diff options
| author | Tim Chen <tim.c.chen@linux.intel.com> | 2026-09-21 17:37:25 -0700 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2026-09-22 10:50:43 +0200 |
| commit | b636fef85bda7d1bab9c0a45067ab1508d79d946 (patch) | |
| tree | 2ec4ab3249c034a2a23d2809fcdcc379f89b9881 /include | |
| parent | 28f9c0e0a0b94c5d3e1b634db545f6e1f94858c5 (diff) | |
| download | linux-stable-b636fef85bda7d1bab9c0a45067ab1508d79d946.tar.gz linux-stable-b636fef85bda7d1bab9c0a45067ab1508d79d946.zip | |
sched/cache: Introduce task_struct->sched_cache_grp to fix UAF
Add a sched_cache_grp pointer to task_struct so that scheduler code
can access the cache group directly via the task, without going
through mm->sched_cache_grp. This decouples the scheduler's hot-path
accesses from the mm_struct.
Each task holds its own refcount on the sched_cache_group, separate
from the reference held by its mm_struct. The reference is acquired
in copy_mm() (fork) and exec_mmap() (exec), and released in exit_mm().
This fixes the use-after-free when account_mm_sched() reaches the group
through a task whose mm is being switched, as reported by Hyunwoo:
https://lore.kernel.org/lkml/apPb-Dr4nPYuHQOK@v4bel/
Convert all scheduler code in fair.c and exit.c to use
p->sched_cache_grp instead of p->mm->sched_cache_grp.
Keep the fork/exec/exit reference management out of the generic mm
paths: add sched_cache_fork(), sched_cache_fork_cleanup(),
sched_cache_exec_mmap() and sched_cache_exit_mm() in
kernel/sched/cache_sched.c (with empty stubs for !CONFIG_SCHED_CACHE),
so fs/exec.c, kernel/fork.c and kernel/exit.c each call one helper
instead of open-coding the refcounting under #ifdef. Also add
sched_cache_group_get() and task_cache_group_get().
Fixes: df0d98475954 ("sched/cache: Introduce infrastructure for cache-aware load balancing")
Closes: https://lore.kernel.org/lkml/apPb-Dr4nPYuHQOK@v4bel/
Closes: https://lore.kernel.org/all/343a7e07-7fad-4979-9c9b-82ec038c293c@linux.dev/
Reported-by: Hyunwoo Kim <imv4bel@gmail.com>
Reported-by: Zenghui Yu (Huawei) <zenghui.yu@linux.dev>
Co-developed-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: <stable@kernel.org> #7.2.x
Link: https://patch.msgid.link/ae7081dc54736bf115215f9867abb2711a7403fb.1790035273.git.tim.c.chen@linux.intel.com
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/sched.h | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h index e14ad4352..d35ae49a9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1433,6 +1433,7 @@ struct task_struct { #ifdef CONFIG_SCHED_CACHE struct callback_head cache_work; + struct sched_cache_group __rcu *sched_cache_grp; int preferred_llc; /* 1: task was enqueued to its preferred LLC, 0 otherwise */ int pref_llc_queued; @@ -2417,10 +2418,23 @@ struct sched_cache_group { struct rcu_head rcu; } ____cacheline_aligned_in_smp; +struct sched_cache_group *sched_cache_group_get(struct sched_cache_group *grp); +struct sched_cache_group *task_cache_group_get(struct task_struct *p); + +void sched_cache_fork(struct task_struct *p); +void sched_cache_fork_cleanup(struct task_struct *p); +void sched_cache_exec_mmap(struct task_struct *p, struct mm_struct *mm); +void sched_cache_exit_mm(struct task_struct *p); + #else struct sched_cache_group { }; +static inline void sched_cache_fork(struct task_struct *p) { } +static inline void sched_cache_fork_cleanup(struct task_struct *p) { } +static inline void sched_cache_exec_mmap(struct task_struct *p, struct mm_struct *mm) { } +static inline void sched_cache_exit_mm(struct task_struct *p) { } + #endif #ifndef MODULE |