JakeHillion/scx-upstream
1
0
Fork 0
mirror of https://github.com/sched-ext/scx.git synced 2024-11-24 20:00:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

scx_rustland: prevent using SCX_DSQ_LOCAL_ON from enqueue()

Browse Source 
When we fail to push a task to the queued BPF map we fallback to direct
dispatch, but we can't use SCX_DSQ_LOCAL_ON. So, make sure to use
SCX_DSQ_GLOBAL in this case to prevent scheduler crashes.

Signed-off-by: Andrea Righi <andrea.righi@canonical.com>
This commit is contained in:
Andrea Righi 2024-01-05 19:39:13 +01:00
parent 05d997c539
commit 0c3bdb16fe
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
scheds/rust/scx_rustland/src/bpf/main.bpf.c
View File

@ -295,6 +295,8 @@ static void dispatch_local(struct task_struct *p, u64 enq_flags)
*/
static s32 get_task_cpu(struct task_struct *p, s32 cpu)
{
if (cpu < 0)
return cpu;
/*
* Check if the designated CPU can be used to dispatch the task.
*/
@ -482,7 +484,7 @@ void BPF_STRUCT_OPS(rustland_enqueue, struct task_struct *p, u64 enq_flags)
if (bpf_map_push_elem(&queued, &task, 0)) {
dbg_msg("scheduler congested: pid=%d", task.pid);
__sync_fetch_and_add(&nr_sched_congested, 1);
dispatch_task(p, task.cpu, enq_flags);
dispatch_task(p, -1, enq_flags);
__sync_fetch_and_add(&nr_kernel_dispatches, 1);
return;
}