From baa888ca02db84bdca59177fb0ebe33b3041ff80 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Mon, 18 Nov 2019 09:18:42 +0200 Subject: [PATCH 001/299] mlxsw: spectrum_router: Fix determining underlay for a GRE tunnel [ Upstream commit 1fc1657775dc1b19e9ac1d46b4054ed8ae5d99ab ] The helper mlxsw_sp_ipip_dev_ul_tb_id() determines the underlay VRF of a GRE tunnel. For a tunnel without a bound device, it uses the same VRF that the tunnel is in. However in Linux, a GRE tunnel without a bound device uses the main VRF as the underlay. Fix the function accordingly. mlxsw further assumed that moving a tunnel to a different VRF could cause conflict in local tunnel endpoint address, which cannot be offloaded. However, the only way that an underlay could be changed by moving the tunnel device itself is if the tunnel device does not have a bound device. But in that case the underlay is always the main VRF, so there is no opportunity to introduce a conflict by moving such device. Thus this check constitutes a dead code, and can be removed, which do. Fixes: 6ddb7426a7d4 ("mlxsw: spectrum_router: Introduce loopback RIFs") Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- .../ethernet/mellanox/mlxsw/spectrum_router.c | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 2ab9cf25a08a..3f54b3ca38ba 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -970,7 +970,7 @@ u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev) if (d) return l3mdev_fib_table(d) ? : RT_TABLE_MAIN; else - return l3mdev_fib_table(ol_dev) ? : RT_TABLE_MAIN; + return RT_TABLE_MAIN; } static struct mlxsw_sp_rif * @@ -1532,27 +1532,10 @@ static int mlxsw_sp_netdevice_ipip_ol_vrf_event(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_ipip_entry *ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); - enum mlxsw_sp_l3proto ul_proto; - union mlxsw_sp_l3addr saddr; - u32 ul_tb_id; if (!ipip_entry) return 0; - /* For flat configuration cases, moving overlay to a different VRF might - * cause local address conflict, and the conflicting tunnels need to be - * demoted. - */ - ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ol_dev); - ul_proto = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]->ul_proto; - saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ol_dev); - if (mlxsw_sp_ipip_demote_tunnel_by_saddr(mlxsw_sp, ul_proto, - saddr, ul_tb_id, - ipip_entry)) { - mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry); - return 0; - } - return __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry, true, false, false, extack); } From 5408138df1dbe85f3986b2756ca998bcdd94d3a7 Mon Sep 17 00:00:00 2001 From: Luigi Rizzo Date: Fri, 15 Nov 2019 12:12:25 -0800 Subject: [PATCH 002/299] net/mlx4_en: fix mlx4 ethtool -N insertion [ Upstream commit 34e59836565e36fade1464e054a3551c1a0364be ] ethtool expects ETHTOOL_GRXCLSRLALL to set ethtool_rxnfc->data with the total number of entries in the rx classifier table. Surprisingly, mlx4 is missing this part (in principle ethtool could still move forward and try the insert). Tested: compiled and run command: phh13:~# ethtool -N eth1 flow-type udp4 queue 4 Added rule with ID 255 Signed-off-by: Luigi Rizzo Reviewed-by: Tariq Toukan Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 94c59939a8cf..949ec70b6c13 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1745,6 +1745,7 @@ static int mlx4_en_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, err = mlx4_en_get_flow(dev, cmd, cmd->fs.location); break; case ETHTOOL_GRXCLSRLALL: + cmd->data = MAX_NUM_OF_FS_RULES; while ((!err || err == -ENOENT) && priority < cmd->rule_cnt) { err = mlx4_en_get_flow(dev, cmd, i); if (!err) From ebcb0840a76b19c5cdf4fc58d71f02e771cafd1c Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 18 Nov 2019 11:41:04 +0200 Subject: [PATCH 003/299] net/mlx4_en: Fix wrong limitation for number of TX rings [ Upstream commit 2744bf42680f64ebf2ee8a00354897857c073331 ] XDP_TX rings should not be limited by max_num_tx_rings_p_up. To make sure total number of TX rings never exceed MAX_TX_RINGS, add similar check in mlx4_en_alloc_tx_queue_per_tc(), where a new value is assigned for num_up. Fixes: 7e1dc5e926d5 ("net/mlx4_en: Limit the number of TX rings") Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 8 ++++---- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 9 +++++++++ 2 files changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 949ec70b6c13..e639a365ac2d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1812,6 +1812,7 @@ static int mlx4_en_set_channels(struct net_device *dev, struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_en_port_profile new_prof; struct mlx4_en_priv *tmp; + int total_tx_count; int port_up = 0; int xdp_count; int err = 0; @@ -1826,13 +1827,12 @@ static int mlx4_en_set_channels(struct net_device *dev, mutex_lock(&mdev->state_lock); xdp_count = priv->tx_ring_num[TX_XDP] ? channel->rx_count : 0; - if (channel->tx_count * priv->prof->num_up + xdp_count > - priv->mdev->profile.max_num_tx_rings_p_up * priv->prof->num_up) { + total_tx_count = channel->tx_count * priv->prof->num_up + xdp_count; + if (total_tx_count > MAX_TX_RINGS) { err = -EINVAL; en_err(priv, "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n", - channel->tx_count * priv->prof->num_up + xdp_count, - MAX_TX_RINGS); + total_tx_count, MAX_TX_RINGS); goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 0d7fd3f043cf..5868ec11db1a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -92,6 +92,7 @@ int mlx4_en_alloc_tx_queue_per_tc(struct net_device *dev, u8 tc) struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_en_port_profile new_prof; struct mlx4_en_priv *tmp; + int total_count; int port_up = 0; int err = 0; @@ -105,6 +106,14 @@ int mlx4_en_alloc_tx_queue_per_tc(struct net_device *dev, u8 tc) MLX4_EN_NUM_UP_HIGH; new_prof.tx_ring_num[TX] = new_prof.num_tx_rings_p_up * new_prof.num_up; + total_count = new_prof.tx_ring_num[TX] + new_prof.tx_ring_num[TX_XDP]; + if (total_count > MAX_TX_RINGS) { + err = -EINVAL; + en_err(priv, + "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n", + total_count, MAX_TX_RINGS); + goto out; + } err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true); if (err) goto out; From 9f6de5cf5390d62a563509873e41415061de1bcd Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 20 Nov 2019 15:34:38 +0300 Subject: [PATCH 004/299] net: rtnetlink: prevent underflows in do_setvfinfo() [ Upstream commit d658c8f56ec7b3de8051a24afb25da9ba3c388c5 ] The "ivm->vf" variable is a u32, but the problem is that a number of drivers cast it to an int and then forget to check for negatives. An example of this is in the cxgb4 driver. drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c 2890 static int cxgb4_mgmt_get_vf_config(struct net_device *dev, 2891 int vf, struct ifla_vf_info *ivi) ^^^^^^ 2892 { 2893 struct port_info *pi = netdev_priv(dev); 2894 struct adapter *adap = pi->adapter; 2895 struct vf_info *vfinfo; 2896 2897 if (vf >= adap->num_vfs) ^^^^^^^^^^^^^^^^^^^ 2898 return -EINVAL; 2899 vfinfo = &adap->vfinfo[vf]; ^^^^^^^^^^^^^^^^^^^^^^^^^^ There are 48 functions affected. drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c:8435 hclge_set_vf_vlan_filter() warn: can 'vfid' underflow 's32min-2147483646' drivers/net/ethernet/freescale/enetc/enetc_pf.c:377 