linux/drivers/hv/vmbus_drv.c

1132 lines
28 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>
* K. Y. Srinivasan <kys@microsoft.com>
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/interrupt.h>
#include <linux/sysctl.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 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/acpi.h>
#include <linux/completion.h>
#include <linux/hyperv.h>
#include <linux/kernel_stat.h>
#include <linux/clockchips.h>
#include <linux/cpu.h>
#include <asm/hyperv.h>
#include <asm/hypervisor.h>
#include <asm/mshyperv.h>
#include <linux/notifier.h>
#include <linux/ptrace.h>
#include "hyperv_vmbus.h"
static struct acpi_device *hv_acpi_dev;
static struct tasklet_struct msg_dpc;
static struct completion probe_event;
static int irq;
static int hyperv_panic_event(struct notifier_block *nb,
unsigned long event, void *ptr)
{
struct pt_regs *regs;
regs = current_pt_regs();
wrmsrl(HV_X64_MSR_CRASH_P0, regs->ip);
wrmsrl(HV_X64_MSR_CRASH_P1, regs->ax);
wrmsrl(HV_X64_MSR_CRASH_P2, regs->bx);
wrmsrl(HV_X64_MSR_CRASH_P3, regs->cx);
wrmsrl(HV_X64_MSR_CRASH_P4, regs->dx);
/*
* Let Hyper-V know there is crash data available
*/
wrmsrl(HV_X64_MSR_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY);
return NOTIFY_DONE;
}
static struct notifier_block hyperv_panic_block = {
.notifier_call = hyperv_panic_event,
};
struct resource hyperv_mmio = {
.name = "hyperv mmio",
.flags = IORESOURCE_MEM,
};
EXPORT_SYMBOL_GPL(hyperv_mmio);
static int vmbus_exists(void)
{
if (hv_acpi_dev == NULL)
return -ENODEV;
return 0;
}
#define VMBUS_ALIAS_LEN ((sizeof((struct hv_vmbus_device_id *)0)->guid) * 2)
static void print_alias_name(struct hv_device *hv_dev, char *alias_name)
{
int i;
for (i = 0; i < VMBUS_ALIAS_LEN; i += 2)
sprintf(&alias_name[i], "%02x", hv_dev->dev_type.b[i/2]);
}
static u8 channel_monitor_group(struct vmbus_channel *channel)
{
return (u8)channel->offermsg.monitorid / 32;
}
static u8 channel_monitor_offset(struct vmbus_channel *channel)
{
return (u8)channel->offermsg.monitorid % 32;
}
static u32 channel_pending(struct vmbus_channel *channel,
struct hv_monitor_page *monitor_page)
{
u8 monitor_group = channel_monitor_group(channel);
return monitor_page->trigger_group[monitor_group].pending;
}
static u32 channel_latency(struct vmbus_channel *channel,
struct hv_monitor_page *monitor_page)
{
u8 monitor_group = channel_monitor_group(channel);
u8 monitor_offset = channel_monitor_offset(channel);
return monitor_page->latency[monitor_group][monitor_offset];
}
static u32 channel_conn_id(struct vmbus_channel *channel,
struct hv_monitor_page *monitor_page)
{
u8 monitor_group = channel_monitor_group(channel);
u8 monitor_offset = channel_monitor_offset(channel);
return monitor_page->parameter[monitor_group][monitor_offset].connectionid.u.id;
}
static ssize_t id_show(struct device *dev, struct device_attribute *dev_attr,
char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
if (!hv_dev->channel)
return -ENODEV;
return sprintf(buf, "%d\n", hv_dev->channel->offermsg.child_relid);
}
static DEVICE_ATTR_RO(id);
static ssize_t state_show(struct device *dev, struct device_attribute *dev_attr,
char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
if (!hv_dev->channel)
return -ENODEV;
return sprintf(buf, "%d\n", hv_dev->channel->state);
}
static DEVICE_ATTR_RO(state);
static ssize_t monitor_id_show(struct device *dev,
struct device_attribute *dev_attr, char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
if (!hv_dev->channel)
return -ENODEV;
return sprintf(buf, "%d\n", hv_dev->channel->offermsg.monitorid);
}
static DEVICE_ATTR_RO(monitor_id);
static ssize_t class_id_show(struct device *dev,
struct device_attribute *dev_attr, char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
if (!hv_dev->channel)
return -ENODEV;
return sprintf(buf, "{%pUl}\n",
hv_dev->channel->offermsg.offer.if_type.b);
}
static DEVICE_ATTR_RO(class_id);
static ssize_t device_id_show(struct device *dev,
struct device_attribute *dev_attr, char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
if (!hv_dev->channel)
return -ENODEV;
return sprintf(buf, "{%pUl}\n",
hv_dev->channel->offermsg.offer.if_instance.b);
}
static DEVICE_ATTR_RO(device_id);
static ssize_t modalias_show(struct device *dev,
struct device_attribute *dev_attr, char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
char alias_name[VMBUS_ALIAS_LEN + 1];
print_alias_name(hv_dev, alias_name);
return sprintf(buf, "vmbus:%s\n", alias_name);
}
static DEVICE_ATTR_RO(modalias);
static ssize_t server_monitor_pending_show(struct device *dev,
struct device_attribute *dev_attr,
char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
if (!hv_dev->channel)
