p71924506
/
linux_old1
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge branch 'big-tcp' 

Eric Dumazet says:

====================
tcp: BIG TCP implementation

This series implements BIG TCP as presented in netdev 0x15:

https://netdevconf.info/0x15/session.html?BIG-TCP

Jonathan Corbet made a nice summary: https://lwn.net/Articles/884104/

Standard TSO/GRO packet limit is 64KB

With BIG TCP, we allow bigger TSO/GRO packet sizes for IPv6 traffic.

Note that this feature is by default not enabled, because it might
break some eBPF programs assuming TCP header immediately follows IPv6 header.

While tcpdump recognizes the HBH/Jumbo header, standard pcap filters
are unable to skip over IPv6 extension headers.

Reducing number of packets traversing networking stack usually improves
performance, as shown on this experiment using a 100Gbit NIC, and 4K MTU.

'Standard' performance with current (74KB) limits.
for i in {1..10}; do ./netperf -t TCP_RR -H iroa23  -- -r80000,80000 -O MIN_LATENCY,P90_LATENCY,P99_LATENCY,THROUGHPUT|tail -1; done
77           138          183          8542.19
79           143          178          8215.28
70           117          164          9543.39
80           144          176          8183.71
78           126          155          9108.47
80           146          184          8115.19
71           113          165          9510.96
74           113          164          9518.74
79           137          178          8575.04
73           111          171          9561.73

Now enable BIG TCP on both hosts.

ip link set dev eth0 gro_max_size 185000 gso_max_size 185000
for i in {1..10}; do ./netperf -t TCP_RR -H iroa23  -- -r80000,80000 -O MIN_LATENCY,P90_LATENCY,P99_LATENCY,THROUGHPUT|tail -1; done
57           83           117          13871.38
64           118          155          11432.94
65           116          148          11507.62
60           105          136          12645.15
60           103          135          12760.34
60           102          134          12832.64
62           109          132          10877.68
58           82           115          14052.93
57           83           124          14212.58
57           82           119          14196.01

We see an increase of transactions per second, and lower latencies as well.

v7: adopt unsafe_memcpy() in mlx5 to avoid FORTIFY warnings.

v6: fix a compilation error for CONFIG_IPV6=n in
    "net: allow gso_max_size to exceed 65536", reported by kernel bots.

v5: Replaced two patches (that were adding new attributes) with patches
    from Alexander Duyck. Idea is to reuse existing gso_max_size/gro_max_size

v4: Rebased on top of Jakub series (Merge branch 'tso-gso-limit-split')
    max_tso_size is now family independent.

v3: Fixed a typo in RFC number (Alexander)
    Added Reviewed-by: tags from Tariq on mlx4/mlx5 parts.

v2: Removed the MAX_SKB_FRAGS change, this belongs to a different series.
    Addressed feedback, for Alexander and nvidia folks.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller 2022-05-16 10:18:56 +01:00
parent 5cf15ce3c8 de78960e02
commit 7fa2e481ff
30 changed files with 321 additions and 67 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
drivers/net/ethernet/amd/xgbe/xgbe.h
View File

@ -151,7 +151,8 @@
#define XGBE_TX_MAX_BUF_SIZE (0x3fff & ~(64 - 1))
/* Descriptors required for maximum contiguous TSO/GSO packet */
#define XGBE_TX_MAX_SPLIT ((GSO_MAX_SIZE / XGBE_TX_MAX_BUF_SIZE) + 1)
#define XGBE_TX_MAX_SPLIT \
((GSO_LEGACY_MAX_SIZE / XGBE_TX_MAX_BUF_SIZE) + 1)
/* Maximum possible descriptors needed for an SKB:
* - Maximum number of SKB frags

3
drivers/net/ethernet/mellanox/mlx4/en_netdev.c
View File

@ -3417,6 +3417,9 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
dev->min_mtu = ETH_MIN_MTU;
dev->max_mtu = priv->max_mtu;
/* supports LSOv2 packets. */
netif_set_tso_max_size(dev, GSO_MAX_SIZE);
mdev->pndev[port] = dev;
mdev->upper[port] = NULL;

