The cache_handle_range macro to handle the arm64 instruction and data
cache operations would return when it was complete. This causes problems
for arm64_icache_sync_range and arm64_icache_sync_range_checked as they
assume they can execute the i-cache handling instruction after it has been
called.
Fix this by making this assumption correct.
While here add missing instruction barriers and adjust the style to
match the rest of the assembly.
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D18838
Sometimes, for negated tables, pf can log 'pfr_update_stats: assertion failed'.
This warning does not clarify anything for users, so silence it, just as
OpenBSD has.
PR: 234874
MFC after: 1 week
o In vm_pager_bufferinit() create pbuf_zone and start accounting on how many
pbufs are we going to have set.
In various subsystems that are going to utilize pbufs create private zones
via call to pbuf_zsecond_create(). The latter calls uma_zsecond_create(),
and sets a limit on created zone. After startup preallocate pbufs according
to requirements of all pbuf zones.
Subsystems that used to have a private limit with old allocator now have
private pbuf zones: md(4), fusefs, NFS client, smbfs, VFS cluster, FFS,
swap, vnode pager.
The following subsystems use shared pbuf zone: cam(4), nvme(4), physio(9),
aio(4). They should have their private limits, but changing that is out of
scope of this commit.
o Fetch tunable value of kern.nswbuf from init_param2() and while here move
NSWBUF_MIN to opt_param.h and eliminate opt_swap.h, that was holding only
this option.
Default values aren't touched by this commit, but they probably should be
reviewed wrt to modern hardware.
This change removes a tight bottleneck from sendfile(2) operation, that
uses pbufs in vnode pager. Other pagers also would benefit from faster
allocation.
Together with: gallatin
Tested by: pho
Do not lose error condition by always returning 0 from set_led.
None of the calls to set_led checks for return value at the moment so
none of API consumers in base is affected.
PR: 231567
Submitted by: Bertrand Petit <bsdpr@phoe.frmug.org>
MFC after: 1 week
mv_pci driver reads PCI memory window layout from DTB data and if the
data is incomplete falls back to default value. The value is too small
to fit two PCI spaces for mwlwifi devices on WRT3200ACM so the resource
allocation for them fails. Increase the default to 4Mb from 1Mb so
the devices can be properly attached.
MFC after: 1 week
two zones sharing a keg may have different limits. Now this is going
to work:
zone = uma_zcreate();
uma_zone_set_max(zone, limit);
zone2 = uma_zsecond_create(zone);
uma_zone_set_max(zone2, limit2);
Kegs no longer have uk_maxpages field, but zones have uz_items. When
set, it may be rounded up to minimum possible CPU bucket cache size.
For small limits bucket cache can also be reconfigured to be smaller.
Counter uz_items is updated whenever items transition from keg to a
bucket cache or directly to a consumer. If zone has uz_maxitems set and
it is reached, then we are going to sleep.
o Since new limits don't play well with multi-keg zones, remove them. The
idea of multi-keg zones was introduced exactly 10 years ago, and never
have had a practical usage. In discussion with Jeff we came to a wild
agreement that if we ever want to reintroduce the idea of a smart allocator
that would be able to choose between two (or more) totally different
backing stores, that choice should be made one level higher than UMA,
e.g. in malloc(9) or in mget(), or whatever and choice should be controlled
by the caller.
o Sleeping code is improved to account number of sleepers and wake them one
by one, to avoid thundering herd problem.
o Flag UMA_ZONE_NOBUCKETCACHE removed, instead uma_zone_set_maxcache()
KPI added. Having no bucket cache basically means setting maxcache to 0.
o Now with many fields added and many removed (no multi-keg zones!) make
sure that struct uma_zone is perfectly aligned.
Reviewed by: markj, jeff
Tested by: pho
Differential Revision: https://reviews.freebsd.org/D17773
vm_kmem_size is u_long, and it might be not capable of holding page
count times PAGE_SIZE, even when scaled down by VM_KMEM_SIZE_SCALE. As
bde reported, 12G PAE config ends up with zero for kmem size.
Explicitly check for overflow and clamp kmem size at vm_kmem_size_max.
If we end up at zero size because VM_KMEM_SIZE_MAX is not defined,
panic with clear explanation rather then failing in a way which is
hard to relate.
Reported by: bde, pho
Tested by: pho
Reviewed by: markj
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D18767
cpu_icache_sync_range(), except that it sets pcb_onfault to catch any page
fault, as doing cache maintenance operations for non-mapped generates a
data abort, and use it in freebsd32_sysarch(), so that a userland program
attempting to sync the icache with unmapped addresses doesn't crash the
kernel.
Spotted out by: andrew
r319722 separated struct socket and parts of the socket I/O path into
listening-socket-specific and dataflow-socket-specific pieces. Listening
socket connection notifications are now handled by solisten_wakeup() instead
of sowakeup(), but solisten_wakeup() does not currently post SIGIO to the
owning process.