return -ENODEV;
return sprintf(buf, "%d\n",
channel_pending(hv_dev->channel,
vmbus_connection.monitor_pages[1]));
}
static DEVICE_ATTR_RO(server_monitor_pending);
static ssize_t client_monitor_pending_show(struct device *dev,
struct device_attribute *dev_attr,
char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
if (!hv_dev->channel)
return -ENODEV;
return sprintf(buf, "%d\n",
channel_pending(hv_dev->channel,
vmbus_connection.monitor_pages[1]));
}
static DEVICE_ATTR_RO(client_monitor_pending);
static ssize_t server_monitor_latency_show(struct device *dev,
struct device_attribute *dev_attr,
char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
if (!hv_dev->channel)
return -ENODEV;
return sprintf(buf, "%d\n",
channel_latency(hv_dev->channel,
vmbus_connection.monitor_pages[0]));
}
static DEVICE_ATTR_RO(server_monitor_latency);
static ssize_t client_monitor_latency_show(struct device *dev,
struct device_attribute *dev_attr,
char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
if (!hv_dev->channel)
return -ENODEV;
return sprintf(buf, "%d\n",
channel_latency(hv_dev->channel,
vmbus_connection.monitor_pages[1]));
}
static DEVICE_ATTR_RO(client_monitor_latency);
static ssize_t server_monitor_conn_id_show(struct device *dev,
struct device_attribute *dev_attr,
char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
if (!hv_dev->channel)
return -ENODEV;
return sprintf(buf, "%d\n",
channel_conn_id(hv_dev->channel,
vmbus_connection.monitor_pages[0]));
}
static DEVICE_ATTR_RO(server_monitor_conn_id);
static ssize_t client_monitor_conn_id_show(struct device *dev,
struct device_attribute *dev_attr,
char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
if (!hv_dev->channel)
return -ENODEV;
return sprintf(buf, "%d\n",
channel_conn_id(hv_dev->channel,
vmbus_connection.monitor_pages[1]));
}
static DEVICE_ATTR_RO(client_monitor_conn_id);
static ssize_t out_intr_mask_show(struct device *dev,
struct device_attribute *dev_attr, char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
struct hv_ring_buffer_debug_info outbound;
if (!hv_dev->channel)
return -ENODEV;
hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound);
return sprintf(buf, "%d\n", outbound.current_interrupt_mask);
}
static DEVICE_ATTR_RO(out_intr_mask);
static ssize_t out_read_index_show(struct device *dev,
struct device_attribute *dev_attr, char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
struct hv_ring_buffer_debug_info outbound;
if (!hv_dev->channel)
return -ENODEV;
hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound);
return sprintf(buf, "%d\n", outbound.current_read_index);
}
static DEVICE_ATTR_RO(out_read_index);
static ssize_t out_write_index_show(struct device *dev,
struct device_attribute *dev_attr,
char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
struct hv_ring_buffer_debug_info outbound;
if (!hv_dev->channel)
return -ENODEV;
hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound);
return sprintf(buf, "%d\n", outbound.current_write_index);
}
static DEVICE_ATTR_RO(out_write_index);
static ssize_t out_read_bytes_avail_show(struct device *dev,
struct device_attribute *dev_attr,
char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
struct hv_ring_buffer_debug_info outbound;
if (!hv_dev->channel)
return -ENODEV;
hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound);
return sprintf(buf, "%d\n", outbound.bytes_avail_toread);
}
static DEVICE_ATTR_RO(out_read_bytes_avail);
static ssize_t out_write_bytes_avail_show(struct device *dev,
struct device_attribute *dev_attr,
char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
struct hv_ring_buffer_debug_info outbound;
if (!hv_dev->channel)
return -ENODEV;
hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound);
return sprintf(buf, "%d\n", outbound.bytes_avail_towrite);
}
static DEVICE_ATTR_RO(out_write_bytes_avail);
static ssize_t in_intr_mask_show(struct device *dev,
struct device_attribute *dev_attr, char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
struct hv_ring_buffer_debug_info inbound;
if (!hv_dev->channel)
return -ENODEV;
hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound);
return sprintf(buf, "%d\n", inbound.current_interrupt_mask);
}
static DEVICE_ATTR_RO(in_intr_mask);
static ssize_t in_read_index_show(struct device *dev,
struct device_attribute *dev_attr, char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
struct hv_ring_buffer_debug_info inbound;
if (!hv_dev->channel)
return -ENODEV;
hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound);
return sprintf(buf, "%d\n", inbound.current_read_index);
}
static DEVICE_ATTR_RO(in_read_index);
static ssize_t in_write_index_show(struct device *dev,
