diff options
| author | Haiyang Zhang <haiyangz@microsoft.com> | 2018-03-05 06:17:17 +0100 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2018-03-06 18:57:16 +0100 |
| commit | ce767047b1b731a1899a528338644f2bfdab8b36 (patch) | |
| tree | 09ea79b28b69ff1b4ed6771ae168fe972808993c | |
| parent | tools: hv: include string.h in hv_fcopy_daemon (diff) | |
| download | linux-ce767047b1b731a1899a528338644f2bfdab8b36.tar.xz linux-ce767047b1b731a1899a528338644f2bfdab8b36.zip | |
hv_vmbus: Correct the stale comments regarding cpu affinity
The comments doesn't match what the current code does, also have a
typo. This patch corrects them.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
| -rw-r--r-- | drivers/hv/channel_mgmt.c | 6 | ||||
| -rw-r--r-- | include/linux/hyperv.h | 2 |
2 files changed, 3 insertions, 5 deletions
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index c21020b69114..c6d9d19bc04e 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -596,10 +596,8 @@ static int next_numa_node_id; /* * Starting with Win8, we can statically distribute the incoming * channel interrupt load by binding a channel to VCPU. - * We do this in a hierarchical fashion: - * First distribute the primary channels across available NUMA nodes - * and then distribute the subchannels amongst the CPUs in the NUMA - * node assigned to the primary channel. + * We distribute the interrupt loads to one or more NUMA nodes based on + * the channel's affinity_policy. * * For pre-win8 hosts or non-performance critical channels we assign the * first CPU in the first NUMA node. diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 93bd6fcd6e62..2048f3c3b68a 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -844,7 +844,7 @@ struct vmbus_channel { /* * NUMA distribution policy: - * We support teo policies: + * We support two policies: * 1) Balanced: Here all performance critical channels are * distributed evenly amongst all the NUMA nodes. * This policy will be the default policy. |