From: Nathan Chancellor nathan@kernel.org

Clang warns:

drivers/iommu/amd_iommu.c:1335:6: warning: variable 'flags' is used uninitialized whenever 'if' condition is true [-Wsometimes-uninitialized] if (!pte) ^~~~ drivers/iommu/amd_iommu.c:1352:40: note: uninitialized use occurs here spin_unlock_irqrestore(&domain->lock, flags); ^~~~~ drivers/iommu/amd_iommu.c:1335:2: note: remove the 'if' if its condition is always false if (!pte) ^~~~~~~~~ drivers/iommu/amd_iommu.c:1331:21: note: initialize the variable 'flags' to silence this warning unsigned long flags; ^ = 0 1 warning generated.

The backport of commit 140456f99419 ("iommu/amd: Fix sleeping in atomic in increase_address_space()") to 4.9 as commit 1d648460d7c5 ("iommu/amd: Fix sleeping in atomic in increase_address_space()") failed to keep the "return false", which in 4.9 needs to be a regular "return" due to a lack of commit f15d9a992f90 ("iommu/amd: Remove domain->updated").

This resolves the warning and matches the 4.14-4.19 backport.

Cc: Andrey Ryabinin arbn@yandex-team.com Cc: Joerg Roedel joro@8bytes.org Cc: Will Deacon will@kernel.org Fixes: 1d648460d7c5 ("iommu/amd: Fix sleeping in atomic in increase_address_space()") Reported-by: kernel test robot lkp@intel.com Signed-off-by: Nathan Chancellor nathan@kernel.org Acked-by: Joerg Roedel jroedel@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iommu/amd_iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1333,7 +1333,7 @@ static void increase_address_space(struc

pte = (void *)get_zeroed_page(gfp); if (!pte) - goto out; + return;

spin_lock_irqsave(&domain->lock, flags);

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 | 76 ----------------------- net/unix/garbage.c | 68 --------------------- net/unix/scm.c | 161 ++++++++++++++++++++++++++++++++++++++++++++++++++ net/unix/scm.h | 10 +++ 8 files changed, 184 insertions(+), 141 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 @@ -8,6 +8,7 @@

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 @@ -16,7 +16,7 @@ obj-$(CONFIG_NET) += ethernet/ 802/ sch obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ obj-$(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 @@ -9,3 +9,5 @@ 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 @@ -118,6 +118,8 @@ #include <linux/security.h> #include <linux/freezer.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); @@ -1505,80 +1507,6 @@ 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; -} - -#define MAX_RECURSION_LEVEL 4 - -static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - unsigned char max_level = 0; - - if (too_many_unix_fds(current)) - return -ETOOMANYREFS; - - for (i = scm->fp->count - 1; i >= 0; i--) { - struct sock *sk = unix_get_socket(scm->fp->fp[i]); - - if (sk) - max_level = max(max_level, - unix_sk(sk)->recursion_level); - } - if (unlikely(max_level > MAX_RECURSION_LEVEL)) - 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 max_level; -} - 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 +1,161 @@ +// 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 "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; +} + +#define MAX_RECURSION_LEVEL 4 + +int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + int i; + unsigned char max_level = 0; + + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + + for (i = scm->fp->count - 1; i >= 0; i--) { + struct sock *sk = unix_get_socket(scm->fp->fp[i]); + + if (sk) + max_level = max(max_level, + unix_sk(sk)->recursion_level); + } + if (unlikely(max_level > MAX_RECURSION_LEVEL)) + 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 max_level; +} +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 @@ -3397,15 +3397,21 @@ 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 b38ee6dcba45..5239b8f244e7 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: Desmond Cheong Zhi Xi desmondcheongzx@gmail.com

[ Upstream commit 16ee572eaf0d09daa4c8a755fdb71e40dbf8562d ]

Patch series "hfs: fix various errors", v2.

This series ultimately aims to address a lockdep warning in hfs_find_init reported by Syzbot [1].

The work done for this led to the discovery of another bug, and the Syzkaller repro test also reveals an invalid memory access error after clearing the lockdep warning. Hence, this series is broken up into three patches:

1. Add a missing call to hfs_find_exit for an error path in hfs_fill_super

2. Fix memory mapping in hfs_bnode_read by fixing calls to kmap

3. Add lock nesting notation to tell lockdep that the observed locking hierarchy is safe

This patch (of 3):

Before exiting hfs_fill_super, the struct hfs_find_data used in hfs_find_init should be passed to hfs_find_exit to be cleaned up, and to release the lock held on the btree.

