Following commit 8f4cccbb ('net: Set device operstate at registration
time') it is now correct and preferable to set the carrier off before
registering a device.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

We also stop clearing *efx in efx_init_struct().  This is safe because
alloc_etherdev_mq() already clears it for us.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

RX DMA is limited by the length specified in each descriptor and not
by the MAC.  Over-length frames may get into the RX FIFO regardless of
the MAC settings, due to a hardware bug, but they will be truncated by
the packet DMA engine and reported as such in the completion event.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

We try to defer resets while the device is not READY, but we're not
doing this quite correctly.  In particular, changes to efx_nic::state
are documented as serialised by the RTNL lock, but they aren't.

1. We check whether a reset was requested during probe (suggesting
broken hardware) before we allow requested resets to be scheduled.
This leaves a window where a requested reset would be deferred
indefinitely.

2. Although we cancel the reset work item during device removal,
there are still later operations that can cause it to be scheduled
again.  We need to check the state before scheduling it.

3. Since the state can change between scheduling and running of
the work item, we still need to check it there, and we need to
do so *after* acquiring the RTNL lock which serialises state
changes.

4. We must cancel the reset work item during device removal, if the
state could ever have been READY.  This wasn't done in some of the
failure paths from efx_pci_probe().  Move the cancellation to
efx_pci_remove_main().
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

The current informational message doesn't properly explain what
happens, and could also appear if we defer a reset during
suspend/resume.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

efx_change_mtu() and efx_realloc_channels() each stop and start much
of the NIC, even if it has been disabled.  Since efx_start_all() is a
no-op when the NIC is disabled, this is probably harmless in the case
of efx_change_mtu(), but efx_realloc_channels() also reenables
interrupts which could be a bad thing to do.

Change efx_start_all() and efx_start_interrupts() to assert that the
NIC is not disabled, but make efx_stop_interrupts() do nothing if the
NIC is disabled (since it is already stopped), consistent with
efx_stop_all().

Update comments for efx_start_all() and efx_stop_all() to describe
their purpose and preconditions more accurately.

Add a common function to check and log if the NIC is disabled, and use
it in efx_net_open(), efx_change_mtu() and efx_realloc_channels().
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Interrupt state should be consistently guarded by the RTNL lock once
the net device is registered.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Currently we ignore and clear the disabled state.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

I don't think these PM functions can race with userland net device
operations, but it's much easier to reason about locking if state is
consistently guarded by the same lock.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

STATE_INIT and STATE_FINI are equivalent and represent incompletely
initialised states; combine them as STATE_UNINIT.

Rename STATE_RUNNING to STATE_READY, to avoid confusion with
netif_running() and IFF_RUNNING.

The comments do not quite match current usage, but this will be
corrected in subsequent fixes.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

We only use tso_state::full_packet_space to calculate the IPv4 tot_len
or IPv6 payload_len, not to set tso_state::packet_space.  Replace it
with an ip_base_len field holding the value of tot_len or payload_len
before including the TCP payload, which is much more useful when
constructing the new headers.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

TSO header buffers contain a control structure immediately followed by
the packet headers, and are kept on a free list when not in use.  This
complicates buffer management and tends to result in cache read misses
when we recycle such buffers (particularly if DMA-coherent memory
requires caches to be disabled).

Replace the free list with a simple mapping by descriptor index.  We
know that there is always a payload descriptor between any two
descriptors with TSO header buffers, so we can allocate only one
such buffer for each two descriptors.

While we're at it, use a standard error code for allocation failure,
not -1.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

We now have a definite upper bound on the number of descriptors per
skb; use that to stop the queue when the next packet might not fit.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Add a flags field to struct efx_tx_buffer, replacing the
continuation and map_single booleans.

Since a single descriptor cannot be both a TSO header and the last
descriptor for an skb, unionise efx_tx_buffer::{skb,tsoh} and add
flags for validity of these fields.

