[PATCH RESEND 00/15] Drivers: hv: vmbus: Miscellaneous fixes/enhancements

[PATCH RESEND 00/15] Drivers: hv: vmbus: Miscellaneous fixes/enhancements

[K. Y. Srinivasan]

Windows hosts starting with Ws2012 R2 permit re-establishing the vmbus
connection from the guest. This patch-set includes patches from Vitaly
to cleanup the VMBUS unload path so we can potentially reload the driver.
Also included here are some bug fixes from Dexuan and me.

Dexuan Cui (3):
  hv: hv_util: move vmbus_open() to a later place
  hv: vmbus_post_msg: retry the hypercall on some transient errors
  hv: vmbus_open(): reset the channel state on ENOMEM

K. Y. Srinivasan (2):
  Drivers: hv: vmbus: Fix a bug in the error path in vmbus_open()
  Drivers: hv: vmbus: Add support for the NetworkDirect GUID

Nicholas Mc Guire (3):
  hv: channel: match var type to return type of wait_for_completion
  hv: channel_mgmt: match var type to return type of
    wait_for_completion
  hv: hv_balloon: match var type to return type of wait_for_completion

Vitaly Kuznetsov (7):
  Drivers: hv: vmbus: prevent cpu offlining on newer hypervisors
  Drivers: hv: vmbus: rename channel work queues
  Drivers: hv: vmbus: avoid double kfree for device_obj
  Drivers: hv: vmbus: teardown hv_vmbus_con workqueue and
    vmbus_connection pages on shutdown
  drivers: hv: vmbus: Teardown synthetic interrupt controllers on
    module unload
  clockevents: export clockevents_unbind_device instead of
    clockevents_unbind
  Drivers: hv: vmbus: Teardown clockevent devices on module unload

 arch/x86/include/uapi/asm/hyperv.h |    2 +
 drivers/hv/channel.c               |   18 ++++++++----
 drivers/hv/channel_mgmt.c          |   11 +++++--
 drivers/hv/connection.c            |   28 ++++++++++++++-----
 drivers/hv/hv.c                    |   34 +++++++++++++++++++++--
 drivers/hv/hv_balloon.c            |    3 +-
 drivers/hv/hv_util.c               |   11 ++++---
 drivers/hv/hyperv_vmbus.h          |    3 ++
 drivers/hv/vmbus_drv.c             |   53 +++++++++++++++++++++++++++++++++---
 include/linux/hyperv.h             |   13 +++++++++
 kernel/time/clockevents.c          |    2 +-
 11 files changed, 148 insertions(+), 30 deletions(-)

-- 
1.7.4.1

[PATCH RESEND 01/15] Drivers: hv: vmbus: prevent cpu offlining on newer hypervisors

[K. Y. Srinivasan]

From: Vitaly Kuznetsov <vkuznets@redhat.com>

When an SMP Hyper-V guest is running on top of 2012R2 Server and secondary
cpus are sent offline (with echo 0 > /sys/devices/system/cpu/cpu$cpu/online)
the system freeze is observed. This happens due to the fact that on newer
hypervisors (Win8, WS2012R2, ...) vmbus channel handlers are distributed
across all cpus (see init_vp_index() function in drivers/hv/channel_mgmt.c)
and on cpu offlining nobody reassigns them to CPU0. Prevent cpu offlining
when vmbus is loaded until the issue is fixed host-side.

This patch also disables hibernation but it is OK as it is also broken (MCE
error is hit on resume). Suspend still works.

Tested with WS2008R2 and WS2012R2.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/vmbus_drv.c |   36 ++++++++++++++++++++++++++++++++++++
 1 files changed, 36 insertions(+), 0 deletions(-)

