Initial commit: Linux kernel 4.19 for Unplugged OS

This commit is contained in:
ziv committed 2025-10-06 13:52:42 +00:00
commit d30235b04c
80519 files changed
+35800681

No files matched your search

+28
View File
@@ -0,0 +1,28 @@
# SPDX-License-Identifier: GPL-2.0
menu "Microsoft Hyper-V guest support"
config HYPERV
tristate "Microsoft Hyper-V client drivers"
depends on X86 && ACPI && X86_LOCAL_APIC && HYPERVISOR_GUEST
select PARAVIRT
help
Select this option to run Linux as a Hyper-V client operating
system.
config HYPERV_TSCPAGE
def_bool HYPERV && X86_64
config HYPERV_UTILS
tristate "Microsoft Hyper-V Utilities driver"
depends on HYPERV && CONNECTOR && NLS
help
Select this option to enable the Hyper-V Utilities.
config HYPERV_BALLOON
tristate "Microsoft Hyper-V Balloon driver"
depends on HYPERV
help
Select this option to enable Hyper-V Balloon driver.
endmenu
+12
View File
@@ -0,0 +1,12 @@
# SPDX-License-Identifier: GPL-2.0
obj-$(CONFIG_HYPERV) += hv_vmbus.o
obj-$(CONFIG_HYPERV_UTILS) += hv_utils.o
obj-$(CONFIG_HYPERV_BALLOON) += hv_balloon.o
CFLAGS_hv_trace.o = -I$(src)
CFLAGS_hv_balloon.o = -I$(src)
hv_vmbus-y := vmbus_drv.o \
hv.o connection.o channel.o \
channel_mgmt.o ring_buffer.o hv_trace.o
hv_utils-y := hv_util.o hv_kvp.o hv_snapshot.o hv_fcopy.o hv_utils_transport.o
+900
View File
@@ -0,0 +1,900 @@
/*
* 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>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/hyperv.h>
#include <linux/uio.h>
#include <linux/interrupt.h>
#include <asm/page.h>
#include "hyperv_vmbus.h"
#define NUM_PAGES_SPANNED(addr, len) \
((PAGE_ALIGN(addr + len) >> PAGE_SHIFT) - (addr >> PAGE_SHIFT))
static unsigned long virt_to_hvpfn(void *addr)
{
phys_addr_t paddr;
if (is_vmalloc_addr(addr))
paddr = page_to_phys(vmalloc_to_page(addr)) +
offset_in_page(addr);
else
paddr = __pa(addr);
return paddr >> PAGE_SHIFT;
}
/*
* vmbus_setevent- Trigger an event notification on the specified
* channel.
*/
void vmbus_setevent(struct vmbus_channel *channel)
{
struct hv_monitor_page *monitorpage;
trace_vmbus_setevent(channel);
/*
* For channels marked as in "low latency" mode
* bypass the monitor page mechanism.
*/
if (channel->offermsg.monitor_allocated && !channel->low_latency) {
vmbus_send_interrupt(channel->offermsg.child_relid);
/* Get the child to parent monitor page */
monitorpage = vmbus_connection.monitor_pages[1];
sync_set_bit(channel->monitor_bit,
(unsigned long *)&monitorpage->trigger_group
[channel->monitor_grp].pending);
} else {
vmbus_set_event(channel);
}
}
EXPORT_SYMBOL_GPL(vmbus_setevent);
/*
* vmbus_open - Open the specified channel.
*/
int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
u32 recv_ringbuffer_size, void *userdata, u32 userdatalen,
void (*onchannelcallback)(void *context), void *context)
{
struct vmbus_channel_open_channel *open_msg;
struct vmbus_channel_msginfo *open_info = NULL;
unsigned long flags;
int ret, err = 0;
struct page *page;
unsigned int order;
if (send_ringbuffer_size % PAGE_SIZE ||
recv_ringbuffer_size % PAGE_SIZE)
return -EINVAL;
order = get_order(send_ringbuffer_size + recv_ringbuffer_size);
spin_lock_irqsave(&newchannel->lock, flags);
if (newchannel->state == CHANNEL_OPEN_STATE) {
newchannel->state = CHANNEL_OPENING_STATE;
} else {
spin_unlock_irqrestore(&newchannel->lock, flags);
return -EINVAL;
}
spin_unlock_irqrestore(&newchannel->lock, flags);
newchannel->onchannel_callback = onchannelcallback;
newchannel->channel_callback_context = context;
/* Allocate the ring buffer */
page = alloc_pages_node(cpu_to_node(newchannel->target_cpu),
GFP_KERNEL|__GFP_ZERO, order);
if (!page)
page = alloc_pages(GFP_KERNEL|__GFP_ZERO, order);
if (!page) {
err = -ENOMEM;
goto error_set_chnstate;
}
newchannel->ringbuffer_page = page;
newchannel->ringbuffer_pagecount = (send_ringbuffer_size +
recv_ringbuffer_size) >> PAGE_SHIFT;
ret = hv_ringbuffer_init(&newchannel->outbound, page,
send_ringbuffer_size >> PAGE_SHIFT);
if (ret != 0) {
err = ret;
goto error_free_pages;
}
ret = hv_ringbuffer_init(&newchannel->inbound,
&page[send_ringbuffer_size >> PAGE_SHIFT],
recv_ringbuffer_size >> PAGE_SHIFT);
if (ret != 0) {
err = ret;
goto error_free_pages;
}
/* Establish the gpadl for the ring buffer */
newchannel->ringbuffer_gpadlhandle = 0;
ret = vmbus_establish_gpadl(newchannel,
page_address(page),
send_ringbuffer_size +
recv_ringbuffer_size,
&newchannel->ringbuffer_gpadlhandle);
if (ret != 0) {
err = ret;
goto error_free_pages;
}
/* Create and init the channel open message */
open_info = kmalloc(sizeof(*open_info) +
sizeof(struct vmbus_channel_open_channel),
GFP_KERNEL);
if (!open_info) {
err = -ENOMEM;
goto error_free_gpadl;
}
init_completion(&open_info->waitevent);
open_info->waiting_channel = newchannel;
open_msg = (struct vmbus_channel_open_channel *)open_info->msg;
open_msg->header.msgtype = CHANNELMSG_OPENCHANNEL;
open_msg->openid = newchannel->offermsg.child_relid;
open_msg->child_relid = newchannel->offermsg.child_relid;
open_msg->ringbuffer_gpadlhandle = newchannel->ringbuffer_gpadlhandle;
open_msg->downstream_ringbuffer_pageoffset = send_ringbuffer_size >>
PAGE_SHIFT;
open_msg->target_vp = newchannel->target_vp;
if (userdatalen > MAX_USER_DEFINED_BYTES) {
err = -EINVAL;
goto error_free_gpadl;
}
if (userdatalen)
memcpy(open_msg->userdata, userdata, userdatalen);
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_add_tail(&open_info->msglistentry,
&vmbus_connection.chn_msg_list);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
if (newchannel->rescind) {
err = -ENODEV;
goto error_free_gpadl;
}
ret = vmbus_post_msg(open_msg,
sizeof(struct vmbus_channel_open_channel), true);
trace_vmbus_open(open_msg, ret);
if (ret != 0) {
err = ret;
goto error_clean_msglist;
}
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 (newchannel->rescind) {
err = -ENODEV;
goto error_free_gpadl;
}
if (open_info->response.open_result.status) {
err = -EAGAIN;
goto error_free_gpadl;
}
newchannel->state = CHANNEL_OPENED_STATE;
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);
error_free_pages:
hv_ringbuffer_cleanup(&newchannel->outbound);
hv_ringbuffer_cleanup(&newchannel->inbound);
__free_pages(page, order);
error_set_chnstate:
newchannel->state = CHANNEL_OPEN_STATE;
return err;
}
EXPORT_SYMBOL_GPL(vmbus_open);
/* Used for Hyper-V Socket: a guest client's connect() to the host */
int vmbus_send_tl_connect_request(const uuid_le *shv_guest_servie_id,
const uuid_le *shv_host_servie_id)
{
struct vmbus_channel_tl_connect_request conn_msg;
int ret;
memset(&conn_msg, 0, sizeof(conn_msg));
conn_msg.header.msgtype = CHANNELMSG_TL_CONNECT_REQUEST;
conn_msg.guest_endpoint_id = *shv_guest_servie_id;
conn_msg.host_service_id = *shv_host_servie_id;
ret = vmbus_post_msg(&conn_msg, sizeof(conn_msg), true);
trace_vmbus_send_tl_connect_request(&conn_msg, ret);
return ret;
}
EXPORT_SYMBOL_GPL(vmbus_send_tl_connect_request);
/*
* create_gpadl_header - Creates a gpadl for the specified buffer
*/
static int create_gpadl_header(void *kbuffer, u32 size,
struct vmbus_channel_msginfo **msginfo)
{
int i;
int pagecount;
struct vmbus_channel_gpadl_header *gpadl_header;
struct vmbus_channel_gpadl_body *gpadl_body;
struct vmbus_channel_msginfo *msgheader;
struct vmbus_channel_msginfo *msgbody = NULL;
u32 msgsize;
int pfnsum, pfncount, pfnleft, pfncurr, pfnsize;
pagecount = size >> PAGE_SHIFT;
/* do we need a gpadl body msg */
pfnsize = MAX_SIZE_CHANNEL_MESSAGE -
sizeof(struct vmbus_channel_gpadl_header) -
sizeof(struct gpa_range);
pfncount = pfnsize / sizeof(u64);
if (pagecount > pfncount) {
/* we need a gpadl body */
/* fill in the header */
msgsize = sizeof(struct vmbus_channel_msginfo) +
sizeof(struct vmbus_channel_gpadl_header) +
sizeof(struct gpa_range) + pfncount * sizeof(u64);
msgheader = kzalloc(msgsize, GFP_KERNEL);
if (!msgheader)
goto nomem;
INIT_LIST_HEAD(&msgheader->submsglist);
msgheader->msgsize = msgsize;
gpadl_header = (struct vmbus_channel_gpadl_header *)
msgheader->msg;
gpadl_header->rangecount = 1;
gpadl_header->range_buflen = sizeof(struct gpa_range) +
pagecount * sizeof(u64);
gpadl_header->range[0].byte_offset = 0;
gpadl_header->range[0].byte_count = size;
for (i = 0; i < pfncount; i++)
gpadl_header->range[0].pfn_array[i] = virt_to_hvpfn(
kbuffer + PAGE_SIZE * i);
*msginfo = msgheader;
pfnsum = pfncount;
pfnleft = pagecount - pfncount;
/* how many pfns can we fit */
pfnsize = MAX_SIZE_CHANNEL_MESSAGE -
sizeof(struct vmbus_channel_gpadl_body);
pfncount = pfnsize / sizeof(u64);
/* fill in the body */
while (pfnleft) {
if (pfnleft > pfncount)
pfncurr = pfncount;
else
pfncurr = pfnleft;
msgsize = sizeof(struct vmbus_channel_msginfo) +
sizeof(struct vmbus_channel_gpadl_body) +
pfncurr * sizeof(u64);
msgbody = kzalloc(msgsize, GFP_KERNEL);
if (!msgbody) {
struct vmbus_channel_msginfo *pos = NULL;
struct vmbus_channel_msginfo *tmp = NULL;
/*
* Free up all the allocated messages.
*/
list_for_each_entry_safe(pos, tmp,
&msgheader->submsglist,
msglistentry) {
list_del(&pos->msglistentry);
kfree(pos);
}
goto nomem;
}
msgbody->msgsize = msgsize;
gpadl_body =
(struct vmbus_channel_gpadl_body *)msgbody->msg;
/*
* Gpadl is u32 and we are using a pointer which could
* be 64-bit
* This is governed by the guest/host protocol and
* so the hypervisor guarantees that this is ok.
*/
for (i = 0; i < pfncurr; i++)
gpadl_body->pfn[i] = virt_to_hvpfn(
kbuffer + PAGE_SIZE * (pfnsum + i));
/* add to msg header */
list_add_tail(&msgbody->msglistentry,
&msgheader->submsglist);
pfnsum += pfncurr;
pfnleft -= pfncurr;
}
} else {
/* everything fits in a header */
msgsize = sizeof(struct vmbus_channel_msginfo) +
sizeof(struct vmbus_channel_gpadl_header) +
sizeof(struct gpa_range) + pagecount * sizeof(u64);
msgheader = kzalloc(msgsize, GFP_KERNEL);
if (msgheader == NULL)
goto nomem;
INIT_LIST_HEAD(&msgheader->submsglist);
msgheader->msgsize = msgsize;
gpadl_header = (struct vmbus_channel_gpadl_header *)
msgheader->msg;
gpadl_header->rangecount = 1;
gpadl_header->range_buflen = sizeof(struct gpa_range) +
pagecount * sizeof(u64);
gpadl_header->range[0].byte_offset = 0;
gpadl_header->range[0].byte_count = size;
for (i = 0; i < pagecount; i++)
gpadl_header->range[0].pfn_array[i] = virt_to_hvpfn(
kbuffer + PAGE_SIZE * i);
*msginfo = msgheader;
}
return 0;
nomem:
kfree(msgheader);
kfree(msgbody);
return -ENOMEM;
}
/*
* vmbus_establish_gpadl - Establish a GPADL for the specified buffer
*
* @channel: a channel
* @kbuffer: from kmalloc or vmalloc
* @size: page-size multiple
* @gpadl_handle: some funky thing
*/
int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
u32 size, u32 *gpadl_handle)
{
struct vmbus_channel_gpadl_header *gpadlmsg;
struct vmbus_channel_gpadl_body *gpadl_body;
struct vmbus_channel_msginfo *msginfo = NULL;
struct vmbus_channel_msginfo *submsginfo, *tmp;
struct list_head *curr;
u32 next_gpadl_handle;
unsigned long flags;
int ret = 0;
next_gpadl_handle =
(atomic_inc_return(&vmbus_connection.next_gpadl_handle) - 1);
ret = create_gpadl_header(kbuffer, size, &msginfo);
if (ret)
return ret;
init_completion(&msginfo->waitevent);
msginfo->waiting_channel = channel;
gpadlmsg = (struct vmbus_channel_gpadl_header *)msginfo->msg;
gpadlmsg->header.msgtype = CHANNELMSG_GPADL_HEADER;
gpadlmsg->child_relid = channel->offermsg.child_relid;
gpadlmsg->gpadl = next_gpadl_handle;
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_add_tail(&msginfo->msglistentry,
&vmbus_connection.chn_msg_list);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
if (channel->rescind) {
ret = -ENODEV;
goto cleanup;
}
ret = vmbus_post_msg(gpadlmsg, msginfo->msgsize -
sizeof(*msginfo), true);
trace_vmbus_establish_gpadl_header(gpadlmsg, ret);
if (ret != 0)
goto cleanup;
list_for_each(curr, &msginfo->submsglist) {
submsginfo = (struct vmbus_channel_msginfo *)curr;
gpadl_body =
(struct vmbus_channel_gpadl_body *)submsginfo->msg;
gpadl_body->header.msgtype =
CHANNELMSG_GPADL_BODY;
gpadl_body->gpadl = next_gpadl_handle;
ret = vmbus_post_msg(gpadl_body,
submsginfo->msgsize - sizeof(*submsginfo),
true);
trace_vmbus_establish_gpadl_body(gpadl_body, ret);
if (ret != 0)
goto cleanup;
}
wait_for_completion(&msginfo->waitevent);
if (msginfo->response.gpadl_created.creation_status != 0) {
pr_err("Failed to establish GPADL: err = 0x%x\n",
msginfo->response.gpadl_created.creation_status);
ret = -EDQUOT;
goto cleanup;
}
if (channel->rescind) {
ret = -ENODEV;
goto cleanup;
}
/* At this point, we received the gpadl created msg */
*gpadl_handle = gpadlmsg->gpadl;
cleanup:
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_del(&msginfo->msglistentry);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
list_for_each_entry_safe(submsginfo, tmp, &msginfo->submsglist,
msglistentry) {
kfree(submsginfo);
}
kfree(msginfo);
return ret;
}
EXPORT_SYMBOL_GPL(vmbus_establish_gpadl);
/*
* vmbus_teardown_gpadl -Teardown the specified GPADL handle
*/
int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
{
struct vmbus_channel_gpadl_teardown *msg;
struct vmbus_channel_msginfo *info;
unsigned long flags;
int ret;
info = kmalloc(sizeof(*info) +
sizeof(struct vmbus_channel_gpadl_teardown), GFP_KERNEL);
if (!info)
return -ENOMEM;
init_completion(&info->waitevent);
info->waiting_channel = channel;
msg = (struct vmbus_channel_gpadl_teardown *)info->msg;
msg->header.msgtype = CHANNELMSG_GPADL_TEARDOWN;
msg->child_relid = channel->offermsg.child_relid;
msg->gpadl = gpadl_handle;
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_add_tail(&info->msglistentry,
&vmbus_connection.chn_msg_list);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
if (channel->rescind)
goto post_msg_err;
ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_gpadl_teardown),
true);
trace_vmbus_teardown_gpadl(msg, ret);
if (ret)
goto post_msg_err;
wait_for_completion(&info->waitevent);
post_msg_err:
/*
* If the channel has been rescinded;
* we will be awakened by the rescind
* handler; set the error code to zero so we don't leak memory.
*/
if (channel->rescind)
ret = 0;
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_del(&info->msglistentry);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
kfree(info);
return ret;
}
EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl);
static void reset_channel_cb(void *arg)
{
struct vmbus_channel *channel = arg;
channel->onchannel_callback = NULL;
}
void vmbus_reset_channel_cb(struct vmbus_channel *channel)
{
/*
* vmbus_on_event(), running in the per-channel tasklet, can race
* with vmbus_close_internal() in the case of SMP guest, e.g., when
* the former is accessing channel->inbound.ring_buffer, the latter
* could be freeing the ring_buffer pages, so here we must stop it
* first.
*/
tasklet_disable(&channel->callback_event);
channel->sc_creation_callback = NULL;
/* Stop the callback asap */
if (channel->target_cpu != get_cpu()) {
put_cpu();
smp_call_function_single(channel->target_cpu, reset_channel_cb,
channel, true);
} else {
reset_channel_cb(channel);
put_cpu();
}
/* Re-enable tasklet for use on re-open */
tasklet_enable(&channel->callback_event);
}
static int vmbus_close_internal(struct vmbus_channel *channel)
{
struct vmbus_channel_close_channel *msg;
int ret;
vmbus_reset_channel_cb(channel);
/*
* In case a device driver's probe() fails (e.g.,
* util_probe() -> vmbus_open() returns -ENOMEM) and the device is
* rescinded later (e.g., we dynamically disable an Integrated Service
* in Hyper-V Manager), the driver's remove() invokes vmbus_close():
* here we should skip most of the below cleanup work.
*/
if (channel->state != CHANNEL_OPENED_STATE) {
ret = -EINVAL;
goto out;
}
channel->state = CHANNEL_OPEN_STATE;
/* Send a closing message */
msg = &channel->close_msg.msg;
msg->header.msgtype = CHANNELMSG_CLOSECHANNEL;
msg->child_relid = channel->offermsg.child_relid;
ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_close_channel),
true);
trace_vmbus_close_internal(msg, ret);
if (ret) {
pr_err("Close failed: close post msg return is %d\n", ret);
/*
* If we failed to post the close msg,
* it is perhaps better to leak memory.
*/
goto out;
}
/* Tear down the gpadl for the channel's ring buffer */
if (channel->ringbuffer_gpadlhandle) {
ret = vmbus_teardown_gpadl(channel,
channel->ringbuffer_gpadlhandle);
if (ret) {
pr_err("Close failed: teardown gpadl return %d\n", ret);
/*
* If we failed to teardown gpadl,
* it is perhaps better to leak memory.
*/
goto out;
}
}
/* Cleanup the ring buffers for this channel */
hv_ringbuffer_cleanup(&channel->outbound);
hv_ringbuffer_cleanup(&channel->inbound);
__free_pages(channel->ringbuffer_page,
get_order(channel->ringbuffer_pagecount << PAGE_SHIFT));
out:
return ret;
}
/*
* vmbus_close - Close the specified channel
*/
void vmbus_close(struct vmbus_channel *channel)
{
struct list_head *cur, *tmp;
struct vmbus_channel *cur_channel;
if (channel->primary_channel != NULL) {
/*
* We will only close sub-channels when
* the primary is closed.
*/
return;
}
/*
* Close all the sub-channels first and then close the
* primary channel.
