3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andreas Larsson andreas@gaisler.com

commit 07b5ab3f71d318e52c18cc3b73c1d44c908aacfa upstream.

Signed-off-by: Andreas Larsson andreas@gaisler.com Signed-off-by: David S. Miller davem@davemloft.net Cc: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/sparc/kernel/signal_32.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -89,7 +89,7 @@ asmlinkage void do_sigreturn(struct pt_r sf = (struct signal_frame __user *) regs->u_regs[UREG_FP];

/* 1. Make sure we are not getting garbage from the user */ - if (!invalid_frame_pointer(sf, sizeof(*sf))) + if (invalid_frame_pointer(sf, sizeof(*sf))) goto segv_and_exit;

if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP])) @@ -150,7 +150,7 @@ asmlinkage void do_rt_sigreturn(struct p

synchronize_user_stack(); sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP]; - if (!invalid_frame_pointer(sf, sizeof(*sf))) + if (invalid_frame_pointer(sf, sizeof(*sf))) goto segv;

if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ross Lagerwall ross.lagerwall@citrix.com

commit b9a74cde94957d82003fb9f7ab4777938ca851cd upstream.

If maxBuf is small but non-zero, it could result in a zero sized lock element array which we would then try and access OOB.

Signed-off-by: Ross Lagerwall ross.lagerwall@citrix.com Signed-off-by: Steve French stfrench@microsoft.com CC: Stable stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/cifs/file.c | 8 ++++---- fs/cifs/smb2file.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-)

--- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1067,10 +1067,10 @@ cifs_push_mandatory_locks(struct cifsFil

/* * Accessing maxBuf is racy with cifs_reconnect - need to store value - * and check it for zero before using. + * and check it before using. */ max_buf = tcon->ses->server->maxBuf; - if (!max_buf) { + if (max_buf < (sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE))) { free_xid(xid); return -EINVAL; } @@ -1404,10 +1404,10 @@ cifs_unlock_range(struct cifsFileInfo *c

/* * Accessing maxBuf is racy with cifs_reconnect - need to store value - * and check it for zero before using. + * and check it before using. */ max_buf = tcon->ses->server->maxBuf; - if (!max_buf) + if (max_buf < (sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE))) return -EINVAL;

max_num = (max_buf - sizeof(struct smb_hdr)) / --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -104,10 +104,10 @@ smb2_unlock_range(struct cifsFileInfo *c

/* * Accessing maxBuf is racy with cifs_reconnect - need to store value - * and check it for zero before using. + * and check it before using. */ max_buf = tcon->ses->server->maxBuf; - if (!max_buf) + if (max_buf < sizeof(struct smb2_lock_element)) return -EINVAL;

max_num = max_buf / sizeof(struct smb2_lock_element);

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Icenowy Zheng icenowy@aosc.io

commit c5603d2fdb424849360fe7e3f8c1befc97571b8c upstream.

Currently the code will set US_FL_SANE_SENSE flag unconditionally if device claims SPC3+, however we should allow US_FL_BAD_SENSE flag to prevent this behavior, because SMI SM3350 UFS-USB bridge controller, which claims SPC4, will show strange behavior with 96-byte sense (put the chip into a wrong state that cannot read/write anything).

Check the presence of US_FL_BAD_SENSE when assuming US_FL_SANE_SENSE on SPC4+ devices.

Signed-off-by: Icenowy Zheng icenowy@aosc.io Cc: stable stable@vger.kernel.org Acked-by: Alan Stern stern@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/storage/scsiglue.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

--- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -223,8 +223,12 @@ static int slave_configure(struct scsi_d if (!(us->fflags & US_FL_NEEDS_CAP16)) sdev->try_rc_10_first = 1;

- /* assume SPC3 or latter devices support sense size > 18 */ - if (sdev->scsi_level > SCSI_SPC_2) + /* + * assume SPC3 or latter devices support sense size > 18 + * unless US_FL_BAD_SENSE quirk is specified. + */ + if (sdev->scsi_level > SCSI_SPC_2 && + !(us->fflags & US_FL_BAD_SENSE)) us->fflags |= US_FL_SANE_SENSE;

/* USB-IDE bridges tend to report SK = 0x04 (Non-recoverable

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christoph Lameter cl@linux.com

commit 09c2e76ed734a1d36470d257a778aaba28e86531 upstream.

Callers of __alloc_alien() check for NULL. We must do the same check in __alloc_alien_cache to avoid NULL pointer dereferences on allocation failures.

Link: http://lkml.kernel.org/r/010001680f42f192-82b4e12e-1565-4ee0-ae1f-1e98974906... Fixes: 49dfc304ba241 ("slab: use the lock on alien_cache, instead of the lock on array_cache") Fixes: c8522a3a5832b ("Slab: introduce alloc_alien") Signed-off-by: Christoph Lameter cl@linux.com Reported-by: syzbot+d6ed4ec679652b4fd4e4@syzkaller.appspotmail.com Reviewed-by: Andrew Morton akpm@linux-foundation.org Cc: Pekka Enberg penberg@kernel.org Cc: David Rientjes rientjes@google.com Cc: Joonsoo Kim iamjoonsoo.kim@lge.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

--- mm/slab.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/mm/slab.c +++ b/mm/slab.c @@ -869,8 +869,10 @@ static struct alien_cache *__alloc_alien struct alien_cache *alc = NULL;

alc = kmalloc_node(memsize, gfp, node); - init_arraycache(&alc->ac, entries, batch); - spin_lock_init(&alc->lock); + if (alc) { + init_arraycache(&alc->ac, entries, batch); + spin_lock_init(&alc->lock); + } return alc; }

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yi Zeng yizeng@asrmicro.com

commit 6ebec961d59bccf65d08b13fc1ad4e6272a89338 upstream.

If adapter->retries is set to a minus value from user space via ioctl, it will make __i2c_transfer and __i2c_smbus_xfer skip the calling to adapter->algo->master_xfer and adapter->algo->smbus_xfer that is registered by the underlying bus drivers, and return value 0 to all the callers. The bus driver will never be accessed anymore by all users, besides, the users may still get successful return value without any error or information log print out.

If adapter->timeout is set to minus value from user space via ioctl, it will make the retrying loop in __i2c_transfer and __i2c_smbus_xfer always break after the the first try, due to the time_after always returns true.

Signed-off-by: Yi Zeng yizeng@asrmicro.com [wsa: minor grammar updates to commit message] Signed-off-by: Wolfram Sang wsa@the-dreams.de Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/i2c/i2c-dev.c | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -462,9 +462,15 @@ static long i2cdev_ioctl(struct file *fi return i2cdev_ioctl_smbus(client, arg);

case I2C_RETRIES: + if (arg > INT_MAX) + return -EINVAL; + client->adapter->retries = arg; break; case I2C_TIMEOUT: + if (arg > INT_MAX) + return -EINVAL; + /* For historical reasons, user-space sets the timeout * value in units of 10 ms. */

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vasily Averin vvs@virtuozzo.com

commit d4b09acf924b84bae77cad090a9d108e70b43643 upstream.

if node have NFSv41+ mounts inside several net namespaces it can lead to use-after-free in svc_process_common()

svc_process_common() /* Setup reply header */ rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp); <<< HERE

svc_process_common() can use incorrect rqstp->rq_xprt, its caller function bc_svc_process() takes it from serv->sv_bc_xprt. The problem is that serv is global structure but sv_bc_xprt is assigned per-netnamespace.

According to Trond, the whole "let's set up rqstp->rq_xprt for the back channel" is nothing but a giant hack in order to work around the fact that svc_process_common() uses it to find the xpt_ops, and perform a couple of (meaningless for the back channel) tests of xpt_flags.

All we really need in svc_process_common() is to be able to run rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr()

Bruce J Fields points that this xpo_prep_reply_hdr() call is an awfully roundabout way just to do "svc_putnl(resv, 0);" in the tcp case.

This patch does not initialiuze rqstp->rq_xprt in bc_svc_process(), now it calls svc_process_common() with rqstp->rq_xprt = NULL.

To adjust reply header svc_process_common() just check rqstp->rq_prot and calls svc_tcp_prep_reply_hdr() for tcp case.

To handle rqstp->rq_xprt = NULL case in functions called from svc_process_common() patch intruduces net namespace pointer svc_rqst->rq_bc_net and adjust SVC_NET() definition. Some other function was also adopted to properly handle described case.

