From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Fix error output of boot instance creation failure Currently if a boot instance creation fails, instead of printing out the name of the instance that failed, it prints "(null)". That is because it prints "cur_str" that had already been processed by strsep(). Print the saved name instead. While at it, print the error code of the failure. - Fix use-after-free for same named historgrams Histograms can be named so that they can be used in multiple events. But if the named histogram has a variable attached, the second event that uses the named histogram which duplicates it and needs to free the original after duplication leaves the old variable in place and still visible. If another histogram uses than variable, it will use the stale one which will try to reference the freed duplicate histogram and crash the kernel. Free the duplicate variables along with the duplicated histogram data. - Check return value of kthread_run() in event self test The events self tests uses a kthread for testing but does not check if it succeeded in creating a kthread. If the kthread creation were to fail, the code will still try to call kthread_stop() on the error returned. - Fix race between reading trace_pipe and updating subbuffer size If a user is reading the trace_pipe file at the same time they update the ring buffer sub-buffer size, can cause the trace_pipe read to read stale data. Add trace_access_lock() around updating the ring buffer sub-buffer size. - Fix eventfs_inode on failure path in creation of the events directory In the creation of the "events" directory, if after allocating the eventfs_inode a failure is detected, it calls cleanup_ei() which calls free_ei(). The free_ei() will test if eventfs_inode being freed has no children. It is a bug if it does. But on the failure case of the creation of the "events" directory, the children lists have not yet been initialized and the free will trigger a warning because list_empty() on an uninitialized list returns false. Move the initialization into init_ei() where it makes more sense and makes sure that a created eventfs_inode has its lists initialized upon creation. - Check return value of kthread_run() in ftrace direct sample code The sample code that shows how to use the ftrace direct calls does not test the return of kthread_run() to see if it succeeds. Return a failure if the kthread_run() doesn't succeed. - Clear user events state on fork in case of alloc failure On fork, the child gets a pointer to the parent's user events state. It makes a copy of it then updates the child's pointer to it. But if the allocation fails, the duplication function leaves the child with a pointer to its parent's descriptor. When the child cleans up its data, it will free the parent's descriptor while the parent is still using it. In the duplication function, set the child's user_event_mm to NULL before testing if the allocation succeeded, and when it exits it will not free the parent's descriptor. - Fix retry exhaustion in simple ring buffer reader swap simple_ring_buffer_swap_reader_page() starts with retry set to 8 and post-decrements it only after a failed link replacement. On the final attempt, a successful replacement leaves retry at zero, while a failed replacement leaves it at -1. But the check for success expects the retry value to be non-zero and exits with an error on zero. This is the opposite result. Fix it. - Fail nicely when the remote swap_reader_page() returns an error Currently, if the swap_reader_page() of a remote buffer fails, it triggers a WARN_ON_ONCE() and continues normally. Instead, have it exit with an error and a pr_warn() print instead of a full WARNING. * tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: ring-buffer: Stop remote reader update when page swap fails tracing: Fix retry exhaustion in simple ring buffer reader swap tracing/user_events: Clear copied tracing state before fork duplication samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify eventfs: Initialize ei->children and ei->list in init_ei() tracing: Fix use-after-free in trace_pipe read on sub-buffer order change tracing: Fix crash passing ERR_PTR to kthread_stop() tracing: Fix use-after-free with same-name named triggers tracing: Fix logged instance name on creation failure --- include/uapi/rdma/efa-abi.h | 175 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 175 insertions(+) create