47
drivers/net/ethernet/mellanox/mlx4/en_tx.c
View File

@ -43,6 +43,7 @@
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/indirect_call_wrapper.h>
#include <net/ipv6.h>
#include "mlx4_en.h"
@ -634,19 +635,28 @@ static int get_real_size(const struct sk_buff *skb,
struct net_device *dev,
int *lso_header_size,
bool *inline_ok,
void **pfrag)
void **pfrag,
int *hopbyhop)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
int real_size;
if (shinfo->gso_size) {
*inline_ok = false;
if (skb->encapsulation)
*hopbyhop = 0;
if (skb->encapsulation) {
*lso_header_size = (skb_inner_transport_header(skb) - skb->data) + inner_tcp_hdrlen(skb);
else
} else {
/* Detects large IPV6 TCP packets and prepares for removal of
* HBH header that has been pushed by ip6_xmit(),
* mainly so that tcpdump can dissect them.
*/
if (ipv6_has_hopopt_jumbo(skb))
*hopbyhop = sizeof(struct hop_jumbo_hdr);
*lso_header_size = skb_transport_offset(skb) + tcp_hdrlen(skb);
}
real_size = CTRL_SIZE + shinfo->nr_frags * DS_SIZE +
ALIGN(*lso_header_size + 4, DS_SIZE);
ALIGN(*lso_header_size - *hopbyhop + 4, DS_SIZE);
if (unlikely(*lso_header_size != skb_headlen(skb))) {
/* We add a segment for the skb linear buffer only if
* it contains data */
@ -873,6 +883,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
int desc_size;
int real_size;
u32 index, bf_index;
struct ipv6hdr *h6;
__be32 op_own;
int lso_header_size;
void *fragptr = NULL;
@ -881,6 +892,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
bool stop_queue;
bool inline_ok;
u8 data_offset;
int hopbyhop;
bool bf_ok;
tx_ind = skb_get_queue_mapping(skb);
@ -890,7 +902,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
goto tx_drop;
real_size = get_real_size(skb, shinfo, dev, &lso_header_size,
&inline_ok, &fragptr);
&inline_ok, &fragptr, &hopbyhop);
if (unlikely(!real_size))
goto tx_drop_count;
@ -943,7 +955,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
data = &tx_desc->data;
data_offset = offsetof(struct mlx4_en_tx_desc, data);
} else {
int lso_align = ALIGN(lso_header_size + 4, DS_SIZE);
int lso_align = ALIGN(lso_header_size - hopbyhop + 4, DS_SIZE);
data = (void *)&tx_desc->lso + lso_align;
data_offset = offsetof(struct mlx4_en_tx_desc, lso) + lso_align;
@ -1008,14 +1020,31 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
((ring->prod & ring->size) ?
cpu_to_be32(MLX4_EN_BIT_DESC_OWN) : 0);
lso_header_size -= hopbyhop;
/* Fill in the LSO prefix */
tx_desc->lso.mss_hdr_size = cpu_to_be32(
shinfo->gso_size << 16 | lso_header_size);
/* Copy headers;
* note that we already verified that it is linear */
memcpy(tx_desc->lso.header, skb->data, lso_header_size);
if (unlikely(hopbyhop)) {
/* remove the HBH header.
* Layout: [Ethernet header][IPv6 header][HBH][TCP header]
*/
memcpy(tx_desc->lso.header, skb->data, ETH_HLEN + sizeof(*h6));
h6 = (struct ipv6hdr *)((char *)tx_desc->lso.header + ETH_HLEN);
h6->nexthdr = IPPROTO_TCP;
/* Copy the TCP header after the IPv6 one */
memcpy(h6 + 1,
skb->data + ETH_HLEN + sizeof(*h6) +
sizeof(struct hop_jumbo_hdr),
tcp_hdrlen(skb));
/* Leave ipv6 payload_len set to 0, as LSO v2 specs request. */
} else {
/* Copy headers;
* note that we already verified that it is linear
*/
memcpy(tx_desc->lso.header, skb->data, lso_header_size);
}
ring->tso_packets++;
i = shinfo->gso_segs;

1
drivers/net/ethernet/mellanox/mlx5/core/en_main.c
View File

@ -4920,6 +4920,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
netdev->priv_flags |= IFF_UNICAST_FLT;
netif_set_tso_max_size(netdev, GSO_MAX_SIZE);
mlx5e_set_netdev_dev_addr(netdev);
mlx5e_ipsec_build_netdev(priv);
mlx5e_ktls_build_netdev(priv);

2
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
View File

@ -2038,7 +2038,7 @@ mlx5e_hw_gro_skb_has_enough_space(struct sk_buff *skb, u16 data_bcnt)
{
int nr_frags = skb_shinfo(skb)->nr_frags;
return PAGE_SIZE * nr_frags + data_bcnt <= GSO_MAX_SIZE;
return PAGE_SIZE * nr_frags + data_bcnt <= GRO_LEGACY_MAX_SIZE;
}
static void

