From: Matt Jolly Kangie@footclan.ninja

commit 78d6de3cfbd342918d31cf68d0d2eda401338aef upstream.

Add support for Dell Wireless 5816e to drivers/usb/serial/qcserial.c

Signed-off-by: Matt Jolly Kangie@footclan.ninja Cc: stable stable@vger.kernel.org Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/serial/qcserial.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -177,6 +177,7 @@ static const struct usb_device_id id_tab {DEVICE_SWI(0x413c, 0x81b3)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {DEVICE_SWI(0x413c, 0x81b5)}, /* Dell Wireless 5811e QDL */ {DEVICE_SWI(0x413c, 0x81b6)}, /* Dell Wireless 5811e QDL */ + {DEVICE_SWI(0x413c, 0x81cc)}, /* Dell Wireless 5816e */ {DEVICE_SWI(0x413c, 0x81cf)}, /* Dell Wireless 5819 */ {DEVICE_SWI(0x413c, 0x81d0)}, /* Dell Wireless 5819 */ {DEVICE_SWI(0x413c, 0x81d1)}, /* Dell Wireless 5818 */

From: Eric Dumazet edumazet@google.com

[ Upstream commit 14695212d4cd8b0c997f6121b6df8520038ce076 ]

My intent was to not let users set a zero drop_batch_size, it seems I once again messed with min()/max().

Fixes: 9d18562a2278 ("fq_codel: add batch ability to fq_codel_drop()") Signed-off-by: Eric Dumazet edumazet@google.com Acked-by: Toke Høiland-Jørgensen toke@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/sch_fq_codel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -427,7 +427,7 @@ static int fq_codel_change(struct Qdisc q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM]));

if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]) - q->drop_batch_size = min(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); + q->drop_batch_size = max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]));

if (tb[TCA_FQ_CODEL_MEMORY_LIMIT]) q->memory_limit = min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT]));

From: Tariq Toukan tariqt@mellanox.com

[ Upstream commit 40e473071dbad04316ddc3613c3a3d1c75458299 ]

When ENOSPC is set the idx is still valid and gets set to the global MLX4_SINK_COUNTER_INDEX. However gcc's static analysis cannot tell that ENOSPC is impossible from mlx4_cmd_imm() and gives this warning:

drivers/net/ethernet/mellanox/mlx4/main.c:2552:28: warning: 'idx' may be used uninitialized in this function [-Wmaybe-uninitialized] 2552 | priv->def_counter[port] = idx;

Also, when ENOSPC is returned mlx4_allocate_default_counters should not fail.

Fixes: 6de5f7f6a1fa ("net/mlx4_core: Allocate default counter per port") Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Tariq Toukan tariqt@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx4/main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2503,6 +2503,7 @@ static int mlx4_allocate_default_counter

if (!err || err == -ENOSPC) { priv->def_counter[port] = idx; + err = 0; } else if (err == -ENOENT) { err = 0; continue; @@ -2553,7 +2554,8 @@ int mlx4_counter_alloc(struct mlx4_dev * MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED); if (!err) *idx = get_param_l(&out_param); - + if (WARN_ON(err == -ENOSPC)) + err = -EINVAL; return err; } return __mlx4_counter_alloc(dev, idx);

From: Eric Dumazet edumazet@google.com

[ Upstream commit 8738c85c72b3108c9b9a369a39868ba5f8e10ae0 ]

If choke_init() could not allocate q->tab, we would crash later in choke_reset().

BUG: KASAN: null-ptr-deref in memset include/linux/string.h:366 [inline] BUG: KASAN: null-ptr-deref in choke_reset+0x208/0x340 net/sched/sch_choke.c:326 Write of size 8 at addr 0000000000000000 by task syz-executor822/7022

CPU: 1 PID: 7022 Comm: syz-executor822 Not tainted 5.7.0-rc1-syzkaller #0 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+0x188/0x20d lib/dump_stack.c:118 __kasan_report.cold+0x5/0x4d mm/kasan/report.c:515 kasan_report+0x33/0x50 mm/kasan/common.c:625 check_memory_region_inline mm/kasan/generic.c:187 [inline] check_memory_region+0x141/0x190 mm/kasan/generic.c:193 memset+0x20/0x40 mm/kasan/common.c:85 memset include/linux/string.h:366 [inline] choke_reset+0x208/0x340 net/sched/sch_choke.c:326 qdisc_reset+0x6b/0x520 net/sched/sch_generic.c:910 dev_deactivate_queue.constprop.0+0x13c/0x240 net/sched/sch_generic.c:1138 netdev_for_each_tx_queue include/linux/netdevice.h:2197 [inline] dev_deactivate_many+0xe2/0xba0 net/sched/sch_generic.c:1195 dev_deactivate+0xf8/0x1c0 net/sched/sch_generic.c:1233 qdisc_graft+0xd25/0x1120 net/sched/sch_api.c:1051 tc_modify_qdisc+0xbab/0x1a00 net/sched/sch_api.c:1670 rtnetlink_rcv_msg+0x44e/0xad0 net/core/rtnetlink.c:5454 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2469 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline] netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:672 ____sys_sendmsg+0x6bf/0x7e0 net/socket.c:2362 ___sys_sendmsg+0x100/0x170 net/socket.c:2416 __sys_sendmsg+0xec/0x1b0 net/socket.c:2449 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295

Fixes: 77e62da6e60c ("sch_choke: drop all packets in queue during reset") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Cc: Cong Wang xiyou.wangcong@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/sch_choke.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -327,7 +327,8 @@ static void choke_reset(struct Qdisc *sc

sch->q.qlen = 0; sch->qstats.backlog = 0; - memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); + if (q->tab) + memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); q->head = q->tail = 0; red_restart(&q->vars); }

From: Michael Chan michael.chan@broadcom.com

[ Upstream commit c72cb303aa6c2ae7e4184f0081c6d11bf03fb96b ]

The current logic in bnxt_fix_features() will inadvertently turn on both CTAG and STAG VLAN offload if the user tries to disable both. Fix it by checking that the user is trying to enable CTAG or STAG before enabling both. The logic is supposed to enable or disable both CTAG and STAG together.

Fixes: 5a9f6b238e59 ("bnxt_en: Enable and disable RX CTAG and RX STAG VLAN acceleration together.") Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6827,6 +6827,7 @@ static netdev_features_t bnxt_fix_featur netdev_features_t features) { struct bnxt *bp = netdev_priv(dev); + netdev_features_t vlan_features;

if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp)) features &= ~NETIF_F_NTUPLE; @@ -6834,12 +6835,14 @@ static netdev_features_t bnxt_fix_featur /* Both CTAG and STAG VLAN accelaration on the RX side have to be * turned on or off together. */ - if ((features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) != - (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) { + vlan_features = features & (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_RX); + if (vlan_features != (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_RX)) { if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) features &= ~(NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX); - else + else if (vlan_features) features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX; }

From: Moshe Shemesh moshe@mellanox.com

[ Upstream commit cece6f432cca9f18900463ed01b97a152a03600a ]

Processing commands by cmd_work_handler() while already in Internal Error State will result in entry leak, since the handler process force completion without doorbell. Forced completion doesn't release the entry and event completion will never arrive, so entry should be released.

Fixes: 73dd3a4839c1 ("net/mlx5: Avoid using pending command interface slots") Signed-off-by: Moshe Shemesh moshe@mellanox.com Signed-off-by: Eran Ben Elisha eranbe@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -865,6 +865,10 @@ static void cmd_work_handler(struct work MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);

mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); + /* no doorbell, no need to keep the entry */ + free_ent(cmd, ent->idx); + if (ent->callback) + free_cmd(ent); return; }

From: Michael Chan michael.chan@broadcom.com

[ Upstream commit c71c4e49afe173823a2a85b0cabc9b3f1176ffa2 ]

Fix the logic that sets the enable/disable flag for the source MAC filter according to firmware spec 1.7.1.

In the original firmware spec. before 1.7.1, the VF spoof check flags were not latched after making the HWRM_FUNC_CFG call, so there was a need to keep the func_flags so that subsequent calls would perserve the VF spoof check setting. A change was made in the 1.7.1 spec so that the flags became latched. So we now set or clear the anti- spoof setting directly without retrieving the old settings in the stored vf->func_flags which are no longer valid. We also remove the unneeded vf->func_flags.

Fixes: 8eb992e876a8 ("bnxt_en: Update firmware interface spec to 1.7.6.2.") Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 1 - drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 9 ++------- 2 files changed, 2 insertions(+), 8 deletions(-)

--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -774,7 +774,6 @@ struct bnxt_vf_info { #define BNXT_VF_SPOOFCHK 0x2 #define BNXT_VF_LINK_FORCED 0x4 #define BNXT_VF_LINK_UP 0x8 - u32 func_flags; /* func cfg flags */ u32 min_tx_rate; u32 max_tx_rate; void *hwrm_cmd_req_addr; --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -99,11 +99,10 @@ int bnxt_set_vf_spoofchk(struct net_devi if (old_setting == setting) return 0;

- func_flags = vf->func_flags; if (setting) - func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE; + func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE; else - func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE; + func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE; /*TODO: if the driver supports VLAN filter on guest VLAN, * the spoof check should also include vlan anti-spoofing */ @@ -112,7 +111,6 @@ int bnxt_set_vf_spoofchk(struct net_devi req.flags = cpu_to_le32(func_flags); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (!rc) { - vf->func_flags = func_flags; if (setting) vf->flags |= BNXT_VF_SPOOFCHK; else @@ -176,7 +174,6 @@ int bnxt_set_vf_mac(struct net_device *d memcpy(vf->mac_addr, mac, ETH_ALEN); bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR); memcpy(req.dflt_mac_addr, mac, ETH_ALEN); return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -214,7 +211,6 @@ int bnxt_set_vf_vlan(struct net_device *

bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); req.dflt_vlan = cpu_to_le16(vlan_tag); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -253,7 +249,6 @@ int bnxt_set_vf_bw(struct net_device *de return 0; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_MAX_BW); req.max_bw = cpu_to_le32(max_tx_rate); req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MIN_BW);

From: Sabrina Dubroca sd@queasysnail.net

commit afe49de44c27a89e8e9631c44b5ffadf6ace65e2 upstream.

Commit 15e668070a64 ("ipv6: reorder icmpv6_init() and ip6_mr_init()") moved the cleanup label for ipmr_fail, but should have changed the contents of the cleanup labels as well. Now we can end up cleaning up icmpv6 even though it hasn't been initialized (jump to icmp_fail or ipmr_fail).

Simply undo things in the reverse order of their initialization.

Example of panic (triggered by faking a failure of icmpv6_init):

kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] PREEMPT SMP KASAN PTI [...] RIP: 0010:__list_del_entry_valid+0x79/0x160 [...] Call Trace: ? lock_release+0x8a0/0x8a0 unregister_pernet_operations+0xd4/0x560 ? ops_free_list+0x480/0x480 ? down_write+0x91/0x130 ? unregister_pernet_subsys+0x15/0x30 ? down_read+0x1b0/0x1b0 ? up_read+0x110/0x110 ? kmem_cache_create_usercopy+0x1b4/0x240 unregister_pernet_subsys+0x1d/0x30 icmpv6_cleanup+0x1d/0x30 inet6_init+0x1b5/0x23f

Fixes: 15e668070a64 ("ipv6: reorder icmpv6_init() and ip6_mr_init()") Signed-off-by: Sabrina Dubroca sd@queasysnail.net 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

--- net/ipv6/af_inet6.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1088,11 +1088,11 @@ netfilter_fail: igmp_fail: ndisc_cleanup(); ndisc_fail: - ip6_mr_cleanup(); + icmpv6_cleanup(); icmp_fail: - unregister_pernet_subsys(&inet6_net_ops); + ip6_mr_cleanup(); ipmr_fail: - icmpv6_cleanup(); + unregister_pernet_subsys(&inet6_net_ops); register_pernet_fail: sock_unregister(PF_INET6); rtnl_unregister_all(PF_INET6);

From: Hangbin Liu liuhangbin@gmail.com

commit f9094b7603c011d27db7ba109e69881c72fa611d upstream.

Stefano pointed that configure or show UDP_ZERO_CSUM6_RX/TX info doesn't make sense if we haven't enabled CONFIG_IPV6. Fix it by adding if IS_ENABLED(CONFIG_IPV6) check.

Fixes: abe492b4f50c ("geneve: UDP checksum configuration via netlink") Fixes: fd7eafd02121 ("geneve: fix fill_info when link down") Signed-off-by: Hangbin Liu liuhangbin@gmail.com Reviewed-by: Stefano Brivio sbrivio@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/geneve.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-)

--- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1369,21 +1369,33 @@ static int geneve_nl2info(struct nlattr }

if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX]) { +#if IS_ENABLED(CONFIG_IPV6) if (changelink) { attrtype = IFLA_GENEVE_UDP_ZERO_CSUM6_TX; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX])) info->key.tun_flags &= ~TUNNEL_CSUM; +#else + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX], + "IPv6 support not enabled in the kernel"); + return -EPFNOSUPPORT; +#endif }

if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX]) { +#if IS_ENABLED(CONFIG_IPV6) if (changelink) { attrtype = IFLA_GENEVE_UDP_ZERO_CSUM6_RX; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX])) *use_udp6_rx_checksums = false; +#else + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX], + "IPv6 support not enabled in the kernel"); + return -EPFNOSUPPORT; +#endif }

return 0; @@ -1559,11 +1571,13 @@ static int geneve_fill_info(struct sk_bu goto nla_put_failure;

if (metadata && nla_put_flag(skb, IFLA_GENEVE_COLLECT_METADATA)) - goto nla_put_failure; + goto nla_put_failure;

+#if IS_ENABLED(CONFIG_IPV6) if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_RX, !geneve->use_udp6_rx_checksums)) goto nla_put_failure; +#endif

return 0;

From: Oliver Neukum oneukum@suse.com

commit 9f04db234af691007bb785342a06abab5fb34474 upstream.

This device needs US_FL_NO_REPORT_OPCODES to avoid going through prolonged error handling on enumeration.

Signed-off-by: Oliver Neukum oneukum@suse.com Reported-by: Julian Groß julian.g@posteo.de Cc: stable stable@vger.kernel.org Link: https://lore.kernel.org/r/20200429155218.7308-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/storage/unusual_uas.h | 7 +++++++ 1 file changed, 7 insertions(+)

--- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -41,6 +41,13 @@ * and don't forget to CC: the USB development list linux-usb@vger.kernel.org */

+/* Reported-by: Julian Groß julian.g@posteo.de */ +UNUSUAL_DEV(0x059f, 0x105f, 0x0000, 0x9999, + "LaCie", + "2Big Quadra USB3", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_REPORT_OPCODES), + /* * Apricorn USB3 dongle sometimes returns "USBSUSBSUSBS" in response to SCSI * commands in UAS mode. Observed with the 1.28 firmware; are there others?

From: Steven Rostedt (VMware) rostedt@goodmis.org

commit 11f5efc3ab66284f7aaacc926e9351d658e2577b upstream.

x86_64 lazily maps in the vmalloc pages, and the way this works with per_cpu areas can be complex, to say the least. Mappings may happen at boot up, and if nothing synchronizes the page tables, those page mappings may not be synced till they are used. This causes issues for anything that might touch one of those mappings in the path of the page fault handler. When one of those unmapped mappings is touched in the page fault handler, it will cause another page fault, which in turn will cause a page fault, and leave us in a loop of page faults.

