From: Greg Kroah-Hartman gregkh@linuxfoundation.org

When backporting 0db282ba2c12 ("selftest: use mmap instead of posix_memalign to allocate memory") to this stable branch, I forgot a { breaking the build.

Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/vm/userfaultfd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -131,7 +131,7 @@ static void anon_allocate_area(void **al { *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - if (*alloc_area == MAP_FAILED) + if (*alloc_area == MAP_FAILED) { fprintf(stderr, "mmap of anonymous memory failed"); *alloc_area = NULL; }

From: Jens Axboe axboe@kernel.dk

commit f4e65870e5cede5ca1ec0006b6c9803994e5f7b8 upstream.

We need this functionality for the io_uring file registration, but we cannot rely on it since CONFIG_UNIX can be modular. Move the helpers to a separate file, that's always builtin to the kernel if CONFIG_UNIX is m/y.

No functional changes in this patch, just moving code around.

Reviewed-by: Hannes Reinecke hare@suse.com Acked-by: David S. Miller davem@davemloft.net Signed-off-by: Jens Axboe axboe@kernel.dk [ backported to older kernels to get access to unix_gc_lock - gregkh ] Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/af_unix.h | 1 net/Makefile | 2 net/unix/Kconfig | 5 + net/unix/Makefile | 2 net/unix/af_unix.c | 63 --------------------- net/unix/garbage.c | 68 ---------------------- net/unix/scm.c | 149 ++++++++++++++++++++++++++++++++++++++++++++++++++ net/unix/scm.h | 10 +++ 8 files changed, 172 insertions(+), 128 deletions(-) create mode 100644 net/unix/scm.c create mode 100644 net/unix/scm.h

--- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -10,6 +10,7 @@

void unix_inflight(struct user_struct *user, struct file *fp); void unix_notinflight(struct user_struct *user, struct file *fp); +void unix_destruct_scm(struct sk_buff *skb); void unix_gc(void); void wait_for_unix_gc(void); struct sock *unix_get_socket(struct file *filp); --- a/net/Makefile +++ b/net/Makefile @@ -18,7 +18,7 @@ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ obj-$(CONFIG_TLS) += tls/ obj-$(CONFIG_XFRM) += xfrm/ -obj-$(CONFIG_UNIX) += unix/ +obj-$(CONFIG_UNIX_SCM) += unix/ obj-$(CONFIG_NET) += ipv6/ obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ --- a/net/unix/Kconfig +++ b/net/unix/Kconfig @@ -19,6 +19,11 @@ config UNIX

Say Y unless you know what you are doing.

+config UNIX_SCM + bool + depends on UNIX + default y + config UNIX_DIAG tristate "UNIX: socket monitoring interface" depends on UNIX --- a/net/unix/Makefile +++ b/net/unix/Makefile @@ -10,3 +10,5 @@ unix-$(CONFIG_SYSCTL) += sysctl_net_unix

obj-$(CONFIG_UNIX_DIAG) += unix_diag.o unix_diag-y := diag.o + +obj-$(CONFIG_UNIX_SCM) += scm.o --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -119,6 +119,8 @@ #include <linux/freezer.h> #include <linux/file.h>

+#include "scm.h" + struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE]; EXPORT_SYMBOL_GPL(unix_socket_table); DEFINE_SPINLOCK(unix_table_lock); @@ -1519,67 +1521,6 @@ out: return err; }

-static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - - scm->fp = UNIXCB(skb).fp; - UNIXCB(skb).fp = NULL; - - for (i = scm->fp->count-1; i >= 0; i--) - unix_notinflight(scm->fp->user, scm->fp->fp[i]); -} - -static void unix_destruct_scm(struct sk_buff *skb) -{ - struct scm_cookie scm; - memset(&scm, 0, sizeof(scm)); - scm.pid = UNIXCB(skb).pid; - if (UNIXCB(skb).fp) - unix_detach_fds(&scm, skb); - - /* Alas, it calls VFS */ - /* So fscking what? fput() had been SMP-safe since the last Summer */ - scm_destroy(&scm); - sock_wfree(skb); -} - -/* - * The "user->unix_inflight" variable is protected by the garbage - * collection lock, and we just read it locklessly here. If you go - * over the limit, there might be a tiny race in actually noticing - * it across threads. Tough. - */ -static inline bool too_many_unix_fds(struct task_struct *p) -{ - struct user_struct *user = current_user(); - - if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE))) - return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); - return false; -} - -static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - - if (too_many_unix_fds(current)) - return -ETOOMANYREFS; - - /* - * Need to duplicate file references for the sake of garbage - * collection. Otherwise a socket in the fps might become a - * candidate for GC while the skb is not yet queued. - */ - UNIXCB(skb).fp = scm_fp_dup(scm->fp); - if (!UNIXCB(skb).fp) - return -ENOMEM; - - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->user, scm->fp->fp[i]); - return 0; -} - static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) { int err = 0; --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -86,77 +86,13 @@ #include <net/scm.h> #include <net/tcp_states.h>

+#include "scm.h" + /* Internal data structures and random procedures: */

-static LIST_HEAD(gc_inflight_list); static LIST_HEAD(gc_candidates); -static DEFINE_SPINLOCK(unix_gc_lock); static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait);