struct device_attribute *dev_attr, char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
struct hv_ring_buffer_debug_info inbound;
if (!hv_dev->channel)
return -ENODEV;
hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound);
return sprintf(buf, "%d\n", inbound.current_write_index);
}
static DEVICE_ATTR_RO(in_write_index);
static ssize_t in_read_bytes_avail_show(struct device *dev,
struct device_attribute *dev_attr,
char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
struct hv_ring_buffer_debug_info inbound;
if (!hv_dev->channel)
return -ENODEV;
hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound);
return sprintf(buf, "%d\n", inbound.bytes_avail_toread);
}
static DEVICE_ATTR_RO(in_read_bytes_avail);
static ssize_t in_write_bytes_avail_show(struct device *dev,
struct device_attribute *dev_attr,
char *buf)
{
struct hv_device *hv_dev = device_to_hv_device(dev);
struct hv_ring_buffer_debug_info inbound;
if (!hv_dev->channel)
return -ENODEV;
hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound);
return sprintf(buf, "%d\n", inbound.bytes_avail_towrite);
}
static DEVICE_ATTR_RO(in_write_bytes_avail);
/* Set up per device attributes in /sys/bus/vmbus/devices/<bus device> */
static struct attribute *vmbus_attrs[] = {
&dev_attr_id.attr,
&dev_attr_state.attr,
&dev_attr_monitor_id.attr,
&dev_attr_class_id.attr,
&dev_attr_device_id.attr,
&dev_attr_modalias.attr,
&dev_attr_server_monitor_pending.attr,
&dev_attr_client_monitor_pending.attr,
&dev_attr_server_monitor_latency.attr,
&dev_attr_client_monitor_latency.attr,
&dev_attr_server_monitor_conn_id.attr,
&dev_attr_client_monitor_conn_id.attr,
&dev_attr_out_intr_mask.attr,
&dev_attr_out_read_index.attr,
&dev_attr_out_write_index.attr,
&dev_attr_out_read_bytes_avail.attr,
&dev_attr_out_write_bytes_avail.attr,
&dev_attr_in_intr_mask.attr,
&dev_attr_in_read_index.attr,
&dev_attr_in_write_index.attr,
&dev_attr_in_read_bytes_avail.attr,
&dev_attr_in_write_bytes_avail.attr,
NULL,
};
ATTRIBUTE_GROUPS(vmbus);
/*
* vmbus_uevent - add uevent for our device
*
* This routine is invoked when a device is added or removed on the vmbus to
* generate a uevent to udev in the userspace. The udev will then look at its
* rule and the uevent generated here to load the appropriate driver
*
* The alias string will be of the form vmbus:guid where guid is the string
* representation of the device guid (each byte of the guid will be
* represented with two hex characters.
*/
static int vmbus_uevent(struct device *device, struct kobj_uevent_env *env)
{
struct hv_device *dev = device_to_hv_device(device);
int ret;
char alias_name[VMBUS_ALIAS_LEN + 1];
print_alias_name(dev, alias_name);
ret = add_uevent_var(env, "MODALIAS=vmbus:%s", alias_name);
return ret;
}
static const uuid_le null_guid;
static inline bool is_null_guid(const __u8 *guid)
{
if (memcmp(guid, &null_guid, sizeof(uuid_le)))
return false;
return true;
}
/*
* Return a matching hv_vmbus_device_id pointer.
* If there is no match, return NULL.
*/
static const struct hv_vmbus_device_id *hv_vmbus_get_id(
const struct hv_vmbus_device_id *id,
const __u8 *guid)
{
for (; !is_null_guid(id->guid); id++)
if (!memcmp(&id->guid, guid, sizeof(uuid_le)))
return id;
return NULL;
}
/*
* vmbus_match - Attempt to match the specified device to the specified driver
*/
static int vmbus_match(struct device *device, struct device_driver *driver)
{
struct hv_driver *drv = drv_to_hv_drv(driver);
struct hv_device *hv_dev = device_to_hv_device(device);
if (hv_vmbus_get_id(drv->id_table, hv_dev->dev_type.b))
return 1;
return 0;
}
/*
* vmbus_probe - Add the new vmbus's child device
*/
static int vmbus_probe(struct device *child_device)
{
int ret = 0;
struct hv_driver *drv =
drv_to_hv_drv(child_device->driver);
struct hv_device *dev = device_to_hv_device(child_device);
const struct hv_vmbus_device_id *dev_id;
dev_id = hv_vmbus_get_id(drv->id_table, dev->dev_type.b);
if (drv->probe) {
ret = drv->probe(dev, dev_id);
if (ret != 0)
pr_err("probe failed for device %s (%d)\n",
dev_name(child_device), ret);
} else {
pr_err("probe not set for driver %s\n",
dev_name(child_device));
ret = -ENODEV;
}
return ret;
}
/*
* vmbus_remove - Remove a vmbus device
*/
static int vmbus_remove(struct device *child_device)
{
struct hv_driver *drv;
struct hv_device *dev = device_to_hv_device(child_device);
u32 relid = dev->channel->offermsg.child_relid;
if (child_device->driver) {
drv = drv_to_hv_drv(child_device->driver);
if (drv->remove)
drv->remove(dev);
else {
hv_process_channel_removal(dev->channel, relid);
pr_err("remove not set for driver %s\n",
dev_name(child_device));
}
} else {
/*
* We don't have a driver for this device; deal with the
* rescind message by removing the channel.
