This series introduces XSK generic zerocopy xmit by adding XSK umem
pages as skb frags instead of copying data to linear space.
The only requirement for this for drivers is to be able to xmit skbs
with skb_headlen(skb) == 0, i.e. all data including hard headers
starts from frag 0.
To indicate whether a particular driver supports this, a new netdev
priv flag, IFF_TX_SKB_NO_LINEAR, is added (and declared in virtio_net
as it's already capable of doing it). So consider implementing this
in your drivers to greatly speed-up generic XSK xmit.
The first two bits refactor netdev_priv_flags a bit to harden them
in terms of bitfield overflow, as IFF_TX_SKB_NO_LINEAR is the last
one that fits into unsigned int.
The fifth patch adds headroom and tailroom reservations for the
allocated skbs on XSK generic xmit path. This ensures there won't
be any unwanted skb reallocations on fast-path due to headroom and/or
tailroom driver/device requirements (own headers/descriptors etc.).
The other three add a new private flag, declare it in virtio_net
driver and introduce generic XSK zerocopy xmit itself.
The main body of work is created and done by Xuan Zhuo. His original
cover letter:
v3:
Optimized code
v2:
1. add priv_flags IFF_TX_SKB_NO_LINEAR instead of netdev_feature
2. split the patch to three:
a. add priv_flags IFF_TX_SKB_NO_LINEAR
b. virtio net add priv_flags IFF_TX_SKB_NO_LINEAR
c. When there is support this flag, construct skb without linear
space
3. use ERR_PTR() and PTR_ERR() to handle the err
v1 message log:
---------------
This patch is used to construct skb based on page to save memory copy
overhead.
This has one problem:
We construct the skb by fill the data page as a frag into the skb. In
this way, the linear space is empty, and the header information is also
in the frag, not in the linear space, which is not allowed for some
network cards. For example, Mellanox Technologies MT27710 Family
[ConnectX-4 Lx] will get the following error message:
mlx5_core 0000:3b:00.1 eth1: Error cqe on cqn 0x817, ci 0x8,
qn 0x1dbb, opcode 0xd, syndrome 0x1, vendor syndrome 0x68
00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000030: 00 00 00 00 60 10 68 01 0a 00 1d bb 00 0f 9f d2
WQE DUMP: WQ size 1024 WQ cur size 0, WQE index 0xf, len: 64
00000000: 00 00 0f 0a 00 1d bb 03 00 00 00 08 00 00 00 00
00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000020: 00 00 00 2b 00 08 00 00 00 00 00 05 9e e3 08 00
00000030: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
mlx5_core 0000:3b:00.1 eth1: ERR CQE on SQ: 0x1dbb
I also tried to use build_skb to construct skb, but because of the
existence of skb_shinfo, it must be behind the linear space, so this
method is not working. We can't put skb_shinfo on desc->addr, it will be
exposed to users, this is not safe.
Finally, I added a feature NETIF_F_SKB_NO_LINEAR to identify whether the
network card supports the header information of the packet in the frag
and not in the linear space.
---------------- Performance Testing ------------
The test environment is Aliyun ECS server.
Test cmd:
```
xdpsock -i eth0 -t -S -s <msg size>
```
Test result data:
size 64 512 1024 1500
copy 1916747 1775988 1600203 1440054
page 1974058 1953655 1945463 1904478
percent 3.0% 10.0% 21.58% 32.3%
From v3 [0]:
- refactor netdev_priv_flags to make it easier to add new ones and
prevent bitwidth overflow;
- add headroom (both standard and zerocopy) and tailroom (standard)
reservation in skb for drivers to avoid potential reallocations;
- fix skb->truesize accounting;
- misc comment rewords.
[0] https://lore.kernel.org/netdev/[email protected]
Alexander Lobakin (3):
netdev_priv_flags: add missing IFF_PHONY_HEADROOM self-definition
netdevice: check for net_device::priv_flags bitfield overflow
xsk: respect device's headroom and tailroom on generic xmit path
Xuan Zhuo (3):
net: add priv_flags for allow tx skb without linear
virtio-net: support IFF_TX_SKB_NO_LINEAR
xsk: build skb by page (aka generic zerocopy xmit)
drivers/net/virtio_net.c | 3 +-
include/linux/netdevice.h | 138 +++++++++++++++++++++-----------------
net/xdp/xsk.c | 113 ++++++++++++++++++++++++++-----
3 files changed, 173 insertions(+), 81 deletions(-)
--
2.30.1
This is harmless for now, but comes fatal for the subsequent patch.
Fixes: 871b642adebe3 ("netdev: introduce ndo_set_rx_headroom")
Signed-off-by: Alexander Lobakin <[email protected]>
---
include/linux/netdevice.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b9bcbfde7849..b895973390ee 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1584,6 +1584,7 @@ enum netdev_priv_flags {
#define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE
#define IFF_TEAM IFF_TEAM
#define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED
+#define IFF_PHONY_HEADROOM IFF_PHONY_HEADROOM
#define IFF_MACSEC IFF_MACSEC
#define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER
#define IFF_FAILOVER IFF_FAILOVER
--
2.30.1
From: Xuan Zhuo <[email protected]>
Virtio net supports the case where the skb linear space is empty, so add
priv_flags.
