There is a retry loop in init_vp_index() where the CPUs from a certain
node are stripped out if they have already been in the allocated cpumask
or not in HK_TYPE_MANAGED_IRQ housekeeping cpumask. If there is no
CPU left, the allocated cpumask is ignored and the process is retried
again. However, if the HK_TYPE_MANAGED_IRQ housekeeping cpumask turns
out not to contain any CPU in that particular node, that will become an
infinite retry loop.  This particular problem was reported by sashiko
[1]. This should rarely happen, but we still need to guard against this.

Fix this infinite loop problem by also skipping NUMA node that has no
housekeeping CPU in the inner while loop of init_vp_index(). Also update
the early abort check to check for the absence of online housekeeping
CPUs instead of just the emptiness of the cpumask. As the outer for
loop will only be reached if the housekeeping cpumask has at least one
online CPU, a NUMA node with housekeeping CPUs will eventually be found.

Link: 
https://sashiko.dev/#/message/20260422030903.E1BFCC2BCB0%40smtp.kernel.org [1]
Fixes: 6640b5df1a38 ("Drivers: hv: vmbus: Don't assign VMbus channel interrupts 
to isolated CPUs")
Signed-off-by: Waiman Long <[email protected]>
---
 drivers/hv/channel_mgmt.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 89d214dda360..9b5ac09fbcf0 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -752,13 +752,14 @@ static void init_vp_index(struct vmbus_channel *channel)
        u32 i, ncpu = num_online_cpus();
        cpumask_var_t available_mask;
        struct cpumask *allocated_mask;
+       const struct cpumask *node_mask;
        const struct cpumask *hk_mask = 
housekeeping_cpumask(HK_TYPE_MANAGED_IRQ);
        u32 target_cpu;
        int numa_node;
 
        if (!perf_chn ||
            !alloc_cpumask_var(&available_mask, GFP_KERNEL) ||
-           cpumask_empty(hk_mask)) {
+           !cpumask_intersects(hk_mask, cpu_online_mask)) {
                /*
                 * If the channel is not a performance critical
                 * channel, bind it to VMBUS_CONNECT_CPU.
@@ -780,14 +781,16 @@ static void init_vp_index(struct vmbus_channel *channel)
                                next_numa_node_id = 0;
                                continue;
                        }
-                       if (cpumask_empty(cpumask_of_node(numa_node)))
+                       node_mask = cpumask_of_node(numa_node);
+                       if (cpumask_empty(node_mask) ||
+                           !cpumask_intersects(node_mask, hk_mask))
                                continue;
                        break;
                }
                allocated_mask = &hv_context.hv_numa_map[numa_node];
 
 retry:
-               cpumask_xor(available_mask, allocated_mask, 
cpumask_of_node(numa_node));
+               cpumask_xor(available_mask, allocated_mask, node_mask);
                cpumask_and(available_mask, available_mask, hk_mask);
 
                if (cpumask_empty(available_mask)) {
-- 
2.55.0


Reply via email to