*/
hv_process_channel_removal(dev->channel, relid);
}
return 0;
}
/*
* vmbus_shutdown - Shutdown a vmbus device
*/
static void vmbus_shutdown(struct device *child_device)
{
struct hv_driver *drv;
struct hv_device *dev = device_to_hv_device(child_device);
/* The device may not be attached yet */
if (!child_device->driver)
return;
drv = drv_to_hv_drv(child_device->driver);
if (drv->shutdown)
drv->shutdown(dev);
return;
}
/*
* vmbus_device_release - Final callback release of the vmbus child device
*/
static void vmbus_device_release(struct device *device)
{
struct hv_device *hv_dev = device_to_hv_device(device);
kfree(hv_dev);
}
/* The one and only one */
static struct bus_type hv_bus = {
.name = "vmbus",
.match = vmbus_match,
.shutdown = vmbus_shutdown,
.remove = vmbus_remove,
.probe = vmbus_probe,
.uevent = vmbus_uevent,
.dev_groups = vmbus_groups,
};
struct onmessage_work_context {
struct work_struct work;
struct hv_message msg;
};
static void vmbus_onmessage_work(struct work_struct *work)
{
struct onmessage_work_context *ctx;
Drivers: hv: vmbus: teardown hv_vmbus_con workqueue and vmbus_connection pages on shutdown We need to destroy hv_vmbus_con on module shutdown, otherwise the following crash is sometimes observed: [ 76.569845] hv_vmbus: Hyper-V Host Build:9600-6.3-17-0.17039; Vmbus version:3.0 [ 82.598859] BUG: unable to handle kernel paging request at ffffffffa0003480 [ 82.599287] IP: [<ffffffffa0003480>] 0xffffffffa0003480 [ 82.599287] PGD 1f34067 PUD 1f35063 PMD 3f72d067 PTE 0 [ 82.599287] Oops: 0010 [#1] SMP [ 82.599287] Modules linked in: [last unloaded: hv_vmbus] [ 82.599287] CPU: 0 PID: 26 Comm: kworker/0:1 Not tainted 3.19.0-rc5_bug923184+ #488 [ 82.599287] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v1.0 11/26/2012 [ 82.599287] Workqueue: hv_vmbus_con 0xffffffffa0003480 [ 82.599287] task: ffff88007b6ddfa0 ti: ffff88007f8f8000 task.ti: ffff88007f8f8000 [ 82.599287] RIP: 0010:[<ffffffffa0003480>] [<ffffffffa0003480>] 0xffffffffa0003480 [ 82.599287] RSP: 0018:ffff88007f8fbe00 EFLAGS: 00010202 ... To avoid memory leaks we need to free monitor_pages and int_page for vmbus_connection. Implement vmbus_disconnect() function by separating cleanup path from vmbus_connect(). As we use hv_vmbus_con to release channels (see free_channel() in channel_mgmt.c) we need to make sure the work was done before we remove the queue, do that with drain_workqueue(). We also need to avoid handling messages which can (potentially) create new channels, so set vmbus_connection.conn_state = DISCONNECTED at the very beginning of vmbus_exit() and check for that in vmbus_onmessage_work(). Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-02-27 19:25:54 +00:00
/* Do not process messages if we're in DISCONNECTED state */
if (vmbus_connection.conn_state == DISCONNECTED)
return;
ctx = container_of(work, struct onmessage_work_context,
work);
vmbus_onmessage(&ctx->msg);
kfree(ctx);
}
static void hv_process_timer_expiration(struct hv_message *msg, int cpu)
{
struct clock_event_device *dev = hv_context.clk_evt[cpu];
if (dev->event_handler)
dev->event_handler(dev);
msg->header.message_type = HVMSG_NONE;
/*
* Make sure the write to MessageType (ie set to
* HVMSG_NONE) happens before we read the
* MessagePending and EOMing. Otherwise, the EOMing
* will not deliver any more messages since there is
* no empty slot
*/
mb();
if (msg->header.message_flags.msg_pending) {
/*
* This will cause message queue rescan to
* possibly deliver another msg from the
* hypervisor
*/
wrmsrl(HV_X64_MSR_EOM, 0);
}
}
static void vmbus_on_msg_dpc(unsigned long data)
{
int cpu = smp_processor_id();
void *page_addr = hv_context.synic_message_page[cpu];
struct hv_message *msg = (struct hv_message *)page_addr +
VMBUS_MESSAGE_SINT;
struct vmbus_channel_message_header *hdr;
struct vmbus_channel_message_table_entry *entry;
