizeof(struct hvm_info_table); - - /* Sensible defaults: these can be overridden by the caller. */ - hvm_info->apic_mode = 1; - hvm_info->nr_vcpus = 1; - memset(hvm_info->vcpu_online, 0xff, sizeof(hvm_info->vcpu_online)); - - /* Memory parameters. */ - hvm_info->low_mem_pgend = lowmem_end >> PAGE_SHIFT; - hvm_info->high_mem_pgend = highmem_end >> PAGE_SHIFT; - hvm_info->reserved_mem_pgstart = special_pfn(0); - - /* Finish with the checksum. */ - for ( i = 0, sum = 0; i < hvm_info->length; i++ ) - sum += ((uint8_t *)hvm_info)[i]; - hvm_info->checksum = -sum; -} - -static int loadelfimage( - xc_interface *xch, - struct elf_binary *elf, uint32_t dom, unsigned long *parray) -{ - privcmd_mmap_entry_t *entries = NULL; - unsigned long pfn_start = elf->pstart >> PAGE_SHIFT; - unsigned long pfn_end = (elf->pend + PAGE_SIZE - 1) >> PAGE_SHIFT; - size_t pages = pfn_end - pfn_start; - int i, rc = -1; - - /* Map address space for initial elf image. */ - entries = calloc(pages, sizeof(privcmd_mmap_entry_t)); - if ( entries == NULL ) - goto err; - - for ( i = 0; i < pages; i++ ) - entries[i].mfn = parray[(elf->pstart >> PAGE_SHIFT) + i]; - - elf->dest = xc_map_foreign_ranges( - xch, dom, pages << PAGE_SHIFT, PROT_READ | PROT_WRITE, 1 << PAGE_SHIFT, - entries, pages); - if ( elf->dest == NULL ) - goto err; - - elf->dest += elf->pstart & (PAGE_SIZE - 1); - - /* Load the initial elf image. */ - rc = elf_load_binary(elf); - if ( rc < 0 ) - PERROR("Failed to load elf binary\n"); - - munmap(elf->dest, pages << PAGE_SHIFT); - elf->dest = NULL; - - err: - free(entries); - - return rc; -} - -/* - * Check whether there exists mmio hole in the specified memory range. - * Returns 1 if exists, else returns 0. - */ -static int check_mmio_hole(uint64_t start, uint64_t memsize) -{ - if ( start + memsize <= HVM_BELOW_4G_MMIO_START || - start >= HVM_BELOW_4G_MMIO_START + HVM_BELOW_4G_MMIO_LENGTH ) - return 0; - else - return 1; -} - -static int setup_guest(xc_interface *xch, - uint32_t dom, int memsize, int target, - char *image, unsigned long image_size) -{ - xen_pfn_t *page_array = NULL; - unsigned long i, nr_pages = (unsigned long)memsize << (20 - PAGE_SHIFT); - unsigned long target_pages = (unsigned long)target << (20 - PAGE_SHIFT); - unsigned long entry_eip, cur_pages, cur_pfn; - void *hvm_info_page; - uint32_t *ident_pt; - struct elf_binary elf; - uint64_t v_start, v_end; - int rc; - xen_capabilities_info_t caps; - unsigned long stat_normal_pages = 0, stat_2mb_pages = 0, - stat_1gb_pages = 0; - int pod_mode = 0; - - /* An HVM guest must be initialised with at least 2MB memory. */ - if ( memsize < 2 || target < 2 ) - goto error_out; - - if ( memsize > target ) - pod_mode = 1; - - memset(&elf, 0, sizeof(elf)); - if ( elf_init(&elf, image, image_size) != 0 ) - goto error_out; - - xc_elf_set_logfile(xch, &elf, 1); - - elf_parse_binary(&elf); - v_start = 0; - v_end = (unsigned long long)memsize << 20; - - if ( xc_version(xch, XENVER_capabilities, &caps) != 0 ) - { - PERROR("Could not get Xen capabilities"); - goto error_out; - } - - IPRINTF("VIRTUAL MEMORY ARRANGEMENT:\n" - " Loader: %016"PRIx64"->%016"PRIx64"\n" - " TOTAL: %016"PRIx64"->%016"PRIx64"\n" - " ENTRY ADDRESS: %016"PRIx64"\n", - elf.pstart, elf.pend, - v_start, v_end, - elf_uval(&elf, elf.ehdr, e_entry)); - - if ( (page_array = malloc(nr_pages * sizeof(xen_pfn_t))) == NULL ) - { - PERROR("Could not allocate memory."); - goto error_out; - } - - for ( i = 0; i < nr_pages; i++ ) - page_array[i] = i; - for ( i = HVM_BELOW_4G_RAM_END >> PAGE_SHIFT; i < nr_pages; i++ ) - page_array[i] += HVM_BELOW_4G_MMIO_LENGTH >> PAGE_SHIFT; - - /* - * Allocate memory for HVM guest, skipping VGA hole 0xA0000-0xC0000. - * - * We attempt to allocate 1GB pages if possible. It falls back on 2MB - * pages if 1GB allocation fails. 4KB pages will be used eventually if - * both fail. - * - * Under 2MB mode, we allocate pages in batches of no more than 8MB to - * ensure that we can be preempted and hence dom0 remains responsive. - */ - rc = xc_domain_populate_physmap_exact( - xch, dom, 0xa0, 0, 0, &page_array[0x00]); - cur_pages = 0xc0; - stat_normal_pages = 0xc0; - while ( (rc == 0) && (nr_pages > cur_pages) ) - { - /* Clip count to maximum 1GB extent. */ - unsigned long count = nr_pages - cur_pages; - unsigned long max_pages = SUPERPAGE_1GB_NR_PFNS; - - if ( count > max_pages ) - count = max_pages; - - cur_pfn = page_array[cur_pages]; - - /* Take care the corner cases of super page tails */ - if ( ((cur_pfn & (SUPERPAGE_1GB_NR_PFNS-1)) != 0) && - (count > (-cur_pfn & (SUPERPAGE_1GB_NR_PFNS-1))) ) - count = -cur_pfn & (SUPERPAGE_1GB_NR_PFNS-1); - else if ( ((count & (SUPERPAGE_1GB_NR_PFNS-1)) != 0) && - (count > SUPERPAGE_1GB_NR_PFNS) ) - count &= ~(SUPERPAGE_1GB_NR_PFNS - 1); - - /* Attemp to allocate 1GB super page. Because in each pass we only - * allocate at most 1GB, we don''t have to clip super page boundaries. - */ - if ( ((count | cur_pfn) & (SUPERPAGE_1GB_NR_PFNS - 1)) == 0 && - /* Check if there exists MMIO hole in the 1GB memory range */ - !check_mmio_hole(cur_pfn << PAGE_SHIFT, - SUPERPAGE_1GB_NR_PFNS << PAGE_SHIFT) ) - { - long done; - unsigned long nr_extents = count >> SUPERPAGE_1GB_SHIFT; - xen_pfn_t sp_extents[nr_extents]; - - for ( i = 0; i < nr_extents; i++ ) - sp_extents[i] = page_array[cur_pages+(i<<SUPERPAGE_1GB_SHIFT)]; - - done = xc_domain_populate_physmap(xch, dom, nr_extents, SUPERPAGE_1GB_SHIFT, - pod_mode ? XENMEMF_populate_on_demand : 0, - sp_extents); - - if ( done > 0 ) - { - stat_1gb_pages += done; - done <<= SUPERPAGE_1GB_SHIFT; - cur_pages += done; - count -= done; - } - } - - if ( count != 0 ) - { - /* Clip count to maximum 8MB extent. */ - max_pages = SUPERPAGE_2MB_NR_PFNS * 4; - if ( count > max_pages ) - count = max_pages; - - /* Clip partial superpage extents to superpage boundaries. */ - if ( ((cur_pfn & (SUPERPAGE_2MB_NR_PFNS-1)) != 0) && - (count > (-cur_pfn & (SUPERPAGE_2MB_NR_PFNS-1))) ) - count = -cur_pfn & (SUPERPAGE_2MB_NR_PFNS-1); - else if ( ((count & (SUPERPAGE_2MB_NR_PFNS-1)) != 0) && - (count > SUPERPAGE_2MB_NR_PFNS) ) - count &= ~(SUPERPAGE_2MB_NR_PFNS - 1); /* clip non-s.p. tail */ - - /* Attempt to allocate superpage extents. */ - if ( ((count | cur_pfn) & (SUPERPAGE_2MB_NR_PFNS - 1)) == 0 ) - { - long done; - unsigned long nr_extents = count >> SUPERPAGE_2MB_SHIFT; - xen_pfn_t sp_extents[nr_extents]; - - for ( i = 0; i < nr_extents; i++ ) - sp_extents[i] = page_array[cur_pages+(i<<SUPERPAGE_2MB_SHIFT)]; - - done = xc_domain_populate_physmap(xch, dom, nr_extents, SUPERPAGE_2MB_SHIFT, - pod_mode ? XENMEMF_populate_on_demand : 0, - sp_extents); - - if ( done > 0 ) - { - stat_2mb_pages += done; - done <<= SUPERPAGE_2MB_SHIFT; - cur_pages += done; - count -= done; - } - } - } - - /* Fall back to 4kB extents. */ - if ( count != 0 ) - { - rc = xc_domain_populate_physmap_exact( - xch, dom, count, 0, 0, &page_array[cur_pages]); - cur_pages += count; - stat_normal_pages += count; - } - } - - /* Subtract 0x20 from target_pages for the VGA "hole". Xen will - * adjust the PoD cache size so that domain tot_pages will be - * target_pages - 0x20 after this call. */ - if ( pod_mode ) - rc = xc_domain_set_pod_target(xch, dom, target_pages - 0x20, - NULL, NULL, NULL); - - if ( rc != 0 ) - { - PERROR("Could not allocate memory for HVM guest."); - goto error_out; - } - - IPRINTF("PHYSICAL MEMORY ALLOCATION:\n" - " 4KB PAGES: 0x%016lx\n" - " 2MB PAGES: 0x%016lx\n" - " 1GB PAGES: 0x%016lx\n", - stat_normal_pages, stat_2mb_pages, stat_1gb_pages); - - if ( loadelfimage(xch, &elf, dom, page_array) != 0 ) - goto error_out; - - if ( (hvm_info_page = xc_map_foreign_range( - xch, dom, PAGE_SIZE, PROT_READ | PROT_WRITE, - HVM_INFO_PFN)) == NULL ) - goto error_out; - build_hvm_info(hvm_info_page, v_end); - munmap(hvm_info_page, PAGE_SIZE); - - /* Allocate and clear special pages. */ - for ( i = 0; i < NR_SPECIAL_PAGES; i++ ) - { - xen_pfn_t pfn = special_pfn(i); - rc = xc_domain_populate_physmap_exact(xch, dom, 1, 0, 0, &pfn); - if ( rc != 0 ) - { - PERROR("Could not allocate %d''th special page.", i); - goto error_out; - } - if ( xc_clear_domain_page(xch, dom, special_pfn(i)) ) - goto error_out; - } - - xc_set_hvm_param(xch, dom, HVM_PARAM_STORE_PFN, - special_pfn(SPECIALPAGE_XENSTORE)); - xc_set_hvm_param(xch, dom, HVM_PARAM_BUFIOREQ_PFN, - special_pfn(SPECIALPAGE_BUFIOREQ)); - xc_set_hvm_param(xch, dom, HVM_PARAM_IOREQ_PFN, - special_pfn(SPECIALPAGE_IOREQ)); - xc_set_hvm_param(xch, dom, HVM_PARAM_CONSOLE_PFN, - special_pfn(SPECIALPAGE_CONSOLE)); - - /* - * Identity-map page table is required for running with CR0.PG=0 when - * using Intel EPT. Create a 32-bit non-PAE page directory of superpages. - */ - if ( (ident_pt = xc_map_foreign_range( - xch, dom, PAGE_SIZE, PROT_READ | PROT_WRITE, - special_pfn(SPECIALPAGE_IDENT_PT))) == NULL ) - goto error_out; - for ( i = 0; i < PAGE_SIZE / sizeof(*ident_pt); i++ ) - ident_pt[i] = ((i << 22) | _PAGE_PRESENT | _PAGE_RW | _PAGE_USER | - _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE); - munmap(ident_pt, PAGE_SIZE); - xc_set_hvm_param(xch, dom, HVM_PARAM_IDENT_PT, - special_pfn(SPECIALPAGE_IDENT_PT) << PAGE_SHIFT); - - /* Insert JMP <rel32> instruction at address 0x0 to reach entry point. */ - entry_eip = elf_uval(&elf, elf.ehdr, e_entry); - if ( entry_eip != 0 ) - { - char *page0 = xc_map_foreign_range( - xch, dom, PAGE_SIZE, PROT_READ | PROT_WRITE, 0); - if ( page0 == NULL ) - goto error_out; - page0[0] = 0xe9; - *(uint32_t *)&page0[1] = entry_eip - 5; - munmap(page0, PAGE_SIZE); - } - - free(page_array); - return 0; - - error_out: - free(page_array); - return -1; -} - -static int xc_hvm_build_internal(xc_interface *xch, - uint32_t domid, - int memsize, - int target, - char *image, - unsigned long image_size) -{ - if ( (image == NULL) || (image_size == 0) ) - { - ERROR("Image required"); - return -1; - } - - return setup_guest(xch, domid, memsize, target, image, image_size); -} - -/* xc_hvm_build: - * Create a domain for a virtualized Linux, using files/filenames. - */ -int xc_hvm_build(xc_interface *xch, - uint32_t domid, - int memsize, - const char *image_name) -{ - char *image; - int sts; - unsigned long image_size; - - if ( (image_name == NULL) || - ((image = xc_read_image(xch, image_name, &image_size)) == NULL) ) - return -1; - - sts = xc_hvm_build_internal(xch, domid, memsize, memsize, image, image_size); - - free(image); - - return sts; -} - -/* xc_hvm_build_target_mem: - * Create a domain for a pre-ballooned virtualized Linux, using - * files/filenames. If target < memsize, domain is created with - * memsize pages marked populate-on-demand, - * calculating pod cache size based on target. - * If target == memsize, pages are populated normally. - */ -int xc_hvm_build_target_mem(xc_interface *xch, - uint32_t domid, - int memsize, - int target, - const char *image_name) -{ - char *image; - int sts; - unsigned long image_size; - - if ( (image_name == NULL) || - ((image = xc_read_image(xch, image_name, &image_size)) == NULL) ) - return -1; - - sts = xc_hvm_build_internal(xch, domid, memsize, target, image, image_size); - - free(image); - - return sts; -} - -/* xc_hvm_build_mem: - * Create a domain for a virtualized Linux, using memory buffers. - */ -int xc_hvm_build_mem(xc_interface *xch, - uint32_t domid, - int memsize, - const char *image_buffer, - unsigned long image_size) -{ - int sts; - unsigned long img_len; - char *img; - - /* Validate that there is a kernel buffer */ - - if ( (image_buffer == NULL) || (image_size == 0) ) - { - ERROR("kernel image buffer not present"); - return -1; - } - - img = xc_inflate_buffer(xch, image_buffer, image_size, &img_len); - if ( img == NULL ) - { - ERROR("unable to inflate ram disk buffer"); - return -1; - } - - sts = xc_hvm_build_internal(xch, domid, memsize, memsize, - img, img_len); - - /* xc_inflate_buffer may return the original buffer pointer (for - for already inflated buffers), so exercise some care in freeing */ - - if ( (img != NULL) && (img != image_buffer) ) - free(img); - - return sts; -} - -/* - * Local variables: - * mode: C - * c-set-style: "BSD" - * c-basic-offset: 4 - * tab-width: 4 - * indent-tabs-mode: nil - * End: - */ diff --git a/tools/libxc/xc_hvm_build_arm.c b/tools/libxc/xc_hvm_build_arm.c new file mode 100644 index 0000000..010ebdb --- /dev/null +++ b/tools/libxc/xc_hvm_build_arm.c @@ -0,0 +1,61 @@ +/****************************************************************************** + * 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 + * + * Copyright (c) 2011, Citrix Systems + */ + +#include <inttypes.h> +#include <errno.h> +#include <xenctrl.h> +#include <xenguest.h> + +int xc_hvm_build(xc_interface *xch, + uint32_t domid, + int memsize, + const char *image_name) +{ + errno = ENOSYS; + return -1; +} + +int xc_hvm_build_target_mem(xc_interface *xch, + uint32_t domid, + int memsize, + int target, + const char *image_name) +{ + errno = ENOSYS; + return -1; +} + +int xc_hvm_build_mem(xc_interface *xch, + uint32_t domid, + int memsize, + const char *image_buffer, + unsigned long image_size) +{ + errno = ENOSYS; + return -1; +} + +/* + * Local variables: + * mode: C + * c-set-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/tools/libxc/xc_hvm_build_x86.c b/tools/libxc/xc_hvm_build_x86.c new file mode 100644 index 0000000..1fa5658 --- /dev/null +++ b/tools/libxc/xc_hvm_build_x86.c @@ -0,0 +1,511 @@ +/****************************************************************************** + * xc_hvm_build.c + * + * 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 <stddef.h> +#include <inttypes.h> +#include <stdlib.h> +#include <unistd.h> +#include <zlib.h> + +#include "xg_private.h" +#include "xc_private.h" + +#include <xen/foreign/x86_32.h> +#include <xen/foreign/x86_64.h> +#include <xen/hvm/hvm_info_table.h> +#include <xen/hvm/params.h> +#include <xen/hvm/e820.h> + +#include <xen/libelf/libelf.h> + +#define SUPERPAGE_2MB_SHIFT 9 +#define SUPERPAGE_2MB_NR_PFNS (1UL << SUPERPAGE_2MB_SHIFT) +#define SUPERPAGE_1GB_SHIFT 18 +#define SUPERPAGE_1GB_NR_PFNS (1UL << SUPERPAGE_1GB_SHIFT) + +#define SPECIALPAGE_BUFIOREQ 0 +#define SPECIALPAGE_XENSTORE 1 +#define SPECIALPAGE_IOREQ 2 +#define SPECIALPAGE_IDENT_PT 3 +#define SPECIALPAGE_CONSOLE 4 +#define NR_SPECIAL_PAGES 5 +#define special_pfn(x) (0xff000u - NR_SPECIAL_PAGES + (x)) + +static void build_hvm_info(void *hvm_info_page, uint64_t mem_size) +{ + struct hvm_info_table *hvm_info = (struct hvm_info_table *) + (((unsigned char *)hvm_info_page) + HVM_INFO_OFFSET); + uint64_t lowmem_end = mem_size, highmem_end = 0; + uint8_t sum; + int i; + + if ( lowmem_end > HVM_BELOW_4G_RAM_END ) + { + highmem_end = lowmem_end + (1ull<<32) - HVM_BELOW_4G_RAM_END; + lowmem_end = HVM_BELOW_4G_RAM_END; + } + + memset(hvm_info_page, 0, PAGE_SIZE); + + /* Fill in the header. */ + strncpy(hvm_info->signature, "HVM INFO", 8); + hvm_info->length = sizeof(struct hvm_info_table); + + /* Sensible defaults: these can be overridden by the caller. */ + hvm_info->apic_mode = 1; + hvm_info->nr_vcpus = 1; + memset(hvm_info->vcpu_online, 0xff, sizeof(hvm_info->vcpu_online)); + + /* Memory parameters. */ + hvm_info->low_mem_pgend = lowmem_end >> PAGE_SHIFT; + hvm_info->high_mem_pgend = highmem_end >> PAGE_SHIFT; + hvm_info->reserved_mem_pgstart = special_pfn(0); + + /* Finish with the checksum. */ + for ( i = 0, sum = 0; i < hvm_info->length; i++ ) + sum += ((uint8_t *)hvm_info)[i]; + hvm_info->checksum = -sum; +} + +static int loadelfimage( + xc_interface *xch, + struct elf_binary *elf, uint32_t dom, unsigned long *parray) +{ + privcmd_mmap_entry_t *entries = NULL; + unsigned long pfn_start = elf->pstart >> PAGE_SHIFT; + unsigned long pfn_end = (elf->pend + PAGE_SIZE - 1) >> PAGE_SHIFT; + size_t pages = pfn_end - pfn_start; + int i, rc = -1; + + /* Map address space for initial elf image. */ + entries = calloc(pages, sizeof(privcmd_mmap_entry_t)); + if ( entries == NULL ) + goto err; + + for ( i = 0; i < pages; i++ ) + entries[i].mfn = parray[(elf->pstart >> PAGE_SHIFT) + i]; + + elf->dest = xc_map_foreign_ranges( + xch, dom, pages << PAGE_SHIFT, PROT_READ | PROT_WRITE, 1 << PAGE_SHIFT, + entries, pages); + if ( elf->dest == NULL ) + goto err; + + elf->dest += elf->pstart & (PAGE_SIZE - 1); + + /* Load the initial elf image. */ + rc = elf_load_binary(elf); + if ( rc < 0 ) + PERROR("Failed to load elf binary\n"); + + munmap(elf->dest, pages << PAGE_SHIFT); + elf->dest = NULL; + + err: + free(entries); + + return rc; +} + +/* + * Check whether there exists mmio hole in the specified memory range. + * Returns 1 if exists, else returns 0. + */ +static int check_mmio_hole(uint64_t start, uint64_t memsize) +{ + if ( start + memsize <= HVM_BELOW_4G_MMIO_START || + start >= HVM_BELOW_4G_MMIO_START + HVM_BELOW_4G_MMIO_LENGTH ) + return 0; + else + return 1; +} + +static int setup_guest(xc_interface *xch, + uint32_t dom, int memsize, int target, + char *image, unsigned long image_size) +{ + xen_pfn_t *page_array = NULL; + unsigned long i, nr_pages = (unsigned long)memsize << (20 - PAGE_SHIFT); + unsigned long target_pages = (unsigned long)target << (20 - PAGE_SHIFT); + unsigned long entry_eip, cur_pages, cur_pfn; + void *hvm_info_page; + uint32_t *ident_pt; + struct elf_binary elf; + uint64_t v_start, v_end; + int rc; + xen_capabilities_info_t caps; + unsigned long stat_normal_pages = 0, stat_2mb_pages = 0, + stat_1gb_pages = 0; + int pod_mode = 0; + + /* An HVM guest must be initialised with at least 2MB memory. */ + if ( memsize < 2 || target < 2 ) + goto error_out; + + if ( memsize > target ) + pod_mode = 1; + + memset(&elf, 0, sizeof(elf)); + if ( elf_init(&elf, image, image_size) != 0 ) + goto error_out; + + xc_elf_set_logfile(xch, &elf, 1); + + elf_parse_binary(&elf); + v_start = 0; + v_end = (unsigned long long)memsize << 20; + + if ( xc_version(xch, XENVER_capabilities, &caps) != 0 ) + { + PERROR("Could not get Xen capabilities"); + goto error_out; + } + + IPRINTF("VIRTUAL MEMORY ARRANGEMENT:\n" + " Loader: %016"PRIx64"->%016"PRIx64"\n" + " TOTAL: %016"PRIx64"->%016"PRIx64"\n" + " ENTRY ADDRESS: %016"PRIx64"\n", + elf.pstart, elf.pend, + v_start, v_end, + elf_uval(&elf, elf.ehdr, e_entry)); + + if ( (page_array = malloc(nr_pages * sizeof(xen_pfn_t))) == NULL ) + { + PERROR("Could not allocate memory."); + goto error_out; + } + + for ( i = 0; i < nr_pages; i++ ) + page_array[i] = i; + for ( i = HVM_BELOW_4G_RAM_END >> PAGE_SHIFT; i < nr_pages; i++ ) + page_array[i] += HVM_BELOW_4G_MMIO_LENGTH >> PAGE_SHIFT; + + /* + * Allocate memory for HVM guest, skipping VGA hole 0xA0000-0xC0000. + * + * We attempt to allocate 1GB pages if possible. It falls back on 2MB + * pages if 1GB allocation fails. 4KB pages will be used eventually if + * both fail. + * + * Under 2MB mode, we allocate pages in batches of no more than 8MB to + * ensure that we can be preempted and hence dom0 remains responsive. + */ + rc = xc_domain_populate_physmap_exact( + xch, dom, 0xa0, 0, 0, &page_array[0x00]); + cur_pages = 0xc0; + stat_normal_pages = 0xc0; + while ( (rc == 0) && (nr_pages > cur_pages) ) + { + /* Clip count to maximum 1GB extent. */ + unsigned long count = nr_pages - cur_pages; + unsigned long max_pages = SUPERPAGE_1GB_NR_PFNS; + + if ( count > max_pages ) + count = max_pages; + + cur_pfn = page_array[cur_pages]; + + /* Take care the corner cases of super page tails */ + if ( ((cur_pfn & (SUPERPAGE_1GB_NR_PFNS-1)) != 0) && + (count > (-cur_pfn & (SUPERPAGE_1GB_NR_PFNS-1))) ) + count = -cur_pfn & (SUPERPAGE_1GB_NR_PFNS-1); + else if ( ((count & (SUPERPAGE_1GB_NR_PFNS-1)) != 0) && + (count > SUPERPAGE_1GB_NR_PFNS) ) + count &= ~(SUPERPAGE_1GB_NR_PFNS - 1); + + /* Attemp to allocate 1GB super page. Because in each pass we only + * allocate at most 1GB, we don''t have to clip super page boundaries. + */ + if ( ((count | cur_pfn) & (SUPERPAGE_1GB_NR_PFNS - 1)) == 0 && + /* Check if there exists MMIO hole in the 1GB memory range */ + !check_mmio_hole(cur_pfn << PAGE_SHIFT, + SUPERPAGE_1GB_NR_PFNS << PAGE_SHIFT) ) + { + long done; + unsigned long nr_extents = count >> SUPERPAGE_1GB_SHIFT; + xen_pfn_t sp_extents[nr_extents]; + + for ( i = 0; i < nr_extents; i++ ) + sp_extents[i] = page_array[cur_pages+(i<<SUPERPAGE_1GB_SHIFT)]; + + done = xc_domain_populate_physmap(xch, dom, nr_extents, SUPERPAGE_1GB_SHIFT, + pod_mode ? XENMEMF_populate_on_demand : 0, + sp_extents); + + if ( done > 0 ) + { + stat_1gb_pages += done; + done <<= SUPERPAGE_1GB_SHIFT; + cur_pages += done; + count -= done; + } + } + + if ( count != 0 ) + { + /* Clip count to maximum 8MB extent. */ + max_pages = SUPERPAGE_2MB_NR_PFNS * 4; + if ( count > max_pages ) + count = max_pages; + + /* Clip partial superpage extents to superpage boundaries. */ + if ( ((cur_pfn & (SUPERPAGE_2MB_NR_PFNS-1)) != 0) && + (count > (-cur_pfn & (SUPERPAGE_2MB_NR_PFNS-1))) ) + count = -cur_pfn & (SUPERPAGE_2MB_NR_PFNS-1); + else if ( ((count & (SUPERPAGE_2MB_NR_PFNS-1)) != 0) && + (count > SUPERPAGE_2MB_NR_PFNS) ) + count &= ~(SUPERPAGE_2MB_NR_PFNS - 1); /* clip non-s.p. tail */ + + /* Attempt to allocate superpage extents. */ + if ( ((count | cur_pfn) & (SUPERPAGE_2MB_NR_PFNS - 1)) == 0 ) + { + long done; + unsigned long nr_extents = count >> SUPERPAGE_2MB_SHIFT; + xen_pfn_t sp_extents[nr_extents]; + + for ( i = 0; i < nr_extents; i++ ) + sp_extents[i] = page_array[cur_pages+(i<<SUPERPAGE_2MB_SHIFT)]; + + done = xc_domain_populate_physmap(xch, dom, nr_extents, SUPERPAGE_2MB_SHIFT, + pod_mode ? XENMEMF_populate_on_demand : 0, + sp_extents); + + if ( done > 0 ) + { + stat_2mb_pages += done; + done <<= SUPERPAGE_2MB_SHIFT; + cur_pages += done; + count -= done; + } + } + } + + /* Fall back to 4kB extents. */ + if ( count != 0 ) + { + rc = xc_domain_populate_physmap_exact( + xch, dom, count, 0, 0, &page_array[cur_pages]); + cur_pages += count; + stat_normal_pages += count; + } + } + + /* Subtract 0x20 from target_pages for the VGA "hole". Xen will + * adjust the PoD cache size so that domain tot_pages will be + * target_pages - 0x20 after this call. */ + if ( pod_mode ) + rc = xc_domain_set_pod_target(xch, dom, target_pages - 0x20, + NULL, NULL, NULL); + + if ( rc != 0 ) + { + PERROR("Could not allocate memory for HVM guest."); + goto error_out; + } + + IPRINTF("PHYSICAL MEMORY ALLOCATION:\n" + " 4KB PAGES: 0x%016lx\n" + " 2MB PAGES: 0x%016lx\n" + " 1GB PAGES: 0x%016lx\n", + stat_normal_pages, stat_2mb_pages, stat_1gb_pages); + + if ( loadelfimage(xch, &elf, dom, page_array) != 0 ) + goto error_out; + + if ( (hvm_info_page = xc_map_foreign_range( + xch, dom, PAGE_SIZE, PROT_READ | PROT_WRITE, + HVM_INFO_PFN)) == NULL ) + goto error_out; + build_hvm_info(hvm_info_page, v_end); + munmap(hvm_info_page, PAGE_SIZE); + + /* Allocate and clear special pages. */ + for ( i = 0; i < NR_SPECIAL_PAGES; i++ ) + { + xen_pfn_t pfn = special_pfn(i); + rc = xc_domain_populate_physmap_exact(xch, dom, 1, 0, 0, &pfn); + if ( rc != 0 ) + { + PERROR("Could not allocate %d''th special page.", i); + goto error_out; + } + if ( xc_clear_domain_page(xch, dom, special_pfn(i)) ) + goto error_out; + } + + xc_set_hvm_param(xch, dom, HVM_PARAM_STORE_PFN, + special_pfn(SPECIALPAGE_XENSTORE)); + xc_set_hvm_param(xch, dom, HVM_PARAM_BUFIOREQ_PFN, + special_pfn(SPECIALPAGE_BUFIOREQ)); + xc_set_hvm_param(xch, dom, HVM_PARAM_IOREQ_PFN, + special_pfn(SPECIALPAGE_IOREQ)); + xc_set_hvm_param(xch, dom, HVM_PARAM_CONSOLE_PFN, + special_pfn(SPECIALPAGE_CONSOLE)); + + /* + * Identity-map page table is required for running with CR0.PG=0 when + * using Intel EPT. Create a 32-bit non-PAE page directory of superpages. + */ + if ( (ident_pt = xc_map_foreign_range( + xch, dom, PAGE_SIZE, PROT_READ | PROT_WRITE, + special_pfn(SPECIALPAGE_IDENT_PT))) == NULL ) + goto error_out; + for ( i = 0; i < PAGE_SIZE / sizeof(*ident_pt); i++ ) + ident_pt[i] = ((i << 22) | _PAGE_PRESENT | _PAGE_RW | _PAGE_USER | + _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE); + munmap(ident_pt, PAGE_SIZE); + xc_set_hvm_param(xch, dom, HVM_PARAM_IDENT_PT, + special_pfn(SPECIALPAGE_IDENT_PT) << PAGE_SHIFT); + + /* Insert JMP <rel32> instruction at address 0x0 to reach entry point. */ + entry_eip = elf_uval(&elf, elf.ehdr, e_entry); + if ( entry_eip != 0 ) + { + char *page0 = xc_map_foreign_range( + xch, dom, PAGE_SIZE, PROT_READ | PROT_WRITE, 0); + if ( page0 == NULL ) + goto error_out; + page0[0] = 0xe9; + *(uint32_t *)&page0[1] = entry_eip - 5; + munmap(page0, PAGE_SIZE); + } + + free(page_array); + return 0; + + error_out: + free(page_array); + return -1; +} + +static int xc_hvm_build_internal(xc_interface *xch, + uint32_t domid, + int memsize, + int target, + char *image, + unsigned long image_size) +{ + if ( (image == NULL) || (image_size == 0) ) + { + ERROR("Image required"); + return -1; + } + + return setup_guest(xch, domid, memsize, target, image, image_size); +} + +/* xc_hvm_build: + * Create a domain for a virtualized Linux, using files/filenames. + */ +int xc_hvm_build(xc_interface *xch, + uint32_t domid, + int memsize, + const char *image_name) +{ + char *image; + int sts; + unsigned long image_size; + + if ( (image_name == NULL) || + ((image = xc_read_image(xch, image_name, &image_size)) == NULL) ) + return -1; + + sts = xc_hvm_build_internal(xch, domid, memsize, memsize, image, image_size); + + free(image); + + return sts; +} + +/* xc_hvm_build_target_mem: + * Create a domain for a pre-ballooned virtualized Linux, using + * files/filenames. If target < memsize, domain is created with + * memsize pages marked populate-on-demand, + * calculating pod cache size based on target. + * If target == memsize, pages are populated normally. + */ +int xc_hvm_build_target_mem(xc_interface *xch, + uint32_t domid, + int memsize, + int target, + const char *image_name) +{ + char *image; + int sts; + unsigned long image_size; + + if ( (image_name == NULL) || + ((image = xc_read_image(xch, image_name, &image_size)) == NULL) ) + return -1; + + sts = xc_hvm_build_internal(xch, domid, memsize, target, image, image_size); + + free(image); + + return sts; +} + +/* xc_hvm_build_mem: + * Create a domain for a virtualized Linux, using memory buffers. + */ +int xc_hvm_build_mem(xc_interface *xch, + uint32_t domid, + int memsize, + const char *image_buffer, + unsigned long image_size) +{ + int sts; + unsigned long img_len; + char *img; + + /* Validate that there is a kernel buffer */ + + if ( (image_buffer == NULL) || (image_size == 0) ) + { + ERROR("kernel image buffer not present"); + return -1; + } + + img = xc_inflate_buffer(xch, image_buffer, image_size, &img_len); + if ( img == NULL ) + { + ERROR("unable to inflate ram disk buffer"); + return -1; + } + + sts = xc_hvm_build_internal(xch, domid, memsize, memsize, + img, img_len); + + /* xc_inflate_buffer may return the original buffer pointer (for + for already inflated buffers), so exercise some care in freeing */ + + if ( (img != NULL) && (img != image_buffer) ) + free(img); + + return sts; +} + +/* + * Local variables: + * mode: C + * c-set-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/tools/libxc/xc_nomigrate.c b/tools/libxc/xc_nomigrate.c new file mode 100644 index 0000000..e734d73 --- /dev/null +++ b/tools/libxc/xc_nomigrate.c @@ -0,0 +1,53 @@ +/****************************************************************************** + * 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 + * + * Copyright (c) 2011, Citrix Systems + */ + +#include <inttypes.h> +#include <errno.h> +#include <xenctrl.h> +#include <xenguest.h> + +int xc_domain_save(xc_interface *xch, int io_fd, uint32_t dom, uint32_t max_iters, + uint32_t max_factor, uint32_t flags, + struct save_callbacks* callbacks, int hvm, + unsigned long vm_generationid_addr) +{ + errno = ENOSYS; + return -1; +} + +int xc_domain_restore(xc_interface *xch, int io_fd, uint32_t dom, + unsigned int store_evtchn, unsigned long *store_mfn, + domid_t store_domid, unsigned int console_evtchn, + unsigned long *console_mfn, domid_t console_domid, + unsigned int hvm, unsigned int pae, int superpages, + int no_incr_generationid, + unsigned long *vm_generationid_addr) +{ + errno = ENOSYS; + return -1; +} + +/* + * Local variables: + * mode: C + * c-set-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ -- 1.7.2.5
