| Message ID | 20250324200540.910962-1-csander@purestorage.com (mailing list archive) |
|---|---|
| Headers | show |
| Series | nvme_map_user_request() cleanup | expand |
On 3/24/25 13:05, Caleb Sander Mateos wrote: > The first commit removes a WARN_ON_ONCE() checking userspace values. > The last 2 move code out of nvme_map_user_request() that belongs better > in its callers, and move the fixed buffer import before going async. > As discussed in [1], this allows an NVMe passthru operation submitted at > the same time as a ublk zero-copy buffer unregister operation to succeed > even if the initial issue goes async. This can improve performance of > userspace applications submitting the operations together like this with > a slow fallback path on failure. This is an alternate approach to [2], > which moved the fixed buffer import to the io_uring layer. > > There will likely be conflicts with the parameter cleanup series Keith > posted last month in [3]. > > The series is based on block/for-6.15/io_uring, with commit 00817f0f1c45 > ("nvme-ioctl: fix leaked requests on mapping error") cherry-picked. > > [1]:https://lore.kernel.org/io-uring/20250321184819.3847386-1-csander@purestorage.com/T/#u > [2]:https://lore.kernel.org/io-uring/20250321184819.3847386-4-csander@purestorage.com/ > [3]:https://lore.kernel.org/all/20250224182128.2042061-1-kbusch@meta.com/T/#u > > v3: Move the fixed buffer import before allocating a blk-mq request > > v2: Fix iov_iter value passed to nvme_map_user_request() Looks good to me. Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com> -ck
On Mon, Mar 24, 2025 at 02:05:37PM -0600, Caleb Sander Mateos wrote: > The first commit removes a WARN_ON_ONCE() checking userspace values. > The last 2 move code out of nvme_map_user_request() that belongs better > in its callers, and move the fixed buffer import before going async. > As discussed in [1], this allows an NVMe passthru operation submitted at > the same time as a ublk zero-copy buffer unregister operation to succeed > even if the initial issue goes async. This can improve performance of > userspace applications submitting the operations together like this with > a slow fallback path on failure. This is an alternate approach to [2], > which moved the fixed buffer import to the io_uring layer. > > There will likely be conflicts with the parameter cleanup series Keith > posted last month in [3]. > > The series is based on block/for-6.15/io_uring, with commit 00817f0f1c45 > ("nvme-ioctl: fix leaked requests on mapping error") cherry-picked. Thanks, I've queued these up internally for 6.15; the next nvme pull request will need to rebase once the upstream branches sync with the existing outstanding pulls, so this series will be included in the next one for this merge window after that happens.
The first commit removes a WARN_ON_ONCE() checking userspace values. The last 2 move code out of nvme_map_user_request() that belongs better in its callers, and move the fixed buffer import before going async. As discussed in [1], this allows an NVMe passthru operation submitted at the same time as a ublk zero-copy buffer unregister operation to succeed even if the initial issue goes async. This can improve performance of userspace applications submitting the operations together like this with a slow fallback path on failure. This is an alternate approach to [2], which moved the fixed buffer import to the io_uring layer. There will likely be conflicts with the parameter cleanup series Keith posted last month in [3]. The series is based on block/for-6.15/io_uring, with commit 00817f0f1c45 ("nvme-ioctl: fix leaked requests on mapping error") cherry-picked. [1]: https://lore.kernel.org/io-uring/20250321184819.3847386-1-csander@purestorage.com/T/#u [2]: https://lore.kernel.org/io-uring/20250321184819.3847386-4-csander@purestorage.com/ [3]: https://lore.kernel.org/all/20250224182128.2042061-1-kbusch@meta.com/T/#u v3: Move the fixed buffer import before allocating a blk-mq request v2: Fix iov_iter value passed to nvme_map_user_request() Caleb Sander Mateos (3): nvme/ioctl: don't warn on vectorized uring_cmd with fixed buffer nvme/ioctl: move blk_mq_free_request() out of nvme_map_user_request() nvme/ioctl: move fixed buffer lookup to nvme_uring_cmd_io() drivers/nvme/host/ioctl.c | 68 +++++++++++++++++++++------------------ 1 file changed, 36 insertions(+), 32 deletions(-)