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 35e3f42..90c3400 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -33,6 +33,7 @@
 #include <linux/hyperv.h>
 #include <linux/kernel_stat.h>
 #include <linux/clockchips.h>
+#include <linux/cpu.h>
 #include <asm/hyperv.h>
 #include <asm/hypervisor.h>
 #include <asm/mshyperv.h>
@@ -704,6 +705,39 @@ static void vmbus_isr(void)
 	}
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+static int hyperv_cpu_disable(void)
+{
+	return -ENOSYS;
+}
+
+static void hv_cpu_hotplug_quirk(bool vmbus_loaded)
+{
+	static void *previous_cpu_disable;
+
+	/*
+	 * Offlining a CPU when running on newer hypervisors (WS2012R2, Win8,
+	 * ...) is not supported at this moment as channel interrupts are
+	 * distributed across all of them.
+	 */
+
+	if ((vmbus_proto_version == VERSION_WS2008) ||
+	    (vmbus_proto_version == VERSION_WIN7))
+		return;
+
+	if (vmbus_loaded) {
+		previous_cpu_disable = smp_ops.cpu_disable;
+		smp_ops.cpu_disable = hyperv_cpu_disable;
+		pr_notice("CPU offlining is not supported by hypervisor\n");
+	} else if (previous_cpu_disable)
+		smp_ops.cpu_disable = previous_cpu_disable;
+}
+#else
+static void hv_cpu_hotplug_quirk(bool vmbus_loaded)
+{
+}
+#endif
+
 /*
  * vmbus_bus_init -Main vmbus driver initialization routine.
  *
@@ -744,6 +778,7 @@ static int vmbus_bus_init(int irq)
 	if (ret)
 		goto err_alloc;
 
+	hv_cpu_hotplug_quirk(true);
 	vmbus_request_offers();
 
 	return 0;
@@ -997,6 +1032,7 @@ static void __exit vmbus_exit(void)
 	bus_unregister(&hv_bus);
 	hv_cleanup();
 	acpi_bus_unregister_driver(&vmbus_acpi_driver);
+	hv_cpu_hotplug_quirk(false);
 }
 
 
-- 
1.7.4.1

[PATCH RESEND 02/15] Drivers: hv: vmbus: rename channel work queues

[K. Y. Srinivasan]

From: Vitaly Kuznetsov <vkuznets@redhat.com>

All channel work queues are named 'hv_vmbus_ctl', this makes them
indistinguishable in ps output and makes it hard to link to the corresponding
vmbus device. Rename them to hv_vmbus_ctl/N and make vmbus device names match,
e.g. now vmbus_1 device is served by hv_vmbus_ctl/1 work queue.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/channel_mgmt.c |    5 ++++-
 drivers/hv/vmbus_drv.c    |    6 ++----
 include/linux/hyperv.h    |    3 +++
 3 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 3736f71..ba4b25f 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -139,19 +139,22 @@ EXPORT_SYMBOL_GPL(vmbus_prep_negotiate_resp);
  */
 static struct vmbus_channel *alloc_channel(void)
 {
+	static atomic_t chan_num = ATOMIC_INIT(0);
 	struct vmbus_channel *channel;
 
 	channel = kzalloc(sizeof(*channel), GFP_ATOMIC);
 	if (!channel)
 		return NULL;
 
+	channel->id = atomic_inc_return(&chan_num);
 	spin_lock_init(&channel->inbound_lock);
 	spin_lock_init(&channel->lock);
 
 	INIT_LIST_HEAD(&channel->sc_list);
 	INIT_LIST_HEAD(&channel->percpu_list);
 
-	channel->controlwq = create_workqueue("hv_vmbus_ctl");
+	channel->controlwq = alloc_workqueue("hv_vmbus_ctl/%d", WQ_MEM_RECLAIM,
+					     1, channel->id);
 	if (!channel->controlwq) {
 		kfree(channel);
 		return NULL;
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 90c3400..4e3760c 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -875,10 +875,8 @@ int vmbus_device_register(struct hv_device *child_device_obj)
 {
 	int ret = 0;
 
-	static atomic_t device_num = ATOMIC_INIT(0);
-
-	dev_set_name(&child_device_obj->device, "vmbus_0_%d",
-		     atomic_inc_return(&device_num));
+	dev_set_name(&child_device_obj->device, "vmbus_%d",
+		     child_device_obj->channel->id);
 
 	child_device_obj->device.bus = &hv_bus;
 	child_device_obj->device.parent = &hv_acpi_dev->dev;
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 5a2ba67..26a32b7 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -646,6 +646,9 @@ struct hv_input_signal_event_buffer {
 };
 
 struct vmbus_channel {
+	/* Unique channel id */
+	int id;
+
 	struct list_head listentry;
 
 	struct hv_device *device_obj;
-- 
1.7.4.1

[PATCH RESEND 03/15] Drivers: hv: vmbus: avoid double kfree for device_obj

[K. Y. Srinivasan]

