From ea08eeccae9297f7aabd2ef7f0c2517ac4549acc Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:18:26 +0000
Subject: [PATCH] write in 30M
---
kernel/drivers/hv/vmbus_drv.c | 996 +++++++++++++++++++++++++++++++++++++++++++++++----------
1 files changed, 810 insertions(+), 186 deletions(-)
diff --git a/kernel/drivers/hv/vmbus_drv.c b/kernel/drivers/hv/vmbus_drv.c
index 0df4a07..e99400f 100644
--- a/kernel/drivers/hv/vmbus_drv.c
+++ b/kernel/drivers/hv/vmbus_drv.c
@@ -1,24 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2009, Microsoft Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
*
* Authors:
* Haiyang Zhang <haiyangz@microsoft.com>
* Hank Janssen <hjanssen@microsoft.com>
* K. Y. Srinivasan <kys@microsoft.com>
- *
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -36,7 +23,7 @@
#include <linux/cpu.h>
#include <linux/sched/task_stack.h>
-#include <asm/mshyperv.h>
+#include <linux/delay.h>
#include <linux/notifier.h>
#include <linux/ptrace.h>
#include <linux/screen_info.h>
@@ -44,6 +31,8 @@
#include <linux/efi.h>
#include <linux/random.h>
#include <linux/kernel.h>
+#include <linux/syscore_ops.h>
+#include <clocksource/hyperv_timer.h>
#include "hyperv_vmbus.h"
struct vmbus_dynid {
@@ -58,6 +47,10 @@
static int hyperv_cpuhp_online;
static void *hv_panic_page;
+
+/* Values parsed from ACPI DSDT */
+static int vmbus_irq;
+int vmbus_interrupt;
/*
* Boolean to control whether to report panic messages over Hyper-V.
@@ -94,8 +87,12 @@
static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
void *args)
{
- struct die_args *die = (struct die_args *)args;
+ struct die_args *die = args;
struct pt_regs *regs = die->regs;
+
+ /* Don't notify Hyper-V if the die event is other than oops */
+ if (val != DIE_OOPS)
+ return NOTIFY_DONE;
/*
* Hyper-V should be notified only once about a panic. If we will be
@@ -117,7 +114,7 @@
static const char *fb_mmio_name = "fb_range";
static struct resource *fb_mmio;
static struct resource *hyperv_mmio;
-static DEFINE_SEMAPHORE(hyperv_mmio_lock);
+static DEFINE_MUTEX(hyperv_mmio_lock);
static int vmbus_exists(void)
{
@@ -125,14 +122,6 @@
return -ENODEV;
return 0;
-}
-
-#define VMBUS_ALIAS_LEN ((sizeof((struct hv_vmbus_device_id *)0)->guid) * 2)
-static void print_alias_name(struct hv_device *hv_dev, char *alias_name)
-{
- int i;
- for (i = 0; i < VMBUS_ALIAS_LEN; i += 2)
- sprintf(&alias_name[i], "%02x", hv_dev->dev_type.b[i/2]);
}
static u8 channel_monitor_group(const struct vmbus_channel *channel)
@@ -211,7 +200,7 @@
if (!hv_dev->channel)
return -ENODEV;
return sprintf(buf, "{%pUl}\n",
- hv_dev->channel->offermsg.offer.if_type.b);
+ &hv_dev->channel->offermsg.offer.if_type);
}
static DEVICE_ATTR_RO(class_id);
@@ -223,7 +212,7 @@
if (!hv_dev->channel)
return -ENODEV;
return sprintf(buf, "{%pUl}\n",
- hv_dev->channel->offermsg.offer.if_instance.b);
+ &hv_dev->channel->offermsg.offer.if_instance);
}
static DEVICE_ATTR_RO(device_id);
@@ -231,10 +220,8 @@
struct device_attribute *dev_attr, char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
- char alias_name[VMBUS_ALIAS_LEN + 1];
- print_alias_name(hv_dev, alias_name);
- return sprintf(buf, "vmbus:%s\n", alias_name);
+ return sprintf(buf, "vmbus:%*phN\n", UUID_SIZE, &hv_dev->dev_type);
}
static DEVICE_ATTR_RO(modalias);
@@ -247,7 +234,7 @@
if (!hv_dev->channel)
return -ENODEV;
- return sprintf(buf, "%d\n", hv_dev->channel->numa_node);
+ return sprintf(buf, "%d\n", cpu_to_node(hv_dev->channel->target_cpu));
}
static DEVICE_ATTR_RO(numa_node);
#endif
@@ -262,7 +249,7 @@
return -ENODEV;
return sprintf(buf, "%d\n",
channel_pending(hv_dev->channel,
- vmbus_connection.monitor_pages[1]));
+ vmbus_connection.monitor_pages[0]));
}
static DEVICE_ATTR_RO(server_monitor_pending);
@@ -528,17 +515,16 @@
{
struct hv_device *hv_dev = device_to_hv_device(dev);
struct vmbus_channel *channel = hv_dev->channel, *cur_sc;
- unsigned long flags;
int buf_size = PAGE_SIZE, n_written, tot_written;
struct list_head *cur;
if (!channel)
return -ENODEV;
+ mutex_lock(&vmbus_connection.channel_mutex);
+
tot_written = snprintf(buf, buf_size, "%u:%u\n",
channel->offermsg.child_relid, channel->target_cpu);
-
- spin_lock_irqsave(&channel->lock, flags);
list_for_each(cur, &channel->sc_list) {
if (tot_written >= buf_size - 1)
@@ -553,7 +539,7 @@
tot_written += n_written;
}
- spin_unlock_irqrestore(&channel->lock, flags);
+ mutex_unlock(&vmbus_connection.channel_mutex);
return tot_written;
}
@@ -576,6 +562,54 @@
return sprintf(buf, "0x%x\n", hv_dev->device_id);
}
static DEVICE_ATTR_RO(device);
+
+static ssize_t driver_override_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct hv_device *hv_dev = device_to_hv_device(dev);
+ char *driver_override, *old, *cp;
+
+ /* We need to keep extra room for a newline */
+ if (count >= (PAGE_SIZE - 1))
+ return -EINVAL;
+
+ driver_override = kstrndup(buf, count, GFP_KERNEL);
+ if (!driver_override)
+ return -ENOMEM;
+
+ cp = strchr(driver_override, '\n');
+ if (cp)
+ *cp = '\0';
+
+ device_lock(dev);
+ old = hv_dev->driver_override;
+ if (strlen(driver_override)) {
+ hv_dev->driver_override = driver_override;
+ } else {
+ kfree(driver_override);
+ hv_dev->driver_override = NULL;
+ }
+ device_unlock(dev);
+
+ kfree(old);
+
+ return count;
+}
+
+static ssize_t driver_override_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct hv_device *hv_dev = device_to_hv_device(dev);
+ ssize_t len;
+
+ device_lock(dev);
+ len = snprintf(buf, PAGE_SIZE, "%s\n", hv_dev->driver_override);
+ device_unlock(dev);
+
+ return len;
+}
+static DEVICE_ATTR_RW(driver_override);
/* Set up per device attributes in /sys/bus/vmbus/devices/<bus device> */
static struct attribute *vmbus_dev_attrs[] = {
@@ -607,6 +641,7 @@
&dev_attr_channel_vp_mapping.attr,
&dev_attr_vendor.attr,
&dev_attr_device.attr,
+ &dev_attr_driver_override.attr,
NULL,
};
@@ -654,59 +689,72 @@
static int vmbus_uevent(struct device *device, struct kobj_uevent_env *env)
{
struct hv_device *dev = device_to_hv_device(device);
- int ret;
- char alias_name[VMBUS_ALIAS_LEN + 1];
+ const char *format = "MODALIAS=vmbus:%*phN";
- print_alias_name(dev, alias_name);
- ret = add_uevent_var(env, "MODALIAS=vmbus:%s", alias_name);
- return ret;
+ return add_uevent_var(env, format, UUID_SIZE, &dev->dev_type);
}
-static const uuid_le null_guid;
-
-static inline bool is_null_guid(const uuid_le *guid)
+static const struct hv_vmbus_device_id *
+hv_vmbus_dev_match(const struct hv_vmbus_device_id *id, const guid_t *guid)
{
- if (uuid_le_cmp(*guid, null_guid))
- return false;
- return true;
+ if (id == NULL)
+ return NULL; /* empty device table */
+
+ for (; !guid_is_null(&id->guid); id++)
+ if (guid_equal(&id->guid, guid))
+ return id;
+
+ return NULL;
}
-/*
- * Return a matching hv_vmbus_device_id pointer.
