| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20200325225505.23998-9-parri.andrea@gmail.com>
Date: Wed, 25 Mar 2020 23:55:02 +0100
From: "Andrea Parri (Microsoft)" <parri.andrea@...il.com>
To: linux-kernel@...r.kernel.org
Cc: "K . Y . Srinivasan" <kys@...rosoft.com>,
Haiyang Zhang <haiyangz@...rosoft.com>,
Stephen Hemminger <sthemmin@...rosoft.com>,
Wei Liu <wei.liu@...nel.org>, linux-hyperv@...r.kernel.org,
Michael Kelley <mikelley@...rosoft.com>,
Dexuan Cui <decui@...rosoft.com>,
Boqun Feng <boqun.feng@...il.com>,
Vitaly Kuznetsov <vkuznets@...hat.com>,
"Andrea Parri (Microsoft)" <parri.andrea@...il.com>
Subject: [RFC PATCH 08/11] Drivers: hv: vmbus: Remove the unused HV_LOCALIZED channel affinity logic
The logic is unused since commit 509879bdb30b8 ("Drivers: hv: Introduce
a policy for controlling channel affinity").
This logic assumes that a channel target_cpu doesn't change during the
lifetime of a channel, but this assumption is incompatible with the new
functionality that allows changing the vCPU a channel will interrupt.
Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@...il.com>
---
drivers/hv/channel_mgmt.c | 105 +++++++++-----------------------------
include/linux/hyperv.h | 27 ----------
2 files changed, 25 insertions(+), 107 deletions(-)
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index c53f58ba06dcf..8f34494bb53fb 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -412,14 +412,6 @@ void hv_process_channel_removal(struct vmbus_channel *channel)
spin_unlock_irqrestore(&primary_channel->lock, flags);
}
- /*
- * We need to free the bit for init_vp_index() to work in the case
- * of sub-channel, when we reload drivers like hv_netvsc.
- */
- if (channel->affinity_policy == HV_LOCALIZED)
- cpumask_clear_cpu(channel->target_cpu,
- &primary_channel->alloced_cpus_in_node);
-
/*
* Upon suspend, an in-use hv_sock channel is marked as "rescinded" and
* the relid is invalidated; after hibernation, when the user-space app
@@ -641,20 +633,21 @@ static DEFINE_SPINLOCK(bind_channel_to_cpu_lock);
/*
* Starting with Win8, we can statically distribute the incoming
* channel interrupt load by binding a channel to VCPU.
- * 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.
+ *
+ * Starting with win8, performance critical channels will be distributed
+ * evenly among all the available NUMA nodes. Once the node is assigned,
+ * we will assign the CPU based on a simple round robin scheme.
*/
static void init_vp_index(struct vmbus_channel *channel, u16 dev_type)
{
- u32 cur_cpu;
bool perf_chn = vmbus_devs[dev_type].perf_device;
- struct vmbus_channel *primary = channel->primary_channel;
- int next_node;
cpumask_var_t available_mask;
struct cpumask *alloced_mask;
+ u32 target_cpu;
+ int numa_node;
if ((vmbus_proto_version == VERSION_WS2008) ||
(vmbus_proto_version == VERSION_WIN7) || (!perf_chn) ||
@@ -672,31 +665,27 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type)
return;
}
- spin_lock(&bind_channel_to_cpu_lock);
-
/*
- * Based on the channel affinity policy, we will assign the NUMA
- * nodes.
+ * Serializes the accesses to the global variable next_numa_node_id.
+ * See also the header comment of the spin lock declaration.
*/
+ spin_lock(&bind_channel_to_cpu_lock);
- if ((channel->affinity_policy == HV_BALANCED) || (!primary)) {
- while (true) {
- next_node = next_numa_node_id++;
- if (next_node == nr_node_ids) {
- next_node = next_numa_node_id = 0;
- continue;
- }
- if (cpumask_empty(cpumask_of_node(next_node)))
- continue;
- break;
+ while (true) {
+ numa_node = next_numa_node_id++;
+ if (numa_node == nr_node_ids) {
+ next_numa_node_id = 0;
+ continue;
}
- channel->numa_node = next_node;
- primary = channel;
+ if (cpumask_empty(cpumask_of_node(numa_node)))
+ continue;
+ break;
}
- alloced_mask = &hv_context.hv_numa_map[primary->numa_node];
+ channel->numa_node = numa_node;
+ alloced_mask = &hv_context.hv_numa_map[numa_node];
if (cpumask_weight(alloced_mask) ==
- cpumask_weight(cpumask_of_node(primary->numa_node))) {
+ cpumask_weight(cpumask_of_node(numa_node))) {
/*
* We have cycled through all the CPUs in the node;
* reset the alloced map.