From: Vitaly Kuznetsov <vkuznets@redhat.com>

On driver shutdown device_obj is being freed twice:
1) In vmbus_free_channels()
2) vmbus_device_release() (which is being triggered by device_unregister() in
   vmbus_device_unregister().
This double kfree leads to the following sporadic crash on driver unload:

[   23.469876] general protection fault: 0000 [#1] SMP
[   23.470036] Modules linked in: hv_vmbus(-)
[   23.470036] CPU: 2 PID: 213 Comm: rmmod Not tainted 3.19.0-rc5_bug923184+ #488
[   23.470036] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090006  05/23/2012
[   23.470036] task: ffff880036ef1cb0 ti: ffff880036ce8000 task.ti: ffff880036ce8000
[   23.470036] RIP: 0010:[<ffffffff811d2e1b>]  [<ffffffff811d2e1b>] __kmalloc_node_track_caller+0xdb/0x1e0
[   23.470036] RSP: 0018:ffff880036cebcc8  EFLAGS: 00010246
...

When this crash does not happen on driver unload the similar one is expected if
we try to load hv_vmbus again.

Remove kfree from vmbus_free_channels() as freeing it from
vmbus_device_release() seems right.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/channel_mgmt.c |    1 -
 1 files changed, 0 insertions(+), 1 deletions(-)

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index ba4b25f..36bacc7 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -262,7 +262,6 @@ void vmbus_free_channels(void)
 
 	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
 		vmbus_device_unregister(channel->device_obj);
-		kfree(channel->device_obj);
 		free_channel(channel);
 	}
 }
-- 
1.7.4.1

[PATCH RESEND 04/15] Drivers: hv: vmbus: teardown hv_vmbus_con workqueue and vmbus_connection pages on shutdown

[K. Y. Srinivasan]

From: Vitaly Kuznetsov <vkuznets@redhat.com>

We need to destroy hv_vmbus_con on module shutdown, otherwise the following
crash is sometimes observed:

[   76.569845] hv_vmbus: Hyper-V Host Build:9600-6.3-17-0.17039; Vmbus version:3.0
[   82.598859] BUG: unable to handle kernel paging request at ffffffffa0003480
[   82.599287] IP: [<ffffffffa0003480>] 0xffffffffa0003480
[   82.599287] PGD 1f34067 PUD 1f35063 PMD 3f72d067 PTE 0
[   82.599287] Oops: 0010 [#1] SMP
[   82.599287] Modules linked in: [last unloaded: hv_vmbus]
[   82.599287] CPU: 0 PID: 26 Comm: kworker/0:1 Not tainted 3.19.0-rc5_bug923184+ #488
[   82.599287] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v1.0 11/26/2012
[   82.599287] Workqueue: hv_vmbus_con 0xffffffffa0003480
[   82.599287] task: ffff88007b6ddfa0 ti: ffff88007f8f8000 task.ti: ffff88007f8f8000
[   82.599287] RIP: 0010:[<ffffffffa0003480>]  [<ffffffffa0003480>] 0xffffffffa0003480
[   82.599287] RSP: 0018:ffff88007f8fbe00  EFLAGS: 00010202
...

To avoid memory leaks we need to free monitor_pages and int_page for
vmbus_connection. Implement vmbus_disconnect() function by separating cleanup
path from vmbus_connect().

As we use hv_vmbus_con to release channels (see free_channel() in channel_mgmt.c)
we need to make sure the work was done before we remove the queue, do that with
drain_workqueue(). We also need to avoid handling messages  which can (potentially)
create new channels, so set vmbus_connection.conn_state = DISCONNECTED at the very
beginning of vmbus_exit() and check for that in vmbus_onmessage_work().

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/connection.c   |   17 ++++++++++++-----
 drivers/hv/hyperv_vmbus.h |    1 +
 drivers/hv/vmbus_drv.c    |    6 ++++++
 3 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index a63a795..c4acd1c 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -216,10 +216,21 @@ int vmbus_connect(void)
 
 cleanup:
 	pr_err("Unable to connect to host\n");
+
 	vmbus_connection.conn_state = DISCONNECTED;
+	vmbus_disconnect();
+
+	kfree(msginfo);
+
+	return ret;
+}
 
