When processing received traffic, pass CHECKSUM_COMPLETE status to the
stack, with calculated checksum for non TCP/UDP packets (such
as GRE or ICMP).
Although the stack expects checksum which doesn't include the pseudo
header, the HW adds it. To address that, we are subtracting the pseudo
header checksum from the checksum value provided by the HW.
In the IPv6 case, we also compute/add the IP header checksum which
is not added by the HW for such packets.
Cc: Jerry Chu <hkchu@google.com>
Signed-off-by: Shani Michaeli <shanim@mellanox.com>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can call napi_gro_frags for all the received traffic regardless
of the checksum status. Specifically, received packets whose status
is CHECKSUM_NONE (and soon to be added CHECKSUM_COMPLETE)
are eligible for napi_gro_frags as well.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Shani Michaeli <shanim@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After commit 1a28817282 ("mlx4: use napi_complete_done()") we ended up
calling napi_complete_done() in the case NAPI poll consumed all its
budget.
This added extra interrupt pressure, this patch restores proper
behavior.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 1a28817282 ("mlx4: use napi_complete_done()")
Signed-off-by: David S. Miller <davem@davemloft.net>
To enable gro_flush_timeout, a driver has to use napi_complete_done()
instead of napi_complete().
Tested:
Ran 200 netperf TCP_STREAM from A to B (10Gbe mlx4 link, 8 RX queues)
Without this feature, we send back about 305,000 ACK per second.
GRO aggregation ratio is low (811/305 = 2.65 segments per GRO packet)
Setting a timer of 2000 nsec is enough to increase GRO packet sizes
and reduce number of ACK packets. (811/19.2 = 42)
Receiver performs less calls to upper stacks, less wakes up.
This also reduces cpu usage on the sender, as it receives less ACK
packets.
Note that reducing number of wakes up increases cpu efficiency, but can
decrease QPS, as applications wont have the chance to warmup cpu caches
doing a partial read of RPC requests/answers if they fit in one skb.
B:~# sar -n DEV 1 10 | grep eth0 | tail -1
Average: eth0 811269.80 305732.30 1199462.57 19705.72 0.00
0.00 0.50
B:~# echo 2000 >/sys/class/net/eth0/gro_flush_timeout
B:~# sar -n DEV 1 10 | grep eth0 | tail -1
Average: eth0 811577.30 19230.80 1199916.51 1239.80 0.00
0.00 0.50
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When events arrive at driver load, the event handler gets called even before
the spinlock and list are initialized. Fix this by moving the initialization
before EQs creation.
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After the EQ is created, it can possibly generate interrupts and the interrupt
handler is referencing eq->dev. It is therefore required to set eq->dev before
calling request_irq() so if an event is generated before request_irq() returns,
we will have a valid eq->dev field.
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add code to issue CONFIG_DEV "get" firmware command.
This command is used in order to obtain certain parameters used for
supporting various RX checksumming options and vxlan UDP port.
The GET operation is allowed for VFs too.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Shani Michaeli <shanim@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Needed in order to get cache cold pages (L3 flushed) for HW scatter.
Otherwise memory may flush those entries when the packet comes from
PCI, causing back pressure resulting in BW decrease.
Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When IP_ALIGN has a non zero value, hardware will write to a non aligned
address. The only reader from this address is when copying the header
from the first frag into the linear buffer (further access to the IP
address will be from the linear buffer, in which the headers are
aligned). Since the penalty of non align access by the hardware is
greater than the software memcpy, changing the frag_align to always be 0.
Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We need to protect set_port_type() for concurrency, as the sysfs code could
call it from mutliple contexts in parallel.
The port_mutex is not enough because we need to protect from concurrent
modification of 'info' and stopping of the port sensing work.
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Added wrapper to the ACCESS_REG command for handling guest HW
registers access, preventing write operations, but do allow reads.
This will prevent SRIOV guests to change port PTYS configuration,
such as speed/advertised link modes.
Fixes: adbc7ac5c1 ('net/mlx4_core: Introduce ACCESS_REG CMD [...]')
