net: tcp: tsq: Convert from tasklet to BH workqueue

The only generic interface to execute asynchronously in the BH context is
tasklet; however, it's marked deprecated and has some design flaws. To
replace tasklets, BH workqueue support was recently added. A BH workqueue
behaves similarly to regular workqueues except that the queued work items
are executed in the BH context.

This patch converts TCP Small Queues implementation from tasklet to BH
workqueue.

Semantically, this is an equivalent conversion and there shouldn't be any
user-visible behavior changes. While workqueue's queueing and execution
paths are a bit heavier than tasklet's, unless the work item is being queued
every packet, the difference hopefully shouldn't matter.

My experience with the networking stack is very limited and this patch
definitely needs attention from someone who actually understands networking.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Cc: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/aFBeJ38AS1ZF3Dq5@slm.duckdns.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9f852f5f8b95ef19cca13a16c1d45a3d49458c47..761c4a0ad386f95f73d72dc013a0952187342b51 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -321,7 +321,7 @@ extern struct proto tcp_prot;
 #define TCP_DEC_STATS(net, field)      SNMP_DEC_STATS((net)->mib.tcp_statistics, field)
 #define TCP_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val)
 
-void tcp_tasklet_init(void);
+void tcp_tsq_work_init(void);
 
 int tcp_v4_err(struct sk_buff *skb, u32);
 

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 27d3ef83ce7b2bbf2cd51c65659e9f18cb004cd7..8a3c99246d2ed32ba45849b56830bf128e265763 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -5242,6 +5242,6 @@ void __init tcp_init(void)
        tcp_v4_init();
        tcp_metrics_init();
        BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0);
-       tcp_tasklet_init();
+       tcp_tsq_work_init();
        mptcp_init();
 }

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index eb50746dc4820aa9b0ce02c5122676e765845985..28f840724fe833d594e1b151f8e130d2d54fd766 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1066,15 +1066,15 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
  * needs to be reallocated in a driver.
  * The invariant being skb->truesize subtracted from sk->sk_wmem_alloc
  *
- * Since transmit from skb destructor is forbidden, we use a tasklet
+ * Since transmit from skb destructor is forbidden, we use a BH work item
  * to process all sockets that eventually need to send more skbs.
- * We use one tasklet per cpu, with its own queue of sockets.
+ * We use one work item per cpu, with its own queue of sockets.
  */
-struct tsq_tasklet {
-       struct tasklet_struct   tasklet;
+struct tsq_work {
+       struct work_struct      work;
        struct list_head        head; /* queue of tcp sockets */
 };
-static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet);
+static DEFINE_PER_CPU(struct tsq_work, tsq_work);
 
 static void tcp_tsq_write(struct sock *sk)
 {
@@ -1104,14 +1104,14 @@ static void tcp_tsq_handler(struct sock *sk)
        bh_unlock_sock(sk);
 }
 /*
- * One tasklet per cpu tries to send more skbs.
- * We run in tasklet context but need to disable irqs when
+ * One work item per cpu tries to send more skbs.
+ * We run in BH context but need to disable irqs when
  * transferring tsq->head because tcp_wfree() might
  * interrupt us (non NAPI drivers)
  */
-static void tcp_tasklet_func(struct tasklet_struct *t)
+static void tcp_tsq_workfn(struct work_struct *work)
 {
-       struct tsq_tasklet *tsq = from_tasklet(tsq,  t, tasklet);
+       struct tsq_work *tsq = container_of(work, struct tsq_work, work);
        LIST_HEAD(list);
        unsigned long flags;
        struct list_head *q, *n;
@@ -1181,15 +1181,15 @@ void tcp_release_cb(struct sock *sk)
 }
 EXPORT_IPV6_MOD(tcp_release_cb);
 
-void __init tcp_tasklet_init(void)
+void __init tcp_tsq_work_init(void)
 {
        int i;
 
        for_each_possible_cpu(i) {
-               struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i);
+               struct tsq_work *tsq = &per_cpu(tsq_work, i);
 
                INIT_LIST_HEAD(&tsq->head);
-               tasklet_setup(&tsq->tasklet, tcp_tasklet_func);
+               INIT_WORK(&tsq->work, tcp_tsq_workfn);
        }
 }
 
@@ -1203,11 +1203,11 @@ void tcp_wfree(struct sk_buff *skb)
        struct sock *sk = skb->sk;
        struct tcp_sock *tp = tcp_sk(sk);
        unsigned long flags, nval, oval;
-       struct tsq_tasklet *tsq;
+       struct tsq_work *tsq;
        bool empty;
 
        /* Keep one reference on sk_wmem_alloc.
-        * Will be released by sk_free() from here or tcp_tasklet_func()
+        * Will be released by sk_free() from here or tcp_tsq_workfn()
         */
        WARN_ON(refcount_sub_and_test(skb->truesize - 1, &sk->sk_wmem_alloc));
 
@@ -1229,13 +1229,13 @@ void tcp_wfree(struct sk_buff *skb)
                nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED;
        } while (!try_cmpxchg(&sk->sk_tsq_flags, &oval, nval));
 
-       /* queue this socket to tasklet queue */
+       /* queue this socket to BH workqueue */
        local_irq_save(flags);
-       tsq = this_cpu_ptr(&tsq_tasklet);
+       tsq = this_cpu_ptr(&tsq_work);
        empty = list_empty(&tsq->head);
        list_add(&tp->tsq_node, &tsq->head);
        if (empty)
-               tasklet_schedule(&tsq->tasklet);
+               queue_work(system_bh_wq, &tsq->work);
        local_irq_restore(flags);
        return;
 out:
@@ -2634,7 +2634,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
        if (refcount_read(&sk->sk_wmem_alloc) > limit) {
                /* Always send skb if rtx queue is empty or has one skb.
                 * No need to wait for TX completion to call us back,
-                * after softirq/tasklet schedule.
+                * after softirq schedule.
                 * This helps when TX completions are delayed too much.
                 */
                if (tcp_rtx_queue_empty_or_single_skb(sk))