The call to hfs_find_exit is missing from an error path. We add it back in by consolidating calls to hfs_find_exit for error paths.

Link: https://syzkaller.appspot.com/bug?id=f007ef1d7a31a469e3be7aeb0fde0769b18585d... [1] Link: https://lkml.kernel.org/r/20210701030756.58760-1-desmondcheongzx@gmail.com Link: https://lkml.kernel.org/r/20210701030756.58760-2-desmondcheongzx@gmail.com Signed-off-by: Desmond Cheong Zhi Xi desmondcheongzx@gmail.com Reviewed-by: Viacheslav Dubeyko slava@dubeyko.com Cc: Gustavo A. R. Silva gustavoars@kernel.org Cc: Al Viro viro@zeniv.linux.org.uk Cc: Shuah Khan skhan@linuxfoundation.org Cc: Greg Kroah-Hartman gregkh@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/super.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/hfs/super.c b/fs/hfs/super.c index bf6304a350a6..c2a5a0ca3948 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -427,14 +427,12 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) if (!res) { if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) { res = -EIO; - goto bail; + goto bail_hfs_find; } hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength); } - if (res) { - hfs_find_exit(&fd); - goto bail_no_root; - } + if (res) + goto bail_hfs_find; res = -EINVAL; root_inode = hfs_iget(sb, &fd.search_key->cat, &rec); hfs_find_exit(&fd); @@ -450,6 +448,8 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) /* everything's okay */ return 0;

+bail_hfs_find: + hfs_find_exit(&fd); bail_no_root: pr_err("get root inode failed\n"); bail:

From: Desmond Cheong Zhi Xi desmondcheongzx@gmail.com

[ Upstream commit b3b2177a2d795e35dc11597b2609eb1e7e57e570 ]

Syzbot reports a possible recursive lock in [1].

This happens due to missing lock nesting information. From the logs, we see that a call to hfs_fill_super is made to mount the hfs filesystem. While searching for the root inode, the lock on the catalog btree is grabbed. Then, when the parent of the root isn't found, a call to __hfs_bnode_create is made to create the parent of the root. This eventually leads to a call to hfs_ext_read_extent which grabs a lock on the extents btree.

Since the order of locking is catalog btree -> extents btree, this lock hierarchy does not lead to a deadlock.

To tell lockdep that this locking is safe, we add nesting notation to distinguish between catalog btrees, extents btrees, and attributes btrees (for HFS+). This has already been done in hfsplus.

Link: https://syzkaller.appspot.com/bug?id=f007ef1d7a31a469e3be7aeb0fde0769b18585d... [1] Link: https://lkml.kernel.org/r/20210701030756.58760-4-desmondcheongzx@gmail.com Signed-off-by: Desmond Cheong Zhi Xi desmondcheongzx@gmail.com Reported-by: syzbot+b718ec84a87b7e73ade4@syzkaller.appspotmail.com Tested-by: syzbot+b718ec84a87b7e73ade4@syzkaller.appspotmail.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/bfind.c | 14 +++++++++++++- fs/hfs/btree.h | 7 +++++++ 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/fs/hfs/bfind.c b/fs/hfs/bfind.c index de69d8a24f6d..7f2ef95dcd05 100644 --- a/fs/hfs/bfind.c +++ b/fs/hfs/bfind.c @@ -24,7 +24,19 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd) fd->key = ptr + tree->max_key_len + 2; hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0)); - mutex_lock(&tree->tree_lock); + switch (tree->cnid) { + case HFS_CAT_CNID: + mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX); + break; + case HFS_EXT_CNID: + mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX); + break; + case HFS_ATTR_CNID: + mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX); + break; + default: + return -EINVAL; + } return 0; }

diff --git a/fs/hfs/btree.h b/fs/hfs/btree.h index 2715f416b5a8..308b5f1af65b 100644 --- a/fs/hfs/btree.h +++ b/fs/hfs/btree.h @@ -12,6 +12,13 @@ typedef int (*btree_keycmp)(const btree_key *, const btree_key *);

#define NODE_HASH_SIZE 256

+/* B-tree mutex nested subclasses */ +enum hfs_btree_mutex_classes { + CATALOG_BTREE_MUTEX, + EXTENTS_BTREE_MUTEX, + ATTR_BTREE_MUTEX, +}; + /* A HFS BTree held in memory */ struct hfs_btree { struct super_block *sb;

From: Matthew Wilcox mawilcox@microsoft.com

commit 3b3c4babd898715926d24ae10aa64778ace33aae upstream.