enetc_pf_set_vf_mac() warn: can 'vf' underflow 's32min-2147483646' drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:2899 cxgb4_mgmt_get_vf_config() warn: can 'vf' underflow 's32min-254' drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:2960 cxgb4_mgmt_set_vf_rate() warn: can 'vf' underflow 's32min-254' drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:3019 cxgb4_mgmt_set_vf_rate() warn: can 'vf' underflow 's32min-254' drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:3038 cxgb4_mgmt_set_vf_vlan() warn: can 'vf' underflow 's32min-254' drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:3086 cxgb4_mgmt_set_vf_link_state() warn: can 'vf' underflow 's32min-254' drivers/net/ethernet/chelsio/cxgb/cxgb2.c:791 get_eeprom() warn: can 'i' underflow 's32min-(-4),0,4-s32max' drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:82 bnxt_set_vf_spoofchk() warn: can 'vf_id' underflow 's32min-65534' drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:164 bnxt_set_vf_trust() warn: can 'vf_id' underflow 's32min-65534' drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:186 bnxt_get_vf_config() warn: can 'vf_id' underflow 's32min-65534' drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:228 bnxt_set_vf_mac() warn: can 'vf_id' underflow 's32min-65534' drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:264 bnxt_set_vf_vlan() warn: can 'vf_id' underflow 's32min-65534' drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:293 bnxt_set_vf_bw() warn: can 'vf_id' underflow 's32min-65534' drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:333 bnxt_set_vf_link_state() warn: can 'vf_id' underflow 's32min-65534' drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c:2595 bnx2x_vf_op_prep() warn: can 'vfidx' underflow 's32min-63' drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c:2595 bnx2x_vf_op_prep() warn: can 'vfidx' underflow 's32min-63' drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c:2281 bnx2x_post_vf_bulletin() warn: can 'vf' underflow 's32min-63' drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c:2285 bnx2x_post_vf_bulletin() warn: can 'vf' underflow 's32min-63' drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c:2286 bnx2x_post_vf_bulletin() warn: can 'vf' underflow 's32min-63' drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c:2292 bnx2x_post_vf_bulletin() warn: can 'vf' underflow 's32min-63' drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c:2297 bnx2x_post_vf_bulletin() warn: can 'vf' underflow 's32min-63' drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:1832 qlcnic_sriov_set_vf_mac() warn: can 'vf' underflow 's32min-254' drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:1864 qlcnic_sriov_set_vf_tx_rate() warn: can 'vf' underflow 's32min-254' drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:1937 qlcnic_sriov_set_vf_vlan() warn: can 'vf' underflow 's32min-254' drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:2005 qlcnic_sriov_get_vf_config() warn: can 'vf' underflow 's32min-254' drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:2036 qlcnic_sriov_set_vf_spoofchk() warn: can 'vf' underflow 's32min-254' drivers/net/ethernet/emulex/benet/be_main.c:1914 be_get_vf_config() warn: can 'vf' underflow 's32min-65534' drivers/net/ethernet/emulex/benet/be_main.c:1915 be_get_vf_config() warn: can 'vf' underflow 's32min-65534' drivers/net/ethernet/emulex/benet/be_main.c:1922 be_set_vf_tvt() warn: can 'vf' underflow 's32min-65534' drivers/net/ethernet/emulex/benet/be_main.c:1951 be_clear_vf_tvt() warn: can 'vf' underflow 's32min-65534' drivers/net/ethernet/emulex/benet/be_main.c:2063 be_set_vf_tx_rate() warn: can 'vf' underflow 's32min-65534' drivers/net/ethernet/emulex/benet/be_main.c:2091 be_set_vf_link_state() warn: can 'vf' underflow 's32min-65534' drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:2609 ice_set_vf_port_vlan() warn: can 'vf_id' underflow 's32min-65534' drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:3050 ice_get_vf_cfg() warn: can 'vf_id' underflow 's32min-65534' drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:3103 ice_set_vf_spoofchk() warn: can 'vf_id' underflow 's32min-65534' drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:3181 ice_set_vf_mac() warn: can 'vf_id' underflow 's32min-65534' drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:3237 ice_set_vf_trust() warn: can 'vf_id' underflow 's32min-65534' drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:3286 ice_set_vf_link_state() warn: can 'vf_id' underflow 's32min-65534' drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:3919 i40e_validate_vf() warn: can 'vf_id' underflow 's32min-2147483646' drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:3957 i40e_ndo_set_vf_mac() warn: can 'vf_id' underflow 's32min-2147483646' drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4104 i40e_ndo_set_vf_port_vlan() warn: can 'vf_id' underflow 's32min-2147483646' drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4263 i40e_ndo_set_vf_bw() warn: can 'vf_id' underflow 's32min-2147483646' drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4309 i40e_ndo_get_vf_config() warn: can 'vf_id' underflow 's32min-2147483646' drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4371 i40e_ndo_set_vf_link_state() warn: can 'vf_id' underflow 's32min-2147483646' drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4441 i40e_ndo_set_vf_spoofchk() warn: can 'vf_id' underflow 's32min-2147483646' drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4441 i40e_ndo_set_vf_spoofchk() warn: can 'vf_id' underflow 's32min-2147483646' drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4504 i40e_ndo_set_vf_trust() warn: can 'vf_id' underflow 's32min-2147483646' Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/rtnetlink.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index c0de73b12580..dbb3c0c7c132 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2126,6 +2126,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_MAC]) { struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]); + if (ivm->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_mac) err = ops->ndo_set_vf_mac(dev, ivm->vf, @@ -2137,6 +2139,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_VLAN]) { struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]); + if (ivv->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_vlan) err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan, @@ -2169,6 +2173,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (len == 0) return -EINVAL; + if (ivvl[0]->vf >= INT_MAX) + return -EINVAL; err = ops->ndo_set_vf_vlan(dev, ivvl[0]->vf, ivvl[0]->vlan, ivvl[0]->qos, ivvl[0]->vlan_proto); if (err < 0) @@ -2179,6 +2185,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]); struct ifla_vf_info ivf; + if (ivt->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_get_vf_config) err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf); @@ -2197,6 +2205,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_RATE]) { struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]); + if (ivt->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_rate) err = ops->ndo_set_vf_rate(dev, ivt->vf, @@ -2209,6 +2219,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_SPOOFCHK]) { struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]); + if (ivs->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_spoofchk) err = ops->ndo_set_vf_spoofchk(dev, ivs->vf, @@ -2220,6 +2232,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_LINK_STATE]) { struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]); + if (ivl->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_link_state) err = ops->ndo_set_vf_link_state(dev, ivl->vf, @@ -2233,6 +2247,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) err = -EOPNOTSUPP; ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]); + if (ivrssq_en->vf >= INT_MAX) + return -EINVAL; if (ops->ndo_set_vf_rss_query_en) err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf, ivrssq_en->setting); @@ -2243,6 +2259,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_TRUST]) { struct ifla_vf_trust *ivt = nla_data(tb[IFLA_VF_TRUST]); + if (ivt->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_trust) err = ops->ndo_set_vf_trust(dev, ivt->vf, ivt->setting); @@ -2253,15 +2271,18 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_IB_NODE_GUID]) { struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_NODE_GUID]); + if (ivt->vf >= INT_MAX) + return -EINVAL; if (!ops->ndo_set_vf_guid) return -EOPNOTSUPP; - return handle_vf_guid(dev, ivt, IFLA_VF_IB_NODE_GUID); } if (tb[IFLA_VF_IB_PORT_GUID]) { struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_PORT_GUID]); + if (ivt->vf >= INT_MAX) + return -EINVAL; if (!ops->ndo_set_vf_guid) return -EOPNOTSUPP; From 2ba6a4f5402e3ac972802178b6b2f1965fcd26a4 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Tue, 19 Nov 2019 23:47:33 +0100 Subject: [PATCH 005/299] net/sched: act_pedit: fix WARN() in the traffic path [ Upstream commit f67169fef8dbcc1ac6a6a109ecaad0d3b259002c ] when configuring act_pedit rules, the number of keys is validated only on addition of a new entry. This is not sufficient to avoid hitting a WARN() in the traffic path: for example, it is possible to replace a valid entry with a new one having 0 extended keys, thus causing splats in dmesg like: pedit BUG: index 42 WARNING: CPU: 2 PID: 4054 at net/sched/act_pedit.c:410 tcf_pedit_act+0xc84/0x1200 [act_pedit] [...] RIP: 0010:tcf_pedit_act+0xc84/0x1200 [act_pedit] Code: 89 fa 48 c1 ea 03 0f b6 04 02 84 c0 74 08 3c 03 0f 8e ac 00 00 00 48 8b 44 24 10 48 c7 c7 a0 c4 e4 c0 8b 70 18 e8 1c 30 95 ea <0f> 0b e9 a0 fa ff ff e8 00 03 f5 ea e9 14 f4 ff ff 48 89 58 40 e9 RSP: 0018:ffff888077c9f320 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffffac2983a2 RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffff888053927bec RBP: dffffc0000000000 R08: ffffed100a726209 R09: ffffed100a726209 R10: 0000000000000001 R11: ffffed100a726208 R12: ffff88804beea780 R13: ffff888079a77400 R14: ffff88804beea780 R15: ffff888027ab2000 FS: 00007fdeec9bd740(0000) GS:ffff888053900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffdb3dfd000 CR3: 000000004adb4006 CR4: 00000000001606e0 Call Trace: tcf_action_exec+0x105/0x3f0 tcf_classify+0xf2/0x410 __dev_queue_xmit+0xcbf/0x2ae0 ip_finish_output2+0x711/0x1fb0 ip_output+0x1bf/0x4b0 ip_send_skb+0x37/0xa0 raw_sendmsg+0x180c/0x2430 sock_sendmsg+0xdb/0x110 __sys_sendto+0x257/0x2b0 __x64_sys_sendto+0xdd/0x1b0 do_syscall_64+0xa5/0x4e0 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fdeeb72e993 Code: 48 8b 0d e0 74 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 0d d6 2c 00 00 75 13 49 89 ca b8 2c 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 4b cc 00 00 48 89 04 24 RSP: 002b:00007ffdb3de8a18 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 000055c81972b700 RCX: 00007fdeeb72e993 RDX: 0000000000000040 RSI: 000055c81972b700 RDI: 0000000000000003 RBP: 00007ffdb3dea130 R08: 000055c819728510 R09: 0000000000000010 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000040 R13: 000055c81972b6c0 R14: 000055c81972969c R15: 0000000000000080 Fix this moving the check on 'nkeys' earlier in tcf_pedit_init(), so that attempts to install rules having 0 keys are always rejected with -EINVAL. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/sched/act_pedit.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 33c0cc5ef229..ce14fafb36a1 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -46,7 +46,7 @@ static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla, int err = -EINVAL; int rem; - if (!nla || !n) + if (!nla) return NULL; keys_ex = kcalloc(n, sizeof(*k), GFP_KERNEL); @@ -169,6 +169,10 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, } parm = nla_data(pattr); + if (!parm->nkeys) { + NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); + return -EINVAL; + } ksize = parm->nkeys * sizeof(struct tc_pedit_key); if (nla_len(pattr) < sizeof(*parm) + ksize) { NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid"); @@ -182,12 +186,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - if (!parm->nkeys) { - tcf_idr_cleanup(tn, index); - NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); - ret = -EINVAL; - goto out_free; - } ret = tcf_idr_create(tn, index, est, a, &act_pedit_ops, bind, false); if (ret) { From 13512a5eb818d6787433eee1d67877437f8c9f12 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 18 Nov 2019 17:39:34 +0800 Subject: [PATCH 006/299] net: sched: ensure opts_len <= IP_TUNNEL_OPTS_MAX in act_tunnel_key [ Upstream commit 4f0e97d070984d487df027f163e52bb72d1713d8 ] info->options_len is 'u8' type, and when opts_len with a value > IP_TUNNEL_OPTS_MAX, 'info->options_len = opts_len' will cast int to u8 and set a wrong value to info->options_len. Kernel crashed in my test when doing: # opts="0102:80:00800022" # for i in {1..99}; do opts="$opts,0102:80:00800022"; done # ip link add name geneve0 type geneve dstport 0 external # tc qdisc add dev eth0 ingress # tc filter add dev eth0 protocol ip parent ffff: \ flower indev eth0 ip_proto udp action tunnel_key \ set src_ip 10.0.99.192 dst_ip 10.0.99.193 \ dst_port 6081 id 11 geneve_opts $opts \ action mirred egress redirect dev geneve0 So we should do the similar check as cls_flower does, return error when opts_len > IP_TUNNEL_OPTS_MAX in tunnel_key_copy_opts(). Fixes: 0ed5269f9e41 ("net/sched: add tunnel option support to act_tunnel_key") Signed-off-by: Xin Long Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/sched/act_tunnel_key.