shinys000114/linux
1
0
Fork 0
mirror of https://github.com/hardkernel/linux.git synced 2026-06-05 10:31:46 +09:00
Code Issues Packages Projects Releases Wiki Activity

io_uring/io-wq: do not allow pinning outside of cpuset

Browse Source 
commit 0997aa5497c714edbb349ca366d28bd550ba3408 upstream.

The io worker threads are userland threads that just never exit to the
userland. By that, they are also assigned to a cgroup (the group of the
creating task).

When changing the affinity of the io_wq thread via syscall, we must only
allow cpumasks within the limits defined by the cpuset controller of the
cgroup (if enabled).

Fixes: da64d6db3b ("io_uring: One wqe per wq")
Signed-off-by: Felix Moessbauer <felix.moessbauer@siemens.com>
Link: https://lore.kernel.org/r/20240910171157.166423-2-felix.moessbauer@siemens.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Felix Moessbauer
2024-09-10 19:11:56 +02:00
committed by Greg Kroah-Hartman
parent d8920d2534
commit fce514611f
1 changed files with 19 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
io_uring/io-wq.c
View File

@@ -13,6 +13,7 @@
#include <linux/slab.h> #include <linux/slab.h>
#include <linux/rculist_nulls.h> #include <linux/rculist_nulls.h>
#include <linux/cpu.h> #include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/task_work.h> #include <linux/task_work.h>
#include <linux/audit.h> #include <linux/audit.h>
#include <uapi/linux/io_uring.h> #include <uapi/linux/io_uring.h>
@@ -1362,22 +1363,34 @@ static int io_wq_cpu_offline(unsigned int cpu, struct hlist_node *node)
int io_wq_cpu_affinity(struct io_uring_task *tctx, cpumask_var_t mask) int io_wq_cpu_affinity(struct io_uring_task *tctx, cpumask_var_t mask)
{ {
cpumask_var_t allowed_mask;
int ret = 0;
int i; int i;
if (!tctx || !tctx->io_wq) if (!tctx || !tctx->io_wq)
return -EINVAL; return -EINVAL;
if (!alloc_cpumask_var(&allowed_mask, GFP_KERNEL))
return -ENOMEM;
cpuset_cpus_allowed(tctx->io_wq->task, allowed_mask);
rcu_read_lock(); rcu_read_lock();
for_each_node(i) { for_each_node(i) {
struct io_wqe *wqe = tctx->io_wq->wqes[i]; struct io_wqe *wqe = tctx->io_wq->wqes[i];
if (mask) {
if (mask) if (cpumask_subset(mask, allowed_mask))
cpumask_copy(wqe->cpu_mask, mask); cpumask_copy(wqe->cpu_mask, mask);
else else
cpumask_copy(wqe->cpu_mask, cpumask_of_node(i)); ret = -EINVAL;
} else {
if (!cpumask_and(wqe->cpu_mask, cpumask_of_node(i), allowed_mask))
cpumask_copy(wqe->cpu_mask, allowed_mask);
}
} }
rcu_read_unlock(); rcu_read_unlock();
return 0;
free_cpumask_var(allowed_mask);
return ret;
} }
/* /*