From: Parav Pandit parav@nvidia.com

[ Upstream commit b187c9b4178b87954dbc94e78a7094715794714f ]

A netdevice of a devlink port can be moved to different net namespace than its parent devlink instance. This scenario occurs when devlink reload is not used.

When netdevice is undergoing migration to net namespace, its ifindex and name may change.

In such use case, devlink port query may read stale netdev attributes.

Fix it by reading them under rtnl lock.

Fixes: bfcd3a466172 ("Introduce devlink infrastructure") Signed-off-by: Parav Pandit parav@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/devlink.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -562,6 +562,8 @@ static int devlink_nl_port_fill(struct s if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure;

+ /* Hold rtnl lock while accessing port's netdev attributes. */ + rtnl_lock(); spin_lock_bh(&devlink_port->type_lock); if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) goto nla_put_failure_type_locked; @@ -588,6 +590,7 @@ static int devlink_nl_port_fill(struct s goto nla_put_failure_type_locked; } spin_unlock_bh(&devlink_port->type_lock); + rtnl_unlock(); if (devlink_nl_port_attrs_put(msg, devlink_port)) goto nla_put_failure;

@@ -596,6 +599,7 @@ static int devlink_nl_port_fill(struct s

nla_put_failure_type_locked: spin_unlock_bh(&devlink_port->type_lock); + rtnl_unlock(); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE;

From: Julian Wiedmann jwi@linux.ibm.com

[ Upstream commit c5dab0941fcdc9664eb0ec0d4d51433216d91336 ]

Child sockets erroneously inherit their parent's sk_type (ie. SOCK_*), instead of the PF_IUCV protocol that the parent was created with in iucv_sock_create().

We're currently not using sk->sk_protocol ourselves, so this shouldn't have much impact (except eg. getting the output in skb_dump() right).

Fixes: eac3731bd04c ("[S390]: Add AF_IUCV socket support") Signed-off-by: Julian Wiedmann jwi@linux.ibm.com Link: https://lore.kernel.org/r/20201120100657.34407-1-jwi@linux.ibm.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/iucv/af_iucv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1785,7 +1785,7 @@ static int iucv_callback_connreq(struct }

/* Create the new socket */ - nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0); + nsk = iucv_sock_alloc(NULL, sk->sk_protocol, GFP_ATOMIC, 0); if (!nsk) { err = pr_iucv->path_sever(path, user_data); iucv_path_free(path); @@ -1991,7 +1991,7 @@ static int afiucv_hs_callback_syn(struct goto out; }

- nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0); + nsk = iucv_sock_alloc(NULL, sk->sk_protocol, GFP_ATOMIC, 0); bh_lock_sock(sk); if ((sk->sk_state != IUCV_LISTEN) || sk_acceptq_is_full(sk) ||

From: Maxim Mikityanskiy maximmi@mellanox.com

[ Upstream commit 025cc2fb6a4e84e9a0552c0017dcd1c24b7ac7da ]

tls_device_offload_cleanup_rx doesn't clear tls_ctx->netdev after calling tls_dev_del if TLX TX offload is also enabled. Clearing tls_ctx->netdev gets postponed until tls_device_gc_task. It leaves a time frame when tls_device_down may get called and call tls_dev_del for RX one extra time, confusing the driver, which may lead to a crash.

This patch corrects this racy behavior by adding a flag to prevent tls_device_down from calling tls_dev_del the second time.

Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure") Signed-off-by: Maxim Mikityanskiy maximmi@mellanox.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Link: https://lore.kernel.org/r/20201125221810.69870-1-saeedm@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/tls.h | 6 ++++++ net/tls/tls_device.c | 5 ++++- 2 files changed, 10 insertions(+), 1 deletion(-)

--- a/include/net/tls.h +++ b/include/net/tls.h @@ -221,6 +221,12 @@ enum tls_context_flags { * to be atomic. */ TLS_TX_SYNC_SCHED = 1, + /* tls_dev_del was called for the RX side, device state was released, + * but tls_ctx->netdev might still be kept, because TX-side driver + * resources might not be released yet. Used to prevent the second + * tls_dev_del call in tls_device_down if it happens simultaneously. + */ + TLS_RX_DEV_CLOSED = 2, };

struct cipher_context { --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1163,6 +1163,8 @@ void tls_device_offload_cleanup_rx(struc if (tls_ctx->tx_conf != TLS_HW) { dev_put(netdev); tls_ctx->netdev = NULL; + } else { + set_bit(TLS_RX_DEV_CLOSED, &tls_ctx->flags); } out: up_read(&device_offload_lock); @@ -1192,7 +1194,8 @@ static int tls_device_down(struct net_de if (ctx->tx_conf == TLS_HW) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX); - if (ctx->rx_conf == TLS_HW) + if (ctx->rx_conf == TLS_HW && + !test_bit(TLS_RX_DEV_CLOSED, &ctx->flags)) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_RX); WRITE_ONCE(ctx->netdev, NULL);

From: Willem de Bruijn willemb@google.com

[ Upstream commit 985f7337421a811cb354ca93882f943c8335a6f5 ]

When setting sk_err, set it to ee_errno, not ee_origin.

Commit f5f99309fa74 ("sock: do not set sk_err in sock_dequeue_err_skb") disabled updating sk_err on errq dequeue, which is correct for most error types (origins):

- sk->sk_err = err;

Commit 38b257938ac6 ("sock: reset sk_err when the error queue is empty") reenabled the behavior for IMCP origins, which do require it:

+ if (icmp_next) + sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_origin;

But read from ee_errno.

