summaryrefslogtreecommitdiffstats
path: root/drivers/xen
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/xen')
-rw-r--r--drivers/xen/events/events_base.c17
-rw-r--r--drivers/xen/events/events_fifo.c41
-rw-r--r--drivers/xen/manage.c77
-rw-r--r--drivers/xen/xen-acpi-processor.c4
-rw-r--r--drivers/xen/xen-pciback/pci_stub.c25
-rw-r--r--drivers/xen/xen-pciback/pciback_ops.c7
-rw-r--r--drivers/xen/xen-pciback/vpci.c2
-rw-r--r--drivers/xen/xen-pciback/xenbus.c4
-rw-r--r--drivers/xen/xenbus/xenbus_xs.c44
9 files changed, 141 insertions, 80 deletions
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index dfa12a4a0a4..c919d3d5c84 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -390,22 +390,7 @@ static void xen_irq_init(unsigned irq)
static int __must_check xen_allocate_irqs_dynamic(int nvec)
{
- int first = 0;
- int i, irq;
-
-#ifdef CONFIG_X86_IO_APIC
- /*
- * For an HVM guest or domain 0 which see "real" (emulated or
- * actual respectively) GSIs we allocate dynamic IRQs
- * e.g. those corresponding to event channels or MSIs
- * etc. from the range above those "real" GSIs to avoid
- * collisions.
- */
- if (xen_initial_domain() || xen_hvm_domain())
- first = get_nr_irqs_gsi();
-#endif
-
- irq = irq_alloc_descs_from(first, nvec, -1);
+ int i, irq = irq_alloc_descs(-1, 0, nvec, -1);
if (irq >= 0) {
for (i = 0; i < nvec; i++)
diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index 96109a9972b..84b4bfb8434 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -66,7 +66,22 @@ static DEFINE_PER_CPU(struct evtchn_fifo_queue, cpu_queue);
static event_word_t *event_array[MAX_EVENT_ARRAY_PAGES] __read_mostly;
static unsigned event_array_pages __read_mostly;
+/*
+ * sync_set_bit() and friends must be unsigned long aligned on non-x86
+ * platforms.
+ */
+#if !defined(CONFIG_X86) && BITS_PER_LONG > 32
+
+#define BM(w) (unsigned long *)((unsigned long)w & ~0x7UL)
+#define EVTCHN_FIFO_BIT(b, w) \
+ (((unsigned long)w & 0x4UL) ? (EVTCHN_FIFO_ ##b + 32) : EVTCHN_FIFO_ ##b)
+
+#else
+
#define BM(w) ((unsigned long *)(w))
+#define EVTCHN_FIFO_BIT(b, w) EVTCHN_FIFO_ ##b
+
+#endif
static inline event_word_t *event_word_from_port(unsigned port)
{
@@ -161,33 +176,38 @@ static void evtchn_fifo_bind_to_cpu(struct irq_info *info, unsigned cpu)
static void evtchn_fifo_clear_pending(unsigned port)
{
event_word_t *word = event_word_from_port(port);
- sync_clear_bit(EVTCHN_FIFO_PENDING, BM(word));
+ sync_clear_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
}
static void evtchn_fifo_set_pending(unsigned port)
{
event_word_t *word = event_word_from_port(port);
- sync_set_bit(EVTCHN_FIFO_PENDING, BM(word));
+ sync_set_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
}
static bool evtchn_fifo_is_pending(unsigned port)
{
event_word_t *word = event_word_from_port(port);
- return sync_test_bit(EVTCHN_FIFO_PENDING, BM(word));
+ return sync_test_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
}
static bool evtchn_fifo_test_and_set_mask(unsigned port)
{
event_word_t *word = event_word_from_port(port);
- return sync_test_and_set_bit(EVTCHN_FIFO_MASKED, BM(word));
+ return sync_test_and_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
}
static void evtchn_fifo_mask(unsigned port)
{
event_word_t *word = event_word_from_port(port);
- sync_set_bit(EVTCHN_FIFO_MASKED, BM(word));
+ sync_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
}
+static bool evtchn_fifo_is_masked(unsigned port)
+{
+ event_word_t *word = event_word_from_port(port);
+ return sync_test_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
+}
/*
* Clear MASKED, spinning if BUSY is set.
