Commit Graph

76 Commits

Author SHA1 Message Date
Hans Petter Selasky
8508e4d730 Make sure the received IP header gets 32-bit aligned for short packets
in the mlx5en(4) driver.

MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-08-08 11:49:36 +00:00
Hans Petter Selasky
869dd4b498 Count drop events due to lack of PCI bandwidth as queue drops and not as
input errors in the mlx5en(4) driver. This improves the sysadmin view of
physical port errors.

Submitted by:		gallatin@
MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-08-08 11:36:57 +00:00
Hans Petter Selasky
713dd5cb9e Resolve locking issue for non-sleepable context in the mlx5core.
Code inspection reveals the busdma unload and free functions
do not write to the belonging dma tag and does not need to be
serialized. This allows mlx5_fwp_free() to be called from
software interrupt context.

MFC after:	3 days
Sponsored by:	Mellanox Technologies
2017-08-03 09:14:43 +00:00
Hans Petter Selasky
1d4905b5b0 Using GFP_ATOMIC with firmware commands is not supported after busdma was
introduced in the mlx5core, because busdma might sleep when loading memory
into DMA.

MFC after:	3 days
Sponsored by:	Mellanox Technologies
2017-08-03 09:11:51 +00:00
Mark Johnston
c73cdca2c4 Update io-mapping.h in the LinuxKPI.
Add io_mapping_init_wc() and add a third (unused) parameter to
io_mapping_map_wc().

Reviewed by:	hselasky
MFC after:	1 week
Differential Revision:	https://reviews.freebsd.org/D11286
2017-06-21 18:20:17 +00:00
Hans Petter Selasky
8b48354659 Improve sysadmin visibility of physical port error counters in the
mlx5en driver.

MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-04-28 19:38:57 +00:00
Hans Petter Selasky
eac79e7755 Make "desc" pointer non-constant inside the mlx5_core_diagnostics_entry
structure. This fixes compilation with amd64-xtoolchain-gcc.

PR:			216588
MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-01-30 08:35:15 +00:00
Hans Petter Selasky
1c807f6795 Use the busdma API to allocate all DMA-able memory.
The MLX5 driver has four different types of DMA allocations which are
now allocated using busdma:

1) The 4K firmware DMA-able blocks. One busdma object per 4K allocation.
2) Data for firmware commands use the 4K firmware blocks split into four 1K blocks.
3) The 4K firmware blocks are also used for doorbell pages.
4) The RQ-, SQ- and CQ- DMA rings. One busdma object per allocation.

After this patch the mlx5en driver can be used with DMAR enabled in
the FreeBSD kernel.

MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-01-27 11:46:55 +00:00
Hans Petter Selasky
30dfc0518a Add support for device surprise removal and other PCI errors.
- When device disappears from PCI indicate error device state and:
  1) Trigger command completion for all pending commands
  2) Prevent new commands from executing and return:
     - success for modify and remove/cleanup commands
     - failure for create/query commands
  3) When reclaiming pages for a device in error state don't ask FW to
     return all given pages, just release the allocated memory

MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-01-27 11:29:33 +00:00
Hans Petter Selasky
44a03e91f3 Wait for all VFs pages to be reclaimed before closing EQ pages.
MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-01-27 11:19:06 +00:00
Hans Petter Selasky
310804912a Rename struct fw_page into struct mlx5_fw_page as a preparation step
for adding busdma support.

MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-01-27 11:03:58 +00:00
Hans Petter Selasky
f361e561a5 Fix command completion with callback scenario.
MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-01-27 10:56:03 +00:00
Hans Petter Selasky
8e7e0ce110 Minor code refactor as a preparation step for suprise removal of CX-4
PCI device(s), changes:
- alloc_entry() now clears bit for page slot entry aswell
- update of cmd->ent_arr[] is now under cmd->alloc_lock
- complete command if alloc_entry() fails

MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-01-27 10:47:53 +00:00
Hans Petter Selasky
d0ce5a0da7 Use ffs() to scan for first bit instead of using a for() loop.
Minor code refactor while at it.

MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-01-27 10:36:49 +00:00
Hans Petter Selasky
115bc9b1d3 Make fw_pages statistics counter 64-bit to avoid overflow.
MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-01-27 10:20:38 +00:00
Hans Petter Selasky
66d53750b9 Add support for reading advanced diagnostic counters.
By default reading the diagnostic counters is disabled. The firmware
decides which counters are supported and only those supported show up
in the dev.mce.X.diagnostics sysctl tree.

To enable reading of diagnostic counters set one or more of the
following sysctls to one:

dev.mce.X.conf.diag_general_enable=1
dev.mce.X.conf.diag_pci_enable=1

MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-01-27 10:03:50 +00:00
Hans Petter Selasky
5e6a76be8a Enforce reading the consumer and producer counters once to ensure
consistent return values from the mlx5e_sq_has_room_for()
function. The two counters are incremented by different threads under
different locks.

MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-01-27 08:32:50 +00:00
Hans Petter Selasky
e16c241deb Remove superfluous return statement.
MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-01-20 15:47:29 +00:00
Hans Petter Selasky
b98ba64027 Allow transmit packet bufring in software to be disabled.
- Add new sysctl node to control the transmit packet bufring.

- Add optimised version of the transmit routine which output packets
directly to the DMA ring instead of using bufring in case the transmit
lock is congested. This can reduce the number of taskswitches which in
turn influence the overall system CPU usage, depending on the
workload.

- Add " TX" suffix to debug name for transmit mutexes to silence some
witness warnings about aquiring duplicate locks having same name.

MFC after:		1 week
Sponsored by:		Mellanox Technologies
Suggested by:		gallatin @
2017-01-20 15:45:21 +00:00
Hans Petter Selasky
3dfa7645c5 Make draining a sendqueue more robust.
Add own state variable to track if a sendqueue is stopped or not.
This will prevent traffic from entering the sendqueue while it is
being destroyed.

Update drain function to wait for traffic to be transmitted before
returning when the link state is active.

Add extra checks in transmit path for stopped SQ's.

While at it:
- Use likely() for a mbuf pointer check.
- Remove redundant IFF_DRV_RUNNING check.

MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-01-20 12:02:40 +00:00
Hans Petter Selasky
d2bf00a918 Add runtime support for modifying the SQ and RQ completion event
moderation mode. The presence of this feature is indicated through the
firmware capabilities.

MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-01-20 11:11:49 +00:00
Hans Petter Selasky
0402eb6bcc Update firmware interface structures and definitions adding support
for new features and commands.

MFC after:		1 week
Sponsored by:		Mellanox Technologies
2017-01-20 10:47:32 +00:00
Hans Petter Selasky
41aa095b2f Make a read only pointer constant.
Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-12-22 10:12:19 +00:00
Hans Petter Selasky
436659135a Add more comments regarding collection of statistics counters.
Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-12-22 10:11:03 +00:00
Hans Petter Selasky
de83258d59 Remove useless NULL checks.
NULL is not returned when allocating memory passing the M_WAITOK flag.

