The logic that polls for the firmware message response uses a shorter
sleep interval for the first few passes.  But there was a typo so it
was using the wrong counter (larger counter) for these short sleep
passes.  The result is a slightly shorter timeout period for these
firmware messages than intended.  Fix it by using the proper counter.

Fixes: 9751e8e7 ("bnxt_en: reduce timeout on initial HWRM calls")
Signed-off-by: NMichael Chan <michael.chan@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since link change polling routine was moved to nicvf side,
we don't need anymore polling function at nicpf side along
with link status info for all enabled Vfs as at VF side
this info is already tracked.

This commit is to remove unnecessary code & fields from
nicpf structure.
Signed-off-by: NVadim Lomovtsev <vlomovtsev@marvell.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Move the link change polling task to VF side in order to
prevent races between VF and PF while sending link change
message(s). This commit is to implement link change request
to be initiated by VF.
Signed-off-by: NVadim Lomovtsev <vlomovtsev@marvell.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In some cases it could happen that nicvf_send_msg_to_pf() could be called
concurrently for the same NIC VF, and thus re-writing mailbox contents and
breaking messaging sequence with PF by re-writing NICVF data.

This commit is to implement mutex for NICVF to protect mailbox registers
and NICVF messaging control data from concurrent access.
Signed-off-by: NVadim Lomovtsev <vlomovtsev@marvell.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

To communicate to PF each of ThunderX NIC VF uses mailbox which is
pair of 64 bit registers available to both VFn and PF.

This commit is to change the xcast message structure in order to
fit it into 64 bit.
Signed-off-by: NVadim Lomovtsev <vlomovtsev@marvell.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The rx_set_mode invokes number of messages to be send to PF for receive
mode configuration. In case if there any issues we need to stop sending
messages and release allocated memory.

This commit is to implement check of nicvf_msg_send_to_pf() result.
Signed-off-by: NVadim Lomovtsev <vlomovtsev@marvell.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

At the end of NIC VF initialization VF sends CFG_DONE message to PF without
using nicvf_msg_send_to_pf routine. This potentially could re-write data in
mailbox. This commit is to implement common way of sending CFG_DONE message
by the same way with other configuration messages by using
nicvf_send_msg_to_pf() routine.
Signed-off-by: NVadim Lomovtsev <vlomovtsev@marvell.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Having one work queue for receive mode configuration ndo_set_rx_mode()
call for all VFs results in making each of them wait till the
set_rx_mode() call completes for another VF if any of close, set
receive mode and change flags calls being already invoked. Potentially
this could cause device state change before appropriate call of receive
mode configuration completes, so the call itself became meaningless,
corrupt data or break configuration sequence.

We don't need any delays in NIC VF configuration sequence so having delayed
work call with 0 delay has no sense.

This commit is to implement one work queue for each NIC VF for set_rx_mode
task and to let them work independently and replacing delayed_work
with work_struct.
Signed-off-by: NVadim Lomovtsev <vlomovtsev@marvell.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Correct STREERING to STEERING at macro name for BGX steering register.
Signed-off-by: NVadim Lomovtsev <vlomovtsev@marvell.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

An issue has been found while testing zero-copy XDP that
causes a reset to be triggered. As it takes some time to
turn the carrier on after setting zc, and we already
start trying to transmit some packets, watchdog considers
this as an erroneous state and triggers a reset.

Don't do any work if netif carrier is not OK.

Fixes: 8221c5eb (ixgbe: add AF_XDP zero-copy Tx support)
Signed-off-by: NJan Sokolowski <jan.sokolowski@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

When the driver clears the XDP xmit ring due to re-configuration or
teardown, in-progress ndo_xdp_xmit must be taken into consideration.

The ndo_xdp_xmit function is typically called from a NAPI context that
the driver does not control. Therefore, we must be careful not to
clear the XDP ring, while the call is on-going. This patch adds a
synchronize_rcu() to wait for napi(s) (preempt-disable regions and
softirqs), prior clearing the queue. Further, the __I40E_CONFIG_BUSY
flag is checked in the ndo_xdp_xmit implementation to avoid touching
the XDP xmit queue during re-configuration.

Fixes: d9314c47 ("i40e: add support for XDP_REDIRECT")
Fixes: 123cecd4 ("i40e: added queue pair disable/enable functions")
Reported-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: NBjörn Töpel <bjorn.topel@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

When the RX rings are created they are also populated with buffers so
that packets can be received. Usually these are kernel buffers, but
for AF_XDP in zero-copy mode, these are user-space buffers and in this
case the application might not have sent down any buffers to the
driver at this point. And if no buffers are allocated at ring creation
time, no packets can be received and no interrupts will be generated so
the NAPI poll function that allocates buffers to the rings will never
get executed.