Fixes: 38b257938ac6 ("sock: reset sk_err when the error queue is empty") Reported-by: Ayush Ranjan ayushranjan@google.com Signed-off-by: Willem de Bruijn willemb@google.com Acked-by: Soheil Hassas Yeganeh soheil@google.com Link: https://lore.kernel.org/r/20201126151220.2819322-1-willemdebruijn.kernel@gma... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/skbuff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4452,7 +4452,7 @@ struct sk_buff *sock_dequeue_err_skb(str if (skb && (skb_next = skb_peek(q))) { icmp_next = is_icmp_err_skb(skb_next); if (icmp_next) - sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_origin; + sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_errno; } spin_unlock_irqrestore(&q->lock, flags);

From: Jens Axboe axboe@kernel.dk

[ Upstream commit 5aac0390a63b8718237a61dd0d24a29201d1c94a ]

tun only checks the file O_NONBLOCK flag, but it should also be checking the iocb IOCB_NOWAIT flag. Any fops using ->read/write_iter() should check both, otherwise it breaks users that correctly expect O_NONBLOCK semantics if IOCB_NOWAIT is set.

Signed-off-by: Jens Axboe axboe@kernel.dk Link: https://lore.kernel.org/r/e9451860-96cc-c7c7-47b8-fe42cadd5f4c@kernel.dk Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/tun.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-)

--- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2028,12 +2028,15 @@ static ssize_t tun_chr_write_iter(struct struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t result; + int noblock = 0;

if (!tun) return -EBADFD;

- result = tun_get_user(tun, tfile, NULL, from, - file->f_flags & O_NONBLOCK, false); + if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) + noblock = 1; + + result = tun_get_user(tun, tfile, NULL, from, noblock, false);

tun_put(tun); return result; @@ -2254,10 +2257,15 @@ static ssize_t tun_chr_read_iter(struct struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t len = iov_iter_count(to), ret; + int noblock = 0;

if (!tun) return -EBADFD; - ret = tun_do_read(tun, tfile, to, file->f_flags & O_NONBLOCK, NULL); + + if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) + noblock = 1; + + ret = tun_do_read(tun, tfile, to, noblock, NULL); ret = min_t(ssize_t, ret, len); if (ret > 0) iocb->ki_pos = ret;

From: Jamie Iles jamie@nuviainc.com

[ Upstream commit b9ad3e9f5a7a760ab068e33e1f18d240ba32ce92 ]

syzkaller found that with CONFIG_DEBUG_KOBJECT_RELEASE=y, releasing a struct slave device could result in the following splat:

kobject: 'bonding_slave' (00000000cecdd4fe): kobject_release, parent 0000000074ceb2b2 (delayed 1000) bond0 (unregistering): (slave bond_slave_1): Releasing backup interface ------------[ cut here ]------------ ODEBUG: free active (active state 0) object type: timer_list hint: workqueue_select_cpu_near kernel/workqueue.c:1549 [inline] ODEBUG: free active (active state 0) object type: timer_list hint: delayed_work_timer_fn+0x0/0x98 kernel/workqueue.c:1600 WARNING: CPU: 1 PID: 842 at lib/debugobjects.c:485 debug_print_object+0x180/0x240 lib/debugobjects.c:485 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 842 Comm: kworker/u4:4 Tainted: G S 5.9.0-rc8+ #96 Hardware name: linux,dummy-virt (DT) Workqueue: netns cleanup_net Call trace: dump_backtrace+0x0/0x4d8 include/linux/bitmap.h:239 show_stack+0x34/0x48 arch/arm64/kernel/traps.c:142 __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x174/0x1f8 lib/dump_stack.c:118 panic+0x360/0x7a0 kernel/panic.c:231 __warn+0x244/0x2ec kernel/panic.c:600 report_bug+0x240/0x398 lib/bug.c:198 bug_handler+0x50/0xc0 arch/arm64/kernel/traps.c:974 call_break_hook+0x160/0x1d8 arch/arm64/kernel/debug-monitors.c:322 brk_handler+0x30/0xc0 arch/arm64/kernel/debug-monitors.c:329 do_debug_exception+0x184/0x340 arch/arm64/mm/fault.c:864 el1_dbg+0x48/0xb0 arch/arm64/kernel/entry-common.c:65 el1_sync_handler+0x170/0x1c8 arch/arm64/kernel/entry-common.c:93 el1_sync+0x80/0x100 arch/arm64/kernel/entry.S:594 debug_print_object+0x180/0x240 lib/debugobjects.c:485 __debug_check_no_obj_freed lib/debugobjects.c:967 [inline] debug_check_no_obj_freed+0x200/0x430 lib/debugobjects.c:998 slab_free_hook mm/slub.c:1536 [inline] slab_free_freelist_hook+0x190/0x210 mm/slub.c:1577 slab_free mm/slub.c:3138 [inline] kfree+0x13c/0x460 mm/slub.c:4119 bond_free_slave+0x8c/0xf8 drivers/net/bonding/bond_main.c:1492 __bond_release_one+0xe0c/0xec8 drivers/net/bonding/bond_main.c:2190 bond_slave_netdev_event drivers/net/bonding/bond_main.c:3309 [inline] bond_netdev_event+0x8f0/0xa70 drivers/net/bonding/bond_main.c:3420 notifier_call_chain+0xf0/0x200 kernel/notifier.c:83 __raw_notifier_call_chain kernel/notifier.c:361 [inline] raw_notifier_call_chain+0x44/0x58 kernel/notifier.c:368 call_netdevice_notifiers_info+0xbc/0x150 net/core/dev.c:2033 call_netdevice_notifiers_extack net/core/dev.c:2045 [inline] call_netdevice_notifiers net/core/dev.c:2059 [inline] rollback_registered_many+0x6a4/0xec0 net/core/dev.c:9347 unregister_netdevice_many.part.0+0x2c/0x1c0 net/core/dev.c:10509 unregister_netdevice_many net/core/dev.c:10508 [inline] default_device_exit_batch+0x294/0x338 net/core/dev.c:10992 ops_exit_list.isra.0+0xec/0x150 net/core/net_namespace.c:189 cleanup_net+0x44c/0x888 net/core/net_namespace.c:603 process_one_work+0x96c/0x18c0 kernel/workqueue.c:2269 worker_thread+0x3f0/0xc30 kernel/workqueue.c:2415 kthread+0x390/0x498 kernel/kthread.c:292 ret_from_fork+0x10/0x18 arch/arm64/kernel/entry.S:925

