summaryrefslogtreecommitdiffstats
path: root/drivers/xen
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/xen')
-rw-r--r--drivers/xen/Kconfig24
-rw-r--r--drivers/xen/Makefile2
-rw-r--r--drivers/xen/acpi.c62
-rw-r--r--drivers/xen/events.c7
-rw-r--r--drivers/xen/gntdev.c2
-rw-r--r--drivers/xen/grant-table.c138
-rw-r--r--drivers/xen/manage.c1
-rw-r--r--drivers/xen/xen-acpi-processor.c6
-rw-r--r--drivers/xen/xen-selfballoon.c34
-rw-r--r--drivers/xen/xenbus/xenbus_comms.c6
-rw-r--r--drivers/xen/xenbus/xenbus_comms.h1
-rw-r--r--drivers/xen/xenbus/xenbus_dev_backend.c51
-rw-r--r--drivers/xen/xenbus/xenbus_probe_frontend.c69
13 files changed, 355 insertions, 48 deletions
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 94243136f6bf..8d2501e604dd 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -71,7 +71,7 @@ config XEN_DEV_EVTCHN
tristate "Xen /dev/xen/evtchn device"
default y
help
- The evtchn driver allows a userspace process to triger event
+ The evtchn driver allows a userspace process to trigger event
channels and to receive notification of an event channel
firing.
If in doubt, say yes.
@@ -183,15 +183,17 @@ config XEN_ACPI_PROCESSOR
depends on XEN && X86 && ACPI_PROCESSOR && CPU_FREQ
default m
help
- This ACPI processor uploads Power Management information to the Xen hypervisor.
-
- To do that the driver parses the Power Management data and uploads said
- information to the Xen hypervisor. Then the Xen hypervisor can select the
- proper Cx and Pxx states. It also registers itslef as the SMM so that
- other drivers (such as ACPI cpufreq scaling driver) will not load.
-
- To compile this driver as a module, choose M here: the
- module will be called xen_acpi_processor If you do not know what to choose,
- select M here. If the CPUFREQ drivers are built in, select Y here.
+ This ACPI processor uploads Power Management information to the Xen
+ hypervisor.
+
+ To do that the driver parses the Power Management data and uploads
+ said information to the Xen hypervisor. Then the Xen hypervisor can
+ select the proper Cx and Pxx states. It also registers itslef as the
+ SMM so that other drivers (such as ACPI cpufreq scaling driver) will
+ not load.
+
+ To compile this driver as a module, choose M here: the module will be
+ called xen_acpi_processor If you do not know what to choose, select
+ M here. If the CPUFREQ drivers are built in, select Y here.
endmenu
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 9adc5be57b13..fc3488631136 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -17,7 +17,7 @@ obj-$(CONFIG_XEN_SYS_HYPERVISOR) += sys-hypervisor.o
obj-$(CONFIG_XEN_PVHVM) += platform-pci.o
obj-$(CONFIG_XEN_TMEM) += tmem.o
obj-$(CONFIG_SWIOTLB_XEN) += swiotlb-xen.o
-obj-$(CONFIG_XEN_DOM0) += pci.o
+obj-$(CONFIG_XEN_DOM0) += pci.o acpi.o
obj-$(CONFIG_XEN_PCIDEV_BACKEND) += xen-pciback/
obj-$(CONFIG_XEN_PRIVCMD) += xen-privcmd.o
obj-$(CONFIG_XEN_ACPI_PROCESSOR) += xen-acpi-processor.o
diff --git a/drivers/xen/acpi.c b/drivers/xen/acpi.c
new file mode 100644
index 000000000000..119d42a2bf57
--- /dev/null
+++ b/drivers/xen/acpi.c
@@ -0,0 +1,62 @@
+/******************************************************************************
+ * acpi.c
+ * acpi file for domain 0 kernel
+ *
+ * Copyright (c) 2011 Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+ * Copyright (c) 2011 Yu Ke ke.yu@intel.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <xen/acpi.h>
+#include <xen/interface/platform.h>
+#include <asm/xen/hypercall.h>
+#include <asm/xen/hypervisor.h>
+
+int xen_acpi_notify_hypervisor_state(u8 sleep_state,
+ u32 pm1a_cnt, u32 pm1b_cnt)
+{
+ struct xen_platform_op op = {
+ .cmd = XENPF_enter_acpi_sleep,
+ .interface_version = XENPF_INTERFACE_VERSION,
+ .u = {
+ .enter_acpi_sleep = {
+ .pm1a_cnt_val = (u16)pm1a_cnt,
+ .pm1b_cnt_val = (u16)pm1b_cnt,
+ .sleep_state = sleep_state,
+ },
+ },
+ };
+
+ if ((pm1a_cnt & 0xffff0000) || (pm1b_cnt & 0xffff0000)) {
+ WARN(1, "Using more than 16bits of PM1A/B 0x%x/0x%x!"