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If mlx4_ib_create_flow() attempts to create > 1 rules with the
firmware, and one of these registrations fail, we leaked the
already created flow rules.
One example of the leak is when the registration of the VXLAN ghost
steering rule fails, we didn't unregister the original rule requested
by the user, introduced in commit d2fce8a906 "mlx4: Set
user-space raw Ethernet QPs to properly handle VXLAN traffic".
While here, add dump of the VXLAN portion of steering rules
so it can actually be seen when flow creation fails.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For VXLAN/NVGRE encapsulation, the current HW doesn't support offloading
both the outer UDP TX checksum and the inner TCP/UDP TX checksum.
The driver doesn't advertize SKB_GSO_UDP_TUNNEL_CSUM, however we are wrongly
telling the HW to offload the outer UDP checksum for encapsulated packets,
fix that.
Fixes: 837052d0cc ('net/mlx4_en: Add netdev support for TCP/IP
offloads of vxlan tunneling')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
mlx4_en_rx_irq() and mlx4_en_tx_irq() run from hard interrupt context.
They can use napi_schedule_irqoff() instead of napi_schedule()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-By: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Hardware requires the number of rings in indirection table to be a power
of 2. When setting number of channels to a non power of 2 number,
indirection table is using only the closest power of 2 rings.
Report this number in 'ethtool -x' and not the total number of rx rings.
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Upon failures, destroy_netdev is called, and spinlocks/works must be
initialized before calling it. Otherwise kernel panic may occur.
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is instead of calling the actual implementation of
napi_synchronize, for better encapsulation.
Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
clang flagged the following. All are actually cosmetic cleanups, not really bugs:
drivers/net/ethernet/mellanox/mlx4/en_main.c:233:3: warning: Value stored to 'err' is never read
err = -ENOMEM;
^ ~~~~~~~
drivers/net/ethernet/mellanox/mlx4/en_main.c:293:3: warning: Value stored to 'err' is never read
err = -ENOMEM;
drivers/net/ethernet/mellanox/mlx4/en_netdev.c:648:16: warning: Assigned value is garbage or undefined
entry->reg_id = reg_id;
^ ~~~~~~
drivers/net/ethernet/mellanox/mlx4/en_netdev.c:659:2: warning: Function call argument is an uninitialized value
mlx4_en_uc_steer_release(priv, priv->dev->dev_addr, *qpn, reg_id);
(NOTE: reg_id is only used in the device-managed flow steering path, in which is it always initialized.
This is not a bug. Cleanup here is therefore cosmetic only).
drivers/net/ethernet/mellanox/mlx4/en_rx.c:122:3: warning: Value stored to 'frag_info' is never read
frag_info = &priv->frag_info[i];
^ ~~~~~~~~~~~~~~~~~~~
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move mlx4_en_reset_config to en_netdev.c as it now serves more general purpose.
Add support for turning OFF/ON the rx/tx vlan offlad.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rename mlx4_en_timestamp_config to mlx4_en_reset_config and extend it to support
choosing RX vlan offload configuration.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Added Support to set speed or advertised link modes via ethtool:
ethtool -s <ifname> [speed <speed>] [advertise <link modes>]
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
- If dev cap MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL is ON, query PTYS register to fill ethtool settings.
else use default values.
- Use autoneg port cap and dev backplane autoneg cap to reprort autoneg interface capbilities.
- Fix typo in mlx4_en_port_state struct field (transciver to transceiver).
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Added 100M, 20G and 56G ethtool speed reporting support.
Update mlx4_en_test_speed self test with the new speeds.
Defined new link speeds in include/uapi/linux/ethtool.h:
+#define SPEED_20000 20000
+#define SPEED_40000 40000
+#define SPEED_56000 56000
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Adding ACCESS REG mlx4 command and use it to implement Query method for
PTYS (Port Type and Speed Register).
Query and store eth_prot_ctrl dev cap.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Added support for get_module_info/get_module_eeprom ethtool support for cable info reading.
Added new cable types enum in include/uapi/linux/ethtool.h for ethtool use.
