Age | Commit message (Collapse) | Author |
|
enetc has no special behaviour in its validation implementation, so can
be switched to phylink_generic_validate().
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
|
|
As phylink checks the interface mode against the supported_interfaces
bitmap, we no longer need to validate the interface mode in the
validation function. Remove this to simplify it.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
|
|
Populate the phy_interface_t bitmap for the Freescale enetc driver with
interfaces modes supported by the MAC.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
|
|
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: Sean Anderson <sean.anderson@seco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Lots of simnple overlapping additions.
With a build fix from Stephen Rothwell.
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The code checks whether the skb had one-step TX timestamping enabled, in
order to schedule the work item for emptying the priv->tx_skbs queue.
That code checks for "tx_swbd->skb" directly, when we already had a skb
retrieved using enetc_tx_swbd_get_skb(tx_swbd) - a TX software BD can
also hold an XDP_TX packet or an XDP frame. But since the direct tx_swbd
dereference is in an "if" block guarded by the non-NULL quality of
"skb", accessing "tx_swbd->skb" directly is not wrong, just confusing.
Just use the local variable named "skb".
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The "priv" variable is needed in the "check_writeback" scope since
commit d39823121911 ("enetc: add hardware timestamping support").
Since commit 7294380c5211 ("enetc: support PTP Sync packet one-step
timestamping"), we also need "priv" in the larger function scope.
So the local variable from the "if" block scope is not needed, and
actually shadows the other one. Delete it.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The enetc driver does not implement .ndo_change_mtu, instead it
configures the MAC register field PTC{Traffic Class}MSDUR[MAXSDU]
statically to a large value during probe time.
The driver used to configure only the max SDU for traffic class 0, and
that was fine while the driver could only use traffic class 0. But with
the introduction of mqprio, sending a large frame into any other TC than
0 is broken.
This patch fixes that by replicating per traffic class the static
configuration done in enetc_configure_port_mac().
Fixes: cbe9e835946f ("enetc: Enable TC offloading with mqprio")
Reported-by: Richie Pearn <richard.pearn@nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: <Claudiu Manoil <claudiu.manoil@nxp.com>
Link: https://lore.kernel.org/r/20211020173340.1089992-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
There are two counters named "MAC tx frames", one of them is actually
incorrect. The correct name for that counter should be "MAC tx error
frames", which is symmetric to the existing "MAC rx error frames".
Fixes: 16eb4c85c964 ("enetc: Add ethtool statistics")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: <Claudiu Manoil <claudiu.manoil@nxp.com>
Link: https://lore.kernel.org/r/20211020165206.1069889-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Coverity complains of a possible dereference of a null return value.
5. returned_null: kzalloc returns NULL. [show details]
6. var_assigned: Assigning: si_data = NULL return value from kzalloc.
488 si_data = kzalloc(data_size, __GFP_DMA | GFP_KERNEL);
489 cbd.length = cpu_to_le16(data_size);
490
491 dma = dma_map_single(&priv->si->pdev->dev, si_data,
492 data_size, DMA_FROM_DEVICE);
While this kzalloc() is unlikely to fail, I did notice that the function
returned without unmapping si_data.
Fix this by refactoring the error paths and checking for kzalloc()
failure.
Fixes: 888ae5a3952ba ("net: enetc: add tc flower psfp offload driver")
Cc: Claudiu Manoil <claudiu.manoil@nxp.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org (open list)
Signed-off-by: Tim Gardner <tim.gardner@canonical.com>
Acked-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 406f42fa0d3c ("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.
Pass a netdev into the helper instead of just the address,
read the address into an array on the stack, then call
eth_hw_addr_set().
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This was supposed to be a check for if dma_alloc_coherent() failed
but it has a copy and paste bug so it will not work.
Fixes: fb8629e2cbfc ("net: enetc: add support for software TSO")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Link: https://lore.kernel.org/r/20211013080456.GC6010@kili
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
For those architectures which do not define_HAVE_ARCH_IPV6_CSUM, we need
to include ip6_checksum.h which provides the csum_ipv6_magic() function.
