Merge tag 'stable/for-linus-3.10-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen
Pull Xen updates from Konrad Rzeszutek Wilk:
"Features:
- Populate the boot_params with EDD data.
- Cleanups in the IRQ code.
Bug-fixes:
- CPU hotplug offline/online in PVHVM mode.
- Re-upload processor PM data after ACPI S3 suspend/resume cycle."
And Konrad gets a gold star for sending the pull request early when he
thought he'd be away for the first week of the merge window (but because
of 3.9 dragging out to -rc8 he then re-sent the reminder on the first
day of the merge window anyway)
* tag 'stable/for-linus-3.10-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
xen: resolve section mismatch warnings in xen-acpi-processor
xen: Re-upload processor PM data to hypervisor after S3 resume (v2)
xen/smp: Unifiy some of the PVs and PVHVM offline CPU path
xen/smp/pvhvm: Don't initialize IRQ_WORKER as we are using the native one.
xen/spinlock: Disable IRQ spinlock (PV) allocation on PVHVM
xen/spinlock: Check against default value of -1 for IRQ line.
xen/time: Add default value of -1 for IRQ and check for that.
xen/events: Check that IRQ value passed in is valid.
xen/time: Fix kasprintf splat when allocating timer%d IRQ line.
xen/smp/spinlock: Fix leakage of the spinlock interrupt line for every CPU online/offline
xen/smp: Fix leakage of timer interrupt line for every CPU online/offline.
xen kconfig: fix select INPUT_XEN_KBDDEV_FRONTEND
xen: drop tracking of IRQ vector
x86/xen: populate boot_params with EDD data
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 94e7662..4a9be6d 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -177,7 +177,7 @@
goto error;
i = 0;
list_for_each_entry(msidesc, &dev->msi_list, list) {
- irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0,
+ irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i],
(type == PCI_CAP_ID_MSIX) ?
"pcifront-msi-x" :
"pcifront-msi",
@@ -244,7 +244,7 @@
dev_dbg(&dev->dev,
"xen: msi already bound to pirq=%d\n", pirq);
}
- irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, 0,
+ irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq,
(type == PCI_CAP_ID_MSIX) ?
"msi-x" : "msi",
DOMID_SELF);
@@ -326,7 +326,7 @@
}
ret = xen_bind_pirq_msi_to_irq(dev, msidesc,
- map_irq.pirq, map_irq.index,
+ map_irq.pirq,
(type == PCI_CAP_ID_MSIX) ?
"msi-x" : "msi",
domid);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c8e1c7b..ddbd54a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -31,6 +31,7 @@
#include <linux/pci.h>
#include <linux/gfp.h>
#include <linux/memblock.h>
+#include <linux/edd.h>
#include <xen/xen.h>
#include <xen/events.h>
@@ -1306,6 +1307,55 @@
.emergency_restart = xen_emergency_restart,
};
+static void __init xen_boot_params_init_edd(void)
+{
+#if IS_ENABLED(CONFIG_EDD)
+ struct xen_platform_op op;
+ struct edd_info *edd_info;
+ u32 *mbr_signature;
+ unsigned nr;
+ int ret;
+
+ edd_info = boot_params.eddbuf;
+ mbr_signature = boot_params.edd_mbr_sig_buffer;
+
+ op.cmd = XENPF_firmware_info;
+
+ op.u.firmware_info.type = XEN_FW_DISK_INFO;
+ for (nr = 0; nr < EDDMAXNR; nr++) {
+ struct edd_info *info = edd_info + nr;
+
+ op.u.firmware_info.index = nr;
