Lacp needs to manage the link state itself. Unlike other
lagg protocols, the ability of lacp to pass traffic
depends not only on the lagg members having link, but also
on the lacp protocol converging to a distributing state with the
link partner.
If we prematurely mark the link as up, then we will send a
gratuitous arp (via arp_handle_ifllchange()) before the lacp
interface is capable of passing traffic. When this happens,
the gratuitous arp is lost, and our link partner may cache
a stale mac address (eg, when the base mac address for the
lagg bundle changes, due to a BIOS change re-ordering NIC
unit numbers)
Reviewed by: jtl, hselasky
Sponsored by: Netflix
modules. It also fails in the same way, we are unable to relocate static
variables as the compiler uses PC-relative loads with nothing for the
kernel linker to relocate.
Sponsored by: DARPA, AFRL
declaired static. This will allow us to change the definition on arm64
as it has the same issues described in r336349.
Reviewed by: bz
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D16147
Since r336313, TSO support for LEM-class devices is removed again as it
was before the conversion of {l,}em(4) to iflib(4) in r311849 and as a
result, isc_tx_tso_segments_max is 0 for LEM-class devices now. Thus,
inappropriate watermarks were used for this class.
This is really only a band-aid, though, because so far iflib(9) doesn't
fully take into account that DMA engines can support different maxima
of segments for transfers of TSO and non-TSO packets. For example, the
DESC_RECLAIMABLE macro is based on isc_tx_nsegments while MAX_TX_DESC
used isc_tx_tso_segments_max only. For most in-tree consumers that
doesn't make a difference as the maxima are the same for both kinds of
transfers (that is, apart from the fact that TSO may require up to 2
sentinel descriptors but also not with every MAC supported). However,
isc_tx_nsegments is 8 but isc_tx_tso_segments_max is 85 by default
with ixl(4).
tests for avail > 0, avail can never be 0 within that loop. Thus, move
decrementing avail and budget_left into the loop and before the code which
checks for additional descriptors having become available in case all the
previous ones have been processed but there still is budget left so the
latter code works as expected. [1]
- In iflib_{busdma_load_mbuf_sg,parse_header}(), remove dead stores to m
and n respectively. [2, 3]
- In collapse_pkthdr(), ensure that m_next isn't NULL before dereferencing
it. [4]
- Remove a duplicate assignment of segs in iflib_encap().
Reported by: Coverity
CID: 1356027 [1], 1356047 [2], 1368205 [3], 1356028 [4]
r323954 changed the mp ring behaviour when 64-bit atomics were
available to abdicate the TX ring rather than having one become a
consumer thereby running to completion on TX. The consumer of the mp
ring was then triggered in the tx task rather than blocking the TX call.
While this significantly lowered the number of RX drops in small-packet
forwarding, it also negatively impacts TX performance.
With this change, the default behaviour is reverted, causing one TX ring
to become a consumer during the enqueue call. A new sysctl,
dev.X.Y.iflib.tx_abdicate is added to control this behaviour.
Reviewed by: gallatin
Sponsored by: Limelight Networks
Differential Revision: https://reviews.freebsd.org/D16302
Use the timer to poll for TX completions when there are
outstanding TX slots. Track when the last driver timer was called
to prevent overcalling it. Also clean up some kring vs NIC ring
usage.
Reviewed by: marius, Johannes Lundberg <johalun0@gmail.com>
Sponsored by: Limelight Networks
Differential Revision: https://reviews.freebsd.org/D16300
This deduplicates the code a bit, and also implicitly adds missing
callout_stop() to in[6]_lltable_delete_entry() functions.
PR: 209682, 225927
Submitted by: hselasky (previous version)
MFC after: 2 weeks
Differential Revision: https://reviews.freebsd.org/D4605
- 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
The typical system now has a lot more memory than when pf was new, and is also
expected to handle more connections. Increase the default size of the state
table.
Note that users can overrule this using 'set limit states' in pf.conf.
From OpenBSD:
The year is 2018.
Mercury, Bowie, Cash, Motorola and DEC all left us.
Just pf still has a default state table limit of 10000.
Had! Now it's a tiny little bit more, 100k.
lead guitar: me
ok chorus: phessler theo claudio benno
background school girl laughing: bob
Obtained from: OpenBSD
Add generic function if_tunnel_check_nesting() that does check for
allowed nesting level for tunneling interfaces and also does loop
detection. Use it in gif(4), gre(4) and me(4) interfaces.
Differential Revision: https://reviews.freebsd.org/D16162
ifioctl(). Move it inside the proper #ifdef. This was throwing a valid
"Assigned but unused" warning with gcc.
Sponsored by: Limelight Networks
Differential Revision: https://reviews.freebsd.org/D16063
Several third-parties use at least some of these ioctls. While it would be
better for regression testing if they were used in base (or at least in the
test suite), it's currently not worth the trouble to push through removal.
