This patch adds a 64-bit flags2 features member to struct mlx4_dev to
export further features of the hardware.  The original flags field
tracks features whose support bits are advertised by the firmware in
offsets 0x40 and 0x44 of the query device capabilities command.
flags2 will track features whose support bits are scattered at various
offsets.

RSS support is the first feature to be exported through flags2.  RSS
capabilities are located at offset 0x2e.  The size of the RSS
indirection table is also given in this offset.
Signed-off-by: NShlomo Pongratz <shlomop@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

The driver uses a 2-order allocation, which is too much on architectures
like ppc64, which has a 64KiB page. This particular allocation is used
for large packet fragments that may have a size of 512, 1024, 4096 or
fill the whole allocation. So, a minimum size of 16384 is good enough
and will be the same size that is used in architectures of 4KiB sized
pages.

This will avoid allocation failures that we see when the system is under
stress, but still has plenty of memory, like the one below.

This will also allow us to set the interface MTU to higher values like
9000, which was not possible on ppc64 without this patch.

Node 1 DMA: 737*64kB 37*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB 0*8192kB 0*16384kB = 51904kB
83137 total pagecache pages
0 pages in swap cache
Swap cache stats: add 0, delete 0, find 0/0
Free swap  = 10420096kB
Total swap = 10420096kB
107776 pages RAM
1184 pages reserved
147343 pages shared
28152 pages non-shared
netstat: page allocation failure. order:2, mode:0x4020
Call Trace:
[c0000001a4fa3770] [c000000000012f04] .show_stack+0x74/0x1c0 (unreliable)
[c0000001a4fa3820] [c00000000016af38] .__alloc_pages_nodemask+0x618/0x930
[c0000001a4fa39a0] [c0000000001a71a0] .alloc_pages_current+0xb0/0x170
[c0000001a4fa3a40] [d00000000dcc3e00] .mlx4_en_alloc_frag+0x200/0x240 [mlx4_en]
[c0000001a4fa3b10] [d00000000dcc3f8c] .mlx4_en_complete_rx_desc+0x14c/0x250 [mlx4_en]
[c0000001a4fa3be0] [d00000000dcc4eec] .mlx4_en_process_rx_cq+0x62c/0x850 [mlx4_en]
[c0000001a4fa3d20] [d00000000dcc5150] .mlx4_en_poll_rx_cq+0x40/0x90 [mlx4_en]
[c0000001a4fa3dc0] [c0000000004e2bb8] .net_rx_action+0x178/0x450
[c0000001a4fa3eb0] [c00000000009c9b8] .__do_softirq+0x118/0x290
[c0000001a4fa3f90] [c000000000031df8] .call_do_softirq+0x14/0x24
[c000000184c3b520] [c00000000000e700] .do_softirq+0xf0/0x110
[c000000184c3b5c0] [c00000000009c6d4] .irq_exit+0xb4/0xc0
[c000000184c3b640] [c00000000000e964] .do_IRQ+0x144/0x230
Signed-off-by: NThadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Signed-off-by: NKleber Sacilotto de Souza <klebers@linux.vnet.ibm.com>
Tested-by: NKleber Sacilotto de Souza <klebers@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Prevent race condition between commands on comm channel.
Happened while unloading the driver when switching from
event to polling mode. VF got completion on the last command
before switching to polling mode, but toggle was not changed.
After the fix - VF will not write the next command before
toggle is updated.
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The current driver defaults to 1M MTT segments, where each segment holds
8 MTT entries.  This limits the total memory registered to 8M * PAGE_SIZE
which is 32GB with 4K pages.  Since systems that have much more memory
are pretty common now (at least among systems with InfiniBand hardware),
this limit ends up getting hit in practice quite a bit.

Handle this by having the driver allocate at least enough MTT entries to
cover 2 * totalram pages.
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Set the MTU for IB ports in the driver instead of using the firmware
default of 2KB (the driver defaults to 4KB).  Allow for dynamic mtu
configuration through a new, per-port sysfs entry.

Since there's a dependency between the port MTU and the max number of
HW VLs the port can support, apply a mim/max approach, using a loop
that goes down from the highest possible number of VLs to the lowest,
using the firmware return status to know whether the requested number
of VLs is possible with a given MTU.

For now, as with the dynamic link type change / VPI support, the sysfs
entry to change the mtu is exposed only when NOT running in SR-IOV
mode.  To allow changing the MTU for the master in SR-IOV mode,
primary-function-initiated FLR (Function Level Reset) needs to be
implemented.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Print an error message when a thermal error async event is reported by the HW.
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NDotan Barak <dotanb@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Commit 22c8bff6 ("mlx4_core: Exported functions can't be static")
fixed most of this up, but forgot about mlx4_is_slave_active().  Fix
this one too.

