Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 30 10月, 2021 1 次提交
  3. 29 10月, 2021 9 次提交
  5. 26 10月, 2021 2 次提交
    • Y
      ice: check whether PTP is initialized in ice_ptp_release() · fd1b5beb
      由 Yongxin Liu 提交于 
      PTP is currently only supported on E810 devices, it is checked
in ice_ptp_init(). However, there is no check in ice_ptp_release().
For other E800 series devices, ice_ptp_release() will be wrongly executed.

Fix the following calltrace.

  INFO: trying to register non-static key.
  The code is fine but needs lockdep annotation, or maybe
  you didn't initialize this object before use?
  turning off the locking correctness validator.
  Workqueue: ice ice_service_task [ice]
  Call Trace:
   dump_stack_lvl+0x5b/0x82
   dump_stack+0x10/0x12
   register_lock_class+0x495/0x4a0
   ? find_held_lock+0x3c/0xb0
   __lock_acquire+0x71/0x1830
   lock_acquire+0x1e6/0x330
   ? ice_ptp_release+0x3c/0x1e0 [ice]
   ? _raw_spin_lock+0x19/0x70
   ? ice_ptp_release+0x3c/0x1e0 [ice]
   _raw_spin_lock+0x38/0x70
   ? ice_ptp_release+0x3c/0x1e0 [ice]
   ice_ptp_release+0x3c/0x1e0 [ice]
   ice_prepare_for_reset+0xcb/0xe0 [ice]
   ice_do_reset+0x38/0x110 [ice]
   ice_service_task+0x138/0xf10 [ice]
   ? __this_cpu_preempt_check+0x13/0x20
   process_one_work+0x26a/0x650
   worker_thread+0x3f/0x3b0
   ? __kthread_parkme+0x51/0xb0
   ? process_one_work+0x650/0x650
   kthread+0x161/0x190
   ? set_kthread_struct+0x40/0x40
   ret_from_fork+0x1f/0x30

Fixes: 4dd0d5c3 ("ice: add lock around Tx timestamp tracker flush")
Signed-off-by: NYongxin Liu <yongxin.liu@windriver.com>
Reviewed-by: NJacob Keller <jacob.e.keller@intel.com>
Tested-by: NGurucharan G <gurucharanx.g@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
      fd1b5beb
    • D
      ice: Respond to a NETDEV_UNREGISTER event for LAG · 6a8b3572
      由 Dave Ertman 提交于 
      When the PF is a member of a link aggregate, and the driver
is removed, the process will hang unless we respond to the
NETDEV_UNREGISTER event that is sent to the event_handler
for LAG.

Add a case statement for the ice_lag_event_handler to unlink
the PF from the link aggregate.

Also remove code that was incorrectly applying a dev_hold to
peer_netdevs that were associated with the ice driver.

Fixes: df006dd4 ("ice: Add initial support framework for LAG")
Signed-off-by: NDave Ertman <david.m.ertman@intel.com>
Tested-by: NTony Brelinski <tony.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
      6a8b3572
  7. 24 10月, 2021 1 次提交
    • S
      net: convert users of bitmap_foo() to linkmode_foo() · 4973056c
      由 Sean Anderson 提交于 
      This converts instances of
	bitmap_foo(args..., __ETHTOOL_LINK_MODE_MASK_NBITS)
to
	linkmode_foo(args...)

I manually fixed up some lines to prevent them from being excessively
long. Otherwise, this change was generated with the following semantic
patch:

// Generated with
// echo linux/linkmode.h > includes
// git grep -Flf includes include/ | cut -f 2- -d / | cat includes - \
// | sort | uniq | tee new_includes | wc -l && mv new_includes includes
// and repeating until the number stopped going up
@i@
@@