Fixes: fb8629e2cbfc ("net: enetc: add support for software TSO")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20211012121358.16641-1-ioana.ciornei@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
This patch adds support for driver level TSO in the enetc driver using
the TSO API.
Beside using the usual tso_build_hdr(), tso_build_data() this specific
implementation also has to compute the checksum, both IP and L4, for
each resulted segment. This is because the ENETC controller does not
support Tx checksum offload which is needed in order to take advantage
of TSO.
With the workaround for the ENETC MDIO erratum in place the Tx path of
the driver is forced to lock/unlock for each skb sent. This is why, even
though we are computing the checksum by hand we see the following
improvement in TCP termination on the LS1028A SoC, on a single A72 core
running at 1.3GHz:
before: 1.63 Gbits/sec
after: 2.34 Gbits/sec
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This is just a preparation patch for software TSO in the enetc driver.
Unfortunately, ENETC does not support Tx checksum offload which would
normally render TSO, even software, impossible.
Declare NETIF_F_HW_CSUM as part of the feature set and do it at driver
level using skb_csum_hwoffload_help() so that we can move forward and
also add support for TSO in the next patch.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Convert all Ethernet drivers from memcpy(... dev->addr_len)
to eth_hw_addr_set():
@@
expression dev, np;
@@
- memcpy(dev->dev_addr, np, dev->addr_len)
+ eth_hw_addr_set(dev, np)
In theory addr_len may not be ETH_ALEN, but we don't expect
non-Ethernet devices to live under this directory, and only
the following cases of setting addr_len exist:
- cxgb4 for mgmt device,
and the drivers which set it to ETH_ALEN: s2io, mlx4, vxge.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
drivers/net/phy/bcm7xxx.c
d88fd1b546ff ("net: phy: bcm7xxx: Fixed indirect MMD operations")
f68d08c437f9 ("net: phy: bcm7xxx: Add EPHY entry for 72165")
net/sched/sch_api.c
b193e15ac69d ("net: prevent user from passing illegal stab size")
69508d43334e ("net_sched: Use struct_size() and flex_array_size() helpers")
Both cases trivial - adjacent code additions.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The enetc phylink .mac_config handler intends to clear the IFMODE field
(bits 1:0) of the PM0_IF_MODE register, but incorrectly clears all the
other fields instead.
For normal operation, the bug was inconsequential, due to the fact that
we write the PM0_IF_MODE register in two stages, first in
phylink .mac_config (which incorrectly cleared out a bunch of stuff),
then we update the speed and duplex to the correct values in
phylink .mac_link_up.
Judging by the code (not tested), it looks like maybe loopback mode was
broken, since this is one of the settings in PM0_IF_MODE which is
incorrectly cleared.
Fixes: c76a97218dcb ("net: enetc: force the RGMII speed and duplex instead of operating in inband mode")
Reported-by: Pavel Machek (CIP) <pavel@denx.de>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
net/mptcp/protocol.c
977d293e23b4 ("mptcp: ensure tx skbs always have the MPTCP ext")
efe686ffce01 ("mptcp: ensure tx skbs always have the MPTCP ext")
same patch merged in both trees, keep net-next.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The only struct dim_sample member that does not get
initialized by dim_update_sample() is comp_ctr. (There
is special API to initialize comp_ctr:
dim_update_sample_with_comps(), and it is currently used
only for RDMA.) comp_ctr is used to compute curr_stats->cmps
and curr_stats->cpe_ratio (see dim_calc_stats()) which in
turn are consumed by the rdma_dim_*() API. Therefore,
functionally, the net_dim*() API consumers are not affected.
Nevertheless, fix the computation of statistics based
on an uninitialized variable, even if the mentioned statistics
are not used at the moment.