+#define ETH_MODULE_SFF_8636 0x3
+#define ETH_MODULE_SFF_8636_LEN 256
+#define ETH_MODULE_SFF_8436 0x4
+#define ETH_MODULE_SFF_8436_LEN 256
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Added new MAD_IFC command to read cable module info with attribute id (0xFF60).
Update include/linux/mlx4/device.h with function declaration (mlx4_get_module_info)
and the needed defines/enums for future use.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After moving the EQ ownership to software effectively destroying it, call
synchronize_irq() to ensure that any handler routines running on other CPU
cores finish execution. Only then free the EQ buffer.
The same thing is done when we destroy a CQ which is one of the sources
generating interrupts. In the case of CQ we want to avoid completion handlers
on a CQ that was destroyed. In the case we do the same to avoid receiving
asynchronous events after the EQ has been destroyed and its buffers freed.
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After destroying the EQ, the object responsible for generating interrupts, call
synchronize_irq() to ensure that any handler routines running on other CPU
cores finish execution. Only then free the EQ buffer. This patch solves a very
rare case when we get panic on driver unload.
The same thing is done when we destroy a CQ which is one of the sources
generating interrupts. In the case of CQ we want to avoid completion handlers
on a CQ that was destroyed. In the case we do the same to avoid receiving
asynchronous events after the EQ has been destroyed and its buffers freed.
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is illegal to use atomic_set(&page->_count, ...) even if we 'own'
the page. Other entities in the kernel need to use get_page_unless_zero()
to get a reference to the page before testing page properties, so we could
loose a refcount increment.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking updates from David Miller:
"Most notable changes in here:
1) By far the biggest accomplishment, thanks to a large range of
contributors, is the addition of multi-send for transmit. This is
the result of discussions back in Chicago, and the hard work of
several individuals.
Now, when the ->ndo_start_xmit() method of a driver sees
skb->xmit_more as true, it can choose to defer the doorbell
telling the driver to start processing the new TX queue entires.
skb->xmit_more means that the generic networking is guaranteed to
call the driver immediately with another SKB to send.
There is logic added to the qdisc layer to dequeue multiple
packets at a time, and the handling mis-predicted offloads in
software is now done with no locks held.
Finally, pktgen is extended to have a "burst" parameter that can
be used to test a multi-send implementation.
Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
virtio_net
Adding support is almost trivial, so export more drivers to
support this optimization soon.
I want to thank, in no particular or implied order, Jesper
Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
David Tat, Hannes Frederic Sowa, and Rusty Russell.
2) PTP and timestamping support in bnx2x, from Michal Kalderon.
3) Allow adjusting the rx_copybreak threshold for a driver via
ethtool, and add rx_copybreak support to enic driver. From
Govindarajulu Varadarajan.
4) Significant enhancements to the generic PHY layer and the bcm7xxx
driver in particular (EEE support, auto power down, etc.) from
Florian Fainelli.
5) Allow raw buffers to be used for flow dissection, allowing drivers
to determine the optimal "linear pull" size for devices that DMA
into pools of pages. The objective is to get exactly the
necessary amount of headers into the linear SKB area pre-pulled,
but no more. The new interface drivers use is eth_get_headlen().
From WANG Cong, with driver conversions (several had their own
by-hand duplicated implementations) by Alexander Duyck and Eric
Dumazet.
6) Support checksumming more smoothly and efficiently for
encapsulations, and add "foo over UDP" facility. From Tom
Herbert.
7) Add Broadcom SF2 switch driver to DSA layer, from Florian
Fainelli.
8) eBPF now can load programs via a system call and has an extensive
testsuite. Alexei Starovoitov and Daniel Borkmann.
9) Major overhaul of the packet scheduler to use RCU in several major
areas such as the classifiers and rate estimators. From John
Fastabend.
10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
Duyck.
11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
Dumazet.
12) Add Datacenter TCP congestion control algorithm support, From
Florian Westphal.
