With cgroup v2, the cpuset's cpus_allowed mask can be empty indicating
that the cpuset will just use the effective cpus of its parent. So
cpuset_can_attach() can call task_can_attach() with an empty mask.
This can lead to cpumask_any_and() returns nr_cpu_ids causing the call
to dl_bw_of() to crash due to percpu value access of an out of bound
cpu value. For example,
[80468.182258] BUG: unable to handle page fault for address: ffffffff8b6648b0
:
[80468.191019] RIP: 0010:dl_cpu_busy+0x30/0x2b0
:
[80468.207946] Call Trace:
[80468.208947] cpuset_can_attach+0xa0/0x140
[80468.209953] cgroup_migrate_execute+0x8c/0x490
[80468.210931] cgroup_update_dfl_csses+0x254/0x270
[80468.211898] cgroup_subtree_control_write+0x322/0x400
[80468.212854] kernfs_fop_write_iter+0x11c/0x1b0
[80468.213777] new_sync_write+0x11f/0x1b0
[80468.214689] vfs_write+0x1eb/0x280
[80468.215592] ksys_write+0x5f/0xe0
[80468.216463] do_syscall_64+0x5c/0x80
[80468.224287] entry_SYSCALL_64_after_hwframe+0x44/0xae
Fix that by using effective_cpus instead. For cgroup v1, effective_cpus
is the same as cpus_allowed. For v2, effective_cpus is the real cpumask
to be used by tasks within the cpuset anyway.
Also update task_can_attach()'s 2nd argument name to cs_effective_cpus to
reflect the change. In addition, a check is added to task_can_attach()
to guard against the possibility that cpumask_any_and() may return a
value >= nr_cpu_ids.
Fixes: 7f51412a415d ("sched/deadline: Fix bandwidth check/update when migrating tasks between exclusive cpusets")
Signed-off-by: Waiman Long <[email protected]>
---
include/linux/sched.h | 2 +-
kernel/cgroup/cpuset.c | 2 +-
kernel/sched/core.c | 8 +++++---
3 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 88b8817b827d..6a060160f0db 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1813,7 +1813,7 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags)
}
extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
-extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed);
+extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus);
#ifdef CONFIG_SMP
extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask);
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 71a418858a5e..58aadfda9b8b 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2239,7 +2239,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
goto out_unlock;
cgroup_taskset_for_each(task, css, tset) {
- ret = task_can_attach(task, cs->cpus_allowed);
+ ret = task_can_attach(task, cs->effective_cpus);
if (ret)
goto out_unlock;
ret = security_task_setscheduler(task);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5555e49c4e12..addc3c2d2122 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8980,7 +8980,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur,
}
int task_can_attach(struct task_struct *p,
- const struct cpumask *cs_cpus_allowed)
+ const struct cpumask *cs_effective_cpus)
{
int ret = 0;
@@ -8999,9 +8999,11 @@ int task_can_attach(struct task_struct *p,
}
if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
- cs_cpus_allowed)) {
- int cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed);
+ cs_effective_cpus)) {
+ int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus);
+ if (unlikely(cpu >= nr_cpu_ids))
+ return -EINVAL;
ret = dl_cpu_busy(cpu, p);
}
--
2.31.1
Hi,
On 02/08/22 21:54, Waiman Long wrote:
> With cgroup v2, the cpuset's cpus_allowed mask can be empty indicating
> that the cpuset will just use the effective cpus of its parent. So
> cpuset_can_attach() can call task_can_attach() with an empty mask.
> This can lead to cpumask_any_and() returns nr_cpu_ids causing the call
> to dl_bw_of() to crash due to percpu value access of an out of bound
> cpu value. For example,
>
> [80468.182258] BUG: unable to handle page fault for address: ffffffff8b6648b0
> :
> [80468.191019] RIP: 0010:dl_cpu_busy+0x30/0x2b0
> :
> [80468.207946] Call Trace:
> [80468.208947] cpuset_can_attach+0xa0/0x140
> [80468.209953] cgroup_migrate_execute+0x8c/0x490
> [80468.210931] cgroup_update_dfl_csses+0x254/0x270
> [80468.211898] cgroup_subtree_control_write+0x322/0x400
> [80468.212854] kernfs_fop_write_iter+0x11c/0x1b0
> [80468.213777] new_sync_write+0x11f/0x1b0
> [80468.214689] vfs_write+0x1eb/0x280
> [80468.215592] ksys_write+0x5f/0xe0
> [80468.216463] do_syscall_64+0x5c/0x80
> [80468.224287] entry_SYSCALL_64_after_hwframe+0x44/0xae
>
> Fix that by using effective_cpus instead. For cgroup v1, effective_cpus
> is the same as cpus_allowed. For v2, effective_cpus is the real cpumask
> to be used by tasks within the cpuset anyway.