This is a potential use-after-free if the sysfs nodes are being accessed whilst removing the struct slave, so wait for the object destruction to complete before freeing the struct slave itself.

Fixes: 07699f9a7c8d ("bonding: add sysfs /slave dir for bond slave devices.") Fixes: a068aab42258 ("bonding: Fix reference count leak in bond_sysfs_slave_add.") Cc: Qiushi Wu wu000273@umn.edu Cc: Jay Vosburgh j.vosburgh@gmail.com Cc: Veaceslav Falico vfalico@gmail.com Cc: Andy Gospodarek andy@greyhouse.net Signed-off-by: Jamie Iles jamie@nuviainc.com Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Link: https://lore.kernel.org/r/20201120142827.879226-1-jamie@nuviainc.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/bonding/bond_main.c | 61 +++++++++++++++++++++++---------- drivers/net/bonding/bond_sysfs_slave.c | 18 --------- include/net/bonding.h | 8 ++++ 3 files changed, 52 insertions(+), 35 deletions(-)

--- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1293,7 +1293,39 @@ static void bond_upper_dev_unlink(struct slave->dev->flags &= ~IFF_SLAVE; }

-static struct slave *bond_alloc_slave(struct bonding *bond) +static void slave_kobj_release(struct kobject *kobj) +{ + struct slave *slave = to_slave(kobj); + struct bonding *bond = bond_get_bond_by_slave(slave); + + cancel_delayed_work_sync(&slave->notify_work); + if (BOND_MODE(bond) == BOND_MODE_8023AD) + kfree(SLAVE_AD_INFO(slave)); + + kfree(slave); +} + +static struct kobj_type slave_ktype = { + .release = slave_kobj_release, +#ifdef CONFIG_SYSFS + .sysfs_ops = &slave_sysfs_ops, +#endif +}; + +static int bond_kobj_init(struct slave *slave) +{ + int err; + + err = kobject_init_and_add(&slave->kobj, &slave_ktype, + &(slave->dev->dev.kobj), "bonding_slave"); + if (err) + kobject_put(&slave->kobj); + + return err; +} + +static struct slave *bond_alloc_slave(struct bonding *bond, + struct net_device *slave_dev) { struct slave *slave = NULL;

@@ -1301,11 +1333,17 @@ static struct slave *bond_alloc_slave(st if (!slave) return NULL;

+ slave->bond = bond; + slave->dev = slave_dev; + + if (bond_kobj_init(slave)) + return NULL; + if (BOND_MODE(bond) == BOND_MODE_8023AD) { SLAVE_AD_INFO(slave) = kzalloc(sizeof(struct ad_slave_info), GFP_KERNEL); if (!SLAVE_AD_INFO(slave)) { - kfree(slave); + kobject_put(&slave->kobj); return NULL; } } @@ -1314,17 +1352,6 @@ static struct slave *bond_alloc_slave(st return slave; }

-static void bond_free_slave(struct slave *slave) -{ - struct bonding *bond = bond_get_bond_by_slave(slave); - - cancel_delayed_work_sync(&slave->notify_work); - if (BOND_MODE(bond) == BOND_MODE_8023AD) - kfree(SLAVE_AD_INFO(slave)); - - kfree(slave); -} - static void bond_fill_ifbond(struct bonding *bond, struct ifbond *info) { info->bond_mode = BOND_MODE(bond); @@ -1508,14 +1535,12 @@ int bond_enslave(struct net_device *bond goto err_undo_flags; }

- new_slave = bond_alloc_slave(bond); + new_slave = bond_alloc_slave(bond, slave_dev); if (!new_slave) { res = -ENOMEM; goto err_undo_flags; }

- new_slave->bond = bond; - new_slave->dev = slave_dev; /* Set the new_slave's queue_id to be zero. Queue ID mapping * is set via sysfs or module option if desired. */ @@ -1837,7 +1862,7 @@ err_restore_mtu: dev_set_mtu(slave_dev, new_slave->original_mtu);

err_free: - bond_free_slave(new_slave); + kobject_put(&new_slave->kobj);

err_undo_flags: /* Enslave of first slave has failed and we need to fix master's mac */ @@ -2017,7 +2042,7 @@ static int __bond_release_one(struct net if (!netif_is_bond_master(slave_dev)) slave_dev->priv_flags &= ~IFF_BONDING;

- bond_free_slave(slave); + kobject_put(&slave->kobj);

return 0; } --- a/drivers/net/bonding/bond_sysfs_slave.c +++ b/drivers/net/bonding/bond_sysfs_slave.c @@ -121,7 +121,6 @@ static const struct slave_attribute *sla };

#define to_slave_attr(_at) container_of(_at, struct slave_attribute, attr) -#define to_slave(obj) container_of(obj, struct slave, kobj)

static ssize_t slave_show(struct kobject *kobj, struct attribute *attr, char *buf) @@ -132,28 +131,15 @@ static ssize_t slave_show(struct kobject return slave_attr->show(slave, buf); }

