From bfa99e31d73034c043d206e484545d4a535e9660 Mon Sep 17 00:00:00 2001 From: Todd Kjos Date: Wed, 10 Nov 2021 15:00:36 -0800 Subject: [PATCH 01/17] binder: use cred instead of task for getsecid stable inclusion from stable-5.10.80 commit afbec52fbce006a775edb21f87ccae713bc0e7d6 category: bugfix issue: I51A19 CVE: CVE-2021-39686 Signed-off-by: gaochao --------------------------------------- binder: use cred instead of task for getsecid commit 4d5b5539742d2554591751b4248b0204d20dcc9d upstream. Use the 'struct cred' saved at binder_open() to lookup the security ID via security_cred_getsecid(). This ensures that the security context that opened binder is the one used to generate the secctx. Cc: stable@vger.kernel.org # 5.4+ Fixes: ec74136ded79 ("binder: create node flag to request sender's security context") Signed-off-by: Todd Kjos Suggested-by: Stephen Smalley Reported-by: kernel test robot Acked-by: Casey Schaufler Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 2 +- include/linux/security.h | 5 +++++ 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 2a3952925855..fb4e95c610b4 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -3090,7 +3090,7 @@ static void binder_transaction(struct binder_proc *proc, u32 secid; size_t added_size; - security_task_getsecid(proc->tsk, &secid); + security_cred_getsecid(proc->cred, &secid); ret = security_secid_to_secctx(secid, &secctx, &secctx_sz); if (ret) { return_error = BR_FAILED_REPLY; diff --git a/include/linux/security.h b/include/linux/security.h index 39642626a707..0d0dea602d6b 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1002,6 +1002,11 @@ static inline void security_transfer_creds(struct cred *new, { } +static inline void security_cred_getsecid(const struct cred *c, u32 *secid) +{ + *secid = 0; +} + static inline int security_kernel_act_as(struct cred *cred, u32 secid) { return 0; -- Gitee From 8d6f1edda2969249628e243c02378e17ecc320f2 Mon Sep 17 00:00:00 2001 From: Todd Kjos Date: Wed, 10 Nov 2021 15:00:35 -0800 Subject: [PATCH 02/17] binder: use cred instead of task for selinux checks stable inclusion from stable-5.10.80 commit 0d9f4ae7cd6f5283dd0e343265268c695ef592b0 category: bugfix issue: I51A19 CVE: CVE-2021-39686 Signed-off-by: gaochao --------------------------------------- binder: use cred instead of task for selinux checks commit 52f88693378a58094c538662ba652aff0253c4fe upstream. Since binder was integrated with selinux, it has passed 'struct task_struct' associated with the binder_proc to represent the source and target of transactions. The conversion of task to SID was then done in the hook implementations. It turns out that there are race conditions which can result in an incorrect security context being used. Fix by using the 'struct cred' saved during binder_open and pass it to the selinux subsystem. Cc: stable@vger.kernel.org # 5.14 (need backport for earlier stables) Fixes: 79af73079d75 ("Add security hooks to binder and implement the hooks for SELinux.") Suggested-by: Jann Horn Signed-off-by: Todd Kjos Acked-by: Casey Schaufler Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 12 ++++++------ include/linux/lsm_hook_defs.h | 14 +++++++------- include/linux/lsm_hooks.h | 14 +++++++------- include/linux/security.h | 28 +++++++++++++-------------- security/security.c | 14 +++++++------- security/selinux/hooks.c | 36 +++++++++++++++-------------------- 6 files changed, 56 insertions(+), 62 deletions(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index fb4e95c610b4..9813a5a62448 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2431,7 +2431,7 @@ static int binder_translate_binder(struct flat_binder_object *fp, ret = -EINVAL; goto done; } - if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) { + if (security_binder_transfer_binder(proc->cred, target_proc->cred)) { ret = -EPERM; goto done; } @@ -2477,7 +2477,7 @@ static int binder_translate_handle(struct flat_binder_object *fp, proc->pid, thread->pid, fp->handle); return -EINVAL; } - if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) { + if (security_binder_transfer_binder(proc->cred, target_proc->cred)) { ret = -EPERM; goto done; } @@ -2565,7 +2565,7 @@ static int binder_translate_fd(u32 fd, binder_size_t fd_offset, ret = -EBADF; goto err_fget; } - ret = security_binder_transfer_file(proc->tsk, target_proc->tsk, file); + ret = security_binder_transfer_file(proc->cred, target_proc->cred, file); if (ret < 0) { ret = -EPERM; goto err_security; @@ -2963,8 +2963,8 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_invalid_target_handle; } - if (security_binder_transaction(proc->tsk, - target_proc->tsk) < 0) { + if (security_binder_transaction(proc->cred, + target_proc->cred) < 0) { return_error = BR_FAILED_REPLY; return_error_param = -EPERM; return_error_line = __LINE__; @@ -4902,7 +4902,7 @@ static int binder_ioctl_set_ctx_mgr(struct file *filp, ret = -EBUSY; goto out; } - ret = security_binder_set_context_mgr(proc->tsk); + ret = security_binder_set_context_mgr(proc->cred); if (ret < 0) goto out; if (uid_valid(context->binder_context_mgr_uid)) { diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 32a940117e7a..a6a3d4ddfc2d 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -26,13 +26,13 @@ * #undef LSM_HOOK * }; */ -LSM_HOOK(int, 0, binder_set_context_mgr, struct task_struct *mgr) -LSM_HOOK(int, 0, binder_transaction, struct task_struct *from, - struct task_struct *to) -LSM_HOOK(int, 0, binder_transfer_binder, struct task_struct *from, - struct task_struct *to) -LSM_HOOK(int, 0, binder_transfer_file, struct task_struct *from, - struct task_struct *to, struct file *file) +LSM_HOOK(int, 0, binder_set_context_mgr, const struct cred *mgr) +LSM_HOOK(int, 0, binder_transaction, const struct cred *from, + const struct cred *to) +LSM_HOOK(int, 0, binder_transfer_binder, const struct cred *from, + const struct cred *to) +LSM_HOOK(int, 0, binder_transfer_file, const struct cred *from, + const struct cred *to, struct file *file) LSM_HOOK(int, 0, ptrace_access_check, struct task_struct *child, unsigned int mode) LSM_HOOK(int, 0, ptrace_traceme, struct task_struct *parent) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index c503f7ab8afb..a8531b37e6f5 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1288,22 +1288,22 @@ * * @binder_set_context_mgr: * Check whether @mgr is allowed to be the binder context manager. - * @mgr contains the task_struct for the task being registered. + * @mgr contains the struct cred for the current binder process. * Return 0 if permission is granted. * @binder_transaction: * Check whether @from is allowed to invoke a binder transaction call * to @to. - * @from contains the task_struct for the sending task. - * @to contains the task_struct for the receiving task. + * @from contains the struct cred for the sending process. + * @to contains the struct cred for the receiving process. * @binder_transfer_binder: * Check whether @from is allowed to transfer a binder reference to @to. - * @from contains the task_struct for the sending task. - * @to contains the task_struct for the receiving task. + * @from contains the struct cred for the sending process. + * @to contains the struct cred for the receiving process. * @binder_transfer_file: * Check whether @from is allowed to transfer @file to @to. - * @from contains the task_struct for the sending task. + * @from contains the struct cred for the sending process. * @file contains the struct file being transferred. - * @to contains the task_struct for the receiving task. + * @to contains the struct cred for the receiving process. * * @ptrace_access_check: * Check permission before allowing the current process to trace the diff --git a/include/linux/security.h b/include/linux/security.h index 0d0dea602d6b..3dfa626fdf97 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -253,13 +253,13 @@ extern int security_init(void); extern int early_security_init(void); /* Security operations */ -int security_binder_set_context_mgr(struct task_struct *mgr); -int security_binder_transaction(struct task_struct *from, - struct task_struct *to); -int security_binder_transfer_binder(struct task_struct *from, - struct task_struct *to); -int security_binder_transfer_file(struct task_struct *from, - struct task_struct *to, struct file *file); +int security_binder_set_context_mgr(const struct cred *mgr); +int security_binder_transaction(const struct cred *from, + const struct cred *to); +int security_binder_transfer_binder(const struct cred *from, + const struct cred *to); +int security_binder_transfer_file(const struct cred *from, + const struct cred *to, struct file *file); int security_ptrace_access_check(struct task_struct *child, unsigned int mode); int security_ptrace_traceme(struct task_struct *parent); int security_capget(struct task_struct *target, @@ -492,25 +492,25 @@ static inline int early_security_init(void) return 0; } -static inline int security_binder_set_context_mgr(struct task_struct *mgr) +static inline int security_binder_set_context_mgr(const struct cred *mgr) { return 0; } -static inline int security_binder_transaction(struct task_struct *from, - struct