From: Jakub Kicinski <kuba@kernel.org>
To: javen <javen_xu@realsil.com.cn>
Cc: <hkallweit1@gmail.com>, <nic_swsd@realtek.com>,
<andrew+netdev@lunn.ch>, <davem@davemloft.net>,
<edumazet@google.com>, <pabeni@redhat.com>, <horms@kernel.org>,
<netdev@vger.kernel.org>, <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH net-next v10 5/7] r8169: add support and enable rss
Date: Mon, 10 Aug 2026 14:38:25 -0700 [thread overview]
Message-ID: <20260810143825.28a3d516@kernel.org> (raw)
In-Reply-To: <20260803021305.488-6-javen_xu@realsil.com.cn>
On Mon, 3 Aug 2026 10:13:03 +0800 javen wrote:
> From: Javen Xu <javen_xu@realsil.com.cn>
>
> This patch adds support and enable rss for RTL8127.
>
> Signed-off-by: Javen Xu <javen_xu@realsil.com.cn>
> ---
> Changes in v2:
> - some changes moved from Patch 2/7
>
> Changes in v3:
> - add struct rtl8169_rss_data. Allocate it dynamically when needed.
> - define rss_key as an u32 array
> - replace some magic bit numbers in rtl8169_set_rss_hash_opt() and
> rtl8125_set_rx_q_num()
> - use union to combine different rx descriptor, refactor struct RxDesc
> - remove dead code from rtl8169_double_check_rss_support()
>
> Changes in v4:
> - rename macro definition, e.g R8127_MAX_IRQ to R8127_MAX_NUM_IRQVEC
> - change hw_supp_indir_tbl_entries type to unsigned int
> - change init_rx_desc_type type to enum
> - remove rtl_check_rss_support(), add helper function
> rtl_hw_support_rss()
> - remove hw_curr_isr_ver, use irq_nvecs to judge whether we should
> enable vector interrupt mapping, use tp->num_rx_ring to judge whether
> we should enable rss
> - remove function rtl8169_double_check_rss_support(), use
> rtl8169_set_rx_ring_num() to set num_rx_ring according to tp->irq_nvecs
>
> Changes in v5:
> - no changes
>
> Changes in v6:
> - change rss_queue_num type from u8 to unsigned int
> - fix rx desc clear in rtl8169_rx_clear() for different desc type
> - clamping num_rx_ring with rounddown_pow_of_two()
>
> Changes in v7:
> - remove unused macro
> - change unfixed type in rtl8169_store_reta
>
> Changes in v8:
> - refill desc->addr when rx_desc reset
> - rtl8169_set_channels fixed in patch 7/7
>
> Changes in v9:
> - remove rtl8169_set_desc_dma_addr, only set desc dma addr for
> RX_DESC_TYPE_RSS desc
>
> Changes in v10:
> - Change rss_key to u8 array and write rss_key_reg as u32 values.
> Use get_unaligned_le32() to keep behavior consistent on big-endian
> and little-endian
> ---
> drivers/net/ethernet/realtek/r8169_main.c | 379 ++++++++++++++++++++--
> 1 file changed, 346 insertions(+), 33 deletions(-)
>
> diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
> index 31f6d0c2e3d1..4e571fcea092 100644
> --- a/drivers/net/ethernet/realtek/r8169_main.c
> +++ b/drivers/net/ethernet/realtek/r8169_main.c
> @@ -88,6 +88,19 @@
> #define R8127_MAX_TX_QUEUES 8