Signed-off-by: Xuan Zhuo <[email protected]>
Acked-by: Michael S. Tsirkin <[email protected]>
Signed-off-by: Alexander Lobakin <[email protected]>
---
drivers/net/virtio_net.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ba8e63792549..f2ff6c3906c1 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2972,7 +2972,8 @@ static int virtnet_probe(struct virtio_device *vdev)
return -ENOMEM;
/* Set up network device as normal. */
- dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE;
+ dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE |
+ IFF_TX_SKB_NO_LINEAR;
dev->netdev_ops = &virtnet_netdev;
dev->features = NETIF_F_HIGHDMA;
--
2.30.1
From: Xuan Zhuo <[email protected]>
In some cases, we hope to construct skb directly based on the existing
memory without copying data. In this case, the page will be placed
directly in the skb, and the linear space of skb is empty. But
unfortunately, many the network card does not support this operation.
For example Mellanox Technologies MT27710 Family [ConnectX-4 Lx] will
get the following error message:
mlx5_core 0000:3b:00.1 eth1: Error cqe on cqn 0x817, ci 0x8,
qn 0x1dbb, opcode 0xd, syndrome 0x1, vendor syndrome 0x68
00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000030: 00 00 00 00 60 10 68 01 0a 00 1d bb 00 0f 9f d2
WQE DUMP: WQ size 1024 WQ cur size 0, WQE index 0xf, len: 64
00000000: 00 00 0f 0a 00 1d bb 03 00 00 00 08 00 00 00 00
00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000020: 00 00 00 2b 00 08 00 00 00 00 00 05 9e e3 08 00
00000030: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
mlx5_core 0000:3b:00.1 eth1: ERR CQE on SQ: 0x1dbb
So a priv_flag is added here to indicate whether the network card
supports this feature.
Signed-off-by: Xuan Zhuo <[email protected]>
Suggested-by: Alexander Lobakin <[email protected]>
[ alobakin: give a new flag more detailed description ]
Signed-off-by: Alexander Lobakin <[email protected]>
---
include/linux/netdevice.h | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index fa4ab77ce81e..86e19f62f978 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1525,6 +1525,8 @@ struct net_device_ops {
* @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device
* @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device
* @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running
+ * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with
+ * skb_headlen(skb) == 0 (data starts from frag0)
*/
enum netdev_priv_flags {
IFF_802_1Q_VLAN_BIT,
@@ -1558,6 +1560,7 @@ enum netdev_priv_flags {
IFF_FAILOVER_SLAVE_BIT,
IFF_L3MDEV_RX_HANDLER_BIT,
IFF_LIVE_RENAME_OK_BIT,
+ IFF_TX_SKB_NO_LINEAR_BIT,
NETDEV_PRIV_FLAG_COUNT,
};
@@ -1600,6 +1603,7 @@ static_assert(sizeof(netdev_priv_flags_t) * BITS_PER_BYTE <=
#define IFF_FAILOVER_SLAVE __IFF(FAILOVER_SLAVE)
#define IFF_L3MDEV_RX_HANDLER __IFF(L3MDEV_RX_HANDLER)
#define IFF_LIVE_RENAME_OK __IFF(LIVE_RENAME_OK)
+#define IFF_TX_SKB_NO_LINEAR __IFF(TX_SKB_NO_LINEAR)
/**
* struct net_device - The DEVICE structure.
--
2.30.1
xsk_generic_xmit() allocates a new skb and then queues it for
xmitting. The size of new skb's headroom is desc->len, so it comes
to the driver/device with no reserved headroom and/or tailroom.
Lots of drivers need some headroom (and sometimes tailroom) to
prepend (and/or append) some headers or data, e.g. CPU tags,
device-specific headers/descriptors (LSO, TLS etc.), and if case
of no available space skb_cow_head() will reallocate the skb.
Reallocations are unwanted on fast-path, especially when it comes
to XDP, so generic XSK xmit should reserve the spaces declared in
dev->needed_headroom and dev->needed tailroom to avoid them.
Note on max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom)):
Usually, output functions reserve LL_RESERVED_SPACE(dev), which
consists of dev->hard_header_len + dev->needed_headroom, aligned
by 16.
However, on XSK xmit hard header is already here in the chunk, so
hard_header_len is not needed. But it'd still be better to align
data up to cacheline, while reserving no less than driver requests
for headroom. NET_SKB_PAD here is to double-insure there will be
no reallocations even when the driver advertises no needed_headroom,
but in fact need it (not so rare case).
Fixes: 35fcde7f8deb ("xsk: support for Tx")
Signed-off-by: Alexander Lobakin <[email protected]>
---
net/xdp/xsk.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 4faabd1ecfd1..143979ea4165 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -454,12 +454,16 @@ static int xsk_generic_xmit(struct sock *sk)
struct sk_buff *skb;
unsigned long flags;
int err = 0;
+ u32 hr, tr;
mutex_lock(&xs->mutex);
if (xs->queue_id >= xs->dev->real_num_tx_queues)
goto out;
+ hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
+ tr = xs->dev->needed_tailroom;
+
while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) {
char *buffer;
u64 addr;
@@ -471,11 +475,13 @@ static int xsk_generic_xmit(struct sock *sk)
}
len = desc.len;
- skb = sock_alloc_send_skb(sk, len, 1, &err);
+ skb = sock_alloc_send_skb(sk, hr + len + tr, 1, &err);
if (unlikely(!skb))
goto out;
+ skb_reserve(skb, hr);
skb_put(skb, len);
+
addr = desc.addr;
buffer = xsk_buff_raw_get_data(xs->pool, addr);
err = skb_store_bits(skb, 0, buffer, len);
--
2.30.1
We almost ran out of unsigned int bitwidth. Define priv flags and
check for potential overflow in the fashion of netdev_features_t.
