mcx(4): enforce full-duplex mark in mcx_media_status(), when link is up.

LACP protocol requires full-duplex to be enabled for lagg(4) to work,
however mcx(4) was not setting this capability making it to fail.

Fixes PR kern/58124. OK'd by msaitoh@

mcx(4): Add Mellanox ConnectX-6 Lx from OpenBSD.

branches: 1.25.4;
Empty if_watchdog functions are useless and now waste resources. Let's
remove them.

Trailing whitespace

mcx(4): ensure that RQT size is always a power of two.
Fixes PR kern/56484.
Thanks riastradh for the power of two patch :). OK: mrg, jmcneill, riastradh.

Enable checksum offload features by default.

We are not mapping registers prefetchable so no need for explicit bs
barriers.

Sync with OpenBSD r1.101:

When processing a received packet, only sync the amount of bytes
mcx(4) told us has arrived. The DMA map's mapsize on RX packets
is the length of the allocated buffer. For mcx(4), this can be
more than around 9000 bytes, as each buffer will be at least as
big as the maximum supported MTU. There's no need to sync the
whole buffer, if it's only a small packet.

Use coherent DMA mappings when possible.

s/structres/structures + s/whenver/whenever

branches: 1.17.4;
Sync with OpenBSD r1.99:

move the rearming of the cq after the refill of the rq.

this is the only real diff we have left outstanding on a box that
experienced rx lockups. since adding this change it's been happy
for the last 4 weeks and counting so far.

mcx: Add if_transmit callback to enable more than one tx queue

Sync with OpenBSD r1.98. Lots of improvements including checksum offload,
hardware vlan tagging, and support for multiple receive queues.

branches: 1.14.2;
Add __KERNEL_RCSID

mcx: sync with OpenBSD sys/dev/pci/if_mcx.c r1.44

1.44:
Fix typo which could lead into a double free

1.43:
Commands that create objects return a 24 bit object ID, so mask off the
high 8 bits of the value we extract, in case the firmware leaves junk there.
Hrvoje Popovski has seen this with newer firmware on a ConnectX 5 card,
which now works properly.

1.42:
Increase the completion queue size to prevent overflow. Under reasonably
unlikely circumstances - lots of single-fragment packets being sent, a
significant number of packets being received, while the interrupt handler
was unable to process the completion queue - the completion queue could
overflow, which would result in the interface locking up.

1.41:
Check if we've reached the end of the current mailbox before writing past
the end of it, rather than after. Now we can actually allocate queues
big enough to need multiple mailboxes.

1.40:
Don't call mcx_intr() from mcx_cmdq_poll(); this was a leftover from early
development that I forgot about, but turns out to be a potential race with
the actual interrupt handler.

1.39:
fix previous: use the correct offset for sq/rq creation, and don't
reset the mbox counter to 0 after calculating it.

1.38:
Add a helper function for writing physical addresses for queues into
command queue mailboxes, and use this for all queue setup commands.
Previously we just assumed the addresses would fit in the first mailbox,
which is currently true but may not be for much longer.

1.37:
(skipped)

1.36:
The event queue consumer counter also needs to be unsigned like the others.

1.35:
try to make if_baudrate look plausible.
this updates the eth proto capability map so it records the baudrate
against the different link types and their media, and then reads
it when the link state changes.

1.34:
(skipped)

branches: 1.12.2; 1.12.4;
Define and implement a locking protocol for the ifmedia / mii layers:
- MP-safe drivers provide a mutex to ifmedia that is used to serialize
access to media-related structures / hardware regsiters. Converted
drivers use the new ifmedia_init_with_lock() function for this. The
new name is provided to ease the transition.
- Un-converted drivers continue to call ifmedia_init(), which will supply
a compatibility lock to be used instead. Several media-related entry
points must be aware of this compatibility lock, and are able to acquire
it recursively a limited number of times, if needed. This is a SPIN
mutex with priority IPL_NET.
- This same lock is used to serialize access to PHY registers and other
MII-related data structures.

The PHY drivers are modified to acquire and release the lock, as needed,
and assert the lock is held as a diagnostic aid.

The "usbnet" framework has had an overhaul of its internal locking
protocols to fit in with the media / mii changes, and the drivers adapted.

USB wifi drivers have been changed to provide their own adaptive mutex
to the ifmedia later via a new ieee80211_media_init_with_lock() function.
This is required because the USB drivers need an adaptive mutex.

Besised "usbnet", a few other drivers are converted: vmx, wm, ixgbe / ixv.

mcx also now calls ifmedia_init_with_lock() because it needs to also use
an adaptive mutex. The mcx driver still needs to be fully converted to
NET_MPSAFE.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

mcx(4): Add Mellanox ConnectX-6 Lx from OpenBSD.

Empty if_watchdog functions are useless and now waste resources. Let's
remove them.

Trailing whitespace

mcx(4): ensure that RQT size is always a power of two.
Fixes PR kern/56484.
Thanks riastradh for the power of two patch :). OK: mrg, jmcneill, riastradh.

Enable checksum offload features by default.

We are not mapping registers prefetchable so no need for explicit bs
barriers.

Sync with OpenBSD r1.101:

When processing a received packet, only sync the amount of bytes
mcx(4) told us has arrived. The DMA map's mapsize on RX packets
is the length of the allocated buffer. For mcx(4), this can be
more than around 9000 bytes, as each buffer will be at least as
big as the maximum supported MTU. There's no need to sync the
whole buffer, if it's only a small packet.

Use coherent DMA mappings when possible.

s/structres/structures + s/whenver/whenever

branches: 1.17.4;
Sync with OpenBSD r1.99:

move the rearming of the cq after the refill of the rq.

this is the only real diff we have left outstanding on a box that
experienced rx lockups. since adding this change it's been happy
for the last 4 weeks and counting so far.

mcx: Add if_transmit callback to enable more than one tx queue

Sync with OpenBSD r1.98. Lots of improvements including checksum offload,
hardware vlan tagging, and support for multiple receive queues.

branches: 1.14.2;
Add __KERNEL_RCSID

mcx: sync with OpenBSD sys/dev/pci/if_mcx.c r1.44

1.44:
Fix typo which could lead into a double free

1.43:
Commands that create objects return a 24 bit object ID, so mask off the
high 8 bits of the value we extract, in case the firmware leaves junk there.
Hrvoje Popovski has seen this with newer firmware on a ConnectX 5 card,
which now works properly.

1.42:
Increase the completion queue size to prevent overflow. Under reasonably
unlikely circumstances - lots of single-fragment packets being sent, a
significant number of packets being received, while the interrupt handler
was unable to process the completion queue - the completion queue could
overflow, which would result in the interface locking up.

1.41:
Check if we've reached the end of the current mailbox before writing past
the end of it, rather than after. Now we can actually allocate queues
big enough to need multiple mailboxes.