Commit 763802b53a42 ("x86/mm: split vmalloc_sync_all()") split vmalloc_sync_all() into vmalloc_sync_unmappings() and vmalloc_sync_mappings(), as on system exit, it did not need to do a full sync on x86_64 (although it still needed to be done on x86_32). By chance, the vmalloc_sync_all() would synchronize the page mappings done at boot up and prevent the per cpu area from being a problem for tracing in the page fault handler. But when that synchronization in the exit of a task became a nop, it caused the problem to appear.

Link: https://lore.kernel.org/r/20200429054857.66e8e333@oasis.local.home

Cc: stable@vger.kernel.org Fixes: 737223fbca3b1 ("tracing: Consolidate buffer allocation code") Reported-by: "Tzvetomir Stoyanov (VMware)" tz.stoyanov@gmail.com Suggested-by: Joerg Roedel jroedel@suse.de Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/trace/trace.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)

--- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7666,6 +7666,19 @@ static int allocate_trace_buffers(struct */ allocate_snapshot = false; #endif + + /* + * Because of some magic with the way alloc_percpu() works on + * x86_64, we need to synchronize the pgd of all the tables, + * otherwise the trace events that happen in x86_64 page fault + * handlers can't cope with accessing the chance that a + * alloc_percpu()'d memory might be touched in the page fault trace + * event. Oh, and we need to audit all other alloc_percpu() and vmalloc() + * calls in tracing, because something might get triggered within a + * page fault trace event! + */ + vmalloc_sync_mappings(); + return 0; }

From: David Hildenbrand david@redhat.com

commit e84fe99b68ce353c37ceeecc95dce9696c976556 upstream.

Without CONFIG_PREEMPT, it can happen that we get soft lockups detected, e.g., while booting up.

watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [swapper/0:1] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.6.0-next-20200331+ #4 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 RIP: __pageblock_pfn_to_page+0x134/0x1c0 Call Trace: set_zone_contiguous+0x56/0x70 page_alloc_init_late+0x166/0x176 kernel_init_freeable+0xfa/0x255 kernel_init+0xa/0x106 ret_from_fork+0x35/0x40

The issue becomes visible when having a lot of memory (e.g., 4TB) assigned to a single NUMA node - a system that can easily be created using QEMU. Inside VMs on a hypervisor with quite some memory overcommit, this is fairly easy to trigger.

Signed-off-by: David Hildenbrand david@redhat.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Reviewed-by: Pavel Tatashin pasha.tatashin@soleen.com Reviewed-by: Pankaj Gupta pankaj.gupta.linux@gmail.com Reviewed-by: Baoquan He bhe@redhat.com Reviewed-by: Shile Zhang shile.zhang@linux.alibaba.com Acked-by: Michal Hocko mhocko@suse.com Cc: Kirill Tkhai ktkhai@virtuozzo.com Cc: Shile Zhang shile.zhang@linux.alibaba.com Cc: Pavel Tatashin pasha.tatashin@soleen.com Cc: Daniel Jordan daniel.m.jordan@oracle.com Cc: Michal Hocko mhocko@kernel.org Cc: Alexander Duyck alexander.duyck@gmail.com Cc: Baoquan He bhe@redhat.com Cc: Oscar Salvador osalvador@suse.de Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20200416073417.5003-1-david@redhat.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- mm/page_alloc.c | 1 + 1 file changed, 1 insertion(+)

--- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1405,6 +1405,7 @@ void set_zone_contiguous(struct zone *zo if (!__pageblock_pfn_to_page(block_start_pfn, block_end_pfn, zone)) return; + cond_resched(); }

/* We confirm that there is no hole */

From: George Spelvin lkml@sdf.org

commit fd0c42c4dea54335967c5a86f15fc064235a2797 upstream.

and change to pseudorandom numbers, as this is a traffic dithering operation that doesn't need crypto-grade.

The previous code operated in 4 steps:

1. Generate a random byte 0 <= rand_tq <= 255 2. Multiply it by BATADV_TQ_MAX_VALUE - tq 3. Divide by 255 (= BATADV_TQ_MAX_VALUE) 4. Return BATADV_TQ_MAX_VALUE - rand_tq

This would apperar to scale (BATADV_TQ_MAX_VALUE - tq) by a random value between 0/255 and 255/255.

But! The intermediate value between steps 3 and 4 is stored in a u8 variable. So it's truncated, and most of the time, is less than 255, after which the division produces 0. Specifically, if tq is odd, the product is always even, and can never be 255. If tq is even, there's exactly one random byte value that will produce a product byte of 255.

Thus, the return value is 255 (511/512 of the time) or 254 (1/512 of the time).

If we assume that the truncation is a bug, and the code is meant to scale the input, a simpler way of looking at it is that it's returning a random value between tq and BATADV_TQ_MAX_VALUE, inclusive.

Well, we have an optimized function for doing just that.

Fixes: 3c12de9a5c75 ("batman-adv: network coding - code and transmit packets if possible") Signed-off-by: George Spelvin lkml@sdf.org Signed-off-by: Sven Eckelmann sven@narfation.org Signed-off-by: Simon Wunderlich sw@simonwunderlich.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/batman-adv/network-coding.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-)

--- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1017,15 +1017,8 @@ static struct batadv_nc_path *batadv_nc_ */ static u8 batadv_nc_random_weight_tq(u8 tq) { - u8 rand_val, rand_tq; - - get_random_bytes(&rand_val, sizeof(rand_val)); - /* randomize the estimated packet loss (max TQ - estimated TQ) */ - rand_tq = rand_val * (BATADV_TQ_MAX_VALUE - tq); - - /* normalize the randomized packet loss */ - rand_tq /= BATADV_TQ_MAX_VALUE; + u8 rand_tq = prandom_u32_max(BATADV_TQ_MAX_VALUE + 1 - tq);

/* convert to (randomized) estimated tq again */ return BATADV_TQ_MAX_VALUE - rand_tq;

From: Xiyu Yang xiyuyang19@fudan.edu.cn

commit 6107c5da0fca8b50b4d3215e94d619d38cc4a18c upstream.

batadv_show_throughput_override() invokes batadv_hardif_get_by_netdev(), which gets a batadv_hard_iface object from net_dev with increased refcnt and its reference is assigned to a local pointer 'hard_iface'.

When batadv_store_throughput_override() returns, "hard_iface" becomes invalid, so the refcount should be decreased to keep refcount balanced.

The issue happens in one error path of batadv_store_throughput_override(). When batadv_parse_throughput() returns NULL, the refcnt increased by batadv_hardif_get_by_netdev() is not decreased, causing a refcnt leak.

Fix this issue by jumping to "out" label when batadv_parse_throughput() returns NULL.

Fixes: 0b5ecc6811bd ("batman-adv: add throughput override attribute to hard_ifaces") Signed-off-by: Xiyu Yang xiyuyang19@fudan.edu.cn Signed-off-by: Xin Tan tanxin.ctf@gmail.com Signed-off-by: Sven Eckelmann sven@narfation.org Signed-off-by: Simon Wunderlich sw@simonwunderlich.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/batman-adv/sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1081,7 +1081,7 @@ static ssize_t batadv_store_throughput_o ret = batadv_parse_throughput(net_dev, buff, "throughput_override", &tp_override); if (!ret) - return count; + goto out;

old_tp_override = atomic_read(&hard_iface->bat_v.throughput_override); if (old_tp_override == tp_override)

From: Josh Poimboeuf jpoimboe@redhat.com

commit 1fb143634a38095b641a3a21220774799772dc4c upstream.

In swapgs_restore_regs_and_return_to_usermode, after the stack is switched to the trampoline stack, the existing UNWIND_HINT_REGS hint is no longer valid, which can result in the following ORC unwinder warning:

WARNING: can't dereference registers at 000000003aeb0cdd for ip swapgs_restore_regs_and_return_to_usermode+0x93/0xa0

For full correctness, we could try to add complicated unwind hints so the unwinder could continue to find the registers, but when when it's this close to kernel exit, unwind hints aren't really needed anymore and it's fine to just use an empty hint which tells the unwinder to stop.

For consistency, also move the UNWIND_HINT_EMPTY in entry_SYSCALL_64_after_hwframe to a similar location.

Fixes: 3e3b9293d392 ("x86/entry/64: Return to userspace from the trampoline stack") Reported-by: Vince Weaver vincent.weaver@maine.edu Reported-by: Dave Jones dsj@fb.com Reported-by: Dr. David Alan Gilbert dgilbert@redhat.com Reported-by: Joe Mario jmario@redhat.com Reported-by: Jann Horn jannh@google.com Reported-by: Linus Torvalds torvalds@linux-foundation.org Reviewed-by: Miroslav Benes mbenes@suse.cz Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Ingo Molnar mingo@kernel.org Cc: Andy Lutomirski luto@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Link: https://lore.kernel.org/r/60ea8f562987ed2d9ace2977502fe481c0d7c9a0.158780874... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/entry/entry_64.S | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -302,7 +302,6 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) */ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ - UNWIND_HINT_EMPTY POP_REGS pop_rdi=0 skip_r11rcx=1

/* @@ -311,6 +310,7 @@ syscall_return_via_sysret: */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY

pushq RSP-RDI(%rdi) /* RSP */ pushq (%rdi) /* RDI */ @@ -606,6 +606,7 @@ GLOBAL(swapgs_restore_regs_and_return_to */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY

/* Copy the IRET frame to the trampoline stack. */ pushq 6*8(%rdi) /* SS */

From: Miroslav Benes mbenes@suse.cz

commit f1d9a2abff66aa8156fbc1493abed468db63ea48 upstream.

When unwinding an inactive task, the ORC unwinder skips the first frame by default. If both the 'regs' and 'first_frame' parameters of unwind_start() are NULL, 'state->sp' and 'first_frame' are later initialized to the same value for an inactive task. Given there is a "less than or equal to" comparison used at the end of __unwind_start() for skipping stack frames, the first frame is skipped.

Drop the equal part of the comparison and make the behavior equivalent to the frame pointer unwinder.

Fixes: ee9f8fce9964 ("x86/unwind: Add the ORC unwinder") Reviewed-by: Miroslav Benes mbenes@suse.cz Signed-off-by: Miroslav Benes mbenes@suse.cz Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Ingo Molnar mingo@kernel.org Cc: Andy Lutomirski luto@kernel.org Cc: Dave Jones dsj@fb.com Cc: Jann Horn jannh@google.com Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Link: https://lore.kernel.org/r/7f08db872ab59e807016910acdbe82f744de7065.158780874... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kernel/unwind_orc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -574,7 +574,7 @@ void __unwind_start(struct unwind_state /* Otherwise, skip ahead to the user-specified starting frame: */ while (!unwind_done(state) && (!on_stack(&state->stack_info, first_frame, sizeof(long)) || - state->sp <= (unsigned long)first_frame)) + state->sp < (unsigned long)first_frame)) unwind_next_frame(state);

return;

From: Josh Poimboeuf jpoimboe@redhat.com

commit a0f81bf26888048100bf017fadf438a5bdffa8d8 upstream.

If the ORC entry type is unknown, nothing else can be done other than reporting an error. Exit the function instead of breaking out of the switch statement.

Fixes: ee9f8fce9964 ("x86/unwind: Add the ORC unwinder") Reviewed-by: Miroslav Benes mbenes@suse.cz Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Ingo Molnar mingo@kernel.org Cc: Andy Lutomirski luto@kernel.org Cc: Dave Jones dsj@fb.com Cc: Jann Horn jannh@google.com Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Link: https://lore.kernel.org/r/a7fa668ca6eabbe81ab18b2424f15adbbfdc810a.158780874... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kernel/unwind_orc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -457,7 +457,7 @@ bool unwind_next_frame(struct unwind_sta default: orc_warn("unknown .orc_unwind entry type %d for ip %pB\n", orc->type, (void *)orig_ip); - break; + goto done; }

/* Find BP: */

From: Josh Poimboeuf jpoimboe@redhat.com

commit d8dd25a461e4eec7190cb9d66616aceacc5110ad upstream.

When the current frame address (CFA) is stored on the stack (i.e., cfa->base == CFI_SP_INDIRECT), objtool neglects to adjust the stack offset when there are subsequent pushes or pops. This results in bad ORC data at the end of the ENTER_IRQ_STACK macro, when it puts the previous stack pointer on the stack and does a subsequent push.

This fixes the following unwinder warning:

WARNING: can't dereference registers at 00000000f0a6bdba for ip interrupt_entry+0x9f/0xa0

Fixes: 627fce14809b ("objtool: Add ORC unwind table generation") Reported-by: Vince Weaver vincent.weaver@maine.edu Reported-by: Dave Jones dsj@fb.com Reported-by: Steven Rostedt rostedt@goodmis.org Reported-by: Vegard Nossum vegard.nossum@oracle.com Reported-by: Joe Mario jmario@redhat.com Reviewed-by: Miroslav Benes mbenes@suse.cz Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Ingo Molnar mingo@kernel.org Cc: Andy Lutomirski luto@kernel.org Cc: Jann Horn jannh@google.com Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Link: https://lore.kernel.org/r/853d5d691b29e250333332f09b8e27410b2d9924.158780874... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- tools/objtool/check.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1291,7 +1291,7 @@ static int update_insn_state_regs(struct struct cfi_reg *cfa = &state->cfa; struct stack_op *op = &insn->stack_op;

- if (cfa->base != CFI_SP) + if (cfa->base != CFI_SP && cfa->base != CFI_SP_INDIRECT) return 0;

/* push */

From: Sabrina Dubroca sd@queasysnail.net

commit c4e85f73afb6384123e5ef1bba3315b2e3ad031e upstream.

This will be used in the conversion of ipv6_stub to ip6_dst_lookup_flow, as some modules currently pass a net argument without a socket to ip6_dst_lookup. This is equivalent to commit 343d60aada5a ("ipv6: change ipv6_stub_impl.ipv6_dst_lookup to take net argument").