*/
@@ -211,7 +231,7 @@ static void evtchn_fifo_unmask(unsigned port)
BUG_ON(!irqs_disabled());
clear_masked(word);
- if (sync_test_bit(EVTCHN_FIFO_PENDING, BM(word))) {
+ if (evtchn_fifo_is_pending(port)) {
struct evtchn_unmask unmask = { .port = port };
(void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask);
}
@@ -243,7 +263,7 @@ static void handle_irq_for_port(unsigned port)
static void consume_one_event(unsigned cpu,
struct evtchn_fifo_control_block *control_block,
- unsigned priority, uint32_t *ready)
+ unsigned priority, unsigned long *ready)
{
struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu);
uint32_t head;
@@ -273,10 +293,9 @@ static void consume_one_event(unsigned cpu,
* copy of the ready word.
*/
if (head == 0)
- clear_bit(priority, BM(ready));
+ clear_bit(priority, ready);
- if (sync_test_bit(EVTCHN_FIFO_PENDING, BM(word))
- && !sync_test_bit(EVTCHN_FIFO_MASKED, BM(word)))
+ if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port))
handle_irq_for_port(port);
q->head[priority] = head;
@@ -285,7 +304,7 @@ static void consume_one_event(unsigned cpu,
static void evtchn_fifo_handle_events(unsigned cpu)
{
struct evtchn_fifo_control_block *control_block;
- uint32_t ready;
+ unsigned long ready;
unsigned q;
control_block = per_cpu(cpu_control_block, cpu);
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index fc6c94c0b43..c3667b202f2 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -41,9 +41,6 @@ static enum shutdown_state shutting_down = SHUTDOWN_INVALID;
struct suspend_info {
int cancelled;
- unsigned long arg; /* extra hypercall argument */
- void (*pre)(void);
- void (*post)(int cancelled);
};
static RAW_NOTIFIER_HEAD(xen_resume_notifier);
@@ -61,26 +58,6 @@ void xen_resume_notifier_unregister(struct notifier_block *nb)
EXPORT_SYMBOL_GPL(xen_resume_notifier_unregister);
#ifdef CONFIG_HIBERNATE_CALLBACKS
-static void xen_hvm_post_suspend(int cancelled)
-{
- xen_arch_hvm_post_suspend(cancelled);
- gnttab_resume();
-}
-
-static void xen_pre_suspend(void)
-{
- xen_mm_pin_all();
- gnttab_suspend();
- xen_arch_pre_suspend();
-}
-
-static void xen_post_suspend(int cancelled)
-{
- xen_arch_post_suspend(cancelled);
- gnttab_resume();
- xen_mm_unpin_all();
-}
-
static int xen_suspend(void *data)
{
struct suspend_info *si = data;
@@ -94,18 +71,20 @@ static int xen_suspend(void *data)
return err;
}
- if (si->pre)
- si->pre();
+ gnttab_suspend();
+ xen_arch_pre_suspend();
/*
* This hypercall returns 1 if suspend was cancelled
* or the domain was merely checkpointed, and 0 if it
* is resuming in a new domain.
