# HG changeset patch
# User kfraser@xxxxxxxxxxxxxxxxxxxxx
# Node ID b60ea69932b1a4d10c3aae945a1ce1aa160c689b
# Parent e4f1519b473f6cda34496e491646d8683a410cae
# Parent 15304ad81c5068e0d4115623cf063c62add22407
Merge with xenppc-unstable.
---
buildconfigs/linux-defconfig_xen0_ia64 | 3
buildconfigs/linux-defconfig_xen0_x86_32 | 1
buildconfigs/linux-defconfig_xen0_x86_64 | 1
buildconfigs/linux-defconfig_xen_ia64 | 3
buildconfigs/linux-defconfig_xen_x86_32 | 1
buildconfigs/linux-defconfig_xen_x86_64 | 1
linux-2.6-xen-sparse/drivers/xen/Kconfig | 11
linux-2.6-xen-sparse/drivers/xen/balloon/balloon.c | 9
linux-2.6-xen-sparse/drivers/xen/blkback/blkback.c | 23
linux-2.6-xen-sparse/drivers/xen/blktap/blktap.c | 50
linux-2.6-xen-sparse/drivers/xen/netback/netback.c | 4
linux-2.6-xen-sparse/drivers/xen/pciback/Makefile | 1
linux-2.6-xen-sparse/drivers/xen/pciback/slot.c | 151 ++
linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/mmu_context.h | 3
tools/Makefile | 2
tools/examples/xend-config.sxp | 2
tools/examples/xmexample.hvm | 4
tools/firmware/Makefile | 2
tools/ioemu/patches/domain-destroy | 10
tools/ioemu/patches/domain-reset | 10
tools/ioemu/patches/domain-timeoffset | 8
tools/ioemu/patches/qemu-target-i386-dm | 25
tools/ioemu/patches/series | 2
tools/ioemu/patches/vnc-display-find-unused | 101 +
tools/ioemu/patches/xen-support-buffered-ioreqs | 77 +
tools/ioemu/patches/xenstore-block-device-config | 45
tools/ioemu/patches/xenstore-write-vnc-port | 10
tools/ioemu/target-i386-dm/helper2.c | 107 +
tools/ioemu/vl.c | 20
tools/ioemu/vl.h | 2
tools/ioemu/vnc.c | 17
tools/libxc/xc_hvm_build.c | 46
tools/libxc/xc_linux_build.c | 6
tools/pygrub/src/GrubConf.py | 72 -
tools/pygrub/src/pygrub | 541
+++++++---
tools/python/xen/util/xmlrpclib2.py | 5
tools/python/xen/xend/XendDomain.py | 4
tools/python/xen/xend/image.py | 5
tools/python/xen/xend/sxp.py | 2
tools/python/xen/xend/tests/test_sxp.py | 21
tools/python/xen/xend/tests/xend-config.sxp | 132 ++
tools/python/xen/xm/create.py | 61 +
tools/python/xen/xm/main.py | 10
tools/python/xen/xm/tests/test_create.py | 3
tools/xenstat/libxenstat/src/xenstat.c | 101 +
xen/arch/ia64/xen/hypercall.c | 2
xen/arch/ia64/xen/xensetup.c | 3
xen/arch/powerpc/setup.c | 2
xen/arch/x86/domain.c | 2
xen/arch/x86/flushtlb.c | 4
xen/arch/x86/hvm/hvm.c | 58 -
xen/arch/x86/hvm/intercept.c | 68 +
xen/arch/x86/hvm/io.c | 89 -
xen/arch/x86/hvm/platform.c | 54
xen/arch/x86/hvm/svm/svm.c | 6
xen/arch/x86/hvm/svm/vmcb.c | 34
xen/arch/x86/hvm/svm/x86_32/exits.S | 3
xen/arch/x86/hvm/svm/x86_64/exits.S | 2
xen/arch/x86/hvm/vlapic.c | 2
xen/arch/x86/hvm/vmx/io.c | 18
xen/arch/x86/hvm/vmx/vmcs.c | 12
xen/arch/x86/hvm/vmx/vmx.c | 131 +-
xen/arch/x86/hvm/vmx/x86_32/exits.S | 3
xen/arch/x86/hvm/vmx/x86_64/exits.S | 2
xen/arch/x86/irq.c | 87 -
xen/arch/x86/mm.c | 84 -
xen/arch/x86/nmi.c | 38
xen/arch/x86/time.c | 64 -
xen/arch/x86/x86_32/domain_page.c | 3
xen/arch/x86/x86_32/traps.c | 2
xen/arch/x86/x86_32/xen.lds.S | 3
xen/arch/x86/x86_64/xen.lds.S | 3
xen/common/domain.c | 11
xen/common/multicall.c | 4
xen/common/sched_bvt.c | 16
xen/common/sched_credit.c | 31
xen/common/sched_sedf.c | 21
xen/common/schedule.c | 65 -
xen/common/timer.c | 86 -
xen/common/trace.c | 17
xen/drivers/char/console.c | 1
xen/include/asm-ia64/linux-xen/asm/cache.h | 2
xen/include/asm-powerpc/cache.h | 2
xen/include/asm-powerpc/flushtlb.h | 15
xen/include/asm-x86/cache.h | 2
xen/include/asm-x86/current.h | 2
xen/include/asm-x86/e820.h | 1
xen/include/asm-x86/flushtlb.h | 16
xen/include/asm-x86/hvm/domain.h | 2
xen/include/asm-x86/hvm/hvm.h | 12
xen/include/asm-x86/hvm/io.h | 3
xen/include/asm-x86/hvm/support.h | 8
xen/include/asm-x86/hvm/vcpu.h | 2
xen/include/asm-x86/hvm/vmx/vmx.h | 359 +++---
xen/include/public/hvm/ioreq.h | 9
xen/include/xen/config.h | 1
xen/include/xen/event.h | 1
xen/include/xen/multicall.h | 5
xen/include/xen/percpu.h | 1
xen/include/xen/sched-if.h | 10
100 files changed, 2152 insertions(+), 1047 deletions(-)
diff -r e4f1519b473f -r b60ea69932b1 buildconfigs/linux-defconfig_xen0_ia64
--- a/buildconfigs/linux-defconfig_xen0_ia64 Tue Aug 08 19:07:32 2006 -0500
+++ b/buildconfigs/linux-defconfig_xen0_ia64 Wed Aug 09 18:04:20 2006 +0100
@@ -1533,8 +1533,9 @@ CONFIG_XEN_BLKDEV_BACKEND=y
# CONFIG_XEN_NETDEV_PIPELINED_TRANSMITTER is not set
CONFIG_XEN_NETDEV_LOOPBACK=y
CONFIG_XEN_PCIDEV_BACKEND=y
-CONFIG_XEN_PCIDEV_BACKEND_VPCI=y
+# CONFIG_XEN_PCIDEV_BACKEND_VPCI is not set
# CONFIG_XEN_PCIDEV_BACKEND_PASS is not set
+CONFIG_XEN_PCIDEV_BACKEND_SLOT=y
# CONFIG_XEN_PCIDEV_BE_DEBUG is not set
# CONFIG_XEN_TPMDEV_BACKEND is not set
CONFIG_XEN_BLKDEV_FRONTEND=y
diff -r e4f1519b473f -r b60ea69932b1 buildconfigs/linux-defconfig_xen0_x86_32
--- a/buildconfigs/linux-defconfig_xen0_x86_32 Tue Aug 08 19:07:32 2006 -0500
+++ b/buildconfigs/linux-defconfig_xen0_x86_32 Wed Aug 09 18:04:20 2006 +0100
@@ -1320,6 +1320,7 @@ CONFIG_XEN_PCIDEV_BACKEND=y
CONFIG_XEN_PCIDEV_BACKEND=y
# CONFIG_XEN_PCIDEV_BACKEND_VPCI is not set
CONFIG_XEN_PCIDEV_BACKEND_PASS=y
+# CONFIG_XEN_PCIDEV_BACKEND_SLOT is not set
# CONFIG_XEN_PCIDEV_BE_DEBUG is not set
CONFIG_XEN_BLKDEV_BACKEND=y
CONFIG_XEN_BLKDEV_TAP=y
diff -r e4f1519b473f -r b60ea69932b1 buildconfigs/linux-defconfig_xen0_x86_64
--- a/buildconfigs/linux-defconfig_xen0_x86_64 Tue Aug 08 19:07:32 2006 -0500
+++ b/buildconfigs/linux-defconfig_xen0_x86_64 Wed Aug 09 18:04:20 2006 +0100
@@ -1261,6 +1261,7 @@ CONFIG_XEN_PCIDEV_BACKEND=y
CONFIG_XEN_PCIDEV_BACKEND=y
# CONFIG_XEN_PCIDEV_BACKEND_VPCI is not set
CONFIG_XEN_PCIDEV_BACKEND_PASS=y
+# CONFIG_XEN_PCIDEV_BACKEND_SLOT is not set
# CONFIG_XEN_PCIDEV_BE_DEBUG is not set
CONFIG_XEN_BLKDEV_BACKEND=y
CONFIG_XEN_BLKDEV_TAP=y
diff -r e4f1519b473f -r b60ea69932b1 buildconfigs/linux-defconfig_xen_ia64
--- a/buildconfigs/linux-defconfig_xen_ia64 Tue Aug 08 19:07:32 2006 -0500
+++ b/buildconfigs/linux-defconfig_xen_ia64 Wed Aug 09 18:04:20 2006 +0100
@@ -1539,8 +1539,9 @@ CONFIG_XEN_BLKDEV_BACKEND=y
# CONFIG_XEN_NETDEV_PIPELINED_TRANSMITTER is not set
CONFIG_XEN_NETDEV_LOOPBACK=y
CONFIG_XEN_PCIDEV_BACKEND=y
-CONFIG_XEN_PCIDEV_BACKEND_VPCI=y
+# CONFIG_XEN_PCIDEV_BACKEND_VPCI is not set
# CONFIG_XEN_PCIDEV_BACKEND_PASS is not set
+CONFIG_XEN_PCIDEV_BACKEND_SLOT=y
# CONFIG_XEN_PCIDEV_BE_DEBUG is not set
# CONFIG_XEN_TPMDEV_BACKEND is not set
CONFIG_XEN_BLKDEV_FRONTEND=y
diff -r e4f1519b473f -r b60ea69932b1 buildconfigs/linux-defconfig_xen_x86_32
--- a/buildconfigs/linux-defconfig_xen_x86_32 Tue Aug 08 19:07:32 2006 -0500
+++ b/buildconfigs/linux-defconfig_xen_x86_32 Wed Aug 09 18:04:20 2006 +0100
@@ -3021,6 +3021,7 @@ CONFIG_XEN_PCIDEV_BACKEND=m
CONFIG_XEN_PCIDEV_BACKEND=m
CONFIG_XEN_PCIDEV_BACKEND_VPCI=y
# CONFIG_XEN_PCIDEV_BACKEND_PASS is not set
+# CONFIG_XEN_PCIDEV_BACKEND_SLOT is not set
# CONFIG_XEN_PCIDEV_BE_DEBUG is not set
CONFIG_XEN_BLKDEV_BACKEND=y
CONFIG_XEN_BLKDEV_TAP=y
diff -r e4f1519b473f -r b60ea69932b1 buildconfigs/linux-defconfig_xen_x86_64
--- a/buildconfigs/linux-defconfig_xen_x86_64 Tue Aug 08 19:07:32 2006 -0500
+++ b/buildconfigs/linux-defconfig_xen_x86_64 Wed Aug 09 18:04:20 2006 +0100
@@ -2853,6 +2853,7 @@ CONFIG_XEN_PCIDEV_BACKEND=m
CONFIG_XEN_PCIDEV_BACKEND=m
# CONFIG_XEN_PCIDEV_BACKEND_VPCI is not set
CONFIG_XEN_PCIDEV_BACKEND_PASS=y
+# CONFIG_XEN_PCIDEV_BACKEND_SLOT is not set
# CONFIG_XEN_PCIDEV_BE_DEBUG is not set
CONFIG_XEN_BLKDEV_BACKEND=y
CONFIG_XEN_BLKDEV_TAP=y
diff -r e4f1519b473f -r b60ea69932b1 linux-2.6-xen-sparse/drivers/xen/Kconfig
--- a/linux-2.6-xen-sparse/drivers/xen/Kconfig Tue Aug 08 19:07:32 2006 -0500
+++ b/linux-2.6-xen-sparse/drivers/xen/Kconfig Wed Aug 09 18:04:20 2006 +0100
@@ -117,7 +117,7 @@ config XEN_PCIDEV_BACKEND_VPCI
This PCI Backend hides the true PCI topology and makes the frontend
think there is a single PCI bus with only the exported devices on it.
For example, a device at 03:05.0 will be re-assigned to 00:00.0. A
- second device at 02:1a.0 will be re-assigned to 00:01.0.
+ second device at 02:1a.1 will be re-assigned to 00:01.1.
config XEN_PCIDEV_BACKEND_PASS
bool "Passthrough"
@@ -129,6 +129,15 @@ config XEN_PCIDEV_BACKEND_PASS
which depend on finding their hardward in certain bus/slot
locations.
+config XEN_PCIDEV_BACKEND_SLOT
+ bool "Slot"
+ ---help---
+ This PCI Backend hides the true PCI topology and makes the frontend
+ think there is a single PCI bus with only the exported devices on it.
+ Contrary to the virtual PCI backend, a function becomes a new slot.
+ For example, a device at 03:05.2 will be re-assigned to 00:00.0. A
+ second device at 02:1a.1 will be re-assigned to 00:01.0.
+
endchoice
config XEN_PCIDEV_BE_DEBUG
diff -r e4f1519b473f -r b60ea69932b1
linux-2.6-xen-sparse/drivers/xen/balloon/balloon.c
--- a/linux-2.6-xen-sparse/drivers/xen/balloon/balloon.c Tue Aug 08
19:07:32 2006 -0500
+++ b/linux-2.6-xen-sparse/drivers/xen/balloon/balloon.c Wed Aug 09
18:04:20 2006 +0100
@@ -563,10 +563,14 @@ struct page *balloon_alloc_empty_page_ra
set_xen_guest_handle(reservation.extent_start, &gmfn);
ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
&reservation);
+ if (ret == -ENOSYS)
+ goto err;
BUG_ON(ret != 1);
} else {
ret = apply_to_page_range(&init_mm, vstart, PAGE_SIZE << order,
dealloc_pte_fn, NULL);
+ if (ret == -ENOSYS)
+ goto err;
BUG_ON(ret);
}
current_pages -= 1UL << order;
@@ -583,6 +587,11 @@ struct page *balloon_alloc_empty_page_ra
set_page_count(page + i, 1);
return page;
+
+ err:
+ free_pages(vstart, order);
+ balloon_unlock(flags);
+ return NULL;
}
void balloon_dealloc_empty_page_range(
diff -r e4f1519b473f -r b60ea69932b1
linux-2.6-xen-sparse/drivers/xen/blkback/blkback.c
--- a/linux-2.6-xen-sparse/drivers/xen/blkback/blkback.c Tue Aug 08
19:07:32 2006 -0500
+++ b/linux-2.6-xen-sparse/drivers/xen/blkback/blkback.c Wed Aug 09
18:04:20 2006 +0100
@@ -518,6 +518,19 @@ static int __init blkif_init(void)
return -ENODEV;
mmap_pages = blkif_reqs * BLKIF_MAX_SEGMENTS_PER_REQUEST;
+
+#ifdef CONFIG_XEN_IA64_DOM0_NON_VP
+ extern unsigned long alloc_empty_foreign_map_page_range(
+ unsigned long pages);
+ mmap_vstart = (unsigned long)
+ alloc_empty_foreign_map_page_range(mmap_pages);
+#else /* ! ia64 */
+ page = balloon_alloc_empty_page_range(mmap_pages);
+ if (page == NULL)
+ return -ENOMEM;
+ mmap_vstart = (unsigned long)pfn_to_kaddr(page_to_pfn(page));
+#endif
+
pending_reqs = kmalloc(sizeof(pending_reqs[0]) *
blkif_reqs, GFP_KERNEL);
pending_grant_handles = kmalloc(sizeof(pending_grant_handles[0]) *
@@ -534,16 +547,6 @@ static int __init blkif_init(void)
blkif_interface_init();
-#ifdef CONFIG_XEN_IA64_DOM0_NON_VP
- extern unsigned long alloc_empty_foreign_map_page_range(
- unsigned long pages);
- mmap_vstart = (unsigned long)
- alloc_empty_foreign_map_page_range(mmap_pages);
-#else /* ! ia64 */
- page = balloon_alloc_empty_page_range(mmap_pages);
- BUG_ON(page == NULL);
- mmap_vstart = (unsigned long)pfn_to_kaddr(page_to_pfn(page));
-#endif
printk("%s: reqs=%d, pages=%d, mmap_vstart=0x%lx\n",
__FUNCTION__, blkif_reqs, mmap_pages, mmap_vstart);
BUG_ON(mmap_vstart == 0);
diff -r e4f1519b473f -r b60ea69932b1
linux-2.6-xen-sparse/drivers/xen/blktap/blktap.c
--- a/linux-2.6-xen-sparse/drivers/xen/blktap/blktap.c Tue Aug 08 19:07:32
2006 -0500
+++ b/linux-2.6-xen-sparse/drivers/xen/blktap/blktap.c Wed Aug 09 18:04:20
2006 +0100
@@ -709,29 +709,18 @@ static void make_response(blkif_t *blkif
/******************************************************************
* misc small helpers
*/
-/* FIXME: Return ENOMEM properly on failure to allocate additional reqs. */
-static void req_increase(void)
+static int req_increase(void)
{
int i, j;
struct page *page;
unsigned long flags;
+ int ret;
spin_lock_irqsave(&pending_free_lock, flags);
+ ret = -EINVAL;
if (mmap_alloc >= MAX_PENDING_REQS || mmap_lock)
goto done;
-
- pending_reqs[mmap_alloc] = kzalloc(sizeof(pending_req_t) *
- blkif_reqs, GFP_KERNEL);
- pending_addrs[mmap_alloc] = kzalloc(sizeof(unsigned long) *
- mmap_pages, GFP_KERNEL);
-
- if (!pending_reqs[mmap_alloc] || !pending_addrs[mmap_alloc]) {
- kfree(pending_reqs[mmap_alloc]);
- kfree(pending_addrs[mmap_alloc]);
- WPRINTK("%s: out of memory\n", __FUNCTION__);
- goto done;
- }
#ifdef __ia64__
extern unsigned long alloc_empty_foreign_map_page_range(
@@ -740,7 +729,11 @@ static void req_increase(void)
alloc_empty_foreign_map_page_range(mmap_pages);
#else /* ! ia64 */
page = balloon_alloc_empty_page_range(mmap_pages);
- BUG_ON(page == NULL);
+ ret = -ENOMEM;
+ if (page == NULL) {
+ printk("%s balloon_alloc_empty_page_range gave NULL\n",
__FUNCTION__);
+ goto done;
+ }
/* Pin all of the pages. */
for (i=0; i<mmap_pages; i++)
@@ -751,6 +744,23 @@ static void req_increase(void)
mmap_start[mmap_alloc].mpage = page;
#endif
+
+ pending_reqs[mmap_alloc] = kzalloc(sizeof(pending_req_t) *
+ blkif_reqs, GFP_KERNEL);
+ pending_addrs[mmap_alloc] = kzalloc(sizeof(unsigned long) *
+ mmap_pages, GFP_KERNEL);
+
+ ret = -ENOMEM;
+ if (!pending_reqs[mmap_alloc] || !pending_addrs[mmap_alloc]) {
+ kfree(pending_reqs[mmap_alloc]);
+ kfree(pending_addrs[mmap_alloc]);
+ WPRINTK("%s: out of memory\n", __FUNCTION__);
+ ret = -ENOMEM;
+ goto done;
+ }
+
+ ret = 0;
+
DPRINTK("%s: reqs=%d, pages=%d, mmap_vstart=0x%lx\n",
__FUNCTION__, blkif_reqs, mmap_pages,
mmap_start[mmap_alloc].start);
@@ -774,7 +784,7 @@ static void req_increase(void)
DPRINTK("# MMAPs increased to %d\n",mmap_alloc);
done:
spin_unlock_irqrestore(&pending_free_lock, flags);
-
+ return ret;
}
static void mmap_req_del(int mmap)
@@ -1394,7 +1404,13 @@ static int __init blkif_init(void)
return -ENODEV;
INIT_LIST_HEAD(&pending_free);
- for(i = 0; i < 2; i++) req_increase();
+ for(i = 0; i < 2; i++) {
+ ret = req_increase();
+ if (ret)
+ break;
+ }
+ if (i == 0)
+ return ret;
tap_blkif_interface_init();
diff -r e4f1519b473f -r b60ea69932b1
linux-2.6-xen-sparse/drivers/xen/netback/netback.c
--- a/linux-2.6-xen-sparse/drivers/xen/netback/netback.c Tue Aug 08
19:07:32 2006 -0500
+++ b/linux-2.6-xen-sparse/drivers/xen/netback/netback.c Wed Aug 09
18:04:20 2006 +0100
@@ -1306,7 +1306,9 @@ static int __init netback_init(void)
net_timer.function = net_alarm;
page = balloon_alloc_empty_page_range(MAX_PENDING_REQS);
- BUG_ON(page == NULL);
+ if (page == NULL)
+ return -ENOMEM;
+
mmap_vstart = (unsigned long)pfn_to_kaddr(page_to_pfn(page));
for (i = 0; i < MAX_PENDING_REQS; i++) {
diff -r e4f1519b473f -r b60ea69932b1
linux-2.6-xen-sparse/drivers/xen/pciback/Makefile
--- a/linux-2.6-xen-sparse/drivers/xen/pciback/Makefile Tue Aug 08 19:07:32
2006 -0500
+++ b/linux-2.6-xen-sparse/drivers/xen/pciback/Makefile Wed Aug 09 18:04:20
2006 +0100
@@ -7,6 +7,7 @@ pciback-y += conf_space.o conf_space_hea
conf_space_capability_pm.o \
conf_space_quirks.o
pciback-$(CONFIG_XEN_PCIDEV_BACKEND_VPCI) += vpci.o
+pciback-$(CONFIG_XEN_PCIDEV_BACKEND_SLOT) += slot.o
pciback-$(CONFIG_XEN_PCIDEV_BACKEND_PASS) += passthrough.o
ifeq ($(CONFIG_XEN_PCIDEV_BE_DEBUG),y)
diff -r e4f1519b473f -r b60ea69932b1
linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/mmu_context.h
--- a/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/mmu_context.h Tue Aug
08 19:07:32 2006 -0500
+++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/mmu_context.h Wed Aug
09 18:04:20 2006 +0100
@@ -51,7 +51,8 @@ static inline void switch_mm(struct mm_s
struct mmuext_op _op[2], *op = _op;
if (likely(prev != next)) {
- BUG_ON(!test_bit(PG_pinned, &virt_to_page(next->pgd)->flags));
+ BUG_ON(!xen_feature(XENFEAT_writable_page_tables) &&
+ !test_bit(PG_pinned, &virt_to_page(next->pgd)->flags));
/* stop flush ipis for the previous mm */
cpu_clear(cpu, prev->cpu_vm_mask);
diff -r e4f1519b473f -r b60ea69932b1 tools/Makefile
--- a/tools/Makefile Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/Makefile Wed Aug 09 18:04:20 2006 +0100
@@ -8,7 +8,7 @@ SUBDIRS-y += examples
SUBDIRS-y += examples
SUBDIRS-y += xentrace
SUBDIRS-$(CONFIG_XCUTILS) += xcutils
-SUBDIRS-y += firmware
+SUBDIRS-$(CONFIG_X86) += firmware
SUBDIRS-y += security
SUBDIRS-y += console
SUBDIRS-y += xenmon
diff -r e4f1519b473f -r b60ea69932b1 tools/examples/xend-config.sxp
--- a/tools/examples/xend-config.sxp Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/examples/xend-config.sxp Wed Aug 09 18:04:20 2006 +0100
@@ -54,7 +54,7 @@
# (xend-relocation-hosts-allow '^localhost$ ^.*\.example\.org$')
#
#(xend-relocation-hosts-allow '')
-(xend-relocation-hosts-allow '^localhost$')
+(xend-relocation-hosts-allow '^localhost$ ^localhost\.localdomain$')
# The limit (in kilobytes) on the size of the console buffer
#(console-limit 1024)
diff -r e4f1519b473f -r b60ea69932b1 tools/examples/xmexample.hvm
--- a/tools/examples/xmexample.hvm Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/examples/xmexample.hvm Wed Aug 09 18:04:20 2006 +0100
@@ -130,6 +130,10 @@ vnc=1
#vncdisplay=1
#----------------------------------------------------------------------------
+# try to find an unused port for the VNC server, default = 1
+#vncunused=1
+
+#----------------------------------------------------------------------------
# enable spawning vncviewer for domain's console
# (only valid when vnc=1), default = 0
#vncconsole=0
diff -r e4f1519b473f -r b60ea69932b1 tools/firmware/Makefile
--- a/tools/firmware/Makefile Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/firmware/Makefile Wed Aug 09 18:04:20 2006 +0100
@@ -30,7 +30,7 @@ all:
.PHONY: install
install: all
[ -d $(INSTALL_DIR) ] || install -d -m0755 $(INSTALL_DIR)
- install -m0644 $(TARGET) $(INSTALL_DIR)
+ [ ! -e $(TARGET) ] || install -m0644 $(TARGET) $(INSTALL_DIR)
.PHONY: clean
clean:
diff -r e4f1519b473f -r b60ea69932b1 tools/ioemu/patches/domain-destroy
--- a/tools/ioemu/patches/domain-destroy Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/ioemu/patches/domain-destroy Wed Aug 09 18:04:20 2006 +0100
@@ -1,7 +1,7 @@ Index: ioemu/monitor.c
Index: ioemu/monitor.c
===================================================================
---- ioemu.orig/monitor.c 2006-08-06 02:22:01.487319736 +0100
-+++ ioemu/monitor.c 2006-08-06 02:23:02.269544103 +0100
+--- ioemu.orig/monitor.c 2006-08-08 11:27:48.555190337 +0100
++++ ioemu/monitor.c 2006-08-08 11:27:53.984584612 +0100
@@ -308,6 +308,7 @@
static void do_quit(void)
@@ -12,10 +12,10 @@ Index: ioemu/monitor.c
Index: ioemu/target-i386-dm/helper2.c
===================================================================
---- ioemu.orig/target-i386-dm/helper2.c 2006-08-06 02:22:59.251880493
+0100
-+++ ioemu/target-i386-dm/helper2.c 2006-08-06 02:23:02.270543991 +0100
-@@ -483,5 +483,25 @@
- shared_page->vcpu_iodata[send_vcpu].dm_eport);
+--- ioemu.orig/target-i386-dm/helper2.c 2006-08-08 11:27:53.063687351
+0100
++++ ioemu/target-i386-dm/helper2.c 2006-08-08 11:27:54.011581601 +0100
+@@ -488,5 +488,25 @@
+ xc_evtchn_notify(xce_handle, ioreq_local_port[send_vcpu]);
}
}
+ destroy_hvm_domain();
@@ -42,8 +42,8 @@ Index: ioemu/target-i386-dm/helper2.c
+}
Index: ioemu/vl.h
===================================================================
---- ioemu.orig/vl.h 2006-08-06 02:22:59.255880047 +0100
-+++ ioemu/vl.h 2006-08-06 02:23:02.271543880 +0100
+--- ioemu.orig/vl.h 2006-08-08 11:27:53.067686905 +0100
++++ ioemu/vl.h 2006-08-08 11:27:54.061576023 +0100
@@ -1189,4 +1189,7 @@
void kqemu_record_dump(void);
diff -r e4f1519b473f -r b60ea69932b1 tools/ioemu/patches/domain-reset
--- a/tools/ioemu/patches/domain-reset Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/ioemu/patches/domain-reset Wed Aug 09 18:04:20 2006 +0100
@@ -1,8 +1,8 @@ Index: ioemu/target-i386-dm/helper2.c
Index: ioemu/target-i386-dm/helper2.c
===================================================================
---- ioemu.orig/target-i386-dm/helper2.c 2006-08-06 02:21:15.779415007
+0100
-+++ ioemu/target-i386-dm/helper2.c 2006-08-06 02:22:59.251880493 +0100
-@@ -123,6 +123,25 @@
+--- ioemu.orig/target-i386-dm/helper2.c 2006-08-08 11:27:45.566523765
+0100
++++ ioemu/target-i386-dm/helper2.c 2006-08-08 11:27:53.063687351 +0100
+@@ -127,6 +127,25 @@
/* called from main_cpu_reset */
void cpu_reset(CPUX86State *env)
{
@@ -28,7 +28,7 @@ Index: ioemu/target-i386-dm/helper2.c
}
void cpu_x86_close(CPUX86State *env)
-@@ -449,6 +468,10 @@
+@@ -455,6 +474,10 @@
if (vm_running) {
if (shutdown_requested)
break;
@@ -41,8 +41,8 @@ Index: ioemu/target-i386-dm/helper2.c
/* Wait up to 10 msec. */
Index: ioemu/vl.c
===================================================================
---- ioemu.orig/vl.c 2006-08-06 02:22:56.618174081 +0100
-+++ ioemu/vl.c 2006-08-06 02:22:59.254880158 +0100
+--- ioemu.orig/vl.c 2006-08-08 11:27:52.994695048 +0100
++++ ioemu/vl.c 2006-08-08 11:27:53.066687017 +0100
@@ -4948,7 +4948,7 @@
} QEMUResetEntry;
@@ -54,8 +54,8 @@ Index: ioemu/vl.c
Index: ioemu/vl.h
===================================================================
---- ioemu.orig/vl.h 2006-08-06 02:22:01.501318175 +0100
-+++ ioemu/vl.h 2006-08-06 02:22:59.255880047 +0100
+--- ioemu.orig/vl.h 2006-08-08 11:27:48.757167803 +0100
++++ ioemu/vl.h 2006-08-08 11:27:53.067686905 +0100
@@ -130,6 +130,7 @@
void qemu_register_reset(QEMUResetHandler *func, void *opaque);
diff -r e4f1519b473f -r b60ea69932b1 tools/ioemu/patches/domain-timeoffset
--- a/tools/ioemu/patches/domain-timeoffset Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/ioemu/patches/domain-timeoffset Wed Aug 09 18:04:20 2006 +0100
@@ -1,7 +1,7 @@ Index: ioemu/hw/mc146818rtc.c
Index: ioemu/hw/mc146818rtc.c
===================================================================
---- ioemu.orig/hw/mc146818rtc.c 2006-08-07 17:44:43.593604340 +0100
-+++ ioemu/hw/mc146818rtc.c 2006-08-07 17:44:47.594168708 +0100
+--- ioemu.orig/hw/mc146818rtc.c 2006-08-09 15:04:17.857242121 +0100
++++ ioemu/hw/mc146818rtc.c 2006-08-09 15:04:24.588603423 +0100
@@ -178,10 +178,27 @@
}
}
@@ -46,8 +46,8 @@ Index: ioemu/hw/mc146818rtc.c
static void rtc_copy_date(RTCState *s)
Index: ioemu/hw/pc.c
===================================================================
---- ioemu.orig/hw/pc.c 2006-08-07 17:44:47.324198106 +0100
-+++ ioemu/hw/pc.c 2006-08-07 17:44:54.830380715 +0100
+--- ioemu.orig/hw/pc.c 2006-08-09 15:04:24.316629266 +0100
++++ ioemu/hw/pc.c 2006-08-09 15:04:24.589603328 +0100
@@ -159,7 +159,7 @@
}
@@ -117,8 +117,8 @@ Index: ioemu/hw/pc.c
QEMUMachine pc_machine = {
Index: ioemu/vl.c
===================================================================
---- ioemu.orig/vl.c 2006-08-07 17:44:47.464182863 +0100
-+++ ioemu/vl.c 2006-08-07 17:44:54.830380715 +0100
+--- ioemu.orig/vl.c 2006-08-09 15:04:24.457615869 +0100
++++ ioemu/vl.c 2006-08-09 15:04:24.592603043 +0100
@@ -163,6 +163,8 @@
int xc_handle;
@@ -174,8 +174,8 @@ Index: ioemu/vl.c
if (usb_enabled) {
Index: ioemu/vl.h
===================================================================
---- ioemu.orig/vl.h 2006-08-07 17:44:47.329197562 +0100
-+++ ioemu/vl.h 2006-08-07 17:44:54.830380715 +0100
+--- ioemu.orig/vl.h 2006-08-09 15:04:24.321628791 +0100
++++ ioemu/vl.h 2006-08-09 15:04:24.593602948 +0100
@@ -575,7 +575,7 @@
int boot_device,
DisplayState *ds, const char **fd_filename, int snapshot,
diff -r e4f1519b473f -r b60ea69932b1 tools/ioemu/patches/qemu-target-i386-dm
--- a/tools/ioemu/patches/qemu-target-i386-dm Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/ioemu/patches/qemu-target-i386-dm Wed Aug 09 18:04:20 2006 +0100
@@ -1,7 +1,7 @@ Index: ioemu/Makefile.target
Index: ioemu/Makefile.target
===================================================================
---- ioemu.orig/Makefile.target 2006-08-06 02:14:09.794902973 +0100
-+++ ioemu/Makefile.target 2006-08-06 02:21:42.270461924 +0100
+--- ioemu.orig/Makefile.target 2006-08-08 11:24:33.479955101 +0100
++++ ioemu/Makefile.target 2006-08-08 11:24:39.008338255 +0100
@@ -62,6 +62,8 @@
QEMU_SYSTEM=qemu-fast
endif
@@ -32,8 +32,8 @@ Index: ioemu/Makefile.target
DEFINES += -DHAS_AUDIO
Index: ioemu/configure
===================================================================