111
drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
View File

@ -40,6 +40,7 @@
#include "en_accel/en_accel.h"
#include "en_accel/ipsec_rxtx.h"
#include "en/ptp.h"
#include <net/ipv6.h>
static void mlx5e_dma_unmap_wqe_err(struct mlx5e_txqsq *sq, u8 num_dma)
{
@ -91,6 +92,13 @@ static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode,
return min_t(u16, hlen, skb_headlen(skb));
}
#define MLX5_UNSAFE_MEMCPY_DISCLAIMER \
"This copy has been bounds-checked earlier in " \
"mlx5i_sq_calc_wqe_attr() and intentionally " \
"crosses a flex array boundary. Since it is " \
"performance sensitive, splitting the copy is " \
"undesirable."
static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs)
{
struct vlan_ethhdr *vhdr = (struct vlan_ethhdr *)start;
@ -100,7 +108,10 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs)
memcpy(&vhdr->addrs, skb->data, cpy1_sz);
vhdr->h_vlan_proto = skb->vlan_proto;
vhdr->h_vlan_TCI = cpu_to_be16(skb_vlan_tag_get(skb));
memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz);
unsafe_memcpy(&vhdr->h_vlan_encapsulated_proto,
skb->data + cpy1_sz,
cpy2_sz,
MLX5_UNSAFE_MEMCPY_DISCLAIMER);
}
static inline void
@ -130,23 +141,32 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
sq->stats->csum_none++;
}
/* Returns the number of header bytes that we plan
* to inline later in the transmit descriptor
*/
static inline u16
mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb)
mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb, int *hopbyhop)
{
struct mlx5e_sq_stats *stats = sq->stats;
u16 ihs;
*hopbyhop = 0;
if (skb->encapsulation) {
ihs = skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb);
stats->tso_inner_packets++;
stats->tso_inner_bytes += skb->len - ihs;
} else {
if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
ihs = skb_transport_offset(skb) + sizeof(struct udphdr);
else
} else {
ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
if (ipv6_has_hopopt_jumbo(skb)) {
*hopbyhop = sizeof(struct hop_jumbo_hdr);
ihs -= sizeof(struct hop_jumbo_hdr);
}
}
stats->tso_packets++;
stats->tso_bytes += skb->len - ihs;
stats->tso_bytes += skb->len - ihs - *hopbyhop;
}
return ihs;
@ -208,6 +228,7 @@ struct mlx5e_tx_attr {
__be16 mss;
u16 insz;
u8 opcode;
u8 hopbyhop;
};
struct mlx5e_tx_wqe_attr {
@ -244,14 +265,16 @@ static void mlx5e_sq_xmit_prepare(struct mlx5e_txqsq *sq, struct sk_buff *skb,
struct mlx5e_sq_stats *stats = sq->stats;
if (skb_is_gso(skb)) {
u16 ihs = mlx5e_tx_get_gso_ihs(sq, skb);
int hopbyhop;
u16 ihs = mlx5e_tx_get_gso_ihs(sq, skb, &hopbyhop);
*attr = (struct mlx5e_tx_attr) {
.opcode = MLX5_OPCODE_LSO,
.mss = cpu_to_be16(skb_shinfo(skb)->gso_size),
.ihs = ihs,
.num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs,
.headlen = skb_headlen(skb) - ihs,
.headlen = skb_headlen(skb) - ihs - hopbyhop,
.hopbyhop = hopbyhop,
};
stats->packets += skb_shinfo(skb)->gso_segs;
@ -365,7 +388,8 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
struct mlx5_wqe_eth_seg *eseg;
struct mlx5_wqe_data_seg *dseg;
struct mlx5e_tx_wqe_info *wi;
u16 ihs = attr->ihs;
struct ipv6hdr *h6;
struct mlx5e_sq_stats *stats = sq->stats;
int num_dma;
@ -379,21 +403,40 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
eseg->mss = attr->mss;
if (attr->ihs) {
if (skb_vlan_tag_present(skb)) {
eseg->inline_hdr.sz |= cpu_to_be16(attr->ihs + VLAN_HLEN);
mlx5e_insert_vlan(eseg->inline_hdr.start, skb, attr->ihs);
if (ihs) {
u8 *start = eseg->inline_hdr.start;
if (unlikely(attr->hopbyhop)) {
/* remove the HBH header.
* Layout: [Ethernet header][IPv6 header][HBH][TCP header]
*/
if (skb_vlan_tag_present(skb)) {
mlx5e_insert_vlan(start, skb, ETH_HLEN + sizeof(*h6));
ihs += VLAN_HLEN;
h6 = (struct ipv6hdr *)(start + sizeof(struct vlan_ethhdr));
} else {
unsafe_memcpy(start, skb->data,
ETH_HLEN + sizeof(*h6),
MLX5_UNSAFE_MEMCPY_DISCLAIMER);
h6 = (struct ipv6hdr *)(start + ETH_HLEN);
}
h6->nexthdr = IPPROTO_TCP;
/* Copy the TCP header after the IPv6 one */
memcpy(h6 + 1,
skb->data + ETH_HLEN + sizeof(*h6) +
sizeof(struct hop_jumbo_hdr),
tcp_hdrlen(skb));
/* Leave ipv6 payload_len set to 0, as LSO v2 specs request. */
} else if (skb_vlan_tag_present(skb)) {
mlx5e_insert_vlan(start, skb, ihs);
ihs += VLAN_HLEN;
stats->added_vlan_packets++;
} else {
eseg->inline_hdr.sz |= cpu_to_be16(attr->ihs);
unsafe_memcpy(eseg->inline_hdr.start, skb->data, attr->ihs,
/* This copy has been bounds-checked earlier in
* mlx5i_sq_calc_wqe_attr() and intentionally
* crosses a flex array boundary. Since it is
* performance sensitive, splitting the copy is
* undesirable.
*/);
unsafe_memcpy(eseg->inline_hdr.start, skb->data,
attr->ihs,
MLX5_UNSAFE_MEMCPY_DISCLAIMER);
}
eseg->inline_hdr.sz |= cpu_to_be16(ihs);
dseg += wqe_attr->ds_cnt_inl;
} else if (skb_vlan_tag_present(skb)) {
eseg->insert.type = cpu_to_be16(MLX5_ETH_WQE_INSERT_VLAN);
@ -404,7 +447,7 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
}
dseg += wqe_attr->ds_cnt_ids;
num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + attr->ihs,
num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + attr->ihs + attr->hopbyhop,
attr->headlen, dseg);
if (unlikely(num_dma < 0))
goto err_drop;
@ -924,12 +967,34 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
eseg->mss = attr.mss;
if (attr.ihs) {
memcpy(eseg->inline_hdr.start, skb->data, attr.ihs);
if (unlikely(attr.hopbyhop)) {
struct ipv6hdr *h6;
/* remove the HBH header.
* Layout: [Ethernet header][IPv6 header][HBH][TCP header]
*/
unsafe_memcpy(eseg->inline_hdr.start, skb->data,
ETH_HLEN + sizeof(*h6),
MLX5_UNSAFE_MEMCPY_DISCLAIMER);
h6 = (struct ipv6hdr *)((char *)eseg->inline_hdr.start + ETH_HLEN);
h6->nexthdr = IPPROTO_TCP;
/* Copy the TCP header after the IPv6 one */
unsafe_memcpy(h6 + 1,
skb->data + ETH_HLEN + sizeof(*h6) +
sizeof(struct hop_jumbo_hdr),
tcp_hdrlen(skb),
MLX5_UNSAFE_MEMCPY_DISCLAIMER);
/* Leave ipv6 payload_len set to 0, as LSO v2 specs request. */
} else {
unsafe_memcpy(eseg->inline_hdr.start, skb->data,
attr.ihs,
MLX5_UNSAFE_MEMCPY_DISCLAIMER);
}
eseg->inline_hdr.sz = cpu_to_be16(attr.ihs);
dseg += wqe_attr.ds_cnt_inl;
}
num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + attr.ihs,
num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + attr.ihs + attr.hopbyhop,
attr.headlen, dseg);
if (unlikely(num_dma < 0))
goto err_drop;