+ info->params.length = sizeof(info->params);
+ set_xen_guest_handle(op.u.firmware_info.u.disk_info.edd_params,
+ &info->params);
+ ret = HYPERVISOR_dom0_op(&op);
+ if (ret)
+ break;
+
+#define C(x) info->x = op.u.firmware_info.u.disk_info.x
+ C(device);
+ C(version);
+ C(interface_support);
+ C(legacy_max_cylinder);
+ C(legacy_max_head);
+ C(legacy_sectors_per_track);
+#undef C
+ }
+ boot_params.eddbuf_entries = nr;
+
+ op.u.firmware_info.type = XEN_FW_DISK_MBR_SIGNATURE;
+ for (nr = 0; nr < EDD_MBR_SIG_MAX; nr++) {
+ op.u.firmware_info.index = nr;
+ ret = HYPERVISOR_dom0_op(&op);
+ if (ret)
+ break;
+ mbr_signature[nr] = op.u.firmware_info.u.disk_mbr_signature.mbr_signature;
+ }
+ boot_params.edd_mbr_sig_buf_entries = nr;
+#endif
+}
+
/*
* Set up the GDT and segment registers for -fstack-protector. Until
* we do this, we have to be careful not to call any stack-protected
@@ -1508,6 +1558,8 @@
/* Avoid searching for BIOS MP tables */
x86_init.mpparse.find_smp_config = x86_init_noop;
x86_init.mpparse.get_smp_config = x86_init_uint_noop;
+
+ xen_boot_params_init_edd();
}
#ifdef CONFIG_PCI
/* PCI BIOS service won't work from a PV guest. */
@@ -1589,8 +1641,11 @@
switch (action) {
case CPU_UP_PREPARE:
xen_vcpu_setup(cpu);
- if (xen_have_vector_callback)
+ if (xen_have_vector_callback) {
xen_init_lock_cpu(cpu);
+ if (xen_feature(XENFEAT_hvm_safe_pvclock))
+ xen_setup_timer(cpu);
+ }
break;
default:
break;
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 09ea61d..0d466d7 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -144,6 +144,13 @@
goto fail;
per_cpu(xen_callfuncsingle_irq, cpu) = rc;
+ /*
+ * The IRQ worker on PVHVM goes through the native path and uses the
+ * IPI mechanism.
+ */
+ if (xen_hvm_domain())
+ return 0;
+
callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu);
rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR,
cpu,
@@ -167,6 +174,9 @@
if (per_cpu(xen_callfuncsingle_irq, cpu) >= 0)
unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu),
NULL);
+ if (xen_hvm_domain())
+ return rc;
+
if (per_cpu(xen_irq_work, cpu) >= 0)
unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
@@ -418,7 +428,7 @@
static void xen_cpu_die(unsigned int cpu)
{
- while (HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) {
+ while (xen_pv_domain() && HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) {
current->state = TASK_UNINTERRUPTIBLE;
schedule_timeout(HZ/10);
}
@@ -426,7 +436,8 @@
unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
- unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
+ if (!xen_hvm_domain())
+ unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
xen_uninit_lock_cpu(cpu);
xen_teardown_timer(cpu);
}
@@ -657,11 +668,7 @@
static void xen_hvm_cpu_die(unsigned int cpu)
{
- unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL);
- unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
- unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
- unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
- unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
+ xen_cpu_die(cpu);
native_cpu_die(cpu);
}
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index f7a080e..8b54603 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -364,6 +364,16 @@