*/
list_for_each_safe(cur, tmp, &channel->sc_list) {
cur_channel = list_entry(cur, struct vmbus_channel, sc_list);
if (cur_channel->rescind) {
wait_for_completion(&cur_channel->rescind_event);
mutex_lock(&vmbus_connection.channel_mutex);
vmbus_close_internal(cur_channel);
hv_process_channel_removal(
cur_channel->offermsg.child_relid);
} else {
mutex_lock(&vmbus_connection.channel_mutex);
vmbus_close_internal(cur_channel);
}
mutex_unlock(&vmbus_connection.channel_mutex);
}
/*
* Now close the primary.
*/
mutex_lock(&vmbus_connection.channel_mutex);
vmbus_close_internal(channel);
mutex_unlock(&vmbus_connection.channel_mutex);
}
EXPORT_SYMBOL_GPL(vmbus_close);
/**
* vmbus_sendpacket() - Send the specified buffer on the given channel
* @channel: Pointer to vmbus_channel structure.
* @buffer: Pointer to the buffer you want to receive the data into.
* @bufferlen: Maximum size of what the the buffer will hold
* @requestid: Identifier of the request
* @type: Type of packet that is being send e.g. negotiate, time
* packet etc.
*
* Sends data in @buffer directly to hyper-v via the vmbus
* This will send the data unparsed to hyper-v.
*
* Mainly used by Hyper-V drivers.
*/
int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer,
u32 bufferlen, u64 requestid,
enum vmbus_packet_type type, u32 flags)
{
struct vmpacket_descriptor desc;
u32 packetlen = sizeof(struct vmpacket_descriptor) + bufferlen;
u32 packetlen_aligned = ALIGN(packetlen, sizeof(u64));
struct kvec bufferlist[3];
u64 aligned_data = 0;
int num_vecs = ((bufferlen != 0) ? 3 : 1);
/* Setup the descriptor */
desc.type = type; /* VmbusPacketTypeDataInBand; */
desc.flags = flags; /* VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED; */
/* in 8-bytes granularity */
desc.offset8 = sizeof(struct vmpacket_descriptor) >> 3;
desc.len8 = (u16)(packetlen_aligned >> 3);
desc.trans_id = requestid;
bufferlist[0].iov_base = &desc;
bufferlist[0].iov_len = sizeof(struct vmpacket_descriptor);
bufferlist[1].iov_base = buffer;
bufferlist[1].iov_len = bufferlen;
bufferlist[2].iov_base = &aligned_data;
bufferlist[2].iov_len = (packetlen_aligned - packetlen);
return hv_ringbuffer_write(channel, bufferlist, num_vecs);
}
EXPORT_SYMBOL(vmbus_sendpacket);
/*
* vmbus_sendpacket_pagebuffer - Send a range of single-page buffer
* packets using a GPADL Direct packet type. This interface allows you
* to control notifying the host. This will be useful for sending
* batched data. Also the sender can control the send flags
* explicitly.
*/
int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel,
struct hv_page_buffer pagebuffers[],
u32 pagecount, void *buffer, u32 bufferlen,
u64 requestid)
{
int i;
struct vmbus_channel_packet_page_buffer desc;
u32 descsize;
u32 packetlen;
u32 packetlen_aligned;
struct kvec bufferlist[3];
u64 aligned_data = 0;
if (pagecount > MAX_PAGE_BUFFER_COUNT)
return -EINVAL;
/*
* Adjust the size down since vmbus_channel_packet_page_buffer is the
* largest size we support
*/
descsize = sizeof(struct vmbus_channel_packet_page_buffer) -
((MAX_PAGE_BUFFER_COUNT - pagecount) *
sizeof(struct hv_page_buffer));
packetlen = descsize + bufferlen;
packetlen_aligned = ALIGN(packetlen, sizeof(u64));
/* Setup the descriptor */
desc.type = VM_PKT_DATA_USING_GPA_DIRECT;
desc.flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED;
desc.dataoffset8 = descsize >> 3; /* in 8-bytes granularity */
desc.length8 = (u16)(packetlen_aligned >> 3);
desc.transactionid = requestid;
desc.reserved = 0;
desc.rangecount = pagecount;
for (i = 0; i < pagecount; i++) {
desc.range[i].len = pagebuffers[i].len;
desc.range[i].offset = pagebuffers[i].offset;
desc.range[i].pfn = pagebuffers[i].pfn;
}
bufferlist[0].iov_base = &desc;
bufferlist[0].iov_len = descsize;
bufferlist[1].iov_base = buffer;
bufferlist[1].iov_len = bufferlen;
bufferlist[2].iov_base = &aligned_data;
bufferlist[2].iov_len = (packetlen_aligned - packetlen);
return hv_ringbuffer_write(channel, bufferlist, 3);
}
EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer);
/*
* vmbus_sendpacket_multipagebuffer - Send a multi-page buffer packet
* using a GPADL Direct packet type.
* The buffer includes the vmbus descriptor.
*/
int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
struct vmbus_packet_mpb_array *desc,
u32 desc_size,
void *buffer, u32 bufferlen, u64 requestid)
{
u32 packetlen;
u32 packetlen_aligned;
struct kvec bufferlist[3];
u64 aligned_data = 0;
packetlen = desc_size + bufferlen;
packetlen_aligned = ALIGN(packetlen, sizeof(u64));
/* Setup the descriptor */
desc->type = VM_PKT_DATA_USING_GPA_DIRECT;
desc->flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED;
desc->dataoffset8 = desc_size >> 3; /* in 8-bytes granularity */
desc->length8 = (u16)(packetlen_aligned >> 3);
desc->transactionid = requestid;
desc->reserved = 0;
desc->rangecount = 1;
bufferlist[0].iov_base = desc;
bufferlist[0].iov_len = desc_size;
bufferlist[1].iov_base = buffer;
bufferlist[1].iov_len = bufferlen;
bufferlist[2].iov_base = &aligned_data;
bufferlist[2].iov_len = (packetlen_aligned - packetlen);
return hv_ringbuffer_write(channel, bufferlist, 3);
}
EXPORT_SYMBOL_GPL(vmbus_sendpacket_mpb_desc);
/**
* vmbus_recvpacket() - Retrieve the user packet on the specified channel
* @channel: Pointer to vmbus_channel structure.
* @buffer: Pointer to the buffer you want to receive the data into.
* @bufferlen: Maximum size of what the the buffer will hold
* @buffer_actual_len: The actual size of the data after it was received
* @requestid: Identifier of the request
*
* Receives directly from the hyper-v vmbus and puts the data it received
* into Buffer. This will receive the data unparsed from hyper-v.
*
* Mainly used by Hyper-V drivers.
*/
static inline int
__vmbus_recvpacket(struct vmbus_channel *channel, void *buffer,
u32 bufferlen, u32 *buffer_actual_len, u64 *requestid,
bool raw)
{
return hv_ringbuffer_read(channel, buffer, bufferlen,
buffer_actual_len, requestid, raw);
}
int vmbus_recvpacket(struct vmbus_channel *channel, void *buffer,
u32 bufferlen, u32 *buffer_actual_len,
u64 *requestid)
{
return __vmbus_recvpacket(channel, buffer, bufferlen,
buffer_actual_len, requestid, false);
}
EXPORT_SYMBOL(vmbus_recvpacket);
/*
* vmbus_recvpacket_raw - Retrieve the raw packet on the specified channel
*/
int vmbus_recvpacket_raw(struct vmbus_channel *channel, void *buffer,
u32 bufferlen, u32 *buffer_actual_len,
u64 *requestid)
{
return __vmbus_recvpacket(channel, buffer, bufferlen,
buffer_actual_len, requestid, true);
}
EXPORT_SYMBOL_GPL(vmbus_recvpacket_raw);
File diff suppressed because it is too large. Load diff
+480
View File
@@ -0,0 +1,480 @@
/*
*
* 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>
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/delay.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/hyperv.h>
#include <linux/export.h>
#include <asm/mshyperv.h>
#include "hyperv_vmbus.h"
struct vmbus_connection vmbus_connection = {
.conn_state = DISCONNECTED,
.next_gpadl_handle = ATOMIC_INIT(0xE1E10),
};
EXPORT_SYMBOL_GPL(vmbus_connection);
/*
* Negotiated protocol version with the host.
*/
__u32 vmbus_proto_version;
EXPORT_SYMBOL_GPL(vmbus_proto_version);
static __u32 vmbus_get_next_version(__u32 current_version)
{
switch (current_version) {
case (VERSION_WIN7):
return VERSION_WS2008;
case (VERSION_WIN8):
return VERSION_WIN7;
case (VERSION_WIN8_1):
return VERSION_WIN8;
case (VERSION_WIN10):
return VERSION_WIN8_1;
case (VERSION_WIN10_V5):
return VERSION_WIN10;
case (VERSION_WS2008):
default:
return VERSION_INVAL;
}
}
static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
__u32 version)
{
int ret = 0;
unsigned int cur_cpu;
struct vmbus_channel_initiate_contact *msg;
unsigned long flags;
init_completion(&msginfo->waitevent);
msg = (struct vmbus_channel_initiate_contact *)msginfo->msg;
memset(msg, 0, sizeof(*msg));
msg->header.msgtype = CHANNELMSG_INITIATE_CONTACT;
msg->vmbus_version_requested = version;
/*
* VMBus protocol 5.0 (VERSION_WIN10_V5) requires that we must use
* VMBUS_MESSAGE_CONNECTION_ID_4 for the Initiate Contact Message,
* and for subsequent messages, we must use the Message Connection ID
* field in the host-returned Version Response Message. And, with
* VERSION_WIN10_V5, we don't use msg->interrupt_page, but we tell
* the host explicitly that we still use VMBUS_MESSAGE_SINT(2) for
* compatibility.
*
* On old hosts, we should always use VMBUS_MESSAGE_CONNECTION_ID (1).
*/
if (version >= VERSION_WIN10_V5) {
msg->msg_sint = VMBUS_MESSAGE_SINT;
vmbus_connection.msg_conn_id = VMBUS_MESSAGE_CONNECTION_ID_4;
} else {
msg->interrupt_page = virt_to_phys(vmbus_connection.int_page);
vmbus_connection.msg_conn_id = VMBUS_MESSAGE_CONNECTION_ID;
}
msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]);
msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]);
/*
* We want all channel messages to be delivered on CPU 0.
* This has been the behavior pre-win8. This is not
* perf issue and having all channel messages delivered on CPU 0
* would be ok.
* For post win8 hosts, we support receiving channel messagges on
* all the CPUs. This is needed for kexec to work correctly where
* the CPU attempting to connect may not be CPU 0.
*/
if (version >= VERSION_WIN8_1) {
cur_cpu = get_cpu();
msg->target_vcpu = hv_cpu_number_to_vp_number(cur_cpu);
vmbus_connection.connect_cpu = cur_cpu;
put_cpu();
} else {
msg->target_vcpu = 0;
vmbus_connection.connect_cpu = 0;
}
/*
* Add to list before we send the request since we may
* receive the response before returning from this routine
*/
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_add_tail(&msginfo->msglistentry,
&vmbus_connection.chn_msg_list);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
ret = vmbus_post_msg(msg,
sizeof(struct vmbus_channel_initiate_contact),
true);
trace_vmbus_negotiate_version(msg, ret);
if (ret != 0) {
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_del(&msginfo->msglistentry);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock,
flags);
return ret;
}
/* Wait for the connection response */
wait_for_completion(&msginfo->waitevent);
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_del(&msginfo->msglistentry);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
/* Check if successful */
if (msginfo->response.version_response.version_supported) {
vmbus_connection.conn_state = CONNECTED;
if (version >= VERSION_WIN10_V5)
vmbus_connection.msg_conn_id =
msginfo->response.version_response.msg_conn_id;
} else {
return -ECONNREFUSED;
}
return ret;
}
/*
* vmbus_connect - Sends a connect request on the partition service connection
*/
int vmbus_connect(void)
{
int ret = 0;
struct vmbus_channel_msginfo *msginfo = NULL;
__u32 version;
/* Initialize the vmbus connection */
vmbus_connection.conn_state = CONNECTING;
vmbus_connection.work_queue = create_workqueue("hv_vmbus_con");
if (!vmbus_connection.work_queue) {
ret = -ENOMEM;
goto cleanup;
}
vmbus_connection.handle_primary_chan_wq =
create_workqueue("hv_pri_chan");
if (!vmbus_connection.handle_primary_chan_wq) {
ret = -ENOMEM;
goto cleanup;
}
vmbus_connection.handle_sub_chan_wq =
create_workqueue("hv_sub_chan");
if (!vmbus_connection.handle_sub_chan_wq) {
ret = -ENOMEM;
goto cleanup;
}
INIT_LIST_HEAD(&vmbus_connection.chn_msg_list);
spin_lock_init(&vmbus_connection.channelmsg_lock);
INIT_LIST_HEAD(&vmbus_connection.chn_list);
mutex_init(&vmbus_connection.channel_mutex);
/*
* Setup the vmbus event connection for channel interrupt
* abstraction stuff
*/
vmbus_connection.int_page =
(void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, 0);
if (vmbus_connection.int_page == NULL) {
ret = -ENOMEM;
goto cleanup;
}
vmbus_connection.recv_int_page = vmbus_connection.int_page;
vmbus_connection.send_int_page =
(void *)((unsigned long)vmbus_connection.int_page +
(PAGE_SIZE >> 1));
/*
* Setup the monitor notification facility. The 1st page for
* parent->child and the 2nd page for child->parent
*/
vmbus_connection.monitor_pages[0] = (void *)__get_free_pages((GFP_KERNEL|__GFP_ZERO), 0);
vmbus_connection.monitor_pages[1] = (void *)__get_free_pages((GFP_KERNEL|__GFP_ZERO), 0);
if ((vmbus_connection.monitor_pages[0] == NULL) ||
(vmbus_connection.monitor_pages[1] == NULL)) {
ret = -ENOMEM;
goto cleanup;
}
msginfo = kzalloc(sizeof(*msginfo) +
sizeof(struct vmbus_channel_initiate_contact),
GFP_KERNEL);
if (msginfo == NULL) {
ret = -ENOMEM;
goto cleanup;
}
/*
* Negotiate a compatible VMBUS version number with the
* host. We start with the highest number we can support
* and work our way down until we negotiate a compatible
* version.
*/
version = VERSION_CURRENT;
do {
ret = vmbus_negotiate_version(msginfo, version);
if (ret == -ETIMEDOUT)
goto cleanup;
if (vmbus_connection.conn_state == CONNECTED)
break;
version = vmbus_get_next_version(version);
} while (version != VERSION_INVAL);
if (version == VERSION_INVAL)
goto cleanup;
vmbus_proto_version = version;
pr_info("Vmbus version:%d.%d\n",
version >> 16, version & 0xFFFF);
kfree(msginfo);
return 0;
cleanup:
pr_err("Unable to connect to host\n");
vmbus_connection.conn_state = DISCONNECTED;
vmbus_disconnect();
kfree(msginfo);
return ret;
}
void vmbus_disconnect(void)
{
/*
* First send the unload request to the host.
*/
vmbus_initiate_unload(false);
if (vmbus_connection.handle_sub_chan_wq)
destroy_workqueue(vmbus_connection.handle_sub_chan_wq);
if (vmbus_connection.handle_primary_chan_wq)
destroy_workqueue(vmbus_connection.handle_primary_chan_wq);
if (vmbus_connection.work_queue)
destroy_workqueue(vmbus_connection.work_queue);
if (vmbus_connection.int_page) {
free_pages((unsigned long)vmbus_connection.int_page, 0);
vmbus_connection.int_page = NULL;
}
free_pages((unsigned long)vmbus_connection.monitor_pages[0], 0);
free_pages((unsigned long)vmbus_connection.monitor_pages[1], 0);
vmbus_connection.monitor_pages[0] = NULL;
vmbus_connection.monitor_pages[1] = NULL;
}
/*
* relid2channel - Get the channel object given its
* child relative id (ie channel id)
*/
struct vmbus_channel *relid2channel(u32 relid)
{
struct vmbus_channel *channel;
struct vmbus_channel *found_channel = NULL;
struct list_head *cur, *tmp;
struct vmbus_channel *cur_sc;
BUG_ON(!mutex_is_locked(&vmbus_connection.channel_mutex));
list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
if (channel->offermsg.child_relid == relid) {
found_channel = channel;
break;
} else if (!list_empty(&channel->sc_list)) {
/*
* Deal with sub-channels.
*/
list_for_each_safe(cur, tmp, &channel->sc_list) {
cur_sc = list_entry(cur, struct vmbus_channel,
sc_list);
if (cur_sc->offermsg.child_relid == relid) {
found_channel = cur_sc;
break;
}
}
}
}
return found_channel;
}
/*
* vmbus_on_event - Process a channel event notification
*
* For batched channels (default) optimize host to guest signaling
* by ensuring:
* 1. While reading the channel, we disable interrupts from host.
* 2. Ensure that we process all posted messages from the host
* before returning from this callback.
* 3. Once we return, enable signaling from the host. Once this
* state is set we check to see if additional packets are
* available to read. In this case we repeat the process.
* If this tasklet has been running for a long time
* then reschedule ourselves.
*/
void vmbus_on_event(unsigned long data)
{
struct vmbus_channel *channel = (void *) data;
unsigned long time_limit = jiffies + 2;
trace_vmbus_on_event(channel);
do {
void (*callback_fn)(void *);
/* A channel once created is persistent even when
* there is no driver handling the device. An
* unloading driver sets the onchannel_callback to NULL.
*/
callback_fn = READ_ONCE(channel->onchannel_callback);
if (unlikely(callback_fn == NULL))
return;
(*callback_fn)(channel->channel_callback_context);
if (channel->callback_mode != HV_CALL_BATCHED)
return;
if (likely(hv_end_read(&channel->inbound) == 0))
return;
hv_begin_read(&channel->inbound);
} while (likely(time_before(jiffies, time_limit)));
/* The time limit (2 jiffies) has been reached */
tasklet_schedule(&channel->callback_event);
}
/*
* vmbus_post_msg - Send a msg on the vmbus's message connection
*/
int vmbus_post_msg(void *buffer, size_t buflen, bool can_sleep)
{
struct vmbus_channel_message_header *hdr;
union hv_connection_id conn_id;
int ret = 0;
int retries = 0;
u32 usec = 1;
conn_id.asu32 = 0;
conn_id.u.id = vmbus_connection.msg_conn_id;
/*
* hv_post_message() can have transient failures because of
* insufficient resources. Retry the operation a couple of
* times before giving up.
*/
while (retries < 100) {
ret = hv_post_message(conn_id, 1, buffer, buflen);
switch (ret) {
case HV_STATUS_INVALID_CONNECTION_ID:
/*
* See vmbus_negotiate_version(): VMBus protocol 5.0
* requires that we must use
* VMBUS_MESSAGE_CONNECTION_ID_4 for the Initiate
* Contact message, but on old hosts that only
* support VMBus protocol 4.0 or lower, here we get
* HV_STATUS_INVALID_CONNECTION_ID and we should
* return an error immediately without retrying.
*/
hdr = buffer;
if (hdr->msgtype == CHANNELMSG_INITIATE_CONTACT)
return -EINVAL;
/*
* We could get this if we send messages too
* frequently.
*/
ret = -EAGAIN;
break;
case HV_STATUS_INSUFFICIENT_MEMORY:
case HV_STATUS_INSUFFICIENT_BUFFERS:
ret = -ENOBUFS;
break;
case HV_STATUS_SUCCESS:
return ret;
default:
pr_err("hv_post_msg() failed; error code:%d\n", ret);
return -EINVAL;
}
retries++;
if (can_sleep && usec > 1000)
msleep(usec / 1000);
else if (usec < MAX_UDELAY_MS * 1000)
udelay(usec);
else
mdelay(usec / 1000);
if (retries < 22)
usec *= 2;
}
return ret;
}
/*
* vmbus_set_event - Send an event notification to the parent
*/
void vmbus_set_event(struct vmbus_channel *channel)
{
u32 child_relid = channel->offermsg.child_relid;
if (!channel->is_dedicated_interrupt)
vmbus_send_interrupt(child_relid);
++channel->sig_events;
hv_do_fast_hypercall8(HVCALL_SIGNAL_EVENT, channel->sig_event);
}
EXPORT_SYMBOL_GPL(vmbus_set_event);
+442
View File
@@ -0,0 +1,442 @@
/*
* 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>
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/hyperv.h>
#include <linux/version.h>
#include <linux/random.h>
#include <linux/clockchips.h>
#include <asm/mshyperv.h>
#include "hyperv_vmbus.h"
/* The one and only */
struct hv_context hv_context = {
.synic_initialized = false,
};
/*
* If false, we're using the old mechanism for stimer0 interrupts
* where it sends a VMbus message when it expires. The old
* mechanism is used when running on older versions of Hyper-V
* that don't support Direct Mode. While Hyper-V provides
* four stimer's per CPU, Linux uses only stimer0.
