Drivers: hv: vmbus: Implement per-CPU mapping of relid to channel

Currently the mapping of the relID to channel is done under the protection of a
single spin lock. Starting with ws2012, each channel is bound to a specific VCPU
in the guest. Use this binding to eliminate the spin lock by setting up
per-cpu state for mapping relId to the channel.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
K. Y. Srinivasan
2014-04-08 18:45:54 -07:00
committed by Greg Kroah-Hartman
parent d3ba720dd5
commit 3a28fa35d6
5 changed files with 75 additions and 2 deletions

View File

@@ -234,6 +234,28 @@ cleanup:
return ret;
}
/*
* Map the given relid to the corresponding channel based on the
* per-cpu list of channels that have been affinitized to this CPU.
* This will be used in the channel callback path as we can do this
* mapping in a lock-free fashion.
*/
static struct vmbus_channel *pcpu_relid2channel(u32 relid)
{
struct vmbus_channel *channel;
struct vmbus_channel *found_channel = NULL;
int cpu = smp_processor_id();
struct list_head *pcpu_head = &hv_context.percpu_list[cpu];
list_for_each_entry(channel, pcpu_head, percpu_list) {
if (channel->offermsg.child_relid == relid) {
found_channel = channel;
break;
}
}
return found_channel;
}
/*
* relid2channel - Get the channel object given its
@@ -285,7 +307,7 @@ static void process_chn_event(u32 relid)
* Find the channel based on this relid and invokes the
* channel callback to process the event
*/
channel = relid2channel(relid);
channel = pcpu_relid2channel(relid);
if (!channel) {
pr_err("channel not found for relid - %u\n", relid);