summaryrefslogtreecommitdiff
path: root/drivers/hv
diff options
context:
space:
mode:
authorAndrea Parri (Microsoft) <parri.andrea@gmail.com>2020-04-06 02:15:13 +0200
committerWei Liu <wei.liu@kernel.org>2020-04-23 13:17:12 +0000
commit7527810573436f00e582d3d5ef2eb3c027c98d7d (patch)
tree997d4cf7717c0aa82de7649cd10f0de9fd99bb7f /drivers/hv
parentd570aec0f2154e1bfba14ffd0df164a185e363b5 (diff)
Drivers: hv: vmbus: Introduce the CHANNELMSG_MODIFYCHANNEL message type
VMBus version 4.1 and later support the CHANNELMSG_MODIFYCHANNEL(22) message type which can be used to request Hyper-V to change the vCPU that a channel will interrupt. Introduce the CHANNELMSG_MODIFYCHANNEL message type, and define the vmbus_send_modifychannel() function to send CHANNELMSG_MODIFYCHANNEL requests to the host via a hypercall. The function is then used to define a sysfs "store" operation, which allows to change the (v)CPU the channel will interrupt by using the sysfs interface. The feature can be used for load balancing or other purposes. One interesting catch here is that Hyper-V can *not* currently ACK CHANNELMSG_MODIFYCHANNEL messages with the promise that (after the ACK is sent) the channel won't send any more interrupts to the "old" CPU. The peculiarity of the CHANNELMSG_MODIFYCHANNEL messages is problematic if the user want to take a CPU offline, since we don't want to take a CPU offline (and, potentially, "lose" channel interrupts on such CPU) if the host is still processing a CHANNELMSG_MODIFYCHANNEL message associated to that CPU. It is worth mentioning, however, that we have been unable to observe the above mentioned "race": in all our tests, CHANNELMSG_MODIFYCHANNEL requests appeared *as if* they were processed synchronously by the host. Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Link: https://lore.kernel.org/r/20200406001514.19876-11-parri.andrea@gmail.com Reviewed-by: Michael Kelley <mikelley@microsoft.com> [ wei: fix conflict in channel_mgmt.c ] Signed-off-by: Wei Liu <wei.liu@kernel.org>
Diffstat (limited to 'drivers/hv')
-rw-r--r--drivers/hv/channel.c28
-rw-r--r--drivers/hv/channel_mgmt.c2
-rw-r--r--drivers/hv/hv_trace.h19
-rw-r--r--drivers/hv/vmbus_drv.c108
4 files changed, 154 insertions, 3 deletions
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 132e476f87b2..90070b337c10 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -290,6 +290,34 @@ int vmbus_send_tl_connect_request(const guid_t *shv_guest_servie_id,
EXPORT_SYMBOL_GPL(vmbus_send_tl_connect_request);
/*
+ * Set/change the vCPU (@target_vp) the channel (@child_relid) will interrupt.
+ *
+ * CHANNELMSG_MODIFYCHANNEL messages are aynchronous. Also, Hyper-V does not
+ * ACK such messages. IOW we can't know when the host will stop interrupting
+ * the "old" vCPU and start interrupting the "new" vCPU for the given channel.
+ *
+ * The CHANNELMSG_MODIFYCHANNEL message type is supported since VMBus version
+ * VERSION_WIN10_V4_1.
+ */
+int vmbus_send_modifychannel(u32 child_relid, u32 target_vp)
+{
+ struct vmbus_channel_modifychannel conn_msg;
+ int ret;
+
+ memset(&conn_msg, 0, sizeof(conn_msg));
+ conn_msg.header.msgtype = CHANNELMSG_MODIFYCHANNEL;
+ conn_msg.child_relid = child_relid;
+ conn_msg.target_vp = target_vp;
+
+ ret = vmbus_post_msg(&conn_msg, sizeof(conn_msg), true);
+
+ trace_vmbus_send_modifychannel(&conn_msg, ret);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(vmbus_send_modifychannel);
+
+/*
* create_gpadl_header - Creates a gpadl for the specified buffer
*/
static int create_gpadl_header(void *kbuffer, u32 size,
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 2db3823f0e59..ffd7fffa5f83 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -1383,7 +1383,7 @@ channel_message_table[CHANNELMSG_COUNT] = {
{ CHANNELMSG_19, 0, NULL, 0},
{ CHANNELMSG_20, 0, NULL, 0},
{ CHANNELMSG_TL_CONNECT_REQUEST, 0, NULL, 0},
- { CHANNELMSG_22, 0, NULL, 0},
+ { CHANNELMSG_MODIFYCHANNEL, 0, NULL, 0},
{ CHANNELMSG_TL_CONNECT_RESULT, 0, NULL, 0},
};
diff --git a/drivers/hv/hv_trace.h b/drivers/hv/hv_trace.h
index e70783e33680..a43bc76c2d5d 100644
--- a/drivers/hv/hv_trace.h
+++ b/drivers/hv/hv_trace.h
@@ -296,6 +296,25 @@ TRACE_EVENT(vmbus_send_tl_connect_request,
)
);
+TRACE_EVENT(vmbus_send_modifychannel,
+ TP_PROTO(const struct vmbus_channel_modifychannel *msg,
+ int ret),
+ TP_ARGS(msg, ret),
+ TP_STRUCT__entry(
+ __field(u32, child_relid)
+ __field(u32, target_vp)
+ __field(int, ret)
+ ),
+ TP_fast_assign(