---- ioemu.orig/configure 2006-08-06 02:14:09.795902861 +0100
-+++ ioemu/configure 2006-08-06 02:15:01.771108621 +0100
+--- ioemu.orig/configure 2006-08-08 11:24:33.480954990 +0100
++++ ioemu/configure 2006-08-08 11:24:38.122437102 +0100
@@ -373,6 +373,8 @@
if [ "$user" = "yes" ] ; then
target_list="i386-user arm-user armeb-user sparc-user ppc-user
mips-user mipsel-user $target_list"
@@ -45,8 +45,8 @@ Index: ioemu/configure
fi
Index: ioemu/monitor.c
===================================================================
---- ioemu.orig/monitor.c 2006-08-06 02:14:49.574468309 +0100
-+++ ioemu/monitor.c 2006-08-06 02:21:16.172371202 +0100
+--- ioemu.orig/monitor.c 2006-08-08 11:24:33.484954543 +0100
++++ ioemu/monitor.c 2006-08-08 11:24:39.253310921 +0100
@@ -1262,6 +1262,10 @@
"", "show profiling information", },
{ "capture", "", do_info_capture,
@@ -60,8 +60,8 @@ Index: ioemu/monitor.c
Index: ioemu/vl.c
===================================================================
---- ioemu.orig/vl.c 2006-08-06 02:14:09.802902081 +0100
-+++ ioemu/vl.c 2006-08-06 02:21:16.369349244 +0100
+--- ioemu.orig/vl.c 2006-08-08 11:24:33.486954320 +0100
++++ ioemu/vl.c 2006-08-08 11:24:39.454288496 +0100
@@ -87,7 +87,7 @@
#include "exec-all.h"
@@ -98,8 +98,8 @@ Index: ioemu/vl.c
{
Index: ioemu/vl.h
===================================================================
---- ioemu.orig/vl.h 2006-08-06 02:13:56.733359091 +0100
-+++ ioemu/vl.h 2006-08-06 02:21:16.369349244 +0100
+--- ioemu.orig/vl.h 2006-08-08 11:24:31.082222636 +0100
++++ ioemu/vl.h 2006-08-08 11:24:39.454288496 +0100
@@ -37,6 +37,8 @@
#include <unistd.h>
#include <fcntl.h>
@@ -132,7 +132,7 @@ Index: ioemu/target-i386-dm/cpu.h
Index: ioemu/target-i386-dm/cpu.h
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
-+++ ioemu/target-i386-dm/cpu.h 2006-08-06 02:21:16.023387810 +0100
++++ ioemu/target-i386-dm/cpu.h 2006-08-08 11:24:39.099328102 +0100
@@ -0,0 +1,86 @@
+/*
+ * i386 virtual CPU header
@@ -223,7 +223,7 @@ Index: ioemu/target-i386-dm/exec-dm.c
Index: ioemu/target-i386-dm/exec-dm.c
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
-+++ ioemu/target-i386-dm/exec-dm.c 2006-08-06 02:21:16.024387698 +0100
++++ ioemu/target-i386-dm/exec-dm.c 2006-08-08 11:24:39.099328102 +0100
@@ -0,0 +1,516 @@
+/*
+ * virtual page mapping and translated block handling
@@ -744,8 +744,8 @@ Index: ioemu/target-i386-dm/helper2.c
Index: ioemu/target-i386-dm/helper2.c
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
-+++ ioemu/target-i386-dm/helper2.c 2006-08-06 02:21:15.779415007 +0100
-@@ -0,0 +1,464 @@
++++ ioemu/target-i386-dm/helper2.c 2006-08-08 11:24:44.888682140 +0100
+@@ -0,0 +1,469 @@
+/*
+ * i386 helpers (without register variable usage)
+ *
@@ -830,6 +830,10 @@ Index: ioemu/target-i386-dm/helper2.c
+/* which vcpu we are serving */
+int send_vcpu = 0;
+
++//the evtchn port for polling the notification,
++#define NR_CPUS 32
++evtchn_port_t ioreq_local_port[NR_CPUS];
++
+CPUX86State *cpu_x86_init(void)
+{
+ CPUX86State *env;
@@ -861,7 +865,7 @@ Index: ioemu/target-i386-dm/helper2.c
+ fprintf(logfile, "bind interdomain ioctl error %d\n", errno);
+ return NULL;
+ }
-+ shared_page->vcpu_iodata[i].dm_eport = rc;
++ ioreq_local_port[i] = rc;
+ }
+ }
+
@@ -913,8 +917,7 @@ Index: ioemu/target-i386-dm/helper2.c
+
+ for (i = 0; i < vcpus; i++) {
+ req = &(shared_page->vcpu_iodata[i].vp_ioreq);
-+ term_printf("vcpu %d: event port %d\n", i,
-+ shared_page->vcpu_iodata[i].vp_eport);
++ term_printf("vcpu %d: event port %d\n", i, ioreq_local_port[i]);
+ term_printf(" req state: %x, pvalid: %x, addr: %"PRIx64", "
+ "data: %"PRIx64", count: %"PRIx64", size: %"PRIx64"\n",
+ req->state, req->pdata_valid, req->addr,
@@ -933,6 +936,7 @@ Index: ioemu/target-i386-dm/helper2.c
+
+ if (req->state == STATE_IOREQ_READY) {
+ req->state = STATE_IOREQ_INPROCESS;
++ rmb();
+ return req;
+ }
+
@@ -955,7 +959,7 @@ Index: ioemu/target-i386-dm/helper2.c
+ port = xc_evtchn_pending(xce_handle);
+ if (port != -1) {
+ for ( i = 0; i < vcpus; i++ )
-+ if ( shared_page->vcpu_iodata[i].dm_eport == port )
++ if ( ioreq_local_port[i] == port )
+ break;
+
+ if ( i == vcpus ) {
@@ -1176,8 +1180,10 @@ Index: ioemu/target-i386-dm/helper2.c
+ }
+
+ /* No state change if state = STATE_IORESP_HOOK */
-+ if (req->state == STATE_IOREQ_INPROCESS)
++ if (req->state == STATE_IOREQ_INPROCESS) {
++ mb();
+ req->state = STATE_IORESP_READY;
++ }
+ env->send_event = 1;
+ }
+}
@@ -1204,8 +1210,7 @@ Index: ioemu/target-i386-dm/helper2.c
+
+ if (env->send_event) {
+ env->send_event = 0;
-+ xc_evtchn_notify(xce_handle,
-+ shared_page->vcpu_iodata[send_vcpu].dm_eport);
++ xc_evtchn_notify(xce_handle, ioreq_local_port[send_vcpu]);
+ }
+ }
+ return 0;
@@ -1213,7 +1218,7 @@ Index: ioemu/target-i386-dm/i8259-dm.c
Index: ioemu/target-i386-dm/i8259-dm.c
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
-+++ ioemu/target-i386-dm/i8259-dm.c 2006-08-06 02:15:01.777107952 +0100
++++ ioemu/target-i386-dm/i8259-dm.c 2006-08-08 11:24:33.505952200 +0100
@@ -0,0 +1,107 @@
+/* Xen 8259 stub for interrupt controller emulation
+ *
@@ -1325,7 +1330,7 @@ Index: ioemu/target-i386-dm/qemu-dm.debu
Index: ioemu/target-i386-dm/qemu-dm.debug
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
-+++ ioemu/target-i386-dm/qemu-dm.debug 2006-08-06 02:15:01.778107841 +0100
++++ ioemu/target-i386-dm/qemu-dm.debug 2006-08-08 11:24:33.505952200 +0100
@@ -0,0 +1,5 @@
+#!/bin/sh
+
@@ -1335,7 +1340,7 @@ Index: ioemu/target-i386-dm/qemu-ifup
Index: ioemu/target-i386-dm/qemu-ifup
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
-+++ ioemu/target-i386-dm/qemu-ifup 2006-08-06 02:15:01.778107841 +0100
++++ ioemu/target-i386-dm/qemu-ifup 2006-08-08 11:24:33.505952200 +0100
@@ -0,0 +1,10 @@
+#!/bin/sh
+
diff -r e4f1519b473f -r b60ea69932b1 tools/ioemu/patches/series
--- a/tools/ioemu/patches/series Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/ioemu/patches/series Wed Aug 09 18:04:20 2006 +0100
@@ -34,8 +34,10 @@ vnc-start-vncviewer
vnc-start-vncviewer
vnc-title-domain-name
vnc-access-monitor-vt
+vnc-display-find-unused
xenstore-block-device-config
xenstore-write-vnc-port
qemu-allow-disable-sdl
qemu-fix-memset-args
qemu-fix-write-to-disk-synchronous
+xen-support-buffered-ioreqs
diff -r e4f1519b473f -r b60ea69932b1
tools/ioemu/patches/xenstore-block-device-config
--- a/tools/ioemu/patches/xenstore-block-device-config Tue Aug 08 19:07:32
2006 -0500
+++ b/tools/ioemu/patches/xenstore-block-device-config Wed Aug 09 18:04:20
2006 +0100
@@ -1,7 +1,7 @@ Index: ioemu/Makefile.target
Index: ioemu/Makefile.target
===================================================================
---- ioemu.orig/Makefile.target 2006-08-07 17:42:27.802386071 +0100
-+++ ioemu/Makefile.target 2006-08-07 17:42:28.683289358 +0100
+--- ioemu.orig/Makefile.target 2006-08-09 15:04:24.795583755 +0100
++++ ioemu/Makefile.target 2006-08-09 15:04:25.373528824 +0100
@@ -358,6 +358,7 @@
VL_OBJS+= cirrus_vga.o mixeng.o parallel.o acpi.o piix_pci.o
VL_OBJS+= usb-uhci.o
@@ -13,7 +13,7 @@ Index: ioemu/xenstore.c
Index: ioemu/xenstore.c
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
-+++ ioemu/xenstore.c 2006-08-07 17:42:28.684289249 +0100
++++ ioemu/xenstore.c 2006-08-09 15:04:25.374528729 +0100
@@ -0,0 +1,187 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General
@@ -204,9 +204,9 @@ Index: ioemu/xenstore.c
+}
Index: ioemu/vl.c
===================================================================
---- ioemu.orig/vl.c 2006-08-07 17:42:28.393320909 +0100
-+++ ioemu/vl.c 2006-08-07 17:42:28.687288922 +0100
-@@ -5242,9 +5242,11 @@
+--- ioemu.orig/vl.c 2006-08-09 15:04:25.312534622 +0100
++++ ioemu/vl.c 2006-08-09 15:04:25.377528443 +0100
+@@ -5243,9 +5243,11 @@
"Standard options:\n"
"-M machine select emulated machine (-M ? for list)\n"
"-fda/-fdb file use 'file' as floppy disk 0/1 image\n"
@@ -218,7 +218,7 @@ Index: ioemu/vl.c
"-boot [a|c|d] boot on floppy (a), hard disk (c) or CD-ROM (d)\n"
"-snapshot write to temporary files instead of disk image
files\n"
#ifdef TARGET_I386
-@@ -5370,11 +5372,13 @@
+@@ -5372,11 +5374,13 @@
QEMU_OPTION_M,
QEMU_OPTION_fda,
QEMU_OPTION_fdb,
@@ -232,7 +232,7 @@ Index: ioemu/vl.c
QEMU_OPTION_boot,
QEMU_OPTION_snapshot,
#ifdef TARGET_I386
-@@ -5445,11 +5449,13 @@
+@@ -5448,11 +5452,13 @@
{ "M", HAS_ARG, QEMU_OPTION_M },
{ "fda", HAS_ARG, QEMU_OPTION_fda },
{ "fdb", HAS_ARG, QEMU_OPTION_fdb },
@@ -246,7 +246,7 @@ Index: ioemu/vl.c
{ "boot", HAS_ARG, QEMU_OPTION_boot },
{ "snapshot", 0, QEMU_OPTION_snapshot },
#ifdef TARGET_I386
-@@ -5797,10 +5803,16 @@
+@@ -5801,10 +5807,16 @@
#ifdef CONFIG_GDBSTUB
int use_gdbstub, gdbstub_port;
#endif
@@ -265,7 +265,7 @@ Index: ioemu/vl.c
const char *kernel_filename, *kernel_cmdline;
DisplayState *ds = &display_state;
int cyls, heads, secs, translation;
-@@ -5861,8 +5873,10 @@
+@@ -5865,8 +5877,10 @@
initrd_filename = NULL;
for(i = 0; i < MAX_FD; i++)
fd_filename[i] = NULL;
@@ -276,8 +276,8 @@ Index: ioemu/vl.c
ram_size = DEFAULT_RAM_SIZE * 1024 * 1024;
vga_ram_size = VGA_RAM_SIZE;
bios_size = BIOS_SIZE;
-@@ -5875,11 +5889,13 @@
- vncviewer = 0;
+@@ -5880,11 +5894,13 @@
+ vncunused = 0;
kernel_filename = NULL;
kernel_cmdline = "";
+#ifndef CONFIG_DM
@@ -290,7 +290,7 @@ Index: ioemu/vl.c
cyls = heads = secs = 0;
translation = BIOS_ATA_TRANSLATION_AUTO;
pstrcpy(monitor_device, sizeof(monitor_device), "vc");
-@@ -5912,7 +5928,11 @@
+@@ -5917,7 +5933,11 @@
break;
r = argv[optind];
if (r[0] != '-') {
@@ -302,7 +302,7 @@ Index: ioemu/vl.c
} else {
const QEMUOption *popt;
-@@ -5956,6 +5976,7 @@
+@@ -5961,6 +5981,7 @@
case QEMU_OPTION_initrd:
initrd_filename = optarg;
break;
@@ -310,7 +310,7 @@ Index: ioemu/vl.c
case QEMU_OPTION_hda:
case QEMU_OPTION_hdb:
case QEMU_OPTION_hdc:
-@@ -5968,6 +5989,7 @@
+@@ -5973,6 +5994,7 @@
cdrom_index = -1;
}
break;
@@ -318,7 +318,7 @@ Index: ioemu/vl.c
case QEMU_OPTION_snapshot:
snapshot = 1;
break;
-@@ -6020,11 +6042,13 @@
+@@ -6025,11 +6047,13 @@
case QEMU_OPTION_append:
kernel_cmdline = optarg;
break;
@@ -332,7 +332,7 @@ Index: ioemu/vl.c
case QEMU_OPTION_boot:
boot_device = optarg[0];
if (boot_device != 'a' &&
-@@ -6274,12 +6298,18 @@
+@@ -6284,12 +6308,18 @@
}
}
@@ -351,7 +351,7 @@ Index: ioemu/vl.c
if (!linux_boot &&
hd_filename[0] == '\0' &&
(cdrom_index >= 0 && hd_filename[cdrom_index] == '\0') &&
-@@ -6293,6 +6323,7 @@
+@@ -6303,6 +6333,7 @@
else
boot_device = 'd';
}
@@ -359,7 +359,7 @@ Index: ioemu/vl.c
setvbuf(stdout, NULL, _IOLBF, 0);
-@@ -6407,6 +6438,7 @@
+@@ -6417,6 +6448,7 @@
#endif /* !CONFIG_DM */
@@ -367,7 +367,7 @@ Index: ioemu/vl.c
/* we always create the cdrom drive, even if no disk is there */
bdrv_init();
if (cdrom_index >= 0) {
-@@ -6433,6 +6465,7 @@
+@@ -6443,6 +6475,7 @@
}
}
}
@@ -375,7 +375,7 @@ Index: ioemu/vl.c
/* we always create at least one floppy disk */
fd_table[0] = bdrv_new("fda");
-@@ -6511,6 +6544,8 @@
+@@ -6521,6 +6554,8 @@
}
}
@@ -386,8 +386,8 @@ Index: ioemu/vl.c
kernel_filename, kernel_cmdline, initrd_filename,
Index: ioemu/monitor.c
===================================================================
---- ioemu.orig/monitor.c 2006-08-07 17:42:27.132461888 +0100
-+++ ioemu/monitor.c 2006-08-07 17:42:28.688288814 +0100
+--- ioemu.orig/monitor.c 2006-08-09 15:04:24.105649313 +0100
++++ ioemu/monitor.c 2006-08-09 15:04:25.379528253 +0100
@@ -24,6 +24,7 @@
#include "vl.h"
#include "disas.h"
@@ -416,8 +416,8 @@ Index: ioemu/monitor.c
int i;
Index: ioemu/block.c
===================================================================
---- ioemu.orig/block.c 2006-08-07 17:42:21.704076241 +0100
-+++ ioemu/block.c 2006-08-07 17:42:28.689288705 +0100
+--- ioemu.orig/block.c 2006-08-09 15:04:17.487277167 +0100
++++ ioemu/block.c 2006-08-09 15:04:25.379528253 +0100
@@ -758,6 +758,7 @@
static void raw_close(BlockDriverState *bs)
{
@@ -428,8 +428,8 @@ Index: ioemu/block.c
Index: ioemu/vl.h
===================================================================
---- ioemu.orig/vl.h 2006-08-07 17:42:28.394320800 +0100
-+++ ioemu/vl.h 2006-08-07 17:42:28.689288705 +0100
+--- ioemu.orig/vl.h 2006-08-09 15:04:25.313534527 +0100
++++ ioemu/vl.h 2006-08-09 15:04:25.380528158 +0100
@@ -1184,6 +1184,8 @@
void term_print_help(void);
void monitor_readline(const char *prompt, int is_password,
@@ -455,8 +455,8 @@ Index: ioemu/vl.h
extern char domain_name[];
Index: ioemu/hw/ide.c
===================================================================
---- ioemu.orig/hw/ide.c 2006-08-07 17:42:27.552414361 +0100
-+++ ioemu/hw/ide.c 2006-08-07 17:42:28.691288487 +0100
+--- ioemu.orig/hw/ide.c 2006-08-09 15:04:24.524609503 +0100
++++ ioemu/hw/ide.c 2006-08-09 15:04:25.381528063 +0100
@@ -1158,6 +1158,7 @@
} else {
ide_atapi_cmd_error(s, SENSE_NOT_READY,
diff -r e4f1519b473f -r b60ea69932b1 tools/ioemu/patches/xenstore-write-vnc-port
--- a/tools/ioemu/patches/xenstore-write-vnc-port Tue Aug 08 19:07:32
2006 -0500
+++ b/tools/ioemu/patches/xenstore-write-vnc-port Wed Aug 09 18:04:20
2006 +0100
@@ -1,7 +1,7 @@ Index: ioemu/xenstore.c
Index: ioemu/xenstore.c
===================================================================
---- ioemu.orig/xenstore.c 2006-08-07 17:42:28.684289249 +0100
-+++ ioemu/xenstore.c 2006-08-07 17:42:28.891266728 +0100
+--- ioemu.orig/xenstore.c 2006-08-09 15:04:25.374528729 +0100
++++ ioemu/xenstore.c 2006-08-09 15:04:25.579509243 +0100
@@ -185,3 +185,31 @@
free(image);
free(vec);
@@ -36,10 +36,10 @@ Index: ioemu/xenstore.c
+}
Index: ioemu/vl.c
===================================================================
---- ioemu.orig/vl.c 2006-08-07 17:42:28.687288922 +0100
-+++ ioemu/vl.c 2006-08-07 17:42:28.894266401 +0100
-@@ -6501,6 +6501,7 @@
- vnc_display_init(ds, vnc_display);
+--- ioemu.orig/vl.c 2006-08-09 15:04:25.377528443 +0100
++++ ioemu/vl.c 2006-08-09 15:04:25.583508863 +0100
+@@ -6511,6 +6511,7 @@
+ vnc_display = vnc_display_init(ds, vnc_display, vncunused);
if (vncviewer)
vnc_start_viewer(vnc_display);
+ xenstore_write_vncport(vnc_display);
@@ -48,8 +48,8 @@ Index: ioemu/vl.c
sdl_display_init(ds, full_screen);
Index: ioemu/vl.h
===================================================================
---- ioemu.orig/vl.h 2006-08-07 17:42:28.689288705 +0100
-+++ ioemu/vl.h 2006-08-07 17:42:28.895266293 +0100
+--- ioemu.orig/vl.h 2006-08-09 15:04:25.380528158 +0100
++++ ioemu/vl.h 2006-08-09 15:04:25.584508768 +0100
@@ -1203,6 +1203,7 @@
int xenstore_fd(void);
void xenstore_process_event(void *opaque);
diff -r e4f1519b473f -r b60ea69932b1 tools/ioemu/target-i386-dm/helper2.c
--- a/tools/ioemu/target-i386-dm/helper2.c Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/ioemu/target-i386-dm/helper2.c Wed Aug 09 18:04:20 2006 +0100
@@ -76,11 +76,19 @@ int xc_handle;
shared_iopage_t *shared_page = NULL;
+#define BUFFER_IO_MAX_DELAY 100
+buffered_iopage_t *buffered_io_page = NULL;
+QEMUTimer *buffered_io_timer;
+
/* the evtchn fd for polling */
int xce_handle = -1;
/* which vcpu we are serving */
int send_vcpu = 0;
+
+//the evtchn port for polling the notification,
+#define NR_CPUS 32
+evtchn_port_t ioreq_local_port[NR_CPUS];
CPUX86State *cpu_x86_init(void)
{
@@ -113,7 +121,7 @@ CPUX86State *cpu_x86_init(void)
fprintf(logfile, "bind interdomain ioctl error %d\n", errno);
return NULL;
}
- shared_page->vcpu_iodata[i].dm_eport = rc;
+ ioreq_local_port[i] = rc;
}
}
@@ -184,8 +192,7 @@ void sp_info()
for (i = 0; i < vcpus; i++) {
req = &(shared_page->vcpu_iodata[i].vp_ioreq);
- term_printf("vcpu %d: event port %d\n", i,
- shared_page->vcpu_iodata[i].vp_eport);
+ term_printf("vcpu %d: event port %d\n", i, ioreq_local_port[i]);
term_printf(" req state: %x, pvalid: %x, addr: %"PRIx64", "
"data: %"PRIx64", count: %"PRIx64", size: %"PRIx64"\n",
req->state, req->pdata_valid, req->addr,
@@ -204,6 +211,7 @@ static ioreq_t *__cpu_get_ioreq(int vcpu
if (req->state == STATE_IOREQ_READY) {
req->state = STATE_IOREQ_INPROCESS;
+ rmb();
return req;
}
@@ -226,7 +234,7 @@ static ioreq_t *cpu_get_ioreq(void)
port = xc_evtchn_pending(xce_handle);
if (port != -1) {
for ( i = 0; i < vcpus; i++ )
- if ( shared_page->vcpu_iodata[i].dm_eport == port )
+ if ( ioreq_local_port[i] == port )
break;
if ( i == vcpus ) {
@@ -415,40 +423,74 @@ void cpu_ioreq_xor(CPUState *env, ioreq_
req->u.data = tmp1;
}
+void __handle_ioreq(CPUState *env, ioreq_t *req)
+{
+ if (!req->pdata_valid && req->dir == IOREQ_WRITE && req->size != 4)
+ req->u.data &= (1UL << (8 * req->size)) - 1;
+
+ switch (req->type) {
+ case IOREQ_TYPE_PIO:
+ cpu_ioreq_pio(env, req);
+ break;
+ case IOREQ_TYPE_COPY:
+ cpu_ioreq_move(env, req);
+ break;
+ case IOREQ_TYPE_AND:
+ cpu_ioreq_and(env, req);
+ break;
+ case IOREQ_TYPE_OR:
+ cpu_ioreq_or(env, req);
+ break;
+ case IOREQ_TYPE_XOR:
+ cpu_ioreq_xor(env, req);
+ break;
+ default:
+ hw_error("Invalid ioreq type 0x%x\n", req->type);
+ }
+}
+
+void __handle_buffered_iopage(CPUState *env)
+{
+ ioreq_t *req = NULL;
+
+ if (!buffered_io_page)
+ return;
+
+ while (buffered_io_page->read_pointer !=
+ buffered_io_page->write_pointer) {
+ req = &buffered_io_page->ioreq[buffered_io_page->read_pointer %
+ IOREQ_BUFFER_SLOT_NUM];
+
+ __handle_ioreq(env, req);
+
+ mb();
+ buffered_io_page->read_pointer++;
+ }
+}
+
+void handle_buffered_io(void *opaque)
+{
+ CPUState *env = opaque;
+
+ __handle_buffered_iopage(env);
+ qemu_mod_timer(buffered_io_timer, BUFFER_IO_MAX_DELAY +
+ qemu_get_clock(rt_clock));
+}
+
void cpu_handle_ioreq(void *opaque)
{
CPUState *env = opaque;
ioreq_t *req = cpu_get_ioreq();
+ handle_buffered_io(env);
if (req) {
- if ((!req->pdata_valid) && (req->dir == IOREQ_WRITE)) {
- if (req->size != 4)
- req->u.data &= (1UL << (8 * req->size))-1;
- }
-
- switch (req->type) {
- case IOREQ_TYPE_PIO:
- cpu_ioreq_pio(env, req);
- break;
- case IOREQ_TYPE_COPY:
- cpu_ioreq_move(env, req);
- break;
- case IOREQ_TYPE_AND:
- cpu_ioreq_and(env, req);
- break;
- case IOREQ_TYPE_OR:
- cpu_ioreq_or(env, req);
- break;
- case IOREQ_TYPE_XOR:
- cpu_ioreq_xor(env, req);
- break;
- default:
- hw_error("Invalid ioreq type 0x%x\n", req->type);
- }
+ __handle_ioreq(env, req);
/* No state change if state = STATE_IORESP_HOOK */
- if (req->state == STATE_IOREQ_INPROCESS)
+ if (req->state == STATE_IOREQ_INPROCESS) {
+ mb();
req->state = STATE_IORESP_READY;
+ }
env->send_event = 1;
}
}
@@ -459,6 +501,10 @@ int main_loop(void)
extern int shutdown_requested;
CPUState *env = cpu_single_env;
int evtchn_fd = xc_evtchn_fd(xce_handle);
+
+ buffered_io_timer = qemu_new_timer(rt_clock, handle_buffered_io,
+ cpu_single_env);
+ qemu_mod_timer(buffered_io_timer, qemu_get_clock(rt_clock));
qemu_set_fd_handler(evtchn_fd, cpu_handle_ioreq, NULL, env);
@@ -479,8 +525,7 @@ int main_loop(void)
if (env->send_event) {
env->send_event = 0;
- xc_evtchn_notify(xce_handle,
- shared_page->vcpu_iodata[send_vcpu].dm_eport);
+ xc_evtchn_notify(xce_handle, ioreq_local_port[send_vcpu]);
}
}
destroy_hvm_domain();
diff -r e4f1519b473f -r b60ea69932b1 tools/ioemu/vl.c
--- a/tools/ioemu/vl.c Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/ioemu/vl.c Wed Aug 09 18:04:20 2006 +0100
@@ -121,6 +121,7 @@ static DisplayState display_state;
static DisplayState display_state;
int nographic;
int vncviewer;
+int vncunused;
const char* keyboard_layout = NULL;
int64_t ticks_per_sec;
int boot_device = 'c';
@@ -5344,6 +5345,7 @@ void help(void)
"-loadvm file start right away with a saved state (loadvm in
monitor)\n"
"-vnc display start a VNC server on display\n"
"-vncviewer start a vncviewer process for this domain\n"
+ "-vncunused bind the VNC server to an unused port\n"
"-timeoffset time offset (in seconds) from local time\n"
"-acpi disable or enable ACPI of HVM domain \n"
"\n"
@@ -5435,6 +5437,7 @@ enum {
QEMU_OPTION_timeoffset,
QEMU_OPTION_acpi,
QEMU_OPTION_vncviewer,
+ QEMU_OPTION_vncunused,
};
typedef struct QEMUOption {
@@ -5512,6 +5515,7 @@ const QEMUOption qemu_options[] = {
{ "smp", HAS_ARG, QEMU_OPTION_smp },
{ "vnc", HAS_ARG, QEMU_OPTION_vnc },
{ "vncviewer", 0, QEMU_OPTION_vncviewer },
+ { "vncunused", 0, QEMU_OPTION_vncunused },
/* temporary options */
{ "usb", 0, QEMU_OPTION_usb },
@@ -5834,6 +5838,7 @@ int main(int argc, char **argv)
unsigned long nr_pages;
xen_pfn_t *page_array;
extern void *shared_page;
+ extern void *buffered_io_page;
char qemu_dm_logfilename[64];
@@ -5887,6 +5892,7 @@ int main(int argc, char **argv)
snapshot = 0;
nographic = 0;
vncviewer = 0;
+ vncunused = 0;
kernel_filename = NULL;
kernel_cmdline = "";
#ifndef CONFIG_DM
@@ -6294,6 +6300,11 @@ int main(int argc, char **argv)
case QEMU_OPTION_vncviewer:
vncviewer++;
break;
+ case QEMU_OPTION_vncunused:
+ vncunused++;
+ if (vnc_display == -1)
+ vnc_display = -2;
+ break;
}
}
}
@@ -6378,11 +6389,16 @@ int main(int argc, char **argv)
phys_ram_base = xc_map_foreign_batch(xc_handle, domid,
PROT_READ|PROT_WRITE, page_array,
- nr_pages - 1);
+ nr_pages - 3);
if (phys_ram_base == 0) {
fprintf(logfile, "xc_map_foreign_batch returned error %d\n", errno);
exit(-1);
}
+
+ /* not yet add for IA64 */
+ buffered_io_page = xc_map_foreign_range(xc_handle, domid, PAGE_SIZE,
+ PROT_READ|PROT_WRITE,
+ page_array[nr_pages - 3]);
shared_page = xc_map_foreign_range(xc_handle, domid, PAGE_SIZE,
PROT_READ|PROT_WRITE,
@@ -6498,7 +6514,7 @@ int main(int argc, char **argv)
if (nographic) {
dumb_display_init(ds);
} else if (vnc_display != -1) {
- vnc_display_init(ds, vnc_display);
+ vnc_display = vnc_display_init(ds, vnc_display, vncunused);
if (vncviewer)
vnc_start_viewer(vnc_display);
xenstore_write_vncport(vnc_display);
diff -r e4f1519b473f -r b60ea69932b1 tools/ioemu/vl.h
--- a/tools/ioemu/vl.h Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/ioemu/vl.h Wed Aug 09 18:04:20 2006 +0100
@@ -784,7 +784,7 @@ void cocoa_display_init(DisplayState *ds
void cocoa_display_init(DisplayState *ds, int full_screen);
/* vnc.c */
-void vnc_display_init(DisplayState *ds, int display);
+int vnc_display_init(DisplayState *ds, int display, int find_unused);
int vnc_start_viewer(int port);
/* ide.c */
diff -r e4f1519b473f -r b60ea69932b1 tools/ioemu/vnc.c
--- a/tools/ioemu/vnc.c Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/ioemu/vnc.c Wed Aug 09 18:04:20 2006 +0100
@@ -1183,7 +1183,7 @@ static void vnc_listen_read(void *opaque
}
}
-void vnc_display_init(DisplayState *ds, int display)
+int vnc_display_init(DisplayState *ds, int display, int find_unused)
{
struct sockaddr_in addr;
int reuse_addr, ret;
@@ -1213,10 +1213,6 @@ void vnc_display_init(DisplayState *ds,
fprintf(stderr, "Could not create socket\n");
exit(1);
}
-
- addr.sin_family = AF_INET;
- addr.sin_port = htons(5900 + display);
- memset(&addr.sin_addr, 0, sizeof(addr.sin_addr));
reuse_addr = 1;
ret = setsockopt(vs->lsock, SOL_SOCKET, SO_REUSEADDR,
@@ -1226,7 +1222,16 @@ void vnc_display_init(DisplayState *ds,
exit(1);
}
+ retry:
+ addr.sin_family = AF_INET;
+ addr.sin_port = htons(5900 + display);
+ memset(&addr.sin_addr, 0, sizeof(addr.sin_addr));
+
if (bind(vs->lsock, (struct sockaddr *)&addr, sizeof(addr)) == -1) {
+ if (find_unused && errno == EADDRINUSE) {
+ display++;
+ goto retry;
+ }
fprintf(stderr, "bind() failed\n");
exit(1);
}
@@ -1247,6 +1252,8 @@ void vnc_display_init(DisplayState *ds,
vs->ds->dpy_refresh = vnc_dpy_refresh;
vnc_dpy_resize(vs->ds, 640, 400);
+
+ return display;
}
int vnc_start_viewer(int port)
diff -r e4f1519b473f -r b60ea69932b1 tools/libxc/xc_hvm_build.c
--- a/tools/libxc/xc_hvm_build.c Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/libxc/xc_hvm_build.c Wed Aug 09 18:04:20 2006 +0100
@@ -26,6 +26,7 @@
#define E820_IO 16
#define E820_SHARED_PAGE 17
#define E820_XENSTORE 18
+#define E820_BUFFERED_IO 19
#define E820_MAP_PAGE 0x00090000
#define E820_MAP_NR_OFFSET 0x000001E8
@@ -96,7 +97,13 @@ static void build_e820map(void *e820_pag
e820entry[nr_map].type = E820_RESERVED;
nr_map++;
-#define STATIC_PAGES 2 /* for ioreq_t and store_mfn */
+#define STATIC_PAGES 3
+ /* 3 static pages:
+ * - ioreq buffer.
+ * - xenstore.
+ * - shared_page.