Defined this way, priv_flags can be easily expanded later with
just changing its typedef.
Signed-off-by: Alexander Lobakin <[email protected]>
---
include/linux/netdevice.h | 135 ++++++++++++++++++++------------------
1 file changed, 72 insertions(+), 63 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b895973390ee..fa4ab77ce81e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1527,70 +1527,79 @@ struct net_device_ops {
* @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running
*/
enum netdev_priv_flags {
- IFF_802_1Q_VLAN = 1<<0,
- IFF_EBRIDGE = 1<<1,
- IFF_BONDING = 1<<2,
- IFF_ISATAP = 1<<3,
- IFF_WAN_HDLC = 1<<4,
- IFF_XMIT_DST_RELEASE = 1<<5,
- IFF_DONT_BRIDGE = 1<<6,
- IFF_DISABLE_NETPOLL = 1<<7,
- IFF_MACVLAN_PORT = 1<<8,
- IFF_BRIDGE_PORT = 1<<9,
- IFF_OVS_DATAPATH = 1<<10,
- IFF_TX_SKB_SHARING = 1<<11,
- IFF_UNICAST_FLT = 1<<12,
- IFF_TEAM_PORT = 1<<13,
- IFF_SUPP_NOFCS = 1<<14,
- IFF_LIVE_ADDR_CHANGE = 1<<15,
- IFF_MACVLAN = 1<<16,
- IFF_XMIT_DST_RELEASE_PERM = 1<<17,
- IFF_L3MDEV_MASTER = 1<<18,
- IFF_NO_QUEUE = 1<<19,
- IFF_OPENVSWITCH = 1<<20,
- IFF_L3MDEV_SLAVE = 1<<21,
- IFF_TEAM = 1<<22,
- IFF_RXFH_CONFIGURED = 1<<23,
- IFF_PHONY_HEADROOM = 1<<24,
- IFF_MACSEC = 1<<25,
- IFF_NO_RX_HANDLER = 1<<26,
- IFF_FAILOVER = 1<<27,
- IFF_FAILOVER_SLAVE = 1<<28,
- IFF_L3MDEV_RX_HANDLER = 1<<29,
- IFF_LIVE_RENAME_OK = 1<<30,
+ IFF_802_1Q_VLAN_BIT,
+ IFF_EBRIDGE_BIT,
+ IFF_BONDING_BIT,
+ IFF_ISATAP_BIT,
+ IFF_WAN_HDLC_BIT,
+ IFF_XMIT_DST_RELEASE_BIT,
+ IFF_DONT_BRIDGE_BIT,
+ IFF_DISABLE_NETPOLL_BIT,
+ IFF_MACVLAN_PORT_BIT,
+ IFF_BRIDGE_PORT_BIT,
+ IFF_OVS_DATAPATH_BIT,
+ IFF_TX_SKB_SHARING_BIT,
+ IFF_UNICAST_FLT_BIT,
+ IFF_TEAM_PORT_BIT,
+ IFF_SUPP_NOFCS_BIT,
+ IFF_LIVE_ADDR_CHANGE_BIT,
+ IFF_MACVLAN_BIT,
+ IFF_XMIT_DST_RELEASE_PERM_BIT,
+ IFF_L3MDEV_MASTER_BIT,
+ IFF_NO_QUEUE_BIT,
+ IFF_OPENVSWITCH_BIT,
+ IFF_L3MDEV_SLAVE_BIT,
+ IFF_TEAM_BIT,
+ IFF_RXFH_CONFIGURED_BIT,
+ IFF_PHONY_HEADROOM_BIT,
+ IFF_MACSEC_BIT,
+ IFF_NO_RX_HANDLER_BIT,
+ IFF_FAILOVER_BIT,
+ IFF_FAILOVER_SLAVE_BIT,
+ IFF_L3MDEV_RX_HANDLER_BIT,
+ IFF_LIVE_RENAME_OK_BIT,
+
+ NETDEV_PRIV_FLAG_COUNT,
};
-#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN
-#define IFF_EBRIDGE IFF_EBRIDGE
-#define IFF_BONDING IFF_BONDING
-#define IFF_ISATAP IFF_ISATAP
-#define IFF_WAN_HDLC IFF_WAN_HDLC
-#define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE
-#define IFF_DONT_BRIDGE IFF_DONT_BRIDGE
-#define IFF_DISABLE_NETPOLL IFF_DISABLE_NETPOLL
-#define IFF_MACVLAN_PORT IFF_MACVLAN_PORT
-#define IFF_BRIDGE_PORT IFF_BRIDGE_PORT
-#define IFF_OVS_DATAPATH IFF_OVS_DATAPATH
-#define IFF_TX_SKB_SHARING IFF_TX_SKB_SHARING
-#define IFF_UNICAST_FLT IFF_UNICAST_FLT
-#define IFF_TEAM_PORT IFF_TEAM_PORT
-#define IFF_SUPP_NOFCS IFF_SUPP_NOFCS
-#define IFF_LIVE_ADDR_CHANGE IFF_LIVE_ADDR_CHANGE
-#define IFF_MACVLAN IFF_MACVLAN
-#define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM
-#define IFF_L3MDEV_MASTER IFF_L3MDEV_MASTER
