67fd12c0 grog Oct. 23, 2019, 1:11 a.m.
dc2b5bb4 jhibbits Oct. 23, 2019, 12:31 a.m.
r353489 added minidump support for powerpc64, but it added a dependency on
the dump_avail array.  Leaving it uninitialized caused breakage in late
boot.  Initialize dump_avail, even though the 64-bit booke pmap doesn't yet
support minidumps, but will in the future.
cgit ViewVC
a8630f59 jkim Oct. 23, 2019, 12:05 a.m.
Reported by:	danfe
MFC after:	3 days
cgit ViewVC
61b8430f mjg Oct. 22, 2019, 10:55 p.m.
Instead of superpages use. The current code employs superpage-wide locking
regardless and the better locking granularity is welcome with NUMA enabled
even when superpage support is not used.

Requested by:	alc
Sponsored by:	The FreeBSD Foundation
Differential Revision:	https://reviews.freebsd.org/D21982
cgit ViewVC
15e33b54 mjg Oct. 22, 2019, 10:54 p.m.
Similarly to r353438, use dummy entry.

Reported and tested by:	Neel Chauhan
Sponsored by:	The FreeBSD Foundation
cgit ViewVC
2e310f6f mjg Oct. 22, 2019, 10:52 p.m.
Vast majority of uses the cache are just checking if there is an entry
present on process exit (and evicting it if so). Both checking and
eviction process are very expensive and put the lock protecting it high
up on the profile during poudriere -j 104.

Convert the linked list into a hash. This allows to almost always avoid
taking the lock in the first place (and consequently almost removes it
from the profile). Note only one lock is preserved as a split did not
meaningfully impact contention.

Should the cache be used for something it will still run into contention
issues. The code needs a rewrite, but should someone want to tidy it up
further the following can be done:

1) per-chain locks (or at least an array)
2) hashing by something else than just pid

Sponsored by:	The FreeBSD Foundation
cgit ViewVC
e39c9298 mckusick Oct. 22, 2019, 10:23 p.m.
superblock when doing recovery with journalled soft updates.

Reported by:  Chuck Silvers
MFC after:    3 days
Sponsored by: Netflix
cgit ViewVC
c89d4b3c kevans Oct. 22, 2019, 9:46 p.m.
This appears to be a copy-pasto from previous lines that propagated to v6
over the years. Indeed, nothing references kernelstack beyond
USPACE_SVC_STACK_TOP and it would be odd if anything did.

Noticed by:	markj
cgit ViewVC
e38a50e8 jhb Oct. 22, 2019, 8:41 p.m.
NIC KTLS will add a new TLS send tag type in cxgbe(4) that is a
distinct tag from a ratelimit tag.  To support this, refactor
cxgbe_snd_tag to be a simple send tag with a type and convert the
existing ratelimit tag to a new cxgbe_rate_tag structure.

Reviewed by:	np
Sponsored by:	Chelsio Communications
Differential Revision:	https://reviews.freebsd.org/D22072
cgit ViewVC
866a7f28 jhb Oct. 22, 2019, 8:01 p.m.
Previously the table was allocated on first use by TOE and the
ratelimit code.  The forthcoming NIC KTLS code also uses this table.
Allocate it unconditionally during attach to simplify consumers.

Reviewed by:	np
Differential Revision:	https://reviews.freebsd.org/D22028
cgit ViewVC
6dc32306 emaste Oct. 22, 2019, 6:30 p.m.
Xr pfctl instead.

PR:		221069
Submitted by:	"fml"
MFC after:	3 days
cgit ViewVC
f2c7768c luporl Oct. 22, 2019, 6:28 p.m.
On POWER8 systems with only one memory domain, the "ibm,associativity"
number that corresponds to it is 0, unlike POWER9 systems with two
or more domains, in which the minimum value is 1.

In POWER8 case, subtracting 1 causes an underflow on the unsigned domain
variable and a subsequent index out-of-bounds access.

Reviewed by:	jhibbits
Tested by:	bdragon, luporl
cgit ViewVC
080e9496 glebius Oct. 22, 2019, 6:05 p.m.
this will help to avoid panic in this function, since it will also use
some stack, but makes code more strict.

Submitted by:	hselasky
cgit ViewVC
86a994d6 markj Oct. 22, 2019, 5:22 p.m.
Reported by:	Jenkins (hardware CI lab)
MFC after:	1 week
Sponsored by:	The FreeBSD Foundation
cgit ViewVC
24b3b8e2 markj Oct. 22, 2019, 5:21 p.m.
Fix style on the line below.

Reported by:	Jenkins (hardware CI lab)
MFC after:	1 week
Sponsored by:	The FreeBSD Foundation
cgit ViewVC