+ */
+
/* Most of the ram goes here */
e820entry[nr_map].addr = 0x100000;
e820entry[nr_map].size = mem_size - 0x100000 - STATIC_PAGES * PAGE_SIZE;
@@ -104,6 +111,12 @@ static void build_e820map(void *e820_pag
nr_map++;
/* Statically allocated special pages */
+
+ /* For buffered IO requests */
+ e820entry[nr_map].addr = mem_size - 3 * PAGE_SIZE;
+ e820entry[nr_map].size = PAGE_SIZE;
+ e820entry[nr_map].type = E820_BUFFERED_IO;
+ nr_map++;
/* For xenstore */
e820entry[nr_map].addr = mem_size - 2 * PAGE_SIZE;
@@ -213,6 +226,9 @@ static int setup_guest(int xc_handle,
unsigned long shared_page_frame = 0;
shared_iopage_t *sp;
+ unsigned long ioreq_buffer_frame = 0;
+ void *ioreq_buffer_page;
+
memset(&dsi, 0, sizeof(struct domain_setup_info));
if ( (parseelfimage(image, image_size, &dsi)) != 0 )
@@ -294,27 +310,27 @@ static int setup_guest(int xc_handle,
shared_info->vcpu_info[i].evtchn_upcall_mask = 1;
munmap(shared_info, PAGE_SIZE);
- /* Populate the event channel port in the shared page */
+ /* Paranoia */
shared_page_frame = page_array[(v_end >> PAGE_SHIFT) - 1];
if ( (sp = (shared_iopage_t *) xc_map_foreign_range(
xc_handle, dom, PAGE_SIZE, PROT_READ | PROT_WRITE,
shared_page_frame)) == 0 )
goto error_out;
memset(sp, 0, PAGE_SIZE);
-
- /* FIXME: how about if we overflow the page here? */
- for ( i = 0; i < vcpus; i++ ) {
- unsigned int vp_eport;
-
- vp_eport = xc_evtchn_alloc_unbound(xc_handle, dom, 0);
- if ( vp_eport < 0 ) {
- PERROR("Couldn't get unbound port from VMX guest.\n");
- goto error_out;
- }
- sp->vcpu_iodata[i].vp_eport = vp_eport;
- }
-
munmap(sp, PAGE_SIZE);
+
+ /* clean the buffered IO requests page */
+ ioreq_buffer_frame = page_array[(v_end >> PAGE_SHIFT) - 3];
+ ioreq_buffer_page = xc_map_foreign_range(xc_handle, dom, PAGE_SIZE,
+ PROT_READ | PROT_WRITE,
+ ioreq_buffer_frame);
+
+ if ( ioreq_buffer_page == NULL )
+ goto error_out;
+
+ memset(ioreq_buffer_page, 0, PAGE_SIZE);
+
+ munmap(ioreq_buffer_page, PAGE_SIZE);
xc_set_hvm_param(xc_handle, dom, HVM_PARAM_STORE_PFN, (v_end >>
PAGE_SHIFT) - 2);
xc_set_hvm_param(xc_handle, dom, HVM_PARAM_STORE_EVTCHN, store_evtchn);
diff -r e4f1519b473f -r b60ea69932b1 tools/libxc/xc_linux_build.c
--- a/tools/libxc/xc_linux_build.c Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/libxc/xc_linux_build.c Wed Aug 09 18:04:20 2006 +0100
@@ -1373,10 +1373,10 @@ int xc_linux_build(int xc_handle,
error_out:
free(image);
- if ( fd >= 0 )
+ if ( initrd_info.type == INITRD_file && initrd_info.u.file_handle )
+ gzclose(initrd_info.u.file_handle);
+ else if ( fd >= 0 )
close(fd);
- if ( initrd_info.u.file_handle )
- gzclose(initrd_info.u.file_handle);
return sts;
}
diff -r e4f1519b473f -r b60ea69932b1 tools/pygrub/src/GrubConf.py
--- a/tools/pygrub/src/GrubConf.py Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/pygrub/src/GrubConf.py Wed Aug 09 18:04:20 2006 +0100
@@ -1,7 +1,7 @@
#
# GrubConf.py - Simple grub.conf parsing
#
-# Copyright 2005 Red Hat, Inc.
+# Copyright 2005-2006 Red Hat, Inc.
# Jeremy Katz <katzj@xxxxxxxxxx>
#
# This software may be freely redistributed under the terms of the GNU
@@ -16,7 +16,6 @@ import logging
import logging
def grub_split(s, maxsplit = -1):
- """Split a grub option screen separated with either '=' or whitespace."""
eq = s.find('=')
if eq == -1:
return s.split(None, maxsplit)
@@ -31,6 +30,12 @@ def grub_split(s, maxsplit = -1):
return s.split('=', maxsplit)
else:
return s.split(None, maxsplit)
+
+def grub_exact_split(s, num):
+ ret = grub_split(s, num - 1)
+ if len(ret) < num:
+ return ret + [""] * (num - len(ret))
+ return ret
def get_path(s):
"""Returns a tuple of (GrubDiskPart, path) corresponding to string."""
@@ -75,25 +80,39 @@ class GrubDiskPart(object):
class GrubImage(object):
def __init__(self, lines):
- self._root = self._initrd = self._kernel = self._args = None
- for l in lines:
- (com, arg) = grub_split(l, 1)
-
- if self.commands.has_key(com):
- if self.commands[com] is not None:
- exec("%s = r\"%s\"" %(self.commands[com], arg.strip()))
- else:
- logging.info("Ignored image directive %s" %(com,))
- else:
- logging.warning("Unknown image directive %s" %(com,))
+ self.reset(lines)
def __repr__(self):
return ("title: %s\n"
" root: %s\n"
" kernel: %s\n"
" args: %s\n"
- " initrd: %s" %(self.title, self.root, self.kernel,
+ " initrd: %s\n" %(self.title, self.root, self.kernel,
self.args, self.initrd))
+
+ def reset(self, lines):
+ self._root = self._initrd = self._kernel = self._args = None
+ self.title = ""
+ self.lines = []
+ map(self.set_from_line, lines)
+
+ def set_from_line(self, line, replace = None):
+ (com, arg) = grub_exact_split(line, 2)
+
+ if self.commands.has_key(com):
+ if self.commands[com] is not None:
+ exec("%s = r\"%s\"" %(self.commands[com], arg.strip()))
+ else:
+ logging.info("Ignored image directive %s" %(com,))
+ else:
+ logging.warning("Unknown image directive %s" %(com,))
+
+ # now put the line in the list of lines
+ if replace is None:
+ self.lines.append(line)
+ else:
+ self.lines.pop(replace)
+ self.lines.insert(replace, line)
def set_root(self, val):
self._root = GrubDiskPart(val)
@@ -137,6 +156,7 @@ class GrubConfigFile(object):
self.filename = fn
self.images = []
self.timeout = -1
+ self._default = 0
if fn is not None:
self.parse()
@@ -164,7 +184,7 @@ class GrubConfigFile(object):
# new image
if l.startswith("title"):
if len(img) > 0:
- self.images.append(GrubImage(img))
+ self.add_image(GrubImage(img))
img = [l]
continue
@@ -172,12 +192,7 @@ class GrubConfigFile(object):
img.append(l)
continue
- try:
- (com, arg) = grub_split(l, 1)
- except ValueError:
- com = l
- arg = ""
-
+ (com, arg) = grub_exact_split(l, 2)
if self.commands.has_key(com):
if self.commands[com] is not None:
exec("%s = r\"%s\"" %(self.commands[com], arg.strip()))
@@ -187,7 +202,20 @@ class GrubConfigFile(object):
logging.warning("Unknown directive %s" %(com,))
if len(img) > 0:
- self.images.append(GrubImage(img))
+ self.add_image(GrubImage(img))
+
+ def set(self, line):
+ (com, arg) = grub_exact_split(line, 2)
+ if self.commands.has_key(com):
+ if self.commands[com] is not None:
+ exec("%s = r\"%s\"" %(self.commands[com], arg.strip()))
+ else:
+ logging.info("Ignored directive %s" %(com,))
+ else:
+ logging.warning("Unknown directive %s" %(com,))
+
+ def add_image(self, image):
+ self.images.append(image)
def _get_default(self):
return self._default
diff -r e4f1519b473f -r b60ea69932b1 tools/pygrub/src/pygrub
--- a/tools/pygrub/src/pygrub Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/pygrub/src/pygrub Wed Aug 09 18:04:20 2006 +0100
@@ -2,7 +2,7 @@
#
# pygrub - simple python-based bootloader for Xen
#
-# Copyright 2005 Red Hat, Inc.
+# Copyright 2005-2006 Red Hat, Inc.
# Jeremy Katz <katzj@xxxxxxxxxx>
#
# This software may be freely redistributed under the terms of the GNU
@@ -14,9 +14,10 @@
#
import os, sys, string, struct, tempfile
+import copy
import logging
-import curses, _curses, curses.wrapper
+import curses, _curses, curses.wrapper, curses.textpad, curses.ascii
import getopt
sys.path = [ '/usr/lib/python' ] + sys.path
@@ -24,122 +25,387 @@ import grub.GrubConf
import grub.GrubConf
import grub.fsys
-PYGRUB_VER = 0.3
-
-
-def draw_window():
- stdscr = curses.initscr()
- if hasattr(curses, 'use_default_colors'):
- curses.use_default_colors()
- try:
- curses.curs_set(0)
- except _curses.error:
- pass
-
- stdscr.addstr(1, 4, "pyGRUB version %s" %(PYGRUB_VER,))
-
- win = curses.newwin(10, 74, 2, 1)
- win.box()
- win.refresh()
-
- stdscr.addstr(12, 5, "Use the U and D keys to select which entry is
highlighted.")
- stdscr.addstr(13, 5, "Press enter to boot the selected OS. 'e' to edit
the")
- stdscr.addstr(14, 5, "commands before booting, 'a' to modify the kernel
arguments ")
- stdscr.addstr(15, 5, "before booting, or 'c' for a command line.")
- stdscr.addch(12, 13, curses.ACS_UARROW)
- stdscr.addch(12, 19, curses.ACS_DARROW)
- (y, x) = stdscr.getmaxyx()
- stdscr.move(y - 1, x - 1)
-
- stdscr.refresh()
- return (stdscr, win)
-
-def fill_entries(win, cfg, selected):
- y = 0
-
- for i in cfg.images:
- if (0, y) > win.getmaxyx():
- break
- if y == selected:
- attr = curses.A_REVERSE
- else:
- attr = 0
- win.addstr(y + 1, 2, i.title.ljust(70), attr)
- y += 1
- win.refresh()
-
-def select(win, line):
- win.attron(curses.A_REVERSE)
- win.redrawln(line + 1, 1)
- win.refresh()
+PYGRUB_VER = 0.4
def is_disk_image(file):
fd = os.open(file, os.O_RDONLY)
buf = os.read(fd, 512)
os.close(fd)
- if len(buf) >= 512 and struct.unpack("H", buf[0x1fe: 0x200]) == (0xaa55,):
+ if len(buf) >= 512 and \
+ struct.unpack("H", buf[0x1fe: 0x200]) == (0xaa55,):
return True
return False
SECTOR_SIZE=512
def get_active_offset(file):
- """Find the offset for the start of the first active partition in the
- disk image file."""
+ """Find the offset for the start of the first active partition "
+ "in the disk image file."""
+
fd = os.open(file, os.O_RDONLY)
buf = os.read(fd, 512)
for poff in (446, 462, 478, 494): # partition offsets
# active partition has 0x80 as the first byte
if struct.unpack("<c", buf[poff:poff+1]) == ('\x80',):
- return struct.unpack("<L", buf[poff+8:poff+12])[0] * SECTOR_SIZE
- return -1
-
-def get_config(fn, isconfig = False):
- if not os.access(fn, os.R_OK):
- raise RuntimeError, "Unable to access %s" %(fn,)
-
- cf = grub.GrubConf.GrubConfigFile()
-
- if isconfig:
- # set the config file and parse it
- cf.filename = fn
- cf.parse()
- return cf
-
- offset = 0
- if is_disk_image(fn):
- offset = get_active_offset(fn)
- if offset == -1:
- raise RuntimeError, "Unable to find active partition on disk"
-
- # open the image and read the grub config
- fs = None
- for fstype in grub.fsys.fstypes.values():
- if fstype.sniff_magic(fn, offset):
- fs = fstype.open_fs(fn, offset)
+ return struct.unpack("<L",
+ buf[poff+8:poff+12])[0] * SECTOR_SIZE
+
+ # if there's not a partition marked as active, fall back to
+ # the first partition
+ P1 = 446
+ return struct.unpack("<L", buf[P1+8:P1+12])[0] * SECTOR_SIZE
+
+class GrubLineEditor(curses.textpad.Textbox):
+ def __init__(self, screen, startx, starty, line = ""):
+ screen.addstr(startx, starty, "> ")
+ screen.refresh()
+ win = curses.newwin(1, 74, startx, starty + 2)
+ curses.textpad.Textbox.__init__(self, win)
+
+ self.line = list(line)
+ self.pos = len(line)
+ self.cancelled = False
+ self.show_text()
+
+ def show_text(self):
+ """Show the text. One of our advantages over standard textboxes
+ is that we can handle lines longer than the window."""
+
+ self.win.clear()
+ if self.pos > 70:
+ if self.pos > 130:
+ off = 120
+ else:
+ off = 55
+ l = [ "<" ] + self.line[off:]
+ p = self.pos - off
+ else:
+ l = self.line[:70]
+ p = self.pos
+ self.win.addstr(0, 0, string.join(l, ("")))
+ if self.pos > 70:
+ self.win.addch(0, 0, curses.ACS_LARROW)
+
+ self.win.move(0, p)
+
+ def do_command(self, ch):
+ # we handle escape as well as moving the line around, so have
+ # to override some of the default handling
+
+ self.lastcmd = ch
+ if ch == 27: # esc
+ self.cancelled = True
+ return 0
+ elif curses.ascii.isprint(ch):
+ self.line.insert(self.pos, chr(ch))
+ self.pos += 1
+ elif ch == curses.ascii.SOH: # ^a
+ self.pos = 0
+ elif ch in (curses.ascii.STX,curses.KEY_LEFT):
+ self.pos -= 1
+ elif ch in (curses.ascii.BS,curses.KEY_BACKSPACE):
+ if self.pos > 0:
+ self.pos -= 1
+ self.line.pop(self.pos)
+ elif ch == curses.ascii.EOT: # ^d
+ self.line.pop(self.pos)
+ elif ch == curses.ascii.ENQ: # ^e
+ self.pos = len(self.line)
+ elif ch in (curses.ascii.ACK, curses.KEY_RIGHT):
+ self.pos +=1
+ elif ch == curses.ascii.VT: # ^k
+ self.line = self.line[:self.pos]
+ else:
+ return curses.textpad.Textbox.do_command(self, ch)
+ self.show_text()
+ return 1
+
+ def edit(self):
+ r = curses.textpad.Textbox.edit(self)
+ if self.cancelled:
+ return None
+ return string.join(self.line, "")
+
+
+class Grub:
+ def __init__(self, file, isconfig = False):
+ self.screen = None
+ self.entry_win = None
+ self.text_win = None
+ if file:
+ self.read_config(file, isconfig)
+
+ def draw_main_windows(self):
+ if self.screen is None: #only init stuff once
+ self.screen = curses.initscr()
+ self.screen.timeout(1000)
+ if hasattr(curses, 'use_default_colors'):
+ curses.use_default_colors()
+ try:
+ curses.curs_set(0)
+ except _curses.error:
+ pass
+ self.entry_win = curses.newwin(10, 74, 2, 1)
+ self.text_win = curses.newwin(10, 70, 12, 5)
+
+ self.screen.clear()
+ self.screen.refresh()
+
+ # create basic grub screen with a box of entries and a textbox
+ self.screen.addstr(1, 4, "pyGRUB version %s" %(PYGRUB_VER,))
+ self.entry_win.box()
+ self.screen.refresh()
+
+ def fill_entry_list(self):
+ self.entry_win.clear()
+ self.entry_win.box()
+ for y in range(0, len(self.cf.images)):
+ i = self.cf.images[y]
+ if (0, y) > self.entry_win.getmaxyx():
+ break
+ if y == self.selected_image:
+ attr = curses.A_REVERSE
+ else:
+ attr = 0
+ self.entry_win.addstr(y + 1, 2, i.title.ljust(70), attr)
+ self.entry_win.refresh()
+
+ def edit_entry(self, origimg):
+ def draw():
+ self.draw_main_windows()
+
+ self.text_win.addstr(0, 0, "Use the U and D keys to select which
entry is highlighted.")
+ self.text_win.addstr(1, 0, "Press 'b' to boot, 'e' to edit the
selected command in the")
+ self.text_win.addstr(2, 0, "boot sequence, 'c' for a command-line,
'o' to open a new line")
+ self.text_win.addstr(3, 0, "after ('O' for before) the selected
line, 'd' to remove the")
+ self.text_win.addstr(4, 0, "selected line, or escape to go back to
the main menu.")
+ self.text_win.addch(0, 8, curses.ACS_UARROW)
+ self.text_win.addch(0, 14, curses.ACS_DARROW)
+ (y, x) = self.text_win.getmaxyx()
+ self.text_win.move(y - 1, x - 1)
+ self.text_win.refresh()
+
+ curline = 1
+ img = copy.deepcopy(origimg)
+ while 1:
+ draw()
+ self.entry_win.clear()
+ self.entry_win.box()
+ for idx in range(1, len(img.lines)):
+ # current line should be highlighted
+ attr = 0
+ if idx == curline:
+ attr = curses.A_REVERSE
+
+ # trim the line
+ l = img.lines[idx].ljust(70)
+ if len(l) > 70:
+ l = l[:69] + ">"
+
+ self.entry_win.addstr(idx, 2, l, attr)
+ self.entry_win.refresh()
+
+ c = self.screen.getch()
+ if c in (ord('q'), 27): # 27 == esc
+ break
+ elif c == curses.KEY_UP:
+ curline -= 1
+ elif c == curses.KEY_DOWN:
+ curline += 1
+ elif c == ord('b'):
+ self.isdone = True
+ break
+ elif c == ord('e'):
+ l = self.edit_line(img.lines[curline])
+ if l is not None:
+ img.set_from_line(l, replace = curline)
+ elif c == ord('d'):
+ img.lines.pop(curline)
+ elif c == ord('o'):
+ img.lines.insert(curline+1, "")
+ curline += 1
+ elif c == ord('O'):
+ img.lines.insert(curline, "")
+ elif c == ord('c'):
+ self.command_line_mode()
+ if self.isdone:
+ return
+
+ # bound at the top and bottom
+ if curline < 1:
+ curline = 1
+ elif curline >= len(img.lines):
+ curline = len(img.lines) - 1
+
+ if self.isdone:
+ origimg.reset(img.lines)
+
+ def edit_line(self, line):
+ self.screen.clear()
+ self.screen.addstr(1, 2, "[ Minimal BASH-like line editing is
supported. ")
+ self.screen.addstr(2, 2, " ESC at any time cancels. ENTER at any
time accepts your changes. ]")
+ self.screen.refresh()
+
+ t = GrubLineEditor(self.screen, 5, 2, line)
+ ret = t.edit()
+ if ret:
+ return ret
+ return None
+
+ def command_line_mode(self):
+ self.screen.clear()
+ self.screen.addstr(1, 2, "[ Minimal BASH-like line editing is
supported. ESC at any time ")
+ self.screen.addstr(2, 2, " exits. Typing 'boot' will boot with your
entered commands. ] ")
+ self.screen.refresh()
+
+ y = 5
+ lines = []
+ while 1:
+ t = GrubLineEditor(self.screen, y, 2)
+ ret = t.edit()
+ if ret:
+ if ret in ("quit", "return"):
+ break
+ elif ret != "boot":
+ y += 1
+ lines.append(ret)
+ continue
+
+ # if we got boot, then we want to boot the entered image
+ img = grub.GrubConf.GrubImage(lines)
+ self.cf.add_image(img)
+ self.selected_image = len(self.cf.images) - 1
+ self.isdone = True
+ break
+
+ # else, we cancelled and should just go back
break
- if fs is not None:
- grubfile = None
- for f in ("/boot/grub/menu.lst", "/boot/grub/grub.conf",
- "/grub/menu.lst", "/grub/grub.conf"):
- if fs.file_exist(f):
- grubfile = f
- break
- if grubfile is None:
- raise RuntimeError, "we couldn't find
/boot/grub{menu.lst,grub.conf} " + \
- "in the image provided. halt!"
- f = fs.open_file(grubfile)
- buf = f.read()
- f.close()
- fs.close()
- # then parse the grub config
- cf.parse(buf)
- else:
- raise RuntimeError, "Unable to read filesystem"
-
- return cf
-
+ def read_config(self, fn, isConfig = False):
+ """Read the given file to parse the config. If isconfig, then
+ we're being given a raw config file rather than a disk image."""
+
+ if not os.access(fn, os.R_OK):
+ raise RuntimeError, "Unable to access %s" %(fn,)
+
+ self.cf = grub.GrubConf.GrubConfigFile()
+
+ if isConfig:
+ # set the config file and parse it
+ self.cf.filename = fn
+ self.cf.parse()
+ return
+
+ offset = 0
+ if is_disk_image(fn):
+ offset = get_active_offset(fn)
+ if offset == -1:
+ raise RuntimeError, "Unable to find active partition on disk"
+
+ # open the image and read the grub config
+ fs = None
+ for fstype in grub.fsys.fstypes.values():
+ if fstype.sniff_magic(fn, offset):
+ fs = fstype.open_fs(fn, offset)
+ break
+
+ if fs is not None:
+ grubfile = None
+ for f in ("/boot/grub/menu.lst", "/boot/grub/grub.conf",
+ "/grub/menu.lst", "/grub/grub.conf"):
+ if fs.file_exist(f):
+ grubfile = f
+ break
+ if grubfile is None:
+ raise RuntimeError, "we couldn't find grub config file in the
image provided."
+ f = fs.open_file(grubfile)
+ buf = f.read()
+ f.close()
+ fs.close()
+ # then parse the grub config
+ self.cf.parse(buf)
+ else:
+ raise RuntimeError, "Unable to read filesystem"
+
+ def run(self):
+ timeout = int(self.cf.timeout)
+
+ self.selected_image = self.cf.default
+ self.isdone = False
+ while not self.isdone:
+ self.run_main(timeout)
+ timeout = -1
+
+ return self.selected_image
+
+ def run_main(self, timeout = -1):
+ def draw():
+ # set up the screen
+ self.draw_main_windows()
+ self.text_win.addstr(0, 0, "Use the U and D keys to select which
entry is highlighted.")
+ self.text_win.addstr(1, 0, "Press enter to boot the selected OS.
'e' to edit the")
+ self.text_win.addstr(2, 0, "commands before booting, 'a' to modify
the kernel arguments ")
+ self.text_win.addstr(3, 0, "before booting, or 'c' for a command
line.")
+ self.text_win.addch(0, 8, curses.ACS_UARROW)
+ self.text_win.addch(0, 14, curses.ACS_DARROW)
+ (y, x) = self.text_win.getmaxyx()
+ self.text_win.move(y - 1, x - 1)
+ self.text_win.refresh()
+
+ # now loop until we hit the timeout or get a go from the user
+ mytime = 0
+ while (timeout == -1 or mytime < int(timeout)):
+ draw()
+ if timeout != -1 and mytime != -1:
+ self.screen.addstr(20, 5, "Will boot selected entry in %2d
seconds"
+ %(int(timeout) - mytime))
+ else:
+ self.screen.addstr(20, 5, " " * 80)
+
+ self.fill_entry_list()
+ c = self.screen.getch()
+ if mytime != -1:
+ mytime += 1
+
+ # handle keypresses
+ if c == ord('c'):
+ self.command_line_mode()
+ break
+ elif c == ord('a'):
+ # find the kernel line, edit it and then boot
+ img = self.cf.images[self.selected_image]
+ for line in img.lines:
+ if line.startswith("kernel"):
+ l = self.edit_line(line)
+ if l is not None:
+ img.set_from_line(l, replace = True)
+ self.isdone = True
+ break
+ break
+ elif c == ord('e'):
+ img = self.cf.images[self.selected_image]
+ self.edit_entry(img)
+ break
+ elif c in (curses.KEY_ENTER, ord('\n'), ord('\r')):
+ self.isdone = True
+ break
+ elif c == curses.KEY_UP:
+ mytime = -1
+ self.selected_image -= 1
+ elif c == curses.KEY_DOWN:
+ mytime = -1
+ self.selected_image += 1
+# elif c in (ord('q'), 27): # 27 == esc
+# self.selected_image = -1
+# self.isdone = True
+# break
+
+ # bound at the top and bottom
+ if self.selected_image < 0:
+ self.selected_image = 0
+ elif self.selected_image >= len(self.cf.images):
+ self.selected_image = len(self.cf.images) - 1
+
def get_entry_idx(cf, entry):
# first, see if the given entry is numeric
try:
@@ -155,63 +421,12 @@ def get_entry_idx(cf, entry):
return None
-def main(cf = None):
- mytime = 0
- timeout = int(cf.timeout)
-
- (stdscr, win) = draw_window()
- stdscr.timeout(1000)
- selected = cf.default
-
- while (timeout == -1 or mytime < int(timeout)):
- if timeout != -1 and mytime != -1:
- stdscr.addstr(20, 5, "Will boot selected entry in %2d seconds"
- %(int(timeout) - mytime))
- else:
- stdscr.addstr(20, 5, " " * 80)
-
- fill_entries(win, cf, selected)
- c = stdscr.getch()
- if mytime != -1:
- mytime += 1
-# if c == ord('q'):
-# selected = -1
-# break
- if c == ord('c'):
- # FIXME: needs to go to command line mode
- continue
- elif c == ord('a'):
- # FIXME: needs to go to append mode
- continue
- elif c == ord('e'):
- # FIXME: needs to go to edit mode
- continue
- elif c in (curses.KEY_ENTER, ord('\n'), ord('\r')):
- break
- elif c == curses.KEY_UP:
- mytime = -1
- selected -= 1
- elif c == curses.KEY_DOWN:
- mytime = -1
- selected += 1
- else:
- pass
-
- # bound at the top and bottom
- if selected < 0:
- selected = 0
- elif selected >= len(cf.images):
- selected = len(cf.images) - 1
-
- if selected >= 0:
- return selected
-
if __name__ == "__main__":
sel = None
def run_main(scr, *args):
global sel
- sel = main(cf)
+ sel = g.run()
def usage():
print >> sys.stderr, "Usage: %s [-q|--quiet] [--output=] [--entry=]
<image>" %(sys.argv[0],)
@@ -253,24 +468,32 @@ if __name__ == "__main__":
else:
fd = os.open(output, os.O_WRONLY)
- cf = get_config(file, isconfig)
+ g = Grub(file, isconfig)
if interactive:
curses.wrapper(run_main)
else:
- sel = cf.default
+ sel = g.cf.default
# set the entry to boot as requested
if entry is not None:
- idx = get_entry_idx(cf, entry)
- if idx is not None and idx > 0 and idx < len(cf.images):
+ idx = get_entry_idx(g.cf, entry)
+ if idx is not None and idx > 0 and idx < len(g.cf.images):
sel = idx
- img = cf.images[sel]
+ if sel == -1:
+ print "No kernel image selected!"
+ sys.exit(1)
+
+ img = g.cf.images[sel]
print "Going to boot %s" %(img.title)
print " kernel: %s" %(img.kernel[1],)
if img.initrd:
print " initrd: %s" %(img.initrd[1],)
+ if isconfig:
+ print " args: %s" %(img.args,)
+ sys.exit(0)
+
offset = 0
if is_disk_image(file):
offset = get_active_offset(file)
@@ -288,14 +511,14 @@ if __name__ == "__main__":
raise RuntimeError, "Unable to open filesystem"
kernel = fs.open_file(img.kernel[1],).read()
- (tfd, fn) = tempfile.mkstemp(prefix="vmlinuz.")
+ (tfd, fn) = tempfile.mkstemp(prefix="vmlinuz.", dir="/var/lib/xen")
os.write(tfd, kernel)
os.close(tfd)
sxp = "linux (kernel %s)" %(fn,)
if img.initrd:
initrd = fs.open_file(img.initrd[1],).read()
- (tfd, fn) = tempfile.mkstemp(prefix="initrd.")
+ (tfd, fn) = tempfile.mkstemp(prefix="initrd.", dir="/var/lib/xen")
os.write(tfd, initrd)
os.close(tfd)
sxp += "(ramdisk %s)" %(fn,)
diff -r e4f1519b473f -r b60ea69932b1 tools/python/xen/util/xmlrpclib2.py
--- a/tools/python/xen/util/xmlrpclib2.py Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/python/xen/util/xmlrpclib2.py Wed Aug 09 18:04:20 2006 +0100
@@ -138,6 +138,11 @@ class TCPXMLRPCServer(SocketServer.Threa
def _marshaled_dispatch(self, data, dispatch_method = None):
params, method = xmlrpclib.loads(data)
+ if False:
+ # Enable this block of code to exit immediately without sending
+ # a response. This allows you to test client-side crash handling.
+ import sys
+ sys.exit(1)
try:
if dispatch_method is not None:
response = dispatch_method(method, params)
diff -r e4f1519b473f -r b60ea69932b1 tools/python/xen/xend/XendDomain.py
--- a/tools/python/xen/xend/XendDomain.py Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/python/xen/xend/XendDomain.py Wed Aug 09 18:04:20 2006 +0100
@@ -402,9 +402,9 @@ class XendDomain:
val = dominfo.destroy()
else:
try:
- val = xc.domain_destroy(domid)
+ val = xc.domain_destroy(int(domid))
except Exception, ex:
- raise XendError(str(ex))
+ raise XendInvalidDomain(str(domid))
return val
def domain_migrate(self, domid, dst, live=False, resource=0, port=0):
diff -r e4f1519b473f -r b60ea69932b1 tools/python/xen/xend/image.py
--- a/tools/python/xen/xend/image.py Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/python/xen/xend/image.py Wed Aug 09 18:04:20 2006 +0100
@@ -260,7 +260,7 @@ class HVMImageHandler(ImageHandler):
if a == 'stdvga': a = 'std-vga'
# Handle booleans gracefully
- if a in ['localtime', 'std-vga', 'isa', 'usb']:
+ if a in ['localtime', 'std-vga', 'isa', 'usb', 'acpi']:
if v != None: v = int(v)
if v: ret.append("-%s" % a)
else:
@@ -307,6 +307,7 @@ class HVMImageHandler(ImageHandler):
vnc = sxp.child_value(config, 'vnc')
vncdisplay = sxp.child_value(config, 'vncdisplay',
int(self.vm.getDomid()))
+ vncunused = sxp.child_value(config, 'vncunused')
sdl = sxp.child_value(config, 'sdl')
ret = []
nographic = sxp.child_value(config, 'nographic')
@@ -315,6 +316,8 @@ class HVMImageHandler(ImageHandler):
return ret
if vnc:
ret = ret + ['-vnc', '%d' % vncdisplay, '-k', 'en-us']
+ if vncunused:
+ ret += ['-vncunused']
return ret
def createDeviceModel(self):
diff -r e4f1519b473f -r b60ea69932b1 tools/python/xen/xend/sxp.py
--- a/tools/python/xen/xend/sxp.py Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/python/xen/xend/sxp.py Wed Aug 09 18:04:20 2006 +0100
@@ -291,7 +291,7 @@ class Parser:
raise ParseError(self, "unexpected EOF")
elif '0' <= c <= '7':
octaldigit(c)
- elif len(self.buf):
+ elif len(self.state.buf):
octaldone()
self.input_char(c)
diff -r e4f1519b473f -r b60ea69932b1 tools/python/xen/xend/tests/test_sxp.py
--- a/tools/python/xen/xend/tests/test_sxp.py Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/python/xen/xend/tests/test_sxp.py Wed Aug 09 18:04:20 2006 +0100
@@ -14,5 +14,26 @@ class test_sxp(unittest.TestCase):
t('(String) (Thing)', [['String'], ['Thing']])
+ def testParseFixed(self):
+ fin = file('../xen/xend/tests/xend-config.sxp', 'rb')
+ try:
+ config = xen.xend.sxp.parse(fin)
+ self.assertEqual(
+ xen.xend.sxp.child_value(
+ config,
+ 'xend-relocation-hosts-allow'),
+ '^localhost$ ^localhost\\.localdomain$')
+ finally:
+ fin.close()
+
+
+ def testParseConfigExample(self):
+ fin = file('../../examples/xend-config.sxp', 'rb')
+ try:
+ config = xen.xend.sxp.parse(fin)
+ finally:
+ fin.close()
+
+
def test_suite():
return unittest.makeSuite(test_sxp)
diff -r e4f1519b473f -r b60ea69932b1 tools/python/xen/xm/create.py
--- a/tools/python/xen/xm/create.py Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/python/xen/xm/create.py Wed Aug 09 18:04:20 2006 +0100
@@ -411,6 +411,11 @@ gopts.var('vncdisplay', val='',
gopts.var('vncdisplay', val='',
fn=set_value, default=None,
use="""VNC display to use""")
+
+gopts.var('vncunused', val='',
+ fn=set_bool, default=1,
+ use="""Try to find an unused port for the VNC server.
+ Only valid when vnc=1.""")
gopts.var('sdl', val='',
fn=set_value, default=None,
@@ -627,7 +632,7 @@ def configure_hvm(config_image, vals):
"""
args = [ 'device_model', 'pae', 'vcpus', 'boot', 'fda', 'fdb',
'localtime', 'serial', 'stdvga', 'isa', 'nographic', 'soundhw',
- 'vnc', 'vncdisplay', 'vncconsole', 'sdl', 'display',
+ 'vnc', 'vncdisplay', 'vncunused', 'vncconsole', 'sdl', 'display',
'acpi', 'apic', 'xauthority', 'usb', 'usbdevice' ]
for a in args:
if (vals.__dict__[a]):
@@ -844,14 +849,58 @@ def choose_vnc_display():
vncpid = None
+def daemonize(prog, args):
+ """Runs a program as a daemon with the list of arguments. Returns the PID
+ of the daemonized program, or returns 0 on error.
