* [PATCH net-next 1/2] net: ethernet: mtk_eth_soc: add 9K jumbo frame
2026-11-01 22:58 [PATCH net-next 0/2] net: ethernet: mtk_eth_soc: 9K jumbo frame support Sandeep Haemoon
@ 2026-11-01 22:48 ` Sandeep Haemoon
2026-11-01 22:48 ` [PATCH net-next 2/2] net: ethernet: mtk_eth_soc: skip page_pool for Sandeep Haemoon
0 siblings, 1 reply; 3+ messages in thread
From: Sandeep Haemoon @ 2026-11-01 22:48 UTC (permalink / raw)
To: netdev
Cc: Felix Fietkau, Lorenzo Bianconi, linux-mediatek,
linux-arm-kernel, linux-kernel
The driver caps max_mtu at 2030 bytes and programs the MAC max-rx field
for at most 2048-byte frames, so MTU > 2K is rejected and 9K jumbo
frames are not usable on the 10G XGMII MACs.
Add a MTK_NETSYS_RX_9K capability for MT7988 and:
- advertise 9K max_mtu on XGMII MACs, derived from the DT phy_mode at
probe time so DSA can raise the conduit MTU before the netdev is
opened;
- program XMAC_RX_CFG2 on the XGMII MACs;
- derive the shared RX buffer length from the largest MTU and size the
RX rings from it;
- program the PDMA RX SDL max frame so the DMA engine accepts jumbo
frames;
- reject a runtime MTU change that would need a different ring buffer
size while DMA is running; the rings are sized at the next open.
This is a forward-port of the MediaTek downstream jumbo series:
Mason Chang's "change default rx buffer length", "add 9k jumbo frame
support" and "add dynamic rx buffer adjustment support" (MediaTek
OpenWrt feed 999-eth-30/31/33, carried in
frank-w/BPI-Router-Linux 92bfdbdd4de1/b4c6cb1d5532/ca4c976dce22),
plus Frank Wunderlich's "try to fix crash the right way"
(a3207a383794).
Link: https://github.com/frank-w/BPI-Router-Linux/commit/b4c6cb1d5532
Link: https://github.com/mediatek/mtk-openwrt-feeds
Signed-off-by: Sandeep Haemoon <sandeeph@loljews.com>
---
drivers/net/ethernet/mediatek/mtk_eth_soc.c | 137 ++++++++++++++++----
drivers/net/ethernet/mediatek/mtk_eth_soc.h | 9 +-
2 files changed, 118 insertions(+), 28 deletions(-)
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index ad0fdc413..b5f7b2a78 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -171,6 +171,7 @@ static const struct mtk_reg_map mt7988_reg_map = {
.glo_cfg = 0x6a04,
.rst_idx = 0x6a08,
.delay_irq = 0x6a0c,
+ .rx_cfg = 0x6a10,
.irq_status = 0x6a20,
.irq_mask = 0x6a28,
.adma_rx_dbg0 = 0x6a38,
@@ -554,6 +555,8 @@ static int mtk_mac_prepare(struct phylink_config *config, unsigned int mode,
return 0;
}
+static void mtk_set_mcr_max_rx(struct mtk_mac *mac, u32 val);
+
static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
const struct phylink_link_state *state)
{
@@ -647,6 +650,7 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
regmap_write(eth->ethsys, ETHSYS_SYSCFG0, val);
mac->interface = state->interface;
+ mtk_set_mcr_max_rx(mac, eth->rx_buf_len);
}
/* SGMII */
@@ -1242,22 +1246,22 @@ static void mtk_get_stats64(struct net_device *dev,
storage->tx_dropped = dev->stats.tx_dropped;
}
-static inline int mtk_max_frag_size(int mtu)
+static inline int mtk_max_frag_size(struct mtk_eth *eth, int mtu)
{
- /* make sure buf_size will be at least MTK_MAX_RX_LENGTH */
- if (mtu + MTK_RX_ETH_HLEN < MTK_MAX_RX_LENGTH_2K)
- mtu = MTK_MAX_RX_LENGTH_2K - MTK_RX_ETH_HLEN;
+ /* make sure buf_size will be at least max rx buffer length */
+ if (mtu + MTK_RX_ETH_HLEN < eth->rx_buf_len)
+ mtu = eth->rx_buf_len - MTK_RX_ETH_HLEN;
return SKB_DATA_ALIGN(MTK_RX_HLEN + mtu) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