+ "Email xen-devel@lists.xensource.com Thank you.\n", \
+ pm1a_cnt, pm1b_cnt);
+ return -1;
+ }
+
+ HYPERVISOR_dom0_op(&op);
+ return 1;
+}
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 4b33acd8ed4e..6908e4ce2a0d 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -274,7 +274,7 @@ static unsigned int cpu_from_evtchn(unsigned int evtchn)
static bool pirq_check_eoi_map(unsigned irq)
{
- return test_bit(irq, pirq_eoi_map);
+ return test_bit(pirq_from_irq(irq), pirq_eoi_map);
}
static bool pirq_needs_eoi_flag(unsigned irq)
@@ -611,7 +611,7 @@ static void disable_pirq(struct irq_data *data)
disable_dynirq(data);
}
-static int find_irq_by_gsi(unsigned gsi)
+int xen_irq_from_gsi(unsigned gsi)
{
struct irq_info *info;
@@ -625,6 +625,7 @@ static int find_irq_by_gsi(unsigned gsi)
return -1;
}
+EXPORT_SYMBOL_GPL(xen_irq_from_gsi);
/*
* Do not make any assumptions regarding the relationship between the
@@ -644,7 +645,7 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
mutex_lock(&irq_mapping_update_lock);
- irq = find_irq_by_gsi(gsi);
+ irq = xen_irq_from_gsi(gsi);
if (irq != -1) {
printk(KERN_INFO "xen_map_pirq_gsi: returning irq %d for gsi %u\n",
irq, gsi);
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 99d8151c824a..1ffd03bf8e10 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -722,7 +722,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
vma->vm_flags |= VM_RESERVED|VM_DONTEXPAND;
if (use_ptemod)
- vma->vm_flags |= VM_DONTCOPY|VM_PFNMAP;
+ vma->vm_flags |= VM_DONTCOPY;
vma->vm_private_data = map;
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index b4d4eac761db..0bfc1ef11259 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -38,6 +38,7 @@
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
#include <linux/io.h>
+#include <linux/hardirq.h>
#include <xen/xen.h>
#include <xen/interface/xen.h>
@@ -426,10 +427,8 @@ static int gnttab_end_foreign_access_ref_v1(grant_ref_t ref, int readonly)
nflags = *pflags;
do {
flags = nflags;
- if (flags & (GTF_reading|GTF_writing)) {
- printk(KERN_ALERT "WARNING: g.e. still in use!\n");
+ if (flags & (GTF_reading|GTF_writing))
return 0;
- }
} while ((nflags = sync_cmpxchg(pflags, flags, 0)) != flags);
return 1;
@@ -458,12 +457,103 @@ static int gnttab_end_foreign_access_ref_v2(grant_ref_t ref, int readonly)
return 1;
}
-int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly)
+static inline int _gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly)
{
return gnttab_interface->end_foreign_access_ref(ref, readonly);
}
+
+int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly)
+{
+ if (_gnttab_end_foreign_access_ref(ref, readonly))
+ return 1;
+ pr_warn("WARNING: g.e. %#x still in use!\n", ref);
+ return 0;
+}
EXPORT_SYMBOL_GPL(gnttab_end_foreign_access_ref);
+struct deferred_entry {
+ struct list_head list;
+ grant_ref_t ref;
+ bool ro;
+ uint16_t warn_delay;
+ struct page *page;
+};
+static LIST_HEAD(deferred_list);
+static void gnttab_handle_deferred(unsigned long);
+static DEFINE_TIMER(deferred_timer, gnttab_handle_deferred, 0, 0);
+
+static void gnttab_handle_deferred(unsigned long unused)
+{
+ unsigned int nr = 10;