mode 100644 include/uapi/rdma/efa-abi.h (limited to 'include/uapi/rdma/efa-abi.h') diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h new file mode 100644 index 000000000..2094b4bcc --- /dev/null +++ b/include/uapi/rdma/efa-abi.h @@ -0,0 +1,175 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ +/* + * Copyright 2018-2026 Amazon.com, Inc. or its affiliates. All rights reserved. + */ + +#ifndef EFA_ABI_USER_H +#define EFA_ABI_USER_H + +#include +#include + +/* + * Increment this value if any changes that break userspace ABI + * compatibility are made. + */ +#define EFA_UVERBS_ABI_VERSION 1 + +/* + * Keep structs aligned to 8 bytes. + * Keep reserved fields as arrays of __u8 named reserved_XXX where XXX is the + * hex bit offset of the field. + */ + +enum { + EFA_ALLOC_UCONTEXT_CMD_SUPP_CAPS_TX_BATCH = 1 << 0, + EFA_ALLOC_UCONTEXT_CMD_SUPP_CAPS_MIN_SQ_WR = 1 << 1, +}; + +struct efa_ibv_alloc_ucontext_cmd { + __u32 supported_caps; + __u8 reserved_20[4]; +}; + +enum efa_ibv_user_cmds_supp_udata { + EFA_USER_CMDS_SUPP_UDATA_QUERY_DEVICE = 1 << 0, + EFA_USER_CMDS_SUPP_UDATA_CREATE_AH = 1 << 1, +}; + +struct efa_ibv_alloc_ucontext_resp { + __u32 comp_mask; + __u32 cmds_supp_udata_mask; + __u16 sub_cqs_per_cq; + __u16 inline_buf_size; + __u32 max_llq_size; /* bytes */ + __u16 max_tx_batch; /* units of 64 bytes */ + __u16 min_sq_wr; + __u16 inline_buf_size_ex; + __u8 reserved_b0[2]; +}; + +struct efa_ibv_alloc_pd_resp { + __u32 comp_mask; + __u16 pdn; + __u8 reserved_30[2]; +}; + +enum { + EFA_CREATE_CQ_WITH_COMPLETION_CHANNEL = 1 << 0, + EFA_CREATE_CQ_WITH_SGID = 1 << 1, + EFA_CREATE_CQ_WITH_SQ_COMP_64_BIT_REQ_ID = 1 << 2, +}; + +struct efa_ibv_create_cq { + __u32 comp_mask; + __u32 cq_entry_size; + __u16 num_sub_cqs; + __u8 flags; + __u8 reserved_58[5]; +}; + +enum { + EFA_CREATE_CQ_RESP_DB_OFF = 1 << 0, +}; + +struct efa_ibv_create_cq_resp { + __u32 comp_mask; + __u8 reserved_20[4]; + __aligned_u64 q_mmap_key; + __aligned_u64 q_mmap_size; + __u16 cq_idx; + __u8 reserved_d0[2]; + __u32 db_off; + __aligned_u64 db_mmap_key; +}; + +enum { + EFA_QP_DRIVER_TYPE_SRD = 0, +}; + +enum { + EFA_CREATE_QP_WITH_UNSOLICITED_WRITE_RECV = 1 << 0, + EFA_CREATE_QP_WITH_SQ_64_BIT_REQ_ID = 1 << 1, +}; + +struct efa_ibv_create_qp { + __u32 comp_mask; + __u32 rq_ring_size; /* bytes */ + __u32 sq_ring_size; /* bytes */ + __u32 driver_qp_type; + __u16 flags; + __u8 sl; + __u8 reserved_98[5]; +}; + +struct efa_ibv_create_qp_resp { + __u32 comp_mask; + /* the offset inside the page of the rq db */ + __u32 rq_db_offset; + /* the offset inside the page of the sq db */ + __u32 sq_db_offset; + /* the offset inside the page of descriptors buffer */ + __u32 llq_desc_offset; + __aligned_u64 rq_mmap_key; + __aligned_u64 rq_mmap_size; + __aligned_u64 rq_db_mmap_key; + __aligned_u64 sq_db_mmap_key; + __aligned_u64 llq_desc_mmap_key; + __u16 send_sub_cq_idx; + __u16 recv_sub_cq_idx; + __u8 reserved_1e0[4]; +}; + +struct efa_ibv_create_ah_resp { + __u32 comp_mask; + __u16 efa_address_handle; + __u8 reserved_30[2]; +}; + +enum { + EFA_QUERY_DEVICE_CAPS_RDMA_READ = 1 << 0, + EFA_QUERY_DEVICE_CAPS_RNR_RETRY = 1 << 1, + EFA_QUERY_DEVICE_CAPS_CQ_NOTIFICATIONS = 1 << 2, + EFA_QUERY_DEVICE_CAPS_CQ_WITH_SGID = 1 << 3, + EFA_QUERY_DEVICE_CAPS_DATA_POLLING_128 = 1 << 4, + EFA_QUERY_DEVICE_CAPS_RDMA_WRITE = 1 << 5, + EFA_QUERY_DEVICE_CAPS_UNSOLICITED_WRITE_RECV = 1 << 6, + EFA_QUERY_DEVICE_CAPS_CQ_WITH_EXT_MEM = 1 << 7, + EFA_QUERY_DEVICE_CAPS_COMP_CNTR = 1 << 8, + EFA_QUERY_DEVICE_CAPS_SQ_64_BIT_REQ_ID = 1 << 9, +}; + +struct efa_ibv_ex_query_device_resp { + __u32 comp_mask; + __u32 max_sq_wr; + __u32 max_rq_wr; + __u16 max_sq_sge; + __u16 max_rq_sge; + __u32 max_rdma_size; + __u32 device_caps; +}; + +enum { + EFA_QUERY_MR_VALIDITY_RECV_IC_ID = 1 << 0, + EFA_QUERY_MR_VALIDITY_RDMA_READ_IC_ID = 1 << 1, + EFA_QUERY_MR_VALIDITY_RDMA_RECV_IC_ID = 1 << 2, +}; + +enum efa_query_mr_attrs { + EFA_IB_ATTR_QUERY_MR_HANDLE = (1U << UVERBS_ID_NS_SHIFT), + EFA_IB_ATTR_QUERY_MR_RESP_IC_ID_VALIDITY, + EFA_IB_ATTR_QUERY_MR_RESP_RECV_IC_ID, + EFA_IB_ATTR_QUERY_MR_RESP_RDMA_READ_IC_ID, + EFA_IB_ATTR_QUERY_MR_RESP_RDMA_RECV_IC_ID, +}; + +enum efa_mr_methods { + EFA_IB_METHOD_MR_QUERY = (1U << UVERBS_ID_NS_SHIFT), +}; + +enum efa_comp_cntr_create_attrs { + EFA_IB_ATTR_CREATE_COMP_CNTR_COMP_BUFFER = (1U << UVERBS_ID_NS_SHIFT), + EFA_IB_ATTR_CREATE_COMP_CNTR_ERR_BUFFER, +}; + +#endif /* EFA_ABI_USER_H */ -- cgit v1.3.1