|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Xen-devel] [PATCH v3 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@xxxxxxxxxxxxx>
---
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
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |