From Krzysztof:
The driver built as KLD cannot be unloaded, if this flag is not set.
Submitted by: Krzysztof Galazka <krzysztof.galazka@intel.com>
Reviewed by: shurd@, erj@
MFC after: 1 week
Sponsored by: Intel Corporation
Differential Revision: https://reviews.freebsd.org/D19402
From Jake:
iflib_fl_setup calculates a suitable buffer size for the Rx mbufs based
on the isc_max_frame_size value that drivers setup. This calculation is
repeated by drivers when programming their hardware with the size of
each Rx buffer.
This can lead to a mismatch where the iflib mbuf size is different from
the expected size of the buffer as programmed by the hardware. This can
lead to unexpected results.
If iflib ever wants to support mbuf sizes larger than one page, every
driver must be updated to account for the new possible buffer sizes.
Fix this by calculating the mbuf size prior to calling IFDI_INIT, and
adding the iflib_get_rx_mbuf_sz function which will expose this value to
drivers, so that they do not repeat the same calculation.
Submitted by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed by: shurd@, erj@
MFC after: 1 week
Sponsored by: Intel Corporation
Differential Revision: https://reviews.freebsd.org/D19489
This patch and commit message are based on r340256 created by Jacob Keller:
The iflib stack does not disable TSO automatically when TXCSUM is
disabled, instead assuming that the driver will correctly handle TSOs
even when CSUM_IP is not set.
This results in iflib calling ixgbe_isc_txd_encap with packets which have
CSUM_IP_TSO, but do not have CSUM_IP or CSUM_IP_TCP set. Because of
this, ixgbe_tx_ctx_setup will not setup the IPv4 checksum offloading.
This results in bad TSO packets being sent if a user disables TXCSUM
without disabling TSO.
Fix this by updating the ixgbe_tx_ctx_setup function to check both
CSUM_IP and CSUM_IP_TSO when deciding whether to enable checksums.
Once this is corrected, another issue for TSO packets is revealed. The
driver sets IFLIB_NEED_ZERO_CSUM in order to enable a work around that
causes the ip->sum field to be zero'd. This is necessary for ix
hardware to correctly perform TSOs.
However, if TXCSUM is disabled, then the work around is not enabled, as
CSUM_IP will not be set when the iflib stack checks to see if it should
clear the sum field.
Fix this by adding IFLIB_TSO_INIT_IP to the iflib flags for the ix and
ixv interface files.
Once both of these changes are made, the ix and ixv drivers should
correctly offload TSO packets when TSO offload is enabled, regardless
of whether TXCSUM is enabled or disabled.
Submitted by: Piotr Pietruszewski <piotr.pietruszewski@intel.com>
Reviewed by: IntelNetworking
Sponsored by: Intel Corporation
Differential Revision: https://reviews.freebsd.org/D18470
iflib is already a module, but it is unconditionally compiled into the
kernel. There are drivers which do not need iflib(4), and there are
situations where somebody might not want iflib in kernel because of
using the corresponding driver as module.
Reviewed by: marius
Discussed with: erj
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Differential revision: https://reviews.freebsd.org/D19041
bus_teardown_intr(9) before pci_release_msi(9).
- Ensure that iflib(4) and associated drivers pass correct RIDs to
bus_release_resource(9) by obtaining the RIDs via rman_get_rid(9)
on the corresponding resources instead of using the RIDs initially
passed to bus_alloc_resource_any(9) as the latter function may
change those RIDs. Solely em(4) for the ioport resource (but not
others) and bnxt(4) were using the correct RIDs by caching the ones
returned by bus_alloc_resource_any(9).
- Change the logic of iflib_msix_init() around to only map the MSI-X
BAR if MSI-X is actually supported, i. e. pci_msix_count(9) returns
> 0. Otherwise the "Unable to map MSIX table " message triggers for
devices that simply don't support MSI-X and the user may think that
something is wrong while in fact everything works as expected.
- Put some (mostly redundant) debug messages emitted by iflib(4)
and em(4) during attachment under bootverbose. The non-verbose
output of em(4) seen during attachment now is close to the one
prior to the conversion to iflib(4).
- Replace various variants of spelling "MSI-X" (several in messages)
with "MSI-X" as used in the PCI specifications.
- Remove some trailing whitespace from messages emitted by iflib(4)
and change them to consistently start with uppercase.
- Remove some obsolete comments about releasing interrupts from
drivers and correct a few others.
Reviewed by: erj, Jacob Keller, shurd
Differential Revision: https://reviews.freebsd.org/D18980
From Jake:
In r341156 ("Fix first-packet completion", 2018-11-28) a hack to work
around a delta calculation determining how many descriptors were used
was added to ixl_isc_tx_credits_update_dwb.
