linux/drivers/hv/connection.c

546 lines
14 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
*
* Copyright (c) 2009, Microsoft Corporation.
*
* 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/module.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 11:04:11 +03:00
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/hyperv.h>
#include <linux/export.h>
#include <linux/io.h>
#include <linux/set_memory.h>
#include <asm/mshyperv.h>
#include "hyperv_vmbus.h"
struct vmbus_connection vmbus_connection = {
.conn_state = DISCONNECTED,
.unload_event = COMPLETION_INITIALIZER(
vmbus_connection.unload_event),
.next_gpadl_handle = ATOMIC_INIT(0xE1E10),
.ready_for_suspend_event = COMPLETION_INITIALIZER(
vmbus_connection.ready_for_suspend_event),
.ready_for_resume_event = COMPLETION_INITIALIZER(
vmbus_connection.ready_for_resume_event),
};
EXPORT_SYMBOL_GPL(vmbus_connection);
/*
* Negotiated protocol version with the host.
*/
__u32 vmbus_proto_version;
EXPORT_SYMBOL_GPL(vmbus_proto_version);
/*
* Table of VMBus versions listed from newest to oldest.
* VERSION_WIN7 and VERSION_WS2008 are no longer supported in
* Linux guests and are not listed.
*/
static __u32 vmbus_versions[] = {
VERSION_WIN10_V5_3,
VERSION_WIN10_V5_2,
VERSION_WIN10_V5_1,
VERSION_WIN10_V5,
VERSION_WIN10_V4_1,
VERSION_WIN10,
VERSION_WIN8_1,
VERSION_WIN8
};
/*
* Maximal VMBus protocol version guests can negotiate. Useful to cap the
* VMBus version for testing and debugging purpose.
*/
static uint max_version = VERSION_WIN10_V5_3;
module_param(max_version, uint, S_IRUGO);
MODULE_PARM_DESC(max_version,
"Maximal VMBus protocol version which can be negotiated");
int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
{
int ret = 0;
struct vmbus_channel_initiate_contact *msg;
unsigned long flags;
init_completion(&msginfo->waitevent);
msg = (struct vmbus_channel_initiate_contact *)msginfo->msg;
2018-05-12 12:30:33 +03:00
memset(msg, 0, sizeof(*msg));
msg->header.msgtype = CHANNELMSG_INITIATE_CONTACT;
msg->vmbus_version_requested = version;
2018-05-12 12:30:33 +03:00
/*
* VMBus protocol 5.0 (VERSION_WIN10_V5) and higher require that we must
* use VMBUS_MESSAGE_CONNECTION_ID_4 for the Initiate Contact Message,
2018-05-12 12:30:33 +03:00
* and for subsequent messages, we must use the Message Connection ID
* field in the host-returned Version Response Message. And, with
* VERSION_WIN10_V5 and higher, we don't use msg->interrupt_page, but we
* tell the host explicitly that we still use VMBUS_MESSAGE_SINT(2) for
2018-05-12 12:30:33 +03:00
* 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 = vmbus_connection.monitor_pages_pa[0];
msg->monitor_page2 = vmbus_connection.monitor_pages_pa[1];
msg->target_vcpu = hv_cpu_number_to_vp_number(VMBUS_CONNECT_CPU);
/*
* 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;
2018-05-12 12:30:33 +03:00
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)
{
struct vmbus_channel_msginfo *msginfo = NULL;
int i, ret = 0;
__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.rescind_work_queue =
create_workqueue("hv_vmbus_rescind");
if (!vmbus_connection.rescind_work_queue) {
ret = -ENOMEM;
goto cleanup;
}
vmbus_connection.ignore_any_offer_msg = false;
