sched_ext: Maintain an online cid mask in the scheduler arenagrafted

Schedulers on the default cid mapping treat [0, nr_online_cids) as the
online set and restart on hotplug. Schedulers that install their own mapping
with scx_bpf_cid_override() have no way to learn which cids are online: the
count no longer identifies members and the CPU-form cpumask is unusable from
cid programs. This is an obvious hole in the cid API.

Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's
arena, allocated alongside the per-CPU scratch masks and populated after the
cid mapping is finalized and before ops.init(), for child schedulers too.
The pointer stays valid through ops.exit() with no reference to take. It is
the arena offset as a void pointer, the same form struct_ops arena arguments
arrive in. The verifier types the void return as a scalar for the program's
arena cast.

The mask follows the SCX hotplug notifications: seeded from cpu_active_mask
and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask
only inside a hotplug transition. Updates walk the scheduler list under the
lock that also serializes unlinking. Reads are live, not atomic snapshots.
Root initialization excludes hotplug.

v2: Reworded the getter kerneldoc (Andrea Righi).

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

1 files changed, 99 insertions, 0 deletions

diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell
new file mode 100644
index 000000000..fe6599800
--- /dev/null
+++ b/tools/memory-model/linux-kernel.bell
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0+
+(*
+ * Copyright (C) 2015 Jade Alglave <j.alglave@ucl.ac.uk>,
+ * Copyright (C) 2016 Luc Maranget <luc.maranget@inria.fr> for Inria
+ * Copyright (C) 2017 Alan Stern <stern@rowland.harvard.edu>,
+ *                    Andrea Parri <parri.andrea@gmail.com>
+ *
+ * An earlier version of this file appeared in the companion webpage for
+ * "Frightening small children and disconcerting grown-ups: Concurrency
+ * in the Linux kernel" by Alglave, Maranget, McKenney, Parri, and Stern,
+ * which appeared in ASPLOS 2018.
+ *)
+
+"Linux-kernel memory consistency model"
+
+enum Accesses = 'ONCE (*READ_ONCE,WRITE_ONCE*) ||
+		'RELEASE (*smp_store_release*) ||
+		'ACQUIRE (*smp_load_acquire*) ||
+		'NORETURN (* R of non-return RMW *) ||
+		'MB (*xchg(),cmpxchg(),...*)
+instructions R[Accesses]
+instructions W[Accesses]
+instructions RMW[Accesses]
+
+enum Barriers = 'wmb (*smp_wmb*) ||
+		'rmb (*smp_rmb*) ||
+		'MB (*smp_mb*) ||
+		'barrier (*barrier*) ||
+		'rcu-lock (*rcu_read_lock*)  ||
+		'rcu-unlock (*rcu_read_unlock*) ||
+		'sync-rcu (*synchronize_rcu*) ||
+		'before-atomic (*smp_mb__before_atomic*) ||
+		'after-atomic (*smp_mb__after_atomic*) ||
+		'after-spinlock (*smp_mb__after_spinlock*) ||
+		'after-unlock-lock (*smp_mb__after_unlock_lock*) ||
+		'after-srcu-read-unlock (*smp_mb__after_srcu_read_unlock*)
+instructions F[Barriers]
+
+
+(*
+ * Filter out syntactic annotations that do not provide the corresponding
+ * semantic ordering, such as Acquire on a store or Mb on a failed RMW.
+ *)
+let FailedRMW = RMW \ (domain(rmw) | range(rmw))
+let Acquire = ACQUIRE \ W \ FailedRMW
+let Release = RELEASE \ R \ FailedRMW
+let Mb = MB \ FailedRMW
+let Noreturn = NORETURN \ W
+
+(* SRCU *)
+enum SRCU = 'srcu-lock || 'srcu-unlock || 'sync-srcu
+instructions SRCU[SRCU]
+(* All srcu events *)
+let Srcu = Srcu-lock | Srcu-unlock | Sync-srcu
+
+(* Compute matching pairs of nested Rcu-lock and Rcu-unlock *)
+let rcu-rscs = let rec
+	    unmatched-locks = Rcu-lock \ domain(matched)
+	and unmatched-unlocks = Rcu-unlock \ range(matched)
+	and unmatched = unmatched-locks | unmatched-unlocks
+	and unmatched-po = [unmatched] ; po ; [unmatched]
+	and unmatched-locks-to-unlocks =
+		[unmatched-locks] ; po ; [unmatched-unlocks]
+	and matched = matched | (unmatched-locks-to-unlocks \
+		(unmatched-po ; unmatched-po))
+	in matched
+
+(* Validate nesting *)
+flag ~empty Rcu-lock \ domain(rcu-rscs) as unmatched-rcu-lock
+flag ~empty Rcu-unlock \ range(rcu-rscs) as unmatched-rcu-unlock
+
+(* Compute matching pairs of nested Srcu-lock and Srcu-unlock *)
+let carry-srcu-data = (data ; [~ Srcu-unlock] ; rf)*
+let srcu-rscs = ([Srcu-lock] ; carry-srcu-data ; data ; [Srcu-unlock]) & loc
+
+(* Validate nesting *)
+flag ~empty Srcu-lock \ domain(srcu-rscs) as unmatched-srcu-lock
+flag ~empty Srcu-unlock \ range(srcu-rscs) as unmatched-srcu-unlock
+flag ~empty (srcu-rscs^-1 ; srcu-rscs) \ id as multiple-srcu-matches
+
+(* Check for use of synchronize_srcu() inside an RCU critical section *)
+flag ~empty rcu-rscs & (po ; [Sync-srcu] ; po) as invalid-sleep
+
+(* Validate SRCU dynamic match *)
+flag ~empty different-values(srcu-rscs) as srcu-bad-value-match
+
+(* Compute marked and plain memory accesses *)
+let Marked = (~M) | IW | ONCE | RELEASE | ACQUIRE | MB | RMW |
+		LKR | LKW | UL | LF | RL | RU | Srcu-lock | Srcu-unlock
+let Plain = M \ Marked
+
+(* Redefine dependencies to include those carried through plain accesses *)
+let carry-dep = (data ; [~ Srcu-unlock] ; rfi)*
+let addr = carry-dep ; addr
+let ctrl = carry-dep ; ctrl
+let data = carry-dep ; data
+
+flag ~empty (if "lkmmv2" then 0 else _)
+  as this-model-requires-variant-higher-than-lkmmv1