*/
static bool direct_mode_enabled;
static int stimer0_irq;
static int stimer0_vector;
#define HV_TIMER_FREQUENCY (10 * 1000 * 1000) /* 100ns period */
#define HV_MAX_MAX_DELTA_TICKS 0xffffffff
#define HV_MIN_DELTA_TICKS 1
/*
* hv_init - Main initialization routine.
*
* This routine must be called before any other routines in here are called
*/
int hv_init(void)
{
hv_context.cpu_context = alloc_percpu(struct hv_per_cpu_context);
if (!hv_context.cpu_context)
return -ENOMEM;
direct_mode_enabled = ms_hyperv.misc_features &
HV_STIMER_DIRECT_MODE_AVAILABLE;
return 0;
}
/*
* hv_post_message - Post a message using the hypervisor message IPC.
*
* This involves a hypercall.
*/
int hv_post_message(union hv_connection_id connection_id,
enum hv_message_type message_type,
void *payload, size_t payload_size)
{
struct hv_input_post_message *aligned_msg;
struct hv_per_cpu_context *hv_cpu;
u64 status;
if (payload_size > HV_MESSAGE_PAYLOAD_BYTE_COUNT)
return -EMSGSIZE;
hv_cpu = get_cpu_ptr(hv_context.cpu_context);
aligned_msg = hv_cpu->post_msg_page;
aligned_msg->connectionid = connection_id;
aligned_msg->reserved = 0;
aligned_msg->message_type = message_type;
aligned_msg->payload_size = payload_size;
memcpy((void *)aligned_msg->payload, payload, payload_size);
status = hv_do_hypercall(HVCALL_POST_MESSAGE, aligned_msg, NULL);
/* Preemption must remain disabled until after the hypercall
* so some other thread can't get scheduled onto this cpu and
* corrupt the per-cpu post_msg_page
*/
put_cpu_ptr(hv_cpu);
return status & 0xFFFF;
}
/*
* ISR for when stimer0 is operating in Direct Mode. Direct Mode
* does not use VMbus or any VMbus messages, so process here and not
* in the VMbus driver code.
*/
static void hv_stimer0_isr(void)
{
struct hv_per_cpu_context *hv_cpu;
hv_cpu = this_cpu_ptr(hv_context.cpu_context);
hv_cpu->clk_evt->event_handler(hv_cpu->clk_evt);
add_interrupt_randomness(stimer0_vector, 0);
}
static int hv_ce_set_next_event(unsigned long delta,
struct clock_event_device *evt)
{
u64 current_tick;
WARN_ON(!clockevent_state_oneshot(evt));
current_tick = hyperv_cs->read(NULL);
current_tick += delta;
hv_init_timer(0, current_tick);
return 0;
}
static int hv_ce_shutdown(struct clock_event_device *evt)
{
hv_init_timer(0, 0);
hv_init_timer_config(0, 0);
if (direct_mode_enabled)
hv_disable_stimer0_percpu_irq(stimer0_irq);
return 0;
}
static int hv_ce_set_oneshot(struct clock_event_device *evt)
{
union hv_timer_config timer_cfg;
timer_cfg.as_uint64 = 0;
timer_cfg.enable = 1;
timer_cfg.auto_enable = 1;
if (direct_mode_enabled) {
/*
* When it expires, the timer will directly interrupt
* on the specified hardware vector/IRQ.
*/
timer_cfg.direct_mode = 1;
timer_cfg.apic_vector = stimer0_vector;
hv_enable_stimer0_percpu_irq(stimer0_irq);
} else {
/*
* When it expires, the timer will generate a VMbus message,
* to be handled by the normal VMbus interrupt handler.
*/
timer_cfg.direct_mode = 0;
timer_cfg.sintx = VMBUS_MESSAGE_SINT;
}
hv_init_timer_config(0, timer_cfg.as_uint64);
return 0;
}
static void hv_init_clockevent_device(struct clock_event_device *dev, int cpu)
{
dev->name = "Hyper-V clockevent";
dev->features = CLOCK_EVT_FEAT_ONESHOT;
dev->cpumask = cpumask_of(cpu);
dev->rating = 1000;
/*
* 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_state_shutdown = hv_ce_shutdown;
dev->set_state_oneshot = hv_ce_set_oneshot;
dev->set_next_event = hv_ce_set_next_event;
}
int hv_synic_alloc(void)
{
int cpu;
struct hv_per_cpu_context *hv_cpu;
/*
* First, zero all per-cpu memory areas so hv_synic_free() can
* detect what memory has been allocated and cleanup properly
* after any failures.
*/
for_each_present_cpu(cpu) {
hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu);
memset(hv_cpu, 0, sizeof(*hv_cpu));
}
hv_context.hv_numa_map = kcalloc(nr_node_ids, sizeof(struct cpumask),
GFP_KERNEL);
if (hv_context.hv_numa_map == NULL) {
pr_err("Unable to allocate NUMA map\n");
goto err;
}
for_each_present_cpu(cpu) {
hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu);
tasklet_init(&hv_cpu->msg_dpc,
vmbus_on_msg_dpc, (unsigned long) hv_cpu);
hv_cpu->clk_evt = kzalloc(sizeof(struct clock_event_device),
GFP_KERNEL);
if (hv_cpu->clk_evt == NULL) {
pr_err("Unable to allocate clock event device\n");
goto err;
}
hv_init_clockevent_device(hv_cpu->clk_evt, cpu);
hv_cpu->synic_message_page =
(void *)get_zeroed_page(GFP_ATOMIC);
if (hv_cpu->synic_message_page == NULL) {
pr_err("Unable to allocate SYNIC message page\n");
goto err;
}
hv_cpu->synic_event_page = (void *)get_zeroed_page(GFP_ATOMIC);
if (hv_cpu->synic_event_page == NULL) {
pr_err("Unable to allocate SYNIC event page\n");
goto err;
}
hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC);
if (hv_cpu->post_msg_page == NULL) {
pr_err("Unable to allocate post msg page\n");
goto err;
}
INIT_LIST_HEAD(&hv_cpu->chan_list);
}
if (direct_mode_enabled &&
hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector,
hv_stimer0_isr))
goto err;
return 0;
err:
/*
* Any memory allocations that succeeded will be freed when
* the caller cleans up by calling hv_synic_free()
*/
return -ENOMEM;
}
void hv_synic_free(void)
{
int cpu;
for_each_present_cpu(cpu) {
struct hv_per_cpu_context *hv_cpu
= per_cpu_ptr(hv_context.cpu_context, cpu);
kfree(hv_cpu->clk_evt);
free_page((unsigned long)hv_cpu->synic_event_page);
free_page((unsigned long)hv_cpu->synic_message_page);
free_page((unsigned long)hv_cpu->post_msg_page);
}
kfree(hv_context.hv_numa_map);
}
/*
* hv_synic_init - Initialize the Synthetic Interrupt Controller.
*
* If it is already initialized by another entity (ie x2v shim), we need to
* retrieve the initialized message and event pages. Otherwise, we create and
* initialize the message and event pages.
*/
int hv_synic_init(unsigned int cpu)
{
struct hv_per_cpu_context *hv_cpu
= per_cpu_ptr(hv_context.cpu_context, cpu);
union hv_synic_simp simp;
union hv_synic_siefp siefp;
union hv_synic_sint shared_sint;
union hv_synic_scontrol sctrl;
/* Setup the Synic's message page */
hv_get_simp(simp.as_uint64);
simp.simp_enabled = 1;
simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page)
>> PAGE_SHIFT;
hv_set_simp(simp.as_uint64);
/* Setup the Synic's event page */
hv_get_siefp(siefp.as_uint64);
siefp.siefp_enabled = 1;
siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page)
>> PAGE_SHIFT;
hv_set_siefp(siefp.as_uint64);
/* Setup the shared SINT. */
hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
shared_sint.vector = HYPERVISOR_CALLBACK_VECTOR;
shared_sint.masked = false;
if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED)
shared_sint.auto_eoi = false;
else
shared_sint.auto_eoi = true;
hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
/* Enable the global synic bit */
hv_get_synic_state(sctrl.as_uint64);
sctrl.enable = 1;
hv_set_synic_state(sctrl.as_uint64);
hv_context.synic_initialized = true;
/*
* Register the per-cpu clockevent source.
*/
if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE)
clockevents_config_and_register(hv_cpu->clk_evt,
HV_TIMER_FREQUENCY,
HV_MIN_DELTA_TICKS,
HV_MAX_MAX_DELTA_TICKS);
return 0;
}
/*
* hv_synic_clockevents_cleanup - Cleanup clockevent devices
*/
void hv_synic_clockevents_cleanup(void)
{
int cpu;
if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE))
return;
if (direct_mode_enabled)
hv_remove_stimer0_irq(stimer0_irq);
for_each_present_cpu(cpu) {
struct hv_per_cpu_context *hv_cpu
= per_cpu_ptr(hv_context.cpu_context, cpu);
clockevents_unbind_device(hv_cpu->clk_evt, cpu);
}
}
/*
* hv_synic_cleanup - Cleanup routine for hv_synic_init().
*/
int hv_synic_cleanup(unsigned int cpu)
{
union hv_synic_sint shared_sint;
union hv_synic_simp simp;
union hv_synic_siefp siefp;
union hv_synic_scontrol sctrl;
struct vmbus_channel *channel, *sc;
bool channel_found = false;
unsigned long flags;
if (!hv_context.synic_initialized)
return -EFAULT;
/*
* Search for channels which are bound to the CPU we're about to
* cleanup. In case we find one and vmbus is still connected we need to
* fail, this will effectively prevent CPU offlining. There is no way
* we can re-bind channels to different CPUs for now.
*/
mutex_lock(&vmbus_connection.channel_mutex);
list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
if (channel->target_cpu == cpu) {
channel_found = true;
break;
}
spin_lock_irqsave(&channel->lock, flags);
list_for_each_entry(sc, &channel->sc_list, sc_list) {
if (sc->target_cpu == cpu) {
channel_found = true;
break;
}
}
spin_unlock_irqrestore(&channel->lock, flags);
if (channel_found)
break;
}
mutex_unlock(&vmbus_connection.channel_mutex);
if (channel_found && vmbus_connection.conn_state == CONNECTED)
return -EBUSY;
/* Turn off clockevent device */
if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) {
struct hv_per_cpu_context *hv_cpu
= this_cpu_ptr(hv_context.cpu_context);
clockevents_unbind_device(hv_cpu->clk_evt, cpu);
hv_ce_shutdown(hv_cpu->clk_evt);
}
hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
shared_sint.masked = 1;
/* Need to correctly cleanup in the case of SMP!!! */
/* Disable the interrupt */
hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
hv_get_simp(simp.as_uint64);
simp.simp_enabled = 0;
simp.base_simp_gpa = 0;
hv_set_simp(simp.as_uint64);
hv_get_siefp(siefp.as_uint64);
siefp.siefp_enabled = 0;
siefp.base_siefp_gpa = 0;
hv_set_siefp(siefp.as_uint64);
/* Disable the global synic bit */
hv_get_synic_state(sctrl.as_uint64);
sctrl.enable = 0;
hv_set_synic_state(sctrl.as_uint64);
return 0;
}
File diff suppressed because it is too large. Load diff
+363
View File
@@ -0,0 +1,363 @@
/*
* An implementation of file copy service.
*
* Copyright (C) 2014, Microsoft, Inc.
*
* Author : K. Y. Srinivasan <ksrinivasan@novell.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
* by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
* NON INFRINGEMENT. See the GNU General Public License for more
* details.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/nls.h>
#include <linux/workqueue.h>
#include <linux/hyperv.h>
#include <linux/sched.h>
#include "hyperv_vmbus.h"
#include "hv_utils_transport.h"
#define WIN8_SRV_MAJOR 1
#define WIN8_SRV_MINOR 1
#define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR)
#define FCOPY_VER_COUNT 1
static const int fcopy_versions[] = {
WIN8_SRV_VERSION
};
#define FW_VER_COUNT 1
static const int fw_versions[] = {
UTIL_FW_VERSION
};
/*
* Global state maintained for transaction that is being processed.
* For a class of integration services, including the "file copy service",
* the specified protocol is a "request/response" protocol which means that
* there can only be single outstanding transaction from the host at any
* given point in time. We use this to simplify memory management in this
* driver - we cache and process only one message at a time.
*
* While the request/response protocol is guaranteed by the host, we further
* ensure this by serializing packet processing in this driver - we do not
* read additional packets from the VMBUs until the current packet is fully
* handled.
*/
static struct {
int state; /* hvutil_device_state */
int recv_len; /* number of bytes received. */
struct hv_fcopy_hdr *fcopy_msg; /* current message */
struct vmbus_channel *recv_channel; /* chn we got the request */
u64 recv_req_id; /* request ID. */
} fcopy_transaction;
static void fcopy_respond_to_host(int error);
static void fcopy_send_data(struct work_struct *dummy);
static void fcopy_timeout_func(struct work_struct *dummy);
static DECLARE_DELAYED_WORK(fcopy_timeout_work, fcopy_timeout_func);
static DECLARE_WORK(fcopy_send_work, fcopy_send_data);
static const char fcopy_devname[] = "vmbus/hv_fcopy";
static u8 *recv_buffer;
static struct hvutil_transport *hvt;
/*
* This state maintains the version number registered by the daemon.
*/
static int dm_reg_value;
static void fcopy_poll_wrapper(void *channel)
{
/* Transaction is finished, reset the state here to avoid races. */
fcopy_transaction.state = HVUTIL_READY;
hv_fcopy_onchannelcallback(channel);
}
static void fcopy_timeout_func(struct work_struct *dummy)
{
/*
* If the timer fires, the user-mode component has not responded;
* process the pending transaction.
*/
fcopy_respond_to_host(HV_E_FAIL);
hv_poll_channel(fcopy_transaction.recv_channel, fcopy_poll_wrapper);
}
static void fcopy_register_done(void)
{
pr_debug("FCP: userspace daemon registered\n");
hv_poll_channel(fcopy_transaction.recv_channel, fcopy_poll_wrapper);
}
static int fcopy_handle_handshake(u32 version)
{
u32 our_ver = FCOPY_CURRENT_VERSION;
switch (version) {
case FCOPY_VERSION_0:
/* Daemon doesn't expect us to reply */
dm_reg_value = version;
break;
case FCOPY_VERSION_1:
/* Daemon expects us to reply with our own version */
if (hvutil_transport_send(hvt, &our_ver, sizeof(our_ver),
fcopy_register_done))
return -EFAULT;
dm_reg_value = version;
break;
default:
/*
* For now we will fail the registration.
* If and when we have multiple versions to
* deal with, we will be backward compatible.
* We will add this code when needed.
*/
return -EINVAL;
}
pr_debug("FCP: userspace daemon ver. %d connected\n", version);
return 0;
}
static void fcopy_send_data(struct work_struct *dummy)
{
struct hv_start_fcopy *smsg_out = NULL;
int operation = fcopy_transaction.fcopy_msg->operation;
struct hv_start_fcopy *smsg_in;
void *out_src;
int rc, out_len;
/*
* The strings sent from the host are encoded in
* in utf16; convert it to utf8 strings.
* The host assures us that the utf16 strings will not exceed
* the max lengths specified. We will however, reserve room
* for the string terminating character - in the utf16s_utf8s()
* function we limit the size of the buffer where the converted
* string is placed to W_MAX_PATH -1 to guarantee
* that the strings can be properly terminated!
*/
switch (operation) {
case START_FILE_COPY:
out_len = sizeof(struct hv_start_fcopy);
smsg_out = kzalloc(sizeof(*smsg_out), GFP_KERNEL);
if (!smsg_out)
return;
smsg_out->hdr.operation = operation;
smsg_in = (struct hv_start_fcopy *)fcopy_transaction.fcopy_msg;
utf16s_to_utf8s((wchar_t *)smsg_in->file_name, W_MAX_PATH,
UTF16_LITTLE_ENDIAN,
(__u8 *)&smsg_out->file_name, W_MAX_PATH - 1);
utf16s_to_utf8s((wchar_t *)smsg_in->path_name, W_MAX_PATH,
UTF16_LITTLE_ENDIAN,
(__u8 *)&smsg_out->path_name, W_MAX_PATH - 1);
smsg_out->copy_flags = smsg_in->copy_flags;
smsg_out->file_size = smsg_in->file_size;
out_src = smsg_out;
break;
case WRITE_TO_FILE:
out_src = fcopy_transaction.fcopy_msg;
out_len = sizeof(struct hv_do_fcopy);
break;
default:
out_src = fcopy_transaction.fcopy_msg;
out_len = fcopy_transaction.recv_len;
break;
}
fcopy_transaction.state = HVUTIL_USERSPACE_REQ;
rc = hvutil_transport_send(hvt, out_src, out_len, NULL);
if (rc) {
pr_debug("FCP: failed to communicate to the daemon: %d\n", rc);
if (cancel_delayed_work_sync(&fcopy_timeout_work)) {
fcopy_respond_to_host(HV_E_FAIL);
fcopy_transaction.state = HVUTIL_READY;
}
}
kfree(smsg_out);
}
/*
* Send a response back to the host.
*/
static void
fcopy_respond_to_host(int error)
{
struct icmsg_hdr *icmsghdr;
u32 buf_len;
struct vmbus_channel *channel;
u64 req_id;
/*
* Copy the global state for completing the transaction. Note that
* only one transaction can be active at a time. This is guaranteed
* by the file copy protocol implemented by the host. Furthermore,
* the "transaction active" state we maintain ensures that there can
* only be one active transaction at a time.
*/
buf_len = fcopy_transaction.recv_len;
channel = fcopy_transaction.recv_channel;
req_id = fcopy_transaction.recv_req_id;
icmsghdr = (struct icmsg_hdr *)
&recv_buffer[sizeof(struct vmbuspipe_hdr)];
if (channel->onchannel_callback == NULL)
/*
* We have raced with util driver being unloaded;
* silently return.
*/
return;
icmsghdr->status = error;
icmsghdr->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE;
vmbus_sendpacket(channel, recv_buffer, buf_len, req_id,
VM_PKT_DATA_INBAND, 0);
}
void hv_fcopy_onchannelcallback(void *context)
{
struct vmbus_channel *channel = context;
u32 recvlen;
u64 requestid;
struct hv_fcopy_hdr *fcopy_msg;
struct icmsg_hdr *icmsghdr;
int fcopy_srv_version;
if (fcopy_transaction.state > HVUTIL_READY)
return;
vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen,
&requestid);
if (recvlen <= 0)
return;
icmsghdr = (struct icmsg_hdr *)&recv_buffer[
sizeof(struct vmbuspipe_hdr)];
if (icmsghdr->icmsgtype == ICMSGTYPE_NEGOTIATE) {
if (vmbus_prep_negotiate_resp(icmsghdr, recv_buffer,
fw_versions, FW_VER_COUNT,
fcopy_versions, FCOPY_VER_COUNT,
NULL, &fcopy_srv_version)) {
pr_info("FCopy IC version %d.%d\n",
fcopy_srv_version >> 16,
fcopy_srv_version & 0xFFFF);
}
} else {
fcopy_msg = (struct hv_fcopy_hdr *)&recv_buffer[
sizeof(struct vmbuspipe_hdr) +
sizeof(struct icmsg_hdr)];
/*
* Stash away this global state for completing the
* transaction; note transactions are serialized.
*/
fcopy_transaction.recv_len = recvlen;
fcopy_transaction.recv_req_id = requestid;
fcopy_transaction.fcopy_msg = fcopy_msg;
if (fcopy_transaction.state < HVUTIL_READY) {
/* Userspace is not registered yet */
fcopy_respond_to_host(HV_E_FAIL);
return;
}
fcopy_transaction.state = HVUTIL_HOSTMSG_RECEIVED;
/*
* Send the information to the user-level daemon.
*/
schedule_work(&fcopy_send_work);
schedule_delayed_work(&fcopy_timeout_work,
HV_UTIL_TIMEOUT * HZ);
return;
}
icmsghdr->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE;
vmbus_sendpacket(channel, recv_buffer, recvlen, requestid,
VM_PKT_DATA_INBAND, 0);
}
/* Callback when data is received from userspace */
static int fcopy_on_msg(void *msg, int len)
{
int *val = (int *)msg;
if (len != sizeof(int))
return -EINVAL;
if (fcopy_transaction.state == HVUTIL_DEVICE_INIT)
return fcopy_handle_handshake(*val);
if (fcopy_transaction.state != HVUTIL_USERSPACE_REQ)
return -EINVAL;
/*
* Complete the transaction by forwarding the result
* to the host. But first, cancel the timeout.
