github/linuxkit
1
0
Fork 0
mirror of https://github.com/linuxkit/linuxkit.git synced 2025-11-04 08:55:13 +00:00
Code Issues Projects Releases Wiki Activity

Merge pull request #1785 from rneugeba/kern-v4.11

Browse Source 
kernel: Add initial support for the 4.11 kernel
This commit is contained in:
Rolf Neugebauer
2017-05-08 17:31:52 +01:00
committed by GitHub
parent 17dd50cec6 d633913c92
commit a4c95be30a
9 changed files with 5167 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
kernel/Makefile
View File

@@ -62,6 +62,8 @@ endef
# Build Targets
# Debug targets only for latest stable and LTS stable
#
$(eval $(call kernel,4.11,4.11.x))
$(eval $(call kernel,4.11,4.11.x,_dbg))
$(eval $(call kernel,4.10.15,4.10.x))
$(eval $(call kernel,4.10.15,4.10.x,_dbg))
$(eval $(call kernel,4.9.27,4.9.x))

3810
kernel/kernel_config-4.11.x Normal file
View File

File diff suppressed because it is too large Load Diff

34
kernel/patches-4.11.x/0001-vmbus-vmbus_open-reset-onchannel_callback-on-error.patch Normal file
View File

@@ -0,0 +1,34 @@
From b7dea38997e358b0f6505432a07647f250e36f0c Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Fri, 5 May 2017 16:57:12 -0600
Subject: [PATCH 1/7] vmbus: vmbus_open(): reset onchannel_callback on error
No real issue is observed without the patch, but let's add this
just in case.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Origin: git@github.com:dcui/linux.git
(cherry picked from commit d66cd1ea748e2e3250aeb58b35f9ad665e310db9)
---
drivers/hv/channel.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 321b8833fa6f..628d6fde1887 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -220,6 +220,8 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
get_order(send_ringbuffer_size + recv_ringbuffer_size));
error_set_chnstate:
newchannel->state = CHANNEL_OPEN_STATE;
+ newchannel->onchannel_callback = NULL;
+ newchannel->channel_callback_context = NULL;
return err;
}
EXPORT_SYMBOL_GPL(vmbus_open);
--
2.11.1

42
kernel/patches-4.11.x/0002-vmbus-add-the-matching-tasklet_enable-in-vmbus_close.patch Normal file
View File

@@ -0,0 +1,42 @@
From ab40355a804892b8977854220a07f055a14c8f5c Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Fri, 5 May 2017 16:57:15 -0600
Subject: [PATCH 2/7] vmbus: add the matching tasklet_enable() in
vmbus_close_internal()
If we disable a tasklet that is scheduled but hasn't started to run,
the tasklet has no chance to run any longer, so later we'll hang
in free_channel() -> tasklet_kill(), because the TASKLET_STATE_SCHED
can't be cleared in tasklet_action().
With the patch, before free_channel() -> tasklet_kill() returns, the
tasklet still has a chance to run with a NULL channel->onchannel_callback,
which will be ignored safely, e.g. by vmbus_on_event().
Fixes: dad72a1d2844 ("vmbus: remove hv_event_tasklet_disable/enable")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Origin: git@github.com:dcui/linux.git
(cherry picked from commit 2e653533181f0c70db04d2ca13a4ae60251d1a93)
---
drivers/hv/channel.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 628d6fde1887..7cd2bd9fd1f1 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -608,6 +608,7 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
get_order(channel->ringbuffer_pagecount * PAGE_SIZE));
out:
+ tasklet_enable(&channel->callback_event);
return ret;
}
--
2.11.1

62
kernel/patches-4.11.x/0003-vmbus-remove-goto-error_clean_msglist-in-vmbus_open.patch Normal file
View File

@@ -0,0 +1,62 @@
From dade92a41fb20bc4224f412f4fb6b9de34f48c56 Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Fri, 5 May 2017 16:57:20 -0600
Subject: [PATCH 3/7] vmbus: remove "goto error_clean_msglist" in vmbus_open()
This is just a cleanup patch to simplify the code a little.
No semantic change.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Origin: git@github.com:dcui/linux.git
(cherry picked from commit 2deba76a449075c5a05bd572bfdee660f710b207)
---
drivers/hv/channel.c | 18 +++++++-----------
1 file changed, 7 insertions(+), 11 deletions(-)
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 7cd2bd9fd1f1..db5e6f8730d2 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -180,17 +180,18 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
ret = vmbus_post_msg(open_msg,
sizeof(struct vmbus_channel_open_channel), true);
- if (ret != 0) {
- err = ret;
- goto error_clean_msglist;
- }
-
- wait_for_completion(&open_info->waitevent);
+ if (ret == 0)
+ wait_for_completion(&open_info->waitevent);
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_del(&open_info->msglistentry);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+ if (ret != 0) {
+ err = ret;
+ goto error_free_gpadl;
+ }
+
if (newchannel->rescind) {
err = -ENODEV;
goto error_free_gpadl;
@@ -205,11 +206,6 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
kfree(open_info);
return 0;
-error_clean_msglist:
- spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
- list_del(&open_info->msglistentry);
- spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
-
error_free_gpadl:
vmbus_teardown_gpadl(newchannel, newchannel->ringbuffer_gpadlhandle);
kfree(open_info);
--
2.11.1

189
kernel/patches-4.11.x/0004-vmbus-dynamically-enqueue-dequeue-a-channel-on-vmbus.patch Normal file
View File