Signed-off-by: Vasily Averin vvs@virtuozzo.com Cc: stable@vger.kernel.org Fixes: 23c20ecd4475 ("NFS: callback up - users counting cleanup") Signed-off-by: J. Bruce Fields bfields@redhat.com v2: - added lost extern svc_tcp_prep_reply_hdr() - context changes in svc_process_common() - dropped trace_svc_process() changes Signed-off-by: Vasily Averin vvs@virtuozzo.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/sunrpc/svc.h | 5 ++++- net/sunrpc/svc.c | 10 +++++++--- net/sunrpc/svc_xprt.c | 5 +++-- net/sunrpc/svcsock.c | 2 +- 4 files changed, 15 insertions(+), 7 deletions(-)

--- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -281,9 +281,12 @@ struct svc_rqst { * to prevent encrypting page * cache pages */ struct task_struct *rq_task; /* service thread */ + struct net *rq_bc_net; /* pointer to backchannel's + * net namespace + */ };

-#define SVC_NET(svc_rqst) (svc_rqst->rq_xprt->xpt_net) +#define SVC_NET(rqst) (rqst->rq_xprt ? rqst->rq_xprt->xpt_net : rqst->rq_bc_net)

/* * Rigorous type checking on sockaddr type conversions --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1061,6 +1061,8 @@ void svc_printk(struct svc_rqst *rqstp, static __printf(2,3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) {} #endif

+extern void svc_tcp_prep_reply_hdr(struct svc_rqst *); + /* * Common routine for processing the RPC request. */ @@ -1090,7 +1092,8 @@ svc_process_common(struct svc_rqst *rqst rqstp->rq_dropme = false;

/* Setup reply header */ - rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp); + if (rqstp->rq_prot == IPPROTO_TCP) + svc_tcp_prep_reply_hdr(rqstp);

svc_putu32(resv, rqstp->rq_xid);

@@ -1137,7 +1140,8 @@ svc_process_common(struct svc_rqst *rqst case SVC_DENIED: goto err_bad_auth; case SVC_CLOSE: - if (test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags)) + if (rqstp->rq_xprt && + test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags)) svc_close_xprt(rqstp->rq_xprt); case SVC_DROP: goto dropit; @@ -1347,10 +1351,10 @@ bc_svc_process(struct svc_serv *serv, st struct kvec *resv = &rqstp->rq_res.head[0];

/* Build the svc_rqst used by the common processing routine */ - rqstp->rq_xprt = serv->sv_bc_xprt; rqstp->rq_xid = req->rq_xid; rqstp->rq_prot = req->rq_xprt->prot; rqstp->rq_server = serv; + rqstp->rq_bc_net = req->rq_xprt->xprt_net;

rqstp->rq_addrlen = sizeof(req->rq_xprt->addr); memcpy(&rqstp->rq_addr, &req->rq_xprt->addr, rqstp->rq_addrlen); --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -438,10 +438,11 @@ static struct svc_xprt *svc_xprt_dequeue */ void svc_reserve(struct svc_rqst *rqstp, int space) { + struct svc_xprt *xprt = rqstp->rq_xprt; + space += rqstp->rq_res.head[0].iov_len;

- if (space < rqstp->rq_reserved) { - struct svc_xprt *xprt = rqstp->rq_xprt; + if (xprt && space < rqstp->rq_reserved) { atomic_sub((rqstp->rq_reserved - space), &xprt->xpt_reserved); rqstp->rq_reserved = space;

--- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1212,7 +1212,7 @@ static int svc_tcp_sendto(struct svc_rqs /* * Setup response header. TCP has a 4B record length field. */ -static void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp) +void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp) { struct kvec *resv = &rqstp->rq_res.head[0];

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Oliver Hartkopp socketcan@hartkopp.net

commit 0aaa81377c5a01f686bcdb8c7a6929a7bf330c68 upstream.

Muyu Yu provided a POC where user root with CAP_NET_ADMIN can create a CAN frame modification rule that makes the data length code a higher value than the available CAN frame data size. In combination with a configured checksum calculation where the result is stored relatively to the end of the data (e.g. cgw_csum_xor_rel) the tail of the skb (e.g. frag_list pointer in skb_shared_info) can be rewritten which finally can cause a system crash.

Michael Kubecek suggested to drop frames that have a DLC exceeding the available space after the modification process and provided a patch that can handle CAN FD frames too. Within this patch we also limit the length for the checksum calculations to the maximum of Classic CAN data length (8).

CAN frames that are dropped by these additional checks are counted with the CGW_DELETED counter which indicates misconfigurations in can-gw rules.

This fixes CVE-2019-3701.

Reported-by: Muyu Yu ieatmuttonchuan@gmail.com Reported-by: Marcus Meissner meissner@suse.de Suggested-by: Michal Kubecek mkubecek@suse.cz Tested-by: Muyu Yu ieatmuttonchuan@gmail.com Tested-by: Oliver Hartkopp socketcan@hartkopp.net Signed-off-by: Oliver Hartkopp socketcan@hartkopp.net Cc: linux-stable stable@vger.kernel.org # >= v3.2 Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/can/gw.c | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-)

--- a/net/can/gw.c +++ b/net/can/gw.c @@ -417,13 +417,29 @@ static void can_can_gw_rcv(struct sk_buf while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx]) (*gwj->mod.modfunc[modidx++])(cf, &gwj->mod);

- /* check for checksum updates when the CAN frame has been modified */ + /* Has the CAN frame been modified? */ if (modidx) { - if (gwj->mod.csumfunc.crc8) + /* get available space for the processed CAN frame type */ + int max_len = nskb->len - offsetof(struct can_frame, data); + + /* dlc may have changed, make sure it fits to the CAN frame */ + if (cf->can_dlc > max_len) + goto out_delete; + + /* check for checksum updates in classic CAN length only */ + if (gwj->mod.csumfunc.crc8) { + if (cf->can_dlc > 8) + goto out_delete; + (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8); + } + + if (gwj->mod.csumfunc.xor) { + if (cf->can_dlc > 8) + goto out_delete;

- if (gwj->mod.csumfunc.xor) (*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor); + } }

/* clear the skb timestamp if not configured the other way */ @@ -435,6 +451,14 @@ static void can_can_gw_rcv(struct sk_buf gwj->dropped_frames++; else gwj->handled_frames++; + + return; + + out_delete: + /* delete frame due to misconfiguration */ + gwj->deleted_frames++; + kfree_skb(nskb); + return; }

static inline int cgw_register_filter(struct cgw_job *gwj)

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

[ Upstream commit 7d033c9f6a7fd3821af75620a0257db87c2b552a ]

This patch makes sure the flow label in the IPv6 header forged in ipv6_local_error() is initialized.

BUG: KMSAN: kernel-infoleak in _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32 CPU: 1 PID: 24675 Comm: syz-executor1 Not tainted 4.20.0-rc7+ #4 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x173/0x1d0 lib/dump_stack.c:113 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613 kmsan_internal_check_memory+0x455/0xb00 mm/kmsan/kmsan.c:675 kmsan_copy_to_user+0xab/0xc0 mm/kmsan/kmsan_hooks.c:601 _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32 copy_to_user include/linux/uaccess.h:177 [inline] move_addr_to_user+0x2e9/0x4f0 net/socket.c:227 ___sys_recvmsg+0x5d7/0x1140 net/socket.c:2284 __sys_recvmsg net/socket.c:2327 [inline] __do_sys_recvmsg net/socket.c:2337 [inline] __se_sys_recvmsg+0x2fa/0x450 net/socket.c:2334 __x64_sys_recvmsg+0x4a/0x70 net/socket.c:2334 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 RIP: 0033:0x457ec9 Code: 6d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f8750c06c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002f RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457ec9 RDX: 0000000000002000 RSI: 0000000020000400 RDI: 0000000000000005 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f8750c076d4 R13: 00000000004c4a60 R14: 00000000004d8140 R15: 00000000ffffffff

Uninit was stored to memory at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:204 [inline] kmsan_save_stack mm/kmsan/kmsan.c:219 [inline] kmsan_internal_chain_origin+0x134/0x230 mm/kmsan/kmsan.c:439 __msan_chain_origin+0x70/0xe0 mm/kmsan/kmsan_instr.c:200 ipv6_recv_error+0x1e3f/0x1eb0 net/ipv6/datagram.c:475 udpv6_recvmsg+0x398/0x2ab0 net/ipv6/udp.c:335 inet_recvmsg+0x4fb/0x600 net/ipv4/af_inet.c:830 sock_recvmsg_nosec net/socket.c:794 [inline] sock_recvmsg+0x1d1/0x230 net/socket.c:801 ___sys_recvmsg+0x4d5/0x1140 net/socket.c:2278 __sys_recvmsg net/socket.c:2327 [inline] __do_sys_recvmsg net/socket.c:2337 [inline] __se_sys_recvmsg+0x2fa/0x450 net/socket.c:2334 __x64_sys_recvmsg+0x4a/0x70 net/socket.c:2334 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:204 [inline] kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:158 kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176 kmsan_slab_alloc+0xe/0x10 mm/kmsan/kmsan_hooks.c:185 slab_post_alloc_hook mm/slab.h:446 [inline] slab_alloc_node mm/slub.c:2759 [inline] __kmalloc_node_track_caller+0xe18/0x1030 mm/slub.c:4383 __kmalloc_reserve net/core/skbuff.c:137 [inline] __alloc_skb+0x309/0xa20 net/core/skbuff.c:205 alloc_skb include/linux/skbuff.h:998 [inline] ipv6_local_error+0x1a7/0x9e0 net/ipv6/datagram.c:334 __ip6_append_data+0x129f/0x4fd0 net/ipv6/ip6_output.c:1311 ip6_make_skb+0x6cc/0xcf0 net/ipv6/ip6_output.c:1775 udpv6_sendmsg+0x3f8e/0x45d0 net/ipv6/udp.c:1384 inet_sendmsg+0x54a/0x720 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] __sys_sendto+0x8c4/0xac0 net/socket.c:1788 __do_sys_sendto net/socket.c:1800 [inline] __se_sys_sendto+0x107/0x130 net/socket.c:1796 __x64_sys_sendto+0x6e/0x90 net/socket.c:1796 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Bytes 4-7 of 28 are uninitialized Memory access of size 28 starts at ffff8881937bfce0 Data copied to user address 0000000020000000

Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/datagram.c | 1 + 1 file changed, 1 insertion(+)

--- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -287,6 +287,7 @@ void ipv6_local_error(struct sock *sk, i skb_reset_network_header(skb); iph = ipv6_hdr(skb); iph->daddr = fl6->daddr; + ip6_flow_hdr(iph, 0, 0);

serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err;

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: JianJhen Chen kchen@synology.com

[ Upstream commit 4c84edc11b76590859b1e45dd676074c59602dc4 ]

When handling DNAT'ed packets on a bridge device, the neighbour cache entry from lookup was used without checking its state. It means that a cache entry in the NUD_STALE state will be used directly instead of entering the NUD_DELAY state to confirm the reachability of the neighbor.