Patch series "Multibyte memset variations", v4.

A relatively common idiom we're missing is a function to fill an area of memory with a pattern which is larger than a single byte. I first noticed this with a zram patch which wanted to fill a page with an 'unsigned long' value. There turn out to be quite a few places in the kernel which can benefit from using an optimised function rather than a loop; sometimes text size, sometimes speed, and sometimes both. The optimised PowerPC version (not included here) improves performance by about 30% on POWER8 on just the raw memset_l().

Most of the extra lines of code come from the three testcases I added.

This patch (of 8):

memset16(), memset32() and memset64() are like memset(), but allow the caller to fill the destination with a value larger than a single byte. memset_l() and memset_p() allow the caller to use unsigned long and pointer values respectively.

Link: http://lkml.kernel.org/r/20170720184539.31609-2-willy@infradead.org Signed-off-by: Matthew Wilcox mawilcox@microsoft.com Cc: "H. Peter Anvin" hpa@zytor.com Cc: "James E.J. Bottomley" jejb@linux.vnet.ibm.com Cc: "Martin K. Petersen" martin.petersen@oracle.com Cc: David Miller davem@davemloft.net Cc: Ingo Molnar mingo@elte.hu Cc: Ivan Kokshaysky ink@jurassic.park.msu.ru Cc: Matt Turner mattst88@gmail.com Cc: Michael Ellerman mpe@ellerman.id.au Cc: Minchan Kim minchan@kernel.org Cc: Ralf Baechle ralf@linux-mips.org Cc: Richard Henderson rth@twiddle.net Cc: Russell King rmk+kernel@armlinux.org.uk Cc: Sam Ravnborg sam@ravnborg.org Cc: Sergey Senozhatsky sergey.senozhatsky@gmail.com Cc: Thomas Gleixner tglx@linutronix.de Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Nobuhiro Iwamatsu (CIP) nobuhiro1.iwamatsu@toshiba.co.jp Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/string.h | 30 ++++++++++++++++++++++ lib/string.c | 66 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 96 insertions(+)

--- a/include/linux/string.h +++ b/include/linux/string.h @@ -103,6 +103,36 @@ extern __kernel_size_t strcspn(const cha #ifndef __HAVE_ARCH_MEMSET extern void * memset(void *,int,__kernel_size_t); #endif + +#ifndef __HAVE_ARCH_MEMSET16 +extern void *memset16(uint16_t *, uint16_t, __kernel_size_t); +#endif + +#ifndef __HAVE_ARCH_MEMSET32 +extern void *memset32(uint32_t *, uint32_t, __kernel_size_t); +#endif + +#ifndef __HAVE_ARCH_MEMSET64 +extern void *memset64(uint64_t *, uint64_t, __kernel_size_t); +#endif + +static inline void *memset_l(unsigned long *p, unsigned long v, + __kernel_size_t n) +{ + if (BITS_PER_LONG == 32) + return memset32((uint32_t *)p, v, n); + else + return memset64((uint64_t *)p, v, n); +} + +static inline void *memset_p(void **p, void *v, __kernel_size_t n) +{ + if (BITS_PER_LONG == 32) + return memset32((uint32_t *)p, (uintptr_t)v, n); + else + return memset64((uint64_t *)p, (uintptr_t)v, n); +} + #ifndef __HAVE_ARCH_MEMCPY extern void * memcpy(void *,const void *,__kernel_size_t); #endif --- a/lib/string.c +++ b/lib/string.c @@ -754,6 +754,72 @@ void memzero_explicit(void *s, size_t co } EXPORT_SYMBOL(memzero_explicit);