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Acked-by: Ian Campbell <Ian.campbell@citrix.com> --- tools/memshr/bidir-hash.c | 31 +++++++++++++++++++++++++++++++ 1 files changed, 31 insertions(+), 0 deletions(-) diff --git a/tools/memshr/bidir-hash.c b/tools/memshr/bidir-hash.c index 6c0dc3d..45d473e 100644 --- a/tools/memshr/bidir-hash.c +++ b/tools/memshr/bidir-hash.c @@ -109,6 +109,37 @@ static void hash_resize(struct __hash *h); } while (0) static inline void atomic_inc(uint32_t *v) { ia64_fetchadd4_rel(v, 1); } static inline void atomic_dec(uint32_t *v) { ia64_fetchadd4_rel(v, -1); } +#elif defined(__arm__) +static inline void atomic_inc(uint32_t *v) +{ + unsigned long tmp; + int result; + + __asm__ __volatile__("@ atomic_add\n" +"1: ldrex %0, [%3]\n" +" add %0, %0, #1\n" +" strex %1, %0, [%3]\n" +" teq %1, #0\n" +" bne 1b" + : "=&r" (result), "=&r" (tmp), "+Qo" (*v) + : "r" (v) + : "cc"); +} +static inline void atomic_dec(uint32_t *v) +{ + unsigned long tmp; + int result; + + __asm__ __volatile__("@ atomic_sub\n" +"1: ldrex %0, [%3]\n" +" sub %0, %0, #1\n" +" strex %1, %0, [%3]\n" +" teq %1, #0\n" +" bne 1b" + : "=&r" (result), "=&r" (tmp), "+Qo" (*v) + : "r" (v) + : "cc"); +} #else /* __x86__ */ static inline void atomic_inc(uint32_t *v) { -- 1.7.2.5
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Acked-by: Ian Campbell <ian.campbell@citrix.com> --- tools/xentrace/xenctx.c | 12 ++++++++++++ 1 files changed, 12 insertions(+), 0 deletions(-) diff --git a/tools/xentrace/xenctx.c b/tools/xentrace/xenctx.c index a12cc21..530ef65 100644 --- a/tools/xentrace/xenctx.c +++ b/tools/xentrace/xenctx.c @@ -60,6 +60,12 @@ int disp_ar_regs; int disp_br_regs; int disp_bank_regs; int disp_tlb; + +#elif defined(__arm__) +#define NO_TRANSLATION +typedef uint64_t guest_word_t; +#define FMT_32B_WORD "%08llx" +#define FMT_64B_WORD "%016llx" #endif struct symbol { @@ -678,6 +684,12 @@ void print_ctx(vcpu_guest_context_any_t *ctx) print_tr(i, &tr->dtrs[i]); } } +#elif defined(__arm__) +static void print_ctx(vcpu_guest_context_any_t *ctx) +{ + /* XXX: properly implement this */ + print_symbol(0); +} #endif #ifndef NO_TRANSLATION -- 1.7.2.5
libxl_cpuid_destroy has been renamed to libxl_cpuid_dispose; also cpuid functions are only available on x86, so ifdef the new cpuid related function in libxl_json.c. Changes in v3: - move libxl_cpuid_policy_list_gen_json to libxl_(no)cpuid.c. Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Acked-by: Ian Campbell <ian.campbell@citrix.com> --- tools/libxl/Makefile | 1 + tools/libxl/libxl_cpuid.c | 60 +++++++++++++++++++++++++++++++++++++++++++ tools/libxl/libxl_json.c | 60 ------------------------------------------- tools/libxl/libxl_nocpuid.c | 8 +++++- 4 files changed, 68 insertions(+), 61 deletions(-) diff --git a/tools/libxl/Makefile b/tools/libxl/Makefile index 06764f2..41b6ac4 100644 --- a/tools/libxl/Makefile +++ b/tools/libxl/Makefile @@ -36,6 +36,7 @@ LIBXL_OBJS-y += libxl_noblktap2.o endif LIBXL_OBJS-$(CONFIG_X86) += libxl_cpuid.o LIBXL_OBJS-$(CONFIG_IA64) += libxl_nocpuid.o +LIBXL_OBJS-$(CONFIG_ARM) += libxl_nocpuid.o ifeq ($(CONFIG_NetBSD),y) LIBXL_OBJS-y += libxl_netbsd.o diff --git a/tools/libxl/libxl_cpuid.c b/tools/libxl/libxl_cpuid.c index dcdb9d02..ff7531f 100644 --- a/tools/libxl/libxl_cpuid.c +++ b/tools/libxl/libxl_cpuid.c @@ -333,6 +333,66 @@ void libxl_cpuid_set(libxl_ctx *ctx, uint32_t domid, (const char**)(cpuid[i].policy), cpuid_res); } +yajl_gen_status libxl_cpuid_policy_list_gen_json(yajl_gen hand, + libxl_cpuid_policy_list *pcpuid) +{ + libxl_cpuid_policy_list cpuid = *pcpuid; + yajl_gen_status s; + const char *input_names[2] = { "leaf", "subleaf" }; + const char *policy_names[4] = { "eax", "ebx", "ecx", "edx" }; + int i, j; + + /* + * Aiming for: + * [ + * { ''leaf'': ''val-eax'', + * ''subleaf'': ''val-ecx'', + * ''eax'': ''filter'', + * ''ebx'': ''filter'', + * ''ecx'': ''filter'', + * ''edx'': ''filter'' }, + * { ''leaf'': ''val-eax'', ..., ''eax'': ''filter'', ... }, + * ... etc ... + * ] + */ + + s = yajl_gen_array_open(hand); + if (s != yajl_gen_status_ok) goto out; + + if (cpuid == NULL) goto empty; + + for (i = 0; cpuid[i].input[0] != XEN_CPUID_INPUT_UNUSED; i++) { + s = yajl_gen_map_open(hand); + if (s != yajl_gen_status_ok) goto out; + + for (j = 0; j < 2; j++) { + if (cpuid[i].input[j] != XEN_CPUID_INPUT_UNUSED) { + s = libxl__yajl_gen_asciiz(hand, input_names[j]); + if (s != yajl_gen_status_ok) goto out; + s = yajl_gen_integer(hand, cpuid[i].input[j]); + if (s != yajl_gen_status_ok) goto out; + } + } + + for (j = 0; j < 4; j++) { + if (cpuid[i].policy[j] != NULL) { + s = libxl__yajl_gen_asciiz(hand, policy_names[j]); + if (s != yajl_gen_status_ok) goto out; + s = yajl_gen_string(hand, + (const unsigned char *)cpuid[i].policy[j], 32); + if (s != yajl_gen_status_ok) goto out; + } + } + s = yajl_gen_map_close(hand); + if (s != yajl_gen_status_ok) goto out; + } + +empty: + s = yajl_gen_array_close(hand); +out: + return s; +} + /* * Local variables: * mode: C diff --git a/tools/libxl/libxl_json.c b/tools/libxl/libxl_json.c index be6ad96..4cbcd57 100644 --- a/tools/libxl/libxl_json.c +++ b/tools/libxl/libxl_json.c @@ -140,66 +140,6 @@ out: return s; } -yajl_gen_status libxl_cpuid_policy_list_gen_json(yajl_gen hand, - libxl_cpuid_policy_list *pcpuid) -{ - libxl_cpuid_policy_list cpuid = *pcpuid; - yajl_gen_status s; - const char *input_names[2] = { "leaf", "subleaf" }; - const char *policy_names[4] = { "eax", "ebx", "ecx", "edx" }; - int i, j; - - /* - * Aiming for: - * [ - * { ''leaf'': ''val-eax'', - * ''subleaf'': ''val-ecx'', - * ''eax'': ''filter'', - * ''ebx'': ''filter'', - * ''ecx'': ''filter'', - * ''edx'': ''filter'' }, - * { ''leaf'': ''val-eax'', ..., ''eax'': ''filter'', ... }, - * ... etc ... - * ] - */ - - s = yajl_gen_array_open(hand); - if (s != yajl_gen_status_ok) goto out; - - if (cpuid == NULL) goto empty; - - for (i = 0; cpuid[i].input[0] != XEN_CPUID_INPUT_UNUSED; i++) { - s = yajl_gen_map_open(hand); - if (s != yajl_gen_status_ok) goto out; - - for (j = 0; j < 2; j++) { - if (cpuid[i].input[j] != XEN_CPUID_INPUT_UNUSED) { - s = libxl__yajl_gen_asciiz(hand, input_names[j]); - if (s != yajl_gen_status_ok) goto out; - s = yajl_gen_integer(hand, cpuid[i].input[j]); - if (s != yajl_gen_status_ok) goto out; - } - } - - for (j = 0; j < 4; j++) { - if (cpuid[i].policy[j] != NULL) { - s = libxl__yajl_gen_asciiz(hand, policy_names[j]); - if (s != yajl_gen_status_ok) goto out; - s = yajl_gen_string(hand, - (const unsigned char *)cpuid[i].policy[j], 32); - if (s != yajl_gen_status_ok) goto out; - } - } - s = yajl_gen_map_close(hand); - if (s != yajl_gen_status_ok) goto out; - } - -empty: - s = yajl_gen_array_close(hand); -out: - return s; -} - yajl_gen_status libxl_string_list_gen_json(yajl_gen hand, libxl_string_list *pl) { libxl_string_list l = *pl; diff --git a/tools/libxl/libxl_nocpuid.c b/tools/libxl/libxl_nocpuid.c index 9e52f8d..5f7cb6a 100644 --- a/tools/libxl/libxl_nocpuid.c +++ b/tools/libxl/libxl_nocpuid.c @@ -14,7 +14,7 @@ #include "libxl_internal.h" -void libxl_cpuid_destroy(libxl_cpuid_policy_list *p_cpuid_list) +void libxl_cpuid_dispose(libxl_cpuid_policy_list *p_cpuid_list) { } @@ -38,6 +38,12 @@ void libxl_cpuid_set(libxl_ctx *ctx, uint32_t domid, { } +yajl_gen_status libxl_cpuid_policy_list_gen_json(yajl_gen hand, + libxl_cpuid_policy_list *pcpuid) +{ + return 0; +} + /* * Local variables: * mode: C -- 1.7.2.5
Stefano Stabellini
2012-Feb-23 14:51 UTC
[PATCH v5 7/7] libxl: Introduce libxl__arch_domain_create
Introduce an arch specific internal domain creation function. At the moment only x86 provides an implementation. Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> --- tools/libxl/Makefile | 6 +- tools/libxl/libxl_arch.h | 22 ++++ tools/libxl/libxl_create.c | 12 +-- tools/libxl/libxl_internal.h | 2 - tools/libxl/libxl_noarch.c | 8 ++ tools/libxl/libxl_pci.c | 242 --------------------------------------- tools/libxl/libxl_x86.c | 259 ++++++++++++++++++++++++++++++++++++++++++ 7 files changed, 294 insertions(+), 257 deletions(-) create mode 100644 tools/libxl/libxl_arch.h create mode 100644 tools/libxl/libxl_noarch.c create mode 100644 tools/libxl/libxl_x86.c diff --git a/tools/libxl/Makefile b/tools/libxl/Makefile index 41b6ac4..ba5852b 100644 --- a/tools/libxl/Makefile +++ b/tools/libxl/Makefile @@ -34,9 +34,9 @@ LIBXL_OBJS-y += libxl_blktap2.o else LIBXL_OBJS-y += libxl_noblktap2.o endif -LIBXL_OBJS-$(CONFIG_X86) += libxl_cpuid.o -LIBXL_OBJS-$(CONFIG_IA64) += libxl_nocpuid.o -LIBXL_OBJS-$(CONFIG_ARM) += libxl_nocpuid.o +LIBXL_OBJS-$(CONFIG_X86) += libxl_cpuid.o libxl_x86.o +LIBXL_OBJS-$(CONFIG_IA64) += libxl_nocpuid.o libxl_noarch.o +LIBXL_OBJS-$(CONFIG_ARM) += libxl_nocpuid.o libxl_noarch.o ifeq ($(CONFIG_NetBSD),y) LIBXL_OBJS-y += libxl_netbsd.o diff --git a/tools/libxl/libxl_arch.h b/tools/libxl/libxl_arch.h new file mode 100644 index 0000000..d1bbdf7 --- /dev/null +++ b/tools/libxl/libxl_arch.h @@ -0,0 +1,22 @@ +/* + * Copyright (C) 2012 Citrix Ltd. + * + * This program 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 only. with the special + * exception on linking described in file LICENSE. + * + * This program 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. + */ + +#ifndef LIBXL_ARCH_H +#define LIBXL_ARCH_H + +/* arch specific internal domain creation function */ +int libxl__arch_domain_create(libxl__gc *gc, libxl_domain_config *d_config, + uint32_t domid); + +#endif diff --git a/tools/libxl/libxl_create.c b/tools/libxl/libxl_create.c index f28d814..ff589a8 100644 --- a/tools/libxl/libxl_create.c +++ b/tools/libxl/libxl_create.c @@ -18,6 +18,7 @@ #include "libxl_osdeps.h" /* must come before any other headers */ #include "libxl_internal.h" +#include "libxl_arch.h" #include <xc_dom.h> #include <xenguest.h> @@ -616,16 +617,7 @@ static int do_domain_create(libxl__gc *gc, libxl_domain_config *d_config, goto error_out; } } - - if (d_config->c_info.type == LIBXL_DOMAIN_TYPE_PV && - d_config->b_info.u.pv.e820_host) { - int rc; - rc = libxl__e820_alloc(gc, domid, d_config); - if (rc) - LIBXL__LOG_ERRNO(ctx, LIBXL__LOG_ERROR, - "Failed while collecting E820 with: %d (errno:%d)\n", - rc, errno); - } + libxl__arch_domain_create(gc, d_config, domid); if ( cb && (d_config->c_info.type == LIBXL_DOMAIN_TYPE_HVM || (d_config->c_info.type == LIBXL_DOMAIN_TYPE_PV && d_config->b_info.u.pv.bootloader ))) { diff --git a/tools/libxl/libxl_internal.h b/tools/libxl/libxl_internal.h index 8846c68..bd384e2 100644 --- a/tools/libxl/libxl_internal.h +++ b/tools/libxl/libxl_internal.h @@ -975,8 +975,6 @@ _hidden int libxl__error_set(libxl__gc *gc, int code); _hidden int libxl__file_reference_map(libxl_file_reference *f); _hidden int libxl__file_reference_unmap(libxl_file_reference *f); -_hidden int libxl__e820_alloc(libxl__gc *gc, uint32_t domid, libxl_domain_config *d_config); - /* parse the string @s as a sequence of 6 colon separated bytes in to @mac */ _hidden int libxl__parse_mac(const char *s, libxl_mac mac); /* compare mac address @a and @b. 0 if the same, -ve if a<b and +ve if a>b */ diff --git a/tools/libxl/libxl_noarch.c b/tools/libxl/libxl_noarch.c new file mode 100644 index 0000000..7893535 --- /dev/null +++ b/tools/libxl/libxl_noarch.c @@ -0,0 +1,8 @@ +#include "libxl_internal.h" +#include "libxl_arch.h" + +int libxl__arch_domain_create(libxl__gc *gc, libxl_domain_config *d_config, + uint32_t domid) +{ + return 0; +} diff --git a/tools/libxl/libxl_pci.c b/tools/libxl/libxl_pci.c index 33425f5..d960f4b 100644 --- a/tools/libxl/libxl_pci.c +++ b/tools/libxl/libxl_pci.c @@ -1147,248 +1147,6 @@ int libxl__device_pci_destroy_all(libxl__gc *gc, uint32_t domid) return 0; } -static const char *e820_names(int type) -{ - switch (type) { - case E820_RAM: return "RAM"; - case E820_RESERVED: return "Reserved"; - case E820_ACPI: return "ACPI"; - case E820_NVS: return "ACPI NVS"; - case E820_UNUSABLE: return "Unusable"; - default: break; - } - return "Unknown"; -} - -static int e820_sanitize(libxl_ctx *ctx, struct e820entry src[], - uint32_t *nr_entries, - unsigned long map_limitkb, - unsigned long balloon_kb) -{ - uint64_t delta_kb = 0, start = 0, start_kb = 0, last = 0, ram_end; - uint32_t i, idx = 0, nr; - struct e820entry e820[E820MAX]; - - if (!src || !map_limitkb || !balloon_kb || !nr_entries) - return ERROR_INVAL; - - nr = *nr_entries; - if (!nr) - return ERROR_INVAL; - - if (nr > E820MAX) - return ERROR_NOMEM; - - /* Weed out anything under 1MB */ - for (i = 0; i < nr; i++) { - if (src[i].addr > 0x100000) - continue; - - src[i].type = 0; - src[i].size = 0; - src[i].addr = -1ULL; - } - - /* Find the lowest and highest entry in E820, skipping over - * undesired entries. */ - start = -1ULL; - last = 0; - for (i = 0; i < nr; i++) { - if ((src[i].type == E820_RAM) || - (src[i].type == E820_UNUSABLE) || - (src[i].type == 0)) - continue; - - start = src[i].addr < start ? src[i].addr : start; - last = src[i].addr + src[i].size > last ? - src[i].addr + src[i].size > last : last; - } - if (start > 1024) - start_kb = start >> 10; - - /* Add the memory RAM region for the guest */ - e820[idx].addr = 0; - e820[idx].size = (uint64_t)map_limitkb << 10; - e820[idx].type = E820_RAM; - - /* .. and trim if neccessary */ - if (start_kb && map_limitkb > start_kb) { - delta_kb = map_limitkb - start_kb; - if (delta_kb) - e820[idx].size -= (uint64_t)(delta_kb << 10); - } - /* Note: We don''t touch balloon_kb here. Will add it at the end. */ - ram_end = e820[idx].addr + e820[idx].size; - idx ++; - - LIBXL__LOG(ctx, LIBXL__LOG_DEBUG, "Memory: %"PRIu64"kB End of RAM: " \ - "0x%"PRIx64" (PFN) Delta: %"PRIu64"kB, PCI start: %"PRIu64"kB " \ - "(0x%"PRIx64" PFN), Balloon %"PRIu64"kB\n", (uint64_t)map_limitkb, - ram_end >> 12, delta_kb, start_kb ,start >> 12, - (uint64_t)balloon_kb); - - - /* This whole code below is to guard against if the Intel IGD is passed into - * the guest. If we don''t pass in IGD, this whole code can be ignored. - * - * The reason for this code is that Intel boxes fill their E820 with - * E820_RAM amongst E820_RESERVED and we can''t just ditch those E820_RAM. - * That is b/c any "gaps" in the E820 is considered PCI I/O space by - * Linux and it would be utilized by the Intel IGD as I/O space while - * in reality it was an RAM region. - * - * What this means is that we have to walk the E820 and for any region - * that is RAM and below 4GB and above ram_end, needs to change its type - * to E820_UNUSED. We also need to move some of the E820_RAM regions if - * the overlap with ram_end. */ - for (i = 0; i < nr; i++) { - uint64_t end = src[i].addr + src[i].size; - - /* We don''t care about E820_UNUSABLE, but we need to - * change the type to zero b/c the loop after this - * sticks E820_UNUSABLE on the guest''s E820 but ignores - * the ones with type zero. */ - if ((src[i].type == E820_UNUSABLE) || - /* Any region that is within the "RAM region" can - * be safely ditched. */ - (end < ram_end)) { - src[i].type = 0; - continue; - } - - /* Look only at RAM regions. */ - if (src[i].type != E820_RAM) - continue; - - /* We only care about RAM regions below 4GB. */ - if (src[i].addr >= (1ULL<<32)) - continue; - - /* E820_RAM overlaps with our RAM region. Move it */ - if (src[i].addr < ram_end) { - uint64_t delta; - - src[i].type = E820_UNUSABLE; - delta = ram_end - src[i].addr; - /* The end < ram_end should weed this out */ - if (src[i].size - delta < 0) - src[i].type = 0; - else { - src[i].size -= delta; - src[i].addr = ram_end; - } - if (src[i].addr + src[i].size != end) { - /* We messed up somewhere */ - src[i].type = 0; - LIBXL__LOG_ERRNO(ctx, LIBXL__LOG_ERROR, "Computed E820 wrongly. Continuing on."); - } - } - /* Lastly, convert the RAM to UNSUABLE. Look in the Linux kernel - at git commit 2f14ddc3a7146ea4cd5a3d1ecd993f85f2e4f948 - "xen/setup: Inhibit resource API from using System RAM E820 - gaps as PCI mem gaps" for full explanation. */ - if (end > ram_end) - src[i].type = E820_UNUSABLE; - } - - /* Check if there is a region between ram_end and start. */ - if (start > ram_end) { - int add_unusable = 1; - for (i = 0; i < nr && add_unusable; i++) { - if (src[i].type != E820_UNUSABLE) - continue; - if (ram_end != src[i].addr) - continue; - if (start != src[i].addr + src[i].size) { - /* there is one, adjust it */ - src[i].size = start - src[i].addr; - } - add_unusable = 0; - } - /* .. and if not present, add it in. This is to guard against - the Linux guest assuming that the gap between the end of - RAM region and the start of the E820_[ACPI,NVS,RESERVED] - is PCI I/O space. Which it certainly is _not_. */ - if (add_unusable) { - e820[idx].type = E820_UNUSABLE; - e820[idx].addr = ram_end; - e820[idx].size = start - ram_end; - idx++; - } - } - /* Almost done: copy them over, ignoring the undesireable ones */ - for (i = 0; i < nr; i++) { - if ((src[i].type == E820_RAM) || - (src[i].type == 0)) - continue; - - e820[idx].type = src[i].type; - e820[idx].addr = src[i].addr; - e820[idx].size = src[i].size; - idx++; - } - /* At this point we have the mapped RAM + E820 entries from src. */ - if (balloon_kb) { - /* and if we truncated the RAM region, then add it to the end. */ - e820[idx].type = E820_RAM; - e820[idx].addr = (uint64_t)(1ULL << 32) > last ? - (uint64_t)(1ULL << 32) : last; - /* also add the balloon memory to the end. */ - e820[idx].size = (uint64_t)(delta_kb << 10) + - (uint64_t)(balloon_kb << 10); - idx++; - - } - nr = idx; - - for (i = 0; i < nr; i++) { - LIBXL__LOG(ctx, LIBXL__LOG_DEBUG, ":\t[%"PRIx64" -> %"PRIx64"] %s", - e820[i].addr >> 12, (e820[i].addr + e820[i].size) >> 12, - e820_names(e820[i].type)); - } - - /* Done: copy the sanitized version. */ - *nr_entries = nr; - memcpy(src, e820, nr * sizeof(struct e820entry)); - return 0; -} - -int libxl__e820_alloc(libxl__gc *gc, uint32_t domid, libxl_domain_config *d_config) -{ - libxl_ctx *ctx = libxl__gc_owner(gc); - int rc; - uint32_t nr; - struct e820entry map[E820MAX]; - libxl_domain_build_info *b_info; - - if (d_config == NULL || d_config->c_info.type == LIBXL_DOMAIN_TYPE_HVM) - return ERROR_INVAL; - - b_info = &d_config->b_info; - if (!b_info->u.pv.e820_host) - return ERROR_INVAL; - - rc = xc_get_machine_memory_map(ctx->xch, map, E820MAX); - if (rc < 0) { - errno = rc; - return ERROR_FAIL; - } - nr = rc; - rc = e820_sanitize(ctx, map, &nr, b_info->target_memkb, - (b_info->max_memkb - b_info->target_memkb) + - b_info->u.pv.slack_memkb); - if (rc) - return ERROR_FAIL; - - rc = xc_domain_set_memory_map(ctx->xch, domid, map, nr); - - if (rc < 0) { - errno = rc; - return ERROR_FAIL; - } - return 0; -} - /* * Local variables: * mode: C diff --git a/tools/libxl/libxl_x86.c b/tools/libxl/libxl_x86.c new file mode 100644 index 0000000..7e11f2d --- /dev/null +++ b/tools/libxl/libxl_x86.c @@ -0,0 +1,259 @@ +#include "libxl_internal.h" +#include "libxl_arch.h" + +static const char *e820_names(int type) +{ + switch (type) { + case E820_RAM: return "RAM"; + case E820_RESERVED: return "Reserved"; + case E820_ACPI: return "ACPI"; + case E820_NVS: return "ACPI NVS"; + case E820_UNUSABLE: return "Unusable"; + default: break; + } + return "Unknown"; +} + +static int e820_sanitize(libxl_ctx *ctx, struct e820entry src[], + uint32_t *nr_entries, + unsigned long map_limitkb, + unsigned long balloon_kb) +{ + uint64_t delta_kb = 0, start = 0, start_kb = 0, last = 0, ram_end; + uint32_t i, idx = 0, nr; + struct e820entry e820[E820MAX]; + + if (!src || !map_limitkb || !balloon_kb || !nr_entries) + return ERROR_INVAL; + + nr = *nr_entries; + if (!nr) + return ERROR_INVAL; + + if (nr > E820MAX) + return ERROR_NOMEM; + + /* Weed out anything under 1MB */ + for (i = 0; i < nr; i++) { + if (src[i].addr > 0x100000) + continue; + + src[i].type = 0; + src[i].size = 0; + src[i].addr = -1ULL; + } + + /* Find the lowest and highest entry in E820, skipping over + * undesired entries. */ + start = -1ULL; + last = 0; + for (i = 0; i < nr; i++) { + if ((src[i].type == E820_RAM) || + (src[i].type == E820_UNUSABLE) || + (src[i].type == 0)) + continue; + + start = src[i].addr < start ? src[i].addr : start; + last = src[i].addr + src[i].size > last ? + src[i].addr + src[i].size > last : last; + } + if (start > 1024) + start_kb = start >> 10; + + /* Add the memory RAM region for the guest */ + e820[idx].addr = 0; + e820[idx].size = (uint64_t)map_limitkb << 10; + e820[idx].type = E820_RAM; + + /* .. and trim if neccessary */ + if (start_kb && map_limitkb > start_kb) { + delta_kb = map_limitkb - start_kb; + if (delta_kb) + e820[idx].size -= (uint64_t)(delta_kb << 10); + } + /* Note: We don''t touch balloon_kb here. Will add it at the end. */ + ram_end = e820[idx].addr + e820[idx].size; + idx ++; + + LIBXL__LOG(ctx, LIBXL__LOG_DEBUG, "Memory: %"PRIu64"kB End of RAM: " \ + "0x%"PRIx64" (PFN) Delta: %"PRIu64"kB, PCI start: %"PRIu64"kB " \ + "(0x%"PRIx64" PFN), Balloon %"PRIu64"kB\n", (uint64_t)map_limitkb, + ram_end >> 12, delta_kb, start_kb ,start >> 12, + (uint64_t)balloon_kb); + + + /* This whole code below is to guard against if the Intel IGD is passed into + * the guest. If we don''t pass in IGD, this whole code can be ignored. + * + * The reason for this code is that Intel boxes fill their E820 with + * E820_RAM amongst E820_RESERVED and we can''t just ditch those E820_RAM. + * That is b/c any "gaps" in the E820 is considered PCI I/O space by + * Linux and it would be utilized by the Intel IGD as I/O space while + * in reality it was an RAM region. + * + * What this means is that we have to walk the E820 and for any region + * that is RAM and below 4GB and above ram_end, needs to change its type + * to E820_UNUSED. We also need to move some of the E820_RAM regions if + * the overlap with ram_end. */ + for (i = 0; i < nr; i++) { + uint64_t end = src[i].addr + src[i].size; + + /* We don''t care about E820_UNUSABLE, but we need to + * change the type to zero b/c the loop after this + * sticks E820_UNUSABLE on the guest''s E820 but ignores + * the ones with type zero. */ + if ((src[i].type == E820_UNUSABLE) || + /* Any region that is within the "RAM region" can + * be safely ditched. */ + (end < ram_end)) { + src[i].type = 0; + continue; + } + + /* Look only at RAM regions. */ + if (src[i].type != E820_RAM) + continue; + + /* We only care about RAM regions below 4GB. */ + if (src[i].addr >= (1ULL<<32)) + continue; + + /* E820_RAM overlaps with our RAM region. Move it */ + if (src[i].addr < ram_end) { + uint64_t delta; + + src[i].type = E820_UNUSABLE; + delta = ram_end - src[i].addr; + /* The end < ram_end should weed this out */ + if (src[i].size - delta < 0) + src[i].type = 0; + else { + src[i].size -= delta; + src[i].addr = ram_end; + } + if (src[i].addr + src[i].size != end) { + /* We messed up somewhere */ + src[i].type = 0; + LIBXL__LOG_ERRNO(ctx, LIBXL__LOG_ERROR, "Computed E820 wrongly. Continuing on."); + } + } + /* Lastly, convert the RAM to UNSUABLE. Look in the Linux kernel + at git commit 2f14ddc3a7146ea4cd5a3d1ecd993f85f2e4f948 + "xen/setup: Inhibit resource API from using System RAM E820 + gaps as PCI mem gaps" for full explanation. */ + if (end > ram_end) + src[i].type = E820_UNUSABLE; + } + + /* Check if there is a region between ram_end and start. */ + if (start > ram_end) { + int add_unusable = 1; + for (i = 0; i < nr && add_unusable; i++) { + if (src[i].type != E820_UNUSABLE) + continue; + if (ram_end != src[i].addr) + continue; + if (start != src[i].addr + src[i].size) { + /* there is one, adjust it */ + src[i].size = start - src[i].addr; + } + add_unusable = 0; + } + /* .. and if not present, add it in. This is to guard against + the Linux guest assuming that the gap between the end of + RAM region and the start of the E820_[ACPI,NVS,RESERVED] + is PCI I/O space. Which it certainly is _not_. */ + if (add_unusable) { + e820[idx].type = E820_UNUSABLE; + e820[idx].addr = ram_end; + e820[idx].size = start - ram_end; + idx++; + } + } + /* Almost done: copy them over, ignoring the undesireable ones */ + for (i = 0; i < nr; i++) { + if ((src[i].type == E820_RAM) || + (src[i].type == 0)) + continue; + + e820[idx].type = src[i].type; + e820[idx].addr = src[i].addr; + e820[idx].size = src[i].size; + idx++; + } + /* At this point we have the mapped RAM + E820 entries from src. */ + if (balloon_kb) { + /* and if we truncated the RAM region, then add it to the end. */ + e820[idx].type = E820_RAM; + e820[idx].addr = (uint64_t)(1ULL << 32) > last ? + (uint64_t)(1ULL << 32) : last; + /* also add the balloon memory to the end. */ + e820[idx].size = (uint64_t)(delta_kb << 10) + + (uint64_t)(balloon_kb << 10); + idx++; + + } + nr = idx; + + for (i = 0; i < nr; i++) { + LIBXL__LOG(ctx, LIBXL__LOG_DEBUG, ":\t[%"PRIx64" -> %"PRIx64"] %s", + e820[i].addr >> 12, (e820[i].addr + e820[i].size) >> 12, + e820_names(e820[i].type)); + } + + /* Done: copy the sanitized version. */ + *nr_entries = nr; + memcpy(src, e820, nr * sizeof(struct e820entry)); + return 0; +} + +static int libxl__e820_alloc(libxl__gc *gc, uint32_t domid, libxl_domain_config *d_config) +{ + libxl_ctx *ctx = libxl__gc_owner(gc); + int rc; + uint32_t nr; + struct e820entry map[E820MAX]; + libxl_domain_build_info *b_info; + + if (d_config == NULL || d_config->c_info.type == LIBXL_DOMAIN_TYPE_HVM) + return ERROR_INVAL; + + b_info = &d_config->b_info; + if (!b_info->u.pv.e820_host) + return ERROR_INVAL; + + rc = xc_get_machine_memory_map(ctx->xch, map, E820MAX); + if (rc < 0) { + errno = rc; + return ERROR_FAIL; + } + nr = rc; + rc = e820_sanitize(ctx, map, &nr, b_info->target_memkb, + (b_info->max_memkb - b_info->target_memkb) + + b_info->u.pv.slack_memkb); + if (rc) + return ERROR_FAIL; + + rc = xc_domain_set_memory_map(ctx->xch, domid, map, nr); + + if (rc < 0) { + errno = rc; + return ERROR_FAIL; + } + return 0; +} + +int libxl__arch_domain_create(libxl__gc *gc, libxl_domain_config *d_config, + uint32_t domid) +{ + int rc = 0; + if (d_config->c_info.type == LIBXL_DOMAIN_TYPE_PV && + d_config->b_info.u.pv.e820_host) { + rc = libxl__e820_alloc(gc, domid, d_config); + if (rc) + LIBXL__LOG_ERRNO(libxl__gc_owner(gc), LIBXL__LOG_ERROR, + "Failed while collecting E820 with: %d (errno:%d)\n", + rc, errno); + } + return rc; +} -- 1.7.2.5