This problem becomes worse after commit 2724680bceee ("neigh: Keep neighbour cache entries if number of them is small enough."), since all neighbour cache entries in the NUD_STALE state will be kept in the neighbour table as long as the number of cache entries does not exceed the value specified in gc_thresh1.

This commit validates the state of a neighbour cache entry before using the entry.

Signed-off-by: JianJhen Chen kchen@synology.com Reviewed-by: JinLin Chen jlchen@synology.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/bridge/br_netfilter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -287,7 +287,7 @@ static int br_nf_pre_routing_finish_brid if (neigh) { int ret;

- if (neigh->hh.hh_len) { + if ((neigh->nud_state & NUD_CONNECTED) && neigh->hh.hh_len) { neigh_hh_bridge(&neigh->hh, skb); skb->dev = nf_bridge->physindev; ret = br_handle_frame_finish(skb);

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Josef Bacik josef@toxicpanda.com

commit 74d5d229b1bf60f93bff244b2dfc0eb21ec32a07 upstream.

If we flip read-only before we initiate writeback on all dirty pages for ordered extents we've created then we'll have ordered extents left over on umount, which results in all sorts of bad things happening. Fix this by making sure we wait on ordered extents if we have to do the aborted transaction cleanup stuff.

generic/475 can produce this warning:

[ 8531.177332] WARNING: CPU: 2 PID: 11997 at fs/btrfs/disk-io.c:3856 btrfs_free_fs_root+0x95/0xa0 [btrfs] [ 8531.183282] CPU: 2 PID: 11997 Comm: umount Tainted: G W 5.0.0-rc1-default+ #394 [ 8531.185164] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),BIOS rel-1.11.2-0-gf9626cc-prebuilt.qemu-project.org 04/01/2014 [ 8531.187851] RIP: 0010:btrfs_free_fs_root+0x95/0xa0 [btrfs] [ 8531.193082] RSP: 0018:ffffb1ab86163d98 EFLAGS: 00010286 [ 8531.194198] RAX: ffff9f3449494d18 RBX: ffff9f34a2695000 RCX:0000000000000000 [ 8531.195629] RDX: 0000000000000002 RSI: 0000000000000001 RDI:0000000000000000 [ 8531.197315] RBP: ffff9f344e930000 R08: 0000000000000001 R09:0000000000000000 [ 8531.199095] R10: 0000000000000000 R11: ffff9f34494d4ff8 R12:ffffb1ab86163dc0 [ 8531.200870] R13: ffff9f344e9300b0 R14: ffffb1ab86163db8 R15:0000000000000000 [ 8531.202707] FS: 00007fc68e949fc0(0000) GS:ffff9f34bd800000(0000)knlGS:0000000000000000 [ 8531.204851] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 8531.205942] CR2: 00007ffde8114dd8 CR3: 000000002dfbd000 CR4:00000000000006e0 [ 8531.207516] Call Trace: [ 8531.208175] btrfs_free_fs_roots+0xdb/0x170 [btrfs] [ 8531.210209] ? wait_for_completion+0x5b/0x190 [ 8531.211303] close_ctree+0x157/0x350 [btrfs] [ 8531.212412] generic_shutdown_super+0x64/0x100 [ 8531.213485] kill_anon_super+0x14/0x30 [ 8531.214430] btrfs_kill_super+0x12/0xa0 [btrfs] [ 8531.215539] deactivate_locked_super+0x29/0x60 [ 8531.216633] cleanup_mnt+0x3b/0x70 [ 8531.217497] task_work_run+0x98/0xc0 [ 8531.218397] exit_to_usermode_loop+0x83/0x90 [ 8531.219324] do_syscall_64+0x15b/0x180 [ 8531.220192] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 8531.221286] RIP: 0033:0x7fc68e5e4d07 [ 8531.225621] RSP: 002b:00007ffde8116608 EFLAGS: 00000246 ORIG_RAX:00000000000000a6 [ 8531.227512] RAX: 0000000000000000 RBX: 00005580c2175970 RCX:00007fc68e5e4d07 [ 8531.229098] RDX: 0000000000000001 RSI: 0000000000000000 RDI:00005580c2175b80 [ 8531.230730] RBP: 0000000000000000 R08: 00005580c2175ba0 R09:00007ffde8114e80 [ 8531.232269] R10: 0000000000000000 R11: 0000000000000246 R12:00005580c2175b80 [ 8531.233839] R13: 00007fc68eac61c4 R14: 00005580c2175a68 R15:0000000000000000

Leaving a tree in the rb-tree:

3853 void btrfs_free_fs_root(struct btrfs_root *root) 3854 { 3855 iput(root->ino_cache_inode); 3856 WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));

CC: stable@vger.kernel.org Reviewed-by: Nikolay Borisov nborisov@suse.com Signed-off-by: Josef Bacik josef@toxicpanda.com [ add stacktrace ] Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/btrfs/disk-io.c | 8 ++++++++ 1 file changed, 8 insertions(+)

--- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3942,6 +3942,14 @@ static void btrfs_destroy_all_ordered_ex spin_lock(&fs_info->ordered_root_lock); } spin_unlock(&fs_info->ordered_root_lock); + + /* + * We need this here because if we've been flipped read-only we won't + * get sync() from the umount, so we need to make sure any ordered + * extents that haven't had their dirty pages IO start writeout yet + * actually get run and error out properly. + */ + btrfs_wait_ordered_roots(fs_info, -1); }

static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ivan Mironov mironov.ivan@gmail.com

commit 44759979a49bfd2d20d789add7fa81a21eb1a4ab upstream.

Changing of caching mode via /sys/devices/.../scsi_disk/.../cache_type may fail if device responds to MODE SENSE command with DPOFUA flag set, and then checks this flag to be not set on MODE SELECT command.

In this scenario, when trying to change cache_type, write always fails:

# echo "none" >cache_type bash: echo: write error: Invalid argument

And following appears in dmesg:

[13007.865745] sd 1:0:1:0: [sda] Sense Key : Illegal Request [current] [13007.865753] sd 1:0:1:0: [sda] Add. Sense: Invalid field in parameter list

From SBC-4 r15, 6.5.1 "Mode pages overview", description of DEVICE-SPECIFIC

PARAMETER field in the mode parameter header: ... The write protect (WP) bit for mode data sent with a MODE SELECT command shall be ignored by the device server. ... The DPOFUA bit is reserved for mode data sent with a MODE SELECT command. ...

The remaining bits in the DEVICE-SPECIFIC PARAMETER byte are also reserved and shall be set to zero.

[mkp: shuffled commentary to commit description]

Cc: stable@vger.kernel.org Signed-off-by: Ivan Mironov mironov.ivan@gmail.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/scsi/sd.c | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -205,6 +205,12 @@ cache_type_store(struct device *dev, str buffer_data[2] |= wce << 2 | rcd; sp = buffer_data[0] & 0x80 ? 1 : 0;

+ /* + * Ensure WP, DPOFUA, and RESERVED fields are cleared in + * received mode parameter buffer before doing MODE SELECT. + */ + data.device_specific = 0; + if (scsi_mode_select(sdp, 1, sp, 8, buffer_data, len, SD_TIMEOUT, SD_MAX_RETRIES, &data, &sshdr)) { if (scsi_sense_valid(&sshdr))

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: YunQiang Su ysu@wavecomp.com

commit a214720cbf50cd8c3f76bbb9c3f5c283910e9d33 upstream.

Octeon has an boot-time option to disable pcie.

Since MSI depends on PCI-E, we should also disable MSI also with this option is on in order to avoid inadvertently accessing PCIe registers.