Signed-off-by: Sabrina Dubroca sd@queasysnail.net Signed-off-by: David S. Miller davem@davemloft.net [bwh: Backported to 4.14: adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/ipv6.h | 2 +- net/dccp/ipv6.c | 6 +++--- net/ipv6/af_inet6.c | 2 +- net/ipv6/datagram.c | 2 +- net/ipv6/inet6_connection_sock.c | 4 ++-- net/ipv6/ip6_output.c | 8 ++++---- net/ipv6/raw.c | 2 +- net/ipv6/syncookies.c | 2 +- net/ipv6/tcp_ipv6.c | 4 ++-- net/l2tp/l2tp_ip6.c | 2 +- net/sctp/ipv6.c | 4 ++-- 11 files changed, 19 insertions(+), 19 deletions(-)

--- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -862,7 +862,7 @@ static inline struct sk_buff *ip6_finish

int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); -struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -211,7 +211,7 @@ static int dccp_v6_send_response(const s final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); rcu_read_unlock();

- dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; @@ -282,7 +282,7 @@ static void dccp_v6_ctl_send_reset(const security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6));

/* sk = NULL, but it is safe for now. RST socket required. */ - dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); + dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(skb, dst); ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0); @@ -912,7 +912,7 @@ static int dccp_v6_connect(struct sock * opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); final_p = fl6_update_dst(&fl6, opt, &final);

- dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -716,7 +716,7 @@ int inet6_sk_rebuild_header(struct sock &final); rcu_read_unlock();

- dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { sk->sk_route_caps = 0; sk->sk_err_soft = -PTR_ERR(dst); --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -88,7 +88,7 @@ int ip6_datagram_dst_update(struct sock final_p = fl6_update_dst(&fl6, opt, &final); rcu_read_unlock();

- dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -52,7 +52,7 @@ struct dst_entry *inet6_csk_route_req(co fl6->flowi6_uid = sk->sk_uid; security_req_classify_flow(req, flowi6_to_flowi(fl6));

- dst = ip6_dst_lookup_flow(sk, fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (IS_ERR(dst)) return NULL;

@@ -107,7 +107,7 @@ static struct dst_entry *inet6_csk_route

dst = __inet6_csk_dst_check(sk, np->dst_cookie); if (!dst) { - dst = ip6_dst_lookup_flow(sk, fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);

if (!IS_ERR(dst)) ip6_dst_store(sk, dst, NULL, NULL); --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1089,19 +1089,19 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup); * It returns a valid dst pointer on success, or a pointer encoded * error code. */ -struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst) { struct dst_entry *dst = NULL; int err;

- err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6); + err = ip6_dst_lookup_tail(net, sk, &dst, fl6); if (err) return ERR_PTR(err); if (final_dst) fl6->daddr = *final_dst;

- return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); + return xfrm_lookup_route(net, dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);

@@ -1126,7 +1126,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow

dst = ip6_sk_dst_check(sk, dst, fl6); if (!dst) - dst = ip6_dst_lookup_flow(sk, fl6, final_dst); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_dst);

return dst; } --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -929,7 +929,7 @@ static int rawv6_sendmsg(struct sock *sk

fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);

- dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -238,7 +238,7 @@ struct sock *cookie_v6_check(struct sock fl6.flowi6_uid = sk->sk_uid; security_req_classify_flow(req, flowi6_to_flowi(&fl6));

- dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) goto out_free; } --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -252,7 +252,7 @@ static int tcp_v6_connect(struct sock *s

security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));

- dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; @@ -865,7 +865,7 @@ static void tcp_v6_send_response(const s * Underlying function will use this to retrieve the network * namespace */ - dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); + dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass); --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -629,7 +629,7 @@ static int l2tp_ip6_sendmsg(struct sock

fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);

- dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -271,7 +271,7 @@ static void sctp_v6_get_dst(struct sctp_ final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); rcu_read_unlock();

- dst = ip6_dst_lookup_flow(sk, fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (!asoc || saddr) { t->dst = dst; memcpy(fl, &_fl, sizeof(_fl)); @@ -329,7 +329,7 @@ static void sctp_v6_get_dst(struct sctp_ fl6->saddr = laddr->a.v6.sin6_addr; fl6->fl6_sport = laddr->a.v6.sin6_port; final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); - bdst = ip6_dst_lookup_flow(sk, fl6, final_p); + bdst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);

if (IS_ERR(bdst)) continue;

From: Jens Axboe axboe@kernel.dk

commit 1f2cac107c591c24b60b115d6050adc213d10fc0 upstream.

sg.c calls into the blktrace functions without holding the proper queue mutex for doing setup, start/stop, or teardown.

Add internal unlocked variants, and export the ones that do the proper locking.

Fixes: 6da127ad0918 ("blktrace: Add blktrace ioctls to SCSI generic devices") Tested-by: Dmitry Vyukov dvyukov@google.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/blktrace.c | 58 +++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 48 insertions(+), 10 deletions(-)

--- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -352,7 +352,7 @@ static void blk_trace_cleanup(struct blk put_probe_ref(); }

-int blk_trace_remove(struct request_queue *q) +static int __blk_trace_remove(struct request_queue *q) { struct blk_trace *bt;

@@ -365,6 +365,17 @@ int blk_trace_remove(struct request_queu

return 0; } + +int blk_trace_remove(struct request_queue *q) +{ + int ret; + + mutex_lock(&q->blk_trace_mutex); + ret = __blk_trace_remove(q); + mutex_unlock(&q->blk_trace_mutex); + + return ret; +} EXPORT_SYMBOL_GPL(blk_trace_remove);

static ssize_t blk_dropped_read(struct file *filp, char __user *buffer, @@ -565,9 +576,8 @@ err: return ret; }

-int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, - struct block_device *bdev, - char __user *arg) +static int __blk_trace_setup(struct request_queue *q, char *name, dev_t dev, + struct block_device *bdev, char __user *arg) { struct blk_user_trace_setup buts; int ret; @@ -586,6 +596,19 @@ int blk_trace_setup(struct request_queue } return 0; } + +int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, + struct block_device *bdev, + char __user *arg) +{ + int ret; + + mutex_lock(&q->blk_trace_mutex); + ret = __blk_trace_setup(q, name, dev, bdev, arg); + mutex_unlock(&q->blk_trace_mutex); + + return ret; +} EXPORT_SYMBOL_GPL(blk_trace_setup);

#if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) @@ -622,7 +645,7 @@ static int compat_blk_trace_setup(struct } #endif

-int blk_trace_startstop(struct request_queue *q, int start) +static int __blk_trace_startstop(struct request_queue *q, int start) { int ret; struct blk_trace *bt = q->blk_trace; @@ -661,6 +684,17 @@ int blk_trace_startstop(struct request_q

return ret; } + +int blk_trace_startstop(struct request_queue *q, int start) +{ + int ret; + + mutex_lock(&q->blk_trace_mutex); + ret = __blk_trace_startstop(q, start); + mutex_unlock(&q->blk_trace_mutex); + + return ret; +} EXPORT_SYMBOL_GPL(blk_trace_startstop);

/* @@ -691,7 +725,7 @@ int blk_trace_ioctl(struct block_device switch (cmd) { case BLKTRACESETUP: bdevname(bdev, b); - ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); + ret = __blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); break; #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) case BLKTRACESETUP32: @@ -702,10 +736,10 @@ int blk_trace_ioctl(struct block_device case BLKTRACESTART: start = 1; case BLKTRACESTOP: - ret = blk_trace_startstop(q, start); + ret = __blk_trace_startstop(q, start); break; case BLKTRACETEARDOWN: - ret = blk_trace_remove(q); + ret = __blk_trace_remove(q); break; default: ret = -ENOTTY; @@ -723,10 +757,14 @@ int blk_trace_ioctl(struct block_device **/ void blk_trace_shutdown(struct request_queue *q) { + mutex_lock(&q->blk_trace_mutex); + if (q->blk_trace) { - blk_trace_startstop(q, 0); - blk_trace_remove(q); + __blk_trace_startstop(q, 0); + __blk_trace_remove(q); } + + mutex_unlock(&q->blk_trace_mutex); }

#ifdef CONFIG_BLK_CGROUP

From: Jan Kara jack@suse.cz

commit c780e86dd48ef6467a1146cf7d0fe1e05a635039 upstream.

KASAN is reporting that __blk_add_trace() has a use-after-free issue when accessing q->blk_trace. Indeed the switching of block tracing (and thus eventual freeing of q->blk_trace) is completely unsynchronized with the currently running tracing and thus it can happen that the blk_trace structure is being freed just while __blk_add_trace() works on it. Protect accesses to q->blk_trace by RCU during tracing and make sure we wait for the end of RCU grace period when shutting down tracing. Luckily that is rare enough event that we can afford that. Note that postponing the freeing of blk_trace to an RCU callback should better be avoided as it could have unexpected user visible side-effects as debugfs files would be still existing for a short while block tracing has been shut down.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=205711 CC: stable@vger.kernel.org Reviewed-by: Chaitanya Kulkarni chaitanya.kulkarni@wdc.com Reviewed-by: Ming Lei ming.lei@redhat.com Tested-by: Ming Lei ming.lei@redhat.com Reviewed-by: Bart Van Assche bvanassche@acm.org Reported-by: Tristan Madani tristmd@gmail.com Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Jens Axboe axboe@kernel.dk [bwh: Backported to 4.14: adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/blkdev.h | 2 include/linux/blktrace_api.h | 18 ++++-- kernel/trace/blktrace.c | 114 +++++++++++++++++++++++++++++++------------ 3 files changed, 97 insertions(+), 37 deletions(-)

--- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -568,7 +568,7 @@ struct request_queue { unsigned int sg_reserved_size; int node; #ifdef CONFIG_BLK_DEV_IO_TRACE - struct blk_trace *blk_trace; + struct blk_trace __rcu *blk_trace; struct mutex blk_trace_mutex; #endif /* --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -51,9 +51,13 @@ void __trace_note_message(struct blk_tra **/ #define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \ do { \ - struct blk_trace *bt = (q)->blk_trace; \ + struct blk_trace *bt; \ + \ + rcu_read_lock(); \ + bt = rcu_dereference((q)->blk_trace); \ if (unlikely(bt)) \ __trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\ + rcu_read_unlock(); \ } while (0) #define blk_add_trace_msg(q, fmt, ...) \ blk_add_cgroup_trace_msg(q, NULL, fmt, ##__VA_ARGS__) @@ -61,10 +65,14 @@ void __trace_note_message(struct blk_tra

static inline bool blk_trace_note_message_enabled(struct request_queue *q) { - struct blk_trace *bt = q->blk_trace; - if (likely(!bt)) - return false; - return bt->act_mask & BLK_TC_NOTIFY; + struct blk_trace *bt; + bool ret; + + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + ret = bt && (bt->act_mask & BLK_TC_NOTIFY); + rcu_read_unlock(); + return ret; }

extern void blk_add_driver_data(struct request_queue *q, struct request *rq, --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -348,6 +348,7 @@ static void put_probe_ref(void)

static void blk_trace_cleanup(struct blk_trace *bt) { + synchronize_rcu(); blk_trace_free(bt); put_probe_ref(); } @@ -648,8 +649,10 @@ static int compat_blk_trace_setup(struct static int __blk_trace_startstop(struct request_queue *q, int start) { int ret; - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt;

+ bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (bt == NULL) return -EINVAL;

@@ -758,8 +761,8 @@ int blk_trace_ioctl(struct block_device void blk_trace_shutdown(struct request_queue *q) { mutex_lock(&q->blk_trace_mutex); - - if (q->blk_trace) { + if (rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex))) { __blk_trace_startstop(q, 0); __blk_trace_remove(q); } @@ -771,8 +774,10 @@ void blk_trace_shutdown(struct request_q static union kernfs_node_id * blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt;

+ /* We don't use the 'bt' value here except as an optimization... */ + bt = rcu_dereference_protected(q->blk_trace, 1); if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return NULL;

@@ -817,10 +822,14 @@ static void blk_add_trace_rq(struct requ unsigned int nr_bytes, u32 what, union kernfs_node_id *cgid) { - struct blk_trace *bt = rq->q->blk_trace; + struct blk_trace *bt;

- if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(rq->q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + }

if (blk_rq_is_passthrough(rq)) what |= BLK_TC_ACT(BLK_TC_PC); @@ -829,6 +838,7 @@ static void blk_add_trace_rq(struct requ

__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq), rq->cmd_flags, what, error, 0, NULL, cgid); + rcu_read_unlock(); }

static void blk_add_trace_rq_insert(void *ignore, @@ -874,13 +884,18 @@ static void blk_add_trace_rq_complete(vo static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, u32 what, int error, union kernfs_node_id *cgid) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt;

- if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + }

__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, what, error, 0, NULL, cgid); + rcu_read_unlock(); }

static void blk_add_trace_bio_bounce(void *ignore, @@ -931,11 +946,14 @@ static void blk_add_trace_getrq(void *ig blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0, blk_trace_bio_get_cgid(q, bio)); else { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt;

+ rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0, NULL, NULL); + rcu_read_unlock(); } }

@@ -948,27 +966,35 @@ static void blk_add_trace_sleeprq(void * blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0, blk_trace_bio_get_cgid(q, bio)); else { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt;

+ rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ, 0, 0, NULL, NULL); + rcu_read_unlock(); } }

static void blk_add_trace_plug(void *ignore, struct request_queue *q) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt;

+ rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, NULL); + rcu_read_unlock(); }

static void blk_add_trace_unplug(void *ignore, struct request_queue *q, unsigned int depth, bool explicit) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt;

+ rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(depth); u32 what; @@ -980,14 +1006,17 @@ static void blk_add_trace_unplug(void *i

__blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, NULL); } + rcu_read_unlock(); }

static void blk_add_trace_split(void *ignore, struct request_queue *q, struct bio *bio, unsigned int pdu) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt;

+ rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(pdu);

@@ -996,6 +1025,7 @@ static void blk_add_trace_split(void *ig BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu), &rpdu, blk_trace_bio_get_cgid(q, bio)); } + rcu_read_unlock(); }

/** @@ -1015,11 +1045,15 @@ static void blk_add_trace_bio_remap(void struct request_queue *q, struct bio *bio, dev_t dev, sector_t from) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; struct blk_io_trace_remap r;

- if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + }

r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(bio_dev(bio)); @@ -1028,6 +1062,7 @@ static void blk_add_trace_bio_remap(void __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status, sizeof(r), &r, blk_trace_bio_get_cgid(q, bio)); + rcu_read_unlock(); }

/** @@ -1048,11 +1083,15 @@ static void blk_add_trace_rq_remap(void struct request *rq, dev_t dev, sector_t from) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; struct blk_io_trace_remap r;

- if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + }

r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(disk_devt(rq->rq_disk)); @@ -1061,6 +1100,7 @@ static void blk_add_trace_rq_remap(void __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rq_data_dir(rq), 0, BLK_TA_REMAP, 0, sizeof(r), &r, blk_trace_request_get_cgid(q, rq)); + rcu_read_unlock(); }

/** @@ -1078,14 +1118,19 @@ void blk_add_driver_data(struct request_ struct request *rq, void *data, size_t len) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt;

- if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + }

__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0, BLK_TA_DRV_DATA, 0, len, data, blk_trace_request_get_cgid(q, rq)); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blk_add_driver_data);

@@ -1612,6 +1657,7 @@ static int blk_trace_remove_queue(struct return -EINVAL;

put_probe_ref(); + synchronize_rcu(); blk_trace_free(bt); return 0; } @@ -1773,6 +1819,7 @@ static ssize_t sysfs_blk_trace_attr_show struct hd_struct *p = dev_to_part(dev); struct request_queue *q; struct block_device *bdev; + struct blk_trace *bt; ssize_t ret = -ENXIO;

bdev = bdget(part_devt(p)); @@ -1785,21 +1832,23 @@ static ssize_t sysfs_blk_trace_attr_show

mutex_lock(&q->blk_trace_mutex);

+ bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (attr == &dev_attr_enable) { - ret = sprintf(buf, "%u\n", !!q->blk_trace); + ret = sprintf(buf, "%u\n", !!bt); goto out_unlock_bdev; }

- if (q->blk_trace == NULL) + if (bt == NULL) ret = sprintf(buf, "disabled\n"); else if (attr == &dev_attr_act_mask) - ret = blk_trace_mask2str(buf, q->blk_trace->act_mask); + ret = blk_trace_mask2str(buf, bt->act_mask); else if (attr == &dev_attr_pid) - ret = sprintf(buf, "%u\n", q->blk_trace->pid); + ret = sprintf(buf, "%u\n", bt->pid); else if (attr == &dev_attr_start_lba) - ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba); + ret = sprintf(buf, "%llu\n", bt->start_lba); else if (attr == &dev_attr_end_lba) - ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); + ret = sprintf(buf, "%llu\n", bt->end_lba);

out_unlock_bdev: mutex_unlock(&q->blk_trace_mutex); @@ -1816,6 +1865,7 @@ static ssize_t sysfs_blk_trace_attr_stor struct block_device *bdev; struct request_queue *q; struct hd_struct *p; + struct blk_trace *bt; u64 value; ssize_t ret = -EINVAL;

@@ -1846,8 +1896,10 @@ static ssize_t sysfs_blk_trace_attr_stor

mutex_lock(&q->blk_trace_mutex);

+ bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (attr == &dev_attr_enable) { - if (!!value == !!q->blk_trace) { + if (!!value == !!bt) { ret = 0; goto out_unlock_bdev; } @@ -1859,18 +1911,18 @@ static ssize_t sysfs_blk_trace_attr_stor }

ret = 0; - if (q->blk_trace == NULL) + if (bt == NULL) ret = blk_trace_setup_queue(q, bdev);

if (ret == 0) { if (attr == &dev_attr_act_mask) - q->blk_trace->act_mask = value; + bt->act_mask = value; else if (attr == &dev_attr_pid) - q->blk_trace->pid = value; + bt->pid = value; else if (attr == &dev_attr_start_lba) - q->blk_trace->start_lba = value; + bt->start_lba = value; else if (attr == &dev_attr_end_lba) - q->blk_trace->end_lba = value; + bt->end_lba = value; }

out_unlock_bdev:

From: Chao Yu yuchao0@huawei.com

commit a5f433f7410530ae6bb907ebc049547d9dce665b upstream.