int irq;
const char *name;
+ WARN(per_cpu(lock_kicker_irq, cpu) > 0, "spinlock on CPU%d exists on IRQ%d!\n",
+ cpu, per_cpu(lock_kicker_irq, cpu));
+
+ /*
+ * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23
+ * (xen: disable PV spinlocks on HVM)
+ */
+ if (xen_hvm_domain())
+ return;
+
name = kasprintf(GFP_KERNEL, "spinlock%d", cpu);
irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR,
cpu,
@@ -382,11 +392,26 @@
void xen_uninit_lock_cpu(int cpu)
{
+ /*
+ * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23
+ * (xen: disable PV spinlocks on HVM)
+ */
+ if (xen_hvm_domain())
+ return;
+
unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL);
+ per_cpu(lock_kicker_irq, cpu) = -1;
}
void __init xen_init_spinlocks(void)
{
+ /*
+ * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23
+ * (xen: disable PV spinlocks on HVM)
+ */
+ if (xen_hvm_domain())
+ return;
+
BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t));
pv_lock_ops.spin_is_locked = xen_spin_is_locked;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 0296a95..3d88bfd 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -377,7 +377,7 @@
static const struct clock_event_device *xen_clockevent =
&xen_timerop_clockevent;
-static DEFINE_PER_CPU(struct clock_event_device, xen_clock_events);
+static DEFINE_PER_CPU(struct clock_event_device, xen_clock_events) = { .irq = -1 };
static irqreturn_t xen_timer_interrupt(int irq, void *dev_id)
{
@@ -401,6 +401,9 @@
struct clock_event_device *evt;
int irq;
+ evt = &per_cpu(xen_clock_events, cpu);
+ WARN(evt->irq >= 0, "IRQ%d for CPU%d is already allocated\n", evt->irq, cpu);
+
printk(KERN_INFO "installing Xen timer for CPU %d\n", cpu);
name = kasprintf(GFP_KERNEL, "timer%d", cpu);
@@ -413,7 +416,6 @@
IRQF_FORCE_RESUME,
name, NULL);
- evt = &per_cpu(xen_clock_events, cpu);
memcpy(evt, xen_clockevent, sizeof(*evt));
evt->cpumask = cpumask_of(cpu);
@@ -426,6 +428,7 @@
BUG_ON(cpu == 0);
evt = &per_cpu(xen_clock_events, cpu);
unbind_from_irqhandler(evt->irq, NULL);
+ evt->irq = -1;
}
void xen_setup_cpu_clockevents(void)
@@ -497,7 +500,11 @@
{
int cpu = smp_processor_id();
xen_setup_runstate_info(cpu);
- xen_setup_timer(cpu);
+ /*
+ * xen_setup_timer(cpu) - snprintf is bad in atomic context. Hence
+ * doing it xen_hvm_cpu_notify (which gets called by smp_init during
+ * early bootup and also during CPU hotplug events).
+ */
xen_setup_cpu_clockevents();
}
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index 4c1546f..0939465 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -2277,7 +2277,7 @@
select FB_SYS_IMAGEBLIT
select FB_SYS_FOPS
select FB_DEFERRED_IO
- select INPUT_XEN_KBDDEV_FRONTEND
+ select INPUT_XEN_KBDDEV_FRONTEND if INPUT_MISC
select XEN_XENBUS_FRONTEND
default y
help
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 2647ad8..d8cc8127 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -85,8 +85,7 @@
* event channel - irq->event channel mapping
* cpu - cpu this event channel is bound to
* index - type-specific information:
- * PIRQ - vector, with MSB being "needs EIO", or physical IRQ of the HVM
- * guest, or GSI (real passthrough IRQ) of the device.