*/
- si->cancelled = HYPERVISOR_suspend(si->arg);
+ si->cancelled = HYPERVISOR_suspend(xen_pv_domain()
+ ? virt_to_mfn(xen_start_info)
+ : 0);
- if (si->post)
- si->post(si->cancelled);
+ xen_arch_post_suspend(si->cancelled);
+ gnttab_resume();
if (!si->cancelled) {
xen_irq_resume();
@@ -154,16 +133,6 @@ static void do_suspend(void)
si.cancelled = 1;
- if (xen_hvm_domain()) {
- si.arg = 0UL;
- si.pre = NULL;
- si.post = &xen_hvm_post_suspend;
- } else {
- si.arg = virt_to_mfn(xen_start_info);
- si.pre = &xen_pre_suspend;
- si.post = &xen_post_suspend;
- }
-
err = stop_machine(xen_suspend, &si, cpumask_of(0));
raw_notifier_call_chain(&xen_resume_notifier, 0, NULL);
@@ -198,10 +167,32 @@ struct shutdown_handler {
void (*cb)(void);
};
+static int poweroff_nb(struct notifier_block *cb, unsigned long code, void *unused)
+{
+ switch (code) {
+ case SYS_DOWN:
+ case SYS_HALT:
+ case SYS_POWER_OFF:
+ shutting_down = SHUTDOWN_POWEROFF;
+ default:
+ break;
+ }
+ return NOTIFY_DONE;
+}
static void do_poweroff(void)
{
- shutting_down = SHUTDOWN_POWEROFF;
- orderly_poweroff(false);
+ switch (system_state) {
+ case SYSTEM_BOOTING:
+ orderly_poweroff(true);
+ break;
+ case SYSTEM_RUNNING:
+ orderly_poweroff(false);
+ break;
+ default:
+ /* Don't do it when we are halting/rebooting. */
+ pr_info("Ignoring Xen toolstack shutdown.\n");
+ break;
+ }
}
static void do_reboot(void)
@@ -307,6 +298,10 @@ static struct xenbus_watch shutdown_watch = {
.callback = shutdown_handler
};
+static struct notifier_block xen_reboot_nb = {
+ .notifier_call = poweroff_nb,
+};
+
static int setup_shutdown_watcher(void)
{
int err;
@@ -317,6 +312,7 @@ static int setup_shutdown_watcher(void)
return err;
}
+
#ifdef CONFIG_MAGIC_SYSRQ
err = register_xenbus_watch(&sysrq_watch);
if (err) {
@@ -345,6 +341,7 @@ int xen_setup_shutdown_event(void)
if (!xen_domain())
return -ENODEV;
register_xenstore_notifier(&xenstore_notifier);
+ register_reboot_notifier(&xen_reboot_nb);
return 0;
}
diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c
index 82358d14ecf..59fc190f1e9 100644
--- a/drivers/xen/xen-acpi-processor.c
+++ b/drivers/xen/xen-acpi-processor.c
@@ -127,7 +127,7 @@ 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 if (ret != -EINVAL)
+ } else if ((ret != -EINVAL) && (ret != -ENOSYS))
/* EINVAL means the ACPI ID is incorrect - meaning the ACPI
* table is referencing a non-existing CPU - which can happen
* with broken ACPI tables. */
@@ -259,7 +259,7 @@ static int push_pxx_to_hypervisor(struct acpi_processor *_pr)
(u32) perf->states[i].power,
(u32) perf->states[i].transition_latency);
}
- } else if (ret != -EINVAL)
+ } else if ((ret != -EINVAL) && (ret != -ENOSYS))
/* EINVAL means the ACPI ID is incorrect - meaning the ACPI
* table is referencing a non-existing CPU - which can happen
* with broken ACPI tables. */
diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c
index 62fcd485f0a..d57a173685f 100644
--- a/drivers/xen/xen-pciback/pci_stub.c
+++ b/drivers/xen/xen-pciback/pci_stub.c
@@ -242,6 +242,15 @@ struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev,
return found_dev;
}
+/*
+ * Called when:
+ * - XenBus state has been reconfigure (pci unplug). See xen_pcibk_remove_device
+ * - XenBus state has been disconnected (guest shutdown). See xen_pcibk_xenbus_remove
+ * - 'echo BDF > unbind' on pciback module with no guest attached. See pcistub_remove
+ * - 'echo BDF > unbind' with a guest still using it. See pcistub_remove
+ *
+ * As such we have to be careful.