*/
if (cancel_delayed_work_sync(&fcopy_timeout_work)) {
fcopy_transaction.state = HVUTIL_USERSPACE_RECV;
fcopy_respond_to_host(*val);
hv_poll_channel(fcopy_transaction.recv_channel,
fcopy_poll_wrapper);
}
return 0;
}
static void fcopy_on_reset(void)
{
/*
* The daemon has exited; reset the state.
*/
fcopy_transaction.state = HVUTIL_DEVICE_INIT;
if (cancel_delayed_work_sync(&fcopy_timeout_work))
fcopy_respond_to_host(HV_E_FAIL);
}
int hv_fcopy_init(struct hv_util_service *srv)
{
recv_buffer = srv->recv_buffer;
fcopy_transaction.recv_channel = srv->channel;
/*
* When this driver loads, the user level daemon that
* processes the host requests may not yet be running.
* Defer processing channel callbacks until the daemon
* has registered.
*/
fcopy_transaction.state = HVUTIL_DEVICE_INIT;
hvt = hvutil_transport_init(fcopy_devname, 0, 0,
fcopy_on_msg, fcopy_on_reset);
if (!hvt)
return -EFAULT;
return 0;
}
void hv_fcopy_deinit(void)
{
fcopy_transaction.state = HVUTIL_DEVICE_DYING;
cancel_delayed_work_sync(&fcopy_timeout_work);
hvutil_transport_destroy(hvt);
}
+767
View File
@@ -0,0 +1,767 @@
/*
* An implementation of key value pair (KVP) functionality for Linux.
*
*
* Copyright (C) 2010, Novell, Inc.
* Author : K. Y. Srinivasan <ksrinivasan@novell.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
* by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
* NON INFRINGEMENT. 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., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/net.h>
#include <linux/nls.h>
#include <linux/connector.h>
#include <linux/workqueue.h>
#include <linux/hyperv.h>
#include "hyperv_vmbus.h"
#include "hv_utils_transport.h"
/*
* Pre win8 version numbers used in ws2008 and ws 2008 r2 (win7)
*/
#define WS2008_SRV_MAJOR 1
#define WS2008_SRV_MINOR 0
#define WS2008_SRV_VERSION (WS2008_SRV_MAJOR << 16 | WS2008_SRV_MINOR)
#define WIN7_SRV_MAJOR 3
#define WIN7_SRV_MINOR 0
#define WIN7_SRV_VERSION (WIN7_SRV_MAJOR << 16 | WIN7_SRV_MINOR)
#define WIN8_SRV_MAJOR 4
#define WIN8_SRV_MINOR 0
#define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR)
#define KVP_VER_COUNT 3
static const int kvp_versions[] = {
WIN8_SRV_VERSION,
WIN7_SRV_VERSION,
WS2008_SRV_VERSION
};
#define FW_VER_COUNT 2
static const int fw_versions[] = {
UTIL_FW_VERSION,
UTIL_WS2K8_FW_VERSION
};
/*
* Global state maintained for transaction that is being processed. For a class
* of integration services, including the "KVP service", the specified protocol
* is a "request/response" protocol which means that there can only be single
* outstanding transaction from the host at any given point in time. We use
* this to simplify memory management in this driver - we cache and process
* only one message at a time.
*
* While the request/response protocol is guaranteed by the host, we further
* ensure this by serializing packet processing in this driver - we do not
* read additional packets from the VMBUS until the current packet is fully
* handled.
*/
static struct {
int state; /* hvutil_device_state */
int recv_len; /* number of bytes received. */
struct hv_kvp_msg *kvp_msg; /* current message */
struct vmbus_channel *recv_channel; /* chn we got the request */
u64 recv_req_id; /* request ID. */
} kvp_transaction;
/*
* This state maintains the version number registered by the daemon.
*/
static int dm_reg_value;
static void kvp_send_key(struct work_struct *dummy);
static void kvp_respond_to_host(struct hv_kvp_msg *msg, int error);
static void kvp_timeout_func(struct work_struct *dummy);
static void kvp_host_handshake_func(struct work_struct *dummy);
static void kvp_register(int);
static DECLARE_DELAYED_WORK(kvp_timeout_work, kvp_timeout_func);
static DECLARE_DELAYED_WORK(kvp_host_handshake_work, kvp_host_handshake_func);
static DECLARE_WORK(kvp_sendkey_work, kvp_send_key);
static const char kvp_devname[] = "vmbus/hv_kvp";
static u8 *recv_buffer;
static struct hvutil_transport *hvt;
/*
* Register the kernel component with the user-level daemon.
* As part of this registration, pass the LIC version number.
* This number has no meaning, it satisfies the registration protocol.
*/
#define HV_DRV_VERSION "3.1"
static void kvp_poll_wrapper(void *channel)
{
/* Transaction is finished, reset the state here to avoid races. */
kvp_transaction.state = HVUTIL_READY;
tasklet_schedule(&((struct vmbus_channel *)channel)->callback_event);
}
static void kvp_register_done(void)
{
/*
* If we're still negotiating with the host cancel the timeout
* work to not poll the channel twice.
*/
pr_debug("KVP: userspace daemon registered\n");
cancel_delayed_work_sync(&kvp_host_handshake_work);
hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper);
}
static void
kvp_register(int reg_value)
{
struct hv_kvp_msg *kvp_msg;
char *version;
kvp_msg = kzalloc(sizeof(*kvp_msg), GFP_KERNEL);
if (kvp_msg) {
version = kvp_msg->body.kvp_register.version;
kvp_msg->kvp_hdr.operation = reg_value;
strcpy(version, HV_DRV_VERSION);
hvutil_transport_send(hvt, kvp_msg, sizeof(*kvp_msg),
kvp_register_done);
kfree(kvp_msg);
}
}
static void kvp_timeout_func(struct work_struct *dummy)
{
/*
* If the timer fires, the user-mode component has not responded;
* process the pending transaction.
*/
kvp_respond_to_host(NULL, HV_E_FAIL);
hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper);
}
static void kvp_host_handshake_func(struct work_struct *dummy)
{
tasklet_schedule(&kvp_transaction.recv_channel->callback_event);
}
static int kvp_handle_handshake(struct hv_kvp_msg *msg)
{
switch (msg->kvp_hdr.operation) {
case KVP_OP_REGISTER:
dm_reg_value = KVP_OP_REGISTER;
pr_info("KVP: IP injection functionality not available\n");
pr_info("KVP: Upgrade the KVP daemon\n");
break;
case KVP_OP_REGISTER1:
dm_reg_value = KVP_OP_REGISTER1;
break;
default:
pr_info("KVP: incompatible daemon\n");
pr_info("KVP: KVP version: %d, Daemon version: %d\n",
KVP_OP_REGISTER1, msg->kvp_hdr.operation);
return -EINVAL;
}
/*
* We have a compatible daemon; complete the handshake.
*/
pr_debug("KVP: userspace daemon ver. %d connected\n",
msg->kvp_hdr.operation);
kvp_register(dm_reg_value);
return 0;
}
/*
* Callback when data is received from user mode.
*/
static int kvp_on_msg(void *msg, int len)
{
struct hv_kvp_msg *message = (struct hv_kvp_msg *)msg;
struct hv_kvp_msg_enumerate *data;
int error = 0;
if (len < sizeof(*message))
return -EINVAL;
/*
* If we are negotiating the version information
* with the daemon; handle that first.
*/
if (kvp_transaction.state < HVUTIL_READY) {
return kvp_handle_handshake(message);
}
/* We didn't send anything to userspace so the reply is spurious */
if (kvp_transaction.state < HVUTIL_USERSPACE_REQ)
return -EINVAL;
kvp_transaction.state = HVUTIL_USERSPACE_RECV;
/*
* Based on the version of the daemon, we propagate errors from the
* daemon differently.
*/
data = &message->body.kvp_enum_data;
switch (dm_reg_value) {
case KVP_OP_REGISTER:
/*
* Null string is used to pass back error condition.
*/
if (data->data.key[0] == 0)
error = HV_S_CONT;
break;
case KVP_OP_REGISTER1:
/*
* We use the message header information from
* the user level daemon to transmit errors.
*/
error = message->error;
break;
}
/*
* Complete the transaction by forwarding the key value
* to the host. But first, cancel the timeout.
*/
if (cancel_delayed_work_sync(&kvp_timeout_work)) {
kvp_respond_to_host(message, error);
hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper);
}
return 0;
}
static int process_ob_ipinfo(void *in_msg, void *out_msg, int op)
{
struct hv_kvp_msg *in = in_msg;
struct hv_kvp_ip_msg *out = out_msg;
int len;
switch (op) {
case KVP_OP_GET_IP_INFO:
/*
* Transform all parameters into utf16 encoding.
*/
len = utf8s_to_utf16s((char *)in->body.kvp_ip_val.ip_addr,
strlen((char *)in->body.kvp_ip_val.ip_addr),
UTF16_HOST_ENDIAN,
(wchar_t *)out->kvp_ip_val.ip_addr,
MAX_IP_ADDR_SIZE);
if (len < 0)
return len;
len = utf8s_to_utf16s((char *)in->body.kvp_ip_val.sub_net,
strlen((char *)in->body.kvp_ip_val.sub_net),
UTF16_HOST_ENDIAN,
(wchar_t *)out->kvp_ip_val.sub_net,
MAX_IP_ADDR_SIZE);
if (len < 0)
return len;
len = utf8s_to_utf16s((char *)in->body.kvp_ip_val.gate_way,
strlen((char *)in->body.kvp_ip_val.gate_way),
UTF16_HOST_ENDIAN,
(wchar_t *)out->kvp_ip_val.gate_way,
MAX_GATEWAY_SIZE);
if (len < 0)
return len;
len = utf8s_to_utf16s((char *)in->body.kvp_ip_val.dns_addr,
strlen((char *)in->body.kvp_ip_val.dns_addr),
UTF16_HOST_ENDIAN,
(wchar_t *)out->kvp_ip_val.dns_addr,
MAX_IP_ADDR_SIZE);
if (len < 0)
return len;
len = utf8s_to_utf16s((char *)in->body.kvp_ip_val.adapter_id,
strlen((char *)in->body.kvp_ip_val.adapter_id),
UTF16_HOST_ENDIAN,
(wchar_t *)out->kvp_ip_val.adapter_id,
MAX_ADAPTER_ID_SIZE);
if (len < 0)
return len;
out->kvp_ip_val.dhcp_enabled =
in->body.kvp_ip_val.dhcp_enabled;
out->kvp_ip_val.addr_family =
in->body.kvp_ip_val.addr_family;
}
return 0;
}
static void process_ib_ipinfo(void *in_msg, void *out_msg, int op)
{
struct hv_kvp_ip_msg *in = in_msg;
struct hv_kvp_msg *out = out_msg;
switch (op) {
case KVP_OP_SET_IP_INFO:
/*
* Transform all parameters into utf8 encoding.
*/
utf16s_to_utf8s((wchar_t *)in->kvp_ip_val.ip_addr,
MAX_IP_ADDR_SIZE,
UTF16_LITTLE_ENDIAN,
(__u8 *)out->body.kvp_ip_val.ip_addr,
MAX_IP_ADDR_SIZE);
utf16s_to_utf8s((wchar_t *)in->kvp_ip_val.sub_net,
MAX_IP_ADDR_SIZE,
UTF16_LITTLE_ENDIAN,
(__u8 *)out->body.kvp_ip_val.sub_net,
MAX_IP_ADDR_SIZE);
utf16s_to_utf8s((wchar_t *)in->kvp_ip_val.gate_way,
MAX_GATEWAY_SIZE,
UTF16_LITTLE_ENDIAN,
(__u8 *)out->body.kvp_ip_val.gate_way,
MAX_GATEWAY_SIZE);
utf16s_to_utf8s((wchar_t *)in->kvp_ip_val.dns_addr,
MAX_IP_ADDR_SIZE,
UTF16_LITTLE_ENDIAN,
(__u8 *)out->body.kvp_ip_val.dns_addr,
MAX_IP_ADDR_SIZE);
out->body.kvp_ip_val.dhcp_enabled = in->kvp_ip_val.dhcp_enabled;
/* fallthrough */
case KVP_OP_GET_IP_INFO:
utf16s_to_utf8s((wchar_t *)in->kvp_ip_val.adapter_id,
MAX_ADAPTER_ID_SIZE,
UTF16_LITTLE_ENDIAN,
(__u8 *)out->body.kvp_ip_val.adapter_id,
MAX_ADAPTER_ID_SIZE);
out->body.kvp_ip_val.addr_family = in->kvp_ip_val.addr_family;
}
}
static void
kvp_send_key(struct work_struct *dummy)
{
struct hv_kvp_msg *message;
struct hv_kvp_msg *in_msg;
__u8 operation = kvp_transaction.kvp_msg->kvp_hdr.operation;
__u8 pool = kvp_transaction.kvp_msg->kvp_hdr.pool;
__u32 val32;
__u64 val64;
int rc;
/* The transaction state is wrong. */
if (kvp_transaction.state != HVUTIL_HOSTMSG_RECEIVED)
return;
message = kzalloc(sizeof(*message), GFP_KERNEL);
if (!message)
return;
message->kvp_hdr.operation = operation;
message->kvp_hdr.pool = pool;
in_msg = kvp_transaction.kvp_msg;
/*
* The key/value strings sent from the host are encoded in
* in utf16; convert it to utf8 strings.
* The host assures us that the utf16 strings will not exceed
* the max lengths specified. We will however, reserve room
* for the string terminating character - in the utf16s_utf8s()
* function we limit the size of the buffer where the converted
* string is placed to HV_KVP_EXCHANGE_MAX_*_SIZE -1 to guarantee
* that the strings can be properly terminated!
*/
switch (message->kvp_hdr.operation) {
case KVP_OP_SET_IP_INFO:
process_ib_ipinfo(in_msg, message, KVP_OP_SET_IP_INFO);
break;
case KVP_OP_GET_IP_INFO:
/*
* We only need to pass on the info of operation, adapter_id
* and addr_family to the userland kvp daemon.
*/
process_ib_ipinfo(in_msg, message, KVP_OP_GET_IP_INFO);
break;
case KVP_OP_SET:
switch (in_msg->body.kvp_set.data.value_type) {
case REG_SZ:
/*
* The value is a string - utf16 encoding.
*/
message->body.kvp_set.data.value_size =
utf16s_to_utf8s(
(wchar_t *)in_msg->body.kvp_set.data.value,
in_msg->body.kvp_set.data.value_size,
UTF16_LITTLE_ENDIAN,
message->body.kvp_set.data.value,
HV_KVP_EXCHANGE_MAX_VALUE_SIZE - 1) + 1;
break;
case REG_U32:
/*
* The value is a 32 bit scalar.
* We save this as a utf8 string.
*/
val32 = in_msg->body.kvp_set.data.value_u32;
message->body.kvp_set.data.value_size =
sprintf(message->body.kvp_set.data.value,
"%d", val32) + 1;
break;
case REG_U64:
/*
* The value is a 64 bit scalar.
* We save this as a utf8 string.
*/
val64 = in_msg->body.kvp_set.data.value_u64;
message->body.kvp_set.data.value_size =
sprintf(message->body.kvp_set.data.value,
"%llu", val64) + 1;
break;
}
/*
* The key is always a string - utf16 encoding.
*/
message->body.kvp_set.data.key_size =
utf16s_to_utf8s(
(wchar_t *)in_msg->body.kvp_set.data.key,
in_msg->body.kvp_set.data.key_size,
UTF16_LITTLE_ENDIAN,
message->body.kvp_set.data.key,
HV_KVP_EXCHANGE_MAX_KEY_SIZE - 1) + 1;
break;
case KVP_OP_GET:
message->body.kvp_get.data.key_size =
utf16s_to_utf8s(
(wchar_t *)in_msg->body.kvp_get.data.key,
in_msg->body.kvp_get.data.key_size,
UTF16_LITTLE_ENDIAN,
message->body.kvp_get.data.key,
HV_KVP_EXCHANGE_MAX_KEY_SIZE - 1) + 1;
break;
case KVP_OP_DELETE:
message->body.kvp_delete.key_size =
utf16s_to_utf8s(
(wchar_t *)in_msg->body.kvp_delete.key,
in_msg->body.kvp_delete.key_size,
UTF16_LITTLE_ENDIAN,
message->body.kvp_delete.key,
HV_KVP_EXCHANGE_MAX_KEY_SIZE - 1) + 1;
break;
case KVP_OP_ENUMERATE:
message->body.kvp_enum_data.index =
in_msg->body.kvp_enum_data.index;
break;
}
kvp_transaction.state = HVUTIL_USERSPACE_REQ;
rc = hvutil_transport_send(hvt, message, sizeof(*message), NULL);
if (rc) {
pr_debug("KVP: failed to communicate to the daemon: %d\n", rc);
if (cancel_delayed_work_sync(&kvp_timeout_work)) {
kvp_respond_to_host(message, HV_E_FAIL);
kvp_transaction.state = HVUTIL_READY;
}
}
kfree(message);
}
/*
* Send a response back to the host.
*/
static void
kvp_respond_to_host(struct hv_kvp_msg *msg_to_host, int error)
{
struct hv_kvp_msg *kvp_msg;
struct hv_kvp_exchg_msg_value *kvp_data;
char *key_name;
char *value;
struct icmsg_hdr *icmsghdrp;
int keylen = 0;
int valuelen = 0;
u32 buf_len;
struct vmbus_channel *channel;
u64 req_id;
int ret;
/*
* Copy the global state for completing the transaction. Note that
* only one transaction can be active at a time.
*/
buf_len = kvp_transaction.recv_len;
channel = kvp_transaction.recv_channel;
req_id = kvp_transaction.recv_req_id;
icmsghdrp = (struct icmsg_hdr *)
&recv_buffer[sizeof(struct vmbuspipe_hdr)];
if (channel->onchannel_callback == NULL)
/*
* We have raced with util driver being unloaded;
* silently return.
*/
return;
icmsghdrp->status = error;
/*
* If the error parameter is set, terminate the host's enumeration
* on this pool.
*/
if (error) {
/*
* Something failed or we have timed out;
* terminate the current host-side iteration.
*/
goto response_done;
}
kvp_msg = (struct hv_kvp_msg *)
&recv_buffer[sizeof(struct vmbuspipe_hdr) +
sizeof(struct icmsg_hdr)];
switch (kvp_transaction.kvp_msg->kvp_hdr.operation) {
case KVP_OP_GET_IP_INFO:
ret = process_ob_ipinfo(msg_to_host,
(struct hv_kvp_ip_msg *)kvp_msg,
KVP_OP_GET_IP_INFO);
if (ret < 0)
icmsghdrp->status = HV_E_FAIL;
goto response_done;
case KVP_OP_SET_IP_INFO:
goto response_done;
case KVP_OP_GET:
kvp_data = &kvp_msg->body.kvp_get.data;
goto copy_value;
case KVP_OP_SET:
case KVP_OP_DELETE:
goto response_done;
default:
break;
}
kvp_data = &kvp_msg->body.kvp_enum_data.data;
key_name = msg_to_host->body.kvp_enum_data.data.key;
/*
* The windows host expects the key/value pair to be encoded
* in utf16. Ensure that the key/value size reported to the host
* will be less than or equal to the MAX size (including the
* terminating character).
*/
keylen = utf8s_to_utf16s(key_name, strlen(key_name), UTF16_HOST_ENDIAN,
(wchar_t *) kvp_data->key,
(HV_KVP_EXCHANGE_MAX_KEY_SIZE / 2) - 2);
kvp_data->key_size = 2*(keylen + 1); /* utf16 encoding */
copy_value:
value = msg_to_host->body.kvp_enum_data.data.value;
valuelen = utf8s_to_utf16s(value, strlen(value), UTF16_HOST_ENDIAN,
(wchar_t *) kvp_data->value,
(HV_KVP_EXCHANGE_MAX_VALUE_SIZE / 2) - 2);
kvp_data->value_size = 2*(valuelen + 1); /* utf16 encoding */
/*
* If the utf8s to utf16s conversion failed; notify host
* of the error.
*/
if ((keylen < 0) || (valuelen < 0))
icmsghdrp->status = HV_E_FAIL;
kvp_data->value_type = REG_SZ; /* all our values are strings */
response_done:
icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE;
vmbus_sendpacket(channel, recv_buffer, buf_len, req_id,
VM_PKT_DATA_INBAND, 0);
}
/*
* This callback is invoked when we get a KVP message from the host.
* The host ensures that only one KVP transaction can be active at a time.
* KVP implementation in Linux needs to forward the key to a user-mde
* component to retrieve the corresponding value. Consequently, we cannot
* respond to the host in the context of this callback. Since the host
* guarantees that at most only one transaction can be active at a time,
* we stash away the transaction state in a set of global variables.
