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/nfs/pnfs_dev.c | 381 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 381 insertions(+) create mode 100644 fs/nfs/pnfs_dev.c (limited to 'fs/nfs/pnfs_dev.c') diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c new file mode 100644 index 000000000..274abdd6d --- /dev/null +++ b/fs/nfs/pnfs_dev.c @@ -0,0 +1,381 @@ +/* + * Device operations for the pnfs client. + * + * Copyright (c) 2002 + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand + * Garth Goodson + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#include +#include +#include "nfs4session.h" +#include "internal.h" +#include "pnfs.h" + +#include "nfs4trace.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS + +/* + * Device ID RCU cache. A device ID is unique per server and layout type. + */ +#define NFS4_DEVICE_ID_HASH_BITS 5 +#define NFS4_DEVICE_ID_HASH_SIZE (1 << NFS4_DEVICE_ID_HASH_BITS) +#define NFS4_DEVICE_ID_HASH_MASK (NFS4_DEVICE_ID_HASH_SIZE - 1) + + +static struct hlist_head nfs4_deviceid_cache[NFS4_DEVICE_ID_HASH_SIZE]; +static DEFINE_SPINLOCK(nfs4_deviceid_lock); + +#ifdef NFS_DEBUG +void +nfs4_print_deviceid(const struct nfs4_deviceid *id) +{ + u32 *p = (u32 *)id; + + dprintk("%s: device id= [%x%x%x%x]\n", __func__, + p[0], p[1], p[2], p[3]); +} +EXPORT_SYMBOL_GPL(nfs4_print_deviceid); +#endif + +static inline u32 +nfs4_deviceid_hash(const struct nfs4_deviceid *id) +{ + unsigned char *cptr = (unsigned char *)id->data; + unsigned int nbytes = NFS4_DEVICEID4_SIZE; + u32 x = 0; + + while (nbytes--) { + x *= 37; + x += *cptr++; + } + return x & NFS4_DEVICE_ID_HASH_MASK; +} + +static struct nfs4_deviceid_node * +_lookup_deviceid(const struct pnfs_layoutdriver_type *ld, + const struct nfs_client *clp, const struct nfs4_deviceid *id, + long hash) +{ + struct nfs4_deviceid_node *d; + + hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[hash], node) + if (d->ld == ld && d->nfs_client == clp && + !memcmp(&d->deviceid, id, sizeof(*id))) { + if (atomic_read(&d->ref)) + return d; + else + continue; + } + return NULL; +} + +static struct nfs4_deviceid_node * +nfs4_get_device_info(struct nfs_server *server, + const struct nfs4_deviceid *dev_id, + const struct cred *cred, gfp_t gfp_flags) +{ + struct nfs4_deviceid_node *d = NULL; + struct pnfs_device *pdev = NULL; + struct page **pages = NULL; + u32 max_resp_sz; + int max_pages; + int rc, i; + + /* + * Use the session max response size as the basis for setting + * GETDEVICEINFO's maxcount + */ + max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; + max_pages = nfs_page_array_len(0, max_resp_sz); + dprintk("%s: server %p max_resp_sz %u max_pages %d\n", + __func__, server, max_resp_sz, max_pages); + + pdev = kzalloc_obj(*pdev, gfp_flags); + if (!pdev) + return NULL; + + pages = kzalloc_objs(struct page *, max_pages, gfp_flags); + if (!pages) + goto out_free_pdev; + + for (i = 0; i < max_pages; i++) { + pages[i] = alloc_page(gfp_flags); + if (!pages[i]) + goto out_free_pages; + } + + memcpy(&pdev->dev_id, dev_id, sizeof(*dev_id)); + pdev->layout_type = server->pnfs_curr_ld->id; + pdev->pages = pages; + pdev->pgbase = 0; + pdev->pglen = max_resp_sz; + pdev->mincount = 