Submitted by: antoine, markj
- Add tracker argument to preemptible epochs
- Inline epoch read path in kernel and tied modules
- Change in_epoch to take an epoch as argument
- Simplify tfb_tcp_do_segment to not take a ti_locked argument,
there's no longer any benefit to dropping the pcbinfo lock
and trying to do so just adds an error prone branchfest to
these functions
- Remove cases of same function recursion on the epoch as
recursing is no longer free.
- Remove the the TAILQ_ENTRY and epoch_section from struct
thread as the tracker field is now stack or heap allocated
as appropriate.
Tested by: pho and Limelight Networks
Reviewed by: kbowling at llnw dot com
Sponsored by: Limelight Networks
Differential Revision: https://reviews.freebsd.org/D16066
Several ioctls are unused in pf, in the sense that no base utility
references them. Additionally, a cursory review of pf-based ports
indicates they're not used elsewhere either. Some of them have been
unused since the original import. As far as I can tell, they're also
unused in OpenBSD. Finally, removing this code removes the need for
future pf work to take them into account.
Reviewed by: kp
Differential Revision: https://reviews.freebsd.org/D16076
encap_lookup_t method can be invoked by IP encap subsytem even if none
of gif/gre/me interfaces are exist. Hash tables are allocated on demand,
when first interface is created. So, make NULL pointer check before
doing access to hash table.
PR: 229378
- In iflib_msix_init(), VMMs with broken MSI-X activation are trying
to be worked around by manually enabling PCIM_MSIXCTRL_MSIX_ENABLE
before calling pci_alloc_msix(9). Apart from constituting a layering
violation, this has the problem of leaving PCIM_MSIXCTRL_MSIX_ENABLE
enabled when falling back to MSI or INTx when e. g. MSI-X is black-
listed and initially also when disabled via hw.pci.enable_msix. The
later in turn was incorrectly worked around in r325166.
Since r310806, pci(4) itself has code to deal with broken MSI-X
handling of VMMs, so all of these workarounds in iflib(9) can go,
fixing non-working interrupts when falling back to MSI/INTx. In
any case, possibly further adjustments to broken MSI-X activation
of VMMs like enabling r310806 by default in VM environments need to
be placed into pci(4), not iflib(9). [1]
- Also remove the pci_enable_busmaster(9) call from iflib_msix_init(),
which is already more properly invoked from iflib_device_attach().
- When falling back to MSI/INTx, release the MSI-X BAR resource again.
- When falling back to INTx, ensure scctx->isc_vectors is set to 1 and
not to something higher from a device with more than one MSI message
supported.
- Make the nearby ring_state(s) stuff (static) const.
Discussed with: jhb at BSDCan 2018 [1]
Reviewed by: imp, jhb
Differential Revision: https://reviews.freebsd.org/D15729
Using of rwlock with multiqueue NICs for IP forwarding on high pps
produces high lock contention and inefficient. Rmlock fits better for
such workloads.
Reviewed by: melifaro, olivier
Obtained from: Yandex LLC
Sponsored by: Yandex LLC
Differential Revision: https://reviews.freebsd.org/D15789
Most kernel memory that is allocated after boot does not need to be
executable. There are a few exceptions. For example, kernel modules
do need executable memory, but they don't use UMA or malloc(9). The
BPF JIT compiler also needs executable memory and did use malloc(9)
until r317072.
(Note that a side effect of r316767 was that the "small allocation"
path in UMA on amd64 already returned non-executable memory. This
meant that some calls to malloc(9) or the UMA zone(9) allocator could
return executable memory, while others could return non-executable
memory. This change makes the behavior consistent.)
This change makes malloc(9) return non-executable memory unless the new
M_EXEC flag is specified. After this change, the UMA zone(9) allocator
will always return non-executable memory, and a KASSERT will catch
attempts to use the M_EXEC flag to allocate executable memory using
uma_zalloc() or its variants.
Allocations that do need executable memory have various choices. They
may use the M_EXEC flag to malloc(9), or they may use a different VM
interfact to obtain executable pages.
Now that malloc(9) again allows executable allocations, this change also
reverts most of r317072.
PR: 228927
Reviewed by: alc, kib, markj, jhb (previous version)
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D15691
of needed interface when many gre interfaces are present.
Remove rmlock from gre_softc, use epoch(9) and CK_LIST instead.
Move more AF-related code into AF-related locations. Use hash table to
speedup lookup of needed softc.
option.
The BPF code was creating a compiled filter in the common filter-creation
path. However, BPF only uses compiled filters in the read direction.
When creating a write filter, the common filter-creation code was
creating an unneeded write filter and leaking the memory used for that.
MFC after: 2 weeks
Sponsored by: Netflix
Since we are setting IFF_UP flag on SIOCSIFADDR, it is possible, that
after this link state information still not initialized properly.
This leads to problems with routing, since now interface has
IFCAP_LINKSTATE capability and a route is considered as working only
when interface's link state is in LINK_STATE_UP (see RT_LINK_IS_UP()
macro).