@@ -0,0 +1,189 @@
From cc8ae5575e4e77b88c134f82161341a4d4f9b094 Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Fri, 5 May 2017 16:57:23 -0600
Subject: [PATCH 4/7] vmbus: dynamically enqueue/dequeue a channel on
vmbus_open/close
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
A just-closed channel may have a pending interrupt, and later when a new
channel with the same channel ID is not being fully initialized, the
pending interrupt of the previous channel with the same channel ID can run
the channel callback on the new channel data structure, causing a crash
of NULL pointer dereferencing.
Normally it’s pretty hard to reproduce the race condition, but it can
indeed happen with specially-designed hv_sock stress test cases.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reported-by: Rolf Neugebauer <rolf.neugebauer@docker.com>
Tested-by: Rolf Neugebauer <rolf.neugebauer@docker.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Origin: git@github.com:dcui/linux.git
(cherry picked from commit fed51f8f6068cb953be480c6b6322a3a6e97745d)
---
drivers/hv/channel.c | 12 +++++++++---
drivers/hv/channel_mgmt.c | 50 +++++++++++++++++++++--------------------------
include/linux/hyperv.h | 3 +++
3 files changed, 34 insertions(+), 31 deletions(-)
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index db5e6f8730d2..f288e506fba0 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -177,6 +177,8 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
&vmbus_connection.chn_msg_list);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+ hv_percpu_channel_enq(newchannel);
+
ret = vmbus_post_msg(open_msg,
sizeof(struct vmbus_channel_open_channel), true);
@@ -189,23 +191,25 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
if (ret != 0) {
err = ret;
- goto error_free_gpadl;
+ goto error_deq_channel;
}
if (newchannel->rescind) {
err = -ENODEV;
- goto error_free_gpadl;
+ goto error_deq_channel;
}
if (open_info->response.open_result.status) {
err = -EAGAIN;
- goto error_free_gpadl;
+ goto error_deq_channel;
}
newchannel->state = CHANNEL_OPENED_STATE;
kfree(open_info);
return 0;
+error_deq_channel:
+ hv_percpu_channel_deq(newchannel);
error_free_gpadl:
vmbus_teardown_gpadl(newchannel, newchannel->ringbuffer_gpadlhandle);
kfree(open_info);
@@ -551,6 +555,8 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
goto out;
}
+ hv_percpu_channel_deq(channel);
+
channel->state = CHANNEL_OPEN_STATE;
channel->sc_creation_callback = NULL;
/* Stop callback and cancel the timer asap */
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index fbcb06352308..c5a01a4d589e 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -363,6 +363,17 @@ static void percpu_channel_enq(void *arg)
list_add_tail_rcu(&channel->percpu_list, &hv_cpu->chan_list);
}
+void hv_percpu_channel_enq(struct vmbus_channel *channel)
+{
+ if (channel->target_cpu != get_cpu())
+ smp_call_function_single(channel->target_cpu,
+ percpu_channel_enq, channel, true);
+ else
+ percpu_channel_enq(channel);
+
+ put_cpu();
+}
+
static void percpu_channel_deq(void *arg)
{
struct vmbus_channel *channel = arg;
@@ -370,6 +381,17 @@ static void percpu_channel_deq(void *arg)
list_del_rcu(&channel->percpu_list);
}
+void hv_percpu_channel_deq(struct vmbus_channel *channel)
+{
+ if (channel->target_cpu != get_cpu())
+ smp_call_function_single(channel->target_cpu,
+ percpu_channel_deq, channel, true);
+ else
+ percpu_channel_deq(channel);
+
+ put_cpu();
+}
+
static void vmbus_release_relid(u32 relid)
{
@@ -390,15 +412,6 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
BUG_ON(!channel->rescind);
BUG_ON(!mutex_is_locked(&vmbus_connection.channel_mutex));
- if (channel->target_cpu != get_cpu()) {
- put_cpu();
- smp_call_function_single(channel->target_cpu,
- percpu_channel_deq, channel, true);
- } else {
- percpu_channel_deq(channel);
- put_cpu();
- }
-
if (channel->primary_channel == NULL) {
list_del(&channel->listentry);
@@ -491,16 +504,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
init_vp_index(newchannel, dev_type);
- if (newchannel->target_cpu != get_cpu()) {
- put_cpu();
- smp_call_function_single(newchannel->target_cpu,
- percpu_channel_enq,
- newchannel, true);
- } else {
- percpu_channel_enq(newchannel);
- put_cpu();
- }
-
/*
* This state is used to indicate a successful open
* so that when we do close the channel normally, we
@@ -549,15 +552,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
list_del(&newchannel->listentry);
mutex_unlock(&vmbus_connection.channel_mutex);
- if (newchannel->target_cpu != get_cpu()) {
- put_cpu();
- smp_call_function_single(newchannel->target_cpu,
- percpu_channel_deq, newchannel, true);
- } else {
- percpu_channel_deq(newchannel);
- put_cpu();
- }
-
vmbus_release_relid(newchannel->offermsg.child_relid);
err_free_chan:
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 970771a5f739..a8bae2caa69f 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1437,6 +1437,9 @@ extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf,
const int *srv_version, int srv_vercnt,
int *nego_fw_version, int *nego_srv_version);
+void hv_percpu_channel_enq(struct vmbus_channel *channel);
+void hv_percpu_channel_deq(struct vmbus_channel *channel);
+
void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid);
void vmbus_setevent(struct vmbus_channel *channel);
--
2.11.1

934
kernel/patches-4.11.x/0005-hv_sock-implements-Hyper-V-transport-for-Virtual-Soc.patch Normal file
View File

