rseq: Reset slice extension when scheduled

When a time slice extension was granted in the need_resched() check on exit
to user space, the task can still be scheduled out in one of the other
pending work items. When it gets scheduled back in, and need_resched() is
not set, then the stale grant would be preserved, which is just wrong.

RSEQ already keeps track of that and sets TIF_RSEQ, which invokes the
critical section and ID update mechanisms.

Utilize them and clear the user space slice control member of struct rseq
unconditionally within the existing user access sections. That's just an
unconditional store more in that path.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20251215155709.131081527@linutronix.de

diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h
index 8d04611056aad8275e9e45f0aa5935c91e406633..fc77b9dd09327f9c8bb8a017cd0f4db79c3fe7ae 100644 (file)
--- a/include/linux/rseq_entry.h
+++ b/include/linux/rseq_entry.h
@@ -102,9 +102,17 @@ static __always_inline bool rseq_arm_slice_extension_timer(void)
        return __rseq_arm_slice_extension_timer();
 }
 
+static __always_inline void rseq_slice_clear_grant(struct task_struct *t)
+{
+       if (IS_ENABLED(CONFIG_RSEQ_STATS) && t->rseq.slice.state.granted)
+               rseq_stat_inc(rseq_stats.s_revoked);
+       t->rseq.slice.state.granted = false;
+}
+
 #else /* CONFIG_RSEQ_SLICE_EXTENSION */
 static inline bool rseq_slice_extension_enabled(void) { return false; }
 static inline bool rseq_arm_slice_extension_timer(void) { return false; }
+static inline void rseq_slice_clear_grant(struct task_struct *t) { }
 #endif /* !CONFIG_RSEQ_SLICE_EXTENSION */
 
 bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr);
@@ -391,8 +399,15 @@ bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids,
                unsafe_put_user(ids->mm_cid, &rseq->mm_cid, efault);
                if (csaddr)
                        unsafe_get_user(*csaddr, &rseq->rseq_cs, efault);
+
+               /* Open coded, so it's in the same user access region */
+               if (rseq_slice_extension_enabled()) {
+                       /* Unconditionally clear it, no point in conditionals */
+                       unsafe_put_user(0U, &rseq->slice_ctrl.all, efault);
+               }
        }
 
+       rseq_slice_clear_grant(t);
        /* Cache the new values */
        t->rseq.ids.cpu_cid = ids->cpu_cid;
        rseq_stat_inc(rseq_stats.ids);
@@ -488,8 +503,17 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t
                 */
                u64 csaddr;
 
-               if (unlikely(get_user_inline(csaddr, &rseq->rseq_cs)))
-                       return false;
+               scoped_user_rw_access(rseq, efault) {
+                       unsafe_get_user(csaddr, &rseq->rseq_cs, efault);
+
+                       /* Open coded, so it's in the same user access region */
+                       if (rseq_slice_extension_enabled()) {
+                               /* Unconditionally clear it, no point in conditionals */
+                               unsafe_put_user(0U, &rseq->slice_ctrl.all, efault);
+                       }
+               }
+
+               rseq_slice_clear_grant(t);
 
                if (static_branch_unlikely(&rseq_debug_enabled) || unlikely(csaddr)) {
                        if (unlikely(!rseq_update_user_cs(t, regs, csaddr)))
@@ -505,6 +529,8 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t
        u32 node_id = cpu_to_node(ids.cpu_id);
 
        return rseq_update_usr(t, regs, &ids, node_id);
+efault:
+       return false;
 }
 
 static __always_inline bool __rseq_exit_to_user_mode_restart(struct pt_regs *regs)