[PATCH OLK-5.10] NFSD: Defer sub-object cleanup in export put callbacks
From: Chuck Lever <chuck.lever@oracle.com> mainline inclusion from mainline-v7.0-rc5 commit 48db892356d6cb80f6942885545de4a6dd8d2a29 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/14130 CVE: CVE-2026-31404 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- svc_export_put() calls path_put() and auth_domain_put() immediately when the last reference drops, before the RCU grace period. RCU readers in e_show() and c_show() access both ex_path (via seq_path/d_path) and ex_client->name (via seq_escape) without holding a reference. If cache_clean removes the entry and drops the last reference concurrently, the sub-objects are freed while still in use, producing a NULL pointer dereference in d_path. Commit 2530766492ec ("nfsd: fix UAF when access ex_uuid or ex_stats") moved kfree of ex_uuid and ex_stats into the call_rcu callback, but left path_put() and auth_domain_put() running before the grace period because both may sleep and call_rcu callbacks execute in softirq context. Replace call_rcu/kfree_rcu with queue_rcu_work(), which defers the callback until after the RCU grace period and executes it in process context where sleeping is permitted. This allows path_put() and auth_domain_put() to be moved into the deferred callback alongside the other resource releases. Apply the same fix to expkey_put(), which has the identical pattern with ek_path and ek_client. A dedicated workqueue scopes the shutdown drain to only NFSD export release work items; flushing the shared system_unbound_wq would stall on unrelated work from other subsystems. nfsd_export_shutdown() uses rcu_barrier() followed by flush_workqueue() to ensure all deferred release callbacks complete before the export caches are destroyed. Reported-by: Misbah Anjum N <misanjum@linux.ibm.com> Closes: https://lore.kernel.org/linux-nfs/dcd371d3a95815a84ba7de52cef447b8@linux.ibm... Fixes: c224edca7af0 ("nfsd: no need get cache ref when protected by rcu") Fixes: 1b10f0b603c0 ("SUNRPC: no need get cache ref when protected by rcu") Cc: stable@vger.kernel.org Reviwed-by: Jeff Layton <jlayton@kernel.org> Reviewed-by: NeilBrown <neil@brown.name> Tested-by: Olga Kornievskaia <okorniev@redhat.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Conflicts: fs/nfsd/export.c fs/nfsd/export.h fs/nfsd/nfsctl.c [Commit 20ad856e4732 ("nfsd: report per-export stats") add EXP_STATS_COUNTERS_NUM in export_stats_reset(); commit 20ad856e4732 ("nfsd: report per-export stats") add "percpu_counter.h" in fs/nfsd/export.h; commit f7fb730cac9a ("NFSD: fix race between nfsd registration and exports_proc") move create_proc_exports_entry() down in init_nfsd().] Signed-off-by: Li Lingfeng <lilingfeng3@huawei.com> --- fs/nfsd/export.c | 63 +++++++++++++++++++++++++++++++++++++++++------- fs/nfsd/export.h | 7 ++++-- fs/nfsd/nfsctl.c | 8 +++++- 3 files changed, 66 insertions(+), 12 deletions(-) diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 0e1caf71296e..5eba1cd9a72e 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -36,19 +36,30 @@ * second map contains a reference to the entry in the first map. */ +static struct workqueue_struct *nfsd_export_wq; + #define EXPKEY_HASHBITS 8 #define EXPKEY_HASHMAX (1 << EXPKEY_HASHBITS) #define EXPKEY_HASHMASK (EXPKEY_HASHMAX -1) -static void expkey_put(struct kref *ref) +static void expkey_release(struct work_struct *work) { - struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); + struct svc_expkey *key = container_of(to_rcu_work(work), + struct svc_expkey, ek_rwork); if (test_bit(CACHE_VALID, &key->h.flags) && !test_bit(CACHE_NEGATIVE, &key->h.flags)) path_put(&key->ek_path); auth_domain_put(key->ek_client); - kfree_rcu(key, ek_rcu); + kfree(key); +} + +static void expkey_put(struct kref *ref) +{ + struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); + + INIT_RCU_WORK(&key->ek_rwork, expkey_release); + queue_rcu_work(nfsd_export_wq, &key->ek_rwork); } static int expkey_upcall(struct cache_detail *cd, struct cache_head *h) @@ -331,11 +342,13 @@ static void nfsd4_fslocs_free(struct nfsd4_fs_locations *fsloc) fsloc->locations = NULL; } -static void svc_export_release(struct rcu_head *rcu_head) +static void svc_export_release(struct work_struct *work) { - struct svc_export *exp = container_of(rcu_head, struct svc_export, - ex_rcu); + struct svc_export *exp = container_of(to_rcu_work(work), + struct