>
> Also update task_can_attach()'s 2nd argument name to cs_effective_cpus to
> reflect the change. In addition, a check is added to task_can_attach()
> to guard against the possibility that cpumask_any_and() may return a
> value >= nr_cpu_ids.
>
> Fixes: 7f51412a415d ("sched/deadline: Fix bandwidth check/update when migrating tasks between exclusive cpusets")
> Signed-off-by: Waiman Long <[email protected]>
> ---
Looks good to me. Thanks for looking into it!
Acked-by: Juri Lelli <[email protected]>
Best,
Juri
The following commit has been merged into the sched/urgent branch of tip:
Commit-ID: b6e8d40d43ae4dec00c8fea2593eeea3114b8f44
Gitweb: https://git.kernel.org/tip/b6e8d40d43ae4dec00c8fea2593eeea3114b8f44
Author: Waiman Long <[email protected]>
AuthorDate: Tue, 02 Aug 2022 21:54:51 -04:00
Committer: Ingo Molnar <[email protected]>
CommitterDate: Wed, 03 Aug 2022 10:34:26 +02:00
sched, cpuset: Fix dl_cpu_busy() panic due to empty cs->cpus_allowed
With cgroup v2, the cpuset's cpus_allowed mask can be empty indicating
that the cpuset will just use the effective CPUs of its parent. So
cpuset_can_attach() can call task_can_attach() with an empty mask.
This can lead to cpumask_any_and() returns nr_cpu_ids causing the call
to dl_bw_of() to crash due to percpu value access of an out of bound
CPU value. For example:
[80468.182258] BUG: unable to handle page fault for address: ffffffff8b6648b0
:
[80468.191019] RIP: 0010:dl_cpu_busy+0x30/0x2b0
:
[80468.207946] Call Trace:
[80468.208947] cpuset_can_attach+0xa0/0x140
[80468.209953] cgroup_migrate_execute+0x8c/0x490
[80468.210931] cgroup_update_dfl_csses+0x254/0x270
[80468.211898] cgroup_subtree_control_write+0x322/0x400
[80468.212854] kernfs_fop_write_iter+0x11c/0x1b0
[80468.213777] new_sync_write+0x11f/0x1b0
[80468.214689] vfs_write+0x1eb/0x280
[80468.215592] ksys_write+0x5f/0xe0
[80468.216463] do_syscall_64+0x5c/0x80
[80468.224287] entry_SYSCALL_64_after_hwframe+0x44/0xae
Fix that by using effective_cpus instead. For cgroup v1, effective_cpus
is the same as cpus_allowed. For v2, effective_cpus is the real cpumask
to be used by tasks within the cpuset anyway.
Also update task_can_attach()'s 2nd argument name to cs_effective_cpus to
reflect the change. In addition, a check is added to task_can_attach()
to guard against the possibility that cpumask_any_and() may return a
value >= nr_cpu_ids.
Fixes: 7f51412a415d ("sched/deadline: Fix bandwidth check/update when migrating tasks between exclusive cpusets")
Signed-off-by: Waiman Long <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Acked-by: Juri Lelli <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
---
include/linux/sched.h | 2 +-
kernel/cgroup/cpuset.c | 2 +-
kernel/sched/core.c | 8 +++++---
3 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 88b8817..6a06016 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1813,7 +1813,7 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags)
}
extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
-extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed);
+extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus);
#ifdef CONFIG_SMP
extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask);
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 71a4188..58aadfd 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2239,7 +2239,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
goto out_unlock;
cgroup_taskset_for_each(task, css, tset) {
- ret = task_can_attach(task, cs->cpus_allowed);
+ ret = task_can_attach(task, cs->effective_cpus);
if (ret)
goto out_unlock;
ret = security_task_setscheduler(task);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5555e49..addc3c2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8980,7 +8980,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur,
}
int task_can_attach(struct task_struct *p,
- const struct cpumask *cs_cpus_allowed)
+ const struct cpumask *cs_effective_cpus)
{
int ret = 0;
@@ -8999,9 +8999,11 @@ int task_can_attach(struct task_struct *p,
}
if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
- cs_cpus_allowed)) {
- int cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed);
+ cs_effective_cpus)) {
+ int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus);
+ if (unlikely(cpu >= nr_cpu_ids))
+ return -EINVAL;
ret = dl_cpu_busy(cpu, p);
}
On Tue, Aug 02, 2022 at 09:54:51PM -0400, Waiman Long <[email protected]> wrote:
> Fixes: 7f51412a415d ("sched/deadline: Fix bandwidth check/update when migrating tasks between exclusive cpusets")
> Signed-off-by: Waiman Long <[email protected]>
> ---
> include/linux/sched.h | 2 +-
> kernel/cgroup/cpuset.c | 2 +-
> kernel/sched/core.c | 8 +++++---
> 3 files changed, 7 insertions(+), 5 deletions(-)
Good catch,
Reviewed-by: Michal Koutn? <[email protected]>