-	if (vmbus_connection.work_queue)
+void vmbus_disconnect(void)
+{
+	if (vmbus_connection.work_queue) {
+		drain_workqueue(vmbus_connection.work_queue);
 		destroy_workqueue(vmbus_connection.work_queue);
+	}
 
 	if (vmbus_connection.int_page) {
 		free_pages((unsigned long)vmbus_connection.int_page, 0);
@@ -230,10 +241,6 @@ cleanup:
 	free_pages((unsigned long)vmbus_connection.monitor_pages[1], 0);
 	vmbus_connection.monitor_pages[0] = NULL;
 	vmbus_connection.monitor_pages[1] = NULL;
-
-	kfree(msginfo);
-
-	return ret;
 }
 
 /*
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 44b1c94..6cf2de9 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -692,6 +692,7 @@ void vmbus_free_channels(void);
 /* Connection interface */
 
 int vmbus_connect(void);
+void vmbus_disconnect(void);
 
 int vmbus_post_msg(void *buffer, size_t buflen);
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 4e3760c..dbd3124 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -574,6 +574,10 @@ static void vmbus_onmessage_work(struct work_struct *work)
 {
 	struct onmessage_work_context *ctx;
 
+	/* Do not process messages if we're in DISCONNECTED state */
+	if (vmbus_connection.conn_state == DISCONNECTED)
+		return;
+
 	ctx = container_of(work, struct onmessage_work_context,
 			   work);
 	vmbus_onmessage(&ctx->msg);
@@ -1025,12 +1029,14 @@ cleanup:
 
 static void __exit vmbus_exit(void)
 {
+	vmbus_connection.conn_state = DISCONNECTED;
 	hv_remove_vmbus_irq();
 	vmbus_free_channels();
 	bus_unregister(&hv_bus);
 	hv_cleanup();
 	acpi_bus_unregister_driver(&vmbus_acpi_driver);
 	hv_cpu_hotplug_quirk(false);
+	vmbus_disconnect();
 }
 
 
-- 
1.7.4.1

[PATCH RESEND 05/15] drivers: hv: vmbus: Teardown synthetic interrupt controllers on module unload

[K. Y. Srinivasan]

From: Vitaly Kuznetsov <vkuznets@redhat.com>

SynIC has to be switched off when we unload the module, otherwise registered
memory pages can get corrupted after (as Hyper-V host still writes there) and
we see the following crashes for random processes:

[   89.116774] BUG: Bad page map in process sh  pte:4989c716 pmd:36f81067
[   89.159454] addr:0000000000437000 vm_flags:00000875 anon_vma:          (null) mapping:ffff88007bba55a0 index:37
[   89.226146] vma->vm_ops->fault: filemap_fault+0x0/0x410
[   89.257776] vma->vm_file->f_op->mmap: generic_file_mmap+0x0/0x60
[   89.297570] CPU: 0 PID: 215 Comm: sh Tainted: G    B          3.19.0-rc5_bug923184+ #488
[   89.353738] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090006  05/23/2012
[   89.409138]  0000000000000000 000000004e083d7b ffff880036e9fa18 ffffffff81a68d31
[   89.468724]  0000000000000000 0000000000437000 ffff880036e9fa68 ffffffff811a1e3a
[   89.519233]  000000004989c716 0000000000000037 ffffea0001edc340 0000000000437000
[   89.575751] Call Trace:
[   89.591060]  [<ffffffff81a68d31>] dump_stack+0x45/0x57
[   89.625164]  [<ffffffff811a1e3a>] print_bad_pte+0x1aa/0x250
[   89.667234]  [<ffffffff811a2c95>] vm_normal_page+0x55/0xa0
[   89.703818]  [<ffffffff811a3105>] unmap_page_range+0x425/0x8a0
[   89.737982]  [<ffffffff811a3601>] unmap_single_vma+0x81/0xf0
[   89.780385]  [<ffffffff81184320>] ? lru_deactivate_fn+0x190/0x190
[   89.820130]  [<ffffffff811a4131>] unmap_vmas+0x51/0xa0
[   89.860168]  [<ffffffff811ad12c>] exit_mmap+0xac/0x1a0
[   89.890588]  [<ffffffff810763c3>] mmput+0x63/0x100
[   89.919205]  [<ffffffff811eba48>] flush_old_exec+0x3f8/0x8b0
[   89.962135]  [<ffffffff8123b5bb>] load_elf_binary+0x32b/0x1260
[   89.998581]  [<ffffffff811a14f2>] ? get_user_pages+0x52/0x60