(
 #include <linux/acpi_mdio.h>
|
 #include <linux/brcmphy.h>
|
 #include <linux/dsa/loop.h>
|
 #include <linux/dsa/sja1105.h>
|
 #include <linux/ethtool.h>
|
 #include <linux/ethtool_netlink.h>
|
 #include <linux/fec.h>
|
 #include <linux/fs_enet_pd.h>
|
 #include <linux/fsl/enetc_mdio.h>
|
 #include <linux/fwnode_mdio.h>
|
 #include <linux/linkmode.h>
|
 #include <linux/lsm_audit.h>
|
 #include <linux/mdio-bitbang.h>
|
 #include <linux/mdio.h>
|
 #include <linux/mdio-mux.h>
|
 #include <linux/mii.h>
|
 #include <linux/mii_timestamper.h>
|
 #include <linux/mlx5/accel.h>
|
 #include <linux/mlx5/cq.h>
|
 #include <linux/mlx5/device.h>
|
 #include <linux/mlx5/driver.h>
|
 #include <linux/mlx5/eswitch.h>
|
 #include <linux/mlx5/fs.h>
|
 #include <linux/mlx5/port.h>
|
 #include <linux/mlx5/qp.h>
|
 #include <linux/mlx5/rsc_dump.h>
|
 #include <linux/mlx5/transobj.h>
|
 #include <linux/mlx5/vport.h>
|
 #include <linux/of_mdio.h>
|
 #include <linux/of_net.h>
|
 #include <linux/pcs-lynx.h>
|
 #include <linux/pcs/pcs-xpcs.h>
|
 #include <linux/phy.h>
|
 #include <linux/phy_led_triggers.h>
|
 #include <linux/phylink.h>
|
 #include <linux/platform_data/bcmgenet.h>
|
 #include <linux/platform_data/xilinx-ll-temac.h>
|
 #include <linux/pxa168_eth.h>
|
 #include <linux/qed/qed_eth_if.h>
|
 #include <linux/qed/qed_fcoe_if.h>
|
 #include <linux/qed/qed_if.h>
|
 #include <linux/qed/qed_iov_if.h>
|
 #include <linux/qed/qed_iscsi_if.h>
|
 #include <linux/qed/qed_ll2_if.h>
|
 #include <linux/qed/qed_nvmetcp_if.h>
|
 #include <linux/qed/qed_rdma_if.h>
|
 #include <linux/sfp.h>
|
 #include <linux/sh_eth.h>
|
 #include <linux/smsc911x.h>
|
 #include <linux/soc/nxp/lpc32xx-misc.h>
|
 #include <linux/stmmac.h>
|
 #include <linux/sunrpc/svc_rdma.h>
|
 #include <linux/sxgbe_platform.h>
|
 #include <net/cfg80211.h>
|
 #include <net/dsa.h>
|
 #include <net/mac80211.h>
|
 #include <net/selftests.h>
|
 #include <rdma/ib_addr.h>
|
 #include <rdma/ib_cache.h>
|
 #include <rdma/ib_cm.h>
|
 #include <rdma/ib_hdrs.h>
|
 #include <rdma/ib_mad.h>
|
 #include <rdma/ib_marshall.h>
|
 #include <rdma/ib_pack.h>
|
 #include <rdma/ib_pma.h>
|
 #include <rdma/ib_sa.h>
|
 #include <rdma/ib_smi.h>
|
 #include <rdma/ib_umem.h>
|
 #include <rdma/ib_umem_odp.h>
|
 #include <rdma/ib_verbs.h>
|
 #include <rdma/iw_cm.h>
|
 #include <rdma/mr_pool.h>
|
 #include <rdma/opa_addr.h>
|
 #include <rdma/opa_port_info.h>
|
 #include <rdma/opa_smi.h>
|
 #include <rdma/opa_vnic.h>
|
 #include <rdma/rdma_cm.h>
|
 #include <rdma/rdma_cm_ib.h>
|
 #include <rdma/rdmavt_cq.h>
|
 #include <rdma/rdma_vt.h>
|
 #include <rdma/rdmavt_qp.h>
|
 #include <rdma/rw.h>
|
 #include <rdma/tid_rdma_defs.h>
|
 #include <rdma/uverbs_ioctl.h>
|
 #include <rdma/uverbs_named_ioctl.h>
|
 #include <rdma/uverbs_std_types.h>
|
 #include <rdma/uverbs_types.h>
|
 #include <soc/mscc/ocelot.h>
|
 #include <soc/mscc/ocelot_ptp.h>
|
 #include <soc/mscc/ocelot_vcap.h>
|
 #include <trace/events/ib_mad.h>
|
 #include <trace/events/rdma_core.h>
|
 #include <trace/events/rdma.h>
|
 #include <trace/events/rpcrdma.h>
|
 #include <uapi/linux/ethtool.h>
|
 #include <uapi/linux/ethtool_netlink.h>
|
 #include <uapi/linux/mdio.h>
|
 #include <uapi/linux/mii.h>
)

