From: Shin-Yi Lin USB RX Aggregation is a performance optimization technique used in USB network devices to increase throughput. Instead of sending every received network packet to the host computer individually, the device hardware groups multiple smaller packets into a single, large USB Bulk Transfer. * toAP/toNB use iperf3 respectively. With BE6000 - iperf3 tcp 10 pair (to another NB) RTL8832CU-USB3.0 before after TX 941 941 RX 847 919 RTL8832CU-USB2.0 before after TX 864 877 RX 864 902 RTL8851BU before after TX 115 114 RX 295 306 Signed-off-by: Shin-Yi Lin Signed-off-by: Ping-Ke Shih --- This one is to add USB RX aggregation to improve performance. The other one is TX aggregation, which we are working on. --- .../net/wireless/realtek/rtw89/rtw8851bu.c | 1 + .../net/wireless/realtek/rtw89/rtw8852au.c | 1 + .../net/wireless/realtek/rtw89/rtw8852bu.c | 1 + .../net/wireless/realtek/rtw89/rtw8852cu.c | 1 + drivers/net/wireless/realtek/rtw89/usb.c | 84 ++++++++++++++++--- drivers/net/wireless/realtek/rtw89/usb.h | 12 +++ 6 files changed, 87 insertions(+), 13 deletions(-) diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851bu.c b/drivers/net/wireless/realtek/rtw89/rtw8851bu.c index 959d62aefdd8..6a8d31544314 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8851bu.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8851bu.c @@ -15,6 +15,7 @@ static const struct rtw89_usb_info rtw8851b_usb_info = { .usb3_mac_npi_config_intf_0 = R_AX_USB3_MAC_NPI_CONFIG_INTF_0, .usb_endpoint_0 = R_AX_USB_ENDPOINT_0, .usb_endpoint_2 = R_AX_USB_ENDPOINT_2, + .rx_agg_alignment = 8, .bulkout_id = { [RTW89_DMA_ACH0] = 3, [RTW89_DMA_ACH1] = 4, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852au.c b/drivers/net/wireless/realtek/rtw89/rtw8852au.c index ccdbcc178c2a..4cced4619b7d 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852au.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852au.c @@ -15,6 +15,7 @@ static const struct rtw89_usb_info rtw8852a_usb_info = { .usb3_mac_npi_config_intf_0 = R_AX_USB3_MAC_NPI_CONFIG_INTF_0, .usb_endpoint_0 = R_AX_USB_ENDPOINT_0, .usb_endpoint_2 = R_AX_USB_ENDPOINT_2, + .rx_agg_alignment = 8, .bulkout_id = { [RTW89_DMA_ACH0] = 3, [RTW89_DMA_ACH2] = 5, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bu.c b/drivers/net/wireless/realtek/rtw89/rtw8852bu.c index 84cd3ec971f9..37111fed276f 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852bu.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852bu.c @@ -15,6 +15,7 @@ static const struct rtw89_usb_info rtw8852b_usb_info = { .usb3_mac_npi_config_intf_0 = R_AX_USB3_MAC_NPI_CONFIG_INTF_0, .usb_endpoint_0 = R_AX_USB_ENDPOINT_0, .usb_endpoint_2 = R_AX_USB_ENDPOINT_2, + .rx_agg_alignment = 8, .bulkout_id = { [RTW89_DMA_ACH0] = 3, [RTW89_DMA_ACH1] = 4, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852cu.c b/drivers/net/wireless/realtek/rtw89/rtw8852cu.c index 3b9825c92a0d..0c5aebaed873 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852cu.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852cu.c @@ -15,6 +15,7 @@ static const struct rtw89_usb_info rtw8852c_usb_info = { .usb3_mac_npi_config_intf_0 = R_AX_USB3_MAC_NPI_CONFIG_INTF_0_V1, .usb_endpoint_0 = R_AX_USB_ENDPOINT_0_V1, .usb_endpoint_2 = R_AX_USB_ENDPOINT_2_V1, + .rx_agg_alignment = 8, .bulkout_id = { [RTW89_DMA_ACH0] = 3, [RTW89_DMA_ACH2] = 5, diff --git a/drivers/net/wireless/realtek/rtw89/usb.c b/drivers/net/wireless/realtek/rtw89/usb.c index da1b7ce8089e..4482ce61592b 100644 --- a/drivers/net/wireless/realtek/rtw89/usb.c +++ b/drivers/net/wireless/realtek/rtw89/usb.c @@ -408,11 +408,14 @@ static int rtw89_usb_ops_tx_write(struct rtw89_dev *rtwdev, static void rtw89_usb_rx_handler(struct work_struct *work) { struct rtw89_usb *rtwusb = container_of(work, struct rtw89_usb, rx_work); + const struct rtw89_usb_info *info = rtwusb->info; struct rtw89_dev *rtwdev = rtwusb->rtwdev; struct rtw89_rx_desc_info desc_info; + s32 aligned_offset, remaining; struct sk_buff *rx_skb; struct sk_buff *skb; u32 pkt_offset; + u8 *pkt_ptr; int limit; for (limit = 0; limit < 200; limit++) { @@ -425,23 +428,38 @@ static void rtw89_usb_rx_handler(struct work_struct *work) goto free_or_reuse; } - memset(&desc_info, 0, sizeof(desc_info)); - rtw89_chip_query_rxdesc(rtwdev, &desc_info, rx_skb->data, 0); + pkt_ptr = rx_skb->data; + remaining = rx_skb->len; - skb = rtw89_alloc_skb_for_rx(rtwdev, desc_info.pkt_size); - if (!skb) { - rtw89_debug(rtwdev, RTW89_DBG_HCI, - "failed to allocate RX skb of size %u\n", - desc_info.pkt_size); - goto free_or_reuse; - } + do { + memset(&desc_info, 0, sizeof(desc_info)); + rtw89_chip_query_rxdesc(rtwdev, &desc_info, pkt_ptr, 0); - pkt_offset = desc_info.offset + desc_info.rxd_len; + pkt_offset = desc_info.offset + desc_info.rxd_len; + if (remaining < (pkt_offset + desc_info.pkt_size)) { + rtw89_debug(rtwdev, RTW89_DBG_HCI, + "Failed to get remaining RX pkt %u > %u\n", + pkt_offset + desc_info.pkt_size, remaining); + goto free_or_reuse; + } - skb_put_data(skb, rx_skb->data + pkt_offset, - desc_info.pkt_size); + skb = rtw89_alloc_skb_for_rx(rtwdev, desc_info.pkt_size); + if (!skb) { + rtw89_debug(rtwdev, RTW89_DBG_HCI, + "failed to allocate RX skb of size %u\n", + desc_info.pkt_size); + goto free_or_reuse; + } + + skb_put_data(skb, pkt_ptr + pkt_offset, desc_info.pkt_size); + rtw89_core_rx(rtwdev, &desc_info, skb); - rtw89_core_rx(rtwdev, &desc_info, skb); + /* next frame */ + pkt_offset += desc_info.pkt_size; + aligned_offset = ALIGN(pkt_offset, info->rx_agg_alignment); + pkt_ptr += aligned_offset; + remaining -= aligned_offset; + } while (remaining > 0); free_or_reuse: if (skb_queue_len(&rtwusb->rx_free_queue) >= RTW89_USB_RX_SKB_NUM) @@ -745,6 +763,44 @@ static int rtw89_usb_ops_mac_pre_deinit(struct rtw89_dev *rtwdev) return 0; /* Nothing to do. */ } +static void usb_rx_agg_cfg_v1(struct rtw89_dev *rtwdev) +{ + const u32 rxagg_0 = FIELD_PREP_CONST(B_AX_RXAGG_0_EN, 1) | + FIELD_PREP_CONST(B_AX_RXAGG_0_NUM_TH, 0) | + FIELD_PREP_CONST(B_AX_RXAGG_0_TIME_32US_TH, 32) | + FIELD_PREP_CONST(B_AX_RXAGG_0_BUF_SZ_4K, 5); + + rtw89_write32(rtwdev, R_AX_RXAGG_0, rxagg_0); +} + +static void usb_rx_agg_cfg_v2(struct rtw89_dev *rtwdev) +{ + const u32 rxagg_0 = FIELD_PREP_CONST(B_AX_RXAGG_0_EN, 1) | + FIELD_PREP_CONST(B_AX_RXAGG_0_NUM_TH, 255) | + FIELD_PREP_CONST(B_AX_RXAGG_0_TIME_32US_TH, 32) | + FIELD_PREP_CONST(B_AX_RXAGG_0_BUF_SZ_K, 20); + + rtw89_write32(rtwdev, R_AX_RXAGG_0_V1, rxagg_0); + rtw89_write32(rtwdev, R_AX_RXAGG_1_V1, 0x1F); +} + +static void usb_rx_agg_cfg(struct rtw89_dev *rtwdev) +{ + switch (rtwdev->chip->chip_id) { + case RTL8851B: + case RTL8852A: + case RTL8852B: + usb_rx_agg_cfg_v1(rtwdev); + break; + case RTL8852C: + usb_rx_agg_cfg_v2(rtwdev); + break; + default: + rtw89_warn(rtwdev, "%s: USB RX agg not support\n", __func__); + return; + } +} + static int rtw89_usb_ops_mac_post_init(struct rtw89_dev *rtwdev) { struct rtw89_usb *rtwusb = rtw89_usb_priv(rtwdev); @@ -773,6 +829,8 @@ static int rtw89_usb_ops_mac_post_init(struct rtw89_dev *rtwdev) rtw89_write8(rtwdev, info->usb_endpoint_2 + 1, NUMP); } + usb_rx_agg_cfg(rtwdev); + return 0; } diff --git a/drivers/net/wireless/realtek/rtw89/usb.h b/drivers/net/wireless/realtek/rtw89/usb.h index 203ec8e993e9..afc62c1f687f 100644 --- a/drivers/net/wireless/realtek/rtw89/usb.h +++ b/drivers/net/wireless/realtek/rtw89/usb.h @@ -20,6 +20,17 @@ #define RTW89_MAX_ENDPOINT_NUM 9 #define RTW89_MAX_BULKOUT_NUM 7 +#define R_AX_RXAGG_0_V1 0x6000 +#define B_AX_RXAGG_0_EN BIT(31) +#define B_AX_RXAGG_0_NUM_TH GENMASK(23, 16) +#define B_AX_RXAGG_0_TIME_32US_TH GENMASK(15, 8) +#define B_AX_RXAGG_0_BUF_SZ_K GENMASK(7, 0) + +#define R_AX_RXAGG_1_V1 0x6004 + +#define R_AX_RXAGG_0 0x8900 +#define B_AX_RXAGG_0_BUF_SZ_4K GENMASK(7, 0) + struct rtw89_usb_info { u32 usb_host_request_2; u32 usb_wlan0_1; @@ -27,6 +38,7 @@ struct rtw89_usb_info { u32 usb3_mac_npi_config_intf_0; u32 usb_endpoint_0; u32 usb_endpoint_2; + u8 rx_agg_alignment; u8 bulkout_id[RTW89_DMA_CH_NUM]; }; base-commit: 039cd522dc70151da13329a5e3ae19b1736f468a -- 2.25.1