hv_synic_cleanup() function exists but noone calls it now. Do the following:
- call hv_synic_cleanup() on each cpu from vmbus_exit();
- write global disable bit through MSR;
- use hv_synic_free_cpu() to avoid memory leask and code duplication.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/hv.c        |    9 +++++++--
 drivers/hv/vmbus_drv.c |    4 ++++
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 50e51a5..39531dc 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -477,6 +477,7 @@ void hv_synic_cleanup(void *arg)
 	union hv_synic_sint shared_sint;
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
+	union hv_synic_scontrol sctrl;
 	int cpu = smp_processor_id();
 
 	if (!hv_context.synic_initialized)
@@ -502,6 +503,10 @@ void hv_synic_cleanup(void *arg)
 
 	wrmsrl(HV_X64_MSR_SIEFP, siefp.as_uint64);
 
-	free_page((unsigned long)hv_context.synic_message_page[cpu]);
-	free_page((unsigned long)hv_context.synic_event_page[cpu]);
+	/* Disable the global synic bit */
+	rdmsrl(HV_X64_MSR_SCONTROL, sctrl.as_uint64);
+	sctrl.enable = 0;
+	wrmsrl(HV_X64_MSR_SCONTROL, sctrl.as_uint64);
+
+	hv_synic_free_cpu(cpu);
 }
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index dbd3124..e7e35c6 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1029,11 +1029,15 @@ cleanup:
 
 static void __exit vmbus_exit(void)
 {
+	int cpu;
+
 	vmbus_connection.conn_state = DISCONNECTED;
 	hv_remove_vmbus_irq();
 	vmbus_free_channels();
 	bus_unregister(&hv_bus);
 	hv_cleanup();
+	for_each_online_cpu(cpu)
+		smp_call_function_single(cpu, hv_synic_cleanup, NULL, 1);
 	acpi_bus_unregister_driver(&vmbus_acpi_driver);
 	hv_cpu_hotplug_quirk(false);
 	vmbus_disconnect();
-- 
1.7.4.1

[PATCH RESEND 06/15] clockevents: export clockevents_unbind_device instead of clockevents_unbind

[K. Y. Srinivasan]

From: Vitaly Kuznetsov <vkuznets@redhat.com>

It looks like clockevents_unbind is being exported by mistake as:
- it is static;
- it is not listed in include/linux/clockchips.h;
- EXPORT_SYMBOL_GPL(clockevents_unbind) follows clockevents_unbind_device()
  implementation.

I think clockevents_unbind_device should be exported instead. This is going to
be used to teardown Hyper-V clockevent devices on module unload.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 kernel/time/clockevents.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 5544990..888ecc1 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -371,7 +371,7 @@ int clockevents_unbind_device(struct clock_event_device *ced, int cpu)
 	mutex_unlock(&clockevents_mutex);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(clockevents_unbind);
+EXPORT_SYMBOL_GPL(clockevents_unbind_device);
 
 /**
  * clockevents_register_device - register a clock event device
-- 
1.7.4.1

[PATCH RESEND 07/15] Drivers: hv: vmbus: Teardown clockevent devices on module unload

[K. Y. Srinivasan]

From: Vitaly Kuznetsov <vkuznets@redhat.com>

Newly introduced clockevent devices made it impossible to unload hv_vmbus
module as clockevents_config_and_register() takes additional reverence to
the module. To make it possible again we do the following:
- avoid setting dev->owner for clockevent devices;
- implement hv_synic_clockevents_cleanup() doing clockevents_unbind_device();
- call it from vmbus_exit().

In theory hv_synic_clockevents_cleanup() can be merged with hv_synic_cleanup(),
however, we call hv_synic_cleanup() from smp_call_function_single() and this
doesn't work for clockevents_unbind_device() as it does such call on its own. I
opted for a separate function.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/hv.c           |   25 ++++++++++++++++++++++++-
 drivers/hv/hyperv_vmbus.h |    2 ++
 drivers/hv/vmbus_drv.c    |    1 +
 3 files changed, 27 insertions(+), 1 deletions(-)

diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 39531dc..d3943bc 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -312,7 +312,11 @@ static void hv_init_clockevent_device(struct clock_event_device *dev, int cpu)
 	dev->features = CLOCK_EVT_FEAT_ONESHOT;
 	dev->cpumask = cpumask_of(cpu);
 	dev->rating = 1000;
-	dev->owner = THIS_MODULE;
+	/*
+	 * Avoid settint dev->owner = THIS_MODULE deliberately as doing so will
+	 * result in clockevents_config_and_register() taking additional
+	 * references to the hv_vmbus module making it impossible to unload.
+	 */
 
 	dev->set_mode = hv_ce_setmode;
 	dev->set_next_event = hv_ce_set_next_event;
@@ -470,6 +474,20 @@ void hv_synic_init(void *arg)
 }
 
