The "!mlx4_is_slave" is totally confusing.  Fix with
constant MLX4_CMD_NATIVE, which is the intended behavior.
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Reviewed-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The range check was performed after using the port number.

Reverse this to prevent a potential array overflow.
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Reviewed-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

- pass the following parameters:
  - firmware version (added QUERY_FW paravirtualization for that)

  - disable Blueflame on slaves. KVM disables write combining on guests,
    and we get better performance without BF in this case. (This requires
    QUERY_DEV_CAP paravirtualization, also in this commit)

  - max qp rdma as destination

- get rid of a chunk of "if (0)" dead code
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Reviewed-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Port is used as an array index before we know if that is proper.

For example, in the catas event case, port is zero; however,
the port index should lie in the range (1..2).

Fix this by using 'port' only in the events where it is of interest.

Test for port out of range in the default (unhandled event) case,
and do not output a message if it is not an ethernet port.
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Reviewed-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In SRIOV mode, the number of EQs used when computing the total ICM size
was incorrect.

To fix this, we do the following:
1. We add a new structure to mlx4_dev, mlx4_phys_caps, to contain physical HCA
   capabilities.  The PPF uses the phys capabilities when it computes things
   like ICM size.

   The dev_caps structure will then contain the paravirtualized values, making
   bookkeeping much easier in SRIOV mode. We add a structure rather than a
   single parameter because there will be other fields in the phys_caps.

   The first field we add to the mlx4_phys_caps structure is num_phys_eqs.

2. In INIT_HCA, when running in SRIOV mode, the "log_num_eqs" parameter
   passed to the FW is the number of EQs per VF/PF; each function (PF or VF)
   has this number of EQs available.

   However, the total number of EQs which must be allowed for in the ICM is
   (1 << log_num_eqs) * (#VFs + #PFs).  Rather than compute this quantity,
   we allocate ICM space for 1024 EQs (which is the device maximum
   number of EQs, and which is the value we place in the mlx4_phys_caps structure).

   For INIT_HCA, however, we use the per-function number of EQs as described
   above.
Signed-off-by: NMarcel Apfelbaum <marcela@dev.mellanox.co.il>
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Reviewed-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Ths fixes the comparison in the FLR (Function Level Reset) event case.
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Reviewed-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Current failure paths attempt to free resources which we failed to request
and disable resources which we failed to enable ones. This leads to kernel
oops/panic. This patch does some simple re-ordering to prevent this from
happening.

Cc: netdev@vger.kernel.org
Signed-off-by: NLee Jones <lee.jones@linaro.org>
Acked-by: NLinus Walleij <linus.walleij@linaro.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

so if mdiobus_alloc fails, the errorpath doesnt do a netif_napi_del and also
doesn't set the priv data of the driver to NULL.

at the driver unload stage the driver doesn't remove the NAPI context, and
doesnt' set the priv data to NULL, and also doesn't call the pci_iounmap.
Signed-off-by: NDevendra Naga <devendra.aaru@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

the calls after the pci_enable_device may fail, and will error out with out
disabling it. disable the device at error paths.
Signed-off-by: NDevendra Naga <devendra.aaru@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When Receive Descriptor Empty happens, rxdesc pointer of the driver
and actual next descriptor of the controller may be mismatch.
This patch fixes it.
Signed-off-by: NYoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

FCB(Frame Control Block) isn't the part of netdev hard header.
Add FCB to hard_header_len will make GRO fail at MAC comparision stage.
Signed-off-by: NJiajun Wu <b06378@freescale.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use single_release() instead of seq_release() to free memory allocated
by single_open().
Signed-off-by: NDjalal Harouni <tixxdz@opendz.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Update our reference driver to use netdev_alloc_frag() API instead of
the temporary custom allocator I introduced in commit 8d4057a9
(tg3: provide frags as skb head)

This removes the memory leak we had, since we could leak one page at
device dismantle.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Matt Carlson <mcarlson@broadcom.com>
Cc: Michael Chan <mchan@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Move blocks of code around to avoid function prototypes.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Introduce and use a debug macro to test and print.
Convert printks to pr_<level>.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Just some stylings.

Use #include <linux... not #include <asm...
Convert a test and print to a printk_once.
Combine an "if (foo) { if (bar) {" to single "if (foo && bar) {"
to save an indent level.
Convert single line "if (foo) bar;" to multiple lines.
Move some braces.
Align some long lines a bit better.