-#define IFF_NO_QUEUE IFF_NO_QUEUE
-#define IFF_OPENVSWITCH IFF_OPENVSWITCH
-#define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE
-#define IFF_TEAM IFF_TEAM
-#define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED
-#define IFF_PHONY_HEADROOM IFF_PHONY_HEADROOM
-#define IFF_MACSEC IFF_MACSEC
-#define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER
-#define IFF_FAILOVER IFF_FAILOVER
-#define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE
-#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER
-#define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK
+typedef u32 netdev_priv_flags_t;
+static_assert(sizeof(netdev_priv_flags_t) * BITS_PER_BYTE <=
+ NETDEV_PRIV_FLAG_COUNT);
+
+#define __IFF_BIT(bit) ((netdev_priv_flags_t)1 << (bit))
+#define __IFF(name) __IFF_BIT(IFF_##name##_BIT)
+
+#define IFF_802_1Q_VLAN __IFF(802_1Q_VLAN)
+#define IFF_EBRIDGE __IFF(EBRIDGE)
+#define IFF_BONDING __IFF(BONDING)
+#define IFF_ISATAP __IFF(ISATAP)
+#define IFF_WAN_HDLC __IFF(WAN_HDLC)
+#define IFF_XMIT_DST_RELEASE __IFF(XMIT_DST_RELEASE)
+#define IFF_DONT_BRIDGE __IFF(DONT_BRIDGE)
+#define IFF_DISABLE_NETPOLL __IFF(DISABLE_NETPOLL)
+#define IFF_MACVLAN_PORT __IFF(MACVLAN_PORT)
+#define IFF_BRIDGE_PORT __IFF(BRIDGE_PORT)
+#define IFF_OVS_DATAPATH __IFF(OVS_DATAPATH)
+#define IFF_TX_SKB_SHARING __IFF(TX_SKB_SHARING)
+#define IFF_UNICAST_FLT __IFF(UNICAST_FLT)
+#define IFF_TEAM_PORT __IFF(TEAM_PORT)
+#define IFF_SUPP_NOFCS __IFF(SUPP_NOFCS)
+#define IFF_LIVE_ADDR_CHANGE __IFF(LIVE_ADDR_CHANGE)
+#define IFF_MACVLAN __IFF(MACVLAN)
+#define IFF_XMIT_DST_RELEASE_PERM __IFF(XMIT_DST_RELEASE_PERM)
+#define IFF_L3MDEV_MASTER __IFF(L3MDEV_MASTER)
+#define IFF_NO_QUEUE __IFF(NO_QUEUE)
+#define IFF_OPENVSWITCH __IFF(OPENVSWITCH)
+#define IFF_L3MDEV_SLAVE __IFF(L3MDEV_SLAVE)
+#define IFF_TEAM __IFF(TEAM)
+#define IFF_RXFH_CONFIGURED __IFF(RXFH_CONFIGURED)
+#define IFF_PHONY_HEADROOM __IFF(PHONY_HEADROOM)
+#define IFF_MACSEC __IFF(MACSEC)
+#define IFF_NO_RX_HANDLER __IFF(NO_RX_HANDLER)
+#define IFF_FAILOVER __IFF(FAILOVER)
+#define IFF_FAILOVER_SLAVE __IFF(FAILOVER_SLAVE)
+#define IFF_L3MDEV_RX_HANDLER __IFF(L3MDEV_RX_HANDLER)
+#define IFF_LIVE_RENAME_OK __IFF(LIVE_RENAME_OK)
/**
* struct net_device - The DEVICE structure.
@@ -1925,7 +1934,7 @@ struct net_device {
const struct header_ops *header_ops;
unsigned int flags;
- unsigned int priv_flags;
+ netdev_priv_flags_t priv_flags;
unsigned short gflags;
unsigned short padded;
--
2.30.1
From: Xuan Zhuo <[email protected]>
This patch is used to construct skb based on page to save memory copy
overhead.
This function is implemented based on IFF_TX_SKB_NO_LINEAR. Only the
network card priv_flags supports IFF_TX_SKB_NO_LINEAR will use page to
directly construct skb. If this feature is not supported, it is still
necessary to copy data to construct skb.
---------------- Performance Testing ------------
The test environment is Aliyun ECS server.