 /*
+ * hv_synic_clockevents_cleanup - Cleanup clockevent devices
+ */
+void hv_synic_clockevents_cleanup(void)
+{
+	int cpu;
+
+	if (!(ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE))
+		return;
+
+	for_each_online_cpu(cpu)
+		clockevents_unbind_device(hv_context.clk_evt[cpu], cpu);
+}
+
+/*
  * hv_synic_cleanup - Cleanup routine for hv_synic_init().
  */
 void hv_synic_cleanup(void *arg)
@@ -483,6 +501,11 @@ void hv_synic_cleanup(void *arg)
 	if (!hv_context.synic_initialized)
 		return;
 
+	/* Turn off clockevent device */
+	if (ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE)
+		hv_ce_setmode(CLOCK_EVT_MODE_SHUTDOWN,
+			      hv_context.clk_evt[cpu]);
+
 	rdmsrl(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
 
 	shared_sint.masked = 1;
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 6cf2de9..b055e53 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -572,6 +572,8 @@ extern void hv_synic_init(void *irqarg);
 
 extern void hv_synic_cleanup(void *arg);
 
+extern void hv_synic_clockevents_cleanup(void);
+
 /*
  * Host version information.
  */
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index e7e35c6..da4333b 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1032,6 +1032,7 @@ static void __exit vmbus_exit(void)
 	int cpu;
 
 	vmbus_connection.conn_state = DISCONNECTED;
+	hv_synic_clockevents_cleanup();
 	hv_remove_vmbus_irq();
 	vmbus_free_channels();
 	bus_unregister(&hv_bus);
-- 
1.7.4.1

[PATCH RESEND 08/15] hv: hv_util: move vmbus_open() to a later place

[K. Y. Srinivasan]

From: Dexuan Cui <decui@microsoft.com>

Before the line vmbus_open() returns, srv->util_cb can be already running
and the variables, like util_fw_version, are needed by the srv->util_cb.

So we have to make sure the variables are initialized before the vmbus_open().

CC: "K. Y. Srinivasan" <kys@microsoft.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/hv_util.c |   11 ++++++-----
 1 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 3b9c9ef..c5be773 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -340,12 +340,8 @@ static int util_probe(struct hv_device *dev,
 
 	set_channel_read_state(dev->channel, false);
 
-	ret = vmbus_open(dev->channel, 4 * PAGE_SIZE, 4 * PAGE_SIZE, NULL, 0,
-			srv->util_cb, dev->channel);
-	if (ret)
-		goto error;
-
 	hv_set_drvdata(dev, srv);
+
 	/*
 	 * Based on the host; initialize the framework and
 	 * service version numbers we will negotiate.
@@ -365,6 +361,11 @@ static int util_probe(struct hv_device *dev,
 		hb_srv_version = HB_VERSION;
 	}
 
+	ret = vmbus_open(dev->channel, 4 * PAGE_SIZE, 4 * PAGE_SIZE, NULL, 0,
+			srv->util_cb, dev->channel);
+	if (ret)
+		goto error;
+
 	return 0;
 
 error:
-- 
1.7.4.1

[PATCH RESEND 09/15] hv: vmbus_post_msg: retry the hypercall on some transient errors

[K. Y. Srinivasan]

From: Dexuan Cui <decui@microsoft.com>

I got HV_STATUS_INVALID_CONNECTION_ID on Hyper-V 2008 R2 when keeping running
"rmmod hv_netvsc; modprobe hv_netvsc; rmmod hv_utils; modprobe hv_utils"
in a Linux guest. Looks the host has some kind of throttling mechanism if
some kinds of hypercalls are sent too frequently.
Without the patch, the driver can occasionally fail to load.