- * If there is no match, return NULL.
- */
-static const struct hv_vmbus_device_id *hv_vmbus_get_id(struct hv_driver *drv,
- const uuid_le *guid)
+static const struct hv_vmbus_device_id *
+hv_vmbus_dynid_match(struct hv_driver *drv, const guid_t *guid)
{
const struct hv_vmbus_device_id *id = NULL;
struct vmbus_dynid *dynid;
- /* Look at the dynamic ids first, before the static ones */
spin_lock(&drv->dynids.lock);
list_for_each_entry(dynid, &drv->dynids.list, node) {
- if (!uuid_le_cmp(dynid->id.guid, *guid)) {
+ if (guid_equal(&dynid->id.guid, guid)) {
id = &dynid->id;
break;
}
}
spin_unlock(&drv->dynids.lock);
- if (id)
- return id;
+ return id;
+}
- id = drv->id_table;
- if (id == NULL)
- return NULL; /* empty device table */
+static const struct hv_vmbus_device_id vmbus_device_null;
- for (; !is_null_guid(&id->guid); id++)
- if (!uuid_le_cmp(id->guid, *guid))
- return id;
+/*
+ * Return a matching hv_vmbus_device_id pointer.
+ * If there is no match, return NULL.
+ */
+static const struct hv_vmbus_device_id *hv_vmbus_get_id(struct hv_driver *drv,
+ struct hv_device *dev)
+{
+ const guid_t *guid = &dev->dev_type;
+ const struct hv_vmbus_device_id *id;
- return NULL;
+ /* When driver_override is set, only bind to the matching driver */
+ if (dev->driver_override && strcmp(dev->driver_override, drv->name))
+ return NULL;
+
+ /* Look at the dynamic ids first, before the static ones */
+ id = hv_vmbus_dynid_match(drv, guid);
+ if (!id)
+ id = hv_vmbus_dev_match(drv->id_table, guid);
+
+ /* driver_override will always match, send a dummy id */
+ if (!id && dev->driver_override)
+ id = &vmbus_device_null;
+
+ return id;
}
/* vmbus_add_dynid - add a new device ID to this driver and re-probe devices */
-static int vmbus_add_dynid(struct hv_driver *drv, uuid_le *guid)
+static int vmbus_add_dynid(struct hv_driver *drv, guid_t *guid)
{
struct vmbus_dynid *dynid;
@@ -744,14 +792,14 @@
size_t count)
{
struct hv_driver *drv = drv_to_hv_drv(driver);
- uuid_le guid;
+ guid_t guid;
ssize_t retval;
- retval = uuid_le_to_bin(buf, &guid);
+ retval = guid_parse(buf, &guid);
if (retval)
return retval;
- if (hv_vmbus_get_id(drv, &guid))
+ if (hv_vmbus_dynid_match(drv, &guid))
return -EEXIST;
retval = vmbus_add_dynid(drv, &guid);
@@ -771,10 +819,10 @@
{
struct hv_driver *drv = drv_to_hv_drv(driver);
struct vmbus_dynid *dynid, *n;
- uuid_le guid;
+ guid_t guid;
ssize_t retval;
- retval = uuid_le_to_bin(buf, &guid);
+ retval = guid_parse(buf, &guid);
if (retval)
return retval;
@@ -783,7 +831,7 @@
list_for_each_entry_safe(dynid, n, &drv->dynids.list, node) {
struct hv_vmbus_device_id *id = &dynid->id;
- if (!uuid_le_cmp(id->guid, guid)) {
+ if (guid_equal(&id->guid, &guid)) {
list_del(&dynid->node);
kfree(dynid);
retval = count;
@@ -816,7 +864,7 @@
if (is_hvsock_channel(hv_dev->channel))
return drv->hvsock;
- if (hv_vmbus_get_id(drv, &hv_dev->dev_type))
+ if (hv_vmbus_get_id(drv, hv_dev))
return 1;
return 0;
@@ -833,7 +881,7 @@
struct hv_device *dev = device_to_hv_device(child_device);
const struct hv_vmbus_device_id *dev_id;
- dev_id = hv_vmbus_get_id(drv, &dev->dev_type);
+ dev_id = hv_vmbus_get_id(drv, dev);
if (drv->probe) {
ret = drv->probe(dev, dev_id);
if (ret != 0)
@@ -885,6 +933,48 @@
drv->shutdown(dev);
}
+#ifdef CONFIG_PM_SLEEP
+/*
+ * vmbus_suspend - Suspend a vmbus device
+ */
+static int vmbus_suspend(struct device *child_device)
+{
+ struct hv_driver *drv;
+ struct hv_device *dev = device_to_hv_device(child_device);
+
+ /* The device may not be attached yet */
+ if (!child_device->driver)
+ return 0;
+
+ drv = drv_to_hv_drv(child_device->driver);
+ if (!drv->suspend)
+ return -EOPNOTSUPP;
+
+ return drv->suspend(dev);
+}
+
+/*
+ * vmbus_resume - Resume a vmbus device
+ */
+static int vmbus_resume(struct device *child_device)
+{
+ struct hv_driver *drv;
+ struct hv_device *dev = device_to_hv_device(child_device);
+
+ /* The device may not be attached yet */
+ if (!child_device->driver)
+ return 0;
+
+ drv = drv_to_hv_drv(child_device->driver);
+ if (!drv->resume)
+ return -EOPNOTSUPP;
+
+ return drv->resume(dev);
+}
+#else
+#define vmbus_suspend NULL
+#define vmbus_resume NULL
+#endif /* CONFIG_PM_SLEEP */
/*
* vmbus_device_release - Final callback release of the vmbus child device
@@ -894,12 +984,32 @@
struct hv_device *hv_dev = device_to_hv_device(device);
struct vmbus_channel *channel = hv_dev->channel;
+ hv_debug_rm_dev_dir(hv_dev);
+
mutex_lock(&vmbus_connection.channel_mutex);
- hv_process_channel_removal(channel->offermsg.child_relid);
+ hv_process_channel_removal(channel);
mutex_unlock(&vmbus_connection.channel_mutex);
kfree(hv_dev);
-
}
+
+/*
+ * Note: we must use the "noirq" ops: see the comment before vmbus_bus_pm.