Test cmd:
```
xdpsock -i eth0 -t -S -s <msg size>
```
Test result data:
size 64 512 1024 1500
copy 1916747 1775988 1600203 1440054
page 1974058 1953655 1945463 1904478
percent 3.0% 10.0% 21.58% 32.3%
Signed-off-by: Xuan Zhuo <[email protected]>
Reviewed-by: Dust Li <[email protected]>
[ alobakin:
- expand subject to make it clearer;
- improve skb->truesize calculation;
- reserve some headroom in skb for drivers;
- tailroom is not needed as skb is non-linear ]
Signed-off-by: Alexander Lobakin <[email protected]>
---
net/xdp/xsk.c | 119 ++++++++++++++++++++++++++++++++++++++++----------
1 file changed, 95 insertions(+), 24 deletions(-)
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 143979ea4165..ff7bd06e1241 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -445,6 +445,96 @@ static void xsk_destruct_skb(struct sk_buff *skb)
sock_wfree(skb);
}
+static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
+ struct xdp_desc *desc)
+{
+ struct xsk_buff_pool *pool = xs->pool;
+ u32 hr, len, offset, copy, copied;
+ struct sk_buff *skb;
+ struct page *page;
+ void *buffer;
+ int err, i;
+ u64 addr;
+
+ hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
+
+ skb = sock_alloc_send_skb(&xs->sk, hr, 1, &err);
+ if (unlikely(!skb))
+ return ERR_PTR(err);
+
+ skb_reserve(skb, hr);
+
+ addr = desc->addr;
+ len = desc->len;
+
+ buffer = xsk_buff_raw_get_data(pool, addr);
+ offset = offset_in_page(buffer);
+ addr = buffer - pool->addrs;
+
+ for (copied = 0, i = 0; copied < len; i++) {
+ page = pool->umem->pgs[addr >> PAGE_SHIFT];
+ get_page(page);
+
+ copy = min_t(u32, PAGE_SIZE - offset, len - copied);
+ skb_fill_page_desc(skb, i, page, offset, copy);
+
+ copied += copy;
+ addr += copy;
+ offset = 0;
+ }
+
+ skb->len += len;
+ skb->data_len += len;
+ skb->truesize += pool->unaligned ? len : pool->chunk_size;
+
+ refcount_add(skb->truesize, &xs->sk.sk_wmem_alloc);
+
+ return skb;
+}
+
+static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
+ struct xdp_desc *desc)
+{
+ struct net_device *dev = xs->dev;
+ struct sk_buff *skb;
+
+ if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) {
+ skb = xsk_build_skb_zerocopy(xs, desc);
+ if (IS_ERR(skb))
+ return skb;
+ } else {
+ u32 hr, tr, len;
+ void *buffer;
+ int err;
+
+ hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom));
+ tr = dev->needed_tailroom;
+ len = desc->len;
+
+ skb = sock_alloc_send_skb(&xs->sk, hr + len + tr, 1, &err);
+ if (unlikely(!skb))
+ return ERR_PTR(err);
+
+ skb_reserve(skb, hr);
+ skb_put(skb, len);
+
+ buffer = xsk_buff_raw_get_data(xs->pool, desc->addr);
+ err = skb_store_bits(skb, 0, buffer, len);
+ if (unlikely(err)) {
+ kfree_skb(skb);
+ return ERR_PTR(err);
+ }
+ }
+
+ skb->dev = dev;
+ skb->priority = xs->sk.sk_priority;
+ skb->mark = xs->sk.sk_mark;
+ skb_shinfo(skb)->destructor_arg = (void *)(long)desc->addr;
+ skb->destructor = xsk_destruct_skb;
+
+ return skb;
+}
+
static int xsk_generic_xmit(struct sock *sk)
{
struct xdp_sock *xs = xdp_sk(sk);
@@ -454,56 +544,37 @@ static int xsk_generic_xmit(struct sock *sk)
struct sk_buff *skb;
unsigned long flags;
int err = 0;
- u32 hr, tr;
mutex_lock(&xs->mutex);
if (xs->queue_id >= xs->dev->real_num_tx_queues)
goto out;
- hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
- tr = xs->dev->needed_tailroom;
-
while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) {
- char *buffer;
- u64 addr;
- u32 len;
-
if (max_batch-- == 0) {
err = -EAGAIN;
goto out;
}
- len = desc.len;
- skb = sock_alloc_send_skb(sk, hr + len + tr, 1, &err);
- if (unlikely(!skb))
+ skb = xsk_build_skb(xs, &desc);
+ if (IS_ERR(skb)) {
+ err = PTR_ERR(skb);
goto out;
+ }
- skb_reserve(skb, hr);
- skb_put(skb, len);
-
- addr = desc.addr;
- buffer = xsk_buff_raw_get_data(xs->pool, addr);
- err = skb_store_bits(skb, 0, buffer, len);
/* This is the backpressure mechanism for the Tx path.
* Reserve space in the completion queue and only proceed
* if there is space in it. This avoids having to implement
* any buffering in the Tx path.
*/
spin_lock_irqsave(&xs->pool->cq_lock, flags);
- if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) {
+ if (xskq_prod_reserve(xs->pool->cq)) {
spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
kfree_skb(skb);
goto out;
}
spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
- skb->dev = xs->dev;
- skb->priority = sk->sk_priority;
- skb->mark = sk->sk_mark;
- skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr;
- skb->destructor = xsk_destruct_skb;
-
err = __dev_direct_xmit(skb, xs->queue_id);
if (err == NETDEV_TX_BUSY) {
/* Tell user-space to retry the send */
--
2.30.1
On Tue, Feb 16, 2021 at 12:44 PM Alexander Lobakin <[email protected]> wrote:
>
> From: Xuan Zhuo <[email protected]>
>
> This patch is used to construct skb based on page to save memory copy
> overhead.
>
> This function is implemented based on IFF_TX_SKB_NO_LINEAR. Only the
> network card priv_flags supports IFF_TX_SKB_NO_LINEAR will use page to
> directly construct skb. If this feature is not supported, it is still
> necessary to copy data to construct skb.
>
> ---------------- Performance Testing ------------
>
> The test environment is Aliyun ECS server.
> Test cmd:
> ```
> xdpsock -i eth0 -t -S -s <msg size>
> ```
>
> Test result data:
>
> size 64 512 1024 1500
> copy 1916747 1775988 1600203 1440054
> page 1974058 1953655 1945463 1904478
> percent 3.0% 10.0% 21.58% 32.3%
>
> Signed-off-by: Xuan Zhuo <[email protected]>
> Reviewed-by: Dust Li <[email protected]>
> [ alobakin:
> - expand subject to make it clearer;
> - improve skb->truesize calculation;
> - reserve some headroom in skb for drivers;
> - tailroom is not needed as skb is non-linear ]
> Signed-off-by: Alexander Lobakin <[email protected]>
Thank you Alexander!