@@ -0,0 +1,934 @@
From aa172b579ab1228c9d4364d2d21ede58927648f4 Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Fri, 5 May 2017 16:57:26 -0600
Subject: [PATCH 5/7] hv_sock: implements Hyper-V transport for Virtual Sockets
(AF_VSOCK)
Hyper-V Sockets (hv_sock) supplies a byte-stream based communication
mechanism between the host and the guest. It uses VMBus ringbuffer as the
transportation layer.
With hv_sock, applications between the host (Windows 10, Windows Server
2016 or newer) and the guest can talk with each other using the traditional
socket APIs.
More info about Hyper-V Sockets is available here:
"Make your own integration services":
https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/user-guide/make-integration-service
The patch implements the necessary support in Linux guest by introducing a new
vsock transport for AF_VSOCK.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Andy King <acking@vmware.com>
Cc: Dmitry Torokhov <dtor@vmware.com>
Cc: George Zhang <georgezhang@vmware.com>
Cc: Jorgen Hansen <jhansen@vmware.com>
Cc: Reilly Grant <grantr@vmware.com>
Cc: Asias He <asias@redhat.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Cathy Avery <cavery@redhat.com>
Cc: Rolf Neugebauer <rolf.neugebauer@docker.com>
Origin: git@github.com:dcui/linux.git
(cherry picked from commit 691aff936c0fa6fc24e2662c0e8cc6ab65509600)
---
MAINTAINERS | 1 +
net/vmw_vsock/Kconfig | 12 +
net/vmw_vsock/Makefile | 3 +
net/vmw_vsock/hyperv_transport.c | 829 +++++++++++++++++++++++++++++++++++++++
4 files changed, 845 insertions(+)
create mode 100644 net/vmw_vsock/hyperv_transport.c
diff --git a/MAINTAINERS b/MAINTAINERS
index 38d3e4ed7208..53bf52ce3173 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6077,6 +6077,7 @@ F: drivers/net/hyperv/
F: drivers/scsi/storvsc_drv.c
F: drivers/uio/uio_hv_generic.c
F: drivers/video/fbdev/hyperv_fb.c
+F: net/vmw_vsock/hyperv_transport.c
F: include/linux/hyperv.h
F: tools/hv/
F: Documentation/ABI/stable/sysfs-bus-vmbus
diff --git a/net/vmw_vsock/Kconfig b/net/vmw_vsock/Kconfig
index 8831e7c42167..a24369d175fd 100644
--- a/net/vmw_vsock/Kconfig
+++ b/net/vmw_vsock/Kconfig
@@ -46,3 +46,15 @@ config VIRTIO_VSOCKETS_COMMON
This option is selected by any driver which needs to access
the virtio_vsock. The module will be called
vmw_vsock_virtio_transport_common.
+
+config HYPERV_VSOCKETS
+ tristate "Hyper-V transport for Virtual Sockets"
+ depends on VSOCKETS && HYPERV
+ help
+ This module implements a Hyper-V transport for Virtual Sockets.
+
+ Enable this transport if your Virtual Machine host supports Virtual
+ Sockets over Hyper-V VMBus.
+
+ To compile this driver as a module, choose M here: the module will be
+ called hv_sock. If unsure, say N.
diff --git a/net/vmw_vsock/Makefile b/net/vmw_vsock/Makefile
index bc27c70e0e59..f70f3e70ce9e 100644
--- a/net/vmw_vsock/Makefile
+++ b/net/vmw_vsock/Makefile
@@ -2,6 +2,7 @@ obj-$(CONFIG_VSOCKETS) += vsock.o
obj-$(CONFIG_VMWARE_VMCI_VSOCKETS) += vmw_vsock_vmci_transport.o
obj-$(CONFIG_VIRTIO_VSOCKETS) += vmw_vsock_virtio_transport.o
obj-$(CONFIG_VIRTIO_VSOCKETS_COMMON) += vmw_vsock_virtio_transport_common.o
+obj-$(CONFIG_HYPERV_VSOCKETS) += hv_sock.o
vsock-y += af_vsock.o vsock_addr.o
@@ -11,3 +12,5 @@ vmw_vsock_vmci_transport-y += vmci_transport.o vmci_transport_notify.o \
vmw_vsock_virtio_transport-y += virtio_transport.o
vmw_vsock_virtio_transport_common-y += virtio_transport_common.o
+
+hv_sock-y += hyperv_transport.o
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
new file mode 100644
index 000000000000..fd89bf357617
--- /dev/null
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -0,0 +1,829 @@
+/*
+ * Hyper-V transport for vsock
+ *
+ * Hyper-V Sockets supplies a byte-stream based communication mechanism
+ * between the host and the VM. This driver implements the necessary
+ * support in the VM by introducing the new vsock transport.
+ *
+ * Copyright (c) 2017, 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.
+ *
+ */
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/hyperv.h>
+#include <net/sock.h>
+#include <net/af_vsock.h>
+
+/* The host side's design of the feature requires 6 exact 4KB pages for
+ * recv/send rings respectively -- this is suboptimal considering memory
+ * consumption, however unluckily we have to live with it, before the
+ * host comes up with a better design in the future.
+ */
+#define PAGE_SIZE_4K 4096
+#define RINGBUFFER_HVS_RCV_SIZE (PAGE_SIZE_4K * 6)
+#define RINGBUFFER_HVS_SND_SIZE (PAGE_SIZE_4K * 6)
+
+/* The MTU is 16KB per the host side's design */
+#define HVS_MTU_SIZE (1024 * 16)
+
+struct vmpipe_proto_header {
+ u32 pkt_type;
+ u32 data_size;
+};
+
+/* For recv, we use the VMBus in-place packet iterator APIs to directly copy
+ * data from the ringbuffer into the userspace buffer.
+ */
+struct hvs_recv_buf {
+ /* The header before the payload data */
+ struct vmpipe_proto_header hdr;
+
+ /* The payload */
+ u8 data[HVS_MTU_SIZE];