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 43309ff2b5dc..e4fc6b2bc29d 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -137,6 +137,10 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, if (opt_len < 0) return opt_len; opts_len += opt_len; + if (opts_len > IP_TUNNEL_OPTS_MAX) { + NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size"); + return -EINVAL; + } if (dst) { dst_len -= opt_len; dst += opt_len; From 1ff2a0f8692f48c1081554a4226cfd3913c0ff4f Mon Sep 17 00:00:00 2001 From: Martin Habets Date: Thu, 21 Nov 2019 17:52:15 +0000 Subject: [PATCH 007/299] sfc: Only cancel the PPS workqueue if it exists [ Upstream commit 723eb53690041740a13ac78efeaf6804f5d684c9 ] The workqueue only exists for the primary PF. For other functions we hit a WARN_ON in kernel/workqueue.c. Fixes: 7c236c43b838 ("sfc: Add support for IEEE-1588 PTP") Signed-off-by: Martin Habets Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/sfc/ptp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index f21661532ed3..cc8fbf398c0d 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -1534,7 +1534,8 @@ void efx_ptp_remove(struct efx_nic *efx) (void)efx_ptp_disable(efx); cancel_work_sync(&efx->ptp_data->work); - cancel_work_sync(&efx->ptp_data->pps_work); + if (efx->ptp_data->pps_workwq) + cancel_work_sync(&efx->ptp_data->pps_work); skb_queue_purge(&efx->ptp_data->rxq); skb_queue_purge(&efx->ptp_data->txq); From 7c1a5381778288e4b4c18780916285ffa4d2ab77 Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Wed, 13 Nov 2019 14:42:00 +0200 Subject: [PATCH 008/299] net/mlx5e: Fix set vf link state error flow [ Upstream commit 751021218f7e66ee9bbaa2be23056e447cd75ec4 ] Before this commit the ndo always returned success. Fix that. Fixes: 1ab2068a4c66 ("net/mlx5: Implement vports admin state backup/restore") Signed-off-by: Roi Dayan Reviewed-by: Vlad Buslov Signed-off-by: Saeed Mahameed Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 55ccd90beeb0..7366033cd31c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1861,7 +1861,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, unlock: mutex_unlock(&esw->state_lock); - return 0; + return err; } int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw, From 28a4cc2b5d6fcf468adb615930ee3439f198dee2 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Sun, 17 Nov 2019 10:18:59 +0200 Subject: [PATCH 009/299] net/mlxfw: Verify FSM error code translation doesn't exceed array size [ Upstream commit 30e9e0550bf693c94bc15827781fe42dd60be634 ] Array mlxfw_fsm_state_err_str contains value to string translation, when values are provided by mlxfw_dev. If value is larger than MLXFW_FSM_STATE_ERR_MAX, return "unknown error" as expected instead of reading an address than exceed array size. Fixes: 410ed13cae39 ("Add the mlxfw module for Mellanox firmware flash process") Signed-off-by: Eran Ben Elisha Acked-by: Jiri Pirko Signed-off-by: Saeed Mahameed Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c index 2cf89126fb23..d765e7a69d6b 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c @@ -86,6 +86,8 @@ retry: return err; if (fsm_state_err != MLXFW_FSM_STATE_ERR_OK) { + fsm_state_err = min_t(enum mlxfw_fsm_state_err, + fsm_state_err, MLXFW_FSM_STATE_ERR_MAX); pr_err("Firmware flash failed: %s\n", mlxfw_fsm_state_err_str[fsm_state_err]); return -EINVAL; From 48bc34efbc655e9f569c1620d13fc7d3182d6f2d Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Thu, 5 Sep 2019 09:56:10 +0300 Subject: [PATCH 010/299] net/mlx5: Fix auto group size calculation [ Upstream commit 97fd8da281f80e7e69e0114bc906575734d4dfaf ] Once all the large flow groups (defined by the user when the flow table is created - max_num_groups) were created, then all the following new flow groups will have only one flow table entry, even though the flow table has place to larger groups. Fix the condition to prefer large flow group. Fixes: f0d22d187473 ("net/mlx5_core: Introduce flow steering autogrouped flow table") Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 10 ++++++---- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 1 + 2 files changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index c079f85593d6..82a53317285d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -520,7 +520,7 @@ static void del_sw_flow_group(struct fs_node *node) rhashtable_destroy(&fg->ftes_hash); ida_destroy(&fg->fte_allocator); - if (ft->autogroup.active) + if (ft->autogroup.active && fg->max_ftes == ft->autogroup.group_size) ft->autogroup.num_groups--; err = rhltable_remove(&ft->fgs_hash, &fg->hash, @@ -1065,6 +1065,8 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, ft->autogroup.active = true; ft->autogroup.required_groups = max_num_groups; + /* We save place for flow groups in addition to max types */ + ft->autogroup.group_size = ft->max_fte / (max_num_groups + 1); return ft; } @@ -1270,8 +1272,7 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table *ft return ERR_PTR(-ENOENT); if (ft->autogroup.num_groups < ft->autogroup.required_groups) - /* We save place for flow groups in addition to max types */ - group_size = ft->max_fte / (ft->autogroup.required_groups + 1); + group_size = ft->autogroup.group_size; /* ft->max_fte == ft->autogroup.max_types */ if (group_size == 0) @@ -1298,7 +1299,8 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table *ft if (IS_ERR(fg)) goto out; - ft->autogroup.num_groups++; + if (group_size == ft->autogroup.group_size) + ft->autogroup.num_groups++; out: return fg; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 32070e5d993d..ba62fbce23a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -121,6 +121,7 @@ struct mlx5_flow_table { struct { bool active; unsigned int required_groups; + unsigned int group_size; unsigned int num_groups; } autogroup; /* Protect fwd_rules */ From 70d594d17ebb5c4e98bba6da2ec665fdbf82b0cb Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 30 Jul 2019 17:43:33 +0200 Subject: [PATCH 011/299] vhost/vsock: split packets to send using multiple buffers commit 6dbd3e66e7785a2f055bf84d98de9b8fd31ff3f5 upstream. If the packets to sent to the guest are bigger than the buffer available, we can split them, using multiple buffers and fixing the length in the packet header. This is safe since virtio-vsock supports only stream sockets. Signed-off-by: Stefano Garzarella Reviewed-by: Stefan Hajnoczi Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/vhost/vsock.c | 66 ++++++++++++++++++------- net/vmw_vsock/virtio_transport_common.c | 15 ++++-- 2 files changed, 60 insertions(+), 21 deletions(-) diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index bab495d73195..8dcee4faf701 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -103,7 +103,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, struct iov_iter iov_iter; unsigned out, in; size_t nbytes; - size_t len; + size_t iov_len, payload_len; int head; spin_lock_bh(&vsock->send_pkt_list_lock); @@ -148,8 +148,24 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, break; } - len = iov_length(&vq->iov[out], in); - iov_iter_init(&iov_iter, READ, &vq->iov[out], in, len); + iov_len = iov_length(&vq->iov[out], in); + if (iov_len < sizeof(pkt->hdr)) { + virtio_transport_free_pkt(pkt); + vq_err(vq, "Buffer len [%zu] too small\n", iov_len); + break; + } + + iov_iter_init(&iov_iter, READ, &vq->iov[out], in, iov_len); + payload_len = pkt->len - pkt->off; + + /* If the packet is greater than the space available in the + * buffer, we split it using multiple buffers. + */ + if (payload_len > iov_len - sizeof(pkt->hdr)) + payload_len = iov_len - sizeof(pkt->hdr); + + /* Set the correct length in the header */ + pkt->hdr.len = cpu_to_le32(payload_len); nbytes = copy_to_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter); if (nbytes != sizeof(pkt->hdr)) { @@ -158,33 +174,47 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, break; } - nbytes = copy_to_iter(pkt->buf, pkt->len, &iov_iter); - if (nbytes != pkt->len) { + nbytes = copy_to_iter(pkt->buf + pkt->off, payload_len, + &iov_iter); + if (nbytes != payload_len) { virtio_transport_free_pkt(pkt); vq_err(vq, "Faulted on copying pkt buf\n"); break; } - vhost_add_used(vq, head, sizeof(pkt->hdr) + pkt->len); + vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len); added = true; - if (pkt->reply) { - int val; - - val = atomic_dec_return(&vsock->queued_replies); - - /* Do we have resources to resume tx processing? */ - if (val + 1 == tx_vq->num) - restart_tx = true; - } - /* Deliver to monitoring devices all correctly transmitted * packets. */ virtio_transport_deliver_tap_pkt(pkt); - total_len += pkt->len; - virtio_transport_free_pkt(pkt); + pkt->off += payload_len; + total_len += payload_len; + + /* If we didn't send all the payload we can requeue the packet + * to send it with the next available buffer. + */ + if (pkt->off < pkt->len) { + spin_lock_bh(&vsock->send_pkt_list_lock); + list_add(&pkt->list, &vsock->send_pkt_list); + spin_unlock_bh(&vsock->send_pkt_list_lock); + } else { + if (pkt->reply) { + int val; + + val = atomic_dec_return(&vsock->queued_replies); + + /* Do we have resources to resume tx + * processing? + */ + if (val + 1 == tx_vq->num) + restart_tx = true; + } + + virtio_transport_free_pkt(pkt); + } } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); if (added) vhost_signal(&vsock->dev, vq); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 2a8651aa90c8..52242a148c70 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -92,8 +92,17 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) struct virtio_vsock_pkt *pkt = opaque; struct af_vsockmon_hdr *hdr; struct sk_buff *skb; + size_t payload_len; + void *payload_buf; - skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + pkt->len, + /* A packet could be split to fit the RX buffer, so we can retrieve + * the payload length from the header and the buffer pointer taking + * care of the offset in the original packet. + */ + payload_len = le32_to_cpu(pkt->hdr.len); + payload_buf = pkt->buf + pkt->off; + + skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + payload_len, GFP_ATOMIC); if (!skb) return NULL; @@ -133,8 +142,8 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) skb_put_data(skb, &pkt->hdr, sizeof(pkt->hdr)); - if (pkt->len) { - skb_put_data(skb, pkt->buf, pkt->len); + if (payload_len) { + skb_put_data(skb, payload_buf, payload_len); } return skb; From 7cb8ee734c18eec586c8ed061696b6211a7f158c Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 8 Nov 2019 17:07:46 +0100 Subject: [PATCH 012/299] gpio: max77620: Fixup debounce delays commit b0391479ae04dfcbd208b9571c375064caad9a57 upstream. When converting milliseconds to microseconds in commit fffa6af94894 ("gpio: max77620: Use correct unit for debounce times") some ~1 ms gaps were introduced between the various ranges supported by the controller. Fix this by changing the start of each range to the value immediately following the end of the previous range. This way a debounce time of, say 8250 us will translate into 16 ms instead of returning an -EINVAL error. Typically the debounce delay is only ever set through device tree and specified in milliseconds, so we can never really hit this issue because debounce times are always a multiple of 1000 us. The only notable exception for this is drivers/mmc/host/mmc-spi.c where the CD GPIO is requested, which passes a 1 us debounce time. According to a comment preceeding that code this should actually be 1 ms (i.e. 1000 us). Reported-by: Pavel Machek Signed-off-by: Thierry Reding Acked-by: Pavel Machek Cc: Signed-off-by: Bartosz Golaszewski Signed-off-by: Greg Kroah-Hartman --- drivers/gpio/gpio-max77620.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpio/gpio-max77620.c b/drivers/gpio/gpio-max77620.c index ac6c1c0548b6..78254ed93206 100644 --- a/drivers/gpio/gpio-max77620.c +++ b/drivers/gpio/gpio-max77620.c @@ -163,13 +163,13 @@ static int max77620_gpio_set_debounce(struct max77620_gpio *mgpio, case 0: val = MAX77620_CNFG_GPIO_DBNC_None; break; - case 1000 ... 8000: + case 1 ... 8000: val = MAX77620_CNFG_GPIO_DBNC_8ms; break; - case 9000 ... 16000: + case 8001 ... 16000: val = MAX77620_CNFG_GPIO_DBNC_16ms; break; - case 17000 ... 32000: + case 16001 ... 32000: val = MAX77620_CNFG_GPIO_DBNC_32ms; break; default: From 036588ec6888ad085c9a2edc5c0bac12297f5e35 Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Tue, 12 Nov 2019 17:10:26 -0500 Subject: [PATCH 013/299] tools: gpio: Correctly add make dependencies for gpio_utils commit 0161a94e2d1c713bd34d72bc0239d87c31747bf7 upstream. gpio tools fail to build correctly with make parallelization: $ make -s -j24 ld: gpio-utils.o: file not recognized: file truncated make[1]: *** [/home/labbott/linux_upstream/tools/build/Makefile.build:145: lsgpio-in.o] Error 1 make: *** [Makefile:43: lsgpio-in.o] Error 2 make: *** Waiting for unfinished jobs.... This is because gpio-utils.o is used across multiple targets. Fix this by making gpio-utios.o a proper dependency. Cc: Signed-off-by: Laura Abbott Signed-off-by: Bartosz Golaszewski Signed-off-by: Greg Kroah-Hartman --- tools/gpio/Build | 1 + tools/gpio/Makefile | 10 +++++++--- 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/tools/gpio/Build b/tools/gpio/Build index 620c1937d957..4141f35837db 100644 --- a/tools/gpio/Build +++ b/tools/gpio/Build @@ -1,3 +1,4 @@ +gpio-utils-y += gpio-utils.o lsgpio-y += lsgpio.o gpio-utils.o gpio-hammer-y += gpio-hammer.o gpio-utils.o gpio-event-mon-y += gpio-event-mon.o gpio-utils.o diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile index f8bc8656a544..6a73c06e069c 100644 --- a/tools/gpio/Makefile +++ b/tools/gpio/Makefile @@ -35,11 +35,15 @@ $(OUTPUT)include/linux/gpio.h: ../../include/uapi/linux/gpio.h prepare: $(OUTPUT)include/linux/gpio.h +GPIO_UTILS_IN := $(output)gpio-utils-in.o +$(GPIO_UTILS_IN): prepare FORCE + $(Q)$(MAKE) $(build)=gpio-utils + # # lsgpio # LSGPIO_IN := $(OUTPUT)lsgpio-in.o -$(LSGPIO_IN): prepare FORCE +$(LSGPIO_IN): prepare FORCE $(OUTPUT)gpio-utils-in.o $(Q)$(MAKE) $(build)=lsgpio $(OUTPUT)lsgpio: $(LSGPIO_IN) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ @@ -48,7 +52,7 @@ $(OUTPUT)lsgpio: $(LSGPIO_IN) # gpio-hammer # GPIO_HAMMER_IN := $(OUTPUT)gpio-hammer-in.o -$(GPIO_HAMMER_IN): prepare FORCE +$(GPIO_HAMMER_IN): prepare FORCE $(OUTPUT)gpio-utils-in.o $(Q)$(MAKE) $(build)=gpio-hammer $(OUTPUT)gpio-hammer: $(GPIO_HAMMER_IN) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ @@ -57,7 +61,7 @@ $(OUTPUT)gpio-hammer: $(GPIO_HAMMER_IN) # gpio-event-mon # GPIO_EVENT_MON_IN := $(OUTPUT)gpio-event-mon-in.o -$(GPIO_EVENT_MON_IN): prepare FORCE +$(GPIO_EVENT_MON_IN): prepare FORCE $(OUTPUT)gpio-utils-in.o $(Q)$(MAKE) $(build)=gpio-event-mon $(OUTPUT)gpio-event-mon: $(GPIO_EVENT_MON_IN) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ From 65d153c8ed6505075740f005122d01298f6e474a Mon Sep 17 00:00:00 2001 From: Sun Ke Date: Tue, 19 Nov 2019 14:09:11 +0800 Subject: [PATCH 014/299] nbd:fix memory leak in nbd_get_socket() commit dff10bbea4be47bdb615b036c834a275b7c68133 upstream. Before returning NULL, put the sock first. Cc: stable@vger.kernel.org Fixes: cf1b2326b734 ("nbd: verify socket is supported during setup") Reviewed-by: Josef Bacik Reviewed-by: Mike Christie Signed-off-by: Sun Ke Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/nbd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 867841c56a6d..d76840873420 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -945,6 +945,7 @@ static struct socket *nbd_get_socket(struct nbd_device *nbd, unsigned long fd, if (sock->ops->shutdown == sock_no_shutdown) { dev_err(disk_to_dev(nbd->disk), "Unsupported socket: shutdown callout must be supported.