Signed-off-by: YunQiang Su ysu@wavecomp.com Signed-off-by: Paul Burton paul.burton@mips.com Cc: pburton@wavecomp.com Cc: linux-mips@vger.kernel.org Cc: aaro.koskinen@iki.fi Cc: stable@vger.kernel.org # v3.3+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/mips/pci/msi-octeon.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/arch/mips/pci/msi-octeon.c +++ b/arch/mips/pci/msi-octeon.c @@ -369,7 +369,9 @@ int __init octeon_msi_initialize(void) int irq; struct irq_chip *msi;

- if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) { + if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_INVALID) { + return 0; + } else if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) { msi_rcv_reg[0] = CVMX_PEXP_NPEI_MSI_RCV0; msi_rcv_reg[1] = CVMX_PEXP_NPEI_MSI_RCV1; msi_rcv_reg[2] = CVMX_PEXP_NPEI_MSI_RCV2;

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans Verkuil hverkuil-cisco@xs4all.nl

commit 701f49bc028edb19ffccd101997dd84f0d71e279 upstream.

kthread_run returns an error pointer, but elsewhere in the code dev->kthread_vid_cap/out is checked against NULL.

If kthread_run returns an error, then set the pointer to NULL.

I chose this method over changing all kthread_vid_cap/out tests elsewhere since this is more robust.

Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Reported-by: syzbot+53d5b2df0d9744411e2e@syzkaller.appspotmail.com Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/media/platform/vivid/vivid-kthread-cap.c | 5 ++++- drivers/media/platform/vivid/vivid-kthread-out.c | 5 ++++- 2 files changed, 8 insertions(+), 2 deletions(-)

--- a/drivers/media/platform/vivid/vivid-kthread-cap.c +++ b/drivers/media/platform/vivid/vivid-kthread-cap.c @@ -829,8 +829,11 @@ int vivid_start_generating_vid_cap(struc "%s-vid-cap", dev->v4l2_dev.name);

if (IS_ERR(dev->kthread_vid_cap)) { + int err = PTR_ERR(dev->kthread_vid_cap); + + dev->kthread_vid_cap = NULL; v4l2_err(&dev->v4l2_dev, "kernel_thread() failed\n"); - return PTR_ERR(dev->kthread_vid_cap); + return err; } *pstreaming = true; vivid_grab_controls(dev, true); --- a/drivers/media/platform/vivid/vivid-kthread-out.c +++ b/drivers/media/platform/vivid/vivid-kthread-out.c @@ -248,8 +248,11 @@ int vivid_start_generating_vid_out(struc "%s-vid-out", dev->v4l2_dev.name);

if (IS_ERR(dev->kthread_vid_out)) { + int err = PTR_ERR(dev->kthread_vid_out); + + dev->kthread_vid_out = NULL; v4l2_err(&dev->v4l2_dev, "kernel_thread() failed\n"); - return PTR_ERR(dev->kthread_vid_out); + return err; } *pstreaming = true; vivid_grab_controls(dev, true);

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans Verkuil hverkuil@xs4all.nl

commit cd26d1c4d1bc947b56ae404998ae2276df7b39b7 upstream.

If a filehandle is dup()ped, then it is possible to close it from one fd and call mmap from the other. This creates a race condition in vb2_mmap where it is using queue data that __vb2_queue_free (called from close()) is in the process of releasing.

By moving up the mutex_lock(mmap_lock) in vb2_mmap this race is avoided since __vb2_queue_free is called with the same mutex locked. So vb2_mmap now reads consistent buffer data.

Signed-off-by: Hans Verkuil hverkuil@xs4all.nl Reported-by: syzbot+be93025dd45dccd8923c@syzkaller.appspotmail.com Signed-off-by: Hans Verkuil hansverk@cisco.com Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/media/v4l2-core/videobuf2-core.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)

--- a/drivers/media/v4l2-core/videobuf2-core.c +++ b/drivers/media/v4l2-core/videobuf2-core.c @@ -2474,9 +2474,13 @@ int vb2_mmap(struct vb2_queue *q, struct return -EINVAL; } } + + mutex_lock(&q->mmap_lock); + if (vb2_fileio_is_active(q)) { dprintk(1, "mmap: file io in progress\n"); - return -EBUSY; + ret = -EBUSY; + goto unlock; }

/* @@ -2484,7 +2488,7 @@ int vb2_mmap(struct vb2_queue *q, struct */ ret = __find_plane_by_offset(q, off, &buffer, &plane); if (ret) - return ret; + goto unlock;

vb = q->bufs[buffer];

@@ -2500,8 +2504,9 @@ int vb2_mmap(struct vb2_queue *q, struct return -EINVAL; }

- mutex_lock(&q->mmap_lock); ret = call_memop(vb, mmap, vb->planes[plane].mem_priv, vma); + +unlock: mutex_unlock(&q->mmap_lock); if (ret) return ret;

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Stephen Smalley sds@tycho.nsa.gov

commit 5b0e7310a2a33c06edc7eb81ffc521af9b2c5610 upstream.

levdatum->level can be NULL if we encounter an error while loading the policy during sens_read prior to initializing it. Make sure sens_destroy handles that case correctly.

Reported-by: syzbot+6664500f0f18f07a5c0e@syzkaller.appspotmail.com Signed-off-by: Stephen Smalley sds@tycho.nsa.gov Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- security/selinux/ss/policydb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -717,7 +717,8 @@ static int sens_destroy(void *key, void kfree(key); if (datum) { levdatum = datum; - ebitmap_destroy(&levdatum->level->cat); + if (levdatum->level) + ebitmap_destroy(&levdatum->level->cat); kfree(levdatum->level); } kfree(datum);

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp

commit 310ca162d779efee8a2dc3731439680f3e9c1e86 upstream.

syzbot is reporting NULL pointer dereference [1] which is caused by race condition between ioctl(loop_fd, LOOP_CLR_FD, 0) versus ioctl(other_loop_fd, LOOP_SET_FD, loop_fd) due to traversing other loop devices at loop_validate_file() without holding corresponding lo->lo_ctl_mutex locks.

Since ioctl() request on loop devices is not frequent operation, we don't need fine grained locking. Let's use global lock in order to allow safe traversal at loop_validate_file().

Note that syzbot is also reporting circular locking dependency between bdev->bd_mutex and lo->lo_ctl_mutex [2] which is caused by calling blkdev_reread_part() with lock held. This patch does not address it.

[1] https://syzkaller.appspot.com/bug?id=f3cfe26e785d85f9ee259f385515291d21bd80a... [2] https://syzkaller.appspot.com/bug?id=bf154052f0eea4bc7712499e4569505907d1588...

Signed-off-by: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp Reported-by: syzbot syzbot+bf89c128e05dd6c62523@syzkaller.appspotmail.com Reviewed-by: Jan Kara jack@suse.cz Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/block/loop.c | 47 ++++++++++++++++++++++++----------------------- drivers/block/loop.h | 1 - 2 files changed, 24 insertions(+), 24 deletions(-)

--- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -81,6 +81,7 @@

static DEFINE_IDR(loop_index_idr); static DEFINE_MUTEX(loop_index_mutex); +static DEFINE_MUTEX(loop_ctl_mutex);

static int max_part; static int part_shift; @@ -1012,7 +1013,7 @@ static int loop_clr_fd(struct loop_devic */ if (lo->lo_refcnt > 1) { lo->lo_flags |= LO_FLAGS_AUTOCLEAR; - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); return 0; }

@@ -1061,12 +1062,12 @@ static int loop_clr_fd(struct loop_devic lo->lo_flags = 0; if (!part_shift) lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); /* - * Need not hold lo_ctl_mutex to fput backing file. - * Calling fput holding lo_ctl_mutex triggers a circular + * Need not hold loop_ctl_mutex to fput backing file. + * Calling fput holding loop_ctl_mutex triggers a circular * lock dependency possibility warning as fput can take - * bd_mutex which is usually taken before lo_ctl_mutex. + * bd_mutex which is usually taken before loop_ctl_mutex. */ fput(filp); return 0; @@ -1300,7 +1301,7 @@ static int lo_ioctl(struct block_device struct loop_device *lo = bdev->bd_disk->private_data; int err;

- mutex_lock_nested(&lo->lo_ctl_mutex, 1); + mutex_lock_nested(&loop_ctl_mutex, 1); switch (cmd) { case LOOP_SET_FD: err = loop_set_fd(lo, mode, bdev, arg); @@ -1309,7 +1310,7 @@ static int lo_ioctl(struct block_device err = loop_change_fd(lo, bdev, arg); break; case LOOP_CLR_FD: - /* loop_clr_fd would have unlocked lo_ctl_mutex on success */ + /* loop_clr_fd would have unlocked loop_ctl_mutex on success */ err = loop_clr_fd(lo); if (!err) goto out_unlocked; @@ -1340,7 +1341,7 @@ static int lo_ioctl(struct block_device default: err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; } - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex);

out_unlocked: return err; @@ -1473,16 +1474,16 @@ static int lo_compat_ioctl(struct block_

switch(cmd) { case LOOP_SET_STATUS: - mutex_lock(&lo->lo_ctl_mutex); + mutex_lock(&loop_ctl_mutex); err = loop_set_status_compat( lo, (const struct compat_loop_info __user *) arg); - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); break; case LOOP_GET_STATUS: - mutex_lock(&lo->lo_ctl_mutex); + mutex_lock(&loop_ctl_mutex); err = loop_get_status_compat( lo, (struct compat_loop_info __user *) arg); - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); break; case LOOP_SET_CAPACITY: case LOOP_CLR_FD: @@ -1513,9 +1514,9 @@ static int lo_open(struct block_device * goto out; }