Fixes: ae0e6a5d1627 ("enetc: Add adaptive interrupt coalescing")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
irq_set_affinity_hit() stores a reference to the cpumask_t
parameter in the irq descriptor, and that reference can be
accessed later from irq_affinity_hint_proc_show(). Since
the cpu_mask parameter passed to irq_set_affinity_hit() has
only temporary storage (it's on the stack memory), later
accesses to it are illegal. Thus reads from the corresponding
procfs affinity_hint file can result in paging request oops.
The issue is fixed by the get_cpu_mask() helper, which provides
a permanent storage for the cpumask_t parameter.
Fixes: d4fd0404c1c9 ("enetc: Introduce basic PF and VF ENETC ethernet drivers")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
NXP Legal insists that the following are not fine:
- Saying "NXP Semiconductors" instead of "NXP", since the company's
registered name is "NXP"
- Putting a "(c)" sign in the copyright string
- Putting a comma in the copyright string
The only accepted copyright string format is "Copyright <year-range> NXP".
This patch changes the copyright headers in the networking files that
were sent by me, or derived from code sent by me.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When possible use dev_err_probe help to properly deal with the
PROBE_DEFER error, the benefit is that DEFER issue will be logged
in the devices_deferred debugfs file.
And using dev_err_probe() can reduce code size, and simplify the code.
Signed-off-by: Cai Huoqing <caihuoqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
In order to support more coalesce parameters through netlink,
add two new parameter kernel_coal and extack for .set_coalesce
and .get_coalesce, then some extra info can return to user with
the netlink API.
Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Most users of ndo_do_ioctl are ethernet drivers that implement
the MII commands SIOCGMIIPHY/SIOCGMIIREG/SIOCSMIIREG, or hardware
timestamping with SIOCSHWTSTAMP/SIOCGHWTSTAMP.
Separate these from the few drivers that use ndo_do_ioctl to
implement SIOCBOND, SIOCBR and SIOCWANDEV commands.
This is a purely cosmetic change intended to help readers find
their way through the implementation.
Cc: Doug Ledford <dledford@redhat.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Vivien Didelot <vivien.didelot@gmail.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Vladimir Oltean <olteanv@gmail.com>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: linux-rdma@vger.kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Use devm_platform_get_and_ioremap_resource() to simplify
code.
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The supplied buffer for the MAC address might not be aligned. Thus
doing a 32bit (or 16bit) access could be on an unaligned address. For
now, enetc is only used on aarch64 which can do unaligned accesses, thus
there is no error. In any case, be correct and use the get/put_unaligned
helpers.
Signed-off-by: Michael Walle <michael@walle.cc>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
After the refactoring introduced in commit 87614b931c24 ("net: enetc:
create a common enetc_pf_to_port helper"), enetc_pf_to_port was coded up
to return -1 in case the passed PCIe device does not have a recognized
BDF.
Make sure the -1 value is checked by the callers, to appease static
checkers.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The previous patch to support PTP Sync packet one-step timestamping
described one-step timestamping packet handling logic as below in
commit message:
- Trasmit packet immediately if no other one in transfer, or queue to
skb queue if there is already one in transfer.
The test_and_set_bit_lock() is used here to lock and check state.
- Start a work when complete transfer on hardware, to release the bit
lock and to send one skb in skb queue if has.
There was not problem of the description, but there was a mistake in
implementation. The locking/test_and_set_bit_lock() should be put in
enetc_start_xmit() which may be called by worker, rather than in
enetc_xmit(). Otherwise, the worker calling enetc_start_xmit() after
bit lock released is not able to lock again for transfer.
Fixes: 7294380c5211 ("enetc: support PTP Sync packet one-step timestamping")
Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Now that enetc supports flow control we have to make sure the settings in
the IERB are correct. Therefore, we actually depend on the enetc-ierb
module. Previously it was possible that this module was disabled while the
enetc was enabled. Fix it by automatically select the enetc-ierb module.