To rectify this, we kick the NAPI context of any queue with an
attached AF_XDP zero-copy socket in two places in the code. Once after
an XDP program has loaded and once after the umem is registered.  This
take care of both cases: XDP program gets loaded first then AF_XDP
socket is created, and the reverse, AF_XDP socket is created first,
then XDP program is loaded.

Fixes: d0bcacd0 ("ixgbe: add AF_XDP zero-copy Rx support")
Signed-off-by: NMagnus Karlsson <magnus.karlsson@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

When the RX rings are created they are also populated with buffers
so that packets can be received. Usually these are kernel buffers,
but for AF_XDP in zero-copy mode, these are user-space buffers and
in this case the application might not have sent down any buffers
to the driver at this point. And if no buffers are allocated at ring
creation time, no packets can be received and no interrupts will be
generated so the NAPI poll function that allocates buffers to the
rings will never get executed.

To rectify this, we kick the NAPI context of any queue with an
attached AF_XDP zero-copy socket in two places in the code. Once
after an XDP program has loaded and once after the umem is registered.
This take care of both cases: XDP program gets loaded first then AF_XDP
socket is created, and the reverse, AF_XDP socket is created first,
then XDP program is loaded.

Fixes: 0a714186 ("i40e: add AF_XDP zero-copy Rx support")
Signed-off-by: NMagnus Karlsson <magnus.karlsson@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The enabling L3/L4 filtering for transmit switched packets for all
devices caused unforeseen issue on older devices when trying to send UDP
traffic in an ordered sequence.  This bit was originally intended for X550
devices, which supported this feature, so limit the scope of this bit to
only X550 devices.
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>

Booting 4.20 on SolidRun Clearfog issues this warning with DMA API
debug enabled:

WARNING: CPU: 0 PID: 555 at kernel/dma/debug.c:1230 check_sync+0x514/0x5bc
mvneta f1070000.ethernet: DMA-API: device driver tries to sync DMA memory it has not allocated [device address=0x000000002dd7dc00] [size=240 bytes]
Modules linked in: ahci mv88e6xxx dsa_core xhci_plat_hcd xhci_hcd devlink armada_thermal marvell_cesa des_generic ehci_orion phy_armada38x_comphy mcp3021 spi_orion evbug sfp mdio_i2c ip_tables x_tables
CPU: 0 PID: 555 Comm: bridge-network- Not tainted 4.20.0+ #291
Hardware name: Marvell Armada 380/385 (Device Tree)
[<c0019638>] (unwind_backtrace) from [<c0014888>] (show_stack+0x10/0x14)
[<c0014888>] (show_stack) from [<c07f54e0>] (dump_stack+0x9c/0xd4)
[<c07f54e0>] (dump_stack) from [<c00312bc>] (__warn+0xf8/0x124)
[<c00312bc>] (__warn) from [<c00313b0>] (warn_slowpath_fmt+0x38/0x48)
[<c00313b0>] (warn_slowpath_fmt) from [<c00b0370>] (check_sync+0x514/0x5bc)
[<c00b0370>] (check_sync) from [<c00b04f8>] (debug_dma_sync_single_range_for_cpu+0x6c/0x74)
[<c00b04f8>] (debug_dma_sync_single_range_for_cpu) from [<c051bd14>] (mvneta_poll+0x298/0xf58)
[<c051bd14>] (mvneta_poll) from [<c0656194>] (net_rx_action+0x128/0x424)
[<c0656194>] (net_rx_action) from [<c000a230>] (__do_softirq+0xf0/0x540)
[<c000a230>] (__do_softirq) from [<c00386e0>] (irq_exit+0x124/0x144)
[<c00386e0>] (irq_exit) from [<c009b5e0>] (__handle_domain_irq+0x58/0xb0)
[<c009b5e0>] (__handle_domain_irq) from [<c03a63c4>] (gic_handle_irq+0x48/0x98)
[<c03a63c4>] (gic_handle_irq) from [<c0009a10>] (__irq_svc+0x70/0x98)
...

This appears to be caused by mvneta_rx_hwbm() calling
dma_sync_single_range_for_cpu() with the wrong struct device pointer,
as the buffer manager device pointer is used to map and unmap the
buffer.  Fix this.
Signed-off-by: NRussell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Another platform requires even longer delay to make the device work
correctly after S3.

So increase the delay to 300ms.

BugLink: https://bugs.launchpad.net/bugs/1798921Signed-off-by: NKai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Recent commit below has introduced a bug in netcp driver that causes
the ethss driver probe failure and thus break the networking function
on K2 SoCs such as K2HK, K2L, K2E etc. This patch fixes the issue to
restore networking on the above SoCs.

