Remove the STDC CX_LIMITED_RANGE pragma and its verbose comment. We still
don't have any C99 compilers (that support fenv pragmas), and if we did
then there are thousands of other places in libm that would need to use
them more than here.
Add module parameter to limit number of MSIX EQ vectors in mlx5en(4).
For setups having a large amount of PCI devices, it makes sense to limit the
number of MSIX vectors per PCI device, in order to avoid running out of IRQ
vectors.
To access the data, set sysctl dev.mce.N.conf.debug_stats to 1.
This enables the sysctl node dev.mce.N.hw_ctx_debug. Its content is
the mapping of each channel' number to used receive queue and associated
completion queue, set of the transmit queues numbers and corresponding
completion queues.
Fix scaling bugs which gave innaccuracies and spurious underflows in csqrt()
and csqrtl().
When one component is huge and the other is tiny, scaling down the tiny
component gave spurious underflow.
When both components are denormal, not scaling them up gave inaccuracies
of 34+ ulps on not very carefully selected args. Fixing this reduces the
maximum error to 1.6 ulps on the same set of args (mosly not denormal ones).
The scaling used multiplication of a complex variable by 2, but clang messes
this on amd64 up by losing the sign of -0.0. Calculate the components
separately, as is well known to be needed for operations on more exceptional
values.
Make sure the state variable is set atomically instead of using a mutex in mlx5core.
Device detach and setting error state may deadlock over the interface mutex
like this:
a) Detach code in mlx5en waits until error state is set while the interface
mutex is locked.
b) The set error handler needs to lock the interface mutex before it can
set the error state.
The solution is to use atomics to set the error state.
Use static device naming instead of dynamic one in mlx5ib.
When resetting mlx5core instances it can happen that the order of attach and
detach for mlx5ib instances is changed. Take the unit number for mlx5_%d from
the parent PCI device, similarly to what is done in mlx5en(4), so that there
is a direct relationship between mce<N> and mlx5_<N>.
When creating address handle from multicast GID, set MAC according to
the appropriate formula instead of searching for it in the GID table:
- For IPv4 multicast GID use ip_eth_mc_map().
- For IPv6 multicast GID use ipv6_eth_mc_map().
Honor return status of ib_init_ah_from_mcmember() in ibcore.
The return status of ib_init_ah_from_mcmember() is ignored by
cma_ib_mc_handler(). Honor it and return error event if ah attribute
initialization failed.
Check port number supplied by user verbs cmds in ibcore.
The ib_uverbs_create_ah() ind ib_uverbs_modify_qp() calls receive
the port number from user input as part of its attributes and assumes
it is valid. Down on the stack, that parameter is used to access kernel
data structures. If the value is invalid, the kernel accesses memory
it should not. To prevent this, verify the port number before using it.
Fix kernel crash during fail to initialize device in ibcore.
This patch fixes the kernel crash that occurs during ib_dealloc_device()
called due to provider driver fails with an error after
ib_alloc_device() and before it can register using ib_register_device().
This crashed seen in tha lab as below which can occur with any IB device
which fails to perform its device initialization before invoking
ib_register_device().
This patch avoids touching cache and port immutable structures if device
is not yet initialized.
It also releases related memory when cache and port immutable data
structure initialization fails during register_device() state.
Check AF family prior resolving address and introduce safer rdma_addr_size() variants in ibcore.
Garbage supplied by user will cause to UCMA module provide zero
memory size for memcpy(), because it wasn't checked, it will
produce unpredictable results in rdma_resolve_addr().
There are several places in the ucma ABI where userspace can pass in a
sockaddr but set the address family to AF_IB. When that happens,
rdma_addr_size() will return a size bigger than sizeof struct sockaddr_in6,
and the ucma kernel code might end up copying past the end of a buffer
not sized for a struct sockaddr_ib.