+#ifndef __HAVE_ARCH_MEMSET16 +/** + * memset16() - Fill a memory area with a uint16_t + * @s: Pointer to the start of the area. + * @v: The value to fill the area with + * @count: The number of values to store + * + * Differs from memset() in that it fills with a uint16_t instead + * of a byte. Remember that @count is the number of uint16_ts to + * store, not the number of bytes. + */ +void *memset16(uint16_t *s, uint16_t v, size_t count) +{ + uint16_t *xs = s; + + while (count--) + *xs++ = v; + return s; +} +EXPORT_SYMBOL(memset16); +#endif + +#ifndef __HAVE_ARCH_MEMSET32 +/** + * memset32() - Fill a memory area with a uint32_t + * @s: Pointer to the start of the area. + * @v: The value to fill the area with + * @count: The number of values to store + * + * Differs from memset() in that it fills with a uint32_t instead + * of a byte. Remember that @count is the number of uint32_ts to + * store, not the number of bytes. + */ +void *memset32(uint32_t *s, uint32_t v, size_t count) +{ + uint32_t *xs = s; + + while (count--) + *xs++ = v; + return s; +} +EXPORT_SYMBOL(memset32); +#endif + +#ifndef __HAVE_ARCH_MEMSET64 +/** + * memset64() - Fill a memory area with a uint64_t + * @s: Pointer to the start of the area. + * @v: The value to fill the area with + * @count: The number of values to store + * + * Differs from memset() in that it fills with a uint64_t instead + * of a byte. Remember that @count is the number of uint64_ts to + * store, not the number of bytes. + */ +void *memset64(uint64_t *s, uint64_t v, size_t count) +{ + uint64_t *xs = s; + + while (count--) + *xs++ = v; + return s; +} +EXPORT_SYMBOL(memset64); +#endif + #ifndef __HAVE_ARCH_MEMCPY /** * memcpy - Copy one area of memory to another

From: Juergen Gross jgross@suse.com

commit 76b4f357d0e7d8f6f0013c733e6cba1773c266d3 upstream.

KVM_MAX_VCPU_ID is the maximum vcpu-id of a guest, and not the number of vcpu-ids. Fix array indexed by vcpu-id to have KVM_MAX_VCPU_ID+1 elements.

Note that this is currently no real problem, as KVM_MAX_VCPU_ID is an odd number, resulting in always enough padding being available at the end of those arrays.

Nevertheless this should be fixed in order to avoid rare problems in case someone is using an even number for KVM_MAX_VCPU_ID.

Signed-off-by: Juergen Gross jgross@suse.com Message-Id: 20210701154105.23215-2-jgross@suse.com Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/ioapic.c | 2 +- arch/x86/kvm/ioapic.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-)

--- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -96,7 +96,7 @@ static unsigned long ioapic_read_indirec static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic) { ioapic->rtc_status.pending_eoi = 0; - bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID); + bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID + 1); }

static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic); --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -42,13 +42,13 @@ struct kvm_vcpu;

struct dest_map { /* vcpu bitmap where IRQ has been sent */ - DECLARE_BITMAP(map, KVM_MAX_VCPU_ID); + DECLARE_BITMAP(map, KVM_MAX_VCPU_ID + 1);

/* * Vector sent to a given vcpu, only valid when * the vcpu's bit in map is set */ - u8 vectors[KVM_MAX_VCPU_ID]; + u8 vectors[KVM_MAX_VCPU_ID + 1]; };

From: Junxiao Bi junxiao.bi@oracle.com

commit 9449ad33be8480f538b11a593e2dda2fb33ca06d upstream.

For punch holes in EOF blocks, fallocate used buffer write to zero the EOF blocks in last cluster. But since ->writepage will ignore EOF pages, those zeros will not be flushed.

This "looks" ok as commit 6bba4471f0cc ("ocfs2: fix data corruption by fallocate") will zero the EOF blocks when extend the file size, but it isn't. The problem happened on those EOF pages, before writeback, those pages had DIRTY flag set and all buffer_head in them also had DIRTY flag set, when writeback run by write_cache_pages(), DIRTY flag on the page was cleared, but DIRTY flag on the buffer_head not.

When next write happened to those EOF pages, since buffer_head already had DIRTY flag set, it would not mark page DIRTY again. That made writeback ignore them forever. That will cause data corruption. Even directio write can't work because it will fail when trying to drop pages caches before direct io, as it found the buffer_head for those pages still had DIRTY flag set, then it will fall back to buffer io mode.

To make a summary of the issue, as writeback ingores EOF pages, once any EOF page is generated, any write to it will only go to the page cache, it will never be flushed to disk even file size extends and that page is not EOF page any more. The fix is to avoid zero EOF blocks with buffer write.

The following code snippet from qemu-img could trigger the corruption.