-unsigned int unix_tot_inflight; - -struct sock *unix_get_socket(struct file *filp) -{ - struct sock *u_sock = NULL; - struct inode *inode = file_inode(filp); - - /* Socket ? */ - if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { - struct socket *sock = SOCKET_I(inode); - struct sock *s = sock->sk; - - /* PF_UNIX ? */ - if (s && sock->ops && sock->ops->family == PF_UNIX) - u_sock = s; - } - return u_sock; -} - -/* Keep the number of times in flight count for the file - * descriptor if it is for an AF_UNIX socket. - */ - -void unix_inflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - if (atomic_long_inc_return(&u->inflight) == 1) { - BUG_ON(!list_empty(&u->link)); - list_add_tail(&u->link, &gc_inflight_list); - } else { - BUG_ON(list_empty(&u->link)); - } - unix_tot_inflight++; - } - user->unix_inflight++; - spin_unlock(&unix_gc_lock); -} - -void unix_notinflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - BUG_ON(!atomic_long_read(&u->inflight)); - BUG_ON(list_empty(&u->link)); - - if (atomic_long_dec_and_test(&u->inflight)) - list_del_init(&u->link); - unix_tot_inflight--; - } - user->unix_inflight--; - spin_unlock(&unix_gc_lock); -} - static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), struct sk_buff_head *hitlist) { --- /dev/null +++ b/net/unix/scm.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/socket.h> +#include <linux/net.h> +#include <linux/fs.h> +#include <net/af_unix.h> +#include <net/scm.h> +#include <linux/init.h> +#include <linux/sched/signal.h> + +#include "scm.h" + +unsigned int unix_tot_inflight; +EXPORT_SYMBOL(unix_tot_inflight); + +LIST_HEAD(gc_inflight_list); +EXPORT_SYMBOL(gc_inflight_list); + +DEFINE_SPINLOCK(unix_gc_lock); +EXPORT_SYMBOL(unix_gc_lock); + +struct sock *unix_get_socket(struct file *filp) +{ + struct sock *u_sock = NULL; + struct inode *inode = file_inode(filp); + + /* Socket ? */ + if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { + struct socket *sock = SOCKET_I(inode); + struct sock *s = sock->sk; + + /* PF_UNIX ? */ + if (s && sock->ops && sock->ops->family == PF_UNIX) + u_sock = s; + } + return u_sock; +} +EXPORT_SYMBOL(unix_get_socket); + +/* Keep the number of times in flight count for the file + * descriptor if it is for an AF_UNIX socket. + */ +void unix_inflight(struct user_struct *user, struct file *fp) +{ + struct sock *s = unix_get_socket(fp); + + spin_lock(&unix_gc_lock); + + if (s) { + struct unix_sock *u = unix_sk(s); + + if (atomic_long_inc_return(&u->inflight) == 1) { + BUG_ON(!list_empty(&u->link)); + list_add_tail(&u->link, &gc_inflight_list); + } else { + BUG_ON(list_empty(&u->link)); + } + unix_tot_inflight++; + } + user->unix_inflight++; + spin_unlock(&unix_gc_lock); +} + +void unix_notinflight(struct user_struct *user, struct file *fp) +{ + struct sock *s = unix_get_socket(fp); + + spin_lock(&unix_gc_lock); + + if (s) { + struct unix_sock *u = unix_sk(s); + + BUG_ON(!atomic_long_read(&u->inflight)); + BUG_ON(list_empty(&u->link)); + + if (atomic_long_dec_and_test(&u->inflight)) + list_del_init(&u->link); + unix_tot_inflight--; + } + user->unix_inflight--; + spin_unlock(&unix_gc_lock); +} + +/* + * The "user->unix_inflight" variable is protected by the garbage + * collection lock, and we just read it locklessly here. If you go + * over the limit, there might be a tiny race in actually noticing + * it across threads. Tough. + */ +static inline bool too_many_unix_fds(struct task_struct *p) +{ + struct user_struct *user = current_user(); + + if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE))) + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); + return false; +} + +int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + int i; + + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + + /* + * Need to duplicate file references for the sake of garbage + * collection. Otherwise a socket in the fps might become a + * candidate for GC while the skb is not yet queued. + */ + UNIXCB(skb).fp = scm_fp_dup(scm->fp); + if (!UNIXCB(skb).fp) + return -ENOMEM; + + for (i = scm->fp->count - 1; i >= 0; i--) + unix_inflight(scm->fp->user, scm->fp->fp[i]); + return 0; +} +EXPORT_SYMBOL(unix_attach_fds); + +void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + int i; + + scm->fp = UNIXCB(skb).fp; + UNIXCB(skb).fp = NULL; + + for (i = scm->fp->count-1; i >= 0; i--) + unix_notinflight(scm->fp->user, scm->fp->fp[i]); +} +EXPORT_SYMBOL(unix_detach_fds); + +void unix_destruct_scm(struct sk_buff *skb) +{ + struct scm_cookie scm; + + memset(&scm, 0, sizeof(scm)); + scm.pid = UNIXCB(skb).pid; + if (UNIXCB(skb).fp) + unix_detach_fds(&scm, skb); + + /* Alas, it calls VFS */ + /* So fscking what? fput() had been SMP-safe since the last Summer */ + scm_destroy(&scm); + sock_wfree(skb); +} +EXPORT_SYMBOL(unix_destruct_scm); --- /dev/null +++ b/net/unix/scm.h @@ -0,0 +1,10 @@ +#ifndef NET_UNIX_SCM_H +#define NET_UNIX_SCM_H + +extern struct list_head gc_inflight_list; +extern spinlock_t unix_gc_lock; + +int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb); +void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb); + +#endif

From: Yang Yingliang yangyingliang@huawei.com

commit b42b0bddcbc87b4c66f6497f66fc72d52b712aa7 upstream.

I got a UAF report when doing fuzz test:

[ 152.880091][ T8030] ================================================================== [ 152.881240][ T8030] BUG: KASAN: use-after-free in pwq_unbound_release_workfn+0x50/0x190 [ 152.882442][ T8030] Read of size 4 at addr ffff88810d31bd00 by task kworker/3:2/8030 [ 152.883578][ T8030] [ 152.883932][ T8030] CPU: 3 PID: 8030 Comm: kworker/3:2 Not tainted 5.13.0+ #249 [ 152.885014][ T8030] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [ 152.886442][ T8030] Workqueue: events pwq_unbound_release_workfn [ 152.887358][ T8030] Call Trace: [ 152.887837][ T8030] dump_stack_lvl+0x75/0x9b [ 152.888525][ T8030] ? pwq_unbound_release_workfn+0x50/0x190 [ 152.889371][ T8030] print_address_description.constprop.10+0x48/0x70 [ 152.890326][ T8030] ? pwq_unbound_release_workfn+0x50/0x190 [ 152.891163][ T8030] ? pwq_unbound_release_workfn+0x50/0x190 [ 152.891999][ T8030] kasan_report.cold.15+0x82/0xdb [ 152.892740][ T8030] ? pwq_unbound_release_workfn+0x50/0x190 [ 152.893594][ T8030] __asan_load4+0x69/0x90 [ 152.894243][ T8030] pwq_unbound_release_workfn+0x50/0x190 [ 152.895057][ T8030] process_one_work+0x47b/0x890 [ 152.895778][ T8030] worker_thread+0x5c/0x790 [ 152.896439][ T8030] ? process_one_work+0x890/0x890 [ 152.897163][ T8030] kthread+0x223/0x250 [ 152.897747][ T8030] ? set_kthread_struct+0xb0/0xb0 [ 152.898471][ T8030] ret_from_fork+0x1f/0x30 [ 152.899114][ T8030] [ 152.899446][ T8030] Allocated by task 8884: [ 152.900084][ T8030] kasan_save_stack+0x21/0x50 [ 152.900769][ T8030] __kasan_kmalloc+0x88/0xb0 [ 152.901416][ T8030] __kmalloc+0x29c/0x460 [ 152.902014][ T8030] alloc_workqueue+0x111/0x8e0 [ 152.902690][ T8030] __btrfs_alloc_workqueue+0x11e/0x2a0 [ 152.903459][ T8030] btrfs_alloc_workqueue+0x6d/0x1d0 [ 152.904198][ T8030] scrub_workers_get+0x1e8/0x490 [ 152.904929][ T8030] btrfs_scrub_dev+0x1b9/0x9c0 [ 152.905599][ T8030] btrfs_ioctl+0x122c/0x4e50 [ 152.906247][ T8030] __x64_sys_ioctl+0x137/0x190 [ 152.906916][ T8030] do_syscall_64+0x34/0xb0 [ 152.907535][ T8030] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 152.908365][ T8030] [ 152.908688][ T8030] Freed by task 8884: [ 152.909243][ T8030] kasan_save_stack+0x21/0x50 [ 152.909893][ T8030] kasan_set_track+0x20/0x30 [ 152.910541][ T8030] kasan_set_free_info+0x24/0x40 [ 152.911265][ T8030] __kasan_slab_free+0xf7/0x140 [ 152.911964][ T8030] kfree+0x9e/0x3d0 [ 152.912501][ T8030] alloc_workqueue+0x7d7/0x8e0 [ 152.913182][ T8030] __btrfs_alloc_workqueue+0x11e/0x2a0 [ 152.913949][ T8030] btrfs_alloc_workqueue+0x6d/0x1d0 [ 152.914703][ T8030] scrub_workers_get+0x1e8/0x490 [ 152.915402][ T8030] btrfs_scrub_dev+0x1b9/0x9c0 [ 152.916077][ T8030] btrfs_ioctl+0x122c/0x4e50 [ 152.916729][ T8030] __x64_sys_ioctl+0x137/0x190 [ 152.917414][ T8030] do_syscall_64+0x34/0xb0 [ 152.918034][ T8030] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 152.918872][ T8030] [ 152.919203][ T8030] The buggy address belongs to the object at ffff88810d31bc00 [ 152.919203][ T8030] which belongs to the cache kmalloc-512 of size 512 [ 152.921155][ T8030] The buggy address is located 256 bytes inside of [ 152.921155][ T8030] 512-byte region [ffff88810d31bc00, ffff88810d31be00) [ 152.922993][ T8030] The buggy address belongs to the page: [ 152.923800][ T8030] page:ffffea000434c600 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x10d318 [ 152.925249][ T8030] head:ffffea000434c600 order:2 compound_mapcount:0 compound_pincount:0 [ 152.926399][ T8030] flags: 0x57ff00000010200(slab|head|node=1|zone=2|lastcpupid=0x7ff) [ 152.927515][ T8030] raw: 057ff00000010200 dead000000000100 dead000000000122 ffff888009c42c80 [ 152.928716][ T8030] raw: 0000000000000000 0000000080100010 00000001ffffffff 0000000000000000 [ 152.929890][ T8030] page dumped because: kasan: bad access detected [ 152.930759][ T8030] [ 152.931076][ T8030] Memory state around the buggy address: [ 152.931851][ T8030] ffff88810d31bc00: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 152.932967][ T8030] ffff88810d31bc80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 152.934068][ T8030] >ffff88810d31bd00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 152.935189][ T8030] ^ [ 152.935763][ T8030] ffff88810d31bd80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 152.936847][ T8030] ffff88810d31be00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 152.937940][ T8030] ==================================================================

