| Message ID | 20250211-nvme-fixes-v1-0-6958b3aa49fe@rosenzweig.io (mailing list archive) |
|---|---|
| Headers | show |
| Series | apple-nvme: bug and perf fixes | expand |
On Tue, Feb 11, 2025 at 01:25:56PM -0500, Alyssa Rosenzweig wrote: > This small series fixes three unrelated issues with the Apple NVMe > driver. > > * fix NVMe on firmware/machine > * fix a power domain leak > * fix pathological driver performance with random writes > > The first two are strict bug fixes, the last is technically an > optimization but given the measured 200x performance difference I do > consider to be a fix ;-) The last two patches look good to me. I don't know anyone qualified to review the first patch, so I'll take your word for it if no one replies in the next few days. :)
On Tue, Feb 11, 2025 at 1:26 PM Alyssa Rosenzweig <alyssa@rosenzweig.io> wrote: > > This small series fixes three unrelated issues with the Apple NVMe > driver. > > * fix NVMe on firmware/machine > * fix a power domain leak > * fix pathological driver performance with random writes > > The first two are strict bug fixes, the last is technically an > optimization but given the measured 200x performance difference I do > consider to be a fix ;-) > > Given the early stage of mainlining for these SoCs, none of this needs > to be backported. > > Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> > --- > Hector Martin (2): > apple-nvme: Support coprocessors left idle > apple-nvme: Release power domains when probe fails > > Jens Axboe (1): > apple-nvme: defer cache flushes by a specified amount > > drivers/nvme/host/apple.c | 124 +++++++++++++++++++++++++++++++++++++++------- > 1 file changed, 107 insertions(+), 17 deletions(-) > --- > base-commit: 2014c95afecee3e76ca4a56956a936e23283f05b > change-id: 20250211-nvme-fixes-29c409c2553f > > Best regards, > -- > Alyssa Rosenzweig <alyssa@rosenzweig.io> > > Series LGTM. Reviewed-by: Neal Gompa <neal@gompa.dev>
This small series fixes three unrelated issues with the Apple NVMe driver. * fix NVMe on firmware/machine * fix a power domain leak * fix pathological driver performance with random writes The first two are strict bug fixes, the last is technically an optimization but given the measured 200x performance difference I do consider to be a fix ;-) Given the early stage of mainlining for these SoCs, none of this needs to be backported. Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> --- Hector Martin (2): apple-nvme: Support coprocessors left idle apple-nvme: Release power domains when probe fails Jens Axboe (1): apple-nvme: defer cache flushes by a specified amount drivers/nvme/host/apple.c | 124 +++++++++++++++++++++++++++++++++++++++------- 1 file changed, 107 insertions(+), 17 deletions(-) --- base-commit: 2014c95afecee3e76ca4a56956a936e23283f05b change-id: 20250211-nvme-fixes-29c409c2553f Best regards,