- mutex_lock(&lo->lo_ctl_mutex); + mutex_lock(&loop_ctl_mutex); lo->lo_refcnt++; - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); out: mutex_unlock(&loop_index_mutex); return err; @@ -1525,7 +1526,7 @@ static void __lo_release(struct loop_dev { int err;

- mutex_lock(&lo->lo_ctl_mutex); + mutex_lock(&loop_ctl_mutex);

if (--lo->lo_refcnt) goto out; @@ -1547,7 +1548,7 @@ static void __lo_release(struct loop_dev }

out: - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); }

static void lo_release(struct gendisk *disk, fmode_t mode) @@ -1593,10 +1594,10 @@ static int unregister_transfer_cb(int id struct loop_device *lo = ptr; struct loop_func_table *xfer = data;

- mutex_lock(&lo->lo_ctl_mutex); + mutex_lock(&loop_ctl_mutex); if (lo->lo_encryption == xfer) loop_release_xfer(lo); - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); return 0; }

@@ -1677,7 +1678,7 @@ static int loop_add(struct loop_device * if (!part_shift) disk->flags |= GENHD_FL_NO_PART_SCAN; disk->flags |= GENHD_FL_EXT_DEVT; - mutex_init(&lo->lo_ctl_mutex); + mutex_init(&loop_ctl_mutex); lo->lo_number = i; lo->lo_thread = NULL; init_waitqueue_head(&lo->lo_event); @@ -1789,19 +1790,19 @@ static long loop_control_ioctl(struct fi ret = loop_lookup(&lo, parm); if (ret < 0) break; - mutex_lock(&lo->lo_ctl_mutex); + mutex_lock(&loop_ctl_mutex); if (lo->lo_state != Lo_unbound) { ret = -EBUSY; - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); break; } if (lo->lo_refcnt > 0) { ret = -EBUSY; - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); break; } lo->lo_disk->private_data = NULL; - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); idr_remove(&loop_index_idr, lo->lo_number); loop_remove(lo); break; --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -55,7 +55,6 @@ struct loop_device { struct bio_list lo_bio_list; unsigned int lo_bio_count; int lo_state; - struct mutex lo_ctl_mutex; struct task_struct *lo_thread; wait_queue_head_t lo_event; /* wait queue for incoming requests */

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mauro Carvalho Chehab mchehab+samsung@kernel.org

commit c06ef2e9acef4cda1feee2ce055b8086e33d251a upstream.

As reported by smatch: drivers/media/common/videobuf2/videobuf2-core.c: drivers/media/common/videobuf2/videobuf2-core.c:2159 vb2_mmap() warn: inconsistent returns 'mutex:&q->mmap_lock'. Locked on: line 2148 Unlocked on: line 2100 line 2108 line 2113 line 2118 line 2156 line 2159

There is one error condition that doesn't unlock a mutex.

Fixes: cd26d1c4d1bc ("media: vb2: vb2_mmap: move lock up") Reviewed-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/media/v4l2-core/videobuf2-core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/media/v4l2-core/videobuf2-core.c +++ b/drivers/media/v4l2-core/videobuf2-core.c @@ -2501,7 +2501,8 @@ int vb2_mmap(struct vb2_queue *q, struct if (length < (vma->vm_end - vma->vm_start)) { dprintk(1, "MMAP invalid, as it would overflow buffer length\n"); - return -EINVAL; + ret = -EINVAL; + goto unlock; }

ret = call_memop(vb, mmap, vb->planes[plane].mem_priv, vma);

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit e4849aff1e169b86c561738daf8ff020e9de1011 ]

The Broadcom SiByte BCM1250, BCM1125, and BCM1125H SOCs have an onchip DRAM controller that supports memory amounts of up to 16GiB, and due to how the address decoder has been wired in the SOC any memory beyond 1GiB is actually mapped starting from 4GiB physical up, that is beyond the 32-bit addressable limit[1]. Consequently if the maximum amount of memory has been installed, then it will span up to 19GiB.

Many of the evaluation boards we support that are based on one of these SOCs have their memory soldered and the amount present fits in the 32-bit address range. The BCM91250A SWARM board however has actual DIMM slots and accepts, depending on the peripherals revision of the SOC, up to 4GiB or 8GiB of memory in commercially available JEDEC modules[2]. I believe this is also the case with the BCM91250C2 LittleSur board. This means that up to either 3GiB or 7GiB of memory requires 64-bit addressing to access.

I believe the BCM91480B BigSur board, which has the BCM1480 SOC instead, accepts at least as much memory, although I have no documentation or actual hardware available to verify that.

Both systems have PCI slots installed for use by any PCI option boards, including ones that only support 32-bit addressing (additionally the 32-bit PCI host bridge of the BCM1250, BCM1125, and BCM1125H SOCs limits addressing to 32-bits), and there is no IOMMU available. Therefore for PCI DMA to work in the presence of memory beyond enable swiotlb for the affected systems.

All the other SOC onchip DMA devices use 40-bit addressing and therefore can address the whole memory, so only enable swiotlb if PCI support and support for DMA beyond 4GiB have been both enabled in the configuration of the kernel.

This shows up as follows:

Broadcom SiByte BCM1250 B2 @ 800 MHz (SB1 rev 2) Board type: SiByte BCM91250A (SWARM) Determined physical RAM map: memory: 000000000fe7fe00 @ 0000000000000000 (usable) memory: 000000001ffffe00 @ 0000000080000000 (usable) memory: 000000000ffffe00 @ 00000000c0000000 (usable) memory: 0000000087fffe00 @ 0000000100000000 (usable) software IO TLB: mapped [mem 0xcbffc000-0xcfffc000] (64MB)

in the bootstrap log and removes failures like these:

defxx 0000:02:00.0: dma_direct_map_page: overflow 0x0000000185bc6080+4608 of device mask ffffffff bus mask 0 fddi0: Receive buffer allocation failed fddi0: Adapter open failed! IP-Config: Failed to open fddi0 defxx 0000:09:08.0: dma_direct_map_page: overflow 0x0000000185bc6080+4608 of device mask ffffffff bus mask 0 fddi1: Receive buffer allocation failed fddi1: Adapter open failed! IP-Config: Failed to open fddi1

when memory beyond 4GiB is handed out to devices that can only do 32-bit addressing.

This updates commit cce335ae47e2 ("[MIPS] 64-bit Sibyte kernels need DMA32.").

References:

[1] "BCM1250/BCM1125/BCM1125H User Manual", Revision 1250_1125-UM100-R, Broadcom Corporation, 21 Oct 2002, Section 3: "System Overview", "Memory Map", pp. 34-38

[2] "BCM91250A User Manual", Revision 91250A-UM100-R, Broadcom Corporation, 18 May 2004, Section 3: "Physical Description", "Supported DRAM", p. 23

Signed-off-by: Maciej W. Rozycki macro@linux-mips.org [paul.burton@mips.com: Remove GPL text from dma.c; SPDX tag covers it] Signed-off-by: Paul Burton paul.burton@mips.com Reviewed-by: Christoph Hellwig hch@lst.de Patchwork: https://patchwork.linux-mips.org/patch/21108/ References: cce335ae47e2 ("[MIPS] 64-bit Sibyte kernels need DMA32.") Cc: Ralf Baechle ralf@linux-mips.org Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/mips/Kconfig | 3 +++ arch/mips/sibyte/common/Makefile | 1 + arch/mips/sibyte/common/dma.c | 14 ++++++++++++++ 3 files changed, 18 insertions(+) create mode 100644 arch/mips/sibyte/common/dma.c

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 9536ef912f59..077ae203e8f9 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -627,6 +627,7 @@ config SIBYTE_SWARM select SYS_SUPPORTS_HIGHMEM select SYS_SUPPORTS_LITTLE_ENDIAN select ZONE_DMA32 if 64BIT + select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI

config SIBYTE_LITTLESUR bool "Sibyte BCM91250C2-LittleSur" @@ -649,6 +650,7 @@ config SIBYTE_SENTOSA select SYS_HAS_CPU_SB1 select SYS_SUPPORTS_BIG_ENDIAN select SYS_SUPPORTS_LITTLE_ENDIAN + select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI

config SIBYTE_BIGSUR bool "Sibyte BCM91480B-BigSur" @@ -662,6 +664,7 @@ config SIBYTE_BIGSUR select SYS_SUPPORTS_HIGHMEM select SYS_SUPPORTS_LITTLE_ENDIAN select ZONE_DMA32 if 64BIT + select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI

config SNI_RM bool "SNI RM200/300/400" diff --git a/arch/mips/sibyte/common/Makefile b/arch/mips/sibyte/common/Makefile index b3d6bf23a662..3ef3fb658136 100644 --- a/arch/mips/sibyte/common/Makefile +++ b/arch/mips/sibyte/common/Makefile @@ -1,4 +1,5 @@ obj-y := cfe.o +obj-$(CONFIG_SWIOTLB) += dma.o obj-$(CONFIG_SIBYTE_BUS_WATCHER) += bus_watcher.o obj-$(CONFIG_SIBYTE_CFE_CONSOLE) += cfe_console.o obj-$(CONFIG_SIBYTE_TBPROF) += sb_tbprof.o diff --git a/arch/mips/sibyte/common/dma.c b/arch/mips/sibyte/common/dma.c new file mode 100644 index 000000000000..eb47a94f3583 --- /dev/null +++ b/arch/mips/sibyte/common/dma.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * DMA support for Broadcom SiByte platforms. + * + * Copyright (c) 2018 Maciej W. Rozycki + */ + +#include <linux/swiotlb.h> +#include <asm/bootinfo.h> + +void __init plat_swiotlb_setup(void) +{ + swiotlb_init(1); +}

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit 30696378f68a9e3dad6bfe55938b112e72af00c2 ]

The ramoops backend currently calls persistent_ram_save_old() even if a buffer is empty. While this appears to work, it is does not seem like the right thing to do and could lead to future bugs so lets avoid that. It also prevents misleading prints in the logs which claim the buffer is valid.