+ * PIRQ - physical IRQ, GSI, flags, and owner domain
* VIRQ - virq number
* IPI - IPI vector
* EVTCHN -
@@ -105,7 +104,6 @@
struct {
unsigned short pirq;
unsigned short gsi;
- unsigned char vector;
unsigned char flags;
uint16_t domid;
} pirq;
@@ -211,7 +209,6 @@
unsigned short evtchn,
unsigned short pirq,
unsigned short gsi,
- unsigned short vector,
uint16_t domid,
unsigned char flags)
{
@@ -221,7 +218,6 @@
info->u.pirq.pirq = pirq;
info->u.pirq.gsi = gsi;
- info->u.pirq.vector = vector;
info->u.pirq.domid = domid;
info->u.pirq.flags = flags;
}
@@ -519,6 +515,9 @@
{
struct irq_info *info = irq_get_handler_data(irq);
+ if (WARN_ON(!info))
+ return;
+
list_del(&info->list);
irq_set_handler_data(irq, NULL);
@@ -714,7 +713,7 @@
goto out;
}
- xen_irq_info_pirq_init(irq, 0, pirq, gsi, irq_op.vector, DOMID_SELF,
+ xen_irq_info_pirq_init(irq, 0, pirq, gsi, DOMID_SELF,
shareable ? PIRQ_SHAREABLE : 0);
pirq_query_unmask(irq);
@@ -762,8 +761,7 @@
}
int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
- int pirq, int vector, const char *name,
- domid_t domid)
+ int pirq, const char *name, domid_t domid)
{
int irq, ret;
@@ -776,7 +774,7 @@
irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_edge_irq,
name);
- xen_irq_info_pirq_init(irq, 0, pirq, 0, vector, domid, 0);
+ xen_irq_info_pirq_init(irq, 0, pirq, 0, domid, 0);
ret = irq_set_msi_desc(irq, msidesc);
if (ret < 0)
goto error_irq;
@@ -1008,6 +1006,9 @@
int evtchn = evtchn_from_irq(irq);
struct irq_info *info = irq_get_handler_data(irq);
+ if (WARN_ON(!info))
+ return;
+
mutex_lock(&irq_mapping_update_lock);
if (info->refcnt > 0) {
@@ -1135,6 +1136,10 @@
void unbind_from_irqhandler(unsigned int irq, void *dev_id)
{
+ struct irq_info *info = irq_get_handler_data(irq);
+
+ if (WARN_ON(!info))
+ return;
free_irq(irq, dev_id);
unbind_from_irq(irq);
}
@@ -1457,6 +1462,9 @@
{
struct irq_info *info = info_for_irq(irq);
+ if (WARN_ON(!info))
+ return;
+
/* Make sure the irq is masked, since the new event channel
will also be masked. */
disable_irq(irq);
@@ -1730,7 +1738,12 @@
int xen_test_irq_shared(int irq)
{
struct irq_info *info = info_for_irq(irq);
- struct physdev_irq_status_query irq_status = { .irq = info->u.pirq.pirq };
+ struct physdev_irq_status_query irq_status;
+
+ if (WARN_ON(!info))
+ return -ENOENT;
+
+ irq_status.irq = info->u.pirq.pirq;
if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status))
return 0;
diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c
index 90e34ac..8abd7d5 100644
--- a/drivers/xen/xen-acpi-processor.c
+++ b/drivers/xen/xen-acpi-processor.c
@@ -25,6 +25,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/types.h>
+#include <linux/syscore_ops.h>
#include <acpi/acpi_bus.h>
#include <acpi/acpi_drivers.h>
#include <acpi/processor.h>
@@ -51,9 +52,9 @@
/* Which ACPI ID we have processed from 'struct acpi_processor'. */
static unsigned long *acpi_ids_done;
/* Which ACPI ID exist in the SSDT/DSDT processor definitions. */
-static unsigned long __initdata *acpi_id_present;
+static unsigned long *acpi_id_present;
/* And if there is an _CST definition (or a PBLK) for the ACPI IDs */
-static unsigned long __initdata *acpi_id_cst_present;
+static unsigned long *acpi_id_cst_present;
static int push_cxx_to_hypervisor(struct acpi_processor *_pr)
{
@@ -329,7 +330,7 @@
* for_each_[present|online]_cpu macros which are banded to the virtual
* CPU amount.
*/
-static acpi_status __init
+static acpi_status
read_acpi_id(acpi_handle handle, u32 lvl, void *context, void **rv)
{
u32 acpi_id;
@@ -384,12 +385,16 @@
return AE_OK;
}
-static int __init check_acpi_ids(struct acpi_processor *pr_backup)
+static int check_acpi_ids(struct acpi_processor *pr_backup)
{
if (!pr_backup)
return -ENODEV;
+ if (acpi_id_present && acpi_id_cst_present)
+ /* OK, done this once .. skip to uploading */
+ goto upload;
+
/* All online CPUs have been processed at this stage. Now verify
* whether in fact "online CPUs" == physical CPUs.