Fix this by introducing new variants
int rdma_addr_size_in6(struct sockaddr_in6 *addr);
int rdma_addr_size_kss(struct __kernel_sockaddr_storage *addr);
that are type-safe for the types used in the ucma ABI and return 0 if the
size computed is bigger than the size of the type passed in. We can use
these new variants to check what size userspace has passed in before
copying any addresses.
Check for a cm_id->device in all user calls that need it in ibcore.
This was done by auditing all callers of ucma_get_ctx and switching the
ones that unconditionally touch ->device to ucma_get_ctx_dev. This covers
a little less than half of the call sites.
The 11 remaining call sites to ucma_get_ctx() were manually audited.
Fix kernel panic while using XRC_TGT QP type in ibcore.
Attempt to modify XRC_TGT QP type from the user space (ibv_xsrq_pingpong
invocation) will trigger the following kernel panic. It is caused by the
fact that such QPs missed uobject initialization.
Fix NULL pointer dereference during device removal in ibcore.
As part of ib_uverbs_remove_one which might be triggered upon
reset flow, we trigger IB_EVENT_DEVICE_FATAL event to userspace
application.
If device was removed after uverbs fd was opened but before
ib_uverbs_get_context was called, the event file will be accessed
before it was allocated, result in NULL pointer dereference:
Ensure that CM_ID exists prior to access it in ibcore.
Prior to access UCMA commands, the context should be initialized
and connected to CM_ID with ucma_create_id(). In case user skips
this step, he can provide non-valid ctx without CM_ID and cause
to multiple NULL dereferences.
Also there are situations where the create_id can be raced with
other user access, ensure that the context is only shared to
other threads once it is fully initialized to avoid the races.
Add support for prio-tagged traffic for RDMA in ibcore.
When receiving a PCP change all GID entries are reloaded.
This ensures the relevant GID entries use prio tagging,
by setting VLAN present and VLAN ID to zero.
The priority for prio tagged traffic is set using the regular
rdma_set_service_type() function.
Fake the real network device to have a VLAN ID of zero
when prio tagging is enabled. This is logic is hidden inside
the rdma_vlan_dev_vlan_id() function which must always be used
to retrieve the VLAN ID throughout all of ibcore and the
infiniband network drivers.
The VLAN presence information then propagates through all
of ibcore and so incoming connections will have the VLAN
bit set. The incoming VLAN ID is then checked against the
return value of rdma_vlan_dev_vlan_id().
RoCEv2 Annex states that for RoCEv2 over IPv4, the corresponding
IPv4 address is encoded into the GID according to the following rule:
GID= :ffff:<IPv4 address>
Remove the 0xff0e prefix for RoCEv2 packets with IPv4 and leave it
zeroed and change rdma_is_multicast_addr() to consider the new logic.
For multicast functions in ibcore, verify that LIDs are multicast LIDs.
The Infiniband spec defines "A multicast address is defined by a
MGID and a MLID" (section 10.5).
Add check to verify that the MLID value is in the correct address
range.
RoCE Annex (A16.9.10/11) declares that during attach (detach) QP to a
multicast group, if the QP is associated with a RoCE port, the
multicast group MLID is unused and is ignored.
During attach or detach multicast, when the QP is associated with a
port, it is enough to check the port's link layer and validate the
LID only if it is Infiniband. Otherwise, avoid validating the
multicast LID.
Implement a more generic solution for detecting loopback.
The problem was that the default netdevice was resolved
for loopback also when VLAN was used. Use real network
device instead of loopback device for bound device
interface.
How to test:
ucmatose -b 127.0.0.1 -p 20090
ucmatose -s 5.6.5.1 -p 20090
Note that RDMA treats the IPv4 and IPv6 loopback
addresses like any address.
If the MGID/MLID pair is not on the list return an error in ibcore.
A list of MGID/MLID pairs is built when doing a multicast attach. When
the multicast detach is called, the list is searched, and regardless of
the search outcome, the driver detach is called.
If an MGID/MLID pair is not on the list, driver detach should not be
called, and an error should be returned. Calling the driver without
removing an MGID/MLID pair from the list can leave the core and driver
out of sync.