task_struct *to) +static inline int security_binder_transaction(const struct cred *from, + const struct cred *to) { return 0; } -static inline int security_binder_transfer_binder(struct task_struct *from, - struct task_struct *to) +static inline int security_binder_transfer_binder(const struct cred *from, + const struct cred *to) { return 0; } -static inline int security_binder_transfer_file(struct task_struct *from, - struct task_struct *to, +static inline int security_binder_transfer_file(const struct cred *from, + const struct cred *to, struct file *file) { return 0; diff --git a/security/security.c b/security/security.c index a28045dc9e7f..c11201dce8be 100644 --- a/security/security.c +++ b/security/security.c @@ -722,25 +722,25 @@ static void __init lsm_early_task(struct task_struct *task) /* Security operations */ -int security_binder_set_context_mgr(struct task_struct *mgr) +int security_binder_set_context_mgr(const struct cred *mgr) { return call_int_hook(binder_set_context_mgr, 0, mgr); } -int security_binder_transaction(struct task_struct *from, - struct task_struct *to) +int security_binder_transaction(const struct cred *from, + const struct cred *to) { return call_int_hook(binder_transaction, 0, from, to); } -int security_binder_transfer_binder(struct task_struct *from, - struct task_struct *to) +int security_binder_transfer_binder(const struct cred *from, + const struct cred *to) { return call_int_hook(binder_transfer_binder, 0, from, to); } -int security_binder_transfer_file(struct task_struct *from, - struct task_struct *to, struct file *file) +int security_binder_transfer_file(const struct cred *from, + const struct cred *to, struct file *file) { return call_int_hook(binder_transfer_file, 0, from, to, file); } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 227eb8967963..f32026bc96b4 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -2004,22 +2004,19 @@ static inline u32 open_file_to_av(struct file *file) /* Hook functions begin here. */ -static int selinux_binder_set_context_mgr(struct task_struct *mgr) +static int selinux_binder_set_context_mgr(const struct cred *mgr) { - u32 mysid = current_sid(); - u32 mgrsid = task_sid(mgr); - return avc_has_perm(&selinux_state, - mysid, mgrsid, SECCLASS_BINDER, + current_sid(), cred_sid(mgr), SECCLASS_BINDER, BINDER__SET_CONTEXT_MGR, NULL); } -static int selinux_binder_transaction(struct task_struct *from, - struct task_struct *to) +static int selinux_binder_transaction(const struct cred *from, + const struct cred *to) { u32 mysid = current_sid(); - u32 fromsid = task_sid(from); - u32 tosid = task_sid(to); + u32 fromsid = cred_sid(from); + u32 tosid = cred_sid(to); int rc; if (mysid != fromsid) { @@ -2030,27 +2027,24 @@ static int selinux_binder_transaction(struct task_struct *from, return rc; } - return avc_has_perm(&selinux_state, - fromsid, tosid, SECCLASS_BINDER, BINDER__CALL, - NULL); + return avc_has_perm(&selinux_state, fromsid, tosid, + SECCLASS_BINDER, BINDER__CALL, NULL); } -static int selinux_binder_transfer_binder(struct task_struct *from, - struct task_struct *to) +static int selinux_binder_transfer_binder(const struct cred *from, + const struct cred *to) { - u32 fromsid = task_sid(from); - u32 tosid = task_sid(to); - return avc_has_perm(&selinux_state, - fromsid, tosid, SECCLASS_BINDER, BINDER__TRANSFER, + cred_sid(from), cred_sid(to), + SECCLASS_BINDER, BINDER__TRANSFER, NULL); } -static int selinux_binder_transfer_file(struct task_struct *from, - struct task_struct *to, +static int selinux_binder_transfer_file(const struct cred *from, + const struct cred *to, struct file *file) { - u32 sid = task_sid(to); + u32 sid = cred_sid(to); struct file_security_struct *fsec = selinux_file(file); struct dentry *dentry = file->f_path.dentry; struct inode_security_struct *isec; -- Gitee From a23e645477f11dcc17c6b8fc44ff53fea951d0c0 Mon Sep 17 00:00:00 2001 From: Todd Kjos Date: Wed, 10 Nov 2021 15:00:34 -0800 Subject: [PATCH 03/17] binder: use euid from cred instead of using task stable inclusion from stable-5.10.80 commit bd9cea41ac6e08f615030dea28b23e12b7a2674f category: bugfix issue: I51A19 CVE:CVE-2021-39686 Signed-off-by: gaochao --------------------------------------- binder: use euid from cred instead of using task commit 29bc22ac5e5bc63275e850f0c8fc549e3d0e306b upstream. Save the 'struct cred' associated with a binder process at initial open to avoid potential race conditions when converting to an euid. Set a transaction's sender_euid from the 'struct cred' saved at binder_open() instead of looking up the euid from the binder proc's 'struct task'. This ensures the euid is associated with the security context that of the task that opened binder. Cc: stable@vger.kernel.org # 4.4+ Fixes: 457b9a6f09f0 ("Staging: android: add binder driver") Signed-off-by: Todd Kjos Suggested-by: Stephen Smalley Suggested-by: Jann Horn Acked-by: Casey Schaufler Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 9813a5a62448..09f40b993787 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -420,6 +420,9 @@ enum binder_deferred_state { * (invariant after initialized) * @tsk task_struct for group_leader of process * (invariant after initialized) + * @cred struct cred associated with the `struct file` + * in binder_open() + * (invariant after initialized) * @deferred_work_node: element for binder_deferred_list * (protected by binder_deferred_lock) * @deferred_work: bitmap of deferred work to perform @@ -465,6 +468,7 @@ struct binder_proc { struct list_head waiting_threads; int pid; struct task_struct *tsk; + const struct cred *cred; struct hlist_node deferred_work_node; int deferred_work; bool is_dead; @@ -3079,7 +3083,7 @@ static void binder_transaction(struct binder_proc *proc, t->from = thread; else t->from = NULL; - t->sender_euid = task_euid(proc->tsk); + t->sender_euid = proc->cred->euid; t->to_proc = target_proc; t->to_thread = target_thread; t->code = tr->code; @@ -4692,6 +4696,7 @@ static void binder_free_proc(struct binder_proc *proc) } binder_alloc_deferred_release(&proc->alloc); put_task_struct(proc->tsk); + put_cred(proc->cred); binder_stats_deleted(BINDER_STAT_PROC); kfree(proc); } @@ -5209,6 +5214,7 @@ static int binder_open(struct inode *nodp, struct file *filp) spin_lock_init(&proc->outer_lock); get_task_struct(current->group_leader); proc->tsk = current->group_leader; + proc->cred = get_cred(filp->f_cred); INIT_LIST_HEAD(&proc->todo); proc->default_priority = task_nice(current); /* binderfs stashes devices in i_private */ -- Gitee From 07db917b97bf2344e754d03731cd17f3ff6a931c Mon Sep 17 00:00:00 2001 From: Todd Kjos Date: Fri, 12 Nov 2021 10:07:20 -0800 Subject: [PATCH 04/17] binder: fix test regression due to sender_euid change stable inclusion from stable-5.10.83 commit 4402cf0402526f7c5befa97481be13b131797838 category: bugfix issue: I51A19 CVE: CVE-2021-39686 Signed-off-by: gaochao --------------------------------------- binder: fix test regression due to sender_euid change commit c21a80ca0684ec2910344d72556c816cb8940c01 upstream. This is a partial revert of commit 29bc22ac5e5b ("binder: use euid from cred instead of using task"). Setting sender_euid using proc->cred caused some Android system test regressions that need further investigation. It is a partial reversion because subsequent patches rely on proc->cred. Fixes: 29bc22ac5e5b ("binder: use euid from cred instead of using task") Cc: stable@vger.kernel.org # 4.4+ Acked-by: Christian Brauner Signed-off-by: Todd Kjos Change-Id: I9b1769a3510fed250bb21859ef8beebabe034c66 Link: https://lore.kernel.org/r/20211112180720.2858135-1-tkjos@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 09f40b993787..81cc40dcb7c2 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -3083,7 +3083,7 @@ static void binder_transaction(struct binder_proc *proc, t->from = thread; else t->from = NULL; - t->sender_euid = proc->cred->euid; + t->sender_euid = task_euid(proc->tsk); t->to_proc = target_proc; t->to_thread = target_thread; t->code = tr->code; -- Gitee From fded71d94fa159feb6e846acd81c5e52597a945a Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 8 Dec 2021 17:04:53 -0800 Subject: [PATCH 05/17] signalfd: use wake_up_pollfree() stable inclusion from stable-5.10.85 commit fc2f636ffc446d8e9530e441897f877922269051 category: bugfix issue: I51A19 CVE: CVE-2021-39698 Signed-off-by: gaochao --------------------------------------- signalfd: use wake_up_pollfree() commit 9537bae0da1f8d1e2361ab6d0479e8af7824e160 upstream. wake_up_poll() uses nr_exclusive=1, so it's not guaranteed to wake up all exclusive waiters. Yet, POLLFREE *must* wake up all waiters. epoll and aio poll are fortunately not affected by this, but it's very fragile. Thus, the new function wake_up_pollfree() has been introduced. Convert signalfd to use wake_up_pollfree(). Reported-by: Linus Torvalds Fixes: d80e731ecab4 ("epoll: introduce POLLFREE to flush ->signalfd_wqh before kfree()") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211209010455.42744-4-ebiggers@kernel.org Signed-off-by: Eric Biggers Signed-off-by: Greg Kroah-Hartman --- fs/signalfd.