@@ -704,57 +693,13 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type)
cpumask_clear(alloced_mask);
}
- cpumask_xor(available_mask, alloced_mask,
- cpumask_of_node(primary->numa_node));
+ cpumask_xor(available_mask, alloced_mask, cpumask_of_node(numa_node));
- cur_cpu = -1;
-
- if (primary->affinity_policy == HV_LOCALIZED) {
- /*
- * Normally Hyper-V host doesn't create more subchannels
- * than there are VCPUs on the node but it is possible when not
- * all present VCPUs on the node are initialized by guest.
- * Clear the alloced_cpus_in_node to start over.
- */
- if (cpumask_equal(&primary->alloced_cpus_in_node,
- cpumask_of_node(primary->numa_node)))
- cpumask_clear(&primary->alloced_cpus_in_node);
- }
-
- while (true) {
- cur_cpu = cpumask_next(cur_cpu, available_mask);
- if (cur_cpu >= nr_cpu_ids) {
- cur_cpu = -1;
- cpumask_copy(available_mask,
- cpumask_of_node(primary->numa_node));
- continue;
- }
-
- if (primary->affinity_policy == HV_LOCALIZED) {
- /*
- * NOTE: in the case of sub-channel, we clear the
- * sub-channel related bit(s) in
- * primary->alloced_cpus_in_node in
- * hv_process_channel_removal(), so when we
- * reload drivers like hv_netvsc in SMP guest, here
- * we're able to re-allocate
- * bit from primary->alloced_cpus_in_node.
- */
- if (!cpumask_test_cpu(cur_cpu,
- &primary->alloced_cpus_in_node)) {
- cpumask_set_cpu(cur_cpu,
- &primary->alloced_cpus_in_node);
- cpumask_set_cpu(cur_cpu, alloced_mask);
- break;
- }
- } else {
- cpumask_set_cpu(cur_cpu, alloced_mask);
- break;
- }
- }
+ target_cpu = cpumask_first(available_mask);
+ cpumask_set_cpu(target_cpu, alloced_mask);
- channel->target_cpu = cur_cpu;
- channel->target_vp = hv_cpu_number_to_vp_number(cur_cpu);
+ channel->target_cpu = target_cpu;
+ channel->target_vp = hv_cpu_number_to_vp_number(target_cpu);
spin_unlock(&bind_channel_to_cpu_lock);
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index ce32ab186192f..f8e7c22d41a1a 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -689,11 +689,6 @@ union hv_connection_id {
} u;
};
-enum hv_numa_policy {
- HV_BALANCED = 0,
- HV_LOCALIZED,
-};
-
enum vmbus_device_type {
HV_IDE = 0,
HV_SCSI,
@@ -808,10 +803,6 @@ struct vmbus_channel {
u32 target_vp;
/* The corresponding CPUID in the guest */
u32 target_cpu;
- /*
- * State to manage the CPU affiliation of channels.
- */
- struct cpumask alloced_cpus_in_node;
int numa_node;
/*
* Support for sub-channels. For high performance devices,
@@ -898,18 +889,6 @@ struct vmbus_channel {
*/
bool low_latency;
- /*
- * NUMA distribution policy:
- * 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.
- * 2) Localized: All channels of a given instance of a
- * performance critical service will be assigned CPUs
- * within a selected NUMA node.
- */
- enum hv_numa_policy affinity_policy;
-
bool probe_done;
/*
@@ -965,12 +944,6 @@ static inline bool is_sub_channel(const struct vmbus_channel *c)
return c->offermsg.offer.sub_channel_index != 0;
}
-static inline void set_channel_affinity_state(struct vmbus_channel *c,
- enum hv_numa_policy policy)
-{
- c->affinity_policy = policy;
-}
-
static inline void set_channel_read_mode(struct vmbus_channel *c,
enum hv_callback_mode mode)
{
--
2.24.0
Powered by blists - more mailing lists