Also let's retry HV_STATUS_INSUFFICIENT_MEMORY, though we didn't get it
before.

Removed 'case -ENOMEM', since the hypervisor doesn't return this.

CC: "K. Y. Srinivasan" <kys@microsoft.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 arch/x86/include/uapi/asm/hyperv.h |    2 ++
 drivers/hv/connection.c            |   11 +++++++++--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 90c458e..ce6068d 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -225,6 +225,8 @@
 #define HV_STATUS_INVALID_HYPERCALL_CODE	2
 #define HV_STATUS_INVALID_HYPERCALL_INPUT	3
 #define HV_STATUS_INVALID_ALIGNMENT		4
+#define HV_STATUS_INSUFFICIENT_MEMORY		11
+#define HV_STATUS_INVALID_CONNECTION_ID		18
 #define HV_STATUS_INSUFFICIENT_BUFFERS		19
 
 typedef struct _HV_REFERENCE_TSC_PAGE {
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index c4acd1c..af2388f 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -440,9 +440,16 @@ int vmbus_post_msg(void *buffer, size_t buflen)
 		ret = hv_post_message(conn_id, 1, buffer, buflen);
 
 		switch (ret) {
+		case HV_STATUS_INVALID_CONNECTION_ID:
+			/*
+			 * We could get this if we send messages too
+			 * frequently.
+			 */
+			ret = -EAGAIN;
+			break;
+		case HV_STATUS_INSUFFICIENT_MEMORY:
 		case HV_STATUS_INSUFFICIENT_BUFFERS:
 			ret = -ENOMEM;
-		case -ENOMEM:
 			break;
 		case HV_STATUS_SUCCESS:
 			return ret;
@@ -452,7 +459,7 @@ int vmbus_post_msg(void *buffer, size_t buflen)
 		}
 
 		retries++;
-		msleep(100);
+		msleep(1000);
 	}
 	return ret;
 }
-- 
1.7.4.1

[PATCH RESEND 10/15] hv: vmbus_open(): reset the channel state on ENOMEM

[K. Y. Srinivasan]

From: Dexuan Cui <decui@microsoft.com>

Without this patch, the state is put to CHANNEL_OPENING_STATE, and when
the driver is loaded next time, vmbus_open() will fail immediately due to
newchannel->state != CHANNEL_OPEN_STATE.

CC: "K. Y. Srinivasan" <kys@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/channel.c |    8 +++++---
 1 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 2978f5e..26dcf26 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -89,9 +89,10 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 	out = (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO,
 		get_order(send_ringbuffer_size + recv_ringbuffer_size));
 
-	if (!out)
-		return -ENOMEM;
-
+	if (!out) {
+		err = -ENOMEM;
+		goto error0;
+	}
 
 	in = (void *)((unsigned long)out + send_ringbuffer_size);
 
@@ -199,6 +200,7 @@ error0:
 	free_pages((unsigned long)out,
 		get_order(send_ringbuffer_size + recv_ringbuffer_size));
 	kfree(open_info);
+	newchannel->state = CHANNEL_OPEN_STATE;
 	return err;
 }
 EXPORT_SYMBOL_GPL(vmbus_open);
-- 
1.7.4.1

[PATCH RESEND 11/15] hv: channel: match var type to return type of wait_for_completion

[K. Y. Srinivasan]

From: Nicholas Mc Guire <der.herr@hofr.at>

return type of wait_for_completion_timeout is unsigned long not int, this
patch changes the type of t from int to unsigned long.

Signed-off-by: Nicholas Mc Guire <der.herr@hofr.at>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/channel.c |    3 ++-
 1 files changed, 2 insertions(+), 1 deletions(-)

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 26dcf26..f687995 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -71,7 +71,8 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 	struct vmbus_channel_msginfo *open_info = NULL;
 	void *in, *out;
 	unsigned long flags;
-	int ret, t, err = 0;
+	int ret, err = 0;
+	unsigned long t;
 
 	spin_lock_irqsave(&newchannel->lock, flags);
 	if (newchannel->state == CHANNEL_OPEN_STATE) {
-- 
1.7.4.1

[PATCH RESEND 12/15] hv: channel_mgmt: match var type to return type of wait_for_completion

[K. Y. Srinivasan]

From: Nicholas Mc Guire <der.herr@hofr.at>

return type of wait_for_completion_timeout is unsigned long not int, this
patch changes the type of t from int to unsigned long.