+ """
+ r, w = os.pipe()
+ pid = os.fork()
+
+ if pid == 0:
+ os.close(r)
+ w = os.fdopen(w, 'w')
+ os.setsid()
+ try:
+ pid2 = os.fork()
+ except:
+ pid2 = None
+ if pid2 == 0:
+ os.chdir("/")
+ for fd in range(0, 256):
+ try:
+ os.close(fd)
+ except:
+ pass
+ os.open("/dev/null", os.O_RDWR)
+ os.dup2(0, 1)
+ os.dup2(0, 2)
+ os.execvp(prog, args)
+ os._exit(1)
+ else:
+ w.write(str(pid2 or 0))
+ w.close()
+ os._exit(0)
+
+ os.close(w)
+ r = os.fdopen(r)
+ daemon_pid = int(r.read())
+ r.close()
+ os.waitpid(pid, 0)
+ return daemon_pid
+
def spawn_vnc(display):
+ """Spawns a vncviewer that listens on the specified display. On success,
+ returns the port that the vncviewer is listening on and sets the global
+ vncpid. On failure, returns 0. Note that vncviewer is daemonized.
+ """
vncargs = (["vncviewer", "-log", "*:stdout:0",
"-listen", "%d" % (VNC_BASE_PORT + display) ])
- global vncpid
- vncpid = os.spawnvp(os.P_NOWAIT, "vncviewer", vncargs)
-
+ global vncpid
+ vncpid = daemonize("vncviewer", vncargs)
+ if vncpid == 0:
+ return 0
return VNC_BASE_PORT + display
-
+
def preprocess_vnc(vals):
"""If vnc was specified, spawn a vncviewer in listen mode
and pass its address to the domain on the kernel command line.
@@ -928,7 +977,7 @@ def make_domain(opts, config):
import signal
if vncpid:
os.kill(vncpid, signal.SIGKILL)
- raise ex
+ raise
dom = sxp.child_value(dominfo, 'name')
diff -r e4f1519b473f -r b60ea69932b1 tools/python/xen/xm/main.py
--- a/tools/python/xen/xm/main.py Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/python/xen/xm/main.py Wed Aug 09 18:04:20 2006 +0100
@@ -1257,6 +1257,16 @@ def main(argv=sys.argv):
else:
print >>sys.stderr, "Error: %s" % ex.faultString
sys.exit(1)
+ except xmlrpclib.ProtocolError, ex:
+ if ex.errcode == -1:
+ print >>sys.stderr, (
+ "Xend has probably crashed! Invalid or missing HTTP "
+ "status code.")
+ else:
+ print >>sys.stderr, (
+ "Xend has probably crashed! ProtocolError(%d, %s)." %
+ (ex.errcode, ex.errmsg))
+ sys.exit(1)
except (ValueError, OverflowError):
err("Invalid argument.")
usage(argv[1])
diff -r e4f1519b473f -r b60ea69932b1 tools/python/xen/xm/tests/test_create.py
--- a/tools/python/xen/xm/tests/test_create.py Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/python/xen/xm/tests/test_create.py Wed Aug 09 18:04:20 2006 +0100
@@ -179,7 +179,8 @@ ne2000=0
'extra' : ('VNC_VIEWER=%s:%d ' %
(xen.xm.create.get_host_addr(),
- xen.xm.create.VNC_BASE_PORT + 1)),
+ xen.xm.create.VNC_BASE_PORT +
+ xen.xm.create.choose_vnc_display())),
'vnc' : 1,
'vncviewer' : 1,
diff -r e4f1519b473f -r b60ea69932b1 tools/xenstat/libxenstat/src/xenstat.c
--- a/tools/xenstat/libxenstat/src/xenstat.c Tue Aug 08 19:07:32 2006 -0500
+++ b/tools/xenstat/libxenstat/src/xenstat.c Wed Aug 09 18:04:20 2006 +0100
@@ -103,7 +103,10 @@ struct xenstat_vbd {
* Data-collection types
*/
/* Called to collect the information for the node and all the domains on
- * it. When called, the domain information has already been collected. */
+ * it. When called, the domain information has already been collected.
+ * Return status is 0 if fatal error occurs, 1 for success. Collectors
+ * may prune a domain from the list if it has been deleted between the
+ * time the list was setup and the time the colector is called */
typedef int (*xenstat_collect_func)(xenstat_node * node);
/* Called to free the information collected by the collect function. The free
* function will only be called on a xenstat_node if that node includes
@@ -134,6 +137,7 @@ static void xenstat_uninit_xen_version(x
static void xenstat_uninit_xen_version(xenstat_handle * handle);
static void xenstat_uninit_vbds(xenstat_handle * handle);
static char *xenstat_get_domain_name(xenstat_handle * handle, unsigned int
domain_id);
+static void xenstat_prune_domain(xenstat_node *node, unsigned int entry);
static xenstat_collector collectors[] = {
{ XENSTAT_VCPU, xenstat_collect_vcpus,
@@ -208,7 +212,7 @@ xenstat_node *xenstat_get_node(xenstat_h
xenstat_node *node;
dom0_physinfo_t physinfo;
dom0_getdomaininfo_t domaininfo[DOMAIN_CHUNK_SIZE];
- unsigned int num_domains, new_domains;
+ unsigned int new_domains;
unsigned int i;
/* Create the node */
@@ -242,15 +246,17 @@ xenstat_node *xenstat_get_node(xenstat_h
return NULL;
}
- num_domains = 0;
+ node->num_domains = 0;
do {
xenstat_domain *domain, *tmp;
new_domains = xc_domain_getinfolist(handle->xc_handle,
- num_domains, DOMAIN_CHUNK_SIZE, domaininfo);
+ node->num_domains,
+ DOMAIN_CHUNK_SIZE,
+ domaininfo);
tmp = realloc(node->domains,
- (num_domains + new_domains)
+ (node->num_domains + new_domains)
* sizeof(xenstat_domain));
if (tmp == NULL) {
free(node->domains);
@@ -259,12 +265,29 @@ xenstat_node *xenstat_get_node(xenstat_h
}
node->domains = tmp;
- domain = node->domains + num_domains;
+ domain = node->domains + node->num_domains;
+
+ /* zero out newly allocated memory in case error occurs below */
+ memset(domain, 0, new_domains * sizeof(xenstat_domain));
for (i = 0; i < new_domains; i++) {
/* Fill in domain using domaininfo[i] */
domain->id = domaininfo[i].domain;
- domain->name = xenstat_get_domain_name(handle,
domaininfo[i].domain);
+ domain->name = xenstat_get_domain_name(handle,
+ domain->id);
+ if (domain->name == NULL) {
+ if (errno == ENOMEM) {
+ /* fatal error */
+ xenstat_free_node(node);
+ return NULL;
+ }
+ else {
+ /* failed to get name -- this means the
+ domain is being destroyed so simply
+ ignore this entry */
+ continue;
+ }
+ }
domain->state = domaininfo[i].flags;
domain->cpu_ns = domaininfo[i].cpu_time;
domain->num_vcpus = (domaininfo[i].max_vcpu_id+1);
@@ -284,10 +307,9 @@ xenstat_node *xenstat_get_node(xenstat_h
domain->vbds = NULL;
domain++;
- }
- num_domains += new_domains;
+ node->num_domains++;
+ }
} while (new_domains == DOMAIN_CHUNK_SIZE);
- node->num_domains = num_domains;
/* Run all the extra data collectors requested */
node->flags = 0;
@@ -495,10 +517,12 @@ xenstat_vbd *xenstat_domain_vbd(xenstat_
/* Collect information about VCPUs */
static int xenstat_collect_vcpus(xenstat_node * node)
{
- unsigned int i, vcpu;
+ unsigned int i, vcpu, inc_index;
/* Fill in VCPU information */
- for (i = 0; i < node->num_domains; i++) {
+ for (i = 0; i < node->num_domains; i+=inc_index) {
+ inc_index = 1; /* default is to increment to next domain */
+
node->domains[i].vcpus = malloc(node->domains[i].num_vcpus
* sizeof(xenstat_vcpu));
if (node->domains[i].vcpus == NULL)
@@ -509,11 +533,25 @@ static int xenstat_collect_vcpus(xenstat
dom0_getvcpuinfo_t info;
if (xc_vcpu_getinfo(node->handle->xc_handle,
- node->domains[i].id, vcpu, &info) != 0)
- return 0;
-
- node->domains[i].vcpus[vcpu].online = info.online;
- node->domains[i].vcpus[vcpu].ns = info.cpu_time;
+ node->domains[i].id, vcpu, &info)
!= 0) {
+ if (errno == ENOMEM) {
+ /* fatal error */
+ return 0;
+ }
+ else {
+ /* domain is in transition - remove
+ from list */
+ xenstat_prune_domain(node, i);
+
+ /* remember not to increment index! */
+ inc_index = 0;
+ break;
+ }
+ }
+ else {
+ node->domains[i].vcpus[vcpu].online =
info.online;
+ node->domains[i].vcpus[vcpu].ns = info.cpu_time;
+ }
}
}
return 1;
@@ -884,13 +922,30 @@ static char *xenstat_get_domain_name(xen
static char *xenstat_get_domain_name(xenstat_handle *handle, unsigned int
domain_id)
{
char path[80];
- char *name;
snprintf(path, sizeof(path),"/local/domain/%i/name", domain_id);
- name = xs_read(handle->xshandle, XBT_NULL, path, NULL);
- if (name == NULL)
- name = strdup(" ");
-
- return name;
+ return xs_read(handle->xshandle, XBT_NULL, path, NULL);
}
+
+/* Remove specified entry from list of domains */
+static void xenstat_prune_domain(xenstat_node *node, unsigned int entry)
+{
+ /* nothing to do if array is empty or entry is beyond end */
+ if (node->num_domains == 0 || entry >= node->num_domains)
+ return;
+
+ /* decrement count of domains */
+ node->num_domains--;
+
+ /* shift entries following specified entry up by one */
+ if (entry < node->num_domains) {
+ xenstat_domain *domain = &node->domains[entry];
+ memmove(domain,domain+1,node->num_domains-entry);
+ }
+
+ /* zero out original last entry from node -- not
+ strictly necessary but safer! */
+ memset(&node->domains[node->num_domains], 0, sizeof(xenstat_domain));
+}
+
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/ia64/xen/hypercall.c
--- a/xen/arch/ia64/xen/hypercall.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/ia64/xen/hypercall.c Wed Aug 09 18:04:20 2006 +0100
@@ -335,7 +335,7 @@ unsigned long hypercall_create_continuat
unsigned long hypercall_create_continuation(
unsigned int op, const char *format, ...)
{
- struct mc_state *mcs = &mc_state[smp_processor_id()];
+ struct mc_state *mcs = &this_cpu(mc_state);
struct vcpu *v = current;
const char *p = format;
unsigned long arg;
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/ia64/xen/xensetup.c
--- a/xen/arch/ia64/xen/xensetup.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/ia64/xen/xensetup.c Wed Aug 09 18:04:20 2006 +0100
@@ -423,13 +423,14 @@ void start_kernel(void)
(xenheap_phys_end-__pa(heap_start)) >> 20,
(xenheap_phys_end-__pa(heap_start)) >> 10);
+ late_setup_arch(&cmdline);
+
scheduler_init();
idle_vcpu[0] = (struct vcpu*) ia64_r13;
idle_domain = domain_create(IDLE_DOMAIN_ID);
if ( (idle_domain == NULL) || (alloc_vcpu(idle_domain, 0, 0) == NULL) )
BUG();
- late_setup_arch(&cmdline);
alloc_dom_xen_and_dom_io();
setup_per_cpu_areas();
mem_init();
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/powerpc/setup.c
--- a/xen/arch/powerpc/setup.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/powerpc/setup.c Wed Aug 09 18:04:20 2006 +0100
@@ -55,7 +55,7 @@ boolean_param("earlygdb", opt_earlygdb);
boolean_param("earlygdb", opt_earlygdb);
u32 tlbflush_clock = 1U;
-u32 tlbflush_time[NR_CPUS];
+DEFINE_PER_CPU(u32, tlbflush_time);
unsigned int watchdog_on;
unsigned long wait_init_idle;
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/domain.c
--- a/xen/arch/x86/domain.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/domain.c Wed Aug 09 18:04:20 2006 +0100
@@ -797,7 +797,7 @@ unsigned long hypercall_create_continuat
unsigned long hypercall_create_continuation(
unsigned int op, const char *format, ...)
{
- struct mc_state *mcs = &mc_state[smp_processor_id()];
+ struct mc_state *mcs = &this_cpu(mc_state);
struct cpu_user_regs *regs;
const char *p = format;
unsigned long arg;
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/flushtlb.c
--- a/xen/arch/x86/flushtlb.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/flushtlb.c Wed Aug 09 18:04:20 2006 +0100
@@ -20,7 +20,7 @@
#endif
u32 tlbflush_clock = 1U;
-u32 tlbflush_time[NR_CPUS];
+DEFINE_PER_CPU(u32, tlbflush_time);
void write_cr3(unsigned long cr3)
{
@@ -71,7 +71,7 @@ void write_cr3(unsigned long cr3)
* case, so really we are being ultra paranoid.
*/
- tlbflush_time[smp_processor_id()] = t2;
+ this_cpu(tlbflush_time) = t2;
local_irq_restore(flags);
}
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/hvm/hvm.c
--- a/xen/arch/x86/hvm/hvm.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/hvm/hvm.c Wed Aug 09 18:04:20 2006 +0100
@@ -29,6 +29,7 @@
#include <xen/domain_page.h>
#include <xen/hypercall.h>
#include <xen/guest_access.h>
+#include <xen/event.h>
#include <asm/current.h>
#include <asm/io.h>
#include <asm/shadow.h>
@@ -133,15 +134,28 @@ static void e820_map_io_shared_callback(
}
}
-void hvm_map_io_shared_page(struct vcpu *v)
-{
- unsigned long mfn = INVALID_MFN;
+static void e820_map_buffered_io_callback(struct domain *d,
+ struct e820entry *e,
+ void *data)
+{
+ unsigned long *mfn = data;
+ if ( e->type == E820_BUFFERED_IO ) {
+ ASSERT(*mfn == INVALID_MFN);
+ *mfn = gmfn_to_mfn(d, e->addr >> PAGE_SHIFT);
+ }
+}
+
+void hvm_map_io_shared_pages(struct vcpu *v)
+{
+ unsigned long mfn;
void *p;
struct domain *d = v->domain;
- if ( d->arch.hvm_domain.shared_page_va )
+ if ( d->arch.hvm_domain.shared_page_va ||
+ d->arch.hvm_domain.buffered_io_va )
return;
+ mfn = INVALID_MFN;
e820_foreach(d, e820_map_io_shared_callback, &mfn);
if ( mfn == INVALID_MFN )
@@ -158,7 +172,38 @@ void hvm_map_io_shared_page(struct vcpu
}
d->arch.hvm_domain.shared_page_va = (unsigned long)p;
-}
+
+ mfn = INVALID_MFN;
+ e820_foreach(d, e820_map_buffered_io_callback, &mfn);
+ if ( mfn != INVALID_MFN ) {
+ p = map_domain_page_global(mfn);
+ if ( p )
+ d->arch.hvm_domain.buffered_io_va = (unsigned long)p;
+ }
+}
+
+void hvm_create_event_channels(struct vcpu *v)
+{
+ vcpu_iodata_t *p;
+ struct vcpu *o;
+
+ if ( v->vcpu_id == 0 ) {
+ /* Ugly: create event channels for every vcpu when vcpu 0
+ starts, so that they're available for ioemu to bind to. */
+ for_each_vcpu(v->domain, o) {
+ p = get_vio(v->domain, o->vcpu_id);
+ o->arch.hvm_vcpu.xen_port = p->vp_eport =
+ alloc_unbound_xen_event_channel(o, 0);
+ DPRINTK("Allocated port %d for hvm.\n", o->arch.hvm_vcpu.xen_port);
+ }
+ }
+}
+
+void hvm_release_assist_channel(struct vcpu *v)
+{
+ free_xen_event_channel(v, v->arch.hvm_vcpu.xen_port);
+}
+
void hvm_setup_platform(struct domain* d)
{
@@ -175,7 +220,6 @@ void hvm_setup_platform(struct domain* d
}
hvm_zap_iommu_pages(d);
- hvm_map_io_shared_page(v);
platform = &d->arch.hvm_domain;
pic_init(&platform->vpic, pic_irq_request, &platform->interrupt_request);
@@ -186,6 +230,8 @@ void hvm_setup_platform(struct domain* d
spin_lock_init(&d->arch.hvm_domain.round_robin_lock);
hvm_vioapic_init(d);
}
+
+ spin_lock_init(&d->arch.hvm_domain.buffered_io_lock);
init_timer(&platform->pl_time.periodic_tm.timer,
pt_timer_fn, v, v->processor);
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/hvm/intercept.c
--- a/xen/arch/x86/hvm/intercept.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/hvm/intercept.c Wed Aug 09 18:04:20 2006 +0100
@@ -36,10 +36,24 @@ extern struct hvm_mmio_handler vioapic_m
#define HVM_MMIO_HANDLER_NR 2
-struct hvm_mmio_handler *hvm_mmio_handlers[HVM_MMIO_HANDLER_NR] =
+static struct hvm_mmio_handler *hvm_mmio_handlers[HVM_MMIO_HANDLER_NR] =
{
&vlapic_mmio_handler,
&vioapic_mmio_handler
+};
+
+struct hvm_buffered_io_range {
+ unsigned long start_addr;
+ unsigned long length;
+};
+
+#define HVM_BUFFERED_IO_RANGE_NR 1
+
+static struct hvm_buffered_io_range buffered_stdvga_range = {0xA0000, 0x20000};
+static struct hvm_buffered_io_range
+*hvm_buffered_io_ranges[HVM_BUFFERED_IO_RANGE_NR] =
+{
+ &buffered_stdvga_range
};
static inline void hvm_mmio_access(struct vcpu *v,
@@ -140,6 +154,56 @@ static inline void hvm_mmio_access(struc
}
}
+int hvm_buffered_io_intercept(ioreq_t *p)
+{
+ struct vcpu *v = current;
+ spinlock_t *buffered_io_lock;
+ buffered_iopage_t *buffered_iopage =
+ (buffered_iopage_t *)(v->domain->arch.hvm_domain.buffered_io_va);
+ unsigned long tmp_write_pointer = 0;
+ int i;
+
+ /* ignore READ ioreq_t! */
+ if ( p->dir == IOREQ_READ )
+ return 0;
+
+ for ( i = 0; i < HVM_BUFFERED_IO_RANGE_NR; i++ ) {
+ if ( p->addr >= hvm_buffered_io_ranges[i]->start_addr &&
+ p->addr + p->size - 1 < hvm_buffered_io_ranges[i]->start_addr +
+ hvm_buffered_io_ranges[i]->length )
+ break;
+ }
+
+ if ( i == HVM_BUFFERED_IO_RANGE_NR )
+ return 0;
+
+ buffered_io_lock = &v->domain->arch.hvm_domain.buffered_io_lock;
+ spin_lock(buffered_io_lock);
+
+ if ( buffered_iopage->write_pointer - buffered_iopage->read_pointer ==
+ (unsigned long)IOREQ_BUFFER_SLOT_NUM ) {
+ /* the queue is full.
+ * send the iopacket through the normal path.
+ * NOTE: The arithimetic operation could handle the situation for
+ * write_pointer overflow.
+ */
+ spin_unlock(buffered_io_lock);
+ return 0;
+ }
+
+ tmp_write_pointer = buffered_iopage->write_pointer % IOREQ_BUFFER_SLOT_NUM;
+
+ memcpy(&buffered_iopage->ioreq[tmp_write_pointer], p, sizeof(ioreq_t));
+
+ /*make the ioreq_t visible before write_pointer*/
+ wmb();
+ buffered_iopage->write_pointer++;
+
+ spin_unlock(buffered_io_lock);
+
+ return 1;
+}
+
int hvm_mmio_intercept(ioreq_t *p)
{
struct vcpu *v = current;
@@ -211,7 +275,7 @@ void hlt_timer_fn(void *data)
{
struct vcpu *v = data;
- evtchn_set_pending(v, iopacket_port(v));
+ hvm_prod_vcpu(v);
}
static __inline__ void missed_ticks(struct periodic_time *pt)
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/hvm/io.c
--- a/xen/arch/x86/hvm/io.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/hvm/io.c Wed Aug 09 18:04:20 2006 +0100
@@ -687,84 +687,17 @@ void hvm_io_assist(struct vcpu *v)
p = &vio->vp_ioreq;
- /* clear IO wait HVM flag */
- if ( test_bit(ARCH_HVM_IO_WAIT, &v->arch.hvm_vcpu.ioflags) ) {
- if ( p->state == STATE_IORESP_READY ) {
- p->state = STATE_INVALID;
- clear_bit(ARCH_HVM_IO_WAIT, &v->arch.hvm_vcpu.ioflags);
-
- if ( p->type == IOREQ_TYPE_PIO )
- hvm_pio_assist(regs, p, io_opp);
- else
- hvm_mmio_assist(regs, p, io_opp);
-
- /* Copy register changes back into current guest state. */
- hvm_load_cpu_guest_regs(v, regs);
- memcpy(guest_cpu_user_regs(), regs, HVM_CONTEXT_STACK_BYTES);
- }
- /* else an interrupt send event raced us */
- }
-}
-
-/*
- * On exit from hvm_wait_io, we're guaranteed not to be waiting on
- * I/O response from the device model.
- */
-void hvm_wait_io(void)
-{
- struct vcpu *v = current;
- struct domain *d = v->domain;
- int port = iopacket_port(v);
-
- for ( ; ; )
- {
- /* Clear master flag, selector flag, event flag each in turn. */
- v->vcpu_info->evtchn_upcall_pending = 0;
- clear_bit(port/BITS_PER_LONG, &v->vcpu_info->evtchn_pending_sel);
- smp_mb__after_clear_bit();
- if ( test_and_clear_bit(port, &d->shared_info->evtchn_pending[0]) )
- hvm_io_assist(v);
-
- /* Need to wait for I/O responses? */
- if ( !test_bit(ARCH_HVM_IO_WAIT, &v->arch.hvm_vcpu.ioflags) )
- break;
-
- do_sched_op_compat(SCHEDOP_block, 0);
- }
-
- /*
- * Re-set the selector and master flags in case any other notifications
- * are pending.
- */
- if ( d->shared_info->evtchn_pending[port/BITS_PER_LONG] )
- set_bit(port/BITS_PER_LONG, &v->vcpu_info->evtchn_pending_sel);
- if ( v->vcpu_info->evtchn_pending_sel )
- v->vcpu_info->evtchn_upcall_pending = 1;
-}
-
-void hvm_safe_block(void)
-{
- struct vcpu *v = current;
- struct domain *d = v->domain;
- int port = iopacket_port(v);
-
- for ( ; ; )
- {
- /* Clear master flag & selector flag so we will wake from block. */
- v->vcpu_info->evtchn_upcall_pending = 0;
- clear_bit(port/BITS_PER_LONG, &v->vcpu_info->evtchn_pending_sel);
- smp_mb__after_clear_bit();
-
- /* Event pending already? */
- if ( test_bit(port, &d->shared_info->evtchn_pending[0]) )
- break;
-
- do_sched_op_compat(SCHEDOP_block, 0);
- }
-
- /* Reflect pending event in selector and master flags. */
- set_bit(port/BITS_PER_LONG, &v->vcpu_info->evtchn_pending_sel);
- v->vcpu_info->evtchn_upcall_pending = 1;
+ if ( p->state == STATE_IORESP_READY ) {
+ p->state = STATE_INVALID;
+ if ( p->type == IOREQ_TYPE_PIO )
+ hvm_pio_assist(regs, p, io_opp);
+ else
+ hvm_mmio_assist(regs, p, io_opp);
+
+ /* Copy register changes back into current guest state. */
+ hvm_load_cpu_guest_regs(v, regs);
+ memcpy(guest_cpu_user_regs(), regs, HVM_CONTEXT_STACK_BYTES);
+ }
}
/*
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/hvm/platform.c
--- a/xen/arch/x86/hvm/platform.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/hvm/platform.c Wed Aug 09 18:04:20 2006 +0100
@@ -669,6 +669,30 @@ int inst_copy_from_guest(unsigned char *
return inst_len;
}
+static void hvm_send_assist_req(struct vcpu *v)
+{
+ ioreq_t *p;
+
+ p = &get_vio(v->domain, v->vcpu_id)->vp_ioreq;
+ if ( unlikely(p->state != STATE_INVALID) ) {
+ /* This indicates a bug in the device model. Crash the
+ domain. */
+ printf("Device model set bad IO state %d.\n", p->state);
+ domain_crash(v->domain);
+ return;
+ }
+ wmb();
+ p->state = STATE_IOREQ_READY;
+ notify_via_xen_event_channel(v->arch.hvm_vcpu.xen_port);
+}
+
+
+/* Wake up a vcpu whihc is waiting for interrupts to come in */
+void hvm_prod_vcpu(struct vcpu *v)
+{
+ vcpu_unblock(v);
+}
+
void send_pio_req(struct cpu_user_regs *regs, unsigned long port,
unsigned long count, int size, long value, int dir, int
pvalid)
{
@@ -682,13 +706,10 @@ void send_pio_req(struct cpu_user_regs *
domain_crash_synchronous();
}
- if (test_bit(ARCH_HVM_IO_WAIT, &v->arch.hvm_vcpu.ioflags)) {
- printf("HVM I/O has not yet completed\n");
- domain_crash_synchronous();
- }
- set_bit(ARCH_HVM_IO_WAIT, &v->arch.hvm_vcpu.ioflags);
-
p = &vio->vp_ioreq;
+ if ( p->state != STATE_INVALID )
+ printf("WARNING: send pio with something already pending (%d)?\n",
+ p->state);
p->dir = dir;
p->pdata_valid = pvalid;
@@ -714,10 +735,7 @@ void send_pio_req(struct cpu_user_regs *
return;
}
- p->state = STATE_IOREQ_READY;
-
- evtchn_send(iopacket_port(v));
- hvm_wait_io();
+ hvm_send_assist_req(v);
}
void send_mmio_req(
@@ -739,12 +757,9 @@ void send_mmio_req(
p = &vio->vp_ioreq;
- if (test_bit(ARCH_HVM_IO_WAIT, &v->arch.hvm_vcpu.ioflags)) {
- printf("HVM I/O has not yet completed\n");
- domain_crash_synchronous();
- }
-
- set_bit(ARCH_HVM_IO_WAIT, &v->arch.hvm_vcpu.ioflags);
+ if ( p->state != STATE_INVALID )
+ printf("WARNING: send mmio with something already pending (%d)?\n",
+ p->state);
p->dir = dir;
p->pdata_valid = pvalid;
@@ -764,16 +779,13 @@ void send_mmio_req(
} else
p->u.data = value;
- if (hvm_mmio_intercept(p)){
+ if ( hvm_mmio_intercept(p) || hvm_buffered_io_intercept(p) ) {
p->state = STATE_IORESP_READY;
hvm_io_assist(v);
return;
}
- p->state = STATE_IOREQ_READY;
-
- evtchn_send(iopacket_port(v));
- hvm_wait_io();
+ hvm_send_assist_req(v);
}
static void mmio_operands(int type, unsigned long gpa, struct instruction
*inst,
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/hvm/svm/svm.c
--- a/xen/arch/x86/hvm/svm/svm.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/hvm/svm/svm.c Wed Aug 09 18:04:20 2006 +0100
@@ -25,6 +25,7 @@
#include <xen/sched.h>
#include <xen/irq.h>
#include <xen/softirq.h>
+#include <xen/hypercall.h>
#include <asm/current.h>
#include <asm/io.h>
#include <asm/shadow.h>
@@ -808,6 +809,9 @@ static void svm_relinquish_guest_resourc
if ( d->arch.hvm_domain.shared_page_va )
unmap_domain_page_global(
(void *)d->arch.hvm_domain.shared_page_va);
+
+ if ( d->arch.hvm_domain.buffered_io_va )
+ unmap_domain_page_global((void *)d->arch.hvm_domain.buffered_io_va);
shadow_direct_map_clean(d);
}
@@ -2121,7 +2125,7 @@ static inline void svm_vmexit_do_hlt(str
next_wakeup = next_pit;
if ( next_wakeup != - 1 )
set_timer(¤t->arch.hvm_svm.hlt_timer, next_wakeup);
- hvm_safe_block();
+ do_sched_op_compat(SCHEDOP_block, 0);
}
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/hvm/svm/vmcb.c
--- a/xen/arch/x86/hvm/svm/vmcb.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/hvm/svm/vmcb.c Wed Aug 09 18:04:20 2006 +0100
@@ -370,18 +370,6 @@ void svm_do_launch(struct vcpu *v)
if (v->vcpu_id == 0)
hvm_setup_platform(v->domain);
- if ( evtchn_bind_vcpu(iopacket_port(v), v->vcpu_id) < 0 )
- {
- printk("HVM domain bind port %d to vcpu %d failed!\n",
- iopacket_port(v), v->vcpu_id);
- domain_crash_synchronous();
- }
-
- HVM_DBG_LOG(DBG_LEVEL_1, "eport: %x", iopacket_port(v));
-
- clear_bit(iopacket_port(v),
- &v->domain->shared_info->evtchn_mask[0]);
-
if (hvm_apic_support(v->domain))
vlapic_init(v);
init_timer(&v->arch.hvm_svm.hlt_timer,
@@ -439,10 +427,12 @@ void set_hsa_to_guest( struct arch_svm_s
/*
* Resume the guest.