Clear all flags in free buffers (whereas previously the continuation
flag would be set).
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Using eth_hw_addr_random() to generate a random Ethernet address
(MAC) to be used by a net device and set addr_assign_type.
Not need to duplicating its implementation.

spatch with a semantic match is used to found this problem.
(http://coccinelle.lip6.fr/)
Signed-off-by: NWei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Using eth_hw_addr_random() to generate a random Ethernet address
(MAC) to be used by a net device and set addr_assign_type.
Not need to duplicating its implementation.

spatch with a semantic match is used to found this problem.
(http://coccinelle.lip6.fr/)
Signed-off-by: NWei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Similar to fsl_pq_mdio.c, this driver is for the 10G MDIO controller on
Freescale Frame Manager Ethernet controllers.
Signed-off-by: NTimur Tabi <timur@freescale.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is the implementation for igb to allow forcing MDI state
via ethtool, allowing users to work around some improperly
behaving switches.

Forcing in this driver is for now only allowed when auto-neg is
enabled.
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
CC: Carolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: Aaron Brown aaron.f.brown@intel.com
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Some users report issues with link failing when connected to certain
switches.  This gives the user the ability to control the MDI state
from the driver, allowing users to work around some improperly
behaving switches.

Forcing in this driver is for now only allowed when auto-neg is
enabled.

This is in regards to the related ethtool app patch and
bugzilla.kernel.org bug 11998
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
CC: bruce.w.allan@intel.com
CC: n.poppelier@xs4all.nl
CC: bastien@durel.org
CC: jsveiga@it.eng.br
Tested-by: Aaron Brown aaron.f.brown@intel.com
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This is the implementation in e1000 to allow ethtool to force
MDI state, allowing users to work around some improperly
behaving switches.

Forcing in this driver is for now only allowed when auto-neg is enabled.

To use must have the matching version of ethtool app that supports
this functionality.
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
CC: Tushar Dave <tushar.n.dave@intel.com>
Tested-by: Aaron Brown aaron.f.brown@intel.com
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

In order for igb to support MDI setting support via
ethtool this code is needed to allow setting the MDI state
via software.

This is in regards to the related ethtool patch
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Aaron Brown aaron.f.brown@intel.com
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

In order for e1000e to support MDI setting support via
ethtool this code is needed to allow setting the MDI state
via software.

This is in regards to the related ethtool patch and
fixes bugzilla.kernel.org bug 11998
Signed-off-by: NBruce W Allan <bruce.w.allan@intel.com>
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Aaron Brown aaron.f.brown@intel.com
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

When getting clock, give a chance to the CPUs without DT support,
which use Common Clock Framework, such as Loongson1B.
Signed-off-by: NKelvin Cheung <keguang.zhang@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NPhil Edworthy <phil.edworthy@renesas.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change updates the code related to configuring the transmit frame
checksum.  Specifically I have updated the code so that we can only skip
inserting the checksum in the case that we are not performing some other
offload that will modify the frame data.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NPeter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>

This change moves the RSC code into the non-EOP descriptor handling
function. The main motivation behind this change is to help reduce the
overhead in the non-RSC case. Previously the non-RSC path code would
always be checking for append count even if RSC had been disabled. Now
this code is completely skipped in a single conditional check instead of
having to make two separate checks.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NPeter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>

This patch creates a function named ixgbe_fetch_rx_buffer. The sole
purpose of this function is to retrieve a single buffer off of the ring and
to place it in an skb.

The advantage to doing this is that it helps improve the readability since
I can decrease the indentation and for the code in this section.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NPeter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>

This change makes it so that if only the first 256 bytes of a buffer are
used we just copy the data out and leave the offset and page count
unchanged. There are multiple advantages to this. First it allows us to
reuse the page much more in the case of pages larger than 4K. It also
allows us to avoid some expensive atomic operations in the form of
get_page/put_page. In perf I have seen CPU utilization for put_page drop
from 3.5% to 1.8% as a result of this patch when doing small packet routing,
and packet rates increased by about 3%.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NPeter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>

This change creates a separate function for functionality similar to
pskb_pull_tail.  The main motivation for moving it to a separate function
is so that later I can just skip this function in the case where we have
already copied the buffer into skb->head.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NPeter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>

This patch makes it so that we will always have ownership of the buffers by
the time we get to ixgbe_add_rx_frag. This is necessary as I am planning to
add a copy-break to ixgbe_add_rx_frag and in order for that to function
correctly we need the CPU to have ownership of the buffer.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NPeter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>

This change makes it so that we do not use double buffering if the page
size is larger than 4K.  Instead we will simply walk through the page using
up to 3K per receive, and if we receive less than we only move the offset
by that amount.  We will free the page when there is no longer any space
left that we can use instead of checking the page count to see if we can
cycle back to the start.