struct onmessage_work_context *ctx;
while (1) {
if (msg->header.message_type == HVMSG_NONE)
/* no msg */
break;
hdr = (struct vmbus_channel_message_header *)msg->u.payload;
if (hdr->msgtype >= CHANNELMSG_COUNT) {
WARN_ONCE(1, "unknown msgtype=%d\n", hdr->msgtype);
goto msg_handled;
}
entry = &channel_message_table[hdr->msgtype];
if (entry->handler_type == VMHT_BLOCKING) {
ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC);
if (ctx == NULL)
continue;
INIT_WORK(&ctx->work, vmbus_onmessage_work);
memcpy(&ctx->msg, msg, sizeof(*msg));
queue_work(vmbus_connection.work_queue, &ctx->work);
} else
entry->message_handler(hdr);
msg_handled:
msg->header.message_type = HVMSG_NONE;
/*
* Make sure the write to MessageType (ie set to
* HVMSG_NONE) happens before we read the
* MessagePending and EOMing. Otherwise, the EOMing
* will not deliver any more messages since there is
* no empty slot
*/
mb();
if (msg->header.message_flags.msg_pending) {
/*
* This will cause message queue rescan to
* possibly deliver another msg from the
* hypervisor
*/
wrmsrl(HV_X64_MSR_EOM, 0);
}
}
}
static void vmbus_isr(void)
{
int cpu = smp_processor_id();
void *page_addr;
struct hv_message *msg;
union hv_synic_event_flags *event;
bool handled = false;
page_addr = hv_context.synic_event_page[cpu];
if (page_addr == NULL)
return;
event = (union hv_synic_event_flags *)page_addr +
VMBUS_MESSAGE_SINT;
/*
* Check for events before checking for messages. This is the order
* in which events and messages are checked in Windows guests on
* Hyper-V, and the Windows team suggested we do the same.
*/
if ((vmbus_proto_version == VERSION_WS2008) ||
(vmbus_proto_version == VERSION_WIN7)) {
/* Since we are a child, we only need to check bit 0 */
if (sync_test_and_clear_bit(0,
(unsigned long *) &event->flags32[0])) {
handled = true;
}
} else {
/*
* Our host is win8 or above. The signaling mechanism
* has changed and we can directly look at the event page.
* If bit n is set then we have an interrup on the channel
* whose id is n.
*/
handled = true;
}
if (handled)
tasklet_schedule(hv_context.event_dpc[cpu]);
page_addr = hv_context.synic_message_page[cpu];
msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT;
/* Check if there are actual msgs to be processed */
if (msg->header.message_type != HVMSG_NONE) {
if (msg->header.message_type == HVMSG_TIMER_EXPIRED)
hv_process_timer_expiration(msg, cpu);
else
tasklet_schedule(&msg_dpc);
}
}
#ifdef CONFIG_HOTPLUG_CPU
static int hyperv_cpu_disable(void)
{
return -ENOSYS;
}
static void hv_cpu_hotplug_quirk(bool vmbus_loaded)
{
static void *previous_cpu_disable;
/*
* Offlining a CPU when running on newer hypervisors (WS2012R2, Win8,
* ...) is not supported at this moment as channel interrupts are
* distributed across all of them.
*/
if ((vmbus_proto_version == VERSION_WS2008) ||
(vmbus_proto_version == VERSION_WIN7))
return;
if (vmbus_loaded) {
previous_cpu_disable = smp_ops.cpu_disable;
smp_ops.cpu_disable = hyperv_cpu_disable;
pr_notice("CPU offlining is not supported by hypervisor\n");
} else if (previous_cpu_disable)
smp_ops.cpu_disable = previous_cpu_disable;
}
#else
static void hv_cpu_hotplug_quirk(bool vmbus_loaded)
{
}
#endif
/*
* vmbus_bus_init -Main vmbus driver initialization routine.
*
* Here, we
* - initialize the vmbus driver context
* - invoke the vmbus hv main init routine
* - get the irq resource
* - retrieve the channel offers
*/
static int vmbus_bus_init(int irq)
{
int ret;
/* Hypervisor initialization...setup hypercall page..etc */
ret = hv_init();
if (ret != 0) {
pr_err("Unable to initialize the hypervisor - 0x%x\n", ret);
return ret;
}
tasklet_init(&msg_dpc, vmbus_on_msg_dpc, 0);
ret = bus_register(&hv_bus);
if (ret)
goto err_cleanup;
hv_setup_vmbus_irq(vmbus_isr);
ret = hv_synic_alloc();
if (ret)
goto err_alloc;
/*
* Initialize the per-cpu interrupt state and
* connect to the host.