+ struct deferred_entry *first = NULL;
+ unsigned long flags;
+
+ spin_lock_irqsave(&gnttab_list_lock, flags);
+ while (nr--) {
+ struct deferred_entry *entry
+ = list_first_entry(&deferred_list,
+ struct deferred_entry, list);
+
+ if (entry == first)
+ break;
+ list_del(&entry->list);
+ spin_unlock_irqrestore(&gnttab_list_lock, flags);
+ if (_gnttab_end_foreign_access_ref(entry->ref, entry->ro)) {
+ put_free_entry(entry->ref);
+ if (entry->page) {
+ pr_debug("freeing g.e. %#x (pfn %#lx)\n",
+ entry->ref, page_to_pfn(entry->page));
+ __free_page(entry->page);
+ } else
+ pr_info("freeing g.e. %#x\n", entry->ref);
+ kfree(entry);
+ entry = NULL;
+ } else {
+ if (!--entry->warn_delay)
+ pr_info("g.e. %#x still pending\n",
+ entry->ref);
+ if (!first)
+ first = entry;
+ }
+ spin_lock_irqsave(&gnttab_list_lock, flags);
+ if (entry)
+ list_add_tail(&entry->list, &deferred_list);
+ else if (list_empty(&deferred_list))
+ break;
+ }
+ if (!list_empty(&deferred_list) && !timer_pending(&deferred_timer)) {
+ deferred_timer.expires = jiffies + HZ;
+ add_timer(&deferred_timer);
+ }
+ spin_unlock_irqrestore(&gnttab_list_lock, flags);
+}
+
+static void gnttab_add_deferred(grant_ref_t ref, bool readonly,
+ struct page *page)
+{
+ struct deferred_entry *entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+ const char *what = KERN_WARNING "leaking";
+
+ if (entry) {
+ unsigned long flags;
+
+ entry->ref = ref;
+ entry->ro = readonly;
+ entry->page = page;
+ entry->warn_delay = 60;
+ spin_lock_irqsave(&gnttab_list_lock, flags);
+ list_add_tail(&entry->list, &deferred_list);
+ if (!timer_pending(&deferred_timer)) {
+ deferred_timer.expires = jiffies + HZ;
+ add_timer(&deferred_timer);
+ }
+ spin_unlock_irqrestore(&gnttab_list_lock, flags);
+ what = KERN_DEBUG "deferring";
+ }
+ printk("%s g.e. %#x (pfn %#lx)\n",
+ what, ref, page ? page_to_pfn(page) : -1);
+}
+
void gnttab_end_foreign_access(grant_ref_t ref, int readonly,
unsigned long page)
{
@@ -471,12 +561,9 @@ void gnttab_end_foreign_access(grant_ref_t ref, int readonly,
put_free_entry(ref);
if (page != 0)
free_page(page);
- } else {
- /* XXX This needs to be fixed so that the ref and page are
- placed on a list to be freed up later. */
- printk(KERN_WARNING
- "WARNING: leaking g.e. and page still in use!\n");
- }
+ } else
+ gnttab_add_deferred(ref, readonly,
+ page ? virt_to_page(page) : NULL);
}
EXPORT_SYMBOL_GPL(gnttab_end_foreign_access);
@@ -741,6 +828,7 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
struct page **pages, unsigned int count)
{
int i, ret;
+ bool lazy = false;
pte_t *pte;
unsigned long mfn;
@@ -751,6 +839,11 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
if (xen_feature(XENFEAT_auto_translated_physmap))
return ret;
+ if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
+ arch_enter_lazy_mmu_mode();
+ lazy = true;
+ }
+
for (i = 0; i < count; i++) {
/* Do not add to override if the map failed. */
if (map_ops[i].status)
@@ -769,6 +862,9 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
return ret;
}
+ if (lazy)
+ arch_leave_lazy_mmu_mode();
+
return ret;
}
EXPORT_SYMBOL_GPL(gnttab_map_refs);