656 open("6b3711ae-3306-4bdd-823c-cf1c0060a095.conv.2", O_RDWR|O_DIRECT|O_CLOEXEC) = 11 ... 660 fallocate(11, FALLOC_FL_KEEP_SIZE|FALLOC_FL_PUNCH_HOLE, 2275868672, 327680 <unfinished ...> 660 fallocate(11, 0, 2275868672, 327680) = 0 658 pwrite64(11, "

Link: https://lkml.kernel.org/r/20210722054923.24389-2-junxiao.bi@oracle.com Signed-off-by: Junxiao Bi junxiao.bi@oracle.com Reviewed-by: Joseph Qi joseph.qi@linux.alibaba.com Cc: Mark Fasheh mark@fasheh.com Cc: Joel Becker jlbec@evilplan.org Cc: Changwei Ge gechangwei@live.cn Cc: Gang He ghe@suse.com Cc: Jun Piao piaojun@huawei.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 | 99 +++++++++++++++++++++++++++++++++----------------------- 1 file changed, 60 insertions(+), 39 deletions(-)

--- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1511,6 +1511,45 @@ static void ocfs2_truncate_cluster_pages } }

+/* + * zero out partial blocks of one cluster. + * + * start: file offset where zero starts, will be made upper block aligned. + * len: it will be trimmed to the end of current cluster if "start + len" + * is bigger than it. + */ +static int ocfs2_zeroout_partial_cluster(struct inode *inode, + u64 start, u64 len) +{ + int ret; + u64 start_block, end_block, nr_blocks; + u64 p_block, offset; + u32 cluster, p_cluster, nr_clusters; + struct super_block *sb = inode->i_sb; + u64 end = ocfs2_align_bytes_to_clusters(sb, start); + + if (start + len < end) + end = start + len; + + start_block = ocfs2_blocks_for_bytes(sb, start); + end_block = ocfs2_blocks_for_bytes(sb, end); + nr_blocks = end_block - start_block; + if (!nr_blocks) + return 0; + + cluster = ocfs2_bytes_to_clusters(sb, start); + ret = ocfs2_get_clusters(inode, cluster, &p_cluster, + &nr_clusters, NULL); + if (ret) + return ret; + if (!p_cluster) + return 0; + + offset = start_block - ocfs2_clusters_to_blocks(sb, cluster); + p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset; + return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS); +} + static int ocfs2_zero_partial_clusters(struct inode *inode, u64 start, u64 len) { @@ -1520,6 +1559,7 @@ static int ocfs2_zero_partial_clusters(s struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); unsigned int csize = osb->s_clustersize; handle_t *handle; + loff_t isize = i_size_read(inode);

/* * The "start" and "end" values are NOT necessarily part of @@ -1540,6 +1580,26 @@ static int ocfs2_zero_partial_clusters(s if ((start & (csize - 1)) == 0 && (end & (csize - 1)) == 0) goto out;

+ /* No page cache for EOF blocks, issue zero out to disk. */ + if (end > isize) { + /* + * zeroout eof blocks in last cluster starting from + * "isize" even "start" > "isize" because it is + * complicated to zeroout just at "start" as "start" + * may be not aligned with block size, buffer write + * would be required to do that, but out of eof buffer + * write is not supported. + */ + ret = ocfs2_zeroout_partial_cluster(inode, isize, + end - isize); + if (ret) { + mlog_errno(ret); + goto out; + } + if (start >= isize) + goto out; + end = isize; + } handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); @@ -1839,45 +1899,6 @@ out: }

/* - * zero out partial blocks of one cluster. - * - * start: file offset where zero starts, will be made upper block aligned. - * len: it will be trimmed to the end of current cluster if "start + len" - * is bigger than it. - */ -static int ocfs2_zeroout_partial_cluster(struct inode *inode, - u64 start, u64 len) -{ - int ret; - u64 start_block, end_block, nr_blocks; - u64 p_block, offset; - u32 cluster, p_cluster, nr_clusters; - struct super_block *sb = inode->i_sb; - u64 end = ocfs2_align_bytes_to_clusters(sb, start); - - if (start + len < end) - end = start + len; - - start_block = ocfs2_blocks_for_bytes(sb, start); - end_block = ocfs2_blocks_for_bytes(sb, end); - nr_blocks = end_block - start_block; - if (!nr_blocks) - return 0; - - cluster = ocfs2_bytes_to_clusters(sb, start); - ret = ocfs2_get_clusters(inode, cluster, &p_cluster, - &nr_clusters, NULL); - if (ret) - return ret; - if (!p_cluster) - return 0; - - offset = start_block - ocfs2_clusters_to_blocks(sb, cluster); - p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset; - return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS); -} - -/* * Parts of this function taken from xfs_change_file_space() */ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,

From: Pavel Skripkin paskripkin@gmail.com

commit 9969e3c5f40c166e3396acc36c34f9de502929f6 upstream.