Signed-off-by: Nicholas Mc Guire <der.herr@hofr.at>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/channel_mgmt.c |    3 ++-
 1 files changed, 2 insertions(+), 1 deletions(-)

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 36bacc7..6be93f0 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -789,7 +789,8 @@ int vmbus_request_offers(void)
 {
 	struct vmbus_channel_message_header *msg;
 	struct vmbus_channel_msginfo *msginfo;
-	int ret, t;
+	int ret;
+	unsigned long t;
 
 	msginfo = kmalloc(sizeof(*msginfo) +
 			  sizeof(struct vmbus_channel_message_header),
-- 
1.7.4.1

[PATCH RESEND 13/15] hv: hv_balloon: match var type to return type of wait_for_completion

[K. Y. Srinivasan]

From: Nicholas Mc Guire <der.herr@hofr.at>

return type of wait_for_completion_timeout is unsigned long not int, this
patch changes the type of t from int to unsigned long.

Signed-off-by: Nicholas Mc Guire <der.herr@hofr.at>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/hv_balloon.c |    3 ++-
 1 files changed, 2 insertions(+), 1 deletions(-)

diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index ff16938..965c37a 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -1414,7 +1414,8 @@ static void balloon_onchannelcallback(void *context)
 static int balloon_probe(struct hv_device *dev,
 			const struct hv_vmbus_device_id *dev_id)
 {
-	int ret, t;
+	int ret;
+	unsigned long t;
 	struct dm_version_request version_req;
 	struct dm_capabilities cap_msg;
 
-- 
1.7.4.1

[PATCH RESEND 14/15] Drivers: hv: vmbus: Fix a bug in the error path in vmbus_open()

[K. Y. Srinivasan]

Correctly rollback state if the failure occurs after we have handed over
the ownership of the buffer to the host.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Cc: stable@vger.kernel.org
---
 drivers/hv/channel.c |    7 +++++--
 1 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index f687995..bf0cf8f 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -137,7 +137,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 			   GFP_KERNEL);
 	if (!open_info) {
 		err = -ENOMEM;
-		goto error0;
+		goto error_gpadl;
 	}
 
 	init_completion(&open_info->waitevent);
@@ -153,7 +153,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 
 	if (userdatalen > MAX_USER_DEFINED_BYTES) {
 		err = -EINVAL;
-		goto error0;
+		goto error_gpadl;
 	}
 
 	if (userdatalen)
@@ -197,6 +197,9 @@ error1:
 	list_del(&open_info->msglistentry);
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 
+error_gpadl:
+	vmbus_teardown_gpadl(newchannel, newchannel->ringbuffer_gpadlhandle);
+
 error0:
 	free_pages((unsigned long)out,
 		get_order(send_ringbuffer_size + recv_ringbuffer_size));
-- 
1.7.4.1

[PATCH RESEND 15/15] Drivers: hv: vmbus: Add support for the NetworkDirect GUID

[K. Y. Srinivasan]

NetworkDirect is a service that supports guest RDMA.
Define the GUID for this service.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/channel_mgmt.c |    2 ++
 include/linux/hyperv.h    |   10 ++++++++++
 2 files changed, 12 insertions(+), 0 deletions(-)

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 6be93f0..0ba6b5c 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -413,6 +413,8 @@ static const struct hv_vmbus_device_id hp_devs[] = {
 	{ HV_SCSI_GUID, },
 	/* Network */
 	{ HV_NIC_GUID, },
+	/* NetworkDirect Guest RDMA */
+	{ HV_ND_GUID, },
 };
 
 
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 26a32b7..7d976ac 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1110,6 +1110,16 @@ void vmbus_driver_unregister(struct hv_driver *hv_driver);
 		}
 
 /*
+ * NetworkDirect. This is the guest RDMA service.
+ * {8c2eaf3d-32a7-4b09-ab99-bd1f1c86b501}
+ */
+#define HV_ND_GUID \
+	.guid = { \
+			0x3d, 0xaf, 0x2e, 0x8c, 0xa7, 0x32, 0x09, 0x4b, \
+			0xab, 0x99, 0xbd, 0x1f, 0x1c, 0x86, 0xb5, 0x01 \
+		}
+
+/*
  * Common header for Hyper-V ICs
  */
 
-- 
1.7.4.1