1.40:
Don't call mcx_intr() from mcx_cmdq_poll(); this was a leftover from early
development that I forgot about, but turns out to be a potential race with
the actual interrupt handler.

1.39:
fix previous: use the correct offset for sq/rq creation, and don't
reset the mbox counter to 0 after calculating it.

1.38:
Add a helper function for writing physical addresses for queues into
command queue mailboxes, and use this for all queue setup commands.
Previously we just assumed the addresses would fit in the first mailbox,
which is currently true but may not be for much longer.

1.37:
(skipped)

1.36:
The event queue consumer counter also needs to be unsigned like the others.

1.35:
try to make if_baudrate look plausible.
this updates the eth proto capability map so it records the baudrate
against the different link types and their media, and then reads
it when the link state changes.

1.34:
(skipped)

branches: 1.12.2; 1.12.4;
Define and implement a locking protocol for the ifmedia / mii layers:
- MP-safe drivers provide a mutex to ifmedia that is used to serialize
access to media-related structures / hardware regsiters. Converted
drivers use the new ifmedia_init_with_lock() function for this. The
new name is provided to ease the transition.
- Un-converted drivers continue to call ifmedia_init(), which will supply
a compatibility lock to be used instead. Several media-related entry
points must be aware of this compatibility lock, and are able to acquire
it recursively a limited number of times, if needed. This is a SPIN
mutex with priority IPL_NET.
- This same lock is used to serialize access to PHY registers and other
MII-related data structures.

The PHY drivers are modified to acquire and release the lock, as needed,
and assert the lock is held as a diagnostic aid.

The "usbnet" framework has had an overhaul of its internal locking
protocols to fit in with the media / mii changes, and the drivers adapted.

USB wifi drivers have been changed to provide their own adaptive mutex
to the ifmedia later via a new ieee80211_media_init_with_lock() function.
This is required because the USB drivers need an adaptive mutex.

Besised "usbnet", a few other drivers are converted: vmx, wm, ixgbe / ixv.

mcx also now calls ifmedia_init_with_lock() because it needs to also use
an adaptive mutex. The mcx driver still needs to be fully converted to
NET_MPSAFE.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Empty if_watchdog functions are useless and now waste resources. Let's
remove them.

Trailing whitespace

mcx(4): ensure that RQT size is always a power of two.
Fixes PR kern/56484.
Thanks riastradh for the power of two patch :). OK: mrg, jmcneill, riastradh.

Enable checksum offload features by default.

We are not mapping registers prefetchable so no need for explicit bs
barriers.

Sync with OpenBSD r1.101:

When processing a received packet, only sync the amount of bytes
mcx(4) told us has arrived. The DMA map's mapsize on RX packets
is the length of the allocated buffer. For mcx(4), this can be
more than around 9000 bytes, as each buffer will be at least as
big as the maximum supported MTU. There's no need to sync the
whole buffer, if it's only a small packet.

Use coherent DMA mappings when possible.

s/structres/structures + s/whenver/whenever

branches: 1.17.4;
Sync with OpenBSD r1.99:

move the rearming of the cq after the refill of the rq.

this is the only real diff we have left outstanding on a box that
experienced rx lockups. since adding this change it's been happy
for the last 4 weeks and counting so far.

mcx: Add if_transmit callback to enable more than one tx queue

Sync with OpenBSD r1.98. Lots of improvements including checksum offload,
hardware vlan tagging, and support for multiple receive queues.

branches: 1.14.2;
Add __KERNEL_RCSID

mcx: sync with OpenBSD sys/dev/pci/if_mcx.c r1.44

1.44:
Fix typo which could lead into a double free

1.43:
Commands that create objects return a 24 bit object ID, so mask off the
high 8 bits of the value we extract, in case the firmware leaves junk there.
Hrvoje Popovski has seen this with newer firmware on a ConnectX 5 card,
which now works properly.

1.42:
Increase the completion queue size to prevent overflow. Under reasonably
unlikely circumstances - lots of single-fragment packets being sent, a
significant number of packets being received, while the interrupt handler
was unable to process the completion queue - the completion queue could
overflow, which would result in the interface locking up.

1.41:
Check if we've reached the end of the current mailbox before writing past
the end of it, rather than after. Now we can actually allocate queues
big enough to need multiple mailboxes.

1.40:
Don't call mcx_intr() from mcx_cmdq_poll(); this was a leftover from early
development that I forgot about, but turns out to be a potential race with
the actual interrupt handler.

1.39:
fix previous: use the correct offset for sq/rq creation, and don't
reset the mbox counter to 0 after calculating it.

1.38:
Add a helper function for writing physical addresses for queues into
command queue mailboxes, and use this for all queue setup commands.
Previously we just assumed the addresses would fit in the first mailbox,
which is currently true but may not be for much longer.

1.37:
(skipped)

1.36:
The event queue consumer counter also needs to be unsigned like the others.

1.35:
try to make if_baudrate look plausible.
this updates the eth proto capability map so it records the baudrate
against the different link types and their media, and then reads
it when the link state changes.

1.34:
(skipped)

branches: 1.12.2; 1.12.4;
Define and implement a locking protocol for the ifmedia / mii layers:
- MP-safe drivers provide a mutex to ifmedia that is used to serialize
access to media-related structures / hardware regsiters. Converted
drivers use the new ifmedia_init_with_lock() function for this. The
new name is provided to ease the transition.
- Un-converted drivers continue to call ifmedia_init(), which will supply
a compatibility lock to be used instead. Several media-related entry
points must be aware of this compatibility lock, and are able to acquire
it recursively a limited number of times, if needed. This is a SPIN
mutex with priority IPL_NET.
- This same lock is used to serialize access to PHY registers and other
MII-related data structures.

The PHY drivers are modified to acquire and release the lock, as needed,
and assert the lock is held as a diagnostic aid.

The "usbnet" framework has had an overhaul of its internal locking
protocols to fit in with the media / mii changes, and the drivers adapted.

USB wifi drivers have been changed to provide their own adaptive mutex
to the ifmedia later via a new ieee80211_media_init_with_lock() function.
This is required because the USB drivers need an adaptive mutex.

Besised "usbnet", a few other drivers are converted: vmx, wm, ixgbe / ixv.

mcx also now calls ifmedia_init_with_lock() because it needs to also use
an adaptive mutex. The mcx driver still needs to be fully converted to
NET_MPSAFE.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Trailing whitespace

mcx(4): ensure that RQT size is always a power of two.
Fixes PR kern/56484.
Thanks riastradh for the power of two patch :). OK: mrg, jmcneill, riastradh.

Enable checksum offload features by default.

We are not mapping registers prefetchable so no need for explicit bs
barriers.