3
drivers/net/ethernet/sfc/ef100_nic.c
View File

@ -1008,7 +1008,8 @@ static int ef100_process_design_param(struct efx_nic *efx,
}
return 0;
case ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_LEN:
nic_data->tso_max_payload_len = min_t(u64, reader->value, GSO_MAX_SIZE);
nic_data->tso_max_payload_len = min_t(u64, reader->value,
GSO_LEGACY_MAX_SIZE);
netif_set_tso_max_size(efx->net_dev,
nic_data->tso_max_payload_len);
return 0;

3
drivers/net/ethernet/sfc/falcon/tx.c
View File

@ -98,7 +98,8 @@ unsigned int ef4_tx_max_skb_descs(struct ef4_nic *efx)
/* Possibly more for PCIe page boundaries within input fragments */
if (PAGE_SIZE > EF4_PAGE_SIZE)
max_descs += max_t(unsigned int, MAX_SKB_FRAGS,
DIV_ROUND_UP(GSO_MAX_SIZE, EF4_PAGE_SIZE));
DIV_ROUND_UP(GSO_LEGACY_MAX_SIZE,
EF4_PAGE_SIZE));
return max_descs;
}

3
drivers/net/ethernet/sfc/tx_common.c
View File

@ -416,7 +416,8 @@ unsigned int efx_tx_max_skb_descs(struct efx_nic *efx)
/* Possibly more for PCIe page boundaries within input fragments */
if (PAGE_SIZE > EFX_PAGE_SIZE)
max_descs += max_t(unsigned int, MAX_SKB_FRAGS,
DIV_ROUND_UP(GSO_MAX_SIZE, EFX_PAGE_SIZE));
DIV_ROUND_UP(GSO_LEGACY_MAX_SIZE,
EFX_PAGE_SIZE));
return max_descs;
}

