mac80211: add a function for running rx without passing skbs to the stack

This can be used to run mac80211 rx processing on a batch of frames in NAPI
poll before passing them to the network stack in a large batch.
This can improve icache footprint, or it can be used to pass frames via
netif_receive_skb_list.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Link: https://lore.kernel.org/r/20200726110611.46886-1-nbd@nbd.name
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 6e26f0ba6fd09aa0f1f8105fe6d92da0b81b1f9e..66e2bfd165e82065c911e310aa7b144b455e57f8 100644 (file)
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -4360,6 +4360,31 @@ void ieee80211_free_hw(struct ieee80211_hw *hw);
  */
 void ieee80211_restart_hw(struct ieee80211_hw *hw);
 
+/**
+ * ieee80211_rx_list - receive frame and store processed skbs in a list
+ *
+ * Use this function to hand received frames to mac80211. The receive
+ * buffer in @skb must start with an IEEE 802.11 header. In case of a
+ * paged @skb is used, the driver is recommended to put the ieee80211
+ * header of the frame on the linear part of the @skb to avoid memory
+ * allocation and/or memcpy by the stack.
+ *
+ * This function may not be called in IRQ context. Calls to this function
+ * for a single hardware must be synchronized against each other. Calls to
+ * this function, ieee80211_rx_ni() and ieee80211_rx_irqsafe() may not be
+ * mixed for a single hardware. Must not run concurrently with
+ * ieee80211_tx_status() or ieee80211_tx_status_ni().
+ *
+ * This function must be called with BHs disabled and RCU read lock
+ *
+ * @hw: the hardware this frame came in on
+ * @sta: the station the frame was received from, or %NULL
+ * @skb: the buffer to receive, owned by mac80211 after this call
+ * @list: the destination list
+ */
+void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
+                      struct sk_buff *skb, struct list_head *list);
+
 /**
  * ieee80211_rx_napi - receive frame from NAPI context
  *

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 1760ce77d89f30878c5f0115d9d7b43743ed3b82..0b1eaec6649f71552c9b5da68ea6c742fa6aeb8e 100644 (file)
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -217,7 +217,7 @@ enum ieee80211_rx_flags {
 };
 
 struct ieee80211_rx_data {
-       struct napi_struct *napi;
+       struct list_head *list;
        struct sk_buff *skb;
        struct ieee80211_local *local;
        struct ieee80211_sub_if_data *sdata;

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 9ac3eaa00ce600f1984b82f489d07ec5b8d90b6f..836cde516a18c079213d9937e56d91c1f9e248f8 100644 (file)
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2578,8 +2578,8 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb,
                memset(skb->cb, 0, sizeof(skb->cb));
 
                /* deliver to local stack */
-               if (rx->napi)
-                       napi_gro_receive(rx->napi, skb);
+               if (rx->list)
+                       list_add_tail(&skb->list, rx->list);
                else
                        netif_receive_skb(skb);
        }
@@ -3869,7 +3869,6 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid)
                /* This is OK -- must be QoS data frame */
                .security_idx = tid,
                .seqno_idx = tid,
-               .napi = NULL, /* must be NULL to not have races */
        };
        struct tid_ampdu_rx *tid_agg_rx;
 
@@ -4479,8 +4478,8 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx,
        /* deliver to local stack */
        skb->protocol = eth_type_trans(skb, fast_rx->dev);
        memset(skb->cb, 0, sizeof(skb->cb));
-       if (rx->napi)
-               napi_gro_receive(rx->napi, skb);
+       if (rx->list)
+               list_add_tail(&skb->list, rx->list);
        else
                netif_receive_skb(skb);
 
@@ -4547,7 +4546,7 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx,
 static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
                                         struct ieee80211_sta *pubsta,
                                         struct sk_buff *skb,
-                                        struct napi_struct *napi)
+                                        struct list_head *list)
 {
        struct ieee80211_local *local = hw_to_local(hw);
        struct ieee80211_sub_if_data *sdata;
@@ -4562,7 +4561,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
        memset(&rx, 0, sizeof(rx));
        rx.skb = skb;
        rx.local = local;
-       rx.napi = napi;
+       rx.list = list;
 
        if (ieee80211_is_data(fc) || ieee80211_is_mgmt(fc))
                I802_DEBUG_INC(local->dot11ReceivedFragmentCount);
@@ -4670,8 +4669,8 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
  * This is the receive path handler. It is called by a low level driver when an
  * 802.11 MPDU is received from the hardware.
  */
-void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
-                      struct sk_buff *skb, struct napi_struct *napi)
+void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
+                      struct sk_buff *skb, struct list_head *list)
 {
        struct ieee80211_local *local = hw_to_local(hw);
        struct ieee80211_rate *rate = NULL;
@@ -4762,13 +4761,6 @@ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
 
        status->rx_flags = 0;
 
-       /*
-        * key references and virtual interfaces are protected using RCU
-        * and this requires that we are in a read-side RCU section during
-        * receive processing
-        */
-       rcu_read_lock();
-
        /*
         * Frames with failed FCS/PLCP checksum are not returned,
         * all other frames are returned without radiotap header
@@ -4776,23 +4768,47 @@ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
         * Also, frames with less than 16 bytes are dropped.
         */
        skb = ieee80211_rx_monitor(local, skb, rate);
-       if (!skb) {
-               rcu_read_unlock();
+       if (!skb)
                return;
-       }
 
        ieee80211_tpt_led_trig_rx(local,
                        ((struct ieee80211_hdr *)skb->data)->frame_control,
                        skb->len);
 
-       __ieee80211_rx_handle_packet(hw, pubsta, skb, napi);
-
-       rcu_read_unlock();
+       __ieee80211_rx_handle_packet(hw, pubsta, skb, list);
 
        return;
  drop:
        kfree_skb(skb);
 }
+EXPORT_SYMBOL(ieee80211_rx_list);
+
+void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
+                      struct sk_buff *skb, struct napi_struct *napi)
+{
+       struct sk_buff *tmp;
+       LIST_HEAD(list);
+
+
+       /*
+        * key references and virtual interfaces are protected using RCU
+        * and this requires that we are in a read-side RCU section during
+        * receive processing
+        */
+       rcu_read_lock();
+       ieee80211_rx_list(hw, pubsta, skb, &list);
+       rcu_read_unlock();
+
+       if (!napi) {
+               netif_receive_skb_list(&list);
+               return;
+       }
+
+       list_for_each_entry_safe(skb, tmp, &list, list) {
+               skb_list_del_init(skb);
+               napi_gro_receive(napi, skb);
+       }
+}
 EXPORT_SYMBOL(ieee80211_rx_napi);
 
 /* This is a version of the rx handler that can be called from hard irq