-static const struct sysfs_ops slave_sysfs_ops = { +const struct sysfs_ops slave_sysfs_ops = { .show = slave_show, };

-static struct kobj_type slave_ktype = { -#ifdef CONFIG_SYSFS - .sysfs_ops = &slave_sysfs_ops, -#endif -}; - int bond_sysfs_slave_add(struct slave *slave) { const struct slave_attribute **a; int err;

- err = kobject_init_and_add(&slave->kobj, &slave_ktype, - &(slave->dev->dev.kobj), "bonding_slave"); - if (err) { - kobject_put(&slave->kobj); - return err; - } - for (a = slave_attrs; *a; ++a) { err = sysfs_create_file(&slave->kobj, &((*a)->attr)); if (err) { @@ -171,6 +157,4 @@ void bond_sysfs_slave_del(struct slave *

for (a = slave_attrs; *a; ++a) sysfs_remove_file(&slave->kobj, &((*a)->attr)); - - kobject_put(&slave->kobj); } --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -180,6 +180,11 @@ struct slave { struct rtnl_link_stats64 slave_stats; };

+static inline struct slave *to_slave(struct kobject *kobj) +{ + return container_of(kobj, struct slave, kobj); +} + struct bond_up_slave { unsigned int count; struct rcu_head rcu; @@ -743,6 +748,9 @@ extern struct bond_parm_tbl ad_select_tb /* exported from bond_netlink.c */ extern struct rtnl_link_ops bond_link_ops;

+/* exported from bond_sysfs_slave.c */ +extern const struct sysfs_ops slave_sysfs_ops; + static inline void bond_tx_drop(struct net_device *dev, struct sk_buff *skb) { atomic_long_inc(&dev->tx_dropped);

From: Maurizio Drocco maurizio.drocco@ibm.com

[ Upstream commit 20c59ce010f84300f6c655d32db2610d3433f85c ]

Registers 8-9 are used to store measurements of the kernel and its command line (e.g., grub2 bootloader with tpm module enabled). IMA should include them in the boot aggregate. Registers 8-9 should be only included in non-SHA1 digests to avoid ambiguity.

Signed-off-by: Maurizio Drocco maurizio.drocco@ibm.com Reviewed-by: Bruno Meneguele bmeneg@redhat.com Tested-by: Bruno Meneguele bmeneg@redhat.com (TPM 1.2, TPM 2.0) Signed-off-by: Mimi Zohar zohar@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- security/integrity/ima/ima.h | 2 +- security/integrity/ima/ima_crypto.c | 15 ++++++++++++++- 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index 8173982e00ab5..5fae6cfe8d910 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -30,7 +30,7 @@

enum ima_show_type { IMA_SHOW_BINARY, IMA_SHOW_BINARY_NO_FIELD_LEN, IMA_SHOW_BINARY_OLD_STRING_FMT, IMA_SHOW_ASCII }; -enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 }; +enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8, TPM_PCR10 = 10 };

/* digest size for IMA, fits SHA1 or MD5 */ #define IMA_DIGEST_SIZE SHA1_DIGEST_SIZE diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c index d86825261b515..b06baf5d3cd32 100644 --- a/security/integrity/ima/ima_crypto.c +++ b/security/integrity/ima/ima_crypto.c @@ -682,7 +682,7 @@ static int ima_calc_boot_aggregate_tfm(char *digest, u16 alg_id, if (rc != 0) return rc;

- /* cumulative sha1 over tpm registers 0-7 */ + /* cumulative digest over TPM registers 0-7 */ for (i = TPM_PCR0; i < TPM_PCR8; i++) { ima_pcrread(i, &d); /* now accumulate with current aggregate */ @@ -691,6 +691,19 @@ static int ima_calc_boot_aggregate_tfm(char *digest, u16 alg_id, if (rc != 0) return rc; } + /* + * Extend cumulative digest over TPM registers 8-9, which contain + * measurement for the kernel command line (reg. 8) and image (reg. 9) + * in a typical PCR allocation. Registers 8-9 are only included in + * non-SHA1 boot_aggregate digests to avoid ambiguity. + */ + if (alg_id != TPM_ALG_SHA1) { + for (i = TPM_PCR8; i < TPM_PCR10; i++) { + ima_pcrread(i, &d); + rc = crypto_shash_update(shash, d.digest, + crypto_shash_digestsize(tfm)); + } + } if (!rc) crypto_shash_final(shash, digest); return rc;

From: Antoine Tenart atenart@kernel.org

[ Upstream commit 44f64f23bae2f0fad25503bc7ab86cd08d04cd47 ]

Netfilter changes PACKET_OTHERHOST to PACKET_HOST before invoking the hooks as, while it's an expected value for a bridge, routing expects PACKET_HOST. The change is undone later on after hook traversal. This can be seen with pairs of functions updating skb>pkt_type and then reverting it to its original value:

For hook NF_INET_PRE_ROUTING: setup_pre_routing / br_nf_pre_routing_finish

For hook NF_INET_FORWARD: br_nf_forward_ip / br_nf_forward_finish

But the third case where netfilter does this, for hook NF_INET_POST_ROUTING, the packet type is changed in br_nf_post_routing but never reverted. A comment says:

/* We assume any code from br_dev_queue_push_xmit onwards doesn't care * about the value of skb->pkt_type. */

But when having a tunnel (say vxlan) attached to a bridge we have the following call trace:

br_nf_pre_routing br_nf_pre_routing_ipv6 br_nf_pre_routing_finish br_nf_forward_ip br_nf_forward_finish br_nf_post_routing <- pkt_type is updated to PACKET_HOST br_nf_dev_queue_xmit <- but not reverted to its original value vxlan_xmit vxlan_xmit_one skb_tunnel_check_pmtu <- a check on pkt_type is performed

In this specific case, this creates issues such as when an ICMPv6 PTB should be sent back. When CONFIG_BRIDGE_NETFILTER is enabled, the PTB isn't sent (as skb_tunnel_check_pmtu checks if pkt_type is PACKET_HOST and returns early).