Fixes: e7d48e5fbf30 ("net: enetc: add a mini driver for the Integrated Endpoint Register Block")
Signed-off-by: Michael Walle <michael@walle.cc>
Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
In the ENETC receive path, a frame received by the MAC is first stored
in a 256KB 'FIFO' memory, then transferred to DRAM when enqueuing it to
the RX ring. The FIFO is a shared resource for all ENETC ports, but
every port keeps track of its own memory utilization, on RX and on TX.
There is a setting for RX rings through which they can either operate in
'lossy' mode (where the lack of a free buffer causes an immediate
discard of the frame) or in 'lossless' mode (where the lack of a free
buffer in the ring makes the frame stay longer in the FIFO).
In turn, when the memory utilization of the FIFO exceeds a certain
margin, the MAC can be configured to emit PAUSE frames.
There is enough FIFO memory to buffer up to 3 MTU-sized frames per RX
port while not jeopardizing the other use cases (jumbo frames), and
also not consume bytes from the port TX allocations. Also, 3 MTU-sized
frames worth of memory is enough to ensure zero loss for 64 byte packets
at 1G line rate.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The NXP ENETC is a 4-port Ethernet controller which 'smells' to
operating systems like 4 distinct PCIe PFs with SR-IOV, each PF having
its own driver instance, but in fact there are some hardware resources
which are shared between all ports, like for example the 256 KB SRAM
FIFO between the MACs and the Host Transfer Agent which DMAs frames to
DRAM.
To hide the stuff that cannot be neatly exposed per port, the hardware
designers came up with this idea of having a dedicated register block
which is supposed to be populated by the bootloader, and contains
everything configuration-related: MAC addresses, FIFO partitioning, etc.
When a port is reset using PCIe Function Level Reset, its defaults are
transferred from the IERB configuration. Most of the time, the settings
made through the IERB are read-only in the port's memory space (if they
are even visible), so they cannot be modified at runtime.
Linux doesn't have any advanced FIFO partitioning requirements at all,
but when reading through the hardware manual, it became clear that, even
though there are many good 'recommendations' for default values, many of
them were not actually put in practice on LS1028A. So we end up with a
default configuration that:
(a) does not have enough TX and RX byte credits to support the max MTU
of 9600 (which the Linux driver claims already) properly (at full speed)
(b) allows the FIFO to be overrun with RX traffic, potentially
overwriting internal data structures.
The last part sounds a bit catastrophic, but it isn't. Frames are
supposed to transit the FIFO for a very short time, but they can
actually accumulate there under 2 conditions:
(a) there is very severe congestion on DRAM memory, or
(b) the RX rings visible to the operating system were configured for
lossless operation, and they just ran out of free buffers to copy
the frame to. This is what is used to put backpressure onto the MAC
with flow control.
So since ENETC has not supported flow control thus far, RX FIFO overruns
were never seen with Linux. But with the addition of flow control, we
should configure some registers to prevent this from happening. What we
are trying to protect against are bad actors which continue to send us
traffic despite the fact that we have signaled a PAUSE condition. Of
course we can't be lossless in that case, but it is best to configure
the FIFO to do tail dropping rather than letting it overrun.
So in a nutshell, this driver is a fixup for all the IERB default values
that should have been but aren't.
The IERB configuration needs to be done _before_ the PFs are enabled.
So every PF searches for the presence of the "fsl,ls1028a-enetc-ierb"
node in the device tree, and if it finds it, it "registers" with the
IERB, which means that it requests the IERB to fix up its default
values. This is done through -EPROBE_DEFER. The IERB driver is part of
the fsl_enetc module, but is technically a platform driver, since the
IERB is a good old fashioned MMIO region, as opposed to ENETC ports
which pretend to be PCIe devices.
The driver was already configuring ENETC_PTXMBAR (FIFO allocation for
TX) because due to an omission, TXMBAR is a read/write register in the
PF memory space. But the manual is quite clear that the formula for this
should depend upon the TX byte credits (TXBCR). In turn, the TX byte
credits are only readable/writable through the IERB. So if we want to
ensure that the TXBCR register also has a value that is correct and in
line with TXMBAR, there is simply no way this can be done from the PF
driver, access to the IERB is needed.