> #define R8169_DEFAULT_RX_QUEUES 1
> #define R8169_MAX_TX_QUEUES 1
> +#define R8127_MAX_NUM_IRQVEC 32
> +#define R8127_MIN_NUM_IRQVEC 30
> +#define R8169_IRQ_DEFAULT 1
> +#define RTL_RSS_KEY_SIZE 40
> +#define RSS_CPU_NUM_MASK GENMASK(18, 16)
> +#define RSS_HASH_MASK GENMASK(10, 8)
> +#define RTL_MAX_INDIRECTION_TABLE_ENTRIES 128
> +#define RXS_RSS_UDP BIT(27)
> +#define RXS_RSS_IPV4 BIT(28)
> +#define RXS_RSS_IPV6 BIT(29)
> +#define RXS_RSS_TCP BIT(30)
> +#define RXS_RSS_L3_TYPE_MASK (RXS_RSS_IPV4 | RXS_RSS_IPV6)
> +#define RXS_RSS_L4_TYPE_MASK (RXS_RSS_TCP | RXS_RSS_UDP)
>
> #define OCP_STD_PHY_BASE 0xa400
>
> @@ -595,6 +608,20 @@ enum rtl_register_content {
> #define ISRIMR_LINKCHG BIT(29)
> #define ISRIMR_TOK_Q0 BIT(8)
> #define ISRIMR_ROK_Q0 BIT(0)
> +#define RTL_DESC_TYPE_CTRL 0xd8
> +#define RSS_KEY_REG 0x4600
> +#define RSS_INDIRECTION_TBL_REG 0x4700
> +#define RSS_CTRL_TCP_IPV4_SUPP BIT(0)
> +#define RTL_DESC_TYPE_RSS BIT(1)
> +#define RSS_CTRL_IPV4_SUPP BIT(1)
> +#define RSS_CTRL_TCP_IPV6_SUPP BIT(2)
> +#define RSS_CTRL_IPV6_SUPP BIT(3)
> +#define RSS_CTRL_IPV6_EXT_SUPP BIT(4)
> +#define RSS_CTRL_TCP_IPV6_EXT_SUPP BIT(5)
> +#define RX_RES_RSS BIT(22)
> +#define RX_RUNT_RSS BIT(21)
> +#define RX_CRC_RSS BIT(20)
> +#define RTL_RX_Q_NUM_MASK GENMASK(4, 2)
> };
>
> enum rtl_desc_bit {
> @@ -652,6 +679,11 @@ enum rtl_rx_desc_bit {
> #define RxProtoIP (PID1 | PID0)
> #define RxProtoMask RxProtoIP
>
> +#define RX_UDPT_DESC_RSS BIT(19)
> +#define RX_TCPT_DESC_RSS BIT(18)
> +#define RX_UDPF_DESC_RSS BIT(16) /* UDP/IP checksum failed */
> +#define RX_TCPF_DESC_RSS BIT(15) /* TCP/IP checksum failed */
> +
> IPFail = (1 << 16), /* IP checksum failed */
> UDPFail = (1 << 15), /* UDP/IP checksum failed */
> TCPFail = (1 << 14), /* TCP/IP checksum failed */
> @@ -673,9 +705,27 @@ struct TxDesc {
> };
>
> struct RxDesc {
> - __le32 opts1;
> - __le32 opts2;
> - __le64 addr;
> + union {
> + /* RX_DESC_TYPE_DEFAULT */
> + struct {
> + __le32 opts1;
> + __le32 opts2;
> + __le64 addr;
> + };
> +
> + /* RX_DESC_TYPE_RSS */
> + struct {
> + union {
> + __le64 rss_addr;
> + struct {
> + __le32 rss_info;
> + __le32 rss_result;
> + } rss_dword;
> + };
> + __le32 rss_opts2;
> + __le32 rss_opts1;
> + };
> + };
> };
>
> struct ring_info {
> @@ -747,6 +797,11 @@ enum rtl_dash_type {
> RTL_DASH_25_BP,
> };
>
> +enum rx_desc_type {
> + RX_DESC_TYPE_DEFAULT,
> + RX_DESC_TYPE_RSS,
> +};
> +
> struct rtl8169_rx_ring {
> u32 cur_rx; /* Index of next Rx pkt. */
> u32 dirty_rx; /* Index for recycling. */
> @@ -756,6 +811,12 @@ struct rtl8169_rx_ring {
> struct page *rx_databuff[NUM_RX_DESC]; /* Rx data buffers */
> };
>
> +struct rtl8169_rss_data {
> + u8 rss_key[RTL_RSS_KEY_SIZE];
> + u8 rss_indir_tbl[RTL_MAX_INDIRECTION_TABLE_ENTRIES];
> + unsigned int hw_supp_indir_tbl_entries;
> +};
> +
> struct rtl8169_private {