3
drivers/net/ethernet/synopsys/dwc-xlgmac.h
View File

@ -38,7 +38,8 @@
#define XLGMAC_RX_DESC_MAX_DIRTY (XLGMAC_RX_DESC_CNT >> 3)
/* Descriptors required for maximum contiguous TSO/GSO packet */
#define XLGMAC_TX_MAX_SPLIT ((GSO_MAX_SIZE / XLGMAC_TX_MAX_BUF_SIZE) + 1)
#define XLGMAC_TX_MAX_SPLIT \
((GSO_LEGACY_MAX_SIZE / XLGMAC_TX_MAX_BUF_SIZE) + 1)
/* Maximum possible descriptors needed for a SKB */
#define XLGMAC_TX_MAX_DESC_NR (MAX_SKB_FRAGS + XLGMAC_TX_MAX_SPLIT + 2)

2
drivers/net/hyperv/rndis_filter.c
View File

@ -1349,7 +1349,7 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device,
struct net_device_context *net_device_ctx = netdev_priv(net);
struct ndis_offload hwcaps;
struct ndis_offload_params offloads;
unsigned int gso_max_size = GSO_MAX_SIZE;
unsigned int gso_max_size = GSO_LEGACY_MAX_SIZE;
int ret;
/* Find HW offload capabilities */

2
drivers/net/loopback.c
View File

@ -191,6 +191,8 @@ static void gen_lo_setup(struct net_device *dev,
dev->netdev_ops = dev_ops;
dev->needs_free_netdev = true;
dev->priv_destructor = dev_destructor;
netif_set_tso_max_size(dev, GSO_MAX_SIZE);
}
/* The loopback device is special. There is only one instance

1
drivers/net/veth.c
View File

@ -1647,6 +1647,7 @@ static void veth_setup(struct net_device *dev)
dev->hw_features = VETH_FEATURES;
dev->hw_enc_features = VETH_FEATURES;
dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE;
netif_set_tso_max_size(dev, GSO_MAX_SIZE);
}
/*

2
drivers/scsi/fcoe/fcoe.c
View File

@ -667,7 +667,7 @@ static void fcoe_netdev_features_change(struct fc_lport *lport,
if (netdev->features & NETIF_F_FSO) {
lport->seq_offload = 1;
lport->lso_max = netdev->gso_max_size;
lport->lso_max = min(netdev->gso_max_size, GSO_LEGACY_MAX_SIZE);
FCOE_NETDEV_DBG(netdev, "Supports LSO for max len 0x%x\n",
lport->lso_max);
} else {

1
include/linux/ipv6.h
View File

@ -145,6 +145,7 @@ struct inet6_skb_parm {
#define IP6SKB_L3SLAVE 64
#define IP6SKB_JUMBOGRAM 128
#define IP6SKB_SEG6 256
#define IP6SKB_FAKEJUMBO 512
};
#if defined(CONFIG_NET_L3_MASTER_DEV)

15
include/linux/netdevice.h
View File

@ -2161,7 +2161,11 @@ struct net_device {
struct bpf_prog __rcu *xdp_prog;
unsigned long gro_flush_timeout;
int napi_defer_hard_irqs;
#define GRO_MAX_SIZE 65536
#define GRO_LEGACY_MAX_SIZE 65536u
/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE),
* and shinfo->gso_segs is a 16bit field.
*/
#define GRO_MAX_SIZE (8 * 65535u)
unsigned int gro_max_size;
rx_handler_func_t __rcu *rx_handler;
void __rcu *rx_handler_data;
@ -2272,12 +2276,17 @@ struct net_device {
const struct rtnl_link_ops *rtnl_link_ops;
/* for setting kernel sock attribute on TCP connection setup */
#define GSO_MAX_SIZE 65536
#define GSO_MAX_SEGS 65535u
#define GSO_LEGACY_MAX_SIZE 65536u
/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE),
* and shinfo->gso_segs is a 16bit field.
*/
#define GSO_MAX_SIZE (8 * GSO_MAX_SEGS)
unsigned int gso_max_size;
#define TSO_LEGACY_MAX_SIZE 65536
#define TSO_MAX_SIZE UINT_MAX
unsigned int tso_max_size;
#define GSO_MAX_SEGS 65535
u16 gso_max_segs;
#define TSO_MAX_SEGS U16_MAX
u16 tso_max_segs;