I got something like:

found existing buffer, size 0, start 0

When I was expecting:

no valid data in buffer (sig = ...)

This bails out early (and reports with pr_debug()), since it's an acceptable state.

Signed-off-by: Joel Fernandes (Google) joel@joelfernandes.org Co-developed-by: Kees Cook keescook@chromium.org Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/pstore/ram_core.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 288ce45f613e..5ffbf60f5c88 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -484,6 +484,11 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig, sig ^= PERSISTENT_RAM_SIG;

if (prz->buffer->sig == sig) { + if (buffer_size(prz) == 0) { + pr_debug("found existing empty buffer\n"); + return 0; + } + if (buffer_size(prz) > prz->buffer_size || buffer_start(prz) > buffer_size(prz)) pr_info("found existing invalid buffer, size %zu, start %zu\n",

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit b2e9a4eda11fd2cb1e6714e9ad3f455c402568ff ]

Clang warns:

drivers/media/firewire/firedtv-avc.c:999:45: warning: implicit conversion from 'int' to 'char' changes value from 159 to -97 [-Wconstant-conversion] app_info[0] = (EN50221_TAG_APP_INFO >> 16) & 0xff; ~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~ drivers/media/firewire/firedtv-avc.c:1000:45: warning: implicit conversion from 'int' to 'char' changes value from 128 to -128 [-Wconstant-conversion] app_info[1] = (EN50221_TAG_APP_INFO >> 8) & 0xff; ~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~ drivers/media/firewire/firedtv-avc.c:1040:44: warning: implicit conversion from 'int' to 'char' changes value from 159 to -97 [-Wconstant-conversion] app_info[0] = (EN50221_TAG_CA_INFO >> 16) & 0xff; ~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~ drivers/media/firewire/firedtv-avc.c:1041:44: warning: implicit conversion from 'int' to 'char' changes value from 128 to -128 [-Wconstant-conversion] app_info[1] = (EN50221_TAG_CA_INFO >> 8) & 0xff; ~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~ 4 warnings generated.

Change app_info's type to unsigned char to match the type of the member msg in struct ca_msg, which is the only thing passed into the app_info parameter in this function.

Link: https://github.com/ClangBuiltLinux/linux/issues/105

Signed-off-by: Nathan Chancellor natechancellor@gmail.com Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/firewire/firedtv-avc.c | 6 ++++-- drivers/media/firewire/firedtv.h | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/media/firewire/firedtv-avc.c b/drivers/media/firewire/firedtv-avc.c index 251a556112a9..280b5ffea592 100644 --- a/drivers/media/firewire/firedtv-avc.c +++ b/drivers/media/firewire/firedtv-avc.c @@ -968,7 +968,8 @@ static int get_ca_object_length(struct avc_response_frame *r) return r->operand[7]; }

-int avc_ca_app_info(struct firedtv *fdtv, char *app_info, unsigned int *len) +int avc_ca_app_info(struct firedtv *fdtv, unsigned char *app_info, + unsigned int *len) { struct avc_command_frame *c = (void *)fdtv->avc_data; struct avc_response_frame *r = (void *)fdtv->avc_data; @@ -1009,7 +1010,8 @@ out: return ret; }

-int avc_ca_info(struct firedtv *fdtv, char *app_info, unsigned int *len) +int avc_ca_info(struct firedtv *fdtv, unsigned char *app_info, + unsigned int *len) { struct avc_command_frame *c = (void *)fdtv->avc_data; struct avc_response_frame *r = (void *)fdtv->avc_data; diff --git a/drivers/media/firewire/firedtv.h b/drivers/media/firewire/firedtv.h index c2ba085e0d20..54853159482e 100644 --- a/drivers/media/firewire/firedtv.h +++ b/drivers/media/firewire/firedtv.h @@ -124,8 +124,10 @@ int avc_lnb_control(struct firedtv *fdtv, char voltage, char burst, struct dvb_diseqc_master_cmd *diseqcmd); void avc_remote_ctrl_work(struct work_struct *work); int avc_register_remote_control(struct firedtv *fdtv); -int avc_ca_app_info(struct firedtv *fdtv, char *app_info, unsigned int *len); -int avc_ca_info(struct firedtv *fdtv, char *app_info, unsigned int *len); +int avc_ca_app_info(struct firedtv *fdtv, unsigned char *app_info, + unsigned int *len); +int avc_ca_info(struct firedtv *fdtv, unsigned char *app_info, + unsigned int *len); int avc_ca_reset(struct firedtv *fdtv); int avc_ca_pmt(struct firedtv *fdtv, char *app_info, int length); int avc_ca_get_time_date(struct firedtv *fdtv, int *interval);

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit 0de263577de5d5e052be5f4f93334e63cc8a7f0b ]

spc5r17.pdf specifies:

4.3.1 ASCII data field requirements ASCII data fields shall contain only ASCII printable characters (i.e., code values 20h to 7Eh) and may be terminated with one or more ASCII null (00h) characters. ASCII data fields described as being left-aligned shall have any unused bytes at the end of the field (i.e., highest offset) and the unused bytes shall be filled with ASCII space characters (20h).

LIO currently space-pads the T10 VENDOR IDENTIFICATION and PRODUCT IDENTIFICATION fields in the standard INQUIRY data. However, the PRODUCT REVISION LEVEL field in the standard INQUIRY data as well as the T10 VENDOR IDENTIFICATION field in the INQUIRY Device Identification VPD Page are zero-terminated/zero-padded.

Fix this inconsistency by using space-padding for all of the above fields.

Signed-off-by: David Disseldorp ddiss@suse.de Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Bryant G. Ly bly@catalogicsoftware.com Reviewed-by: Lee Duncan lduncan@suse.com Reviewed-by: Hannes Reinecke hare@suse.com Reviewed-by: Roman Bolshakov r.bolshakov@yadro.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/target/target_core_spc.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index 614005b6b08b..3ab264d4fb1f 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -112,12 +112,17 @@ spc_emulate_inquiry_std(struct se_cmd *cmd, unsigned char *buf)

buf[7] = 0x2; /* CmdQue=1 */

- memcpy(&buf[8], "LIO-ORG ", 8); - memset(&buf[16], 0x20, 16); + /* + * ASCII data fields described as being left-aligned shall have any + * unused bytes at the end of the field (i.e., highest offset) and the + * unused bytes shall be filled with ASCII space characters (20h). + */ + memset(&buf[8], 0x20, 8 + 16 + 4); + memcpy(&buf[8], "LIO-ORG", sizeof("LIO-ORG") - 1); memcpy(&buf[16], dev->t10_wwn.model, - min_t(size_t, strlen(dev->t10_wwn.model), 16)); + strnlen(dev->t10_wwn.model, 16)); memcpy(&buf[32], dev->t10_wwn.revision, - min_t(size_t, strlen(dev->t10_wwn.revision), 4)); + strnlen(dev->t10_wwn.revision, 4)); buf[4] = 31; /* Set additional length to 31 */

return 0; @@ -257,7 +262,9 @@ check_t10_vend_desc: buf[off] = 0x2; /* ASCII */ buf[off+1] = 0x1; /* T10 Vendor ID */ buf[off+2] = 0x0; - memcpy(&buf[off+4], "LIO-ORG", 8); + /* left align Vendor ID and pad with spaces */ + memset(&buf[off+4], 0x20, 8); + memcpy(&buf[off+4], "LIO-ORG", sizeof("LIO-ORG") - 1); /* Extra Byte for NULL Terminator */ id_len++; /* Identifier Length */

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit fbac5977d81cb2b2b7e37b11c459055d9585273c ]

An unterminated string literal followed by new line is passed to the parser (with "multi-line strings not supported" warning shown), then handled properly there.

On the other hand, an unterminated string literal at end of file is never passed to the parser, then results in memory leak.

[Test Code]

----------(Kconfig begin)---------- source "Kconfig.inc"

config A bool "a" -----------(Kconfig end)-----------

--------(Kconfig.inc begin)-------- config B bool "b\No new line at end of file ---------(Kconfig.inc end)---------

[Summary from Valgrind]

Before the fix:

LEAK SUMMARY: definitely lost: 16 bytes in 1 blocks ...

After the fix:

LEAK SUMMARY: definitely lost: 0 bytes in 0 blocks ...

Eliminate the memory leak path by handling this case. Of course, such a Kconfig file is wrong already, so I will add an error message later.