If apply_wqattrs_prepare() fails in alloc_workqueue(), it will call put_pwq() which invoke a work queue to call pwq_unbound_release_workfn() and use the 'wq'. The 'wq' allocated in alloc_workqueue() will be freed in error path when apply_wqattrs_prepare() fails. So it will lead a UAF.

CPU0 CPU1 alloc_workqueue() alloc_and_link_pwqs() apply_wqattrs_prepare() fails apply_wqattrs_cleanup() schedule_work(&pwq->unbound_release_work) kfree(wq) worker_thread() pwq_unbound_release_workfn() <- trigger uaf here

If apply_wqattrs_prepare() fails, the new pwq are not linked, it doesn't hold any reference to the 'wq', 'wq' is invalid to access in the worker, so add check pwq if linked to fix this.

Fixes: 2d5f0764b526 ("workqueue: split apply_workqueue_attrs() into 3 stages") Cc: stable@vger.kernel.org # v4.2+ Reported-by: Hulk Robot hulkci@huawei.com Suggested-by: Lai Jiangshan jiangshanlai@gmail.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Lai Jiangshan jiangshanlai@gmail.com Tested-by: Pavel Skripkin paskripkin@gmail.com Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/workqueue.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-)

--- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3441,15 +3441,21 @@ static void pwq_unbound_release_workfn(s unbound_release_work); struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; - bool is_last; + bool is_last = false;

- if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) - return; + /* + * when @pwq is not linked, it doesn't hold any reference to the + * @wq, and @wq is invalid to access. + */ + if (!list_empty(&pwq->pwqs_node)) { + if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) + return;

- mutex_lock(&wq->mutex); - list_del_rcu(&pwq->pwqs_node); - is_last = list_empty(&wq->pwqs); - mutex_unlock(&wq->mutex); + mutex_lock(&wq->mutex); + list_del_rcu(&pwq->pwqs_node); + is_last = list_empty(&wq->pwqs); + mutex_unlock(&wq->mutex); + }

mutex_lock(&wq_pool_mutex); put_unbound_pool(pool);

From: Yang Yingliang yangyingliang@huawei.com

[ Upstream commit 42ca63f980842918560b25f0244307fd83b4777c ]

I got kmemleak report when doing fuzz test:

BUG: memory leak unreferenced object 0xffff88810c909b80 (size 64): comm "syz", pid 957, jiffies 4295220394 (age 399.090s) hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 08 00 00 00 01 02 00 04 ................ backtrace: [<00000000ca1f2e2e>] garp_request_join+0x285/0x3d0 [<00000000bf153351>] vlan_gvrp_request_join+0x15b/0x190 [<0000000024005e72>] vlan_dev_open+0x706/0x980 [<00000000dc20c4d4>] __dev_open+0x2bb/0x460 [<0000000066573004>] __dev_change_flags+0x501/0x650 [<0000000035b42f83>] rtnl_configure_link+0xee/0x280 [<00000000a5e69de0>] __rtnl_newlink+0xed5/0x1550 [<00000000a5258f4a>] rtnl_newlink+0x66/0x90 [<00000000506568ee>] rtnetlink_rcv_msg+0x439/0xbd0 [<00000000b7eaeae1>] netlink_rcv_skb+0x14d/0x420 [<00000000c373ce66>] netlink_unicast+0x550/0x750 [<00000000ec74ce74>] netlink_sendmsg+0x88b/0xda0 [<00000000381ff246>] sock_sendmsg+0xc9/0x120 [<000000008f6a2db3>] ____sys_sendmsg+0x6e8/0x820 [<000000008d9c1735>] ___sys_sendmsg+0x145/0x1c0 [<00000000aa39dd8b>] __sys_sendmsg+0xfe/0x1d0

Calling garp_request_leave() after garp_request_join(), the attr->state is set to GARP_APPLICANT_VO, garp_attr_destroy() won't be called in last transmit event in garp_uninit_applicant(), the attr of applicant will be leaked. To fix this leak, iterate and free each attr of applicant before rerturning from garp_uninit_applicant().

Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/802/garp.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)

diff --git a/net/802/garp.c b/net/802/garp.c index 2dac647ff420..237f6f076355 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -206,6 +206,19 @@ static void garp_attr_destroy(struct garp_applicant *app, struct garp_attr *attr kfree(attr); }

+static void garp_attr_destroy_all(struct garp_applicant *app) +{ + struct rb_node *node, *next; + struct garp_attr *attr; + + for (node = rb_first(&app->gid); + next = node ? rb_next(node) : NULL, node != NULL; + node = next) { + attr = rb_entry(node, struct garp_attr, node); + garp_attr_destroy(app, attr); + } +} + static int garp_pdu_init(struct garp_applicant *app) { struct sk_buff *skb; @@ -612,6 +625,7 @@ void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl

spin_lock_bh(&app->lock); garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); + garp_attr_destroy_all(app); garp_pdu_queue(app); spin_unlock_bh(&app->lock);

From: Xin Long lucien.xin@gmail.com

[ Upstream commit 1d11fa231cabeae09a95cb3e4cf1d9dd34e00f08 ]

The doc draft-stewart-tsvwg-sctp-ipv4-00 that restricts 198 addresses was never published. These addresses as private addresses should be allowed to use in SCTP.

As Michael Tuexen suggested, this patch is to move 198 addresses from unusable to private scope.