When two handlers used the same object in the old schema, we blocked
the process in the kernel. The new schema just returns -EBUSY. This
could lead to different behaviour in applications between the old
schema and the new schema. In most cases, using such handlers
concurrently could lead to crashing the process. For example, if
thread A destroys a QP and thread B modifies it, we could have the
destruction happens before the modification. In this case, we are
accessing freed memory which could lead to crashing the process.
This is true for most cases. However, attaching and detaching
a multicast address from QP concurrently is safe. Therefore, we
preserve the original behaviour by adding a lock there.
Only update source address when resolving is successful in ibcore.
When resolving an IP address in ibcore, only update the source address
upon normal completion. The ibcore address resolve function does not
care about the scope ID value of the IPv6 link-local addresses and expects
this information has already been extracted into the bound_dev_if field.
Because the same IPv6 link-local address can exist on multiple interfaces
the ibcore address resolver gets confused and returns ENETUNREACH.
Instead of updating both source address and bound_dev_if just keep the
address set to any address until resolving completes. For the sake of code
symmetry a similar change has been applied to the IPv4 address resolve path.
Process address resolve requests at least one time per second in ibcore.
When setting a large address resolve timeout it was observed that the
address resolving would succeed at the timeout and not when the address
was available. Make sure the address resolving requests are processed no
slower than one time every second.
While at it use "int" for jiffies instead of "unsigned long" to match
FreeBSD ticks.
Add a macro nan_mix() and use it to get NaN results that are (bitwise)
independent of the precision in most cases. This is mainly to simplify
checking for errors. r176266 did this for e_pow[f].c using a less
refined expression that often didn't work. r176276 fixes an error in
the log message for r176266. The main refinement is to always expand
to long double precision. See old log messages (especially these 2)
and the comment on the macro for more general details.
Specific details:
- using nan_mix() consistently for the new and old pow*() functions was
the only thing needed to make my consistency test for powl() vs pow()
pass on amd64.
- catrig[fl].c already had all the refinements, but open-coded.
- e_atan2[fl].c, e_fmod[fl].c and s_remquo[fl] only had primitive NaN
mixing.
- e_hypot[fl].c already had a different refined version of r176266. Refine
this further. nan_mix() is not directly usable here since we want to
clear the sign bit.
- e_remainder[f].c already had an earlier version of r176266.
- s_ccosh[f].c,/s_csinh[f].c already had a version equivalent to r176266.
Refine this further. nan_mix() is not directly usable here since the
expression has to handle some non-NaN cases.
- s_csqrt.[fl]: the mixing was special and mostly wrong. Partially fix the
special version.
Revert 336358 and step away fron machine for the day...
VERSREQ < 7.+ physically will not work with new config(8) due to major bump,
which is why I bumped it in the first place... Back to the original version
Modify the reasons for not issuing a delegation in the NFSv4.1 server.
The ESXi NFSv4.1 client will generate warning messages when the reason for
not issuing a delegation is two. Two refers to a resource limit and I do
not see why it would be considered invalid. However it probably was not the
best choice of reason for not issuing a delegation.
This patch changes the reasons used to ones that the ESXi client doesn't
complain about. This change does not affect the FreeBSD client and does
not appear to affect behaviour of the Linux NFSv4.1 client.
RFC5661 defines these "reasons" but does not give any guidance w.r.t. which
ones are more appropriate to return to a client.
config-generated hints.c/env.c from r335998 and later are incompatible with
earlier kernels due to no longer setting envmode/hintmode. A minor bump for
this is insufficient, as matching major version with a later minor version
is still viewed as backwards-compatible.
This was an MI kernel change, soo all VERSREQ's are bumped.
sysrc(8): Send error message to stderr (not stdout)
PR: bin/229806
Reported by: Andreas Sommer <andreas.sommer87@googlemail.com>
MFC after: 3 days
X-MFC-to: stable/11 stable/10 stable/9
Sponsored by: Smule, Inc.
andrew [Mon, 16 Jul 2018 18:21:29 +0000 (18:21 +0000)]
Don't use the static keyword with DPCPU defines in arm64 modules.
