Messages in this thread | | | From | Jason Gunthorpe <> | Subject | [GIT PULL] Please pull RDMA subsystem changes | Date | Sun, 28 Apr 2019 11:52:12 +0000 |
| |
Hi Linus,
Third rc pull request
Nothing particularly special here. There is a small merge conflict with Adrea's mm_still_valid patches which is resolved as below:
diff --cc drivers/infiniband/core/uverbs_main.c index db20b6e0f253c9,f2e7ffe6fc5466..7843e89235c34b --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@@ -1039,7 -992,9 +1039,9 @@@ void uverbs_user_mmap_disassociate(stru * at a time to get the lock ordering right. Typically there * will only be one mm, so no big deal. */ - down_write(&mm->mmap_sem); + down_read(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; mutex_lock(&ufile->umap_lock); list_for_each_entry_safe (priv, next_priv, &ufile->umaps, list) { @@@ -1051,9 -1006,11 +1053,10 @@@ zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); - vma->vm_flags &= ~(VM_SHARED | VM_MAYSHARE); } mutex_unlock(&ufile->umap_lock); + skip_mm: - up_write(&mm->mmap_sem); + up_read(&mm->mmap_sem); mmput(mm); } }
The tag for-linus-merged with my merge resolution to your tree is also available to pull.
Thanks, Jason
The following changes since commit dc4060a5dc2557e6b5aa813bf5b73677299d62d2:
Linux 5.1-rc5 (2019-04-14 15:17:41 -0700)
are available in the Git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git tags/for-linus
for you to fetch changes up to 2557fabd6e29f349bfa0ac13f38ac98aa5eafc74:
RDMA/hns: Bugfix for mapping user db (2019-04-25 10:40:04 -0300)
---------------------------------------------------------------- 5.1 Third RC pull request
One core bug fix and a few driver ones
- FRWR memory registration for hfi1/qib didn't work with with some iovas causing a NFSoRDMA failure regression due to a fix in the NFS side
- A command flow error in mlx5 allowed user space to send a corrupt command (and also smash the kernel stack we've since learned)
- Fix a regression and some bugs with device hot unplug that was discovered while reviewing Andrea's patches
- hns has a failure if the user asks for certain QP configurations
---------------------------------------------------------------- Guy Levi (1): IB/mlx5: Fix scatter to CQE in DCT QP creation
Jason Gunthorpe (3): RDMA/mlx5: Do not allow the user to write to the clock page RDMA/mlx5: Use rdma_user_map_io for mapping BAR pages RDMA/ucontext: Fix regression with disassociate
Josh Collier (1): IB/rdmavt: Fix frwr memory registration
Lijun Ou (1): RDMA/hns: Bugfix for mapping user db
drivers/infiniband/core/uverbs.h | 1 + drivers/infiniband/core/uverbs_main.c | 52 +++++++++++++++++++++++++++++++-- drivers/infiniband/hw/hns/hns_roce_qp.c | 2 +- drivers/infiniband/hw/mlx5/main.c | 12 ++++---- drivers/infiniband/hw/mlx5/qp.c | 11 ++++--- drivers/infiniband/sw/rdmavt/mr.c | 17 ++++++----- include/uapi/rdma/mlx5-abi.h | 1 + 7 files changed, 76 insertions(+), 20 deletions(-) (diffstat from tag for-linus-merged) [unhandled content-type:application/pgp-signature] | |