+ *
+ * suspend_noirq/resume_noirq are set to NULL to support Suspend-to-Idle: we
+ * shouldn't suspend the vmbus devices upon Suspend-to-Idle, otherwise there
+ * is no way to wake up a Generation-2 VM.
+ *
+ * The other 4 ops are for hibernation.
+ */
+
+static const struct dev_pm_ops vmbus_pm = {
+ .suspend_noirq = NULL,
+ .resume_noirq = NULL,
+ .freeze_noirq = vmbus_suspend,
+ .thaw_noirq = vmbus_resume,
+ .poweroff_noirq = vmbus_suspend,
+ .restore_noirq = vmbus_resume,
+};
/* The one and only one */
static struct bus_type hv_bus = {
@@ -911,11 +1021,15 @@
.uevent = vmbus_uevent,
.dev_groups = vmbus_dev_groups,
.drv_groups = vmbus_drv_groups,
+ .pm = &vmbus_pm,
};
struct onmessage_work_context {
struct work_struct work;
- struct hv_message msg;
+ struct {
+ struct hv_message_header header;
+ u8 payload[];
+ } msg;
};
static void vmbus_onmessage_work(struct work_struct *work)
@@ -928,19 +1042,9 @@
ctx = container_of(work, struct onmessage_work_context,
work);
- vmbus_onmessage(&ctx->msg);
+ vmbus_onmessage((struct vmbus_channel_message_header *)
+ &ctx->msg.payload);
kfree(ctx);
-}
-
-static void hv_process_timer_expiration(struct hv_message *msg,
- struct hv_per_cpu_context *hv_cpu)
-{
- struct clock_event_device *dev = hv_cpu->clk_evt;
-
- if (dev->event_handler)
- dev->event_handler(dev);
-
- vmbus_signal_eom(msg, HVMSG_TIMER_EXPIRED);
}
void vmbus_on_msg_dpc(unsigned long data)
@@ -953,6 +1057,13 @@
const struct vmbus_channel_message_table_entry *entry;
struct onmessage_work_context *ctx;
u32 message_type = msg->header.message_type;
+
+ /*
+ * 'enum vmbus_channel_message_type' is supposed to always be 'u32' as
+ * it is being used in 'struct vmbus_channel_message_header' definition
+ * which is supposed to match hypervisor ABI.
+ */
+ BUILD_BUG_ON(sizeof(enum vmbus_channel_message_type) != sizeof(u32));
if (message_type == HVMSG_NONE)
/* no msg */
@@ -967,41 +1078,88 @@
goto msg_handled;
}
+ if (msg->header.payload_size > HV_MESSAGE_PAYLOAD_BYTE_COUNT) {
+ WARN_ONCE(1, "payload size is too large (%d)\n",
+ msg->header.payload_size);
+ goto msg_handled;
+ }
+
entry = &channel_message_table[hdr->msgtype];
if (!entry->message_handler)
goto msg_handled;
+ if (msg->header.payload_size < entry->min_payload_len) {
+ WARN_ONCE(1, "message too short: msgtype=%d len=%d\n",
+ hdr->msgtype, msg->header.payload_size);
+ goto msg_handled;
+ }
+
if (entry->handler_type == VMHT_BLOCKING) {
- ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC);
+ ctx = kmalloc(sizeof(*ctx) + msg->header.payload_size,
+ GFP_ATOMIC);
if (ctx == NULL)
return;
INIT_WORK(&ctx->work, vmbus_onmessage_work);
- memcpy(&ctx->msg, msg, sizeof(*msg));
+ memcpy(&ctx->msg, msg, sizeof(msg->header) +
+ msg->header.payload_size);
/*
* The host can generate a rescind message while we
* may still be handling the original offer. We deal with
- * this condition by ensuring the processing is done on the
- * same CPU.
+ * this condition by relying on the synchronization provided
+ * by offer_in_progress and by channel_mutex. See also the
+ * inline comments in vmbus_onoffer_rescind().
*/
switch (hdr->msgtype) {
case CHANNELMSG_RESCIND_CHANNELOFFER:
/*
* If we are handling the rescind message;
* schedule the work on the global work queue.
+ *
+ * The OFFER message and the RESCIND message should
+ * not be handled by the same serialized work queue,
+ * because the OFFER handler may call vmbus_open(),
+ * which tries to open the channel by sending an
+ * OPEN_CHANNEL message to the host and waits for
+ * the host's response; however, if the host has
+ * rescinded the channel before it receives the
+ * OPEN_CHANNEL message, the host just silently
+ * ignores the OPEN_CHANNEL message; as a result,
+ * the guest's OFFER handler hangs for ever, if we
+ * handle the RESCIND message in the same serialized
+ * work queue: the RESCIND handler can not start to
+ * run before the OFFER handler finishes.
*/
- schedule_work_on(vmbus_connection.connect_cpu,
- &ctx->work);
+ schedule_work(&ctx->work);
break;
case CHANNELMSG_OFFERCHANNEL:
+ /*
+ * The host sends the offer message of a given channel
+ * before sending the rescind message of the same
+ * channel. These messages are sent to the guest's
+ * connect CPU; the guest then starts processing them
+ * in the tasklet handler on this CPU:
+ *
+ * VMBUS_CONNECT_CPU
+ *
+ * [vmbus_on_msg_dpc()]
+ * atomic_inc() // CHANNELMSG_OFFERCHANNEL
+ * queue_work()
+ * ...
+ * [vmbus_on_msg_dpc()]
+ * schedule_work() // CHANNELMSG_RESCIND_CHANNELOFFER
+ *
+ * We rely on the memory-ordering properties of the
+ * queue_work() and schedule_work() primitives, which
+ * guarantee that the atomic increment will be visible
+ * to the CPUs which will execute the offer & rescind
+ * works by the time these works will start execution.
+ */
atomic_inc(&vmbus_connection.offer_in_progress);
- queue_work_on(vmbus_connection.connect_cpu,
- vmbus_connection.work_queue,
- &ctx->work);
- break;
+ fallthrough;
default:
queue_work(vmbus_connection.work_queue, &ctx->work);
@@ -1013,18 +1171,42 @@
vmbus_signal_eom(msg, message_type);
}
-
+#ifdef CONFIG_PM_SLEEP
/*
- * Direct callback for channels using other deferred processing
+ * Fake RESCIND_CHANNEL messages to clean up hv_sock channels by force for
+ * hibernation, because hv_sock connections can not persist across hibernation.
*/
-static void vmbus_channel_isr(struct vmbus_channel *channel)
+static void vmbus_force_channel_rescinded(struct vmbus_channel *channel)
{
- void (*callback_fn)(void *);
+ struct onmessage_work_context *ctx;
+ struct vmbus_channel_rescind_offer *rescind;
- callback_fn = READ_ONCE(channel->onchannel_callback);
- if (likely(callback_fn != NULL))
- (*callback_fn)(channel->channel_callback_context);
+ WARN_ON(!is_hvsock_channel(channel));
+
+ /*
+ * Allocation size is small and the allocation should really not fail,
+ * otherwise the state of the hv_sock connections ends up in limbo.