The same fix was also applied to the em and igb drivers in r340310, and
to ix in r341156.
The hack checked the case where prev and cur were equal, and then added
one. This works, because by the time we do the delta check, we already
know there is at least one packet available, so the delta should be at
least one.
However, it's not a complete fix, and as indicated by the comment is
really a hack to work around the real bug.
The real problem is that the first time that we transmit a packet,
tx_cidx_processed will be set to point to the start of the ring.
Ultimately, the credits_update function expects it to point to the
*last* descriptor that was processed. Since we haven't yet processed any
descriptors, pointing it to 0 results in this incorrect calculation.
Fix the initialization code to have it point to the end of the ring
instead. One way to think about this, is that we are setting the value
to be one prior to the first available descriptor.
Doing so, corrects the delta calculation in all cases. The original fix
only works if the first packet has exactly one descriptor. Otherwise, we
will report 1 less than the correct value.
As part of this fix, also update the MPASS assertions to match the real
expectations. First, ensure that prev is not equal to cur, since this
should never happen. Second, remove the assertion about prev==0 || delta
!= 0. It looks like that originated from when the em driver was
converted to iflib. It seems like it was supposed to ensure that delta
was non-zero. However, because we originally returned 0 delta for the
first calculation, the "prev == 0" was tacked on.
Instead, replace this with a check that delta is greater than zero,
after the correction necessary when the ring pointers wrap around.
This new solution should fix the same bug as r341156 did, but in a more
robust way.
Submitted by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed by: shurd@
Sponsored by: Intel Corporation
Differential Revision: https://reviews.freebsd.org/D18545
Remove unused and easy to misuse PNP macro parameter
Inspired by r338025, just remove the element size parameter to the
MODULE_PNP_INFO macro entirely. The 'table' parameter is now required to
have correct pointer (or array) type. Since all invocations of the macro
already had this property and the emitted PNP data continues to include the
element size, there is no functional change.
Mostly done with the coccinelle 'spatch' tool:
$ cat modpnpsize0.cocci
@normaltables@
identifier b,c;
expression a,d,e;
declarer MODULE_PNP_INFO;
@@
MODULE_PNP_INFO(a,b,c,d,
-sizeof(d[0]),
e);
@singletons@
identifier b,c,d;
expression a;
declarer MODULE_PNP_INFO;
@@
MODULE_PNP_INFO(a,b,c,&d,
-sizeof(d),
1);
$ rg -l MODULE_PNP_INFO -- sys | \
xargs spatch --in-place --sp-file modpnpsize0.cocci
(Note that coccinelle invokes diff(1) via a PATH search and expects diff to
tolerate the -B flag, which BSD diff does not. So I had to link gdiff into
PATH as diff to use spatch.)
Tinderbox'd (-DMAKE_JUST_KERNELS).
Approved by: re (glen)
From Piotr:
ix(4), ixv(4): Add VLAN tag strip check when receiving packets
ixv(4): Fix support for VLAN_HWTAGGING and VLAN_HWFILTER flags
This change will prevent driver from passing VLAN tags when
interface configuration is not expecting them. VF driver will
check for VLAN_HWTAGGING and VLAN_HWFILTER flags and act adequately.
This patch resolves problem occuring on EC2 platforms.
Submitted by: Piotr Pietruszewski <piotr.pietruszewski@intel.com>
Reported by: cperciva@
Reviewed by: cperciva@, Intel Networking
Approved by: re
Sponsored by: Intel Corporation
Differential Revision: https://reviews.freebsd.org/D17061
I was not aware Warner was making or planning to make forward progress in
this area and have since been informed of that.
It's easy to apply/reapply when churn dies down.
Inspired by r338025, just remove the element size parameter to the
MODULE_PNP_INFO macro entirely. The 'table' parameter is now required to
have correct pointer (or array) type. Since all invocations of the macro
already had this property and the emitted PNP data continues to include the
element size, there is no functional change.
Mostly done with the coccinelle 'spatch' tool:
$ cat modpnpsize0.cocci
@normaltables@
identifier b,c;
expression a,d,e;
declarer MODULE_PNP_INFO;
@@
MODULE_PNP_INFO(a,b,c,d,
-sizeof(d[0]),
e);
@singletons@
identifier b,c,d;
expression a;
declarer MODULE_PNP_INFO;
@@
MODULE_PNP_INFO(a,b,c,&d,
-sizeof(d),
1);
$ rg -l MODULE_PNP_INFO -- sys | \
xargs spatch --in-place --sp-file modpnpsize0.cocci
(Note that coccinelle invokes diff(1) via a PATH search and expects diff to
tolerate the -B flag, which BSD diff does not. So I had to link gdiff into
PATH as diff to use spatch.)