*/
void hv_kvp_onchannelcallback(void *context)
{
struct vmbus_channel *channel = context;
u32 recvlen;
u64 requestid;
struct hv_kvp_msg *kvp_msg;
struct icmsg_hdr *icmsghdrp;
int kvp_srv_version;
static enum {NEGO_NOT_STARTED,
NEGO_IN_PROGRESS,
NEGO_FINISHED} host_negotiatied = NEGO_NOT_STARTED;
if (kvp_transaction.state < HVUTIL_READY) {
/*
* If userspace daemon is not connected and host is asking
* us to negotiate we need to delay to not lose messages.
* This is important for Failover IP setting.
*/
if (host_negotiatied == NEGO_NOT_STARTED) {
host_negotiatied = NEGO_IN_PROGRESS;
schedule_delayed_work(&kvp_host_handshake_work,
HV_UTIL_NEGO_TIMEOUT * HZ);
}
return;
}
if (kvp_transaction.state > HVUTIL_READY)
return;
vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 4, &recvlen,
&requestid);
if (recvlen > 0) {
icmsghdrp = (struct icmsg_hdr *)&recv_buffer[
sizeof(struct vmbuspipe_hdr)];
if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
if (vmbus_prep_negotiate_resp(icmsghdrp,
recv_buffer, fw_versions, FW_VER_COUNT,
kvp_versions, KVP_VER_COUNT,
NULL, &kvp_srv_version)) {
pr_info("KVP IC version %d.%d\n",
kvp_srv_version >> 16,
kvp_srv_version & 0xFFFF);
}
} else {
kvp_msg = (struct hv_kvp_msg *)&recv_buffer[
sizeof(struct vmbuspipe_hdr) +
sizeof(struct icmsg_hdr)];
/*
* Stash away this global state for completing the
* transaction; note transactions are serialized.
*/
kvp_transaction.recv_len = recvlen;
kvp_transaction.recv_req_id = requestid;
kvp_transaction.kvp_msg = kvp_msg;
if (kvp_transaction.state < HVUTIL_READY) {
/* Userspace is not registered yet */
kvp_respond_to_host(NULL, HV_E_FAIL);
return;
}
kvp_transaction.state = HVUTIL_HOSTMSG_RECEIVED;
/*
* Get the information from the
* user-mode component.
* component. This transaction will be
* completed when we get the value from
* the user-mode component.
* Set a timeout to deal with
* user-mode not responding.
*/
schedule_work(&kvp_sendkey_work);
schedule_delayed_work(&kvp_timeout_work,
HV_UTIL_TIMEOUT * HZ);
return;
}
icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION
| ICMSGHDRFLAG_RESPONSE;
vmbus_sendpacket(channel, recv_buffer,
recvlen, requestid,
VM_PKT_DATA_INBAND, 0);
host_negotiatied = NEGO_FINISHED;
hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper);
}
}
static void kvp_on_reset(void)
{
if (cancel_delayed_work_sync(&kvp_timeout_work))
kvp_respond_to_host(NULL, HV_E_FAIL);
kvp_transaction.state = HVUTIL_DEVICE_INIT;
}
int
hv_kvp_init(struct hv_util_service *srv)
{
recv_buffer = srv->recv_buffer;
kvp_transaction.recv_channel = srv->channel;
/*
* When this driver loads, the user level daemon that
* processes the host requests may not yet be running.
* Defer processing channel callbacks until the daemon
* has registered.
*/
kvp_transaction.state = HVUTIL_DEVICE_INIT;
hvt = hvutil_transport_init(kvp_devname, CN_KVP_IDX, CN_KVP_VAL,
kvp_on_msg, kvp_on_reset);
if (!hvt)
return -EFAULT;
return 0;
}
void hv_kvp_deinit(void)
{
kvp_transaction.state = HVUTIL_DEVICE_DYING;
cancel_delayed_work_sync(&kvp_host_handshake_work);
cancel_delayed_work_sync(&kvp_timeout_work);
cancel_work_sync(&kvp_sendkey_work);
hvutil_transport_destroy(hvt);
}
+398
View File
@@ -0,0 +1,398 @@
/*
* An implementation of host initiated guest snapshot.
*
*
* Copyright (C) 2013, Microsoft, Inc.
* Author : K. Y. Srinivasan <kys@microsoft.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
* by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
* NON INFRINGEMENT. See the GNU General Public License for more
* details.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/net.h>
#include <linux/nls.h>
#include <linux/connector.h>
#include <linux/workqueue.h>
#include <linux/hyperv.h>
#include "hyperv_vmbus.h"
#include "hv_utils_transport.h"
#define VSS_MAJOR 5
#define VSS_MINOR 0
#define VSS_VERSION (VSS_MAJOR << 16 | VSS_MINOR)
#define VSS_VER_COUNT 1
static const int vss_versions[] = {
VSS_VERSION
};
#define FW_VER_COUNT 1
static const int fw_versions[] = {
UTIL_FW_VERSION
};
/*
* Timeout values are based on expecations from host
*/
#define VSS_FREEZE_TIMEOUT (15 * 60)
/*
* Global state maintained for transaction that is being processed. For a class
* of integration services, including the "VSS service", the specified protocol
* is a "request/response" protocol which means that there can only be single
* outstanding transaction from the host at any given point in time. We use
* this to simplify memory management in this driver - we cache and process
* only one message at a time.
*
* While the request/response protocol is guaranteed by the host, we further
* ensure this by serializing packet processing in this driver - we do not
* read additional packets from the VMBUs until the current packet is fully
* handled.
*/
static struct {
int state; /* hvutil_device_state */
int recv_len; /* number of bytes received. */
struct vmbus_channel *recv_channel; /* chn we got the request */
u64 recv_req_id; /* request ID. */
struct hv_vss_msg *msg; /* current message */
} vss_transaction;
static void vss_respond_to_host(int error);
/*
* This state maintains the version number registered by the daemon.
*/
static int dm_reg_value;
static const char vss_devname[] = "vmbus/hv_vss";
static __u8 *recv_buffer;
static struct hvutil_transport *hvt;
static void vss_timeout_func(struct work_struct *dummy);
static void vss_handle_request(struct work_struct *dummy);
static DECLARE_DELAYED_WORK(vss_timeout_work, vss_timeout_func);
static DECLARE_WORK(vss_handle_request_work, vss_handle_request);
static void vss_poll_wrapper(void *channel)
{
/* Transaction is finished, reset the state here to avoid races. */
vss_transaction.state = HVUTIL_READY;
hv_vss_onchannelcallback(channel);
}
/*
* Callback when data is received from user mode.
*/
static void vss_timeout_func(struct work_struct *dummy)
{
/*
* Timeout waiting for userspace component to reply happened.
*/
pr_warn("VSS: timeout waiting for daemon to reply\n");
vss_respond_to_host(HV_E_FAIL);
hv_poll_channel(vss_transaction.recv_channel, vss_poll_wrapper);
}
static void vss_register_done(void)
{
hv_poll_channel(vss_transaction.recv_channel, vss_poll_wrapper);
pr_debug("VSS: userspace daemon registered\n");
}
static int vss_handle_handshake(struct hv_vss_msg *vss_msg)
{
u32 our_ver = VSS_OP_REGISTER1;
switch (vss_msg->vss_hdr.operation) {
case VSS_OP_REGISTER:
/* Daemon doesn't expect us to reply */
dm_reg_value = VSS_OP_REGISTER;
break;
case VSS_OP_REGISTER1:
/* Daemon expects us to reply with our own version */
if (hvutil_transport_send(hvt, &our_ver, sizeof(our_ver),
vss_register_done))
return -EFAULT;
dm_reg_value = VSS_OP_REGISTER1;
break;
default:
return -EINVAL;
}
pr_info("VSS: userspace daemon ver. %d connected\n", dm_reg_value);
return 0;
}
static int vss_on_msg(void *msg, int len)
{
struct hv_vss_msg *vss_msg = (struct hv_vss_msg *)msg;
if (len != sizeof(*vss_msg)) {
pr_debug("VSS: Message size does not match length\n");
return -EINVAL;
}
if (vss_msg->vss_hdr.operation == VSS_OP_REGISTER ||
vss_msg->vss_hdr.operation == VSS_OP_REGISTER1) {
/*
* Don't process registration messages if we're in the middle
* of a transaction processing.
*/
if (vss_transaction.state > HVUTIL_READY) {
pr_debug("VSS: Got unexpected registration request\n");
return -EINVAL;
}
return vss_handle_handshake(vss_msg);
} else if (vss_transaction.state == HVUTIL_USERSPACE_REQ) {
vss_transaction.state = HVUTIL_USERSPACE_RECV;
if (vss_msg->vss_hdr.operation == VSS_OP_HOT_BACKUP)
vss_transaction.msg->vss_cf.flags =
VSS_HBU_NO_AUTO_RECOVERY;
if (cancel_delayed_work_sync(&vss_timeout_work)) {
vss_respond_to_host(vss_msg->error);
/* Transaction is finished, reset the state. */
hv_poll_channel(vss_transaction.recv_channel,
vss_poll_wrapper);
}
} else {
/* This is a spurious call! */
pr_debug("VSS: Transaction not active\n");
return -EINVAL;
}
return 0;
}
static void vss_send_op(void)
{
int op = vss_transaction.msg->vss_hdr.operation;
int rc;
struct hv_vss_msg *vss_msg;
/* The transaction state is wrong. */
if (vss_transaction.state != HVUTIL_HOSTMSG_RECEIVED) {
pr_debug("VSS: Unexpected attempt to send to daemon\n");
return;
}
vss_msg = kzalloc(sizeof(*vss_msg), GFP_KERNEL);
if (!vss_msg)
return;
vss_msg->vss_hdr.operation = op;
vss_transaction.state = HVUTIL_USERSPACE_REQ;
schedule_delayed_work(&vss_timeout_work, op == VSS_OP_FREEZE ?
VSS_FREEZE_TIMEOUT * HZ : HV_UTIL_TIMEOUT * HZ);
rc = hvutil_transport_send(hvt, vss_msg, sizeof(*vss_msg), NULL);
if (rc) {
pr_warn("VSS: failed to communicate to the daemon: %d\n", rc);
if (cancel_delayed_work_sync(&vss_timeout_work)) {
vss_respond_to_host(HV_E_FAIL);
vss_transaction.state = HVUTIL_READY;
}
}
kfree(vss_msg);
}
static void vss_handle_request(struct work_struct *dummy)
{
switch (vss_transaction.msg->vss_hdr.operation) {
/*
* Initiate a "freeze/thaw" operation in the guest.
* We respond to the host once the operation is complete.
*
* We send the message to the user space daemon and the operation is
* performed in the daemon.
*/
case VSS_OP_THAW:
case VSS_OP_FREEZE:
case VSS_OP_HOT_BACKUP:
if (vss_transaction.state < HVUTIL_READY) {
/* Userspace is not registered yet */
pr_debug("VSS: Not ready for request.\n");
vss_respond_to_host(HV_E_FAIL);
return;
}
pr_debug("VSS: Received request for op code: %d\n",
vss_transaction.msg->vss_hdr.operation);
vss_transaction.state = HVUTIL_HOSTMSG_RECEIVED;
vss_send_op();
return;
case VSS_OP_GET_DM_INFO:
vss_transaction.msg->dm_info.flags = 0;
break;
default:
break;
}
vss_respond_to_host(0);
hv_poll_channel(vss_transaction.recv_channel, vss_poll_wrapper);
}
/*
* Send a response back to the host.
*/
static void
vss_respond_to_host(int error)
{
struct icmsg_hdr *icmsghdrp;
u32 buf_len;
struct vmbus_channel *channel;
u64 req_id;
/*
* Copy the global state for completing the transaction. Note that
* only one transaction can be active at a time.
*/
buf_len = vss_transaction.recv_len;
channel = vss_transaction.recv_channel;
req_id = vss_transaction.recv_req_id;
icmsghdrp = (struct icmsg_hdr *)
&recv_buffer[sizeof(struct vmbuspipe_hdr)];
if (channel->onchannel_callback == NULL)
/*
* We have raced with util driver being unloaded;
* silently return.
*/
return;
icmsghdrp->status = error;
icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE;
vmbus_sendpacket(channel, recv_buffer, buf_len, req_id,
VM_PKT_DATA_INBAND, 0);
}
/*
* This callback is invoked when we get a VSS message from the host.
* The host ensures that only one VSS transaction can be active at a time.
*/
void hv_vss_onchannelcallback(void *context)
{
struct vmbus_channel *channel = context;
u32 recvlen;
u64 requestid;
struct hv_vss_msg *vss_msg;
int vss_srv_version;
struct icmsg_hdr *icmsghdrp;
if (vss_transaction.state > HVUTIL_READY)
return;
vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen,
&requestid);
if (recvlen > 0) {
icmsghdrp = (struct icmsg_hdr *)&recv_buffer[
sizeof(struct vmbuspipe_hdr)];
if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
if (vmbus_prep_negotiate_resp(icmsghdrp,
recv_buffer, fw_versions, FW_VER_COUNT,
vss_versions, VSS_VER_COUNT,
NULL, &vss_srv_version)) {
pr_info("VSS IC version %d.%d\n",
vss_srv_version >> 16,
vss_srv_version & 0xFFFF);
}
} else {
vss_msg = (struct hv_vss_msg *)&recv_buffer[
sizeof(struct vmbuspipe_hdr) +
sizeof(struct icmsg_hdr)];
/*
* Stash away this global state for completing the
* transaction; note transactions are serialized.
*/
vss_transaction.recv_len = recvlen;
vss_transaction.recv_req_id = requestid;
vss_transaction.msg = (struct hv_vss_msg *)vss_msg;
schedule_work(&vss_handle_request_work);
return;
}
icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION
| ICMSGHDRFLAG_RESPONSE;
vmbus_sendpacket(channel, recv_buffer,
recvlen, requestid,
VM_PKT_DATA_INBAND, 0);
}
}
static void vss_on_reset(void)
{
if (cancel_delayed_work_sync(&vss_timeout_work))
vss_respond_to_host(HV_E_FAIL);
vss_transaction.state = HVUTIL_DEVICE_INIT;
}
int
hv_vss_init(struct hv_util_service *srv)
{
if (vmbus_proto_version < VERSION_WIN8_1) {
pr_warn("Integration service 'Backup (volume snapshot)'"
" not supported on this host version.\n");
return -ENOTSUPP;
}
recv_buffer = srv->recv_buffer;
vss_transaction.recv_channel = srv->channel;
/*
* When this driver loads, the user level daemon that
* processes the host requests may not yet be running.
* Defer processing channel callbacks until the daemon
* has registered.
