For some drivers (especially 802.11 drivers), doing a lot of work in the NAPI
poll function does not perform well. Since NAPI poll is bound to the CPU it
was scheduled from, we can easily end up with a few very busy CPUs spending
most of their time in softirq/ksoftirqd and some idle ones.
Introduce threaded NAPI for such drivers based on a workqueue. The API is the
same except for using netif_threaded_napi_add instead of netif_napi_add.
In my tests with mt76 on MT7621 using threaded NAPI + a thread for tx scheduling
improves LAN->WLAN bridging throughput by 10-50%. Throughput without threaded
NAPI is wildly inconsistent, depending on the CPU that runs the tx scheduling
thread.
With threaded NAPI, throughput seems stable and consistent (and higher than
the best results I got without it).
Based on a patch by Hillf Danton
Cc: Hillf Danton <hdan...@sina.com>
Signed-off-by: Felix Fietkau <n...@nbd.name>
---
Changes since RFC v2:
- fix unused but set variable reported by kbuild test robot
Changes since RFC:
- disable softirq around threaded poll functions
- reuse most parts of napi_poll()
- fix re-schedule condition
include/linux/netdevice.h | 23 ++++++
net/core/dev.c | 162 ++++++++++++++++++++++++++------------
2 files changed, 133 insertions(+), 52 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ac2cd3f49aba..3a39211c7598 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -347,6 +347,7 @@ struct napi_struct {
struct list_head dev_list;
struct hlist_node napi_hash_node;
unsigned int napi_id;
+ struct work_struct work;
};
enum {
@@ -357,6 +358,7 @@ enum {
NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */
NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */
NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */
+ NAPI_STATE_THREADED, /* Use threaded NAPI */
};
enum {
@@ -367,6 +369,7 @@ enum {
NAPIF_STATE_HASHED = BIT(NAPI_STATE_HASHED),
NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
+ NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED),
};
enum gro_result {
@@ -2315,6 +2318,26 @@ static inline void *netdev_priv(const struct net_device
*dev)
void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int), int weight);
+/**
+ * netif_threaded_napi_add - initialize a NAPI context
+ * @dev: network device
+ * @napi: NAPI context
+ * @poll: polling function
+ * @weight: default weight
+ *
+ * This variant of netif_napi_add() should be used from drivers using NAPI
+ * with CPU intensive poll functions.
+ * This will schedule polling from a high priority workqueue that
+ */
+static inline void netif_threaded_napi_add(struct net_device *dev,
+ struct napi_struct *napi,
+ int (*poll)(struct napi_struct *, int),
+ int weight)
+{
+ set_bit(NAPI_STATE_THREADED, &napi->state);
+ netif_napi_add(dev, napi, poll, weight);
+}
+
/**
* netif_tx_napi_add - initialize a NAPI context
* @dev: network device
diff --git a/net/core/dev.c b/net/core/dev.c
index 19f1abc26fcd..11b027f3a2b9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -158,6 +158,7 @@ static DEFINE_SPINLOCK(offload_lock);
struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
struct list_head ptype_all __read_mostly; /* Taps */
static struct list_head offload_base __read_mostly;
+static struct workqueue_struct *napi_workq __read_mostly;
static int netif_rx_internal(struct sk_buff *skb);
static int call_netdevice_notifiers_info(unsigned long val,
@@ -6286,6 +6287,11 @@ void __napi_schedule(struct napi_struct *n)
{
unsigned long flags;
+ if (test_bit(NAPI_STATE_THREADED, &n->state)) {
+ queue_work(napi_workq, &n->work);
+ return;
+ }
+