I could have modified U-Boot to fix up the IERB values, but that is
quite undesirable, as old U-Boot versions are likely to be floating
around for quite some time from now.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Even though ENETC interfaces are exposed as individual PCIe PFs with
their own driver instances, the ENETC is still fundamentally a
multi-port Ethernet controller, and some parts of the IP take a port
number (as can be seen in the PSFP implementation).
Create a common helper that can be used outside of the TSN code for
retrieving the ENETC port number based on the PF number. This is only
correct for LS1028A, the only Linux-capable instantiation of ENETC thus
far.
Note that ENETC port 3 is PF 6. The TSN code did not care about this
because ENETC port 3 does not support TSN, so the wrong mapping done by
enetc_get_port for PF 6 could have never been hit.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Described in fd5736bf9f23 ("enetc: Workaround for MDIO register access
issue") is a workaround for a hardware bug that requires a register
access of the MDIO controller to never happen concurrently with a
register access of a port PF. To avoid that, a mutual exclusion scheme
with rwlocks was implemented - the port PF accessors are the 'read'
side, and the MDIO accessors are the 'write' side.
When we do XDP_REDIRECT between two ENETC interfaces, all is fine
because the MDIO lock is already taken from the NAPI poll loop.
But when the ingress interface is not ENETC, just the egress is, the
MDIO lock is not taken, so we might access the port PF registers
concurrently with MDIO, which will make the link flap due to wrong
values returned from the PHY.
To avoid this, let's just slap an enetc_lock_mdio/enetc_unlock_mdio at
the beginning and ending of enetc_xdp_xmit. The fact that the MDIO lock
is designed as a rwlock is important here, because the read side is
reentrant (that is one of the main reasons why we chose it). Usually,
the way we benefit of its reentrancy is by running the data path
concurrently on both CPUs, but in this case, we benefit from the
reentrancy by taking the lock even when the lock is already taken
(and that's the situation where ENETC is both the ingress and the egress
interface for XDP_REDIRECT, which was fine before and still is fine now).
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
If the TX ring is congested, enetc_xdp_tx() returns false for the
current XDP frame (represented as an array of software BDs).
This array of software TX BDs is constructed in enetc_rx_swbd_to_xdp_tx_swbd
from software BDs freshly cleaned from the RX ring. The issue is that we
scrub the RX software BDs too soon, more precisely before we know that
we can enqueue the TX BDs successfully into the TX ring.
If we can't enqueue them (and enetc_xdp_tx returns false), we call
enetc_xdp_drop which attempts to recycle the buffers held by the RX
software BDs. But because we scrubbed those RX BDs already, two things
happen:
(a) we leak their memory
(b) we populate the RX software BD ring with an all-zero rx_swbd
structure, which makes the buffer refill path allocate more memory.
enetc_refill_rx_ring
-> if (unlikely(!rx_swbd->page))
-> enetc_new_page
That is a recipe for fast OOM.
Fixes: 7ed2bc80074e ("net: enetc: add support for XDP_TX")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When the XDP program returns an invalid action, we should free the RX
buffer.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
It is possible for one CPU to perform TX hashing (see netdev_pick_tx)
between the 8 ENETC TX rings, and the TX hashing to select TX queue 1.
At the same time, it is possible for the other CPU to already use TX
ring 1 for XDP (either XDP_TX or XDP_REDIRECT). Since there is no mutual
exclusion between XDP and the network stack, we run into an issue
because the ENETC TX procedure is not reentrant.
The obvious approach would be to just make XDP take the lock of the
network stack's TX queue corresponding to the ring it's about to enqueue
in.
For XDP_REDIRECT, this is quite straightforward, a lock at the beginning
and end of enetc_xdp_xmit() should do the trick.