Drivers: hv: vmbus: Offload the handling of channels to two workqueues vmbus_process_offer() mustn't call channel->sc_creation_callback() directly for sub-channels, because sc_creation_callback() -> vmbus_open() may never get the host's response to the OPEN_CHANNEL message (the host may rescind a channel at any time, e.g. in the case of hot removing a NIC), and vmbus_onoffer_rescind() may not wake up the vmbus_open() as it's blocked due to a non-zero vmbus_connection.offer_in_progress, and finally we have a deadlock. The above is also true for primary channels, if the related device drivers use sync probing mode by default. And, usually the handling of primary channels and sub-channels can depend on each other, so we should offload them to different workqueues to avoid possible deadlock, e.g. in sync-probing mode, NIC1's netvsc_subchan_work() can race with NIC2's netvsc_probe() -> rtnl_lock(), and causes deadlock: the former gets the rtnl_lock and waits for all the sub-channels to appear, but the latter can't get the rtnl_lock and this blocks the handling of sub-channels. The patch can fix the multiple-NIC deadlock described above for v3.x kernels (e.g. RHEL 7.x) which don't support async-probing of devices, and v4.4, v4.9, v4.14 and v4.18 which support async-probing but don't enable async-probing for Hyper-V drivers (yet). The patch can also fix the hang issue in sub-channel's handling described above for all versions of kernels, including v4.19 and v4.20-rc4. So actually the patch should be applied to all the existing kernels, not only the kernels that have 8195b1396ec8. Fixes: 8195b1396ec8 ("hv_netvsc: fix deadlock on hotplug") Cc: stable@vger.kernel.org Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-03 03:54:35 +03:00
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 *)hv_alloc_hyperv_zeroed_page();
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 +
(HV_HYP_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 *)hv_alloc_hyperv_zeroed_page();
vmbus_connection.monitor_pages[1] = (void *)hv_alloc_hyperv_zeroed_page();
if ((vmbus_connection.monitor_pages[0] == NULL) ||
(vmbus_connection.monitor_pages[1] == NULL)) {
ret = -ENOMEM;
goto cleanup;
}
vmbus_connection.monitor_pages_original[0]
= vmbus_connection.monitor_pages[0];
vmbus_connection.monitor_pages_original[1]
= vmbus_connection.monitor_pages[1];
vmbus_connection.monitor_pages_pa[0]
= virt_to_phys(vmbus_connection.monitor_pages[0]);
vmbus_connection.monitor_pages_pa[1]
= virt_to_phys(vmbus_connection.monitor_pages[1]);
if (hv_is_isolation_supported()) {
ret = set_memory_decrypted((unsigned long)
vmbus_connection.monitor_pages[0],
1);
ret |= set_memory_decrypted((unsigned long)
vmbus_connection.monitor_pages[1],
1);
if (ret)
goto cleanup;
/*
* Isolation VM with AMD SNP needs to access monitor page via
* address space above shared gpa boundary.
*/
if (hv_isolation_type_snp()) {
vmbus_connection.monitor_pages_pa[0] +=
ms_hyperv.shared_gpa_boundary;
vmbus_connection.monitor_pages_pa[1] +=
ms_hyperv.shared_gpa_boundary;
vmbus_connection.monitor_pages[0]
= memremap(vmbus_connection.monitor_pages_pa[0],
HV_HYP_PAGE_SIZE,
MEMREMAP_WB);
if (!vmbus_connection.monitor_pages[0]) {
ret = -ENOMEM;
goto cleanup;
}
vmbus_connection.monitor_pages[1]
= memremap(vmbus_connection.monitor_pages_pa[1],
HV_HYP_PAGE_SIZE,
MEMREMAP_WB);
if (!vmbus_connection.monitor_pages[1]) {
ret = -ENOMEM;
goto cleanup;
}
}
/*
* Set memory host visibility hvcall smears memory
* and so zero monitor pages here.
*/
memset(vmbus_connection.monitor_pages[0], 0x00,
HV_HYP_PAGE_SIZE);
memset(vmbus_connection.monitor_pages[1], 0x00,
HV_HYP_PAGE_SIZE);
}
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.