+};
+
+/* We can send up to HVS_MTU_SIZE bytes of payload to the host, but let's use
+ * a small size, i.e. HVS_SEND_BUF_SIZE, to minimize the dynamically-allocated
+ * buffer, because tests show there is no significant performance difference.
+ *
+ * Note: the buffer can be eliminated in the future when we add new VMBus
+ * ringbuffer APIs that allow us to directly copy data from userspace buffer
+ * to VMBus ringbuffer.
+ */
+#define HVS_SEND_BUF_SIZE (PAGE_SIZE_4K - sizeof(struct vmpipe_proto_header))
+
+struct hvs_send_buf {
+ /* The header before the payload data */
+ struct vmpipe_proto_header hdr;
+
+ /* The payload */
+ u8 data[HVS_SEND_BUF_SIZE];
+};
+
+#define HVS_HEADER_LEN (sizeof(struct vmpacket_descriptor) + \
+ sizeof(struct vmpipe_proto_header))
+
+/* See 'prev_indices' in hv_ringbuffer_read(), hv_ringbuffer_write(), and
+ * __hv_pkt_iter_next().
+ */
+#define VMBUS_PKT_TRAILER (sizeof(u64))
+
+#define HVS_PKT_LEN(payload_len) (HVS_HEADER_LEN + \
+ ALIGN((payload_len), 8) + \
+ VMBUS_PKT_TRAILER)
+
+/* Per-socket state (accessed via vsk->trans) */
+struct hvsock {
+ struct vsock_sock *vsk;
+
+ uuid_le vm_srv_id;
+ uuid_le host_srv_id;
+
+ struct vmbus_channel *chan;
+ struct vmpacket_descriptor *recv_desc;
+
+ /* The length of the payload not delivered to userland yet */
+ u32 recv_data_len;
+ /* The offset of the payload */
+ u32 recv_data_off;
+};
+
+/* In the VM, we support Hyper-V Sockets with AF_VSOCK, and the endpoint is
+ * <cid, port> (see struct sockaddr_vm). Note: cid is not really used here:
+ * when we write apps to connect to the host, we can only use VMADDR_CID_ANY
+ * or VMADDR_CID_HOST (both are equivalent) as the remote cid, and when we
+ * write apps to bind() & listen() in the VM, we can only use VMADDR_CID_ANY
+ * as the local cid.
+ *
+ * On the host, Hyper-V Sockets are supported by Winsock AF_HYPERV:
+ * https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/user-
+ * guide/make-integration-service, and the endpoint is <VmID, ServiceId> with
+ * the below sockaddr:
+ *
+ * struct SOCKADDR_HV
+ * {
+ * ADDRESS_FAMILY Family;
+ * USHORT Reserved;
+ * GUID VmId;
+ * GUID ServiceId;
+ * };
+ * Note: VmID is not used by Linux VM and actually it isn't transmitted via
+ * VMBus, because here it's obvious the host and the VM can easily identify
+ * each other. Though the VmID is useful on the host, especially in the case
+ * of Windows container, Linux VM doesn't need it at all.
+ *
+ * To make use of the AF_VSOCK infrastructure in Linux VM, we have to limit
+ * the available GUID space of SOCKADDR_HV so that we can create a mapping
+ * between AF_VSOCK port and SOCKADDR_HV Service GUID. The rule of writing
+ * Hyper-V Sockets apps on the host and in Linux VM is:
+ *
+ ****************************************************************************
+ * the only valid Service GUIDs, from the perspectives of both the host and *
+ * Linux VM, that can be connected by the other end, must conform to this *
+ * format: <port>-facb-11e6-bd58-64006a7986d3, and the "port" must be in *
+ * this range [0, 0x7FFFFFFF]. *
+ ****************************************************************************
+ *
+ * When we write apps on the host to connect(), the GUID ServiceID is used.
+ * When we write apps in Linux VM to connect(), we only need to specify the
+ * port and the driver will form the GUID and use that to request the host.
+ *
+ * From the perspective of Linux VM:
+ * 1. the local ephemeral port (i.e. the local auto-bound port when we call
+ * connect() without explicit bind()) is generated by __vsock_bind_stream(),
+ * and the range is [1024, 0xFFFFFFFF).
+ * 2. the remote ephemeral port (i.e. the auto-generated remote port for
+ * a connect request initiated by the host's connect()) is generated by
+ * hvs_remote_addr_init() and the range is [0x80000000, 0xFFFFFFFF).
+ */
+
+#define MAX_LISTEN_PORT ((u32)0x7FFFFFFF)
+#define MAX_VM_LISTEN_PORT MAX_LISTEN_PORT
+#define MAX_HOST_LISTEN_PORT MAX_LISTEN_PORT
+#define MIN_HOST_EPHEMERAL_PORT (MAX_HOST_LISTEN_PORT + 1)
+
+/* 00000000-facb-11e6-bd58-64006a7986d3 */
+static const uuid_le srv_id_template =
+ UUID_LE(0x00000000, 0xfacb, 0x11e6, 0xbd, 0x58,
+ 0x64, 0x00, 0x6a, 0x79, 0x86, 0xd3);
+
+static inline bool is_valid_srv_id(const uuid_le *id)
+{
+ return !memcmp(&id->b[4], &srv_id_template.b[4], sizeof(uuid_le) - 4);
+}
+
+static inline unsigned int get_port_by_srv_id(const uuid_le *svr_id)
+{
+ return *((unsigned int *)svr_id);
+}
+
+static inline void hvs_addr_init(struct sockaddr_vm *addr,
+ const uuid_le *svr_id)
+{
+ unsigned int port = get_port_by_srv_id(svr_id);
+
+ vsock_addr_init(addr, VMADDR_CID_ANY, port);
+}
+
+static inline void hvs_remote_addr_init(struct sockaddr_vm *remote,
+ struct sockaddr_vm *local)
+{
+ static u32 host_ephemeral_port = MIN_HOST_EPHEMERAL_PORT;
+ struct sock *sk;
+
+ vsock_addr_init(remote, VMADDR_CID_ANY, VMADDR_PORT_ANY);
+
+ while (1) {
