efx_unregister_netdev() should not call efx_release_tx_buffers()
directly, as it is already done when closing the device:
efx_net_stop() -> efx_stop_all() -> efx_stop_datapath() ->
efx_fini_tx_queue() -> efx_release_tx_buffers().

(This was presumably a workaround for a race between efx_stop_all()
and the data path that has since been properly fixed.)
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

rx_queue::enabled guards refill, so rename it to reflect that.  Clear
it at the start of the queue teardown process rather than waiting for
the RX queue to be flushed.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

There are many problems with the current efx_stop_interrupts() and
efx_start_interrupts():

1. On Siena, it is unsafe to disable the master IRQ enable bit
(DRV_INT_EN_KER) while any IRQ sources are enabled.

2. On EF10 there is no master IRQ enable bit, so we cannot expect to
defer IRQs without tearing down event queues.  (Though I don't think
we will need to keep any event queues around while the device is down,
as we do for VFDI on Siena.)

3. synchronize_irq() only waits for a running IRQ handler to finish,
not for any propagation through IRQ controllers.  Therefore an IRQ may
still be received and handled after efx_stop_interrupts() returns.
IRQ handlers can then race with channel reallocation.

To fix this:

a. Introduce a software IRQ enable flag.  So long as this is clear,
IRQ handlers will only acknowledge IRQs and not touch the channel
structures.

b. Define a new struct efx_msi_context as the context for MSIs.  This
is never reallocated and is sufficient to find the software enable
flag and the channel structure.  It also includes the channel/IRQ
name, which was previously separated out as it must also not be
reallocated.

c. Split efx_{start,stop}_interrupts() into
efx_{,soft_}_{enable,disable}_interrupts().  The 'soft' functions
don't touch the hardware master enable flag (if it exists) and don't
reinitialise or tear down channels with the keep_eventq flag set.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

efx_process_channel_now() is unneeded since self-tests can rely on
normal NAPI polling.  Remove it and all calls to it.

efx_channel::work_pending and efx_channel_processed() are also
unneeded (the latter being the same as efx_nic_eventq_read_ack()).
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

The lifetime of an irq_cpu_rmap is odd: we have to allocate it before
installing IRQ handlers and free it before removing the IRQ handlers.
As a result of this asymmetry, it was omitted from some failure paths.

On another failure path, we could try to remove IRQ handlers we
had not yet installed.

Move the irq_cpu_rmap allocation and freeing alongside IRQ handler
installation and removal, in efx_nic_{init,fini}_interrupts().
Count the number of IRQ handlers successfully installed and only
remove those on the failure path.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

PCI legacy interrupts are level-triggered, and we cannot mask them up
on an isolated device.  Instead, disable the IRQ at the controller
until we have recovered.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Driver probe currently results in:

WARNING: at drivers/base/core.c:576 device_create_file+0x57/0x7e()
Attribute phy_type: write permission without 'store'
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

So far, only net_device * could be passed along with netdevice notifier
event. This patch provides a possibility to pass custom structure
able to provide info that event listener needs to know.
Signed-off-by: NJiri Pirko <jiri@resnulli.us>

v2->v3: fix typo on simeth
	shortened dev_getter
	shortened notifier_info struct name
v1->v2: fix notifier_call parameter in call_netdevice_notifier()
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

efx_start_datapath() asserts that we can fit 2 RX scatter buffers plus
a software structure, each appropriately aligned, into a single page.
Where L1_CACHE_BYTES == 256 and PAGE_SIZE == 4096, which is the case
on s390, this assertion fails.

The current scatter buffer size is also not a multiple of 64 or 128,
which are more common cache line sizes.  If we can make both the start
and end of a scatter buffer cache-aligned, this will reduce the need
for read-modify-write operations on inter- processor links.

Fix the alignment by reducing EFX_RX_USR_BUF_SIZE to 2048 - 256 ==
1792.  (We could use 2048 - L1_CACHE_BYTES, but EFX_RX_USR_BUF_SIZE
also affects user-level networking where a larger amount of
housekeeping data may be needed.  Although this version of the driver
does not support user-level networking, I prefer to keep scattering
behaviour consistent with the out-of-tree version.)

This still doesn't fix the s390 build because like most architectures
it has NET_IP_ALIGN == 2.  When NET_IP_ALIGN != 0 we cannot achieve
cache line alignment at either the start or end of a scatter buffer,
so there is actually no point in padding the buffers to a multiple of
the cache line size.  All we need is 4-byte alignment of the network
header, so do that.

Adjust the assertions accordingly.
Reported-by: NGeert Uytterhoeven <geert@linux-m68k.org>
Reported-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>
Acked-by: NGeert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The two architectures that define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
(powerpc and x86) now both define NET_IP_ALIGN as 0, so there is no
need for this optimisation any more.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Trivial sparse detected functions that should be static.
Signed-off-by: NStephen Hemminger <stephen@networkplumber.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Remove duplicated include.
Signed-off-by: NWei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Allocating 2 buffers per page is insanely inefficient when MTU is 1500
and PAGE_SIZE is 64K (as it usually is on POWER).  Allocate as many as
we can fit, and choose the refill batch size at run-time so that we
still always use a whole page at once.

[bwh: Fix loop condition to allow for compound pages; rebase]
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

On POWER systems, DMA mapping/unmapping operations are very expensive.
These changes reduce these costs by trying to reuse DMA mapped pages.