Acked-by: Magnus Karlsson <[email protected]>
> ---
> net/xdp/xsk.c | 119 ++++++++++++++++++++++++++++++++++++++++----------
> 1 file changed, 95 insertions(+), 24 deletions(-)
>
> diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
> index 143979ea4165..ff7bd06e1241 100644
> --- a/net/xdp/xsk.c
> +++ b/net/xdp/xsk.c
> @@ -445,6 +445,96 @@ static void xsk_destruct_skb(struct sk_buff *skb)
> sock_wfree(skb);
> }
>
> +static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
> + struct xdp_desc *desc)
> +{
> + struct xsk_buff_pool *pool = xs->pool;
> + u32 hr, len, offset, copy, copied;
> + struct sk_buff *skb;
> + struct page *page;
> + void *buffer;
> + int err, i;
> + u64 addr;
> +
> + hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
> +
> + skb = sock_alloc_send_skb(&xs->sk, hr, 1, &err);
> + if (unlikely(!skb))
> + return ERR_PTR(err);
> +
> + skb_reserve(skb, hr);
> +
> + addr = desc->addr;
> + len = desc->len;
> +
> + buffer = xsk_buff_raw_get_data(pool, addr);
> + offset = offset_in_page(buffer);
> + addr = buffer - pool->addrs;
> +
> + for (copied = 0, i = 0; copied < len; i++) {
> + page = pool->umem->pgs[addr >> PAGE_SHIFT];
> + get_page(page);
> +
> + copy = min_t(u32, PAGE_SIZE - offset, len - copied);
> + skb_fill_page_desc(skb, i, page, offset, copy);
> +
> + copied += copy;
> + addr += copy;
> + offset = 0;
> + }
> +
> + skb->len += len;
> + skb->data_len += len;
> + skb->truesize += pool->unaligned ? len : pool->chunk_size;
> +
> + refcount_add(skb->truesize, &xs->sk.sk_wmem_alloc);
> +
> + return skb;
> +}
> +
> +static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
> + struct xdp_desc *desc)
> +{
> + struct net_device *dev = xs->dev;
> + struct sk_buff *skb;
> +
> + if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) {
> + skb = xsk_build_skb_zerocopy(xs, desc);
> + if (IS_ERR(skb))
> + return skb;
> + } else {
> + u32 hr, tr, len;
> + void *buffer;
> + int err;
> +
> + hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom));
> + tr = dev->needed_tailroom;
> + len = desc->len;
> +
> + skb = sock_alloc_send_skb(&xs->sk, hr + len + tr, 1, &err);
> + if (unlikely(!skb))
> + return ERR_PTR(err);
> +
> + skb_reserve(skb, hr);
> + skb_put(skb, len);
> +
> + buffer = xsk_buff_raw_get_data(xs->pool, desc->addr);
> + err = skb_store_bits(skb, 0, buffer, len);
> + if (unlikely(err)) {
> + kfree_skb(skb);
> + return ERR_PTR(err);
> + }
> + }
> +
> + skb->dev = dev;
> + skb->priority = xs->sk.sk_priority;
> + skb->mark = xs->sk.sk_mark;
> + skb_shinfo(skb)->destructor_arg = (void *)(long)desc->addr;
> + skb->destructor = xsk_destruct_skb;
> +
> + return skb;
> +}
> +
> static int xsk_generic_xmit(struct sock *sk)
> {
> struct xdp_sock *xs = xdp_sk(sk);
> @@ -454,56 +544,37 @@ static int xsk_generic_xmit(struct sock *sk)
> struct sk_buff *skb;
> unsigned long flags;
> int err = 0;
> - u32 hr, tr;
>
> mutex_lock(&xs->mutex);
>
> if (xs->queue_id >= xs->dev->real_num_tx_queues)
> goto out;
>
> - hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
> - tr = xs->dev->needed_tailroom;
> -
> while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) {
> - char *buffer;
> - u64 addr;
> - u32 len;
> -
> if (max_batch-- == 0) {
> err = -EAGAIN;
> goto out;
> }
>
> - len = desc.len;
> - skb = sock_alloc_send_skb(sk, hr + len + tr, 1, &err);
> - if (unlikely(!skb))
> + skb = xsk_build_skb(xs, &desc);
> + if (IS_ERR(skb)) {
> + err = PTR_ERR(skb);
> goto out;
> + }
>
> - skb_reserve(skb, hr);
> - skb_put(skb, len);
> -
> - addr = desc.addr;
> - buffer = xsk_buff_raw_get_data(xs->pool, addr);
> - err = skb_store_bits(skb, 0, buffer, len);
> /* This is the backpressure mechanism for the Tx path.
> * Reserve space in the completion queue and only proceed
> * if there is space in it. This avoids having to implement
> * any buffering in the Tx path.