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/fs/signalfd.c b/fs/signalfd.c index 456046e15873..b94fb5f81797 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -35,17 +35,7 @@ void signalfd_cleanup(struct sighand_struct *sighand) { - wait_queue_head_t *wqh = &sighand->signalfd_wqh; - /* - * The lockless check can race with remove_wait_queue() in progress, - * but in this case its caller should run under rcu_read_lock() and - * sighand_cachep is SLAB_TYPESAFE_BY_RCU, we can safely return. - */ - if (likely(!waitqueue_active(wqh))) - return; - - /* wait_queue_entry_t->func(POLLFREE) should do remove_wait_queue() */ - wake_up_poll(wqh, EPOLLHUP | POLLFREE); + wake_up_pollfree(&sighand->signalfd_wqh); } struct signalfd_ctx { -- Gitee From 8d42c88e0b7e99532ede122814766ed9dddfe462 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 8 Dec 2021 17:04:52 -0800 Subject: [PATCH 06/17] binder: use wake_up_pollfree() stable inclusion from stable-5.10.85 commit 9f3acee7eac8d8690134b09ba55e2c12164d24ae category: bugfix issue: I51A19 CVE: CVE-2021-39698 Signed-off-by: gaochao --------------------------------------- binder: use wake_up_pollfree() commit a880b28a71e39013e357fd3adccd1d8a31bc69a8 upstream. wake_up_poll() uses nr_exclusive=1, so it's not guaranteed to wake up all exclusive waiters. Yet, POLLFREE *must* wake up all waiters. epoll and aio poll are fortunately not affected by this, but it's very fragile. Thus, the new function wake_up_pollfree() has been introduced. Convert binder to use wake_up_pollfree(). Reported-by: Linus Torvalds Fixes: f5cb779ba163 ("ANDROID: binder: remove waitqueue when thread exits.") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211209010455.42744-3-ebiggers@kernel.org Signed-off-by: Eric Biggers Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 81cc40dcb7c2..c2f0e00655a2 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -4773,23 +4773,20 @@ static int binder_thread_release(struct binder_proc *proc, __release(&t->lock); /* - * If this thread used poll, make sure we remove the waitqueue - * from any epoll data structures holding it with POLLFREE. - * waitqueue_active() is safe to use here because we're holding - * the inner lock. + * If this thread used poll, make sure we remove the waitqueue from any + * poll data structures holding it. */ - if ((thread->looper & BINDER_LOOPER_STATE_POLL) && - waitqueue_active(&thread->wait)) { - wake_up_poll(&thread->wait, EPOLLHUP | POLLFREE); - } + if (thread->looper & BINDER_LOOPER_STATE_POLL) + wake_up_pollfree(&thread->wait); binder_inner_proc_unlock(thread->proc); /* - * This is needed to avoid races between wake_up_poll() above and - * and ep_remove_waitqueue() called for other reasons (eg the epoll file - * descriptor being closed); ep_remove_waitqueue() holds an RCU read - * lock, so we can be sure it's done after calling synchronize_rcu(). + * This is needed to avoid races between wake_up_pollfree() above and + * someone else removing the last entry from the queue for other reasons + * (e.g. ep_remove_wait_queue() being called due to an epoll file + * descriptor being closed). Such other users hold an RCU read lock, so + * we can be sure they're done after we call synchronize_rcu(). */ if (thread->looper & BINDER_LOOPER_STATE_POLL) synchronize_rcu(); -- Gitee From a0a1bc56ff854d2343c0308d7a5c9d83d76d5027 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 8 Dec 2021 17:04:51 -0800 Subject: [PATCH 07/17] wait: add wake_up_pollfree() stable inclusion from stable-5.10.85 commit 8e04c8397bf98235b1aa41153717de7a05e652a2 category: bugfix issue: I51A19 CVE: CVE-2021-39698 Signed-off-by: gaochao --------------------------------------- wait: add wake_up_pollfree() commit 42288cb44c4b5fff7653bc392b583a2b8bd6a8c0 upstream. Several ->poll() implementations are special in that they use a waitqueue whose lifetime is the current task, rather than the struct file as is normally the case. This is okay for blocking polls, since a blocking poll occurs within one task; however, non-blocking polls require another solution. This solution is for the queue to be cleared before it is freed, using 'wake_up_poll(wq, EPOLLHUP | POLLFREE);'. However, that has a bug: wake_up_poll() calls __wake_up() with nr_exclusive=1. Therefore, if there are multiple "exclusive" waiters, and the wakeup function for the first one returns a positive value, only that one will be called. That's *not* what's needed for POLLFREE; POLLFREE is special in that it really needs to wake up everyone. Considering the three non-blocking poll systems: - io_uring poll doesn't handle POLLFREE at all, so it is broken anyway. - aio poll is unaffected, since it doesn't support exclusive waits. However, that's fragile, as someone could add this feature later. - epoll doesn't appear to be broken by this, since its wakeup function returns 0 when it sees POLLFREE. But this is fragile. Although there is a workaround (see epoll), it's better to define a function which always sends POLLFREE to all waiters. Add such a function. Also make it verify that the queue really becomes empty after all waiters have been woken up. Reported-by: Linus Torvalds Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211209010455.42744-2-ebiggers@kernel.org Signed-off-by: Eric Biggers Signed-off-by: Greg Kroah-Hartman --- include/linux/wait.h | 26 ++++++++++++++++++++++++++ kernel/sched/wait.c | 7 +++++++ 2 files changed, 33 insertions(+) diff --git a/include/linux/wait.h b/include/linux/wait.h index f8b0704968a1..9b8b0833100a 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -207,6 +207,7 @@ void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); +void __wake_up_pollfree(struct wait_queue_head *wq_head); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) @@ -235,6 +236,31 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); #define wake_up_interruptible_sync_poll_locked(x, m) \ __wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) +/** + * wake_up_pollfree - signal that a polled waitqueue is going away + * @wq_head: the wait queue head + * + * In the very rare cases where a ->poll() implementation uses a waitqueue whose + * lifetime is tied to a task rather than to the 'struct file' being polled, + * this function must be called before the waitqueue is freed so that + * non-blocking polls (e.g. epoll) are notified that the queue is going away. + * + * The caller must also RCU-delay the freeing of the wait_queue_head, e.g. via + * an explicit synchronize_rcu() or call_rcu(), or via SLAB_TYPESAFE_BY_RCU. + */ +static inline void wake_up_pollfree(struct wait_queue_head *wq_head) +{ + /* + * For performance reasons, we don't always take the queue lock here. + * Therefore, we might race with someone removing the last entry from + * the queue, and proceed while they still hold the queue lock. + * However, rcu_read_lock() is required to be held in such cases, so we + * can safely proceed with an RCU-delayed free. + */ + if (waitqueue_active(wq_head)) + __wake_up_pollfree(wq_head); +} + #define ___wait_cond_timeout(condition) \ ({ \ bool __cond = (condition); \ diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 21005b980a6b..a55642aa3f68 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -223,6 +223,13 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode) } EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ +void __wake_up_pollfree(struct wait_queue_head *wq_head) +{ + __wake_up(wq_head, TASK_NORMAL, 0, poll_to_key(EPOLLHUP | POLLFREE)); + /* POLLFREE must have cleared the queue. */ + WARN_ON_ONCE(waitqueue_active(wq_head)); +} + /* * Note: we use "set_current_state()" _after_ the wait-queue add, * because we need a memory barrier there on SMP, so that any -- Gitee From 1ed630879efd8399f903e5773c2a1a7f1c21b589 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 10 Dec 2021 15:48:04 -0800 Subject: [PATCH 08/17] aio: keep poll requests on waitqueue until completed stable inclusion from stable-5.10.85 commit e4d19740bccab792f16c7ca6fd1f9aea06193cb2 category: bugfix issue: I51A19 CVE: CVE-2021-39698 Signed-off-by: gaochao --------------------------------------- aio: keep poll requests on waitqueue until completed commit 363bee27e25804d8981dd1c025b4ad49dc39c530 upstream. Currently, aio_poll_wake() will always remove the poll request from the waitqueue. Then, if aio_poll_complete_work() sees that none of the polled events are ready and the request isn't cancelled, it re-adds the request to the waitqueue. (This can easily happen when polling a file that doesn't pass an event mask when waking up its waitqueue.) This is fundamentally broken for two reasons: 1. If a wakeup occurs between vfs_poll() and the request being re-added to the waitqueue, it will be missed because the request wasn't on the waitqueue at the time. Therefore, IOCB_CMD_POLL might never complete even if the polled file is ready. 