Sync with OpenBSD r1.101:

When processing a received packet, only sync the amount of bytes
mcx(4) told us has arrived. The DMA map's mapsize on RX packets
is the length of the allocated buffer. For mcx(4), this can be
more than around 9000 bytes, as each buffer will be at least as
big as the maximum supported MTU. There's no need to sync the
whole buffer, if it's only a small packet.

Use coherent DMA mappings when possible.

s/structres/structures + s/whenver/whenever

branches: 1.17.4;
Sync with OpenBSD r1.99:

move the rearming of the cq after the refill of the rq.

this is the only real diff we have left outstanding on a box that
experienced rx lockups. since adding this change it's been happy
for the last 4 weeks and counting so far.

mcx: Add if_transmit callback to enable more than one tx queue

Sync with OpenBSD r1.98. Lots of improvements including checksum offload,
hardware vlan tagging, and support for multiple receive queues.

branches: 1.14.2;
Add __KERNEL_RCSID

mcx: sync with OpenBSD sys/dev/pci/if_mcx.c r1.44

1.44:
Fix typo which could lead into a double free

1.43:
Commands that create objects return a 24 bit object ID, so mask off the
high 8 bits of the value we extract, in case the firmware leaves junk there.
Hrvoje Popovski has seen this with newer firmware on a ConnectX 5 card,
which now works properly.

1.42:
Increase the completion queue size to prevent overflow. Under reasonably
unlikely circumstances - lots of single-fragment packets being sent, a
significant number of packets being received, while the interrupt handler
was unable to process the completion queue - the completion queue could
overflow, which would result in the interface locking up.

1.41:
Check if we've reached the end of the current mailbox before writing past
the end of it, rather than after. Now we can actually allocate queues
big enough to need multiple mailboxes.

1.40:
Don't call mcx_intr() from mcx_cmdq_poll(); this was a leftover from early
development that I forgot about, but turns out to be a potential race with
the actual interrupt handler.

1.39:
fix previous: use the correct offset for sq/rq creation, and don't
reset the mbox counter to 0 after calculating it.

1.38:
Add a helper function for writing physical addresses for queues into
command queue mailboxes, and use this for all queue setup commands.
Previously we just assumed the addresses would fit in the first mailbox,
which is currently true but may not be for much longer.

1.37:
(skipped)

1.36:
The event queue consumer counter also needs to be unsigned like the others.

1.35:
try to make if_baudrate look plausible.
this updates the eth proto capability map so it records the baudrate
against the different link types and their media, and then reads
it when the link state changes.

1.34:
(skipped)

branches: 1.12.2; 1.12.4;
Define and implement a locking protocol for the ifmedia / mii layers:
- MP-safe drivers provide a mutex to ifmedia that is used to serialize
access to media-related structures / hardware regsiters. Converted
drivers use the new ifmedia_init_with_lock() function for this. The
new name is provided to ease the transition.
- Un-converted drivers continue to call ifmedia_init(), which will supply
a compatibility lock to be used instead. Several media-related entry
points must be aware of this compatibility lock, and are able to acquire
it recursively a limited number of times, if needed. This is a SPIN
mutex with priority IPL_NET.
- This same lock is used to serialize access to PHY registers and other
MII-related data structures.

The PHY drivers are modified to acquire and release the lock, as needed,
and assert the lock is held as a diagnostic aid.

The "usbnet" framework has had an overhaul of its internal locking
protocols to fit in with the media / mii changes, and the drivers adapted.

USB wifi drivers have been changed to provide their own adaptive mutex
to the ifmedia later via a new ieee80211_media_init_with_lock() function.
This is required because the USB drivers need an adaptive mutex.

Besised "usbnet", a few other drivers are converted: vmx, wm, ixgbe / ixv.

mcx also now calls ifmedia_init_with_lock() because it needs to also use
an adaptive mutex. The mcx driver still needs to be fully converted to
NET_MPSAFE.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

mcx(4): ensure that RQT size is always a power of two.
Fixes PR kern/56484.
Thanks riastradh for the power of two patch :). OK: mrg, jmcneill, riastradh.

Enable checksum offload features by default.

We are not mapping registers prefetchable so no need for explicit bs
barriers.

Sync with OpenBSD r1.101:

When processing a received packet, only sync the amount of bytes
mcx(4) told us has arrived. The DMA map's mapsize on RX packets
is the length of the allocated buffer. For mcx(4), this can be
more than around 9000 bytes, as each buffer will be at least as
big as the maximum supported MTU. There's no need to sync the
whole buffer, if it's only a small packet.

Use coherent DMA mappings when possible.

s/structres/structures + s/whenver/whenever

branches: 1.17.4;
Sync with OpenBSD r1.99:

move the rearming of the cq after the refill of the rq.

this is the only real diff we have left outstanding on a box that
experienced rx lockups. since adding this change it's been happy
for the last 4 weeks and counting so far.

mcx: Add if_transmit callback to enable more than one tx queue

Sync with OpenBSD r1.98. Lots of improvements including checksum offload,
hardware vlan tagging, and support for multiple receive queues.

branches: 1.14.2;
Add __KERNEL_RCSID

mcx: sync with OpenBSD sys/dev/pci/if_mcx.c r1.44

1.44:
Fix typo which could lead into a double free

1.43:
Commands that create objects return a 24 bit object ID, so mask off the
high 8 bits of the value we extract, in case the firmware leaves junk there.
Hrvoje Popovski has seen this with newer firmware on a ConnectX 5 card,
which now works properly.

1.42:
Increase the completion queue size to prevent overflow. Under reasonably
unlikely circumstances - lots of single-fragment packets being sent, a
significant number of packets being received, while the interrupt handler
was unable to process the completion queue - the completion queue could
overflow, which would result in the interface locking up.

1.41:
Check if we've reached the end of the current mailbox before writing past
the end of it, rather than after. Now we can actually allocate queues
big enough to need multiple mailboxes.

1.40:
Don't call mcx_intr() from mcx_cmdq_poll(); this was a leftover from early
development that I forgot about, but turns out to be a potential race with
the actual interrupt handler.

1.39:
fix previous: use the correct offset for sq/rq creation, and don't
reset the mbox counter to 0 after calculating it.

1.38:
Add a helper function for writing physical addresses for queues into
command queue mailboxes, and use this for all queue setup commands.
Previously we just assumed the addresses would fit in the first mailbox,
which is currently true but may not be for much longer.

1.37:
(skipped)

1.36:
The event queue consumer counter also needs to be unsigned like the others.

1.35:
try to make if_baudrate look plausible.
this updates the eth proto capability map so it records the baudrate
against the different link types and their media, and then reads
it when the link state changes.