But for XDP_TX, it's a bit more complicated. For one, we do TX batching
all by ourselves for frames with the XDP_TX verdict. This is something
we would like to keep the way it is, for performance reasons. But
batching means that the network stack's lock should be kept from the
first enqueued XDP_TX frame and until we ring the doorbell. That is
mostly fine, except for cases when in the same NAPI loop we have mixed
XDP_TX and XDP_REDIRECT frames. So if enetc_xdp_xmit() gets called while
we are holding the lock from the RX NAPI, then bam, deadlock. The naive
answer could be 'just flush the XDP_TX frames first, then release the
network stack's TX queue lock, then call xdp_do_flush_map()'. But even
xdp_do_redirect() is capable of flushing the batched XDP_REDIRECT
frames, so unless we unlock/relock the TX queue around xdp_do_redirect(),
there simply isn't any clean way to protect XDP_TX from concurrent
network stack .ndo_start_xmit() on another CPU.
So we need to take a different approach, and that is to reserve two
rings for the sole use of XDP. We leave TX rings
0..ndev->real_num_tx_queues-1 to be handled by the network stack, and we
pick them from the end of the priv->tx_ring array.
We make an effort to keep the mapping done by enetc_alloc_msix() which
decides which CPU handles the TX completions of which TX ring in its
NAPI poll. So the XDP TX ring of CPU 0 is handled by TX ring 6, and the
XDP TX ring of CPU 1 is handled by TX ring 7.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Now that commit d6a2829e82cf ("net: enetc: increase RX ring default
size") has increased the RX ring size, it is quite easy to congest the
TX rings when the traffic is predominantly XDP_TX, as the RX ring is
quite a bit larger than the TX one.
Since we bit the bullet and did the expensive thing already (larger RX
rings consume more memory pages), it seems quite foolish to keep the TX
rings small. So make them equally sized with TX.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
xdp_do_redirect already contains:
-> dev_map_enqueue
-> __xdp_enqueue
-> bq_enqueue
-> bq_xmit_all // if we have more than 16 frames
So the logic from enetc will never be hit, because ENETC_DEFAULT_TX_WORK
is 128.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When the code path below fails:
enetc_clean_rx_ring_xdp // XDP_PASS
-> enetc_build_skb
-> enetc_map_rx_buff_to_skb
-> build_skb
enetc_clean_rx_ring_xdp will 'break', but that 'break' instruction isn't
strong enough to actually break the NAPI poll loop, just the switch/case
statement for XDP actions. So we increment rx_frm_cnt and go to the next
frames minding our own business.
Instead let's do what the skb NAPI poll function does, and break the
loop now, waiting for the memory pressure to go away. Otherwise the next
calls to build_skb() are likely to fail too.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When receiving a frame with errors, currently we do nothing with it (we
don't construct an skb or an xdp_buff), we just exit the NAPI poll loop.
Let's put the buffer back into the RX ring (similar to XDP_DROP).
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
enetc_put_xdp_buff has nothing to do with XDP, frankly, it is just a
helper to populate the recycle end of the shadow RX BD ring
(next_to_alloc) with a given buffer.
On the other hand, enetc_put_rx_buff plays more tricks than its name
would suggest.
So let's rename enetc_put_rx_buff into enetc_flip_rx_buff to reflect the
half-page buffer reuse tricks that it employs, and enetc_put_xdp_buff
into enetc_put_rx_buff which suggests a more garden-variety operation.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Later in enetc_clean_tx_ring we have:
/* Scrub the swbd here so we don't have to do that
* when we reuse it during xmit
*/
memset(tx_swbd, 0, sizeof(*tx_swbd));
So these assignments are unnecessary.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Convert system_wq queue_work() to schedule_work() which is
a wrapper around it, since the former is a rare construct.
Fixes: 7294380c5211 ("enetc: support PTP Sync packet one-step timestamping")
Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Normally, the bootloader will already initialize the MAC address
registers of the ENETC and the driver will just use them or generate a
random one, if it is not initialized.