Commit ba38c27eb93e ("f2fs: enhance lookup xattr") introduces lookup_all_xattrs duplicating from read_all_xattrs, which leaves lots of similar codes in between them, so introduce new help read_inline_xattr to clean up redundant codes.

Signed-off-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/xattr.c | 59 +++++++++++++++++++++++++++----------------------------- 1 file changed, 29 insertions(+), 30 deletions(-)

--- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -241,6 +241,29 @@ static struct f2fs_xattr_entry *__find_i return entry; }

+static int read_inline_xattr(struct inode *inode, struct page *ipage, + void *txattr_addr) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + unsigned int inline_size = inline_xattr_size(inode); + struct page *page = NULL; + void *inline_addr; + + if (ipage) { + inline_addr = inline_xattr_addr(ipage); + } else { + page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(page)) + return PTR_ERR(page); + + inline_addr = inline_xattr_addr(page); + } + memcpy(txattr_addr, inline_addr, inline_size); + f2fs_put_page(page, 1); + + return 0; +} + static int lookup_all_xattrs(struct inode *inode, struct page *ipage, unsigned int index, unsigned int len, const char *name, struct f2fs_xattr_entry **xe, @@ -263,21 +286,9 @@ static int lookup_all_xattrs(struct inod

/* read from inline xattr */ if (inline_size) { - struct page *page = NULL; - void *inline_addr; - - if (ipage) { - inline_addr = inline_xattr_addr(ipage); - } else { - page = get_node_page(sbi, inode->i_ino); - if (IS_ERR(page)) { - err = PTR_ERR(page); - goto out; - } - inline_addr = inline_xattr_addr(page); - } - memcpy(txattr_addr, inline_addr, inline_size); - f2fs_put_page(page, 1); + err = read_inline_xattr(inode, ipage, txattr_addr); + if (err) + goto out;

*xe = __find_inline_xattr(txattr_addr, &last_addr, index, len, name); @@ -339,21 +350,9 @@ static int read_all_xattrs(struct inode

/* read from inline xattr */ if (inline_size) { - struct page *page = NULL; - void *inline_addr; - - if (ipage) { - inline_addr = inline_xattr_addr(ipage); - } else { - page = get_node_page(sbi, inode->i_ino); - if (IS_ERR(page)) { - err = PTR_ERR(page); - goto fail; - } - inline_addr = inline_xattr_addr(page); - } - memcpy(txattr_addr, inline_addr, inline_size); - f2fs_put_page(page, 1); + err = read_inline_xattr(inode, ipage, txattr_addr); + if (err) + goto fail; }

/* read from xattr node block */

From: Jaegeuk Kim jaegeuk@kernel.org

commit 64beba0558fce7b59e9a8a7afd77290e82a22163 upstream.

There is a security report where f2fs_getxattr() has a hole to expose wrong memory region when the image is malformed like this.

f2fs_getxattr: entry->e_name_len: 4, size: 12288, buffer_size: 16384, len: 4

Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org [bwh: Backported to 4.14: Keep using kzalloc()] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/xattr.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-)

--- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -287,7 +287,7 @@ static int read_xattr_block(struct inode static int lookup_all_xattrs(struct inode *inode, struct page *ipage, unsigned int index, unsigned int len, const char *name, struct f2fs_xattr_entry **xe, - void **base_addr) + void **base_addr, int *base_size) { void *cur_addr, *txattr_addr, *last_addr = NULL; nid_t xnid = F2FS_I(inode)->i_xattr_nid; @@ -298,8 +298,8 @@ static int lookup_all_xattrs(struct inod if (!size && !inline_size) return -ENODATA;

- txattr_addr = kzalloc(inline_size + size + XATTR_PADDING_SIZE, - GFP_F2FS_ZERO); + *base_size = inline_size + size + XATTR_PADDING_SIZE; + txattr_addr = kzalloc(*base_size, GFP_F2FS_ZERO); if (!txattr_addr) return -ENOMEM;

@@ -311,8 +311,10 @@ static int lookup_all_xattrs(struct inod

*xe = __find_inline_xattr(txattr_addr, &last_addr, index, len, name); - if (*xe) + if (*xe) { + *base_size = inline_size; goto check; + } }

/* read from xattr node block */ @@ -462,6 +464,7 @@ int f2fs_getxattr(struct inode *inode, i int error = 0; unsigned int size, len; void *base_addr = NULL; + int base_size;

if (name == NULL) return -EINVAL; @@ -472,7 +475,7 @@ int f2fs_getxattr(struct inode *inode, i

down_read(&F2FS_I(inode)->i_xattr_sem); error = lookup_all_xattrs(inode, ipage, index, len, name, - &entry, &base_addr); + &entry, &base_addr, &base_size); up_read(&F2FS_I(inode)->i_xattr_sem); if (error) return error; @@ -486,6 +489,11 @@ int f2fs_getxattr(struct inode *inode, i

if (buffer) { char *pval = entry->e_name + entry->e_name_len; + + if (base_size - (pval - (char *)base_addr) < size) { + error = -ERANGE; + goto out; + } memcpy(buffer, pval, size); } error = size;

From: Randall Huang huangrandall@google.com

commit 688078e7f36c293dae25b338ddc9e0a2790f6e06 upstream.

In f2fs_listxattr, there is no boundary check before memcpy e_name to buffer. If the e_name_len is corrupted, unexpected memory contents may be returned to the buffer.

Signed-off-by: Randall Huang huangrandall@google.com Reviewed-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org [bwh: Backported to 4.14: Use f2fs_msg() instead of f2fs_err()] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/xattr.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-)

--- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -516,8 +516,9 @@ out: ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { struct inode *inode = d_inode(dentry); + nid_t xnid = F2FS_I(inode)->i_xattr_nid; struct f2fs_xattr_entry *entry; - void *base_addr; + void *base_addr, *last_base_addr; int error = 0; size_t rest = buffer_size;

@@ -527,6 +528,8 @@ ssize_t f2fs_listxattr(struct dentry *de if (error) return error;

+ last_base_addr = (void *)base_addr + XATTR_SIZE(xnid, inode); + list_for_each_xattr(entry, base_addr) { const struct xattr_handler *handler = f2fs_xattr_handler(entry->e_name_index); @@ -534,6 +537,16 @@ ssize_t f2fs_listxattr(struct dentry *de size_t prefix_len; size_t size;

+ if ((void *)(entry) + sizeof(__u32) > last_base_addr || + (void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) { + f2fs_msg(dentry->d_sb, KERN_ERR, + "inode (%lu) has corrupted xattr", + inode->i_ino); + set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK); + error = -EFSCORRUPTED; + goto cleanup; + } + if (!handler || (handler->list && !handler->list(dentry))) continue;

From: Hugh Dickins hughd@google.com

[ Upstream commit ea0dfeb4209b4eab954d6e00ed136bc6b48b380d ]

Recent commit 71725ed10c40 ("mm: huge tmpfs: try to split_huge_page() when punching hole") has allowed syzkaller to probe deeper, uncovering a long-standing lockdep issue between the irq-unsafe shmlock_user_lock, the irq-safe xa_lock on mapping->i_pages, and shmem inode's info->lock which nests inside xa_lock (or tree_lock) since 4.8's shmem_uncharge().

user_shm_lock(), servicing SysV shmctl(SHM_LOCK), wants shmlock_user_lock while its caller shmem_lock() holds info->lock with interrupts disabled; but hugetlbfs_file_setup() calls user_shm_lock() with interrupts enabled, and might be interrupted by a writeback endio wanting xa_lock on i_pages.

This may not risk an actual deadlock, since shmem inodes do not take part in writeback accounting, but there are several easy ways to avoid it.

Requiring interrupts disabled for shmlock_user_lock would be easy, but it's a high-level global lock for which that seems inappropriate. Instead, recall that the use of info->lock to guard info->flags in shmem_lock() dates from pre-3.1 days, when races with SHMEM_PAGEIN and SHMEM_TRUNCATE could occur: nowadays it serves no purpose, the only flag added or removed is VM_LOCKED itself, and calls to shmem_lock() an inode are already serialized by the caller.

Take info->lock out of the chain and the possibility of deadlock or lockdep warning goes away.

Fixes: 4595ef88d136 ("shmem: make shmem_inode_info::lock irq-safe") Reported-by: syzbot+c8a8197c8852f566b9d9@syzkaller.appspotmail.com Reported-by: syzbot+40b71e145e73f78f81ad@syzkaller.appspotmail.com Signed-off-by: Hugh Dickins hughd@google.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Acked-by: Yang Shi yang.shi@linux.alibaba.com Cc: Yang Shi yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/alpine.LSU.2.11.2004161707410.16322@eggly.anvils Link: https://lore.kernel.org/lkml/000000000000e5838c05a3152f53@google.com/ Link: https://lore.kernel.org/lkml/0000000000003712b305a331d3b1@google.com/ Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- mm/shmem.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c index f9a1e0ba259f3..24005c3b345ca 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2129,7 +2129,11 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) struct shmem_inode_info *info = SHMEM_I(inode); int retval = -ENOMEM;

- spin_lock_irq(&info->lock); + /* + * What serializes the accesses to info->flags? + * ipc_lock_object() when called from shmctl_do_lock(), + * no serialization needed when called from shm_destroy(). + */ if (lock && !(info->flags & VM_LOCKED)) { if (!user_shm_lock(inode->i_size, user)) goto out_nomem; @@ -2144,7 +2148,6 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) retval = 0;

out_nomem: - spin_unlock_irq(&info->lock); return retval; }

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit ee8d2267f0e39a1bfd95532da3a6405004114b27 ]

Should an irq requested with 'devm_request_irq' be released explicitly, it should be done by 'devm_free_irq()', not 'free_irq()'.

Fixes: 6c821bd9edc9 ("net: Add MOXA ART SoCs ethernet driver") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/moxa/moxart_ether.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index 2e4effa9fe456..beb730ff5d421 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -561,7 +561,7 @@ static int moxart_remove(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev);

unregister_netdev(ndev); - free_irq(ndev->irq, ndev); + devm_free_irq(&pdev->dev, ndev->irq, ndev); moxart_mac_free_memory(ndev); free_netdev(ndev);

From: Stefan Hajnoczi stefanha@redhat.com

[ Upstream commit 90b5feb8c4bebc76c27fcaf3e1a0e5ca2d319e9e ]

A userspace process holding a file descriptor to a virtio_blk device can still invoke block_device_operations after hot unplug. This leads to a use-after-free accessing vblk->vdev in virtblk_getgeo() when ioctl(HDIO_GETGEO) is invoked:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000090 IP: [<ffffffffc00e5450>] virtio_check_driver_offered_feature+0x10/0x90 [virtio] PGD 800000003a92f067 PUD 3a930067 PMD 0 Oops: 0000 [#1] SMP CPU: 0 PID: 1310 Comm: hdio-getgeo Tainted: G OE ------------ 3.10.0-1062.el7.x86_64 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 task: ffff9be5fbfb8000 ti: ffff9be5fa890000 task.ti: ffff9be5fa890000 RIP: 0010:[<ffffffffc00e5450>] [<ffffffffc00e5450>] virtio_check_driver_offered_feature+0x10/0x90 [virtio] RSP: 0018:ffff9be5fa893dc8 EFLAGS: 00010246 RAX: ffff9be5fc3f3400 RBX: ffff9be5fa893e30 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000004 RDI: ffff9be5fbc10b40 RBP: ffff9be5fa893dc8 R08: 0000000000000301 R09: 0000000000000301 R10: 0000000000000000 R11: 0000000000000000 R12: ffff9be5fdc24680 R13: ffff9be5fbc10b40 R14: ffff9be5fbc10480 R15: 0000000000000000 FS: 00007f1bfb968740(0000) GS:ffff9be5ffc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000090 CR3: 000000003a894000 CR4: 0000000000360ff0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: [<ffffffffc016ac37>] virtblk_getgeo+0x47/0x110 [virtio_blk] [<ffffffff8d3f200d>] ? handle_mm_fault+0x39d/0x9b0 [<ffffffff8d561265>] blkdev_ioctl+0x1f5/0xa20 [<ffffffff8d488771>] block_ioctl+0x41/0x50 [<ffffffff8d45d9e0>] do_vfs_ioctl+0x3a0/0x5a0 [<ffffffff8d45dc81>] SyS_ioctl+0xa1/0xc0

A related problem is that virtblk_remove() leaks the vd_index_ida index when something still holds a reference to vblk->disk during hot unplug. This causes virtio-blk device names to be lost (vda, vdb, etc).

Fix these issues by protecting vblk->vdev with a mutex and reference counting vblk so the vd_index_ida index can be removed in all cases.

