<feed xmlns='http://www.w3.org/2005/Atom'>
<title>passt/iov.h, branch bug209</title>
<subtitle>Plug A Simple Socket Transport</subtitle>
<link rel='alternate' type='text/html' href='https://passt.top/passt/'/>
<entry>
<title>tap: Trim Ethernet padding from short IPv4 frames instead of dropping them</title>
<updated>2026-06-19T11:10:24+00:00</updated>
<author>
<name>David du Colombier</name>
<email>0intro@gmail.com</email>
</author>
<published>2026-06-16T16:37:05+00:00</published>
<link rel='alternate' type='text/html' href='https://passt.top/passt/commit/?id=f072bc07b8251e513823cbb08c69a336187ec56c'/>
<id>f072bc07b8251e513823cbb08c69a336187ec56c</id>
<content type='text'>
tap4_handler() requires the L2 payload after the IP header to match
the IP datagram length exactly. Guests whose drivers pad transmitted
frames to the 60 byte Ethernet minimum, as real hardware requires and
as drivers modelled on hardware do (Plan 9's virtio-net, for one),
send pure ACK and FIN segments as 60 byte frames: 14 byte Ethernet
header, 40 byte IPv4 datagram, 6 padding octets. Those frames fail
the exact length check and are dropped without trace.

passt then never sees such a guest's acknowledgements: it
retransmits from the lowest unacknowledged sequence with exponential
backoff while the guest, which received and acknowledged everything,
waits. Every fresh connection stalls for minutes (a 1 MiB HTTP fetch
over --map-host-loopback measured 248 s before this change, 0.27 s
after; bulk transfer over established connections, whose ACKs ride
data segments above the padding threshold, is unaffected). FIN
segments are padded too, so teardown hangs as well. Note that
tap_send_single() pads passt's own outbound frames to ETH_ZLEN, so
the receive path was already stricter than the send path.

Trim the trailing padding to the IP datagram length instead, using a
new iov_tail_trim() helper, and keep dropping frames genuinely
shorter than the datagram they claim to carry. IPv6 is unaffected:
its minimal TCP frame is 74 bytes, above the padding threshold.

Signed-off-by: David du Colombier &lt;0intro@gmail.com&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
tap4_handler() requires the L2 payload after the IP header to match
the IP datagram length exactly. Guests whose drivers pad transmitted
frames to the 60 byte Ethernet minimum, as real hardware requires and
as drivers modelled on hardware do (Plan 9's virtio-net, for one),
send pure ACK and FIN segments as 60 byte frames: 14 byte Ethernet
header, 40 byte IPv4 datagram, 6 padding octets. Those frames fail
the exact length check and are dropped without trace.

passt then never sees such a guest's acknowledgements: it
retransmits from the lowest unacknowledged sequence with exponential
backoff while the guest, which received and acknowledged everything,
waits. Every fresh connection stalls for minutes (a 1 MiB HTTP fetch
over --map-host-loopback measured 248 s before this change, 0.27 s
after; bulk transfer over established connections, whose ACKs ride
data segments above the padding threshold, is unaffected). FIN
segments are padded too, so teardown hangs as well. Note that
tap_send_single() pads passt's own outbound frames to ETH_ZLEN, so
the receive path was already stricter than the send path.

Trim the trailing padding to the IP datagram length instead, using a
new iov_tail_trim() helper, and keep dropping frames genuinely
shorter than the datagram they claim to carry. IPv6 is unaffected:
its minimal TCP frame is 74 bytes, above the padding threshold.

Signed-off-by: David du Colombier &lt;0intro@gmail.com&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>iov: Introduce IOV_PUSH_HEADER() macro</title>
<updated>2026-05-26T10:17:01+00:00</updated>
<author>
<name>Laurent Vivier</name>
<email>lvivier@redhat.com</email>
</author>
<published>2026-05-20T09:55:25+00:00</published>
<link rel='alternate' type='text/html' href='https://passt.top/passt/commit/?id=9361b6bab7b7e661b1a4a6b4847800e82dad0224'/>
<id>9361b6bab7b7e661b1a4a6b4847800e82dad0224</id>
<content type='text'>
Add iov_push_header_() and its typed wrapper IOV_PUSH_HEADER() to write
a header into an iov_tail at the current offset and advance past it.

