lkml.org 
[lkml]   [2020]   [Mar]   [25]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[RFC PATCH 09/11] Drivers: hv: vmbus: Synchronize init_vp_index() vs. CPU hotplug
Date
init_vp_index() may access the cpu_online_mask mask via its calls of
cpumask_of_node(). Make sure to protect these accesses with a
cpus_read_lock() critical section.

Also, remove some (hardcoded) instances of CPU(0) from init_vp_index()
and replace them with VMBUS_CONNECT_CPU. The connect CPU can not go
offline, since Hyper-V does not provide a way to change it.

Finally, order the accesses of target_cpu from init_vp_index() and
hv_synic_cleanup() by relying on the channel_mutex; this is achieved
by moving the call of init_vp_index() into vmbus_process_offer().

Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
---
drivers/hv/channel_mgmt.c | 47 ++++++++++++++++++++++++++++-----------
drivers/hv/hv.c | 7 +++---
2 files changed, 38 insertions(+), 16 deletions(-)

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 8f34494bb53fb..34672dc2fc935 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -18,6 +18,7 @@
#include <linux/module.h>
#include <linux/completion.h>
#include <linux/delay.h>
+#include <linux/cpu.h>
#include <linux/hyperv.h>
#include <asm/mshyperv.h>

@@ -445,13 +446,8 @@ static void vmbus_add_channel_work(struct work_struct *work)
container_of(work, struct vmbus_channel, add_channel_work);
struct vmbus_channel *primary_channel = newchannel->primary_channel;
unsigned long flags;
- u16 dev_type;
int ret;

- dev_type = hv_get_dev_type(newchannel);
-
- init_vp_index(newchannel, dev_type);
-
/*
* This state is used to indicate a successful open
* so that when we do close the channel normally, we
@@ -483,7 +479,7 @@ static void vmbus_add_channel_work(struct work_struct *work)
if (!newchannel->device_obj)
goto err_deq_chan;

- newchannel->device_obj->device_id = dev_type;
+ newchannel->device_obj->device_id = hv_get_dev_type(newchannel);
/*
* Add the new device to the bus. This will kick off device-driver
* binding which eventually invokes the device driver's AddDevice()
@@ -539,6 +535,25 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
unsigned long flags;
bool fnew = true;

+ /*
+ * Initialize the target_CPU before inserting the channel in
+ * the chn_list and sc_list lists, within the channel_mutex
+ * critical section:
+ *
+ * CPU1 CPU2
+ *
+ * [vmbus_process_offer()] [hv_syninc_cleanup()]
+ *
+ * STORE target_cpu LOCK channel_mutex
+ * LOCK channel_mutex SEARCH chn_list
+ * INSERT chn_list LOAD target_cpu
+ * UNLOCK channel_mutex UNLOCK channel_mutex
+ *
+ * Forbids: CPU2's SEARCH from seeing CPU1's INSERT &&
+ * CPU2's LOAD from *not* seing CPU1's STORE
+ */
+ init_vp_index(newchannel, hv_get_dev_type(newchannel));
+
mutex_lock(&vmbus_connection.channel_mutex);

/* Remember the channels that should be cleaned up upon suspend. */
@@ -635,7 +650,7 @@ static DEFINE_SPINLOCK(bind_channel_to_cpu_lock);
* channel interrupt load by binding a channel to VCPU.
*
* For pre-win8 hosts or non-performance critical channels we assign the
- * first CPU in the first NUMA node.
+ * VMBUS_CONNECT_CPU.
*
* Starting with win8, performance critical channels will be distributed
* evenly among all the available NUMA nodes. Once the node is assigned,
@@ -654,17 +669,22 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type)
!alloc_cpumask_var(&available_mask, GFP_KERNEL)) {
/*
* Prior to win8, all channel interrupts are
- * delivered on cpu 0.
+ * delivered on VMBUS_CONNECT_CPU.
* Also if the channel is not a performance critical
- * channel, bind it to cpu 0.
- * In case alloc_cpumask_var() fails, bind it to cpu 0.
+ * channel, bind it to VMBUS_CONNECT_CPU.
+ * In case alloc_cpumask_var() fails, bind it to
+ * VMBUS_CONNECT_CPU.
*/
- channel->numa_node = 0;
- channel->target_cpu = 0;
- channel->target_vp = hv_cpu_number_to_vp_number(0);
+ channel->numa_node = cpu_to_node(VMBUS_CONNECT_CPU);
+ channel->target_cpu = VMBUS_CONNECT_CPU;
+ channel->target_vp =
+ hv_cpu_number_to_vp_number(VMBUS_CONNECT_CPU);
return;
}

+ /* No CPUs can come up or down during this. */
+ cpus_read_lock();
+
/*
* Serializes the accesses to the global variable next_numa_node_id.
* See also the header comment of the spin lock declaration.
@@ -702,6 +722,7 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type)
channel->target_vp = hv_cpu_number_to_vp_number(target_cpu);

spin_unlock(&bind_channel_to_cpu_lock);
+ cpus_read_unlock();

free_cpumask_var(available_mask);
}
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 17bf1f229152b..188b42b07f07b 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -256,9 +256,10 @@ int hv_synic_cleanup(unsigned int cpu)

/*
* Search for channels which are bound to the CPU we're about to
- * cleanup. In case we find one and vmbus is still connected we need to
- * fail, this will effectively prevent CPU offlining. There is no way
- * we can re-bind channels to different CPUs for now.
+ * cleanup. In case we find one and vmbus is still connected, we
+ * fail; this will effectively prevent CPU offlining.
+ *
+ * TODO: Re-bind the channels to different CPUs.
*/
mutex_lock(&vmbus_connection.channel_mutex);
list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
--
2.24.0
\
 
 \ /
  Last update: 2020-03-25 23:57    [W:0.166 / U:8.332 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site