Cc: <stable@vger.kernel.org>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

The actual FW command is called in procedure "handle_resize".
Code incorrectly invoked the FW command again (in good flow), in
the modify_cq wrapper function.

Fix by skipping second FW invocation unconditionally for resize.
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

While doing the work for commit a6f7feae ("IB/mlx4: pass SMP
vendor-specific attribute MADs to firmware") we realized that the
firmware would respond on all sorts of vendor-specific MADs.
Therefore commit 97285b78 ("mlx4_core: Add extended port
capabilities support") adds redundant code into the driver, since
there's no real reaon to maintain the extended capabilities of the
port, as they can be queried on demand (e.g the FDR10 capability).

This patch reverts commit 97285b78 and removes the check for
extended caps from the mlx4_ib driver port query flow.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Fixing sparse warnings, the 2 functions are only used in same
file. Defining them as static and not exporting them.
Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Removing functions that are no longer in use, but still exist
Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The SET_PORT functions are implemented in port.c, which is part
of mlx4_core, these functions are exported. The functions are in use by
the mlx4_en module (were originally part of mlx4_en).
Their declaration remained in mlx4_en module, moving the declaration to the right location.
Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The mac should be written as __be64 the gid. The warning was because
we changed the mac parameter, which is u64, by writing result of cpu_to_be64
into it. Fixing by using new variable of type __be64.
Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The keys used for the hardware RSS topelitz hash are of type __be32
where the values provided by the driver are from array of u32,
this triggered sparse warning on incorrect type in assignment as of different base types.
Since these values are picked randomly,
the fix is to transform the key to __be32 by executing cpu_to_be_32()
Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The blue flame buffer is defined to be of type void __iomem *
but was passed to mlx4_bf_copy which gets unsigned long * .
This triggered sparse warning on different address spaces,
fix that by changing mlx4_bf_copy first param to be of type void __iomem * .
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix sparse warnings on incompatibility between the endianess of the ctrl_flags
field of struct mlx4_en_priv to the srcrb_flags field of struct
mlx4_wqe_ctrl_seg by changing the former to be __be32 instead of u32.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Localized the pdev->dev, and using dma_map instead of pci_map
There are multiple map/unmap operations on data path,
optimizing those by saving redundant pointer access.
Those places were identified as hot-spots when running kernel profiling
during some benchmarks.
The fixes had most impact when testing packet rate with small packets,
reducing several % from CPU load, and in some case being the difference
between reaching wire speed or being CPU bound.
Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fixes a bug introduced by commit fe9a2603, where the priority bits
in the schedule queue field were masked out.
Signed-off-by: NAmir Vadai <amirv@mellanox.co.il>
Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix new sparse errors introduced in commit 62212171 (mlx4_en: dont
change mac_header on xmit)
Reported-by: NOr Gerlitz <or.gerlitz@gmail.com>
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Cc: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A driver xmit function is not allowed to change skb without special
care.

mlx4_en_xmit() should not call skb_reset_mac_header() and instead should
use skb->data to access ethernet header.

This removes a dumb test : if (ethh && ethh->h_dest)

Also remove this slow mlx4_en_mac_to_u64() call, we can use
get_unaligned() to get faster code.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Cc: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ConnectX devices have a limit on the number of mappings that can be
done on an FMR before having to call sync_tpt.  The current
mlx4_ib driver reports the limit correctly in max_map_per_fmr in
.query_device(), but mlx4_core doesn't check it when actually
allocating FMRs.

Add a max_fmr_maps field to struct mlx4_caps and enforce this maximum
value on FMR allocations.
Signed-off-by: NEli Cohen <eli@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

At least on powerpc, it breaks the build if exported functions are
static.  Fix some static exported functions introduced with the mlx4
SR-IOV support added in 3.3-rc1.
Signed-off-by: NDoug Ledford <dledford@redhat.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

In port type change flow, need to set the new port types only after
all interfaces have finished the unregister process.
Otherwise, during unregister, one of the interfaces might issue a SET_PORT
command with wrong port types, it can cause bad FW behavior.
Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Under the spinlock we call request_irq(), which allocates memory with GFP_KERNEL,
This causes the following trace when DEBUG_SPINLOCK is enabled, it can cause
the following trace:

