Remove the 'All Rights Reserved' clause from some of the stuff I've
done for Netflix, since I'm in the neighborhood.

Move setting of CAM_SIM_QUEUED to before we actually submit it to the
hardware. Setting it after is racy, and we can lose the race on a
heavily loaded system.

Reviewed by: scottl@, gallatin@
Sponsor

Move setting of CAM_SIM_QUEUED to before we actually submit it to the
hardware. Setting it after is racy, and we can lose the race on a
heavily loaded system.

Reviewed by: scottl@, gallatin@
Sponsored by: Netflix

show more ...

Merge ^/head r326936 through r327149.

Return domain, bus, slot, and function for the transport settings in
PATH_INQ requests for nvme.

Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D13546

Merge ^/head r325663 through r325841.

Inline pcie_link_{status,caps} where needed. Remove them as they
aren't really needed and I don't want to document them.

Suggested by: jhb@
Sponsored by: Netflix

Provide link speed data in XPT_GET_TRAN_SETTINGS. Provide full version
information for that and XPT_PATH_INQ. Provide macros to encode/decode
major/minor versions. Read the link speed and lane count

Provide link speed data in XPT_GET_TRAN_SETTINGS. Provide full version
information for that and XPT_PATH_INQ. Provide macros to encode/decode
major/minor versions. Read the link speed and lane count to compute
the base_transfer_speed for XPT_PATH_INQ.

Sponsored by: Netflix

show more ...

Merge ^/head r323559 through r325504.

MFhead@r324837

While here, diff reduce some of the changes in sys/boot by moving
MK_COVERAGE=no to sys/boot/Makefile.inc .

Use nvme_ctrlr_poll instead of nvme_ctrlr_intx_handler since it is
more general and doesn't try to access registers that may be undefined
when the card is in MSIX mode.

This change, along with r3246

Use nvme_ctrlr_poll instead of nvme_ctrlr_intx_handler since it is
more general and doesn't try to access registers that may be undefined
when the card is in MSIX mode.

This change, along with r324630, r324631, r324632, makes nda crash
dumps work again. Previously, they only worked on CPU 0 when the stack
garbage was just so.

Sponsored by: Netflix
Suggested by: scottl@ (who provided earlier version of the patch)

show more ...

MFhead@r324075

Tweak performance of nda completions

Use xpt_done_direct in preference to xpt_done when completing a
successful I/O. Continue to use xpt_done when there's an error, or for
completion of the submissi

Tweak performance of nda completions

Use xpt_done_direct in preference to xpt_done when completing a
successful I/O. Continue to use xpt_done when there's an error, or for
completion of the submission of a CCB. This eliminates a context
switch to the cam_doneq thread.

Sponsored by: Netflix
Suggested by: scottl@

show more ...

MFH @ r323558.

MFhead@r323343

Add CAM/NVMe support for CAM_DATA_SG

This adds support in pass(4) for data to be described with a
scatter-gather list (sglist) to augment the existing (single) virtual
address.

Differential Revisio

Add CAM/NVMe support for CAM_DATA_SG

This adds support in pass(4) for data to be described with a
scatter-gather list (sglist) to augment the existing (single) virtual
address.

Differential Revision: https://reviews.freebsd.org/D11361
Submitted by: Chuck Tuffli
Reviewed by: imp@, scottl@, kenm@

show more ...

Set the max transactions for NVMe drives better.

Provided a better estimate for the number of transactions that can be
pending at one time. This will be number of queues * number of
trackers / 4, as

Set the max transactions for NVMe drives better.

Provided a better estimate for the number of transactions that can be
pending at one time. This will be number of queues * number of
trackers / 4, as suggested by Jim Harris. This gives a better estimate
of the number of transactions that CAM should queue before applying
back pressure. This should be revisted when we have real multi-queue
support in CAM and the upper layers of the I/O stack.

Sponsored by: Netflix

show more ...

MFhead@r322451

Merge ^/head r321383 through r322397.

Use the correct queue depth for nda devices.

Submitted by: Matt Williams

MFhead@r322057

Make nvd vs nda choice boot-time rather than build-time

Introduce hw.nvme.use_nvd tunable. This tunable allows both nvd and
nda to be installed in the kernel, while allowing only one of them to
crea

Make nvd vs nda choice boot-time rather than build-time

Introduce hw.nvme.use_nvd tunable. This tunable allows both nvd and
nda to be installed in the kernel, while allowing only one of them to
create devices. This is an all-or-nothing setting, and you can't
change it after boot-time. However, it will allow easier A/B testing.

Differential Revision: https://reviews.freebsd.org/D11825

show more ...

MFhead@r320180

Merge ^/head r319973 through 321382.

Merge ^/head r320971 through r320993.

This adds CAM pass(4) support for NVMe IO's. Applications indicate
the IO type (Admin or NVM) using XPT op-codes XPT_NVME_ADMIN or
XPT_NVME_IO.

Submitted by: Chuck Tuffli <chuck@tuffli.net>
Differ

This adds CAM pass(4) support for NVMe IO's. Applications indicate
the IO type (Admin or NVM) using XPT op-codes XPT_NVME_ADMIN or
XPT_NVME_IO.

Submitted by: Chuck Tuffli <chuck@tuffli.net>
Differential Revision: https://reviews.freebsd.org/D10247

show more ...