2. When the request isn't on the waitqueue, there is no way to be notified that the waitqueue is being freed (which happens when its lifetime is shorter than the struct file's). This is supposed to happen via the waitqueue entries being woken up with POLLFREE. Therefore, leave the requests on the waitqueue until they are actually completed (or cancelled). To keep track of when aio_poll_complete_work needs to be scheduled, use new fields in struct poll_iocb. Remove the 'done' field which is now redundant. Note that this is consistent with how sys_poll() and eventpoll work; their wakeup functions do *not* remove the waitqueue entries. Fixes: 2c14fa838cbe ("aio: implement IOCB_CMD_POLL") Cc: # v4.18+ Link: https://lore.kernel.org/r/20211209010455.42744-5-ebiggers@kernel.org Signed-off-by: Eric Biggers Signed-off-by: Greg Kroah-Hartman --- fs/aio.c | 83 ++++++++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 63 insertions(+), 20 deletions(-) diff --git a/fs/aio.c b/fs/aio.c index bd182bcca23a..fbc276633eb2 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -182,8 +182,9 @@ struct poll_iocb { struct file *file; struct wait_queue_head *head; __poll_t events; - bool done; bool cancelled; + bool work_scheduled; + bool work_need_resched; struct wait_queue_entry wait; struct work_struct work; }; @@ -1640,14 +1641,26 @@ static void aio_poll_complete_work(struct work_struct *work) * avoid further branches in the fast path. */ spin_lock_irq(&ctx->ctx_lock); + spin_lock(&req->head->lock); if (!mask && !READ_ONCE(req->cancelled)) { - add_wait_queue(req->head, &req->wait); + /* + * The request isn't actually ready to be completed yet. + * Reschedule completion if another wakeup came in. + */ + if (req->work_need_resched) { + schedule_work(&req->work); + req->work_need_resched = false; + } else { + req->work_scheduled = false; + } + spin_unlock(&req->head->lock); spin_unlock_irq(&ctx->ctx_lock); return; } + list_del_init(&req->wait.entry); + spin_unlock(&req->head->lock); list_del_init(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); - req->done = true; spin_unlock_irq(&ctx->ctx_lock); iocb_put(iocb); @@ -1661,9 +1674,9 @@ static int aio_poll_cancel(struct kiocb *iocb) spin_lock(&req->head->lock); WRITE_ONCE(req->cancelled, true); - if (!list_empty(&req->wait.entry)) { - list_del_init(&req->wait.entry); + if (!req->work_scheduled) { schedule_work(&aiocb->poll.work); + req->work_scheduled = true; } spin_unlock(&req->head->lock); @@ -1682,20 +1695,26 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, if (mask && !(mask & req->events)) return 0; - list_del_init(&req->wait.entry); - - if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { + /* + * Complete the request inline if possible. This requires that three + * conditions be met: + * 1. An event mask must have been passed. If a plain wakeup was done + * instead, then mask == 0 and we have to call vfs_poll() to get + * the events, so inline completion isn't possible. + * 2. The completion work must not have already been scheduled. + * 3. ctx_lock must not be busy. We have to use trylock because we + * already hold the waitqueue lock, so this inverts the normal + * locking order. Use irqsave/irqrestore because not all + * filesystems (e.g. fuse) call this function with IRQs disabled, + * yet IRQs have to be disabled before ctx_lock is obtained. + */ + if (mask && !req->work_scheduled && + spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { struct kioctx *ctx = iocb->ki_ctx; - /* - * Try to complete the iocb inline if we can. Use - * irqsave/irqrestore because not all filesystems (e.g. fuse) - * call this function with IRQs disabled and because IRQs - * have to be disabled before ctx_lock is obtained. - */ + list_del_init(&req->wait.entry); list_del(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); - req->done = true; if (iocb->ki_eventfd && eventfd_signal_count()) { iocb = NULL; INIT_WORK(&req->work, aio_poll_put_work); @@ -1705,7 +1724,20 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, if (iocb) iocb_put(iocb); } else { - schedule_work(&req->work); + /* + * Schedule the completion work if needed. If it was already + * scheduled, record that another wakeup came in. + * + * Don't remove the request from the waitqueue here, as it might + * not actually be complete yet (we won't know until vfs_poll() + * is called), and we must not miss any wakeups. + */ + if (req->work_scheduled) { + req->work_need_resched = true; + } else { + schedule_work(&req->work); + req->work_scheduled = true; + } } return 1; } @@ -1752,8 +1784,9 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP; req->head = NULL; - req->done = false; req->cancelled = false; + req->work_scheduled = false; + req->work_need_resched = false; apt.pt._qproc = aio_poll_queue_proc; apt.pt._key = req->events; @@ -1768,17 +1801,27 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) spin_lock_irq(&ctx->ctx_lock); if (likely(req->head)) { spin_lock(&req->head->lock); - if (unlikely(list_empty(&req->wait.entry))) { - if (apt.error) + if (list_empty(&req->wait.entry) || req->work_scheduled) { + /* + * aio_poll_wake() already either scheduled the async + * completion work, or completed the request inline. + */ + if (apt.error) /* unsupported case: multiple queues */ cancel = true; apt.error = 0; mask = 0; } if (mask || apt.error) { + /* Steal to complete synchronously. */ list_del_init(&req->wait.entry); } else if (cancel) { + /* Cancel if possible (may be too late though). */ WRITE_ONCE(req->cancelled, true); - } else if (!req->done) { /* actually waiting for an event */ + } else if (!list_empty(&req->wait.entry)) { + /* + * Actually waiting for an event, so add the request to + * active_reqs so that it can be cancelled if needed. + */ list_add_tail(&aiocb->ki_list, &ctx->active_reqs); aiocb->ki_cancel = aio_poll_cancel; } -- Gitee From cd3367e599a1629d1b4037d8c41a9c14c7565854 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 10 Dec 2021 15:48:05 -0800 Subject: [PATCH 09/17] aio: fix use-after-free due to missing POLLFREE handling stable inclusion from stable-5.10.85 commit 47ffefd88abfffe8a040bcc1dd0554d4ea6f7689 category: bugfix issue: I51A19 CVE: CVE-2021-39698 Signed-off-by: gaochao --------------------------------------- aio: fix use-after-free due to missing POLLFREE handling commit 50252e4b5e989ce64555c7aef7516bdefc2fea72 upstream. signalfd_poll() and binder_poll() are special in that they use a waitqueue whose lifetime is the current task, rather than the struct file as is normally the case. This is okay for blocking polls, since a blocking poll occurs within one task; however, non-blocking polls require another solution. This solution is for the queue to be cleared before it is freed, by sending a POLLFREE notification to all waiters. Unfortunately, only eventpoll handles POLLFREE. A second type of non-blocking poll, aio poll, was added in kernel v4.18, and it doesn't handle POLLFREE. This allows a use-after-free to occur if a signalfd or binder fd is polled with aio poll, and the waitqueue gets freed. Fix this by making aio poll handle POLLFREE. A patch by Ramji Jiyani (https://lore.kernel.org/r/20211027011834.2497484-1-ramjiyani@google.com) tried to do this by making aio_poll_wake() always complete the request inline if POLLFREE is seen. However, that solution had two bugs. First, it introduced a deadlock, as it unconditionally locked the aio context while holding the waitqueue lock, which inverts the normal locking order. Second, it didn't consider that POLLFREE notifications are missed while the request has been temporarily de-queued. The second problem was solved by my previous patch. This patch then properly fixes the use-after-free by handling POLLFREE in a deadlock-free way. It does this by taking advantage of the fact that freeing of the waitqueue is RCU-delayed, similar to what eventpoll does. Fixes: 2c14fa838cbe ("aio: implement IOCB_CMD_POLL") Cc: # v4.18+ Link: https://lore.kernel.org/r/20211209010455.42744-6-ebiggers@kernel.org Signed-off-by: Eric Biggers Signed-off-by: Greg Kroah-Hartman --- fs/aio.c | 137 ++++++++++++++++++++++++-------- include/uapi/asm-generic/poll.h | 2 +- 2 files changed, 107 insertions(+), 32 deletions(-) diff --git a/fs/aio.c b/fs/aio.c index fbc276633eb2..5e5333d72c69 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1622,6 +1622,51 @@ static void aio_poll_put_work(struct work_struct *work) iocb_put(iocb); } +/* + * Safely lock the waitqueue which the request is on, synchronizing with the + * case where the ->poll() provider decides to free its waitqueue early. + * + * Returns true on success, meaning that req->head->lock was locked, req->wait + * is on req->head, and an RCU read lock was taken. Returns false if the + * request was already removed from its waitqueue (which might no longer exist). + */ +static bool poll_iocb_lock_wq(struct poll_iocb *req) +{ + wait_queue_head_t *head; + + /* + * While we hold the waitqueue lock and the waitqueue is nonempty, + * wake_up_pollfree() will wait for us. However, taking the waitqueue + * lock in the first place can race with the waitqueue being freed. + * + * We solve this as eventpoll does: by taking advantage of the fact that + * all users of wake_up_pollfree() will RCU-delay the actual free. If + * we enter rcu_read_lock() and see that the pointer to the queue is + * non-NULL, we can then lock it without