+ /* Wrap around ? */
+ if (host_ephemeral_port < MIN_HOST_EPHEMERAL_PORT ||
+ host_ephemeral_port == VMADDR_PORT_ANY)
+ host_ephemeral_port = MIN_HOST_EPHEMERAL_PORT;
+
+ remote->svm_port = host_ephemeral_port++;
+
+ sk = vsock_find_connected_socket(remote, local);
+ if (!sk) {
+ /* Found an available ephemeral port */
+ return;
+ }
+
+ /* Release refcnt got in vsock_find_connected_socket */
+ sock_put(sk);
+ }
+}
+
+static bool hvs_channel_readable(struct vmbus_channel *chan)
+{
+ u32 readable = hv_get_bytes_to_read(&chan->inbound);
+
+ /* 0-size payload means FIN */
+ return readable >= HVS_PKT_LEN(0);
+}
+
+static int hvs_channel_readable_payload(struct vmbus_channel *chan)
+{
+ u32 readable = hv_get_bytes_to_read(&chan->inbound);
+
+ if (readable > HVS_PKT_LEN(0)) {
+ /* At least we have 1 byte to read. We don't need to return
+ * the exact readable bytes: see vsock_stream_recvmsg() ->
+ * vsock_stream_has_data().
+ */
+ return 1;
+ }
+
+ if (readable == HVS_PKT_LEN(0)) {
+ /* 0-size payload means FIN */
+ return 0;
+ }
+
+ /* No payload or FIN */
+ return -1;
+}
+
+static inline size_t hvs_channel_writable_bytes(struct vmbus_channel *chan)
+{
+ u32 writeable = hv_get_bytes_to_write(&chan->outbound);
+ size_t ret;
+
+ /* The ringbuffer mustn't be 100% full, and we should reserve a
+ * zero-length-payload packet for the FIN: see hv_ringbuffer_write()
+ * and hvs_shutdown().
+ */
+ if (writeable <= HVS_PKT_LEN(1) + HVS_PKT_LEN(0))
+ return 0;
+
+ ret = writeable - HVS_PKT_LEN(1) - HVS_PKT_LEN(0);
+
+ return round_down(ret, 8);
+}
+
+static int hvs_send_data(struct vmbus_channel *chan,
+ struct hvs_send_buf *send_buf, size_t to_write)
+{
+ send_buf->hdr.pkt_type = 1;
+ send_buf->hdr.data_size = to_write;
+ return vmbus_sendpacket(chan, &send_buf->hdr,
+ sizeof(send_buf->hdr) + to_write,
+ 0, VM_PKT_DATA_INBAND, 0);
+}
+
+static void hvs_channel_cb(void *ctx)
+{
+ struct sock *sk = (struct sock *)ctx;
+ struct vsock_sock *vsk = vsock_sk(sk);
+ struct hvsock *hvs = vsk->trans;
+ struct vmbus_channel *chan = hvs->chan;
+
+ if (hvs_channel_readable(chan))
+ sk->sk_data_ready(sk);
+
+ /* Mark it writable only if there is enough space */
+ if (hvs_channel_writable_bytes(chan) >= HVS_SEND_BUF_SIZE)
+ sk->sk_write_space(sk);
+}
+
+static void hvs_close_connection(struct vmbus_channel *chan)
+{
+ struct sock *sk = get_per_channel_state(chan);
+ struct vsock_sock *vsk = vsock_sk(sk);
+
+ sk->sk_state = SS_UNCONNECTED;
+ sock_set_flag(sk, SOCK_DONE);
+ vsk->peer_shutdown |= SEND_SHUTDOWN | RCV_SHUTDOWN;
+
+ sk->sk_state_change(sk);
+}
+
+static void hvs_open_connection(struct vmbus_channel *chan)
+{
+ uuid_le *if_instance, *if_type;
+ unsigned char conn_from_host;
+
+ struct sockaddr_vm addr;
+ struct sock *sk, *new = NULL;
+ struct vsock_sock *vnew;
+ struct hvsock *hvs, *hvs_new;
+ int ret;
+
+ if_type = &chan->offermsg.offer.if_type;
+ if_instance = &chan->offermsg.offer.if_instance;
+ conn_from_host = chan->offermsg.offer.u.pipe.user_def[0];
+
+ /* The host or the VM should only listen on a port in
+ * [0, MAX_LISTEN_PORT]
+ */
+ if (!is_valid_srv_id(if_type) ||
+ get_port_by_srv_id(if_type) > MAX_LISTEN_PORT)
+ return;
+
+ hvs_addr_init(&addr, conn_from_host ? if_type : if_instance);
+ sk = vsock_find_bound_socket(&addr);
+ if (!sk)
+ return;
+
+ if ((conn_from_host && sk->sk_state != VSOCK_SS_LISTEN) ||
+ (!conn_from_host && sk->sk_state != SS_CONNECTING))
+ goto out;
+
+ if (conn_from_host) {
+ if (sk->sk_ack_backlog >= sk->sk_max_ack_backlog)
+ goto out;
+
+ new = __vsock_create(sock_net(sk), NULL, sk, GFP_KERNEL,
+ sk->sk_type, 0);
+ if (!new)
+ goto out;
+
+ new->sk_state = SS_CONNECTING;
+ vnew = vsock_sk(new);
+ hvs_new = vnew->trans;
+ hvs_new->chan = chan;
+ } else {
+ hvs = vsock_sk(sk)->trans;
+ hvs->chan = chan;
+ }
+
+ set_channel_read_mode(chan, HV_CALL_DIRECT);
+ ret = vmbus_open(chan, RINGBUFFER_HVS_SND_SIZE,
+ RINGBUFFER_HVS_RCV_SIZE, NULL, 0,
+ hvs_channel_cb, conn_from_host ? new : sk);
+ if (ret != 0) {
+ if (conn_from_host) {
+ hvs_new->chan = NULL;
+ sock_put(new);
+ } else {
+ hvs->chan = NULL;
+ }
+ goto out;
+ }
+
+ set_per_channel_state(chan, conn_from_host ? new : sk);
+ vmbus_set_chn_rescind_callback(chan, hvs_close_connection);
+
+ /* See hvs_channel_cb() and hvs_notify_poll_out() */
+ set_channel_pending_send_size(chan,
+ HVS_PKT_LEN(HVS_SEND_BUF_SIZE) + 1);
+
+ if (conn_from_host) {
+ new->sk_state = SS_CONNECTED;
+ sk->sk_ack_backlog++;
+
+ hvs_addr_init(&vnew->local_addr, if_type);
+ hvs_remote_addr_init(&vnew->remote_addr, &vnew->local_addr);
+
+ hvs_new->vm_srv_id = *if_type;
+ hvs_new->host_srv_id = *if_instance;
+
+ vsock_insert_connected(vnew);
+ vsock_enqueue_accept(sk, new);
+ } else {
+ sk->sk_state = SS_CONNECTED;
+ sk->sk_socket->state = SS_CONNECTED;
+
+ vsock_insert_connected(vsock_sk(sk));
+ }
+
+ sk->sk_state_change(sk);
+
+out:
+ /* Release refcnt obtained when we called vsock_find_bound_socket() */
+ sock_put(sk);