In ems_usb_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 ems_usb_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: 702171adeed3 ("ems_usb: Added support for EMS CPC-USB/ARM7 CAN/USB interface") Link: https://lore.kernel.org/r/59aa9fbc9a8cbf9af2bbd2f61a659c480b415800.162740447... 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/ems_usb.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-)

--- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -267,6 +267,8 @@ struct ems_usb { unsigned int free_slots; /* remember number of available slots */

struct ems_cpc_msg active_params; /* active controller parameters */ + void *rxbuf[MAX_RX_URBS]; + dma_addr_t rxbuf_dma[MAX_RX_URBS]; };

static void ems_usb_read_interrupt_callback(struct urb *urb) @@ -598,6 +600,7 @@ static int ems_usb_start(struct ems_usb 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); @@ -607,7 +610,7 @@ static int ems_usb_start(struct ems_usb }

buf = usb_alloc_coherent(dev->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); @@ -615,6 +618,8 @@ static int ems_usb_start(struct ems_usb break; }

+ urb->transfer_dma = buf_dma; + usb_fill_bulk_urb(urb, dev->udev, usb_rcvbulkpipe(dev->udev, 2), buf, RX_BUFFER_SIZE, ems_usb_read_bulk_callback, dev); @@ -630,6 +635,9 @@ static int ems_usb_start(struct ems_usb break; }

+ dev->rxbuf[i] = buf; + dev->rxbuf_dma[i] = buf_dma; + /* Drop reference, USB core will take care of freeing it */ usb_free_urb(urb); } @@ -695,6 +703,10 @@ static void unlink_all_urbs(struct ems_u

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]); + usb_kill_anchored_urbs(&dev->tx_submitted); atomic_set(&dev->active_tx_urbs, 0);

From: Paul Jakma paul@jakma.org

commit 15bbf8bb4d4ab87108ecf5f4155ec8ffa3c141d6 upstream.

Commit 7930742d6, reverting 26fd962, missed out on reverting an incorrect change to a return value. The niu_pci_vpd_scan_props(..) == 1 case appears to be a normal path - treating it as an error and return -EINVAL was breaking VPD_SCAN and causing the driver to fail to load.

Fix, so my Neptune card works again.

Cc: Kangjie Lu kjlu@umn.edu Cc: Shannon Nelson shannon.lee.nelson@gmail.com Cc: David S. Miller davem@davemloft.net Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: stable stable@vger.kernel.org Fixes: 7930742d ('Revert "niu: fix missing checks of niu_pci_eeprom_read"') Signed-off-by: Paul Jakma paul@jakma.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/sun/niu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -8213,8 +8213,9 @@ static int niu_pci_vpd_fetch(struct niu err = niu_pci_vpd_scan_props(np, here, end); if (err < 0) return err; + /* ret == 1 is not an error */ if (err == 1) - return -EINVAL; + return 0; } return 0; }

From: Jan Kiszka jan.kiszka@siemens.com

[ Upstream commit f7b21a0e41171d22296b897dac6e4c41d2a3643c ]

Fix:

../arch/x86/include/asm/proto.h:14:30: warning: ‘struct task_struct’ declared \ inside parameter list will not be visible outside of this definition or declaration long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2); ^~~~~~~~~~~

.../arch/x86/include/asm/proto.h:40:34: warning: ‘struct task_struct’ declared \ inside parameter list will not be visible outside of this definition or declaration long do_arch_prctl_common(struct task_struct *task, int option, ^~~~~~~~~~~

if linux/sched.h hasn't be included previously. This fixes a build error when this header is used outside of the kernel tree.

[ bp: Massage commit message. ]

Signed-off-by: Jan Kiszka jan.kiszka@siemens.com Signed-off-by: Borislav Petkov bp@suse.de Link: https://lkml.kernel.org/r/b76b4be3-cf66-f6b2-9a6c-3e7ef54f9845@web.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/include/asm/proto.h | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 9b9b30b19441..36a7a3f11839 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -3,6 +3,8 @@

#include <asm/ldt.h>

+struct task_struct; + /* misc architecture specific prototypes */

void syscall_init(void);

From: Florian Westphal fw@strlen.de

[ Upstream commit 30a56a2b881821625f79837d4d968c679852444e ]

In case the entry is evicted via garbage collection there is delay between the timeout value and the eviction event.