+ */
+ ctx = kzalloc(sizeof(*ctx) + sizeof(*rescind),
+ GFP_KERNEL | __GFP_NOFAIL);
+
+ /*
+ * So far, these are not really used by Linux. Just set them to the
+ * reasonable values conforming to the definitions of the fields.
+ */
+ ctx->msg.header.message_type = 1;
+ ctx->msg.header.payload_size = sizeof(*rescind);
+
+ /* These values are actually used by Linux. */
+ rescind = (struct vmbus_channel_rescind_offer *)ctx->msg.payload;
+ rescind->header.msgtype = CHANNELMSG_RESCIND_CHANNELOFFER;
+ rescind->child_relid = channel->offermsg.child_relid;
+
+ INIT_WORK(&ctx->work, vmbus_onmessage_work);
+
+ queue_work(vmbus_connection.work_queue, &ctx->work);
}
+#endif /* CONFIG_PM_SLEEP */
/*
* Schedule all channels with events pending
@@ -1056,6 +1238,7 @@
return;
for_each_set_bit(relid, recv_int_page, maxbits) {
+ void (*callback_fn)(void *context);
struct vmbus_channel *channel;
if (!sync_test_and_clear_bit(relid, recv_int_page))
@@ -1065,33 +1248,54 @@
if (relid == 0)
continue;
+ /*
+ * Pairs with the kfree_rcu() in vmbus_chan_release().
+ * Guarantees that the channel data structure doesn't
+ * get freed while the channel pointer below is being
+ * dereferenced.
+ */
rcu_read_lock();
/* Find channel based on relid */
- list_for_each_entry_rcu(channel, &hv_cpu->chan_list, percpu_list) {
- if (channel->offermsg.child_relid != relid)
- continue;
+ channel = relid2channel(relid);
+ if (channel == NULL)
+ goto sched_unlock_rcu;
- if (channel->rescind)
- continue;
+ if (channel->rescind)
+ goto sched_unlock_rcu;
- trace_vmbus_chan_sched(channel);
+ /*
+ * Make sure that the ring buffer data structure doesn't get
+ * freed while we dereference the ring buffer pointer. Test
+ * for the channel's onchannel_callback being NULL within a
+ * sched_lock critical section. See also the inline comments
+ * in vmbus_reset_channel_cb().
+ */
+ spin_lock(&channel->sched_lock);
- ++channel->interrupts;
+ callback_fn = channel->onchannel_callback;
+ if (unlikely(callback_fn == NULL))
+ goto sched_unlock;
- switch (channel->callback_mode) {
- case HV_CALL_ISR:
- vmbus_channel_isr(channel);
- break;
+ trace_vmbus_chan_sched(channel);
- case HV_CALL_BATCHED:
- hv_begin_read(&channel->inbound);
- /* fallthrough */
- case HV_CALL_DIRECT:
- tasklet_schedule(&channel->callback_event);
- }
+ ++channel->interrupts;
+
+ switch (channel->callback_mode) {
+ case HV_CALL_ISR:
+ (*callback_fn)(channel->channel_callback_context);
+ break;
+
+ case HV_CALL_BATCHED:
+ hv_begin_read(&channel->inbound);
+ fallthrough;
+ case HV_CALL_DIRECT:
+ tasklet_schedule(&channel->callback_event);
}
+sched_unlock:
+ spin_unlock(&channel->sched_lock);
+sched_unlock_rcu:
rcu_read_unlock();
}
}
@@ -1103,8 +1307,6 @@
void *page_addr = hv_cpu->synic_event_page;
struct hv_message *msg;
union hv_synic_event_flags *event;
- struct pt_regs *regs = get_irq_regs();
- u64 ip = regs ? instruction_pointer(regs) : 0;
bool handled = false;
if (unlikely(page_addr == NULL))
@@ -1142,13 +1344,14 @@
/* Check if there are actual msgs to be processed */
if (msg->header.message_type != HVMSG_NONE) {
- if (msg->header.message_type == HVMSG_TIMER_EXPIRED)
- hv_process_timer_expiration(msg, hv_cpu);
- else
+ if (msg->header.message_type == HVMSG_TIMER_EXPIRED) {
+ hv_stimer0_isr();
+ vmbus_signal_eom(msg, HVMSG_TIMER_EXPIRED);
+ } else
tasklet_schedule(&hv_cpu->msg_dpc);
}
- add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0, ip);
+ add_interrupt_randomness(hv_get_vector());
}
/*
@@ -1171,7 +1374,7 @@
* Write dump contents to the page. No need to synchronize; panic should
* be single-threaded.
*/
- kmsg_dump_get_buffer(dumper, true, hv_panic_page, PAGE_SIZE,
+ kmsg_dump_get_buffer(dumper, false, hv_panic_page, HV_HYP_PAGE_SIZE,
&bytes_written);
if (bytes_written)
hyperv_report_panic_msg(panic_pa, bytes_written);
@@ -1182,8 +1385,6 @@
};
static struct ctl_table_header *hv_ctl_table_hdr;
-static int zero;
-static int one = 1;
/*
* sysctl option to allow the user to control whether kmsg data should be
@@ -1196,8 +1397,8 @@
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
- .extra2 = &one
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE
},
{}
};
@@ -1223,7 +1424,6 @@
{
int ret;
- /* Hypervisor initialization...setup hypercall page..etc */
ret = hv_init();
if (ret != 0) {
pr_err("Unable to initialize the hypervisor - 0x%x\n", ret);
@@ -1234,19 +1434,22 @@
if (ret)
return ret;
- hv_setup_vmbus_irq(vmbus_isr);
+ ret = hv_setup_vmbus_irq(vmbus_irq, vmbus_isr);
+ if (ret)
+ goto err_setup;
ret = hv_synic_alloc();
if (ret)
goto err_alloc;
+
/*
- * Initialize the per-cpu interrupt state and
- * connect to the host.
+ * Initialize the per-cpu interrupt state and stimer state.
+ * Then connect to the host.