> void __iomem *mmio_addr; /* memory map physical address */
> struct pci_dev *pci_dev;
> @@ -775,7 +836,9 @@ struct rtl8169_private {
> u16 tx_lpi_timer;
> u32 irq_mask;
> unsigned int hw_supp_num_rx_queues;
> + struct rtl8169_rss_data *rss_data;
> unsigned int irq_nvecs;
> + enum rx_desc_type init_rx_desc_type;
> struct clk *clk;
>
> struct {
> @@ -1605,6 +1668,11 @@ static bool rtl_dash_is_enabled(struct rtl8169_private *tp)
> }
> }
>
> +static bool rtl_hw_support_rss(struct rtl8169_private *tp)
> +{
> + return tp->mac_version == RTL_GIGA_MAC_VER_80;
> +}
> +
> static enum rtl_dash_type rtl_get_dash_type(struct rtl8169_private *tp)
> {
> switch (tp->mac_version) {
> @@ -1906,9 +1974,20 @@ static inline u32 rtl8169_tx_vlan_tag(struct sk_buff *skb)
> TxVlanTag | swab16(skb_vlan_tag_get(skb)) : 0x00;
> }
>
> -static void rtl8169_rx_vlan_tag(struct RxDesc *desc, struct sk_buff *skb)
> +static void rtl8169_rx_vlan_tag(struct rtl8169_private *tp,
> + struct RxDesc *desc,
> + struct sk_buff *skb)
> {
> - u32 opts2 = le32_to_cpu(desc->opts2);
> + u32 opts2;
> +
> + switch (tp->init_rx_desc_type) {
> + case RX_DESC_TYPE_RSS:
> + opts2 = le32_to_cpu(desc->rss_opts2);
> + break;
> + default:
> + opts2 = le32_to_cpu(desc->opts2);
> + break;
> + }
>
> if (opts2 & RxVlanTag)
> __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), swab16(opts2 & 0xffff));
> @@ -2736,17 +2815,27 @@ static void rtl_hw_reset(struct rtl8169_private *tp)
> rtl_loop_wait_low(tp, &rtl_chipcmd_cond, 100, 100);
> }
>
> +static void rtl8169_init_rss(struct rtl8169_private *tp)
> +{
> + for (int i = 0; i < tp->rss_data->hw_supp_indir_tbl_entries; i++)
> + tp->rss_data->rss_indir_tbl[i] = ethtool_rxfh_indir_default(i, tp->num_rx_rings);
> +
> + netdev_rss_key_fill(tp->rss_data->rss_key, RTL_RSS_KEY_SIZE);
> +}
> +
> static void rtl_setup_rx_params(struct rtl8169_private *tp)
> {
> tp->num_rx_rings = 1;
> switch (tp->mac_version) {
> case RTL_GIGA_MAC_VER_80:
> tp->hw_supp_num_rx_queues = R8169_MAX_RX_QUEUES;
> + tp->rss_data->hw_supp_indir_tbl_entries = RTL_MAX_INDIRECTION_TABLE_ENTRIES;
> break;
> default:
> tp->hw_supp_num_rx_queues = R8169_DEFAULT_RX_QUEUES;
> break;
> }
> + tp->init_rx_desc_type = RX_DESC_TYPE_DEFAULT;
> }
>
> static void rtl_request_firmware(struct rtl8169_private *tp)
> @@ -2871,6 +2960,58 @@ static void rtl_set_rx_max_size(struct rtl8169_private *tp)
> RTL_W16(tp, RxMaxSize, R8169_RX_BUF_SIZE + 1);
> }
>
> +static void rtl8169_store_rss_key(struct rtl8169_private *tp)
> +{
> + u8 *rss_key = tp->rss_data->rss_key;
> + const u16 rss_key_reg = RSS_KEY_REG;
> +
> + /* Write redirection table to HW */
> + for (int i = 0; i < RTL_RSS_KEY_SIZE; i += sizeof(u32))
> + RTL_W32(tp, rss_key_reg + i, get_unaligned_le32(rss_key + i));
you fetched packed word of the key with get_unaligned_le32()..