*/
+/* XXX svm_do_resume and vmx_do_resume are remarkably similar; could
+ they be unified? */
void svm_do_resume(struct vcpu *v)
{
- struct domain *d = v->domain;
- struct periodic_time *pt = &d->arch.hvm_domain.pl_time.periodic_tm;
+ struct periodic_time *pt = &v->domain->arch.hvm_domain.pl_time.periodic_tm;
+ ioreq_t *p;
svm_stts(v);
@@ -455,12 +445,16 @@ void svm_do_resume(struct vcpu *v)
pickup_deactive_ticks(pt);
}
- if ( test_bit(iopacket_port(v), &d->shared_info->evtchn_pending[0]) ||
- test_bit(ARCH_HVM_IO_WAIT, &v->arch.hvm_vcpu.ioflags) )
- hvm_wait_io();
-
- /* We can't resume the guest if we're waiting on I/O */
- ASSERT(!test_bit(ARCH_HVM_IO_WAIT, &v->arch.hvm_vcpu.ioflags));
+ p = &get_vio(v->domain, v->vcpu_id)->vp_ioreq;
+ wait_on_xen_event_channel(v->arch.hvm.xen_port,
+ p->state != STATE_IOREQ_READY &&
+ p->state != STATE_IOREQ_INPROCESS);
+ if ( p->state == STATE_IORESP_READY )
+ hvm_io_assist(v);
+ if ( p->state != STATE_INVALID ) {
+ printf("Weird HVM iorequest state %d.\n", p->state);
+ domain_crash(v->domain);
+ }
}
void svm_launch_fail(unsigned long eflags)
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/hvm/svm/x86_32/exits.S
--- a/xen/arch/x86/hvm/svm/x86_32/exits.S Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/hvm/svm/x86_32/exits.S Wed Aug 09 18:04:20 2006 +0100
@@ -132,6 +132,9 @@ ENTRY(svm_asm_do_resume)
ENTRY(svm_asm_do_resume)
svm_test_all_events:
GET_CURRENT(%ebx)
+ pushl %ebx
+ call svm_do_resume
+ addl $4, %esp
/*test_all_events:*/
xorl %ecx,%ecx
notl %ecx
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/hvm/svm/x86_64/exits.S
--- a/xen/arch/x86/hvm/svm/x86_64/exits.S Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/hvm/svm/x86_64/exits.S Wed Aug 09 18:04:20 2006 +0100
@@ -147,6 +147,8 @@ ENTRY(svm_asm_do_resume)
ENTRY(svm_asm_do_resume)
svm_test_all_events:
GET_CURRENT(%rbx)
+ movq %rbx, %rdi
+ call svm_do_resume
/*test_all_events:*/
cli # tests must not race interrupts
/*test_softirqs:*/
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/hvm/vlapic.c
--- a/xen/arch/x86/hvm/vlapic.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/hvm/vlapic.c Wed Aug 09 18:04:20 2006 +0100
@@ -232,7 +232,7 @@ static int vlapic_accept_irq(struct vcpu
"level trig mode for vector %d\n", vector);
set_bit(vector, vlapic->regs + APIC_TMR);
}
- evtchn_set_pending(v, iopacket_port(v));
+ hvm_prod_vcpu(v);
result = 1;
break;
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/hvm/vmx/io.c
--- a/xen/arch/x86/hvm/vmx/io.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/hvm/vmx/io.c Wed Aug 09 18:04:20 2006 +0100
@@ -221,7 +221,7 @@ asmlinkage void vmx_intr_assist(void)
void vmx_do_resume(struct vcpu *v)
{
- struct domain *d = v->domain;
+ ioreq_t *p;
struct periodic_time *pt = &v->domain->arch.hvm_domain.pl_time.periodic_tm;
vmx_stts();
@@ -235,12 +235,16 @@ void vmx_do_resume(struct vcpu *v)
pickup_deactive_ticks(pt);
}
- if ( test_bit(iopacket_port(v), &d->shared_info->evtchn_pending[0]) ||
- test_bit(ARCH_HVM_IO_WAIT, &v->arch.hvm_vcpu.ioflags) )
- hvm_wait_io();
-
- /* We can't resume the guest if we're waiting on I/O */
- ASSERT(!test_bit(ARCH_HVM_IO_WAIT, &v->arch.hvm_vcpu.ioflags));
+ p = &get_vio(v->domain, v->vcpu_id)->vp_ioreq;
+ wait_on_xen_event_channel(v->arch.hvm.xen_port,
+ p->state != STATE_IOREQ_READY &&
+ p->state != STATE_IOREQ_INPROCESS);
+ if ( p->state == STATE_IORESP_READY )
+ hvm_io_assist(v);
+ if ( p->state != STATE_INVALID ) {
+ printf("Weird HVM iorequest state %d.\n", p->state);
+ domain_crash(v->domain);
+ }
}
/*
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/hvm/vmx/vmcs.c
--- a/xen/arch/x86/hvm/vmx/vmcs.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/hvm/vmx/vmcs.c Wed Aug 09 18:04:20 2006 +0100
@@ -245,18 +245,6 @@ static void vmx_do_launch(struct vcpu *v
if (v->vcpu_id == 0)
hvm_setup_platform(v->domain);
- if ( evtchn_bind_vcpu(iopacket_port(v), v->vcpu_id) < 0 )
- {
- printk("VMX domain bind port %d to vcpu %d failed!\n",
- iopacket_port(v), v->vcpu_id);
- domain_crash_synchronous();
- }
-
- HVM_DBG_LOG(DBG_LEVEL_1, "eport: %x", iopacket_port(v));
-
- clear_bit(iopacket_port(v),
- &v->domain->shared_info->evtchn_mask[0]);
-
__asm__ __volatile__ ("mov %%cr0,%0" : "=r" (cr0) : );
error |= __vmwrite(GUEST_CR0, cr0);
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/hvm/vmx/vmx.c
--- a/xen/arch/x86/hvm/vmx/vmx.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/hvm/vmx/vmx.c Wed Aug 09 18:04:20 2006 +0100
@@ -25,6 +25,7 @@
#include <xen/irq.h>
#include <xen/softirq.h>
#include <xen/domain_page.h>
+#include <xen/hypercall.h>
#include <asm/current.h>
#include <asm/io.h>
#include <asm/shadow.h>
@@ -48,8 +49,8 @@
#include <asm/hvm/vpic.h>
#include <asm/hvm/vlapic.h>
-static unsigned long trace_values[NR_CPUS][5];
-#define TRACE_VMEXIT(index,value) trace_values[smp_processor_id()][index]=value
+static DEFINE_PER_CPU(unsigned long, trace_values[5]);
+#define TRACE_VMEXIT(index,value) this_cpu(trace_values)[index]=value
static void vmx_ctxt_switch_from(struct vcpu *v);
static void vmx_ctxt_switch_to(struct vcpu *v);
@@ -141,6 +142,7 @@ static void vmx_relinquish_guest_resourc
free_domheap_page(VLAPIC(v)->regs_page);
xfree(VLAPIC(v));
}
+ hvm_release_assist_channel(v);
}
kill_timer(&d->arch.hvm_domain.pl_time.periodic_tm.timer);
@@ -149,12 +151,15 @@ static void vmx_relinquish_guest_resourc
unmap_domain_page_global(
(void *)d->arch.hvm_domain.shared_page_va);
+ if ( d->arch.hvm_domain.buffered_io_va )
+ unmap_domain_page_global((void *)d->arch.hvm_domain.buffered_io_va);
+
shadow_direct_map_clean(d);
}
#ifdef __x86_64__
-static struct vmx_msr_state percpu_msr[NR_CPUS];
+static DEFINE_PER_CPU(struct vmx_msr_state, percpu_msr);
static u32 msr_data_index[VMX_MSR_COUNT] =
{
@@ -175,7 +180,7 @@ static void vmx_save_segments(struct vcp
*/
static void vmx_load_msrs(void)
{
- struct vmx_msr_state *host_state = &percpu_msr[smp_processor_id()];
+ struct vmx_msr_state *host_state = &this_cpu(percpu_msr);
int i;
while ( host_state->flags )
@@ -188,7 +193,7 @@ static void vmx_load_msrs(void)
static void vmx_save_init_msrs(void)
{
- struct vmx_msr_state *host_state = &percpu_msr[smp_processor_id()];
+ struct vmx_msr_state *host_state = &this_cpu(percpu_msr);
int i;
for ( i = 0; i < VMX_MSR_COUNT; i++ )
@@ -277,7 +282,7 @@ static inline int long_mode_do_msr_write
u64 msr_content = regs->eax | ((u64)regs->edx << 32);
struct vcpu *v = current;
struct vmx_msr_state *msr = &v->arch.hvm_vmx.msr_content;
- struct vmx_msr_state *host_state = &percpu_msr[smp_processor_id()];
+ struct vmx_msr_state *host_state = &this_cpu(percpu_msr);
HVM_DBG_LOG(DBG_LEVEL_1, "msr 0x%lx msr_content 0x%"PRIx64"\n",
(unsigned long)regs->ecx, msr_content);
@@ -359,7 +364,7 @@ static void vmx_restore_msrs(struct vcpu
unsigned long guest_flags ;
guest_state = &v->arch.hvm_vmx.msr_content;;
- host_state = &percpu_msr[smp_processor_id()];
+ host_state = &this_cpu(percpu_msr);
wrmsrl(MSR_SHADOW_GS_BASE, guest_state->shadow_gs);
guest_flags = guest_state->flags;
@@ -671,28 +676,6 @@ static int check_vmx_controls(u32 ctrls,
return 1;
}
-/* Setup HVM interfaces */
-static void vmx_setup_hvm_funcs(void)
-{
- if ( hvm_enabled )
- return;
-
- hvm_funcs.disable = stop_vmx;
-
- hvm_funcs.initialize_guest_resources = vmx_initialize_guest_resources;
- hvm_funcs.relinquish_guest_resources = vmx_relinquish_guest_resources;
-
- hvm_funcs.store_cpu_guest_regs = vmx_store_cpu_guest_regs;
- hvm_funcs.load_cpu_guest_regs = vmx_load_cpu_guest_regs;
-
- hvm_funcs.realmode = vmx_realmode;
- hvm_funcs.paging_enabled = vmx_paging_enabled;
- hvm_funcs.instruction_length = vmx_instruction_length;
- hvm_funcs.get_guest_ctrl_reg = vmx_get_ctrl_reg;
-
- hvm_funcs.init_ap_context = vmx_init_ap_context;
-}
-
static void vmx_init_hypercall_page(struct domain *d, void *hypercall_page)
{
char *p;
@@ -713,6 +696,30 @@ static void vmx_init_hypercall_page(stru
/* Don't support HYPERVISOR_iret at the moment */
*(u16 *)(hypercall_page + (__HYPERVISOR_iret * 32)) = 0x0b0f; /* ud2 */
+}
+
+/* Setup HVM interfaces */
+static void vmx_setup_hvm_funcs(void)
+{
+ if ( hvm_enabled )
+ return;
+
+ hvm_funcs.disable = stop_vmx;
+
+ hvm_funcs.initialize_guest_resources = vmx_initialize_guest_resources;
+ hvm_funcs.relinquish_guest_resources = vmx_relinquish_guest_resources;
+
+ hvm_funcs.store_cpu_guest_regs = vmx_store_cpu_guest_regs;
+ hvm_funcs.load_cpu_guest_regs = vmx_load_cpu_guest_regs;
+
+ hvm_funcs.realmode = vmx_realmode;
+ hvm_funcs.paging_enabled = vmx_paging_enabled;
+ hvm_funcs.instruction_length = vmx_instruction_length;
+ hvm_funcs.get_guest_ctrl_reg = vmx_get_ctrl_reg;
+
+ hvm_funcs.init_ap_context = vmx_init_ap_context;
+
+ hvm_funcs.init_hypercall_page = vmx_init_hypercall_page;
}
int start_vmx(void)
@@ -780,8 +787,6 @@ int start_vmx(void)
vmx_save_init_msrs();
vmx_setup_hvm_funcs();
-
- hvm_funcs.init_hypercall_page = vmx_init_hypercall_page;
hvm_enabled = 1;
@@ -2014,7 +2019,7 @@ void vmx_vmexit_do_hlt(void)
next_wakeup = next_pit;
if ( next_wakeup != - 1 )
set_timer(¤t->arch.hvm_vmx.hlt_timer, next_wakeup);
- hvm_safe_block();
+ do_sched_op_compat(SCHEDOP_block, 0);
}
static inline void vmx_vmexit_do_extint(struct cpu_user_regs *regs)
@@ -2128,12 +2133,10 @@ asmlinkage void vmx_vmexit_handler(struc
asmlinkage void vmx_vmexit_handler(struct cpu_user_regs regs)
{
unsigned int exit_reason;
- unsigned long exit_qualification, eip, inst_len = 0;
+ unsigned long exit_qualification, rip, inst_len = 0;
struct vcpu *v = current;
- int error;
-
- error = __vmread(VM_EXIT_REASON, &exit_reason);
- BUG_ON(error);
+
+ __vmread(VM_EXIT_REASON, &exit_reason);
perfc_incra(vmexits, exit_reason);
@@ -2172,11 +2175,9 @@ asmlinkage void vmx_vmexit_handler(struc
domain_crash_synchronous();
}
- __vmread(GUEST_RIP, &eip);
TRACE_VMEXIT(0,exit_reason);
- switch ( exit_reason )
- {
+ switch ( exit_reason ) {
case EXIT_REASON_EXCEPTION_NMI:
{
/*
@@ -2187,15 +2188,15 @@ asmlinkage void vmx_vmexit_handler(struc
unsigned int vector;
unsigned long va;
- if (__vmread(VM_EXIT_INTR_INFO, &vector)
- || !(vector & INTR_INFO_VALID_MASK))
- __hvm_bug(®s);
+ if ( __vmread(VM_EXIT_INTR_INFO, &vector) ||
+ !(vector & INTR_INFO_VALID_MASK) )
+ domain_crash_synchronous();
vector &= INTR_INFO_VECTOR_MASK;
TRACE_VMEXIT(1,vector);
perfc_incra(cause_vector, vector);
- switch (vector) {
+ switch ( vector ) {
#ifdef XEN_DEBUGGER
case TRAP_debug:
{
@@ -2236,7 +2237,7 @@ asmlinkage void vmx_vmexit_handler(struc
{
if ( test_bit(_DOMF_debugging, &v->domain->domain_flags) )
domain_pause_for_debugger();
- else
+ else
vmx_reflect_exception(v);
break;
}
@@ -2260,7 +2261,7 @@ asmlinkage void vmx_vmexit_handler(struc
(unsigned long)regs.ecx, (unsigned long)regs.edx,
(unsigned long)regs.esi, (unsigned long)regs.edi);
- if (!vmx_do_page_fault(va, ®s)) {
+ if ( !vmx_do_page_fault(va, ®s) ) {
/*
* Inject #PG using Interruption-Information Fields
*/
@@ -2281,6 +2282,9 @@ asmlinkage void vmx_vmexit_handler(struc
}
case EXIT_REASON_EXTERNAL_INTERRUPT:
vmx_vmexit_do_extint(®s);
+ break;
+ case EXIT_REASON_TRIPLE_FAULT:
+ domain_crash_synchronous();
break;
case EXIT_REASON_PENDING_INTERRUPT:
/*
@@ -2296,7 +2300,7 @@ asmlinkage void vmx_vmexit_handler(struc
v->arch.hvm_vcpu.u.vmx.exec_control);
break;
case EXIT_REASON_TASK_SWITCH:
- __hvm_bug(®s);
+ domain_crash_synchronous();
break;
case EXIT_REASON_CPUID:
vmx_vmexit_do_cpuid(®s);
@@ -2321,7 +2325,7 @@ asmlinkage void vmx_vmexit_handler(struc
case EXIT_REASON_VMCALL:
{
__get_instruction_length(inst_len);
- __vmread(GUEST_RIP, &eip);
+ __vmread(GUEST_RIP, &rip);
__vmread(EXIT_QUALIFICATION, &exit_qualification);
hvm_do_hypercall(®s);
@@ -2330,13 +2334,13 @@ asmlinkage void vmx_vmexit_handler(struc
}
case EXIT_REASON_CR_ACCESS:
{
- __vmread(GUEST_RIP, &eip);
+ __vmread(GUEST_RIP, &rip);
__get_instruction_length(inst_len);
__vmread(EXIT_QUALIFICATION, &exit_qualification);
- HVM_DBG_LOG(DBG_LEVEL_1, "eip = %lx, inst_len =%lx, exit_qualification
= %lx",
- eip, inst_len, exit_qualification);
- if (vmx_cr_access(exit_qualification, ®s))
+ HVM_DBG_LOG(DBG_LEVEL_1, "rip = %lx, inst_len =%lx, exit_qualification
= %lx",
+ rip, inst_len, exit_qualification);
+ if ( vmx_cr_access(exit_qualification, ®s) )
__update_guest_eip(inst_len);
TRACE_VMEXIT(3,regs.error_code);
TRACE_VMEXIT(4,exit_qualification);
@@ -2360,13 +2364,14 @@ asmlinkage void vmx_vmexit_handler(struc
__update_guest_eip(inst_len);
break;
case EXIT_REASON_MSR_WRITE:
- __vmread(GUEST_RIP, &eip);
vmx_do_msr_write(®s);
__get_instruction_length(inst_len);
__update_guest_eip(inst_len);
break;
case EXIT_REASON_MWAIT_INSTRUCTION:
- __hvm_bug(®s);
+ case EXIT_REASON_MONITOR_INSTRUCTION:
+ case EXIT_REASON_PAUSE_INSTRUCTION:
+ domain_crash_synchronous();
break;
case EXIT_REASON_VMCLEAR:
case EXIT_REASON_VMLAUNCH:
@@ -2375,15 +2380,15 @@ asmlinkage void vmx_vmexit_handler(struc
case EXIT_REASON_VMREAD:
case EXIT_REASON_VMRESUME:
case EXIT_REASON_VMWRITE:
- case EXIT_REASON_VMOFF:
- case EXIT_REASON_VMON:
- /* Report invalid opcode exception when a VMX guest tries to execute
+ case EXIT_REASON_VMXOFF:
+ case EXIT_REASON_VMXON:
+ /* Report invalid opcode exception when a VMX guest tries to execute
any of the VMX instructions */
vmx_inject_hw_exception(v, TRAP_invalid_op, VMX_DELIVER_NO_ERROR_CODE);
break;
default:
- __hvm_bug(®s); /* should not happen */
+ domain_crash_synchronous(); /* should not happen */
}
}
@@ -2398,11 +2403,11 @@ asmlinkage void vmx_trace_vmentry (void)
asmlinkage void vmx_trace_vmentry (void)
{
TRACE_5D(TRC_VMX_VMENTRY,
- trace_values[smp_processor_id()][0],
- trace_values[smp_processor_id()][1],
- trace_values[smp_processor_id()][2],
- trace_values[smp_processor_id()][3],
- trace_values[smp_processor_id()][4]);
+ this_cpu(trace_values)[0],
+ this_cpu(trace_values)[1],
+ this_cpu(trace_values)[2],
+ this_cpu(trace_values)[3],
+ this_cpu(trace_values)[4]);
TRACE_VMEXIT(0,9);
TRACE_VMEXIT(1,9);
TRACE_VMEXIT(2,9);
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/hvm/vmx/x86_32/exits.S
--- a/xen/arch/x86/hvm/vmx/x86_32/exits.S Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/hvm/vmx/x86_32/exits.S Wed Aug 09 18:04:20 2006 +0100
@@ -94,6 +94,9 @@ vmx_process_softirqs:
ALIGN
ENTRY(vmx_asm_do_vmentry)
GET_CURRENT(%ebx)
+ pushl %ebx
+ call vmx_do_resume
+ addl $4, %esp
cli # tests must not race interrupts
movl VCPU_processor(%ebx),%eax
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/hvm/vmx/x86_64/exits.S
--- a/xen/arch/x86/hvm/vmx/x86_64/exits.S Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/hvm/vmx/x86_64/exits.S Wed Aug 09 18:04:20 2006 +0100
@@ -105,6 +105,8 @@ vmx_process_softirqs:
ALIGN
ENTRY(vmx_asm_do_vmentry)
GET_CURRENT(%rbx)
+ movq %rbx, %rdi
+ call vmx_do_resume
cli # tests must not race interrupts
movl VCPU_processor(%rbx),%eax
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/irq.c
--- a/xen/arch/x86/irq.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/irq.c Wed Aug 09 18:04:20 2006 +0100
@@ -160,11 +160,12 @@ typedef struct {
* Stack of interrupts awaiting EOI on each CPU. These must be popped in
* order, as only the current highest-priority pending irq can be EOIed.
*/
-static struct {
+struct pending_eoi {
u8 vector; /* Vector awaiting EOI */
u8 ready; /* Ready for EOI now? */
-} pending_eoi[NR_CPUS][NR_VECTORS] __cacheline_aligned;
-#define pending_eoi_sp(cpu) (pending_eoi[cpu][NR_VECTORS-1].vector)
+};
+static DEFINE_PER_CPU(struct pending_eoi, pending_eoi[NR_VECTORS]);
+#define pending_eoi_sp(p) ((p)[NR_VECTORS-1].vector)
static void __do_IRQ_guest(int vector)
{
@@ -172,7 +173,8 @@ static void __do_IRQ_guest(int vector)
irq_desc_t *desc = &irq_desc[vector];
irq_guest_action_t *action = (irq_guest_action_t *)desc->action;
struct domain *d;
- int i, sp, cpu = smp_processor_id();
+ int i, sp;
+ struct pending_eoi *peoi = this_cpu(pending_eoi);
if ( unlikely(action->nr_guests == 0) )
{
@@ -185,13 +187,13 @@ static void __do_IRQ_guest(int vector)
if ( action->ack_type == ACKTYPE_EOI )
{
- sp = pending_eoi_sp(cpu);
- ASSERT((sp == 0) || (pending_eoi[cpu][sp-1].vector < vector));
+ sp = pending_eoi_sp(peoi);
+ ASSERT((sp == 0) || (peoi[sp-1].vector < vector));
ASSERT(sp < (NR_VECTORS-1));
- pending_eoi[cpu][sp].vector = vector;
- pending_eoi[cpu][sp].ready = 0;
- pending_eoi_sp(cpu) = sp+1;
- cpu_set(cpu, action->cpu_eoi_map);
+ peoi[sp].vector = vector;
+ peoi[sp].ready = 0;
+ pending_eoi_sp(peoi) = sp+1;
+ cpu_set(smp_processor_id(), action->cpu_eoi_map);
}
for ( i = 0; i < action->nr_guests; i++ )
@@ -207,43 +209,45 @@ static void __do_IRQ_guest(int vector)
/* Flush all ready EOIs from the top of this CPU's pending-EOI stack. */
static void flush_ready_eoi(void *unused)
{
- irq_desc_t *desc;
- int vector, sp, cpu = smp_processor_id();
+ struct pending_eoi *peoi = this_cpu(pending_eoi);
+ irq_desc_t *desc;
+ int vector, sp;
ASSERT(!local_irq_is_enabled());
- sp = pending_eoi_sp(cpu);
-
- while ( (--sp >= 0) && pending_eoi[cpu][sp].ready )
- {
- vector = pending_eoi[cpu][sp].vector;
+ sp = pending_eoi_sp(peoi);
+
+ while ( (--sp >= 0) && peoi[sp].ready )
+ {
+ vector = peoi[sp].vector;
desc = &irq_desc[vector];
spin_lock(&desc->lock);
desc->handler->end(vector);
spin_unlock(&desc->lock);
}
- pending_eoi_sp(cpu) = sp+1;
+ pending_eoi_sp(peoi) = sp+1;
}
static void __set_eoi_ready(irq_desc_t *desc)
{
irq_guest_action_t *action = (irq_guest_action_t *)desc->action;
- int vector, sp, cpu = smp_processor_id();
+ struct pending_eoi *peoi = this_cpu(pending_eoi);
+ int vector, sp;
vector = desc - irq_desc;
if ( !(desc->status & IRQ_GUEST) ||
(action->in_flight != 0) ||
- !cpu_test_and_clear(cpu, action->cpu_eoi_map) )
+ !cpu_test_and_clear(smp_processor_id(), action->cpu_eoi_map) )
return;
- sp = pending_eoi_sp(cpu);
+ sp = pending_eoi_sp(peoi);
do {
ASSERT(sp > 0);
- } while ( pending_eoi[cpu][--sp].vector != vector );
- ASSERT(!pending_eoi[cpu][sp].ready);
- pending_eoi[cpu][sp].ready = 1;
+ } while ( peoi[--sp].vector != vector );
+ ASSERT(!peoi[sp].ready);
+ peoi[sp].ready = 1;
}
/* Mark specified IRQ as ready-for-EOI (if it really is) and attempt to EOI. */
@@ -269,16 +273,17 @@ static void flush_all_pending_eoi(void *
{
irq_desc_t *desc;
irq_guest_action_t *action;
- int i, vector, sp, cpu = smp_processor_id();
+ struct pending_eoi *peoi = this_cpu(pending_eoi);
+ int i, vector, sp;
ASSERT(!local_irq_is_enabled());
- sp = pending_eoi_sp(cpu);
+ sp = pending_eoi_sp(peoi);
while ( --sp >= 0 )
{
- if ( pending_eoi[cpu][sp].ready )
+ if ( peoi[sp].ready )
continue;
- vector = pending_eoi[cpu][sp].vector;
+ vector = peoi[sp].vector;
desc = &irq_desc[vector];
spin_lock(&desc->lock);
action = (irq_guest_action_t *)desc->action;
@@ -668,7 +673,7 @@ static int __init setup_dump_irqs(void)
}
__initcall(setup_dump_irqs);
-static struct timer end_irq_timer[NR_CPUS];
+static DEFINE_PER_CPU(struct timer, end_irq_timer);
/*
* force_intack: Forcibly emit all pending EOIs on each CPU every second.
@@ -677,22 +682,13 @@ static struct timer end_irq_timer[NR_CPU
static void end_irq_timeout(void *unused)
{
- int cpu = smp_processor_id();
-
local_irq_disable();
flush_all_pending_eoi(NULL);
local_irq_enable();
on_selected_cpus(cpu_online_map, flush_ready_eoi, NULL, 1, 0);
- set_timer(&end_irq_timer[cpu], NOW() + MILLISECS(1000));
-}
-
-static void __init __setup_irq_timeout(void *unused)
-{
- int cpu = smp_processor_id();
- init_timer(&end_irq_timer[cpu], end_irq_timeout, NULL, cpu);
- set_timer(&end_irq_timer[cpu], NOW() + MILLISECS(1000));
+ set_timer(&this_cpu(end_irq_timer), NOW() + MILLISECS(1000));
}
static int force_intack;
@@ -700,8 +696,17 @@ boolean_param("force_intack", force_inta
static int __init setup_irq_timeout(void)
{
- if ( force_intack )
- on_each_cpu(__setup_irq_timeout, NULL, 1, 1);
+ unsigned int cpu;
+
+ if ( !force_intack )
+ return 0;
+
+ for_each_online_cpu ( cpu )
+ {
+ init_timer(&per_cpu(end_irq_timer, cpu), end_irq_timeout, NULL, cpu);
+ set_timer(&per_cpu(end_irq_timer, cpu), NOW() + MILLISECS(1000));
+ }
+
return 0;
}
__initcall(setup_irq_timeout);
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/mm.c
--- a/xen/arch/x86/mm.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/mm.c Wed Aug 09 18:04:20 2006 +0100
@@ -139,20 +139,21 @@ static int mod_l1_entry(l1_pgentry_t *,
static int mod_l1_entry(l1_pgentry_t *, l1_pgentry_t);
/* Used to defer flushing of memory structures. */
-static struct {
+struct percpu_mm_info {
#define DOP_FLUSH_TLB (1<<0) /* Flush the local TLB. */
#define DOP_FLUSH_ALL_TLBS (1<<1) /* Flush TLBs of all VCPUs of current dom. */
#define DOP_RELOAD_LDT (1<<2) /* Reload the LDT shadow mapping. */
unsigned int deferred_ops;
/* If non-NULL, specifies a foreign subject domain for some operations. */
struct domain *foreign;
-} __cacheline_aligned percpu_info[NR_CPUS];
+};
+static DEFINE_PER_CPU(struct percpu_mm_info, percpu_mm_info);
/*
* Returns the current foreign domain; defaults to the currently-executing
* domain if a foreign override hasn't been specified.
*/
-#define FOREIGNDOM (percpu_info[smp_processor_id()].foreign ?: current->domain)
+#define FOREIGNDOM (this_cpu(percpu_mm_info).foreign ?: current->domain)
/* Private domain structs for DOMID_XEN and DOMID_IO. */
static struct domain *dom_xen, *dom_io;
@@ -189,8 +190,6 @@ void arch_init_memory(void)
extern void subarch_init_memory(void);
unsigned long i, pfn, rstart_pfn, rend_pfn;
-
- memset(percpu_info, 0, sizeof(percpu_info));
/*
* Initialise our DOMID_XEN domain.
@@ -378,7 +377,8 @@ void invalidate_shadow_ldt(struct vcpu *
}
/* Dispose of the (now possibly invalid) mappings from the TLB. */
- percpu_info[v->processor].deferred_ops |= DOP_FLUSH_TLB | DOP_RELOAD_LDT;
+ ASSERT(v->processor == smp_processor_id());
+ this_cpu(percpu_mm_info).deferred_ops |= DOP_FLUSH_TLB | DOP_RELOAD_LDT;
}
@@ -1503,7 +1503,7 @@ void free_page_type(struct page_info *pa
* (e.g., update_va_mapping()) or we could end up modifying a page
* that is no longer a page table (and hence screw up ref counts).
*/
- percpu_info[smp_processor_id()].deferred_ops |= DOP_FLUSH_ALL_TLBS;
+ this_cpu(percpu_mm_info).deferred_ops |= DOP_FLUSH_ALL_TLBS;
if ( unlikely(shadow_mode_enabled(owner)) )
{
@@ -1781,7 +1781,8 @@ int new_guest_cr3(unsigned long mfn)
/* Failure here is unrecoverable: the VCPU has no pagetable! */
MEM_LOG("Fatal error while installing new baseptr %lx", mfn);
domain_crash(d);
- percpu_info[v->processor].deferred_ops = 0;
+ ASSERT(v->processor == smp_processor_id());
+ this_cpu(percpu_mm_info).deferred_ops = 0;
return 0;
}
}
@@ -1817,13 +1818,14 @@ int new_guest_cr3(unsigned long mfn)
return 1;
}
-static void process_deferred_ops(unsigned int cpu)
+static void process_deferred_ops(void)
{
unsigned int deferred_ops;
struct domain *d = current->domain;
-
- deferred_ops = percpu_info[cpu].deferred_ops;
- percpu_info[cpu].deferred_ops = 0;
+ struct percpu_mm_info *info = &this_cpu(percpu_mm_info);
+
+ deferred_ops = info->deferred_ops;
+ info->deferred_ops = 0;
if ( deferred_ops & (DOP_FLUSH_ALL_TLBS|DOP_FLUSH_TLB) )
{
@@ -1838,19 +1840,20 @@ static void process_deferred_ops(unsigne
if ( deferred_ops & DOP_RELOAD_LDT )
(void)map_ldt_shadow_page(0);
- if ( unlikely(percpu_info[cpu].foreign != NULL) )
- {
- put_domain(percpu_info[cpu].foreign);
- percpu_info[cpu].foreign = NULL;
- }
-}
-
-static int set_foreigndom(unsigned int cpu, domid_t domid)
+ if ( unlikely(info->foreign != NULL) )
+ {
+ put_domain(info->foreign);
+ info->foreign = NULL;
+ }
+}
+
+static int set_foreigndom(domid_t domid)
{
struct domain *e, *d = current->domain;
+ struct percpu_mm_info *info = &this_cpu(percpu_mm_info);
int okay = 1;
- ASSERT(percpu_info[cpu].foreign == NULL);
+ ASSERT(info->foreign == NULL);
if ( likely(domid == DOMID_SELF) )
goto out;
@@ -1867,7 +1870,7 @@ static int set_foreigndom(unsigned int c
{
case DOMID_IO:
get_knownalive_domain(dom_io);
- percpu_info[cpu].foreign = dom_io;
+ info->foreign = dom_io;
break;
default:
MEM_LOG("Dom %u cannot set foreign dom", d->domain_id);
@@ -1877,18 +1880,18 @@ static int set_foreigndom(unsigned int c
}
else
{
- percpu_info[cpu].foreign = e = find_domain_by_id(domid);
+ info->foreign = e = find_domain_by_id(domid);
if ( e == NULL )
{
switch ( domid )
{
case DOMID_XEN:
get_knownalive_domain(dom_xen);
- percpu_info[cpu].foreign = dom_xen;
+ info->foreign = dom_xen;
break;
case DOMID_IO:
get_knownalive_domain(dom_io);
- percpu_info[cpu].foreign = dom_io;
+ info->foreign = dom_io;
break;
default:
MEM_LOG("Unknown domain '%u'", domid);
@@ -1928,7 +1931,7 @@ int do_mmuext_op(
unsigned int foreigndom)
{
struct mmuext_op op;
- int rc = 0, i = 0, okay, cpu = smp_processor_id();
+ int rc = 0, i = 0, okay;
unsigned long mfn, type;
unsigned int done = 0;
struct page_info *page;
@@ -1946,7 +1949,7 @@ int do_mmuext_op(
(void)copy_from_guest(&done, pdone, 1);
}
- if ( !set_foreigndom(cpu, foreigndom) )
+ if ( !set_foreigndom(foreigndom) )
{
rc = -ESRCH;
goto out;
@@ -2042,7 +2045,7 @@ int do_mmuext_op(
case MMUEXT_NEW_BASEPTR:
mfn = gmfn_to_mfn(current->domain, mfn);
okay = new_guest_cr3(mfn);
- percpu_info[cpu].deferred_ops &= ~DOP_FLUSH_TLB;
+ this_cpu(percpu_mm_info).deferred_ops &= ~DOP_FLUSH_TLB;
break;
#ifdef __x86_64__
@@ -2065,7 +2068,7 @@ int do_mmuext_op(
#endif
case MMUEXT_TLB_FLUSH_LOCAL:
- percpu_info[cpu].deferred_ops |= DOP_FLUSH_TLB;
+ this_cpu(percpu_mm_info).deferred_ops |= DOP_FLUSH_TLB;
break;
case MMUEXT_INVLPG_LOCAL:
@@ -2137,9 +2140,9 @@ int do_mmuext_op(
v->arch.guest_context.ldt_base = ptr;
v->arch.guest_context.ldt_ents = ents;
load_LDT(v);
- percpu_info[cpu].deferred_ops &= ~DOP_RELOAD_LDT;
+ this_cpu(percpu_mm_info).deferred_ops &= ~DOP_RELOAD_LDT;
if ( ents != 0 )
- percpu_info[cpu].deferred_ops |= DOP_RELOAD_LDT;
+ this_cpu(percpu_mm_info).deferred_ops |= DOP_RELOAD_LDT;
}
break;
}
@@ -2160,7 +2163,7 @@ int do_mmuext_op(
}
out:
- process_deferred_ops(cpu);
+ process_deferred_ops();
/* Add incremental work we have done to the @done output parameter. */
done += i;
@@ -2181,7 +2184,7 @@ int do_mmu_update(
void *va;
unsigned long gpfn, gmfn, mfn;
struct page_info *page;
- int rc = 0, okay = 1, i = 0, cpu = smp_processor_id();
+ int rc = 0, okay = 1, i = 0;
unsigned int cmd, done = 0;
struct vcpu *v = current;
struct domain *d = v->domain;
@@ -2205,7 +2208,7 @@ int do_mmu_update(
domain_mmap_cache_init(&mapcache);
domain_mmap_cache_init(&sh_mapcache);
- if ( !set_foreigndom(cpu, foreigndom) )
+ if ( !set_foreigndom(foreigndom) )
{
rc = -ESRCH;
goto out;
@@ -2396,7 +2399,7 @@ int do_mmu_update(
domain_mmap_cache_destroy(&mapcache);
domain_mmap_cache_destroy(&sh_mapcache);
- process_deferred_ops(cpu);
+ process_deferred_ops();
/* Add incremental work we have done to the @done output parameter. */
done += i;
@@ -2690,7 +2693,6 @@ int do_update_va_mapping(unsigned long v
l1_pgentry_t val = l1e_from_intpte(val64);
struct vcpu *v = current;
struct domain *d = v->domain;
- unsigned int cpu = smp_processor_id();
unsigned long vmask, bmap_ptr;
cpumask_t pmask;
int rc = 0;
@@ -2713,9 +2715,10 @@ int do_update_va_mapping(unsigned long v
if ( likely(rc == 0) && unlikely(shadow_mode_enabled(d)) )
{
- if ( unlikely(percpu_info[cpu].foreign &&
+ if ( unlikely(this_cpu(percpu_mm_info).foreign &&
(shadow_mode_translate(d) ||
- shadow_mode_translate(percpu_info[cpu].foreign))) )
+ shadow_mode_translate(
+ this_cpu(percpu_mm_info).foreign))) )
{
/*
* The foreign domain's pfn's are in a different namespace. There's
@@ -2773,7 +2776,7 @@ int do_update_va_mapping(unsigned long v
break;
}
- process_deferred_ops(cpu);
+ process_deferred_ops();
UNLOCK_BIGLOCK(d);
@@ -2784,13 +2787,12 @@ int do_update_va_mapping_otherdomain(uns
unsigned long flags,
domid_t domid)
{
- unsigned int cpu = smp_processor_id();
int rc;
if ( unlikely(!IS_PRIV(current->domain)) )
return -EPERM;
- if ( !set_foreigndom(cpu, domid) )
+ if ( !set_foreigndom(domid) )
return -ESRCH;
rc = do_update_va_mapping(va, val64, flags);
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/nmi.c
--- a/xen/arch/x86/nmi.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/nmi.c Wed Aug 09 18:04:20 2006 +0100
@@ -36,8 +36,8 @@ static unsigned int nmi_hz = HZ;
static unsigned int nmi_hz = HZ;
static unsigned int nmi_perfctr_msr; /* the MSR to reset in NMI handler */
static unsigned int nmi_p4_cccr_val;
-static struct timer nmi_timer[NR_CPUS];
-static unsigned int nmi_timer_ticks[NR_CPUS];
+static DEFINE_PER_CPU(struct timer, nmi_timer);
+static DEFINE_PER_CPU(unsigned int, nmi_timer_ticks);
/*
* lapic_nmi_owner tracks the ownership of the lapic NMI hardware:
@@ -132,9 +132,8 @@ int __init check_nmi_watchdog (void)
static void nmi_timer_fn(void *unused)
{
- int cpu = smp_processor_id();
- nmi_timer_ticks[cpu]++;
- set_timer(&nmi_timer[cpu], NOW() + MILLISECS(1000));
+ this_cpu(nmi_timer_ticks)++;
+ set_timer(&this_cpu(nmi_timer), NOW() + MILLISECS(1000));
}
static void disable_lapic_nmi_watchdog(void)
@@ -340,9 +339,8 @@ void __pminit setup_apic_nmi_watchdog(vo
nmi_active = 1;
}
-static unsigned int
-last_irq_sums [NR_CPUS],
- alert_counter [NR_CPUS];
+static DEFINE_PER_CPU(unsigned int, last_irq_sums);
+static DEFINE_PER_CPU(unsigned int, alert_counter);
static atomic_t watchdog_disable_count = ATOMIC_INIT(1);
@@ -366,35 +364,35 @@ void watchdog_enable(void)
*/
for_each_online_cpu ( cpu )
{
- init_timer(&nmi_timer[cpu], nmi_timer_fn, NULL, cpu);
- set_timer(&nmi_timer[cpu], NOW());
+ init_timer(&per_cpu(nmi_timer, cpu), nmi_timer_fn, NULL, cpu);
+ set_timer(&per_cpu(nmi_timer, cpu), NOW());
}
}
void nmi_watchdog_tick(struct cpu_user_regs * regs)
{
- int sum, cpu = smp_processor_id();
-
- sum = nmi_timer_ticks[cpu];
-
- if ( (last_irq_sums[cpu] == sum) && !atomic_read(&watchdog_disable_count) )
+ unsigned int sum = this_cpu(nmi_timer_ticks);
+
+ if ( (this_cpu(last_irq_sums) == sum) &&
+ !atomic_read(&watchdog_disable_count) )
{
/*
* Ayiee, looks like this CPU is stuck ... wait a few IRQs (5 seconds)
* before doing the oops ...