@depends on i@
expression list args;
@@

(
- bitmap_zero(args, __ETHTOOL_LINK_MODE_MASK_NBITS)
+ linkmode_zero(args)
|
- bitmap_copy(args, __ETHTOOL_LINK_MODE_MASK_NBITS)
+ linkmode_copy(args)
|
- bitmap_and(args, __ETHTOOL_LINK_MODE_MASK_NBITS)
+ linkmode_and(args)
|
- bitmap_or(args, __ETHTOOL_LINK_MODE_MASK_NBITS)
+ linkmode_or(args)
|
- bitmap_empty(args, ETHTOOL_LINK_MODE_MASK_NBITS)
+ linkmode_empty(args)
|
- bitmap_andnot(args, __ETHTOOL_LINK_MODE_MASK_NBITS)
+ linkmode_andnot(args)
|
- bitmap_equal(args, __ETHTOOL_LINK_MODE_MASK_NBITS)
+ linkmode_equal(args)
|
- bitmap_intersects(args, __ETHTOOL_LINK_MODE_MASK_NBITS)
+ linkmode_intersects(args)
|
- bitmap_subset(args, __ETHTOOL_LINK_MODE_MASK_NBITS)
+ linkmode_subset(args)
)

Add missing linux/mii.h include to mellanox. -DaveM
Signed-off-by: NSean Anderson <sean.anderson@seco.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      4973056c
  9. 22 10月, 2021 1 次提交
  11. 21 10月, 2021 6 次提交
  13. 20 10月, 2021 11 次提交
  15. 19 10月, 2021 4 次提交
  17. 16 10月, 2021 1 次提交
    • J
      ethernet: ixgb: use eth_hw_addr_set() · ec356ede
      由 Jakub Kicinski 提交于 
      Commit 406f42fa ("net-next: When a bond have a massive amount
of VLANs...") introduced a rbtree for faster Ethernet address look
up. To maintain netdev->dev_addr in this tree we need to make all
the writes to it got through appropriate helpers.

Read the address into an array on the stack, then call
eth_hw_addr_set(). ixgb_get_ee_mac_addr() is used with
a non-nevdev->dev_addr pointer so we can't deal with the problem
inside it.
Signed-off-by: NJakub Kicinski <kuba@kernel.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      ec356ede
  19. 15 10月, 2021 4 次提交
    • M
      ice: make use of ice_for_each_* macros · 2faf63b6
      由 Maciej Fijalkowski 提交于 
      Go through the code base and use ice_for_each_* macros.  While at it,
introduce ice_for_each_xdp_txq() macro that can be used for looping over
xdp_rings array.

Commit is not introducing any new functionality.
Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: NGurucharan G <gurucharanx.g@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
      2faf63b6
    • M
      ice: introduce XDP_TX fallback path · 22bf877e
      由 Maciej Fijalkowski 提交于 
      Under rare circumstances there might be a situation where a requirement
of having XDP Tx queue per CPU could not be fulfilled and some of the Tx
resources have to be shared between CPUs. This yields a need for placing
accesses to xdp_ring inside a critical section protected by spinlock.
These accesses happen to be in the hot path, so let's introduce the
static branch that will be triggered from the control plane when driver
could not provide Tx queue dedicated for XDP on each CPU.

Currently, the design that has been picked is to allow any number of XDP
Tx queues that is at least half of a count of CPUs that platform has.
For lower number driver will bail out with a response to user that there
were not enough Tx resources that would allow configuring XDP. The
sharing of rings is signalled via static branch enablement which in turn
indicates that lock for xdp_ring accesses needs to be taken in hot path.

Approach based on static branch has no impact on performance of a
non-fallback path. One thing that is needed to be mentioned is a fact
that the static branch will act as a global driver switch, meaning that
if one PF got out of Tx resources, then other PFs that ice driver is
servicing will suffer. However, given the fact that HW that ice driver
is handling has 1024 Tx queues per each PF, this is currently an
unlikely scenario.
Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: NGeorge Kuruvinakunnel <george.kuruvinakunnel@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
      22bf877e
    • M
      ice: optimize XDP_TX workloads · 9610bd98
      由 Maciej Fijalkowski 提交于 
      Optimize Tx descriptor cleaning for XDP. Current approach doesn't
really scale and chokes when multiple flows are handled.