Long lines and printks with KERN_ checkpatch complaints
still exist.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use more current logging styles.

Add pr_fmt.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Neaten the comments and reflow the code without
changing anything other than whitespace.

git diff -w shows just comment neatening and a few
line removals.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

recover LLD EQs for DB drop interrupts.  This includes adding a new
db_lock, a spin lock disabling BH too, used by the recovery thread and
the ring_tx_db() paths to allow db drop recovery.

Clean up initial DB avoidance code.

Add read_eq_indices() - this allows the LLD to use the PCIe mw to
efficiently read hw eq contexts.

Add cxgb4_sync_txq_pidx() - called by iw_cxgb4 to sync up the sw/hw
pidx value.

Add flush_eq_cache() and cxgb4_flush_eq_cache().  This allows iw_cxgb4
to flush the sge eq context cache before beginning db drop recovery.

Add module parameter, dbfoifo_int_thresh, to allow tuning the db
interrupt threshold value.

Add dbfifo_int_thresh to cxgb4_lld_info so iw_cxgb4 knows the threshold.

Add module parameter, dbfoifo_drain_delay, to allow tuning the amount
of time delay between DB FULL and EMPTY upcalls to iw_cxgb4.
Signed-off-by: NVipul Pandya <vipul@chelsio.com>
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Add platform-specific callback functions for interrupts.  This is
needed to do a single read-clear of the CAUSE register and then call
out to platform specific functions for DB threshold interrupts and DB
drop interrupts.

Add t4_mem_win_read_len() - mem-window reads for arbitrary lengths.
This is used to read the CIDX/PIDX values from EC contexts during DB
drop recovery.

Add t4_fwaddrspace_write() - sends addrspace write cmds to the fw.
Needed to flush the sge eq context cache.
Signed-off-by: NVipul Pandya <vipul@chelsio.com>
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Signed-off-by: NVipul Pandya <vipul@chelsio.com>
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Patch re-spin.
Incorporated review comments by Ben Hutchings.
Signed-off-by: NSuresh Reddy <suresh.reddy@emulex.com>
Signed-off-by: NSomnath Kotur <somnath.kotur@emulex.com>
Acked-by: NBen Hutchings <bhutchings@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The use of the inw/outw functions by the cs89x0 platform driver
results in NULL pointer references on ARM platforms and
platforms that do not provide ISA-style programmed I/O accessors.

Using inw/outw also accesses the wrong address space on platforms
that have a PCI I/O space that is not identity-mapped into the
physical address space.
Signed-off-by: NJaccon Bastiaansen <jaccon.bastiaansen@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Killing reset task while adapter is resetting causes deadlock.
Only kill reset task if adapter is not resetting.
Ref bug #43132 on bugzilla.kernel.org

CC: stable@vger.kernel.org
Signed-off-by: NTushar Dave <tushar.n.dave@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The support for CONFIG_MCA is being removed, since the 20
year old hardware simply isn't capable of meeting today's
software demands on CPU and memory resources.

This commit removes any MCA specific net drivers, and removes
any MCA specific probe/support code from drivers that were
doing a dual ISA/MCA role.

Cc: "David S. Miller" <davem@davemloft.net>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: netdev@vger.kernel.org
Signed-off-by: NPaul Gortmaker <paul.gortmaker@windriver.com>

Change the TX ring scheme such that the number of rings for untagged packets
and for tagged packets (per each of the vlan priorities) is the same, unlike
the current situation where for tagged traffic there's one ring per priority
and for untagged rings as the number of core.

Queue selection is done as follows:

If the mqprio qdisc is operates on the interface, such that the core networking
code invoked the device setup_tc ndo callback, a mapping of skb->priority =>
queue set is forced - for both, tagged and untagged traffic.

Else, the egress map skb->priority =>  User priority is used for tagged traffic, and
all untagged traffic is sent through tx rings of UP 0.

