linux_dsm_epyc7002/drivers/hv/connection.c

319 lines
8.1 KiB
C
Raw Normal View History

/*
*
* 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 cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/hyperv.h>
#include <asm/hyperv.h>
#include "hyperv_vmbus.h"
struct vmbus_connection vmbus_connection = {
.conn_state = DISCONNECTED,
.next_gpadl_handle = ATOMIC_INIT(0xE1E10),
};
/*
* vmbus_connect - Sends a connect request on the partition service connection
*/
int vmbus_connect(void)
{
int ret = 0;
int t;
struct vmbus_channel_msginfo *msginfo = NULL;
struct vmbus_channel_initiate_contact *msg;
unsigned long flags;
/* 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;
}
INIT_LIST_HEAD(&vmbus_connection.chn_msg_list);
spin_lock_init(&vmbus_connection.channelmsg_lock);
INIT_LIST_HEAD(&vmbus_connection.chn_list);
spin_lock_init(&vmbus_connection.channel_lock);
/*
* 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 =
(void *)__get_free_pages((GFP_KERNEL|__GFP_ZERO), 1);
if (vmbus_connection.monitor_pages == NULL) {
ret = -ENOMEM;
goto cleanup;
}
msginfo = kzalloc(sizeof(*msginfo) +
sizeof(struct vmbus_channel_initiate_contact),
GFP_KERNEL);
if (msginfo == NULL) {
ret = -ENOMEM;
goto cleanup;
}
init_completion(&msginfo->waitevent);
msg = (struct vmbus_channel_initiate_contact *)msginfo->msg;
msg->header.msgtype = CHANNELMSG_INITIATE_CONTACT;
msg->vmbus_version_requested = VMBUS_REVISION_NUMBER;
msg->interrupt_page = virt_to_phys(vmbus_connection.int_page);
msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages);
msg->monitor_page2 = virt_to_phys(
(void *)((unsigned long)vmbus_connection.monitor_pages +
PAGE_SIZE));
/*
* 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));
if (ret != 0) {
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_del(&msginfo->msglistentry);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock,
flags);
goto cleanup;
}
/* Wait for the connection response */
t = wait_for_completion_timeout(&msginfo->waitevent, 5*HZ);
if (t == 0) {
spin_lock_irqsave(&vmbus_connection.channelmsg_lock,
flags);
list_del(&msginfo->msglistentry);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock,
flags);
ret = -ETIMEDOUT;
goto cleanup;
}
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;
} else {
pr_err("Unable to connect, "
"Version %d not supported by Hyper-V\n",
VMBUS_REVISION_NUMBER);
ret = -ECONNREFUSED;
goto cleanup;
}
kfree(msginfo);
return 0;
cleanup:
vmbus_connection.conn_state = DISCONNECTED;
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;
}
if (vmbus_connection.monitor_pages) {
free_pages((unsigned long)vmbus_connection.monitor_pages, 1);
vmbus_connection.monitor_pages = NULL;
}
kfree(msginfo);
return ret;
}
/*
* 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;
unsigned long flags;
spin_lock_irqsave(&vmbus_connection.channel_lock, flags);
list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
if (channel->offermsg.child_relid == relid) {
found_channel = channel;
break;
}
}
spin_unlock_irqrestore(&vmbus_connection.channel_lock, flags);
return found_channel;
}
/*
* process_chn_event - Process a channel event notification
*/
static void process_chn_event(u32 relid)
{
struct vmbus_channel *channel;
unsigned long flags;
/*
* Find the channel based on this relid and invokes the
* channel callback to process the event
*/
channel = relid2channel(relid);
if (!channel) {
pr_err("channel not found for relid - %u\n", relid);
return;
}
/*
* A channel once created is persistent even when there
* is no driver handling the device. An unloading driver
* sets the onchannel_callback to NULL under the
* protection of the channel inbound_lock. Thus, checking
* and invoking the driver specific callback takes care of
* orderly unloading of the driver.
*/
spin_lock_irqsave(&channel->inbound_lock, flags);
if (channel->onchannel_callback != NULL)
channel->onchannel_callback(channel->channel_callback_context);
else
pr_err("no channel callback for relid - %u\n", relid);
spin_unlock_irqrestore(&channel->inbound_lock, flags);
}
/*
* vmbus_on_event - Handler for events
*/
void vmbus_on_event(unsigned long data)
{
u32 dword;
u32 maxdword = MAX_NUM_CHANNELS_SUPPORTED >> 5;
int bit;
u32 relid;
u32 *recv_int_page = vmbus_connection.recv_int_page;
/* Check events */
if (!recv_int_page)
return;
for (dword = 0; dword < maxdword; dword++) {
if (!recv_int_page[dword])
continue;
for (bit = 0; bit < 32; bit++) {
if (sync_test_and_clear_bit(bit,
(unsigned long *)&recv_int_page[dword])) {
relid = (dword << 5) + bit;
if (relid == 0)
/*
* Special case - vmbus
* channel protocol msg
*/
continue;
process_chn_event(relid);
}
}
}
}
/*
* vmbus_post_msg - Send a msg on the vmbus's message connection
*/
int vmbus_post_msg(void *buffer, size_t buflen)
{
union hv_connection_id conn_id;
int ret = 0;
int retries = 0;
conn_id.asu32 = 0;
conn_id.u.id = VMBUS_MESSAGE_CONNECTION_ID;
/*
* hv_post_message() can have transient failures because of
* insufficient resources. Retry the operation a couple of
* times before giving up.
*/
while (retries < 3) {
ret = hv_post_message(conn_id, 1, buffer, buflen);
if (ret != HV_STATUS_INSUFFICIENT_BUFFERS)
return ret;
retries++;
msleep(100);
}
return ret;
}
/*
* vmbus_set_event - Send an event notification to the parent
*/
int vmbus_set_event(u32 child_relid)
{
/* Each u32 represents 32 channels */
sync_set_bit(child_relid & 31,
(unsigned long *)vmbus_connection.send_int_page +
(child_relid >> 5));
return hv_signal_event();
}