*/
ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "hyperv/vmbus:online",
hv_synic_init, hv_synic_cleanup);
if (ret < 0)
- goto err_alloc;
+ goto err_cpuhp;
hyperv_cpuhp_online = ret;
ret = vmbus_connect();
@@ -1272,13 +1475,13 @@
*/
hv_get_crash_ctl(hyperv_crash_ctl);
if (hyperv_crash_ctl & HV_CRASH_CTL_CRASH_NOTIFY_MSG) {
- hv_panic_page = (void *)get_zeroed_page(GFP_KERNEL);
+ hv_panic_page = (void *)hv_alloc_hyperv_zeroed_page();
if (hv_panic_page) {
ret = kmsg_dump_register(&hv_kmsg_dumper);
if (ret) {
pr_err("Hyper-V: kmsg dump register "
"error 0x%x\n", ret);
- free_page(
+ hv_free_hyperv_page(
(unsigned long)hv_panic_page);
hv_panic_page = NULL;
}
@@ -1304,10 +1507,11 @@
err_connect:
cpuhp_remove_state(hyperv_cpuhp_online);
-err_alloc:
+err_cpuhp:
hv_synic_free();
+err_alloc:
hv_remove_vmbus_irq();
-
+err_setup:
bus_unregister(&hv_bus);
unregister_sysctl_table(hv_ctl_table_hdr);
hv_ctl_table_hdr = NULL;
@@ -1382,7 +1586,7 @@
struct vmbus_chan_attribute {
struct attribute attr;
- ssize_t (*show)(const struct vmbus_channel *chan, char *buf);
+ ssize_t (*show)(struct vmbus_channel *chan, char *buf);
ssize_t (*store)(struct vmbus_channel *chan,
const char *buf, size_t count);
};
@@ -1401,61 +1605,207 @@
{
const struct vmbus_chan_attribute *attribute
= container_of(attr, struct vmbus_chan_attribute, attr);
- const struct vmbus_channel *chan
+ struct vmbus_channel *chan
= container_of(kobj, struct vmbus_channel, kobj);
if (!attribute->show)
return -EIO;
- if (chan->state != CHANNEL_OPENED_STATE)
- return -EINVAL;
-
return attribute->show(chan, buf);
+}
+
+static ssize_t vmbus_chan_attr_store(struct kobject *kobj,
+ struct attribute *attr, const char *buf,
+ size_t count)
+{
+ const struct vmbus_chan_attribute *attribute
+ = container_of(attr, struct vmbus_chan_attribute, attr);
+ struct vmbus_channel *chan
+ = container_of(kobj, struct vmbus_channel, kobj);
+
+ if (!attribute->store)
+ return -EIO;
+
+ return attribute->store(chan, buf, count);
}
static const struct sysfs_ops vmbus_chan_sysfs_ops = {
.show = vmbus_chan_attr_show,
+ .store = vmbus_chan_attr_store,
};
-static ssize_t out_mask_show(const struct vmbus_channel *channel, char *buf)
+static ssize_t out_mask_show(struct vmbus_channel *channel, char *buf)
{
- const struct hv_ring_buffer_info *rbi = &channel->outbound;
+ struct hv_ring_buffer_info *rbi = &channel->outbound;
+ ssize_t ret;
- return sprintf(buf, "%u\n", rbi->ring_buffer->interrupt_mask);
+ mutex_lock(&rbi->ring_buffer_mutex);
+ if (!rbi->ring_buffer) {
+ mutex_unlock(&rbi->ring_buffer_mutex);
+ return -EINVAL;
+ }
+
+ ret = sprintf(buf, "%u\n", rbi->ring_buffer->interrupt_mask);
+ mutex_unlock(&rbi->ring_buffer_mutex);
+ return ret;
}
static VMBUS_CHAN_ATTR_RO(out_mask);
-static ssize_t in_mask_show(const struct vmbus_channel *channel, char *buf)
+static ssize_t in_mask_show(struct vmbus_channel *channel, char *buf)
{
- const struct hv_ring_buffer_info *rbi = &channel->inbound;
+ struct hv_ring_buffer_info *rbi = &channel->inbound;
+ ssize_t ret;
- return sprintf(buf, "%u\n", rbi->ring_buffer->interrupt_mask);
+ mutex_lock(&rbi->ring_buffer_mutex);
+ if (!rbi->ring_buffer) {
+ mutex_unlock(&rbi->ring_buffer_mutex);
+ return -EINVAL;
+ }
+
+ ret = sprintf(buf, "%u\n", rbi->ring_buffer->interrupt_mask);
+ mutex_unlock(&rbi->ring_buffer_mutex);
+ return ret;
}
static VMBUS_CHAN_ATTR_RO(in_mask);
-static ssize_t read_avail_show(const struct vmbus_channel *channel, char *buf)
+static ssize_t read_avail_show(struct vmbus_channel *channel, char *buf)
{
- const struct hv_ring_buffer_info *rbi = &channel->inbound;
+ struct hv_ring_buffer_info *rbi = &channel->inbound;
+ ssize_t ret;
- return sprintf(buf, "%u\n", hv_get_bytes_to_read(rbi));
+ mutex_lock(&rbi->ring_buffer_mutex);
+ if (!rbi->ring_buffer) {
+ mutex_unlock(&rbi->ring_buffer_mutex);
+ return -EINVAL;
+ }
+
+ ret = sprintf(buf, "%u\n", hv_get_bytes_to_read(rbi));
+ mutex_unlock(&rbi->ring_buffer_mutex);
+ return ret;
}
static VMBUS_CHAN_ATTR_RO(read_avail);
-static ssize_t write_avail_show(const struct vmbus_channel *channel, char *buf)
+static ssize_t write_avail_show(struct vmbus_channel *channel, char *buf)
{
- const struct hv_ring_buffer_info *rbi = &channel->outbound;
+ struct hv_ring_buffer_info *rbi = &channel->outbound;
+ ssize_t ret;
- return sprintf(buf, "%u\n", hv_get_bytes_to_write(rbi));
+ mutex_lock(&rbi->ring_buffer_mutex);
+ if (!rbi->ring_buffer) {
+ mutex_unlock(&rbi->ring_buffer_mutex);
+ return -EINVAL;
+ }
+
+ ret = sprintf(buf, "%u\n", hv_get_bytes_to_write(rbi));
+ mutex_unlock(&rbi->ring_buffer_mutex);
+ return ret;
}
static VMBUS_CHAN_ATTR_RO(write_avail);
-static ssize_t show_target_cpu(const struct vmbus_channel *channel, char *buf)
+static ssize_t target_cpu_show(struct vmbus_channel *channel, char *buf)
{
return sprintf(buf, "%u\n", channel->target_cpu);
}
-static VMBUS_CHAN_ATTR(cpu, S_IRUGO, show_target_cpu, NULL);
+static ssize_t target_cpu_store(struct vmbus_channel *channel,
+ const char *buf, size_t count)
+{
+ u32 target_cpu, origin_cpu;
+ ssize_t ret = count;
-static ssize_t channel_pending_show(const struct vmbus_channel *channel,
+ if (vmbus_proto_version < VERSION_WIN10_V4_1)
+ return -EIO;
+
+ if (sscanf(buf, "%uu", &target_cpu) != 1)
+ return -EIO;
+
+ /* Validate target_cpu for the cpumask_test_cpu() operation below. */
+ if (target_cpu >= nr_cpumask_bits)
+ return -EINVAL;
+
+ /* No CPUs should come up or down during this. */
+ cpus_read_lock();
+
+ if (!cpu_online(target_cpu)) {
+ cpus_read_unlock();
+ return -EINVAL;
+ }
+
+ /*
+ * Synchronizes target_cpu_store() and channel closure:
+ *
+ * { Initially: state = CHANNEL_OPENED }
+ *
+ * CPU1 CPU2
+ *
+ * [target_cpu_store()] [vmbus_disconnect_ring()]
+ *
+ * LOCK channel_mutex LOCK channel_mutex
+ * LOAD r1 = state LOAD r2 = state
+ * IF (r1 == CHANNEL_OPENED) IF (r2 == CHANNEL_OPENED)
+ * SEND MODIFYCHANNEL STORE state = CHANNEL_OPEN
+ * [...] SEND CLOSECHANNEL
+ * UNLOCK channel_mutex UNLOCK channel_mutex
+ *
+ * Forbids: r1 == r2 == CHANNEL_OPENED (i.e., CPU1's LOCK precedes
+ * CPU2's LOCK) && CPU2's SEND precedes CPU1's SEND
+ *
+ * Note. The host processes the channel messages "sequentially", in
+ * the order in which they are received on a per-partition basis.
