Merge from head

IFC @ r255209

MFC

Implement the ip, tcp, and udp DTrace providers. The probe definitions use
dynamic translation so that their arguments match the definitions for
these providers in Solaris and illumos. Thus, existing

Implement the ip, tcp, and udp DTrace providers. The probe definitions use
dynamic translation so that their arguments match the definitions for
these providers in Solaris and illumos. Thus, existing scripts for these
providers should work unmodified on FreeBSD.

Tested by: gnn, hiren
MFC after: 1 month

show more ...

IFC @ r254014

IFC @253398

Merge fresh head.

Allow drivers to specify a maximum TSO length in bytes if they are
limited in the amount of data they can handle at once.

Drivers can set ifp->if_hw_tsomax before calling ether_ifattach() to
change

Allow drivers to specify a maximum TSO length in bytes if they are
limited in the amount of data they can handle at once.

Drivers can set ifp->if_hw_tsomax before calling ether_ifattach() to
change the limit.

The lowest allowable size is IP_MAXPACKET / 8 (8192 bytes) as anything
less wouldn't be very useful anymore. The upper limit is still at
IP_MAXPACKET (65536 bytes). Raising it requires further auditing of
the IPv4/v6 code path's as the length field in the IP header would
overflow leading to confusion in firewalls and others packet handler on
the real size of the packet.

The placement into "struct ifnet" is a bit hackish but the best place
that was found. When the stack/driver boundary is updated it should
be handled in a better way.

Submitted by: cperciva (earlier version)
Reviewed by: cperciva
Tested by: cperciva
MFC after: 1 week (using spare struct members to preserve ABI)

show more ...

sync from head

Fix tcp_output() so that tcpcb is updated in the same manner when an
mbuf allocation fails, as in a case when ip_output() returns error.

To achieve that, move large block of code that updates tcpcb

Fix tcp_output() so that tcpcb is updated in the same manner when an
mbuf allocation fails, as in a case when ip_output() returns error.

To achieve that, move large block of code that updates tcpcb below
the out: label.

This fixes a panic, that requires the following sequence to happen:

1) The SYN was sent to the network, tp->snd_nxt = iss + 1, tp->snd_una = iss
2) The retransmit timeout happened for the SYN we had sent,
tcp_timer_rexmt() sets tp->snd_nxt = tp->snd_una, and calls tcp_output().
In tcp_output m_get() fails.
3) Later on the SYN|ACK for the SYN sent in step 1) came,
tcp_input sets tp->snd_una += 1, which leads to
tp->snd_una > tp->snd_nxt inconsistency, that later panics in
socket buffer code.

For reference, this bug fixed in DragonflyBSD repo:

http://gitweb.dragonflybsd.org/dragonfly.git/commitdiff/1ff9b7d322dc5a26f7173aa8c38ecb79da80e419

Reviewed by: andre
Tested by: pho
Sponsored by: Nginx, Inc.
PR: kern/177456
Submitted by: HouYeFei&XiBoLiu <lglion718 163.com>

show more ...

MFC @248461

- Replace compat macros with function calls.

- Use m_getcl() instead of hand allocating.

Sponsored by: Nginx, Inc.

IFC @247348.

Sync with HEAD.

IFC @ r244983.

Mechanically substitute flags from historic mbuf allocator with
malloc(9) flags within sys.

Exceptions:

- sys/contrib not touched
- sys/mbuf.h edited manually

MFC

MFC @ r241285

IFC @ r242940

IFC @ r242684

Fix typo; s/ouput/output

Sync from head

Forced commit to provide the correct commit message to r242251:

Defer sending an independent window update if a delayed ACK is pending
saving a packet. The window update then gets piggy-backed

Forced commit to provide the correct commit message to r242251:

Defer sending an independent window update if a delayed ACK is pending
saving a packet. The window update then gets piggy-backed on the next
already scheduled ACK.

Added grammar fixes as well.

MFC after: 2 weeks

show more ...

Prevent a flurry of forced window updates when an application is
doing small reads on a (partially) filled receive socket buffer.

Normally one would a send a window update every time the available
s

Prevent a flurry of forced window updates when an application is
doing small reads on a (partially) filled receive socket buffer.

Normally one would a send a window update every time the available
space in the socket buffer increases by two times MSS. This leads
to a flurry of window updates that do not provide any meaningful
new information to the sender. There still is available space in
the window and the sender can continue sending data. All window
updates then get carried by the regular ACKs. Only when the socket
buffer was (almost) full and the window closed accordingly a window
updates delivery new information and allows the sender to start
sending more data again.

Send window updates only every two MSS when the socket buffer
has less than 1/8 space available, or the available space in the
socket buffer increased by 1/4 its full capacity, or the socket
buffer is very small. The next regular data ACK will carry and
report the exact window size again.

Reported by: sbruno
Tested by: darrenr
Tested by: Darren Baginski
PR: kern/116335
MFC after: 2 weeks

show more ...