+ */
void pcistub_put_pci_dev(struct pci_dev *dev)
{
struct pcistub_device *psdev, *found_psdev = NULL;
@@ -272,16 +281,16 @@ void pcistub_put_pci_dev(struct pci_dev *dev)
* and want to inhibit the user from fiddling with 'reset'
*/
pci_reset_function(dev);
- pci_restore_state(psdev->dev);
+ pci_restore_state(dev);
/* This disables the device. */
- xen_pcibk_reset_device(found_psdev->dev);
+ xen_pcibk_reset_device(dev);
/* And cleanup up our emulated fields. */
- xen_pcibk_config_free_dyn_fields(found_psdev->dev);
- xen_pcibk_config_reset_dev(found_psdev->dev);
+ xen_pcibk_config_reset_dev(dev);
+ xen_pcibk_config_free_dyn_fields(dev);
- xen_unregister_device_domain_owner(found_psdev->dev);
+ xen_unregister_device_domain_owner(dev);
spin_lock_irqsave(&found_psdev->lock, flags);
found_psdev->pdev = NULL;
@@ -493,6 +502,8 @@ static int pcistub_seize(struct pci_dev *dev)
return err;
}
+/* Called when 'bind'. This means we must _NOT_ call pci_reset_function or
+ * other functions that take the sysfs lock. */
static int pcistub_probe(struct pci_dev *dev, const struct pci_device_id *id)
{
int err = 0;
@@ -520,6 +531,8 @@ out:
return err;
}
+/* Called when 'unbind'. This means we must _NOT_ call pci_reset_function or
+ * other functions that take the sysfs lock. */
static void pcistub_remove(struct pci_dev *dev)
{
struct pcistub_device *psdev, *found_psdev = NULL;
@@ -551,6 +564,8 @@ static void pcistub_remove(struct pci_dev *dev)
pr_warn("****** shutdown driver domain before binding device\n");
pr_warn("****** to other drivers or domains\n");
+ /* N.B. This ends up calling pcistub_put_pci_dev which ends up
+ * doing the FLR. */
xen_pcibk_release_pci_dev(found_psdev->pdev,
found_psdev->dev);
}
diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c
index 929dd46bb40..c4a0666de6f 100644
--- a/drivers/xen/xen-pciback/pciback_ops.c
+++ b/drivers/xen/xen-pciback/pciback_ops.c
@@ -217,7 +217,7 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev,
if (result == 0) {
for (i = 0; i < op->value; i++) {
op->msix_entries[i].entry = entries[i].entry;
- if (entries[i].vector)
+ if (entries[i].vector) {
op->msix_entries[i].vector =
xen_pirq_from_irq(entries[i].vector);
if (unlikely(verbose_request))
@@ -225,6 +225,7 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev,
"MSI-X[%d]: %d\n",
pci_name(dev), i,
op->msix_entries[i].vector);
+ }
}
} else
pr_warn_ratelimited("%s: error enabling MSI-X for guest %u: err %d!\n",
@@ -347,9 +348,9 @@ void xen_pcibk_do_op(struct work_struct *data)
notify_remote_via_irq(pdev->evtchn_irq);
/* Mark that we're done. */
- smp_mb__before_clear_bit(); /* /after/ clearing PCIF_active */
+ smp_mb__before_atomic(); /* /after/ clearing PCIF_active */
clear_bit(_PDEVF_op_active, &pdev->flags);
- smp_mb__after_clear_bit(); /* /before/ final check for work */
+ smp_mb__after_atomic(); /* /before/ final check for work */
/* Check to see if the driver domain tried to start another request in
* between clearing _XEN_PCIF_active and clearing _PDEVF_op_active.