*/
on_each_cpu(hv_synic_init, NULL, 1);
ret = vmbus_connect();
if (ret)
goto err_alloc;
hv_cpu_hotplug_quirk(true);
/*
* Only register if the crash MSRs are available
*/
if (ms_hyperv.features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
atomic_notifier_chain_register(&panic_notifier_list,
&hyperv_panic_block);
}
vmbus_request_offers();
return 0;
err_alloc:
hv_synic_free();
hv_remove_vmbus_irq();
bus_unregister(&hv_bus);
err_cleanup:
hv_cleanup();
return ret;
}
/**
* __vmbus_child_driver_register - Register a vmbus's driver
* @drv: Pointer to driver structure you want to register
* @owner: owner module of the drv
* @mod_name: module name string
*
* Registers the given driver with Linux through the 'driver_register()' call
* and sets up the hyper-v vmbus handling for this driver.
* It will return the state of the 'driver_register()' call.
*
*/
int __vmbus_driver_register(struct hv_driver *hv_driver, struct module *owner, const char *mod_name)
{
int ret;
pr_info("registering driver %s\n", hv_driver->name);
ret = vmbus_exists();
if (ret < 0)
return ret;
hv_driver->driver.name = hv_driver->name;
hv_driver->driver.owner = owner;
hv_driver->driver.mod_name = mod_name;
hv_driver->driver.bus = &hv_bus;
ret = driver_register(&hv_driver->driver);
return ret;
}
EXPORT_SYMBOL_GPL(__vmbus_driver_register);
/**
* vmbus_driver_unregister() - Unregister a vmbus's driver
* @drv: Pointer to driver structure you want to un-register
*
* Un-register the given driver that was previous registered with a call to
* vmbus_driver_register()
*/
void vmbus_driver_unregister(struct hv_driver *hv_driver)
{
pr_info("unregistering driver %s\n", hv_driver->name);
if (!vmbus_exists())
driver_unregister(&hv_driver->driver);
}
EXPORT_SYMBOL_GPL(vmbus_driver_unregister);
/*
* vmbus_device_create - Creates and registers a new child device
* on the vmbus.
*/
struct hv_device *vmbus_device_create(const uuid_le *type,
const uuid_le *instance,
struct vmbus_channel *channel)
{
struct hv_device *child_device_obj;
child_device_obj = kzalloc(sizeof(struct hv_device), GFP_KERNEL);
if (!child_device_obj) {
pr_err("Unable to allocate device object for child device\n");
return NULL;
}
child_device_obj->channel = channel;
memcpy(&child_device_obj->dev_type, type, sizeof(uuid_le));
memcpy(&child_device_obj->dev_instance, instance,
sizeof(uuid_le));
return child_device_obj;
}
/*
* vmbus_device_register - Register the child device
*/
int vmbus_device_register(struct hv_device *child_device_obj)
{
int ret = 0;
dev_set_name(&child_device_obj->device, "vmbus_%d",
child_device_obj->channel->id);
child_device_obj->device.bus = &hv_bus;
child_device_obj->device.parent = &hv_acpi_dev->dev;
child_device_obj->device.release = vmbus_device_release;
/*
* Register with the LDM. This will kick off the driver/device
* binding...which will eventually call vmbus_match() and vmbus_probe()
*/
ret = device_register(&child_device_obj->device);
if (ret)
pr_err("Unable to register child device\n");
else
pr_debug("child device %s registered\n",
dev_name(&child_device_obj->device));
return ret;
}
/*
* vmbus_device_unregister - Remove the specified child device
* from the vmbus.
*/
void vmbus_device_unregister(struct hv_device *device_obj)
{
pr_debug("child device %s unregistered\n",
dev_name(&device_obj->device));
/*
* Kick off the process of unregistering the device.
* This will call vmbus_remove() and eventually vmbus_device_release()
*/
device_unregister(&device_obj->device);
}
/*
* VMBUS is an acpi enumerated device. Get the the information we
* need from DSDT.
*/
static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *ctx)
{
switch (res->type) {
case ACPI_RESOURCE_TYPE_IRQ:
irq = res->data.irq.interrupts[0];
break;
case ACPI_RESOURCE_TYPE_ADDRESS64:
hyperv_mmio.start = res->data.address64.address.minimum;
hyperv_mmio.end = res->data.address64.address.maximum;
break;
}
return AE_OK;
}
static int vmbus_acpi_add(struct acpi_device *device)
{
acpi_status result;
int ret_val = -ENODEV;
hv_acpi_dev = device;
result = acpi_walk_resources(device->handle, METHOD_NAME__CRS,
vmbus_walk_resources, NULL);
if (ACPI_FAILURE(result))
goto acpi_walk_err;
/*
* The parent of the vmbus acpi device (Gen2 firmware) is the VMOD that
* has the mmio ranges. Get that.