*/
- alert_counter[cpu]++;
- if ( alert_counter[cpu] == 5*nmi_hz )
+ this_cpu(alert_counter)++;
+ if ( this_cpu(alert_counter) == 5*nmi_hz )
{
console_force_unlock();
- printk("Watchdog timer detects that CPU%d is stuck!\n", cpu);
+ printk("Watchdog timer detects that CPU%d is stuck!\n",
+ smp_processor_id());
fatal_trap(TRAP_nmi, regs);
}
}
else
{
- last_irq_sums[cpu] = sum;
- alert_counter[cpu] = 0;
+ this_cpu(last_irq_sums) = sum;
+ this_cpu(alert_counter) = 0;
}
if ( nmi_perfctr_msr )
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/time.c
--- a/xen/arch/x86/time.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/time.c Wed Aug 09 18:04:20 2006 +0100
@@ -56,9 +56,9 @@ struct cpu_time {
s_time_t stime_master_stamp;
struct time_scale tsc_scale;
struct timer calibration_timer;
-} __cacheline_aligned;
-
-static struct cpu_time cpu_time[NR_CPUS];
+};
+
+static DEFINE_PER_CPU(struct cpu_time, cpu_time);
/*
* Protected by platform_timer_lock, which must be acquired with interrupts
@@ -263,7 +263,7 @@ void calibrate_tsc_ap(void)
rdtscll(t2);
ticks_per_sec = (t2 - t1) * (u64)CALIBRATE_FRAC;
- set_time_scale(&cpu_time[smp_processor_id()].tsc_scale, ticks_per_sec);
+ set_time_scale(&this_cpu(cpu_time).tsc_scale, ticks_per_sec);
atomic_dec(&tsc_calibrate_gang);
}
@@ -646,7 +646,7 @@ static unsigned long get_cmos_time(void)
s_time_t get_s_time(void)
{
- struct cpu_time *t = &cpu_time[smp_processor_id()];
+ struct cpu_time *t = &this_cpu(cpu_time);
u64 tsc, delta;
s_time_t now;
@@ -675,7 +675,7 @@ static inline void __update_vcpu_system_
struct cpu_time *t;
struct vcpu_time_info *u;
- t = &cpu_time[smp_processor_id()];
+ t = &this_cpu(cpu_time);
u = &v->domain->shared_info->vcpu_info[v->vcpu_id].time;
version_update_begin(&u->version);
@@ -691,7 +691,7 @@ void update_vcpu_system_time(struct vcpu
void update_vcpu_system_time(struct vcpu *v)
{
if ( v->domain->shared_info->vcpu_info[v->vcpu_id].time.tsc_timestamp !=
- cpu_time[smp_processor_id()].local_tsc_stamp )
+ this_cpu(cpu_time).local_tsc_stamp )
__update_vcpu_system_time(v);
}
@@ -728,7 +728,7 @@ void do_settime(unsigned long secs, unsi
static void local_time_calibration(void *unused)
{
- unsigned int cpu = smp_processor_id();
+ struct cpu_time *t = &this_cpu(cpu_time);
/*
* System timestamps, extrapolated from local and master oscillators,
@@ -759,9 +759,9 @@ static void local_time_calibration(void
/* The overall calibration scale multiplier. */
u32 calibration_mul_frac;
- prev_tsc = cpu_time[cpu].local_tsc_stamp;
- prev_local_stime = cpu_time[cpu].stime_local_stamp;
- prev_master_stime = cpu_time[cpu].stime_master_stamp;
+ prev_tsc = t->local_tsc_stamp;
+ prev_local_stime = t->stime_local_stamp;
+ prev_master_stime = t->stime_master_stamp;
/* Disable IRQs to get 'instantaneous' current timestamps. */
local_irq_disable();
@@ -772,9 +772,9 @@ static void local_time_calibration(void
#if 0
printk("PRE%d: tsc=%lld stime=%lld master=%lld\n",
- cpu, prev_tsc, prev_local_stime, prev_master_stime);
+ smp_processor_id(), prev_tsc, prev_local_stime, prev_master_stime);
printk("CUR%d: tsc=%lld stime=%lld master=%lld -> %lld\n",
- cpu, curr_tsc, curr_local_stime, curr_master_stime,
+ smp_processor_id(), curr_tsc, curr_local_stime, curr_master_stime,
curr_master_stime - curr_local_stime);
#endif
@@ -844,41 +844,41 @@ static void local_time_calibration(void
calibration_mul_frac = mul_frac(calibration_mul_frac, error_factor);
#if 0
- printk("---%d: %08x %08x %d\n", cpu,
+ printk("---%d: %08x %08x %d\n", smp_processor_id(),
error_factor, calibration_mul_frac, tsc_shift);
#endif
/* Record new timestamp information. */
- cpu_time[cpu].tsc_scale.mul_frac = calibration_mul_frac;
- cpu_time[cpu].tsc_scale.shift = tsc_shift;
- cpu_time[cpu].local_tsc_stamp = curr_tsc;
- cpu_time[cpu].stime_local_stamp = curr_local_stime;
- cpu_time[cpu].stime_master_stamp = curr_master_stime;
+ t->tsc_scale.mul_frac = calibration_mul_frac;
+ t->tsc_scale.shift = tsc_shift;
+ t->local_tsc_stamp = curr_tsc;
+ t->stime_local_stamp = curr_local_stime;
+ t->stime_master_stamp = curr_master_stime;
out:
- set_timer(&cpu_time[cpu].calibration_timer, NOW() + EPOCH);
-
- if ( cpu == 0 )
+ set_timer(&t->calibration_timer, NOW() + EPOCH);
+
+ if ( smp_processor_id() == 0 )
platform_time_calibration();
}
void init_percpu_time(void)
{
- unsigned int cpu = smp_processor_id();
+ struct cpu_time *t = &this_cpu(cpu_time);
unsigned long flags;
s_time_t now;
local_irq_save(flags);
- rdtscll(cpu_time[cpu].local_tsc_stamp);
- now = (cpu == 0) ? 0 : read_platform_stime();
+ rdtscll(t->local_tsc_stamp);
+ now = (smp_processor_id() == 0) ? 0 : read_platform_stime();
local_irq_restore(flags);
- cpu_time[cpu].stime_master_stamp = now;
- cpu_time[cpu].stime_local_stamp = now;
-
- init_timer(&cpu_time[cpu].calibration_timer,
- local_time_calibration, NULL, cpu);
- set_timer(&cpu_time[cpu].calibration_timer, NOW() + EPOCH);
+ t->stime_master_stamp = now;
+ t->stime_local_stamp = now;
+
+ init_timer(&t->calibration_timer, local_time_calibration,
+ NULL, smp_processor_id());
+ set_timer(&t->calibration_timer, NOW() + EPOCH);
}
/* Late init function (after all CPUs are booted). */
@@ -904,7 +904,7 @@ void __init early_time_init(void)
{
u64 tmp = calibrate_boot_tsc();
- set_time_scale(&cpu_time[0].tsc_scale, tmp);
+ set_time_scale(&per_cpu(cpu_time, 0).tsc_scale, tmp);
do_div(tmp, 1000);
cpu_khz = (unsigned long)tmp;
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/x86_32/domain_page.c
--- a/xen/arch/x86/x86_32/domain_page.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/x86_32/domain_page.c Wed Aug 09 18:04:20 2006 +0100
@@ -73,8 +73,7 @@ void *map_domain_page(unsigned long pfn)
if ( unlikely(cache->epoch != cache->shadow_epoch[vcpu]) )
{
cache->shadow_epoch[vcpu] = cache->epoch;
- if ( NEED_FLUSH(tlbflush_time[smp_processor_id()],
- cache->tlbflush_timestamp) )
+ if ( NEED_FLUSH(this_cpu(tlbflush_time), cache->tlbflush_timestamp) )
{
perfc_incrc(domain_page_tlb_flush);
local_flush_tlb();
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/x86_32/traps.c
--- a/xen/arch/x86/x86_32/traps.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/x86_32/traps.c Wed Aug 09 18:04:20 2006 +0100
@@ -19,7 +19,7 @@
#include <public/callback.h>
/* All CPUs have their own IDT to allow int80 direct trap. */
-idt_entry_t *idt_tables[NR_CPUS] = { 0 };
+idt_entry_t *idt_tables[NR_CPUS] __read_mostly;
void show_registers(struct cpu_user_regs *regs)
{
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/x86_32/xen.lds.S
--- a/xen/arch/x86/x86_32/xen.lds.S Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/x86_32/xen.lds.S Wed Aug 09 18:04:20 2006 +0100
@@ -46,6 +46,9 @@ SECTIONS
CONSTRUCTORS
} :text
+ . = ALIGN(128);
+ .data.read_mostly : { *(.data.read_mostly) } :text
+
. = ALIGN(4096); /* Init code and data */
__init_begin = .;
.text.init : { *(.text.init) } :text
diff -r e4f1519b473f -r b60ea69932b1 xen/arch/x86/x86_64/xen.lds.S
--- a/xen/arch/x86/x86_64/xen.lds.S Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/arch/x86/x86_64/xen.lds.S Wed Aug 09 18:04:20 2006 +0100
@@ -44,6 +44,9 @@ SECTIONS
CONSTRUCTORS
} :text
+ . = ALIGN(128);
+ .data.read_mostly : { *(.data.read_mostly) } :text
+
. = ALIGN(4096); /* Init code and data */
__init_begin = .;
.text.init : { *(.text.init) } :text
diff -r e4f1519b473f -r b60ea69932b1 xen/common/domain.c
--- a/xen/common/domain.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/common/domain.c Wed Aug 09 18:04:20 2006 +0100
@@ -21,6 +21,7 @@
#include <xen/hypercall.h>
#include <xen/delay.h>
#include <xen/shutdown.h>
+#include <xen/percpu.h>
#include <asm/debugger.h>
#include <public/dom0_ops.h>
#include <public/sched.h>
@@ -33,7 +34,7 @@ struct domain *domain_list;
struct domain *dom0;
-struct vcpu *idle_vcpu[NR_CPUS];
+struct vcpu *idle_vcpu[NR_CPUS] __read_mostly;
struct domain *alloc_domain(domid_t domid)
{
@@ -245,15 +246,15 @@ void __domain_crash_synchronous(void)
}
-static struct domain *domain_shuttingdown[NR_CPUS];
+static DEFINE_PER_CPU(struct domain *, domain_shuttingdown);
static void domain_shutdown_finalise(void)
{
struct domain *d;
struct vcpu *v;
- d = domain_shuttingdown[smp_processor_id()];
- domain_shuttingdown[smp_processor_id()] = NULL;
+ d = this_cpu(domain_shuttingdown);
+ this_cpu(domain_shuttingdown) = NULL;
BUG_ON(d == NULL);
BUG_ON(d == current->domain);
@@ -302,7 +303,7 @@ void domain_shutdown(struct domain *d, u
vcpu_sleep_nosync(v);
get_knownalive_domain(d);
- domain_shuttingdown[smp_processor_id()] = d;
+ this_cpu(domain_shuttingdown) = d;
raise_softirq(DOMAIN_SHUTDOWN_FINALISE_SOFTIRQ);
}
diff -r e4f1519b473f -r b60ea69932b1 xen/common/multicall.c
--- a/xen/common/multicall.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/common/multicall.c Wed Aug 09 18:04:20 2006 +0100
@@ -14,13 +14,13 @@
#include <asm/current.h>
#include <asm/hardirq.h>
-struct mc_state mc_state[NR_CPUS];
+DEFINE_PER_CPU(struct mc_state, mc_state);
long
do_multicall(
XEN_GUEST_HANDLE(multicall_entry_t) call_list, unsigned int nr_calls)
{
- struct mc_state *mcs = &mc_state[smp_processor_id()];
+ struct mc_state *mcs = &this_cpu(mc_state);
unsigned int i;
if ( unlikely(__test_and_set_bit(_MCSF_in_multicall, &mcs->flags)) )
diff -r e4f1519b473f -r b60ea69932b1 xen/common/sched_bvt.c
--- a/xen/common/sched_bvt.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/common/sched_bvt.c Wed Aug 09 18:04:20 2006 +0100
@@ -60,7 +60,8 @@ struct bvt_cpu_info
#define BVT_INFO(p) ((struct bvt_dom_info *)(p)->sched_priv)
#define EBVT_INFO(p) ((struct bvt_vcpu_info *)(p)->sched_priv)
-#define CPU_INFO(cpu) ((struct bvt_cpu_info *)(schedule_data[cpu]).sched_priv)
+#define CPU_INFO(cpu) \
+ ((struct bvt_cpu_info *)(per_cpu(schedule_data, cpu).sched_priv))
#define RUNLIST(p) ((struct list_head *)&(EBVT_INFO(p)->run_list))
#define RUNQUEUE(cpu) ((struct list_head *)&(CPU_INFO(cpu)->runqueue))
#define CPU_SVT(cpu) (CPU_INFO(cpu)->svt)
@@ -203,7 +204,8 @@ static int bvt_init_vcpu(struct vcpu *v)
/* Allocate per-CPU context if this is the first domain to be added. */
if ( CPU_INFO(v->processor) == NULL )
{
- schedule_data[v->processor].sched_priv = xmalloc(struct bvt_cpu_info);
+ per_cpu(schedule_data, v->processor).sched_priv =
+ xmalloc(struct bvt_cpu_info);
BUG_ON(CPU_INFO(v->processor) == NULL);
INIT_LIST_HEAD(RUNQUEUE(v->processor));
CPU_SVT(v->processor) = 0;
@@ -251,7 +253,7 @@ static void bvt_wake(struct vcpu *v)
/* Deal with warping here. */
einf->evt = calc_evt(v, einf->avt);
- curr = schedule_data[cpu].curr;
+ curr = per_cpu(schedule_data, cpu).curr;
curr_evt = calc_evt(curr, calc_avt(curr, now));
/* Calculate the time the current domain would run assuming
the second smallest evt is of the newly woken domain */
@@ -261,14 +263,14 @@ static void bvt_wake(struct vcpu *v)
if ( is_idle_vcpu(curr) || (einf->evt <= curr_evt) )
cpu_raise_softirq(cpu, SCHEDULE_SOFTIRQ);
- else if ( schedule_data[cpu].s_timer.expires > r_time )
- set_timer(&schedule_data[cpu].s_timer, r_time);
+ else if ( per_cpu(schedule_data, cpu).s_timer.expires > r_time )
+ set_timer(&per_cpu(schedule_data, cpu).s_timer, r_time);
}
static void bvt_sleep(struct vcpu *v)
{
- if ( schedule_data[v->processor].curr == v )
+ if ( per_cpu(schedule_data, v->processor).curr == v )
cpu_raise_softirq(v->processor, SCHEDULE_SOFTIRQ);
else if ( __task_on_runqueue(v) )
__del_from_runqueue(v);
@@ -418,7 +420,7 @@ static struct task_slice bvt_do_schedule
* *and* the task the second lowest evt.
* this code is O(n) but we expect n to be small.
*/
- next_einf = EBVT_INFO(schedule_data[cpu].idle);
+ next_einf = EBVT_INFO(per_cpu(schedule_data, cpu).idle);
next_prime_einf = NULL;
next_evt = ~0U;
diff -r e4f1519b473f -r b60ea69932b1 xen/common/sched_credit.c
--- a/xen/common/sched_credit.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/common/sched_credit.c Wed Aug 09 18:04:20 2006 +0100
@@ -55,7 +55,8 @@
/*
* Useful macros
*/
-#define CSCHED_PCPU(_c) ((struct csched_pcpu
*)schedule_data[_c].sched_priv)
+#define CSCHED_PCPU(_c) \
+ ((struct csched_pcpu *)per_cpu(schedule_data, _c).sched_priv)
#define CSCHED_VCPU(_vcpu) ((struct csched_vcpu *) (_vcpu)->sched_priv)
#define CSCHED_DOM(_dom) ((struct csched_dom *) (_dom)->sched_priv)
#define RUNQ(_cpu) (&(CSCHED_PCPU(_cpu)->runq))
@@ -253,7 +254,8 @@ static inline void
static inline void
__runq_tickle(unsigned int cpu, struct csched_vcpu *new)
{
- struct csched_vcpu * const cur = CSCHED_VCPU(schedule_data[cpu].curr);
+ struct csched_vcpu * const cur =
+ CSCHED_VCPU(per_cpu(schedule_data, cpu).curr);
cpumask_t mask;
ASSERT(cur);
@@ -318,10 +320,10 @@ csched_pcpu_init(int cpu)
INIT_LIST_HEAD(&spc->runq);
spc->runq_sort_last = csched_priv.runq_sort;
- schedule_data[cpu].sched_priv = spc;
+ per_cpu(schedule_data, cpu).sched_priv = spc;
/* Start off idling... */
- BUG_ON( !is_idle_vcpu(schedule_data[cpu].curr) );
+ BUG_ON( !is_idle_vcpu(per_cpu(schedule_data, cpu).curr) );
cpu_set(cpu, csched_priv.idlers);
spin_unlock_irqrestore(&csched_priv.lock, flags);
@@ -533,7 +535,7 @@ csched_vcpu_sleep(struct vcpu *vc)
BUG_ON( is_idle_vcpu(vc) );
- if ( schedule_data[vc->processor].curr == vc )
+ if ( per_cpu(schedule_data, vc->processor).curr == vc )
cpu_raise_softirq(vc->processor, SCHEDULE_SOFTIRQ);
else if ( __vcpu_on_runq(svc) )
__runq_remove(svc);
@@ -547,7 +549,7 @@ csched_vcpu_wake(struct vcpu *vc)
BUG_ON( is_idle_vcpu(vc) );
- if ( unlikely(schedule_data[cpu].curr == vc) )
+ if ( unlikely(per_cpu(schedule_data, cpu).curr == vc) )
{
CSCHED_STAT_CRANK(vcpu_wake_running);
return;
@@ -599,7 +601,8 @@ csched_vcpu_set_affinity(struct vcpu *vc
vc->processor = first_cpu(vc->cpu_affinity);
- spin_unlock_irqrestore(&schedule_data[lcpu].schedule_lock, flags);
+ spin_unlock_irqrestore(&per_cpu(schedule_data, lcpu).schedule_lock,
+ flags);
}
vcpu_unpause(vc);
@@ -685,7 +688,7 @@ csched_runq_sort(unsigned int cpu)
spc->runq_sort_last = sort_epoch;
- spin_lock_irqsave(&schedule_data[cpu].schedule_lock, flags);
+ spin_lock_irqsave(&per_cpu(schedule_data, cpu).schedule_lock, flags);
runq = &spc->runq;
elem = runq->next;
@@ -710,7 +713,7 @@ csched_runq_sort(unsigned int cpu)
elem = next;
}
- spin_unlock_irqrestore(&schedule_data[cpu].schedule_lock, flags);
+ spin_unlock_irqrestore(&per_cpu(schedule_data, cpu).schedule_lock, flags);
}
static void
@@ -900,7 +903,7 @@ csched_tick(unsigned int cpu)
* we could distribute or at the very least cycle the duty.
*/
if ( (csched_priv.master == cpu) &&
- (schedule_data[cpu].tick % CSCHED_ACCT_NTICKS) == 0 )
+ (per_cpu(schedule_data, cpu).tick % CSCHED_ACCT_NTICKS) == 0 )
{
csched_acct();
}
@@ -984,7 +987,7 @@ csched_load_balance(int cpu, struct csch
* cause a deadlock if the peer CPU is also load balancing and trying
* to lock this CPU.
*/
- if ( spin_trylock(&schedule_data[peer_cpu].schedule_lock) )
+ if ( spin_trylock(&per_cpu(schedule_data, peer_cpu).schedule_lock) )
{
spc = CSCHED_PCPU(peer_cpu);
@@ -998,7 +1001,7 @@ csched_load_balance(int cpu, struct csch
speer = csched_runq_steal(spc, cpu, snext->pri);
}
- spin_unlock(&schedule_data[peer_cpu].schedule_lock);
+ spin_unlock(&per_cpu(schedule_data, peer_cpu).schedule_lock);
/* Got one! */
if ( speer )
@@ -1120,11 +1123,11 @@ csched_dump_pcpu(int cpu)
runq = &spc->runq;
printk(" tick=%lu, sort=%d\n",
- schedule_data[cpu].tick,
+ per_cpu(schedule_data, cpu).tick,
spc->runq_sort_last);
/* current VCPU */
- svc = CSCHED_VCPU(schedule_data[cpu].curr);
+ svc = CSCHED_VCPU(per_cpu(schedule_data, cpu).curr);
if ( svc )
{
printk("\trun: ");
diff -r e4f1519b473f -r b60ea69932b1 xen/common/sched_sedf.c
--- a/xen/common/sched_sedf.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/common/sched_sedf.c Wed Aug 09 18:04:20 2006 +0100
@@ -113,13 +113,14 @@ struct sedf_cpu_info {
};
#define EDOM_INFO(d) ((struct sedf_vcpu_info *)((d)->sched_priv))
-#define CPU_INFO(cpu) ((struct sedf_cpu_info *)schedule_data[cpu].sched_priv)
+#define CPU_INFO(cpu) \
+ ((struct sedf_cpu_info *)per_cpu(schedule_data, cpu).sched_priv)
#define LIST(d) (&EDOM_INFO(d)->list)
#define EXTRALIST(d,i) (&(EDOM_INFO(d)->extralist[i]))
#define RUNQ(cpu) (&CPU_INFO(cpu)->runnableq)
#define WAITQ(cpu) (&CPU_INFO(cpu)->waitq)
#define EXTRAQ(cpu,i) (&(CPU_INFO(cpu)->extraq[i]))
-#define IDLETASK(cpu) ((struct vcpu *)schedule_data[cpu].idle)
+#define IDLETASK(cpu) ((struct vcpu *)per_cpu(schedule_data, cpu).idle)
#define PERIOD_BEGIN(inf) ((inf)->deadl_abs - (inf)->period)
@@ -348,11 +349,11 @@ static int sedf_init_vcpu(struct vcpu *v
inf->vcpu = v;
/* Allocate per-CPU context if this is the first domain to be added. */
- if ( unlikely(schedule_data[v->processor].sched_priv == NULL) )
- {
- schedule_data[v->processor].sched_priv =
+ if ( unlikely(per_cpu(schedule_data, v->processor).sched_priv == NULL) )
+ {
+ per_cpu(schedule_data, v->processor).sched_priv =
xmalloc(struct sedf_cpu_info);
- BUG_ON(schedule_data[v->processor].sched_priv == NULL);
+ BUG_ON(per_cpu(schedule_data, v->processor).sched_priv == NULL);
memset(CPU_INFO(v->processor), 0, sizeof(*CPU_INFO(v->processor)));
INIT_LIST_HEAD(WAITQ(v->processor));
INIT_LIST_HEAD(RUNQ(v->processor));
@@ -847,7 +848,7 @@ static void sedf_sleep(struct vcpu *d)
EDOM_INFO(d)->status |= SEDF_ASLEEP;
- if ( schedule_data[d->processor].curr == d )
+ if ( per_cpu(schedule_data, d->processor).curr == d )
{
cpu_raise_softirq(d->processor, SCHEDULE_SOFTIRQ);
}
@@ -1167,9 +1168,9 @@ void sedf_wake(struct vcpu *d)
Save approximation: Always switch to scheduler!*/
ASSERT(d->processor >= 0);
ASSERT(d->processor < NR_CPUS);
- ASSERT(schedule_data[d->processor].curr);
-
- if ( should_switch(schedule_data[d->processor].curr, d, now) )
+ ASSERT(per_cpu(schedule_data, d->processor).curr);
+
+ if ( should_switch(per_cpu(schedule_data, d->processor).curr, d, now) )
cpu_raise_softirq(d->processor, SCHEDULE_SOFTIRQ);
}
diff -r e4f1519b473f -r b60ea69932b1 xen/common/schedule.c
--- a/xen/common/schedule.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/common/schedule.c Wed Aug 09 18:04:20 2006 +0100
@@ -46,7 +46,7 @@ static void poll_timer_fn(void *data);
static void poll_timer_fn(void *data);
/* This is global for now so that private implementations can reach it */
-struct schedule_data schedule_data[NR_CPUS];
+DEFINE_PER_CPU(struct schedule_data, schedule_data);
extern struct scheduler sched_bvt_def;
extern struct scheduler sched_sedf_def;
@@ -67,13 +67,13 @@ static struct scheduler ops;
: (typeof(ops.fn(__VA_ARGS__)))0 )
/* Per-CPU periodic timer sends an event to the currently-executing domain. */
-static struct timer t_timer[NR_CPUS];
+static DEFINE_PER_CPU(struct timer, t_timer);
static inline void vcpu_runstate_change(
struct vcpu *v, int new_state, s_time_t new_entry_time)
{
ASSERT(v->runstate.state != new_state);
- ASSERT(spin_is_locked(&schedule_data[v->processor].schedule_lock));
+ ASSERT(spin_is_locked(&per_cpu(schedule_data,v->processor).schedule_lock));
v->runstate.time[v->runstate.state] +=
new_entry_time - v->runstate.state_entry_time;
@@ -107,8 +107,8 @@ int sched_init_vcpu(struct vcpu *v)
if ( is_idle_vcpu(v) )
{
- schedule_data[v->processor].curr = v;
- schedule_data[v->processor].idle = v;
+ per_cpu(schedule_data, v->processor).curr = v;
+ per_cpu(schedule_data, v->processor).idle = v;
set_bit(_VCPUF_running, &v->vcpu_flags);
}
@@ -500,19 +500,21 @@ long sched_adjdom(struct sched_adjdom_cm
*/
static void __enter_scheduler(void)
{
- struct vcpu *prev = current, *next = NULL;
- int cpu = smp_processor_id();
- s_time_t now = NOW();
- struct task_slice next_slice;
- s32 r_time; /* time for new dom to run */
+ struct vcpu *prev = current, *next = NULL;
+ s_time_t now = NOW();
+ struct schedule_data *sd;
+ struct task_slice next_slice;
+ s32 r_time; /* time for new dom to run */
ASSERT(!in_irq());
perfc_incrc(sched_run);
- spin_lock_irq(&schedule_data[cpu].schedule_lock);
-
- stop_timer(&schedule_data[cpu].s_timer);
+ sd = &this_cpu(schedule_data);
+
+ spin_lock_irq(&sd->schedule_lock);
+
+ stop_timer(&sd->s_timer);
/* get policy-specific decision on scheduling... */
next_slice = ops.do_schedule(now);
@@ -520,13 +522,13 @@ static void __enter_scheduler(void)
r_time = next_slice.time;
next = next_slice.task;
- schedule_data[cpu].curr = next;
+ sd->curr = next;
- set_timer(&schedule_data[cpu].s_timer, now + r_time);
+ set_timer(&sd->s_timer, now + r_time);
if ( unlikely(prev == next) )
{
- spin_unlock_irq(&schedule_data[cpu].schedule_lock);
+ spin_unlock_irq(&sd->schedule_lock);
return continue_running(prev);
}
@@ -552,17 +554,17 @@ static void __enter_scheduler(void)
ASSERT(!test_bit(_VCPUF_running, &next->vcpu_flags));
set_bit(_VCPUF_running, &next->vcpu_flags);
- spin_unlock_irq(&schedule_data[cpu].schedule_lock);
+ spin_unlock_irq(&sd->schedule_lock);
perfc_incrc(sched_ctx);
- prev->sleep_tick = schedule_data[cpu].tick;
+ prev->sleep_tick = sd->tick;
/* Ensure that the domain has an up-to-date time base. */
if ( !is_idle_vcpu(next) )
{
update_vcpu_system_time(next);
- if ( next->sleep_tick != schedule_data[cpu].tick )
+ if ( next->sleep_tick != sd->tick )
send_timer_event(next);
}
@@ -591,10 +593,9 @@ static void s_timer_fn(void *unused)
/* Periodic tick timer: send timer event to current domain */
static void t_timer_fn(void *unused)
{
- struct vcpu *v = current;
- unsigned int cpu = smp_processor_id();
-
- schedule_data[cpu].tick++;
+ struct vcpu *v = current;
+
+ this_cpu(schedule_data).tick++;
if ( !is_idle_vcpu(v) )
{
@@ -604,9 +605,9 @@ static void t_timer_fn(void *unused)
page_scrub_schedule_work();
- SCHED_OP(tick, cpu);
-
- set_timer(&t_timer[cpu], NOW() + MILLISECS(10));
+ SCHED_OP(tick, smp_processor_id());
+
+ set_timer(&this_cpu(t_timer), NOW() + MILLISECS(10));
}
/* Per-VCPU timer function: sends a virtual timer interrupt. */
@@ -633,9 +634,9 @@ void __init scheduler_init(void)
for ( i = 0; i < NR_CPUS; i++ )
{
- spin_lock_init(&schedule_data[i].schedule_lock);
- init_timer(&schedule_data[i].s_timer, s_timer_fn, NULL, i);
- init_timer(&t_timer[i], t_timer_fn, NULL, i);
+ spin_lock_init(&per_cpu(schedule_data, i).schedule_lock);
+ init_timer(&per_cpu(schedule_data, i).s_timer, s_timer_fn, NULL, i);
+ init_timer(&per_cpu(t_timer, i), t_timer_fn, NULL, i);
}
for ( i = 0; schedulers[i] != NULL; i++ )
@@ -676,10 +677,10 @@ void dump_runq(unsigned char key)
for_each_online_cpu ( i )
{
- spin_lock(&schedule_data[i].schedule_lock);
+ spin_lock(&per_cpu(schedule_data, i).schedule_lock);
printk("CPU[%02d] ", i);
- SCHED_OP(dump_cpu_state,i);
- spin_unlock(&schedule_data[i].schedule_lock);
+ SCHED_OP(dump_cpu_state, i);
+ spin_unlock(&per_cpu(schedule_data, i).schedule_lock);
}
local_irq_restore(flags);
diff -r e4f1519b473f -r b60ea69932b1 xen/common/timer.c
--- a/xen/common/timer.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/common/timer.c Wed Aug 09 18:04:20 2006 +0100
@@ -17,6 +17,7 @@
#include <xen/softirq.h>
#include <xen/timer.h>
#include <xen/keyhandler.h>
+#include <xen/percpu.h>
#include <asm/system.h>
#include <asm/desc.h>
@@ -32,7 +33,7 @@ struct timers {
struct timer *running;
} __cacheline_aligned;
-struct timers timers[NR_CPUS];
+static DEFINE_PER_CPU(struct timers, timers);
extern int reprogram_timer(s_time_t timeout);
@@ -149,7 +150,7 @@ static inline void __add_timer(struct ti
static inline void __add_timer(struct timer *timer)
{
int cpu = timer->cpu;
- if ( add_entry(&timers[cpu].heap, timer) )
+ if ( add_entry(&per_cpu(timers, cpu).heap, timer) )
cpu_raise_softirq(cpu, TIMER_SOFTIRQ);
}
@@ -157,7 +158,7 @@ static inline void __stop_timer(struct t
static inline void __stop_timer(struct timer *timer)
{
int cpu = timer->cpu;
- if ( remove_entry(timers[cpu].heap, timer) )
+ if ( remove_entry(per_cpu(timers, cpu).heap, timer) )
cpu_raise_softirq(cpu, TIMER_SOFTIRQ);
}
@@ -168,10 +169,10 @@ static inline void timer_lock(struct tim
for ( ; ; )
{
cpu = timer->cpu;
- spin_lock(&timers[cpu].lock);
+ spin_lock(&per_cpu(timers, cpu).lock);
if ( likely(timer->cpu == cpu) )
break;
- spin_unlock(&timers[cpu].lock);
+ spin_unlock(&per_cpu(timers, cpu).lock);
}
}
@@ -182,7 +183,7 @@ static inline void timer_lock(struct tim
static inline void timer_unlock(struct timer *timer)
{
- spin_unlock(&timers[timer->cpu].lock);
+ spin_unlock(&per_cpu(timers, timer->cpu).lock);
}
#define timer_unlock_irq(t) \
@@ -234,20 +235,20 @@ void migrate_timer(struct timer *timer,
if ( old_cpu < new_cpu )
{
- spin_lock_irqsave(&timers[old_cpu].lock, flags);
- spin_lock(&timers[new_cpu].lock);
+ spin_lock_irqsave(&per_cpu(timers, old_cpu).lock, flags);
+ spin_lock(&per_cpu(timers, new_cpu).lock);
}
else
{
- spin_lock_irqsave(&timers[new_cpu].lock, flags);
- spin_lock(&timers[old_cpu].lock);
+ spin_lock_irqsave(&per_cpu(timers, new_cpu).lock, flags);
+ spin_lock(&per_cpu(timers, old_cpu).lock);
}
if ( likely(timer->cpu == old_cpu) )
break;
- spin_unlock(&timers[old_cpu].lock);
- spin_unlock_irqrestore(&timers[new_cpu].lock, flags);
+ spin_unlock(&per_cpu(timers, old_cpu).lock);
+ spin_unlock_irqrestore(&per_cpu(timers, new_cpu).lock, flags);
}
if ( active_timer(timer) )
@@ -261,8 +262,8 @@ void migrate_timer(struct timer *timer,
timer->cpu = new_cpu;
}
- spin_unlock(&timers[old_cpu].lock);
- spin_unlock_irqrestore(&timers[new_cpu].lock, flags);
+ spin_unlock(&per_cpu(timers, old_cpu).lock);
+ spin_unlock_irqrestore(&per_cpu(timers, new_cpu).lock, flags);
}
@@ -271,7 +272,7 @@ void kill_timer(struct timer *timer)
int cpu;
unsigned long flags;
- BUG_ON(timers[smp_processor_id()].running == timer);
+ BUG_ON(this_cpu(timers).running == timer);
timer_lock_irqsave(timer, flags);
@@ -282,23 +283,25 @@ void kill_timer(struct timer *timer)
timer_unlock_irqrestore(timer, flags);
for_each_online_cpu ( cpu )
- while ( timers[cpu].running == timer )
+ while ( per_cpu(timers, cpu).running == timer )
cpu_relax();
}
static void timer_softirq_action(void)
{
- int cpu = smp_processor_id();
- struct timer *t, **heap;
- s_time_t now;
- void (*fn)(void *);
- void *data;
-
- spin_lock_irq(&timers[cpu].lock);
+ struct timer *t, **heap;
+ struct timers *ts;
+ s_time_t now;
+ void (*fn)(void *);
+ void *data;
+
+ ts = &this_cpu(timers);
+
+ spin_lock_irq(&ts->lock);
do {
- heap = timers[cpu].heap;
+ heap = ts->heap;
now = NOW();
while ( (GET_HEAP_SIZE(heap) != 0) &&
@@ -306,24 +309,24 @@ static void timer_softirq_action(void)
{
remove_entry(heap, t);
- timers[cpu].running = t;
+ ts->running = t;
fn = t->function;
data = t->data;
- spin_unlock_irq(&timers[cpu].lock);
+ spin_unlock_irq(&ts->lock);
(*fn)(data);
- spin_lock_irq(&timers[cpu].lock);
+ spin_lock_irq(&ts->lock);
/* Heap may have grown while the lock was released. */
- heap = timers[cpu].heap;
+ heap = ts->heap;
}
- timers[cpu].running = NULL;
+ ts->running = NULL;
}
while ( !reprogram_timer(GET_HEAP_SIZE(heap) ? heap[1]->expires : 0) );
- spin_unlock_irq(&timers[cpu].lock);
+ spin_unlock_irq(&ts->lock);
}
@@ -338,25 +341,28 @@ void process_pending_timers(void)
static void dump_timerq(unsigned char key)
{
- struct timer *t;
- unsigned long flags;
- s_time_t now = NOW();
- int i, j;
+ struct timer *t;
+ struct timers *ts;
+ unsigned long flags;
+ s_time_t now = NOW();
+ int i, j;
printk("Dumping timer queues: NOW=0x%08X%08X\n",
(u32)(now>>32), (u32)now);
for_each_online_cpu( i )
{
+ ts = &per_cpu(timers, i);
+
printk("CPU[%02d] ", i);
- spin_lock_irqsave(&timers[i].lock, flags);
- for ( j = 1; j <= GET_HEAP_SIZE(timers[i].heap); j++ )
+ spin_lock_irqsave(&ts->lock, flags);
+ for ( j = 1; j <= GET_HEAP_SIZE(ts->heap); j++ )
{
- t = timers[i].heap[j];
+ t = ts->heap[j];
printk (" %d : %p ex=0x%08X%08X %p\n",
j, t, (u32)(t->expires>>32), (u32)t->expires, t->data);
}
- spin_unlock_irqrestore(&timers[i].lock, flags);
+ spin_unlock_irqrestore(&ts->lock, flags);
printk("\n");
}
}
@@ -378,8 +384,8 @@ void __init timer_init(void)
for ( i = 0; i < NR_CPUS; i++ )
{
- spin_lock_init(&timers[i].lock);
- timers[i].heap = &dummy_heap;
+ spin_lock_init(&per_cpu(timers, i).lock);
+ per_cpu(timers, i).heap = &dummy_heap;
}
register_keyhandler('a', dump_timerq, "dump timer queues");
diff -r e4f1519b473f -r b60ea69932b1 xen/common/trace.c
--- a/xen/common/trace.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/common/trace.c Wed Aug 09 18:04:20 2006 +0100
@@ -39,8 +39,8 @@ integer_param("tbuf_size", opt_tbuf_size
integer_param("tbuf_size", opt_tbuf_size);
/* Pointers to the meta-data objects for all system trace buffers */
-static struct t_buf *t_bufs[NR_CPUS];
-static struct t_rec *t_recs[NR_CPUS];
+static DEFINE_PER_CPU(struct t_buf *, t_bufs);
+static DEFINE_PER_CPU(struct t_rec *, t_recs);
static int nr_recs;
/* High water mark for trace buffers; */
@@ -105,9 +105,10 @@ static int alloc_trace_bufs(void)
for_each_online_cpu ( i )
{
- buf = t_bufs[i] = (struct t_buf *)&rawbuf[i*opt_tbuf_size*PAGE_SIZE];
+ buf = per_cpu(t_bufs, i) = (struct t_buf *)
+ &rawbuf[i*opt_tbuf_size*PAGE_SIZE];
buf->cons = buf->prod = 0;
- t_recs[i] = (struct t_rec *)(buf + 1);
+ per_cpu(t_recs, i) = (struct t_rec *)(buf + 1);
}
t_buf_highwater = nr_recs >> 1; /* 50% high water */
@@ -186,7 +187,7 @@ int tb_control(dom0_tbufcontrol_t *tbc)
case DOM0_TBUF_GET_INFO:
tbc->cpu_mask = tb_cpu_mask;
tbc->evt_mask = tb_event_mask;
- tbc->buffer_mfn = opt_tbuf_size ? virt_to_mfn(t_bufs[0]) : 0UL;
+ tbc->buffer_mfn = opt_tbuf_size ? virt_to_mfn(per_cpu(t_bufs, 0)) : 0;
tbc->size = opt_tbuf_size * PAGE_SIZE;
break;
case DOM0_TBUF_SET_CPU_MASK:
@@ -258,7 +259,7 @@ void trace(u32 event, unsigned long d1,
/* Read tb_init_done /before/ t_bufs. */
rmb();
- buf = t_bufs[smp_processor_id()];
+ buf = this_cpu(t_bufs);
local_irq_save(flags);
@@ -272,7 +273,7 @@ void trace(u32 event, unsigned long d1,
if ( unlikely(this_cpu(lost_records) != 0) )
{
- rec = &t_recs[smp_processor_id()][buf->prod % nr_recs];
+ rec = &this_cpu(t_recs)[buf->prod % nr_recs];
memset(rec, 0, sizeof(*rec));
rec->cycles = (u64)get_cycles();
rec->event = TRC_LOST_RECORDS;
@@ -283,7 +284,7 @@ void trace(u32 event, unsigned long d1,
buf->prod++;
}
- rec = &t_recs[smp_processor_id()][buf->prod % nr_recs];
+ rec = &this_cpu(t_recs)[buf->prod % nr_recs];
rec->cycles = (u64)get_cycles();
rec->event = event;
rec->data[0] = d1;
diff -r e4f1519b473f -r b60ea69932b1 xen/drivers/char/console.c
--- a/xen/drivers/char/console.c Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/drivers/char/console.c Wed Aug 09 18:04:20 2006 +0100
@@ -716,7 +716,6 @@ void panic(const char *fmt, ...)