1.34:
(skipped)

branches: 1.12.2; 1.12.4;
Define and implement a locking protocol for the ifmedia / mii layers:
- MP-safe drivers provide a mutex to ifmedia that is used to serialize
access to media-related structures / hardware regsiters. Converted
drivers use the new ifmedia_init_with_lock() function for this. The
new name is provided to ease the transition.
- Un-converted drivers continue to call ifmedia_init(), which will supply
a compatibility lock to be used instead. Several media-related entry
points must be aware of this compatibility lock, and are able to acquire
it recursively a limited number of times, if needed. This is a SPIN
mutex with priority IPL_NET.
- This same lock is used to serialize access to PHY registers and other
MII-related data structures.

The PHY drivers are modified to acquire and release the lock, as needed,
and assert the lock is held as a diagnostic aid.

The "usbnet" framework has had an overhaul of its internal locking
protocols to fit in with the media / mii changes, and the drivers adapted.

USB wifi drivers have been changed to provide their own adaptive mutex
to the ifmedia later via a new ieee80211_media_init_with_lock() function.
This is required because the USB drivers need an adaptive mutex.

Besised "usbnet", a few other drivers are converted: vmx, wm, ixgbe / ixv.

mcx also now calls ifmedia_init_with_lock() because it needs to also use
an adaptive mutex. The mcx driver still needs to be fully converted to
NET_MPSAFE.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Enable checksum offload features by default.

We are not mapping registers prefetchable so no need for explicit bs
barriers.

Sync with OpenBSD r1.101:

When processing a received packet, only sync the amount of bytes
mcx(4) told us has arrived. The DMA map's mapsize on RX packets
is the length of the allocated buffer. For mcx(4), this can be
more than around 9000 bytes, as each buffer will be at least as
big as the maximum supported MTU. There's no need to sync the
whole buffer, if it's only a small packet.

Use coherent DMA mappings when possible.

s/structres/structures + s/whenver/whenever

branches: 1.17.4;
Sync with OpenBSD r1.99:

move the rearming of the cq after the refill of the rq.

this is the only real diff we have left outstanding on a box that
experienced rx lockups. since adding this change it's been happy
for the last 4 weeks and counting so far.

mcx: Add if_transmit callback to enable more than one tx queue

Sync with OpenBSD r1.98. Lots of improvements including checksum offload,
hardware vlan tagging, and support for multiple receive queues.

branches: 1.14.2;
Add __KERNEL_RCSID

mcx: sync with OpenBSD sys/dev/pci/if_mcx.c r1.44

1.44:
Fix typo which could lead into a double free

1.43:
Commands that create objects return a 24 bit object ID, so mask off the
high 8 bits of the value we extract, in case the firmware leaves junk there.
Hrvoje Popovski has seen this with newer firmware on a ConnectX 5 card,
which now works properly.

1.42:
Increase the completion queue size to prevent overflow. Under reasonably
unlikely circumstances - lots of single-fragment packets being sent, a
significant number of packets being received, while the interrupt handler
was unable to process the completion queue - the completion queue could
overflow, which would result in the interface locking up.

1.41:
Check if we've reached the end of the current mailbox before writing past
the end of it, rather than after. Now we can actually allocate queues
big enough to need multiple mailboxes.

1.40:
Don't call mcx_intr() from mcx_cmdq_poll(); this was a leftover from early
development that I forgot about, but turns out to be a potential race with
the actual interrupt handler.

1.39:
fix previous: use the correct offset for sq/rq creation, and don't
reset the mbox counter to 0 after calculating it.

1.38:
Add a helper function for writing physical addresses for queues into
command queue mailboxes, and use this for all queue setup commands.
Previously we just assumed the addresses would fit in the first mailbox,
which is currently true but may not be for much longer.

1.37:
(skipped)

1.36:
The event queue consumer counter also needs to be unsigned like the others.

1.35:
try to make if_baudrate look plausible.
this updates the eth proto capability map so it records the baudrate
against the different link types and their media, and then reads
it when the link state changes.

1.34:
(skipped)

branches: 1.12.2; 1.12.4;
Define and implement a locking protocol for the ifmedia / mii layers:
- MP-safe drivers provide a mutex to ifmedia that is used to serialize
access to media-related structures / hardware regsiters. Converted
drivers use the new ifmedia_init_with_lock() function for this. The
new name is provided to ease the transition.
- Un-converted drivers continue to call ifmedia_init(), which will supply
a compatibility lock to be used instead. Several media-related entry
points must be aware of this compatibility lock, and are able to acquire
it recursively a limited number of times, if needed. This is a SPIN
mutex with priority IPL_NET.
- This same lock is used to serialize access to PHY registers and other
MII-related data structures.

The PHY drivers are modified to acquire and release the lock, as needed,
and assert the lock is held as a diagnostic aid.

The "usbnet" framework has had an overhaul of its internal locking
protocols to fit in with the media / mii changes, and the drivers adapted.

USB wifi drivers have been changed to provide their own adaptive mutex
to the ifmedia later via a new ieee80211_media_init_with_lock() function.
This is required because the USB drivers need an adaptive mutex.

Besised "usbnet", a few other drivers are converted: vmx, wm, ixgbe / ixv.

mcx also now calls ifmedia_init_with_lock() because it needs to also use
an adaptive mutex. The mcx driver still needs to be fully converted to
NET_MPSAFE.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Sync with OpenBSD r1.101:

When processing a received packet, only sync the amount of bytes
mcx(4) told us has arrived. The DMA map's mapsize on RX packets
is the length of the allocated buffer. For mcx(4), this can be
more than around 9000 bytes, as each buffer will be at least as
big as the maximum supported MTU. There's no need to sync the
whole buffer, if it's only a small packet.

Use coherent DMA mappings when possible.

s/structres/structures + s/whenver/whenever

branches: 1.17.4;
Sync with OpenBSD r1.99:

move the rearming of the cq after the refill of the rq.

this is the only real diff we have left outstanding on a box that
experienced rx lockups. since adding this change it's been happy
for the last 4 weeks and counting so far.

mcx: Add if_transmit callback to enable more than one tx queue

Sync with OpenBSD r1.98. Lots of improvements including checksum offload,
hardware vlan tagging, and support for multiple receive queues.

branches: 1.14.2;
Add __KERNEL_RCSID

mcx: sync with OpenBSD sys/dev/pci/if_mcx.c r1.44

1.44:
Fix typo which could lead into a double free

1.43:
Commands that create objects return a 24 bit object ID, so mask off the
high 8 bits of the value we extract, in case the firmware leaves junk there.
Hrvoje Popovski has seen this with newer firmware on a ConnectX 5 card,
which now works properly.

1.42:
Increase the completion queue size to prevent overflow. Under reasonably
unlikely circumstances - lots of single-fragment packets being sent, a
significant number of packets being received, while the interrupt handler
was unable to process the completion queue - the completion queue could
overflow, which would result in the interface locking up.