0; + pdev->maxcount = max_resp_sz - nfs41_maxgetdevinfo_overhead; + + rc = nfs4_proc_getdeviceinfo(server, pdev, cred); + dprintk("%s getdevice info returns %d\n", __func__, rc); + if (rc) + goto out_free_pages; + + /* + * Found new device, need to decode it and then add it to the + * list of known devices for this mountpoint. + */ + d = server->pnfs_curr_ld->alloc_deviceid_node(server, pdev, + gfp_flags); + if (d && pdev->nocache) + set_bit(NFS_DEVICEID_NOCACHE, &d->flags); + +out_free_pages: + while (--i >= 0) + __free_page(pages[i]); + kfree(pages); +out_free_pdev: + kfree(pdev); + dprintk("<-- %s d %p\n", __func__, d); + return d; +} + +/* + * Lookup a deviceid in cache and get a reference count on it if found + * + * @clp nfs_client associated with deviceid + * @id deviceid to look up + */ +static struct nfs4_deviceid_node * +__nfs4_find_get_deviceid(struct nfs_server *server, + const struct nfs4_deviceid *id, long hash) +{ + struct nfs4_deviceid_node *d; + + rcu_read_lock(); + d = _lookup_deviceid(server->pnfs_curr_ld, server->nfs_client, id, + hash); + if (d != NULL && !atomic_inc_not_zero(&d->ref)) + d = NULL; + rcu_read_unlock(); + return d; +} + +struct nfs4_deviceid_node * +nfs4_find_get_deviceid(struct nfs_server *server, + const struct nfs4_deviceid *id, const struct cred *cred, + gfp_t gfp_mask) +{ + long hash = nfs4_deviceid_hash(id); + struct nfs4_deviceid_node *d, *new; + + d = __nfs4_find_get_deviceid(server, id, hash); + if (d) + goto found; + + new = nfs4_get_device_info(server, id, cred, gfp_mask); + if (!new) { + trace_nfs4_find_deviceid(server, id, -ENOENT); + return new; + } + + spin_lock(&nfs4_deviceid_lock); + d = __nfs4_find_get_deviceid(server, id, hash); + if (d) { + spin_unlock(&nfs4_deviceid_lock); + server->pnfs_curr_ld->free_deviceid_node(new); + } else { + atomic_inc(&new->ref); + hlist_add_head_rcu(&new->node, &nfs4_deviceid_cache[hash]); + spin_unlock(&nfs4_deviceid_lock); + d = new; + } +found: + trace_nfs4_find_deviceid(server, id, 0); + return d; +} +EXPORT_SYMBOL_GPL(nfs4_find_get_deviceid); + +/* + * Remove a deviceid from cache + * + * @clp nfs_client associated with deviceid + * @id the deviceid to unhash + * + * @ret the unhashed node, if found and dereferenced to zero, NULL otherwise. + */ +void +nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *ld, + const struct nfs_client *clp, const struct nfs4_deviceid *id) +{ + struct nfs4_deviceid_node *d; + + spin_lock(&nfs4_deviceid_lock); + rcu_read_lock(); + d = _lookup_deviceid(ld, clp, id, nfs4_deviceid_hash(id)); + rcu_read_unlock(); + if (!d) { + spin_unlock(&nfs4_deviceid_lock); + return; + } + hlist_del_init_rcu(&d->node); + clear_bit(NFS_DEVICEID_NOCACHE, &d->flags); + spin_unlock(&nfs4_deviceid_lock); + + /* balance the initial ref set in pnfs_insert_deviceid */ + nfs4_put_deviceid_node(d); +} +EXPORT_SYMBOL_GPL(nfs4_delete_deviceid); + +void +nfs4_init_deviceid_node(struct nfs4_deviceid_node *d, struct nfs_server *server, + const struct nfs4_deviceid *id) +{ + INIT_HLIST_NODE(&d->node); + INIT_HLIST_NODE(&d->tmpnode); + d->ld = server->pnfs_curr_ld; + d->nfs_client = server->nfs_client; + d->flags = 0; + d->deviceid = *id; + atomic_set(&d->ref, 