*/
for (i = 0; ; i++) {
if (i == ARRAY_SIZE(vmbus_versions)) {
ret = -EDOM;
goto cleanup;
}
version = vmbus_versions[i];
if (version > max_version)
continue;
ret = vmbus_negotiate_version(msginfo, version);
if (ret == -ETIMEDOUT)
goto cleanup;
if (vmbus_connection.conn_state == CONNECTED)
break;
}
if (hv_is_isolation_supported() && version < VERSION_WIN10_V5_2) {
pr_err("Invalid VMBus version %d.%d (expected >= %d.%d) from the host supporting isolation\n",
version >> 16, version & 0xFFFF, VERSION_WIN10_V5_2 >> 16, VERSION_WIN10_V5_2 & 0xFFFF);
ret = -EINVAL;
goto cleanup;
}
vmbus_proto_version = version;
pr_info("Vmbus version:%d.%d\n",
version >> 16, version & 0xFFFF);
Drivers: hv: vmbus: Replace the per-CPU channel lists with a global array of channels When Hyper-V sends an interrupt to the guest, the guest has to figure out which channel the interrupt is associated with. Hyper-V sets a bit in a memory page that is shared with the guest, indicating a particular "relid" that the interrupt is associated with. The current Linux code then uses a set of per-CPU linked lists to map a given "relid" to a pointer to a channel structure. This design introduces a synchronization problem if the CPU that Hyper-V will interrupt for a certain channel is changed. If the interrupt comes on the "old CPU" and the channel was already moved to the per-CPU list of the "new CPU", then the relid -> channel mapping will fail and the interrupt is dropped. Similarly, if the interrupt comes on the new CPU but the channel was not moved to the per-CPU list of the new CPU, then the mapping will fail and the interrupt is dropped. Relids are integers ranging from 0 to 2047. The mapping from relids to channel structures can be done by setting up an array with 2048 entries, each entry being a pointer to a channel structure (hence total size ~16K bytes, which is not a problem). The array is global, so there are no per-CPU linked lists to update. The array can be searched and updated by loading from/storing to the array at the specified index. With no per-CPU data structures, the above mentioned synchronization problem is avoided and the relid2channel() function gets simpler. Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Link: https://lore.kernel.org/r/20200406001514.19876-4-parri.andrea@gmail.com Reviewed-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-06 03:15:06 +03:00
vmbus_connection.channels = kcalloc(MAX_CHANNEL_RELIDS,
sizeof(struct vmbus_channel *),
GFP_KERNEL);
if (vmbus_connection.channels == NULL) {
ret = -ENOMEM;
goto cleanup;
}
kfree(msginfo);
return 0;
cleanup:
pr_err("Unable to connect to host\n");
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 22:25:54 +03:00
vmbus_connection.conn_state = DISCONNECTED;
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 22:25:54 +03:00
vmbus_disconnect();
kfree(msginfo);
return ret;
}
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 22:25:54 +03:00
void vmbus_disconnect(void)
{
/*
* First send the unload request to the host.
*/
vmbus_initiate_unload(false);
Drivers: hv: vmbus: Offload the handling of channels to two workqueues vmbus_process_offer() mustn't call channel->sc_creation_callback() directly for sub-channels, because sc_creation_callback() -> vmbus_open() may never get the host's response to the OPEN_CHANNEL message (the host may rescind a channel at any time, e.g. in the case of hot removing a NIC), and vmbus_onoffer_rescind() may not wake up the vmbus_open() as it's blocked due to a non-zero vmbus_connection.offer_in_progress, and finally we have a deadlock. The above is also true for primary channels, if the related device drivers use sync probing mode by default. And, usually the handling of primary channels and sub-channels can depend on each other, so we should offload them to different workqueues to avoid possible deadlock, e.g. in sync-probing mode, NIC1's netvsc_subchan_work() can race with NIC2's netvsc_probe() -> rtnl_lock(), and causes deadlock: the former gets the rtnl_lock and waits for all the sub-channels to appear, but the latter can't get the rtnl_lock and this blocks the handling of sub-channels. The patch can fix the multiple-NIC deadlock described above for v3.x kernels (e.g. RHEL 7.x) which don't support async-probing of devices, and v4.4, v4.9, v4.14 and v4.18 which support async-probing but don't enable async-probing for Hyper-V drivers (yet). The patch can also fix the hang issue in sub-channel's handling described above for all versions of kernels, including v4.19 and v4.20-rc4. So actually the patch should be applied to all the existing kernels, not only the kernels that have 8195b1396ec8. Fixes: 8195b1396ec8 ("hv_netvsc: fix deadlock on hotplug") Cc: stable@vger.kernel.org Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-03 03:54:35 +03:00
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.rescind_work_queue)
destroy_workqueue(vmbus_connection.rescind_work_queue);
Drivers: hv: vmbus: Offload the handling of channels to two workqueues vmbus_process_offer() mustn't call channel->sc_creation_callback() directly for sub-channels, because sc_creation_callback() -> vmbus_open() may never get the host's response to the OPEN_CHANNEL message (the host may rescind a channel at any time, e.g. in the case of hot removing a NIC), and vmbus_onoffer_rescind() may not wake up the vmbus_open() as it's blocked due to a non-zero vmbus_connection.offer_in_progress, and finally we have a deadlock. The above is also true for primary channels, if the related device drivers use sync probing mode by default. And, usually the handling of primary channels and sub-channels can depend on each other, so we should offload them to different workqueues to avoid possible deadlock, e.g. in sync-probing mode, NIC1's netvsc_subchan_work() can race with NIC2's netvsc_probe() -> rtnl_lock(), and causes deadlock: the former gets the rtnl_lock and waits for all the sub-channels to appear, but the latter can't get the rtnl_lock and this blocks the handling of sub-channels. The patch can fix the multiple-NIC deadlock described above for v3.x kernels (e.g. RHEL 7.x) which don't support async-probing of devices, and v4.4, v4.9, v4.14 and v4.18 which support async-probing but don't enable async-probing for Hyper-V drivers (yet). The patch can also fix the hang issue in sub-channel's handling described above for all versions of kernels, including v4.19 and v4.20-rc4. So actually the patch should be applied to all the existing kernels, not only the kernels that have 8195b1396ec8. Fixes: 8195b1396ec8 ("hv_netvsc: fix deadlock on hotplug") Cc: stable@vger.kernel.org Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-03 03:54:35 +03:00
if (vmbus_connection.work_queue)
destroy_workqueue(vmbus_connection.work_queue);
if (vmbus_connection.int_page) {
hv_free_hyperv_page((unsigned long)vmbus_connection.int_page);
vmbus_connection.int_page = NULL;
}
if (hv_is_isolation_supported()) {
/*
* memunmap() checks input address is ioremap address or not
* inside. It doesn't unmap any thing in the non-SNP CVM and
* so not check CVM type here.