+ __entry->child_relid = msg->child_relid;
+ __entry->target_vp = msg->target_vp;
+ __entry->ret = ret;
+ ),
+ TP_printk("binding child_relid 0x%x to target_vp 0x%x, ret %d",
+ __entry->child_relid, __entry->target_vp, __entry->ret
+ )
+ );
+
DECLARE_EVENT_CLASS(vmbus_channel,
TP_PROTO(const struct vmbus_channel *channel),
TP_ARGS(channel),
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 0f7dfa507a40..5d24b25fb5aa 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1606,8 +1606,24 @@ static ssize_t vmbus_chan_attr_show(struct kobject *kobj,
return attribute->show(chan, buf);
}
+static ssize_t vmbus_chan_attr_store(struct kobject *kobj,
+ struct attribute *attr, const char *buf,
+ size_t count)
+{
+ const struct vmbus_chan_attribute *attribute
+ = container_of(attr, struct vmbus_chan_attribute, attr);
+ struct vmbus_channel *chan
+ = container_of(kobj, struct vmbus_channel, kobj);
+
+ if (!attribute->store)
+ return -EIO;
+
+ return attribute->store(chan, buf, count);
+}
+
static const struct sysfs_ops vmbus_chan_sysfs_ops = {
.show = vmbus_chan_attr_show,
+ .store = vmbus_chan_attr_store,
};
static ssize_t out_mask_show(struct vmbus_channel *channel, char *buf)
@@ -1678,11 +1694,99 @@ static ssize_t write_avail_show(struct vmbus_channel *channel, char *buf)
}
static VMBUS_CHAN_ATTR_RO(write_avail);
-static ssize_t show_target_cpu(struct vmbus_channel *channel, char *buf)
+static ssize_t target_cpu_show(struct vmbus_channel *channel, char *buf)
{
return sprintf(buf, "%u\n", channel->target_cpu);
}
-static VMBUS_CHAN_ATTR(cpu, S_IRUGO, show_target_cpu, NULL);
+static ssize_t target_cpu_store(struct vmbus_channel *channel,
+ const char *buf, size_t count)
+{
+ ssize_t ret = count;
+ u32 target_cpu;
+
+ if (vmbus_proto_version < VERSION_WIN10_V4_1)
+ return -EIO;
+
+ if (sscanf(buf, "%uu", &target_cpu) != 1)
+ return -EIO;
+
+ /* Validate target_cpu for the cpumask_test_cpu() operation below. */
+ if (target_cpu >= nr_cpumask_bits)
+ return -EINVAL;
+
+ /* No CPUs should come up or down during this. */
+ cpus_read_lock();
+
+ if (!cpumask_test_cpu(target_cpu, cpu_online_mask)) {
+ cpus_read_unlock();
+ return -EINVAL;
+ }
+
+ /*
+ * Synchronizes target_cpu_store() and channel closure:
+ *
+ * { Initially: state = CHANNEL_OPENED }
+ *
+ * CPU1 CPU2
+ *
+ * [target_cpu_store()] [vmbus_disconnect_ring()]
+ *
+ * LOCK channel_mutex LOCK channel_mutex
+ * LOAD r1 = state LOAD r2 = state
+ * IF (r1 == CHANNEL_OPENED) IF (r2 == CHANNEL_OPENED)
+ * SEND MODIFYCHANNEL STORE state = CHANNEL_OPEN
+ * [...] SEND CLOSECHANNEL
+ * UNLOCK channel_mutex UNLOCK channel_mutex
+ *
+ * Forbids: r1 == r2 == CHANNEL_OPENED (i.e., CPU1's LOCK precedes
+ * CPU2's LOCK) && CPU2's SEND precedes CPU1's SEND
+ *
+ * Note. The host processes the channel messages "sequentially", in
+ * the order in which they are received on a per-partition basis.
+ */
+ mutex_lock(&vmbus_connection.channel_mutex);
+
+ /*
+ * Hyper-V will ignore MODIFYCHANNEL messages for "non-open" channels;
+ * avoid sending the message and fail here for such channels.
+ */
+ if (channel->state != CHANNEL_OPENED_STATE) {
+ ret = -EIO;
+ goto cpu_store_unlock;
+ }
+
+ if (channel->target_cpu == target_cpu)
+ goto cpu_store_unlock;
+
+ if (vmbus_send_modifychannel(channel->offermsg.child_relid,
+ hv_cpu_number_to_vp_number(target_cpu))) {
+ ret = -EIO;
+ goto cpu_store_unlock;
+ }
+
+ /*
+ * Warning. At this point, there is *no* guarantee that the host will
+ * have successfully processed the vmbus_send_modifychannel() request.
+ * See the header comment of vmbus_send_modifychannel() for more info.
+ *
+ * Lags in the processing of the above vmbus_send_modifychannel() can
+ * result in missed interrupts if the "old" target CPU is taken offline
+ * before Hyper-V starts sending interrupts to the "new" target CPU.
+ * But apart from this offlining scenario, the code tolerates such
+ * lags. It will function correctly even if a channel interrupt comes
+ * in on a CPU that is different from the channel target_cpu value.
+ */
+
+ channel->target_cpu = target_cpu;
+ channel->target_vp = hv_cpu_number_to_vp_number(target_cpu);
+ channel->numa_node = cpu_to_node(target_cpu);
+
+cpu_store_unlock:
+ mutex_unlock(&vmbus_connection.channel_mutex);
+ cpus_read_unlock();
+ return ret;
+}
+static VMBUS_CHAN_ATTR(cpu, 0644, target_cpu_show, target_cpu_store);
static ssize_t channel_pending_show(struct vmbus_channel *channel,
char *buf)