Submitted by:		trasz @
Differential Revision:  https://reviews.freebsd.org/D5772
Sponsored by:           Mellanox Technologies
MFC after:		1 week
2016-12-02 09:41:54 +00:00
Hans Petter Selasky
6f4cab6cc3 Add timer to watch the RQ when we are out of mbufs.
The firmware/hardware does not generate additional completion
events unless we post new buffers. Use a timer to try to post
more buffers in case we are temporarily out of mbufs. Else
the receive schedule completely stops.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-11-07 11:39:45 +00:00
Hans Petter Selasky
cb02244355 Add more firmware related structures and update existing ones in the
MLX5 core module. Update the set and query diagnostics counter API.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-11-07 11:28:50 +00:00
Hans Petter Selasky
627ef61aab Query flow table capabilities according to the correct capability bit
for infiniband.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-11-07 11:26:25 +00:00
Hans Petter Selasky
adea303c2a Correct checksum fields in the "mlx5_mini_cqe8" structure. The fields
in question are currently not used.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-11-07 11:22:50 +00:00
Hans Petter Selasky
91951e3978 Ensure the firmware is notified of any host memory allocation
failures. Else firmware commands may time out waiting for host
memory.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-11-07 11:20:13 +00:00
Hans Petter Selasky
97ac390861 When a firmware command times out do not free the command structure to
avoid use after free.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-11-07 11:15:40 +00:00
Hans Petter Selasky
478c1a9932 Set hardware stats flag to avoid double counting the number of incoming bytes.
Found by:	Ben RUBSON <ben.rubson@gmail.com>
Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-09-29 16:35:52 +00:00
Hans Petter Selasky
a2c320d7c7 mlx5en: Fix duplicate mbuf free-by-code.
When mlx5e_sq_xmit() returns an error code and the mbuf pointer is set,
we should not free the mbuf, because the caller will keep the mbuf in
the drbr. Make sure the mbuf pointer is correctly set upon function
exit.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-09-16 11:57:48 +00:00
Hans Petter Selasky
14997cc16a mlx5en: Remove unused pdev pointer.
Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-09-16 11:55:38 +00:00
Hans Petter Selasky
f5344e8333 mlx5en: Verify port type is ethernet before creating network device
Else the mlx5en driver might attach to infiniband ports.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-09-16 11:53:53 +00:00
Hans Petter Selasky
431fe47416 mlx5en: Allow setting the software MTU size below 1500 bytes
The hardware MTU size can't be set to a value less than 1500 bytes due
to side-band management support. Allow setting the software MTU size
below 1500 bytes, thus creating a mismatch between hardware and
software MTU sizes.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-09-16 11:51:31 +00:00
Hans Petter Selasky
7b4e6e4ac9 mlx5en: Factor out common sendqueue code for use with rate limiting SQs.
Try to reuse code to setup sendqueues when possible by making some static
functions global. Further split the mlx5e_close_sq_wait() function to
separate out reusable parts.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-09-16 11:47:16 +00:00
Hans Petter Selasky
81b3cdc1bb mlx5en: Properly declare doorbell lock for 32-bit CPUs.
Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-09-16 11:45:35 +00:00
Hans Petter Selasky
5eadc44ceb mlx5en: Optimise away duplicate UAR pointers.
This change also reduces the size of the mlx5e_sq structure so that the last
queue_state element will fit into the previous cacheline and then the mlx5e_sq
structure becomes one cacheline less for amd64.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-09-16 11:40:45 +00:00
Hans Petter Selasky
28f22ccea3 mlx5en: Make the mlx5e_open_cq() and mlx5e_close_cq() functions global.
Make some functions and structures global to allow for code reuse
when creating rate limiting sendqueues.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-09-16 11:39:15 +00:00
Hans Petter Selasky
941cd5d1a4 mlx5en: Minor completion queue control path code refactor.
Move setting of CQ moderation mode together with the other
CQ moderation parameters. Pass completion event vector as
a separate argument to mlx5e_open_cq(), because its value is
different for each call. Pass mlx5e_priv pointer instead of
mlx5e_channel pointer so that code can be used by rate
limiting sendqueues.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-09-16 11:37:35 +00:00
Hans Petter Selasky
98626886ee mlx5en: Separate the sendqueue from using the mlx5e_channel structure.
This change allows for reusing the transmit path for so called
rate limited senqueues. While at it optimise some pointer lookups
in the fast path.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-09-16 11:35:45 +00:00
Hans Petter Selasky
cb4e4a6ed6 Update the MLX5 core module:
- Add new firmware commands and update existing ones.
- Add more firmware related structures and update existing ones.
- Some minor fixes, like adding missing \n to some prints.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-09-16 11:28:16 +00:00
Hans Petter Selasky
351a9c7c0b Increase the maximum RX/TX queue size. This allows for a RX/TX queue
size of 16384 mbufs. Previously the limit was 8192.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-08-22 13:43:25 +00:00
Hans Petter Selasky
5f9e5b5e62 Fix for use after free.
Clear the device description to avoid use after free because the
bsddev is not destroyed when the mlx5en module is unloaded. Only when
the parent mlx5 module is unloaded the bsddev is destroyed. This fixes
a panic on listing sysctls which refer strings in the bsddev after the
mlx5en module has been unloaded.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-08-09 07:43:15 +00:00
Hans Petter Selasky
57d5dd7907 Switch to the new block based LRO input function for the mlx5en
driver. This change significantly increases the overall RX aggregation
ratio for heavily loaded networks handling 10-80 thousand simultaneous
connections.

Remove the turbo LRO code and all references to it which has now been
superceeded by the tcp_lro_queue_mbuf() function.

Tested by:	Netflix
Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-08-08 16:22:16 +00:00
Hans Petter Selasky
5b0c29decf Use correct Q-counter output array.
Sponsored by:	Mellanox Technologies
Approved by:	re (kib)
MFC after:	3 days
2016-06-23 09:23:37 +00:00
Hans Petter Selasky
76a5241f2c Add SR-IOV guest support to the mlx5en driver.
This patch adds the missing pieces needed for device setup using the
mlx5en driver inside a virtual machine which is providing hardware
access through SR-IOV.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-06-07 13:58:52 +00:00
Sepherosa Ziehau
36ad8372d4 net: Use M_HASHTYPE_OPAQUE_HASH if the mbuf flowid has hash properties
Reviewed by:	hps, erj, tuexen
Sponsored by:	Microsoft OSTC
Differential Revision:	https://reviews.freebsd.org/D6688
2016-06-07 04:51:50 +00:00
Hans Petter Selasky
fa201e28fc Prepare for activation of LinuxKPI module parameters as read-only
tunable SYSCTL's. Linux module parameters are associated with the
module they belong to. FreeBSD does not share this concept of a parent
module. Instead add macros which define the prefix to use for the
module parameters in the LinuxKPI consumers.

While at it convert all "bool" LinuxKPI module parameters to "byte"
type, because we don't have a "bool" type of SYSCTL in FreeBSD.

Sponsored by:	Mellanox Technologies
MFC after:	1 week
2016-05-25 12:03:21 +00:00