This is the write counterpart to IOV_PEEK_HEADER() / IOV_REMOVE_HEADER(),
using iov_from_buf() to copy the header data across iovec boundaries.

Signed-off-by: Laurent Vivier &lt;lvivier@redhat.com&gt;
Reviewed-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add iov_push_header_() and its typed wrapper IOV_PUSH_HEADER() to write
a header into an iov_tail at the current offset and advance past it.

This is the write counterpart to IOV_PEEK_HEADER() / IOV_REMOVE_HEADER(),
using iov_from_buf() to copy the header data across iovec boundaries.

Signed-off-by: Laurent Vivier &lt;lvivier@redhat.com&gt;
Reviewed-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>iov: Add iov_memcpy() to copy data between iovec arrays</title>
<updated>2026-05-19T23:21:09+00:00</updated>
<author>
<name>Laurent Vivier</name>
<email>lvivier@redhat.com</email>
</author>
<published>2026-05-13T11:52:10+00:00</published>
<link rel='alternate' type='text/html' href='https://passt.top/passt/commit/?id=d7259ea24c8aa4908f60d54f4df40bfcb3da6407'/>
<id>d7259ea24c8aa4908f60d54f4df40bfcb3da6407</id>
<content type='text'>
Add a helper to copy data from a source iovec array to a destination
iovec array, each starting at an arbitrary byte offset, iterating
through both arrays simultaneously and copying in chunks matching the
smaller of the two current segments.

Signed-off-by: Laurent Vivier &lt;lvivier@redhat.com&gt;
Reviewed-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Reviewed-by: Jon Maloy &lt;jmaloy@redhat.com&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add a helper to copy data from a source iovec array to a destination
iovec array, each starting at an arbitrary byte offset, iterating
through both arrays simultaneously and copying in chunks matching the
smaller of the two current segments.

Signed-off-by: Laurent Vivier &lt;lvivier@redhat.com&gt;
Reviewed-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Reviewed-by: Jon Maloy &lt;jmaloy@redhat.com&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>iov: Introduce iov_memset()</title>
<updated>2026-05-19T23:21:03+00:00</updated>
<author>
<name>Laurent Vivier</name>
<email>lvivier@redhat.com</email>
</author>
<published>2026-05-13T11:52:09+00:00</published>
<link rel='alternate' type='text/html' href='https://passt.top/passt/commit/?id=a804574bc42c73915944b38ef638f667067bbf8c'/>
<id>a804574bc42c73915944b38ef638f667067bbf8c</id>
<content type='text'>
Add a helper to set a range of bytes across an IO vector to a given
value, similar to memset() but operating over scatter-gather buffers.
It skips to the given offset and fills across iovec entries up to the
requested length.

Signed-off-by: Laurent Vivier &lt;lvivier@redhat.com&gt;
Reviewed-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Reviewed-by: Jon Maloy &lt;jmaloy@redhat.com&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add a helper to set a range of bytes across an IO vector to a given
value, similar to memset() but operating over scatter-gather buffers.
It skips to the given offset and fills across iovec entries up to the
requested length.

Signed-off-by: Laurent Vivier &lt;lvivier@redhat.com&gt;
Reviewed-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Reviewed-by: Jon Maloy &lt;jmaloy@redhat.com&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>iov: Add iov_truncate() helper and use it in vu handlers</title>
<updated>2026-03-10T14:26:43+00:00</updated>
<author>
<name>Laurent Vivier</name>
<email>lvivier@redhat.com</email>
</author>
<published>2026-03-06T11:51:19+00:00</published>
<link rel='alternate' type='text/html' href='https://passt.top/passt/commit/?id=045560c20a45a452ca1ed79b15fb01d9da5421e4'/>
<id>045560c20a45a452ca1ed79b15fb01d9da5421e4</id>
<content type='text'>
Add a generic iov_truncate() function that truncates an IO vector to a
given number of bytes, returning the number of iov entries that contain
data after truncation.