*/
if (device->parent) {
result = acpi_walk_resources(device->parent->handle,
METHOD_NAME__CRS,
vmbus_walk_resources, NULL);
if (ACPI_FAILURE(result))
goto acpi_walk_err;
if (hyperv_mmio.start && hyperv_mmio.end)
request_resource(&iomem_resource, &hyperv_mmio);
}
ret_val = 0;
acpi_walk_err:
complete(&probe_event);
return ret_val;
}
static int vmbus_acpi_remove(struct acpi_device *device)
{
int ret = 0;
if (hyperv_mmio.start && hyperv_mmio.end)
ret = release_resource(&hyperv_mmio);
return ret;
}
static const struct acpi_device_id vmbus_acpi_device_ids[] = {
{"VMBUS", 0},
{"VMBus", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, vmbus_acpi_device_ids);
static struct acpi_driver vmbus_acpi_driver = {
.name = "vmbus",
.ids = vmbus_acpi_device_ids,
.ops = {
.add = vmbus_acpi_add,
.remove = vmbus_acpi_remove,
},
};
static int __init hv_acpi_init(void)
{
int ret, t;
if (x86_hyper != &x86_hyper_ms_hyperv)
return -ENODEV;
init_completion(&probe_event);
/*
* Get irq resources first.
*/
ret = acpi_bus_register_driver(&vmbus_acpi_driver);
if (ret)
return ret;
t = wait_for_completion_timeout(&probe_event, 5*HZ);
if (t == 0) {
ret = -ETIMEDOUT;
goto cleanup;
}
if (irq <= 0) {
ret = -ENODEV;
goto cleanup;
}
ret = vmbus_bus_init(irq);
if (ret)
goto cleanup;
return 0;
cleanup:
acpi_bus_unregister_driver(&vmbus_acpi_driver);
hv_acpi_dev = NULL;
return ret;
}
static void __exit vmbus_exit(void)
{
drivers: hv: vmbus: Teardown synthetic interrupt controllers on module unload SynIC has to be switched off when we unload the module, otherwise registered memory pages can get corrupted after (as Hyper-V host still writes there) and we see the following crashes for random processes: [ 89.116774] BUG: Bad page map in process sh pte:4989c716 pmd:36f81067 [ 89.159454] addr:0000000000437000 vm_flags:00000875 anon_vma: (null) mapping:ffff88007bba55a0 index:37 [ 89.226146] vma->vm_ops->fault: filemap_fault+0x0/0x410 [ 89.257776] vma->vm_file->f_op->mmap: generic_file_mmap+0x0/0x60 [ 89.297570] CPU: 0 PID: 215 Comm: sh Tainted: G B 3.19.0-rc5_bug923184+ #488 [ 89.353738] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090006 05/23/2012 [ 89.409138] 0000000000000000 000000004e083d7b ffff880036e9fa18 ffffffff81a68d31 [ 89.468724] 0000000000000000 0000000000437000 ffff880036e9fa68 ffffffff811a1e3a [ 89.519233] 000000004989c716 0000000000000037 ffffea0001edc340 0000000000437000 [ 89.575751] Call Trace: [ 89.591060] [<ffffffff81a68d31>] dump_stack+0x45/0x57 [ 89.625164] [<ffffffff811a1e3a>] print_bad_pte+0x1aa/0x250 [ 89.667234] [<ffffffff811a2c95>] vm_normal_page+0x55/0xa0 [ 89.703818] [<ffffffff811a3105>] unmap_page_range+0x425/0x8a0 [ 89.737982] [<ffffffff811a3601>] unmap_single_vma+0x81/0xf0 [ 89.780385] [<ffffffff81184320>] ? lru_deactivate_fn+0x190/0x190 [ 89.820130] [<ffffffff811a4131>] unmap_vmas+0x51/0xa0 [ 89.860168] [<ffffffff811ad12c>] exit_mmap+0xac/0x1a0 [ 89.890588] [<ffffffff810763c3>] mmput+0x63/0x100 [ 89.919205] [<ffffffff811eba48>] flush_old_exec+0x3f8/0x8b0 [ 89.962135] [<ffffffff8123b5bb>] load_elf_binary+0x32b/0x1260 [ 89.998581] [<ffffffff811a14f2>] ? get_user_pages+0x52/0x60 hv_synic_cleanup() function exists but noone calls it now. Do the following: - call hv_synic_cleanup() on each cpu from vmbus_exit(); - write global disable bit through MSR; - use hv_synic_free_cpu() to avoid memory leask and code duplication. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-02-27 19:25:55 +00:00
int cpu;