This adjusts the stop value based on how much time has passed.

Fixes: b87a2f9199ea82 ("netfilter: conntrack: add gc worker to remove timed-out entries") Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_conntrack_core.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index ddd90a3820d3..d03f06717844 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -491,8 +491,13 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) return false;

tstamp = nf_conn_tstamp_find(ct); - if (tstamp && tstamp->stop == 0) + if (tstamp) { + s32 timeout = ct->timeout - nfct_time_stamp; + tstamp->stop = ktime_get_real_ns(); + if (timeout < 0) + tstamp->stop -= jiffies_to_nsecs(-timeout); + }

if (nf_conntrack_event_report(IPCT_DESTROY, ct, portid, report) < 0) {

From: Hoang Le hoang.h.le@dektech.com.au

[ Upstream commit d237a7f11719ff9320721be5818352e48071aab6 ]

The release_sock() is blocking function, it would change the state after sleeping. In order to evaluate the stated condition outside the socket lock context, switch to use wait_woken() instead.

Fixes: 6398e23cdb1d8 ("tipc: standardize accept routine") Acked-by: Jon Maloy jmaloy@redhat.com Signed-off-by: Hoang Le hoang.h.le@dektech.com.au Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/tipc/socket.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c index c1b9074f3325..607785077445 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1985,7 +1985,7 @@ static int tipc_listen(struct socket *sock, int len) static int tipc_wait_for_accept(struct socket *sock, long timeo) { struct sock *sk = sock->sk; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); int err;

/* True wake-one mechanism for incoming connections: only @@ -1994,12 +1994,12 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) * anymore, the common case will execute the loop only once. */ for (;;) { - prepare_to_wait_exclusive(sk_sleep(sk), &wait, - TASK_INTERRUPTIBLE); if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { + add_wait_queue(sk_sleep(sk), &wait); release_sock(sk); - timeo = schedule_timeout(timeo); + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); + remove_wait_queue(sk_sleep(sk), &wait); } err = 0; if (!skb_queue_empty(&sk->sk_receive_queue)) @@ -2014,7 +2014,6 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) if (signal_pending(current)) break; } - finish_wait(sk_sleep(sk), &wait); return err; }

From: Pavel Skripkin paskripkin@gmail.com

[ Upstream commit c7c9d2102c9c098916ab9e0ab248006107d00d6c ]

Syzbot reported skb_over_panic() in llc_pdu_init_as_xid_cmd(). The problem was in wrong LCC header manipulations.

Syzbot's reproducer tries to send XID packet. llc_ui_sendmsg() is doing following steps:

1. skb allocation with size = len + header size len is passed from userpace and header size is 3 since addr->sllc_xid is set.

2. skb_reserve() for header_len = 3 3. filling all other space with memcpy_from_msg()

Ok, at this moment we have fully loaded skb, only headers needs to be filled.

Then code comes to llc_sap_action_send_xid_c(). This function pushes 3 bytes for LLC PDU header and initializes it. Then comes llc_pdu_init_as_xid_cmd(). It initalizes next 3 bytes *AFTER* LLC PDU header and call skb_push(skb, 3). This looks wrong for 2 reasons:

1. Bytes rigth after LLC header are user data, so this function was overwriting payload.

2. skb_push(skb, 3) call can cause skb_over_panic() since all free space was filled in llc_ui_sendmsg(). (This can happen is user passed 686 len: 686 + 14 (eth header) + 3 (LLC header) = 703. SKB_DATA_ALIGN(703) = 704)

So, in this patch I added 2 new private constansts: LLC_PDU_TYPE_U_XID and LLC_PDU_LEN_U_XID. LLC_PDU_LEN_U_XID is used to correctly reserve header size to handle LLC + XID case. LLC_PDU_TYPE_U_XID is used by llc_pdu_header_init() function to push 6 bytes instead of 3. And finally I removed skb_push() call from llc_pdu_init_as_xid_cmd().