}
-static inline int mtk_max_buf_size(int frag_size)
+static inline int mtk_max_buf_size(struct mtk_eth *eth, int frag_size)
{
int buf_size = frag_size - NET_SKB_PAD - NET_IP_ALIGN -
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
- WARN_ON(buf_size < MTK_MAX_RX_LENGTH_2K);
+ WARN_ON(buf_size < eth->rx_buf_len);
return buf_size;
}
@@ -1280,9 +1284,8 @@ static bool mtk_rx_get_desc(struct mtk_eth *eth, struct mtk_rx_dma_v2 *rxd,
return true;
}
-static void *mtk_max_lro_buf_alloc(gfp_t gfp_mask)
+static void *mtk_max_buf_alloc(unsigned int size, gfp_t gfp_mask)
{
- unsigned int size = mtk_max_frag_size(MTK_MAX_LRO_RX_LENGTH);
unsigned long data;
data = __get_free_pages(gfp_mask | __GFP_COMP | __GFP_NOWARN,
@@ -2310,7 +2313,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
if (ring->frag_size <= PAGE_SIZE)
new_data = napi_alloc_frag(ring->frag_size);
else
- new_data = mtk_max_lro_buf_alloc(GFP_ATOMIC);
+ new_data = mtk_max_buf_alloc(ring->frag_size, GFP_ATOMIC);
if (unlikely(!new_data)) {
netdev->stats.rx_dropped++;
@@ -2788,6 +2791,9 @@ static void mtk_tx_clean(struct mtk_eth *eth)
}
}
+static int mtk_max_gmac_mtu(struct mtk_eth *eth);
+static u32 mtk_rx_buf_len(struct mtk_eth *eth);
+
static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
{
const struct mtk_reg_map *reg_map = eth->soc->reg_map;
@@ -2812,8 +2818,8 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
rx_dma_size = soc->rx.dma_size;
}
- ring->frag_size = mtk_max_frag_size(rx_data_len);
- ring->buf_size = mtk_max_buf_size(ring->frag_size);
+ ring->frag_size = mtk_max_frag_size(eth, rx_data_len);
+ ring->buf_size = mtk_max_buf_size(eth, ring->frag_size);
ring->data = kcalloc(rx_dma_size, sizeof(*ring->data),
GFP_KERNEL);
if (!ring->data)
@@ -2852,7 +2858,7 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
if (ring->frag_size <= PAGE_SIZE)
data = netdev_alloc_frag(ring->frag_size);
else
- data = mtk_max_lro_buf_alloc(GFP_KERNEL);
+ data = mtk_max_buf_alloc(ring->frag_size, GFP_KERNEL);
if (!data)
return -ENOMEM;
@@ -3256,6 +3262,12 @@ static int mtk_dma_init(struct mtk_eth *eth)
if (mtk_dma_busy_wait(eth))
return -EBUSY;
+ /* Derived here, at ring allocation, so eth->rx_buf_len always describes
+ * the buffers the rings actually hold and mtk_mac_config() never lets
+ * a MAC accept a frame the rings cannot take.
+ */
+ eth->rx_buf_len = mtk_rx_buf_len(eth);
+
if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) {
/* QDMA needs scratch memory for internal reordering of the
* descriptors
@@ -3299,6 +3311,17 @@ static int mtk_dma_init(struct mtk_eth *eth)
mtk_w32(eth, 0x0, eth->soc->reg_map->qdma.hred);
}
+ /* Program the PDMA max RX frame (SDL) from rx_buf_len so jumbo
+ * frames up to it are accepted by the DMA engine.
+ */
+ if (mtk_is_netsys_v3_or_greater(eth)) {
+ u32 val = mtk_r32(eth, eth->soc->reg_map->pdma.rx_cfg);
+
+ mtk_w32(eth, val | ((MTK_PDMA_LRO_SDL + eth->rx_buf_len) <<
+ MTK_RX_CFG_SDL_OFFSET),
+ eth->soc->reg_map->pdma.rx_cfg);
+ }
+
return 0;
}
@@ -3600,6 +3623,24 @@ static int mtk_max_gmac_mtu(struct mtk_eth *eth)
return max_mtu;
}
+static u32 mtk_rx_buf_len_from_mtu(int max_mtu)
+{
+ int length = max_mtu + MTK_RX_ETH_HLEN;
+
+ if (length <= MTK_MAX_RX_LENGTH)
+ return MTK_MAX_RX_LENGTH;
+
+ return DIV_ROUND_UP(length, 1024) * 1024;
+}
+
+/* The rx rings are shared by every MAC, so their buffers are sized for the
+ * largest MTU configured on any of them.