@@ -777,6 +873,7 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
struct page **pages, unsigned int count, bool clear_pte)
{
int i, ret;
+ bool lazy = false;
ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap_ops, count);
if (ret)
@@ -785,12 +882,20 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
if (xen_feature(XENFEAT_auto_translated_physmap))
return ret;
+ if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
+ arch_enter_lazy_mmu_mode();
+ lazy = true;
+ }
+
for (i = 0; i < count; i++) {
ret = m2p_remove_override(pages[i], clear_pte);
if (ret)
return ret;
}
+ if (lazy)
+ arch_leave_lazy_mmu_mode();
+
return ret;
}
EXPORT_SYMBOL_GPL(gnttab_unmap_refs);
@@ -1029,6 +1134,7 @@ int gnttab_init(void)
int i;
unsigned int max_nr_glist_frames, nr_glist_frames;
unsigned int nr_init_grefs;
+ int ret;
nr_grant_frames = 1;
boot_max_nr_grant_frames = __max_nr_grant_frames();
@@ -1047,12 +1153,16 @@ int gnttab_init(void)
nr_glist_frames = (nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) / RPP;
for (i = 0; i < nr_glist_frames; i++) {
gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_KERNEL);
- if (gnttab_list[i] == NULL)
+ if (gnttab_list[i] == NULL) {
+ ret = -ENOMEM;
goto ini_nomem;
+ }
}
- if (gnttab_resume() < 0)
- return -ENODEV;
+ if (gnttab_resume() < 0) {
+ ret = -ENODEV;
+ goto ini_nomem;
+ }
nr_init_grefs = nr_grant_frames * GREFS_PER_GRANT_FRAME;
@@ -1070,7 +1180,7 @@ int gnttab_init(void)
for (i--; i >= 0; i--)
free_page((unsigned long)gnttab_list[i]);
kfree(gnttab_list);
- return -ENOMEM;
+ return ret;
}
EXPORT_SYMBOL_GPL(gnttab_init);
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 9e14ae6cd49c..412b96cc5305 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -132,6 +132,7 @@ static void do_suspend(void)
err = dpm_suspend_end(PMSG_FREEZE);
if (err) {
printk(KERN_ERR "dpm_suspend_end failed: %d\n", err);
+ si.cancelled = 0;
goto out_resume;
}
diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c
index 174b5653cd8a..7ff2569e17ae 100644
--- a/drivers/xen/xen-acpi-processor.c
+++ b/drivers/xen/xen-acpi-processor.c
@@ -29,6 +29,7 @@
#include <acpi/acpi_drivers.h>
#include <acpi/processor.h>
+#include <xen/xen.h>
#include <xen/interface/platform.h>
#include <asm/xen/hypercall.h>
@@ -128,7 +129,10 @@ static int push_cxx_to_hypervisor(struct acpi_processor *_pr)
pr_debug(" C%d: %s %d uS\n",
cx->type, cx->desc, (u32)cx->latency);
}
- } else
+ } else if (ret != -EINVAL)
+ /* EINVAL means the ACPI ID is incorrect - meaning the ACPI
+ * table is referencing a non-existing CPU - which can happen
+ * with broken ACPI tables. */
pr_err(DRV_NAME "(CX): Hypervisor error (%d) for ACPI CPU%u\n",
ret, _pr->acpi_id);
diff --git a/drivers/xen/xen-selfballoon.c b/drivers/xen/xen-selfballoon.c
index 146c94897016..7d041cb6da26 100644
--- a/drivers/xen/xen-selfballoon.c
+++ b/drivers/xen/xen-selfballoon.c
@@ -105,6 +105,12 @@ static unsigned int selfballoon_interval __read_mostly = 5;
*/
static unsigned int selfballoon_min_usable_mb;
+/*
+ * Amount of RAM in MB to add to the target number of pages.
+ * Can be used to reserve some more room for caches and the like.