Signed-off-by: Masahiro Yamada yamada.masahiro@socionext.com Signed-off-by: Sasha Levin sashal@kernel.org --- scripts/kconfig/zconf.l | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/scripts/kconfig/zconf.l b/scripts/kconfig/zconf.l index 6c62d93b4ffb..485b19a461f8 100644 --- a/scripts/kconfig/zconf.l +++ b/scripts/kconfig/zconf.l @@ -180,6 +180,8 @@ n [A-Za-z0-9_] } <<EOF>> { BEGIN(INITIAL); + yylval.string = text; + return T_WORD_QUOTE; } }

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit 2f5302533f306d5ee87bd375aef9ca35b91762cb ]

The strncpy() function may leave the destination string buffer unterminated, better use strlcpy() that we have a __weak fallback implementation for systems without it.

In this specific case this would only happen if fgets() was buggy, as its man page states that it should read one less byte than the size of the destination buffer, so that it can put the nul byte at the end of it, so it would never copy 255 non-nul chars, as fgets reads into the orig buffer at most 254 non-nul chars and terminates it. But lets just switch to strlcpy to keep the original intent and silence the gcc 8.2 warning.

This fixes this warning on an Alpine Linux Edge system with gcc 8.2:

In function 'cpu_model', inlined from 'svg_cpu_box' at util/svghelper.c:378:2: util/svghelper.c:337:5: error: 'strncpy' output may be truncated copying 255 bytes from a string of length 255 [-Werror=stringop-truncation] strncpy(cpu_m, &buf[13], 255); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Cc: Adrian Hunter adrian.hunter@intel.com Cc: Jiri Olsa jolsa@kernel.org Cc: Namhyung Kim namhyung@kernel.org Cc: Arjan van de Ven arjan@linux.intel.com Fixes: f48d55ce7871 ("perf: Add a SVG helper library file") Link: https://lkml.kernel.org/n/tip-xzkoo0gyr56gej39ltivuh9g@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/util/svghelper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 283d3e73e2f2..48a841462536 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -333,7 +333,7 @@ static char *cpu_model(void) if (file) { while (fgets(buf, 255, file)) { if (strstr(buf, "model name")) { - strncpy(cpu_m, &buf[13], 255); + strlcpy(cpu_m, &buf[13], 255); break; } }

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit d7e6b8dfc7bcb3f4f3a18313581f67486a725b52 ]

When using kcopyd to run callbacks through dm_kcopyd_do_callback() or submitting copy jobs with a source size of 0, the jobs are pushed directly to the complete_jobs list, which could be under processing by the kcopyd thread. As a result, the kcopyd thread can continue running completed jobs indefinitely, without releasing the CPU, as long as someone keeps submitting new completed jobs through the aforementioned paths. Processing of work items, queued for execution on the same CPU as the currently running kcopyd thread, is thus stalled for excessive amounts of time, hurting performance.

Running the following test, from the device mapper test suite [1],

dmtest run --suite snapshot -n parallel_io_to_many_snaps_N

, with 8 active snapshots, we get, in dmesg, messages like the following:

[68899.948523] BUG: workqueue lockup - pool cpus=0 node=0 flags=0x0 nice=0 stuck for 95s! [68899.949282] Showing busy workqueues and worker pools: [68899.949288] workqueue events: flags=0x0 [68899.949295] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=2/256 [68899.949306] pending: vmstat_shepherd, cache_reap [68899.949331] workqueue mm_percpu_wq: flags=0x8 [68899.949337] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/256 [68899.949345] pending: vmstat_update [68899.949387] workqueue dm_bufio_cache: flags=0x8 [68899.949392] pwq 4: cpus=2 node=0 flags=0x0 nice=0 active=1/256 [68899.949400] pending: work_fn [dm_bufio] [68899.949423] workqueue kcopyd: flags=0x8 [68899.949429] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/256 [68899.949437] pending: do_work [dm_mod] [68899.949452] workqueue kcopyd: flags=0x8 [68899.949458] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=2/256 [68899.949466] in-flight: 13:do_work [dm_mod] [68899.949474] pending: do_work [dm_mod] [68899.949487] workqueue kcopyd: flags=0x8 [68899.949493] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/256 [68899.949501] pending: do_work [dm_mod] [68899.949515] workqueue kcopyd: flags=0x8 [68899.949521] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/256 [68899.949529] pending: do_work [dm_mod] [68899.949541] workqueue kcopyd: flags=0x8 [68899.949547] pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/256 [68899.949555] pending: do_work [dm_mod] [68899.949568] pool 0: cpus=0 node=0 flags=0x0 nice=0 hung=95s workers=4 idle: 27130 27223 1084

Fix this by splitting the complete_jobs list into two parts: A user facing part, named callback_jobs, and one used internally by kcopyd, retaining the name complete_jobs. dm_kcopyd_do_callback() and dispatch_job() now push their jobs to the callback_jobs list, which is spliced to the complete_jobs list once, every time the kcopyd thread wakes up. This prevents kcopyd from hogging the CPU indefinitely and causing workqueue stalls.

Re-running the aforementioned test:

* Workqueue stalls are eliminated * The maximum writing time among all targets is reduced from 09m37.10s to 06m04.85s and the total run time of the test is reduced from 10m43.591s to 7m19.199s

[1] https://github.com/jthornber/device-mapper-test-suite

Signed-off-by: Nikos Tsironis ntsironis@arrikto.com Signed-off-by: Ilias Tsitsimpis iliastsi@arrikto.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/md/dm-kcopyd.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 77833b65e01e..9e626e5df2f6 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -55,15 +55,17 @@ struct dm_kcopyd_client { struct dm_kcopyd_throttle *throttle;

/* - * We maintain three lists of jobs: + * We maintain four lists of jobs: * * i) jobs waiting for pages * ii) jobs that have pages, and are waiting for the io to be issued. - * iii) jobs that have completed. + * iii) jobs that don't need to do any IO and just run a callback + * iv) jobs that have completed. * - * All three of these are protected by job_lock. + * All four of these are protected by job_lock. */ spinlock_t job_lock; + struct list_head callback_jobs; struct list_head complete_jobs; struct list_head io_jobs; struct list_head pages_jobs; @@ -583,6 +585,7 @@ static void do_work(struct work_struct *work) struct dm_kcopyd_client *kc = container_of(work, struct dm_kcopyd_client, kcopyd_work); struct blk_plug plug; + unsigned long flags;

/* * The order that these are called is *very* important. @@ -591,6 +594,10 @@ static void do_work(struct work_struct *work) * list. io jobs call wake when they complete and it all * starts again. */ + spin_lock_irqsave(&kc->job_lock, flags); + list_splice_tail_init(&kc->callback_jobs, &kc->complete_jobs); + spin_unlock_irqrestore(&kc->job_lock, flags); + blk_start_plug(&plug); process_jobs(&kc->complete_jobs, kc, run_complete_job); process_jobs(&kc->pages_jobs, kc, run_pages_job); @@ -608,7 +615,7 @@ static void dispatch_job(struct kcopyd_job *job) struct dm_kcopyd_client *kc = job->kc; atomic_inc(&kc->nr_jobs); if (unlikely(!job->source.count)) - push(&kc->complete_jobs, job); + push(&kc->callback_jobs, job); else if (job->pages == &zero_page_list) push(&kc->io_jobs, job); else @@ -795,7 +802,7 @@ void dm_kcopyd_do_callback(void *j, int read_err, unsigned long write_err) job->read_err = read_err; job->write_err = write_err;

- push(&kc->complete_jobs, job); + push(&kc->callback_jobs, job); wake(kc); } EXPORT_SYMBOL(dm_kcopyd_do_callback); @@ -825,6 +832,7 @@ struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *thro return ERR_PTR(-ENOMEM);

spin_lock_init(&kc->job_lock); + INIT_LIST_HEAD(&kc->callback_jobs); INIT_LIST_HEAD(&kc->complete_jobs); INIT_LIST_HEAD(&kc->io_jobs); INIT_LIST_HEAD(&kc->pages_jobs); @@ -874,6 +882,7 @@ void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc) /* Wait for completion of all jobs submitted by this client. */ wait_event(kc->destroyq, !atomic_read(&kc->nr_jobs));

+ BUG_ON(!list_empty(&kc->callback_jobs)); BUG_ON(!list_empty(&kc->complete_jobs)); BUG_ON(!list_empty(&kc->io_jobs)); BUG_ON(!list_empty(&kc->pages_jobs));

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit 644b2e97405b0b74845e1d3c2b4fe4c34858062b ]

This commit fixes hard-coded model-id for an unit of Apogee Ensemble with a correct value. This unit uses DM1500 ASIC produced ArchWave AG (formerly known as BridgeCo AG).

I note that this model supports three modes in the number of data channels in tx/rx streams; 8 ch pairs, 10 ch pairs, 18 ch pairs. The mode is switched by Vendor-dependent AV/C command, like:

$ cd linux-firewire-utils $ ./firewire-request /dev/fw1 fcp 0x00ff000003dbeb0600000000 (8ch pairs) $ ./firewire-request /dev/fw1 fcp 0x00ff000003dbeb0601000000 (10ch pairs) $ ./firewire-request /dev/fw1 fcp 0x00ff000003dbeb0602000000 (18ch pairs)

When switching between different mode, the unit disappears from IEEE 1394 bus, then appears on the bus with different combination of stream formats. In a mode of 18 ch pairs, available sampling rate is up to 96.0 kHz, else up to 192.0 kHz.