Drivers: hv: vmbus: teardown hv_vmbus_con workqueue and vmbus_connection pages on shutdown We need to destroy hv_vmbus_con on module shutdown, otherwise the following crash is sometimes observed: [ 76.569845] hv_vmbus: Hyper-V Host Build:9600-6.3-17-0.17039; Vmbus version:3.0 [ 82.598859] BUG: unable to handle kernel paging request at ffffffffa0003480 [ 82.599287] IP: [<ffffffffa0003480>] 0xffffffffa0003480 [ 82.599287] PGD 1f34067 PUD 1f35063 PMD 3f72d067 PTE 0 [ 82.599287] Oops: 0010 [#1] SMP [ 82.599287] Modules linked in: [last unloaded: hv_vmbus] [ 82.599287] CPU: 0 PID: 26 Comm: kworker/0:1 Not tainted 3.19.0-rc5_bug923184+ #488 [ 82.599287] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v1.0 11/26/2012 [ 82.599287] Workqueue: hv_vmbus_con 0xffffffffa0003480 [ 82.599287] task: ffff88007b6ddfa0 ti: ffff88007f8f8000 task.ti: ffff88007f8f8000 [ 82.599287] RIP: 0010:[<ffffffffa0003480>] [<ffffffffa0003480>] 0xffffffffa0003480 [ 82.599287] RSP: 0018:ffff88007f8fbe00 EFLAGS: 00010202 ... To avoid memory leaks we need to free monitor_pages and int_page for vmbus_connection. Implement vmbus_disconnect() function by separating cleanup path from vmbus_connect(). As we use hv_vmbus_con to release channels (see free_channel() in channel_mgmt.c) we need to make sure the work was done before we remove the queue, do that with drain_workqueue(). We also need to avoid handling messages which can (potentially) create new channels, so set vmbus_connection.conn_state = DISCONNECTED at the very beginning of vmbus_exit() and check for that in vmbus_onmessage_work(). Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-02-27 19:25:54 +00:00
vmbus_connection.conn_state = DISCONNECTED;
hv_synic_clockevents_cleanup();
vmbus_disconnect();
hv_remove_vmbus_irq();
tasklet_kill(&msg_dpc);
vmbus_free_channels();
if (ms_hyperv.features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
atomic_notifier_chain_unregister(&panic_notifier_list,
&hyperv_panic_block);
}
bus_unregister(&hv_bus);
hv_cleanup();
for_each_online_cpu(cpu) {
tasklet_kill(hv_context.event_dpc[cpu]);
drivers: hv: vmbus: Teardown synthetic interrupt controllers on module unload SynIC has to be switched off when we unload the module, otherwise registered memory pages can get corrupted after (as Hyper-V host still writes there) and we see the following crashes for random processes: [ 89.116774] BUG: Bad page map in process sh pte:4989c716 pmd:36f81067 [ 89.159454] addr:0000000000437000 vm_flags:00000875 anon_vma: (null) mapping:ffff88007bba55a0 index:37 [ 89.226146] vma->vm_ops->fault: filemap_fault+0x0/0x410 [ 89.257776] vma->vm_file->f_op->mmap: generic_file_mmap+0x0/0x60 [ 89.297570] CPU: 0 PID: 215 Comm: sh Tainted: G B 3.19.0-rc5_bug923184+ #488 [ 89.353738] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090006 05/23/2012 [ 89.409138] 0000000000000000 000000004e083d7b ffff880036e9fa18 ffffffff81a68d31 [ 89.468724] 0000000000000000 0000000000437000 ffff880036e9fa68 ffffffff811a1e3a [ 89.519233] 000000004989c716 0000000000000037 ffffea0001edc340 0000000000437000 [ 89.575751] Call Trace: [ 89.591060] [<ffffffff81a68d31>] dump_stack+0x45/0x57 [ 89.625164] [<ffffffff811a1e3a>] print_bad_pte+0x1aa/0x250 [ 89.667234] [<ffffffff811a2c95>] vm_normal_page+0x55/0xa0 [ 89.703818] [<ffffffff811a3105>] unmap_page_range+0x425/0x8a0 [ 89.737982] [<ffffffff811a3601>] unmap_single_vma+0x81/0xf0 [ 89.780385] [<ffffffff81184320>] ? lru_deactivate_fn+0x190/0x190 [ 89.820130] [<ffffffff811a4131>] unmap_vmas+0x51/0xa0 [ 89.860168] [<ffffffff811ad12c>] exit_mmap+0xac/0x1a0 [ 89.890588] [<ffffffff810763c3>] mmput+0x63/0x100 [ 89.919205] [<ffffffff811eba48>] flush_old_exec+0x3f8/0x8b0 [ 89.962135] [<ffffffff8123b5bb>] load_elf_binary+0x32b/0x1260 [ 89.998581] [<ffffffff811a14f2>] ? get_user_pages+0x52/0x60 hv_synic_cleanup() function exists but noone calls it now. Do the following: - call hv_synic_cleanup() on each cpu from vmbus_exit(); - write global disable bit through MSR; - use hv_synic_free_cpu() to avoid memory leask and code duplication. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-02-27 19:25:55 +00:00
smp_call_function_single(cpu, hv_synic_cleanup, NULL, 1);
}
acpi_bus_unregister_driver(&vmbus_acpi_driver);
hv_cpu_hotplug_quirk(false);
}
MODULE_LICENSE("GPL");
subsys_initcall(hv_acpi_init);
module_exit(vmbus_exit);