+ */
+ mutex_lock(&vmbus_connection.channel_mutex);
+
+ /*
+ * Hyper-V will ignore MODIFYCHANNEL messages for "non-open" channels;
+ * avoid sending the message and fail here for such channels.
+ */
+ if (channel->state != CHANNEL_OPENED_STATE) {
+ ret = -EIO;
+ goto cpu_store_unlock;
+ }
+
+ origin_cpu = channel->target_cpu;
+ if (target_cpu == origin_cpu)
+ goto cpu_store_unlock;
+
+ if (vmbus_send_modifychannel(channel->offermsg.child_relid,
+ hv_cpu_number_to_vp_number(target_cpu))) {
+ ret = -EIO;
+ goto cpu_store_unlock;
+ }
+
+ /*
+ * Warning. At this point, there is *no* guarantee that the host will
+ * have successfully processed the vmbus_send_modifychannel() request.
+ * See the header comment of vmbus_send_modifychannel() for more info.
+ *
+ * Lags in the processing of the above vmbus_send_modifychannel() can
+ * result in missed interrupts if the "old" target CPU is taken offline
+ * before Hyper-V starts sending interrupts to the "new" target CPU.
+ * But apart from this offlining scenario, the code tolerates such
+ * lags. It will function correctly even if a channel interrupt comes
+ * in on a CPU that is different from the channel target_cpu value.
+ */
+
+ channel->target_cpu = target_cpu;
+
+ /* See init_vp_index(). */
+ if (hv_is_perf_channel(channel))
+ hv_update_alloced_cpus(origin_cpu, target_cpu);
+
+ /* Currently set only for storvsc channels. */
+ if (channel->change_target_cpu_callback) {
+ (*channel->change_target_cpu_callback)(channel,
+ origin_cpu, target_cpu);
+ }
+
+cpu_store_unlock:
+ mutex_unlock(&vmbus_connection.channel_mutex);
+ cpus_read_unlock();
+ return ret;
+}
+static VMBUS_CHAN_ATTR(cpu, 0644, target_cpu_show, target_cpu_store);
+
+static ssize_t channel_pending_show(struct vmbus_channel *channel,
char *buf)
{
return sprintf(buf, "%d\n",
@@ -1464,7 +1814,7 @@
}
static VMBUS_CHAN_ATTR(pending, S_IRUGO, channel_pending_show, NULL);
-static ssize_t channel_latency_show(const struct vmbus_channel *channel,
+static ssize_t channel_latency_show(struct vmbus_channel *channel,
char *buf)
{
return sprintf(buf, "%d\n",
@@ -1473,26 +1823,58 @@
}
static VMBUS_CHAN_ATTR(latency, S_IRUGO, channel_latency_show, NULL);
-static ssize_t channel_interrupts_show(const struct vmbus_channel *channel, char *buf)
+static ssize_t channel_interrupts_show(struct vmbus_channel *channel, char *buf)
{
return sprintf(buf, "%llu\n", channel->interrupts);
}
static VMBUS_CHAN_ATTR(interrupts, S_IRUGO, channel_interrupts_show, NULL);
-static ssize_t channel_events_show(const struct vmbus_channel *channel, char *buf)
+static ssize_t channel_events_show(struct vmbus_channel *channel, char *buf)
{
return sprintf(buf, "%llu\n", channel->sig_events);
}
static VMBUS_CHAN_ATTR(events, S_IRUGO, channel_events_show, NULL);
-static ssize_t subchannel_monitor_id_show(const struct vmbus_channel *channel,
+static ssize_t channel_intr_in_full_show(struct vmbus_channel *channel,
+ char *buf)
+{
+ return sprintf(buf, "%llu\n",
+ (unsigned long long)channel->intr_in_full);
+}
+static VMBUS_CHAN_ATTR(intr_in_full, 0444, channel_intr_in_full_show, NULL);
+
+static ssize_t channel_intr_out_empty_show(struct vmbus_channel *channel,
+ char *buf)
+{
+ return sprintf(buf, "%llu\n",
+ (unsigned long long)channel->intr_out_empty);
+}
+static VMBUS_CHAN_ATTR(intr_out_empty, 0444, channel_intr_out_empty_show, NULL);
+
+static ssize_t channel_out_full_first_show(struct vmbus_channel *channel,
+ char *buf)
+{
+ return sprintf(buf, "%llu\n",
+ (unsigned long long)channel->out_full_first);
+}
+static VMBUS_CHAN_ATTR(out_full_first, 0444, channel_out_full_first_show, NULL);
+
+static ssize_t channel_out_full_total_show(struct vmbus_channel *channel,
+ char *buf)
+{
+ return sprintf(buf, "%llu\n",
+ (unsigned long long)channel->out_full_total);
+}
+static VMBUS_CHAN_ATTR(out_full_total, 0444, channel_out_full_total_show, NULL);
+
+static ssize_t subchannel_monitor_id_show(struct vmbus_channel *channel,
char *buf)
{
return sprintf(buf, "%u\n", channel->offermsg.monitorid);
}
static VMBUS_CHAN_ATTR(monitor_id, S_IRUGO, subchannel_monitor_id_show, NULL);
-static ssize_t subchannel_id_show(const struct vmbus_channel *channel,
+static ssize_t subchannel_id_show(struct vmbus_channel *channel,
char *buf)
{
return sprintf(buf, "%u\n",
@@ -1510,6 +1892,10 @@
&chan_attr_latency.attr,
&chan_attr_interrupts.attr,
&chan_attr_events.attr,
+ &chan_attr_intr_in_full.attr,
+ &chan_attr_intr_out_empty.attr,
+ &chan_attr_out_full_first.attr,
+ &chan_attr_out_full_total.attr,
&chan_attr_monitor_id.attr,
&chan_attr_subchannel_id.attr,
NULL
@@ -1592,8 +1978,8 @@
* vmbus_device_create - Creates and registers a new child device
* on the vmbus.