+ */
+static u32 mtk_rx_buf_len(struct mtk_eth *eth)
+{
+ return mtk_rx_buf_len_from_mtu(mtk_max_gmac_mtu(eth));
+}
+
static int mtk_open(struct net_device *dev)
{
struct mtk_mac *mac = netdev_priv(dev);
@@ -3924,20 +3965,33 @@ static void mtk_set_mcr_max_rx(struct mtk_mac *mac, u32 val)
if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
return;
- mcr_cur = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id));
- mcr_new = mcr_cur & ~MAC_MCR_MAX_RX_MASK;
-
- if (val <= 1518)
- mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_1518);
- else if (val <= 1536)
- mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_1536);
- else if (val <= 1552)
- mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_1552);
- else
- mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_2048);
+ if (!mtk_interface_mode_is_xgmii(eth, mac->interface)) {
+ mcr_cur = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id));
+ mcr_new = mcr_cur & ~MAC_MCR_MAX_RX_MASK;
- if (mcr_new != mcr_cur)
- mtk_w32(mac->hw, mcr_new, MTK_MAC_MCR(mac->id));
+ if (val <= 1518)
+ mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_1518);
+ else if (val <= 1536)
+ mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_1536);
+ else if (val <= 1552)
+ mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_1552);
+ else
+ mcr_new |= MAC_MCR_MAX_RX(MAC_MCR_MAX_RX_2048);
+
+ if (mcr_new != mcr_cur)
+ mtk_w32(mac->hw, mcr_new, MTK_MAC_MCR(mac->id));
+ } else if (mtk_is_netsys_v3_or_greater(mac->hw) &&
+ mac->id != MTK_GMAC1_ID) {
+ mcr_cur = mtk_r32(mac->hw, MTK_XMAC_RX_CFG2(mac->id));
+
+ if (val < MTK_MAX_RX_LENGTH_9K)
+ mcr_new = FIELD_PREP(MTK_XMAC_MAX_RX_MASK, val);
+ else
+ mcr_new = MTK_MAX_RX_LENGTH_9K;
+
+ if (mcr_new != mcr_cur)
+ mtk_w32(mac->hw, mcr_new, MTK_XMAC_RX_CFG2(mac->id));
+ }
}
static void mtk_hw_reset(struct mtk_eth *eth)
@@ -4349,6 +4403,7 @@ static int mtk_change_mtu(struct net_device *dev, int new_mtu)
int length = new_mtu + MTK_RX_ETH_HLEN;
struct mtk_mac *mac = netdev_priv(dev);
struct mtk_eth *eth = mac->hw;
+ u32 rx_buf_len;
int max_mtu, i;
if (rcu_access_pointer(eth->prog) &&
@@ -4357,6 +4412,17 @@ static int mtk_change_mtu(struct net_device *dev, int new_mtu)
return -EINVAL;
}
+ /* The RX rings are shared and cannot be resized in place while DMA is
+ * running. Until the reallocation worker lands, reject a runtime MTU
+ * change that would need a different ring buffer size.
+ */
+ max_mtu = mtk_max_gmac_mtu(eth);
+ if (new_mtu > max_mtu)
+ max_mtu = new_mtu;
+ rx_buf_len = mtk_rx_buf_len_from_mtu(max_mtu);
+ if (refcount_read(ð->dma_refcnt) && rx_buf_len != eth->rx_buf_len)
+ return -EBUSY;
+
mtk_set_mcr_max_rx(mac, length);
WRITE_ONCE(dev->mtu, new_mtu);
@@ -4364,6 +4430,15 @@ static int mtk_change_mtu(struct net_device *dev, int new_mtu)
for (i = 0; i < ARRAY_SIZE(eth->ppe); i++)
mtk_ppe_update_mtu(eth->ppe[i], max_mtu);
+ eth->rx_buf_len = rx_buf_len;
+ if (mtk_is_netsys_v3_or_greater(eth)) {
+ u32 val = mtk_r32(eth, eth->soc->reg_map->pdma.rx_cfg);
+
+ mtk_w32(eth, val | ((MTK_PDMA_LRO_SDL + eth->rx_buf_len) <<
+ MTK_RX_CFG_SDL_OFFSET),
+ eth->soc->reg_map->pdma.rx_cfg);
+ }
+
return 0;
}
@@ -5009,8 +5084,14 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
eth->netdev[id]->irq = eth->irq[MTK_FE_IRQ_SHARED];
eth->netdev[id]->dev.of_node = np;
- if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
- eth->netdev[id]->max_mtu = MTK_MAX_RX_LENGTH - MTK_RX_ETH_HLEN;
+ /* DSA sets the conduit MTU (user MTU + tag) before the netdev is
+ * opened, so max_mtu must already be final here. Deriving it only
+ * in mtk_open() leaves the conduit at its 1504 default and blocks
+ * 9K frames on the DSA user ports.
