r345418 avg March 22, 2019, 5:44 p.m.
I overlooked the fact that that VOP_FSYNC() call is not a FreeBSD VFS
call, but a macro that provides an illumos-compatible wrapper for the
FreeBSD operation.

PR:		236475
Reported by:	lwhsu
Pointyhat to:	avg
r345417 mhorne March 22, 2019, 5:37 p.m.
Add an entry for myself (mhorne) to these files.

Approved by:	markj
r345412 cy March 22, 2019, 11:46 a.m.
Reported by:	rgrimes@
MFC after:	13 days
X-MFC with:	r345400
r345411 avg March 22, 2019, 10:38 a.m.
PIIX4_SMBHSTSTAT_ERR can be set for several reasons that, unfortunately,
cannot be distinguished, but the most typical case is a missing or hung
slave (SMB_ENOACK).

PIIX4_SMBHSTSTAT_FAIL means failed or killed / aborted transaction, so
it's previous mapping to SMB_ENOACK was not ideal.

After this change an smb(4) access to a missing slave results in ENXIO
rather than EIO.  To me, that seems to be more appropriate.

MFC after:	3 weeks
r345410 avg March 22, 2019, 9:11 a.m.
PR:		236475
Reported by:	asomers
MFC after:	2 weeks
r345409 kp March 22, 2019, 7:39 a.m.
Verify that pf correctly drops inconsistent ICMP packets (i.e. where the
IP src/dst do not match the IP src/dst in the ICMP packet.
r345408 cperciva March 22, 2019, 6:36 a.m.
Submitted by:	Greg V
Differential Revision:	https://reviews.freebsd.org/D19657
r345407 cperciva March 22, 2019, 6:33 a.m.
This module provides support for the Amazon Elastic Network Adapter; it
was previously only built on x86 architectures, but Amazon EC2 now also
has ARM64 instances with this hardware.

Submitted by:	Greg V
r345406 cperciva March 22, 2019, 6:28 a.m.
This value was being used uninitialized, resulting in predictable issues
on systems with memory-mapped UART registers.

A case could be made that memmap_bus should be declared in a header
rather than being declared in each .c file which needs to refer to it,
but that's a broader style question.

This commit unbreaks hw.uart.console="mm:..." on ARM64.

Submitted by:	Greg V
r345405 cperciva March 22, 2019, 6:21 a.m.
The "access width" value was hard-coded as 2, indicating 32-bit accesses;
instead, use the value specified in the SPCR table.

This unbreaks the console on EC2 "A1" family instances.

Submitted by:	Greg V
r345403 cy March 22, 2019, 1:43 a.m.
by the user.

PR:		218433
MFC after:	2 weeks
X-MFC with:	r345400
r345402 jhibbits March 22, 2019, 1:43 a.m.
By happenstance gcc4 puts 'vpn' into r0 in all uses of TLBIE(), but modern
gcc does not.  Also, the single-argument form of tlbie zeros all unused
arguments, making the modern tlbie instruction use r0 as the RS field

The vpn argument has the bottom 12 bits cleared (the input having been
left-shifted by 12 bits), which just so happens, on the POWER9 and previous
incarnations, to be the number of LPID bits supported.  With those bits
being zero, the instruction:

	tlbie r0, r0

will invalidate the VPN in r0, in LPAR 0 (ignoring the upper bits of r0 for
the RS field).  One build with gcc8 yields:

	tlbie r9, r0

with r0 having arbitrary contents, not equal to r9.  This leads to strange
crashes, behaviors, and panics, due to the requested TLB entry not actually
being invalidated.

As the moea64_native must work on both old and new, we explicitly zero out
r0 so that it can work with only the single argument, built with base gcc
and modern gcc.  isa3_hashtb takes a different approach, encoding the
two-argument form, soas not to explicitly clobber r0, and instead let the
compiler decide.

Reported by:	Brandon Bergren
Tested by:	Brandon Bergren
MFC after:	1 week
r345401 cy March 22, 2019, 1:42 a.m.
PR:		218433
MFC after:	2 weeks
X-MFC with:	r345400
r345400 cy March 22, 2019, 1:30 a.m.
I've been using ippool at my site for approximately two years. It's
about time this was committed.

PR:		218433
MFC after:	2 weeks
r345388 jkim March 21, 2019, 9:45 p.m.