Tinderbox'd (-DMAKE_JUST_KERNELS).
- Ever since the workaround for the silicon bug of TSO4 causing MAC hangs
was committed in r295133, CSUM_TSO always got disabled unconditionally
by em(4) on the first invocation of em_init_locked(). However, even with
that problem fixed, it turned out that for at least e. g. 82579 not all
necessary TSO workarounds are in place, still causing MAC hangs even at
Gigabit speed. Thus, for stable/11, TSO usage was deliberately disabled
in r323292 (r323293 for stable/10) for the EM-class by default, allowing
users to turn it on if it happens to work with their particular EM MAC
in a Gigabit-only environment.
In head, the TSO workaround for speeds other than Gigabit was lost with
the conversion to iflib(9) in r311849 (possibly along with another one
or two TSO workarounds). Yet at the same time, for EM-class MACs TSO4
got enabled by default again, causing device hangs. Therefore, change the
default for this hardware class back to have TSO4 off, allowing users
to turn it on manually if it happens to work in their environment as
we do in stable/{10,11}. An alternative would be to add a whitelist of
EM-class devices where TSO4 actually is reliable with the workarounds in
place, but given that the advantage of TSO at Gigabit speed is rather
limited - especially with the overhead of these workarounds -, that's
really not worth it. [1]
This change includes the addition of an isc_capabilities to struct
if_softc_ctx so iflib(9) can also handle interface capabilities that
shouldn't be enabled by default which is used to handle the default-off
capabilities of e1000 as suggested by shurd@ and moving their handling
from em_setup_interface() to em_if_attach_pre() accordingly.
- Although 82543 support TSO4 in theory, the former lem(4) didn't have
support for TSO4, presumably because TSO4 is even more broken in the
LEM-class of MACs than the later EM ones. Still, TSO4 for LEM-class
devices was enabled as part of the conversion to iflib(9) in r311849,
causing device hangs. So revert back to the pre-r311849 behavior of
not supporting TSO4 for LEM-class at all, which includes not creating
a TSO DMA tag in iflib(9) for devices not having IFCAP_TSO4 set. [2]
- In fact, the FreeBSD TCP stack can handle a TSO size of IP_MAXPACKET
(65535) rather than FREEBSD_TSO_SIZE_MAX (65518). However, the TSO
DMA must have a maxsize of the maximum TSO size plus the size of a
VLAN header for software VLAN tagging. The iflib(9) converted em(4),
thus, first correctly sets scctx->isc_tx_tso_size_max to EM_TSO_SIZE
in em_if_attach_pre(), but later on overrides it with IP_MAXPACKET
in em_setup_interface() (apparently, left-over from pre-iflib(9)
times). So remove the later and correct iflib(9) to correctly cap
the maximum TSO size reported to the stack at IP_MAXPACKET. While at
it, let iflib(9) use if_sethwtsomax*().
This change includes the addition of isc_tso_max{seg,}size DMA engine
constraints for the TSO DMA tag to struct if_shared_ctx and letting
iflib_txsd_alloc() automatically adjust the maxsize of that tag in case
IFCAP_VLAN_MTU is supported as requested by shurd@.
- Move the if_setifheaderlen(9) call for adjusting the maximum Ethernet
header length from {ixgbe,ixl,ixlv,ixv,em}_setup_interface() to iflib(9)
so adjustment is automatically done in case IFCAP_VLAN_MTU is supported.
As a consequence, this adjustment now is also done in case of bnxt(4)
which missed it previously.
- Move the reduction of the maximum TSO segment count reported to the
stack by the number of m_pullup(9) calls (which in the worst case,
can add another mbuf and, thus, the requirement for another DMA
segment each) in the transmit path for performance reasons from
em_setup_interface() to iflib_txsd_alloc() as these pull-ups are now
done in iflib_parse_header() rather than in the no longer existing
em_xmit(). Moreover, this optimization applies to all drivers using
iflib(9) and not just em(4); all in-tree iflib(9) consumers still
have enough room to handle full size TSO packets. Also, reduce the
adjustment to the maximum number of m_pullup(9)'s now performed in
iflib_parse_header().