char buf[128];
unsigned long flags;
static DEFINE_SPINLOCK(lock);
- extern void machine_restart(char *);
debugtrace_dump();
diff -r e4f1519b473f -r b60ea69932b1 xen/include/asm-ia64/linux-xen/asm/cache.h
--- a/xen/include/asm-ia64/linux-xen/asm/cache.h Tue Aug 08 19:07:32
2006 -0500
+++ b/xen/include/asm-ia64/linux-xen/asm/cache.h Wed Aug 09 18:04:20
2006 +0100
@@ -32,4 +32,6 @@
#endif
#endif
+#define __read_mostly
+
#endif /* _ASM_IA64_CACHE_H */
diff -r e4f1519b473f -r b60ea69932b1 xen/include/asm-powerpc/cache.h
--- a/xen/include/asm-powerpc/cache.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/asm-powerpc/cache.h Wed Aug 09 18:04:20 2006 +0100
@@ -57,4 +57,6 @@ static __inline__ void synchronize_cache
isync();
}
+#define __read_mostly
+
#endif
diff -r e4f1519b473f -r b60ea69932b1 xen/include/asm-powerpc/flushtlb.h
--- a/xen/include/asm-powerpc/flushtlb.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/asm-powerpc/flushtlb.h Wed Aug 09 18:04:20 2006 +0100
@@ -22,6 +22,7 @@
#define _ASM_FLUSHTLB_H_
#include <xen/config.h>
+#include <xen/percpu.h>
#include <xen/types.h>
#include <asm/misc.h>
@@ -30,7 +31,7 @@ extern u32 tlbflush_clock;
#define tlbflush_current_time() tlbflush_clock
/* Time at which each CPU's TLB was last flushed. */
-extern u32 tlbflush_time[NR_CPUS];
+DECLARE_PER_CPU(u32, tlbflush_time);
static inline int NEED_FLUSH(u32 cpu_stamp, u32 lastuse_stamp)
{
@@ -44,12 +45,12 @@ static inline int NEED_FLUSH(u32 cpu_sta
* Filter the given set of CPUs, removing those that definitely flushed their
* TLB since @page_timestamp.
*/
-#define tlbflush_filter(mask, page_timestamp) \
-do { \
- unsigned int cpu; \
- for_each_cpu_mask ( cpu, mask ) \
- if ( !NEED_FLUSH(tlbflush_time[cpu], page_timestamp) ) \
- cpu_clear(cpu, mask); \
+#define tlbflush_filter(mask, page_timestamp) \
+do { \
+ unsigned int cpu; \
+ for_each_cpu_mask ( cpu, mask ) \
+ if ( !NEED_FLUSH(per_cpu(tlbflush_time, cpu), page_timestamp) ) \
+ cpu_clear(cpu, mask); \
} while ( 0 )
diff -r e4f1519b473f -r b60ea69932b1 xen/include/asm-x86/cache.h
--- a/xen/include/asm-x86/cache.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/asm-x86/cache.h Wed Aug 09 18:04:20 2006 +0100
@@ -10,4 +10,6 @@
#define L1_CACHE_SHIFT (CONFIG_X86_L1_CACHE_SHIFT)
#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
+#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+
#endif
diff -r e4f1519b473f -r b60ea69932b1 xen/include/asm-x86/current.h
--- a/xen/include/asm-x86/current.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/asm-x86/current.h Wed Aug 09 18:04:20 2006 +0100
@@ -8,6 +8,7 @@
#define __X86_CURRENT_H__
#include <xen/config.h>
+#include <xen/percpu.h>
#include <public/xen.h>
#include <asm/page.h>
@@ -53,7 +54,6 @@ static inline struct cpu_info *get_cpu_i
#define schedule_tail(vcpu) (((vcpu)->arch.schedule_tail)(vcpu))
-#include <xen/percpu.h>
/*
* Which VCPU's state is currently running on each CPU?
* This is not necesasrily the same as 'current' as a CPU may be
diff -r e4f1519b473f -r b60ea69932b1 xen/include/asm-x86/e820.h
--- a/xen/include/asm-x86/e820.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/asm-x86/e820.h Wed Aug 09 18:04:20 2006 +0100
@@ -12,6 +12,7 @@
#define E820_IO 16
#define E820_SHARED_PAGE 17
#define E820_XENSTORE 18
+#define E820_BUFFERED_IO 19
#define E820_MAP_PAGE 0x00090000
#define E820_MAP_NR_OFFSET 0x000001E8
diff -r e4f1519b473f -r b60ea69932b1 xen/include/asm-x86/flushtlb.h
--- a/xen/include/asm-x86/flushtlb.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/asm-x86/flushtlb.h Wed Aug 09 18:04:20 2006 +0100
@@ -11,13 +11,15 @@
#define __FLUSHTLB_H__
#include <xen/config.h>
+#include <xen/percpu.h>
#include <xen/smp.h>
+#include <xen/types.h>
/* The current time as shown by the virtual TLB clock. */
extern u32 tlbflush_clock;
/* Time at which each CPU's TLB was last flushed. */
-extern u32 tlbflush_time[NR_CPUS];
+DECLARE_PER_CPU(u32, tlbflush_time);
#define tlbflush_current_time() tlbflush_clock
@@ -47,12 +49,12 @@ static inline int NEED_FLUSH(u32 cpu_sta
* Filter the given set of CPUs, removing those that definitely flushed their
* TLB since @page_timestamp.
*/
-#define tlbflush_filter(mask, page_timestamp) \
-do { \
- unsigned int cpu; \
- for_each_cpu_mask ( cpu, mask ) \
- if ( !NEED_FLUSH(tlbflush_time[cpu], page_timestamp) ) \
- cpu_clear(cpu, mask); \
+#define tlbflush_filter(mask, page_timestamp) \
+do { \
+ unsigned int cpu; \
+ for_each_cpu_mask ( cpu, mask ) \
+ if ( !NEED_FLUSH(per_cpu(tlbflush_time, cpu), page_timestamp) ) \
+ cpu_clear(cpu, mask); \
} while ( 0 )
extern void new_tlbflush_clock_period(void);
diff -r e4f1519b473f -r b60ea69932b1 xen/include/asm-x86/hvm/domain.h
--- a/xen/include/asm-x86/hvm/domain.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/asm-x86/hvm/domain.h Wed Aug 09 18:04:20 2006 +0100
@@ -33,6 +33,8 @@
struct hvm_domain {
unsigned long shared_page_va;
+ unsigned long buffered_io_va;
+ spinlock_t buffered_io_lock;
s64 tsc_frequency;
struct pl_time pl_time;
diff -r e4f1519b473f -r b60ea69932b1 xen/include/asm-x86/hvm/hvm.h
--- a/xen/include/asm-x86/hvm/hvm.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/asm-x86/hvm/hvm.h Wed Aug 09 18:04:20 2006 +0100
@@ -77,12 +77,20 @@ hvm_disable(void)
hvm_funcs.disable();
}
+void hvm_create_event_channels(struct vcpu *v);
+void hvm_map_io_shared_pages(struct vcpu *v);
+
static inline int
hvm_initialize_guest_resources(struct vcpu *v)
{
+ int ret = 1;
if ( hvm_funcs.initialize_guest_resources )
- return hvm_funcs.initialize_guest_resources(v);
- return 0;
+ ret = hvm_funcs.initialize_guest_resources(v);
+ if ( ret == 1 ) {
+ hvm_map_io_shared_pages(v);
+ hvm_create_event_channels(v);
+ }
+ return ret;
}
static inline void
diff -r e4f1519b473f -r b60ea69932b1 xen/include/asm-x86/hvm/io.h
--- a/xen/include/asm-x86/hvm/io.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/asm-x86/hvm/io.h Wed Aug 09 18:04:20 2006 +0100
@@ -150,13 +150,12 @@ static inline int irq_masked(unsigned lo
#endif
extern void handle_mmio(unsigned long, unsigned long);
-extern void hvm_wait_io(void);
-extern void hvm_safe_block(void);
extern void hvm_io_assist(struct vcpu *v);
extern void pic_irq_request(void *data, int level);
extern void hvm_pic_assist(struct vcpu *v);
extern int cpu_get_interrupt(struct vcpu *v, int *type);
extern int cpu_has_pending_irq(struct vcpu *v);
+extern void hvm_release_assist_channel(struct vcpu *v);
// XXX - think about this, maybe use bit 30 of the mfn to signify an MMIO
frame.
#define mmio_space(gpa) (!VALID_MFN(get_mfn_from_gpfn((gpa) >> PAGE_SHIFT)))
diff -r e4f1519b473f -r b60ea69932b1 xen/include/asm-x86/hvm/support.h
--- a/xen/include/asm-x86/hvm/support.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/asm-x86/hvm/support.h Wed Aug 09 18:04:20 2006 +0100
@@ -42,11 +42,6 @@ static inline vcpu_iodata_t *get_vio(str
static inline vcpu_iodata_t *get_vio(struct domain *d, unsigned long cpu)
{
return &get_sp(d)->vcpu_iodata[cpu];
-}
-
-static inline int iopacket_port(struct vcpu *v)
-{
- return get_vio(v->domain, v->vcpu_id)->vp_eport;
}
/* XXX these are really VMX specific */
@@ -144,10 +139,13 @@ extern void hvm_setup_platform(struct do
extern void hvm_setup_platform(struct domain* d);
extern int hvm_mmio_intercept(ioreq_t *p);
extern int hvm_io_intercept(ioreq_t *p, int type);
+extern int hvm_buffered_io_intercept(ioreq_t *p);
extern void hvm_hooks_assist(struct vcpu *v);
extern void hvm_print_line(struct vcpu *v, const char c);
extern void hlt_timer_fn(void *data);
void hvm_do_hypercall(struct cpu_user_regs *pregs);
+void hvm_prod_vcpu(struct vcpu *v);
+
#endif /* __ASM_X86_HVM_SUPPORT_H__ */
diff -r e4f1519b473f -r b60ea69932b1 xen/include/asm-x86/hvm/vcpu.h
--- a/xen/include/asm-x86/hvm/vcpu.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/asm-x86/hvm/vcpu.h Wed Aug 09 18:04:20 2006 +0100
@@ -38,6 +38,8 @@ struct hvm_vcpu {
/* For AP startup */
unsigned long init_sipi_sipi_state;
+ int xen_port;
+
/* Flags */
int flag_dr_dirty;
diff -r e4f1519b473f -r b60ea69932b1 xen/include/asm-x86/hvm/vmx/vmx.h
--- a/xen/include/asm-x86/hvm/vmx/vmx.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/asm-x86/hvm/vmx/vmx.h Wed Aug 09 18:04:20 2006 +0100
@@ -40,82 +40,91 @@ extern unsigned int cpu_rev;
* Need fill bits for SENTER
*/
-#define MONITOR_PIN_BASED_EXEC_CONTROLS_RESERVED_VALUE 0x00000016
-
-#define MONITOR_PIN_BASED_EXEC_CONTROLS \
- ( \
- MONITOR_PIN_BASED_EXEC_CONTROLS_RESERVED_VALUE | \
- PIN_BASED_EXT_INTR_MASK | \
- PIN_BASED_NMI_EXITING \
- )
-
-#define MONITOR_CPU_BASED_EXEC_CONTROLS_RESERVED_VALUE 0x0401e172
-
-#define _MONITOR_CPU_BASED_EXEC_CONTROLS \
- ( \
+#define MONITOR_PIN_BASED_EXEC_CONTROLS_RESERVED_VALUE 0x00000016
+
+#define MONITOR_PIN_BASED_EXEC_CONTROLS \
+ ( \
+ MONITOR_PIN_BASED_EXEC_CONTROLS_RESERVED_VALUE | \
+ PIN_BASED_EXT_INTR_MASK | \
+ PIN_BASED_NMI_EXITING \
+ )
+
+#define MONITOR_CPU_BASED_EXEC_CONTROLS_RESERVED_VALUE 0x0401e172
+
+#define _MONITOR_CPU_BASED_EXEC_CONTROLS \
+ ( \
MONITOR_CPU_BASED_EXEC_CONTROLS_RESERVED_VALUE | \
- CPU_BASED_HLT_EXITING | \
- CPU_BASED_INVDPG_EXITING | \
- CPU_BASED_MWAIT_EXITING | \
- CPU_BASED_MOV_DR_EXITING | \
- CPU_BASED_ACTIVATE_IO_BITMAP | \
- CPU_BASED_USE_TSC_OFFSETING \
- )
-
-#define MONITOR_CPU_BASED_EXEC_CONTROLS_IA32E_MODE \
- ( \
- CPU_BASED_CR8_LOAD_EXITING | \
- CPU_BASED_CR8_STORE_EXITING \
- )
-
-#define MONITOR_VM_EXIT_CONTROLS_RESERVED_VALUE 0x0003edff
-
-#define MONITOR_VM_EXIT_CONTROLS_IA32E_MODE 0x00000200
-
-#define _MONITOR_VM_EXIT_CONTROLS \
- ( \
- MONITOR_VM_EXIT_CONTROLS_RESERVED_VALUE |\
- VM_EXIT_ACK_INTR_ON_EXIT \
+ CPU_BASED_HLT_EXITING | \
+ CPU_BASED_INVDPG_EXITING | \
+ CPU_BASED_MWAIT_EXITING | \
+ CPU_BASED_MOV_DR_EXITING | \
+ CPU_BASED_ACTIVATE_IO_BITMAP | \
+ CPU_BASED_USE_TSC_OFFSETING \
+ )
+
+#define MONITOR_CPU_BASED_EXEC_CONTROLS_IA32E_MODE \
+ ( \
+ CPU_BASED_CR8_LOAD_EXITING | \
+ CPU_BASED_CR8_STORE_EXITING \
+ )
+
+#define MONITOR_VM_EXIT_CONTROLS_RESERVED_VALUE 0x0003edff
+
+#define MONITOR_VM_EXIT_CONTROLS_IA32E_MODE 0x00000200
+
+#define _MONITOR_VM_EXIT_CONTROLS \
+ ( \
+ MONITOR_VM_EXIT_CONTROLS_RESERVED_VALUE | \
+ VM_EXIT_ACK_INTR_ON_EXIT \
)
#if defined (__x86_64__)
-#define MONITOR_CPU_BASED_EXEC_CONTROLS \
- ( \
- _MONITOR_CPU_BASED_EXEC_CONTROLS | \
- MONITOR_CPU_BASED_EXEC_CONTROLS_IA32E_MODE \
- )
-#define MONITOR_VM_EXIT_CONTROLS \
- ( \
- _MONITOR_VM_EXIT_CONTROLS | \
- MONITOR_VM_EXIT_CONTROLS_IA32E_MODE \
+#define MONITOR_CPU_BASED_EXEC_CONTROLS \
+ ( \
+ _MONITOR_CPU_BASED_EXEC_CONTROLS | \
+ MONITOR_CPU_BASED_EXEC_CONTROLS_IA32E_MODE \
+ )
+#define MONITOR_VM_EXIT_CONTROLS \
+ ( \
+ _MONITOR_VM_EXIT_CONTROLS | \
+ MONITOR_VM_EXIT_CONTROLS_IA32E_MODE \
)
#else
-#define MONITOR_CPU_BASED_EXEC_CONTROLS \
- _MONITOR_CPU_BASED_EXEC_CONTROLS
-
-#define MONITOR_VM_EXIT_CONTROLS \
+#define MONITOR_CPU_BASED_EXEC_CONTROLS \
+ _MONITOR_CPU_BASED_EXEC_CONTROLS
+
+#define MONITOR_VM_EXIT_CONTROLS \
_MONITOR_VM_EXIT_CONTROLS
#endif
-#define VM_ENTRY_CONTROLS_RESERVED_VALUE 0x000011ff
-#define VM_ENTRY_CONTROLS_IA32E_MODE 0x00000200
-#define MONITOR_VM_ENTRY_CONTROLS VM_ENTRY_CONTROLS_RESERVED_VALUE
+#define VM_ENTRY_CONTROLS_RESERVED_VALUE 0x000011ff
+#define VM_ENTRY_CONTROLS_IA32E_MODE 0x00000200
+
+#define MONITOR_VM_ENTRY_CONTROLS \
+ VM_ENTRY_CONTROLS_RESERVED_VALUE
+
/*
* Exit Reasons
*/
-#define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000
+#define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000
#define EXIT_REASON_EXCEPTION_NMI 0
#define EXIT_REASON_EXTERNAL_INTERRUPT 1
-
+#define EXIT_REASON_TRIPLE_FAULT 2
+#define EXIT_REASON_INIT 3
+#define EXIT_REASON_SIPI 4
+#define EXIT_REASON_IO_SMI 5
+#define EXIT_REASON_OTHER_SMI 6
#define EXIT_REASON_PENDING_INTERRUPT 7
#define EXIT_REASON_TASK_SWITCH 9
#define EXIT_REASON_CPUID 10
#define EXIT_REASON_HLT 12
+#define EXIT_REASON_INVD 13
#define EXIT_REASON_INVLPG 14
#define EXIT_REASON_RDPMC 15
#define EXIT_REASON_RDTSC 16
+#define EXIT_REASON_RSM 17
#define EXIT_REASON_VMCALL 18
#define EXIT_REASON_VMCLEAR 19
#define EXIT_REASON_VMLAUNCH 20
@@ -124,19 +133,24 @@ extern unsigned int cpu_rev;
#define EXIT_REASON_VMREAD 23
#define EXIT_REASON_VMRESUME 24
#define EXIT_REASON_VMWRITE 25
-#define EXIT_REASON_VMOFF 26
-#define EXIT_REASON_VMON 27
+#define EXIT_REASON_VMXOFF 26
+#define EXIT_REASON_VMXON 27
#define EXIT_REASON_CR_ACCESS 28
#define EXIT_REASON_DR_ACCESS 29
#define EXIT_REASON_IO_INSTRUCTION 30
#define EXIT_REASON_MSR_READ 31
#define EXIT_REASON_MSR_WRITE 32
-#define EXIT_REASON_MWAIT_INSTRUCTION 36
#define EXIT_REASON_INVALID_GUEST_STATE 33
#define EXIT_REASON_MSR_LOADING 34
+
+#define EXIT_REASON_MWAIT_INSTRUCTION 36
+#define EXIT_REASON_MONITOR_INSTRUCTION 39
+#define EXIT_REASON_PAUSE_INSTRUCTION 40
+
#define EXIT_REASON_MACHINE_CHECK 41
+#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
/*
* Interruption-information format
@@ -146,9 +160,9 @@ extern unsigned int cpu_rev;
#define INTR_INFO_DELIVER_CODE_MASK 0x800 /* 11 */
#define INTR_INFO_VALID_MASK 0x80000000 /* 31 */
-#define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */
-#define INTR_TYPE_HW_EXCEPTION (3 << 8) /* hardware exception */
-#define INTR_TYPE_SW_EXCEPTION (6 << 8) /* software exception */
+#define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */
+#define INTR_TYPE_HW_EXCEPTION (3 << 8) /* hardware exception */
+#define INTR_TYPE_SW_EXCEPTION (6 << 8) /* software exception */
/*
* Exit Qualifications for MOV for Control Register Access
@@ -156,33 +170,33 @@ extern unsigned int cpu_rev;
#define CONTROL_REG_ACCESS_NUM 0xf /* 3:0, number of control
register */
#define CONTROL_REG_ACCESS_TYPE 0x30 /* 5:4, access type */
#define CONTROL_REG_ACCESS_REG 0xf00 /* 10:8, general purpose
register */
-#define LMSW_SOURCE_DATA (0xFFFF << 16) /* 16:31 lmsw source */
-#define REG_EAX (0 << 8)
-#define REG_ECX (1 << 8)
-#define REG_EDX (2 << 8)
-#define REG_EBX (3 << 8)
-#define REG_ESP (4 << 8)
-#define REG_EBP (5 << 8)
-#define REG_ESI (6 << 8)
-#define REG_EDI (7 << 8)
-#define REG_R8 (8 << 8)
-#define REG_R9 (9 << 8)
-#define REG_R10 (10 << 8)
-#define REG_R11 (11 << 8)
-#define REG_R12 (12 << 8)
-#define REG_R13 (13 << 8)
-#define REG_R14 (14 << 8)
-#define REG_R15 (15 << 8)
+#define LMSW_SOURCE_DATA (0xFFFF << 16) /* 16:31 lmsw source */
+#define REG_EAX (0 << 8)
+#define REG_ECX (1 << 8)
+#define REG_EDX (2 << 8)
+#define REG_EBX (3 << 8)
+#define REG_ESP (4 << 8)
+#define REG_EBP (5 << 8)
+#define REG_ESI (6 << 8)
+#define REG_EDI (7 << 8)
+#define REG_R8 (8 << 8)
+#define REG_R9 (9 << 8)
+#define REG_R10 (10 << 8)
+#define REG_R11 (11 << 8)
+#define REG_R12 (12 << 8)
+#define REG_R13 (13 << 8)
+#define REG_R14 (14 << 8)
+#define REG_R15 (15 << 8)
/*
* Exit Qualifications for MOV for Debug Register Access
*/
#define DEBUG_REG_ACCESS_NUM 0x7 /* 2:0, number of debug
register */
#define DEBUG_REG_ACCESS_TYPE 0x10 /* 4, direction of access */
-#define TYPE_MOV_TO_DR (0 << 4)
+#define TYPE_MOV_TO_DR (0 << 4)
#define TYPE_MOV_FROM_DR (1 << 4)
#define DEBUG_REG_ACCESS_REG 0xf00 /* 11:8, general purpose
register */
-
+
/* These bits in the CR4 are owned by the host */
#if CONFIG_PAGING_LEVELS >= 3
#define VMX_CR4_HOST_MASK (X86_CR4_VMXE | X86_CR4_PAE)
@@ -212,7 +226,7 @@ static inline void __vmptrld(u64 addr)
/* CF==1 or ZF==1 --> crash (ud2) */
"ja 1f ; ud2 ; 1:\n"
:
- : "a" (&addr)
+ : "a" (&addr)
: "memory");
}
@@ -221,7 +235,7 @@ static inline void __vmptrst(u64 addr)
__asm__ __volatile__ ( VMPTRST_OPCODE
MODRM_EAX_07
:
- : "a" (&addr)
+ : "a" (&addr)
: "memory");
}
@@ -232,7 +246,7 @@ static inline void __vmpclear(u64 addr)
/* CF==1 or ZF==1 --> crash (ud2) */
"ja 1f ; ud2 ; 1:\n"
:
- : "a" (&addr)
+ : "a" (&addr)
: "memory");
}
@@ -252,7 +266,7 @@ static always_inline int ___vmread(
: "0" (0), "a" (field)
: "memory");
- switch (size) {
+ switch ( size ) {
case 1:
*((u8 *) (ptr)) = ecx;
break;
@@ -274,43 +288,45 @@ static always_inline int ___vmread(
}
-static always_inline void __vmwrite_vcpu(struct vcpu *v, unsigned long field,
unsigned long value)
-{
- switch(field) {
+static always_inline void __vmwrite_vcpu(
+ struct vcpu *v, unsigned long field, unsigned long value)
+{
+ switch ( field ) {
case CR0_READ_SHADOW:
- v->arch.hvm_vmx.cpu_shadow_cr0 = value;
- break;
+ v->arch.hvm_vmx.cpu_shadow_cr0 = value;
+ break;
case GUEST_CR0:
- v->arch.hvm_vmx.cpu_cr0 = value;
- break;
+ v->arch.hvm_vmx.cpu_cr0 = value;
+ break;
case CPU_BASED_VM_EXEC_CONTROL:
- v->arch.hvm_vmx.cpu_based_exec_control = value;
- break;
+ v->arch.hvm_vmx.cpu_based_exec_control = value;
+ break;
default:
- printk("__vmwrite_cpu: invalid field %lx\n", field);
- break;
- }
-}
-
-static always_inline void __vmread_vcpu(struct vcpu *v, unsigned long field,
unsigned long *value)
-{
- switch(field) {
+ printk("__vmwrite_cpu: invalid field %lx\n", field);
+ break;
+ }
+}
+
+static always_inline void __vmread_vcpu(
+ struct vcpu *v, unsigned long field, unsigned long *value)
+{
+ switch ( field ) {
case CR0_READ_SHADOW:
- *value = v->arch.hvm_vmx.cpu_shadow_cr0;
- break;
+ *value = v->arch.hvm_vmx.cpu_shadow_cr0;
+ break;
case GUEST_CR0:
- *value = v->arch.hvm_vmx.cpu_cr0;
- break;
+ *value = v->arch.hvm_vmx.cpu_cr0;
+ break;
case CPU_BASED_VM_EXEC_CONTROL:
- *value = v->arch.hvm_vmx.cpu_based_exec_control;
- break;
+ *value = v->arch.hvm_vmx.cpu_based_exec_control;
+ break;
default:
- printk("__vmread_cpu: invalid field %lx\n", field);
- break;
- }
-}
-
-static inline int __vmwrite (unsigned long field, unsigned long value)
+ printk("__vmread_cpu: invalid field %lx\n", field);
+ break;
+ }
+}
+
+static inline int __vmwrite(unsigned long field, unsigned long value)
{
struct vcpu *v = current;
int rc;
@@ -323,12 +339,12 @@ static inline int __vmwrite (unsigned lo
: "0" (0), "a" (field) , "c" (value)
: "memory");
- switch(field) {
+ switch ( field ) {
case CR0_READ_SHADOW:
case GUEST_CR0:
case CPU_BASED_VM_EXEC_CONTROL:
- __vmwrite_vcpu(v, field, value);
- break;
+ __vmwrite_vcpu(v, field, value);
+ break;
}
return rc;
@@ -336,31 +352,31 @@ static inline int __vmwrite (unsigned lo
static inline int __vm_set_bit(unsigned long field, unsigned long mask)
{
- unsigned long tmp;
- int err = 0;
-
- err |= __vmread(field, &tmp);
- tmp |= mask;
- err |= __vmwrite(field, tmp);
-
- return err;
+ unsigned long tmp;
+ int err = 0;
+
+ err |= __vmread(field, &tmp);
+ tmp |= mask;
+ err |= __vmwrite(field, tmp);
+
+ return err;
}
static inline int __vm_clear_bit(unsigned long field, unsigned long mask)
{
- unsigned long tmp;
- int err = 0;
-
- err |= __vmread(field, &tmp);
- tmp &= ~mask;
- err |= __vmwrite(field, tmp);
-
- return err;
+ unsigned long tmp;
+ int err = 0;
+
+ err |= __vmread(field, &tmp);
+ tmp &= ~mask;
+ err |= __vmwrite(field, tmp);
+
+ return err;
}
static inline void __vmxoff (void)
{
- __asm__ __volatile__ ( VMXOFF_OPCODE
+ __asm__ __volatile__ ( VMXOFF_OPCODE
::: "memory");
}
@@ -373,7 +389,7 @@ static inline int __vmxon (u64 addr)
/* CF==1 or ZF==1 --> rc = -1 */
"setna %b0 ; neg %0"
: "=q" (rc)
- : "0" (0), "a" (&addr)
+ : "0" (0), "a" (&addr)
: "memory");
return rc;
@@ -390,9 +406,9 @@ static inline void vmx_stts(void)
return;
/*
- * If the guest does not have TS enabled then we must cause and handle an
- * exception on first use of the FPU. If the guest *does* have TS enabled
- * then this is not necessary: no FPU activity can occur until the guest
+ * If the guest does not have TS enabled then we must cause and handle an
+ * exception on first use of the FPU. If the guest *does* have TS enabled
+ * then this is not necessary: no FPU activity can occur until the guest
* clears CR0.TS, and we will initialise the FPU when that happens.