The main motivation behind this is to avoid the unnecessary truesize cost
for using a half page when most packets are 2K or smaller. With this new
approach the largest possible truesize for a page fragment will be 3K when
PAGE_SIZE is larger than 4K.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NPeter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>

This patch combines ixgbe_add_rx_frag and ixgbe_can_reuse_page into a
single function. The main motivation behind this is to make better use of
the values so that we don't have to load them from memory and into
registers twice.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NPeter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>

This change reverts an earlier patch that introduced
ixgbe_init_rx_page_offset. The idea behind the function was to provide
some variation in the starting offset for the page in order to reduce
hot-spots in the cache. However it doesn't appear to provide any
significant benefit in the testing I have done. It has however been a
source of several bugs, and it blocks us from being able to use 2K
fragments on larger page sizes. So the decision I made was to remove it.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NPeter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>

 - Use kcalloc() / vzalloc() instead of an extra bitmap_zero().
 - Add __GFP_NOWARN to kcalloc() since we'll try vzalloc() if it fails.
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Fix some issues around int variables used in data structures related
to memory registration.

Handle int overflow in mlx4_init_icm_table by using a u64 intermediate
variable and changing struct mlx4_icm_table num_obj field to be u32.

Change some more fields/variables to use u32 instead of int to prevent
a case where the variable becomes negative when bit 31 is set.

Also subtract log_mtts_per_seg from the exponent when computing
num_mtt, since its added later on in that very same code area.

This and the previous commit fixes some issues which actually prevent
commit db5a7a65 ("mlx4_core: Scale size of MTT table with system
RAM") from working.  Now, when the number of MTTs is scaled with the
size of the RAM we can map up to 8TB.
Signed-off-by: NYishai Hadas <yishaih@mellanox.com>
Signed-off-by: NJack Morgenstein <jackm@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

mlx4_buddy_init uses kmalloc() to allocate bitmaps, which fails when
the required size is beyond the max supported value (or when memory is
too fragmented to handle a huge allocation).  Extend this to use use
vmalloc() if kmalloc() fails, and take that into account when freeing
the bitmaps as well.

This fixes a driver load failure when log num mtt is 26 or higher, and
is a step in the direction of allowing to register huge amounts of
memory on large memory systems.
Signed-off-by: NYishai Hadas <yishaih@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Convert a 0 error return code to a negative one, as returned elsewhere in the
function.

A simplified version of the semantic match that finds this problem is as
follows: (http://coccinelle.lip6.fr/)

// <smpl>
@@
identifier ret;
expression e,e1,e2,e3,e4,x;
@@

(
if (\(ret != 0\|ret < 0\) || ...) { ... return ...; }
|
ret = 0
)
... when != ret = e1
*x = \(kmalloc\|kzalloc\|kcalloc\|devm_kzalloc\|ioremap\|ioremap_nocache\|devm_ioremap\|devm_ioremap_nocache\)(...);
... when != x = e2
    when != ret = e3
*if (x == NULL || ...)
{
  ... when != ret = e4
*  return ret;
}
// </smpl>
Signed-off-by: NJulia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Convert a 0 error return code to a negative one, as returned elsewhere in the
function.

A simplified version of the semantic match that finds this problem is as
follows: (http://coccinelle.lip6.fr/)

// <smpl>
@@
identifier ret;
expression e,e1,e2,e3,e4,x;
@@

(
if (\(ret != 0\|ret < 0\) || ...) { ... return ...; }
|
ret = 0
)
... when != ret = e1
*x = \(kmalloc\|kzalloc\|kcalloc\|devm_kzalloc\|ioremap\|ioremap_nocache\|devm_ioremap\|devm_ioremap_nocache\)(...);
... when != x = e2
    when != ret = e3
*if (x == NULL || ...)
{
  ... when != ret = e4
*  return ret;
}
// </smpl>
Signed-off-by: NJulia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>