On Thu, 2012-02-23 at 14:51 +0000, Stefano Stabellini wrote:> Introduce an empty implementation of the arch specific ARM functions in > xc_dom_arm.c. > Provide empty implementations of xc_domain_save and xc_domain_restore > when CONFIG_MIGRATE is not set. > Move xc_hvm_build.c to xc_hvm_build_x86.c because the implementation is > x86 specific, introduce xc_hvm_build_arm.c with empty stubs. > > > Changes in v3: > > - rename xc_hvm_build.c to xc_hvm_build_x86.c; > > - remove xc_nohvm, introduce xc_hvm_build_arm.c instead; > > > > Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>Acked-by: Ian Campbell <ian.campbell@citrix.com> If you happen to repost then updating the copyright lines to say 2012 instead of 2011 might be useful. I''d also encourage the use of "format-patch -M" in the future -- it makes renames much easier to review.> --- > tools/libxc/Makefile | 12 +- > tools/libxc/xc_dom_arm.c | 50 ++++ > tools/libxc/xc_hvm_build.c | 511 ---------------------------------------- > tools/libxc/xc_hvm_build_arm.c | 61 +++++ > tools/libxc/xc_hvm_build_x86.c | 511 ++++++++++++++++++++++++++++++++++++++++ > tools/libxc/xc_nomigrate.c | 53 ++++ > 6 files changed, 684 insertions(+), 514 deletions(-) > create mode 100644 tools/libxc/xc_dom_arm.c > delete mode 100644 tools/libxc/xc_hvm_build.c > create mode 100644 tools/libxc/xc_hvm_build_arm.c > create mode 100644 tools/libxc/xc_hvm_build_x86.c > create mode 100644 tools/libxc/xc_nomigrate.c > > diff --git a/tools/libxc/Makefile b/tools/libxc/Makefile > index f2e1ba7..02d39a3 100644 > --- a/tools/libxc/Makefile > +++ b/tools/libxc/Makefile > @@ -42,9 +42,12 @@ CTRL_SRCS-$(CONFIG_MiniOS) += xc_minios.c > > GUEST_SRCS-y :> GUEST_SRCS-y += xg_private.c xc_suspend.c > -GUEST_SRCS-$(CONFIG_MIGRATE) += xc_domain_restore.c xc_domain_save.c > -GUEST_SRCS-$(CONFIG_MIGRATE) += xc_offline_page.c xc_compression.c > -GUEST_SRCS-$(CONFIG_HVM) += xc_hvm_build.c > +ifeq ($(CONFIG_MIGRATE),y) > +GUEST_SRCS-y += xc_domain_restore.c xc_domain_save.c > +GUEST_SRCS-y += xc_offline_page.c xc_compression.c > +else > +GUEST_SRCS-y += xc_nomigrate.c > +endif > > vpath %.c ../../xen/common/libelf > CFLAGS += -I../../xen/common/libelf > @@ -61,7 +64,10 @@ GUEST_SRCS-y += xc_dom_compat_linux.c > > GUEST_SRCS-$(CONFIG_X86) += xc_dom_x86.c > GUEST_SRCS-$(CONFIG_X86) += xc_cpuid_x86.c > +GUEST_SRCS-$(CONFIG_X86) += xc_hvm_build_x86.c > GUEST_SRCS-$(CONFIG_IA64) += xc_dom_ia64.c > +GUEST_SRCS-$(CONFIG_ARM) += xc_dom_arm.c > +GUEST_SRCS-$(CONFIG_ARM) += xc_hvm_build_arm.c > > OSDEP_SRCS-y += xenctrl_osdep_ENOSYS.c > > diff --git a/tools/libxc/xc_dom_arm.c b/tools/libxc/xc_dom_arm.c > new file mode 100644 > index 0000000..122d0e8 > --- /dev/null > +++ b/tools/libxc/xc_dom_arm.c > @@ -0,0 +1,50 @@ > +/* > + * Xen domain builder -- ARM > + * > + * 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 > + * > + * Copyright (c) 2011, Citrix Systems > + */ > +#include <inttypes.h> > +#include <xen/xen.h> > +#include "xg_private.h" > +#include "xc_dom.h" > + > +int arch_setup_meminit(struct xc_dom_image *dom) > +{ > + errno = ENOSYS; > + return -1; > +} > + > +int arch_setup_bootearly(struct xc_dom_image *dom) > +{ > + DOMPRINTF("%s: doing nothing", __FUNCTION__); > + return 0; > +} > + > +int arch_setup_bootlate(struct xc_dom_image *dom) > +{ > + DOMPRINTF("%s: doing nothing", __FUNCTION__); > + return 0; > +} > +/* > + * Local variables: > + * mode: C > + * c-set-style: "BSD" > + * c-basic-offset: 4 > + * tab-width: 4 > + * indent-tabs-mode: nil > + * End: > + */ > diff --git a/tools/libxc/xc_hvm_build.c b/tools/libxc/xc_hvm_build.c > deleted file mode 100644 > index 1fa5658..0000000 > --- a/tools/libxc/xc_hvm_build.c > +++ /dev/null > @@ -1,511 +0,0 @@ > -/****************************************************************************** > - * xc_hvm_build.c > - * > - * 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 <stddef.h> > -#include <inttypes.h> > -#include <stdlib.h> > -#include <unistd.h> > -#include <zlib.h> > - > -#include "xg_private.h" > -#include "xc_private.h" > - > -#include <xen/foreign/x86_32.h> > -#include <xen/foreign/x86_64.h> > -#include <xen/hvm/hvm_info_table.h> > -#include <xen/hvm/params.h> > -#include <xen/hvm/e820.h> > - > -#include <xen/libelf/libelf.h> > - > -#define SUPERPAGE_2MB_SHIFT 9 > -#define SUPERPAGE_2MB_NR_PFNS (1UL << SUPERPAGE_2MB_SHIFT) > -#define SUPERPAGE_1GB_SHIFT 18 > -#define SUPERPAGE_1GB_NR_PFNS (1UL << SUPERPAGE_1GB_SHIFT) > - > -#define SPECIALPAGE_BUFIOREQ 0 > -#define SPECIALPAGE_XENSTORE 1 > -#define SPECIALPAGE_IOREQ 2 > -#define SPECIALPAGE_IDENT_PT 3 > -#define SPECIALPAGE_CONSOLE 4 > -#define NR_SPECIAL_PAGES 5 > -#define special_pfn(x) (0xff000u - NR_SPECIAL_PAGES + (x)) > - > -static void build_hvm_info(void *hvm_info_page, uint64_t mem_size) > -{ > - struct hvm_info_table *hvm_info = (struct hvm_info_table *) > - (((unsigned char *)hvm_info_page) + HVM_INFO_OFFSET); > - uint64_t lowmem_end = mem_size, highmem_end = 0; > - uint8_t sum; > - int i; > - > - if ( lowmem_end > HVM_BELOW_4G_RAM_END ) > - { > - highmem_end = lowmem_end + (1ull<<32) - HVM_BELOW_4G_RAM_END; > - lowmem_end = HVM_BELOW_4G_RAM_END; > - } > - > - memset(hvm_info_page, 0, PAGE_SIZE); > - > - /* Fill in the header. */ > - strncpy(hvm_info->signature, "HVM INFO", 8); > - hvm_info->length = sizeof(struct hvm_info_table); > - > - /* Sensible defaults: these can be overridden by the caller. */ > - hvm_info->apic_mode = 1; > - hvm_info->nr_vcpus = 1; > - memset(hvm_info->vcpu_online, 0xff, sizeof(hvm_info->vcpu_online)); > - > - /* Memory parameters. */ > - hvm_info->low_mem_pgend = lowmem_end >> PAGE_SHIFT; > - hvm_info->high_mem_pgend = highmem_end >> PAGE_SHIFT; > - hvm_info->reserved_mem_pgstart = special_pfn(0); > - > - /* Finish with the checksum. */ > - for ( i = 0, sum = 0; i < hvm_info->length; i++ ) > - sum += ((uint8_t *)hvm_info)[i]; > - hvm_info->checksum = -sum; > -} > - > -static int loadelfimage( > - xc_interface *xch, > - struct elf_binary *elf, uint32_t dom, unsigned long *parray) > -{ > - privcmd_mmap_entry_t *entries = NULL; > - unsigned long pfn_start = elf->pstart >> PAGE_SHIFT; > - unsigned long pfn_end = (elf->pend + PAGE_SIZE - 1) >> PAGE_SHIFT; > - size_t pages = pfn_end - pfn_start; > - int i, rc = -1; > - > - /* Map address space for initial elf image. */ > - entries = calloc(pages, sizeof(privcmd_mmap_entry_t)); > - if ( entries == NULL ) > - goto err; > - > - for ( i = 0; i < pages; i++ ) > - entries[i].mfn = parray[(elf->pstart >> PAGE_SHIFT) + i]; > - > - elf->dest = xc_map_foreign_ranges( > - xch, dom, pages << PAGE_SHIFT, PROT_READ | PROT_WRITE, 1 << PAGE_SHIFT, > - entries, pages); > - if ( elf->dest == NULL ) > - goto err; > - > - elf->dest += elf->pstart & (PAGE_SIZE - 1); > - > - /* Load the initial elf image. */ > - rc = elf_load_binary(elf); > - if ( rc < 0 ) > - PERROR("Failed to load elf binary\n"); > - > - munmap(elf->dest, pages << PAGE_SHIFT); > - elf->dest = NULL; > - > - err: > - free(entries); > - > - return rc; > -} > - > -/* > - * Check whether there exists mmio hole in the specified memory range. > - * Returns 1 if exists, else returns 0. > - */ > -static int check_mmio_hole(uint64_t start, uint64_t memsize) > -{ > - if ( start + memsize <= HVM_BELOW_4G_MMIO_START || > - start >= HVM_BELOW_4G_MMIO_START + HVM_BELOW_4G_MMIO_LENGTH ) > - return 0; > - else > - return 1; > -} > - > -static int setup_guest(xc_interface *xch, > - uint32_t dom, int memsize, int target, > - char *image, unsigned long image_size) > -{ > - xen_pfn_t *page_array = NULL; > - unsigned long i, nr_pages = (unsigned long)memsize << (20 - PAGE_SHIFT); > - unsigned long target_pages = (unsigned long)target << (20 - PAGE_SHIFT); > - unsigned long entry_eip, cur_pages, cur_pfn; > - void *hvm_info_page; > - uint32_t *ident_pt; > - struct elf_binary elf; > - uint64_t v_start, v_end; > - int rc; > - xen_capabilities_info_t caps; > - unsigned long stat_normal_pages = 0, stat_2mb_pages = 0, > - stat_1gb_pages = 0; > - int pod_mode = 0; > - > - /* An HVM guest must be initialised with at least 2MB memory. */ > - if ( memsize < 2 || target < 2 ) > - goto error_out; > - > - if ( memsize > target ) > - pod_mode = 1; > - > - memset(&elf, 0, sizeof(elf)); > - if ( elf_init(&elf, image, image_size) != 0 ) > - goto error_out; > - > - xc_elf_set_logfile(xch, &elf, 1); > - > - elf_parse_binary(&elf); > - v_start = 0; > - v_end = (unsigned long long)memsize << 20; > - > - if ( xc_version(xch, XENVER_capabilities, &caps) != 0 ) > - { > - PERROR("Could not get Xen capabilities"); > - goto error_out; > - } > - > - IPRINTF("VIRTUAL MEMORY ARRANGEMENT:\n" > - " Loader: %016"PRIx64"->%016"PRIx64"\n" > - " TOTAL: %016"PRIx64"->%016"PRIx64"\n" > - " ENTRY ADDRESS: %016"PRIx64"\n", > - elf.pstart, elf.pend, > - v_start, v_end, > - elf_uval(&elf, elf.ehdr, e_entry)); > - > - if ( (page_array = malloc(nr_pages * sizeof(xen_pfn_t))) == NULL ) > - { > - PERROR("Could not allocate memory."); > - goto error_out; > - } > - > - for ( i = 0; i < nr_pages; i++ ) > - page_array[i] = i; > - for ( i = HVM_BELOW_4G_RAM_END >> PAGE_SHIFT; i < nr_pages; i++ ) > - page_array[i] += HVM_BELOW_4G_MMIO_LENGTH >> PAGE_SHIFT; > - > - /* > - * Allocate memory for HVM guest, skipping VGA hole 0xA0000-0xC0000. > - * > - * We attempt to allocate 1GB pages if possible. It falls back on 2MB > - * pages if 1GB allocation fails. 4KB pages will be used eventually if > - * both fail. > - * > - * Under 2MB mode, we allocate pages in batches of no more than 8MB to > - * ensure that we can be preempted and hence dom0 remains responsive. > - */ > - rc = xc_domain_populate_physmap_exact( > - xch, dom, 0xa0, 0, 0, &page_array[0x00]); > - cur_pages = 0xc0; > - stat_normal_pages = 0xc0; > - while ( (rc == 0) && (nr_pages > cur_pages) ) > - { > - /* Clip count to maximum 1GB extent. */ > - unsigned long count = nr_pages - cur_pages; > - unsigned long max_pages = SUPERPAGE_1GB_NR_PFNS; > - > - if ( count > max_pages ) > - count = max_pages; > - > - cur_pfn = page_array[cur_pages]; > - > - /* Take care the corner cases of super page tails */ > - if ( ((cur_pfn & (SUPERPAGE_1GB_NR_PFNS-1)) != 0) && > - (count > (-cur_pfn & (SUPERPAGE_1GB_NR_PFNS-1))) ) > - count = -cur_pfn & (SUPERPAGE_1GB_NR_PFNS-1); > - else if ( ((count & (SUPERPAGE_1GB_NR_PFNS-1)) != 0) && > - (count > SUPERPAGE_1GB_NR_PFNS) ) > - count &= ~(SUPERPAGE_1GB_NR_PFNS - 1); > - > - /* Attemp to allocate 1GB super page. Because in each pass we only > - * allocate at most 1GB, we don''t have to clip super page boundaries. > - */ > - if ( ((count | cur_pfn) & (SUPERPAGE_1GB_NR_PFNS - 1)) == 0 && > - /* Check if there exists MMIO hole in the 1GB memory range */ > - !check_mmio_hole(cur_pfn << PAGE_SHIFT, > - SUPERPAGE_1GB_NR_PFNS << PAGE_SHIFT) ) > - { > - long done; > - unsigned long nr_extents = count >> SUPERPAGE_1GB_SHIFT; > - xen_pfn_t sp_extents[nr_extents]; > - > - for ( i = 0; i < nr_extents; i++ ) > - sp_extents[i] = page_array[cur_pages+(i<<SUPERPAGE_1GB_SHIFT)]; > - > - done = xc_domain_populate_physmap(xch, dom, nr_extents, SUPERPAGE_1GB_SHIFT, > - pod_mode ? XENMEMF_populate_on_demand : 0, > - sp_extents); > - > - if ( done > 0 ) > - { > - stat_1gb_pages += done; > - done <<= SUPERPAGE_1GB_SHIFT; > - cur_pages += done; > - count -= done; > - } > - } > - > - if ( count != 0 ) > - { > - /* Clip count to maximum 8MB extent. */ > - max_pages = SUPERPAGE_2MB_NR_PFNS * 4; > - if ( count > max_pages ) > - count = max_pages; > - > - /* Clip partial superpage extents to superpage boundaries. */ > - if ( ((cur_pfn & (SUPERPAGE_2MB_NR_PFNS-1)) != 0) && > - (count > (-cur_pfn & (SUPERPAGE_2MB_NR_PFNS-1))) ) > - count = -cur_pfn & (SUPERPAGE_2MB_NR_PFNS-1); > - else if ( ((count & (SUPERPAGE_2MB_NR_PFNS-1)) != 0) && > - (count > SUPERPAGE_2MB_NR_PFNS) ) > - count &= ~(SUPERPAGE_2MB_NR_PFNS - 1); /* clip non-s.p. tail */ > - > - /* Attempt to allocate superpage extents. */ > - if ( ((count | cur_pfn) & (SUPERPAGE_2MB_NR_PFNS - 1)) == 0 ) > - { > - long done; > - unsigned long nr_extents = count >> SUPERPAGE_2MB_SHIFT; > - xen_pfn_t sp_extents[nr_extents]; > - > - for ( i = 0; i < nr_extents; i++ ) > - sp_extents[i] = page_array[cur_pages+(i<<SUPERPAGE_2MB_SHIFT)]; > - > - done = xc_domain_populate_physmap(xch, dom, nr_extents, SUPERPAGE_2MB_SHIFT, > - pod_mode ? XENMEMF_populate_on_demand : 0, > - sp_extents); > - > - if ( done > 0 ) > - { > - stat_2mb_pages += done; > - done <<= SUPERPAGE_2MB_SHIFT; > - cur_pages += done; > - count -= done; > - } > - } > - } > - > - /* Fall back to 4kB extents. */ > - if ( count != 0 ) > - { > - rc = xc_domain_populate_physmap_exact( > - xch, dom, count, 0, 0, &page_array[cur_pages]); > - cur_pages += count; > - stat_normal_pages += count; > - } > - } > - > - /* Subtract 0x20 from target_pages for the VGA "hole". Xen will > - * adjust the PoD cache size so that domain tot_pages will be > - * target_pages - 0x20 after this call. */ > - if ( pod_mode ) > - rc = xc_domain_set_pod_target(xch, dom, target_pages - 0x20, > - NULL, NULL, NULL); > - > - if ( rc != 0 ) > - { > - PERROR("Could not allocate memory for HVM guest."); > - goto error_out; > - } > - > - IPRINTF("PHYSICAL MEMORY ALLOCATION:\n" > - " 4KB PAGES: 0x%016lx\n" > - " 2MB PAGES: 0x%016lx\n" > - " 1GB PAGES: 0x%016lx\n", > - stat_normal_pages, stat_2mb_pages, stat_1gb_pages); > - > - if ( loadelfimage(xch, &elf, dom, page_array) != 0 ) > - goto error_out; > - > - if ( (hvm_info_page = xc_map_foreign_range( > - xch, dom, PAGE_SIZE, PROT_READ | PROT_WRITE, > - HVM_INFO_PFN)) == NULL ) > - goto error_out; > - build_hvm_info(hvm_info_page, v_end); > - munmap(hvm_info_page, PAGE_SIZE); > - > - /* Allocate and clear special pages. */ > - for ( i = 0; i < NR_SPECIAL_PAGES; i++ ) > - { > - xen_pfn_t pfn = special_pfn(i); > - rc = xc_domain_populate_physmap_exact(xch, dom, 1, 0, 0, &pfn); > - if ( rc != 0 ) > - { > - PERROR("Could not allocate %d''th special page.", i); > - goto error_out; > - } > - if ( xc_clear_domain_page(xch, dom, special_pfn(i)) ) > - goto error_out; > - } > - > - xc_set_hvm_param(xch, dom, HVM_PARAM_STORE_PFN, > - special_pfn(SPECIALPAGE_XENSTORE)); > - xc_set_hvm_param(xch, dom, HVM_PARAM_BUFIOREQ_PFN, > - special_pfn(SPECIALPAGE_BUFIOREQ)); > - xc_set_hvm_param(xch, dom, HVM_PARAM_IOREQ_PFN, > - special_pfn(SPECIALPAGE_IOREQ)); > - xc_set_hvm_param(xch, dom, HVM_PARAM_CONSOLE_PFN, > - special_pfn(SPECIALPAGE_CONSOLE)); > - > - /* > - * Identity-map page table is required for running with CR0.PG=0 when > - * using Intel EPT. Create a 32-bit non-PAE page directory of superpages. > - */ > - if ( (ident_pt = xc_map_foreign_range( > - xch, dom, PAGE_SIZE, PROT_READ | PROT_WRITE, > - special_pfn(SPECIALPAGE_IDENT_PT))) == NULL ) > - goto error_out; > - for ( i = 0; i < PAGE_SIZE / sizeof(*ident_pt); i++ ) > - ident_pt[i] = ((i << 22) | _PAGE_PRESENT | _PAGE_RW | _PAGE_USER | > - _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE); > - munmap(ident_pt, PAGE_SIZE); > - xc_set_hvm_param(xch, dom, HVM_PARAM_IDENT_PT, > - special_pfn(SPECIALPAGE_IDENT_PT) << PAGE_SHIFT); > - > - /* Insert JMP <rel32> instruction at address 0x0 to reach entry point. */ > - entry_eip = elf_uval(&elf, elf.ehdr, e_entry); > - if ( entry_eip != 0 ) > - { > - char *page0 = xc_map_foreign_range( > - xch, dom, PAGE_SIZE, PROT_READ | PROT_WRITE, 0); > - if ( page0 == NULL ) > - goto error_out; > - page0[0] = 0xe9; > - *(uint32_t *)&page0[1] = entry_eip - 5; > - munmap(page0, PAGE_SIZE); > - } > - > - free(page_array); > - return 0; > - > - error_out: > - free(page_array); > - return -1; > -} > - > -static int xc_hvm_build_internal(xc_interface *xch, > - uint32_t domid, > - int memsize, > - int target, > - char *image, > - unsigned long image_size) > -{ > - if ( (image == NULL) || (image_size == 0) ) > - { > - ERROR("Image required"); > - return -1; > - } > - > - return setup_guest(xch, domid, memsize, target, image, image_size); > -} > - > -/* xc_hvm_build: > - * Create a domain for a virtualized Linux, using files/filenames. > - */ > -int xc_hvm_build(xc_interface *xch, > - uint32_t domid, > - int memsize, > - const char *image_name) > -{ > - char *image; > - int sts; > - unsigned long image_size; > - > - if ( (image_name == NULL) || > - ((image = xc_read_image(xch, image_name, &image_size)) == NULL) ) > - return -1; > - > - sts = xc_hvm_build_internal(xch, domid, memsize, memsize, image, image_size); > - > - free(image); > - > - return sts; > -} > - > -/* xc_hvm_build_target_mem: > - * Create a domain for a pre-ballooned virtualized Linux, using > - * files/filenames. If target < memsize, domain is created with > - * memsize pages marked populate-on-demand, > - * calculating pod cache size based on target. > - * If target == memsize, pages are populated normally. > - */ > -int xc_hvm_build_target_mem(xc_interface *xch, > - uint32_t domid, > - int memsize, > - int target, > - const char *image_name) > -{ > - char *image; > - int sts; > - unsigned long image_size; > - > - if ( (image_name == NULL) || > - ((image = xc_read_image(xch, image_name, &image_size)) == NULL) ) > - return -1; > - > - sts = xc_hvm_build_internal(xch, domid, memsize, target, image, image_size); > - > - free(image); > - > - return sts; > -} > - > -/* xc_hvm_build_mem: > - * Create a domain for a virtualized Linux, using memory buffers. > - */ > -int xc_hvm_build_mem(xc_interface *xch, > - uint32_t domid, > - int memsize, > - const char *image_buffer, > - unsigned long image_size) > -{ > - int sts; > - unsigned long img_len; > - char *img; > - > - /* Validate that there is a kernel buffer */ > - > - if ( (image_buffer == NULL) || (image_size == 0) ) > - { > - ERROR("kernel image buffer not present"); > - return -1; > - } > - > - img = xc_inflate_buffer(xch, image_buffer, image_size, &img_len); > - if ( img == NULL ) > - { > - ERROR("unable to inflate ram disk buffer"); > - return -1; > - } > - > - sts = xc_hvm_build_internal(xch, domid, memsize, memsize, > - img, img_len); > - > - /* xc_inflate_buffer may return the original buffer pointer (for > - for already inflated buffers), so exercise some care in freeing */ > - > - if ( (img != NULL) && (img != image_buffer) ) > - free(img); > - > - return sts; > -} > - > -/* > - * Local variables: > - * mode: C > - * c-set-style: "BSD" > - * c-basic-offset: 4 > - * tab-width: 4 > - * indent-tabs-mode: nil > - * End: > - */ > diff --git a/tools/libxc/xc_hvm_build_arm.c b/tools/libxc/xc_hvm_build_arm.c > new file mode 100644 > index 0000000..010ebdb > --- /dev/null > +++ b/tools/libxc/xc_hvm_build_arm.c > @@ -0,0 +1,61 @@ > +/****************************************************************************** > + * 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 > + * > + * Copyright (c) 2011, Citrix Systems > + */ > + > +#include <inttypes.h> > +#include <errno.h> > +#include <xenctrl.h> > +#include <xenguest.h> > + > +int xc_hvm_build(xc_interface *xch, > + uint32_t domid, > + int memsize, > + const char *image_name) > +{ > + errno = ENOSYS; > + return -1; > +} > + > +int xc_hvm_build_target_mem(xc_interface *xch, > + uint32_t domid, > + int memsize, > + int target, > + const char *image_name) > +{ > + errno = ENOSYS; > + return -1; > +} > + > +int xc_hvm_build_mem(xc_interface *xch, > + uint32_t domid, > + int memsize, > + const char *image_buffer, > + unsigned long image_size) > +{ > + errno = ENOSYS; > + return -1; > +} > + > +/* > + * Local variables: > + * mode: C > + * c-set-style: "BSD" > + * c-basic-offset: 4 > + * tab-width: 4 > + * indent-tabs-mode: nil > + * End: > + */ > diff --git a/tools/libxc/xc_hvm_build_x86.c b/tools/libxc/xc_hvm_build_x86.c > new file mode 100644 > index 0000000..1fa5658 > --- /dev/null > +++ b/tools/libxc/xc_hvm_build_x86.c > @@ -0,0 +1,511 @@ > +/****************************************************************************** > + * xc_hvm_build.c > + * > + * 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 <stddef.h> > +#include <inttypes.h> > +#include <stdlib.h> > +#include <unistd.h> > +#include <zlib.h> > + > +#include "xg_private.h" > +#include "xc_private.h" > + > +#include <xen/foreign/x86_32.h> > +#include <xen/foreign/x86_64.h> > +#include <xen/hvm/hvm_info_table.h> > +#include <xen/hvm/params.h> > +#include <xen/hvm/e820.h> > + > +#include <xen/libelf/libelf.h> > + > +#define SUPERPAGE_2MB_SHIFT 9 > +#define SUPERPAGE_2MB_NR_PFNS (1UL << SUPERPAGE_2MB_SHIFT) > +#define SUPERPAGE_1GB_SHIFT 18 > +#define SUPERPAGE_1GB_NR_PFNS (1UL << SUPERPAGE_1GB_SHIFT) > + > +#define SPECIALPAGE_BUFIOREQ 0 > +#define SPECIALPAGE_XENSTORE 1 > +#define SPECIALPAGE_IOREQ 2 > +#define SPECIALPAGE_IDENT_PT 3 > +#define SPECIALPAGE_CONSOLE 4 > +#define NR_SPECIAL_PAGES 5 > +#define special_pfn(x) (0xff000u - NR_SPECIAL_PAGES + (x)) > + > +static void build_hvm_info(void *hvm_info_page, uint64_t mem_size) > +{ > + struct hvm_info_table *hvm_info = (struct hvm_info_table *) > + (((unsigned char *)hvm_info_page) + HVM_INFO_OFFSET); > + uint64_t lowmem_end = mem_size, highmem_end = 0; > + uint8_t sum; > + int i; > + > + if ( lowmem_end > HVM_BELOW_4G_RAM_END ) > + { > + highmem_end = lowmem_end + (1ull<<32) - HVM_BELOW_4G_RAM_END; > + lowmem_end = HVM_BELOW_4G_RAM_END; > + } > + > + memset(hvm_info_page, 0, PAGE_SIZE); > + > + /* Fill in the header. */ > + strncpy(hvm_info->signature, "HVM INFO", 8); > + hvm_info->length = sizeof(struct hvm_info_table); > + > + /* Sensible defaults: these can be overridden by the caller. */ > + hvm_info->apic_mode = 1; > + hvm_info->nr_vcpus = 1; > + memset(hvm_info->vcpu_online, 0xff, sizeof(hvm_info->vcpu_online)); > + > + /* Memory parameters. */ > + hvm_info->low_mem_pgend = lowmem_end >> PAGE_SHIFT; > + hvm_info->high_mem_pgend = highmem_end >> PAGE_SHIFT; > + hvm_info->reserved_mem_pgstart = special_pfn(0); > + > + /* Finish with the checksum. */ > + for ( i = 0, sum = 0; i < hvm_info->length; i++ ) > + sum += ((uint8_t *)hvm_info)[i]; > + hvm_info->checksum = -sum; > +} > + > +static int loadelfimage( > + xc_interface *xch, > + struct elf_binary *elf, uint32_t dom, unsigned long *parray) > +{ > + privcmd_mmap_entry_t *entries = NULL; > + unsigned long pfn_start = elf->pstart >> PAGE_SHIFT; > + unsigned long pfn_end = (elf->pend + PAGE_SIZE - 1) >> PAGE_SHIFT; > + size_t pages = pfn_end - pfn_start; > + int i, rc = -1; > + > + /* Map address space for initial elf image. */ > + entries = calloc(pages, sizeof(privcmd_mmap_entry_t)); > + if ( entries == NULL ) > + goto err; > + > + for ( i = 0; i < pages; i++ ) > + entries[i].mfn = parray[(elf->pstart >> PAGE_SHIFT) + i]; > + > + elf->dest = xc_map_foreign_ranges( > + xch, dom, pages << PAGE_SHIFT, PROT_READ | PROT_WRITE, 1 << PAGE_SHIFT, > + entries, pages); > + if ( elf->dest == NULL ) > + goto err; > + > + elf->dest += elf->pstart & (PAGE_SIZE - 1); > + > + /* Load the initial elf image. */ > + rc = elf_load_binary(elf); > + if ( rc < 0 ) > + PERROR("Failed to load elf binary\n"); > + > + munmap(elf->dest, pages << PAGE_SHIFT); > + elf->dest = NULL; > + > + err: > + free(entries); > + > + return rc; > +} > + > +/* > + * Check whether there exists mmio hole in the specified memory range. > + * Returns 1 if exists, else returns 0. > + */ > +static int check_mmio_hole(uint64_t start, uint64_t memsize) > +{ > + if ( start + memsize <= HVM_BELOW_4G_MMIO_START || > + start >= HVM_BELOW_4G_MMIO_START + HVM_BELOW_4G_MMIO_LENGTH ) > + return 0; > + else > + return 1; > +} > + > +static int setup_guest(xc_interface *xch, > + uint32_t dom, int memsize, int target, > + char *image, unsigned long image_size) > +{ > + xen_pfn_t *page_array = NULL; > + unsigned long i, nr_pages = (unsigned long)memsize << (20 - PAGE_SHIFT); > + unsigned long target_pages = (unsigned long)target << (20 - PAGE_SHIFT); > + unsigned long entry_eip, cur_pages, cur_pfn; > + void *hvm_info_page; > + uint32_t *ident_pt; > + struct elf_binary elf; > + uint64_t v_start, v_end; > + int rc; > + xen_capabilities_info_t caps; > + unsigned long stat_normal_pages = 0, stat_2mb_pages = 0, > + stat_1gb_pages = 0; > + int pod_mode = 0; > + > + /* An HVM guest must be initialised with at least 2MB memory. */ > + if ( memsize < 2 || target < 2 ) > + goto error_out; > + > + if ( memsize > target ) > + pod_mode = 1; > + > + memset(&elf, 0, sizeof(elf)); > + if ( elf_init(&elf, image, image_size) != 0 ) > + goto error_out; > + > + xc_elf_set_logfile(xch, &elf, 1); > + > + elf_parse_binary(&elf); > + v_start = 0; > + v_end = (unsigned long long)memsize << 20; > + > + if ( xc_version(xch, XENVER_capabilities, &caps) != 0 ) > + { > + PERROR("Could not get Xen capabilities"); > + goto error_out; > + } > + > + IPRINTF("VIRTUAL MEMORY ARRANGEMENT:\n" > + " Loader: %016"PRIx64"->%016"PRIx64"\n" > + " TOTAL: %016"PRIx64"->%016"PRIx64"\n" > + " ENTRY ADDRESS: %016"PRIx64"\n", > + elf.pstart, elf.pend, > + v_start, v_end, > + elf_uval(&elf, elf.ehdr, e_entry)); > + > + if ( (page_array = malloc(nr_pages * sizeof(xen_pfn_t))) == NULL ) > + { > + PERROR("Could not allocate memory."); > + goto error_out; > + } > + > + for ( i = 0; i < nr_pages; i++ ) > + page_array[i] = i; > + for ( i = HVM_BELOW_4G_RAM_END >> PAGE_SHIFT; i < nr_pages; i++ ) > + page_array[i] += HVM_BELOW_4G_MMIO_LENGTH >> PAGE_SHIFT; > + > + /* > + * Allocate memory for HVM guest, skipping VGA hole 0xA0000-0xC0000. > + * > + * We attempt to allocate 1GB pages if possible. It falls back on 2MB > + * pages if 1GB allocation fails. 4KB pages will be used eventually if > + * both fail. > + * > + * Under 2MB mode, we allocate pages in batches of no more than 8MB to > + * ensure that we can be preempted and hence dom0 remains responsive. > + */ > + rc = xc_domain_populate_physmap_exact( > + xch, dom, 0xa0, 0, 0, &page_array[0x00]); > + cur_pages = 0xc0; > + stat_normal_pages = 0xc0; > + while ( (rc == 0) && (nr_pages > cur_pages) ) > + { > + /* Clip count to maximum 1GB extent. */ > + unsigned long count = nr_pages - cur_pages; > + unsigned long max_pages = SUPERPAGE_1GB_NR_PFNS; > + > + if ( count > max_pages ) > + count = max_pages; > + > + cur_pfn = page_array[cur_pages]; > + > + /* Take care the corner cases of super page tails */ > + if ( ((cur_pfn & (SUPERPAGE_1GB_NR_PFNS-1)) != 0) && > + (count > (-cur_pfn & (SUPERPAGE_1GB_NR_PFNS-1))) ) > + count = -cur_pfn & (SUPERPAGE_1GB_NR_PFNS-1); > + else if ( ((count & (SUPERPAGE_1GB_NR_PFNS-1)) != 0) && > + (count > SUPERPAGE_1GB_NR_PFNS) ) > + count &= ~(SUPERPAGE_1GB_NR_PFNS - 1); > + > + /* Attemp to allocate 1GB super page. Because in each pass we only > + * allocate at most 1GB, we don''t have to clip super page boundaries. > + */ > + if ( ((count | cur_pfn) & (SUPERPAGE_1GB_NR_PFNS - 1)) == 0 && > + /* Check if there exists MMIO hole in the 1GB memory range */ > + !check_mmio_hole(cur_pfn << PAGE_SHIFT, > + SUPERPAGE_1GB_NR_PFNS << PAGE_SHIFT) ) > + { > + long done; > + unsigned long nr_extents = count >> SUPERPAGE_1GB_SHIFT; > + xen_pfn_t sp_extents[nr_extents]; > + > + for ( i = 0; i < nr_extents; i++ ) > + sp_extents[i] = page_array[cur_pages+(i<<SUPERPAGE_1GB_SHIFT)]; > + > + done = xc_domain_populate_physmap(xch, dom, nr_extents, SUPERPAGE_1GB_SHIFT, > + pod_mode ? XENMEMF_populate_on_demand : 0, > + sp_extents); > + > + if ( done > 0 ) > + { > + stat_1gb_pages += done; > + done <<= SUPERPAGE_1GB_SHIFT; > + cur_pages += done; > + count -= done; > + } > + } > + > + if ( count != 0 ) > + { > + /* Clip count to maximum 8MB extent. */ > + max_pages = SUPERPAGE_2MB_NR_PFNS * 4; > + if ( count > max_pages ) > + count = max_pages; > + > + /* Clip partial superpage extents to superpage boundaries. */ > + if ( ((cur_pfn & (SUPERPAGE_2MB_NR_PFNS-1)) != 0) && > + (count > (-cur_pfn & (SUPERPAGE_2MB_NR_PFNS-1))) ) > + count = -cur_pfn & (SUPERPAGE_2MB_NR_PFNS-1); > + else if ( ((count & (SUPERPAGE_2MB_NR_PFNS-1)) != 0) && > + (count > SUPERPAGE_2MB_NR_PFNS) ) > + count &= ~(SUPERPAGE_2MB_NR_PFNS - 1); /* clip non-s.p. tail */ > + > + /* Attempt to allocate superpage extents. */ > + if ( ((count | cur_pfn) & (SUPERPAGE_2MB_NR_PFNS - 1)) == 0 ) > + { > + long done; > + unsigned long nr_extents = count >> SUPERPAGE_2MB_SHIFT; > + xen_pfn_t sp_extents[nr_extents]; > + > + for ( i = 0; i < nr_extents; i++ ) > + sp_extents[i] = page_array[cur_pages+(i<<SUPERPAGE_2MB_SHIFT)]; > + > + done = xc_domain_populate_physmap(xch, dom, nr_extents, SUPERPAGE_2MB_SHIFT, > + pod_mode ? XENMEMF_populate_on_demand : 0, > + sp_extents); > + > + if ( done > 0 ) > + { > + stat_2mb_pages += done; > + done <<= SUPERPAGE_2MB_SHIFT; > + cur_pages += done; > + count -= done; > + } > + } > + } > + > + /* Fall back to 4kB extents. */ > + if ( count != 0 ) > + { > + rc = xc_domain_populate_physmap_exact( > + xch, dom, count, 0, 0, &page_array[cur_pages]); > + cur_pages += count; > + stat_normal_pages += count; > + } > + } > + > + /* Subtract 0x20 from target_pages for the VGA "hole". Xen will > + * adjust the PoD cache size so that domain tot_pages will be > + * target_pages - 0x20 after this call. */ > + if ( pod_mode ) > + rc = xc_domain_set_pod_target(xch, dom, target_pages - 0x20, > + NULL, NULL, NULL); > + > + if ( rc != 0 ) > + { > + PERROR("Could not allocate memory for HVM guest."); > + goto error_out; > + } > + > + IPRINTF("PHYSICAL MEMORY ALLOCATION:\n" > + " 4KB PAGES: 0x%016lx\n" > + " 2MB PAGES: 0x%016lx\n" > + " 1GB PAGES: 0x%016lx\n", > + stat_normal_pages, stat_2mb_pages, stat_1gb_pages); > + > + if ( loadelfimage(xch, &elf, dom, page_array) != 0 ) > + goto error_out; > + > + if ( (hvm_info_page = xc_map_foreign_range( > + xch, dom, PAGE_SIZE, PROT_READ | PROT_WRITE, > + HVM_INFO_PFN)) == NULL ) > + goto error_out; > + build_hvm_info(hvm_info_page, v_end); > + munmap(hvm_info_page, PAGE_SIZE); > + > + /* Allocate and clear special pages. */ > + for ( i = 0; i < NR_SPECIAL_PAGES; i++ ) > + { > + xen_pfn_t pfn = special_pfn(i); > + rc = xc_domain_populate_physmap_exact(xch, dom, 1, 0, 0, &pfn); > + if ( rc != 0 ) > + { > + PERROR("Could not allocate %d''th special page.", i); > + goto error_out; > + } > + if ( xc_clear_domain_page(xch, dom, special_pfn(i)) ) > + goto error_out; > + } > + > + xc_set_hvm_param(xch, dom, HVM_PARAM_STORE_PFN, > + special_pfn(SPECIALPAGE_XENSTORE)); > + xc_set_hvm_param(xch, dom, HVM_PARAM_BUFIOREQ_PFN, > + special_pfn(SPECIALPAGE_BUFIOREQ)); > + xc_set_hvm_param(xch, dom, HVM_PARAM_IOREQ_PFN, > + special_pfn(SPECIALPAGE_IOREQ)); > + xc_set_hvm_param(xch, dom, HVM_PARAM_CONSOLE_PFN, > + special_pfn(SPECIALPAGE_CONSOLE)); > + > + /* > + * Identity-map page table is required for running with CR0.PG=0 when > + * using Intel EPT. Create a 32-bit non-PAE page directory of superpages. > + */ > + if ( (ident_pt = xc_map_foreign_range( > + xch, dom, PAGE_SIZE, PROT_READ | PROT_WRITE, > + special_pfn(SPECIALPAGE_IDENT_PT))) == NULL ) > + goto error_out; > + for ( i = 0; i < PAGE_SIZE / sizeof(*ident_pt); i++ ) > + ident_pt[i] = ((i << 22) | _PAGE_PRESENT | _PAGE_RW | _PAGE_USER | > + _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE); > + munmap(ident_pt, PAGE_SIZE); > + xc_set_hvm_param(xch, dom, HVM_PARAM_IDENT_PT, > + special_pfn(SPECIALPAGE_IDENT_PT) << PAGE_SHIFT); > + > + /* Insert JMP <rel32> instruction at address 0x0 to reach entry point. */ > + entry_eip = elf_uval(&elf, elf.ehdr, e_entry); > + if ( entry_eip != 0 ) > + { > + char *page0 = xc_map_foreign_range( > + xch, dom, PAGE_SIZE, PROT_READ | PROT_WRITE, 0); > + if ( page0 == NULL ) > + goto error_out; > + page0[0] = 0xe9; > + *(uint32_t *)&page0[1] = entry_eip - 5; > + munmap(page0, PAGE_SIZE); > + } > + > + free(page_array); > + return 0; > + > + error_out: > + free(page_array); > + return -1; > +} > + > +static int xc_hvm_build_internal(xc_interface *xch, > + uint32_t domid, > + int memsize, > + int target, > + char *image, > + unsigned long image_size) > +{ > + if ( (image == NULL) || (image_size == 0) ) > + { > + ERROR("Image required"); > + return -1; > + } > + > + return setup_guest(xch, domid, memsize, target, image, image_size); > +} > + > +/* xc_hvm_build: > + * Create a domain for a virtualized Linux, using files/filenames. > + */ > +int xc_hvm_build(xc_interface *xch, > + uint32_t domid, > + int memsize, > + const char *image_name) > +{ > + char *image; > + int sts; > + unsigned long image_size; > + > + if ( (image_name == NULL) || > + ((image = xc_read_image(xch, image_name, &image_size)) == NULL) ) > + return -1; > + > + sts = xc_hvm_build_internal(xch, domid, memsize, memsize, image, image_size); > + > + free(image); > + > + return sts; > +} > + > +/* xc_hvm_build_target_mem: > + * Create a domain for a pre-ballooned virtualized Linux, using > + * files/filenames. If target < memsize, domain is created with > + * memsize pages marked populate-on-demand, > + * calculating pod cache size based on target. > + * If target == memsize, pages are populated normally. > + */ > +int xc_hvm_build_target_mem(xc_interface *xch, > + uint32_t domid, > + int memsize, > + int target, > + const char *image_name) > +{ > + char *image; > + int sts; > + unsigned long image_size; > + > + if ( (image_name == NULL) || > + ((image = xc_read_image(xch, image_name, &image_size)) == NULL) ) > + return -1; > + > + sts = xc_hvm_build_internal(xch, domid, memsize, target, image, image_size); > + > + free(image); > + > + return sts; > +} > + > +/* xc_hvm_build_mem: > + * Create a domain for a virtualized Linux, using memory buffers. > + */ > +int xc_hvm_build_mem(xc_interface *xch, > + uint32_t domid, > + int memsize, > + const char *image_buffer, > + unsigned long image_size) > +{ > + int sts; > + unsigned long img_len; > + char *img; > + > + /* Validate that there is a kernel buffer */ > + > + if ( (image_buffer == NULL) || (image_size == 0) ) > + { > + ERROR("kernel image buffer not present"); > + return -1; > + } > + > + img = xc_inflate_buffer(xch, image_buffer, image_size, &img_len); > + if ( img == NULL ) > + { > + ERROR("unable to inflate ram disk buffer"); > + return -1; > + } > + > + sts = xc_hvm_build_internal(xch, domid, memsize, memsize, > + img, img_len); > + > + /* xc_inflate_buffer may return the original buffer pointer (for > + for already inflated buffers), so exercise some care in freeing */ > + > + if ( (img != NULL) && (img != image_buffer) ) > + free(img); > + > + return sts; > +} > + > +/* > + * Local variables: > + * mode: C > + * c-set-style: "BSD" > + * c-basic-offset: 4 > + * tab-width: 4 > + * indent-tabs-mode: nil > + * End: > + */ > diff --git a/tools/libxc/xc_nomigrate.c b/tools/libxc/xc_nomigrate.c > new file mode 100644 > index 0000000..e734d73 > --- /dev/null > +++ b/tools/libxc/xc_nomigrate.c > @@ -0,0 +1,53 @@ > +/****************************************************************************** > + * 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 > + * > + * Copyright (c) 2011, Citrix Systems > + */ > + > +#include <inttypes.h> > +#include <errno.h> > +#include <xenctrl.h> > +#include <xenguest.h> > + > +int xc_domain_save(xc_interface *xch, int io_fd, uint32_t dom, uint32_t max_iters, > + uint32_t max_factor, uint32_t flags, > + struct save_callbacks* callbacks, int hvm, > + unsigned long vm_generationid_addr) > +{ > + errno = ENOSYS; > + return -1; > +} > + > +int xc_domain_restore(xc_interface *xch, int io_fd, uint32_t dom, > + unsigned int store_evtchn, unsigned long *store_mfn, > + domid_t store_domid, unsigned int console_evtchn, > + unsigned long *console_mfn, domid_t console_domid, > + unsigned int hvm, unsigned int pae, int superpages, > + int no_incr_generationid, > + unsigned long *vm_generationid_addr) > +{ > + errno = ENOSYS; > + return -1; > +} > + > +/* > + * Local variables: > + * mode: C > + * c-set-style: "BSD" > + * c-basic-offset: 4 > + * tab-width: 4 > + * indent-tabs-mode: nil > + * End: > + */ > -- > 1.7.2.5 >
Ian Campbell
2012-Feb-24 09:25 UTC
Re: [PATCH v5 7/7] libxl: Introduce libxl__arch_domain_create
On Thu, 2012-02-23 at 14:51 +0000, Stefano Stabellini wrote:> Introduce an arch specific internal domain creation function. At the > moment only x86 provides an implementation. > > Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>Acked-by: Ian Campbell <ian.campbell@citrix.com> (I thought I acked this last time)> --- > tools/libxl/Makefile | 6 +- > tools/libxl/libxl_arch.h | 22 ++++ > tools/libxl/libxl_create.c | 12 +-- > tools/libxl/libxl_internal.h | 2 - > tools/libxl/libxl_noarch.c | 8 ++ > tools/libxl/libxl_pci.c | 242 --------------------------------------- > tools/libxl/libxl_x86.c | 259 ++++++++++++++++++++++++++++++++++++++++++ > 7 files changed, 294 insertions(+), 257 deletions(-) > create mode 100644 tools/libxl/libxl_arch.h > create mode 100644 tools/libxl/libxl_noarch.c > create mode 100644 tools/libxl/libxl_x86.c > > diff --git a/tools/libxl/Makefile b/tools/libxl/Makefile > index 41b6ac4..ba5852b 100644 > --- a/tools/libxl/Makefile > +++ b/tools/libxl/Makefile > @@ -34,9 +34,9 @@ LIBXL_OBJS-y += libxl_blktap2.o > else > LIBXL_OBJS-y += libxl_noblktap2.o > endif > -LIBXL_OBJS-$(CONFIG_X86) += libxl_cpuid.o > -LIBXL_OBJS-$(CONFIG_IA64) += libxl_nocpuid.o > -LIBXL_OBJS-$(CONFIG_ARM) += libxl_nocpuid.o > +LIBXL_OBJS-$(CONFIG_X86) += libxl_cpuid.o libxl_x86.o > +LIBXL_OBJS-$(CONFIG_IA64) += libxl_nocpuid.o libxl_noarch.o > +LIBXL_OBJS-$(CONFIG_ARM) += libxl_nocpuid.o libxl_noarch.o > > ifeq ($(CONFIG_NetBSD),y) > LIBXL_OBJS-y += libxl_netbsd.o > diff --git a/tools/libxl/libxl_arch.h b/tools/libxl/libxl_arch.h > new file mode 100644 > index 0000000..d1bbdf7 > --- /dev/null > +++ b/tools/libxl/libxl_arch.h > @@ -0,0 +1,22 @@ > +/* > + * Copyright (C) 2012 Citrix Ltd. > + * > + * This program 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 only. with the special > + * exception on linking described in file LICENSE. > + * > + * This program 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. > + */ > + > +#ifndef LIBXL_ARCH_H > +#define LIBXL_ARCH_H > + > +/* arch specific internal domain creation function */ > +int libxl__arch_domain_create(libxl__gc *gc, libxl_domain_config *d_config, > + uint32_t domid); > + > +#endif > diff --git a/tools/libxl/libxl_create.c b/tools/libxl/libxl_create.c > index f28d814..ff589a8 100644 > --- a/tools/libxl/libxl_create.c > +++ b/tools/libxl/libxl_create.c > @@ -18,6 +18,7 @@ > #include "libxl_osdeps.h" /* must come before any other headers */ > > #include "libxl_internal.h" > +#include "libxl_arch.h" > > #include <xc_dom.h> > #include <xenguest.h> > @@ -616,16 +617,7 @@ static int do_domain_create(libxl__gc *gc, libxl_domain_config *d_config, > goto error_out; > } > } > - > - if (d_config->c_info.type == LIBXL_DOMAIN_TYPE_PV && > - d_config->b_info.u.pv.e820_host) { > - int rc; > - rc = libxl__e820_alloc(gc, domid, d_config); > - if (rc) > - LIBXL__LOG_ERRNO(ctx, LIBXL__LOG_ERROR, > - "Failed while collecting E820 with: %d (errno:%d)\n", > - rc, errno); > - } > + libxl__arch_domain_create(gc, d_config, domid); > if ( cb && (d_config->c_info.type == LIBXL_DOMAIN_TYPE_HVM || > (d_config->c_info.type == LIBXL_DOMAIN_TYPE_PV && > d_config->b_info.u.pv.bootloader ))) { > diff --git a/tools/libxl/libxl_internal.h b/tools/libxl/libxl_internal.h > index 8846c68..bd384e2 100644 > --- a/tools/libxl/libxl_internal.h > +++ b/tools/libxl/libxl_internal.h > @@ -975,8 +975,6 @@ _hidden int libxl__error_set(libxl__gc *gc, int code); > _hidden int libxl__file_reference_map(libxl_file_reference *f); > _hidden int libxl__file_reference_unmap(libxl_file_reference *f); > > -_hidden int libxl__e820_alloc(libxl__gc *gc, uint32_t domid, libxl_domain_config *d_config); > - > /* parse the string @s as a sequence of 6 colon separated bytes in to @mac */ > _hidden int libxl__parse_mac(const char *s, libxl_mac mac); > /* compare mac address @a and @b. 0 if the same, -ve if a<b and +ve if a>b */ > diff --git a/tools/libxl/libxl_noarch.c b/tools/libxl/libxl_noarch.c > new file mode 100644 > index 0000000..7893535 > --- /dev/null > +++ b/tools/libxl/libxl_noarch.c > @@ -0,0 +1,8 @@ > +#include "libxl_internal.h" > +#include "libxl_arch.h" > + > +int libxl__arch_domain_create(libxl__gc *gc, libxl_domain_config *d_config, > + uint32_t domid) > +{ > + return 0; > +} > diff --git a/tools/libxl/libxl_pci.c b/tools/libxl/libxl_pci.c > index 33425f5..d960f4b 100644 > --- a/tools/libxl/libxl_pci.c > +++ b/tools/libxl/libxl_pci.c > @@ -1147,248 +1147,6 @@ int libxl__device_pci_destroy_all(libxl__gc *gc, uint32_t domid) > return 0; > } > > -static const char *e820_names(int type) > -{ > - switch (type) { > - case E820_RAM: return "RAM"; > - case E820_RESERVED: return "Reserved"; > - case E820_ACPI: return "ACPI"; > - case E820_NVS: return "ACPI NVS"; > - case E820_UNUSABLE: return "Unusable"; > - default: break; > - } > - return "Unknown"; > -} > - > -static int e820_sanitize(libxl_ctx *ctx, struct e820entry src[], > - uint32_t *nr_entries, > - unsigned long map_limitkb, > - unsigned long balloon_kb) > -{ > - uint64_t delta_kb = 0, start = 0, start_kb = 0, last = 0, ram_end; > - uint32_t i, idx = 0, nr; > - struct e820entry e820[E820MAX]; > - > - if (!src || !map_limitkb || !balloon_kb || !nr_entries) > - return ERROR_INVAL; > - > - nr = *nr_entries; > - if (!nr) > - return ERROR_INVAL; > - > - if (nr > E820MAX) > - return ERROR_NOMEM; > - > - /* Weed out anything under 1MB */ > - for (i = 0; i < nr; i++) { > - if (src[i].addr > 0x100000) > - continue; > - > - src[i].type = 0; > - src[i].size = 0; > - src[i].addr = -1ULL; > - } > - > - /* Find the lowest and highest entry in E820, skipping over > - * undesired entries. */ > - start = -1ULL; > - last = 0; > - for (i = 0; i < nr; i++) { > - if ((src[i].type == E820_RAM) || > - (src[i].type == E820_UNUSABLE) || > - (src[i].type == 0)) > - continue; > - > - start = src[i].addr < start ? src[i].addr : start; > - last = src[i].addr + src[i].size > last ? > - src[i].addr + src[i].size > last : last; > - } > - if (start > 1024) > - start_kb = start >> 10; > - > - /* Add the memory RAM region for the guest */ > - e820[idx].addr = 0; > - e820[idx].size = (uint64_t)map_limitkb << 10; > - e820[idx].type = E820_RAM; > - > - /* .. and trim if neccessary */ > - if (start_kb && map_limitkb > start_kb) { > - delta_kb = map_limitkb - start_kb; > - if (delta_kb) > - e820[idx].size -= (uint64_t)(delta_kb << 10); > - } > - /* Note: We don''t touch balloon_kb here. Will add it at the end. */ > - ram_end = e820[idx].addr + e820[idx].size; > - idx ++; > - > - LIBXL__LOG(ctx, LIBXL__LOG_DEBUG, "Memory: %"PRIu64"kB End of RAM: " \ > - "0x%"PRIx64" (PFN) Delta: %"PRIu64"kB, PCI start: %"PRIu64"kB " \ > - "(0x%"PRIx64" PFN), Balloon %"PRIu64"kB\n", (uint64_t)map_limitkb, > - ram_end >> 12, delta_kb, start_kb ,start >> 12, > - (uint64_t)balloon_kb); > - > - > - /* This whole code below is to guard against if the Intel IGD is passed into > - * the guest. If we don''t pass in IGD, this whole code can be ignored. > - * > - * The reason for this code is that Intel boxes fill their E820 with > - * E820_RAM amongst E820_RESERVED and we can''t just ditch those E820_RAM. > - * That is b/c any "gaps" in the E820 is considered PCI I/O space by > - * Linux and it would be utilized by the Intel IGD as I/O space while > - * in reality it was an RAM region. > - * > - * What this means is that we have to walk the E820 and for any region > - * that is RAM and below 4GB and above ram_end, needs to change its type > - * to E820_UNUSED. We also need to move some of the E820_RAM regions if > - * the overlap with ram_end. */ > - for (i = 0; i < nr; i++) { > - uint64_t end = src[i].addr + src[i].size; > - > - /* We don''t care about E820_UNUSABLE, but we need to > - * change the type to zero b/c the loop after this > - * sticks E820_UNUSABLE on the guest''s E820 but ignores > - * the ones with type zero. */ > - if ((src[i].type == E820_UNUSABLE) || > - /* Any region that is within the "RAM region" can > - * be safely ditched. */ > - (end < ram_end)) { > - src[i].type = 0; > - continue; > - } > - > - /* Look only at RAM regions. */ > - if (src[i].type != E820_RAM) > - continue; > - > - /* We only care about RAM regions below 4GB. */ > - if (src[i].addr >= (1ULL<<32)) > - continue; > - > - /* E820_RAM overlaps with our RAM region. Move it */ > - if (src[i].addr < ram_end) { > - uint64_t delta; > - > - src[i].type = E820_UNUSABLE; > - delta = ram_end - src[i].addr; > - /* The end < ram_end should weed this out */ > - if (src[i].size - delta < 0) > - src[i].type = 0; > - else { > - src[i].size -= delta; > - src[i].addr = ram_end; > - } > - if (src[i].addr + src[i].size != end) { > - /* We messed up somewhere */ > - src[i].type = 0; > - LIBXL__LOG_ERRNO(ctx, LIBXL__LOG_ERROR, "Computed E820 wrongly. Continuing on."); > - } > - } > - /* Lastly, convert the RAM to UNSUABLE. Look in the Linux kernel > - at git commit 2f14ddc3a7146ea4cd5a3d1ecd993f85f2e4f948 > - "xen/setup: Inhibit resource API from using System RAM E820 > - gaps as PCI mem gaps" for full explanation. */ > - if (end > ram_end) > - src[i].type = E820_UNUSABLE; > - } > - > - /* Check if there is a region between ram_end and start. */ > - if (start > ram_end) { > - int add_unusable = 1; > - for (i = 0; i < nr && add_unusable; i++) { > - if (src[i].type != E820_UNUSABLE) > - continue; > - if (ram_end != src[i].addr) > - continue; > - if (start != src[i].addr + src[i].size) { > - /* there is one, adjust it */ > - src[i].size = start - src[i].addr; > - } > - add_unusable = 0; > - } > - /* .. and if not present, add it in. This is to guard against > - the Linux guest assuming that the gap between the end of > - RAM region and the start of the E820_[ACPI,NVS,RESERVED] > - is PCI I/O space. Which it certainly is _not_. */ > - if (add_unusable) { > - e820[idx].type = E820_UNUSABLE; > - e820[idx].addr = ram_end; > - e820[idx].size = start - ram_end; > - idx++; > - } > - } > - /* Almost done: copy them over, ignoring the undesireable ones */ > - for (i = 0; i < nr; i++) { > - if ((src[i].type == E820_RAM) || > - (src[i].type == 0)) > - continue; > - > - e820[idx].type = src[i].type; > - e820[idx].addr = src[i].addr; > - e820[idx].size = src[i].size; > - idx++; > - } > - /* At this point we have the mapped RAM + E820 entries from src. */ > - if (balloon_kb) { > - /* and if we truncated the RAM region, then add it to the end. */ > - e820[idx].type = E820_RAM; > - e820[idx].addr = (uint64_t)(1ULL << 32) > last ? > - (uint64_t)(1ULL << 32) : last; > - /* also add the balloon memory to the end. */ > - e820[idx].size = (uint64_t)(delta_kb << 10) + > - (uint64_t)(balloon_kb << 10); > - idx++; > - > - } > - nr = idx; > - > - for (i = 0; i < nr; i++) { > - LIBXL__LOG(ctx, LIBXL__LOG_DEBUG, ":\t[%"PRIx64" -> %"PRIx64"] %s", > - e820[i].addr >> 12, (e820[i].addr + e820[i].size) >> 12, > - e820_names(e820[i].type)); > - } > - > - /* Done: copy the sanitized version. */ > - *nr_entries = nr; > - memcpy(src, e820, nr * sizeof(struct e820entry)); > - return 0; > -} > - > -int libxl__e820_alloc(libxl__gc *gc, uint32_t domid, libxl_domain_config *d_config) > -{ > - libxl_ctx *ctx = libxl__gc_owner(gc); > - int rc; > - uint32_t nr; > - struct e820entry map[E820MAX]; > - libxl_domain_build_info *b_info; > - > - if (d_config == NULL || d_config->c_info.type == LIBXL_DOMAIN_TYPE_HVM) > - return ERROR_INVAL; > - > - b_info = &d_config->b_info; > - if (!b_info->u.pv.e820_host) > - return ERROR_INVAL; > - > - rc = xc_get_machine_memory_map(ctx->xch, map, E820MAX); > - if (rc < 0) { > - errno = rc; > - return ERROR_FAIL; > - } > - nr = rc; > - rc = e820_sanitize(ctx, map, &nr, b_info->target_memkb, > - (b_info->max_memkb - b_info->target_memkb) + > - b_info->u.pv.slack_memkb); > - if (rc) > - return ERROR_FAIL; > - > - rc = xc_domain_set_memory_map(ctx->xch, domid, map, nr); > - > - if (rc < 0) { > - errno = rc; > - return ERROR_FAIL; > - } > - return 0; > -} > - > /* > * Local variables: > * mode: C > diff --git a/tools/libxl/libxl_x86.c b/tools/libxl/libxl_x86.c > new file mode 100644 > index 0000000..7e11f2d > --- /dev/null > +++ b/tools/libxl/libxl_x86.c > @@ -0,0 +1,259 @@ > +#include "libxl_internal.h" > +#include "libxl_arch.h" > + > +static const char *e820_names(int type) > +{ > + switch (type) { > + case E820_RAM: return "RAM"; > + case E820_RESERVED: return "Reserved"; > + case E820_ACPI: return "ACPI"; > + case E820_NVS: return "ACPI NVS"; > + case E820_UNUSABLE: return "Unusable"; > + default: break; > + } > + return "Unknown"; > +} > + > +static int e820_sanitize(libxl_ctx *ctx, struct e820entry src[], > + uint32_t *nr_entries, > + unsigned long map_limitkb, > + unsigned long balloon_kb) > +{ > + uint64_t delta_kb = 0, start = 0, start_kb = 0, last = 0, ram_end; > + uint32_t i, idx = 0, nr; > + struct e820entry e820[E820MAX]; > + > + if (!src || !map_limitkb || !balloon_kb || !nr_entries) > + return ERROR_INVAL; > + > + nr = *nr_entries; > + if (!nr) > + return ERROR_INVAL; > + > + if (nr > E820MAX) > + return ERROR_NOMEM; > + > + /* Weed out anything under 1MB */ > + for (i = 0; i < nr; i++) { > + if (src[i].addr > 0x100000) > + continue; > + > + src[i].type = 0; > + src[i].size = 0; > + src[i].addr = -1ULL; > + } > + > + /* Find the lowest and highest entry in E820, skipping over > + * undesired entries. */ > + start = -1ULL; > + last = 0; > + for (i = 0; i < nr; i++) { > + if ((src[i].type == E820_RAM) || > + (src[i].type == E820_UNUSABLE) || > + (src[i].type == 0)) > + continue; > + > + start = src[i].addr < start ? src[i].addr : start; > + last = src[i].addr + src[i].size > last ? > + src[i].addr + src[i].size > last : last; > + } > + if (start > 1024) > + start_kb = start >> 10; > + > + /* Add the memory RAM region for the guest */ > + e820[idx].addr = 0; > + e820[idx].size = (uint64_t)map_limitkb << 10; > + e820[idx].type = E820_RAM; > + > + /* .. and trim if neccessary */ > + if (start_kb && map_limitkb > start_kb) { > + delta_kb = map_limitkb - start_kb; > + if (delta_kb) > + e820[idx].size -= (uint64_t)(delta_kb << 10); > + } > + /* Note: We don''t touch balloon_kb here. Will add it at the end. */ > + ram_end = e820[idx].addr + e820[idx].size; > + idx ++; > + > + LIBXL__LOG(ctx, LIBXL__LOG_DEBUG, "Memory: %"PRIu64"kB End of RAM: " \ > + "0x%"PRIx64" (PFN) Delta: %"PRIu64"kB, PCI start: %"PRIu64"kB " \ > + "(0x%"PRIx64" PFN), Balloon %"PRIu64"kB\n", (uint64_t)map_limitkb, > + ram_end >> 12, delta_kb, start_kb ,start >> 12, > + (uint64_t)balloon_kb); > + > + > + /* This whole code below is to guard against if the Intel IGD is passed into > + * the guest. If we don''t pass in IGD, this whole code can be ignored. > + * > + * The reason for this code is that Intel boxes fill their E820 with > + * E820_RAM amongst E820_RESERVED and we can''t just ditch those E820_RAM. > + * That is b/c any "gaps" in the E820 is considered PCI I/O space by > + * Linux and it would be utilized by the Intel IGD as I/O space while > + * in reality it was an RAM region. > + * > + * What this means is that we have to walk the E820 and for any region > + * that is RAM and below 4GB and above ram_end, needs to change its type > + * to E820_UNUSED. We also need to move some of the E820_RAM regions if > + * the overlap with ram_end. */ > + for (i = 0; i < nr; i++) { > + uint64_t end = src[i].addr + src[i].size; > + > + /* We don''t care about E820_UNUSABLE, but we need to > + * change the type to zero b/c the loop after this > + * sticks E820_UNUSABLE on the guest''s E820 but ignores > + * the ones with type zero. */ > + if ((src[i].type == E820_UNUSABLE) || > + /* Any region that is within the "RAM region" can > + * be safely ditched. */ > + (end < ram_end)) { > + src[i].type = 0; > + continue; > + } > + > + /* Look only at RAM regions. */ > + if (src[i].type != E820_RAM) > + continue; > + > + /* We only care about RAM regions below 4GB. */ > + if (src[i].addr >= (1ULL<<32)) > + continue; > + > + /* E820_RAM overlaps with our RAM region. Move it */ > + if (src[i].addr < ram_end) { > + uint64_t delta; > + > + src[i].type = E820_UNUSABLE; > + delta = ram_end - src[i].addr; > + /* The end < ram_end should weed this out */ > + if (src[i].size - delta < 0) > + src[i].type = 0; > + else { > + src[i].size -= delta; > + src[i].addr = ram_end; > + } > + if (src[i].addr + src[i].size != end) { > + /* We messed up somewhere */ > + src[i].type = 0; > + LIBXL__LOG_ERRNO(ctx, LIBXL__LOG_ERROR, "Computed E820 wrongly. Continuing on."); > + } > + } > + /* Lastly, convert the RAM to UNSUABLE. Look in the Linux kernel > + at git commit 2f14ddc3a7146ea4cd5a3d1ecd993f85f2e4f948 > + "xen/setup: Inhibit resource API from using System RAM E820 > + gaps as PCI mem gaps" for full explanation. */ > + if (end > ram_end) > + src[i].type = E820_UNUSABLE; > + } > + > + /* Check if there is a region between ram_end and start. */ > + if (start > ram_end) { > + int add_unusable = 1; > + for (i = 0; i < nr && add_unusable; i++) { > + if (src[i].type != E820_UNUSABLE) > + continue; > + if (ram_end != src[i].addr) > + continue; > + if (start != src[i].addr + src[i].size) { > + /* there is one, adjust it */ > + src[i].size = start - src[i].addr; > + } > + add_unusable = 0; > + } > + /* .. and if not present, add it in. This is to guard against > + the Linux guest assuming that the gap between the end of > + RAM region and the start of the E820_[ACPI,NVS,RESERVED] > + is PCI I/O space. Which it certainly is _not_. */ > + if (add_unusable) { > + e820[idx].type = E820_UNUSABLE; > + e820[idx].addr = ram_end; > + e820[idx].size = start - ram_end; > + idx++; > + } > + } > + /* Almost done: copy them over, ignoring the undesireable ones */ > + for (i = 0; i < nr; i++) { > + if ((src[i].type == E820_RAM) || > + (src[i].type == 0)) > + continue; > + > + e820[idx].type = src[i].type; > + e820[idx].addr = src[i].addr; > + e820[idx].size = src[i].size; > + idx++; > + } > + /* At this point we have the mapped RAM + E820 entries from src. */ > + if (balloon_kb) { > + /* and if we truncated the RAM region, then add it to the end. */ > + e820[idx].type = E820_RAM; > + e820[idx].addr = (uint64_t)(1ULL << 32) > last ? > + (uint64_t)(1ULL << 32) : last; > + /* also add the balloon memory to the end. */ > + e820[idx].size = (uint64_t)(delta_kb << 10) + > + (uint64_t)(balloon_kb << 10); > + idx++; > + > + } > + nr = idx; > + > + for (i = 0; i < nr; i++) { > + LIBXL__LOG(ctx, LIBXL__LOG_DEBUG, ":\t[%"PRIx64" -> %"PRIx64"] %s", > + e820[i].addr >> 12, (e820[i].addr + e820[i].size) >> 12, > + e820_names(e820[i].type)); > + } > + > + /* Done: copy the sanitized version. */ > + *nr_entries = nr; > + memcpy(src, e820, nr * sizeof(struct e820entry)); > + return 0; > +} > + > +static int libxl__e820_alloc(libxl__gc *gc, uint32_t domid, libxl_domain_config *d_config) > +{ > + libxl_ctx *ctx = libxl__gc_owner(gc); > + int rc; > + uint32_t nr; > + struct e820entry map[E820MAX]; > + libxl_domain_build_info *b_info; > + > + if (d_config == NULL || d_config->c_info.type == LIBXL_DOMAIN_TYPE_HVM) > + return ERROR_INVAL; > + > + b_info = &d_config->b_info; > + if (!b_info->u.pv.e820_host) > + return ERROR_INVAL; > + > + rc = xc_get_machine_memory_map(ctx->xch, map, E820MAX); > + if (rc < 0) { > + errno = rc; > + return ERROR_FAIL; > + } > + nr = rc; > + rc = e820_sanitize(ctx, map, &nr, b_info->target_memkb, > + (b_info->max_memkb - b_info->target_memkb) + > + b_info->u.pv.slack_memkb); > + if (rc) > + return ERROR_FAIL; > + > + rc = xc_domain_set_memory_map(ctx->xch, domid, map, nr); > + > + if (rc < 0) { > + errno = rc; > + return ERROR_FAIL; > + } > + return 0; > +} > + > +int libxl__arch_domain_create(libxl__gc *gc, libxl_domain_config *d_config, > + uint32_t domid) > +{ > + int rc = 0; > + if (d_config->c_info.type == LIBXL_DOMAIN_TYPE_PV && > + d_config->b_info.u.pv.e820_host) { > + rc = libxl__e820_alloc(gc, domid, d_config); > + if (rc) > + LIBXL__LOG_ERRNO(libxl__gc_owner(gc), LIBXL__LOG_ERROR, > + "Failed while collecting E820 with: %d (errno:%d)\n", > + rc, errno); > + } > + return rc; > +} > -- > 1.7.2.5 >
Stefano Stabellini writes ("[Xen-devel] [PATCH v5 0/7] arm: compile tools"):> this patch series allows tools/ to compile on ARM, mostly providing an > empty implementation for all the arch specific functions that are needed.Thanks. I applied 1/7 and 2/7. 3/7 had conflicts due to David Vrabel''s change to the libxc hvm build API so I stopped there. The others look plausible though and you can put my ack on them. Ian.