*/
@@ -408,6 +413,7 @@
read_acpi_id, NULL, NULL, NULL);
acpi_get_devices("ACPI0007", read_acpi_id, NULL, NULL);
+upload:
if (!bitmap_equal(acpi_id_present, acpi_ids_done, nr_acpi_bits)) {
unsigned int i;
for_each_set_bit(i, acpi_id_present, nr_acpi_bits) {
@@ -417,10 +423,7 @@
(void)upload_pm_data(pr_backup);
}
}
- kfree(acpi_id_present);
- acpi_id_present = NULL;
- kfree(acpi_id_cst_present);
- acpi_id_cst_present = NULL;
+
return 0;
}
static int __init check_prereq(void)
@@ -467,10 +470,47 @@
free_percpu(acpi_perf_data);
}
-static int __init xen_acpi_processor_init(void)
+static int xen_upload_processor_pm_data(void)
{
struct acpi_processor *pr_backup = NULL;
unsigned int i;
+ int rc = 0;
+
+ pr_info(DRV_NAME "Uploading Xen processor PM info\n");
+
+ for_each_possible_cpu(i) {
+ struct acpi_processor *_pr;
+ _pr = per_cpu(processors, i /* APIC ID */);
+ if (!_pr)
+ continue;
+
+ if (!pr_backup) {
+ pr_backup = kzalloc(sizeof(struct acpi_processor), GFP_KERNEL);
+ if (pr_backup)
+ memcpy(pr_backup, _pr, sizeof(struct acpi_processor));
+ }
+ (void)upload_pm_data(_pr);
+ }
+
+ rc = check_acpi_ids(pr_backup);
+ kfree(pr_backup);
+
+ return rc;
+}
+
+static void xen_acpi_processor_resume(void)
+{
+ bitmap_zero(acpi_ids_done, nr_acpi_bits);
+ xen_upload_processor_pm_data();
+}
+
+static struct syscore_ops xap_syscore_ops = {
+ .resume = xen_acpi_processor_resume,
+};
+
+static int __init xen_acpi_processor_init(void)
+{
+ unsigned int i;
int rc = check_prereq();
if (rc)
@@ -514,27 +554,12 @@
goto err_out;
}
- for_each_possible_cpu(i) {
- struct acpi_processor *_pr;
- _pr = per_cpu(processors, i /* APIC ID */);
- if (!_pr)
- continue;
-
- if (!pr_backup) {
- pr_backup = kzalloc(sizeof(struct acpi_processor), GFP_KERNEL);
- if (pr_backup)
- memcpy(pr_backup, _pr, sizeof(struct acpi_processor));
- }
- (void)upload_pm_data(_pr);
- }
- rc = check_acpi_ids(pr_backup);
-
- kfree(pr_backup);
- pr_backup = NULL;
-
+ rc = xen_upload_processor_pm_data();
if (rc)
goto err_unregister;
+ register_syscore_ops(&xap_syscore_ops);
+
return 0;
err_unregister:
for_each_possible_cpu(i) {
@@ -552,7 +577,10 @@
{
int i;
+ unregister_syscore_ops(&xap_syscore_ops);
kfree(acpi_ids_done);
+ kfree(acpi_id_present);
+ kfree(acpi_id_cst_present);
for_each_possible_cpu(i) {
struct acpi_processor_performance *perf;
perf = per_cpu_ptr(acpi_perf_data, i);
diff --git a/include/xen/events.h b/include/xen/events.h
index c6bfe01..b2b27c6 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -90,8 +90,7 @@
int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc);
/* Bind an PSI pirq to an irq. */
int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
- int pirq, int vector, const char *name,
- domid_t domid);
+ int pirq, const char *name, domid_t domid);
#endif
/* De-allocates the above mentioned physical interrupt. */