svc_export, ex_rwork); + path_put(&exp->ex_path); + auth_domain_put(exp->ex_client); nfsd4_fslocs_free(&exp->ex_fslocs); kfree(exp->ex_uuid); kfree(exp); @@ -345,9 +358,8 @@ static void svc_export_put(struct kref *ref) { struct svc_export *exp = container_of(ref, struct svc_export, h.ref); - path_put(&exp->ex_path); - auth_domain_put(exp->ex_client); - call_rcu(&exp->ex_rcu, svc_export_release); + INIT_RCU_WORK(&exp->ex_rwork, svc_export_release); + queue_rcu_work(nfsd_export_wq, &exp->ex_rwork); } static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h) @@ -1268,6 +1280,36 @@ const struct seq_operations nfs_exports_op = { .show = e_show, }; +/** + * nfsd_export_wq_init - allocate the export release workqueue + * + * Called once at module load. The workqueue runs deferred svc_export and + * svc_expkey release work scheduled by queue_rcu_work() in the cache put + * callbacks. + * + * Return values: + * %0: workqueue allocated + * %-ENOMEM: allocation failed + */ +int nfsd_export_wq_init(void) +{ + nfsd_export_wq = alloc_workqueue("nfsd_export", WQ_UNBOUND, 0); + if (!nfsd_export_wq) + return -ENOMEM; + return 0; +} + +/** + * nfsd_export_wq_shutdown - drain and free the export release workqueue + * + * Called once at module unload. Per-namespace teardown in + * nfsd_export_shutdown() has already drained all deferred work. + */ +void nfsd_export_wq_shutdown(void) +{ + destroy_workqueue(nfsd_export_wq); +} + /* * Initialize the exports module. */ @@ -1329,6 +1371,9 @@ nfsd_export_shutdown(struct net *net) cache_unregister_net(nn->svc_expkey_cache, net); cache_unregister_net(nn->svc_export_cache, net); + /* Drain deferred export and expkey release work. */ + rcu_barrier(); + flush_workqueue(nfsd_export_wq); cache_destroy_net(nn->svc_expkey_cache, net); cache_destroy_net(nn->svc_export_cache, net); svcauth_unix_purge(net); diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index e7daa1f246f0..d87fd4b57ea2 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -6,6 +6,7 @@ #define NFSD_EXPORT_H #include <linux/sunrpc/cache.h> +#include <linux/workqueue.h> #include <uapi/linux/nfsd/export.h> #include <linux/nfs4.h> @@ -61,7 +62,7 @@ struct svc_export { u32 ex_layout_types; struct nfsd4_deviceid_map *ex_devid_map; struct cache_detail *cd; - struct rcu_head ex_rcu; + struct rcu_work ex_rwork; }; /* an "export key" (expkey) maps a filehandlefragement to an @@ -76,7 +77,7 @@ struct svc_expkey { u32 ek_fsid[6]; struct path ek_path; - struct rcu_head ek_rcu; + struct rcu_work ek_rwork; }; #define EX_ISSYNC(exp) (!((exp)->ex_flags & NFSEXP_ASYNC)) @@ -89,6 +90,8 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp); /* * Function declarations */ +int nfsd_export_wq_init(void); +void nfsd_export_wq_shutdown(void); int nfsd_export_init(struct net *); void nfsd_export_shutdown(struct net *); void nfsd_export_flush(struct net *); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index e84c8cf8e2c0..7ede258033a1 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1529,9 +1529,12 @@ static int __init init_nfsd(void) if (retval) goto out_free_stat; nfsd_lockd_init(); /* lockd->nfsd callbacks */ - retval = create_proc_exports_entry(); + retval = nfsd_export_wq_init(); if (retval) goto out_free_lockd; + retval = create_proc_exports_entry(); + if (retval) + goto out_free_export_wq; retval = register_pernet_subsys(&nfsd_net_ops); if (retval < 0) goto out_free_exports; @@ -1549,6 +1552,8 @@ static int __init init_nfsd(void) out_free_exports: remove_proc_entry("fs/nfs/exports", NULL); remove_proc_entry("fs/nfs", NULL); +out_free_export_wq: + nfsd_export_wq_shutdown(); out_free_lockd: nfsd_lockd_shutdown(); nfsd_drc_slab_free(); @@ -1566,6 +1571,7 @@ static void __exit exit_nfsd(void) unregister_filesystem(&nfsd_fs_type); unregister_cld_notifier(); unregister_pernet_subsys(&nfsd_net_ops); + nfsd_export_wq_shutdown(); nfsd_drc_slab_free(); remove_proc_entry("fs/nfs/exports", NULL); remove_proc_entry("fs/nfs", NULL); -- 2.52.0
反馈: 您发送到kernel@openeuler.org的补丁/补丁集,已成功转换为PR! PR链接地址: https://atomgit.com/openeuler/kernel/merge_requests/22094 邮件列表地址:https://mailweb.openeuler.org/archives/list/kernel@openeuler.org/message/OED... FeedBack: The patch(es) which you have sent to kernel@openeuler.org mailing list has been converted to a pull request successfully! Pull request link: https://atomgit.com/openeuler/kernel/merge_requests/22094 Mailing list address: https://mailweb.openeuler.org/archives/list/kernel@openeuler.org/message/OED...
participants (2)
-
Li Lingfeng -
patchwork bot