44
include/net/ipv6.h
View File

@ -151,6 +151,17 @@ struct frag_hdr {
__be32 identification;
};
/*
* Jumbo payload option, as described in RFC 2675 2.
*/
struct hop_jumbo_hdr {
u8 nexthdr;
u8 hdrlen;
u8 tlv_type; /* IPV6_TLV_JUMBO, 0xC2 */
u8 tlv_len; /* 4 */
__be32 jumbo_payload_len;
};
#define IP6_MF 0x0001
#define IP6_OFFSET 0xFFF8
@ -456,6 +467,39 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb,
struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
struct ipv6_txoptions *opt);
/* This helper is specialized for BIG TCP needs.
* It assumes the hop_jumbo_hdr will immediately follow the IPV6 header.
* It assumes headers are already in skb->head.
* Returns 0, or IPPROTO_TCP if a BIG TCP packet is there.
*/
static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb)
{
const struct hop_jumbo_hdr *jhdr;
const struct ipv6hdr *nhdr;
if (likely(skb->len <= GRO_LEGACY_MAX_SIZE))
return 0;
if (skb->protocol != htons(ETH_P_IPV6))
return 0;
if (skb_network_offset(skb) +
sizeof(struct ipv6hdr) +
sizeof(struct hop_jumbo_hdr) > skb_headlen(skb))
return 0;
nhdr = ipv6_hdr(skb);
if (nhdr->nexthdr != NEXTHDR_HOP)
return 0;
jhdr = (const struct hop_jumbo_hdr *) (nhdr + 1);
if (jhdr->tlv_type != IPV6_TLV_JUMBO || jhdr->hdrlen != 0 ||
jhdr->nexthdr != IPPROTO_TCP)
return 0;
return jhdr->nexthdr;
}
static inline bool ipv6_accept_ra(struct inet6_dev *idev)
{
/* If forwarding is enabled, RA are not accepted unless the special

2
include/uapi/linux/if_link.h
View File

@ -368,6 +368,8 @@ enum {
IFLA_PARENT_DEV_NAME,
IFLA_PARENT_DEV_BUS_NAME,
IFLA_GRO_MAX_SIZE,
IFLA_TSO_MAX_SIZE,
IFLA_TSO_MAX_SEGS,
__IFLA_MAX
};

2
net/bpf/test_run.c
View File

@ -1001,7 +1001,7 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
cb->pkt_len = skb->len;
} else {
if (__skb->wire_len < skb->len ||
__skb->wire_len > GSO_MAX_SIZE)
__skb->wire_len > GSO_LEGACY_MAX_SIZE)
return -EINVAL;
cb->pkt_len = __skb->wire_len;
}

9
net/core/dev.c
View File

@ -2998,11 +2998,12 @@ EXPORT_SYMBOL(netif_set_real_num_queues);
* @size: max skb->len of a TSO frame
*
* Set the limit on the size of TSO super-frames the device can handle.
* Unless explicitly set the stack will assume the value of %GSO_MAX_SIZE.
* Unless explicitly set the stack will assume the value of
* %GSO_LEGACY_MAX_SIZE.
*/
void netif_set_tso_max_size(struct net_device *dev, unsigned int size)
{
dev->tso_max_size = size;
dev->tso_max_size = min(GSO_MAX_SIZE, size);
if (size < READ_ONCE(dev->gso_max_size))
netif_set_gso_max_size(dev, size);
}
@ -10595,9 +10596,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
dev_net_set(dev, &init_net);
dev->gso_max_size = GSO_MAX_SIZE;
dev->gso_max_size = GSO_LEGACY_MAX_SIZE;
dev->gso_max_segs = GSO_MAX_SEGS;
dev->gro_max_size = GRO_MAX_SIZE;
dev->gro_max_size = GRO_LEGACY_MAX_SIZE;
dev->tso_max_size = TSO_LEGACY_MAX_SIZE;
dev->tso_max_segs = TSO_MAX_SEGS;
dev->upper_level = 1;

8
net/core/gro.c
View File

@ -167,6 +167,14 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush))
return -E2BIG;
if (unlikely(p->len + len >= GRO_LEGACY_MAX_SIZE)) {
if (p->protocol != htons(ETH_P_IPV6) ||
skb_headroom(p) < sizeof(struct hop_jumbo_hdr) ||
ipv6_hdr(p)->nexthdr != IPPROTO_TCP ||
p->encapsulation)
return -E2BIG;
}
lp = NAPI_GRO_CB(p)->last;
pinfo = skb_shinfo(lp);

