summaryrefslogtreecommitdiff
path: root/scripts/Makefile.thinlto
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2026-10-22 13:51:18 -1000
committerLinus Torvalds <torvalds@linux-foundation.org>2026-10-22 13:51:18 -1000
commitfcb92ecd733e11f37c32e7485da976a40d878e72 (patch)
treea890fddbbb6804eb812cc3b7c7e605fc8ddbe12f /scripts/Makefile.thinlto
parent1021679bed5acc46e1b2dac78bdd006bd50970f4 (diff)
parentc3e8e9451e6f1b69f685b75e0fbf14f3d0fb2539 (diff)
downloadlwn-fcb92ecd733e11f37c32e7485da976a40d878e72.tar.gz
lwn-fcb92ecd733e11f37c32e7485da976a40d878e72.zip
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma
Pull rdma updates from Jason Gunthorpe: "A smaller cycle for features, still mostly AI and tool found bug fixes for long standing issues: - Bug fixes and minor cleanups across bnxt_re, cxgb4, EFA, ERDMA, HFI1, HNS, ionic, iRDMA, mlx4/mlx5, rdmavt, rtrs, RXE, SIW, SRP, isert and IPoIB. Lots of error unwind leaks, integer overflows, and use after free during teardown from timers/work that was not cancelled - Core fixes for uverbs DMABUF lifetime, RMPP reassembly use after free, multicast rb-tree corruption, restrack, and a user triggerable NULL deref when creating a WQ without a CQ - Prevent userspace from getting a writable mmap of the cxgb4 status page and the mlx4 clock page - Many rxe hardening fixes for bad user and network input, plus netdev and tunnel socket lifetime fixes - Peer supplied values are now validated in rtrs-clt, which is remote triggerable - umem now picks the DMA direction from the access flags instead of always using DMA_BIDIRECTIONAL, so an IOMMU can stop the device from writing to read-only memory. Several drivers were fixed to pin CQ and queue memory as writable to go along with this - SRQ support, firmware assigned CQ IDs and RCQ userspace support for ionic - RC QP improvements in MANA: MMQ creation, fixed size send WQEs and power of two send queues. Also multi-port GSI QPs and a rework of the UD send/receive and CQ polling paths - Relaxed ordering MRs for EFA - Non-contiguous kernel QP and CQ buffers for ERDMA - Move the mlx5 data direct infrastructure from mlx5_ib to mlx5_core so netdev can use it too. The data direct PCI driver is now named "mlx5_dd" - debugfs knob in hns to fix the SL used by the GSI QP, working around a HW problem with dropped CQEs - Selftest fixes, removal of the qib sysfs ABI docs, DT schema conversion for hns, and MANA maintainer handover" * tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (153 commits) RDMA/irdma: Bound in-flight CQP ops across deferred completions RDMA/mlx5: Validate priority in STEERING_ANCHOR_CREATE handler RDMA/mlx5: Fix CQ resize destination index mask RDMA/usnic: Bound buffer size to sizeof(buf) in flowinfo_read() RDMA/rxe: Clear pkt->qp before the early drop exits in rxe_rcv() dt-bindings: infiniband: Convert hisilicon,hns-roce-v1 to DT schema RDMA/srp: Avoid reading uninitialized has_port on srp_parse_in() failure RDMA/irdma: Fix PBLE_LEVEL_2 FRWR generation RDMA/core: Reject LAG selection when source MAC lookup fails RDMA/core: Free unpublished port statistics after initial-read failure RDMA/core: Preserve the selected source GID on failed AH modification RDMA/uverbs: Fix DMABUF use-after-free during ufile cleanup RDMA/uverbs: Fix uobject leak in DMABUF release RDMA/irdma: Fix FRWR IRDMAQPSQ_PBLADDR field population IB/rdmavt: Fix error unwind path for qp_priv_init() in rvt_create_qp() RDMA/irdma: Check MR contiguity before PBLE alloc IB/mlx4: Avoid requeueing executing CM timeout work RDMA/rxe: bound the WQE opcode before indexing rxe_wr_opcode_info[] RDMA/rxe: Fix out-of-range unsigned-to-signed conversion for RDMA message in 2GiB size RDMA/rxe: validate inline sge_offset in finish_packet() before indexing inline_data[] ...
Diffstat (limited to 'scripts/Makefile.thinlto')
0 files changed, 0 insertions, 0 deletions