$ ./hinawa-config-rom-printer /dev/fw1 { 'bus-info': { 'adj': False, 'bmc': True, 'chip_ID': 21474898341, 'cmc': True, 'cyc_clk_acc': 100, 'generation': 2, 'imc': True, 'isc': True, 'link_spd': 2, 'max_ROM': 1, 'max_rec': 512, 'name': '1394', 'node_vendor_ID': 987, 'pmc': False}, 'root-directory': [ ['HARDWARE_VERSION', 19], [ 'NODE_CAPABILITIES', { 'addressing': {'64': True, 'fix': True, 'prv': False}, 'misc': {'int': False, 'ms': False, 'spt': True}, 'state': { 'atn': False, 'ded': False, 'drq': True, 'elo': False, 'init': False, 'lst': True, 'off': False}, 'testing': {'bas': False, 'ext': False}}], ['VENDOR', 987], ['DESCRIPTOR', 'Apogee Electronics'], ['MODEL', 126702], ['DESCRIPTOR', 'Ensemble'], ['VERSION', 5297], [ 'UNIT', [ ['SPECIFIER_ID', 41005], ['VERSION', 65537], ['MODEL', 126702], ['DESCRIPTOR', 'Ensemble']]], [ 'DEPENDENT_INFO', [ ['SPECIFIER_ID', 2037], ['VERSION', 1], [(58, 'IMMEDIATE'), 16777159], [(59, 'IMMEDIATE'), 1048576], [(60, 'IMMEDIATE'), 16777159], [(61, 'IMMEDIATE'), 6291456]]]]}

Signed-off-by: Takashi Sakamoto o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/firewire/bebob/bebob.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/firewire/bebob/bebob.c b/sound/firewire/bebob/bebob.c index fc19c99654aa..e4312afe2ce5 100644 --- a/sound/firewire/bebob/bebob.c +++ b/sound/firewire/bebob/bebob.c @@ -356,7 +356,7 @@ static const struct ieee1394_device_id bebob_id_table[] = { /* Apogee Electronics, DA/AD/DD-16X (X-FireWire card) */ SND_BEBOB_DEV_ENTRY(VEN_APOGEE, 0x00010048, &spec_normal), /* Apogee Electronics, Ensemble */ - SND_BEBOB_DEV_ENTRY(VEN_APOGEE, 0x00001eee, &spec_normal), + SND_BEBOB_DEV_ENTRY(VEN_APOGEE, 0x01eeee, &spec_normal), /* ESI, Quatafire610 */ SND_BEBOB_DEV_ENTRY(VEN_ESI, 0x00010064, &spec_normal), /* AcousticReality, eARMasterOne */

3.18-stable review patch. If anyone has any objections, please let me know.

------------------

[ Upstream commit 532e1e54c8140188e192348c790317921cb2dc1c ]

mount.ocfs2 ignore the inconsistent error that journal is clean but local alloc is unrecovered. After mount, local alloc not empty, then reserver cluster didn't alloc a new local alloc window, reserveration map is empty(ocfs2_reservation_map.m_bitmap_len = 0), that triggered the following panic.

This issue was reported at

https://oss.oracle.com/pipermail/ocfs2-devel/2015-May/010854.html

and was advised to fixed during mount. But this is a very unusual inconsistent state, usually journal dirty flag should be cleared at the last stage of umount until every other things go right. We may need do further debug to check that. Any way to avoid possible futher corruption, mount should be abort and fsck should be run.

(mount.ocfs2,1765,1):ocfs2_load_local_alloc:353 ERROR: Local alloc hasn't been recovered! found = 6518, set = 6518, taken = 8192, off = 15912372 ocfs2: Mounting device (202,64) on (node 0, slot 3) with ordered data mode. o2dlm: Joining domain 89CEAC63CC4F4D03AC185B44E0EE0F3F ( 0 1 2 3 4 5 6 8 ) 8 nodes ocfs2: Mounting device (202,80) on (node 0, slot 3) with ordered data mode. o2hb: Region 89CEAC63CC4F4D03AC185B44E0EE0F3F (xvdf) is now a quorum device o2net: Accepted connection from node yvwsoa17p (num 7) at 172.22.77.88:7777 o2dlm: Node 7 joins domain 64FE421C8C984E6D96ED12C55FEE2435 ( 0 1 2 3 4 5 6 7 8 ) 9 nodes o2dlm: Node 7 joins domain 89CEAC63CC4F4D03AC185B44E0EE0F3F ( 0 1 2 3 4 5 6 7 8 ) 9 nodes ------------[ cut here ]------------ kernel BUG at fs/ocfs2/reservations.c:507! invalid opcode: 0000 [#1] SMP Modules linked in: ocfs2 rpcsec_gss_krb5 auth_rpcgss nfsv4 nfs fscache lockd grace ocfs2_dlmfs ocfs2_stack_o2cb ocfs2_dlm ocfs2_nodemanager ocfs2_stackglue configfs sunrpc ipt_REJECT nf_reject_ipv4 nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_reject_ipv6 nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables ib_ipoib rdma_ucm ib_ucm ib_uverbs ib_umad rdma_cm ib_cm iw_cm ib_sa ib_mad ib_core ib_addr ipv6 ovmapi ppdev parport_pc parport xen_netfront fb_sys_fops sysimgblt sysfillrect syscopyarea acpi_cpufreq pcspkr i2c_piix4 i2c_core sg ext4 jbd2 mbcache2 sr_mod cdrom xen_blkfront pata_acpi ata_generic ata_piix floppy dm_mirror dm_region_hash dm_log dm_mod CPU: 0 PID: 4349 Comm: startWebLogic.s Not tainted 4.1.12-124.19.2.el6uek.x86_64 #2 Hardware name: Xen HVM domU, BIOS 4.4.4OVM 09/06/2018 task: ffff8803fb04e200 ti: ffff8800ea4d8000 task.ti: ffff8800ea4d8000 RIP: 0010:[<ffffffffa05e96a8>] [<ffffffffa05e96a8>] __ocfs2_resv_find_window+0x498/0x760 [ocfs2] Call Trace: ocfs2_resmap_resv_bits+0x10d/0x400 [ocfs2] ocfs2_claim_local_alloc_bits+0xd0/0x640 [ocfs2] __ocfs2_claim_clusters+0x178/0x360 [ocfs2] ocfs2_claim_clusters+0x1f/0x30 [ocfs2] ocfs2_convert_inline_data_to_extents+0x634/0xa60 [ocfs2] ocfs2_write_begin_nolock+0x1c6/0x1da0 [ocfs2] ocfs2_write_begin+0x13e/0x230 [ocfs2] generic_perform_write+0xbf/0x1c0 __generic_file_write_iter+0x19c/0x1d0 ocfs2_file_write_iter+0x589/0x1360 [ocfs2] __vfs_write+0xb8/0x110 vfs_write+0xa9/0x1b0 SyS_write+0x46/0xb0 system_call_fastpath+0x18/0xd7 Code: ff ff 8b 75 b8 39 75 b0 8b 45 c8 89 45 98 0f 84 e5 fe ff ff 45 8b 74 24 18 41 8b 54 24 1c e9 56 fc ff ff 85 c0 0f 85 48 ff ff ff <0f> 0b 48 8b 05 cf c3 de ff 48 ba 00 00 00 00 00 00 00 10 48 85 RIP __ocfs2_resv_find_window+0x498/0x760 [ocfs2] RSP <ffff8800ea4db668> ---[ end trace 566f07529f2edf3c ]--- Kernel panic - not syncing: Fatal exception Kernel Offset: disabled

Link: http://lkml.kernel.org/r/20181121020023.3034-2-junxiao.bi@oracle.com Signed-off-by: Junxiao Bi junxiao.bi@oracle.com Reviewed-by: Yiwen Jiang jiangyiwen@huawei.com Acked-by: Joseph Qi jiangqi903@gmail.com Cc: Jun Piao piaojun@huawei.com Cc: Mark Fasheh mfasheh@versity.com Cc: Joel Becker jlbec@evilplan.org Cc: Changwei Ge ge.changwei@h3c.com 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/ocfs2/localalloc.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 044013455621..12675bb5304a 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -345,13 +345,18 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb) if (num_used || alloc->id1.bitmap1.i_used || alloc->id1.bitmap1.i_total - || la->la_bm_off) - mlog(ML_ERROR, "Local alloc hasn't been recovered!\n" + || la->la_bm_off) { + mlog(ML_ERROR, "inconsistent detected, clean journal with" + " unrecovered local alloc, please run fsck.ocfs2!\n" "found = %u, set = %u, taken = %u, off = %u\n", num_used, le32_to_cpu(alloc->id1.bitmap1.i_used), le32_to_cpu(alloc->id1.bitmap1.i_total), OCFS2_LOCAL_ALLOC(alloc)->la_bm_off);

+ status = -EINVAL; + goto bail; + } + osb->local_alloc_bh = alloc_bh; osb->local_alloc_state = OCFS2_LA_ENABLED;