> */
> spin_lock_irqsave(&xs->pool->cq_lock, flags);
> - if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) {
> + if (xskq_prod_reserve(xs->pool->cq)) {
> spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
> kfree_skb(skb);
> goto out;
> }
> spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
>
> - skb->dev = xs->dev;
> - skb->priority = sk->sk_priority;
> - skb->mark = sk->sk_mark;
> - skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr;
> - skb->destructor = xsk_destruct_skb;
> -
> err = __dev_direct_xmit(skb, xs->queue_id);
> if (err == NETDEV_TX_BUSY) {
> /* Tell user-space to retry the send */
> --
> 2.30.1
>
>
On Tue, Feb 16, 2021 at 12:44 PM Alexander Lobakin <[email protected]> wrote:
>
> xsk_generic_xmit() allocates a new skb and then queues it for
> xmitting. The size of new skb's headroom is desc->len, so it comes
> to the driver/device with no reserved headroom and/or tailroom.
> Lots of drivers need some headroom (and sometimes tailroom) to
> prepend (and/or append) some headers or data, e.g. CPU tags,
> device-specific headers/descriptors (LSO, TLS etc.), and if case
> of no available space skb_cow_head() will reallocate the skb.
> Reallocations are unwanted on fast-path, especially when it comes
> to XDP, so generic XSK xmit should reserve the spaces declared in
> dev->needed_headroom and dev->needed tailroom to avoid them.
>
> Note on max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom)):
>
> Usually, output functions reserve LL_RESERVED_SPACE(dev), which
> consists of dev->hard_header_len + dev->needed_headroom, aligned
> by 16.
> However, on XSK xmit hard header is already here in the chunk, so
> hard_header_len is not needed. But it'd still be better to align
> data up to cacheline, while reserving no less than driver requests
> for headroom. NET_SKB_PAD here is to double-insure there will be
> no reallocations even when the driver advertises no needed_headroom,
> but in fact need it (not so rare case).
>
> Fixes: 35fcde7f8deb ("xsk: support for Tx")
> Signed-off-by: Alexander Lobakin <[email protected]>
Acked-by: Magnus Karlsson <[email protected]>
> ---
> net/xdp/xsk.c | 8 +++++++-
> 1 file changed, 7 insertions(+), 1 deletion(-)
>
> diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
> index 4faabd1ecfd1..143979ea4165 100644
> --- a/net/xdp/xsk.c
> +++ b/net/xdp/xsk.c
> @@ -454,12 +454,16 @@ static int xsk_generic_xmit(struct sock *sk)
> struct sk_buff *skb;
> unsigned long flags;
> int err = 0;
> + u32 hr, tr;
>
> mutex_lock(&xs->mutex);
>
> if (xs->queue_id >= xs->dev->real_num_tx_queues)
> goto out;
>
> + hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
> + tr = xs->dev->needed_tailroom;
> +
> while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) {
> char *buffer;
> u64 addr;
> @@ -471,11 +475,13 @@ static int xsk_generic_xmit(struct sock *sk)
> }
>
> len = desc.len;
> - skb = sock_alloc_send_skb(sk, len, 1, &err);
> + skb = sock_alloc_send_skb(sk, hr + len + tr, 1, &err);
> if (unlikely(!skb))
> goto out;
>
> + skb_reserve(skb, hr);
> skb_put(skb, len);
> +
> addr = desc.addr;
> buffer = xsk_buff_raw_get_data(xs->pool, addr);
> err = skb_store_bits(skb, 0, buffer, len);
> --
> 2.30.1
>
>
From: Magnus Karlsson <[email protected]>
Date: Tue, 16 Feb 2021 15:08:26 +0100
> On Tue, Feb 16, 2021 at 12:44 PM Alexander Lobakin <[email protected]> wrote:
> >
> > From: Xuan Zhuo <[email protected]>
> >
> > This patch is used to construct skb based on page to save memory copy
> > overhead.
> >
> > This function is implemented based on IFF_TX_SKB_NO_LINEAR. Only the
> > network card priv_flags supports IFF_TX_SKB_NO_LINEAR will use page to
> > directly construct skb. If this feature is not supported, it is still
> > necessary to copy data to construct skb.
> >
> > ---------------- Performance Testing ------------
> >
> > The test environment is Aliyun ECS server.
> > Test cmd:
> > ```
> > xdpsock -i eth0 -t -S -s <msg size>
> > ```
> >
> > Test result data:
> >
> > size 64 512 1024 1500
> > copy 1916747 1775988 1600203 1440054
> > page 1974058 1953655 1945463 1904478
> > percent 3.0% 10.0% 21.58% 32.3%
> >
> > Signed-off-by: Xuan Zhuo <[email protected]>
> > Reviewed-by: Dust Li <[email protected]>
> > [ alobakin:
> > - expand subject to make it clearer;
> > - improve skb->truesize calculation;
> > - reserve some headroom in skb for drivers;
> > - tailroom is not needed as skb is non-linear ]
> > Signed-off-by: Alexander Lobakin <[email protected]>
>
> Thank you Alexander!
>
> Acked-by: Magnus Karlsson <[email protected]>
Thanks!
I have one more generic zerocopy to offer (inspired by this series)
that wouldn't require IFF_TX_SKB_NO_LINEAR, only a capability to xmit
S/G packets that almost every NIC has. I'll publish an RFC once this
and your upcoming changes get merged.
