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 --- fs/afs/write.c | 308 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 308 insertions(+) create mode 100644 fs/afs/write.c (limited to 'fs/afs/write.c') diff --git a/fs/afs/write.c b/fs/afs/write.c new file mode 100644 index 000000000..7f34b9397 --- /dev/null +++ b/fs/afs/write.c @@ -0,0 +1,308 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* handling of writes to regular files and writing back to the server + * + * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + +/* + * completion of write to server + */ +static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsigned int len) +{ + _enter("{%llx:%llu},{%x @%llx}", + vnode->fid.vid, vnode->fid.vnode, len, start); + + afs_prune_wb_keys(vnode); + _leave(""); +} + +/* + * Find a key to use for the writeback. We cached the keys used to author the + * writes on the vnode. wreq->netfs_priv2 will contain the last writeback key + * record used or NULL and we need to start from there if it's set. + * wreq->netfs_priv will be set to the key itself or NULL. + */ +static void afs_get_writeback_key(struct netfs_io_request *wreq) +{ + struct afs_wb_key *wbk, *old = wreq->netfs_priv2; + struct afs_vnode *vnode = AFS_FS_I(wreq->inode); + + key_put(wreq->netfs_priv); + wreq->netfs_priv = NULL; + wreq->netfs_priv2 = NULL; + + spin_lock(&vnode->wb_lock); + if (old) + wbk = list_next_entry(old, vnode_link); + else + wbk = list_first_entry(&vnode->wb_keys, struct afs_wb_key, vnode_link); + + list_for_each_entry_from(wbk, &vnode->wb_keys, vnode_link) { + _debug("wbk %u", key_serial(wbk->key)); + if (key_validate(wbk->key) == 0) { + refcount_inc(&wbk->usage); + wreq->netfs_priv = key_get(wbk->key); + wreq->netfs_priv2 = wbk; + _debug("USE WB KEY %u", key_serial(wbk->key)); + break; + } + } + + spin_unlock(&vnode->wb_lock); + + afs_put_wb_key(old); +} + +static void afs_store_data_success(struct afs_operation *op) +{ + struct afs_vnode *vnode = op->file[0].vnode; + + op->ctime = op->file[0].scb.status.mtime_client; + afs_vnode_commit_status(op, &op->file[0]); + if (!afs_op_error(op)) { + afs_pages_written_back(vnode, op->store.pos, op->store.size); + afs_stat_v(vnode, n_stores); + atomic_long_add(op->store.size, &afs_v2net(vnode)->n_store_bytes); + } +} + +static const struct afs_operation_ops afs_store_data_operation = { + .issue_afs_rpc = afs_fs_store_data, + .issue_yfs_rpc = yfs_fs_store_data, + .success = afs_store_data_success, +}; + +/* + * Prepare a subrequest to write to the server. This sets the max_len + * parameter. + */ +void afs_prepare_write(struct netfs_io_subrequest *subreq) +{ + struct netfs_io_stream *stream = &subreq->rreq->io_streams[subreq->stream_nr]; + + //if (test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) + // subreq->max_len = 512 * 1024; + //else + stream->sreq_max_len = 256 * 1024 * 1024; +} + +/* + * Issue a subrequest to write to the server. + */ +static void afs_issue_write_worker(struct work_struct *work) +{ + struct netfs_io_subrequest *subreq = container_of(work, struct netfs_io_subrequest, work); + struct netfs_io_request *wreq = subreq->rreq; + struct afs_operation *op; + struct afs_vnode *vnode = AFS_FS_I(wreq->inode); + unsigned long long pos = subreq->start + subreq->transferred; + size_t len = subreq->len - subreq->transferred; + int ret = -ENOKEY; + + _enter("R=%x[%x],%s{%llx:%llu.%u},%llx,%zx", + wreq->debug_id, subreq->debug_index, + vnode->volume->name, + vnode->fid.vid, + vnode->fid.vnode, + vnode->fid.unique, + pos, len); + +#if 0 // Error injection + if (subreq->debug_index == 3) + return netfs_write_subrequest_terminated(subreq, -ENOANO); + + if (!subreq->retry_count) { + set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + return netfs_write_subrequest_terminated(subreq, -EAGAIN); + } +#endif + + op = afs_alloc_operation(wreq->netfs_priv, vnode->volume); + if (IS_ERR(op)) + return netfs_write_subrequest_terminated(subreq, -EAGAIN); + + afs_op_set_vnode(op, 0, vnode); + op->file[0].dv_delta = 1; + op->file[0].modification = true; + op->store.pos = pos; + op->store.size = len; + op->flags |= AFS_OPERATION_UNINTR; + op->ops = &afs_store_data_operation; + + afs_begin_vnode_operation(op); + + op->store.write_iter = &subreq->io_iter; + op->store.i_size = umax(pos + len, netfs_read_remote_i_size(&vnode->netfs.inode)); + op->mtime = inode_get_mtime(&vnode->netfs.inode); + + afs_wait_for_operation(op); + ret = afs_put_operation(op); + switch (ret) { + case 0: + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + break; + case -EACCES: + case -EPERM: + case -ENOKEY: + case -EKEYEXPIRED: + case -EKEYREJECTED: + case -EKEYREVOKED: + /* If there are more keys we can try, use the retry algorithm + * to rotate the keys. + */ + if (wreq->netfs_priv2) + set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + break; + } + + netfs_write_subrequest_terminated(subreq, ret < 0 ? ret : subreq->len); +} + +void afs_issue_write(struct netfs_io_subrequest *subreq) +{ + subreq->work.func = afs_issue_write_worker; + if (!queue_work(system_dfl_wq, &subreq->work)) + WARN_ON_ONCE(1); +} + +/* + * Writeback calls this when it finds a folio that needs uploading. This isn't + * called if writeback only has copy-to-cache to deal with. + */ +void afs_begin_writeback(struct netfs_io_request *wreq) +{ + if (S_ISREG(wreq->inode->i_mode)) + afs_get_writeback_key(wreq); +} + +/* + * Prepare to retry the writes in request. Use this to try rotating the + * available writeback keys. + */ +void afs_retry_request(struct netfs_io_request *wreq, struct netfs_io_stream *stream) +{ + struct netfs_io_subrequest *subreq = + list_first_entry(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); + + switch (wreq->origin) { + case NETFS_READAHEAD: + case NETFS_READPAGE: + case NETFS_READ_GAPS: + case NETFS_READ_SINGLE: + case NETFS_READ_FOR_WRITE: + case NETFS_UNBUFFERED_READ: + case NETFS_DIO_READ: + return; + default: + break; + } + + switch (subreq->error) { + case -EACCES: + case -EPERM: + case -ENOKEY: + case -EKEYEXPIRED: + case -EKEYREJECTED: + case -EKEYREVOKED: + afs_get_writeback_key(wreq); + if (!wreq->netfs_priv) + stream->failed = true; + break; + } +} + +/* + * write some of the pending data back to the server + */ +int afs_writepages(struct address_space *mapping, struct writeback_control *wbc) +{ + struct afs_vnode *vnode = AFS_FS_I(mapping->host); + int ret; + + /* We have to be careful as we can end up racing with setattr() + * truncating the pagecache since the caller doesn't take a lock here + * to prevent it. + */ + if (wbc->sync_mode == WB_SYNC_ALL) + down_read(&vnode->validate_lock); + else if (!down_read_trylock(&vnode->validate_lock)) + return 0; + + ret = netfs_writepages(mapping, wbc); + up_read(&vnode->validate_lock); + return ret; +} + +/* + * flush any dirty pages for this process, and check for write errors. + * - the return status from this call provides a reliable indication of + * whether any write errors occurred for this process. + */ +int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync) +{ + struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); + struct afs_file *af = file->private_data; + int ret; + + _enter("{%llx:%llu},{n=%pD},%d", + vnode->fid.vid, vnode->fid.vnode, file, + datasync); + + ret = afs_validate(vnode, af->key); + if (ret < 0) + return ret; + + return file_write_and_wait_range(file, start, end); +} + +/* + * notification that a previously read-only page is about to become writable + * - if it returns an error, the caller will deliver a bus error signal + */ +vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) +{ + struct file *file = vmf->vma->vm_file; + + if (afs_validate(AFS_FS_I(file_inode(file)), afs_file_key(file)) < 0) + return VM_FAULT_SIGBUS; + return netfs_page_mkwrite(vmf, NULL); +} + +/* + * Prune the keys cached for writeback. The caller must hold vnode->wb_lock. + */ +void afs_prune_wb_keys(struct afs_vnode *vnode) +{ + LIST_HEAD(graveyard); + struct afs_wb_key *wbk, *tmp; + + /* Discard unused keys */ + spin_lock(&vnode->wb_lock); + + if (!mapping_tagged(&vnode->netfs.inode.i_data, PAGECACHE_TAG_WRITEBACK) && + !mapping_tagged(&vnode->netfs.inode.i_data, PAGECACHE_TAG_DIRTY)) { + list_for_each_entry_safe(wbk, tmp, &vnode->wb_keys, vnode_link) { + if (refcount_read(&wbk->usage) == 1) + list_move(&wbk->vnode_link, &graveyard); + } + } + + spin_unlock(&vnode->wb_lock); + + while (!list_empty(&graveyard)) { + wbk = list_entry(graveyard.next, struct afs_wb_key, vnode_link); + list_del(&wbk->vnode_link); + afs_put_wb_key(wbk); + } +} -- cgit v1.3.1