If the comment is right and no one cares about the value of skb->pkt_type after br_dev_queue_push_xmit (which isn't true), resetting it to its original value should be safe.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Antoine Tenart atenart@kernel.org Reviewed-by: Florian Westphal fw@strlen.de Link: https://lore.kernel.org/r/20201123174902.622102-1-atenart@kernel.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bridge/br_netfilter_hooks.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

--- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -735,6 +735,11 @@ static int br_nf_dev_queue_xmit(struct n mtu_reserved = nf_bridge_mtu_reduction(skb); mtu = skb->dev->mtu;

+ if (nf_bridge->pkt_otherhost) { + skb->pkt_type = PACKET_OTHERHOST; + nf_bridge->pkt_otherhost = false; + } + if (nf_bridge->frag_max_size && nf_bridge->frag_max_size < mtu) mtu = nf_bridge->frag_max_size;

@@ -835,8 +840,6 @@ static unsigned int br_nf_post_routing(v else return NF_ACCEPT;

- /* We assume any code from br_dev_queue_push_xmit onwards doesn't care - * about the value of skb->pkt_type. */ if (skb->pkt_type == PACKET_OTHERHOST) { skb->pkt_type = PACKET_HOST; nf_bridge->pkt_otherhost = true;

From: Krzysztof Kozlowski krzk@kernel.org

[ Upstream commit 4d521943f76bd0d1e68ea5e02df7aadd30b2838a ]

GPIO_ACTIVE_x flags are not correct in the context of interrupt flags. These are simple defines so they could be used in DTS but they will not have the same meaning: 1. GPIO_ACTIVE_HIGH = 0 = IRQ_TYPE_NONE 2. GPIO_ACTIVE_LOW = 1 = IRQ_TYPE_EDGE_RISING

Correct the interrupt flags, assuming the author of the code wanted same logical behavior behind the name "ACTIVE_xxx", this is: ACTIVE_LOW => IRQ_TYPE_LEVEL_LOW ACTIVE_HIGH => IRQ_TYPE_LEVEL_HIGH

Fixes: a1a8b4594f8d ("NFC: pn544: i2c: Add DTS Documentation") Fixes: 6be88670fc59 ("NFC: nxp-nci_i2c: Add I2C support to NXP NCI driver") Fixes: e3b329221567 ("dt-bindings: can: tcan4x5x: Update binding to use interrupt property") Signed-off-by: Krzysztof Kozlowski krzk@kernel.org Acked-by: Rob Herring robh@kernel.org Acked-by: Marc Kleine-Budde mkl@pengutronix.de # for tcan4x5x.txt Link: https://lore.kernel.org/r/20201026153620.89268-1-krzk@kernel.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/devicetree/bindings/net/can/tcan4x5x.txt | 2 +- Documentation/devicetree/bindings/net/nfc/nxp-nci.txt | 2 +- Documentation/devicetree/bindings/net/nfc/pn544.txt | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-)

--- a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt +++ b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt @@ -33,7 +33,7 @@ tcan4x5x: tcan4x5x@0 { spi-max-frequency = <10000000>; bosch,mram-cfg = <0x0 0 0 32 0 0 1 1>; interrupt-parent = <&gpio1>; - interrupts = <14 GPIO_ACTIVE_LOW>; + interrupts = <14 IRQ_TYPE_LEVEL_LOW>; device-state-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; device-wake-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; reset-gpios = <&gpio1 27 GPIO_ACTIVE_LOW>; --- a/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt +++ b/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt @@ -25,7 +25,7 @@ Example (for ARM-based BeagleBone with N clock-frequency = <100000>;

interrupt-parent = <&gpio1>; - interrupts = <29 GPIO_ACTIVE_HIGH>; + interrupts = <29 IRQ_TYPE_LEVEL_HIGH>;

enable-gpios = <&gpio0 30 GPIO_ACTIVE_HIGH>; firmware-gpios = <&gpio0 31 GPIO_ACTIVE_HIGH>; --- a/Documentation/devicetree/bindings/net/nfc/pn544.txt +++ b/Documentation/devicetree/bindings/net/nfc/pn544.txt @@ -25,7 +25,7 @@ Example (for ARM-based BeagleBone with P clock-frequency = <400000>;

interrupt-parent = <&gpio1>; - interrupts = <17 GPIO_ACTIVE_HIGH>; + interrupts = <17 IRQ_TYPE_LEVEL_HIGH>;

enable-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; firmware-gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>;

From: Thomas Falcon tlfalcon@linux.ibm.com

[ Upstream commit b71ec952234610b4f90ef17a2fdcb124d5320070 ]

Ensure that received Subordinate Command-Response Queue (SCRQ) entries are properly read in order by the driver. These queues are used in the ibmvnic device to process RX buffer and TX completion descriptors. dma_rmb barriers have been added after checking for a pending descriptor to ensure the correct descriptor entry is checked and after reading the SCRQ descriptor to ensure the entire descriptor is read before processing.