PR: 234258
Reported by: Kenneth Adelman
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D18664
There may be various side effects (device timeout, firmware and / or
kernel panic) when an invalid (or inapplicable - e.g., an MCS rate
for 11g-only device) is set; check rates before sending the frame to
the driver.
How-to-reproduce:
Set an MCS (real or bogus - with 0x80 bit set) rate in ibp_rate0 field
for any device that uses ieee80211_isratevalid() for rate checks -
rum(4), run(4), ural(4), bwi(4) or ral(4); if kernel is compiled
with INVARIANTS the check will result in "rate %d is basic/mcs?" panic.
Tested with WUSB54GC (rum(4)), AP mode.
MFC after: 1 week
Don't clobber the low part of the register restoring the high component of.
This could lead to very bad behavior if it's an ABI-affected register.
While here, also mark the asm volatile in the SPE high save case, to match
the load case.
Reported by: Branden Bergren (git_bdragon.rtk0.net)
MFC after: 1 week
Summary:
I was working on implementing ifuncs on powerpc64 elfv2 today, and I suddenly
realized that the reason I was having so much trouble with AT_HWCAP and
AT_HWCAP2 is they are missing from the sysentvec.
After adding them, the auxv is being filled like it should.
Submitted by: Brandon Bergren (git_bdragon.rtk0.net)
Differential Revision: https://reviews.freebsd.org/D18575
Family 15h is a bit of an oddball. Early models used the same temperature
register and spec (mostly[1]) as earlier CPU families.
Model 60h-6Fh and 70-7Fh use something more like Family 17h's Service
Management Network, communicating with it in a similar fashion. To support
them, add support for their version of SMU indirection to amdsmn(4) and use
it in amdtemp(4) on these models.
While here, clarify some of the deviceid macros in amdtemp(4) that were
added with arbitrary, incorrect family numbers, and remove ones that were
not used. Additionally, clarify intent and condition of heterogenous
multi-socket system detection.
[1]: 15h adds the "adjust range by -49°C if a certain condition is met,"
which previous families did not have.
Reported by: D. C. <tjoard AT gmail.com>
PR: 234657
Tested by: D. C. <tjoard AT gmail.com>
The IPI vector is static, and happens to be the most common interrupt by far
on some systems. Rather than searching for the interrupt every time, cache
the index.
This appears to yield a small performance boost, of about 8% reduction in
buildworld times, on my POWER9 system, when paired with r342975.
The XICS and XIVE need extra data beyond irq and vector. Rather than
performing a separate search, it's better for the general interrupt facility
to hold a private pointer, since the search already must be done anyway at
that level.
Check if rate control structures were allocated before trying to
access them in various places; this was possible before on
allocation failure (unlikely), but was revealed after r342211
where allocation was deferred.
In case if driver uses wlan_amrr(4) and it is loaded it
is possible to reproduce the panic via
sysctl net.wlan.<number>.rate_stats
(for wlan0 the number will be 0).
Tested with: RTL8188EE, AP mode + RTL8188CUS, STA mode.
MFC after: 3 days
When building with KCOV enabled the compiler will insert function calls
to probes allowing us to trace the execution of the kernel from userspace.
These probes are on function entry (trace-pc) and on comparison operations
(trace-cmp).
Userspace can enable the use of these probes on a single kernel thread with
an ioctl interface. It can allocate space for the probe with KIOSETBUFSIZE,
then mmap the allocated buffer and enable tracing with KIOENABLE, with the
trace mode being passed in as the int argument. When complete KIODISABLE
is used to disable tracing.
The first item in the buffer is the number of trace event that have
happened. Userspace can write 0 to this to reset the tracing, and is
expected to do so on first use.
The format of the buffer depends on the trace mode. When in PC tracing just
the return address of the probe is stored. Under comparison tracing the
comparison type, the two arguments, and the return address are traced. The
former method uses on entry per trace event, while the later uses 4. As
such they are incompatible so only a single mode may be enabled.
KCOV is expected to help fuzzing the kernel, and while in development has
already found a number of issues. It is required for the syzkaller system
call fuzzer [1]. Other kernel fuzzers could also make use of it, either
with the current interface, or by extending it with new modes.
A man page is currently being worked on and is expected to be committed
soon, however having the code in the kernel now is useful for other
developers to use.
[1] https://github.com/google/syzkaller
Submitted by: Mitchell Horne <mhorne063@gmail.com> (Earlier version)
Reviewed by: kib
Testing by: tuexen
Sponsored by: DARPA, AFRL
Sponsored by: The FreeBSD Foundation (Mitchell Horne)
Differential Revision: https://reviews.freebsd.org/D14599
Extend the vendor class USB audio quirk to cover devices without
the USB audio control descriptor.
PR: 234794
MFC after: 1 week
Sponsored by: Mellanox Technologies
Issue:
ocs_fc(4) driver panics. It's induced by setting the port_state
sysctl to offline, then online, then offline, then online, and so
forth and so on in rapid succession.