16
net/core/rtnetlink.c
View File

@ -1064,6 +1064,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(4) /* IFLA_GSO_MAX_SEGS */
+ nla_total_size(4) /* IFLA_GSO_MAX_SIZE */
+ nla_total_size(4) /* IFLA_GRO_MAX_SIZE */
+ nla_total_size(4) /* IFLA_TSO_MAX_SIZE */
+ nla_total_size(4) /* IFLA_TSO_MAX_SEGS */
+ nla_total_size(1) /* IFLA_OPERSTATE */
+ nla_total_size(1) /* IFLA_LINKMODE */
+ nla_total_size(4) /* IFLA_CARRIER_CHANGES */
@ -1769,6 +1771,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
nla_put_u32(skb, IFLA_GSO_MAX_SEGS, dev->gso_max_segs) ||
nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) ||
nla_put_u32(skb, IFLA_GRO_MAX_SIZE, dev->gro_max_size) ||
nla_put_u32(skb, IFLA_TSO_MAX_SIZE, dev->tso_max_size) ||
nla_put_u32(skb, IFLA_TSO_MAX_SEGS, dev->tso_max_segs) ||
#ifdef CONFIG_RPS
nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||
#endif
@ -1922,6 +1926,8 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_NEW_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1),
[IFLA_PARENT_DEV_NAME] = { .type = NLA_NUL_STRING },
[IFLA_GRO_MAX_SIZE] = { .type = NLA_U32 },
[IFLA_TSO_MAX_SIZE] = { .type = NLA_REJECT },
[IFLA_TSO_MAX_SEGS] = { .type = NLA_REJECT },
};
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@ -2354,14 +2360,6 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[],
}
}
if (tb[IFLA_GRO_MAX_SIZE]) {
u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_MAX_SIZE]);
if (gro_max_size > GRO_MAX_SIZE) {
NL_SET_ERR_MSG(extack, "too big gro_max_size");
return -EINVAL;
}
}
return 0;
}
@ -2811,7 +2809,7 @@ static int do_setlink(const struct sk_buff *skb,
if (tb[IFLA_GSO_MAX_SIZE]) {
u32 max_size = nla_get_u32(tb[IFLA_GSO_MAX_SIZE]);
if (max_size > GSO_MAX_SIZE || max_size > dev->tso_max_size) {
if (max_size > dev->tso_max_size) {
err = -EINVAL;
goto errout;
}

14
net/core/sock.c
View File

@ -2293,6 +2293,19 @@ void sk_free_unlock_clone(struct sock *sk)
}
EXPORT_SYMBOL_GPL(sk_free_unlock_clone);
static void sk_trim_gso_size(struct sock *sk)
{
if (sk->sk_gso_max_size <= GSO_LEGACY_MAX_SIZE)
return;
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6 &&
sk_is_tcp(sk) &&
!ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
return;
#endif
sk->sk_gso_max_size = GSO_LEGACY_MAX_SIZE;
}
void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
{
u32 max_segs = 1;
@ -2312,6 +2325,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
/* pairs with the WRITE_ONCE() in netif_set_gso_max_size() */
sk->sk_gso_max_size = READ_ONCE(dst->dev->gso_max_size);
sk_trim_gso_size(sk);
sk->sk_gso_max_size -= (MAX_TCP_HEADER + 1);
/* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */
max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1);

2
net/ipv4/tcp_bbr.c
View File

@ -310,7 +310,7 @@ static u32 bbr_tso_segs_goal(struct sock *sk)
*/
bytes = min_t(unsigned long,
sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift),
GSO_MAX_SIZE - 1 - MAX_TCP_HEADER);
GSO_LEGACY_MAX_SIZE - 1 - MAX_TCP_HEADER);
segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk));
return min(segs, 0x7FU);

4
net/ipv4/tcp_cubic.c
View File

@ -372,7 +372,7 @@ static void cubictcp_state(struct sock *sk, u8 new_state)
* We apply another 100% factor because @rate is doubled at this point.
* We cap the cushion to 1ms.
*/
static u32 hystart_ack_delay(struct sock *sk)
static u32 hystart_ack_delay(const struct sock *sk)
{
unsigned long rate;
@ -380,7 +380,7 @@ static u32 hystart_ack_delay(struct sock *sk)
if (!rate)
return 0;
return min_t(u64, USEC_PER_MSEC,
div64_ul((u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate));
div64_ul((u64)sk->sk_gso_max_size * 4 * USEC_PER_SEC, rate));
}
static void hystart_update(struct sock *sk, u32 delay)

2
net/ipv4/tcp_output.c
View File

@ -1553,7 +1553,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
* SO_SNDBUF values.
* Also allow first and last skb in retransmit queue to be split.
*/
limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE);
limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_LEGACY_MAX_SIZE);
if (unlikely((sk->sk_wmem_queued >> 1) > limit &&
tcp_queue != TCP_FRAG_IN_WRITE_QUEUE &&
skb != tcp_rtx_queue_head(sk) &&