1.41:
Check if we've reached the end of the current mailbox before writing past
the end of it, rather than after. Now we can actually allocate queues
big enough to need multiple mailboxes.

1.40:
Don't call mcx_intr() from mcx_cmdq_poll(); this was a leftover from early
development that I forgot about, but turns out to be a potential race with
the actual interrupt handler.

1.39:
fix previous: use the correct offset for sq/rq creation, and don't
reset the mbox counter to 0 after calculating it.

1.38:
Add a helper function for writing physical addresses for queues into
command queue mailboxes, and use this for all queue setup commands.
Previously we just assumed the addresses would fit in the first mailbox,
which is currently true but may not be for much longer.

1.37:
(skipped)

1.36:
The event queue consumer counter also needs to be unsigned like the others.

1.35:
try to make if_baudrate look plausible.
this updates the eth proto capability map so it records the baudrate
against the different link types and their media, and then reads
it when the link state changes.

1.34:
(skipped)

branches: 1.12.2; 1.12.4;
Define and implement a locking protocol for the ifmedia / mii layers:
- MP-safe drivers provide a mutex to ifmedia that is used to serialize
access to media-related structures / hardware regsiters. Converted
drivers use the new ifmedia_init_with_lock() function for this. The
new name is provided to ease the transition.
- Un-converted drivers continue to call ifmedia_init(), which will supply
a compatibility lock to be used instead. Several media-related entry
points must be aware of this compatibility lock, and are able to acquire
it recursively a limited number of times, if needed. This is a SPIN
mutex with priority IPL_NET.
- This same lock is used to serialize access to PHY registers and other
MII-related data structures.

The PHY drivers are modified to acquire and release the lock, as needed,
and assert the lock is held as a diagnostic aid.

The "usbnet" framework has had an overhaul of its internal locking
protocols to fit in with the media / mii changes, and the drivers adapted.

USB wifi drivers have been changed to provide their own adaptive mutex
to the ifmedia later via a new ieee80211_media_init_with_lock() function.
This is required because the USB drivers need an adaptive mutex.

Besised "usbnet", a few other drivers are converted: vmx, wm, ixgbe / ixv.

mcx also now calls ifmedia_init_with_lock() because it needs to also use
an adaptive mutex. The mcx driver still needs to be fully converted to
NET_MPSAFE.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Use coherent DMA mappings when possible.

s/structres/structures + s/whenver/whenever

branches: 1.17.4;
Sync with OpenBSD r1.99:

move the rearming of the cq after the refill of the rq.

this is the only real diff we have left outstanding on a box that
experienced rx lockups. since adding this change it's been happy
for the last 4 weeks and counting so far.

mcx: Add if_transmit callback to enable more than one tx queue

Sync with OpenBSD r1.98. Lots of improvements including checksum offload,
hardware vlan tagging, and support for multiple receive queues.

branches: 1.14.2;
Add __KERNEL_RCSID

mcx: sync with OpenBSD sys/dev/pci/if_mcx.c r1.44

1.44:
Fix typo which could lead into a double free

1.43:
Commands that create objects return a 24 bit object ID, so mask off the
high 8 bits of the value we extract, in case the firmware leaves junk there.
Hrvoje Popovski has seen this with newer firmware on a ConnectX 5 card,
which now works properly.

1.42:
Increase the completion queue size to prevent overflow. Under reasonably
unlikely circumstances - lots of single-fragment packets being sent, a
significant number of packets being received, while the interrupt handler
was unable to process the completion queue - the completion queue could
overflow, which would result in the interface locking up.

1.41:
Check if we've reached the end of the current mailbox before writing past
the end of it, rather than after. Now we can actually allocate queues
big enough to need multiple mailboxes.

1.40:
Don't call mcx_intr() from mcx_cmdq_poll(); this was a leftover from early
development that I forgot about, but turns out to be a potential race with
the actual interrupt handler.

1.39:
fix previous: use the correct offset for sq/rq creation, and don't
reset the mbox counter to 0 after calculating it.

1.38:
Add a helper function for writing physical addresses for queues into
command queue mailboxes, and use this for all queue setup commands.
Previously we just assumed the addresses would fit in the first mailbox,
which is currently true but may not be for much longer.

1.37:
(skipped)

1.36:
The event queue consumer counter also needs to be unsigned like the others.

1.35:
try to make if_baudrate look plausible.
this updates the eth proto capability map so it records the baudrate
against the different link types and their media, and then reads
it when the link state changes.

1.34:
(skipped)

branches: 1.12.2; 1.12.4;
Define and implement a locking protocol for the ifmedia / mii layers:
- MP-safe drivers provide a mutex to ifmedia that is used to serialize
access to media-related structures / hardware regsiters. Converted
drivers use the new ifmedia_init_with_lock() function for this. The
new name is provided to ease the transition.
- Un-converted drivers continue to call ifmedia_init(), which will supply
a compatibility lock to be used instead. Several media-related entry
points must be aware of this compatibility lock, and are able to acquire
it recursively a limited number of times, if needed. This is a SPIN
mutex with priority IPL_NET.
- This same lock is used to serialize access to PHY registers and other
MII-related data structures.

The PHY drivers are modified to acquire and release the lock, as needed,
and assert the lock is held as a diagnostic aid.

The "usbnet" framework has had an overhaul of its internal locking
protocols to fit in with the media / mii changes, and the drivers adapted.

USB wifi drivers have been changed to provide their own adaptive mutex
to the ifmedia later via a new ieee80211_media_init_with_lock() function.
This is required because the USB drivers need an adaptive mutex.

Besised "usbnet", a few other drivers are converted: vmx, wm, ixgbe / ixv.

mcx also now calls ifmedia_init_with_lock() because it needs to also use
an adaptive mutex. The mcx driver still needs to be fully converted to
NET_MPSAFE.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

s/structres/structures + s/whenver/whenever

Sync with OpenBSD r1.99:

move the rearming of the cq after the refill of the rq.

this is the only real diff we have left outstanding on a box that
experienced rx lockups. since adding this change it's been happy
for the last 4 weeks and counting so far.

mcx: Add if_transmit callback to enable more than one tx queue

Sync with OpenBSD r1.98. Lots of improvements including checksum offload,
hardware vlan tagging, and support for multiple receive queues.

branches: 1.14.2;
Add __KERNEL_RCSID

mcx: sync with OpenBSD sys/dev/pci/if_mcx.c r1.44

1.44:
Fix typo which could lead into a double free

1.43:
Commands that create objects return a 24 bit object ID, so mask off the
high 8 bits of the value we extract, in case the firmware leaves junk there.
Hrvoje Popovski has seen this with newer firmware on a ConnectX 5 card,
which now works properly.