the memory being freed out from + * under us, then check whether the request is still on the queue. + * + * Keep holding rcu_read_lock() as long as we hold the queue lock, in + * case the caller deletes the entry from the queue, leaving it empty. + * In that case, only RCU prevents the queue memory from being freed. + */ + rcu_read_lock(); + head = smp_load_acquire(&req->head); + if (head) { + spin_lock(&head->lock); + if (!list_empty(&req->wait.entry)) + return true; + spin_unlock(&head->lock); + } + rcu_read_unlock(); + return false; +} + +static void poll_iocb_unlock_wq(struct poll_iocb *req) +{ + spin_unlock(&req->head->lock); + rcu_read_unlock(); +} + static void aio_poll_complete_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); @@ -1641,24 +1686,25 @@ static void aio_poll_complete_work(struct work_struct *work) * avoid further branches in the fast path. */ spin_lock_irq(&ctx->ctx_lock); - spin_lock(&req->head->lock); - if (!mask && !READ_ONCE(req->cancelled)) { - /* - * The request isn't actually ready to be completed yet. - * Reschedule completion if another wakeup came in. - */ - if (req->work_need_resched) { - schedule_work(&req->work); - req->work_need_resched = false; - } else { - req->work_scheduled = false; + if (poll_iocb_lock_wq(req)) { + if (!mask && !READ_ONCE(req->cancelled)) { + /* + * The request isn't actually ready to be completed yet. + * Reschedule completion if another wakeup came in. + */ + if (req->work_need_resched) { + schedule_work(&req->work); + req->work_need_resched = false; + } else { + req->work_scheduled = false; + } + poll_iocb_unlock_wq(req); + spin_unlock_irq(&ctx->ctx_lock); + return; } - spin_unlock(&req->head->lock); - spin_unlock_irq(&ctx->ctx_lock); - return; - } - list_del_init(&req->wait.entry); - spin_unlock(&req->head->lock); + list_del_init(&req->wait.entry); + poll_iocb_unlock_wq(req); + } /* else, POLLFREE has freed the waitqueue, so we must complete */ list_del_init(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); spin_unlock_irq(&ctx->ctx_lock); @@ -1672,13 +1718,14 @@ static int aio_poll_cancel(struct kiocb *iocb) struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw); struct poll_iocb *req = &aiocb->poll; - spin_lock(&req->head->lock); - WRITE_ONCE(req->cancelled, true); - if (!req->work_scheduled) { - schedule_work(&aiocb->poll.work); - req->work_scheduled = true; - } - spin_unlock(&req->head->lock); + if (poll_iocb_lock_wq(req)) { + WRITE_ONCE(req->cancelled, true); + if (!req->work_scheduled) { + schedule_work(&aiocb->poll.work); + req->work_scheduled = true; + } + poll_iocb_unlock_wq(req); + } /* else, the request was force-cancelled by POLLFREE already */ return 0; } @@ -1730,7 +1777,8 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, * * Don't remove the request from the waitqueue here, as it might * not actually be complete yet (we won't know until vfs_poll() - * is called), and we must not miss any wakeups. + * is called), and we must not miss any wakeups. POLLFREE is an + * exception to this; see below. */ if (req->work_scheduled) { req->work_need_resched = true; @@ -1738,6 +1786,28 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, schedule_work(&req->work); req->work_scheduled = true; } + + /* + * If the waitqueue is being freed early but we can't complete + * the request inline, we have to tear down the request as best + * we can. That means immediately removing the request from its + * waitqueue and preventing all further accesses to the + * waitqueue via the request. We also need to schedule the + * completion work (done above). Also mark the request as + * cancelled, to potentially skip an unneeded call to ->poll(). + */ + if (mask & POLLFREE) { + WRITE_ONCE(req->cancelled, true); + list_del_init(&req->wait.entry); + + /* + * Careful: this *must* be the last step, since as soon + * as req->head is NULL'ed out, the request can be + * completed and freed, since aio_poll_complete_work() + * will no longer need to take the waitqueue lock. + */ + smp_store_release(&req->head, NULL); + } } return 1; } @@ -1745,6 +1815,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, struct aio_poll_table { struct poll_table_struct pt; struct aio_kiocb *iocb; + bool queued; int error; }; @@ -1755,11 +1826,12 @@ aio_poll_queue_proc(struct file *file, struct wait_queue_head *head, struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt); /* multiple wait queues per file are not supported */ - if (unlikely(pt->iocb->poll.head)) { + if (unlikely(pt->queued)) { pt->error = -EINVAL; return; } + pt->queued = true; pt->error = 0; pt->iocb->poll.head = head; add_wait_queue(head, &pt->iocb->poll.wait); @@ -1791,6 +1863,7 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) apt.pt._qproc = aio_poll_queue_proc; apt.pt._key = req->events; apt.iocb = aiocb; + apt.queued = false; apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */ /* initialized the list so that we can do list_empty checks */ @@ -1799,9 +1872,10 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) mask = vfs_poll(req->file, &apt.pt) & req->events; spin_lock_irq(&ctx->ctx_lock); - if (likely(req->head)) { - spin_lock(&req->head->lock); - if (list_empty(&req->wait.entry) || req->work_scheduled) { + if (likely(apt.queued)) { + bool on_queue = poll_iocb_lock_wq(req); + + if (!on_queue || req->work_scheduled) { /* * aio_poll_wake() already either scheduled the async * completion work, or completed the request inline. @@ -1817,7 +1891,7 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) } else if (cancel) { /* Cancel if possible (may be too late though). */ WRITE_ONCE(req->cancelled, true); - } else if (!list_empty(&req->wait.entry)) { + } else if (on_queue) { /* * Actually waiting for an event, so add the request to * active_reqs so that it can be cancelled if needed. @@ -1825,7 +1899,8 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) list_add_tail(&aiocb->ki_list, &ctx->active_reqs); aiocb->ki_cancel = aio_poll_cancel; } - spin_unlock(&req->head->lock); + if (on_queue) + poll_iocb_unlock_wq(req); } if (mask) { /* no async, we'd stolen it */ aiocb->ki_res.res = mangle_poll(mask); diff --git a/include/uapi/asm-generic/poll.h b/include/uapi/asm-generic/poll.h index 41b509f410bf..f9c520ce4bf4 100644 --- a/include/uapi/asm-generic/poll.h +++ b/include/uapi/asm-generic/poll.h @@ -29,7 +29,7 @@ #define POLLRDHUP 0x2000 #endif -#define POLLFREE (__force __poll_t)0x4000 /* currently only for epoll */ +#define POLLFREE (__force __poll_t)0x4000 #define POLL_BUSY_LOOP (__force __poll_t)0x8000 -- Gitee From cba819263a23bf16720a80c21e1d7949f9b5dc14 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 31 Jan 2022 09:20:18 -0800 Subject: [PATCH 10/17] net: sched: fix use-after-free in tc_new_tfilter() stable inclusion from stable-5.10.97 commit e7be56926397cf9d992be8913f74a76152f8f08d category: bugfix issue: I51A19 CVE: CVE-2022-1055 Signed-off-by: gaochao --------------------------------------- net: sched: fix use-after-free in tc_new_tfilter() commit 04c2a47ffb13c29778e2a14e414ad4cb5a5db4b5 upstream. Whenever tc_new_tfilter() jumps back to replay: label, we need to make sure @q and @chain local variables are cleared again, or risk use-after-free as in [1] For consistency, apply the same fix in tc_ctl_chain() BUG: KASAN: use-after-free in mini_qdisc_pair_swap+0x1b9/0x1f0 net/sched/sch_generic.c:1581 Write of size 8 at addr ffff8880985c4b08 by task syz-executor.4/1945 CPU: 0 PID: 1945 Comm: syz-executor.4 Not tainted 5.17.0-rc1-syzkaller-00495-gff58831fa02d #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description.constprop.0.cold+0x8d/0x336 mm/kasan/report.c:255 __kasan_report mm/kasan/report.c:442 [inline] kasan_report.cold+0x83/0xdf mm/kasan/report.c:459 mini_qdisc_pair_swap+0x1b9/0x1f0 net/sched/sch_generic.c:1581 tcf_chain_head_change_item net/sched/cls_api.c:372 [inline] tcf_chain0_head_change.isra.0+0xb9/0x120 net/sched/cls_api.c:386 tcf_chain_tp_insert net/sched/cls_api.c:1657 [inline] tcf_chain_tp_insert_unique net/sched/cls_api.c:1707 [inline] tc_new_tfilter+0x1e67/0x2350 net/sched/cls_api.c:2086 rtnetlink_rcv_msg+0x80d/0xb80 net/core/rtnetlink.c:5583 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2494 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x539/0x7e0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x904/0xe00 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:725 ____sys_sendmsg+0x331/0x810 net/socket.c:2413 ___sys_sendmsg+0xf3/0x170 net/socket.c:2467 __sys_sendmmsg+0x195/0x470 net/socket.c:2553 __do_sys_sendmmsg net/socket.c:2582 [inline] __se_sys_sendmmsg net/socket.c:2579 [inline] __x64_sys_sendmmsg+0x99/0x100 net/socket.c:2579 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f2647172059 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f2645aa5168 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 00007f2647285100 RCX: 00007f2647172059 RDX: 040000000000009f RSI: 00000000200002c0 RDI: 0000000000000006 RBP: 00007f26471cc08d R08: 0000000000000000 R09: 0000000000000000 R10: 9e00000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fffb3f7f02f R14: 00007f2645aa5300 