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

[ Upstream commit 0997aa5497c714edbb349ca366d28bd550ba3408 ]

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: da64d6db3bd3 ("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: Sasha Levin <sashal@kernel.org>

diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index 22dac5850327fcca8538d252618dcaaab4834081..e38bbd07563ee9135178120b68905c07e81ddb4a 100644 (file)
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/rculist_nulls.h>
 #include <linux/cpu.h>
+#include <linux/cpuset.h>
 #include <linux/task_work.h>
 #include <linux/audit.h>
 #include <linux/mmu_context.h>
@@ -1321,17 +1322,29 @@ 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)
 {
+       cpumask_var_t allowed_mask;
+       int ret = 0;
+
        if (!tctx || !tctx->io_wq)
                return -EINVAL;
 
+       if (!alloc_cpumask_var(&allowed_mask, GFP_KERNEL))
+               return -ENOMEM;
+
        rcu_read_lock();
-       if (mask)
-               cpumask_copy(tctx->io_wq->cpu_mask, mask);
-       else
-               cpumask_copy(tctx->io_wq->cpu_mask, cpu_possible_mask);
+       cpuset_cpus_allowed(tctx->io_wq->task, allowed_mask);
+       if (mask) {
+               if (cpumask_subset(mask, allowed_mask))
+                       cpumask_copy(tctx->io_wq->cpu_mask, mask);
+               else
+                       ret = -EINVAL;
+       } else {
+               cpumask_copy(tctx->io_wq->cpu_mask, allowed_mask);
+       }
        rcu_read_unlock();
 
-       return 0;
+       free_cpumask_var(allowed_mask);
+       return ret;
 }
 
 /*