+}
+
+static u32 hvs_get_local_cid(void)
+{
+ return VMADDR_CID_ANY;
+}
+
+static int hvs_sock_init(struct vsock_sock *vsk, struct vsock_sock *psk)
+{
+ struct hvsock *hvs;
+
+ hvs = kzalloc(sizeof(*hvs), GFP_KERNEL);
+ if (!hvs)
+ return -ENOMEM;
+
+ vsk->trans = hvs;
+ hvs->vsk = vsk;
+
+ return 0;
+}
+
+static int hvs_connect(struct vsock_sock *vsk)
+{
+ struct hvsock *h = vsk->trans;
+
+ h->vm_srv_id = srv_id_template;
+ h->host_srv_id = srv_id_template;
+
+ *((u32 *)&h->vm_srv_id) = vsk->local_addr.svm_port;
+ *((u32 *)&h->host_srv_id) = vsk->remote_addr.svm_port;
+
+ return vmbus_send_tl_connect_request(&h->vm_srv_id, &h->host_srv_id);
+}
+
+static int hvs_shutdown(struct vsock_sock *vsk, int mode)
+{
+ struct vmpipe_proto_header hdr;
+ struct hvs_send_buf *send_buf;
+ struct hvsock *hvs;
+
+ if (!(mode & SEND_SHUTDOWN))
+ return 0;
+
+ hvs = vsk->trans;
+
+ send_buf = (struct hvs_send_buf *)&hdr;
+
+ /* It can't fail: see hvs_channel_writable_bytes(). */
+ (void)hvs_send_data(hvs->chan, send_buf, 0);
+
+ return 0;
+}
+
+static void hvs_release(struct vsock_sock *vsk)
+{
+ struct hvsock *hvs = vsk->trans;
+ struct vmbus_channel *chan = hvs->chan;
+
+ if (chan)
+ hvs_shutdown(vsk, RCV_SHUTDOWN | SEND_SHUTDOWN);
+
+ vsock_remove_sock(vsk);
+}
+
+static void hvs_destruct(struct vsock_sock *vsk)
+{
+ struct hvsock *hvs = vsk->trans;
+ struct vmbus_channel *chan = hvs->chan;
+
+ if (chan)
+ vmbus_hvsock_device_unregister(chan);
+
+ kfree(hvs);
+}
+
+static int hvs_dgram_bind(struct vsock_sock *vsk, struct sockaddr_vm *addr)
+{
+ return -EOPNOTSUPP;
+}
+
+static int hvs_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg,
+ size_t len, int flags)
+{
+ return -EOPNOTSUPP;
+}
+
+static int hvs_dgram_enqueue(struct vsock_sock *vsk,
+ struct sockaddr_vm *remote, struct msghdr *msg,
+ size_t dgram_len)
+{
+ return -EOPNOTSUPP;
+}
+
+static bool hvs_dgram_allow(u32 cid, u32 port)
+{
+ return false;
+}
+
+static ssize_t hvs_stream_dequeue(struct vsock_sock *vsk, struct msghdr *msg,
+ size_t len, int flags)
+{
+ struct hvsock *hvs = vsk->trans;
+ bool need_refill = !hvs->recv_desc;
+ struct hvs_recv_buf *recv_buf;
+ u32 payload_len, to_read;
+ int ret;
+
+ if (flags & MSG_PEEK)
+ return -EOPNOTSUPP;
+
+ if (need_refill) {
+ hvs->recv_desc = hv_pkt_iter_first(hvs->chan);
+ recv_buf = (struct hvs_recv_buf *)(hvs->recv_desc + 1);
+
+ payload_len = recv_buf->hdr.data_size;
+ if (payload_len == 0 || payload_len > HVS_MTU_SIZE)
+ return -EIO;
+
+ hvs->recv_data_len = payload_len;
+ hvs->recv_data_off = 0;
+ } else {
+ recv_buf = (struct hvs_recv_buf *)(hvs->recv_desc + 1);
+ }
+
+ to_read = min_t(u32, len, hvs->recv_data_len);
+ ret = memcpy_to_msg(msg, recv_buf->data + hvs->recv_data_off, to_read);
+ if (ret != 0)
+ return ret;
+
+ hvs->recv_data_len -= to_read;
+
+ if (hvs->recv_data_len == 0)
+ hvs->recv_desc = hv_pkt_iter_next(hvs->chan, hvs->recv_desc);
+ else
+ hvs->recv_data_off += to_read;
+
+ return to_read;
+}
+
+static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg,
+ size_t len)
+{
+ struct hvsock *hvs = vsk->trans;
+ struct vmbus_channel *chan = hvs->chan;
+ struct hvs_send_buf *send_buf;
+ size_t to_write, max_writable, ret;
+
+ BUILD_BUG_ON(sizeof(*send_buf) != PAGE_SIZE_4K);
+
+ send_buf = kmalloc(sizeof(*send_buf), GFP_KERNEL);
+ if (!send_buf)
+ return -ENOMEM;
+
+ max_writable = hvs_channel_writable_bytes(chan);
+ to_write = min_t(size_t, len, max_writable);
+ to_write = min_t(size_t, to_write, HVS_SEND_BUF_SIZE);
+
+ ret = memcpy_from_msg(send_buf->data, msg, to_write);
+ if (ret < 0)
+ goto out;
+
+ ret = hvs_send_data(hvs->chan, send_buf, to_write);
+ if (ret < 0)
+ goto out;
+
+ ret = to_write;
+out:
+ kfree(send_buf);
+ return ret;
+}
+
+static s64 hvs_stream_has_data(struct vsock_sock *vsk)
+{
+ struct hvsock *hvs = vsk->trans;
+ s64 ret;
+
+ switch (hvs_channel_readable_payload(hvs->chan)) {
+ case 1:
+ ret = 1;
+ break;
+ case 0:
+ vsk->peer_shutdown |= SEND_SHUTDOWN;
+ ret = 0;
+ break;
+ default: /* -1 */
+ ret = 0;
+ break;
+ }
+
+ return ret;
+}
+
+static s64 hvs_stream_has_space(struct vsock_sock *vsk)
+{
+ struct hvsock *hvs = vsk->trans;
+
+ return hvs_channel_writable_bytes(hvs->chan);
+}
+
+static u64 hvs_stream_rcvhiwat(struct vsock_sock *vsk)
+{
+ return HVS_MTU_SIZE + 1;
+}
+
+static bool hvs_stream_is_active(struct vsock_sock *vsk)
+{
+ struct hvsock *hvs = vsk->trans;
+
+ return hvs->chan != NULL;
+}
+
+static bool hvs_stream_allow(u32 cid, u32 port)
+{
+ static const u32 valid_cids[] = {
+ VMADDR_CID_ANY,
+ VMADDR_CID_HOST,
+ };
+ int i;
+
+ /* The host's port range [MIN_HOST_EPHEMERAL_PORT, 0xFFFFFFFF) is
+ * reserved as ephemeral ports, which are used as the host's ports
+ * when the host initiates connections.
+ */
+ if (port > MAX_HOST_LISTEN_PORT)
+ return false;
+
+ for (i = 0; i < ARRAY_SIZE(valid_cids); i++) {
+ if (cid == valid_cids[i])
+ return true;
+ }
+
+ return false;
+}
+
+static