+ */
+static unsigned int selfballoon_reserved_mb;
+
static void selfballoon_process(struct work_struct *work);
static DECLARE_DELAYED_WORK(selfballoon_worker, selfballoon_process);
@@ -217,7 +223,8 @@ static void selfballoon_process(struct work_struct *work)
cur_pages = totalram_pages;
tgt_pages = cur_pages; /* default is no change */
goal_pages = percpu_counter_read_positive(&vm_committed_as) +
- totalreserve_pages;
+ totalreserve_pages +
+ MB2PAGES(selfballoon_reserved_mb);
#ifdef CONFIG_FRONTSWAP
/* allow space for frontswap pages to be repatriated */
if (frontswap_selfshrinking && frontswap_enabled)
@@ -397,6 +404,30 @@ static DEVICE_ATTR(selfballoon_min_usable_mb, S_IRUGO | S_IWUSR,
show_selfballoon_min_usable_mb,
store_selfballoon_min_usable_mb);
+SELFBALLOON_SHOW(selfballoon_reserved_mb, "%d\n",
+ selfballoon_reserved_mb);
+
+static ssize_t store_selfballoon_reserved_mb(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ unsigned long val;
+ int err;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ err = strict_strtoul(buf, 10, &val);
+ if (err || val == 0)
+ return -EINVAL;
+ selfballoon_reserved_mb = val;
+ return count;
+}
+
+static DEVICE_ATTR(selfballoon_reserved_mb, S_IRUGO | S_IWUSR,
+ show_selfballoon_reserved_mb,
+ store_selfballoon_reserved_mb);
+
#ifdef CONFIG_FRONTSWAP
SELFBALLOON_SHOW(frontswap_selfshrinking, "%d\n", frontswap_selfshrinking);
@@ -480,6 +511,7 @@ static struct attribute *selfballoon_attrs[] = {
&dev_attr_selfballoon_downhysteresis.attr,
&dev_attr_selfballoon_uphysteresis.attr,
&dev_attr_selfballoon_min_usable_mb.attr,
+ &dev_attr_selfballoon_reserved_mb.attr,
#ifdef CONFIG_FRONTSWAP
&dev_attr_frontswap_selfshrinking.attr,
&dev_attr_frontswap_hysteresis.attr,
diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c
index 2eff7a6aaa20..52fe7ad07666 100644
--- a/drivers/xen/xenbus/xenbus_comms.c
+++ b/drivers/xen/xenbus/xenbus_comms.c
@@ -234,3 +234,9 @@ int xb_init_comms(void)
return 0;
}
+
+void xb_deinit_comms(void)
+{
+ unbind_from_irqhandler(xenbus_irq, &xb_waitq);
+ xenbus_irq = 0;
+}
diff --git a/drivers/xen/xenbus/xenbus_comms.h b/drivers/xen/xenbus/xenbus_comms.h
index 6e42800fa499..c8abd3b8a6c4 100644
--- a/drivers/xen/xenbus/xenbus_comms.h
+++ b/drivers/xen/xenbus/xenbus_comms.h
@@ -35,6 +35,7 @@
int xs_init(void);
int xb_init_comms(void);
+void xb_deinit_comms(void);
/* Low level routines. */
int xb_write(const void *data, unsigned len);
diff --git a/drivers/xen/xenbus/xenbus_dev_backend.c b/drivers/xen/xenbus/xenbus_dev_backend.c
index 3d3be78c1093..be738c43104b 100644
--- a/drivers/xen/xenbus/xenbus_dev_backend.c
+++ b/drivers/xen/xenbus/xenbus_dev_backend.c
@@ -8,7 +8,11 @@
#include <xen/xen.h>
#include <xen/page.h>
+#include <xen/xenbus.h>
#include <xen/xenbus_dev.h>
+#include <xen/grant_table.h>
+#include <xen/events.h>
+#include <asm/xen/hypervisor.h>
#include "xenbus_comms.h"
@@ -22,6 +26,50 @@ static int xenbus_backend_open(struct inode *inode, struct file *filp)
return nonseekable_open(inode, filp);
}
+static long xenbus_alloc(domid_t domid)
+{
+ struct evtchn_alloc_unbound arg;
+ int err = -EEXIST;
+
+ xs_suspend();
+
+ /* If xenstored_ready is nonzero, that means we have already talked to
+ * xenstore and set up watches. These watches will be restored by
+ * xs_resume, but that requires communication over the port established
+ * below that is not visible to anyone until the ioctl returns.
+ *
+ * This can be resolved by splitting the ioctl into two parts
+ * (postponing the resume until xenstored is active) but this is
+ * unnecessarily complex for the intended use where xenstored is only
+ * started once - so return -EEXIST if it's already running.