Fixes: 032c5e82847a ("Driver for IBM System i/p VNIC protocol") Signed-off-by: Thomas Falcon tlfalcon@linux.ibm.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/ibm/ibmvnic.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)

--- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2307,6 +2307,12 @@ restart_poll:

if (!pending_scrq(adapter, adapter->rx_scrq[scrq_num])) break; + /* The queue entry at the current index is peeked at above + * to determine that there is a valid descriptor awaiting + * processing. We want to be sure that the current slot + * holds a valid descriptor before reading its contents. + */ + dma_rmb(); next = ibmvnic_next_scrq(adapter, adapter->rx_scrq[scrq_num]); rx_buff = (struct ibmvnic_rx_buff *)be64_to_cpu(next-> @@ -2988,6 +2994,13 @@ restart_loop: unsigned int pool = scrq->pool_index; int num_entries = 0;

+ /* The queue entry at the current index is peeked at above + * to determine that there is a valid descriptor awaiting + * processing. We want to be sure that the current slot + * holds a valid descriptor before reading its contents. + */ + dma_rmb(); + next = ibmvnic_next_scrq(adapter, scrq); for (i = 0; i < next->tx_comp.num_comps; i++) { if (next->tx_comp.rcs[i]) { @@ -3388,6 +3401,11 @@ static union sub_crq *ibmvnic_next_scrq( } spin_unlock_irqrestore(&scrq->lock, flags);

+ /* Ensure that the entire buffer descriptor has been + * loaded before reading its contents + */ + dma_rmb(); + return entry; }

From: "Toke H�iland-J�rgensen" toke@redhat.com

[ Upstream commit 2867e1eac61016f59b3d730e3f7aa488e186e917 ]

When adding support for propagating ECT(1) marking in IP headers it seems I suffered from endianness-confusion in the checksum update calculation: In fact the ECN field is in the *lower* bits of the first 16-bit word of the IP header when calculating in network byte order. This means that the addition performed to update the checksum field was wrong; let's fix that.

Fixes: b723748750ec ("tunnel: Propagate ECT(1) when decapsulating as recommended by RFC6040") Reported-by: Jonathan Morton chromatix99@gmail.com Tested-by: Pete Heist pete@heistp.net Signed-off-by: Toke Høiland-Jørgensen toke@redhat.com Link: https://lore.kernel.org/r/20201130183705.17540-1-toke@redhat.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/inet_ecn.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -107,7 +107,7 @@ static inline int IP_ECN_set_ect1(struct if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0) return 0;

- check += (__force u16)htons(0x100); + check += (__force u16)htons(0x1);

iph->check = (__force __sum16)(check + (check>=0xFFFF)); iph->tos ^= INET_ECN_MASK;

From: Antoine Tenart atenart@kernel.org

[ Upstream commit 832ba596494b2c9eac7760259eff2d8b7dcad0ee ]

syzkaller managed to crash the kernel using an NBMA ip6gre interface. I could reproduce it creating an NBMA ip6gre interface and forwarding traffic to it:

skbuff: skb_under_panic: text:ffffffff8250e927 len:148 put:44 head:ffff8c03c7a33 ------------[ cut here ]------------ kernel BUG at net/core/skbuff.c:109! Call Trace: skb_push+0x10/0x10 ip6gre_header+0x47/0x1b0 neigh_connected_output+0xae/0xf0

ip6gre tunnel provides its own header_ops->create, and sets it conditionally when initializing the tunnel in NBMA mode. When header_ops->create is used, dev->hard_header_len should reflect the length of the header created. Otherwise, when not used, dev->needed_headroom should be used.

Fixes: eb95f52fc72d ("net: ipv6_gre: Fix GRO to work on IPv6 over GRE tap") Cc: Maria Pasechnik mariap@mellanox.com Signed-off-by: Antoine Tenart atenart@kernel.org Link: https://lore.kernel.org/r/20201130161911.464106-1-atenart@kernel.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/ip6_gre.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-)

--- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1120,8 +1120,13 @@ static void ip6gre_tnl_link_config_route return;

if (rt->dst.dev) { - dev->needed_headroom = rt->dst.dev->hard_header_len + - t_hlen; + unsigned short dst_len = rt->dst.dev->hard_header_len + + t_hlen; + + if (t->dev->header_ops) + dev->hard_header_len = dst_len; + else + dev->needed_headroom = dst_len;

if (set_mtu) { dev->mtu = rt->dst.dev->mtu - t_hlen; @@ -1146,7 +1151,12 @@ static int ip6gre_calc_hlen(struct ip6_t tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;

t_hlen = tunnel->hlen + sizeof(struct ipv6hdr); - tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen; + + if (tunnel->dev->header_ops) + tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen; + else + tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen; + return t_hlen; }

From: Zhang Changzhong zhangchangzhong@huawei.com

[ Upstream commit ff9924897f8bfed82e61894b373ab9d2dfea5b10 ]

Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function.

Fixes: b1fb1f280d09 ("cxgb3 - Fix dma mapping error path") Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Zhang Changzhong zhangchangzhong@huawei.com Acked-by: Raju Rangoju rajur@chelsio.com Link: https://lore.kernel.org/r/1606902965-1646-1-git-send-email-zhangchangzhong@h... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/chelsio/cxgb3/sge.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c @@ -3176,6 +3176,7 @@ int t3_sge_alloc_qset(struct adapter *ad GFP_KERNEL | __GFP_COMP); if (!avail) { CH_ALERT(adapter, "free list queue 0 initialization failed\n"); + ret = -ENOMEM; goto err; } if (avail < q->fl[0].size)

From: Zhang Changzhong zhangchangzhong@huawei.com

[ Upstream commit 832e09798c261cf58de3a68cfcc6556408c16a5a ]

Fix to return a negative error code from the error handling case instead of 0, as done elsewhere in this function.