1.42:
Increase the completion queue size to prevent overflow. Under reasonably
unlikely circumstances - lots of single-fragment packets being sent, a
significant number of packets being received, while the interrupt handler
was unable to process the completion queue - the completion queue could
overflow, which would result in the interface locking up.

1.41:
Check if we've reached the end of the current mailbox before writing past
the end of it, rather than after. Now we can actually allocate queues
big enough to need multiple mailboxes.

1.40:
Don't call mcx_intr() from mcx_cmdq_poll(); this was a leftover from early
development that I forgot about, but turns out to be a potential race with
the actual interrupt handler.

1.39:
fix previous: use the correct offset for sq/rq creation, and don't
reset the mbox counter to 0 after calculating it.

1.38:
Add a helper function for writing physical addresses for queues into
command queue mailboxes, and use this for all queue setup commands.
Previously we just assumed the addresses would fit in the first mailbox,
which is currently true but may not be for much longer.

1.37:
(skipped)

1.36:
The event queue consumer counter also needs to be unsigned like the others.

1.35:
try to make if_baudrate look plausible.
this updates the eth proto capability map so it records the baudrate
against the different link types and their media, and then reads
it when the link state changes.

1.34:
(skipped)

branches: 1.12.2; 1.12.4;
Define and implement a locking protocol for the ifmedia / mii layers:
- MP-safe drivers provide a mutex to ifmedia that is used to serialize
access to media-related structures / hardware regsiters. Converted
drivers use the new ifmedia_init_with_lock() function for this. The
new name is provided to ease the transition.
- Un-converted drivers continue to call ifmedia_init(), which will supply
a compatibility lock to be used instead. Several media-related entry
points must be aware of this compatibility lock, and are able to acquire
it recursively a limited number of times, if needed. This is a SPIN
mutex with priority IPL_NET.
- This same lock is used to serialize access to PHY registers and other
MII-related data structures.

The PHY drivers are modified to acquire and release the lock, as needed,
and assert the lock is held as a diagnostic aid.

The "usbnet" framework has had an overhaul of its internal locking
protocols to fit in with the media / mii changes, and the drivers adapted.

USB wifi drivers have been changed to provide their own adaptive mutex
to the ifmedia later via a new ieee80211_media_init_with_lock() function.
This is required because the USB drivers need an adaptive mutex.

Besised "usbnet", a few other drivers are converted: vmx, wm, ixgbe / ixv.

mcx also now calls ifmedia_init_with_lock() because it needs to also use
an adaptive mutex. The mcx driver still needs to be fully converted to
NET_MPSAFE.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Sync with OpenBSD r1.99:

move the rearming of the cq after the refill of the rq.

this is the only real diff we have left outstanding on a box that
experienced rx lockups. since adding this change it's been happy
for the last 4 weeks and counting so far.

mcx: Add if_transmit callback to enable more than one tx queue

Sync with OpenBSD r1.98. Lots of improvements including checksum offload,
hardware vlan tagging, and support for multiple receive queues.

Add __KERNEL_RCSID

mcx: sync with OpenBSD sys/dev/pci/if_mcx.c r1.44

1.44:
Fix typo which could lead into a double free

1.43:
Commands that create objects return a 24 bit object ID, so mask off the
high 8 bits of the value we extract, in case the firmware leaves junk there.
Hrvoje Popovski has seen this with newer firmware on a ConnectX 5 card,
which now works properly.

1.42:
Increase the completion queue size to prevent overflow. Under reasonably
unlikely circumstances - lots of single-fragment packets being sent, a
significant number of packets being received, while the interrupt handler
was unable to process the completion queue - the completion queue could
overflow, which would result in the interface locking up.

1.41:
Check if we've reached the end of the current mailbox before writing past
the end of it, rather than after. Now we can actually allocate queues
big enough to need multiple mailboxes.

1.40:
Don't call mcx_intr() from mcx_cmdq_poll(); this was a leftover from early
development that I forgot about, but turns out to be a potential race with
the actual interrupt handler.

1.39:
fix previous: use the correct offset for sq/rq creation, and don't
reset the mbox counter to 0 after calculating it.

1.38:
Add a helper function for writing physical addresses for queues into
command queue mailboxes, and use this for all queue setup commands.
Previously we just assumed the addresses would fit in the first mailbox,
which is currently true but may not be for much longer.

1.37:
(skipped)

1.36:
The event queue consumer counter also needs to be unsigned like the others.

1.35:
try to make if_baudrate look plausible.
this updates the eth proto capability map so it records the baudrate
against the different link types and their media, and then reads
it when the link state changes.

1.34:
(skipped)

branches: 1.12.2; 1.12.4;
Define and implement a locking protocol for the ifmedia / mii layers:
- MP-safe drivers provide a mutex to ifmedia that is used to serialize
access to media-related structures / hardware regsiters. Converted
drivers use the new ifmedia_init_with_lock() function for this. The
new name is provided to ease the transition.
- Un-converted drivers continue to call ifmedia_init(), which will supply
a compatibility lock to be used instead. Several media-related entry
points must be aware of this compatibility lock, and are able to acquire
it recursively a limited number of times, if needed. This is a SPIN
mutex with priority IPL_NET.
- This same lock is used to serialize access to PHY registers and other
MII-related data structures.

The PHY drivers are modified to acquire and release the lock, as needed,
and assert the lock is held as a diagnostic aid.

The "usbnet" framework has had an overhaul of its internal locking
protocols to fit in with the media / mii changes, and the drivers adapted.

USB wifi drivers have been changed to provide their own adaptive mutex
to the ifmedia later via a new ieee80211_media_init_with_lock() function.
This is required because the USB drivers need an adaptive mutex.

Besised "usbnet", a few other drivers are converted: vmx, wm, ixgbe / ixv.

mcx also now calls ifmedia_init_with_lock() because it needs to also use
an adaptive mutex. The mcx driver still needs to be fully converted to
NET_MPSAFE.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

mcx: Add if_transmit callback to enable more than one tx queue

Sync with OpenBSD r1.98. Lots of improvements including checksum offload,
hardware vlan tagging, and support for multiple receive queues.

Add __KERNEL_RCSID

mcx: sync with OpenBSD sys/dev/pci/if_mcx.c r1.44

1.44:
Fix typo which could lead into a double free

1.43:
Commands that create objects return a 24 bit object ID, so mask off the
high 8 bits of the value we extract, in case the firmware leaves junk there.
Hrvoje Popovski has seen this with newer firmware on a ConnectX 5 card,
which now works properly.

1.42:
Increase the completion queue size to prevent overflow. Under reasonably
unlikely circumstances - lots of single-fragment packets being sent, a
significant number of packets being received, while the interrupt handler
was unable to process the completion queue - the completion queue could
overflow, which would result in the interface locking up.

1.41:
Check if we've reached the end of the current mailbox before writing past
the end of it, rather than after. Now we can actually allocate queues
big enough to need multiple mailboxes.