R15: 0000000000022000 Allocated by task 1944: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:45 [inline] set_alloc_info mm/kasan/common.c:436 [inline] ____kasan_kmalloc mm/kasan/common.c:515 [inline] ____kasan_kmalloc mm/kasan/common.c:474 [inline] __kasan_kmalloc+0xa9/0xd0 mm/kasan/common.c:524 kmalloc_node include/linux/slab.h:604 [inline] kzalloc_node include/linux/slab.h:726 [inline] qdisc_alloc+0xac/0xa10 net/sched/sch_generic.c:941 qdisc_create.constprop.0+0xce/0x10f0 net/sched/sch_api.c:1211 tc_modify_qdisc+0x4c5/0x1980 net/sched/sch_api.c:1660 rtnetlink_rcv_msg+0x413/0xb80 net/core/rtnetlink.c:5592 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2494 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x539/0x7e0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x904/0xe00 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:725 ____sys_sendmsg+0x331/0x810 net/socket.c:2413 ___sys_sendmsg+0xf3/0x170 net/socket.c:2467 __sys_sendmmsg+0x195/0x470 net/socket.c:2553 __do_sys_sendmmsg net/socket.c:2582 [inline] __se_sys_sendmmsg net/socket.c:2579 [inline] __x64_sys_sendmmsg+0x99/0x100 net/socket.c:2579 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Freed by task 3609: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 kasan_set_track+0x21/0x30 mm/kasan/common.c:45 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:370 ____kasan_slab_free mm/kasan/common.c:366 [inline] ____kasan_slab_free+0x130/0x160 mm/kasan/common.c:328 kasan_slab_free include/linux/kasan.h:236 [inline] slab_free_hook mm/slub.c:1728 [inline] slab_free_freelist_hook+0x8b/0x1c0 mm/slub.c:1754 slab_free mm/slub.c:3509 [inline] kfree+0xcb/0x280 mm/slub.c:4562 rcu_do_batch kernel/rcu/tree.c:2527 [inline] rcu_core+0x7b8/0x1540 kernel/rcu/tree.c:2778 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 Last potentially related work creation: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 __kasan_record_aux_stack+0xbe/0xd0 mm/kasan/generic.c:348 __call_rcu kernel/rcu/tree.c:3026 [inline] call_rcu+0xb1/0x740 kernel/rcu/tree.c:3106 qdisc_put_unlocked+0x6f/0x90 net/sched/sch_generic.c:1109 tcf_block_release+0x86/0x90 net/sched/cls_api.c:1238 tc_new_tfilter+0xc0d/0x2350 net/sched/cls_api.c:2148 rtnetlink_rcv_msg+0x80d/0xb80 net/core/rtnetlink.c:5583 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2494 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x539/0x7e0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x904/0xe00 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:725 ____sys_sendmsg+0x331/0x810 net/socket.c:2413 ___sys_sendmsg+0xf3/0x170 net/socket.c:2467 __sys_sendmmsg+0x195/0x470 net/socket.c:2553 __do_sys_sendmmsg net/socket.c:2582 [inline] __se_sys_sendmmsg net/socket.c:2579 [inline] __x64_sys_sendmmsg+0x99/0x100 net/socket.c:2579 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae The buggy address belongs to the object at ffff8880985c4800 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 776 bytes inside of 1024-byte region [ffff8880985c4800, ffff8880985c4c00) The buggy address belongs to the page: page:ffffea0002617000 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x985c0 head:ffffea0002617000 order:3 compound_mapcount:0 compound_pincount:0 flags: 0xfff00000010200(slab|head|node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000010200 0000000000000000 dead000000000122 ffff888010c41dc0 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 3, migratetype Unmovable, gfp_mask 0x1d20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC|__GFP_HARDWALL), pid 1941, ts 1038999441284, free_ts 1033444432829 prep_new_page mm/page_alloc.c:2434 [inline] get_page_from_freelist+0xa72/0x2f50 mm/page_alloc.c:4165 __alloc_pages+0x1b2/0x500 mm/page_alloc.c:5389 alloc_pages+0x1aa/0x310 mm/mempolicy.c:2271 alloc_slab_page mm/slub.c:1799 [inline] allocate_slab mm/slub.c:1944 [inline] new_slab+0x28a/0x3b0 mm/slub.c:2004 ___slab_alloc+0x87c/0xe90 mm/slub.c:3018 __slab_alloc.constprop.0+0x4d/0xa0 mm/slub.c:3105 slab_alloc_node mm/slub.c:3196 [inline] slab_alloc mm/slub.c:3238 [inline] __kmalloc+0x2fb/0x340 mm/slub.c:4420 kmalloc include/linux/slab.h:586 [inline] kzalloc include/linux/slab.h:715 [inline] __register_sysctl_table+0x112/0x1090 fs/proc/proc_sysctl.c:1335 neigh_sysctl_register+0x2c8/0x5e0 net/core/neighbour.c:3787 devinet_sysctl_register+0xb1/0x230 net/ipv4/devinet.c:2618 inetdev_init+0x286/0x580 net/ipv4/devinet.c:278 inetdev_event+0xa8a/0x15d0 net/ipv4/devinet.c:1532 notifier_call_chain+0xb5/0x200 kernel/notifier.c:84 call_netdevice_notifiers_info+0xb5/0x130 net/core/dev.c:1919 call_netdevice_notifiers_extack net/core/dev.c:1931 [inline] call_netdevice_notifiers net/core/dev.c:1945 [inline] register_netdevice+0x1073/0x1500 net/core/dev.c:9698 veth_newlink+0x59c/0xa90 drivers/net/veth.c:1722 page last free stack trace: reset_page_owner include/linux/page_owner.h:24 [inline] free_pages_prepare mm/page_alloc.c:1352 [inline] free_pcp_prepare+0x374/0x870 mm/page_alloc.c:1404 free_unref_page_prepare mm/page_alloc.c:3325 [inline] free_unref_page+0x19/0x690 mm/page_alloc.c:3404 release_pages+0x748/0x1220 mm/swap.c:956 tlb_batch_pages_flush mm/mmu_gather.c:50 [inline] tlb_flush_mmu_free mm/mmu_gather.c:243 [inline] tlb_flush_mmu+0xe9/0x6b0 mm/mmu_gather.c:250 zap_pte_range mm/memory.c:1441 [inline] zap_pmd_range mm/memory.c:1490 [inline] zap_pud_range mm/memory.c:1519 [inline] zap_p4d_range mm/memory.c:1540 [inline] unmap_page_range+0x1d1d/0x2a30 mm/memory.c:1561 unmap_single_vma+0x198/0x310 mm/memory.c:1606 unmap_vmas+0x16b/0x2f0 mm/memory.c:1638 exit_mmap+0x201/0x670 mm/mmap.c:3178 __mmput+0x122/0x4b0 kernel/fork.c:1114 mmput+0x56/0x60 kernel/fork.c:1135 exit_mm kernel/exit.c:507 [inline] do_exit+0xa3c/0x2a30 kernel/exit.c:793 do_group_exit+0xd2/0x2f0 kernel/exit.c:935 __do_sys_exit_group kernel/exit.c:946 [inline] __se_sys_exit_group kernel/exit.c:944 [inline] __x64_sys_exit_group+0x3a/0x50 kernel/exit.c:944 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Memory state around the buggy address: ffff8880985c4a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880985c4a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8880985c4b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8880985c4b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880985c4c00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc Fixes: 470502de5bdb ("net: sched: unlock rules update API") Signed-off-by: Eric Dumazet Cc: Vlad Buslov Cc: Jiri Pirko Cc: Cong Wang Reported-by: syzbot Link: https://lore.kernel.org/r/20220131172018.3704490-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/sched/cls_api.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 31ac76a9189e..f1a07b518077 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1953,9 +1953,9 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, bool prio_allocate; u32 parent; u32 chain_index; - struct Qdisc *q = NULL; + struct Qdisc *q; struct tcf_chain_info chain_info; - struct tcf_chain *chain = NULL; + struct tcf_chain *chain; struct tcf_block *block; struct tcf_proto *tp; unsigned long cl; @@ -1983,6 +1983,8 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, tp = NULL; cl = 0; block = NULL; + q = NULL; + chain = NULL; if (prio == 0) { /* If no priority is provided by the user, @@ -2803,8 +2805,8 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n, struct tcmsg *t; u32 parent; u32 chain_index; - struct Qdisc *q = NULL; - struct tcf_chain *chain = NULL; + struct Qdisc *q; + struct tcf_chain *chain; struct tcf_block *block; unsigned long cl; int err; @@ -2814,6 +2816,7 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n, return -EPERM; replay: + q = NULL; err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack); if (err < 0) -- Gitee From 0f3acb51042fb4feb9bd503b8a0e50a641022227 Mon Sep 17 00:00:00 2001 From: Haimin Zhang Date: Wed, 16 Feb 2022 16:40:38 +0800 Subject: [PATCH 11/17] block-map: add __GFP_ZERO flag for alloc_page in function bio_copy_kern stable inclusion from stable-5.17-rc5 commit cc8f7fe1f5eab010191aa4570f27641876fa1267 category: bugfix issue: I51A19 CVE: CVE-2022-0494 Signed-off-by: gaochao --------------------------------------- block-map: add __GFP_ZERO flag for alloc_page in function bio_copy_kern Add __GFP_ZERO flag for alloc_page in function bio_copy_kern to initialize the buffer of a bio. Signed-off-by: Haimin Zhang Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220216084038.15635-1-tcs.kernel@gmail.com Signed-off-by: Jens Axboe --- block/blk-map.