+int hvs_notify_poll_in(struct vsock_sock *vsk, size_t target, bool *readable)
+{
+ struct hvsock *hvs = vsk->trans;
+
+ *readable = hvs_channel_readable(hvs->chan);
+ return 0;
+}
+
+static
+int hvs_notify_poll_out(struct vsock_sock *vsk, size_t target, bool *writable)
+{
+ /* Report writable only if there is enough space */
+ *writable = hvs_stream_has_space(vsk) >= HVS_SEND_BUF_SIZE;
+
+ return 0;
+}
+
+static
+int hvs_notify_recv_init(struct vsock_sock *vsk, size_t target,
+ struct vsock_transport_recv_notify_data *d)
+{
+ return 0;
+}
+
+static
+int hvs_notify_recv_pre_block(struct vsock_sock *vsk, size_t target,
+ struct vsock_transport_recv_notify_data *d)
+{
+ return 0;
+}
+
+static
+int hvs_notify_recv_pre_dequeue(struct vsock_sock *vsk, size_t target,
+ struct vsock_transport_recv_notify_data *d)
+{
+ return 0;
+}
+
+static
+int hvs_notify_recv_post_dequeue(struct vsock_sock *vsk, size_t target,
+ ssize_t copied, bool data_read,
+ struct vsock_transport_recv_notify_data *d)
+{
+ return 0;
+}
+
+static
+int hvs_notify_send_init(struct vsock_sock *vsk,
+ struct vsock_transport_send_notify_data *d)
+{
+ return 0;
+}
+
+static
+int hvs_notify_send_pre_block(struct vsock_sock *vsk,
+ struct vsock_transport_send_notify_data *d)
+{
+ return 0;
+}
+
+static
+int hvs_notify_send_pre_enqueue(struct vsock_sock *vsk,
+ struct vsock_transport_send_notify_data *d)
+{
+ return 0;
+}
+
+static
+int hvs_notify_send_post_enqueue(struct vsock_sock *vsk, ssize_t written,
+ struct vsock_transport_send_notify_data *d)
+{
+ return 0;
+}
+
+static void hvs_set_buffer_size(struct vsock_sock *vsk, u64 val)
+{
+ /* Ignored. */
+}
+
+static void hvs_set_min_buffer_size(struct vsock_sock *vsk, u64 val)
+{
+ /* Ignored. */
+}
+
+static void hvs_set_max_buffer_size(struct vsock_sock *vsk, u64 val)
+{
+ /* Ignored. */
+}
+
+static u64 hvs_get_buffer_size(struct vsock_sock *vsk)
+{
+ return -ENOPROTOOPT;
+}
+
+static u64 hvs_get_min_buffer_size(struct vsock_sock *vsk)
+{
+ return -ENOPROTOOPT;
+}
+
+static u64 hvs_get_max_buffer_size(struct vsock_sock *vsk)
+{
+ return -ENOPROTOOPT;
+}
+
+static struct vsock_transport hvs_transport = {
+ .get_local_cid = hvs_get_local_cid,
+
+ .init = hvs_sock_init,
+ .destruct = hvs_destruct,
+ .release = hvs_release,
+ .connect = hvs_connect,
+ .shutdown = hvs_shutdown,
+
+ .dgram_bind = hvs_dgram_bind,
+ .dgram_dequeue = hvs_dgram_dequeue,
+ .dgram_enqueue = hvs_dgram_enqueue,
+ .dgram_allow = hvs_dgram_allow,
+
+ .stream_dequeue = hvs_stream_dequeue,
+ .stream_enqueue = hvs_stream_enqueue,
+ .stream_has_data = hvs_stream_has_data,
+ .stream_has_space = hvs_stream_has_space,
+ .stream_rcvhiwat = hvs_stream_rcvhiwat,
+ .stream_is_active = hvs_stream_is_active,
+ .stream_allow = hvs_stream_allow,
+
+ .notify_poll_in = hvs_notify_poll_in,
+ .notify_poll_out = hvs_notify_poll_out,
+ .notify_recv_init = hvs_notify_recv_init,
+ .notify_recv_pre_block = hvs_notify_recv_pre_block,
+ .notify_recv_pre_dequeue = hvs_notify_recv_pre_dequeue,
+ .notify_recv_post_dequeue = hvs_notify_recv_post_dequeue,
+ .notify_send_init = hvs_notify_send_init,
+ .notify_send_pre_block = hvs_notify_send_pre_block,
+ .notify_send_pre_enqueue = hvs_notify_send_pre_enqueue,
+ .notify_send_post_enqueue = hvs_notify_send_post_enqueue,
+
+ .set_buffer_size = hvs_set_buffer_size,
+ .set_min_buffer_size = hvs_set_min_buffer_size,
+ .set_max_buffer_size = hvs_set_max_buffer_size,
+ .get_buffer_size = hvs_get_buffer_size,
+ .get_min_buffer_size = hvs_get_min_buffer_size,
+ .get_max_buffer_size = hvs_get_max_buffer_size,
+};
+
+static int hvs_probe(struct hv_device *hdev,
+ const struct hv_vmbus_device_id *dev_id)
+{
+ struct vmbus_channel *chan = hdev->channel;
+
+ hvs_open_connection(chan);
+
+ /* Always return success to suppress the unnecessary error message
+ * in vmbus_probe(): on error the host will rescind the device in
+ * 30 seconds and we can do cleanup at that time in
+ * vmbus_onoffer_rescind().
+ */
+ return 0;
+}
+
+static int hvs_remove(struct hv_device *hdev)
+{
+ struct vmbus_channel *chan = hdev->channel;
+
+ vmbus_close(chan);
+
+ return 0;
+}
+
+/* This isn't really used. See vmbus_match() and vmbus_probe() */
+static const struct hv_vmbus_device_id id_table[] = {
+ {},
+};
+
+static struct hv_driver hvs_drv = {
+ .name = "hv_sock",
+ .hvsock = true,
+ .id_table = id_table,
+ .probe = hvs_probe,
+ .remove = hvs_remove,
+};
+
+static int __init hvs_init(void)
+{
+ int ret;
+
+ if (vmbus_proto_version < VERSION_WIN10)
+ return -ENODEV;
+
+ ret = vmbus_driver_register(&hvs_drv);
+ if (ret != 0)
+ return ret;
+
+ ret = vsock_core_init(&hvs_transport);
+ if (ret) {
+ vmbus_driver_unregister(&hvs_drv);
+ return ret;
+ }
+
+ return 0;
+}
+
+static void __exit hvs_exit(void)
+{
+ vsock_core_exit();
+ vmbus_driver_unregister(&hvs_drv);
+}
+
+module_init(hvs_init);
+module_exit(hvs_exit);
+
+MODULE_DESCRIPTION("Hyper-V sockets");
+MODULE_VERSION("1.0.0");
+MODULE_LICENSE("GPL");
--
2.11.1