56
net/ipv6/ip6_offload.c
View File

@ -77,7 +77,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct ipv6hdr *ipv6h;
const struct net_offload *ops;
int proto;
int proto, nexthdr;
struct frag_hdr *fptr;
unsigned int payload_len;
u8 *prevhdr;
@ -87,6 +87,28 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
bool gso_partial;
skb_reset_network_header(skb);
nexthdr = ipv6_has_hopopt_jumbo(skb);
if (nexthdr) {
const int hophdr_len = sizeof(struct hop_jumbo_hdr);
int err;
err = skb_cow_head(skb, 0);
if (err < 0)
return ERR_PTR(err);
/* remove the HBH header.
* Layout: [Ethernet header][IPv6 header][HBH][TCP header]
*/
memmove(skb_mac_header(skb) + hophdr_len,
skb_mac_header(skb),
ETH_HLEN + sizeof(struct ipv6hdr));
skb->data += hophdr_len;
skb->len -= hophdr_len;
skb->network_header += hophdr_len;
skb->mac_header += hophdr_len;
ipv6h = (struct ipv6hdr *)skb->data;
ipv6h->nexthdr = nexthdr;
}
nhoff = skb_network_header(skb) - skb_mac_header(skb);
if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
goto out;
@ -320,15 +342,43 @@ static struct sk_buff *ip4ip6_gro_receive(struct list_head *head,
INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
{
const struct net_offload *ops;
struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
struct ipv6hdr *iph;
int err = -ENOSYS;
u32 payload_len;
if (skb->encapsulation) {
skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6));
skb_set_inner_network_header(skb, nhoff);
}
iph->payload_len = htons(skb->len - nhoff - sizeof(*iph));
payload_len = skb->len - nhoff - sizeof(*iph);
if (unlikely(payload_len > IPV6_MAXPLEN)) {
struct hop_jumbo_hdr *hop_jumbo;
int hoplen = sizeof(*hop_jumbo);
/* Move network header left */
memmove(skb_mac_header(skb) - hoplen, skb_mac_header(skb),
skb->transport_header - skb->mac_header);
skb->data -= hoplen;
skb->len += hoplen;
skb->mac_header -= hoplen;
skb->network_header -= hoplen;
iph = (struct ipv6hdr *)(skb->data + nhoff);
hop_jumbo = (struct hop_jumbo_hdr *)(iph + 1);
/* Build hop-by-hop options */
hop_jumbo->nexthdr = iph->nexthdr;
hop_jumbo->hdrlen = 0;
hop_jumbo->tlv_type = IPV6_TLV_JUMBO;
hop_jumbo->tlv_len = 4;
hop_jumbo->jumbo_payload_len = htonl(payload_len + hoplen);
iph->nexthdr = NEXTHDR_HOP;
iph->payload_len = 0;
} else {
iph = (struct ipv6hdr *)(skb->data + nhoff);
iph->payload_len = htons(payload_len);
}
nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops);
if (WARN_ON(!ops || !ops->callbacks.gro_complete))

22
net/ipv6/ip6_output.c
View File

@ -182,7 +182,9 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
#endif
mtu = ip6_skb_dst_mtu(skb);
if (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))
if (skb_is_gso(skb) &&
!(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) &&
!skb_gso_validate_network_len(skb, mtu))
return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
if ((skb->len > mtu && !skb_is_gso(skb)) ||
@ -252,6 +254,8 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
struct inet6_dev *idev = ip6_dst_idev(dst);
struct hop_jumbo_hdr *hop_jumbo;
int hoplen = sizeof(*hop_jumbo);
unsigned int head_room;
struct ipv6hdr *hdr;
u8 proto = fl6->flowi6_proto;
@ -259,7 +263,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
int hlimit = -1;
u32 mtu;
head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dev);
head_room = sizeof(struct ipv6hdr) + hoplen + LL_RESERVED_SPACE(dev);
if (opt)
head_room += opt->opt_nflen + opt->opt_flen;
@ -282,6 +286,20 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
&fl6->saddr);
}
if (unlikely(seg_len > IPV6_MAXPLEN)) {
hop_jumbo = skb_push(skb, hoplen);
hop_jumbo->nexthdr = proto;
hop_jumbo->hdrlen = 0;
hop_jumbo->tlv_type = IPV6_TLV_JUMBO;
hop_jumbo->tlv_len = 4;
hop_jumbo->jumbo_payload_len = htonl(seg_len + hoplen);
proto = IPPROTO_HOPOPTS;
seg_len = 0;
IP6CB(skb)->flags |= IP6SKB_FAKEJUMBO;
}
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
hdr = ipv6_hdr(skb);

3
net/sctp/output.c
View File

@ -134,7 +134,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
dst_hold(tp->dst);
sk_setup_caps(sk, tp->dst);
}
packet->max_size = sk_can_gso(sk) ? READ_ONCE(tp->dst->dev->gso_max_size)
packet->max_size = sk_can_gso(sk) ? min(READ_ONCE(tp->dst->dev->gso_max_size),
GSO_LEGACY_MAX_SIZE)
: asoc->pathmtu;
rcu_read_unlock();
}

2
tools/include/uapi/linux/if_link.h
View File

@ -348,6 +348,8 @@ enum {
IFLA_PARENT_DEV_NAME,
IFLA_PARENT_DEV_BUS_NAME,
IFLA_GRO_MAX_SIZE,
IFLA_TSO_MAX_SIZE,
IFLA_TSO_MAX_SEGS,
__IFLA_MAX
};