Fixes: 0ce1822c2a08 ("vxlan: add adjacent link to limit depth level") Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Zhang Changzhong zhangchangzhong@huawei.com Link: https://lore.kernel.org/r/1606903122-2098-1-git-send-email-zhangchangzhong@h... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/vxlan.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3617,8 +3617,10 @@ static int __vxlan_dev_create(struct net

if (dst->remote_ifindex) { remote_dev = __dev_get_by_index(net, dst->remote_ifindex); - if (!remote_dev) + if (!remote_dev) { + err = -ENODEV; goto errout; + }

err = netdev_upper_dev_link(remote_dev, dev, extack); if (err)

From: Wang Hai wanghai38@huawei.com

[ Upstream commit 82a10dc7f0960735f40e8d7d3bee56934291600f ]

Fix to return negative error code -ENOENT from invalid configuration error handling case instead of 0, as done elsewhere in this function.

Fixes: 4bb043262878 ("net: mvpp2: phylink support") Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Wang Hai wanghai38@huawei.com Reviewed-by: Andrew Lunn andrew@lunn.ch Link: https://lore.kernel.org/r/20201203141806.37966-1-wanghai38@huawei.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -3696,6 +3696,7 @@ static int mvpp2_open(struct net_device if (!valid) { netdev_err(port->dev, "invalid configuration: no dt or link IRQ"); + err = -ENOENT; goto err_free_irq; }

From: Davide Caratti dcaratti@redhat.com

[ Upstream commit 43c13605bad44b8abbc9776d6e63f62ccb7a47d6 ]

when openvswitch is configured to mangle the LSE, the current value is read from the packet dereferencing 4 bytes at mpls_hdr(): ensure that the label is contained in the skb "linear" area.

Found by code inspection.

Fixes: d27cf5c59a12 ("net: core: add MPLS update core helper and use in OvS") Signed-off-by: Davide Caratti dcaratti@redhat.com Link: https://lore.kernel.org/r/aa099f245d93218b84b5c056b67b6058ccf81a66.160698718... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/openvswitch/actions.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -196,6 +196,9 @@ static int set_mpls(struct sk_buff *skb, __be32 lse; int err;

+ if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN)) + return -ENOMEM; + stack = mpls_hdr(skb); lse = OVS_MASKED(stack->label_stack_entry, *mpls_lse, *mask); err = skb_mpls_update_lse(skb, lse);

From: Yevgeny Kliteynik kliteyn@nvidia.com

[ Upstream commit d421e466c2373095f165ddd25cbabd6c5b077928 ]

STEs format for Connect-X5 and Connect-X6DX different. Currently, on Connext-X6DX the SW steering would break at some point when building STEs w/o giving a proper error message. Fix this by checking the STE format of the current device when initializing domain: add mlx5_ifc definitions for Connect-X6DX SW steering, read FW capability to get the current format version, and check this version when domain is being created.

Fixes: 26d688e33f88 ("net/mlx5: DR, Add Steering entry (STE) utilities") Signed-off-by: Yevgeny Kliteynik kliteyn@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c | 5 +++++ drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h | 1 + include/linux/mlx5/mlx5_ifc.h | 9 ++++++++- 4 files changed, 15 insertions(+), 1 deletion(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -92,6 +92,7 @@ int mlx5dr_cmd_query_device(struct mlx5_ caps->eswitch_manager = MLX5_CAP_GEN(mdev, eswitch_manager); caps->gvmi = MLX5_CAP_GEN(mdev, vhca_id); caps->flex_protocols = MLX5_CAP_GEN(mdev, flex_parser_protocols); + caps->sw_format_ver = MLX5_CAP_GEN(mdev, steering_format_version);

if (mlx5dr_matcher_supp_flex_parser_icmp_v4(caps)) { caps->flex_parser_id_icmp_dw0 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw0); --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -223,6 +223,11 @@ static int dr_domain_caps_init(struct ml if (ret) return ret;

+ if (dmn->info.caps.sw_format_ver != MLX5_STEERING_FORMAT_CONNECTX_5) { + mlx5dr_err(dmn, "SW steering is not supported on this device\n"); + return -EOPNOTSUPP; + } + ret = dr_domain_query_fdb_caps(mdev, dmn); if (ret) return ret; --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -613,6 +613,7 @@ struct mlx5dr_cmd_caps { u8 max_ft_level; u16 roce_min_src_udp; u8 num_esw_ports; + u8 sw_format_ver; bool eswitch_manager; bool rx_sw_owner; bool tx_sw_owner; --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1139,6 +1139,11 @@ enum mlx5_fc_bulk_alloc_bitmask {

#define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum))

+enum { + MLX5_STEERING_FORMAT_CONNECTX_5 = 0, + MLX5_STEERING_FORMAT_CONNECTX_6DX = 1, +}; + struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x30]; u8 vhca_id[0x10]; @@ -1419,7 +1424,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {

u8 general_obj_types[0x40];

- u8 reserved_at_440[0x20]; + u8 reserved_at_440[0x4]; + u8 steering_format_version[0x4]; + u8 create_qp_start_hint[0x18];

u8 reserved_at_460[0x3]; u8 log_max_uctx[0x5];

From: Hector Martin marcan@marcan.st

commit 402d5840b0d40a2a26c8651165d29b534abb6d36 upstream.

The level meter control returns 34 integers of info. This fixes:

snd-usb-audio 3-1:1.0: control 2:0:0:Level Meter:0: access overflow

Fixes: d2bb390a2081 ("ALSA: usb-audio: Tascam US-16x08 DSP mixer quirk") Cc: stable@vger.kernel.org Signed-off-by: Hector Martin marcan@marcan.st Link: https://lore.kernel.org/r/20201127132635.18947-1-marcan@marcan.st Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/usb/mixer_us16x08.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/sound/usb/mixer_us16x08.c +++ b/sound/usb/mixer_us16x08.c @@ -607,7 +607,7 @@ static int snd_us16x08_eq_put(struct snd static int snd_us16x08_meter_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) { - uinfo->count = 1; + uinfo->count = 34; uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; uinfo->value.integer.max = 0x7FFF; uinfo->value.integer.min = 0;

From: Po-Hsu Lin po-hsu.lin@canonical.com

commit a48491c65b513e5cdc3e7a886a4db915f848a5f5 upstream.