+ */
+ if (xenstored_ready)
+ goto out_err;
+
+ gnttab_grant_foreign_access_ref(GNTTAB_RESERVED_XENSTORE, domid,
+ virt_to_mfn(xen_store_interface), 0 /* writable */);
+
+ arg.dom = DOMID_SELF;
+ arg.remote_dom = domid;
+
+ err = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound, &arg);
+ if (err)
+ goto out_err;
+
+ if (xen_store_evtchn > 0)
+ xb_deinit_comms();
+
+ xen_store_evtchn = arg.port;
+
+ xs_resume();
+
+ return arg.port;
+
+ out_err:
+ xs_suspend_cancel();
+ return err;
+}
+
static long xenbus_backend_ioctl(struct file *file, unsigned int cmd, unsigned long data)
{
if (!capable(CAP_SYS_ADMIN))
@@ -33,6 +81,9 @@ static long xenbus_backend_ioctl(struct file *file, unsigned int cmd, unsigned l
return xen_store_evtchn;
return -ENODEV;
+ case IOCTL_XENBUS_BACKEND_SETUP:
+ return xenbus_alloc(data);
+
default:
return -ENOTTY;
}
diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c
index f20c5f178b40..a31b54d48839 100644
--- a/drivers/xen/xenbus/xenbus_probe_frontend.c
+++ b/drivers/xen/xenbus/xenbus_probe_frontend.c
@@ -135,7 +135,7 @@ static int read_backend_details(struct xenbus_device *xendev)
return xenbus_read_otherend_details(xendev, "backend-id", "backend");
}
-static int is_device_connecting(struct device *dev, void *data)
+static int is_device_connecting(struct device *dev, void *data, bool ignore_nonessential)
{
struct xenbus_device *xendev = to_xenbus_device(dev);
struct device_driver *drv = data;
@@ -152,16 +152,41 @@ static int is_device_connecting(struct device *dev, void *data)
if (drv && (dev->driver != drv))
return 0;
+ if (ignore_nonessential) {
+ /* With older QEMU, for PVonHVM guests the guest config files
+ * could contain: vfb = [ 'vnc=1, vnclisten=0.0.0.0']
+ * which is nonsensical as there is no PV FB (there can be
+ * a PVKB) running as HVM guest. */
+
+ if ((strncmp(xendev->nodename, "device/vkbd", 11) == 0))
+ return 0;
+
+ if ((strncmp(xendev->nodename, "device/vfb", 10) == 0))
+ return 0;
+ }
xendrv = to_xenbus_driver(dev->driver);
return (xendev->state < XenbusStateConnected ||
(xendev->state == XenbusStateConnected &&
xendrv->is_ready && !xendrv->is_ready(xendev)));
}
+static int essential_device_connecting(struct device *dev, void *data)
+{
+ return is_device_connecting(dev, data, true /* ignore PV[KBB+FB] */);
+}
+static int non_essential_device_connecting(struct device *dev, void *data)
+{
+ return is_device_connecting(dev, data, false);
+}
-static int exists_connecting_device(struct device_driver *drv)
+static int exists_essential_connecting_device(struct device_driver *drv)
{
return bus_for_each_dev(&xenbus_frontend.bus, NULL, drv,
- is_device_connecting);
+ essential_device_connecting);
+}
+static int exists_non_essential_connecting_device(struct device_driver *drv)
+{
+ return bus_for_each_dev(&xenbus_frontend.bus, NULL, drv,
+ non_essential_device_connecting);
}
static int print_device_status(struct device *dev, void *data)
@@ -192,6 +217,23 @@ static int print_device_status(struct device *dev, void *data)
/* We only wait for device setup after most initcalls have run. */
static int ready_to_wait_for_devices;
+static bool wait_loop(unsigned long start, unsigned int max_delay,
+ unsigned int *seconds_waited)
+{
+ if (time_after(jiffies, start + (*seconds_waited+5)*HZ)) {
+ if (!*seconds_waited)
+ printk(KERN_WARNING "XENBUS: Waiting for "
+ "devices to initialise: ");
+ *seconds_waited += 5;
+ printk("%us...", max_delay - *seconds_waited);
+ if (*seconds_waited == max_delay)
+ return true;
+ }
+
+ schedule_timeout_interruptible(HZ/10);
+
+ return false;
+}
/*
* On a 5-minute timeout, wait for all devices currently configured. We need
* to do this to guarantee that the filesystems and / or network devices
@@ -215,19 +257,14 @@ static void wait_for_devices(struct xenbus_driver *xendrv)
if (!ready_to_wait_for_devices || !xen_domain())
return;
- while (exists_connecting_device(drv)) {
- if (time_after(jiffies, start + (seconds_waited+5)*HZ)) {
- if (!seconds_waited)
- printk(KERN_WARNING "XENBUS: Waiting for "
- "devices to initialise: ");
- seconds_waited += 5;
- printk("%us...", 300 - seconds_waited);
- if (seconds_waited == 300)
- break;
- }
-
- schedule_timeout_interruptible(HZ/10);
- }
+ while (exists_non_essential_connecting_device(drv))
+ if (wait_loop(start, 30, &seconds_waited))
+ break;
+
+ /* Skips PVKB and PVFB check.*/
+ while (exists_essential_connecting_device(drv))
+ if (wait_loop(start, 270, &seconds_waited))
+ break;
if (seconds_waited)
printk("\n");
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-22 21:36:16 +0100