Fixes: 48e4043d4529 ("virtio: add virtio disk geometry feature") Reported-by: Lance Digby ldigby@redhat.com Signed-off-by: Stefan Hajnoczi stefanha@redhat.com Link: https://lore.kernel.org/r/20200430140442.171016-1-stefanha@redhat.com Signed-off-by: Michael S. Tsirkin mst@redhat.com Reviewed-by: Stefano Garzarella sgarzare@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/block/virtio_blk.c | 86 ++++++++++++++++++++++++++++++++++---- 1 file changed, 78 insertions(+), 8 deletions(-)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 19d226ff15ef8..0e18eed62c575 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -31,6 +31,15 @@ struct virtio_blk_vq { } ____cacheline_aligned_in_smp;

struct virtio_blk { + /* + * This mutex must be held by anything that may run after + * virtblk_remove() sets vblk->vdev to NULL. + * + * blk-mq, virtqueue processing, and sysfs attribute code paths are + * shut down before vblk->vdev is set to NULL and therefore do not need + * to hold this mutex. + */ + struct mutex vdev_mutex; struct virtio_device *vdev;

/* The disk structure for the kernel. */ @@ -42,6 +51,13 @@ struct virtio_blk { /* Process context for config space updates */ struct work_struct config_work;

+ /* + * Tracks references from block_device_operations open/release and + * virtio_driver probe/remove so this object can be freed once no + * longer in use. + */ + refcount_t refs; + /* What host tells us, plus 2 for header & tailer. */ unsigned int sg_elems;

@@ -315,10 +331,55 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str) return err; }

+static void virtblk_get(struct virtio_blk *vblk) +{ + refcount_inc(&vblk->refs); +} + +static void virtblk_put(struct virtio_blk *vblk) +{ + if (refcount_dec_and_test(&vblk->refs)) { + ida_simple_remove(&vd_index_ida, vblk->index); + mutex_destroy(&vblk->vdev_mutex); + kfree(vblk); + } +} + +static int virtblk_open(struct block_device *bd, fmode_t mode) +{ + struct virtio_blk *vblk = bd->bd_disk->private_data; + int ret = 0; + + mutex_lock(&vblk->vdev_mutex); + + if (vblk->vdev) + virtblk_get(vblk); + else + ret = -ENXIO; + + mutex_unlock(&vblk->vdev_mutex); + return ret; +} + +static void virtblk_release(struct gendisk *disk, fmode_t mode) +{ + struct virtio_blk *vblk = disk->private_data; + + virtblk_put(vblk); +} + /* We provide getgeo only to please some old bootloader/partitioning tools */ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo) { struct virtio_blk *vblk = bd->bd_disk->private_data; + int ret = 0; + + mutex_lock(&vblk->vdev_mutex); + + if (!vblk->vdev) { + ret = -ENXIO; + goto out; + }

/* see if the host passed in geometry config */ if (virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_GEOMETRY)) { @@ -334,12 +395,16 @@ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo) geo->sectors = 1 << 5; geo->cylinders = get_capacity(bd->bd_disk) >> 11; } - return 0; +out: + mutex_unlock(&vblk->vdev_mutex); + return ret; }

static const struct block_device_operations virtblk_fops = { .ioctl = virtblk_ioctl, .owner = THIS_MODULE, + .open = virtblk_open, + .release = virtblk_release, .getgeo = virtblk_getgeo, };

@@ -659,6 +724,10 @@ static int virtblk_probe(struct virtio_device *vdev) goto out_free_index; }

+ /* This reference is dropped in virtblk_remove(). */ + refcount_set(&vblk->refs, 1); + mutex_init(&vblk->vdev_mutex); + vblk->vdev = vdev; vblk->sg_elems = sg_elems;

@@ -821,8 +890,6 @@ static int virtblk_probe(struct virtio_device *vdev) static void virtblk_remove(struct virtio_device *vdev) { struct virtio_blk *vblk = vdev->priv; - int index = vblk->index; - int refc;

/* Make sure no work handler is accessing the device. */ flush_work(&vblk->config_work); @@ -832,18 +899,21 @@ static void virtblk_remove(struct virtio_device *vdev)

blk_mq_free_tag_set(&vblk->tag_set);

+ mutex_lock(&vblk->vdev_mutex); + /* Stop all the virtqueues. */ vdev->config->reset(vdev);

- refc = kref_read(&disk_to_dev(vblk->disk)->kobj.kref); + /* Virtqueues are stopped, nothing can use vblk->vdev anymore. */ + vblk->vdev = NULL; + put_disk(vblk->disk); vdev->config->del_vqs(vdev); kfree(vblk->vqs); - kfree(vblk);

- /* Only free device id if we don't have any users */ - if (refc == 1) - ida_simple_remove(&vd_index_ida, index); + mutex_unlock(&vblk->vdev_mutex); + + virtblk_put(vblk); }

#ifdef CONFIG_PM_SLEEP

From: Madhuparna Bhowmik madhuparnabhowmik10@gmail.com

[ Upstream commit 2e45676a4d33af47259fa186ea039122ce263ba9 ]

pd->dma.dev is read in irq handler pd_irq(). However, it is set to pdev->dev after request_irq(). Therefore, set pd->dma.dev to pdev->dev before request_irq() to avoid data race between pch_dma_probe() and pd_irq().

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Madhuparna Bhowmik madhuparnabhowmik10@gmail.com Link: https://lore.kernel.org/r/20200416062335.29223-1-madhuparnabhowmik10@gmail.c... Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/pch_dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c index f9028e9d0dfc2..d6af2d439b979 100644 --- a/drivers/dma/pch_dma.c +++ b/drivers/dma/pch_dma.c @@ -873,6 +873,7 @@ static int pch_dma_probe(struct pci_dev *pdev, }

pci_set_master(pdev); + pd->dma.dev = &pdev->dev;

err = request_irq(pdev->irq, pd_irq, IRQF_SHARED, DRV_NAME, pd); if (err) { @@ -888,7 +889,6 @@ static int pch_dma_probe(struct pci_dev *pdev, goto err_free_irq; }

- pd->dma.dev = &pdev->dev;

INIT_LIST_HEAD(&pd->dma.channels);

From: Chris Wilson chris@chris-wilson.co.uk

[ Upstream commit 8c539776ac83c0857395e1ccc9c6b516521a2d32 ]

Make a note of the first time we discover the turbo mode has been disabled by the BIOS, as otherwise we complain every time we try to update the mode.

Signed-off-by: Chris Wilson chris@chris-wilson.co.uk Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/cpufreq/intel_pstate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 7a5662425b291..1aa0b05c8cbdf 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -935,7 +935,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b,

update_turbo_state(); if (global.turbo_disabled) { - pr_warn("Turbo disabled by BIOS or unavailable on processor\n"); + pr_notice_once("Turbo disabled by BIOS or unavailable on processor\n"); mutex_unlock(&intel_pstate_limits_lock); mutex_unlock(&intel_pstate_driver_lock); return -EPERM;

From: Vasily Averin vvs@virtuozzo.com

[ Upstream commit 5b5703dbafae74adfbe298a56a81694172caf5e6 ]

v2: removed TODO reminder

Signed-off-by: Vasily Averin vvs@virtuozzo.com Link: http://patchwork.freedesktop.org/patch/msgid/a4e0ae09-a73c-1c62-04ef-3f990d4... Signed-off-by: Gerd Hoffmann kraxel@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/qxl/qxl_image.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/qxl/qxl_image.c b/drivers/gpu/drm/qxl/qxl_image.c index 7fbcc35e8ad35..c89c10055641e 100644 --- a/drivers/gpu/drm/qxl/qxl_image.c +++ b/drivers/gpu/drm/qxl/qxl_image.c @@ -210,7 +210,8 @@ qxl_image_init_helper(struct qxl_device *qdev, break; default: DRM_ERROR("unsupported image bit depth\n"); - return -EINVAL; /* TODO: cleanup */ + qxl_bo_kunmap_atomic_page(qdev, image_bo, ptr); + return -EINVAL; } image->u.bitmap.flags = QXL_BITMAP_TOP_DOWN; image->u.bitmap.x = width;

From: Kai-Heng Feng kai.heng.feng@canonical.com

[ Upstream commit 52e4e36807aeac1cdd07b14e509c8a64101e1a09 ]

Commit 317d9313925c ("ALSA: hda/realtek - Set default power save node to 0") makes the ALC225 have pop noise on S3 resume and cold boot.

The previous fix enable power save node universally for ALC225, however it makes some ALC225 systems unable to produce any sound.

So let's only enable power save node for the affected Dell Wyse platform.

Fixes: 317d9313925c ("ALSA: hda/realtek - Set default power save node to 0") BugLink: https://bugs.launchpad.net/bugs/1866357 Signed-off-by: Kai-Heng Feng kai.heng.feng@canonical.com Link: https://lore.kernel.org/r/20200503152449.22761-2-kai.heng.feng@canonical.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/pci/hda/patch_realtek.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index b2aec97414fb8..d578f6594223f 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5354,6 +5354,15 @@ static void alc233_alc662_fixup_lenovo_dual_codecs(struct hda_codec *codec, } }

+static void alc225_fixup_s3_pop_noise(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action != HDA_FIXUP_ACT_PRE_PROBE) + return; + + codec->power_save_node = 1; +} + /* Forcibly assign NID 0x03 to HP/LO while NID 0x02 to SPK for EQ */ static void alc274_fixup_bind_dacs(struct hda_codec *codec, const struct hda_fixup *fix, int action) @@ -5507,6 +5516,7 @@ enum { ALC233_FIXUP_LENOVO_MULTI_CODECS, ALC294_FIXUP_LENOVO_MIC_LOCATION, ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE, + ALC225_FIXUP_S3_POP_NOISE, ALC700_FIXUP_INTEL_REFERENCE, ALC274_FIXUP_DELL_BIND_DACS, ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, @@ -6339,6 +6349,12 @@ static const struct hda_fixup alc269_fixups[] = { { } }, .chained = true, + .chain_id = ALC225_FIXUP_S3_POP_NOISE + }, + [ALC225_FIXUP_S3_POP_NOISE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc225_fixup_s3_pop_noise, + .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC }, [ALC700_FIXUP_INTEL_REFERENCE] = {

From: Gustavo A. R. Silva gustavo@embeddedor.com

[ Upstream commit a8627cda7cfffe1792c199660c2b4f03ba2bd97b ]

There is a potential execution path in which function ssif_info_find() returns NULL, hence there is a NULL pointer dereference when accessing pointer *addr_info*

Fix this by null checking *addr_info* before dereferencing it.

Addresses-Coverity-ID: 1473145 ("Explicit null dereferenced") Fixes: e333054a91d1 ("ipmi: Fix I2C client removal in the SSIF driver") Signed-off-by: Gustavo A. R. Silva gustavo@embeddedor.com Signed-off-by: Corey Minyard cminyard@mvista.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/char/ipmi/ipmi_ssif.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 0146bc3252c5a..cf87bfe971e6b 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -1731,7 +1731,9 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id)

out: if (rv) { - addr_info->client = NULL; + if (addr_info) + addr_info->client = NULL; + dev_err(&client->dev, "Unable to start IPMI SSIF: %d\n", rv); kfree(ssif_info); }

From: Grace Kao grace.kao@intel.com

[ Upstream commit 69388e15f5078c961b9e5319e22baea4c57deff1 ]

According to Braswell NDA Specification Update (#557593), concurrent read accesses may result in returning 0xffffffff and write instructions may be dropped. We have an established format for the commit references, i.e. cdca06e4e859 ("pinctrl: baytrail: Add missing spinlock usage in byt_gpio_irq_handler")

Fixes: 0bd50d719b00 ("pinctrl: cherryview: prevent concurrent access to GPIO controllers") Signed-off-by: Grace Kao grace.kao@intel.com Reported-by: Brian Norris briannorris@chromium.org Reviewed-by: Brian Norris briannorris@chromium.org Acked-by: Mika Westerberg mika.westerberg@linux.intel.com Signed-off-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pinctrl/intel/pinctrl-cherryview.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 0907531a02caa..d39718b4242d9 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1514,11 +1514,15 @@ static void chv_gpio_irq_handler(struct irq_desc *desc) struct chv_pinctrl *pctrl = gpiochip_get_data(gc); struct irq_chip *chip = irq_desc_get_chip(desc); unsigned long pending; + unsigned long flags; u32 intr_line;

chained_irq_enter(chip, desc);

+ raw_spin_lock_irqsave(&chv_lock, flags); pending = readl(pctrl->regs + CHV_INTSTAT); + raw_spin_unlock_irqrestore(&chv_lock, flags); + for_each_set_bit(intr_line, &pending, pctrl->community->nirqs) { unsigned irq, offset;

From: Arnd Bergmann arnd@arndb.de

[ Upstream commit 2c407aca64977ede9b9f35158e919773cae2082f ]

gcc-10 warns around a suspicious access to an empty struct member:

net/netfilter/nf_conntrack_core.c: In function '__nf_conntrack_alloc': net/netfilter/nf_conntrack_core.c:1522:9: warning: array subscript 0 is outside the bounds of an interior zero-length array 'u8[0]' {aka 'unsigned char[0]'} [-Wzero-length-bounds] 1522 | memset(&ct->__nfct_init_offset[0], 0, | ^~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from net/netfilter/nf_conntrack_core.c:37: include/net/netfilter/nf_conntrack.h:90:5: note: while referencing '__nfct_init_offset' 90 | u8 __nfct_init_offset[0]; | ^~~~~~~~~~~~~~~~~~

The code is correct but a bit unusual. Rework it slightly in a way that does not trigger the warning, using an empty struct instead of an empty array. There are probably more elegant ways to do this, but this is the smallest change.

Fixes: c41884ce0562 ("netfilter: conntrack: avoid zeroing timer") Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/netfilter/nf_conntrack.h | 2 +- net/netfilter/nf_conntrack_core.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 93bbae8f96414..b6dbc80b6ed15 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -80,7 +80,7 @@ struct nf_conn { struct hlist_node nat_bysource; #endif /* all members below initialized via memset */ - u8 __nfct_init_offset[0]; + struct { } __nfct_init_offset;

/* If we were expected by an expectation, this will be it */ struct nf_conn *master; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index a79f5a89cab14..8064d769c953c 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1208,9 +1208,9 @@ __nf_conntrack_alloc(struct net *net, *(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash; ct->status = 0; write_pnet(&ct->ct_net, net); - memset(&ct->__nfct_init_offset[0], 0, + memset(&ct->__nfct_init_offset, 0, offsetof(struct nf_conn, proto) - - offsetof(struct nf_conn, __nfct_init_offset[0])); + offsetof(struct nf_conn, __nfct_init_offset));

nf_ct_zone_add(ct, zone);

From: Samu Nuutamo samu.nuutamo@vincit.fi

[ Upstream commit 333e22db228f0bd0c839553015a6a8d3db4ba569 ]

When tsi-as-adc is configured it is possible for in7[0123]_input read to return an incorrect value if a concurrent read to in[456]_input is performed. This is caused by a concurrent manipulation of the mux channel without proper locking as hwmon and mfd use different locks for synchronization.

Switch hwmon to use the same lock as mfd when accessing the TSI channel.

Fixes: 4f16cab19a3d5 ("hwmon: da9052: Add support for TSI channel") Signed-off-by: Samu Nuutamo samu.nuutamo@vincit.fi [rebase to current master, reword commit message slightly] Signed-off-by: Sebastian Reichel sebastian.reichel@collabora.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/da9052-hwmon.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c index a973eb6a28908..9e44d2385e6f9 100644 --- a/drivers/hwmon/da9052-hwmon.c +++ b/drivers/hwmon/da9052-hwmon.c @@ -250,9 +250,9 @@ static ssize_t da9052_read_tsi(struct device *dev, int channel = to_sensor_dev_attr(devattr)->index; int ret;

- mutex_lock(&hwmon->hwmon_lock); + mutex_lock(&hwmon->da9052->auxadc_lock); ret = __da9052_read_tsi(dev, channel); - mutex_unlock(&hwmon->hwmon_lock); + mutex_unlock(&hwmon->da9052->auxadc_lock);

if (ret < 0) return ret;

From: Linus Torvalds torvalds@linux-foundation.org

commit 9d82973e032e246ff5663c9805fbb5407ae932e3 upstream.

Due to a bug-report that was compiler-dependent, I updated one of my machines to gcc-10. That shows a lot of new warnings. Happily they seem to be mostly the valid kind, but it's going to cause a round of churn for getting rid of them..

This is the really low-hanging fruit of removing a couple of zero-sized arrays in some core code. We have had a round of these patches before, and we'll have many more coming, and there is nothing special about these except that they were particularly trivial, and triggered more warnings than most.

Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/linux/fs.h | 2 +- include/linux/tty.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

--- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -900,7 +900,7 @@ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ - unsigned char f_handle[0]; + unsigned char f_handle[]; };

static inline struct file *get_file(struct file *f) --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -65,7 +65,7 @@ struct tty_buffer { int read; int flags; /* Data points here */ - unsigned long data[0]; + unsigned long data[]; };

/* Values for .flags field of tty_buffer */

From: Linus Torvalds torvalds@linux-foundation.org

commit 78a5255ffb6a1af189a83e493d916ba1c54d8c75 upstream.

We have some rather random rules about when we accept the "maybe-initialized" warnings, and when we don't.

For example, we consider it unreliable for gcc versions < 4.9, but also if -O3 is enabled, or if optimizing for size. And then various kernel config options disabled it, because they know that they trigger that warning by confusing gcc sufficiently (ie PROFILE_ALL_BRANCHES).

And now gcc-10 seems to be introducing a lot of those warnings too, so it falls under the same heading as 4.9 did.

At the same time, we have a very straightforward way to _enable_ that warning when wanted: use "W=2" to enable more warnings.

So stop playing these ad-hoc games, and just disable that warning by default, with the known and straight-forward "if you want to work on the extra compiler warnings, use W=123".

Would it be great to have code that is always so obvious that it never confuses the compiler whether a variable is used initialized or not? Yes, it would. In a perfect world, the compilers would be smarter, and our source code would be simpler.

That's currently not the world we live in, though.

Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- Makefile | 7 +++---- init/Kconfig | 17 ----------------- kernel/trace/Kconfig | 1 - 3 files changed, 3 insertions(+), 22 deletions(-)

--- a/Makefile +++ b/Makefile @@ -661,10 +661,6 @@ else KBUILD_CFLAGS += -O2 endif

-ifdef CONFIG_CC_DISABLE_WARN_MAYBE_UNINITIALIZED -KBUILD_CFLAGS += -Wno-maybe-uninitialized -endif - # Tell gcc to never replace conditional load with a non-conditional one KBUILD_CFLAGS += $(call cc-option,--param=allow-store-data-races=0)

@@ -804,6 +800,9 @@ KBUILD_CFLAGS += $(call cc-disable-warni # disable stringop warnings in gcc 8+ KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation)

+# Enabled with W=2, disabled by default as noisy +KBUILD_CFLAGS += $(call cc-disable-warning, maybe-uninitialized) + # disable invalid "can't wrap" optimizations for signed / pointers KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow)

--- a/init/Kconfig +++ b/init/Kconfig @@ -16,22 +16,6 @@ config DEFCONFIG_LIST default "$ARCH_DEFCONFIG" default "arch/$ARCH/defconfig"

-config CC_HAS_WARN_MAYBE_UNINITIALIZED - def_bool $(cc-option,-Wmaybe-uninitialized) - help - GCC >= 4.7 supports this option. - -config CC_DISABLE_WARN_MAYBE_UNINITIALIZED - bool - depends on CC_HAS_WARN_MAYBE_UNINITIALIZED - default CC_IS_GCC && GCC_VERSION < 40900 # unreliable for GCC < 4.9 - help - GCC's -Wmaybe-uninitialized is not reliable by definition. - Lots of false positive warnings are produced in some cases. - - If this option is enabled, -Wno-maybe-uninitialzed is passed - to the compiler to suppress maybe-uninitialized warnings. - config CONSTRUCTORS bool depends on !UML @@ -1060,7 +1044,6 @@ config CC_OPTIMIZE_FOR_PERFORMANCE

config CC_OPTIMIZE_FOR_SIZE bool "Optimize for size" - imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives help Enabling this option will pass "-Os" instead of "-O2" to your compiler resulting in a smaller kernel. --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -345,7 +345,6 @@ config PROFILE_ANNOTATED_BRANCHES config PROFILE_ALL_BRANCHES bool "Profile all if conditionals" if !FORTIFY_SOURCE select TRACE_BRANCH_PROFILING - imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives help This tracer profiles all branch conditions. Every if () taken in the kernel is recorded whether it hit or miss.

From: Linus Torvalds torvalds@linux-foundation.org

commit 44720996e2d79e47d508b0abe99b931a726a3197 upstream.

This is another fine warning, related to the 'zero-length-bounds' one, but hitting the same historical code in the kernel.

Because C didn't historically support flexible array members, we have code that instead uses a one-sized array, the same way we have cases of zero-sized arrays.

The one-sized arrays come from either not wanting to use the gcc zero-sized array extension, or from a slight convenience-feature, where particularly for strings, the size of the structure now includes the allocation for the final NUL character.

So with a "char name[1];" at the end of a structure, you can do things like

v = my_malloc(sizeof(struct vendor) + strlen(name));

and avoid the "+1" for the terminator.

Yes, the modern way to do that is with a flexible array, and using 'offsetof()' instead of 'sizeof()', and adding the "+1" by hand. That also technically gets the size "more correct" in that it avoids any alignment (and thus padding) issues, but this is another long-term cleanup thing that will not happen for 5.7.

So disable the warning for now, even though it's potentially quite useful. Having a slew of warnings that then hide more urgent new issues is not an improvement.

Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- Makefile | 1 + 1 file changed, 1 insertion(+)

--- a/Makefile +++ b/Makefile @@ -802,6 +802,7 @@ KBUILD_CFLAGS += $(call cc-disable-warni

# We'll want to enable this eventually, but it's not going away for 5.7 at least KBUILD_CFLAGS += $(call cc-disable-warning, zero-length-bounds) +KBUILD_CFLAGS += $(call cc-disable-warning, array-bounds)

# Enabled with W=2, disabled by default as noisy KBUILD_CFLAGS += $(call cc-disable-warning, maybe-uninitialized)

From: Linus Torvalds torvalds@linux-foundation.org

commit adc71920969870dfa54e8f40dac8616284832d02 upstream.

gcc-10 now warns about passing aliasing pointers to functions that take restricted pointers.

That's actually a great warning, and if we ever start using 'restrict' in the kernel, it might be quite useful. But right now we don't, and it turns out that the only thing this warns about is an idiom where we have declared a few functions to be "printf-like" (which seems to make gcc pick up the restricted pointer thing), and then we print to the same buffer that we also use as an input.

And people do that as an odd concatenation pattern, with code like this:

#define sysfs_show_gen_prop(buffer, fmt, ...) \ snprintf(buffer, PAGE_SIZE, "%s"fmt, buffer, __VA_ARGS__)

where we have 'buffer' as both the destination of the final result, and as the initial argument.

Yes, it's a bit questionable. And outside of the kernel, people do have standard declarations like

int snprintf( char *restrict buffer, size_t bufsz, const char *restrict format, ... );

where that output buffer is marked as a restrict pointer that cannot alias with any other arguments.

But in the context of the kernel, that 'use snprintf() to concatenate to the end result' does work, and the pattern shows up in multiple places. And we have not marked our own version of snprintf() as taking restrict pointers, so the warning is incorrect for now, and gcc picks it up on its own.

If we do start using 'restrict' in the kernel (and it might be a good idea if people find places where it matters), we'll need to figure out how to avoid this issue for snprintf and friends. But in the meantime, this warning is not useful.

Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- Makefile | 3 +++ 1 file changed, 3 insertions(+)

--- a/Makefile +++ b/Makefile @@ -805,6 +805,9 @@ KBUILD_CFLAGS += $(call cc-disable-warni KBUILD_CFLAGS += $(call cc-disable-warning, array-bounds) KBUILD_CFLAGS += $(call cc-disable-warning, stringop-overflow)

+# Another good warning that we'll want to enable eventually +KBUILD_CFLAGS += $(call cc-disable-warning, restrict) + # Enabled with W=2, disabled by default as noisy KBUILD_CFLAGS += $(call cc-disable-warning, maybe-uninitialized)

From: Jan Beulich JBeulich@suse.com

commit 22636f8c9511245cb3c8412039f1dd95afb3aa59 upstream.

Omitting suffixes from instructions in AT&T mode is bad practice when operand size cannot be determined by the assembler from register operands, and is likely going to be warned about by upstream gas in the future (mine does already). Add the missing suffixes here. Note that for 64-bit this means some operations change from being 32-bit to 64-bit.

Signed-off-by: Jan Beulich jbeulich@suse.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Link: https://lkml.kernel.org/r/5A93F98702000078001ABACC@prv-mh.provo.novell.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/include/asm/bitops.h | 29 ++++++++++++++++------------- arch/x86/include/asm/percpu.h | 2 +- 2 files changed, 17 insertions(+), 14 deletions(-)

--- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -78,7 +78,7 @@ set_bit(long nr, volatile unsigned long : "iq" ((u8)CONST_MASK(nr)) : "memory"); } else { - asm volatile(LOCK_PREFIX "bts %1,%0" + asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0" : BITOP_ADDR(addr) : "Ir" (nr) : "memory"); } } @@ -94,7 +94,7 @@ set_bit(long nr, volatile unsigned long */ static __always_inline void __set_bit(long nr, volatile unsigned long *addr) { - asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory"); + asm volatile(__ASM_SIZE(bts) " %1,%0" : ADDR : "Ir" (nr) : "memory"); }

/** @@ -115,7 +115,7 @@ clear_bit(long nr, volatile unsigned lon : CONST_MASK_ADDR(nr, addr) : "iq" ((u8)~CONST_MASK(nr))); } else { - asm volatile(LOCK_PREFIX "btr %1,%0" + asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0" : BITOP_ADDR(addr) : "Ir" (nr)); } @@ -137,7 +137,7 @@ static __always_inline void clear_bit_un

static __always_inline void __clear_bit(long nr, volatile unsigned long *addr) { - asm volatile("btr %1,%0" : ADDR : "Ir" (nr)); + asm volatile(__ASM_SIZE(btr) " %1,%0" : ADDR : "Ir" (nr)); }

static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) @@ -182,7 +182,7 @@ static __always_inline void __clear_bit_ */ static __always_inline void __change_bit(long nr, volatile unsigned long *addr) { - asm volatile("btc %1,%0" : ADDR : "Ir" (nr)); + asm volatile(__ASM_SIZE(btc) " %1,%0" : ADDR : "Ir" (nr)); }

/** @@ -201,7 +201,7 @@ static __always_inline void change_bit(l : CONST_MASK_ADDR(nr, addr) : "iq" ((u8)CONST_MASK(nr))); } else { - asm volatile(LOCK_PREFIX "btc %1,%0" + asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0" : BITOP_ADDR(addr) : "Ir" (nr)); } @@ -217,7 +217,8 @@ static __always_inline void change_bit(l */ static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) { - GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", c); + GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), + *addr, "Ir", nr, "%0", c); }

/** @@ -246,7 +247,7 @@ static __always_inline bool __test_and_s { bool oldbit;

- asm("bts %2,%1" + asm(__ASM_SIZE(bts) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -263,7 +264,8 @@ static __always_inline bool __test_and_s */ static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) { - GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", c); + GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), + *addr, "Ir", nr, "%0", c); }

/** @@ -286,7 +288,7 @@ static __always_inline bool __test_and_c { bool oldbit;

- asm volatile("btr %2,%1" + asm volatile(__ASM_SIZE(btr) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -298,7 +300,7 @@ static __always_inline bool __test_and_c { bool oldbit;

- asm volatile("btc %2,%1" + asm volatile(__ASM_SIZE(btc) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr) : "memory"); @@ -316,7 +318,8 @@ static __always_inline bool __test_and_c */ static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) { - GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", c); + GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), + *addr, "Ir", nr, "%0", c); }

static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) @@ -329,7 +332,7 @@ static __always_inline bool variable_tes { bool oldbit;

- asm volatile("bt %2,%1" + asm volatile(__ASM_SIZE(bt) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long *)addr), "Ir" (nr)); --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -526,7 +526,7 @@ static inline bool x86_this_cpu_variable { bool oldbit;

- asm volatile("bt "__percpu_arg(2)",%1" + asm volatile("btl "__percpu_arg(2)",%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long __percpu *)addr), "Ir" (nr));

From: Cong Wang xiyou.wangcong@gmail.com

[ Upstream commit dd912306ff008891c82cd9f63e8181e47a9cb2fb ]

syzbot managed to trigger a recursive NETDEV_FEAT_CHANGE event between bonding master and slave. I managed to find a reproducer for this:

ip li set bond0 up ifenslave bond0 eth0 brctl addbr br0 ethtool -K eth0 lro off brctl addif br0 bond0 ip li set br0 up

When a NETDEV_FEAT_CHANGE event is triggered on a bonding slave, it captures this and calls bond_compute_features() to fixup its master's and other slaves' features. However, when syncing with its lower devices by netdev_sync_lower_features() this event is triggered again on slaves when the LRO feature fails to change, so it goes back and forth recursively until the kernel stack is exhausted.

Commit 17b85d29e82c intentionally lets __netdev_update_features() return -1 for such a failure case, so we have to just rely on the existing check inside netdev_sync_lower_features() and skip NETDEV_FEAT_CHANGE event only for this specific failure case.

Fixes: fd867d51f889 ("net/core: generic support for disabling netdev features down stack") Reported-by: syzbot+e73ceacfd8560cc8a3ca@syzkaller.appspotmail.com Reported-by: syzbot+c2fb6f9ddcea95ba49b5@syzkaller.appspotmail.com Cc: Jarod Wilson jarod@redhat.com Cc: Nikolay Aleksandrov nikolay@cumulusnetworks.com Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: Jann Horn jannh@google.com Reviewed-by: Jay Vosburgh jay.vosburgh@canonical.com Signed-off-by: Cong Wang xiyou.wangcong@gmail.com Acked-by: Nikolay Aleksandrov nikolay@cumulusnetworks.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/dev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/net/core/dev.c +++ b/net/core/dev.c @@ -7282,11 +7282,13 @@ static void netdev_sync_lower_features(s netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", &feature, lower->name); lower->wanted_features &= ~feature; - netdev_update_features(lower); + __netdev_update_features(lower);

if (unlikely(lower->features & feature)) netdev_WARN(upper, "failed to disable %pNF on %s!\n", &feature, lower->name); + else + netdev_features_change(lower); } } }

From: Heiner Kallweit hkallweit1@gmail.com

[ Upstream commit 9de5d235b60a7cdfcdd5461e70c5663e713fde87 ]

phy_restart_aneg() enables aneg in the PHY. That's not what we want if phydev->autoneg is disabled. In this case still update EEE advertisement register, but don't enable aneg and don't trigger an aneg restart.

Fixes: f75abeb8338e ("net: phy: restart phy autonegotiation after EEE advertisment change") Signed-off-by: Heiner Kallweit hkallweit1@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/phy/phy.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)

--- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -1257,9 +1257,11 @@ int phy_ethtool_set_eee(struct phy_devic /* Restart autonegotiation so the new modes get sent to the * link partner. */ - ret = phy_restart_aneg(phydev); - if (ret < 0) - return ret; + if (phydev->autoneg == AUTONEG_ENABLE) { + ret = phy_restart_aneg(phydev); + if (ret < 0) + return ret; + } }

return 0;

From: Luo bin luobin9@huawei.com

[ Upstream commit e8a1b0efd632d1c9db7d4e93da66377c7b524862 ]

if some function in ndo_stop interface returns failure because of hardware fault, must go on excuting rest steps rather than return failure directly, otherwise will cause memory leak.And bump the timeout for SET_FUNC_STATE to ensure that cmd won't return failure when hw is busy. Otherwise hw may stomp host memory if we free memory regardless of the return value of SET_FUNC_STATE.