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/blk-map.c b/block/blk-map.c index 21630dccac62..ede73f4f7014 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -488,7 +488,7 @@ static struct bio *bio_copy_kern(struct request_queue *q, void *data, if (bytes > len) bytes = len; - page = alloc_page(q->bounce_gfp | gfp_mask); + page = alloc_page(q->bounce_gfp | __GFP_ZERO | gfp_mask); if (!page) goto cleanup; -- Gitee From 3e64bca26335ba4af9078e8d7fa6f33b3860201d Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Mar 2022 13:23:31 +0000 Subject: [PATCH 12/17] watch_queue: Fix filter limit check stable inclusion from stable-5.10.106 commit 648895da69ced90ca770fd941c3d9479a9d72c16 category: bugfix issue: I51A19 CVE: CVE-2022-0995 Signed-off-by: gaochao --------------------------------------- watch_queue: Fix filter limit check commit c993ee0f9f81caf5767a50d1faeba39a0dc82af2 upstream. In watch_queue_set_filter(), there are a couple of places where we check that the filter type value does not exceed what the type_filter bitmap can hold. One place calculates the number of bits by: if (tf[i].type >= sizeof(wfilter->type_filter) * 8) which is fine, but the second does: if (tf[i].type >= sizeof(wfilter->type_filter) * BITS_PER_LONG) which is not. This can lead to a couple of out-of-bounds writes due to a too-large type: (1) __set_bit() on wfilter->type_filter (2) Writing more elements in wfilter->filters[] than we allocated. Fix this by just using the proper WATCH_TYPE__NR instead, which is the number of types we actually know about. The bug may cause an oops looking something like: BUG: KASAN: slab-out-of-bounds in watch_queue_set_filter+0x659/0x740 Write of size 4 at addr ffff88800d2c66bc by task watch_queue_oob/611 ... Call Trace: dump_stack_lvl+0x45/0x59 print_address_description.constprop.0+0x1f/0x150 ... kasan_report.cold+0x7f/0x11b ... watch_queue_set_filter+0x659/0x740 ... __x64_sys_ioctl+0x127/0x190 do_syscall_64+0x43/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae Allocated by task 611: kasan_save_stack+0x1e/0x40 __kasan_kmalloc+0x81/0xa0 watch_queue_set_filter+0x23a/0x740 __x64_sys_ioctl+0x127/0x190 do_syscall_64+0x43/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae The buggy address belongs to the object at ffff88800d2c66a0 which belongs to the cache kmalloc-32 of size 32 The buggy address is located 28 bytes inside of 32-byte region [ffff88800d2c66a0, ffff88800d2c66c0) Fixes: c73be61cede5 ("pipe: Add general notification queue support") Reported-by: Jann Horn Signed-off-by: David Howells Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/watch_queue.h | 3 ++- kernel/watch_queue.c | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/include/linux/watch_queue.h b/include/linux/watch_queue.h index c994d1b2cdba..3b9a40ae8bdb 100644 --- a/include/linux/watch_queue.h +++ b/include/linux/watch_queue.h @@ -28,7 +28,8 @@ struct watch_type_filter { struct watch_filter { union { struct rcu_head rcu; - unsigned long type_filter[2]; /* Bitmask of accepted types */ + /* Bitmask of accepted types */ + DECLARE_BITMAP(type_filter, WATCH_TYPE__NR); }; u32 nr_filters; /* Number of filters */ struct watch_type_filter filters[]; diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 0ef8f65bd2d7..0defb921d8a1 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -320,7 +320,7 @@ long watch_queue_set_filter(struct pipe_inode_info *pipe, tf[i].info_mask & WATCH_INFO_LENGTH) goto err_filter; /* Ignore any unknown types */ - if (tf[i].type >= sizeof(wfilter->type_filter) * 8) + if (tf[i].type >= WATCH_TYPE__NR) continue; nr_filter++; } @@ -336,7 +336,7 @@ long watch_queue_set_filter(struct pipe_inode_info *pipe, q = wfilter->filters; for (i = 0; i < filter.nr_filters; i++) { - if (tf[i].type >= sizeof(wfilter->type_filter) * BITS_PER_LONG) + if (tf[i].type >= WATCH_TYPE__NR) continue; q->type = tf[i].type; -- Gitee From 69be78f1ec1171dc8caea5f7fa16a7efdeae4ed9 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 17 Mar 2022 12:04:42 +0100 Subject: [PATCH 13/17] netfilter: nf_tables: initialize registers in nft_do_chain() stable inclusion from stable-5.10.109 commit 2c74374c2e88c7b7992bf808d9f9391f7452f9d9 category: bugfix issue: I51A19 CVE: CVE-2022-1016 Signed-off-by: gaochao --------------------------------------- netfilter: nf_tables: initialize registers in nft_do_chain() commit 4c905f6740a365464e91467aa50916555b28213d upstream. Initialize registers to avoid stack leak into userspace. Fixes: 96518518cc41 ("netfilter: add nftables") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_tables_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index dbc2e945c98e..a61b5bf5aa0f 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -162,7 +162,7 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) struct nft_rule *const *rules; const struct nft_rule *rule; const struct nft_expr *expr, *last; - struct nft_regs regs; + struct nft_regs regs = {}; unsigned int stackptr = 0; struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE]; bool genbit = READ_ONCE(net->nft.gencursor); -- Gitee From f81fbdbf176ac11a96bc6d31f7906f39888518d0 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 22 Mar 2022 18:07:20 +0100 Subject: [PATCH 14/17] ALSA: pcm: Fix races among concurrent prealloc proc writes stable inclusion from stable-5.10.109 commit b560d670c87d7d40b3cf6949246fa4c7aa65a00a category: bugfix issue: I51A19 CVE: CVE-2022-1048 Signed-off-by: gaochao --------------------------------------- ALSA: pcm: Fix races among concurrent prealloc proc writes commit 69534c48ba8ce552ce383b3dfdb271ffe51820c3 upstream. We have no protection against concurrent PCM buffer preallocation changes via proc files, and it may potentially lead to UAF or some weird problem. This patch applies the PCM open_mutex to the proc write operation for avoiding the racy proc writes and the PCM stream open (and further operations). Cc: Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20220322170720.3529-5-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/pcm_memory.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/sound/core/pcm_memory.c b/sound/core/pcm_memory.c index 4f03ba8ed0ae..a9a0d74f3165 100644 --- a/sound/core/pcm_memory.c +++ b/sound/core/pcm_memory.c @@ -164,19 +164,20 @@ static void snd_pcm_lib_preallocate_proc_write(struct snd_info_entry *entry, size_t size; struct snd_dma_buffer new_dmab; + mutex_lock(&substream->pcm->open_mutex); if (substream->runtime) { buffer->error = -EBUSY; - return; + goto unlock; } if (!snd_info_get_line(buffer, line, sizeof(line))) { snd_info_get_str(str, line, sizeof(str)); size = simple_strtoul(str, NULL, 10) * 1024; if ((size != 0 && size < 8192) || size > substream->dma_max) { buffer->error = -EINVAL; - return; + goto unlock; } if (substream->dma_buffer.bytes == size) - return; + goto unlock; memset(&new_dmab, 0, sizeof(new_dmab)); new_dmab.dev = substream->dma_buffer.dev; if (size > 0) { @@ -185,7 +186,7 @@ static void snd_pcm_lib_preallocate_proc_write(struct snd_info_entry *entry, substream->dma_buffer.dev.dev, size, &new_dmab) < 0) { buffer->error = -ENOMEM; - return; + goto unlock; } substream->buffer_bytes_max = size; } else { @@ -197,6 +198,8 @@ static void snd_pcm_lib_preallocate_proc_write(struct snd_info_entry *entry, } else { buffer->error = -EINVAL; } + unlock: + mutex_unlock(&substream->pcm->open_mutex); } static inline void preallocate_info_init(struct snd_pcm_substream *substream) -- Gitee From a05096831047cabd9beaf4660cf4a02a737cde43 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 22 Mar 2022 18:07:19 +0100 Subject: [PATCH 15/17] ALSA: pcm: Fix races among concurrent prepare and hw_params/hw_free calls stable inclusion from stable-5.10.109 commit a38440f006974e693f92a1ea10f819eccc4dcc37 category: bugfix issue: I51A19 CVE: CVE-2022-1048 Signed-off-by: gaochao --------------------------------------- ALSA: pcm: Fix races among concurrent prepare and hw_params/hw_free calls commit 3c3201f8c7bb77eb53b08a3ca8d9a4ddc500b4c0 upstream. Like the previous fixes to hw_params and hw_free ioctl races, we need to paper over the concurrent prepare ioctl calls against hw_params and hw_free, too. This patch implements the locking with the existing runtime->buffer_mutex for prepare ioctls. Unlike the previous case for snd_pcm_hw_hw_params() and snd_pcm_hw_free(), snd_pcm_prepare() is performed to the linked streams, hence the lock can't be applied simply on the top. For tracking the lock in each linked substream, we modify snd_pcm_action_group() slightly and apply the buffer_mutex for the case stream_lock=false (formerly there was no lock applied) there. Cc: Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20220322170720.3529-4-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/pcm_native.