Reported-by: Sérgio surkamp@gmail.com Signed-off-by: Xin Long lucien.xin@gmail.com Acked-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/sctp/constants.h | 4 +--- net/sctp/protocol.c | 3 ++- 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index d4da07048aa3..cbf96458ce22 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -348,8 +348,7 @@ enum { #define SCTP_SCOPE_POLICY_MAX SCTP_SCOPE_POLICY_LINK

/* Based on IPv4 scoping <draft-stewart-tsvwg-sctp-ipv4-00.txt>, - * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 198.18.0.0/24, - * 192.88.99.0/24. + * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 192.88.99.0/24. * Also, RFC 8.4, non-unicast addresses are not considered valid SCTP * addresses. */ @@ -357,7 +356,6 @@ enum { ((htonl(INADDR_BROADCAST) == a) || \ ipv4_is_multicast(a) || \ ipv4_is_zeronet(a) || \ - ipv4_is_test_198(a) || \ ipv4_is_anycast_6to4(a))

/* Flags used for the bind address copy functions. */ diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index d5cf05efddfd..868b97607601 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -423,7 +423,8 @@ static enum sctp_scope sctp_v4_scope(union sctp_addr *addr) retval = SCTP_SCOPE_LINK; } else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) || ipv4_is_private_172(addr->v4.sin_addr.s_addr) || - ipv4_is_private_192(addr->v4.sin_addr.s_addr)) { + ipv4_is_private_192(addr->v4.sin_addr.s_addr) || + ipv4_is_test_198(addr->v4.sin_addr.s_addr)) { retval = SCTP_SCOPE_PRIVATE; } else { retval = SCTP_SCOPE_GLOBAL;

From: Desmond Cheong Zhi Xi desmondcheongzx@gmail.com

[ Upstream commit 54a5ead6f5e2b47131a7385d0c0af18e7b89cb02 ]

Pages that we read in hfs_bnode_read need to be kmapped into kernel address space. However, currently only the 0th page is kmapped. If the given offset + length exceeds this 0th page, then we have an invalid memory access.

To fix this, we kmap relevant pages one by one and copy their relevant portions of data.

An example of invalid memory access occurring without this fix can be seen in the following crash report:

================================================================== BUG: KASAN: use-after-free in memcpy include/linux/fortify-string.h:191 [inline] BUG: KASAN: use-after-free in hfs_bnode_read+0xc4/0xe0 fs/hfs/bnode.c:26 Read of size 2 at addr ffff888125fdcffe by task syz-executor5/4634

CPU: 0 PID: 4634 Comm: syz-executor5 Not tainted 5.13.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x195/0x1f8 lib/dump_stack.c:120 print_address_description.constprop.0+0x1d/0x110 mm/kasan/report.c:233 __kasan_report mm/kasan/report.c:419 [inline] kasan_report.cold+0x7b/0xd4 mm/kasan/report.c:436 check_region_inline mm/kasan/generic.c:180 [inline] kasan_check_range+0x154/0x1b0 mm/kasan/generic.c:186 memcpy+0x24/0x60 mm/kasan/shadow.c:65 memcpy include/linux/fortify-string.h:191 [inline] hfs_bnode_read+0xc4/0xe0 fs/hfs/bnode.c:26 hfs_bnode_read_u16 fs/hfs/bnode.c:34 [inline] hfs_bnode_find+0x880/0xcc0 fs/hfs/bnode.c:365 hfs_brec_find+0x2d8/0x540 fs/hfs/bfind.c:126 hfs_brec_read+0x27/0x120 fs/hfs/bfind.c:165 hfs_cat_find_brec+0x19a/0x3b0 fs/hfs/catalog.c:194 hfs_fill_super+0xc13/0x1460 fs/hfs/super.c:419 mount_bdev+0x331/0x3f0 fs/super.c:1368 hfs_mount+0x35/0x40 fs/hfs/super.c:457 legacy_get_tree+0x10c/0x220 fs/fs_context.c:592 vfs_get_tree+0x93/0x300 fs/super.c:1498 do_new_mount fs/namespace.c:2905 [inline] path_mount+0x13f5/0x20e0 fs/namespace.c:3235 do_mount fs/namespace.c:3248 [inline] __do_sys_mount fs/namespace.c:3456 [inline] __se_sys_mount fs/namespace.c:3433 [inline] __x64_sys_mount+0x2b8/0x340 fs/namespace.c:3433 do_syscall_64+0x37/0xc0 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x45e63a Code: 48 c7 c2 bc ff ff ff f7 d8 64 89 02 b8 ff ff ff ff eb d2 e8 88 04 00 00 0f 1f 84 00 00 00 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f9404d410d8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 0000000020000248 RCX: 000000000045e63a RDX: 0000000020000000 RSI: 0000000020000100 RDI: 00007f9404d41120 RBP: 00007f9404d41120 R08: 00000000200002c0 R09: 0000000020000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000003 R13: 0000000000000003 R14: 00000000004ad5d8 R15: 0000000000000000

The buggy address belongs to the page: page:00000000dadbcf3e refcount:0 mapcount:0 mapping:0000000000000000 index:0x1 pfn:0x125fdc flags: 0x2fffc0000000000(node=0|zone=2|lastcpupid=0x3fff) raw: 02fffc0000000000 ffffea000497f748 ffffea000497f6c8 0000000000000000 raw: 0000000000000001 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected

Memory state around the buggy address: ffff888125fdce80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888125fdcf00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

ffff888125fdcf80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

^ ffff888125fdd000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888125fdd080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ==================================================================

Link: https://lkml.kernel.org/r/20210701030756.58760-3-desmondcheongzx@gmail.com Signed-off-by: Desmond Cheong Zhi Xi desmondcheongzx@gmail.com Reviewed-by: Viacheslav Dubeyko slava@dubeyko.com Cc: Al Viro viro@zeniv.linux.org.uk Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: Gustavo A. R. Silva gustavoars@kernel.org Cc: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/hfs/bnode.c | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index 8aec5e732abf..bca3ea4137ee 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -15,16 +15,31 @@

#include "btree.h"

-void hfs_bnode_read(struct hfs_bnode *node, void *buf, - int off, int len) +void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len) { struct page *page; + int pagenum; + int bytes_read; + int bytes_to_read; + void *vaddr;

off += node->page_offset; - page = node->page[0]; + pagenum = off >> PAGE_SHIFT; + off &= ~PAGE_MASK; /* compute page offset for the first page */

- memcpy(buf, kmap(page) + off, len); - kunmap(page); + for (bytes_read = 0; bytes_read < len; bytes_read += bytes_to_read) { + if (pagenum >= node->tree->pages_per_bnode) + break; + page = node->page[pagenum]; + bytes_to_read = min_t(int, len - bytes_read, PAGE_SIZE - off); + + vaddr = kmap_atomic(page); + memcpy(buf + bytes_read, vaddr + off, bytes_to_read); + kunmap_atomic(vaddr); + + pagenum++; + off = 0; /* page offset only applies to the first page */ + } }

u16 hfs_bnode_read_u16(struct hfs_bnode *node, int off)

From: Sudeep Holla sudeep.holla@arm.com

[ Upstream commit 82a1c67554dff610d6be4e1982c425717b3c6a23 ]

Once the new schema interrupt-controller/arm,vic.yaml is added, we get the below warnings:

arch/arm/boot/dts/versatile-ab.dt.yaml: intc@10140000: $nodename:0: 'intc@10140000' does not match '^interrupt-controller(@[0-9a-f,]+)*$'

arch/arm/boot/dts/versatile-ab.dt.yaml: intc@10140000: 'clear-mask' does not match any of the regexes

Fix the node names for the interrupt controller to conform to the standard node name interrupt-controller@.. Also drop invalid clear-mask property.