Fixes: 51ba902a16e6 ("net-next/hinic: Initialize hw interface") Signed-off-by: Luo bin luobin9@huawei.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c | 16 ++++++++++++---- drivers/net/ethernet/huawei/hinic/hinic_main.c | 18 +++--------------- 2 files changed, 15 insertions(+), 19 deletions(-)

--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c @@ -54,6 +54,8 @@

#define MGMT_MSG_TIMEOUT 5000

+#define SET_FUNC_PORT_MGMT_TIMEOUT 25000 + #define mgmt_to_pfhwdev(pf_mgmt) \ container_of(pf_mgmt, struct hinic_pfhwdev, pf_to_mgmt)

@@ -247,12 +249,13 @@ static int msg_to_mgmt_sync(struct hinic u8 *buf_in, u16 in_size, u8 *buf_out, u16 *out_size, enum mgmt_direction_type direction, - u16 resp_msg_id) + u16 resp_msg_id, u32 timeout) { struct hinic_hwif *hwif = pf_to_mgmt->hwif; struct pci_dev *pdev = hwif->pdev; struct hinic_recv_msg *recv_msg; struct completion *recv_done; + unsigned long timeo; u16 msg_id; int err;

@@ -276,8 +279,9 @@ static int msg_to_mgmt_sync(struct hinic goto unlock_sync_msg; }

- if (!wait_for_completion_timeout(recv_done, - msecs_to_jiffies(MGMT_MSG_TIMEOUT))) { + timeo = msecs_to_jiffies(timeout ? timeout : MGMT_MSG_TIMEOUT); + + if (!wait_for_completion_timeout(recv_done, timeo)) { dev_err(&pdev->dev, "MGMT timeout, MSG id = %d\n", msg_id); err = -ETIMEDOUT; goto unlock_sync_msg; @@ -351,6 +355,7 @@ int hinic_msg_to_mgmt(struct hinic_pf_to { struct hinic_hwif *hwif = pf_to_mgmt->hwif; struct pci_dev *pdev = hwif->pdev; + u32 timeout = 0;

if (sync != HINIC_MGMT_MSG_SYNC) { dev_err(&pdev->dev, "Invalid MGMT msg type\n"); @@ -362,9 +367,12 @@ int hinic_msg_to_mgmt(struct hinic_pf_to return -EINVAL; }

+ if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE) + timeout = SET_FUNC_PORT_MGMT_TIMEOUT; + return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size, buf_out, out_size, MGMT_DIRECT_SEND, - MSG_NOT_RESP); + MSG_NOT_RESP, timeout); }

/** --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -473,7 +473,6 @@ static int hinic_close(struct net_device { struct hinic_dev *nic_dev = netdev_priv(netdev); unsigned int flags; - int err;

down(&nic_dev->mgmt_lock);

@@ -487,20 +486,9 @@ static int hinic_close(struct net_device

up(&nic_dev->mgmt_lock);

- err = hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE); - if (err) { - netif_err(nic_dev, drv, netdev, - "Failed to set func port state\n"); - nic_dev->flags |= (flags & HINIC_INTF_UP); - return err; - } - - err = hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE); - if (err) { - netif_err(nic_dev, drv, netdev, "Failed to set port state\n"); - nic_dev->flags |= (flags & HINIC_INTF_UP); - return err; - } + hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE); + + hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE);

free_rxqs(nic_dev); free_txqs(nic_dev);

From: Paolo Abeni pabeni@redhat.com

[ Upstream commit 57644431a6c2faac5d754ebd35780cf43a531b1a ]

In commit b406472b5ad7 ("net: ipv4: avoid mixed n_redirects and rate_tokens usage") I missed the fact that a 0 'rate_tokens' will bypass the backoff algorithm.

Since rate_tokens is cleared after a redirect silence, and never incremented on redirects, if the host keeps receiving packets requiring redirect it will reply ignoring the backoff.

Additionally, the 'rate_last' field will be updated with the cadence of the ingress packet requiring redirect. If that rate is high enough, that will prevent the host from generating any other kind of ICMP messages

The check for a zero 'rate_tokens' value was likely a shortcut to avoid the more complex backoff algorithm after a redirect silence period. Address the issue checking for 'n_redirects' instead, which is incremented on successful redirect, and does not interfere with other ICMP replies.

Fixes: b406472b5ad7 ("net: ipv4: avoid mixed n_redirects and rate_tokens usage") Reported-and-tested-by: Colin Walters walters@redhat.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -921,7 +921,7 @@ void ip_rt_send_redirect(struct sk_buff /* Check for load limit; set rate_last to the latest sent * redirect. */ - if (peer->rate_tokens == 0 || + if (peer->n_redirects == 0 || time_after(jiffies, (peer->rate_last + (ip_rt_redirect_load << peer->n_redirects)))) {

From: Kelly Littlepage kelly@onechronos.com

[ Upstream commit cc4de047b33be247f9c8150d3e496743a49642b8 ]

The stated intent of the original commit is to is to "return the timestamp corresponding to the highest sequence number data returned." The current implementation returns the timestamp for the last byte of the last fully read skb, which is not necessarily the last byte in the recv buffer. This patch converts behavior to the original definition, and to the behavior of the previous draft versions of commit 98aaa913b4ed ("tcp: Extend SOF_TIMESTAMPING_RX_SOFTWARE to TCP recvmsg") which also match this behavior.

Fixes: 98aaa913b4ed ("tcp: Extend SOF_TIMESTAMPING_RX_SOFTWARE to TCP recvmsg") Co-developed-by: Iris Liu iris@onechronos.com Signed-off-by: Iris Liu iris@onechronos.com Signed-off-by: Kelly Littlepage kelly@onechronos.com Signed-off-by: Eric Dumazet edumazet@google.com Acked-by: Soheil Hassas Yeganeh soheil@google.com Acked-by: Willem de Bruijn willemb@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/tcp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1977,13 +1977,15 @@ skip_copy: tp->urg_data = 0; tcp_fast_path_check(sk); } - if (used + offset < skb->len) - continue;

if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, &tss); has_tss = true; } + + if (used + offset < skb->len) + continue; + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; if (!(flags & MSG_PEEK))

From: Takashi Iwai tiwai@suse.de

commit 5a7b44a8df822e0667fc76ed7130252523993bda upstream.

syzbot reported the uninitialized value exposure in certain situations using virmidi loop. It's likely a very small race at writing and reading, and the influence is almost negligible. But it's safer to paper over this just by replacing the existing kvmalloc() with kvzalloc().

Reported-by: syzbot+194dffdb8b22fc5d207a@syzkaller.appspotmail.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/core/rawmidi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -125,7 +125,7 @@ static int snd_rawmidi_runtime_create(st runtime->avail = 0; else runtime->avail = runtime->buffer_size; - if ((runtime->buffer = kmalloc(runtime->buffer_size, GFP_KERNEL)) == NULL) { + if ((runtime->buffer = kzalloc(runtime->buffer_size, GFP_KERNEL)) == NULL) { kfree(runtime); return -ENOMEM; } @@ -650,7 +650,7 @@ int snd_rawmidi_output_params(struct snd return -EINVAL; } if (params->buffer_size != runtime->buffer_size) { - newbuf = kmalloc(params->buffer_size, GFP_KERNEL); + newbuf = kzalloc(params->buffer_size, GFP_KERNEL); if (!newbuf) return -ENOMEM; spin_lock_irq(&runtime->lock);

From: Kishon Vijay Abraham I kishon@ti.com

commit 90d4d3f4ea45370d482fa609dbae4d2281b4074f upstream.

Even though commit cfb5d65f2595 ("ARM: dts: dra7: Add bus_dma_limit for L3 bus") added bus_dma_limit for L3 bus, the PCIe controller gets incorrect value of bus_dma_limit.

Fix it by adding empty dma-ranges property to axi@0 and axi@1 (parent device tree node of PCIe controller).

Cc: stable@kernel.org Signed-off-by: Kishon Vijay Abraham I kishon@ti.com Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/boot/dts/dra7.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -289,6 +289,7 @@ #address-cells = <1>; ranges = <0x51000000 0x51000000 0x3000 0x0 0x20000000 0x10000000>; + dma-ranges; /** * To enable PCI endpoint mode, disable the pcie1_rc * node and enable pcie1_ep mode. @@ -303,7 +304,6 @@ device_type = "pci"; ranges = <0x81000000 0 0 0x03000 0 0x00010000 0x82000000 0 0x20013000 0x13000 0 0xffed000>; - dma-ranges = <0x02000000 0x0 0x00000000 0x00000000 0x1 0x00000000>; bus-range = <0x00 0xff>; #interrupt-cells = <1>; num-lanes = <1>; @@ -347,6 +347,7 @@ #address-cells = <1>; ranges = <0x51800000 0x51800000 0x3000 0x0 0x30000000 0x10000000>; + dma-ranges; status = "disabled"; pcie@51800000 { compatible = "ti,dra7-pcie"; @@ -358,7 +359,6 @@ device_type = "pci"; ranges = <0x81000000 0 0 0x03000 0 0x00010000 0x82000000 0 0x30013000 0x13000 0 0xffed000>; - dma-ranges = <0x02000000 0x0 0x00000000 0x00000000 0x1 0x00000000>; bus-range = <0x00 0xff>; #interrupt-cells = <1>; num-lanes = <1>;

From: Borislav Petkov bp@suse.de

commit a9a3ed1eff3601b63aea4fb462d8b3b92c7c1e7e upstream.

... or the odyssey of trying to disable the stack protector for the function which generates the stack canary value.

The whole story started with Sergei reporting a boot crash with a kernel built with gcc-10:

Kernel panic — not syncing: stack-protector: Kernel stack is corrupted in: start_secondary CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.6.0-rc5—00235—gfffb08b37df9 #139 Hardware name: Gigabyte Technology Co., Ltd. To be filled by O.E.M./H77M—D3H, BIOS F12 11/14/2013 Call Trace: dump_stack panic ? start_secondary __stack_chk_fail start_secondary secondary_startup_64 -—-[ end Kernel panic — not syncing: stack—protector: Kernel stack is corrupted in: start_secondary

This happens because gcc-10 tail-call optimizes the last function call in start_secondary() - cpu_startup_entry() - and thus emits a stack canary check which fails because the canary value changes after the boot_init_stack_canary() call.

To fix that, the initial attempt was to mark the one function which generates the stack canary with:

__attribute__((optimize("-fno-stack-protector"))) ... start_secondary(void *unused)

however, using the optimize attribute doesn't work cumulatively as the attribute does not add to but rather replaces previously supplied optimization options - roughly all -fxxx options.

The key one among them being -fno-omit-frame-pointer and thus leading to not present frame pointer - frame pointer which the kernel needs.

The next attempt to prevent compilers from tail-call optimizing the last function call cpu_startup_entry(), shy of carving out start_secondary() into a separate compilation unit and building it with -fno-stack-protector, was to add an empty asm("").

This current solution was short and sweet, and reportedly, is supported by both compilers but we didn't get very far this time: future (LTO?) optimization passes could potentially eliminate this, which leads us to the third attempt: having an actual memory barrier there which the compiler cannot ignore or move around etc.

That should hold for a long time, but hey we said that about the other two solutions too so...

Reported-by: Sergei Trofimovich slyfox@gentoo.org Signed-off-by: Borislav Petkov bp@suse.de Tested-by: Kalle Valo kvalo@codeaurora.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20200314164451.346497-1-slyfox@gentoo.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/include/asm/stackprotector.h | 7 ++++++- arch/x86/kernel/smpboot.c | 8 ++++++++ arch/x86/xen/smp_pv.c | 1 + include/linux/compiler.h | 6 ++++++ init/main.c | 2 ++ 5 files changed, 23 insertions(+), 1 deletion(-)

--- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -55,8 +55,13 @@ /* * Initialize the stackprotector canary value. * - * NOTE: this must only be called from functions that never return, + * NOTE: this must only be called from functions that never return * and it must always be inlined. + * + * In addition, it should be called from a compilation unit for which + * stack protector is disabled. Alternatively, the caller should not end + * with a function call which gets tail-call optimized as that would + * lead to checking a modified canary value. */ static __always_inline void boot_init_stack_canary(void) { --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -270,6 +270,14 @@ static void notrace start_secondary(void

wmb(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); + + /* + * Prevent tail call to cpu_startup_entry() because the stack protector + * guard has been changed a couple of function calls up, in + * boot_init_stack_canary() and must not be checked before tail calling + * another function. + */ + prevent_tail_call_optimization(); }

/** --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -89,6 +89,7 @@ asmlinkage __visible void cpu_bringup_an { cpu_bringup(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); + prevent_tail_call_optimization(); }

void xen_smp_intr_free_pv(unsigned int cpu) --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -382,4 +382,10 @@ unsigned long read_word_at_a_time(const (_________p1); \ })

+/* + * This is needed in functions which generate the stack canary, see + * arch/x86/kernel/smpboot.c::start_secondary() for an example. + */ +#define prevent_tail_call_optimization() mb() + #endif /* __LINUX_COMPILER_H */ --- a/init/main.c +++ b/init/main.c @@ -706,6 +706,8 @@ asmlinkage __visible void __init start_k

/* Do the rest non-__init'ed, we're now alive */ rest_init(); + + prevent_tail_call_optimization(); }

/* Call all constructor functions linked into the kernel. */

From: Eugeniu Rosca erosca@de.adit-jv.com

commit 76e1ef1d81a4129d7e2fb8c48c83b166d1c8e040 upstream.

On Tue, May 12, 2020 at 09:36:07PM +0800, Kai-Heng Feng wrote [1]:

This patch prevents my Raven Ridge xHCI from getting runtime suspend.

The problem described in v5.6 commit 1208f9e1d758c9 ("USB: hub: Fix the broken detection of USB3 device in SMSC hub") applies solely to the USB5534B hub [2] present on the Kingfisher Infotainment Carrier Board, manufactured by Shimafuji Electric Inc [3].

Despite that, the aforementioned commit applied the quirk to _all_ hubs carrying vendor ID 0x424 (i.e. SMSC), of which there are more [4] than initially expected. Consequently, the quirk is now enabled on platforms carrying SMSC/Microchip hub models which potentially don't exhibit the original issue.

To avoid reports like [1], further limit the quirk's scope to USB5534B [2], by employing both Vendor and Product ID checks.

Tested on H3ULCB + Kingfisher rev. M05.

[1] https://lore.kernel.org/linux-renesas-soc/73933975-6F0E-40F5-9584-D2B8F615C0... [2] https://www.microchip.com/wwwproducts/en/USB5534B [3] http://www.shimafuji.co.jp/wp/wp-content/uploads/2018/08/SBEV-RCAR-KF-M06Boa... [4] https://devicehunt.com/search/type/usb/vendor/0424/device/any

Fixes: 1208f9e1d758c9 ("USB: hub: Fix the broken detection of USB3 device in SMSC hub") Cc: stable@vger.kernel.org # v4.14+ Cc: Alan Stern stern@rowland.harvard.edu Cc: Hardik Gajjar hgajjar@de.adit-jv.com Cc: linux-renesas-soc@vger.kernel.org Cc: linux-usb@vger.kernel.org Reported-by: Kai-Heng Feng kai.heng.feng@canonical.com Signed-off-by: Eugeniu Rosca erosca@de.adit-jv.com Tested-by: Kai-Heng Feng kai.heng.feng@canonical.com Link: https://lore.kernel.org/r/20200514220246.13290-1-erosca@de.adit-jv.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/core/hub.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -37,6 +37,7 @@

#define USB_VENDOR_GENESYS_LOGIC 0x05e3 #define USB_VENDOR_SMSC 0x0424 +#define USB_PRODUCT_USB5534B 0x5534 #define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND 0x01 #define HUB_QUIRK_DISABLE_AUTOSUSPEND 0x02

@@ -5317,8 +5318,11 @@ out_hdev_lock: }

static const struct usb_device_id hub_id_table[] = { - { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_CLASS, + { .match_flags = USB_DEVICE_ID_MATCH_VENDOR + | USB_DEVICE_ID_MATCH_PRODUCT + | USB_DEVICE_ID_MATCH_INT_CLASS, .idVendor = USB_VENDOR_SMSC, + .idProduct = USB_PRODUCT_USB5534B, .bInterfaceClass = USB_CLASS_HUB, .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND}, { .match_flags = USB_DEVICE_ID_MATCH_VENDOR

From: Kyungtae Kim kt0755@gmail.com

commit 15753588bcd4bbffae1cca33c8ced5722477fe1f upstream.