The patch follows the convergence of discussing that issue with John Fastabend
over this thread http://comments.gmane.org/gmane.linux.network/229877

Cc: John Fastabend <john.r.fastabend@intel.com>
Cc: Liran Liss <liranl@mellanox.com>
Signed-off-by: NAmir Vadai <amirv@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

That old mail address doesnt exist any more.
This changes all occurences to my new address.
Signed-off-by: NOskar Schirmer <oskar@scara.com>
Cc: netdev@vger.kernel.org
Signed-off-by: NJiri Kosina <jkosina@suse.cz>

Under certain scenarios, it's possible that bursty manageability traffic
over the BMC-to-OS path may overrun the internal manageability receive
buffer causing dropped manageability packets. Clearing this bit prevents
this situation by interrupting coalescing to allow manageability traffic
through.
Signed-off-by: NMatthew Vick <matthew.vick@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The code seems to want to look at the last byte where the HW puts some
information. Since the skb->data area is never seen by the HW I guess it
does not work as expected. We pass the page address to the HW so I
*think* in order to get to the last byte where the information might be
one should use the page buffer and take a look.
This is of course not more than just compile tested.
Signed-off-by: NSebastian Andrzej Siewior <bigeasy@linutronix.de>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

According to the comment, errata 23 says that the memory we allocate
can't cross a 64KiB boundary. In case of jumbo frames we allocate
complete pages which can never cross the 64KiB boundary because
PAGE_SIZE should be a multiple of 64KiB so we stop either before the
boundary or start after it but never cross it. Furthermore the check
seems bogus because it looks at skb->data which is not seen by the HW
at all because we only pass the DMA address of the page we allocated. So
I *think* the workaround is not required here.
Signed-off-by: NSebastian Andrzej Siewior <bigeasy@linutronix.de>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This define is needed by i217.
Reported-by: NBjorn Mork <bjorn@mork.no>
Signed-off-by: NBruce Allan <bruce.w.allan@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add missing resource tracking for XRC domains and complete the tracking for HCA
network flow counters.
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently the slave and master resources are deleted after master freed
all bitmaps. If any resources were not properly cleaned up during the
shutdown process, an Oops would result.

Fix so that delete slave (only) resources during cleanup. Master resources
are cleaned up during unload process, and need not separately be cleaned.

Note that during cleanup, we need to split the resource-tracker freeing
functionality.

Before removing all the bitmaps, we free any leftover slave resources.
However, we can only remove the resource tracker linked list after
all bitmap frees, since some of the freeing functions (e.g.,
mlx4_cleanup_eq_table) use paravirtualized FW commands which expect
the resource tracker linked list to be present.
Found-by: NAviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Consider the following scenario: 2 HCAs, where only one of which can run SRIOV.

If we reset the module parameter, all the VFs of the SRIOV HCA will be
claimed by the PPF host (-- the code relies on num_vfs being non-zero
to avoid this claiming, and num_vfs was reset when pci_enable_sriov failed
for the non-SRIOV HCA).

The solution is not to touch the num_vfs parameter.

Also, eliminate the unneeded check of num_vfs when disabling sriov
(the dev flag bit is sufficient).
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Removed unsued *_str helper functions from resource_tracker.c
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The "wrapped" was incorrect, since no wrapper function was defined.
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In function mlx4_INIT_PORT_wrapper, the port state mask for the
slave is only set if we are invoking the INIT_PORT fw command.

However, the reference count for the (initialized) port is
incremented anyway.

This creates a problem in that when we have multiple slaves,
then the CLOSE_PORT command will never be invoked. The
reason is that in the CLOSE_PORT wrapper, if the port-state
mask is zero for the slave (which it is), the wrapper returns
without doing anything. The only slave which will not return
immediately in the CLOSE_PORT wrapper is that slave for which
INIT_PORT was invoked.

The fix is to not have the port-state mask setting depend
on the logic for calling the INIT_PORT fw command.
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Handle the compiler warnings on variables which are set but not used
by removing the relevant variable or casting a return value which is
ignored on purpose to void.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Andy reported pch_gbe triggered "NETDEV WATCHDOG" errors.

May 11 11:06:09 kontron kernel: WARNING: at net/sched/sch_generic.c:261
dev_watchdog+0x1ec/0x200() (Not tainted)
May 11 11:06:09 kontron kernel: Hardware name: N/A
May 11 11:06:09 kontron kernel: NETDEV WATCHDOG: eth0 (pch_gbe):
transmit queue 0 timed out

It seems pch_gbe has a racy tx path (races with TX completion path)

Remove tx_queue_lock lock since it has no purpose, we must use tx_lock
instead.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Reported-by: NAndy Cress <andy.cress@us.kontron.com>
Tested-by: NAndy Cress <andy.cress@us.kontron.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>