*/
-struct hv_device *vmbus_device_create(const uuid_le *type,
- const uuid_le *instance,
+struct hv_device *vmbus_device_create(const guid_t *type,
+ const guid_t *instance,
struct vmbus_channel *channel)
{
struct hv_device *child_device_obj;
@@ -1605,11 +1991,9 @@
}
child_device_obj->channel = channel;
- memcpy(&child_device_obj->dev_type, type, sizeof(uuid_le));
- memcpy(&child_device_obj->dev_instance, instance,
- sizeof(uuid_le));
+ guid_copy(&child_device_obj->dev_type, type);
+ guid_copy(&child_device_obj->dev_instance, instance);
child_device_obj->vendor_id = 0x1414; /* MSFT vendor ID */
-
return child_device_obj;
}
@@ -1623,7 +2007,7 @@
int ret;
dev_set_name(&child_device_obj->device, "%pUl",
- child_device_obj->channel->offermsg.offer.if_instance.b);
+ &child_device_obj->channel->offermsg.offer.if_instance);
child_device_obj->device.bus = &hv_bus;
child_device_obj->device.parent = &hv_acpi_dev->dev;
@@ -1636,6 +2020,7 @@
ret = device_register(&child_device_obj->device);
if (ret) {
pr_err("Unable to register child device\n");
+ put_device(&child_device_obj->device);
return ret;
}
@@ -1652,6 +2037,7 @@
pr_err("Unable to register primary channeln");
goto err_kset_unregister;
}
+ hv_debug_add_dev_dir(child_device_obj);
return 0;
@@ -1694,6 +2080,7 @@
struct resource *new_res;
struct resource **old_res = &hyperv_mmio;
struct resource **prev_res = NULL;
+ struct resource r;
switch (res->type) {
@@ -1711,6 +2098,23 @@
start = res->data.address64.address.minimum;
end = res->data.address64.address.maximum;
break;
+
+ /*
+ * The IRQ information is needed only on ARM64, which Hyper-V
+ * sets up in the extended format. IRQ information is present
+ * on x86/x64 in the non-extended format but it is not used by
+ * Linux. So don't bother checking for the non-extended format.
+ */
+ case ACPI_RESOURCE_TYPE_EXTENDED_IRQ:
+ if (!acpi_dev_resource_interrupt(res, 0, &r)) {
+ pr_err("Unable to parse Hyper-V ACPI interrupt\n");
+ return AE_ERROR;
+ }
+ /* ARM64 INTID for VMbus */
+ vmbus_interrupt = res->data.extended_irq.interrupts[0];
+ /* Linux IRQ number */
+ vmbus_irq = r.start;
+ return AE_OK;
default:
/* Unused resource type */
@@ -1848,12 +2252,12 @@
bool fb_overlap_ok)
{
struct resource *iter, *shadow;
- resource_size_t range_min, range_max, start;
+ resource_size_t range_min, range_max, start, end;
const char *dev_n = dev_name(&device_obj->device);
int retval;
retval = -ENXIO;
- down(&hyperv_mmio_lock);
+ mutex_lock(&hyperv_mmio_lock);
/*
* If overlaps with frame buffers are allowed, then first attempt to
@@ -1883,6 +2287,14 @@
range_max = iter->end;
start = (range_min + align - 1) & ~(align - 1);
for (; start + size - 1 <= range_max; start += align) {
+ end = start + size - 1;
+
+ /* Skip the whole fb_mmio region if not fb_overlap_ok */
+ if (!fb_overlap_ok && fb_mmio &&
+ (((start >= fb_mmio->start) && (start <= fb_mmio->end)) ||
+ ((end >= fb_mmio->start) && (end <= fb_mmio->end))))
+ continue;
+
shadow = __request_region(iter, start, size, NULL,
IORESOURCE_BUSY);
if (!shadow)
@@ -1900,7 +2312,7 @@
}
exit:
- up(&hyperv_mmio_lock);
+ mutex_unlock(&hyperv_mmio_lock);
return retval;
}
EXPORT_SYMBOL_GPL(vmbus_allocate_mmio);
@@ -1917,7 +2329,7 @@
{
struct resource *iter;
- down(&hyperv_mmio_lock);
+ mutex_lock(&hyperv_mmio_lock);
for (iter = hyperv_mmio; iter; iter = iter->sibling) {
if ((iter->start >= start + size) || (iter->end <= start))
continue;
@@ -1925,7 +2337,7 @@
__release_region(iter, start, size);
}
release_mem_region(start, size);
- up(&hyperv_mmio_lock);
+ mutex_unlock(&hyperv_mmio_lock);
}
EXPORT_SYMBOL_GPL(vmbus_free_mmio);
@@ -1967,12 +2379,163 @@
return ret_val;
}
+#ifdef CONFIG_PM_SLEEP
+static int vmbus_bus_suspend(struct device *dev)
+{
+ struct vmbus_channel *channel, *sc;
+
+ while (atomic_read(&vmbus_connection.offer_in_progress) != 0) {
+ /*
+ * We wait here until the completion of any channel
+ * offers that are currently in progress.
+ */
+ msleep(1);
+ }
+
+ mutex_lock(&vmbus_connection.channel_mutex);
+ list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
+ if (!is_hvsock_channel(channel))
+ continue;
+
+ vmbus_force_channel_rescinded(channel);
+ }
+ mutex_unlock(&vmbus_connection.channel_mutex);
+
+ /*
+ * Wait until all the sub-channels and hv_sock channels have been
+ * cleaned up. Sub-channels should be destroyed upon suspend, otherwise
+ * they would conflict with the new sub-channels that will be created
+ * in the resume path. hv_sock channels should also be destroyed, but
+ * a hv_sock channel of an established hv_sock connection can not be
+ * really destroyed since it may still be referenced by the userspace
+ * application, so we just force the hv_sock channel to be rescinded
+ * by vmbus_force_channel_rescinded(), and the userspace application
+ * will thoroughly destroy the channel after hibernation.
+ *
+ * Note: the counter nr_chan_close_on_suspend may never go above 0 if
+ * the VM has no sub-channel and hv_sock channel, e.g. a 1-vCPU VM.
+ */
+ if (atomic_read(&vmbus_connection.nr_chan_close_on_suspend) > 0)
+ wait_for_completion(&vmbus_connection.ready_for_suspend_event);
+
+ if (atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) != 0) {
+ pr_err("Can not suspend due to a previous failed resuming\n");
+ return -EBUSY;
+ }
+
+ mutex_lock(&vmbus_connection.channel_mutex);
+
+ list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
+ /*
+ * Remove the channel from the array of channels and invalidate
+ * the channel's relid. Upon resume, vmbus_onoffer() will fix
+ * up the relid (and other fields, if necessary) and add the
+ * channel back to the array.
+ */
+ vmbus_channel_unmap_relid(channel);
+ channel->offermsg.child_relid = INVALID_RELID;
+
+ if (is_hvsock_channel(channel)) {
+ if (!channel->rescind) {
+ pr_err("hv_sock channel not rescinded!\n");
+ WARN_ON_ONCE(1);
+ }
+ continue;
+ }
+
+ list_for_each_entry(sc, &channel->sc_list, sc_list) {
+ pr_err("Sub-channel not deleted!\n");
+ WARN_ON_ONCE(1);
+ }
+
+ atomic_inc(&vmbus_connection.nr_chan_fixup_on_resume);
+ }
+
+ mutex_unlock(&vmbus_connection.channel_mutex);
+
+ vmbus_initiate_unload(false);
+
+ /* Reset the event for the next resume. */
+ reinit_completion(&vmbus_connection.ready_for_resume_event);
+
+ return 0;
+}
+
+static int vmbus_bus_resume(struct device *dev)
+{
+ struct vmbus_channel_msginfo *msginfo;
+ size_t msgsize;
+ int ret;
+
+ /*
+ * We only use the 'vmbus_proto_version', which was in use before
+ * hibernation, to re-negotiate with the host.
