From 3f1fe48a36b0b6722dc3fd421d93512bac138e9a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 2 Oct 2026 12:17:24 -0700 Subject: Merge tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux Pull io_uring fixes from Jens Axboe: - Fix a task_work add use-after-free with SQPOLL. The sqpoll thread could pop and complete the last request while io_req_normal_work_add() was still looking at them after the mpscq push. Use the same approach as DEFER_TASKRUN to protect from that, holding an RCU read lock across the add, and have exit wait for an RCU grace period for SQPOLL rings as well. - CQE32 ring fixes: correct the free entry check for 32b CQEs, zero the big_cqe for aux CQEs, and only post the dummy skip CQE on CQE_MIXED rings - Mark the source filter table as COW when cloning bpf filters, so registering another filter on the source doesn't modify the shared table in place - Initialize the task context before running the BPF loop - Requeue zcrx multishot receives stopped by a local resource - End a TX_TIMESTAMP multishot cmd when the CQ is full (lollipopkit) * tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: io_uring: fix task_work add use-after-free with SQPOLL io_uring/cmd_net: end TX_TIMESTAMP multishot when the CQ is full io_uring/zcrx: requeue multishot receives stopped by a local resource io_uring: initialize task context before running the BPF loop io_uring: zero big_cqe for aux CQEs on CQE32 rings io_uring: fix free entry check for 32b CQEs on CQE32 rings io_uring: only post the dummy skip CQE on CQE_MIXED rings io_uring/bpf_filter: mark source as COW when cloning filters --- net/ceph/msgpool.c | 94 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 94 insertions(+) create mode 100644 net/ceph/msgpool.c (limited to 'net/ceph/msgpool.c') diff --git a/net/ceph/msgpool.c b/net/ceph/msgpool.c new file mode 100644 index 000000000..e3ecb80cd --- /dev/null +++ b/net/ceph/msgpool.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0 +#include + +#include +#include +#include +#include + +#include +#include + +static void *msgpool_alloc(gfp_t gfp_mask, void *arg) +{ + struct ceph_msgpool *pool = arg; + struct ceph_msg *msg; + + msg = ceph_msg_new2(pool->type, pool->front_len, pool->max_data_items, + gfp_mask, true); + if (!msg) { + dout("msgpool_alloc %s failed\n", pool->name); + } else { + dout("msgpool_alloc %s %p\n", pool->name, msg); + msg->pool = pool; + } + return msg; +} + +static void msgpool_free(void *element, void *arg) +{ + struct ceph_msgpool *pool = arg; + struct ceph_msg *msg = element; + + dout("msgpool_release %s %p\n", pool->name, msg); + msg->pool = NULL; + ceph_msg_put(msg); +} + +int ceph_msgpool_init(struct ceph_msgpool *pool, int type, + int front_len, int max_data_items, int size, + const char *name) +{ + dout("msgpool %s init\n", name); + pool->type = type; + pool->front_len = front_len; + pool->max_data_items = max_data_items; + pool->pool = mempool_create(size, msgpool_alloc, msgpool_free, pool); + if (!pool->pool) + return -ENOMEM; + pool->name = name; + return 0; +} + +void ceph_msgpool_destroy(struct ceph_msgpool *pool) +{ + dout("msgpool %s destroy\n", pool->name); + mempool_destroy(pool->pool); +} + +struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, int front_len, + int max_data_items) +{ + struct ceph_msg *msg; + + if (front_len > pool->front_len || + max_data_items > pool->max_data_items) { + pr_warn_ratelimited("%s need %d/%d, pool %s has %d/%d\n", + __func__, front_len, max_data_items, pool->name, + pool->front_len, pool->max_data_items); + WARN_ON_ONCE(1); + + /* try to alloc a fresh message */ + return ceph_msg_new2(pool->type, front_len, max_data_items, + GFP_NOFS, false); + } + + msg = mempool_alloc(pool->pool, GFP_NOFS); + dout("msgpool_get %s %p\n", pool->name, msg); + return msg; +} + +void ceph_msgpool_put(struct ceph_msgpool *pool, struct ceph_msg *msg) +{ + dout("msgpool_put %s %p\n", pool->name, msg); + + /* reset msg front_len; user may have changed it */ + msg->front.iov_len = pool->front_len; + msg->hdr.front_len = cpu_to_le32(pool->front_len); + + msg->data_length = 0; + msg->num_data_items = 0; + + kref_init(&msg->kref); /* retake single ref */ + mempool_free(msg, pool->pool); +} -- cgit v1.3.1