ath11k: optimize RX path latency

This patch drops ath11k_hal_rx_parse_dst_ring_desc(). This function was
creating a huge amount of load, which lead to a signifcant latency delay
when processing data in the RX path.

Pegging the processing on a specific core and running perf --top we get
the following output when running HE80 at a fixed bandwidth of 1gbit.

with patch
    19.19%  [ath11k]       [k] ath11k_dp_process_rx
     5.02%  [ath11k]       [k] ath11k_dp_rx_tid_del_func
     4.39%  [kernel]       [k] v7_dma_inv_range
     4.15%  [kernel]       [k] __slab_alloc.constprop.1
     4.03%  [kernel]       [k] dev_gro_receive
     3.86%  [kernel]       [k] tcp_gro_receive
     3.07%  [ip_tables]    [k] ipt_do_table
     2.96%  [kernel]       [k] dma_cache_maint_page

without patch
    21.64%  [ath11k]       [k] ath11k_hal_rx_parse_dst_ring_desc
    10.80%  [ath11k]       [k] ath11k_dp_process_rx
     3.77%  [kernel]       [k] v7_dma_inv_range
     3.48%  [kernel]       [k] dev_gro_receive
     3.32%  [ath11k]       [k] ath11k_dp_rx_tid_del_func
     3.17%  [mac80211]     [k] ieee80211_rx_napi
     2.70%  [kernel]       [k] dma_cache_maint_page
     2.65%  [mac80211]     [k] ieee80211_sta_ps_transition

When removing the the bandwidth limit and rerunning the test we see an
overall throughput improvement of 3-400mbit when running 4x4 HE80.

Signed-off-by: Shashidhar Lakkavalli <slakkavalli@datto.com>
Signed-off-by: John Crispin <john@phrozen.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>

1 files changed, 1 insertions, 27 deletions

diff --git a/drivers/net/wireless/ath/ath11k/hal_rx.h b/drivers/net/wireless/ath/ath11k/hal_rx.h
index 96555e4f4ef3..2271bf56183b 100644
--- a/drivers/net/wireless/ath/ath11k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath11k/hal_rx.h
@@ -6,30 +6,6 @@
 #ifndef ATH11K_HAL_RX_H
 #define ATH11K_HAL_RX_H
 
-struct hal_rx_mpdu_meta {
-	u32 peer_meta;
-	u16 msdu_cnt;
-	u16 seq_num;
-	bool frag;
-	bool retry;
-	bool ampdu;
-	bool raw;
-};
-
-struct hal_rx_msdu_meta {
-	u32 cookie;
-	u32 msdu_len;
-	bool first;
-	bool last;
-	bool continuation;
-};
-
-struct hal_rx_meta_info {
-	enum hal_reo_dest_ring_push_reason push_reason;
-	struct hal_rx_mpdu_meta mpdu_meta;
-	struct hal_rx_msdu_meta msdu_meta;
-};
-
 struct hal_rx_wbm_rel_info {
 	u32 cookie;
 	enum hal_wbm_rel_src_module err_rel_src;
@@ -320,7 +296,7 @@ void ath11k_hal_reo_update_rx_reo_queue_status(struct ath11k_base *ab,
 					       struct hal_reo_status *status);
 int ath11k_hal_reo_process_status(u8 *reo_desc, u8 *status);
 void ath11k_hal_rx_msdu_link_info_get(void *link_desc, u32 *num_msdus,
-				      struct hal_rx_msdu_meta *meta,
+				      u32 *msdu_cookies,
 				      enum hal_rx_buf_return_buf_manager *rbm);
 void ath11k_hal_rx_msdu_link_desc_set(struct ath11k_base *ab, void *desc,
 				      void *link_desc,
@@ -331,8 +307,6 @@ void ath11k_hal_rx_buf_addr_info_get(void *desc, dma_addr_t *paddr,
 				     u32 *cookie, u8 *rbm);
 int ath11k_hal_desc_reo_parse_err(struct ath11k_base *ab, u32 *rx_desc,
 				  dma_addr_t *paddr, u32 *desc_bank);
-void ath11k_hal_rx_parse_dst_ring_desc(struct ath11k_base *ab, u32 *rx_desc,
-				       struct hal_rx_meta_info *meta_info);
 int ath11k_hal_wbm_desc_parse_err(struct ath11k_base *ab, void *desc,
 				  struct hal_rx_wbm_rel_info *rel_info);
 void ath11k_hal_rx_reo_ent_paddr_get(struct ath11k_base *ab, void *desc,