Signed-off-by: Sudeep Holla sudeep.holla@arm.com Acked-by: Linus Walleij linus.walleij@linaro.org Link: https://lore.kernel.org/r/20210701132118.759454-1-sudeep.holla@arm.com' Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/versatile-ab.dts | 5 ++--- arch/arm/boot/dts/versatile-pb.dts | 2 +- 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/arch/arm/boot/dts/versatile-ab.dts b/arch/arm/boot/dts/versatile-ab.dts index a9000d22b2c0..873889ddecbe 100644 --- a/arch/arm/boot/dts/versatile-ab.dts +++ b/arch/arm/boot/dts/versatile-ab.dts @@ -155,16 +155,15 @@ #size-cells = <1>; ranges;

- vic: intc@10140000 { + vic: interrupt-controller@10140000 { compatible = "arm,versatile-vic"; interrupt-controller; #interrupt-cells = <1>; reg = <0x10140000 0x1000>; - clear-mask = <0xffffffff>; valid-mask = <0xffffffff>; };

- sic: intc@10003000 { + sic: interrupt-controller@10003000 { compatible = "arm,versatile-sic"; interrupt-controller; #interrupt-cells = <1>; diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts index 06a0fdf24026..e7e751a858d8 100644 --- a/arch/arm/boot/dts/versatile-pb.dts +++ b/arch/arm/boot/dts/versatile-pb.dts @@ -7,7 +7,7 @@

amba { /* The Versatile PB is using more SIC IRQ lines than the AB */ - sic: intc@10003000 { + sic: interrupt-controller@10003000 { clear-mask = <0xffffffff>; /* * Valid interrupt lines mask according to

From: Eric Dumazet edumazet@google.com

commit 38ec4944b593fd90c5ef42aaaa53e66ae5769d04 upstream.

After commit 0f6925b3e8da ("virtio_net: Do not pull payload in skb->head") Guenter Roeck reported one failure in his tests using sh architecture.

After much debugging, we have been able to spot silent unaligned accesses in inet_gro_receive()

The issue at hand is that upper networking stacks assume their header is word-aligned. Low level drivers are supposed to reserve NET_IP_ALIGN bytes before the Ethernet header to make that happen.

This patch hardens skb_gro_reset_offset() to not allow frag0 fast-path if the fragment is not properly aligned.

Some arches like x86, arm64 and powerpc do not care and define NET_IP_ALIGN as 0, this extra check will be a NOP for them.

Note that if frag0 is not used, GRO will call pskb_may_pull() as many times as needed to pull network and transport headers.

Fixes: 0f6925b3e8da ("virtio_net: Do not pull payload in skb->head") Fixes: 78a478d0efd9 ("gro: Inline skb_gro_header and cache frag0 virtual address") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: Guenter Roeck linux@roeck-us.net Cc: Xuan Zhuo xuanzhuo@linux.alibaba.com Cc: "Michael S. Tsirkin" mst@redhat.com Cc: Jason Wang jasowang@redhat.com Acked-by: Michael S. Tsirkin mst@redhat.com Tested-by: Guenter Roeck linux@roeck-us.net Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/skbuff.h | 9 +++++++++ net/core/dev.c | 3 ++- 2 files changed, 11 insertions(+), 1 deletion(-)

--- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2785,6 +2785,15 @@ static inline void skb_propagate_pfmemal }

/** + * skb_frag_off() - Returns the offset of a skb fragment + * @frag: the paged fragment + */ +static inline unsigned int skb_frag_off(const skb_frag_t *frag) +{ + return frag->page_offset; +} + +/** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4763,7 +4763,8 @@ static void skb_gro_reset_offset(struct

if (skb_mac_header(skb) == skb_tail_pointer(skb) && pinfo->nr_frags && - !PageHighMem(skb_frag_page(frag0))) { + !PageHighMem(skb_frag_page(frag0)) && + (!NET_IP_ALIGN || !(skb_frag_off(frag0) & 3))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, skb_frag_size(frag0),

From: Junxiao Bi junxiao.bi@oracle.com

commit f267aeb6dea5e468793e5b8eb6a9c72c0020d418 upstream.

If append-dio feature is enabled, direct-io write and fallocate could run in parallel to extend file size, fallocate used "orig_isize" to record i_size before taking "ip_alloc_sem", when ocfs2_zeroout_partial_cluster() zeroout EOF blocks, i_size maybe already extended by ocfs2_dio_end_io_write(), that will cause valid data zeroed out.

Link: https://lkml.kernel.org/r/20210722054923.24389-1-junxiao.bi@oracle.com Fixes: 6bba4471f0cc ("ocfs2: fix data corruption by fallocate") Signed-off-by: Junxiao Bi junxiao.bi@oracle.com Reviewed-by: Joseph Qi joseph.qi@linux.alibaba.com Cc: Changwei Ge gechangwei@live.cn Cc: Gang He ghe@suse.com Cc: Joel Becker jlbec@evilplan.org Cc: Jun Piao piaojun@huawei.com Cc: Mark Fasheh mark@fasheh.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ocfs2/file.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1941,7 +1941,6 @@ static int __ocfs2_change_file_space(str goto out_inode_unlock; }

- orig_isize = i_size_read(inode); switch (sr->l_whence) { case 0: /*SEEK_SET*/ break; @@ -1949,7 +1948,7 @@ static int __ocfs2_change_file_space(str sr->l_start += f_pos; break; case 2: /*SEEK_END*/ - sr->l_start += orig_isize; + sr->l_start += i_size_read(inode); break; default: ret = -EINVAL; @@ -2004,6 +2003,7 @@ static int __ocfs2_change_file_space(str ret = -EINVAL; }

+ orig_isize = i_size_read(inode); /* zeroout eof blocks in the cluster. */ if (!ret && change_size && orig_isize < size) { ret = ocfs2_zeroout_partial_cluster(inode, orig_isize,

From: Ziyang Xuan william.xuanziyang@huawei.com

commit 54f93336d000229f72c26d8a3f69dd256b744528 upstream.

We get a bug during ltp can_filter test as following.