\n"); *err = -EINVAL; + sockfd_put(sock); return NULL; } From 67380639dfdbb6be15563b4973785d2bd4bc8f8a Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Thu, 14 Nov 2019 13:25:48 +0100 Subject: [PATCH 015/299] virtio_console: allocate inbufs in add_port() only if it is needed commit d791cfcbf98191122af70b053a21075cb450d119 upstream. When we hot unplug a virtserialport and then try to hot plug again, it fails: (qemu) chardev-add socket,id=serial0,path=/tmp/serial0,server,nowait (qemu) device_add virtserialport,bus=virtio-serial0.0,nr=2,\ chardev=serial0,id=serial0,name=serial0 (qemu) device_del serial0 (qemu) device_add virtserialport,bus=virtio-serial0.0,nr=2,\ chardev=serial0,id=serial0,name=serial0 kernel error: virtio-ports vport2p2: Error allocating inbufs qemu error: virtio-serial-bus: Guest failure in adding port 2 for device \ virtio-serial0.0 This happens because buffers for the in_vq are allocated when the port is added but are not released when the port is unplugged. They are only released when virtconsole is removed (see a7a69ec0d8e4) To avoid the problem and to be symmetric, we could allocate all the buffers in init_vqs() as they are released in remove_vqs(), but it sounds like a waste of memory. Rather than that, this patch changes add_port() logic to ignore ENOSPC error in fill_queue(), which means queue has already been filled. Fixes: a7a69ec0d8e4 ("virtio_console: free buffers after reset") Cc: mst@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Laurent Vivier Signed-off-by: Michael S. Tsirkin Signed-off-by: Greg Kroah-Hartman --- drivers/char/virtio_console.c | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index c55f6aeb4227..b353a5e5f8b1 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1349,24 +1349,24 @@ static void set_console_size(struct port *port, u16 rows, u16 cols) port->cons.ws.ws_col = cols; } -static unsigned int fill_queue(struct virtqueue *vq, spinlock_t *lock) +static int fill_queue(struct virtqueue *vq, spinlock_t *lock) { struct port_buffer *buf; - unsigned int nr_added_bufs; + int nr_added_bufs; int ret; nr_added_bufs = 0; do { buf = alloc_buf(vq->vdev, PAGE_SIZE, 0); if (!buf) - break; + return -ENOMEM; spin_lock_irq(lock); ret = add_inbuf(vq, buf); if (ret < 0) { spin_unlock_irq(lock); free_buf(buf, true); - break; + return ret; } nr_added_bufs++; spin_unlock_irq(lock); @@ -1386,7 +1386,6 @@ static int add_port(struct ports_device *portdev, u32 id) char debugfs_name[16]; struct port *port; dev_t devt; - unsigned int nr_added_bufs; int err; port = kmalloc(sizeof(*port), GFP_KERNEL); @@ -1445,11 +1444,13 @@ static int add_port(struct ports_device *portdev, u32 id) spin_lock_init(&port->outvq_lock); init_waitqueue_head(&port->waitqueue); - /* Fill the in_vq with buffers so the host can send us data. */ - nr_added_bufs = fill_queue(port->in_vq, &port->inbuf_lock); - if (!nr_added_bufs) { + /* We can safely ignore ENOSPC because it means + * the queue already has buffers. Buffers are removed + * only by virtcons_remove(), not by unplug_port() + */ + err = fill_queue(port->in_vq, &port->inbuf_lock); + if (err < 0 && err != -ENOSPC) { dev_err(port->dev, "Error allocating inbufs\n"); - err = -ENOMEM; goto free_device; } @@ -2083,14 +2084,11 @@ static int virtcons_probe(struct virtio_device *vdev) INIT_WORK(&portdev->control_work, &control_work_handler); if (multiport) { - unsigned int nr_added_bufs; - spin_lock_init(&portdev->c_ivq_lock); spin_lock_init(&portdev->c_ovq_lock); - nr_added_bufs = fill_queue(portdev->c_ivq, - &portdev->c_ivq_lock); - if (!nr_added_bufs) { + err = fill_queue(portdev->c_ivq, &portdev->c_ivq_lock); + if (err < 0) { dev_err(&vdev->dev, "Error allocating buffers for control queue\n"); /* @@ -2101,7 +2099,7 @@ static int virtcons_probe(struct virtio_device *vdev) VIRTIO_CONSOLE_DEVICE_READY, 0); /* Device was functional: we need full cleanup. */ virtcons_remove(vdev); - return -ENOMEM; + return err; } } else { /* From b28da9da6e51544f7e876ed6892f30b75c926742 Mon Sep 17 00:00:00 2001 From: Joseph Qi Date: Thu, 21 Nov 2019 17:53:52 -0800 Subject: [PATCH 016/299] Revert "fs: ocfs2: fix possible null-pointer dereferences in ocfs2_xa_prepare_entry()" commit 94b07b6f9e2e996afff7395de6b35f34f4cb10bf upstream. This reverts commit 56e94ea132bb5c2c1d0b60a6aeb34dcb7d71a53d. Commit 56e94ea132bb ("fs: ocfs2: fix possible null-pointer dereferences in ocfs2_xa_prepare_entry()") introduces a regression that fail to create directory with mount option user_xattr and acl. Actually the reported NULL pointer dereference case can be correctly handled by loc->xl_ops->xlo_add_entry(), so revert it. Link: http://lkml.kernel.org/r/1573624916-83825-1-git-send-email-joseph.qi@linux.alibaba.com Fixes: 56e94ea132bb ("fs: ocfs2: fix possible null-pointer dereferences in ocfs2_xa_prepare_entry()") Signed-off-by: Joseph Qi Reported-by: Thomas Voegtle Acked-by: Changwei Ge Cc: Jia-Ju Bai Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/xattr.c | 58 ++++++++++++++++++++++++++++-------------------- 1 file changed, 34 insertions(+), 24 deletions(-) diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 0d80e0df6c24..c146e12a8601 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -1498,6 +1498,18 @@ static int ocfs2_xa_check_space(struct ocfs2_xa_loc *loc, return loc->xl_ops->xlo_check_space(loc, xi); } +static void ocfs2_xa_add_entry(struct ocfs2_xa_loc *loc, u32 name_hash) +{ + loc->xl_ops->xlo_add_entry(loc, name_hash); + loc->xl_entry->xe_name_hash = cpu_to_le32(name_hash); + /* + * We can't leave the new entry's xe_name_offset at zero or + * add_namevalue() will go nuts. We set it to the size of our + * storage so that it can never be less than any other entry. + */ + loc->xl_entry->xe_name_offset = cpu_to_le16(loc->xl_size); +} + static void ocfs2_xa_add_namevalue(struct ocfs2_xa_loc *loc, struct ocfs2_xattr_info *xi) { @@ -2129,31 +2141,29 @@ static int ocfs2_xa_prepare_entry(struct ocfs2_xa_loc *loc, if (rc) goto out; - if (!loc->xl_entry) { - rc = -EINVAL; - goto out; - } - - if (ocfs2_xa_can_reuse_entry(loc, xi)) { - orig_value_size = loc->xl_entry->xe_value_size; - rc = ocfs2_xa_reuse_entry(loc, xi, ctxt); - if (rc) - goto out; - goto alloc_value; - } - - if (!ocfs2_xattr_is_local(loc->xl_entry)) { - orig_clusters = ocfs2_xa_value_clusters(loc); - rc = ocfs2_xa_value_truncate(loc, 0, ctxt); - if (rc) { - mlog_errno(rc); - ocfs2_xa_cleanup_value_truncate(loc, - "overwriting", - orig_clusters); - goto out; + if (loc->xl_entry) { + if (ocfs2_xa_can_reuse_entry(loc, xi)) { + orig_value_size = loc->xl_entry->xe_value_size; + rc = ocfs2_xa_reuse_entry(loc, xi, ctxt); + if (rc) + goto out; + goto alloc_value; } - } - ocfs2_xa_wipe_namevalue(loc); + + if (!ocfs2_xattr_is_local(loc->xl_entry)) { + orig_clusters = ocfs2_xa_value_clusters(loc); + rc = ocfs2_xa_value_truncate(loc, 0, ctxt); + if (rc) { + mlog_errno(rc); + ocfs2_xa_cleanup_value_truncate(loc, + "overwriting", + orig_clusters); + goto out; + } + } + ocfs2_xa_wipe_namevalue(loc); + } else + ocfs2_xa_add_entry(loc, name_hash); /* * If we get here, we have a blank entry. Fill it. We grow our From e8d355befc4220a6f15c8d75c76858f2eb36611d Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Thu, 21 Nov 2019 17:54:01 -0800 Subject: [PATCH 017/299] mm/ksm.c: don't WARN if page is still mapped in remove_stable_node() commit 9a63236f1ad82d71a98aa80320b6cb618fb32f44 upstream. It's possible to hit the WARN_ON_ONCE(page_mapped(page)) in remove_stable_node() when it races with __mmput() and squeezes in between ksm_exit() and exit_mmap(). WARNING: CPU: 0 PID: 3295 at mm/ksm.c:888 remove_stable_node+0x10c/0x150 Call Trace: remove_all_stable_nodes+0x12b/0x330 run_store+0x4ef/0x7b0 kernfs_fop_write+0x200/0x420 vfs_write+0x154/0x450 ksys_write+0xf9/0x1d0 do_syscall_64+0x99/0x510 entry_SYSCALL_64_after_hwframe+0x49/0xbe Remove the warning as there is nothing scary going on. Link: http://lkml.kernel.org/r/20191119131850.5675-1-aryabinin@virtuozzo.com Fixes: cbf86cfe04a6 ("ksm: remove old stable nodes more thoroughly") Signed-off-by: Andrey Ryabinin Acked-by: Hugh Dickins Cc: Andrea Arcangeli Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/ksm.