*/
vss_transaction.state = HVUTIL_DEVICE_INIT;
hvt = hvutil_transport_init(vss_devname, CN_VSS_IDX, CN_VSS_VAL,
vss_on_msg, vss_on_reset);
if (!hvt) {
pr_warn("VSS: Failed to initialize transport\n");
return -EFAULT;
}
return 0;
}
void hv_vss_deinit(void)
{
vss_transaction.state = HVUTIL_DEVICE_DYING;
cancel_delayed_work_sync(&vss_timeout_work);
cancel_work_sync(&vss_handle_request_work);
hvutil_transport_destroy(hvt);
}
+6
View File
@@ -0,0 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include "hyperv_vmbus.h"
#define CREATE_TRACE_POINTS
#include "hv_trace.h"
+329
View File
@@ -0,0 +1,329 @@
// SPDX-License-Identifier: GPL-2.0
#undef TRACE_SYSTEM
#define TRACE_SYSTEM hyperv
#if !defined(_HV_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
#define _HV_TRACE_H
#include <linux/tracepoint.h>
DECLARE_EVENT_CLASS(vmbus_hdr_msg,
TP_PROTO(const struct vmbus_channel_message_header *hdr),
TP_ARGS(hdr),
TP_STRUCT__entry(__field(unsigned int, msgtype)),
TP_fast_assign(__entry->msgtype = hdr->msgtype;),
TP_printk("msgtype=%u", __entry->msgtype)
);
DEFINE_EVENT(vmbus_hdr_msg, vmbus_on_msg_dpc,
TP_PROTO(const struct vmbus_channel_message_header *hdr),
TP_ARGS(hdr)
);
DEFINE_EVENT(vmbus_hdr_msg, vmbus_on_message,
TP_PROTO(const struct vmbus_channel_message_header *hdr),
TP_ARGS(hdr)
);
TRACE_EVENT(vmbus_onoffer,
TP_PROTO(const struct vmbus_channel_offer_channel *offer),
TP_ARGS(offer),
TP_STRUCT__entry(
__field(u32, child_relid)
__field(u8, monitorid)
__field(u16, is_ddc_int)
__field(u32, connection_id)
__array(char, if_type, 16)
__array(char, if_instance, 16)
__field(u16, chn_flags)
__field(u16, mmio_mb)
__field(u16, sub_idx)
),
TP_fast_assign(__entry->child_relid = offer->child_relid;
__entry->monitorid = offer->monitorid;
__entry->is_ddc_int = offer->is_dedicated_interrupt;
__entry->connection_id = offer->connection_id;
memcpy(__entry->if_type,
&offer->offer.if_type.b, 16);
memcpy(__entry->if_instance,
&offer->offer.if_instance.b, 16);
__entry->chn_flags = offer->offer.chn_flags;
__entry->mmio_mb = offer->offer.mmio_megabytes;
__entry->sub_idx = offer->offer.sub_channel_index;
),
TP_printk("child_relid 0x%x, monitorid 0x%x, is_dedicated %d, "
"connection_id 0x%x, if_type %pUl, if_instance %pUl, "
"chn_flags 0x%x, mmio_megabytes %d, sub_channel_index %d",
__entry->child_relid, __entry->monitorid,
__entry->is_ddc_int, __entry->connection_id,
__entry->if_type, __entry->if_instance,
__entry->chn_flags, __entry->mmio_mb,
__entry->sub_idx
)
);
TRACE_EVENT(vmbus_onoffer_rescind,
TP_PROTO(const struct vmbus_channel_rescind_offer *offer),
TP_ARGS(offer),
TP_STRUCT__entry(__field(u32, child_relid)),
TP_fast_assign(__entry->child_relid = offer->child_relid),
TP_printk("child_relid 0x%x", __entry->child_relid)
);
TRACE_EVENT(vmbus_onopen_result,
TP_PROTO(const struct vmbus_channel_open_result *result),
TP_ARGS(result),
TP_STRUCT__entry(
__field(u32, child_relid)
__field(u32, openid)
__field(u32, status)
),
TP_fast_assign(__entry->child_relid = result->child_relid;
__entry->openid = result->openid;
__entry->status = result->status;
),
TP_printk("child_relid 0x%x, openid %d, status %d",
__entry->child_relid, __entry->openid, __entry->status
)
);
TRACE_EVENT(vmbus_ongpadl_created,
TP_PROTO(const struct vmbus_channel_gpadl_created *gpadlcreated),
TP_ARGS(gpadlcreated),
TP_STRUCT__entry(
__field(u32, child_relid)
__field(u32, gpadl)
__field(u32, status)
),
TP_fast_assign(__entry->child_relid = gpadlcreated->child_relid;
__entry->gpadl = gpadlcreated->gpadl;
__entry->status = gpadlcreated->creation_status;
),
TP_printk("child_relid 0x%x, gpadl 0x%x, creation_status %d",
__entry->child_relid, __entry->gpadl, __entry->status
)
);
TRACE_EVENT(vmbus_ongpadl_torndown,
TP_PROTO(const struct vmbus_channel_gpadl_torndown *gpadltorndown),
TP_ARGS(gpadltorndown),
TP_STRUCT__entry(__field(u32, gpadl)),
TP_fast_assign(__entry->gpadl = gpadltorndown->gpadl),
TP_printk("gpadl 0x%x", __entry->gpadl)
);
TRACE_EVENT(vmbus_onversion_response,
TP_PROTO(const struct vmbus_channel_version_response *response),
TP_ARGS(response),
TP_STRUCT__entry(
__field(u8, ver)
),
TP_fast_assign(__entry->ver = response->version_supported;
),
TP_printk("version_supported %d", __entry->ver)
);
TRACE_EVENT(vmbus_request_offers,
TP_PROTO(int ret),
TP_ARGS(ret),
TP_STRUCT__entry(__field(int, ret)),
TP_fast_assign(__entry->ret = ret),
TP_printk("sending ret %d", __entry->ret)
);
TRACE_EVENT(vmbus_open,
TP_PROTO(const struct vmbus_channel_open_channel *msg, int ret),
TP_ARGS(msg, ret),
TP_STRUCT__entry(
__field(u32, child_relid)
__field(u32, openid)
__field(u32, gpadlhandle)
__field(u32, target_vp)
__field(u32, offset)
__field(int, ret)
),
TP_fast_assign(
__entry->child_relid = msg->child_relid;
__entry->openid = msg->openid;
__entry->gpadlhandle = msg->ringbuffer_gpadlhandle;
__entry->target_vp = msg->target_vp;
__entry->offset = msg->downstream_ringbuffer_pageoffset;
__entry->ret = ret;
),
TP_printk("sending child_relid 0x%x, openid %d, "
"gpadlhandle 0x%x, target_vp 0x%x, offset 0x%x, ret %d",
__entry->child_relid, __entry->openid,
__entry->gpadlhandle, __entry->target_vp,
__entry->offset, __entry->ret
)
);
TRACE_EVENT(vmbus_close_internal,
TP_PROTO(const struct vmbus_channel_close_channel *msg, int ret),
TP_ARGS(msg, ret),
TP_STRUCT__entry(
__field(u32, child_relid)
__field(int, ret)
),
TP_fast_assign(
__entry->child_relid = msg->child_relid;
__entry->ret = ret;
),
TP_printk("sending child_relid 0x%x, ret %d", __entry->child_relid,
__entry->ret)
);
TRACE_EVENT(vmbus_establish_gpadl_header,
TP_PROTO(const struct vmbus_channel_gpadl_header *msg, int ret),
TP_ARGS(msg, ret),
TP_STRUCT__entry(
__field(u32, child_relid)
__field(u32, gpadl)
__field(u16, range_buflen)
__field(u16, rangecount)
__field(int, ret)
),
TP_fast_assign(
__entry->child_relid = msg->child_relid;
__entry->gpadl = msg->gpadl;
__entry->range_buflen = msg->range_buflen;
__entry->rangecount = msg->rangecount;
__entry->ret = ret;
),
TP_printk("sending child_relid 0x%x, gpadl 0x%x, range_buflen %d "
"rangecount %d, ret %d",
__entry->child_relid, __entry->gpadl,
__entry->range_buflen, __entry->rangecount, __entry->ret
)
);
TRACE_EVENT(vmbus_establish_gpadl_body,
TP_PROTO(const struct vmbus_channel_gpadl_body *msg, int ret),
TP_ARGS(msg, ret),
TP_STRUCT__entry(
__field(u32, msgnumber)
__field(u32, gpadl)
__field(int, ret)
),
TP_fast_assign(
__entry->msgnumber = msg->msgnumber;
__entry->gpadl = msg->gpadl;
__entry->ret = ret;
),
TP_printk("sending msgnumber %d, gpadl 0x%x, ret %d",
__entry->msgnumber, __entry->gpadl, __entry->ret
)
);
TRACE_EVENT(vmbus_teardown_gpadl,
TP_PROTO(const struct vmbus_channel_gpadl_teardown *msg, int ret),
TP_ARGS(msg, ret),
TP_STRUCT__entry(
__field(u32, child_relid)
__field(u32, gpadl)
__field(int, ret)
),
TP_fast_assign(
__entry->child_relid = msg->child_relid;
__entry->gpadl = msg->gpadl;
__entry->ret = ret;
),
TP_printk("sending child_relid 0x%x, gpadl 0x%x, ret %d",
__entry->child_relid, __entry->gpadl, __entry->ret
)
);
TRACE_EVENT(vmbus_negotiate_version,
TP_PROTO(const struct vmbus_channel_initiate_contact *msg, int ret),
TP_ARGS(msg, ret),
TP_STRUCT__entry(
__field(u32, ver)
__field(u32, target_vcpu)
__field(int, ret)
__field(u64, int_page)
__field(u64, mon_page1)
__field(u64, mon_page2)
),
TP_fast_assign(
__entry->ver = msg->vmbus_version_requested;
__entry->target_vcpu = msg->target_vcpu;
__entry->int_page = msg->interrupt_page;
__entry->mon_page1 = msg->monitor_page1;
__entry->mon_page2 = msg->monitor_page2;
__entry->ret = ret;
),
TP_printk("sending vmbus_version_requested %d, target_vcpu 0x%x, "
"pages %llx:%llx:%llx, ret %d",
__entry->ver, __entry->target_vcpu, __entry->int_page,
__entry->mon_page1, __entry->mon_page2, __entry->ret
)
);
TRACE_EVENT(vmbus_release_relid,
TP_PROTO(const struct vmbus_channel_relid_released *msg, int ret),
TP_ARGS(msg, ret),
TP_STRUCT__entry(
__field(u32, child_relid)
__field(int, ret)
),
TP_fast_assign(
__entry->child_relid = msg->child_relid;
__entry->ret = ret;
),
TP_printk("sending child_relid 0x%x, ret %d",
__entry->child_relid, __entry->ret
)
);
TRACE_EVENT(vmbus_send_tl_connect_request,
TP_PROTO(const struct vmbus_channel_tl_connect_request *msg,
int ret),
TP_ARGS(msg, ret),
TP_STRUCT__entry(
__array(char, guest_id, 16)
__array(char, host_id, 16)
__field(int, ret)
),
TP_fast_assign(
memcpy(__entry->guest_id, &msg->guest_endpoint_id.b, 16);
memcpy(__entry->host_id, &msg->host_service_id.b, 16);
__entry->ret = ret;
),
TP_printk("sending guest_endpoint_id %pUl, host_service_id %pUl, "
"ret %d",
__entry->guest_id, __entry->host_id, __entry->ret
)
);
DECLARE_EVENT_CLASS(vmbus_channel,
TP_PROTO(const struct vmbus_channel *channel),
TP_ARGS(channel),
TP_STRUCT__entry(__field(u32, relid)),
TP_fast_assign(__entry->relid = channel->offermsg.child_relid),
TP_printk("relid 0x%x", __entry->relid)
);
DEFINE_EVENT(vmbus_channel, vmbus_chan_sched,
TP_PROTO(const struct vmbus_channel *channel),
TP_ARGS(channel)
);
DEFINE_EVENT(vmbus_channel, vmbus_setevent,
TP_PROTO(const struct vmbus_channel *channel),
TP_ARGS(channel)
);
DEFINE_EVENT(vmbus_channel, vmbus_on_event,
TP_PROTO(const struct vmbus_channel *channel),
TP_ARGS(channel)
);
#undef TRACE_INCLUDE_PATH
#define TRACE_INCLUDE_PATH .
#undef TRACE_INCLUDE_FILE
#define TRACE_INCLUDE_FILE hv_trace
#endif /* _HV_TRACE_H */
/* This part must be outside protection */
#include <trace/define_trace.h>
+48
View File
@@ -0,0 +1,48 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM hyperv
#if !defined(_HV_TRACE_BALLOON_H) || defined(TRACE_HEADER_MULTI_READ)
#define _HV_TRACE_BALLOON_H
#include <linux/tracepoint.h>
TRACE_EVENT(balloon_status,
TP_PROTO(u64 available, u64 committed,
unsigned long vm_memory_committed,
unsigned long pages_ballooned,
unsigned long pages_added,
unsigned long pages_onlined),
TP_ARGS(available, committed, vm_memory_committed,
pages_ballooned, pages_added, pages_onlined),
TP_STRUCT__entry(
__field(u64, available)
__field(u64, committed)
__field(unsigned long, vm_memory_committed)
__field(unsigned long, pages_ballooned)
__field(unsigned long, pages_added)
__field(unsigned long, pages_onlined)
),
TP_fast_assign(
__entry->available = available;
__entry->committed = committed;
__entry->vm_memory_committed = vm_memory_committed;
__entry->pages_ballooned = pages_ballooned;
__entry->pages_added = pages_added;
__entry->pages_onlined = pages_onlined;
),
TP_printk("available %lld, committed %lld; vm_memory_committed %ld;"
" pages_ballooned %ld, pages_added %ld, pages_onlined %ld",
__entry->available, __entry->committed,
__entry->vm_memory_committed, __entry->pages_ballooned,
__entry->pages_added, __entry->pages_onlined
)
);
#undef TRACE_INCLUDE_PATH
#define TRACE_INCLUDE_PATH .
#undef TRACE_INCLUDE_FILE
#define TRACE_INCLUDE_FILE hv_trace_balloon
#endif /* _HV_TRACE_BALLOON_H */
/* This part must be outside protection */
#include <trace/define_trace.h>
+584
View File
@@ -0,0 +1,584 @@
/*
* Copyright (c) 2010, 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>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/reboot.h>
#include <linux/hyperv.h>
#include <linux/clockchips.h>
#include <linux/ptp_clock_kernel.h>
#include <asm/mshyperv.h>
#include "hyperv_vmbus.h"
#define SD_MAJOR 3
#define SD_MINOR 0
#define SD_VERSION (SD_MAJOR << 16 | SD_MINOR)
#define SD_MAJOR_1 1
#define SD_VERSION_1 (SD_MAJOR_1 << 16 | SD_MINOR)
#define TS_MAJOR 4
#define TS_MINOR 0
#define TS_VERSION (TS_MAJOR << 16 | TS_MINOR)
#define TS_MAJOR_1 1
#define TS_VERSION_1 (TS_MAJOR_1 << 16 | TS_MINOR)
#define TS_MAJOR_3 3
#define TS_VERSION_3 (TS_MAJOR_3 << 16 | TS_MINOR)
#define HB_MAJOR 3
#define HB_MINOR 0
#define HB_VERSION (HB_MAJOR << 16 | HB_MINOR)
#define HB_MAJOR_1 1
#define HB_VERSION_1 (HB_MAJOR_1 << 16 | HB_MINOR)
static int sd_srv_version;
static int ts_srv_version;
static int hb_srv_version;
#define SD_VER_COUNT 2
static const int sd_versions[] = {
SD_VERSION,
SD_VERSION_1
};
#define TS_VER_COUNT 3
static const int ts_versions[] = {
TS_VERSION,
TS_VERSION_3,
TS_VERSION_1
};
#define HB_VER_COUNT 2
static const int hb_versions[] = {
HB_VERSION,
HB_VERSION_1
};
#define FW_VER_COUNT 2
static const int fw_versions[] = {
UTIL_FW_VERSION,
UTIL_WS2K8_FW_VERSION
};
static void shutdown_onchannelcallback(void *context);
static struct hv_util_service util_shutdown = {
.util_cb = shutdown_onchannelcallback,
};
static int hv_timesync_init(struct hv_util_service *srv);
static void hv_timesync_deinit(void);
static void timesync_onchannelcallback(void *context);
static struct hv_util_service util_timesynch = {
.util_cb = timesync_onchannelcallback,
.util_init = hv_timesync_init,
.util_deinit = hv_timesync_deinit,
};
static void heartbeat_onchannelcallback(void *context);
static struct hv_util_service util_heartbeat = {
.util_cb = heartbeat_onchannelcallback,
};
static struct hv_util_service util_kvp = {
.util_cb = hv_kvp_onchannelcallback,
.util_init = hv_kvp_init,
.util_deinit = hv_kvp_deinit,
};
static struct hv_util_service util_vss = {
.util_cb = hv_vss_onchannelcallback,
.util_init = hv_vss_init,
.util_deinit = hv_vss_deinit,
};
static struct hv_util_service util_fcopy = {
.util_cb = hv_fcopy_onchannelcallback,
.util_init = hv_fcopy_init,
.util_deinit = hv_fcopy_deinit,
};
static void perform_shutdown(struct work_struct *dummy)
{
orderly_poweroff(true);
}
/*
* Perform the shutdown operation in a thread context.
*/
static DECLARE_WORK(shutdown_work, perform_shutdown);
static void shutdown_onchannelcallback(void *context)
{
struct vmbus_channel *channel = context;
u32 recvlen;
u64 requestid;
bool execute_shutdown = false;
u8 *shut_txf_buf = util_shutdown.recv_buffer;
struct shutdown_msg_data *shutdown_msg;
struct icmsg_hdr *icmsghdrp;
vmbus_recvpacket(channel, shut_txf_buf,
PAGE_SIZE, &recvlen, &requestid);
if (recvlen > 0) {
icmsghdrp = (struct icmsg_hdr *)&shut_txf_buf[
sizeof(struct vmbuspipe_hdr)];
if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
if (vmbus_prep_negotiate_resp(icmsghdrp, shut_txf_buf,
fw_versions, FW_VER_COUNT,
sd_versions, SD_VER_COUNT,
NULL, &sd_srv_version)) {
pr_info("Shutdown IC version %d.%d\n",
sd_srv_version >> 16,
sd_srv_version & 0xFFFF);
}
} else {
shutdown_msg =
(struct shutdown_msg_data *)&shut_txf_buf[
sizeof(struct vmbuspipe_hdr) +
sizeof(struct icmsg_hdr)];
switch (shutdown_msg->flags) {
case 0:
case 1:
icmsghdrp->status = HV_S_OK;
execute_shutdown = true;
pr_info("Shutdown request received -"
" graceful shutdown initiated\n");
break;
default:
icmsghdrp->status = HV_E_FAIL;
execute_shutdown = false;
pr_info("Shutdown request received -"
" Invalid request\n");
break;
}
}
icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION
| ICMSGHDRFLAG_RESPONSE;
vmbus_sendpacket(channel, shut_txf_buf,
recvlen, requestid,
VM_PKT_DATA_INBAND, 0);
}
if (execute_shutdown == true)
schedule_work(&shutdown_work);
}
/*
* Set the host time in a process context.
*/
static struct work_struct adj_time_work;
/*
* The last time sample, received from the host. PTP device responds to
* requests by using this data and the current partition-wide time reference
* count.
*/
static struct {
u64 host_time;
u64 ref_time;
spinlock_t lock;
} host_ts;
static struct timespec64 hv_get_adj_host_time(void)
{
struct timespec64 ts;
u64 newtime, reftime;
unsigned long flags;
spin_lock_irqsave(&host_ts.lock, flags);
reftime = hyperv_cs->read(hyperv_cs);
newtime = host_ts.host_time + (reftime - host_ts.ref_time);
ts = ns_to_timespec64((newtime - WLTIMEDELTA) * 100);
spin_unlock_irqrestore(&host_ts.lock, flags);
return ts;
}
static void hv_set_host_time(struct work_struct *work)
{
struct timespec64 ts = hv_get_adj_host_time();
do_settimeofday64(&ts);
}
/*
* Synchronize time with host after reboot, restore, etc.
*
* ICTIMESYNCFLAG_SYNC flag bit indicates reboot, restore events of the VM.
* After reboot the flag ICTIMESYNCFLAG_SYNC is included in the first time
* message after the timesync channel is opened. Since the hv_utils module is
* loaded after hv_vmbus, the first message is usually missed. This bit is
* considered a hard request to discipline the clock.
*
* ICTIMESYNCFLAG_SAMPLE bit indicates a time sample from host. This is
* typically used as a hint to the guest. The guest is under no obligation
* to discipline the clock.
*/
static inline void adj_guesttime(u64 hosttime, u64 reftime, u8 adj_flags)
{
unsigned long flags;
u64 cur_reftime;
/*
* Save the adjusted time sample from the host and the snapshot
* of the current system time.
*/
spin_lock_irqsave(&host_ts.lock, flags);
cur_reftime = hyperv_cs->read(hyperv_cs);
host_ts.host_time = hosttime;
host_ts.ref_time = cur_reftime;
/*
* TimeSync v4 messages contain reference time (guest's Hyper-V
* clocksource read when the time sample was generated), we can
* improve the precision by adding the delta between now and the
* time of generation. For older protocols we set
* reftime == cur_reftime on call.
*/
host_ts.host_time += (cur_reftime - reftime);
spin_unlock_irqrestore(&host_ts.lock, flags);
/* Schedule work to do do_settimeofday64() */
if (adj_flags & ICTIMESYNCFLAG_SYNC)
schedule_work(&adj_time_work);
}
/*
* Time Sync Channel message handler.
*/
static void timesync_onchannelcallback(void *context)
{
struct vmbus_channel *channel = context;
u32 recvlen;
u64 requestid;
struct icmsg_hdr *icmsghdrp;
struct ictimesync_data *timedatap;
struct ictimesync_ref_data *refdata;
u8 *time_txf_buf = util_timesynch.recv_buffer;
vmbus_recvpacket(channel, time_txf_buf,
PAGE_SIZE, &recvlen, &requestid);
if (recvlen > 0) {
icmsghdrp = (struct icmsg_hdr *)&time_txf_buf[
sizeof(struct vmbuspipe_hdr)];
if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
if (vmbus_prep_negotiate_resp(icmsghdrp, time_txf_buf,
fw_versions, FW_VER_COUNT,
ts_versions, TS_VER_COUNT,
NULL, &ts_srv_version)) {
pr_info("TimeSync IC version %d.%d\n",
ts_srv_version >> 16,
ts_srv_version & 0xFFFF);
}
} else {
if (ts_srv_version > TS_VERSION_3) {
refdata = (struct ictimesync_ref_data *)
&time_txf_buf[
sizeof(struct vmbuspipe_hdr) +
sizeof(struct icmsg_hdr)];
adj_guesttime(refdata->parenttime,
refdata->vmreferencetime,
refdata->flags);
} else {
timedatap = (struct ictimesync_data *)
&time_txf_buf[
sizeof(struct vmbuspipe_hdr) +
sizeof(struct icmsg_hdr)];
adj_guesttime(timedatap->parenttime,
hyperv_cs->read(hyperv_cs),
timedatap->flags);
}
}
icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION
| ICMSGHDRFLAG_RESPONSE;
vmbus_sendpacket(channel, time_txf_buf,
recvlen, requestid,
VM_PKT_DATA_INBAND, 0);
}
}
/*
* Heartbeat functionality.
* Every two seconds, Hyper-V send us a heartbeat request message.
* we respond to this message, and Hyper-V knows we are alive.
*/
static void heartbeat_onchannelcallback(void *context)
{
struct vmbus_channel *channel = context;
u32 recvlen;
u64 requestid;
struct icmsg_hdr *icmsghdrp;
struct heartbeat_msg_data *heartbeat_msg;
u8 *hbeat_txf_buf = util_heartbeat.recv_buffer;
while (1) {
vmbus_recvpacket(channel, hbeat_txf_buf,
PAGE_SIZE, &recvlen, &requestid);
if (!recvlen)
break;
icmsghdrp = (struct icmsg_hdr *)&hbeat_txf_buf[
sizeof(struct vmbuspipe_hdr)];
if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
if (vmbus_prep_negotiate_resp(icmsghdrp,
hbeat_txf_buf,
fw_versions, FW_VER_COUNT,
hb_versions, HB_VER_COUNT,
NULL, &hb_srv_version)) {
pr_info("Heartbeat IC version %d.%d\n",
hb_srv_version >> 16,
hb_srv_version & 0xFFFF);
}
} else {
heartbeat_msg =
(struct heartbeat_msg_data *)&hbeat_txf_buf[
sizeof(struct vmbuspipe_hdr) +
sizeof(struct icmsg_hdr)];
heartbeat_msg->seq_num += 1;
}
icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION
| ICMSGHDRFLAG_RESPONSE;
vmbus_sendpacket(channel, hbeat_txf_buf,
recvlen, requestid,
VM_PKT_DATA_INBAND, 0);
}
}
static int util_probe(struct hv_device *dev,
const struct hv_vmbus_device_id *dev_id)
{
struct hv_util_service *srv =
(struct hv_util_service *)dev_id->driver_data;
int ret;
srv->recv_buffer = kmalloc(PAGE_SIZE * 4, GFP_KERNEL);
if (!srv->recv_buffer)
return -ENOMEM;
srv->channel = dev->channel;
if (srv->util_init) {
ret = srv->util_init(srv);
if (ret) {
ret = -ENODEV;
goto error1;
}
}
/*
* The set of services managed by the util driver are not performance
* critical and do not need batched reading. Furthermore, some services
* such as KVP can only handle one message from the host at a time.
* Turn off batched reading for all util drivers before we open the
* channel.