*/
__vmread_vcpu(v, CR0_READ_SHADOW, &cr0);
@@ -421,66 +437,64 @@ static inline int vmx_pgbit_test(struct
return (cr0 & X86_CR0_PG);
}
-static inline int __vmx_inject_exception(struct vcpu *v, int trap, int type,
+static inline void __vmx_inject_exception(struct vcpu *v, int trap, int type,
int error_code, int ilen)
{
unsigned long intr_fields;
/* Reflect it back into the guest */
intr_fields = (INTR_INFO_VALID_MASK | type | trap);
- if (error_code != VMX_DELIVER_NO_ERROR_CODE) {
+ if ( error_code != VMX_DELIVER_NO_ERROR_CODE ) {
__vmwrite(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
intr_fields |= INTR_INFO_DELIVER_CODE_MASK;
}
- if(ilen)
+ if ( ilen )
__vmwrite(VM_ENTRY_INSTRUCTION_LEN, ilen);
__vmwrite(VM_ENTRY_INTR_INFO_FIELD, intr_fields);
- return 0;
-}
-
-static inline int vmx_inject_hw_exception(struct vcpu *v, int trap, int
error_code)
+}
+
+static inline void vmx_inject_hw_exception(
+ struct vcpu *v, int trap, int error_code)
{
v->arch.hvm_vmx.vector_injected = 1;
- return __vmx_inject_exception(v, trap, INTR_TYPE_HW_EXCEPTION,
- error_code, 0);
-}
-
-static inline int vmx_inject_sw_exception(struct vcpu *v, int trap, int
instruction_len) {
- v->arch.hvm_vmx.vector_injected=1;
- return __vmx_inject_exception(v, trap, INTR_TYPE_SW_EXCEPTION,
- VMX_DELIVER_NO_ERROR_CODE,
- instruction_len);
-}
-
-static inline int vmx_inject_extint(struct vcpu *v, int trap, int error_code)
+ __vmx_inject_exception(v, trap, INTR_TYPE_HW_EXCEPTION, error_code, 0);
+}
+
+static inline void vmx_inject_sw_exception(
+ struct vcpu *v, int trap, int instruction_len)
+{
+ v->arch.hvm_vmx.vector_injected = 1;
+ __vmx_inject_exception(v, trap, INTR_TYPE_SW_EXCEPTION,
+ VMX_DELIVER_NO_ERROR_CODE,
+ instruction_len);
+}
+
+static inline void vmx_inject_extint(struct vcpu *v, int trap, int error_code)
{
__vmx_inject_exception(v, trap, INTR_TYPE_EXT_INTR, error_code, 0);
__vmwrite(GUEST_INTERRUPTIBILITY_INFO, 0);
-
- return 0;
-}
-
-static inline int vmx_reflect_exception(struct vcpu *v)
+}
+
+static inline void vmx_reflect_exception(struct vcpu *v)
{
int error_code, intr_info, vector;
__vmread(VM_EXIT_INTR_INFO, &intr_info);
vector = intr_info & 0xff;
- if (intr_info & INTR_INFO_DELIVER_CODE_MASK)
+ if ( intr_info & INTR_INFO_DELIVER_CODE_MASK )
__vmread(VM_EXIT_INTR_ERROR_CODE, &error_code);
else
error_code = VMX_DELIVER_NO_ERROR_CODE;
#ifndef NDEBUG
{
- unsigned long eip;
-
- __vmread(GUEST_RIP, &eip);
- HVM_DBG_LOG(DBG_LEVEL_1,
- "vmx_reflect_exception: eip = %lx, error_code = %x",
- eip, error_code);
+ unsigned long rip;
+
+ __vmread(GUEST_RIP, &rip);
+ HVM_DBG_LOG(DBG_LEVEL_1, "rip = %lx, error_code = %x",
+ rip, error_code);
}
#endif /* NDEBUG */
@@ -489,15 +503,14 @@ static inline int vmx_reflect_exception(
2.8.3, SW_EXCEPTION should be used for #BP and #OV, and
HW_EXCPEPTION used for everything else. The main difference
appears to be that for SW_EXCEPTION, the EIP/RIP is incremented
- by VM_ENTER_INSTRUCTION_LEN bytes, whereas for HW_EXCEPTION,
+ by VM_ENTER_INSTRUCTION_LEN bytes, whereas for HW_EXCEPTION,
it is not. */
- if((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_SW_EXCEPTION) {
- int ilen;
- __vmread(VM_EXIT_INSTRUCTION_LEN, &ilen);
- vmx_inject_sw_exception(v, vector, ilen);
+ if ( (intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_SW_EXCEPTION ) {
+ int ilen;
+ __vmread(VM_EXIT_INSTRUCTION_LEN, &ilen);
+ vmx_inject_sw_exception(v, vector, ilen);
} else
- vmx_inject_hw_exception(v, vector, error_code);
- return 0;
+ vmx_inject_hw_exception(v, vector, error_code);
}
#endif /* __ASM_X86_HVM_VMX_VMX_H__ */
diff -r e4f1519b473f -r b60ea69932b1 xen/include/public/hvm/ioreq.h
--- a/xen/include/public/hvm/ioreq.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/public/hvm/ioreq.h Wed Aug 09 18:04:20 2006 +0100
@@ -69,7 +69,6 @@ struct vcpu_iodata {
struct ioreq vp_ioreq;
/* Event channel port */
unsigned int vp_eport; /* VMX vcpu uses this to notify DM */
- unsigned int dm_eport; /* DM uses this to notify VMX vcpu */
};
typedef struct vcpu_iodata vcpu_iodata_t;
@@ -78,6 +77,14 @@ struct shared_iopage {
struct vcpu_iodata vcpu_iodata[1];
};
typedef struct shared_iopage shared_iopage_t;
+
+#define IOREQ_BUFFER_SLOT_NUM 80
+struct buffered_iopage {
+ unsigned long read_pointer;
+ unsigned long write_pointer;
+ ioreq_t ioreq[IOREQ_BUFFER_SLOT_NUM];
+}; /* sizeof this structure must be in one page */
+typedef struct buffered_iopage buffered_iopage_t;
#endif /* _IOREQ_H_ */
diff -r e4f1519b473f -r b60ea69932b1 xen/include/xen/config.h
--- a/xen/include/xen/config.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/xen/config.h Wed Aug 09 18:04:20 2006 +0100
@@ -50,6 +50,5 @@
#endif /* !__ASSEMBLY__ */
#define fastcall
-#define __read_mostly
#endif /* __XEN_CONFIG_H__ */
diff -r e4f1519b473f -r b60ea69932b1 xen/include/xen/event.h
--- a/xen/include/xen/event.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/xen/event.h Wed Aug 09 18:04:20 2006 +0100
@@ -12,6 +12,7 @@
#include <xen/config.h>
#include <xen/sched.h>
#include <xen/smp.h>
+#include <xen/softirq.h>
#include <asm/bitops.h>
#include <asm/event.h>
diff -r e4f1519b473f -r b60ea69932b1 xen/include/xen/multicall.h
--- a/xen/include/xen/multicall.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/xen/multicall.h Wed Aug 09 18:04:20 2006 +0100
@@ -5,6 +5,7 @@
#ifndef __XEN_MULTICALL_H__
#define __XEN_MULTICALL_H__
+#include <xen/percpu.h>
#include <asm/multicall.h>
#define _MCSF_in_multicall 0
@@ -14,8 +15,8 @@ struct mc_state {
struct mc_state {
unsigned long flags;
struct multicall_entry call;
-} __cacheline_aligned;
+};
-extern struct mc_state mc_state[NR_CPUS];
+DECLARE_PER_CPU(struct mc_state, mc_state);
#endif /* __XEN_MULTICALL_H__ */
diff -r e4f1519b473f -r b60ea69932b1 xen/include/xen/percpu.h
--- a/xen/include/xen/percpu.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/xen/percpu.h Wed Aug 09 18:04:20 2006 +0100
@@ -2,7 +2,6 @@
#define __XEN_PERCPU_H__
#include <xen/config.h>
-#include <xen/smp.h>
#include <asm/percpu.h>
/* Preferred on Xen. Also see arch-defined per_cpu(). */
diff -r e4f1519b473f -r b60ea69932b1 xen/include/xen/sched-if.h
--- a/xen/include/xen/sched-if.h Tue Aug 08 19:07:32 2006 -0500
+++ b/xen/include/xen/sched-if.h Wed Aug 09 18:04:20 2006 +0100
@@ -8,6 +8,8 @@
#ifndef __XEN_SCHED_IF_H__
#define __XEN_SCHED_IF_H__
+#include <xen/percpu.h>
+
struct schedule_data {
spinlock_t schedule_lock; /* spinlock protecting curr */
struct vcpu *curr; /* current task */
@@ -17,7 +19,7 @@ struct schedule_data {
unsigned long tick; /* current periodic 'tick' */
} __cacheline_aligned;
-extern struct schedule_data schedule_data[];
+DECLARE_PER_CPU(struct schedule_data, schedule_data);
static inline void vcpu_schedule_lock(struct vcpu *v)
{
@@ -26,10 +28,10 @@ static inline void vcpu_schedule_lock(st
for ( ; ; )
{
cpu = v->processor;
- spin_lock(&schedule_data[cpu].schedule_lock);
+ spin_lock(&per_cpu(schedule_data, cpu).schedule_lock);
if ( likely(v->processor == cpu) )
break;
- spin_unlock(&schedule_data[cpu].schedule_lock);
+ spin_unlock(&per_cpu(schedule_data, cpu).schedule_lock);
}
}
@@ -40,7 +42,7 @@ static inline void vcpu_schedule_lock(st
static inline void vcpu_schedule_unlock(struct vcpu *v)
{
- spin_unlock(&schedule_data[v->processor].schedule_lock);
+ spin_unlock(&per_cpu(schedule_data, v->processor).schedule_lock);
}
#define vcpu_schedule_unlock_irq(v) \
diff -r e4f1519b473f -r b60ea69932b1
linux-2.6-xen-sparse/drivers/xen/pciback/slot.c
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/linux-2.6-xen-sparse/drivers/xen/pciback/slot.c Wed Aug 09 18:04:20
2006 +0100
@@ -0,0 +1,151 @@
+/*
+ * PCI Backend - Provides a Virtual PCI bus (with real devices)
+ * to the frontend
+ *
+ * Author: Ryan Wilson <hap9@xxxxxxxxxxxxxx> (vpci.c)
+ * Author: Tristan Gingold <tristan.gingold@xxxxxxxx>, from vpci.c
+ */
+
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/spinlock.h>
+#include "pciback.h"
+
+/* There are at most 32 slots in a pci bus. */
+#define PCI_SLOT_MAX 32
+
+#define PCI_BUS_NBR 2
+
+struct slot_dev_data {
+ /* Access to dev_list must be protected by lock */
+ struct pci_dev *slots[PCI_BUS_NBR][PCI_SLOT_MAX];
+ spinlock_t lock;
+};
+
+struct pci_dev *pciback_get_pci_dev(struct pciback_device *pdev,
+ unsigned int domain, unsigned int bus,
+ unsigned int devfn)
+{
+ struct pci_dev *dev = NULL;
+ struct slot_dev_data *slot_dev = pdev->pci_dev_data;
+ unsigned long flags;
+
+ if (domain != 0 || PCI_FUNC(devfn) != 0)
+ return NULL;
+
+ if (PCI_SLOT(devfn) >= PCI_SLOT_MAX || bus >= PCI_BUS_NBR)
+ return NULL;
+
+ spin_lock_irqsave(&slot_dev->lock, flags);
+ dev = slot_dev->slots[bus][PCI_SLOT(devfn)];
+ spin_unlock_irqrestore(&slot_dev->lock, flags);
+
+ return dev;
+}
+
+int pciback_add_pci_dev(struct pciback_device *pdev, struct pci_dev *dev)
+{
+ int err = 0, slot, bus;
+ struct slot_dev_data *slot_dev = pdev->pci_dev_data;
+ unsigned long flags;
+
+ if ((dev->class >> 24) == PCI_BASE_CLASS_BRIDGE) {
+ err = -EFAULT;
+ xenbus_dev_fatal(pdev->xdev, err,
+ "Can't export bridges on the virtual PCI bus");
+ goto out;
+ }
+
+ spin_lock_irqsave(&slot_dev->lock, flags);
+
+ /* Assign to a new slot on the virtual PCI bus */
+ for (bus = 0; bus < PCI_BUS_NBR; bus++)
+ for (slot = 0; slot < PCI_SLOT_MAX; slot++) {
+ if (slot_dev->slots[bus][slot] == NULL) {
+ printk(KERN_INFO
+ "pciback: slot: %s: assign to virtual
slot %d, bus %d\n",
+ pci_name(dev), slot, bus);
+ slot_dev->slots[bus][slot] = dev;
+ goto unlock;
+ }
+ }
+
+ err = -ENOMEM;
+ xenbus_dev_fatal(pdev->xdev, err,
+ "No more space on root virtual PCI bus");
+
+ unlock:
+ spin_unlock_irqrestore(&slot_dev->lock, flags);
+ out:
+ return err;
+}
+
+void pciback_release_pci_dev(struct pciback_device *pdev, struct pci_dev *dev)
+{
+ int slot, bus;
+ struct slot_dev_data *slot_dev = pdev->pci_dev_data;
+ struct pci_dev *found_dev = NULL;
+ unsigned long flags;
+
+ spin_lock_irqsave(&slot_dev->lock, flags);
+
+ for (bus = 0; bus < PCI_BUS_NBR; bus++)
+ for (slot = 0; slot < PCI_SLOT_MAX; slot++) {
+ if (slot_dev->slots[bus][slot] == dev) {
+ slot_dev->slots[bus][slot] = NULL;
+ found_dev = dev;
+ goto out;
+ }
+ }
+
+ out:
+ spin_unlock_irqrestore(&slot_dev->lock, flags);
+
+ if (found_dev)
+ pcistub_put_pci_dev(found_dev);
+}
+
+int pciback_init_devices(struct pciback_device *pdev)
+{
+ int slot, bus;
+ struct slot_dev_data *slot_dev;
+
+ slot_dev = kmalloc(sizeof(*slot_dev), GFP_KERNEL);
+ if (!slot_dev)
+ return -ENOMEM;
+
+ spin_lock_init(&slot_dev->lock);
+
+ for (bus = 0; bus < PCI_BUS_NBR; bus++)
+ for (slot = 0; slot < PCI_SLOT_MAX; slot++)
+ slot_dev->slots[bus][slot] = NULL;
+
+ pdev->pci_dev_data = slot_dev;
+
+ return 0;
+}
+
+int pciback_publish_pci_roots(struct pciback_device *pdev,
+ publish_pci_root_cb publish_cb)
+{
+ /* The Virtual PCI bus has only one root */
+ return publish_cb(pdev, 0, 0);
+}
+
+void pciback_release_devices(struct pciback_device *pdev)
+{
+ int slot, bus;
+ struct slot_dev_data *slot_dev = pdev->pci_dev_data;
+ struct pci_dev *dev;
+
+ for (bus = 0; bus < PCI_BUS_NBR; bus++)
+ for (slot = 0; slot < PCI_SLOT_MAX; slot++) {
+ dev = slot_dev->slots[bus][slot];
+ if (dev != NULL)
+ pcistub_put_pci_dev(dev);
+ }
+
+ kfree(slot_dev);
+ pdev->pci_dev_data = NULL;
+}
diff -r e4f1519b473f -r b60ea69932b1 tools/ioemu/patches/vnc-display-find-unused
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/ioemu/patches/vnc-display-find-unused Wed Aug 09 18:04:20
2006 +0100
@@ -0,0 +1,128 @@
+Index: ioemu/vnc.c
+===================================================================
+--- ioemu.orig/vnc.c 2006-08-09 14:44:44.721942535 +0100
++++ ioemu/vnc.c 2006-08-09 14:52:37.262165292 +0100
+@@ -1183,7 +1183,7 @@
+ }
+ }
+
+-void vnc_display_init(DisplayState *ds, int display)
++int vnc_display_init(DisplayState *ds, int display, int find_unused)
+ {
+ struct sockaddr_in addr;
+ int reuse_addr, ret;
+@@ -1214,10 +1214,6 @@
+ exit(1);
+ }
+
+- addr.sin_family = AF_INET;
+- addr.sin_port = htons(5900 + display);
+- memset(&addr.sin_addr, 0, sizeof(addr.sin_addr));
+-
+ reuse_addr = 1;
+ ret = setsockopt(vs->lsock, SOL_SOCKET, SO_REUSEADDR,
+ (const char *)&reuse_addr, sizeof(reuse_addr));
+@@ -1226,7 +1222,16 @@
+ exit(1);
+ }
+
++ retry:
++ addr.sin_family = AF_INET;
++ addr.sin_port = htons(5900 + display);
++ memset(&addr.sin_addr, 0, sizeof(addr.sin_addr));
++
+ if (bind(vs->lsock, (struct sockaddr *)&addr, sizeof(addr)) == -1) {
++ if (find_unused && errno == EADDRINUSE) {
++ display++;
++ goto retry;
++ }
+ fprintf(stderr, "bind() failed\n");
+ exit(1);
+ }
+@@ -1247,6 +1252,8 @@
+ vs->ds->dpy_refresh = vnc_dpy_refresh;
+
+ vnc_dpy_resize(vs->ds, 640, 400);
++
++ return display;
+ }
+
+ int vnc_start_viewer(int port)
+Index: ioemu/vl.c
+===================================================================
+--- ioemu.orig/vl.c 2006-08-09 14:44:44.721942535 +0100
++++ ioemu/vl.c 2006-08-09 14:52:06.783905832 +0100
+@@ -121,6 +121,7 @@
+ static DisplayState display_state;
+ int nographic;
+ int vncviewer;
++int vncunused;
+ const char* keyboard_layout = NULL;
+ int64_t ticks_per_sec;
+ int boot_device = 'c';
+@@ -5342,6 +5343,7 @@
+ "-loadvm file start right away with a saved state (loadvm in
monitor)\n"
+ "-vnc display start a VNC server on display\n"
+ "-vncviewer start a vncviewer process for this domain\n"
++ "-vncunused bind the VNC server to an unused port\n"
+ "-timeoffset time offset (in seconds) from local time\n"
+ "-acpi disable or enable ACPI of HVM domain \n"
+ "\n"
+@@ -5431,6 +5433,7 @@
+ QEMU_OPTION_timeoffset,
+ QEMU_OPTION_acpi,
+ QEMU_OPTION_vncviewer,
++ QEMU_OPTION_vncunused,
+ };
+
+ typedef struct QEMUOption {
+@@ -5506,6 +5509,7 @@
+ { "smp", HAS_ARG, QEMU_OPTION_smp },
+ { "vnc", HAS_ARG, QEMU_OPTION_vnc },
+ { "vncviewer", 0, QEMU_OPTION_vncviewer },
++ { "vncunused", 0, QEMU_OPTION_vncunused },
+
+ /* temporary options */
+ { "usb", 0, QEMU_OPTION_usb },
+@@ -5873,6 +5877,7 @@
+ snapshot = 0;
+ nographic = 0;
+ vncviewer = 0;
++ vncunused = 0;
+ kernel_filename = NULL;
+ kernel_cmdline = "";
+ #ifdef TARGET_PPC
+@@ -6270,6 +6275,11 @@
+ case QEMU_OPTION_vncviewer:
+ vncviewer++;
+ break;
++ case QEMU_OPTION_vncunused:
++ vncunused++;
++ if (vnc_display == -1)
++ vnc_display = -2;
++ break;
+ }
+ }
+ }
+@@ -6465,7 +6475,7 @@
+ if (nographic) {
+ dumb_display_init(ds);
+ } else if (vnc_display != -1) {
+- vnc_display_init(ds, vnc_display);
++ vnc_display = vnc_display_init(ds, vnc_display, vncunused);
+ if (vncviewer)
+ vnc_start_viewer(vnc_display);
+ } else {
+Index: ioemu/vl.h
+===================================================================
+--- ioemu.orig/vl.h 2006-08-09 14:44:44.721942535 +0100
++++ ioemu/vl.h 2006-08-09 14:52:06.783905832 +0100
+@@ -784,7 +784,7 @@
+ void cocoa_display_init(DisplayState *ds, int full_screen);
+
+ /* vnc.c */
+-void vnc_display_init(DisplayState *ds, int display);
++int vnc_display_init(DisplayState *ds, int display, int find_unused);
+ int vnc_start_viewer(int port);
+
+ /* ide.c */
diff -r e4f1519b473f -r b60ea69932b1
tools/ioemu/patches/xen-support-buffered-ioreqs
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/ioemu/patches/xen-support-buffered-ioreqs Wed Aug 09 18:04:20
2006 +0100
@@ -0,0 +1,150 @@
+Index: ioemu/vl.c
+===================================================================
+--- ioemu.orig/vl.c 2006-08-09 15:04:25.583508863 +0100
++++ ioemu/vl.c 2006-08-09 15:04:26.034465993 +0100
+@@ -5838,6 +5838,7 @@
+ unsigned long nr_pages;
+ xen_pfn_t *page_array;
+ extern void *shared_page;
++ extern void *buffered_io_page;
+
+ char qemu_dm_logfilename[64];
+
+@@ -6388,12 +6389,17 @@
+
+ phys_ram_base = xc_map_foreign_batch(xc_handle, domid,
+ PROT_READ|PROT_WRITE, page_array,
+- nr_pages - 1);
++ nr_pages - 3);
+ if (phys_ram_base == 0) {
+ fprintf(logfile, "xc_map_foreign_batch returned error %d\n", errno);
+ exit(-1);
+ }
+
++ /* not yet add for IA64 */
++ buffered_io_page = xc_map_foreign_range(xc_handle, domid, PAGE_SIZE,
++ PROT_READ|PROT_WRITE,
++ page_array[nr_pages - 3]);
++
+ shared_page = xc_map_foreign_range(xc_handle, domid, PAGE_SIZE,
+ PROT_READ|PROT_WRITE,
+ page_array[nr_pages - 1]);
+Index: ioemu/target-i386-dm/helper2.c
+===================================================================
+--- ioemu.orig/target-i386-dm/helper2.c 2006-08-09 15:04:24.105649313
+0100
++++ ioemu/target-i386-dm/helper2.c 2006-08-09 15:04:26.040465422 +0100
+@@ -76,6 +76,10 @@
+
+ shared_iopage_t *shared_page = NULL;
+
++#define BUFFER_IO_MAX_DELAY 100
++buffered_iopage_t *buffered_io_page = NULL;
++QEMUTimer *buffered_io_timer;
++
+ /* the evtchn fd for polling */
+ int xce_handle = -1;
+
+@@ -419,36 +423,68 @@
+ req->u.data = tmp1;
+ }
+
++void __handle_ioreq(CPUState *env, ioreq_t *req)
++{
++ if (!req->pdata_valid && req->dir == IOREQ_WRITE && req->size != 4)
++ req->u.data &= (1UL << (8 * req->size)) - 1;
++
++ switch (req->type) {
++ case IOREQ_TYPE_PIO:
++ cpu_ioreq_pio(env, req);
++ break;
++ case IOREQ_TYPE_COPY:
++ cpu_ioreq_move(env, req);
++ break;
++ case IOREQ_TYPE_AND:
++ cpu_ioreq_and(env, req);
++ break;
++ case IOREQ_TYPE_OR:
++ cpu_ioreq_or(env, req);
++ break;
++ case IOREQ_TYPE_XOR:
++ cpu_ioreq_xor(env, req);
++ break;
++ default:
++ hw_error("Invalid ioreq type 0x%x\n", req->type);
++ }
++}
++
++void __handle_buffered_iopage(CPUState *env)
++{
++ ioreq_t *req = NULL;
++
++ if (!buffered_io_page)
++ return;
++
++ while (buffered_io_page->read_pointer !=
++ buffered_io_page->write_pointer) {
++ req = &buffered_io_page->ioreq[buffered_io_page->read_pointer %
++ IOREQ_BUFFER_SLOT_NUM];
++
++ __handle_ioreq(env, req);
++
++ mb();
++ buffered_io_page->read_pointer++;
++ }
++}
++
++void handle_buffered_io(void *opaque)
++{
++ CPUState *env = opaque;
++
++ __handle_buffered_iopage(env);
++ qemu_mod_timer(buffered_io_timer, BUFFER_IO_MAX_DELAY +
++ qemu_get_clock(rt_clock));
++}
++
+ void cpu_handle_ioreq(void *opaque)
+ {
+ CPUState *env = opaque;
+ ioreq_t *req = cpu_get_ioreq();
+
++ handle_buffered_io(env);
+ if (req) {
+- if ((!req->pdata_valid) && (req->dir == IOREQ_WRITE)) {
+- if (req->size != 4)
+- req->u.data &= (1UL << (8 * req->size))-1;
+- }
+-
+- switch (req->type) {
+- case IOREQ_TYPE_PIO:
+- cpu_ioreq_pio(env, req);
+- break;
+- case IOREQ_TYPE_COPY:
+- cpu_ioreq_move(env, req);
+- break;
+- case IOREQ_TYPE_AND:
+- cpu_ioreq_and(env, req);
+- break;
+- case IOREQ_TYPE_OR:
+- cpu_ioreq_or(env, req);
+- break;
+- case IOREQ_TYPE_XOR:
+- cpu_ioreq_xor(env, req);
+- break;
+- default:
+- hw_error("Invalid ioreq type 0x%x\n", req->type);
+- }
++ __handle_ioreq(env, req);
+
+ /* No state change if state = STATE_IORESP_HOOK */
+ if (req->state == STATE_IOREQ_INPROCESS) {
+@@ -466,6 +502,10 @@
+ CPUState *env = cpu_single_env;
+ int evtchn_fd = xc_evtchn_fd(xce_handle);
+
++ buffered_io_timer = qemu_new_timer(rt_clock, handle_buffered_io,
++ cpu_single_env);
++ qemu_mod_timer(buffered_io_timer, qemu_get_clock(rt_clock));
++
+ qemu_set_fd_handler(evtchn_fd, cpu_handle_ioreq, NULL, env);
+
+ env->send_event = 0;
diff -r e4f1519b473f -r b60ea69932b1 tools/python/xen/xend/tests/xend-config.sxp
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/python/xen/xend/tests/xend-config.sxp Wed Aug 09 18:04:20
2006 +0100
@@ -0,0 +1,132 @@
+# -*- sh -*-
+
+#
+# Xend configuration file.
+#
+
+# This example configuration is appropriate for an installation that
+# utilizes a bridged network configuration. Access to xend via http
+# is disabled.
+
+# Commented out entries show the default for that entry, unless otherwise
+# specified.
+
+#(logfile /var/log/xend.log)
+#(loglevel DEBUG)
+
+#(xend-http-server no)
+#(xend-unix-server no)
+#(xend-tcp-xmlrpc-server no)
+#(xend-unix-xmlrpc-server yes)
+#(xend-relocation-server no)
+(xend-relocation-server yes)
+
+#(xend-unix-path /var/lib/xend/xend-socket)
+
+# Port xend should use for the HTTP interface, if xend-http-server is set.
+#(xend-port 8000)
+
+# Port xend should use for the relocation interface, if xend-relocation-server
+# is set.
+#(xend-relocation-port 8002)
+
+# Address xend should listen on for HTTP connections, if xend-http-server is
+# set.
+# Specifying 'localhost' prevents remote connections.
+# Specifying the empty string '' (the default) allows all connections.
+#(xend-address '')
+#(xend-address localhost)
+
+# Address xend should listen on for relocation-socket connections, if
+# xend-relocation-server is set.
+# Meaning and default as for xend-address above.
+#(xend-relocation-address '')
+
+# The hosts allowed to talk to the relocation port. If this is empty (the
+# default), then all connections are allowed (assuming that the connection
+# arrives on a port and interface on which we are listening; see
+# xend-relocation-port and xend-relocation-address above). Otherwise, this
+# should be a space-separated sequence of regular expressions. Any host with
+# a fully-qualified domain name or an IP address that matches one of these
+# regular expressions will be accepted.
+#
+# For example:
+# (xend-relocation-hosts-allow '^localhost$ ^.*\\.example\\.org$')
+#
+#(xend-relocation-hosts-allow '')
+(xend-relocation-hosts-allow '^localhost$ ^localhost\\.localdomain$')
+
+# The limit (in kilobytes) on the size of the console buffer
+#(console-limit 1024)
+
+##
+# To bridge network traffic, like this:
+#
+# dom0: fake eth0 -> vif0.0 -+
+# |
+# bridge -> real eth0 -> the network
+# |
+# domU: fake eth0 -> vifN.0 -+
+#
+# use
+#
+# (network-script network-bridge)
+#
+# Your default ethernet device is used as the outgoing interface, by default.
+# To use a different one (e.g. eth1) use
+#
+# (network-script 'network-bridge netdev=eth1')
+#
+# The bridge is named xenbr0, by default. To rename the bridge, use
+#
+# (network-script 'network-bridge bridge=<name>')
+#
+# It is possible to use the network-bridge script in more complicated
+# scenarios, such as having two outgoing interfaces, with two bridges, and
+# two fake interfaces per guest domain. To do things like this, write
+# yourself a wrapper script, and call network-bridge from it, as appropriate.
+#
+(network-script network-bridge)
+
+# The script used to control virtual interfaces. This can be overridden on a
+# per-vif basis when creating a domain or a configuring a new vif. The
+# vif-bridge script is designed for use with the network-bridge script, or
+# similar configurations.
+#
+# If you have overridden the bridge name using
+# (network-script 'network-bridge bridge=<name>') then you may wish to do the
+# same here. The bridge name can also be set when creating a domain or
+# configuring a new vif, but a value specified here would act as a default.
+#
+# If you are using only one bridge, the vif-bridge script will discover that,
+# so there is no need to specify it explicitly.
+#
+(vif-script vif-bridge)
+
+
+## Use the following if network traffic is routed, as an alternative to the
+# settings for bridged networking given above.
+#(network-script network-route)
+#(vif-script vif-route)
+
+
+## Use the following if network traffic is routed with NAT, as an alternative
+# to the settings for bridged networking given above.
+#(network-script network-nat)
+#(vif-script vif-nat)
+
+
+# Dom0 will balloon out when needed to free memory for domU.
+# dom0-min-mem is the lowest memory level (in MB) dom0 will get down to.
+# If dom0-min-mem=0, dom0 will never balloon out.
+(dom0-min-mem 196)
+
+# In SMP system, dom0 will use dom0-cpus # of CPUS
+# If dom0-cpus = 0, dom0 will take all cpus available
+(dom0-cpus 0)
+
+# Whether to enable core-dumps when domains crash.
+#(enable-dump no)
+
+# The tool used for initiating virtual TPM migration
+#(external-migration-tool '')
_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-changelog
|
Home