Add a new way to provide the MAC address: via device tree. Besides the
usual 'mac-address' property, there is also the possibility to fetch it
via a NVMEM provider. The sl28 board stores the MAC address in the SPI
NOR flash OTP region. Having this will allow linux to fetch the MAC
address from there without being dependent on the bootloader.
No in-tree boards have the device tree properties set, thus for these,
this is a no-op.
Signed-off-by: Michael Walle <michael@walle.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch is to add support for PTP Sync packet one-step timestamping.
Since ENETC single-step register has to be configured dynamically per
packet for correctionField offeset and UDP checksum update, current
one-step timestamping packet has to be sent only when the last one
completes transmitting on hardware. So, on the TX, this patch handles
one-step timestamping packet as below:
- Trasmit packet immediately if no other one in transfer, or queue to
skb queue if there is already one in transfer.
The test_and_set_bit_lock() is used here to lock and check state.
- Start a work when complete transfer on hardware, to release the bit
lock and to send one skb in skb queue if has.
And the configuration for one-step timestamping on ENETC before
transmitting is,
- Set one-step timestamping flag in extension BD.
- Write 30 bits current timestamp in tstamp field of extension BD.
- Update PTP Sync packet originTimestamp field with current timestamp.
- Configure single-step register for correctionField offeset and UDP
checksum update.
Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Mark TX timestamp type per skb on skb->cb[0], instead of
global variable for all skbs. This is a preparation for
one step timestamp support.
For one-step timestamping enablement, there will be both
one-step and two-step PTP messages to transfer. And a skb
queue is needed for one-step PTP messages making sure
start to send current message only after the last one
completed on hardware. (ENETC single-step register has to
be dynamically configured per message.) So, marking TX
timestamp type per skb is required.
Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Even if the current mapping is correct for the 1 CPU and 2 CPU cases
(currently enetc is included in SoCs with up to 2 CPUs only), better
use a generic rule for the mapping to cover all possible cases.
The number of CPUs is the same as the number of interrupt vectors:
Per device Tx rings -
device_tx_ring[idx], where idx = 0..n_rings_total-1
Per interrupt vector Tx rings -
int_vector[i].ring[j], where i = 0..n_int_vects-1
j = 0..n_rings_per_v-1
Mapping rule -
n_rings_per_v = n_rings_total / n_int_vects
for i = 0..n_int_vects - 1:
for j = 0..n_rings_per_v - 1:
idx = n_int_vects * j + i
int_vector[i].ring[j] <- device_tx_ring[idx]
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20210409071613.28912-1-claudiu.manoil@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The blamed commit introduced a bit in the TX software buffer descriptor
structure for determining whether a BD is final or not; we rearm the TX
interrupt vector for every frame (hence final BD) transmitted.
But there is a problem with the patch: it replaced a condition whose
expression is a bool which was evaluated at the beginning of the "while"
loop with a bool expression that is evaluated on the spot: tx_swbd->is_eof.
The problem with the latter expression is that the tx_swbd has already
been incremented at that stage, so the tx_swbd->is_eof check is in fact
with the _next_ software BD. Which is _not_ final.
The effect is that the CPU is in 100% load with ksoftirqd because it
does not acknowledge the TX interrupt, so the handler keeps getting
called again and again.
The fix is to restore the code structure, and keep the local bool is_eof
variable, just to assign it the tx_swbd->is_eof value instead of
!!tx_swbd->skb.
Fixes: d504498d2eb3 ("net: enetc: add a dedicated is_eof bit in the TX software BD")
Reported-by: Alex Marginean <alexandru.marginean@nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Link: https://lore.kernel.org/r/20210409192759.3895104-1-olteanv@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
This loop will try to unmap enetc_unmap_tx_buff[-1] and crash.
Fixes: 9d2b68cc108d ("net: enetc: add support for XDP_REDIRECT")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/YHBHfCY/yv3EnM9z@mwanda
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|