*/
set_channel_read_mode(dev->channel, HV_CALL_DIRECT);
hv_set_drvdata(dev, srv);
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:
if (srv->util_deinit)
srv->util_deinit();
error1:
kfree(srv->recv_buffer);
return ret;
}
static int util_remove(struct hv_device *dev)
{
struct hv_util_service *srv = hv_get_drvdata(dev);
if (srv->util_deinit)
srv->util_deinit();
vmbus_close(dev->channel);
kfree(srv->recv_buffer);
return 0;
}
static const struct hv_vmbus_device_id id_table[] = {
/* Shutdown guid */
{ HV_SHUTDOWN_GUID,
.driver_data = (unsigned long)&util_shutdown
},
/* Time synch guid */
{ HV_TS_GUID,
.driver_data = (unsigned long)&util_timesynch
},
/* Heartbeat guid */
{ HV_HEART_BEAT_GUID,
.driver_data = (unsigned long)&util_heartbeat
},
/* KVP guid */
{ HV_KVP_GUID,
.driver_data = (unsigned long)&util_kvp
},
/* VSS GUID */
{ HV_VSS_GUID,
.driver_data = (unsigned long)&util_vss
},
/* File copy GUID */
{ HV_FCOPY_GUID,
.driver_data = (unsigned long)&util_fcopy
},
{ },
};
MODULE_DEVICE_TABLE(vmbus, id_table);
/* The one and only one */
static struct hv_driver util_drv = {
.name = "hv_util",
.id_table = id_table,
.probe = util_probe,
.remove = util_remove,
.driver = {
.probe_type = PROBE_PREFER_ASYNCHRONOUS,
},
};
static int hv_ptp_enable(struct ptp_clock_info *info,
struct ptp_clock_request *request, int on)
{
return -EOPNOTSUPP;
}
static int hv_ptp_settime(struct ptp_clock_info *p, const struct timespec64 *ts)
{
return -EOPNOTSUPP;
}
static int hv_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
{
return -EOPNOTSUPP;
}
static int hv_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
{
return -EOPNOTSUPP;
}
static int hv_ptp_gettime(struct ptp_clock_info *info, struct timespec64 *ts)
{
*ts = hv_get_adj_host_time();
return 0;
}
static struct ptp_clock_info ptp_hyperv_info = {
.name = "hyperv",
.enable = hv_ptp_enable,
.adjtime = hv_ptp_adjtime,
.adjfreq = hv_ptp_adjfreq,
.gettime64 = hv_ptp_gettime,
.settime64 = hv_ptp_settime,
.owner = THIS_MODULE,
};
static struct ptp_clock *hv_ptp_clock;
static int hv_timesync_init(struct hv_util_service *srv)
{
/* TimeSync requires Hyper-V clocksource. */
if (!hyperv_cs)
return -ENODEV;
spin_lock_init(&host_ts.lock);
INIT_WORK(&adj_time_work, hv_set_host_time);
/*
* ptp_clock_register() returns NULL when CONFIG_PTP_1588_CLOCK is
* disabled but the driver is still useful without the PTP device
* as it still handles the ICTIMESYNCFLAG_SYNC case.
*/
hv_ptp_clock = ptp_clock_register(&ptp_hyperv_info, NULL);
if (IS_ERR_OR_NULL(hv_ptp_clock)) {
pr_err("cannot register PTP clock: %ld\n",
PTR_ERR(hv_ptp_clock));
hv_ptp_clock = NULL;
}
return 0;
}
static void hv_timesync_deinit(void)
{
if (hv_ptp_clock)
ptp_clock_unregister(hv_ptp_clock);
cancel_work_sync(&adj_time_work);
}
static int __init init_hyperv_utils(void)
{
pr_info("Registering HyperV Utility Driver\n");
return vmbus_driver_register(&util_drv);
}
static void exit_hyperv_utils(void)
{
pr_info("De-Registered HyperV Utility Driver\n");
vmbus_driver_unregister(&util_drv);
}
module_init(init_hyperv_utils);
module_exit(exit_hyperv_utils);
MODULE_DESCRIPTION("Hyper-V Utilities");
MODULE_LICENSE("GPL");
+360
View File
@@ -0,0 +1,360 @@
/*
* Kernel/userspace transport abstraction for Hyper-V util driver.
*
* Copyright (C) 2015, Vitaly Kuznetsov <vkuznets@redhat.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
* by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
* NON INFRINGEMENT. See the GNU General Public License for more
* details.
*
*/
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/poll.h>
#include "hyperv_vmbus.h"
#include "hv_utils_transport.h"
static DEFINE_SPINLOCK(hvt_list_lock);
static struct list_head hvt_list = LIST_HEAD_INIT(hvt_list);
static void hvt_reset(struct hvutil_transport *hvt)
{
kfree(hvt->outmsg);
hvt->outmsg = NULL;
hvt->outmsg_len = 0;
if (hvt->on_reset)
hvt->on_reset();
}
static ssize_t hvt_op_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
struct hvutil_transport *hvt;
int ret;
hvt = container_of(file->f_op, struct hvutil_transport, fops);
if (wait_event_interruptible(hvt->outmsg_q, hvt->outmsg_len > 0 ||
hvt->mode != HVUTIL_TRANSPORT_CHARDEV))
return -EINTR;
mutex_lock(&hvt->lock);
if (hvt->mode == HVUTIL_TRANSPORT_DESTROY) {
ret = -EBADF;
goto out_unlock;
}
if (!hvt->outmsg) {
ret = -EAGAIN;
goto out_unlock;
}
if (count < hvt->outmsg_len) {
ret = -EINVAL;
goto out_unlock;
}
if (!copy_to_user(buf, hvt->outmsg, hvt->outmsg_len))
ret = hvt->outmsg_len;
else
ret = -EFAULT;
kfree(hvt->outmsg);
hvt->outmsg = NULL;
hvt->outmsg_len = 0;
if (hvt->on_read)
hvt->on_read();
hvt->on_read = NULL;
out_unlock:
mutex_unlock(&hvt->lock);
return ret;
}
static ssize_t hvt_op_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
struct hvutil_transport *hvt;
u8 *inmsg;
int ret;
hvt = container_of(file->f_op, struct hvutil_transport, fops);
inmsg = memdup_user(buf, count);
if (IS_ERR(inmsg))
return PTR_ERR(inmsg);
if (hvt->mode == HVUTIL_TRANSPORT_DESTROY)
ret = -EBADF;
else
ret = hvt->on_msg(inmsg, count);
kfree(inmsg);
return ret ? ret : count;
}
static __poll_t hvt_op_poll(struct file *file, poll_table *wait)
{
struct hvutil_transport *hvt;
hvt = container_of(file->f_op, struct hvutil_transport, fops);
poll_wait(file, &hvt->outmsg_q, wait);
if (hvt->mode == HVUTIL_TRANSPORT_DESTROY)
return EPOLLERR | EPOLLHUP;
if (hvt->outmsg_len > 0)
return EPOLLIN | EPOLLRDNORM;
return 0;
}
static int hvt_op_open(struct inode *inode, struct file *file)
{
struct hvutil_transport *hvt;
int ret = 0;
bool issue_reset = false;
hvt = container_of(file->f_op, struct hvutil_transport, fops);
mutex_lock(&hvt->lock);
if (hvt->mode == HVUTIL_TRANSPORT_DESTROY) {
ret = -EBADF;
} else if (hvt->mode == HVUTIL_TRANSPORT_INIT) {
/*
* Switching to CHARDEV mode. We switch bach to INIT when
* device gets released.
*/
hvt->mode = HVUTIL_TRANSPORT_CHARDEV;
}
else if (hvt->mode == HVUTIL_TRANSPORT_NETLINK) {
/*
* We're switching from netlink communication to using char
* device. Issue the reset first.
*/
issue_reset = true;
hvt->mode = HVUTIL_TRANSPORT_CHARDEV;
} else {
ret = -EBUSY;
}
if (issue_reset)
hvt_reset(hvt);
mutex_unlock(&hvt->lock);
return ret;
}
static void hvt_transport_free(struct hvutil_transport *hvt)
{
misc_deregister(&hvt->mdev);
kfree(hvt->outmsg);
kfree(hvt);
}
static int hvt_op_release(struct inode *inode, struct file *file)
{
struct hvutil_transport *hvt;
int mode_old;
hvt = container_of(file->f_op, struct hvutil_transport, fops);
mutex_lock(&hvt->lock);
mode_old = hvt->mode;
if (hvt->mode != HVUTIL_TRANSPORT_DESTROY)
hvt->mode = HVUTIL_TRANSPORT_INIT;
/*
* Cleanup message buffers to avoid spurious messages when the daemon
* connects back.
*/
hvt_reset(hvt);
if (mode_old == HVUTIL_TRANSPORT_DESTROY)
complete(&hvt->release);
mutex_unlock(&hvt->lock);
return 0;
}
static void hvt_cn_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp)
{
struct hvutil_transport *hvt, *hvt_found = NULL;
spin_lock(&hvt_list_lock);
list_for_each_entry(hvt, &hvt_list, list) {
if (hvt->cn_id.idx == msg->id.idx &&
hvt->cn_id.val == msg->id.val) {
hvt_found = hvt;
break;
}
}
spin_unlock(&hvt_list_lock);
if (!hvt_found) {
pr_warn("hvt_cn_callback: spurious message received!\n");
return;
}
/*
* Switching to NETLINK mode. Switching to CHARDEV happens when someone
* opens the device.
*/
mutex_lock(&hvt->lock);
if (hvt->mode == HVUTIL_TRANSPORT_INIT)
hvt->mode = HVUTIL_TRANSPORT_NETLINK;
if (hvt->mode == HVUTIL_TRANSPORT_NETLINK)
hvt_found->on_msg(msg->data, msg->len);
else
pr_warn("hvt_cn_callback: unexpected netlink message!\n");
mutex_unlock(&hvt->lock);
}
int hvutil_transport_send(struct hvutil_transport *hvt, void *msg, int len,
void (*on_read_cb)(void))
{
struct cn_msg *cn_msg;
int ret = 0;
if (hvt->mode == HVUTIL_TRANSPORT_INIT ||
hvt->mode == HVUTIL_TRANSPORT_DESTROY) {
return -EINVAL;
} else if (hvt->mode == HVUTIL_TRANSPORT_NETLINK) {
cn_msg = kzalloc(sizeof(*cn_msg) + len, GFP_ATOMIC);
if (!cn_msg)
return -ENOMEM;
cn_msg->id.idx = hvt->cn_id.idx;
cn_msg->id.val = hvt->cn_id.val;
cn_msg->len = len;
memcpy(cn_msg->data, msg, len);
ret = cn_netlink_send(cn_msg, 0, 0, GFP_ATOMIC);
kfree(cn_msg);
/*
* We don't know when netlink messages are delivered but unlike
* in CHARDEV mode we're not blocked and we can send next
* messages right away.
*/
if (on_read_cb)
on_read_cb();
return ret;
}
/* HVUTIL_TRANSPORT_CHARDEV */
mutex_lock(&hvt->lock);
if (hvt->mode != HVUTIL_TRANSPORT_CHARDEV) {
ret = -EINVAL;
goto out_unlock;
}
if (hvt->outmsg) {
/* Previous message wasn't received */
ret = -EFAULT;
goto out_unlock;
}
hvt->outmsg = kzalloc(len, GFP_KERNEL);
if (hvt->outmsg) {
memcpy(hvt->outmsg, msg, len);
hvt->outmsg_len = len;
hvt->on_read = on_read_cb;
wake_up_interruptible(&hvt->outmsg_q);
} else
ret = -ENOMEM;
out_unlock:
mutex_unlock(&hvt->lock);
return ret;
}
struct hvutil_transport *hvutil_transport_init(const char *name,
u32 cn_idx, u32 cn_val,
int (*on_msg)(void *, int),
void (*on_reset)(void))
{
struct hvutil_transport *hvt;
hvt = kzalloc(sizeof(*hvt), GFP_KERNEL);
if (!hvt)
return NULL;
hvt->cn_id.idx = cn_idx;
hvt->cn_id.val = cn_val;
hvt->mdev.minor = MISC_DYNAMIC_MINOR;
hvt->mdev.name = name;
hvt->fops.owner = THIS_MODULE;
hvt->fops.read = hvt_op_read;
hvt->fops.write = hvt_op_write;
hvt->fops.poll = hvt_op_poll;
hvt->fops.open = hvt_op_open;
hvt->fops.release = hvt_op_release;
hvt->mdev.fops = &hvt->fops;
init_waitqueue_head(&hvt->outmsg_q);
mutex_init(&hvt->lock);
init_completion(&hvt->release);
spin_lock(&hvt_list_lock);
list_add(&hvt->list, &hvt_list);
spin_unlock(&hvt_list_lock);
hvt->on_msg = on_msg;
hvt->on_reset = on_reset;
if (misc_register(&hvt->mdev))
goto err_free_hvt;
/* Use cn_id.idx/cn_id.val to determine if we need to setup netlink */
if (hvt->cn_id.idx > 0 && hvt->cn_id.val > 0 &&
cn_add_callback(&hvt->cn_id, name, hvt_cn_callback))
goto err_free_hvt;
return hvt;
err_free_hvt:
spin_lock(&hvt_list_lock);
list_del(&hvt->list);
spin_unlock(&hvt_list_lock);
kfree(hvt);
return NULL;
}
void hvutil_transport_destroy(struct hvutil_transport *hvt)
{
int mode_old;
mutex_lock(&hvt->lock);
mode_old = hvt->mode;
hvt->mode = HVUTIL_TRANSPORT_DESTROY;
wake_up_interruptible(&hvt->outmsg_q);
mutex_unlock(&hvt->lock);
/*
* In case we were in 'chardev' mode we still have an open fd so we
* have to defer freeing the device. Netlink interface can be freed
* now.
*/
spin_lock(&hvt_list_lock);
list_del(&hvt->list);
spin_unlock(&hvt_list_lock);
if (hvt->cn_id.idx > 0 && hvt->cn_id.val > 0)
cn_del_callback(&hvt->cn_id);
if (mode_old == HVUTIL_TRANSPORT_CHARDEV)
wait_for_completion(&hvt->release);
hvt_transport_free(hvt);
}
+55
View File
@@ -0,0 +1,55 @@
/*
* Kernel/userspace transport abstraction for Hyper-V util driver.
*
* Copyright (C) 2015, Vitaly Kuznetsov <vkuznets@redhat.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
* by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
* NON INFRINGEMENT. See the GNU General Public License for more
* details.
*
*/
#ifndef _HV_UTILS_TRANSPORT_H
#define _HV_UTILS_TRANSPORT_H
#include <linux/connector.h>
#include <linux/miscdevice.h>
enum hvutil_transport_mode {
HVUTIL_TRANSPORT_INIT = 0,
HVUTIL_TRANSPORT_NETLINK,
HVUTIL_TRANSPORT_CHARDEV,
HVUTIL_TRANSPORT_DESTROY,
};
struct hvutil_transport {
int mode; /* hvutil_transport_mode */
struct file_operations fops; /* file operations */
struct miscdevice mdev; /* misc device */
struct cb_id cn_id; /* CN_*_IDX/CN_*_VAL */
struct list_head list; /* hvt_list */
int (*on_msg)(void *, int); /* callback on new user message */
void (*on_reset)(void); /* callback when userspace drops */
void (*on_read)(void); /* callback on message read */
u8 *outmsg; /* message to the userspace */
int outmsg_len; /* its length */
wait_queue_head_t outmsg_q; /* poll/read wait queue */
struct mutex lock; /* protects struct members */
struct completion release; /* synchronize with fd release */
};
struct hvutil_transport *hvutil_transport_init(const char *name,
u32 cn_idx, u32 cn_val,
int (*on_msg)(void *, int),
void (*on_reset)(void));
int hvutil_transport_send(struct hvutil_transport *hvt, void *msg, int len,
void (*on_read_cb)(void));
void hvutil_transport_destroy(struct hvutil_transport *hvt);
#endif /* _HV_UTILS_TRANSPORT_H */
+443
View File
@@ -0,0 +1,443 @@
/*
*
* Copyright (c) 2011, 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>
*
*/
#ifndef _HYPERV_VMBUS_H
#define _HYPERV_VMBUS_H
#include <linux/list.h>
#include <asm/sync_bitops.h>
#include <asm/hyperv-tlfs.h>
#include <linux/atomic.h>
#include <linux/hyperv.h>
#include <linux/interrupt.h>
#include "hv_trace.h"
/*
* Timeout for services such as KVP and fcopy.
*/
#define HV_UTIL_TIMEOUT 30
/*
* Timeout for guest-host handshake for services.
*/
#define HV_UTIL_NEGO_TIMEOUT 55
/* Define synthetic interrupt controller flag constants. */
#define HV_EVENT_FLAGS_COUNT (256 * 8)
#define HV_EVENT_FLAGS_LONG_COUNT (256 / sizeof(unsigned long))
/*
* Timer configuration register.
*/
union hv_timer_config {
u64 as_uint64;
struct {
u64 enable:1;
u64 periodic:1;
u64 lazy:1;
u64 auto_enable:1;
u64 apic_vector:8;
u64 direct_mode:1;
u64 reserved_z0:3;
u64 sintx:4;
u64 reserved_z1:44;
};
};
/* Define the synthetic interrupt controller event flags format. */
union hv_synic_event_flags {
unsigned long flags[HV_EVENT_FLAGS_LONG_COUNT];
};
/* Define SynIC control register. */
union hv_synic_scontrol {
u64 as_uint64;
struct {
u64 enable:1;
u64 reserved:63;
};
};
/* Define synthetic interrupt source. */
union hv_synic_sint {
u64 as_uint64;
struct {
u64 vector:8;
u64 reserved1:8;
u64 masked:1;
u64 auto_eoi:1;
u64 reserved2:46;
};
};
/* Define the format of the SIMP register */
union hv_synic_simp {
u64 as_uint64;
struct {
u64 simp_enabled:1;
u64 preserved:11;
u64 base_simp_gpa:52;
};
};
/* Define the format of the SIEFP register */
union hv_synic_siefp {
u64 as_uint64;
struct {
u64 siefp_enabled:1;
u64 preserved:11;
u64 base_siefp_gpa:52;
};
};
/* Definitions for the monitored notification facility */
union hv_monitor_trigger_group {
u64 as_uint64;
struct {
u32 pending;
u32 armed;
};
};
struct hv_monitor_parameter {
union hv_connection_id connectionid;
u16 flagnumber;
u16 rsvdz;
};
union hv_monitor_trigger_state {
u32 asu32;
struct {
u32 group_enable:4;
u32 rsvdz:28;
};
};
/* struct hv_monitor_page Layout */
/* ------------------------------------------------------ */
/* | 0 | TriggerState (4 bytes) | Rsvd1 (4 bytes) | */
/* | 8 | TriggerGroup[0] | */
/* | 10 | TriggerGroup[1] | */
/* | 18 | TriggerGroup[2] | */
/* | 20 | TriggerGroup[3] | */
/* | 28 | Rsvd2[0] | */
/* | 30 | Rsvd2[1] | */
/* | 38 | Rsvd2[2] | */
/* | 40 | NextCheckTime[0][0] | NextCheckTime[0][1] | */
/* | ... | */
/* | 240 | Latency[0][0..3] | */
/* | 340 | Rsvz3[0] | */
/* | 440 | Parameter[0][0] | */
/* | 448 | Parameter[0][1] | */
/* | ... | */
/* | 840 | Rsvd4[0] | */
/* ------------------------------------------------------ */
struct hv_monitor_page {
union hv_monitor_trigger_state trigger_state;
u32 rsvdz1;
union hv_monitor_trigger_group trigger_group[4];
u64 rsvdz2[3];
s32 next_checktime[4][32];
u16 latency[4][32];
u64 rsvdz3[32];
struct hv_monitor_parameter parameter[4][32];
u8 rsvdz4[1984];
};
#define HV_HYPERCALL_PARAM_ALIGN sizeof(u64)
/* Definition of the hv_post_message hypercall input structure. */
struct hv_input_post_message {
union hv_connection_id connectionid;
u32 reserved;
u32 message_type;
u32 payload_size;
u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT];
};
enum {
VMBUS_MESSAGE_CONNECTION_ID = 1,
VMBUS_MESSAGE_CONNECTION_ID_4 = 4,
VMBUS_MESSAGE_PORT_ID = 1,
VMBUS_EVENT_CONNECTION_ID = 2,
VMBUS_EVENT_PORT_ID = 2,
VMBUS_MONITOR_CONNECTION_ID = 3,
VMBUS_MONITOR_PORT_ID = 3,
VMBUS_MESSAGE_SINT = 2,
};
/*
* Per cpu state for channel handling
*/
struct hv_per_cpu_context {
void *synic_message_page;
void *synic_event_page;
/*
* buffer to post messages to the host.
*/
void *post_msg_page;
/*
* Starting with win8, we can take channel interrupts on any CPU;
* we will manage the tasklet that handles events messages on a per CPU
* basis.
*/
struct tasklet_struct msg_dpc;
/*
* To optimize the mapping of relid to channel, maintain
* per-cpu list of the channels based on their CPU affinity.
*/
struct list_head chan_list;
struct clock_event_device *clk_evt;
};
struct hv_context {
/* We only support running on top of Hyper-V
* So at this point this really can only contain the Hyper-V ID
*/
u64 guestid;
void *tsc_page;
bool synic_initialized;
struct hv_per_cpu_context __percpu *cpu_context;
/*
* To manage allocations in a NUMA node.
* Array indexed by numa node ID.