=========================================== [60919.264984] BUG: unable to handle kernel NULL pointer dereference at 0000000000000010 [60919.265223] PGD 8000003dda726067 P4D 8000003dda726067 PUD 3dda727067 PMD 0 [60919.265443] Oops: 0000 [#1] SMP PTI [60919.265550] CPU: 30 PID: 3638365 Comm: can_filter Kdump: loaded Tainted: G W 4.19.90+ #1 [60919.266068] RIP: 0010:selinux_socket_sock_rcv_skb+0x3e/0x200 [60919.293289] RSP: 0018:ffff8d53bfc03cf8 EFLAGS: 00010246 [60919.307140] RAX: 0000000000000000 RBX: 000000000000001d RCX: 0000000000000007 [60919.320756] RDX: 0000000000000001 RSI: ffff8d5104a8ed00 RDI: ffff8d53bfc03d30 [60919.334319] RBP: ffff8d9338056800 R08: ffff8d53bfc29d80 R09: 0000000000000001 [60919.347969] R10: ffff8d53bfc03ec0 R11: ffffb8526ef47c98 R12: ffff8d53bfc03d30 [60919.350320] perf: interrupt took too long (3063 > 2500), lowering kernel.perf_event_max_sample_rate to 65000 [60919.361148] R13: 0000000000000001 R14: ffff8d53bcf90000 R15: 0000000000000000 [60919.361151] FS: 00007fb78b6b3600(0000) GS:ffff8d53bfc00000(0000) knlGS:0000000000000000 [60919.400812] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [60919.413730] CR2: 0000000000000010 CR3: 0000003e3f784006 CR4: 00000000007606e0 [60919.426479] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [60919.439339] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [60919.451608] PKRU: 55555554 [60919.463622] Call Trace: [60919.475617] <IRQ> [60919.487122] ? update_load_avg+0x89/0x5d0 [60919.498478] ? update_load_avg+0x89/0x5d0 [60919.509822] ? account_entity_enqueue+0xc5/0xf0 [60919.520709] security_sock_rcv_skb+0x2a/0x40 [60919.531413] sk_filter_trim_cap+0x47/0x1b0 [60919.542178] ? kmem_cache_alloc+0x38/0x1b0 [60919.552444] sock_queue_rcv_skb+0x17/0x30 [60919.562477] raw_rcv+0x110/0x190 [can_raw] [60919.572539] can_rcv_filter+0xbc/0x1b0 [can] [60919.582173] can_receive+0x6b/0xb0 [can] [60919.591595] can_rcv+0x31/0x70 [can] [60919.600783] __netif_receive_skb_one_core+0x5a/0x80 [60919.609864] process_backlog+0x9b/0x150 [60919.618691] net_rx_action+0x156/0x400 [60919.627310] ? sched_clock_cpu+0xc/0xa0 [60919.635714] __do_softirq+0xe8/0x2e9 [60919.644161] do_softirq_own_stack+0x2a/0x40 [60919.652154] </IRQ> [60919.659899] do_softirq.part.17+0x4f/0x60 [60919.667475] __local_bh_enable_ip+0x60/0x70 [60919.675089] __dev_queue_xmit+0x539/0x920 [60919.682267] ? finish_wait+0x80/0x80 [60919.689218] ? finish_wait+0x80/0x80 [60919.695886] ? sock_alloc_send_pskb+0x211/0x230 [60919.702395] ? can_send+0xe5/0x1f0 [can] [60919.708882] can_send+0xe5/0x1f0 [can] [60919.715037] raw_sendmsg+0x16d/0x268 [can_raw]

It's because raw_setsockopt() concurrently with unregister_netdevice_many(). Concurrent scenario as following.

cpu0 cpu1 raw_bind raw_setsockopt unregister_netdevice_many unlist_netdevice dev_get_by_index raw_notifier raw_enable_filters ...... can_rx_register can_rcv_list_find(..., net->can.rx_alldev_list)

......

sock_close raw_release(sock_a)

......

can_receive can_rcv_filter(net->can.rx_alldev_list, ...) raw_rcv(skb, sock_a) BUG

After unlist_netdevice(), dev_get_by_index() return NULL in raw_setsockopt(). Function raw_enable_filters() will add sock and can_filter to net->can.rx_alldev_list. Then the sock is closed. Followed by, we sock_sendmsg() to a new vcan device use the same can_filter. Protocol stack match the old receiver whose sock has been released on net->can.rx_alldev_list in can_rcv_filter(). Function raw_rcv() uses the freed sock. UAF BUG is triggered.

We can find that the key issue is that net_device has not been protected in raw_setsockopt(). Use rtnl_lock to protect net_device in raw_setsockopt().

Fixes: c18ce101f2e4 ("[CAN]: Add raw protocol") Link: https://lore.kernel.org/r/20210722070819.1048263-1-william.xuanziyang@huawei... Cc: linux-stable stable@vger.kernel.org Signed-off-by: Ziyang Xuan william.xuanziyang@huawei.com Acked-by: Oliver Hartkopp socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/can/raw.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-)

--- a/net/can/raw.c +++ b/net/can/raw.c @@ -549,10 +549,18 @@ static int raw_setsockopt(struct socket return -EFAULT; }

+ rtnl_lock(); lock_sock(sk);

- if (ro->bound && ro->ifindex) + if (ro->bound && ro->ifindex) { dev = dev_get_by_index(sock_net(sk), ro->ifindex); + if (!dev) { + if (count > 1) + kfree(filter); + err = -ENODEV; + goto out_fil; + } + }

if (ro->bound) { /* (try to) register the new filters */ @@ -591,6 +599,7 @@ static int raw_setsockopt(struct socket dev_put(dev);

release_sock(sk); + rtnl_unlock();

break;

@@ -603,10 +612,16 @@ static int raw_setsockopt(struct socket

err_mask &= CAN_ERR_MASK;

+ rtnl_lock(); lock_sock(sk);

- if (ro->bound && ro->ifindex) + if (ro->bound && ro->ifindex) { dev = dev_get_by_index(sock_net(sk), ro->ifindex); + if (!dev) { + err = -ENODEV; + goto out_err; + } + }

/* remove current error mask */ if (ro->bound) { @@ -630,6 +645,7 @@ static int raw_setsockopt(struct socket dev_put(dev);

release_sock(sk); + rtnl_unlock();

break;

From: Pavel Skripkin paskripkin@gmail.com

commit 0e865f0c31928d6a313269ef624907eec55287c4 upstream.

In usb_8dev_start() MAX_RX_URBS coherent buffers are allocated and there is nothing, that frees them:

1) In callback function the urb is resubmitted and that's all 2) In disconnect function urbs are simply killed, but URB_FREE_BUFFER is not set (see usb_8dev_start) and this flag cannot be used with coherent buffers.

So, all allocated buffers should be freed with usb_free_coherent() explicitly.

Side note: This code looks like a copy-paste of other can drivers. The same patch was applied to mcba_usb driver and it works nice with real hardware. There is no change in functionality, only clean-up code for coherent buffers.

Fixes: 0024d8ad1639 ("can: usb_8dev: Add support for USB2CAN interface from 8 devices") Link: https://lore.kernel.org/r/d39b458cd425a1cf7f512f340224e6e9563b07bd.162740447... Cc: linux-stable stable@vger.kernel.org Signed-off-by: Pavel Skripkin paskripkin@gmail.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/can/usb/usb_8dev.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-)

--- a/drivers/net/can/usb/usb_8dev.c +++ b/drivers/net/can/usb/usb_8dev.c @@ -148,7 +148,8 @@ struct usb_8dev_priv { u8 *cmd_msg_buffer;

struct mutex usb_8dev_cmd_lock; - + void *rxbuf[MAX_RX_URBS]; + dma_addr_t rxbuf_dma[MAX_RX_URBS]; };

/* tx frame */ @@ -744,6 +745,7 @@ static int usb_8dev_start(struct usb_8de for (i = 0; i < MAX_RX_URBS; i++) { struct urb *urb = NULL; u8 *buf; + dma_addr_t buf_dma;

/* create a URB, and a buffer for it */ urb = usb_alloc_urb(0, GFP_KERNEL); @@ -753,7 +755,7 @@ static int usb_8dev_start(struct usb_8de }

buf = usb_alloc_coherent(priv->udev, RX_BUFFER_SIZE, GFP_KERNEL, - &urb->transfer_dma); + &buf_dma); if (!buf) { netdev_err(netdev, "No memory left for USB buffer\n"); usb_free_urb(urb); @@ -761,6 +763,8 @@ static int usb_8dev_start(struct usb_8de break; }

+ urb->transfer_dma = buf_dma; + usb_fill_bulk_urb(urb, priv->udev, usb_rcvbulkpipe(priv->udev, USB_8DEV_ENDP_DATA_RX), @@ -778,6 +782,9 @@ static int usb_8dev_start(struct usb_8de break; }

+ priv->rxbuf[i] = buf; + priv->rxbuf_dma[i] = buf_dma; + /* Drop reference, USB core will take care of freeing it */ usb_free_urb(urb); } @@ -847,6 +854,10 @@ static void unlink_all_urbs(struct usb_8

usb_kill_anchored_urbs(&priv->rx_submitted);

+ for (i = 0; i < MAX_RX_URBS; ++i) + usb_free_coherent(priv->udev, RX_BUFFER_SIZE, + priv->rxbuf[i], priv->rxbuf_dma[i]); + usb_kill_anchored_urbs(&priv->tx_submitted); atomic_set(&priv->active_tx_urbs, 0);

From: Pavel Skripkin paskripkin@gmail.com

commit 928150fad41ba16df7fcc9f7f945747d0f56cbb6 upstream.