1); +} +EXPORT_SYMBOL_GPL(nfs4_init_deviceid_node); + +/* + * Dereference a deviceid node and delete it when its reference count drops + * to zero. + * + * @d deviceid node to put + * + * return true iff the node was deleted + * Note that since the test for d->ref == 0 is sufficient to establish + * that the node is no longer hashed in the global device id cache. + */ +bool +nfs4_put_deviceid_node(struct nfs4_deviceid_node *d) +{ + if (test_bit(NFS_DEVICEID_NOCACHE, &d->flags)) { + if (atomic_add_unless(&d->ref, -1, 2)) + return false; + nfs4_delete_deviceid(d->ld, d->nfs_client, &d->deviceid); + } + if (!atomic_dec_and_test(&d->ref)) + return false; + trace_nfs4_deviceid_free(d->nfs_client, &d->deviceid); + d->ld->free_deviceid_node(d); + return true; +} +EXPORT_SYMBOL_GPL(nfs4_put_deviceid_node); + +void +nfs4_mark_deviceid_available(struct nfs4_deviceid_node *node) +{ + if (test_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags)) { + clear_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags); + smp_mb__after_atomic(); + } +} +EXPORT_SYMBOL_GPL(nfs4_mark_deviceid_available); + +void +nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node) +{ + node->timestamp_unavailable = jiffies; + smp_mb__before_atomic(); + set_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags); + smp_mb__after_atomic(); +} +EXPORT_SYMBOL_GPL(nfs4_mark_deviceid_unavailable); + +bool +nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node) +{ + if (test_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags)) { + unsigned long start, end; + + end = jiffies; + start = end - PNFS_DEVICE_RETRY_TIMEOUT; + if (time_in_range(node->timestamp_unavailable, start, end)) + return true; + clear_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags); + smp_mb__after_atomic(); + } + return false; +} +EXPORT_SYMBOL_GPL(nfs4_test_deviceid_unavailable); + +static void +_deviceid_purge_client(const struct nfs_client *clp, long hash) +{ + struct nfs4_deviceid_node *d; + HLIST_HEAD(tmp); + + spin_lock(&nfs4_deviceid_lock); + rcu_read_lock(); + hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[hash], node) + if (d->nfs_client == clp && atomic_read(&d->ref)) { + hlist_del_init_rcu(&d->node); + hlist_add_head(&d->tmpnode, &tmp); + clear_bit(NFS_DEVICEID_NOCACHE, &d->flags); + } + rcu_read_unlock(); + spin_unlock(&nfs4_deviceid_lock); + + if (hlist_empty(&tmp)) + return; + + while (!hlist_empty(&tmp)) { + d = hlist_entry(tmp.first, struct nfs4_deviceid_node, tmpnode); + hlist_del(&d->tmpnode); + nfs4_put_deviceid_node(d); + } +} + +void +nfs4_deviceid_purge_client(const struct nfs_client *clp) +{ + long h; + + if (!(clp->cl_exchange_flags & EXCHGID4_FLAG_USE_PNFS_MDS)) + return; + for (h = 0; h < NFS4_DEVICE_ID_HASH_SIZE; h++) + _deviceid_purge_client(clp, h); +} + +/* + * Stop use of all deviceids associated with an nfs_client + */ +void +nfs4_deviceid_mark_client_invalid(struct nfs_client *clp) +{ + struct nfs4_deviceid_node *d; + int i; + + rcu_read_lock(); + for (i = 0; i < NFS4_DEVICE_ID_HASH_SIZE; i ++){ + hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[i], node) + if (d->nfs_client == clp) + set_bit(NFS_DEVICEID_INVALID, &d->flags); + } + rcu_read_unlock(); +} -- cgit v1.3.1