- Prior to the conversion of em(4)/igb(4)/lem(4) and ixl(4) to iflib(9)
in r311849 and r335338 respectively, these drivers didn't enable
IFCAP_VLAN_HWFILTER by default due to VLAN events not being passed
through by lagg(4). With iflib(9), IFCAP_VLAN_HWFILTER was turned on
by default but also lagg(4) was fixed in that regard in r203548. So
just remove the now redundant and defunct IFCAP_VLAN_HWFILTER handling
in {em,ixl,ixlv}_setup_interface().
- Nuke other redundant IFCAP_* setting in {em,ixl,ixlv}_setup_interface()
which is (more completely) already done in {em,ixl,ixlv}_if_attach_pre()
now.
- Remove some redundant/dead setting of scctx->isc_tx_csum_flags in
em_if_attach_pre().
- Remove some IFCAP_* duplicated either directly or indirectly (e. g.
via IFCAP_HWCSUM) in {EM,IGB,IXL}_CAPS.
- Don't bother to fiddle with IFCAP_HWSTATS in ixgbe(4)/ixgbev(4) as
iflib(9) adds that capability unconditionally.
- Remove some unused macros from em(4).
- Bump __FreeBSD_version as some of the above changes require the modules
of drivers using iflib(9) to be recompiled.
Okayed by: sbruno@ at 201806 DevSummit Transport Working Group [1]
Reviewed by: sbruno (earlier version), erj
PR: 219428 (part of; comment #10) [1], 220997 (part of; comment #3) [2]
Differential Revision: https://reviews.freebsd.org/D15720
Changelist:
- Turn tx_rings and rx_rings arrays into arrays of pointers to kring
structs. This patch includes fixes for ixv, ixl, ix, re, cxgbe, iflib,
vtnet and ptnet drivers to cope with the change.
- Generalize the nm_config() callback to accept a struct containing many
parameters.
- Introduce NKR_FAKERING to support buffers sharing (used for netmap
pipes)
- Improved API for external VALE modules.
- Various bug fixes and improvements to the netmap memory allocator,
including support for externally (userspace) allocated memory.
- Refactoring of netmap pipes: now linked rings share the same netmap
buffers, with a separate set of kring pointers (rhead, rcur, rtail).
Buffer swapping does not need to happen anymore.
- Large refactoring of the control API towards an extensible solution;
the goal is to allow the addition of more commands and extension of
existing ones (with new options) without the need of hacks or the
risk of running out of configuration space.
A new NIOCCTRL ioctl has been added to handle all the requests of the
new control API, which cover all the functionalities so far supported.
The netmap API bumps from 11 to 12 with this patch. Full backward
compatibility is provided for the old control command (NIOCREGIF), by
means of a new netmap_legacy module. Many parts of the old netmap.h
header has now been moved to netmap_legacy.h (included by netmap.h).
Approved by: hrs (mentor)
This patch will:
- Update ixgbe shared code
- Add support for Intel(R) Ethernet Connection X552 1000BASE-T
- Add error handling for link state check preventing VF from stopping traffic
after changing PF's MTU value
Submitted by: Krzysztof Galazka <krzysztof.galazka@intel.com>
Reviewed by: Intel Networking
Sponsored by: Intel Corporation
Differential Revision: https://reviews.freebsd.org/D13885
In iflib, the device-specific init() function isn't supposed to edit
the struct ifnet driver flags. If it does, it'll cause an MPASS() assert
in iflib to fail.
PR: 225312
Reported by: bhughes@
Initial update to the ixgbe PF and VF drivers to support the iflib interface.
The PF driver version is bumped to 4.0.0, and the VF driver version is bumped to 2.0.0.
Special thanks to sbruno@ for the support in helping make this conversion happen.
Submitted by: Jeb Cramer <cramerj@intel.com>, Krzysztof Galazka (Chris) <krzysztof.galazka@intel.com>, Piotr Pietruszewski <piotr.pietruszewski@intel.com>
Reviewed by: sbruno@, shurd@, #IntelNetworking
Tested by: Jeffrey Pieper <jeffrey.e.pieper@intel.com>, Sergey Kozlov <kozlov.sergey.404@gmail.com>
Sponsored by: Limelight Networks, Intel Corporation
Differential Revision: https://reviews.freebsd.org/D11727
The previous update to the driver to 3.2.12-k changed the VF's API version
to 1.2, but did not let the VF fall back to 1.1 or 1.0 versions. So, this
patch tries 1.2 first, then the older versions in succession if that fails.
This should allow the VF driver to negotiate 1.1 and work with older PF
drivers, such as the one used in Amazon's EC2 service.
PR: 220872
Submitted by: Jeb Cramer <jeb.j.cramer@intel.com>
MFC after: 1 week
Sponsored by: Intel Corporation
Includes:
- Support for X550EM devices.