1.40:
Don't call mcx_intr() from mcx_cmdq_poll(); this was a leftover from early
development that I forgot about, but turns out to be a potential race with
the actual interrupt handler.

1.39:
fix previous: use the correct offset for sq/rq creation, and don't
reset the mbox counter to 0 after calculating it.

1.38:
Add a helper function for writing physical addresses for queues into
command queue mailboxes, and use this for all queue setup commands.
Previously we just assumed the addresses would fit in the first mailbox,
which is currently true but may not be for much longer.

1.37:
(skipped)

1.36:
The event queue consumer counter also needs to be unsigned like the others.

1.35:
try to make if_baudrate look plausible.
this updates the eth proto capability map so it records the baudrate
against the different link types and their media, and then reads
it when the link state changes.

1.34:
(skipped)

branches: 1.12.2; 1.12.4;
Define and implement a locking protocol for the ifmedia / mii layers:
- MP-safe drivers provide a mutex to ifmedia that is used to serialize
access to media-related structures / hardware regsiters. Converted
drivers use the new ifmedia_init_with_lock() function for this. The
new name is provided to ease the transition.
- Un-converted drivers continue to call ifmedia_init(), which will supply
a compatibility lock to be used instead. Several media-related entry
points must be aware of this compatibility lock, and are able to acquire
it recursively a limited number of times, if needed. This is a SPIN
mutex with priority IPL_NET.
- This same lock is used to serialize access to PHY registers and other
MII-related data structures.

The PHY drivers are modified to acquire and release the lock, as needed,
and assert the lock is held as a diagnostic aid.

The "usbnet" framework has had an overhaul of its internal locking
protocols to fit in with the media / mii changes, and the drivers adapted.

USB wifi drivers have been changed to provide their own adaptive mutex
to the ifmedia later via a new ieee80211_media_init_with_lock() function.
This is required because the USB drivers need an adaptive mutex.

Besised "usbnet", a few other drivers are converted: vmx, wm, ixgbe / ixv.

mcx also now calls ifmedia_init_with_lock() because it needs to also use
an adaptive mutex. The mcx driver still needs to be fully converted to
NET_MPSAFE.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Sync with OpenBSD r1.98. Lots of improvements including checksum offload,
hardware vlan tagging, and support for multiple receive queues.

Add __KERNEL_RCSID

mcx: sync with OpenBSD sys/dev/pci/if_mcx.c r1.44

1.44:
Fix typo which could lead into a double free

1.43:
Commands that create objects return a 24 bit object ID, so mask off the
high 8 bits of the value we extract, in case the firmware leaves junk there.
Hrvoje Popovski has seen this with newer firmware on a ConnectX 5 card,
which now works properly.

1.42:
Increase the completion queue size to prevent overflow. Under reasonably
unlikely circumstances - lots of single-fragment packets being sent, a
significant number of packets being received, while the interrupt handler
was unable to process the completion queue - the completion queue could
overflow, which would result in the interface locking up.

1.41:
Check if we've reached the end of the current mailbox before writing past
the end of it, rather than after. Now we can actually allocate queues
big enough to need multiple mailboxes.

1.40:
Don't call mcx_intr() from mcx_cmdq_poll(); this was a leftover from early
development that I forgot about, but turns out to be a potential race with
the actual interrupt handler.

1.39:
fix previous: use the correct offset for sq/rq creation, and don't
reset the mbox counter to 0 after calculating it.

1.38:
Add a helper function for writing physical addresses for queues into
command queue mailboxes, and use this for all queue setup commands.
Previously we just assumed the addresses would fit in the first mailbox,
which is currently true but may not be for much longer.

1.37:
(skipped)

1.36:
The event queue consumer counter also needs to be unsigned like the others.

1.35:
try to make if_baudrate look plausible.
this updates the eth proto capability map so it records the baudrate
against the different link types and their media, and then reads
it when the link state changes.

1.34:
(skipped)

branches: 1.12.2; 1.12.4;
Define and implement a locking protocol for the ifmedia / mii layers:
- MP-safe drivers provide a mutex to ifmedia that is used to serialize
access to media-related structures / hardware regsiters. Converted
drivers use the new ifmedia_init_with_lock() function for this. The
new name is provided to ease the transition.
- Un-converted drivers continue to call ifmedia_init(), which will supply
a compatibility lock to be used instead. Several media-related entry
points must be aware of this compatibility lock, and are able to acquire
it recursively a limited number of times, if needed. This is a SPIN
mutex with priority IPL_NET.
- This same lock is used to serialize access to PHY registers and other
MII-related data structures.

The PHY drivers are modified to acquire and release the lock, as needed,
and assert the lock is held as a diagnostic aid.

The "usbnet" framework has had an overhaul of its internal locking
protocols to fit in with the media / mii changes, and the drivers adapted.

USB wifi drivers have been changed to provide their own adaptive mutex
to the ifmedia later via a new ieee80211_media_init_with_lock() function.
This is required because the USB drivers need an adaptive mutex.

Besised "usbnet", a few other drivers are converted: vmx, wm, ixgbe / ixv.

mcx also now calls ifmedia_init_with_lock() because it needs to also use
an adaptive mutex. The mcx driver still needs to be fully converted to
NET_MPSAFE.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Add __KERNEL_RCSID

mcx: sync with OpenBSD sys/dev/pci/if_mcx.c r1.44

1.44:
Fix typo which could lead into a double free

1.43:
Commands that create objects return a 24 bit object ID, so mask off the
high 8 bits of the value we extract, in case the firmware leaves junk there.
Hrvoje Popovski has seen this with newer firmware on a ConnectX 5 card,
which now works properly.

1.42:
Increase the completion queue size to prevent overflow. Under reasonably
unlikely circumstances - lots of single-fragment packets being sent, a
significant number of packets being received, while the interrupt handler
was unable to process the completion queue - the completion queue could
overflow, which would result in the interface locking up.

1.41:
Check if we've reached the end of the current mailbox before writing past
the end of it, rather than after. Now we can actually allocate queues
big enough to need multiple mailboxes.

1.40:
Don't call mcx_intr() from mcx_cmdq_poll(); this was a leftover from early
development that I forgot about, but turns out to be a potential race with
the actual interrupt handler.

1.39:
fix previous: use the correct offset for sq/rq creation, and don't
reset the mbox counter to 0 after calculating it.

1.38:
Add a helper function for writing physical addresses for queues into
command queue mailboxes, and use this for all queue setup commands.
Previously we just assumed the addresses would fit in the first mailbox,
which is currently true but may not be for much longer.

1.37:
(skipped)

1.36:
The event queue consumer counter also needs to be unsigned like the others.