In esd_usb2_setup_rx_urbs() MAX_RX_URBS coherent buffers are allocated and there is nothing, that frees them:

1) In callback function the urb is resubmitted and that's all 2) In disconnect function urbs are simply killed, but URB_FREE_BUFFER is not set (see esd_usb2_setup_rx_urbs) and this flag cannot be used with coherent buffers.

So, all allocated buffers should be freed with usb_free_coherent() explicitly.

Side note: This code looks like a copy-paste of other can drivers. The same patch was applied to mcba_usb driver and it works nice with real hardware. There is no change in functionality, only clean-up code for coherent buffers.

Fixes: 96d8e90382dc ("can: Add driver for esd CAN-USB/2 device") Link: https://lore.kernel.org/r/b31b096926dcb35998ad0271aac4b51770ca7cc8.162740447... Cc: linux-stable stable@vger.kernel.org Signed-off-by: Pavel Skripkin paskripkin@gmail.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/can/usb/esd_usb2.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-)

--- a/drivers/net/can/usb/esd_usb2.c +++ b/drivers/net/can/usb/esd_usb2.c @@ -207,6 +207,8 @@ struct esd_usb2 { int net_count; u32 version; int rxinitdone; + void *rxbuf[MAX_RX_URBS]; + dma_addr_t rxbuf_dma[MAX_RX_URBS]; };

struct esd_usb2_net_priv { @@ -556,6 +558,7 @@ static int esd_usb2_setup_rx_urbs(struct for (i = 0; i < MAX_RX_URBS; i++) { struct urb *urb = NULL; u8 *buf = NULL; + dma_addr_t buf_dma;

/* create a URB, and a buffer for it */ urb = usb_alloc_urb(0, GFP_KERNEL); @@ -565,7 +568,7 @@ static int esd_usb2_setup_rx_urbs(struct }

buf = usb_alloc_coherent(dev->udev, RX_BUFFER_SIZE, GFP_KERNEL, - &urb->transfer_dma); + &buf_dma); if (!buf) { dev_warn(dev->udev->dev.parent, "No memory left for USB buffer\n"); @@ -573,6 +576,8 @@ static int esd_usb2_setup_rx_urbs(struct goto freeurb; }

+ urb->transfer_dma = buf_dma; + usb_fill_bulk_urb(urb, dev->udev, usb_rcvbulkpipe(dev->udev, 1), buf, RX_BUFFER_SIZE, @@ -585,8 +590,12 @@ static int esd_usb2_setup_rx_urbs(struct usb_unanchor_urb(urb); usb_free_coherent(dev->udev, RX_BUFFER_SIZE, buf, urb->transfer_dma); + goto freeurb; }

+ dev->rxbuf[i] = buf; + dev->rxbuf_dma[i] = buf_dma; + freeurb: /* Drop reference, USB core will take care of freeing it */ usb_free_urb(urb); @@ -674,6 +683,11 @@ static void unlink_all_urbs(struct esd_u int i, j;

usb_kill_anchored_urbs(&dev->rx_submitted); + + for (i = 0; i < MAX_RX_URBS; ++i) + usb_free_coherent(dev->udev, RX_BUFFER_SIZE, + dev->rxbuf[i], dev->rxbuf_dma[i]); + for (i = 0; i < dev->net_count; i++) { priv = dev->nets[i]; if (priv) {

From: Krzysztof Kozlowski krzysztof.kozlowski@canonical.com

commit 5e7b30d24a5b8cb691c173b45b50e3ca0191be19 upstream.

There is a use after free memory corruption during module exit: - nfcsim_exit() - nfcsim_device_free(dev0) - nfc_digital_unregister_device() This iterates over command queue and frees all commands, - dev->up = false - nfcsim_link_shutdown() - nfcsim_link_recv_wake() This wakes the sleeping thread nfcsim_link_recv_skb().

- nfcsim_link_recv_skb() Wake from wait_event_interruptible_timeout(), call directly the deb->cb callback even though (dev->up == false), - digital_send_cmd_complete() Dereference of "struct digital_cmd" cmd which was freed earlier by nfc_digital_unregister_device().

This causes memory corruption shortly after (with unrelated stack trace):

nfc nfc0: NFC: nfcsim_recv_wq: Device is down llcp: nfc_llcp_recv: err -19 nfc nfc1: NFC: nfcsim_recv_wq: Device is down BUG: unable to handle page fault for address: ffffffffffffffed Call Trace: fsnotify+0x54b/0x5c0 __fsnotify_parent+0x1fe/0x300 ? vfs_write+0x27c/0x390 vfs_write+0x27c/0x390 ksys_write+0x63/0xe0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae

KASAN report:

BUG: KASAN: use-after-free in digital_send_cmd_complete+0x16/0x50 Write of size 8 at addr ffff88800a05f720 by task kworker/0:2/71 Workqueue: events nfcsim_recv_wq [nfcsim] Call Trace:  dump_stack_lvl+0x45/0x59  print_address_description.constprop.0+0x21/0x140  ? digital_send_cmd_complete+0x16/0x50  ? digital_send_cmd_complete+0x16/0x50  kasan_report.cold+0x7f/0x11b  ? digital_send_cmd_complete+0x16/0x50  ? digital_dep_link_down+0x60/0x60  digital_send_cmd_complete+0x16/0x50  nfcsim_recv_wq+0x38f/0x3d5 [nfcsim]  ? nfcsim_in_send_cmd+0x4a/0x4a [nfcsim]  ? lock_is_held_type+0x98/0x110  ? finish_wait+0x110/0x110  ? rcu_read_lock_sched_held+0x9c/0xd0  ? rcu_read_lock_bh_held+0xb0/0xb0  ? lockdep_hardirqs_on_prepare+0x12e/0x1f0

This flow of calling digital_send_cmd_complete() callback on driver exit is specific to nfcsim which implements reading and sending work queues. Since the NFC digital device was unregistered, the callback should not be called.

Fixes: 204bddcb508f ("NFC: nfcsim: Make use of the Digital layer") Cc: stable@vger.kernel.org Signed-off-by: Krzysztof Kozlowski krzysztof.kozlowski@canonical.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/nfc/nfcsim.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/nfc/nfcsim.c +++ b/drivers/nfc/nfcsim.c @@ -201,8 +201,7 @@ static void nfcsim_recv_wq(struct work_s

if (!IS_ERR(skb)) dev_kfree_skb(skb); - - skb = ERR_PTR(-ENODEV); + return; }

dev->cb(dev->nfc_digital_dev, dev->arg, skb);

From: Nguyen Dinh Phi phind.uet@gmail.com

commit f9a5c358c8d26fed0cc45f2afc64633d4ba21dff upstream.

When we exceed the limit of BSS entries, this function will free the new entry, however, at this time, it is the last door to access the inputed ies, so these ies will be unreferenced objects and cause memory leak. Therefore we should free its ies before deallocating the new entry, beside of dropping it from hidden_list.