diff --git a/drivers/xen/xen-pciback/vpci.c b/drivers/xen/xen-pciback/vpci.c
index 3165ce361b0..51afff96c51 100644
--- a/drivers/xen/xen-pciback/vpci.c
+++ b/drivers/xen/xen-pciback/vpci.c
@@ -137,6 +137,8 @@ unlock:
/* Publish this device. */
if (!err)
err = publish_cb(pdev, 0, 0, PCI_DEVFN(slot, func), devid);
+ else
+ kfree(dev_entry);
out:
return err;
diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c
index a9ed867afab..4a7e6e0a5f4 100644
--- a/drivers/xen/xen-pciback/xenbus.c
+++ b/drivers/xen/xen-pciback/xenbus.c
@@ -93,6 +93,8 @@ static void free_pdev(struct xen_pcibk_device *pdev)
xen_pcibk_disconnect(pdev);
+ /* N.B. This calls pcistub_put_pci_dev which does the FLR on all
+ * of the PCIe devices. */
xen_pcibk_release_devices(pdev);
dev_set_drvdata(&pdev->xdev->dev, NULL);
@@ -286,6 +288,8 @@ static int xen_pcibk_remove_device(struct xen_pcibk_device *pdev,
dev_dbg(&dev->dev, "unregistering for %d\n", pdev->xdev->otherend_id);
xen_unregister_device_domain_owner(dev);
+ /* N.B. This ends up calling pcistub_put_pci_dev which ends up
+ * doing the FLR. */
xen_pcibk_release_pci_dev(pdev, dev);
out:
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index b6d5fff43d1..ba804f3d827 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -50,6 +50,7 @@
#include <xen/xenbus.h>
#include <xen/xen.h>
#include "xenbus_comms.h"
+#include "xenbus_probe.h"
struct xs_stored_msg {
struct list_head list;
@@ -139,6 +140,29 @@ static int get_error(const char *errorstring)
return xsd_errors[i].errnum;
}
+static bool xenbus_ok(void)
+{
+ switch (xen_store_domain_type) {
+ case XS_LOCAL:
+ switch (system_state) {
+ case SYSTEM_POWER_OFF:
+ case SYSTEM_RESTART:
+ case SYSTEM_HALT:
+ return false;
+ default:
+ break;
+ }
+ return true;
+ case XS_PV:
+ case XS_HVM:
+ /* FIXME: Could check that the remote domain is alive,
+ * but it is normally initial domain. */
+ return true;
+ default:
+ break;
+ }
+ return false;
+}
static void *read_reply(enum xsd_sockmsg_type *type, unsigned int *len)
{
struct xs_stored_msg *msg;
@@ -148,9 +172,20 @@ static void *read_reply(enum xsd_sockmsg_type *type, unsigned int *len)
while (list_empty(&xs_state.reply_list)) {
spin_unlock(&xs_state.reply_lock);
- /* XXX FIXME: Avoid synchronous wait for response here. */
- wait_event(xs_state.reply_waitq,
- !list_empty(&xs_state.reply_list));
+ if (xenbus_ok())
+ /* XXX FIXME: Avoid synchronous wait for response here. */
+ wait_event_timeout(xs_state.reply_waitq,
+ !list_empty(&xs_state.reply_list),
+ msecs_to_jiffies(500));
+ else {
+ /*
+ * If we are in the process of being shut-down there is
+ * no point of trying to contact XenBus - it is either
+ * killed (xenstored application) or the other domain
+ * has been killed or is unreachable.
+ */
+ return ERR_PTR(-EIO);
+ }
spin_lock(&xs_state.reply_lock);
}
@@ -215,6 +250,9 @@ void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg)
mutex_unlock(&xs_state.request_mutex);
+ if (IS_ERR(ret))
+ return ret;
+
if ((msg->type == XS_TRANSACTION_END) ||
((req_msg.type == XS_TRANSACTION_START) &&
(msg->type == XS_ERROR)))
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-29 09:22:02 +0000