Fixes: 21c328dc ("net: ethernet: Convert to using %pOFn instead of device_node.name")
Signed-off-by: NMurali Karicheri <m-karicheri2@ti.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch fixes the missing device reference release-after-use in
the positive leg of the roce reset API of the HNS DSAF.

Fixes: c969c6e7 ("net: hns: Fix object reference leaks in hns_dsaf_roce_reset()")
Reported-by: NJohn Garry <john.garry@huawei.com>
Signed-off-by: NSalil Mehta <salil.mehta@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We are saving the status of EEE even before we try to enable it. This
leads to a race with XMIT function that tries to arm EEE timer before we
set it up.

Fix this by only saving the EEE parameters after all operations are
performed with success.
Signed-off-by: NJose Abreu <joabreu@synopsys.com>
Fixes: d765955d ("stmmac: add the Energy Efficient Ethernet support")
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The ll2 forwards all syn packets to the driver without validating the mac
address. Add validation check in the driver's iWARP listener flow and drop
the packet if it isn't intended for the device.
Signed-off-by: NAriel Elior <ariel.elior@marvell.com>
Signed-off-by: NMichal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The assumption that the maximum size of a syn packet is 128 bytes
is wrong. Tunneling headers were not accounted for.
Allocate buffers large enough for mtu.
Signed-off-by: NAriel Elior <ariel.elior@marvell.com>
Signed-off-by: NMichal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is a spelling mistake in a en_err error message. Fix it.
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Reviewed-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If mv643xx_eth_shared_of_probe() fails, mv643xx_eth_shared_probe()
leaves clk enabled.

Found by Linux Driver Verification project (linuxtesting.org).
Signed-off-by: NAlexey Khoroshilov <khoroshilov@ispras.ru>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

GMAC IP is little-endian and used on several kind of CPU (big or little
endian). Main callbacks functions of the stmmac drivers take care about
it. It was not the case for dwmac4_get_timestamp function.

Fixes: ba1ffd74 ("stmmac: fix PTP support for GMAC4")
Signed-off-by: NAlexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The function-local variable "delay" enters the loop interpreted as delay
in bits. However, inside the loop it gets overwritten by the result of
mlxsw_sp_pg_buf_delay_get(), and thus leaves the loop as quantity in
cells. Thus on second and further loop iterations, the headroom for a
given priority is configured with a wrong size.

Fix by introducing a loop-local variable, delay_cells. Rename thres to
thres_cells for consistency.

Fixes: f417f04d ("mlxsw: spectrum: Refactor port buffer configuration")
Signed-off-by: NPetr Machata <petrm@mellanox.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

SYSTEMPORT has its RXCHK parser block that attempts to validate the
packet structures, unfortunately setting the L2 header check bit will
cause Bridge PDUs (BPDUs) to be incorrectly rejected because they look
like LLC/SNAP packets with a non-IPv4 or non-IPv6 Ethernet Type.

Fixes: 4e8aedfe78c7 ("net: systemport: Turn on offloads by default")
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently the ethtool_regs version is set to 0 for FEC devices.

Use this field to store the register dump version exposed by the
kernel. The choosen version 2 corresponds to the kernel compile test:

        #if defined(CONFIG_M523x) || defined(CONFIG_M527x)
        || defined(CONFIG_M528x) || defined(CONFIG_M520x)
        || defined(CONFIG_M532x) || defined(CONFIG_ARM)
        || defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST)

and version 1 corresponds to the opposite. Binaries of ethtool unaware
of this version will dump the whole set as usual.
Signed-off-by: NVivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The of_find_device_by_node() takes a reference to the underlying device
structure, we should release that reference.
Signed-off-by: NHuang Zijiang <huang.zijiang@zte.com.cn>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently mlx5 driver creates xdp redirect hw queues unconditionally on
netdevice open, This is great until someone starts redirecting XDP traffic
via ndo_xdp_xmit on mlx5 device and changes the device configuration at
the same time, this might cause crashes, since the other device's napi
is not aware of the mlx5 state change (resources un-availability).

To fix this we must synchronize with other devices napi's on the system.
Added a new flag under mlx5e_priv to determine XDP TX resources are
available, set/clear it up when necessary and use synchronize_rcu()
when the flag is turned off, so other napi's are in-sync with it, before
we actually cleanup the hw resources.

The flag is tested prior to committing to transmit on mlx5e_xdp_xmit, and
it is sufficient to determine if it safe to transmit or not. The other
two internal flags (MLX5E_STATE_OPENED and MLX5E_SQ_STATE_ENABLED) become
unnecessary. Thus, they are removed from data path.