13) Reorganize sk_buff so that __copy_skb_header() is significantly
faster. From Eric Dumazet"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
netlabel: directly return netlbl_unlabel_genl_init()
net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
net: description of dma_cookie cause make xmldocs warning
cxgb4: clean up a type issue
cxgb4: potential shift wrapping bug
i40e: skb->xmit_more support
net: fs_enet: Add NAPI TX
net: fs_enet: Remove non NAPI RX
r8169:add support for RTL8168EP
net_sched: copy exts->type in tcf_exts_change()
wimax: convert printk to pr_foo()
af_unix: remove 0 assignment on static
ipv6: Do not warn for informational ICMP messages, regardless of type.
Update Intel Ethernet Driver maintainers list
bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
tipc: fix bug in multicast congestion handling
net: better IFF_XMIT_DST_RELEASE support
net/mlx4_en: remove NETDEV_TX_BUSY
3c59x: fix bad split of cpu_to_le32(pci_map_single())
net: bcmgenet: fix Tx ring priority programming
...
Add two helpers so that drivers do not have to care of BQL being
available or not.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jim Davis <jim.epost@gmail.com>
Fixes: 29d40c9032 ("net/mlx4_en: Use prefetch in tx path")
Signed-off-by: David S. Miller <davem@davemloft.net>
Drivers should avoid NETDEV_TX_BUSY as much as possible.
They should stop the tx queue before qdisc even tries to push another
packet, to avoid requeues.
For a driver supporting skb->xmit_more, this is likely to be a prereq
anyway, otherwise we could have a tx deadlock : We need to force a
doorbell if TX ring is full.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of setting inline threshold using module parameter only on
driver load, use set_tunable() to set it dynamically.
No need to store the threshold per ring, using instead the netdev global
priv->prof->inline_thold
Initial value still is set using the module parameter, therefore
backward compatability is kept.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reorganize code to call is_inline() once, so compiler can inline it
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Properly clear tx_info->ts_requested
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Access skb_headlen() once in tx flow
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acces skb_shinfo(skb) once in tx flow.
Also, rename @i variable to @i_frag to avoid confusion, as the "goto
tx_drop_unmap;" relied on this @i variable.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
mlx4_en_process_tx_cq() carefully fetches and writes ring->last_nr_txbb
and ring->cons only one time to avoid false sharing
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
mlx4_en_free_tx_desc() uses a prefetchw(&skb->users) to speed up
consume_skb()
prefetchw(&ring->tx_queue->dql) to speed up BQL update
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add frag0_dma/frag0_byte_count into mlx4_en_tx_info to avoid a cache
line miss in TX completion for frames having one dma element. (We avoid
reading back the tx descriptor)
Note this could be extended to 2/3 dma elements later, as we have free
room in mlx4_en_tx_info
Also, mlx4_en_free_tx_desc() no longer accesses skb_shinfo(). We use a
new nr_maps fields in mlx4_en_tx_info to avoid 2 or 3 cache misses.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Try to allocate using kmalloc_node() first, only on failure use
vmalloc()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
- doorbell_qpn is stored in the cpu_to_be32() way to avoid bswap() in fast
path.
- mdev->mr.key stored in ring->mr_key to also avoid bswap() and access to
cold cache line.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reorganize struct mlx4_en_tx_ring to have:
- One cache line containing last_nr_txbb & cons & wake_queue, used by tx
completion.
- One cache line containing fields dirtied by mlx4_en_xmit()
- Following part is read mostly and shared by cpus.
Align struct mlx4_en_tx_info to a cache line
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
- Remove unused variable ring->poll_cnt
- No need to set some fields if using blueflame
- Add missing const's
- Use unlikely
- Remove unneeded new line
- Make some comments more precise
- struct mlx4_bf @offset field reduced to unsigned int to save space
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ethtool -S reports a new counter, tracking number of time doorbell
was not triggered, because skb->xmit_more was set.
$ ethtool -S eth0 | egrep "tx_packet|xmit_more"
tx_packets: 2413288400
xmit_more: 666121277
I merged the tso_packet false sharing avoidance in this patch as well.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Shani Michaeli