1.35:
try to make if_baudrate look plausible.
this updates the eth proto capability map so it records the baudrate
against the different link types and their media, and then reads
it when the link state changes.

1.34:
(skipped)

branches: 1.12.2; 1.12.4;
Define and implement a locking protocol for the ifmedia / mii layers:
- MP-safe drivers provide a mutex to ifmedia that is used to serialize
access to media-related structures / hardware regsiters. Converted
drivers use the new ifmedia_init_with_lock() function for this. The
new name is provided to ease the transition.
- Un-converted drivers continue to call ifmedia_init(), which will supply
a compatibility lock to be used instead. Several media-related entry
points must be aware of this compatibility lock, and are able to acquire
it recursively a limited number of times, if needed. This is a SPIN
mutex with priority IPL_NET.
- This same lock is used to serialize access to PHY registers and other
MII-related data structures.

The PHY drivers are modified to acquire and release the lock, as needed,
and assert the lock is held as a diagnostic aid.

The "usbnet" framework has had an overhaul of its internal locking
protocols to fit in with the media / mii changes, and the drivers adapted.

USB wifi drivers have been changed to provide their own adaptive mutex
to the ifmedia later via a new ieee80211_media_init_with_lock() function.
This is required because the USB drivers need an adaptive mutex.

Besised "usbnet", a few other drivers are converted: vmx, wm, ixgbe / ixv.

mcx also now calls ifmedia_init_with_lock() because it needs to also use
an adaptive mutex. The mcx driver still needs to be fully converted to
NET_MPSAFE.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

mcx: sync with OpenBSD sys/dev/pci/if_mcx.c r1.44

1.44:
Fix typo which could lead into a double free

1.43:
Commands that create objects return a 24 bit object ID, so mask off the
high 8 bits of the value we extract, in case the firmware leaves junk there.
Hrvoje Popovski has seen this with newer firmware on a ConnectX 5 card,
which now works properly.

1.42:
Increase the completion queue size to prevent overflow. Under reasonably
unlikely circumstances - lots of single-fragment packets being sent, a
significant number of packets being received, while the interrupt handler
was unable to process the completion queue - the completion queue could
overflow, which would result in the interface locking up.

1.41:
Check if we've reached the end of the current mailbox before writing past
the end of it, rather than after. Now we can actually allocate queues
big enough to need multiple mailboxes.

1.40:
Don't call mcx_intr() from mcx_cmdq_poll(); this was a leftover from early
development that I forgot about, but turns out to be a potential race with
the actual interrupt handler.

1.39:
fix previous: use the correct offset for sq/rq creation, and don't
reset the mbox counter to 0 after calculating it.

1.38:
Add a helper function for writing physical addresses for queues into
command queue mailboxes, and use this for all queue setup commands.
Previously we just assumed the addresses would fit in the first mailbox,
which is currently true but may not be for much longer.

1.37:
(skipped)

1.36:
The event queue consumer counter also needs to be unsigned like the others.

1.35:
try to make if_baudrate look plausible.
this updates the eth proto capability map so it records the baudrate
against the different link types and their media, and then reads
it when the link state changes.

1.34:
(skipped)

branches: 1.12.4;
Define and implement a locking protocol for the ifmedia / mii layers:
- MP-safe drivers provide a mutex to ifmedia that is used to serialize
access to media-related structures / hardware regsiters. Converted
drivers use the new ifmedia_init_with_lock() function for this. The
new name is provided to ease the transition.
- Un-converted drivers continue to call ifmedia_init(), which will supply
a compatibility lock to be used instead. Several media-related entry
points must be aware of this compatibility lock, and are able to acquire
it recursively a limited number of times, if needed. This is a SPIN
mutex with priority IPL_NET.
- This same lock is used to serialize access to PHY registers and other
MII-related data structures.

The PHY drivers are modified to acquire and release the lock, as needed,
and assert the lock is held as a diagnostic aid.

The "usbnet" framework has had an overhaul of its internal locking
protocols to fit in with the media / mii changes, and the drivers adapted.

USB wifi drivers have been changed to provide their own adaptive mutex
to the ifmedia later via a new ieee80211_media_init_with_lock() function.
This is required because the USB drivers need an adaptive mutex.

Besised "usbnet", a few other drivers are converted: vmx, wm, ixgbe / ixv.

mcx also now calls ifmedia_init_with_lock() because it needs to also use
an adaptive mutex. The mcx driver still needs to be fully converted to
NET_MPSAFE.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Define and implement a locking protocol for the ifmedia / mii layers:
- MP-safe drivers provide a mutex to ifmedia that is used to serialize
access to media-related structures / hardware regsiters. Converted
drivers use the new ifmedia_init_with_lock() function for this. The
new name is provided to ease the transition.
- Un-converted drivers continue to call ifmedia_init(), which will supply
a compatibility lock to be used instead. Several media-related entry
points must be aware of this compatibility lock, and are able to acquire
it recursively a limited number of times, if needed. This is a SPIN
mutex with priority IPL_NET.
- This same lock is used to serialize access to PHY registers and other
MII-related data structures.

The PHY drivers are modified to acquire and release the lock, as needed,
and assert the lock is held as a diagnostic aid.

The "usbnet" framework has had an overhaul of its internal locking
protocols to fit in with the media / mii changes, and the drivers adapted.

USB wifi drivers have been changed to provide their own adaptive mutex
to the ifmedia later via a new ieee80211_media_init_with_lock() function.
This is required because the USB drivers need an adaptive mutex.

Besised "usbnet", a few other drivers are converted: vmx, wm, ixgbe / ixv.

mcx also now calls ifmedia_init_with_lock() because it needs to also use
an adaptive mutex. The mcx driver still needs to be fully converted to
NET_MPSAFE.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Use the 64-bit PCI DMA tag if available. Otherwise, we are needlessly
allocating (and using) bounce buffers on sytems with >4GB of RAM.

XXX pullup-9

Adopt <net/if_stats.h>.

branches: 1.9.2;
Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Adopt <net/if_stats.h>.

Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Set if_baudrate.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

- Change IFM_10G_T(10GBase-T) entry to IFM_10G_CR1(10GBASE-CR1)
- Add the following entries:

20GBASE-KR2
56GBASE-R4
100GBASE-LR4
100BaseTX
1000baseT
10GBase-T

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Fix IFF_ALLMULTI handling.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Fixed incorrect m_defrag return value check.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Use unsigned to avoid undefined behavior. Found by kUBSan.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

len -> m_len

mcx(4): fix rx mbuf DMA overrun

pullup-9

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Use IFM_50G_SR2.

branches: 1.1.2;
Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.

Add support for Mellanox 5th generation ethernet devices. This driver
supports the ConnectX-4 Lx EN, ConnectX-4 EN, ConnectX-5 EN, and
ConnectX-6 EN adapters.

Driver ported from OpenBSD.