+ */
+ if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_RX_9K) &&
+ mtk_interface_mode_is_xgmii(eth, phy_mode))
+ eth->netdev[id]->max_mtu = MTK_MAX_RX_LENGTH_9K - MTK_RX_ETH_HLEN;
else
eth->netdev[id]->max_mtu = MTK_MAX_RX_LENGTH_2K - MTK_RX_ETH_HLEN;
@@ -5151,6 +5232,8 @@ static int mtk_probe(struct platform_device *pdev)
spin_lock_init(ð->rx_irq_lock);
spin_lock_init(ð->dim_lock);
+ eth->rx_buf_len = MTK_MAX_RX_LENGTH;
+
eth->rx_dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
INIT_WORK(ð->rx_dim.work, mtk_dim_rx);
INIT_DELAYED_WORK(ð->reset.monitor_work, mtk_hw_reset_monitor_work);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 88a9b3b23..9aad21ea3 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -29,6 +29,7 @@
#define MTK_QDMA_PAGE_SIZE 2048
#define MTK_MAX_RX_LENGTH 1536
#define MTK_MAX_RX_LENGTH_2K 2048
+#define MTK_MAX_RX_LENGTH_9K 9216
#define MTK_TX_DMA_BUF_LEN 0x3fff
#define MTK_TX_DMA_BUF_LEN_V2 0xffff
#define MTK_QDMA_RING_SIZE 2048
@@ -530,6 +531,8 @@
/* XFI Mac control registers */
#define MTK_XMAC_BASE(x) (0x12000 + (((x) - 1) * 0x1000))
#define MTK_XMAC_MCR(x) (MTK_XMAC_BASE(x))
+#define MTK_XMAC_RX_CFG2(x) (MTK_XMAC_MCR(x) + 0xd0)
+#define MTK_XMAC_MAX_RX_MASK GENMASK(13, 0)
#define XMAC_MCR_TRX_DISABLE 0xf
#define XMAC_MCR_FORCE_TX_FC BIT(5)
#define XMAC_MCR_FORCE_RX_FC BIT(4)
@@ -985,6 +988,7 @@ enum mkt_eth_capabilities {
MTK_INFRA_BIT,
MTK_SHARED_SGMII_BIT,
MTK_HWLRO_BIT,
+ MTK_NETSYS_RX_9K_BIT,
MTK_SHARED_INT_BIT,
MTK_TRGMII_MT7621_CLK_BIT,
MTK_QDMA_BIT,
@@ -1026,6 +1030,7 @@ enum mkt_eth_capabilities {
#define MTK_INFRA BIT_ULL(MTK_INFRA_BIT)
#define MTK_SHARED_SGMII BIT_ULL(MTK_SHARED_SGMII_BIT)
#define MTK_HWLRO BIT_ULL(MTK_HWLRO_BIT)
+#define MTK_NETSYS_RX_9K BIT_ULL(MTK_NETSYS_RX_9K_BIT)
#define MTK_SHARED_INT BIT_ULL(MTK_SHARED_INT_BIT)
#define MTK_TRGMII_MT7621_CLK BIT_ULL(MTK_TRGMII_MT7621_CLK_BIT)
#define MTK_QDMA BIT_ULL(MTK_QDMA_BIT)
@@ -1127,7 +1132,7 @@ enum mkt_eth_capabilities {
#define MT7988_CAPS (MTK_36BIT_DMA | MTK_GDM1_ESW | MTK_GMAC2_2P5GPHY | \
MTK_MUX_GMAC2_TO_2P5GPHY | MTK_QDMA | MTK_RSTCTRL_PPE1 | \
- MTK_RSTCTRL_PPE2 | MTK_SRAM)
+ MTK_RSTCTRL_PPE2 | MTK_SRAM | MTK_NETSYS_RX_9K)
struct mtk_tx_dma_desc_info {
dma_addr_t addr;
@@ -1151,6 +1156,7 @@ struct mtk_reg_map {
u32 glo_cfg; /* global configuration */
u32 rst_idx; /* reset index */
u32 delay_irq; /* delay interrupt */
+ u32 rx_cfg; /* rx dma configuration */
u32 irq_status; /* interrupt status */
u32 irq_mask; /* interrupt mask */
u32 adma_rx_dbg0;
@@ -1314,6 +1320,7 @@ struct mtk_eth {
struct mtk_tx_ring tx_ring;
struct mtk_rx_ring rx_ring[MTK_MAX_RX_RING_NUM];
struct mtk_rx_ring rx_ring_qdma;
+ u32 rx_buf_len;
struct napi_struct tx_napi;
struct napi_struct rx_napi;
void *scratch_ring;
--
2.53.0
^ permalink raw reply [flat|nested] 3+ messages in thread