 BUG: spinlock wrong CPU on CPU#2, ethtool/2595
 lock: ffff8801f9cbc2b0, .magic: dead4ead, .owner: ethtool/2595, .owner_cpu: 0
 Pid: 2595, comm: ethtool Not tainted 3.0.18 #2
 Call Trace:
 spin_bug+0xa2/0xf0
 do_raw_spin_unlock+0x71/0xa0
 _raw_spin_unlock+0xe/0x10
 mlx4_assign_eq+0x12b/0x190 [mlx4_core]
 mlx4_en_activate_cq+0x252/0x2d0 [mlx4_en]
 ? mlx4_en_activate_rx_rings+0x227/0x370 [mlx4_en]
 mlx4_en_start_port+0x189/0xb90 [mlx4_en]
 mlx4_en_set_ringparam+0x29a/0x340 [mlx4_en]
 dev_ethtool+0x816/0xb10
 ? dev_get_by_name_rcu+0xa4/0xe0
 dev_ioctl+0x2b5/0x470
 handle_mm_fault+0x1cd/0x2d0
 sock_do_ioctl+0x5d/0x70
 sock_ioctl+0x79/0x2f0
 do_vfs_ioctl+0x8c/0x340
 sys_ioctl+0xa1/0xb0
 system_call_fastpath+0x16/0x1b

Replacing with mutex, which is enough in this case.
Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

BF can be disabled in some cases, the capability field, bf_reg_size is set
to zero in this case. Don't map the BF area in this case, it would cause
failures.  In addition, leaving the BF area unmapped
also alerts the ETH driver to not use BF.
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add unicast steering entries to resource tracker.
Do qp_detach also for these entries when VF doesn't shut down gracefully.
Otherwise there is leakage of these resources, since they are not tracked.
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.co.il>
Reviewed-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When adding new unicast steer entry, before moving qp to state ready,
actually before calling mlx4_RST2INIT_QP_wrapper(), there were added
a lot of entries with local_qpn=0 into radix tree.
This fact impacted the get_res() function and proper functioning
of resource tracker in addition to adding trash entries into radix tree.
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.co.il>
Reviewed-by: NYevgeny Petrilin <yevgenyp@melllanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When passing MLX4_UC_STEER=1 it was translated to value 2
after mlx4_QP_ATTACH_wrapper. Therefore in new_steering_entry()
unicast steer entries were added to index 2 of array of size 2.
Fixing this bug by shift right to one position.
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.co.il>
Reviewed-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add unicast steering entries to resource tracker.
Do qp_detach also for these entries when VF doesn't shut down gracefully.
Otherwise there is leakage of these resources, since they are not tracked.
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.co.il>
Reviewed-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

mlx4_multicast_attach/detach() should use always MLX4_MC_STEER flag
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.co.il>
Reviewed-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

mlx4_uc_steer_add/release() should not add MLX4_UC_STEER flag to gid.
It is added in mlx4_unicast_attach/detach().
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.co.il>
Reviewed-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

mlx4_qp_attach/detach_common() don't use hash variable, move it to find_entry()
static find_entry() in mcg.c doesn't use steer argument
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.co.il>
Reviewed-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Remove unnecessary field high_prios from mlx4_steer struct and initialization
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.co.il>
Reviewed-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When adding new unicast steer entry, before moving qp to state ready,
actually before calling mlx4_RST2INIT_QP_wrapper(), there were added
a lot of entries with local_qpn=0 into radix tree.
This fact impacted the get_res() function and proper functioning
of resource tracker in addition to adding trash entries into radix tree.
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.co.il>
Reviewed-by: NYevgeny Petrilin <yevgenyp@melllanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When passing MLX4_UC_STEER=1 it was translated to value 2
after mlx4_QP_ATTACH_wrapper. Therefore in new_steering_entry()
unicast steer entries were added to index 2 of array of size 2.
Fixing this bug by shift right to one position.
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.co.il>
Reviewed-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The first parameter should be "number of elements" and the second parameter
should be "element size".
Signed-off-by: NAxel Lin <axel.lin@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

mlx4_en_prepare_rx_desc does not correctly clean up after it finds an
allocation failure. It should unmap a page before calling put_page, but
it only calls the later.

This bug would prevent a device removal using hotplug after setting the
device MTU to 9000 and opening the network interface. After the fix, we
still see the allocation failure with MTU 9000, but we are able to
remove the device.
Signed-off-by: NThadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After opening the network interface, Mellanox ConnectX device cannot be
removed by hotplug because it has not properly unmapped all DMA memory.

It happens that mlx4_en_activate_rx_rings overrides the variable that
keeps the size of the memory mapped.

This is fixed by passing to mlx4_en_destroy_rx_ring the same size that is
given to mlx4_en_create_rx_ring.

After applying this patch, hot unplugging the device works after opening
the interface.
Signed-off-by: NThadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use port number for correct steering (list per port).
Before the fix all steering entries (for both physical ports)
were managed in first port structures, so we had leakage of resources
for port 2.
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>