* [PATCH v3 3/7] arm: compile libxenguest
2012-02-14 19:53 [PATCH v3 0/7] arm: compile tools Stefano Stabellini
2012-02-14 19:54 ` [PATCH v3 1/7] arm: add stub hvm/save.h Stefano Stabellini
2012-02-14 19:54 ` [PATCH v3 2/7] arm: compile libxc Stefano Stabellini
@ 2012-02-14 19:54 ` Stefano Stabellini
2012-02-14 19:54 ` [PATCH v3 4/7] arm: compile memshr Stefano Stabellini
` (4 subsequent siblings)
7 siblings, 0 replies; 9+ messages in thread
From: Stefano Stabellini @ 2012-02-14 19:54 UTC (permalink / raw)
To: xen-devel; +Cc: david.vrabel, Ian.Campbell, Stefano Stabellini, Tim.Deegan
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 | 49 ++++
tools/libxc/xc_hvm_build.c | 511 ----------------------------------------
tools/libxc/xc_hvm_build_arm.c | 48 ++++
tools/libxc/xc_hvm_build_x86.c | 511 ++++++++++++++++++++++++++++++++++++++++
tools/libxc/xc_nomigrate.c | 41 ++++
6 files changed, 658 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..bdd28e1
--- /dev/null
+++ b/tools/libxc/xc_dom_arm.c
@@ -0,0 +1,49 @@
+/*
+ * 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)
+{
+ return -ENOSYS;
+}
+
+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..6cf65a1
--- /dev/null
+++ b/tools/libxc/xc_hvm_build_arm.c
@@ -0,0 +1,48 @@
+/******************************************************************************
+ * 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)
+{
+ return -ENOSYS;
+}
+
+int xc_hvm_build_target_mem(xc_interface *xch,
+ uint32_t domid,
+ int memsize,
+ int target,
+ const char *image_name)
+{
+ return -ENOSYS;
+}
+
+int xc_hvm_build_mem(xc_interface *xch,
+ uint32_t domid,
+ int memsize,
+ const char *image_buffer,
+ unsigned long image_size)
+{
+ return -ENOSYS;
+}
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..054b8e9
--- /dev/null
+++ b/tools/libxc/xc_nomigrate.c
@@ -0,0 +1,41 @@
+/******************************************************************************
+ * 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)
+{
+ return -ENOSYS;
+}
+
+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)
+{
+ return -ENOSYS;
+}
--
1.7.8.3
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH v3 7/7] libxl: Introduce libxl__arch_domain_create
2012-02-14 19:53 [PATCH v3 0/7] arm: compile tools Stefano Stabellini
` (5 preceding siblings ...)
2012-02-14 19:54 ` [PATCH v3 6/7] arm: compile libxl Stefano Stabellini
@ 2012-02-14 19:54 ` Stefano Stabellini
2012-02-14 20:15 ` [PATCH v3 0/7] arm: compile tools Stefano Stabellini
7 siblings, 0 replies; 9+ messages in thread
From: Stefano Stabellini @ 2012-02-14 19:54 UTC (permalink / raw)
To: xen-devel; +Cc: david.vrabel, Ian.Campbell, Stefano Stabellini, Tim.Deegan
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_noarch.c | 8 ++
tools/libxl/libxl_pci.c | 242 -----------------------------------------
tools/libxl/libxl_x86.c | 258 ++++++++++++++++++++++++++++++++++++++++++++
6 files changed, 293 insertions(+), 255 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_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..dd8eef9
--- /dev/null
+++ b/tools/libxl/libxl_x86.c
@@ -0,0 +1,258 @@
+#include "libxl_arch.h"
+#include "libxl_internal.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)
+{
+ 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);
+ }
+}
--
1.7.8.3
^ permalink raw reply related [flat|nested] 9+ messages in thread