After all the buffers associated with a page have been processed and
passed up, the page is placed into a ring (if there is room).  For
each page that is required for a refill operation, a page in the ring
is examined to determine if its page count has fallen to 1, ie. the
kernel has released its reference to these packets.  If this is the
case, the page can be immediately added back into the RX descriptor
ring, without having to re-map it for DMA.

If the kernel is still holding a reference to this page, it is removed
from the ring and unmapped for DMA.  Then a new page, which can
immediately be used by RX buffers in the descriptor ring, is allocated
and DMA mapped.

The time a page needs to spend in the recycle ring before the kernel
has released its page references is based on the number of buffers
that use this page.  As large pages can hold more RX buffers, the RX
recycle ring can be shorter.  This reduces memory usage on POWER
systems, while maintaining the performance gain achieved by recycling
pages, following the driver change to pack more than two RX buffers
into large pages.

When an IOMMU is not present, the recycle ring can be small to reduce
memory usage, since DMA mapping operations are inexpensive.

With a small recycle ring, attempting to refill the descriptor queue
with more buffers than the equivalent size of the recycle ring could
ultimately lead to memory leaks if page entries in the recycle ring
were overwritten.  To prevent this, the check to see if the recycle
ring is full is changed to check if the next entry to be written is
NULL.

[bwh: Combine and rebase several commits so this is complete
 before the following buffer-packing changes.  Remove module
 parameter.]
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Enable RX DMA scattering iff an RX buffer large enough for the current
MTU will not fit into a single page and the NIC supports DMA
scattering for kernel-mode RX queues.

On Falcon and Siena, the RX_USR_BUF_SIZE field is used as the DMA
limit for both all RX queues with scatter enabled.  Set it to 1824,
matching what Onload uses now.

Maintain a statistic for frames truncated due to lack of descriptors
(rx_nodesc_trunc).  This is distinct from rx_frm_trunc which may be
incremented when scattering is disabled and implies an over-length
frame.

Whenever an MTU change causes scattering to be turned on or off,
update filters that point to the PF queues, but leave others
unchanged, as VF drivers assume scattering is off.

Add n_frags parameters to various functions, and make them iterate:
- efx_rx_packet()
- efx_recycle_rx_buffers()
- efx_rx_mk_skb()
- efx_rx_deliver()

Make efx_handle_rx_event() responsible for updating
efx_rx_queue::removed_count.

Change the RX pipeline state to a starting ring index and number of
fragments, and make __efx_rx_packet() responsible for clearing it.

Based on earlier versions by David Riddoch and Jon Cooper.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

The pipeline mechanism will need to change a bit for scattered
packets.  Add a wrapper to insulate efx_process_channel() from this.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Replace efx_nic::rx_buffer_len with efx_nic::rx_dma_len, the maximum
RX DMA length.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

The Linux side of EEH is triggered by MMIO reads, but this
driver's data path does not issue any MMIO reads (except in
legacy interrupt mode).  Therefore add a monitor function
to poll EEH periodically.

When preparing to reset the device based on our own error
detection, also poll EEH and defer to its recovery mechanism
if appropriate.

[bwh: Use a separate condition for the initial link poll; fix some
 style errors]
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

[bwh: Remove more dead code, and make efx_ptp_rx() pull the data it
 needs into the header area.]
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

We must only ever stop TX queues when they are full or the net device
is not 'ready' so far as the net core, and specifically the watchdog,
is concerned.  Otherwise, the watchdog may fire *immediately* if no
packets have been added to the queue in the last 5 seconds.

The device is ready if all the following are true:

(a) It has a qdisc
(b) It is marked present
(c) It is running
(d) The link is reported up

(a) and (c) are normally true, and must not be changed by a driver.
(d) is under our control, but fake link changes may disturb userland.
This leaves (b).  We already mark the device absent during reset
and self-test, but we need to do the same during MTU changes and ring
reallocation.  We don't need to do this when the device is brought
down because then (c) is already false.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

The __dev* removal patches for the network drivers ended up messing up
the function prototypes for a bunch of drivers.  This patch fixes all of
them back up to be properly aligned.

Bonus is that this almost removes 100 lines of code, always a nice
surprise.
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

CONFIG_HOTPLUG is going away as an option.  As result the __dev*
markings will be going away.

Remove use of __devinit, __devexit_p, __devinitdata, __devinitconst,
and __devexit.
Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Most of the module parameters treated as boolean are currently exposed
as type int or uint.  Defining them with the proper type is useful
documentation for both users and developers.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

The assertion of netif_device_present() at the top of
efx_hard_start_xmit() may fail if we don't do this.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

There are now standard functions for dealing with little-endian bit
arrays, so use them instead of our own implementations.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>
Signed-off-by: NTakuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Add PTP IEEE-1588 support and make accesible via the PHC subsystem.

This work is based on prior code by Andrew Jackson
Signed-off-by: NStuart Hodgson <smhodgson@solarflare.com>
[bwh:
 - Add byte order conversion in efx_ptp_send_times()
 - Simplify conversion of PPS event times
 - Add the built-in vs module check to CONFIG_SFC_PTP dependencies]
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Allows an extra channel to override the standard receive_skb handler
and also for extra non generic operations to be performed on remove.

Also set default rx strategy so only skbs can be delivered to the
PTP receive function.
Signed-off-by: NStuart Hodgson <smhodgson@solarflare.com>
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

The PTP channel will have its own RX queue even though it's not
a regular traffic channel.

Original work by Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: NStuart Hodgson <smhodgson@solarflare.com>
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

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>

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>