*/
struct cpumask *hv_numa_map;
};
extern struct hv_context hv_context;
/* Hv Interface */
extern int hv_init(void);
extern int hv_post_message(union hv_connection_id connection_id,
enum hv_message_type message_type,
void *payload, size_t payload_size);
extern int hv_synic_alloc(void);
extern void hv_synic_free(void);
extern int hv_synic_init(unsigned int cpu);
extern int hv_synic_cleanup(unsigned int cpu);
extern void hv_synic_clockevents_cleanup(void);
/* Interface */
int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
struct page *pages, u32 pagecnt);
void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info);
int hv_ringbuffer_write(struct vmbus_channel *channel,
const struct kvec *kv_list, u32 kv_count);
int hv_ringbuffer_read(struct vmbus_channel *channel,
void *buffer, u32 buflen, u32 *buffer_actual_len,
u64 *requestid, bool raw);
/*
* Maximum channels is determined by the size of the interrupt page
* which is PAGE_SIZE. 1/2 of PAGE_SIZE is for send endpoint interrupt
* and the other is receive endpoint interrupt
*/
#define MAX_NUM_CHANNELS ((PAGE_SIZE >> 1) << 3) /* 16348 channels */
/* The value here must be in multiple of 32 */
/* TODO: Need to make this configurable */
#define MAX_NUM_CHANNELS_SUPPORTED 256
enum vmbus_connect_state {
DISCONNECTED,
CONNECTING,
CONNECTED,
DISCONNECTING
};
#define MAX_SIZE_CHANNEL_MESSAGE HV_MESSAGE_PAYLOAD_BYTE_COUNT
struct vmbus_connection {
/*
* CPU on which the initial host contact was made.
*/
int connect_cpu;
u32 msg_conn_id;
atomic_t offer_in_progress;
enum vmbus_connect_state conn_state;
atomic_t next_gpadl_handle;
struct completion unload_event;
/*
* Represents channel interrupts. Each bit position represents a
* channel. When a channel sends an interrupt via VMBUS, it finds its
* bit in the sendInterruptPage, set it and calls Hv to generate a port
* event. The other end receives the port event and parse the
* recvInterruptPage to see which bit is set
*/
void *int_page;
void *send_int_page;
void *recv_int_page;
/*
* 2 pages - 1st page for parent->child notification and 2nd
* is child->parent notification
*/
struct hv_monitor_page *monitor_pages[2];
struct list_head chn_msg_list;
spinlock_t channelmsg_lock;
/* List of channels */
struct list_head chn_list;
struct mutex channel_mutex;
/*
* An offer message is handled first on the work_queue, and then
* is further handled on handle_primary_chan_wq or
* handle_sub_chan_wq.
*/
struct workqueue_struct *work_queue;
struct workqueue_struct *handle_primary_chan_wq;
struct workqueue_struct *handle_sub_chan_wq;
};
struct vmbus_msginfo {
/* Bookkeeping stuff */
struct list_head msglist_entry;
/* The message itself */
unsigned char msg[0];
};
extern struct vmbus_connection vmbus_connection;
static inline void vmbus_send_interrupt(u32 relid)
{
sync_set_bit(relid, vmbus_connection.send_int_page);
}
enum vmbus_message_handler_type {
/* The related handler can sleep. */
VMHT_BLOCKING = 0,
/* The related handler must NOT sleep. */
VMHT_NON_BLOCKING = 1,
};
struct vmbus_channel_message_table_entry {
enum vmbus_channel_message_type message_type;
enum vmbus_message_handler_type handler_type;
void (*message_handler)(struct vmbus_channel_message_header *msg);
};
extern const struct vmbus_channel_message_table_entry
channel_message_table[CHANNELMSG_COUNT];
/* General vmbus interface */
struct hv_device *vmbus_device_create(const uuid_le *type,
const uuid_le *instance,
struct vmbus_channel *channel);
int vmbus_device_register(struct hv_device *child_device_obj);
void vmbus_device_unregister(struct hv_device *device_obj);
int vmbus_add_channel_kobj(struct hv_device *device_obj,
struct vmbus_channel *channel);
struct vmbus_channel *relid2channel(u32 relid);
void vmbus_free_channels(void);
/* Connection interface */
int vmbus_connect(void);
void vmbus_disconnect(void);
int vmbus_post_msg(void *buffer, size_t buflen, bool can_sleep);
void vmbus_on_event(unsigned long data);
void vmbus_on_msg_dpc(unsigned long data);
int hv_kvp_init(struct hv_util_service *srv);
void hv_kvp_deinit(void);
void hv_kvp_onchannelcallback(void *context);
int hv_vss_init(struct hv_util_service *srv);
void hv_vss_deinit(void);
void hv_vss_onchannelcallback(void *context);
int hv_fcopy_init(struct hv_util_service *srv);
void hv_fcopy_deinit(void);
void hv_fcopy_onchannelcallback(void *context);
void vmbus_initiate_unload(bool crash);
static inline void hv_poll_channel(struct vmbus_channel *channel,
void (*cb)(void *))
{
if (!channel)
return;
if (in_interrupt() && (channel->target_cpu == smp_processor_id())) {
cb(channel);
return;
}
smp_call_function_single(channel->target_cpu, cb, channel, true);
}
enum hvutil_device_state {
HVUTIL_DEVICE_INIT = 0, /* driver is loaded, waiting for userspace */
HVUTIL_READY, /* userspace is registered */
HVUTIL_HOSTMSG_RECEIVED, /* message from the host was received */
HVUTIL_USERSPACE_REQ, /* request to userspace was sent */
HVUTIL_USERSPACE_RECV, /* reply from userspace was received */
HVUTIL_DEVICE_DYING, /* driver unload is in progress */
};
#endif /* _HYPERV_VMBUS_H */
+534
View File
@@ -0,0 +1,534 @@
/*
*
* 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
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/hyperv.h>
#include <linux/uio.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/prefetch.h>
#include "hyperv_vmbus.h"
#define VMBUS_PKT_TRAILER 8
/*
* When we write to the ring buffer, check if the host needs to
* be signaled. Here is the details of this protocol:
*
* 1. The host guarantees that while it is draining the
* ring buffer, it will set the interrupt_mask to
* indicate it does not need to be interrupted when
* new data is placed.
*
* 2. The host guarantees that it will completely drain
* the ring buffer before exiting the read loop. Further,
* once the ring buffer is empty, it will clear the
* interrupt_mask and re-check to see if new data has
* arrived.
*
* KYS: Oct. 30, 2016:
* It looks like Windows hosts have logic to deal with DOS attacks that
* can be triggered if it receives interrupts when it is not expecting
* the interrupt. The host expects interrupts only when the ring
* transitions from empty to non-empty (or full to non full on the guest
* to host ring).
* So, base the signaling decision solely on the ring state until the
* host logic is fixed.
*/
static void hv_signal_on_write(u32 old_write, struct vmbus_channel *channel)
{
struct hv_ring_buffer_info *rbi = &channel->outbound;
virt_mb();
if (READ_ONCE(rbi->ring_buffer->interrupt_mask))
return;
/* check interrupt_mask before read_index */
virt_rmb();
/*
* This is the only case we need to signal when the
* ring transitions from being empty to non-empty.
*/
if (old_write == READ_ONCE(rbi->ring_buffer->read_index))
vmbus_setevent(channel);
}
/* Get the next write location for the specified ring buffer. */
static inline u32
hv_get_next_write_location(struct hv_ring_buffer_info *ring_info)
{
u32 next = ring_info->ring_buffer->write_index;
return next;
}
/* Set the next write location for the specified ring buffer. */
static inline void
hv_set_next_write_location(struct hv_ring_buffer_info *ring_info,
u32 next_write_location)
{
ring_info->ring_buffer->write_index = next_write_location;
}
/* Set the next read location for the specified ring buffer. */
static inline void
hv_set_next_read_location(struct hv_ring_buffer_info *ring_info,
u32 next_read_location)
{
ring_info->ring_buffer->read_index = next_read_location;
ring_info->priv_read_index = next_read_location;
}
/* Get the size of the ring buffer. */
static inline u32
hv_get_ring_buffersize(const struct hv_ring_buffer_info *ring_info)
{
return ring_info->ring_datasize;
}
/* Get the read and write indices as u64 of the specified ring buffer. */
static inline u64
hv_get_ring_bufferindices(struct hv_ring_buffer_info *ring_info)
{
return (u64)ring_info->ring_buffer->write_index << 32;
}
/*
* Helper routine to copy from source to ring buffer.
* Assume there is enough room. Handles wrap-around in dest case only!!
*/
static u32 hv_copyto_ringbuffer(
struct hv_ring_buffer_info *ring_info,
u32 start_write_offset,
const void *src,
u32 srclen)
{
void *ring_buffer = hv_get_ring_buffer(ring_info);
u32 ring_buffer_size = hv_get_ring_buffersize(ring_info);
memcpy(ring_buffer + start_write_offset, src, srclen);
start_write_offset += srclen;
if (start_write_offset >= ring_buffer_size)
start_write_offset -= ring_buffer_size;
return start_write_offset;
}
/*
*
* hv_get_ringbuffer_availbytes()
*
* Get number of bytes available to read and to write to
* for the specified ring buffer
*/
static void
hv_get_ringbuffer_availbytes(const struct hv_ring_buffer_info *rbi,
u32 *read, u32 *write)
{
u32 read_loc, write_loc, dsize;
/* Capture the read/write indices before they changed */
read_loc = READ_ONCE(rbi->ring_buffer->read_index);
write_loc = READ_ONCE(rbi->ring_buffer->write_index);
dsize = rbi->ring_datasize;
*write = write_loc >= read_loc ? dsize - (write_loc - read_loc) :
read_loc - write_loc;
*read = dsize - *write;
}
/* Get various debug metrics for the specified ring buffer. */
int hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info,
struct hv_ring_buffer_debug_info *debug_info)
{
u32 bytes_avail_towrite;
u32 bytes_avail_toread;
if (!ring_info->ring_buffer)
return -EINVAL;
hv_get_ringbuffer_availbytes(ring_info,
&bytes_avail_toread,
&bytes_avail_towrite);
debug_info->bytes_avail_toread = bytes_avail_toread;
debug_info->bytes_avail_towrite = bytes_avail_towrite;
debug_info->current_read_index = ring_info->ring_buffer->read_index;
debug_info->current_write_index = ring_info->ring_buffer->write_index;
debug_info->current_interrupt_mask
= ring_info->ring_buffer->interrupt_mask;
return 0;
}
EXPORT_SYMBOL_GPL(hv_ringbuffer_get_debuginfo);
/* Initialize the ring buffer. */
int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
struct page *pages, u32 page_cnt)
{
int i;
struct page **pages_wraparound;
BUILD_BUG_ON((sizeof(struct hv_ring_buffer) != PAGE_SIZE));
memset(ring_info, 0, sizeof(struct hv_ring_buffer_info));
/*
* First page holds struct hv_ring_buffer, do wraparound mapping for
* the rest.
*/
pages_wraparound = kcalloc(page_cnt * 2 - 1, sizeof(struct page *),
GFP_KERNEL);
if (!pages_wraparound)
return -ENOMEM;
pages_wraparound[0] = pages;
for (i = 0; i < 2 * (page_cnt - 1); i++)
pages_wraparound[i + 1] = &pages[i % (page_cnt - 1) + 1];
ring_info->ring_buffer = (struct hv_ring_buffer *)
vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP, PAGE_KERNEL);
kfree(pages_wraparound);
if (!ring_info->ring_buffer)
return -ENOMEM;
ring_info->ring_buffer->read_index =
ring_info->ring_buffer->write_index = 0;
/* Set the feature bit for enabling flow control. */
ring_info->ring_buffer->feature_bits.value = 1;
ring_info->ring_size = page_cnt << PAGE_SHIFT;
ring_info->ring_size_div10_reciprocal =
reciprocal_value(ring_info->ring_size / 10);
ring_info->ring_datasize = ring_info->ring_size -
sizeof(struct hv_ring_buffer);
spin_lock_init(&ring_info->ring_lock);
return 0;
}
/* Cleanup the ring buffer. */
void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info)
{
vunmap(ring_info->ring_buffer);
}
/* Write to the ring buffer. */
int hv_ringbuffer_write(struct vmbus_channel *channel,
const struct kvec *kv_list, u32 kv_count)
{
int i;
u32 bytes_avail_towrite;
u32 totalbytes_towrite = sizeof(u64);
u32 next_write_location;
u32 old_write;
u64 prev_indices;
unsigned long flags;
struct hv_ring_buffer_info *outring_info = &channel->outbound;
if (channel->rescind)
return -ENODEV;
for (i = 0; i < kv_count; i++)
totalbytes_towrite += kv_list[i].iov_len;
spin_lock_irqsave(&outring_info->ring_lock, flags);
bytes_avail_towrite = hv_get_bytes_to_write(outring_info);
/*
* If there is only room for the packet, assume it is full.
* Otherwise, the next time around, we think the ring buffer
* is empty since the read index == write index.
*/
if (bytes_avail_towrite <= totalbytes_towrite) {
spin_unlock_irqrestore(&outring_info->ring_lock, flags);
return -EAGAIN;
}
/* Write to the ring buffer */
next_write_location = hv_get_next_write_location(outring_info);
old_write = next_write_location;
for (i = 0; i < kv_count; i++) {
next_write_location = hv_copyto_ringbuffer(outring_info,
next_write_location,
kv_list[i].iov_base,
kv_list[i].iov_len);
}
/* Set previous packet start */
prev_indices = hv_get_ring_bufferindices(outring_info);
next_write_location = hv_copyto_ringbuffer(outring_info,
next_write_location,
&prev_indices,
sizeof(u64));
/* Issue a full memory barrier before updating the write index */
virt_mb();
/* Now, update the write location */
hv_set_next_write_location(outring_info, next_write_location);
spin_unlock_irqrestore(&outring_info->ring_lock, flags);
hv_signal_on_write(old_write, channel);
if (channel->rescind)
return -ENODEV;
return 0;
}
int hv_ringbuffer_read(struct vmbus_channel *channel,
void *buffer, u32 buflen, u32 *buffer_actual_len,
u64 *requestid, bool raw)
{
struct vmpacket_descriptor *desc;
u32 packetlen, offset;
if (unlikely(buflen == 0))
return -EINVAL;
*buffer_actual_len = 0;
*requestid = 0;
/* Make sure there is something to read */
desc = hv_pkt_iter_first(channel);
if (desc == NULL) {
/*
* No error is set when there is even no header, drivers are
* supposed to analyze buffer_actual_len.
*/
return 0;
}
offset = raw ? 0 : (desc->offset8 << 3);
packetlen = (desc->len8 << 3) - offset;
*buffer_actual_len = packetlen;
*requestid = desc->trans_id;
if (unlikely(packetlen > buflen))
return -ENOBUFS;
/* since ring is double mapped, only one copy is necessary */
memcpy(buffer, (const char *)desc + offset, packetlen);
/* Advance ring index to next packet descriptor */
__hv_pkt_iter_next(channel, desc);
/* Notify host of update */
hv_pkt_iter_close(channel);
return 0;
}
/*
* Determine number of bytes available in ring buffer after
* the current iterator (priv_read_index) location.
*
* This is similar to hv_get_bytes_to_read but with private
* read index instead.
*/
static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi)
{
u32 priv_read_loc = rbi->priv_read_index;
u32 write_loc = READ_ONCE(rbi->ring_buffer->write_index);
if (write_loc >= priv_read_loc)
return write_loc - priv_read_loc;
else
return (rbi->ring_datasize - priv_read_loc) + write_loc;
}
/*
* Get first vmbus packet from ring buffer after read_index
*
* If ring buffer is empty, returns NULL and no other action needed.
*/
struct vmpacket_descriptor *hv_pkt_iter_first(struct vmbus_channel *channel)
{
struct hv_ring_buffer_info *rbi = &channel->inbound;
struct vmpacket_descriptor *desc;
if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor))
return NULL;
desc = hv_get_ring_buffer(rbi) + rbi->priv_read_index;
if (desc)
prefetch((char *)desc + (desc->len8 << 3));
return desc;
}
EXPORT_SYMBOL_GPL(hv_pkt_iter_first);
/*
* Get next vmbus packet from ring buffer.
*
* Advances the current location (priv_read_index) and checks for more
* data. If the end of the ring buffer is reached, then return NULL.
*/
struct vmpacket_descriptor *
__hv_pkt_iter_next(struct vmbus_channel *channel,
const struct vmpacket_descriptor *desc)
{
struct hv_ring_buffer_info *rbi = &channel->inbound;
u32 packetlen = desc->len8 << 3;
u32 dsize = rbi->ring_datasize;
/* bump offset to next potential packet */
rbi->priv_read_index += packetlen + VMBUS_PKT_TRAILER;
if (rbi->priv_read_index >= dsize)
rbi->priv_read_index -= dsize;
/* more data? */
return hv_pkt_iter_first(channel);
}
EXPORT_SYMBOL_GPL(__hv_pkt_iter_next);
/* How many bytes were read in this iterator cycle */
static u32 hv_pkt_iter_bytes_read(const struct hv_ring_buffer_info *rbi,
u32 start_read_index)
{
if (rbi->priv_read_index >= start_read_index)
return rbi->priv_read_index - start_read_index;
else
return rbi->ring_datasize - start_read_index +
rbi->priv_read_index;
}
/*
* Update host ring buffer after iterating over packets. If the host has
* stopped queuing new entries because it found the ring buffer full, and
* sufficient space is being freed up, signal the host. But be careful to
* only signal the host when necessary, both for performance reasons and
* because Hyper-V protects itself by throttling guests that signal
* inappropriately.
*
* Determining when to signal is tricky. There are three key data inputs
* that must be handled in this order to avoid race conditions:
*
* 1. Update the read_index
* 2. Read the pending_send_sz
* 3. Read the current write_index
*
* The interrupt_mask is not used to determine when to signal. The
* interrupt_mask is used only on the guest->host ring buffer when
* sending requests to the host. The host does not use it on the host->
* guest ring buffer to indicate whether it should be signaled.
*/
void hv_pkt_iter_close(struct vmbus_channel *channel)
{
struct hv_ring_buffer_info *rbi = &channel->inbound;
u32 curr_write_sz, pending_sz, bytes_read, start_read_index;
/*
* Make sure all reads are done before we update the read index since
* the writer may start writing to the read area once the read index
* is updated.
*/
virt_rmb();
start_read_index = rbi->ring_buffer->read_index;
rbi->ring_buffer->read_index = rbi->priv_read_index;
/*
* Older versions of Hyper-V (before WS2102 and Win8) do not
* implement pending_send_sz and simply poll if the host->guest
* ring buffer is full. No signaling is needed or expected.
*/
if (!rbi->ring_buffer->feature_bits.feat_pending_send_sz)
return;
/*
* Issue a full memory barrier before making the signaling decision.
* If reading pending_send_sz were to be reordered and happen
* before we commit the new read_index, a race could occur. If the
* host were to set the pending_send_sz after we have sampled
* pending_send_sz, and the ring buffer blocks before we commit the
* read index, we could miss sending the interrupt. Issue a full
* memory barrier to address this.
*/
virt_mb();
/*
* If the pending_send_sz is zero, then the ring buffer is not
* blocked and there is no need to signal. This is far by the
* most common case, so exit quickly for best performance.
*/
pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz);
if (!pending_sz)
return;
/*
* Ensure the read of write_index in hv_get_bytes_to_write()
* happens after the read of pending_send_sz.
*/
virt_rmb();
curr_write_sz = hv_get_bytes_to_write(rbi);
bytes_read = hv_pkt_iter_bytes_read(rbi, start_read_index);
/*
* We want to signal the host only if we're transitioning
* from a "not enough free space" state to a "enough free
* space" state. For example, it's possible that this function
* could run and free up enough space to signal the host, and then
* run again and free up additional space before the host has a
* chance to clear the pending_send_sz. The 2nd invocation would
* be a null transition from "enough free space" to "enough free
* space", which doesn't warrant a signal.
*
* Exactly filling the ring buffer is treated as "not enough
* space". The ring buffer always must have at least one byte
* empty so the empty and full conditions are distinguishable.
* hv_get_bytes_to_write() doesn't fully tell the truth in
* this regard.
*
* So first check if we were in the "enough free space" state
* before we began the iteration. If so, the host was not
* blocked, and there's no need to signal.
*/
if (curr_write_sz - bytes_read > pending_sz)
return;
/*
* Similarly, if the new state is "not enough space", then
* there's no need to signal.
*/
if (curr_write_sz <= pending_sz)
return;
vmbus_setevent(channel);
}
EXPORT_SYMBOL_GPL(hv_pkt_iter_close);
File diff suppressed because it is too large. Load diff