summaryrefslogtreecommitdiff
path: root/net/sched
diff options
context:
space:
mode:
authorVladimir Oltean <vladimir.oltean@nxp.com>2023-08-07 22:33:15 +0300
committerJakub Kicinski <kuba@kernel.org>2023-08-10 01:59:20 +0300
commit25b0d4e4e41fcf0d2f43c431a82d344149e91258 (patch)
tree4526ff6065be39a2a0340a1adf90696ff1013b9e /net/sched
parent09e0c3bbde901f17837ad5088a13c3985534b860 (diff)
downloadlinux-25b0d4e4e41fcf0d2f43c431a82d344149e91258.tar.xz
net/sched: taprio: keep child Qdisc refcount elevated at 2 in offload mode
Normally, Qdiscs have one reference on them held by their owner and one held for each TXQ to which they are attached, however this is not the case with the children of an offloaded taprio. Instead, the taprio qdisc currently lives in the following fragile equilibrium. In the software scheduling case, taprio attaches itself (the root Qdisc) to all TXQs, thus having a refcount of 1 + the number of TX queues. In this mode, the q->qdiscs[] children are not visible directly to the Qdisc API. The lifetime of the Qdiscs from this private array lasts until qdisc_destroy() -> taprio_destroy(). In the fully offloaded case, the root taprio has a refcount of 1, and all child q->qdiscs[] also have a refcount of 1. The child q->qdiscs[] are attached to the netdev TXQs directly and thus are visible to the Qdisc API, however taprio loses a reference to them very early - during qdisc_graft(parent==NULL) -> taprio_attach(). At that time, taprio frees the q->qdiscs[] array to not leak memory, but interestingly, it does not release a reference on these qdiscs because it doesn't effectively own them - they are created by taprio but owned by the Qdisc core, and will be freed by qdisc_graft(parent==NULL, new==NULL) -> qdisc_put(old) when the Qdisc is deleted or when the child Qdisc is replaced with something else. My interest is to change this equilibrium such that taprio also owns a reference on the q->qdiscs[] child Qdiscs for the lifetime of the root Qdisc, including in full offload mode. I want this because I would like taprio_leaf(), taprio_dump_class(), taprio_dump_class_stats() to have insight into q->qdiscs[] for the software scheduling mode - currently they look at dev_queue->qdisc_sleeping, which is, as mentioned, the same as the root taprio. The following set of changes is necessary: - don't free q->qdiscs[] early in taprio_attach(), free it late in taprio_destroy() for consistency with software mode. But: - currently that's not possible, because taprio doesn't own a reference on q->qdiscs[]. So hold that reference - once during the initial attach() and once during subsequent graft() calls when the child is changed. - always keep track of the current child in q->qdiscs[], even for full offload mode, so that we free in taprio_destroy() what we should, and not something stale. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Link: https://lore.kernel.org/r/20230807193324.4128292-3-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net/sched')
-rw-r--r--net/sched/sch_taprio.c39
1 files changed, 25 insertions, 14 deletions
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 1cbc7fcd56c0..7c1fc3dc3e55 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -2146,30 +2146,31 @@ static void taprio_attach(struct Qdisc *sch)
/* Attach underlying qdisc */
for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx);
- struct Qdisc *old;
+ struct Qdisc *old, *dev_queue_qdisc;
if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
struct Qdisc *qdisc = q->qdiscs[ntx];
+ /* In offload mode, the root taprio qdisc is bypassed
+ * and the netdev TX queues see the children directly
+ */
qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
- old = dev_graft_qdisc(dev_queue, qdisc);
+ dev_queue_qdisc = qdisc;
} else {
/* In software mode, attach the root taprio qdisc
* to all netdev TX queues, so that dev_qdisc_enqueue()
* goes through taprio_enqueue().
*/
- old = dev_graft_qdisc(dev_queue, sch);
- qdisc_refcount_inc(sch);
+ dev_queue_qdisc = sch;
}
+ old = dev_graft_qdisc(dev_queue, dev_queue_qdisc);
+ /* The qdisc's refcount requires to be elevated once
+ * for each netdev TX queue it is grafted onto
+ */
+ qdisc_refcount_inc(dev_queue_qdisc);
if (old)
qdisc_put(old);
}
-
- /* access to the child qdiscs is not needed in offload mode */
- if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
- kfree(q->qdiscs);
- q->qdiscs = NULL;
- }
}
static struct netdev_queue *taprio_queue_get(struct Qdisc *sch,
@@ -2198,13 +2199,23 @@ static int taprio_graft(struct Qdisc *sch, unsigned long cl,
if (dev->flags & IFF_UP)
dev_deactivate(dev);
+ /* In offload mode, the child Qdisc is directly attached to the netdev
+ * TX queue, and thus, we need to keep its refcount elevated in order
+ * to counteract qdisc_graft()'s call to qdisc_put() once per TX queue.
+ * However, save the reference to the new qdisc in the private array in
+ * both software and offload cases, to have an up-to-date reference to
+ * our children.
+ */
+ *old = q->qdiscs[cl - 1];
if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
- *old = dev_graft_qdisc(dev_queue, new);
- } else {
- *old = q->qdiscs[cl - 1];
- q->qdiscs[cl - 1] = new;
+ WARN_ON_ONCE(dev_graft_qdisc(dev_queue, new) != *old);
+ if (new)
+ qdisc_refcount_inc(new);
+ if (*old)
+ qdisc_put(*old);
}
+ q->qdiscs[cl - 1] = new;
if (new)
new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;