Reason:
While we set the port_state to online fc discovery will start and OS
is enumerating the target discs by calling ocs_action(), then set the
port state to "offline" which deletes domain/sport/nodes.
In ocs_action()->XPT_GET_TRAN_SETTINGS we are accessing the remote
node which can be invalid to get the wwpn, wwnn and port.
Fix:
Removed accessing of remote node and domain in some ocs_action() cases.
Populated the required values from ocs_fcport.
This removes the dependency of node and domain structures while
processing XPT_PATH_INQ and XPT_GET_TRAN_SETTINGS.
We will invalidate the target entries after the device lost
timeout(30 seconds).
Approved by: ken, mav
MFC after: 3 weeks
In cpu_thread_alloc we would allocate space for the trap frame at the top of
the kernel stack. This is just below the pcb, however due to a missing cast
the pointer arithmetic would use the pcb size, not the trapframe size. As
the pcb is larger than the trapframe this is safe, however later in cpu_fork
we include the case leading to the two disagreeing on the location.
Fix by using the same arithmetic in both locations.
Found by: An early KASAN patch
Sponsored by: DARPA, AFRL
UFS will return EINVAL when quotas are not enabled on a filesystem; ZFS'
equivalent involves not having quotas (there is not way to enable or disable
quotas as such). My initial implementation had it return ENOENT, but
quotactl(2) indicates EINVAL is more appropriate.
MFC after: 2 weeks
Approved by: mav
Reviewed by: markj
Reported by: Emrion <kmachine@free.fr>
Sponsored by: iXsystems Inc
PR: https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=234413
CARP shares protocol number 112 with VRRP (RFC 5798). And the size of
VRRP packet may be smaller than CARP. ipfw_chk() does m_pullup() to at
least sizeof(struct carp_header) and can fail when packet is VRRP. This
leads to packet drop and message about failed pullup attempt.
Also, RFC 5798 defines version 3 of VRRP protocol, this version number
also unsupported by CARP and such check leads to packet drop.
carp_input() does its own checks for protocol version and packet size,
so we can remove these checks to be able pass VRRP packets.
PR: 234207
MFC after: 1 week
The code is similar to the one for RTL8188E* and probably
should be shared with RTL8188CE (needs to be tested).
Checked with RTL8188CUS, STA mode.
MFC after: 5 days
And refactor the code to avoid unneeded initialization to reduce overhead
of per-packet processing.
ipfw(4) can be invoked by pfil(9) framework for each packet several times.
Each call uses on-stack variable of type struct ip_fw_args to keep the
state of ipfw(4) processing. Currently this variable has 240 bytes size
on amd64. Each time ipfw(4) does bzero() on it, and then it initializes
some fields.
glebius@ has reported that they at Netflix discovered, that initialization
of this variable produces significant overhead on packet processing.
After patching I managed to increase performance of packet processing on
simple routing with ipfw(4) firewalling to about 11% from 9.8Mpps up to
11Mpps (Xeon E5-2660 v4@ + Mellanox 100G card).
Introduced new field flags, it is used to keep track of what fields was
initialized. Some fields were moved into the anonymous union, to reduce
the size. They all are mutually exclusive. dummypar field was unused, and
therefore it is removed. The hopstore6 field type was changed from
sockaddr_in6 to a bit smaller struct ip_fw_nh6. And now the size of struct
ip_fw_args is 128 bytes.
ipfw_chk() was modified to properly handle ip_fw_args.flags instead of
rely on checking for NULL pointers.
Reviewed by: gallatin
Obtained from: Yandex LLC
MFC after: 1 month
Sponsored by: Yandex LLC
Differential Revision: https://reviews.freebsd.org/D18690
There are several reasons:
- The structure being exported via IFDATA_LINKSPECIFIC doesn't appear
to be a standard MIB.
- The structure being exported is private to the kernel and always
has been.
- No other drivers in common use set the if_linkmib field.
- Because IFDATA_LINKSPECIFIC can be used to overwrite the linkmib
structure, a privileged user could use it to corrupt internal
vlan(4) state. [1]
PR: 219472
Reported by: CTurt <ecturt@gmail.com> [1]
Reviewed by: kp (previous version)
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D18779
The loopback interface can only receive packets with a single scope ID,
namely the scope ID of the loopback interface itself. To mitigate this
packets which use the scope ID are appearing as received by the real
network interface, see "origifp" in the patch. The current code would
drop packets which are designated for loopback which use a link-local
scope ID in the destination address or source address, because they
won't match the lo0's scope ID. To fix this restore the network
interface pointer from the scope ID in the destination address for
the problematic cases. See comments added in patch for a more detailed
description.
This issue was introduced with route caching (ae@).
Reviewed by: bz (network)
Differential Revision: https://reviews.freebsd.org/D18769
MFC after: 1 week
Sponsored by: Mellanox Technologies
if_dead() is called during device detach - check if interface is
still exists before trying to refresh vap MAC address
(IF_LLADDR will trigger page fault otherwise).
MFC after: 5 days