Introduce two ring fields, @next_dd and @next_rs that will keep track of
descriptor that should be looked at when the need for cleaning arise and
the descriptor that should have the RS bit set, respectively.

Note that at this point the threshold is a constant (32), but it is
something that we could make configurable.

First thing is to get away from setting RS bit on each descriptor. Let's
do this only once NTU is higher than the currently @next_rs value. In
such case, grab the tx_desc[next_rs], set the RS bit in descriptor and
advance the @next_rs by a 32.

Second thing is to clean the Tx ring only when there are less than 32
free entries. For that case, look up the tx_desc[next_dd] for a DD bit.
This bit is written back by HW to let the driver know that xmit was
successful. It will happen only for those descriptors that had RS bit
set. Clean only 32 descriptors and advance the DD bit.

Actual cleaning routine is moved from ice_napi_poll() down to the
ice_xmit_xdp_ring(). It is safe to do so as XDP ring will not get any
SKBs in there that would rely on interrupts for the cleaning. Nice side
effect is that for rare case of Tx fallback path (that next patch is
going to introduce) we don't have to trigger the SW irq to clean the
ring.

With those two concepts, ring is kept at being almost full, but it is
guaranteed that driver will be able to produce Tx descriptors.

This approach seems to work out well even though the Tx descriptors are
produced in one-by-one manner. Test was conducted with the ice HW
bombarded with packets from HW generator, configured to generate 30
flows.

Xdp2 sample yields the following results:
<snip>
proto 17:   79973066 pkt/s
proto 17:   80018911 pkt/s
proto 17:   80004654 pkt/s
proto 17:   79992395 pkt/s
proto 17:   79975162 pkt/s
proto 17:   79955054 pkt/s
proto 17:   79869168 pkt/s
proto 17:   79823947 pkt/s
proto 17:   79636971 pkt/s
</snip>

As that sample reports the Rx'ed frames, let's look at sar output.
It says that what we Rx'ed we do actually Tx, no noticeable drops.
Average:        IFACE   rxpck/s   txpck/s    rxkB/s    txkB/s   rxcmp/s txcmp/s  rxmcst/s   %ifutil
Average:       ens4f1 79842324.00 79842310.40 4678261.17 4678260.38 0.00      0.00      0.00     38.32

with tx_busy staying calm.

When compared to a state before:
Average:        IFACE   rxpck/s   txpck/s    rxkB/s    txkB/s   rxcmp/s txcmp/s  rxmcst/s   %ifutil
Average:       ens4f1 90919711.60 42233822.60 5327326.85 2474638.04 0.00      0.00      0.00     43.64

it can be observed that the amount of txpck/s is almost doubled, meaning
that the performance is improved by around 90%. All of this due to the
drops in the driver, previously the tx_busy stat was bumped at a 7mpps
rate.
Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: NGeorge Kuruvinakunnel <george.kuruvinakunnel@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
      9610bd98
    • M
      ice: propagate xdp_ring onto rx_ring · eb087cd8
      由 Maciej Fijalkowski 提交于 
      With rings being split, it is now convenient to introduce a pointer to
XDP ring within the Rx ring. For XDP_TX workloads this means that
xdp_rings array access will be skipped, which was executed per each
processed frame.

Also, read the XDP prog once per NAPI and if prog is present, set up the
local xdp_ring pointer. Reading prog a single time was discussed in [1]
with some concern raised by Toke around dispatcher handling and having
the need for going through the RCU grace period in the ndo_bpf driver
callback, but ice currently is torning down NAPI instances regardless of
the prog presence on VSI.

Although the pointer to XDP ring introduced to Rx ring makes things a
lot slimmer/simpler, I still feel that single prog read per NAPI
lifetime is beneficial.

Further patch that will introduce the fallback path will also get a
profit from that as xdp_ring pointer will be set during the XDP rings
setup.

[1]: https://lore.kernel.org/bpf/87k0oseo6e.fsf@toke.dk/Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: NGeorge Kuruvinakunnel <george.kuruvinakunnel@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
      eb087cd8