Signed-off-by: Nguyen Dinh Phi phind.uet@gmail.com Link: https://lore.kernel.org/r/20210628132334.851095-1-phind.uet@gmail.com Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/wireless/scan.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

--- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1026,16 +1026,14 @@ cfg80211_bss_update(struct cfg80211_regi * be grouped with this beacon for updates ... */ if (!cfg80211_combine_bsses(rdev, new)) { - kfree(new); + bss_ref_put(rdev, new); goto drop; } }

if (rdev->bss_entries >= bss_entries_limit && !cfg80211_bss_expire_oldest(rdev)) { - if (!list_empty(&new->hidden_list)) - list_del(&new->hidden_list); - kfree(new); + bss_ref_put(rdev, new); goto drop; }

From: Pablo Neira Ayuso pablo@netfilter.org

[ Upstream commit a33f387ecd5aafae514095c2c4a8c24f7aea7e8b ]

nft_nat reports a bogus EAFNOSUPPORT if no layer 3 information is specified.

Fixes: d07db9884a5f ("netfilter: nf_tables: introduce nft_validate_register_load()") Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nft_nat.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index a18cceecef88..04dd813ed775 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -153,7 +153,9 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, alen = FIELD_SIZEOF(struct nf_nat_range, min_addr.ip6); break; default: - return -EAFNOSUPPORT; + if (tb[NFTA_NAT_REG_ADDR_MIN]) + return -EAFNOSUPPORT; + break; } priv->family = family;

From: Jiapeng Chong jiapeng.chong@linux.alibaba.com

[ Upstream commit 7e4960b3d66d7248b23de3251118147812b42da2 ]

The error code is missing in this code scenario, add the error code '-EINVAL' to the return value 'err'.

Eliminate the follow smatch warning:

drivers/net/ethernet/mellanox/mlx4/main.c:3538 mlx4_load_one() warn: missing error code 'err'.

Reported-by: Abaci Robot abaci@linux.alibaba.com Fixes: 7ae0e400cd93 ("net/mlx4_core: Flexible (asymmetric) allocation of EQs and MSI-X vectors for PF/VFs") Signed-off-by: Jiapeng Chong jiapeng.chong@linux.alibaba.com Reviewed-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx4/main.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index c6660b61e836..69692f7a523c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3469,6 +3469,7 @@ slave_start:

if (!SRIOV_VALID_STATE(dev->flags)) { mlx4_err(dev, "Invalid SRIOV state\n"); + err = -EINVAL; goto err_close; } }

From: Maor Gottlieb maorg@nvidia.com

[ Upstream commit 8b54874ef1617185048029a3083d510569e93751 ]

Fix a bug when flow table is created in priority that already has other flow tables as shown in the below diagram. If the new flow table (FT-B) has the lowest level in the priority, we need to connect the flow tables from the previous priority (p0) to this new table. In addition when this flow table is destroyed (FT-B), we need to connect the flow tables from the previous priority (p0) to the next level flow table (FT-C) in the same priority of the destroyed table (if exists).

--------- |root_ns| --------- | -------------------------------- | | | ---------- ---------- --------- |p(prio)-x| | p-y | | p-n | ---------- ---------- --------- | | ---------------- ------------------ |ns(e.g bypass)| |ns(e.g. kernel) | ---------------- ------------------ | | | ------- ------ ---- | p0 | | p1 | |p2| ------- ------ ---- | | \ -------- ------- ------ | FT-A | |FT-B | |FT-C| -------- ------- ------

Fixes: f90edfd279f3 ("net/mlx5_core: Connect flow tables") Signed-off-by: Maor Gottlieb maorg@nvidia.com Reviewed-by: Mark Bloch mbloch@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 24d1b0be5a68..24f70c337d8f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -795,17 +795,19 @@ static int connect_fwd_rules(struct mlx5_core_dev *dev, static int connect_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft, struct fs_prio *prio) { - struct mlx5_flow_table *next_ft; + struct mlx5_flow_table *next_ft, *first_ft; int err = 0;

/* Connect_prev_fts and update_root_ft_create are mutually exclusive */

- if (list_empty(&prio->node.children)) { + first_ft = list_first_entry_or_null(&prio->node.children, + struct mlx5_flow_table, node.list); + if (!first_ft || first_ft->level > ft->level) { err = connect_prev_fts(dev, ft, prio); if (err) return err;

- next_ft = find_next_chained_ft(prio); + next_ft = first_ft ? first_ft : find_next_chained_ft(prio); err = connect_fwd_rules(dev, ft, next_ft); if (err) return err; @@ -1703,7 +1705,7 @@ static int disconnect_flow_table(struct mlx5_flow_table *ft) node.list) == ft)) return 0;

- next_ft = find_next_chained_ft(prio); + next_ft = find_next_ft(ft); err = connect_fwd_rules(dev, next_ft, ft); if (err) return err;

From: Wang Hai wanghai38@huawei.com

[ Upstream commit 76a16be07b209a3f507c72abe823bd3af1c8661a ]

Replace pci_enable_device() with pcim_enable_device(), pci_disable_device() and pci_release_regions() will be called in release automatically.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Wang Hai wanghai38@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/dec/tulip/winbond-840.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c index 32d7229544fa..e3b4345b2cc8 100644 --- a/drivers/net/ethernet/dec/tulip/winbond-840.c +++ b/drivers/net/ethernet/dec/tulip/winbond-840.c @@ -367,7 +367,7 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) int i, option = find_cnt < MAX_UNITS ? options[find_cnt] : 0; void __iomem *ioaddr;

- i = pci_enable_device(pdev); + i = pcim_enable_device(pdev); if (i) return i;

pci_set_master(pdev); @@ -389,7 +389,7 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent)

ioaddr = pci_iomap(pdev, TULIP_BAR, netdev_res_size); if (!ioaddr) - goto err_out_free_res; + goto err_out_netdev;

for (i = 0; i < 3; i++) ((__le16 *)dev->dev_addr)[i] = cpu_to_le16(eeprom_read(ioaddr, i)); @@ -468,8 +468,6 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent)

err_out_cleardev: pci_iounmap(pdev, ioaddr); -err_out_free_res: - pci_release_regions(pdev); err_out_netdev: free_netdev (dev); return -ENODEV; @@ -1537,7 +1535,6 @@ static void w840_remove1(struct pci_dev *pdev) if (dev) { struct netdev_private *np = netdev_priv(dev); unregister_netdev(dev); - pci_release_regions(pdev); pci_iounmap(pdev, np->base_addr); free_netdev(dev); }

From: Dan Carpenter dan.carpenter@oracle.com

[ Upstream commit f6b3c7848e66e9046c8a79a5b88fd03461cc252b ]

The hi3110_cmd() is supposed to return zero on success and negative error codes on failure, but it was accidentally declared as a u8 when it needs to be an int type.

Fixes: 57e83fb9b746 ("can: hi311x: Add Holt HI-311x CAN driver") Link: https://lore.kernel.org/r/20210729141246.GA1267@kili Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/can/spi/hi311x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c index ddaf46239e39..472175e37055 100644 --- a/drivers/net/can/spi/hi311x.c +++ b/drivers/net/can/spi/hi311x.c @@ -236,7 +236,7 @@ static int hi3110_spi_trans(struct spi_device *spi, int len) return ret; }

-static u8 hi3110_cmd(struct spi_device *spi, u8 command) +static int hi3110_cmd(struct spi_device *spi, u8 command) { struct hi3110_priv *priv = spi_get_drvdata(spi);