- Support for Bypass adapters.
- Flow Director code moved to separate files
- SR-IOV code moved to separate files
- Netmap code moved to separate files
Differential Revision: https://reviews.freebsd.org/D11232
Submitted by: Jeb Cramer <cramerj@intel.com>
Reviewed by: erj@
Tested by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Sponsored by: Intel Corporation
- Add optimizing LRO wrapper which pre-sorts all incoming packets
according to the hash type and flowid. This prevents exhaustion of
the LRO entries due to too many connections at the same time.
Testing using a larger number of higher bandwidth TCP connections
showed that the incoming ACK packet aggregation rate increased from
~1.3:1 to almost 3:1. Another test showed that for a number of TCP
connections greater than 16 per hardware receive ring, where 8 TCP
connections was the LRO active entry limit, there was a significant
improvement in throughput due to being able to fully aggregate more
than 8 TCP stream. For very few very high bandwidth TCP streams, the
optimizing LRO wrapper will add CPU usage instead of reducing CPU
usage. This is expected. Network drivers which want to use the
optimizing LRO wrapper needs to call "tcp_lro_queue_mbuf()" instead
of "tcp_lro_rx()" and "tcp_lro_flush_all()" instead of
"tcp_lro_flush()". Further the LRO control structure must be
initialized using "tcp_lro_init_args()" passing a non-zero number
into the "lro_mbufs" argument.
- Make LRO statistics 64-bit. Previously 32-bit integers were used for
statistics which can be prone to wrap-around. Fix this while at it
and update all SYSCTL's which expose LRO statistics.
- Ensure all data is freed when destroying a LRO control structures,
especially leftover LRO entries.
- Reduce number of memory allocations needed when setting up a LRO
control structure by precomputing the total amount of memory needed.
- Add own memory allocation counter for LRO.
- Bump the FreeBSD version to force recompilation of all KLDs due to
change of the LRO control structure size.
Sponsored by: Mellanox Technologies
Reviewed by: gallatin, sbruno, rrs, gnn, transport
Tested by: Netflix
Differential Revision: https://reviews.freebsd.org/D4914
This helps immensily with our ability to operate in the Amazon Cloud.
Discussed on Intel Networking Community call this morning.
Submitted by: Jarrod Petz(petz@nisshoko.net)
MFC after: 2 weeks
Differential Revision: https://reviews.freebsd.org/D4788
Add support for two new devices: X552 SFP+ 10 GbE, and the single port
version of X550T.
Submitted by: erj
Reviewed by: gnn
Sponsored by: Intel Corporation
Differential Revision: https://reviews.freebsd.org/D4186
an if_ixv instance can now set at creation time, and the receive ring
tail pointer is correctly initialized (previously, things still worked
because the receive ring tail pointer was being fixed up as a side
effect of other activity).
Differential Revision: https://reviews.freebsd.org/D2922
Reviewed by: erj, gnn
Approved by: jmallett (mentor)
Sponsored by: Norse Corp, Inc.
NOTE: This is a technology preview, while it has undergone
development testing, Intel has not yet completed full
validation of the feature. It is being integrated for
early access and customer testing.
NOTE: This is a technology preview, while it has undergone development
tests, Intel has not yet completed full validation of the feature.
It is being integrated for early access and customer testing.
These include standalone X550 adapters, X552 10GbE backplane, and
X552/X557-AT 10GBASE-T; with the latter two being integrated into Xeon D SoCs.
As well, this bumps the ixgbe version number to 2.8.3, and includes updates
to shared code for support for the new devices.
Differential Revision: D2414
Reviewed by: gnn, adrian
Approved by: jfv (mentor), gnn (mentor)
* Fix the multiple same-named devclasses; the duplicate name
trips up the linker.
* Re-do the taskqueue stuff to use the new cpuset API, not the old
pinned API.
* Add includes for the new location of the RSS configuration routines.
This allows ixgbe to compile as a module /and/ linked into the kernel,
along with RSS working.
Sponsored by: Norse Corp, Inc.
- Split the driver into independent pf and vf loadables. This is
in preparation for SRIOV support which will be following shortly.
This also allows us to keep a seperate revision control over the
two parts, making for easier sustaining.
- Make the TX/RX code a shared/seperated file, in the old code base
the ixv code would miss fixes that went into ixgbe, this model
will eliminate that problem.
- The driver loadables will now match the device names, something that
has been requested for some time.
- Rather than a modules/ixgbe there is now modules/ix and modules/ixv
- It will also be possible to make your static kernel with only one
or the other for streamlined installs, or both.
Enjoy!
Submitted by: jfv and erj