On arm64 compiler will create PC-relative loads and stores for static data.
This means it doesn't emit a relocation. Unfortunately the in-kernel linker
expects there to be one for DPCPU defines so it can modify its value so the
code will use the correct DPCPU region.
To workaround the lack of a relocation with static data remove it when
building modules on arm64. The kernel is unaffected as it doesn't rely on
modifying these relocations to find the data.
PR: 225684
Reported by: Johannes Lundberg <johalun0@gmail.com>
Reported by: Jose Luis Duran <jlduran@gmail.com>
Reported by: Greg V <greg@unrelenting.technology>
Reviewed by: bz
Sponsored by: ABT Systems Ltd
Differential Revision: https://reviews.freebsd.org/D16145
andrew [Mon, 16 Jul 2018 15:39:33 +0000 (15:39 +0000)]
Create an empty stdint.h for arm_neon.h to include.
The armv8crypto module includes arm_neon.h for the compiler intrinsic
functions. This includes the userland stdint.h file that doesn't exist in
the kernel. Fix this by providing an empty stdint.h to be used when we
include arm_neon.h.
No longer install sys/nv.h and sys/cnv.h in lib/libnv/Makefile
Use tools/build/Makefile to install the headers into ${WORLDTMP}/legacy
instead. Compared to r336026 this has the minor advantage that it avoids
unncessary header installation when building the non-bootstrap libnv.
indent(1): rewrite the integer/floating constant scanning part of lexi.c
Remove procedural code that did the scanning, which was faulty and didn't
support complex constants such as 0x1p-61. Replace it with a finite state
machine expressed as a transition table. The table was rewritten by hand
from lx's output, given parts of grammar expressed as regular expressions.
lx is Katherine Flavel's lexer generator, currently available at
https://github.com/katef/libfsm and the parts of grammar were taken from
http://quut.com/c/ANSI-C-grammar-l-2011.html and extended to support binary
integer constants which are a popular GCC extension.
ig4(4) does not support suspend/resume but present on the hardware where
such functionality is critical, like laptops. Remove PNP info to avoid
breaking suspend/resume on the systems where ig4(4) load is not explicitly
requested by the user.
Don't require a local sshd for the local TCP state dtrace test
This change is similar to the one done in r286171 for
tst.ipv4localtcp.ksh. This not only reduces the requirements on the
system used for testing but results also in a graceful teardown of
the TCP connection.
Reviewed by: gnn@
Sponsored by: Netflix, Inc.
Differential Revision: https://reviews.freebsd.org/D16276
The code imported from opensolaris was depending on ping supporting
UDP for sending probes. Since this is not supported by ping on FreeBSD
use a perl script instead.
The remote test requires the usage of ksh93, so state that in the
sheband.
Enable the local test, but keep the remote test disabled, since it
requires a remote machine on the LAN.
Test PGA_REFERENCED after calling pmap_ts_referenced(), rather than before,
so that a reference from a concurrently destroyed mapping is observed
during the current scan.
marius [Sun, 15 Jul 2018 19:04:23 +0000 (19:04 +0000)]
Assorted TSO fixes for em(4)/iflib(9) and dead code removal:
- 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
Shut down the TCP connection to a DS in the pNFS client when Renew fails.
When a NFSv4.1 client mount using pNFS detects a failure trying to do a
Renew (actually just a Sequence operation), the code would simply try
again and again and again every 30sec.
This would tie up the "nfscl" thread, which should also be doing other
things like Renews on other DSs and the MDS.
This patch adds code which closes down the TCP connection and marks it
defunct when Renew detects an failure to communicate with the DS, so
further Renews will not be attempted until a new working TCP connection to
the DS is established.
It also makes the call to nfscl_cancelreqs() unconditional, since
nfscl_cancelreqs() checks the NFSCLDS_SAMECONN flag and does so while holding
the lock.