This changes should not affect other parts of LLC, since after all steps we just transmit buffer.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-and-tested-by: syzbot+5e5a981ad7cc54c4b2b4@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin paskripkin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/llc_pdu.h | 31 +++++++++++++++++++++++-------- net/llc/af_llc.c | 10 +++++++++- net/llc/llc_s_ac.c | 2 +- 3 files changed, 33 insertions(+), 10 deletions(-)

diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index c0f0a13ed818..49aa79c7b278 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -15,9 +15,11 @@ #include <linux/if_ether.h>

/* Lengths of frame formats */ -#define LLC_PDU_LEN_I 4 /* header and 2 control bytes */ -#define LLC_PDU_LEN_S 4 -#define LLC_PDU_LEN_U 3 /* header and 1 control byte */ +#define LLC_PDU_LEN_I 4 /* header and 2 control bytes */ +#define LLC_PDU_LEN_S 4 +#define LLC_PDU_LEN_U 3 /* header and 1 control byte */ +/* header and 1 control byte and XID info */ +#define LLC_PDU_LEN_U_XID (LLC_PDU_LEN_U + sizeof(struct llc_xid_info)) /* Known SAP addresses */ #define LLC_GLOBAL_SAP 0xFF #define LLC_NULL_SAP 0x00 /* not network-layer visible */ @@ -50,9 +52,10 @@ #define LLC_PDU_TYPE_U_MASK 0x03 /* 8-bit control field */ #define LLC_PDU_TYPE_MASK 0x03

-#define LLC_PDU_TYPE_I 0 /* first bit */ -#define LLC_PDU_TYPE_S 1 /* first two bits */ -#define LLC_PDU_TYPE_U 3 /* first two bits */ +#define LLC_PDU_TYPE_I 0 /* first bit */ +#define LLC_PDU_TYPE_S 1 /* first two bits */ +#define LLC_PDU_TYPE_U 3 /* first two bits */ +#define LLC_PDU_TYPE_U_XID 4 /* private type for detecting XID commands */

#define LLC_PDU_TYPE_IS_I(pdu) \ ((!(pdu->ctrl_1 & LLC_PDU_TYPE_I_MASK)) ? 1 : 0) @@ -230,9 +233,18 @@ static inline struct llc_pdu_un *llc_pdu_un_hdr(struct sk_buff *skb) static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, u8 ssap, u8 dsap, u8 cr) { - const int hlen = type == LLC_PDU_TYPE_U ? 3 : 4; + int hlen = 4; /* default value for I and S types */ struct llc_pdu_un *pdu;

+ switch (type) { + case LLC_PDU_TYPE_U: + hlen = 3; + break; + case LLC_PDU_TYPE_U_XID: + hlen = 6; + break; + } + skb_push(skb, hlen); skb_reset_network_header(skb); pdu = llc_pdu_un_hdr(skb); @@ -374,7 +386,10 @@ static inline void llc_pdu_init_as_xid_cmd(struct sk_buff *skb, xid_info->fmt_id = LLC_XID_FMT_ID; /* 0x81 */ xid_info->type = svcs_supported; xid_info->rw = rx_window << 1; /* size of receive window */ - skb_put(skb, sizeof(struct llc_xid_info)); + + /* no need to push/put since llc_pdu_header_init() has already + * pushed 3 + 3 bytes + */ }

/** diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 1a77d0687d74..a8866455e8b2 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -96,8 +96,16 @@ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr) { u8 rc = LLC_PDU_LEN_U;

- if (addr->sllc_test || addr->sllc_xid) + if (addr->sllc_test) rc = LLC_PDU_LEN_U; + else if (addr->sllc_xid) + /* We need to expand header to sizeof(struct llc_xid_info) + * since llc_pdu_init_as_xid_cmd() sets 4,5,6 bytes of LLC header + * as XID PDU. In llc_ui_sendmsg() we reserved header size and then + * filled all other space with user data. If we won't reserve this + * bytes, llc_pdu_init_as_xid_cmd() will overwrite user data + */ + rc = LLC_PDU_LEN_U_XID; else if (sk->sk_type == SOCK_STREAM) rc = LLC_PDU_LEN_I; return rc; diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c index 7ae4cc684d3a..9fa3342c7a82 100644 --- a/net/llc/llc_s_ac.c +++ b/net/llc/llc_s_ac.c @@ -79,7 +79,7 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb) struct llc_sap_state_ev *ev = llc_sap_ev(skb); int rc;

- llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap, + llc_pdu_header_init(skb, LLC_PDU_TYPE_U_XID, ev->saddr.lsap, ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);

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 1f62b9423851..31dfb695eded 100644 --- a/drivers/net/ethernet/dec/tulip/winbond-840.c +++ b/drivers/net/ethernet/dec/tulip/winbond-840.c @@ -368,7 +368,7 @@ 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); @@ -390,7 +390,7 @@ 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)); @@ -469,8 +469,6 @@ 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); }