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 6d1759b9ccb2..be0f1f20ad1d 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -1151,15 +1151,17 @@ struct action_ops { static int snd_pcm_action_group(const struct action_ops *ops, struct snd_pcm_substream *substream, snd_pcm_state_t state, - bool do_lock) + bool stream_lock) { struct snd_pcm_substream *s = NULL; struct snd_pcm_substream *s1; int res = 0, depth = 1; snd_pcm_group_for_each_entry(s, substream) { - if (do_lock && s != substream) { - if (s->pcm->nonatomic) + if (s != substream) { + if (!stream_lock) + mutex_lock_nested(&s->runtime->buffer_mutex, depth); + else if (s->pcm->nonatomic) mutex_lock_nested(&s->self_group.mutex, depth); else spin_lock_nested(&s->self_group.lock, depth); @@ -1187,18 +1189,18 @@ static int snd_pcm_action_group(const struct action_ops *ops, ops->post_action(s, state); } _unlock: - if (do_lock) { - /* unlock streams */ - snd_pcm_group_for_each_entry(s1, substream) { - if (s1 != substream) { - if (s1->pcm->nonatomic) - mutex_unlock(&s1->self_group.mutex); - else - spin_unlock(&s1->self_group.lock); - } - if (s1 == s) /* end */ - break; + /* unlock streams */ + snd_pcm_group_for_each_entry(s1, substream) { + if (s1 != substream) { + if (!stream_lock) + mutex_unlock(&s1->runtime->buffer_mutex); + else if (s1->pcm->nonatomic) + mutex_unlock(&s1->self_group.mutex); + else + spin_unlock(&s1->self_group.lock); } + if (s1 == s) /* end */ + break; } return res; } @@ -1328,10 +1330,12 @@ static int snd_pcm_action_nonatomic(const struct action_ops *ops, /* Guarantee the group members won't change during non-atomic action */ down_read(&snd_pcm_link_rwsem); + mutex_lock(&substream->runtime->buffer_mutex); if (snd_pcm_stream_linked(substream)) res = snd_pcm_action_group(ops, substream, state, false); else res = snd_pcm_action_single(ops, substream, state); + mutex_unlock(&substream->runtime->buffer_mutex); up_read(&snd_pcm_link_rwsem); return res; } -- Gitee From 161a76483bb48f649428f42909ce14edaf58839f Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 22 Mar 2022 18:07:18 +0100 Subject: [PATCH 16/17] ALSA: pcm: Fix races among concurrent read/write and buffer changes stable inclusion from stable-5.10.109 commit 8527c8f052fb42091c6569cb928e472376a4a889 category: bugfix issue: I51A19 CVE: CVE-2022-1048 Signed-off-by: gaochao --------------------------------------- ALSA: pcm: Fix races among concurrent read/write and buffer changes commit dca947d4d26dbf925a64a6cfb2ddbc035e831a3d upstream. In the current PCM design, the read/write syscalls (as well as the equivalent ioctls) are allowed before the PCM stream is running, that is, at PCM PREPARED state. Meanwhile, we also allow to re-issue hw_params and hw_free ioctl calls at the PREPARED state that may change or free the buffers, too. The problem is that there is no protection against those mix-ups. This patch applies the previously introduced runtime->buffer_mutex to the read/write operations so that the concurrent hw_params or hw_free call can no longer interfere during the operation. The mutex is unlocked before scheduling, so we don't take it too long. Cc: Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20220322170720.3529-3-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/pcm_lib.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index bda3514c7b2d..03dcfc9205ca 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -1871,9 +1871,11 @@ static int wait_for_avail(struct snd_pcm_substream *substream, if (avail >= runtime->twake) break; snd_pcm_stream_unlock_irq(substream); + mutex_unlock(&runtime->buffer_mutex); tout = schedule_timeout(wait_time); + mutex_lock(&runtime->buffer_mutex); snd_pcm_stream_lock_irq(substream); set_current_state(TASK_INTERRUPTIBLE); switch (runtime->status->state) { @@ -2167,6 +2169,7 @@ snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream, nonblock = !!(substream->f_flags & O_NONBLOCK); + mutex_lock(&runtime->buffer_mutex); snd_pcm_stream_lock_irq(substream); err = pcm_accessible_state(runtime); if (err < 0) @@ -2254,6 +2257,7 @@ snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream, if (xfer > 0 && err >= 0) snd_pcm_update_state(substream, runtime); snd_pcm_stream_unlock_irq(substream); + mutex_unlock(&runtime->buffer_mutex); return xfer > 0 ? (snd_pcm_sframes_t)xfer : err; } EXPORT_SYMBOL(__snd_pcm_lib_xfer); -- Gitee From 524df91c41f688ca264b869e18496206e60265eb Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 22 Mar 2022 18:07:17 +0100 Subject: [PATCH 17/17] ALSA: pcm: Fix races among concurrent hw_params and hw_free calls stable inclusion from stable-5.10.109 commit 0f6947f5f5208f6ebd4d76a82a4757e2839a23f8 category: bugfix issue: I51A19 CVE: CVE-2022-1048 Signed-off-by: gaochao --------------------------------------- ALSA: pcm: Fix races among concurrent hw_params and hw_free calls commit 92ee3c60ec9fe64404dc035e7c41277d74aa26cb upstream. Currently we have neither proper check nor protection against the concurrent calls of PCM hw_params and hw_free ioctls, which may result in a UAF. Since the existing PCM stream lock can't be used for protecting the whole ioctl operations, we need a new mutex to protect those racy calls. This patch introduced a new mutex, runtime->buffer_mutex, and applies it to both hw_params and hw_free ioctl code paths. Along with it, the both functions are slightly modified (the mmap_count check is moved into the state-check block) for code simplicity. Reported-by: Hu Jiahui Cc: Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20220322170720.3529-2-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- include/sound/pcm.h | 1 + sound/core/pcm.c | 2 ++ sound/core/pcm_native.c | 61 ++++++++++++++++++++++++++--------------- 3 files changed, 42 insertions(+), 22 deletions(-) diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 2336bf9243e1..ab966563e852 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -398,6 +398,7 @@ struct snd_pcm_runtime { wait_queue_head_t tsleep; /* transfer sleep */ struct fasync_struct *fasync; bool stop_operating; /* sync_stop will be called */ + struct mutex buffer_mutex; /* protect for buffer changes */ /* -- private section -- */ void *private_data; diff --git a/sound/core/pcm.c b/sound/core/pcm.c index 41cbdac5b1cf..450212e956f5 100644 --- a/sound/core/pcm.c +++ b/sound/core/pcm.c @@ -965,6 +965,7 @@ int snd_pcm_attach_substream(struct snd_pcm *pcm, int stream, init_waitqueue_head(&runtime->tsleep); runtime->status->state = SNDRV_PCM_STATE_OPEN; + mutex_init(&runtime->buffer_mutex); substream->runtime = runtime; substream->private_data = pcm->private_data; @@ -998,6 +999,7 @@ void snd_pcm_detach_substream(struct snd_pcm_substream *substream) } else { substream->runtime = NULL; } + mutex_destroy(&runtime->buffer_mutex); kfree(runtime); put_pid(substream->pid); substream->pid = NULL; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index be0f1f20ad1d..c72af733ab28 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -664,33 +664,40 @@ static int snd_pcm_hw_params_choose(struct snd_pcm_substream *pcm, return 0; } +#if IS_ENABLED(CONFIG_SND_PCM_OSS) +#define is_oss_stream(substream) ((substream)->oss.oss) +#else +#define is_oss_stream(substream) false +#endif + static int snd_pcm_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) { struct snd_pcm_runtime *runtime; - int err, usecs; + int err = 0, usecs; unsigned int bits; snd_pcm_uframes_t frames; if (PCM_RUNTIME_CHECK(substream)) return -ENXIO; runtime = substream->runtime; + mutex_lock(&runtime->buffer_mutex); snd_pcm_stream_lock_irq(substream); switch (runtime->status->state) { case SNDRV_PCM_STATE_OPEN: case SNDRV_PCM_STATE_SETUP: case SNDRV_PCM_STATE_PREPARED: + if (!is_oss_stream(substream) && + atomic_read(&substream->mmap_count)) + err = -EBADFD; break; default: - snd_pcm_stream_unlock_irq(substream); - return -EBADFD; + err = -EBADFD; + break; } snd_pcm_stream_unlock_irq(substream); -#if IS_ENABLED(CONFIG_SND_PCM_OSS) - if (!substream->oss.oss) -#endif - if (atomic_read(&substream->mmap_count)) - return -EBADFD; + if (err) + goto unlock; snd_pcm_sync_stop(substream, true); @@ -777,16 +784,21 @@ static int snd_pcm_hw_params(struct snd_pcm_substream *substream, if ((usecs = period_to_usecs(runtime)) >= 0) cpu_latency_qos_add_request(&substream->latency_pm_qos_req, usecs); - return 0; + err = 0; _error: - /* hardware might be unusable from this time, - so we force application to retry to set - the correct hardware parameter settings */ - snd_pcm_set_state(substream, SNDRV_PCM_STATE_OPEN); - if (substream->ops->hw_free != NULL) - substream->ops->hw_free(substream); - if (substream->managed_buffer_alloc) - snd_pcm_lib_free_pages(substream); + if (err) { + /* hardware might be unusable from this time, + * so we force application to retry to set + * the correct hardware parameter settings + */ + snd_pcm_set_state(substream, SNDRV_PCM_STATE_OPEN); + if (substream->ops->hw_free != NULL) + substream->ops->hw_free(substream); + if (substream->managed_buffer_alloc) + snd_pcm_lib_free_pages(substream); + } + unlock: + mutex_unlock(&runtime->buffer_mutex); return err; } @@ -826,26 +838,31 @@ static int do_hw_free(struct snd_pcm_substream *substream) static int snd_pcm_hw_free(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime; - int result; + int result = 0; if (PCM_RUNTIME_CHECK(substream)) return -ENXIO; runtime = substream->runtime; + mutex_lock(&runtime->buffer_mutex); snd_pcm_stream_lock_irq(substream); switch (runtime->status->state) { case SNDRV_PCM_STATE_SETUP: case SNDRV_PCM_STATE_PREPARED: + if (atomic_read(&substream->mmap_count)) + result = -EBADFD; break; default: - snd_pcm_stream_unlock_irq(substream); - return -EBADFD; + result = -EBADFD; + break; } snd_pcm_stream_unlock_irq(substream); - if (atomic_read(&substream->mmap_count)) - return -EBADFD; + if (result) + goto unlock; result = do_hw_free(substream); snd_pcm_set_state(substream, SNDRV_PCM_STATE_OPEN); cpu_latency_qos_remove_request(&substream->latency_pm_qos_req); + unlock: + mutex_unlock(&runtime->buffer_mutex); return result; } -- Gitee