> +}
> +
> +static void rtl8169_store_reta(struct rtl8169_private *tp)
> +{
> + u8 *indir_tbl = tp->rss_data->rss_indir_tbl;
> + unsigned int i;
> +
> + /* Write redirection table to HW */
> + for (i = 0; i < tp->rss_data->hw_supp_indir_tbl_entries; i += 4) {
> + u32 reta = (u32)indir_tbl[i] |
> + (u32)indir_tbl[i + 1] << 8 |
> + (u32)indir_tbl[i + 2] << 16 |
> + (u32)indir_tbl[i + 3] << 24;
.. but the indir table you pack manually, why?
> + RTL_W32(tp, RSS_INDIRECTION_TBL_REG + i, reta);
> + }
> +}
> +
> +static void rtl8169_set_rss_hash_opt(struct rtl8169_private *tp)
> +{
> + u32 rss_ctrl;
> +
> + rss_ctrl = FIELD_PREP(RSS_CPU_NUM_MASK, ilog2(tp->num_rx_rings));
> +
> + /* Perform hash on these packet types */
> + rss_ctrl |= RSS_CTRL_TCP_IPV4_SUPP
> + | RSS_CTRL_IPV4_SUPP
> + | RSS_CTRL_IPV6_SUPP
> + | RSS_CTRL_IPV6_EXT_SUPP
> + | RSS_CTRL_TCP_IPV6_SUPP
> + | RSS_CTRL_TCP_IPV6_EXT_SUPP;
| should be at the end of the lines
> + rss_ctrl |= FIELD_PREP(RSS_HASH_MASK,
> + ilog2(tp->rss_data->hw_supp_indir_tbl_entries));
> +
> + RTL_W32(tp, RSS_CTRL_8125, rss_ctrl);
> +}
> +
> +static void rtl_set_rss_config(struct rtl8169_private *tp)
> +{
> + rtl8169_set_rss_hash_opt(tp);
> + rtl8169_store_reta(tp);
> + rtl8169_store_rss_key(tp);
> +}
> + /* enable rx descriptor type v4 and set queue num for rss*/
nit: missing space at the end of the comment
> - nvecs = pci_alloc_irq_vectors(pdev, 1, 1, flags);
> + nvecs = pci_alloc_irq_vectors(pdev, get_min_irq_nvecs(tp), get_max_irq_nvecs(tp), flags);
> +
> + if (nvecs < 0)
> + nvecs = pci_alloc_irq_vectors(pdev, 1, 1, flags);
Why the two calls to pci_alloc_irq_vectors() ?
It should select the best number of IRQs it can, so why not just call
pci_alloc_irq_vectors(pdev, 1, get_max_irq_nvecs(tp), flags);
note: please review the submission for unnecessarily going over 80
chars, we still prefer <=80 lines in netdev
> if (nvecs < 0)
> return nvecs;
next prev parent reply other threads:[~2026-08-10 21:38 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-03 2:12 [PATCH net-next v10 0/7] r8169: add RSS support for RTL8127 javen
2026-08-03 2:12 ` [PATCH net-next v10 1/7] r8169: add support for multi irqs javen
2026-08-03 2:13 ` [PATCH net-next v10 2/7] r8169: refactor RX path to prepare for multi-queue javen
2026-08-10 21:26 ` Jakub Kicinski
2026-08-03 2:13 ` [PATCH net-next v10 3/7] r8169: add support for new interrupt mapping javen
2026-08-10 21:29 ` Jakub Kicinski
2026-08-03 2:13 ` [PATCH net-next v10 4/7] r8169: enable " javen
2026-08-10 21:31 ` Jakub Kicinski
2026-08-03 2:13 ` [PATCH net-next v10 5/7] r8169: add support and enable rss javen
2026-08-10 21:31 ` Jakub Kicinski
2026-08-10 21:38 ` Jakub Kicinski [this message]
2026-08-03 2:13 ` [PATCH net-next v10 6/7] r8169: move struct ethtool_ops javen
2026-08-03 2:13 ` [PATCH net-next v10 7/7] r8169: support setting rx queue numbers via ethtool javen
2026-08-10 21:41 ` Jakub Kicinski
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260810143825.28a3d516@kernel.org \
--to=kuba@kernel.org \
--cc=andrew+netdev@lunn.ch \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=hkallweit1@gmail.com \
--cc=horms@kernel.org \
--cc=javen_xu@realsil.com.cn \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=nic_swsd@realtek.com \
--cc=pabeni@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.