Reported by: Marek Zarychta
MFC after: 3 days
This caused issues with PASTE. Just remove the reschedule since the DELAY()
should be enough for use cases such as pkt-gen which were failing before the
change.
Reported by: Michio Honda
Sponsored by: Limelight Networks
Turns out there is code which ends up passing M_ZERO to counters.
Since counters zero unconditionally on their own, just ignore drop the
flag in that place.
ixl(4) (when it switches over to using iflib) devices need the TCP header
length in order to do TCP checksum offload.
Reviewed by: gallatin@, shurd@
MFC after: 1 week
Sponsored by: Intel Corporation
Differential Revision: https://reviews.freebsd.org/D15558
of needed interface when many gif interfaces are present.
Remove rmlock from gif_softc, use epoch(9) and CK_LIST instead.
Move more AF-related code into AF-related locations.
Use hash table to speedup lookup of needed softc. Interfaces
with GIF_IGNORE_SOURCE flag are stored in plain CK_LIST.
Sysctl net.link.gif.parallel_tunnels is removed. The removal was planed
16 years ago, and actually it could work only for outbound direction.
Each protocol, that can be handled by if_gif(4) interface is registered
by separate encap handler, this helps avoid invoking the handler
for unrelated protocols (GRE, PIM, etc.).
This change allows dramatically improve performance when many gif(4)
interfaces are used.
Sponsored by: Yandex LLC
Currently it has several disadvantages:
- it uses single mutex to protect internal structures. It is used by
data- and control- path, thus there are no parallelism at all.
- it uses single list to keep encap handlers for both INET and INET6
families.
- struct encaptab keeps unneeded information (src, dst, masks, protosw),
that isn't used by code in the source tree.
- matches are prioritized and when many tunneling interfaces are
registered, encapcheck handler of each interface is invoked for each
packet. The search takes O(n) for n interfaces. All this work is done
with exclusive lock held.
What this patch includes:
- the datapath is converted to be lockless using epoch(9) KPI.
- struct encaptab now linked using CK_LIST.
- all unused fields removed from struct encaptab. Several new fields
addedr: min_length is the minimum packet length, that encapsulation
handler expects to see; exact_match is maximum number of bits, that
can return an encapsulation handler, when it wants to consume a packet.
- IPv6 and IPv4 handlers are stored in separate lists;
- added new "encap_lookup_t" method, that will be used later. It is
targeted to speedup lookup of needed interface, when gif(4)/gre(4) have
many interfaces.
- the need to use protosw structure is eliminated. The only pr_input
method was used from this structure, so I don't see the need to keep
using it.
- encap_input_t method changed to avoid using mbuf tags to store softc
pointer. Now it is passed directly trough encap_input_t method.
encap_getarg() funtions is removed.
- all sockaddr structures and code that uses them removed. We don't have
any code in the tree that uses them. All consumers use encap_attach_func()
method, that relies on invoking of encapcheck() to determine the needed
handler.
- introduced struct encap_config, it contains parameters of encap handler
that is going to be registered by encap_attach() function.
- encap handlers are stored in lists ordered by exact_match value, thus
handlers that need more bits to match will be checked first, and if
encapcheck method returns exact_match value, the search will be stopped.
- all current consumers changed to use new KPI.
Reviewed by: mmacy
Sponsored by: Yandex LLC
Differential Revision: https://reviews.freebsd.org/D15617
- move harvest mask check inline
- move harvest mask to frequently_read out of actively
modified cache line
- disable ether_input collection and describe its limitations
in NOTES
Typically entropy collection in ether_input was stirring zero
in to the entropy pool while at the same time greatly reducing
max pps. This indicates that perhaps we should more closely
scrutinize how much entropy we're getting from a given source
as well as what our actual entropy collection needs are for
seeding Yarrow.
Reviewed by: cem, gallatin, delphij
Approved by: secteam
Differential Revision: https://reviews.freebsd.org/D15526
- Restore local change to include <net/bpf.h> inside pcap.h.
This fixes ports build problems.
- Update local copy of dlt.h with new DLT types.
- Revert no longer needed <net/bpf.h> includes which were added
as part of r334277.
Suggested by: antoine@, delphij@, np@
MFC after: 3 weeks
Sponsored by: Mellanox Technologies
Given that PF_RULES_LOCK is a mostly read lock, replace the rwlock with rmlock.
This change improves packet processing rate in high pps environments.
Benchmarking by olivier@ shows a 65% improvement in pps.
While here, also eliminate all appearances of "sys/rwlock.h" includes since it
is not used anymore.
Submitted by: farrokhi@
Differential Revision: https://reviews.freebsd.org/D15502
The *name parameter passed to iflib_irq_alloc_generic and
iflib_softirq_alloc_generic is never modified. Many places in code pass
string literals and thus should not be modified.
Mark the *name parameter as a const char * instead, so that we enforce
that the name is not modified before passing to bus_describe_intr()
Submitted by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed by: kmacy
Sponsored by: Intel Corporation
Differential Revision: https://reviews.freebsd.org/D15343