> > ---
> > net/xdp/xsk.c | 119 ++++++++++++++++++++++++++++++++++++++++----------
> > 1 file changed, 95 insertions(+), 24 deletions(-)
> >
> > diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
> > index 143979ea4165..ff7bd06e1241 100644
> > --- a/net/xdp/xsk.c
> > +++ b/net/xdp/xsk.c
> > @@ -445,6 +445,96 @@ static void xsk_destruct_skb(struct sk_buff *skb)
> > sock_wfree(skb);
> > }
> >
> > +static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
> > + struct xdp_desc *desc)
> > +{
> > + struct xsk_buff_pool *pool = xs->pool;
> > + u32 hr, len, offset, copy, copied;
> > + struct sk_buff *skb;
> > + struct page *page;
> > + void *buffer;
> > + int err, i;
> > + u64 addr;
> > +
> > + hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
> > +
> > + skb = sock_alloc_send_skb(&xs->sk, hr, 1, &err);
> > + if (unlikely(!skb))
> > + return ERR_PTR(err);
> > +
> > + skb_reserve(skb, hr);
> > +
> > + addr = desc->addr;
> > + len = desc->len;
> > +
> > + buffer = xsk_buff_raw_get_data(pool, addr);
> > + offset = offset_in_page(buffer);
> > + addr = buffer - pool->addrs;
> > +
> > + for (copied = 0, i = 0; copied < len; i++) {
> > + page = pool->umem->pgs[addr >> PAGE_SHIFT];
> > + get_page(page);
> > +
> > + copy = min_t(u32, PAGE_SIZE - offset, len - copied);
> > + skb_fill_page_desc(skb, i, page, offset, copy);
> > +
> > + copied += copy;
> > + addr += copy;
> > + offset = 0;
> > + }
> > +
> > + skb->len += len;
> > + skb->data_len += len;
> > + skb->truesize += pool->unaligned ? len : pool->chunk_size;
> > +
> > + refcount_add(skb->truesize, &xs->sk.sk_wmem_alloc);
> > +
> > + return skb;
> > +}
> > +
> > +static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
> > + struct xdp_desc *desc)
> > +{
> > + struct net_device *dev = xs->dev;
> > + struct sk_buff *skb;
> > +
> > + if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) {
> > + skb = xsk_build_skb_zerocopy(xs, desc);
> > + if (IS_ERR(skb))
> > + return skb;
> > + } else {
> > + u32 hr, tr, len;
> > + void *buffer;
> > + int err;
> > +
> > + hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom));
> > + tr = dev->needed_tailroom;
> > + len = desc->len;
> > +
> > + skb = sock_alloc_send_skb(&xs->sk, hr + len + tr, 1, &err);
> > + if (unlikely(!skb))
> > + return ERR_PTR(err);
> > +
> > + skb_reserve(skb, hr);
> > + skb_put(skb, len);
> > +
> > + buffer = xsk_buff_raw_get_data(xs->pool, desc->addr);
> > + err = skb_store_bits(skb, 0, buffer, len);
> > + if (unlikely(err)) {
> > + kfree_skb(skb);
> > + return ERR_PTR(err);
> > + }
> > + }
> > +
> > + skb->dev = dev;
> > + skb->priority = xs->sk.sk_priority;
> > + skb->mark = xs->sk.sk_mark;
> > + skb_shinfo(skb)->destructor_arg = (void *)(long)desc->addr;
> > + skb->destructor = xsk_destruct_skb;
> > +
> > + return skb;
> > +}
> > +
> > static int xsk_generic_xmit(struct sock *sk)
> > {
> > struct xdp_sock *xs = xdp_sk(sk);
> > @@ -454,56 +544,37 @@ static int xsk_generic_xmit(struct sock *sk)
> > struct sk_buff *skb;
> > unsigned long flags;
> > int err = 0;
> > - u32 hr, tr;
> >
> > mutex_lock(&xs->mutex);
> >
> > if (xs->queue_id >= xs->dev->real_num_tx_queues)
> > goto out;
> >
> > - hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
> > - tr = xs->dev->needed_tailroom;
> > -
> > while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) {
> > - char *buffer;
> > - u64 addr;
> > - u32 len;
> > -
> > if (max_batch-- == 0) {
> > err = -EAGAIN;
> > goto out;
> > }
> >
> > - len = desc.len;
> > - skb = sock_alloc_send_skb(sk, hr + len + tr, 1, &err);
> > - if (unlikely(!skb))
> > + skb = xsk_build_skb(xs, &desc);
> > + if (IS_ERR(skb)) {
> > + err = PTR_ERR(skb);
> > goto out;
> > + }
> >
> > - skb_reserve(skb, hr);
> > - skb_put(skb, len);
> > -
> > - addr = desc.addr;
> > - buffer = xsk_buff_raw_get_data(xs->pool, addr);
> > - err = skb_store_bits(skb, 0, buffer, len);
> > /* This is the backpressure mechanism for the Tx path.
> > * Reserve space in the completion queue and only proceed
> > * if there is space in it. This avoids having to implement
> > * any buffering in the Tx path.
> > */
> > spin_lock_irqsave(&xs->pool->cq_lock, flags);
> > - if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) {
> > + if (xskq_prod_reserve(xs->pool->cq)) {
> > spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
> > kfree_skb(skb);
> > goto out;
> > }
> > spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
> >
> > - skb->dev = xs->dev;
> > - skb->priority = sk->sk_priority;
> > - skb->mark = sk->sk_mark;
> > - skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr;
> > - skb->destructor = xsk_destruct_skb;
> > -
> > err = __dev_direct_xmit(skb, xs->queue_id);
> > if (err == NETDEV_TX_BUSY) {
> > /* Tell user-space to retry the send */
> > --
> > 2.30.1
Al