*/
memunmap(vmbus_connection.monitor_pages[0]);
memunmap(vmbus_connection.monitor_pages[1]);
set_memory_encrypted((unsigned long)
vmbus_connection.monitor_pages_original[0],
1);
set_memory_encrypted((unsigned long)
vmbus_connection.monitor_pages_original[1],
1);
}
hv_free_hyperv_page((unsigned long)
vmbus_connection.monitor_pages_original[0]);
hv_free_hyperv_page((unsigned long)
vmbus_connection.monitor_pages_original[1]);
vmbus_connection.monitor_pages_original[0] =
vmbus_connection.monitor_pages[0] = NULL;
vmbus_connection.monitor_pages_original[1] =
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)
{
Drivers: hv: vmbus: Replace the per-CPU channel lists with a global array of channels When Hyper-V sends an interrupt to the guest, the guest has to figure out which channel the interrupt is associated with. Hyper-V sets a bit in a memory page that is shared with the guest, indicating a particular "relid" that the interrupt is associated with. The current Linux code then uses a set of per-CPU linked lists to map a given "relid" to a pointer to a channel structure. This design introduces a synchronization problem if the CPU that Hyper-V will interrupt for a certain channel is changed. If the interrupt comes on the "old CPU" and the channel was already moved to the per-CPU list of the "new CPU", then the relid -> channel mapping will fail and the interrupt is dropped. Similarly, if the interrupt comes on the new CPU but the channel was not moved to the per-CPU list of the new CPU, then the mapping will fail and the interrupt is dropped. Relids are integers ranging from 0 to 2047. The mapping from relids to channel structures can be done by setting up an array with 2048 entries, each entry being a pointer to a channel structure (hence total size ~16K bytes, which is not a problem). The array is global, so there are no per-CPU linked lists to update. The array can be searched and updated by loading from/storing to the array at the specified index. With no per-CPU data structures, the above mentioned synchronization problem is avoided and the relid2channel() function gets simpler. Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Link: https://lore.kernel.org/r/20200406001514.19876-4-parri.andrea@gmail.com Reviewed-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-06 03:15:06 +03:00
if (WARN_ON(relid >= MAX_CHANNEL_RELIDS))
return NULL;
return READ_ONCE(vmbus_connection.channels[relid]);
}
/*
* 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;
void (*callback_fn)(void *context);
trace_vmbus_on_event(channel);
hv_debug_delay_test(channel, INTERRUPT_DELAY);
/* 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))
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);
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)
{
2018-05-12 12:30:33 +03:00
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;
2018-05-12 12:30:33 +03:00
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:
2018-05-12 12:30:33 +03:00
/*
* See vmbus_negotiate_version(): VMBus protocol 5.0
* and higher require that we must use
2018-05-12 12:30:33 +03:00
* 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;
2018-05-12 12:30:33 +03:00
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;
if (hv_isolation_type_snp())
hv_ghcb_hypercall(HVCALL_SIGNAL_EVENT, &channel->sig_event,
NULL, sizeof(channel->sig_event));
else
hv_do_fast_hypercall8(HVCALL_SIGNAL_EVENT, channel->sig_event);
}
EXPORT_SYMBOL_GPL(vmbus_set_event);