Use it in udp_vu_sock_recv() and tcp_vu_sock_recv() to replace the
open-coded truncation logic that adjusted iov entries after recvmsg().
Also convert the direct iov_len assignment in tcp_vu_send_flag() to use
iov_truncate() for consistency.

Add an ASSERT() in tcp_vu_data_from_sock() to quiet the Coverity error:

passt/tcp_vu.c:457:3:
  19. overflow_const: Expression "dlen + hdrlen", where "dlen" is known to
      be equal to -86,  and "hdrlen" is known to be equal to 86, underflows
      the type of "dlen + hdrlen", which is type "unsigned long".

Signed-off-by: Laurent Vivier &lt;lvivier@redhat.com&gt;
Reviewed-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add a generic iov_truncate() function that truncates an IO vector to a
given number of bytes, returning the number of iov entries that contain
data after truncation.

Use it in udp_vu_sock_recv() and tcp_vu_sock_recv() to replace the
open-coded truncation logic that adjusted iov entries after recvmsg().
Also convert the direct iov_len assignment in tcp_vu_send_flag() to use
iov_truncate() for consistency.

Add an ASSERT() in tcp_vu_data_from_sock() to quiet the Coverity error:

passt/tcp_vu.c:457:3:
  19. overflow_const: Expression "dlen + hdrlen", where "dlen" is known to
      be equal to -86,  and "hdrlen" is known to be equal to 86, underflows
      the type of "dlen + hdrlen", which is type "unsigned long".

Signed-off-by: Laurent Vivier &lt;lvivier@redhat.com&gt;
Reviewed-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Add missing includes to headers</title>
<updated>2026-03-04T16:39:57+00:00</updated>
<author>
<name>Peter Foley</name>
<email>pefoley@google.com</email>
</author>
<published>2026-02-23T18:11:19+00:00</published>
<link rel='alternate' type='text/html' href='https://passt.top/passt/commit/?id=adbf5c135f19db5b6751393b7f5cbf516031bde8'/>
<id>adbf5c135f19db5b6751393b7f5cbf516031bde8</id>
<content type='text'>
Support build systems like bazel that check that headers are
self-contained.

Also update includes so that clang-include-cleaner succeeds.

Tested with:
clang-include-cleaner-19 --extra-arg=-D_GNU_SOURCE --extra-arg=-DPAGE_SIZE=4096 --extra-arg=-DVERSION=\"git\" --extra-arg=-DHAS_GETRANDOM *.h *.c

Signed-off-by: Peter Foley &lt;pefoley@google.com&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Support build systems like bazel that check that headers are
self-contained.

Also update includes so that clang-include-cleaner succeeds.

Tested with:
clang-include-cleaner-19 --extra-arg=-D_GNU_SOURCE --extra-arg=-DPAGE_SIZE=4096 --extra-arg=-DVERSION=\"git\" --extra-arg=-DHAS_GETRANDOM *.h *.c

Signed-off-by: Peter Foley &lt;pefoley@google.com&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>treewide: Fix places where we incorrectly indented with spaces</title>
<updated>2026-01-11T00:31:50+00:00</updated>
<author>
<name>David Gibson</name>
<email>david@gibson.dropbear.id.au</email>
</author>
<published>2026-01-09T04:09:22+00:00</published>
<link rel='alternate' type='text/html' href='https://passt.top/passt/commit/?id=b973f4a6cc50571f8375c60a7e511a77bcf5c202'/>
<id>b973f4a6cc50571f8375c60a7e511a77bcf5c202</id>
<content type='text'>
Had a moment to address this trivial issue.

The passt convention is to indent code with tabs (K&amp;R / kernel style).
However there were a handful of places where we used spaces instead.  Fix
them.

Link: https://bugs.passt.top/show_bug.cgi?id=135
Reported-by: Xun Gu &lt;xugu@redhat.com&gt;
Signed-off-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Had a moment to address this trivial issue.

The passt convention is to indent code with tabs (K&amp;R / kernel style).
However there were a handful of places where we used spaces instead.  Fix
them.