64
kernel/patches-4.11.x/0006-VMCI-only-try-to-load-on-VMware-hypervisor.patch Normal file
View File

@@ -0,0 +1,64 @@
From 56e37d5939cd7da4e7b9dd8a699e11f0b004c999 Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Fri, 5 May 2017 16:57:29 -0600
Subject: [PATCH 6/7] VMCI: only try to load on VMware hypervisor
Without the patch, vmw_vsock_vmci_transport.ko and vmw_vmci.ko can
automatically load when an application creates an AF_VSOCK socket.
This is the expected good behavior on VMware hypervisor, but as we
are adding hv_sock.ko (i.e. Hyper-V transport for AF_VSOCK), we should
make sure vmw_vsock_vmci_transport.ko can't load on Hyper-V, otherwise
there is a -EBUSY conflict when both vmw_vsock_vmci_transport.ko and
hv_sock.ko try to call vsock_core_init().
On the other hand, hv_sock.ko can only load on Hyper-V, because it
depends on hv_vmbus.ko, which deteces Hyper-V in hv_acpi_init().
KVM's vsock_virtio_transport doesn't have the issue because it doesn't
define MODULE_ALIAS_NETPROTO(PF_VSOCK).
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: Alok Kataria <akataria@vmware.com>
Cc: Andy King <acking@vmware.com>
Cc: Adit Ranadive <aditr@vmware.com>
Cc: George Zhang <georgezhang@vmware.com>
Cc: Jorgen Hansen <jhansen@vmware.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Origin: git@github.com:dcui/linux.git
(cherry picked from commit d643b934352ffea88cd9ce50a709667574523a8d)
---
drivers/misc/vmw_vmci/vmci_driver.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/misc/vmw_vmci/vmci_driver.c b/drivers/misc/vmw_vmci/vmci_driver.c
index d7eaf1eb11e7..1789ea71ff5d 100644
--- a/drivers/misc/vmw_vmci/vmci_driver.c
+++ b/drivers/misc/vmw_vmci/vmci_driver.c
@@ -19,6 +19,7 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
+#include <linux/hypervisor.h>
#include "vmci_driver.h"
#include "vmci_event.h"
@@ -58,6 +59,13 @@ static int __init vmci_drv_init(void)
int vmci_err;
int error;
+ /*
+ * Check if we are running on VMware's hypervisor and bail out
+ * if we are not.
+ */
+ if (x86_hyper != &x86_hyper_vmware)
+ return -ENODEV;
+
vmci_err = vmci_event_init();
if (vmci_err < VMCI_SUCCESS) {
pr_err("Failed to initialize VMCIEvent (result=%d)\n",
--
2.11.1

30
kernel/patches-4.11.x/0007-hv_sock-add-the-support-of-auto-loading.patch Normal file
View File

@@ -0,0 +1,30 @@
From 6b2c2ccb78ab847ac1db6009abc9cc4954a562ef Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Fri, 5 May 2017 16:57:35 -0600
Subject: [PATCH 7/7] hv_sock: add the support of auto-loading
After we disable VMWare virtual sockets driver's auto-loading on Hyper-V,
we can enable hv_sock's auto-loading now.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Origin: git@github.com:dcui/linux.git
(cherry picked from commit d02cd7376ce780f3d46b72a2f553f266ad558cd4)
---
net/vmw_vsock/hyperv_transport.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index fd89bf357617..f465b0b662df 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -827,3 +827,4 @@ module_exit(hvs_exit);
MODULE_DESCRIPTION("Hyper-V sockets");
MODULE_VERSION("1.0.0");
MODULE_LICENSE("GPL");
+MODULE_ALIAS_NETPROTO(PF_VSOCK);
--
2.11.1