It looks like the C15B laptop got another vendor: ByteSpeed LLC.

Avoid AUX loopback on this touchpad as well, thus input subsystem will be able to recognize a Synaptics touchpad in the AUX port.

BugLink: https://bugs.launchpad.net/bugs/1906128 Signed-off-by: Po-Hsu Lin po-hsu.lin@canonical.com Link: https://lore.kernel.org/r/20201201054723.5939-1-po-hsu.lin@canonical.com Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/input/serio/i8042-x86ia64io.h | 4 ++++ 1 file changed, 4 insertions(+)

--- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -219,6 +219,10 @@ static const struct dmi_system_id __init DMI_MATCH(DMI_SYS_VENDOR, "PEGATRON CORPORATION"), DMI_MATCH(DMI_PRODUCT_NAME, "C15B"), }, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ByteSpeed LLC"), + DMI_MATCH(DMI_PRODUCT_NAME, "ByteSpeed Laptop C15B"), + }, }, { } };

From: Shiraz Saleem shiraz.saleem@intel.com

commit 2ed381439e89fa6d1a0839ef45ccd45d99d8e915 upstream.

i40iw_mmap manipulates the vma->vm_pgoff to differentiate a push page mmap vs a doorbell mmap, and uses it to compute the pfn in remap_pfn_range without any validation. This is vulnerable to an mmap exploit as described in: https://lore.kernel.org/r/20201119093523.7588-1-zhudi21@huawei.com

The push feature is disabled in the driver currently and therefore no push mmaps are issued from user-space. The feature does not work as expected in the x722 product.

Remove the push module parameter and all VMA attribute manipulations for this feature in i40iw_mmap. Update i40iw_mmap to only allow DB user mmapings at offset = 0. Check vm_pgoff for zero and if the mmaps are bound to a single page.

Cc: stable@kernel.org Fixes: d37498417947 ("i40iw: add files for iwarp interface") Link: https://lore.kernel.org/r/20201125005616.1800-2-shiraz.saleem@intel.com Reported-by: Di Zhu zhudi21@huawei.com Signed-off-by: Shiraz Saleem shiraz.saleem@intel.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/infiniband/hw/i40iw/i40iw_main.c | 5 ---- drivers/infiniband/hw/i40iw/i40iw_verbs.c | 36 +++++------------------------- 2 files changed, 7 insertions(+), 34 deletions(-)

--- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -54,10 +54,6 @@ #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." __stringify(DRV_VERSION_BUILD)

-static int push_mode; -module_param(push_mode, int, 0644); -MODULE_PARM_DESC(push_mode, "Low latency mode: 0=disabled (default), 1=enabled)"); - static int debug; module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "debug flags: 0=disabled (default), 0x7fffffff=all"); @@ -1588,7 +1584,6 @@ static enum i40iw_status_code i40iw_setu if (status) goto exit; iwdev->obj_next = iwdev->obj_mem; - iwdev->push_mode = push_mode;

init_waitqueue_head(&iwdev->vchnl_waitq); init_waitqueue_head(&dev->vf_reqs); --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -168,38 +168,16 @@ static void i40iw_dealloc_ucontext(struc */ static int i40iw_mmap(struct ib_ucontext *context, struct vm_area_struct *vma) { - struct i40iw_ucontext *ucontext; - u64 db_addr_offset; - u64 push_offset; + struct i40iw_ucontext *ucontext = to_ucontext(context); + u64 dbaddr;

- ucontext = to_ucontext(context); - if (ucontext->iwdev->sc_dev.is_pf) { - db_addr_offset = I40IW_DB_ADDR_OFFSET; - push_offset = I40IW_PUSH_OFFSET; - if (vma->vm_pgoff) - vma->vm_pgoff += I40IW_PF_FIRST_PUSH_PAGE_INDEX - 1; - } else { - db_addr_offset = I40IW_VF_DB_ADDR_OFFSET; - push_offset = I40IW_VF_PUSH_OFFSET; - if (vma->vm_pgoff) - vma->vm_pgoff += I40IW_VF_FIRST_PUSH_PAGE_INDEX - 1; - } + if (vma->vm_pgoff || vma->vm_end - vma->vm_start != PAGE_SIZE) + return -EINVAL;

- vma->vm_pgoff += db_addr_offset >> PAGE_SHIFT; + dbaddr = I40IW_DB_ADDR_OFFSET + pci_resource_start(ucontext->iwdev->ldev->pcidev, 0);

- if (vma->vm_pgoff == (db_addr_offset >> PAGE_SHIFT)) { - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - vma->vm_private_data = ucontext; - } else { - if ((vma->vm_pgoff - (push_offset >> PAGE_SHIFT)) % 2) - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - else - vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); - } - - if (io_remap_pfn_range(vma, vma->vm_start, - vma->vm_pgoff + (pci_resource_start(ucontext->iwdev->ldev->pcidev, 0) >> PAGE_SHIFT), - PAGE_SIZE, vma->vm_page_prot)) + if (io_remap_pfn_range(vma, vma->vm_start, dbaddr >> PAGE_SHIFT, PAGE_SIZE, + pgprot_noncached(vma->vm_page_prot))) return -EAGAIN;

return 0;