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/mm/ksm.c b/mm/ksm.c index 5b0894b45ee5..b3ea0f0316eb 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -870,13 +870,13 @@ static int remove_stable_node(struct stable_node *stable_node) return 0; } - if (WARN_ON_ONCE(page_mapped(page))) { - /* - * This should not happen: but if it does, just refuse to let - * merge_across_nodes be switched - there is no need to panic. - */ - err = -EBUSY; - } else { + /* + * Page could be still mapped if this races with __mmput() running in + * between ksm_exit() and exit_mmap(). Just refuse to let + * merge_across_nodes/max_page_sharing be switched. + */ + err = -EBUSY; + if (!page_mapped(page)) { /* * The stable node did not yet appear stale to get_ksm_page(), * since that allows for an unmapped ksm page to be recognized From 8a67fbf6597122c4a5e2c48716bc441364357eef Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Thu, 14 Nov 2019 15:30:39 +0800 Subject: [PATCH 018/299] drm/amd/powerplay: issue no PPSMC_MSG_GetCurrPkgPwr on unsupported ASICs commit 355d991cb6ff6ae76b5e28b8edae144124c730e4 upstream. Otherwise, the error message prompted will confuse user. Signed-off-by: Evan Quan Acked-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- .../gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 23 +++++++++++++++---- 1 file changed, 18 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index c7c505095402..6bf032e81e39 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3472,18 +3472,31 @@ static int smu7_get_pp_table_entry(struct pp_hwmgr *hwmgr, static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr, u32 *query) { + struct amdgpu_device *adev = hwmgr->adev; int i; u32 tmp = 0; if (!query) return -EINVAL; - smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetCurrPkgPwr, 0); - tmp = cgs_read_register(hwmgr->device, mmSMC_MSG_ARG_0); - *query = tmp; + /* + * PPSMC_MSG_GetCurrPkgPwr is not supported on: + * - Hawaii + * - Bonaire + * - Fiji + * - Tonga + */ + if ((adev->asic_type != CHIP_HAWAII) && + (adev->asic_type != CHIP_BONAIRE) && + (adev->asic_type != CHIP_FIJI) && + (adev->asic_type != CHIP_TONGA)) { + smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetCurrPkgPwr, 0); + tmp = cgs_read_register(hwmgr->device, mmSMC_MSG_ARG_0); + *query = tmp; - if (tmp != 0) - return 0; + if (tmp != 0) + return 0; + } smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PmStatusLogStart); cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, From a0ee03bb5269b336f9d75f507f59dbcd83397fa1 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Sat, 9 Nov 2019 10:53:56 +0000 Subject: [PATCH 019/299] drm/i915/pmu: "Frequency" is reported as accumulated cycles commit add3eeed3683e2636ef524db48e1a678757c8e96 upstream. We report "frequencies" (actual-frequency, requested-frequency) as the number of accumulated cycles so that the average frequency over that period may be determined by the user. This means the units we report to the user are Mcycles (or just M), not MHz. Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Cc: stable@vger.kernel.org Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20191109105356.5273-1-chris@chris-wilson.co.uk (cherry picked from commit e88866ef02851c88fe95a4bb97820b94b4d46f36) Signed-off-by: Joonas Lahtinen (cherry picked from commit a7d87b70d6da96c6772e50728c8b4e78e4cbfd55) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_pmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index d6c8f8fdfda5..b7fda69342fc 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -827,8 +827,8 @@ create_event_attributes(struct drm_i915_private *i915) const char *name; const char *unit; } events[] = { - __event(I915_PMU_ACTUAL_FREQUENCY, "actual-frequency", "MHz"), - __event(I915_PMU_REQUESTED_FREQUENCY, "requested-frequency", "MHz"), + __event(I915_PMU_ACTUAL_FREQUENCY, "actual-frequency", "M"), + __event(I915_PMU_REQUESTED_FREQUENCY, "requested-frequency", "M"), __event(I915_PMU_INTERRUPTS, "interrupts", NULL), __event(I915_PMU_RC6_RESIDENCY, "rc6-residency", "ns"), }; From e80e88ef6057c7947409bda9898387d25e54aaa9 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 11 Nov 2019 13:32:03 +0000 Subject: [PATCH 020/299] drm/i915/userptr: Try to acquire the page lock around set_page_dirty() commit 2d691aeca4aecbb8d0414a777a46981a8e142b05 upstream. set_page_dirty says: For pages with a mapping this should be done under the page lock for the benefit of asynchronous memory errors who prefer a consistent dirty state. This rule can be broken in some special cases, but should be better not to. Under those rules, it is only safe for us to use the plain set_page_dirty calls for shmemfs/anonymous memory. Userptr may be used with real mappings and so needs to use the locked version (set_page_dirty_lock). However, following a try_to_unmap() we may want to remove the userptr and so call put_pages(). However, try_to_unmap() acquires the page lock and so we must avoid recursively locking the pages ourselves -- which means that we cannot safely acquire the lock around set_page_dirty(). Since we can't be sure of the lock, we have to risk skip dirtying the page, or else risk calling set_page_dirty() without a lock and so risk fs corruption. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203317 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=112012 Fixes: 5cc9ed4b9a7a ("drm/i915: Introduce mapping of user pages into video memory (userptr) ioctl") References: cb6d7c7dc7ff ("drm/i915/userptr: Acquire the page lock around set_page_dirty()") References: 505a8ec7e11a ("Revert "drm/i915/userptr: Acquire the page lock around set_page_dirty()"") References: 6dcc693bc57f ("ext4: warn when page is dirtied without buffers") Signed-off-by: Chris Wilson Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Joonas Lahtinen Cc: stable@vger.kernel.org Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20191111133205.11590-1-chris@chris-wilson.co.uk (cherry picked from commit 0d4bbe3d407f79438dc4f87943db21f7134cfc65) Signed-off-by: Joonas Lahtinen (cherry picked from commit cee7fb437edcdb2f9f8affa959e274997f5dca4d) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_gem_userptr.