FuzzUSB (a variant of syzkaller) found an illegal array access using an incorrect index while binding a gadget with UDC.

Reference: https://www.spinics.net/lists/linux-usb/msg194331.html

This bug occurs when a size variable used for a buffer is misused to access its strcpy-ed buffer. Given a buffer along with its size variable (taken from user input), from which, a new buffer is created using kstrdup(). Due to the original buffer containing 0 value in the middle, the size of the kstrdup-ed buffer becomes smaller than that of the original. So accessing the kstrdup-ed buffer with the same size variable triggers memory access violation.

The fix makes sure no zero value in the buffer, by comparing the strlen() of the orignal buffer with the size variable, so that the access to the kstrdup-ed buffer is safe.

BUG: KASAN: slab-out-of-bounds in gadget_dev_desc_UDC_store+0x1ba/0x200 drivers/usb/gadget/configfs.c:266 Read of size 1 at addr ffff88806a55dd7e by task syz-executor.0/17208

CPU: 2 PID: 17208 Comm: syz-executor.0 Not tainted 5.6.8 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0xce/0x128 lib/dump_stack.c:118 print_address_description.constprop.4+0x21/0x3c0 mm/kasan/report.c:374 __kasan_report+0x131/0x1b0 mm/kasan/report.c:506 kasan_report+0x12/0x20 mm/kasan/common.c:641 __asan_report_load1_noabort+0x14/0x20 mm/kasan/generic_report.c:132 gadget_dev_desc_UDC_store+0x1ba/0x200 drivers/usb/gadget/configfs.c:266 flush_write_buffer fs/configfs/file.c:251 [inline] configfs_write_file+0x2f1/0x4c0 fs/configfs/file.c:283 __vfs_write+0x85/0x110 fs/read_write.c:494 vfs_write+0x1cd/0x510 fs/read_write.c:558 ksys_write+0x18a/0x220 fs/read_write.c:611 __do_sys_write fs/read_write.c:623 [inline] __se_sys_write fs/read_write.c:620 [inline] __x64_sys_write+0x73/0xb0 fs/read_write.c:620 do_syscall_64+0x9e/0x510 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Signed-off-by: Kyungtae Kim kt0755@gmail.com Reported-and-tested-by: Kyungtae Kim kt0755@gmail.com Cc: Felipe Balbi balbi@kernel.org Cc: stable stable@vger.kernel.org Link: https://lore.kernel.org/r/20200510054326.GA19198@pizza01 Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/gadget/configfs.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -259,6 +259,9 @@ static ssize_t gadget_dev_desc_UDC_store char *name; int ret;

+ if (strlen(page) < len) + return -EOVERFLOW; + name = kstrdup(page, GFP_KERNEL); if (!name) return -ENOMEM;

From: Josh Poimboeuf jpoimboe@redhat.com

commit 71c95825289f585014fe9741b051d32a7a916680 upstream.

The unwind_state 'error' field is used to inform the reliable unwinding code that the stack trace can't be trusted. Set this field for all errors in __unwind_start().

Also, move the zeroing out of the unwind_state struct to before the ORC table initialization check, to prevent the caller from reading uninitialized data if the ORC table is corrupted.

Fixes: af085d9084b4 ("stacktrace/x86: add function for detecting reliable stack traces") Fixes: d3a09104018c ("x86/unwinder/orc: Dont bail on stack overflow") Fixes: 98d0c8ebf77e ("x86/unwind/orc: Prevent unwinding before ORC initialization") Reported-by: Pavel Machek pavel@denx.de Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/d6ac7215a84ca92b895fdd2e1aa546729417e6e6.158948727... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kernel/unwind_orc.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-)

--- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -505,23 +505,23 @@ EXPORT_SYMBOL_GPL(unwind_next_frame); void __unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long *first_frame) { - if (!orc_init) - goto done; - memset(state, 0, sizeof(*state)); state->task = task;

+ if (!orc_init) + goto err; + /* * Refuse to unwind the stack of a task while it's executing on another * CPU. This check is racy, but that's ok: the unwinder has other * checks to prevent it from going off the rails. */ if (task_on_another_cpu(task)) - goto done; + goto err;

if (regs) { if (user_mode(regs)) - goto done; + goto the_end;

state->ip = regs->ip; state->sp = kernel_stack_pointer(regs); @@ -554,6 +554,7 @@ void __unwind_start(struct unwind_state * generate some kind of backtrace if this happens. */ void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp); + state->error = true; if (get_stack_info(next_page, state->task, &state->stack_info, &state->stack_mask)) return; @@ -579,8 +580,9 @@ void __unwind_start(struct unwind_state

return;

-done: +err: + state->error = true; +the_end: state->stack_info.type = STACK_TYPE_UNKNOWN; - return; } EXPORT_SYMBOL_GPL(__unwind_start);

From: Justin Swartz justin.swartz@risingedge.co.za

commit cec9d101d70a3509da9bd2e601e0b242154ce616 upstream.

The following changes prevent the unrecoverable freezes and rcu_sched stall warnings experienced in each of my attempts to take advantage of lima.

Replace the COMPOSITE_NOGATE definition of aclk_gpu_pre with a COMPOSITE that retains the selection of HDMIPHY as the PLL source, but instead makes uses of the aclk_gpu PLL source gate and parent names defined by mux_pll_src_4plls_p rather than mux_aclk_gpu_pre_p.

Remove the now unused mux_aclk_gpu_pre_p and the four named but also unused definitions (cpll_gpu, gpll_gpu, hdmiphy_gpu and usb480m_gpu) of the aclk_gpu PLL source gate.

Use the correct gate offset for aclk_gpu and aclk_gpu_noc.

Fixes: 307a2e9ac524 ("clk: rockchip: add clock controller for rk3228") Cc: stable@vger.kernel.org Signed-off-by: Justin Swartz justin.swartz@risingedge.co.za [double-checked against SoC manual and added fixes tag] Link: https://lore.kernel.org/r/20200114162503.7548-1-justin.swartz@risingedge.co.... Signed-off-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/clk/rockchip/clk-rk3228.c | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-)

--- a/drivers/clk/rockchip/clk-rk3228.c +++ b/drivers/clk/rockchip/clk-rk3228.c @@ -163,8 +163,6 @@ PNAME(mux_i2s_out_p) = { "i2s1_pre", "x PNAME(mux_i2s2_p) = { "i2s2_src", "i2s2_frac", "xin12m" }; PNAME(mux_sclk_spdif_p) = { "sclk_spdif_src", "spdif_frac", "xin12m" };

-PNAME(mux_aclk_gpu_pre_p) = { "cpll_gpu", "gpll_gpu", "hdmiphy_gpu", "usb480m_gpu" }; - PNAME(mux_uart0_p) = { "uart0_src", "uart0_frac", "xin24m" }; PNAME(mux_uart1_p) = { "uart1_src", "uart1_frac", "xin24m" }; PNAME(mux_uart2_p) = { "uart2_src", "uart2_frac", "xin24m" }; @@ -475,16 +473,9 @@ static struct rockchip_clk_branch rk3228 RK2928_CLKSEL_CON(24), 6, 10, DFLAGS, RK2928_CLKGATE_CON(2), 8, GFLAGS),

- GATE(0, "cpll_gpu", "cpll", 0, - RK2928_CLKGATE_CON(3), 13, GFLAGS), - GATE(0, "gpll_gpu", "gpll", 0, - RK2928_CLKGATE_CON(3), 13, GFLAGS), - GATE(0, "hdmiphy_gpu", "hdmiphy", 0, - RK2928_CLKGATE_CON(3), 13, GFLAGS), - GATE(0, "usb480m_gpu", "usb480m", 0, + COMPOSITE(0, "aclk_gpu_pre", mux_pll_src_4plls_p, 0, + RK2928_CLKSEL_CON(34), 5, 2, MFLAGS, 0, 5, DFLAGS, RK2928_CLKGATE_CON(3), 13, GFLAGS), - COMPOSITE_NOGATE(0, "aclk_gpu_pre", mux_aclk_gpu_pre_p, 0, - RK2928_CLKSEL_CON(34), 5, 2, MFLAGS, 0, 5, DFLAGS),

COMPOSITE(SCLK_SPI0, "sclk_spi0", mux_pll_src_2plls_p, 0, RK2928_CLKSEL_CON(25), 8, 1, MFLAGS, 0, 7, DFLAGS, @@ -589,8 +580,8 @@ static struct rockchip_clk_branch rk3228 GATE(0, "pclk_peri_noc", "pclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(12), 2, GFLAGS),

/* PD_GPU */ - GATE(ACLK_GPU, "aclk_gpu", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(13), 14, GFLAGS), - GATE(0, "aclk_gpu_noc", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(13), 15, GFLAGS), + GATE(ACLK_GPU, "aclk_gpu", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(7), 14, GFLAGS), + GATE(0, "aclk_gpu_noc", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(7), 15, GFLAGS),

/* PD_BUS */ GATE(0, "sclk_initmem_mbist", "aclk_cpu", 0, RK2928_CLKGATE_CON(8), 1, GFLAGS),

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

commit 19b94c1f9c9a16d41a8de3ccbdb8536cf1aecdbf upstream.

If 'usb_otg_descriptor_alloc()' fails, we must return an error code, not 0.

Fixes: 56023ce0fd70 ("usb: gadget: audio: allocate and init otg descriptor by otg capabilities") Reviewed-by: Peter Chen peter.chen@nxp.com Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Signed-off-by: Felipe Balbi balbi@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/gadget/legacy/audio.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/drivers/usb/gadget/legacy/audio.c +++ b/drivers/usb/gadget/legacy/audio.c @@ -303,8 +303,10 @@ static int audio_bind(struct usb_composi struct usb_descriptor_header *usb_desc;

usb_desc = usb_otg_descriptor_alloc(cdev->gadget); - if (!usb_desc) + if (!usb_desc) { + status = -ENOMEM; goto fail; + } usb_otg_descriptor_init(cdev->gadget, usb_desc); otg_desc[0] = usb_desc; otg_desc[1] = NULL;

From: Wei Yongjun weiyongjun1@huawei.com

commit e8f7f9e3499a6d96f7f63a4818dc7d0f45a7783b upstream.

If 'usb_otg_descriptor_alloc()' fails, we must return a negative error code -ENOMEM, not 0.

Fixes: ab6796ae9833 ("usb: gadget: cdc2: allocate and init otg descriptor by otg capabilities") Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Wei Yongjun weiyongjun1@huawei.com Signed-off-by: Felipe Balbi balbi@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/gadget/legacy/cdc2.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/drivers/usb/gadget/legacy/cdc2.c +++ b/drivers/usb/gadget/legacy/cdc2.c @@ -183,8 +183,10 @@ static int cdc_bind(struct usb_composite struct usb_descriptor_header *usb_desc;

usb_desc = usb_otg_descriptor_alloc(gadget); - if (!usb_desc) + if (!usb_desc) { + status = -ENOMEM; goto fail1; + } usb_otg_descriptor_init(gadget, usb_desc); otg_desc[0] = usb_desc; otg_desc[1] = NULL;

From: Chen-Yu Tsai wens@csie.org

commit 83b994129fb4c18a8460fd395864a28740e5e7fb upstream.

In some board device tree files, "rk805" was used for the RK805 PMIC's node name. However the policy for device trees is that generic names should be used.

Replace the "rk805" node name with the generic "pmic" name.

Fixes: 1e28037ec88e ("arm64: dts: rockchip: add rk805 node for rk3328-evb") Fixes: 955bebde057e ("arm64: dts: rockchip: add rk3328-rock64 board") Signed-off-by: Chen-Yu Tsai wens@csie.org Link: https://lore.kernel.org/r/20200327030414.5903-3-wens@kernel.org Signed-off-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/boot/dts/rockchip/rk3328-evb.dts | 2 +- arch/arm64/boot/dts/rockchip/rk3328-rock64.dts | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

--- a/arch/arm64/boot/dts/rockchip/rk3328-evb.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-evb.dts @@ -91,7 +91,7 @@ &i2c1 { status = "okay";

- rk805: rk805@18 { + rk805: pmic@18 { compatible = "rockchip,rk805"; reg = <0x18>; interrupt-parent = <&gpio2>; --- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts @@ -149,7 +149,7 @@ &i2c1 { status = "okay";

- rk805: rk805@18 { + rk805: pmic@18 { compatible = "rockchip,rk805"; reg = <0x18>; interrupt-parent = <&gpio2>;

From: Geert Uytterhoeven geert+renesas@glider.be

commit 0f739fdfe9e5ce668bd6d3210f310df282321837 upstream.

The R-Mobile APE6 Compare Match Timer 1 generates 8 interrupts, one for each channel, but currently only 1 is described. Fix this by adding the missing interrupts.

Fixes: f7b65230019b9dac ("ARM: shmobile: r8a73a4: Add CMT1 node") Signed-off-by: Geert Uytterhoeven geert+renesas@glider.be Link: https://lore.kernel.org/r/20200408090926.25201-1-geert+renesas@glider.be Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/boot/dts/r8a73a4.dtsi | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

--- a/arch/arm/boot/dts/r8a73a4.dtsi +++ b/arch/arm/boot/dts/r8a73a4.dtsi @@ -133,7 +133,14 @@ cmt1: timer@e6130000 { compatible = "renesas,cmt-48-r8a73a4", "renesas,cmt-48-gen2"; reg = <0 0xe6130000 0 0x1004>; - interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>; clocks = <&mstp3_clks R8A73A4_CLK_CMT1>; clock-names = "fck"; power-domains = <&pd_c5>;

From: Jim Mattson jmattson@google.com

commit c4e0e4ab4cf3ec2b3f0b628ead108d677644ebd9 upstream.

Bank_num is a one-based count of banks, not a zero-based index. It overflows the allocated space only when strictly greater than KVM_MAX_MCE_BANKS.

Fixes: a9e38c3e01ad ("KVM: x86: Catch potential overrun in MCE setup") Signed-off-by: Jue Wang juew@google.com Signed-off-by: Jim Mattson jmattson@google.com Reviewed-by: Peter Shier pshier@google.com Message-Id: 20200511225616.19557-1-jmattson@google.com Reviewed-by: Vitaly Kuznetsov vkuznets@redhat.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kvm/x86.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3214,7 +3214,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce( unsigned bank_num = mcg_cap & 0xff, bank;

r = -EINVAL; - if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS) + if (!bank_num || bank_num > KVM_MAX_MCE_BANKS) goto out; if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000)) goto out;