Link: https://bugs.passt.top/show_bug.cgi?id=135
Reported-by: Xun Gu &lt;xugu@redhat.com&gt;
Signed-off-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>tap: Use iov_tail with tap_add_packet()</title>
<updated>2025-09-03T18:42:20+00:00</updated>
<author>
<name>Laurent Vivier</name>
<email>lvivier@redhat.com</email>
</author>
<published>2025-09-02T07:52:27+00:00</published>
<link rel='alternate' type='text/html' href='https://passt.top/passt/commit/?id=720d8fc06946bef73ddb042c431a0c71bd6cf409'/>
<id>720d8fc06946bef73ddb042c431a0c71bd6cf409</id>
<content type='text'>
Use IOV_PEEK_HEADER() to get the ethernet header from the iovec.

Move the workaround about multiple iovec array from vu_handle_tx() to
tap_add_packet(). Removing the offset out of the iovec array should
reduce the iovec count to 1.

Signed-off-by: Laurent Vivier &lt;lvivier@redhat.com&gt;
Reviewed-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Use IOV_PEEK_HEADER() to get the ethernet header from the iovec.

Move the workaround about multiple iovec array from vu_handle_tx() to
tap_add_packet(). Removing the offset out of the iovec array should
reduce the iovec count to 1.

Signed-off-by: Laurent Vivier &lt;lvivier@redhat.com&gt;
Reviewed-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>iov: Update IOV_REMOVE_HEADER() and IOV_PEEK_HEADER()</title>
<updated>2025-09-03T18:42:17+00:00</updated>
<author>
<name>Laurent Vivier</name>
<email>lvivier@redhat.com</email>
</author>
<published>2025-09-02T07:52:26+00:00</published>
<link rel='alternate' type='text/html' href='https://passt.top/passt/commit/?id=70b9c0c0a2281fe332692283e4b4edd1f6db092c'/>
<id>70b9c0c0a2281fe332692283e4b4edd1f6db092c</id>
<content type='text'>
Provide a temporary variable of the wanted type to store
the header if the memory in the iovec array is not contiguous.

Signed-off-by: Laurent Vivier &lt;lvivier@redhat.com&gt;
Reviewed-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Provide a temporary variable of the wanted type to store
the header if the memory in the iovec array is not contiguous.

Signed-off-by: Laurent Vivier &lt;lvivier@redhat.com&gt;
Reviewed-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>iov: Introduce iov_tail_clone() and iov_drop_header().</title>
<updated>2025-09-03T18:42:15+00:00</updated>
<author>
<name>Laurent Vivier</name>
<email>lvivier@redhat.com</email>
</author>
<published>2025-09-02T07:52:25+00:00</published>
<link rel='alternate' type='text/html' href='https://passt.top/passt/commit/?id=066e6b1dc52a5f37feb6915fbda080eb29e042f3'/>
<id>066e6b1dc52a5f37feb6915fbda080eb29e042f3</id>
<content type='text'>
These utilities enhance iov_tail manipulation, useful for
efficient packet processing by enabling iovec array cloning and
header stripping without data copies.

- iov_drop_header(): Discards a specified number of bytes from the
  beginning of an iov_tail by advancing its internal offset and pruning
  consumed elements.

- iov_tail_clone(): Clone an iov_tail into an iovec array, adjusting the
first iovec entry to remove the iov_tail offset.

Signed-off-by: Laurent Vivier &lt;lvivier@redhat.com&gt;
Reviewed-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
These utilities enhance iov_tail manipulation, useful for
efficient packet processing by enabling iovec array cloning and
header stripping without data copies.

- iov_drop_header(): Discards a specified number of bytes from the
  beginning of an iov_tail by advancing its internal offset and pruning
  consumed elements.

- iov_tail_clone(): Clone an iov_tail into an iovec array, adjusting the
first iovec entry to remove the iov_tail offset.

Signed-off-by: Laurent Vivier &lt;lvivier@redhat.com&gt;
Reviewed-by: David Gibson &lt;david@gibson.dropbear.id.au&gt;
Signed-off-by: Stefano Brivio &lt;sbrivio@redhat.com&gt;
</pre>
</div>
</content>
</entry>
</feed>