Fixes: 58b99ee3 ("net/mlx5e: Add support for XDP_REDIRECT in device-out side")
Reported-by: NToke Høiland-Jørgensen <toke@redhat.com>
Reviewed-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Eliminate the following compilation warning:

drivers/net/ethernet/mellanox/mlx5/core/events.c: warning: 'error_str'
may be used uninitialized in this function [-Wuninitialized]:  => 238:3

Fixes: c2fb3db2 ("net/mlx5: Rework handling of port module events")
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Reviewed-by: NMikhael Goikhman <migo@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

When EEH is injected and PCI bus stalls, mlx5's pci error detect
function is called to deactivate the command interface and tear down
the device. The issue is that there can be a thread that already
passed MLX5_DEVICE_STATE_INTERNAL_ERROR check, it will send the command
and stuck in the wait_func.

Solution:
Add function mlx5_cmd_flush to disable command interface and clear all
the pending commands. When device state is set to
MLX5_DEVICE_STATE_INTERNAL_ERROR, call mlx5_cmd_flush to ensure all
pending threads waiting for firmware commands completion are terminated.

Fixes: c1d4d2e9 ("net/mlx5: Avoid calling sleeping function by the health poll thread")
Signed-off-by: NHuy Nguyen <huyn@mellanox.com>
Reviewed-by: NDaniel Jurgens <danielj@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

New channels are applied to the priv channels only after they
are successfully opened. Then, the indirection table should be built
according to the new number of channels.
Currently, such build is preformed independently of whether the
channels opening is successful, and is not reverted on failure.

The bug is caused due to removal of rss params from channels struct
and moving it to priv struct. That change cause to independency between
channels and rss params.
This causes a crash on a later point, when accessing rqn of a non
existing channel.

This patch fixes it by moving the indirection table build right before
switching the priv channels to new channels struct, after the new set of
channels was successfully opened.

Fixes: bbeb53b8 ("net/mlx5e: Move RSS params to a dedicated struct")
Signed-off-by: NMaria Pasechnik <mariap@mellanox.com>
Reviewed-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Update driver version due to bug fix.
Signed-off-by: NArthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix race condition between ena_update_on_link_change() and
ena_restore_device().

This race can occur if link notification arrives while the driver
is performing a reset sequence. In this case link can be set up,
enabling the device, before it is fully restored. If packets are
sent at this time, the driver might access uninitialized data
structures, causing kernel crash.

Move the clearing of ENA_FLAG_ONGOING_RESET and netif_carrier_on()
after ena_up() to ensure the device is ready when link is set up.

Fixes: d18e4f68 ("net: ena: fix race condition between device reset and link up setup")
Signed-off-by: NArthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When an ethernet frame is padded to meet the minimum ethernet frame
size, the padding octets are not covered by the hardware checksum.
Fortunately the padding octets are usually zero's, which don't affect
checksum. However, it is not guaranteed. For example, switches might
choose to make other use of these octets.
This repeatedly causes kernel hardware checksum fault.

Prior to the cited commit below, skb checksum was forced to be
CHECKSUM_NONE when padding is detected. After it, we need to keep
skb->csum updated. However, fixing up CHECKSUM_COMPLETE requires to
verify and parse IP headers, it does not worth the effort as the packets
are so small that CHECKSUM_COMPLETE has no significant advantage.

Future work: when reporting checksum complete is not an option for
IP non-TCP/UDP packets, we can actually fallback to report checksum
unnecessary, by looking at cqe IPOK bit.

Fixes: 88078d98 ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends")
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The bitmap of found partitions in efx_ef10_mtd_probe was not
initialised, causing partitions to be suppressed based off whatever
value was in the bitmap at the start.

Fixes: 33664635 ("sfc: suppress duplicate nvmem partition types in efx_ef10_mtd_probe")
Signed-off-by: NBert Kenward <bkenward@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This reverts commit 2e6eedb4.

Sander reported a regression causing a kernel panic[1],
therefore let's revert this commit.

[1] https://marc.info/?t=154965066400001&r=1&w=2Signed-off-by: NHeiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This reverts commit bd7153bd.

There doesn't seem to be anything wrong with this patch,
it's just reverted to get a stable baseline again.
Signed-off-by: NHeiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

8c56df37 ("net: add support for Cavium PTP coprocessor") added the
Cavium PTP coprocessor driver and enabled it by default.  Remove the
"default y" because the driver only applies to Cavium ThunderX processors.

Fixes: 8c56df37 ("net: add support for Cavium PTP coprocessor")
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

dev_consume_skb_irq() should be called in sbdma_tx_process() when
skb xmit done. It makes drop profiles(dropwatch, perf) more
friendly.
Signed-off-by: NYang Wei <yang.wei9@zte.com.cn>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>