+ */
+ if (!vmbus_proto_version) {
+ pr_err("Invalid proto version = 0x%x\n", vmbus_proto_version);
+ return -EINVAL;
+ }
+
+ msgsize = sizeof(*msginfo) +
+ sizeof(struct vmbus_channel_initiate_contact);
+
+ msginfo = kzalloc(msgsize, GFP_KERNEL);
+
+ if (msginfo == NULL)
+ return -ENOMEM;
+
+ ret = vmbus_negotiate_version(msginfo, vmbus_proto_version);
+
+ kfree(msginfo);
+
+ if (ret != 0)
+ return ret;
+
+ WARN_ON(atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) == 0);
+
+ vmbus_request_offers();
+
+ if (wait_for_completion_timeout(
+ &vmbus_connection.ready_for_resume_event, 10 * HZ) == 0)
+ pr_err("Some vmbus device is missing after suspending?\n");
+
+ /* Reset the event for the next suspend. */
+ reinit_completion(&vmbus_connection.ready_for_suspend_event);
+
+ return 0;
+}
+#else
+#define vmbus_bus_suspend NULL
+#define vmbus_bus_resume NULL
+#endif /* CONFIG_PM_SLEEP */
+
static const struct acpi_device_id vmbus_acpi_device_ids[] = {
{"VMBUS", 0},
{"VMBus", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, vmbus_acpi_device_ids);
+
+/*
+ * Note: we must use the "no_irq" ops, otherwise hibernation can not work with
+ * PCI device assignment, because "pci_dev_pm_ops" uses the "noirq" ops: in
+ * the resume path, the pci "noirq" restore op runs before "non-noirq" op (see
+ * resume_target_kernel() -> dpm_resume_start(), and hibernation_restore() ->
+ * dpm_resume_end()). This means vmbus_bus_resume() and the pci-hyperv's
+ * resume callback must also run via the "noirq" ops.
+ *
+ * Set suspend_noirq/resume_noirq to NULL for Suspend-to-Idle: see the comment
+ * earlier in this file before vmbus_pm.
+ */
+
+static const struct dev_pm_ops vmbus_bus_pm = {
+ .suspend_noirq = NULL,
+ .resume_noirq = NULL,
+ .freeze_noirq = vmbus_bus_suspend,
+ .thaw_noirq = vmbus_bus_resume,
+ .poweroff_noirq = vmbus_bus_suspend,
+ .restore_noirq = vmbus_bus_resume
+};
static struct acpi_driver vmbus_acpi_driver = {
.name = "vmbus",
@@ -1981,28 +2544,75 @@
.add = vmbus_acpi_add,
.remove = vmbus_acpi_remove,
},
+ .drv.pm = &vmbus_bus_pm,
};
static void hv_kexec_handler(void)
{
- hv_synic_clockevents_cleanup();
+ hv_stimer_global_cleanup();
vmbus_initiate_unload(false);
/* Make sure conn_state is set as hv_synic_cleanup checks for it */
mb();
cpuhp_remove_state(hyperv_cpuhp_online);
- hyperv_cleanup();
};
static void hv_crash_handler(struct pt_regs *regs)
{
+ int cpu;
+
vmbus_initiate_unload(true);
/*
* In crash handler we can't schedule synic cleanup for all CPUs,
* doing the cleanup for current CPU only. This should be sufficient
* for kdump.
*/
- hv_synic_cleanup(smp_processor_id());
- hyperv_cleanup();
+ cpu = smp_processor_id();
+ hv_stimer_cleanup(cpu);
+ hv_synic_disable_regs(cpu);
+};
+
+static int hv_synic_suspend(void)
+{
+ /*
+ * When we reach here, all the non-boot CPUs have been offlined.
+ * If we're in a legacy configuration where stimer Direct Mode is
+ * not enabled, the stimers on the non-boot CPUs have been unbound
+ * in hv_synic_cleanup() -> hv_stimer_legacy_cleanup() ->
+ * hv_stimer_cleanup() -> clockevents_unbind_device().
+ *
+ * hv_synic_suspend() only runs on CPU0 with interrupts disabled.
+ * Here we do not call hv_stimer_legacy_cleanup() on CPU0 because:
+ * 1) it's unnecessary as interrupts remain disabled between
+ * syscore_suspend() and syscore_resume(): see create_image() and
+ * resume_target_kernel()
+ * 2) the stimer on CPU0 is automatically disabled later by
+ * syscore_suspend() -> timekeeping_suspend() -> tick_suspend() -> ...
+ * -> clockevents_shutdown() -> ... -> hv_ce_shutdown()
+ * 3) a warning would be triggered if we call
+ * clockevents_unbind_device(), which may sleep, in an
+ * interrupts-disabled context.
+ */
+
+ hv_synic_disable_regs(0);
+
+ return 0;
+}
+
+static void hv_synic_resume(void)
+{
+ hv_synic_enable_regs(0);
+
+ /*
+ * Note: we don't need to call hv_stimer_init(0), because the timer
+ * on CPU0 is not unbound in hv_synic_suspend(), and the timer is
+ * automatically re-enabled in timekeeping_resume().
+ */
+}
+
+/* The callbacks run only on CPU0, with irqs_disabled. */
+static struct syscore_ops hv_synic_syscore_ops = {
+ .suspend = hv_synic_suspend,
+ .resume = hv_synic_resume,
};
static int __init hv_acpi_init(void)
@@ -2027,6 +2637,7 @@
ret = -ETIMEDOUT;
goto cleanup;
}
+ hv_debug_init();
ret = vmbus_bus_init();
if (ret)
@@ -2034,6 +2645,8 @@
hv_setup_kexec_handler(hv_kexec_handler);
hv_setup_crash_handler(hv_crash_handler);
+
+ register_syscore_ops(&hv_synic_syscore_ops);
return 0;
@@ -2047,10 +2660,12 @@
{
int cpu;
+ unregister_syscore_ops(&hv_synic_syscore_ops);
+
hv_remove_kexec_handler();
hv_remove_crash_handler();
vmbus_connection.conn_state = DISCONNECTED;
- hv_synic_clockevents_cleanup();
+ hv_stimer_global_cleanup();
vmbus_disconnect();
hv_remove_vmbus_irq();
for_each_online_cpu(cpu) {
@@ -2059,14 +2674,22 @@
tasklet_kill(&hv_cpu->msg_dpc);
}
+ hv_debug_rm_all_dir();
+
vmbus_free_channels();
+ kfree(vmbus_connection.channels);
if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
kmsg_dump_unregister(&hv_kmsg_dumper);
unregister_die_notifier(&hyperv_die_block);
- atomic_notifier_chain_unregister(&panic_notifier_list,
- &hyperv_panic_block);
}
+
+ /*
+ * The panic notifier is always registered, hence we should
+ * also unconditionally unregister it here as well.
+ */
+ atomic_notifier_chain_unregister(&panic_notifier_list,
+ &hyperv_panic_block);
free_page((unsigned long)hv_panic_page);
unregister_sysctl_table(hv_ctl_table_hdr);
@@ -2080,6 +2703,7 @@
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Microsoft Hyper-V VMBus Driver");
subsys_initcall(hv_acpi_init);
module_exit(vmbus_exit);
--
Gitblit v1.6.2