This fix only applies to the NFSv4.1 client whne using pNFS and without it
the only effect would have been an "nfscl" thread busy doing Renew attempts
on an unresponsive DS.
marius [Sun, 15 Jul 2018 18:03:56 +0000 (18:03 +0000)]
Remove code to disable IFCAP_VLAN_HWFILTER by default for ixgbe(4) as VLAN
events are passed through by lagg(4) ever since r203548. Deactivation of
this capability by default due to lagg(4) was already not done for ixgbev(4)
and has been - although inadvertently - broken when em(4)/igb(4)/lem(4) and
ixl(4) were converted to iflib(9) in r311849 and r335338 respectively.
Use EF_SEG_READ_STRING instead of EF_SEG_READ when reading strings.
Normally, we can get away with just reading the 1k buffer for the
string, since the placement of the data is generally no where near the
end of the file. However, it's possible that the string is within the
last 1k of the file, in which case the read will fail, and we'll not
produce the proper records needed for devmatch to work. By reading
using EF_SEG_READ_STRING, we automatically work around these problems
while still retaining safety.
This fix a problem with devmatch where we wouldn't load certain
modules (like ums). This didn't always happen (my tree didn't exhibit
it, while nathan's did because his optimization options were more
agressive).
acquire inp lock around ip6_pcbopt to fix IPV6_TCLASS panic
Simple fix to address panics relating to setting IPV6_TCLASS
with setsockopt(). The premise of this change is that it is
ok to call malloc with M_NOWAIT while holding a lock on the
in6p.
If it later turns out that it is not ok, then major surgery
will be required, as ip6_setpktopt() will have to be fixed
(as it also calls malloc with M_NOWAIT) which pulls in the
ip6_pcbopts(), ip6_setpktopts(), ip6_setpktopt() call chain.
msun: add ld80/ld128 powl, cpow, cpowf, cpowl from openbsd
This corresponds to the latest status (hasn't changed in 9+
years) from openbsd of ld80/ld128 powl, and source cpowf, cpow,
cpowl (the complex power functions for float complex, double
complex, and long double complex) which are required for C99
compliance and were missing from FreeBSD. Also required for
some numerical codes using complex numbered Hamiltonians.
Thanks to jhb for tracking down the issue with making
weak_reference compile on powerpc.
When asked to review, bde said "I don't like it" - but
provided no actionable feedback or superior implementations.
Invalidate the mapping before updating its physical address.
Doing so ensures that all threads sharing the pmap have a consistent
view of the mapping. This fixes the problem described in the commit
log message for r329254 without the overhead of an extra page fault
in the common case. (Now that all pmap_enter() implementations are
similarly modified, the workaround added in r329254 can be removed,
reducing the overhead of COW faults.)
With this change we can reuse the PV entry from the old mapping,
potentially avoiding a call to reclaim_pv_chunk(). Otherwise, there is
nothing preventing the old PV entry from being reclaimed. In rare
cases this could result in the PTE's page table page being freed,
leading to a use-after-free of the page when the updated PTE is written
following the allocation of the PV entry for the new mapping.
Fix the pNFS client when mirrors aren't on the same machine.
Without this patch, the client side NFSv4.1 pNFS code erroneously did writes
and commits to both DS mirrors using the TCP connection of the first one.
For my test setup this worked, since I have both DSs running on the same
machine, but it would have failed when the DSs are on separate machines.
This patch fixes the code to use the correct TCP connection for each DS.
This patch should only affect the NFSv4.1 client when using "pnfs" mounts
to mirrored DSs.
Since we don't have /usr/bin/ksh, use a generic way of specifying
ksh. Some of the tests only run with ksh93, so use this shell
for these tests. Two of the tests don't have the execute bit set,
so fix this, too.
Reviewed by: markj@
Sponsored by: Netflix, Inc.
Differential Revision: https://reviews.freebsd.org/D16270