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c index 2c9b284036d1..961abb6ea18e 100644 --- a/drivers/gpu/drm/i915/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -691,8 +691,28 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj, i915_gem_gtt_finish_pages(obj, pages); for_each_sgt_page(page, sgt_iter, pages) { - if (obj->mm.dirty) + if (obj->mm.dirty && trylock_page(page)) { + /* + * As this may not be anonymous memory (e.g. shmem) + * but exist on a real mapping, we have to lock + * the page in order to dirty it -- holding + * the page reference is not sufficient to + * prevent the inode from being truncated. + * Play safe and take the lock. + * + * However...! + * + * The mmu-notifier can be invalidated for a + * migrate_page, that is alreadying holding the lock + * on the page. Such a try_to_unmap() will result + * in us calling put_pages() and so recursively try + * to lock the page. We avoid that deadlock with + * a trylock_page() and in exchange we risk missing + * some page dirtying. + */ set_page_dirty(page); + unlock_page(page); + } mark_page_accessed(page); put_page(page); From 49a9643b5e8d305876f8de52af7946379c77033d Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 13 Feb 2019 15:59:38 +0200 Subject: [PATCH 021/299] mwifiex: Fix NL80211_TX_POWER_LIMITED [ Upstream commit 65a576e27309120e0621f54d5c81eb9128bd56be ] NL80211_TX_POWER_LIMITED was treated as NL80211_TX_POWER_AUTOMATIC, which is the opposite of what should happen and can cause nasty regulatory problems. if/else converted to a switch without default to make gcc warn on unhandled enum values. Signed-off-by: Adrian Bunk Signed-off-by: Kalle Valo Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/mwifiex/cfg80211.c | 13 +++++++++++-- drivers/net/wireless/marvell/mwifiex/ioctl.h | 1 + drivers/net/wireless/marvell/mwifiex/sta_ioctl.c | 11 +++++++---- 3 files changed, 19 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c index 47ec5293c045..7b74ef71bef1 100644 --- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c +++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c @@ -376,11 +376,20 @@ mwifiex_cfg80211_set_tx_power(struct wiphy *wiphy, struct mwifiex_power_cfg power_cfg; int dbm = MBM_TO_DBM(mbm); - if (type == NL80211_TX_POWER_FIXED) { + switch (type) { + case NL80211_TX_POWER_FIXED: power_cfg.is_power_auto = 0; + power_cfg.is_power_fixed = 1; power_cfg.power_level = dbm; - } else { + break; + case NL80211_TX_POWER_LIMITED: + power_cfg.is_power_auto = 0; + power_cfg.is_power_fixed = 0; + power_cfg.power_level = dbm; + break; + case NL80211_TX_POWER_AUTOMATIC: power_cfg.is_power_auto = 1; + break; } priv = mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_ANY); diff --git a/drivers/net/wireless/marvell/mwifiex/ioctl.h b/drivers/net/wireless/marvell/mwifiex/ioctl.h index 48e154e1865d..0dd592ea6e83 100644 --- a/drivers/net/wireless/marvell/mwifiex/ioctl.h +++ b/drivers/net/wireless/marvell/mwifiex/ioctl.h @@ -267,6 +267,7 @@ struct mwifiex_ds_encrypt_key { struct mwifiex_power_cfg { u32 is_power_auto; + u32 is_power_fixed; u32 power_level; }; diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c index 843d65bba181..74e50566db1f 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c @@ -688,6 +688,9 @@ int mwifiex_set_tx_power(struct mwifiex_private *priv, txp_cfg = (struct host_cmd_ds_txpwr_cfg *) buf; txp_cfg->action = cpu_to_le16(HostCmd_ACT_GEN_SET); if (!power_cfg->is_power_auto) { + u16 dbm_min = power_cfg->is_power_fixed ? + dbm : priv->min_tx_power_level; + txp_cfg->mode = cpu_to_le32(1); pg_tlv = (struct mwifiex_types_power_group *) (buf + sizeof(struct host_cmd_ds_txpwr_cfg)); @@ -702,7 +705,7 @@ int mwifiex_set_tx_power(struct mwifiex_private *priv, pg->last_rate_code = 0x03; pg->modulation_class = MOD_CLASS_HR_DSSS; pg->power_step = 0; - pg->power_min = (s8) dbm; + pg->power_min = (s8) dbm_min; pg->power_max = (s8) dbm; pg++; /* Power group for modulation class OFDM */ @@ -710,7 +713,7 @@ int mwifiex_set_tx_power(struct mwifiex_private *priv, pg->last_rate_code = 0x07; pg->modulation_class = MOD_CLASS_OFDM; pg->power_step = 0; - pg->power_min = (s8) dbm; + pg->power_min = (s8) dbm_min; pg->power_max = (s8) dbm; pg++; /* Power group for modulation class HTBW20 */ @@ -718,7 +721,7 @@ int mwifiex_set_tx_power(struct mwifiex_private *priv, pg->last_rate_code = 0x20; pg->modulation_class = MOD_CLASS_HT; pg->power_step = 0; - pg->power_min = (s8) dbm; + pg->power_min = (s8) dbm_min; pg->power_max = (s8) dbm; pg->ht_bandwidth = HT_BW_20; pg++; @@ -727,7 +730,7 @@ int mwifiex_set_tx_power(struct mwifiex_private *priv, pg->last_rate_code = 0x20; pg->modulation_class = MOD_CLASS_HT; pg->power_step = 0; - pg->power_min = (s8) dbm; + pg->power_min = (s8) dbm_min; pg->power_max = (s8) dbm; pg->ht_bandwidth = HT_BW_40; } From 3757657af27ea8314c05f78dbae3105d2b40ed29 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Fri, 12 Oct 2018 14:25:22 +0900 Subject: [PATCH 022/299] ALSA: isight: fix leak of reference to firewire unit in error path of .probe callback [ Upstream commit 51e68fb0929c29e47e9074ca3e99ffd6021a1c5a ] In some error paths, reference count of firewire unit is not decreased. This commit fixes the bug. Fixes: 5b14ec25a79b('ALSA: firewire: release reference count of firewire unit in .remove callback of bus driver') Signed-off-by: Takashi Sakamoto Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/firewire/isight.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/sound/firewire/isight.c b/sound/firewire/isight.c index 30957477e005..0717ab9e48e3 100644 --- a/sound/firewire/isight.c +++ b/sound/firewire/isight.c @@ -640,7 +640,7 @@ static int isight_probe(struct fw_unit *unit, if (!isight->audio_base) { dev_err(&unit->device, "audio unit base not found\n"); err = -ENXIO; - goto err_unit; + goto error; } fw_iso_resources_init(&isight->resources, unit); @@ -669,12 +669,12 @@ static int isight_probe(struct fw_unit *unit, dev_set_drvdata(&unit->device, isight); return 0; - -err_unit: - fw_unit_put(isight->unit); - mutex_destroy(&isight->mutex); error: snd_card_free(card); + + mutex_destroy(&isight->mutex); + fw_unit_put(isight->unit); + return err; } From 8888689bd43356f17750992e3723e3271a6abeee Mon Sep 17 00:00:00 2001 From: Michael Schupikov Date: Sun, 7 Oct 2018 13:58:10 +0200 Subject: [PATCH 023/299] crypto: testmgr - fix sizeof() on COMP_BUF_SIZE [ Upstream commit 22a8118d329334833cd30f2ceb36d28e8cae8a4f ] After allocation, output and decomp_output both point to memory chunks of size COMP_BUF_SIZE. Then, only the first bytes are zeroed out using sizeof(COMP_BUF_SIZE) as parameter to memset(), because sizeof(COMP_BUF_SIZE) provides the size of the constant and not the size of allocated memory. Instead, the whole allocated memory is meant to be zeroed out. Use COMP_BUF_SIZE as parameter to memset() directly in order to accomplish this. Fixes: 336073840a872 ("crypto: testmgr - Allow different compression results") Signed-off-by: Michael Schupikov Reviewed-by: Ard Biesheuvel Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- crypto/testmgr.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/crypto/testmgr.c b/crypto/testmgr.c index 3664c26f4838..13cb2ea99d6a 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -1400,8 +1400,8 @@ static int test_comp(struct crypto_comp *tfm, int ilen; unsigned int dlen = COMP_BUF_SIZE; - memset(output, 0, sizeof(COMP_BUF_SIZE)); - memset(decomp_output, 0, sizeof(COMP_BUF_SIZE)); + memset(output, 0, COMP_BUF_SIZE); + memset(decomp_output, 0, COMP_BUF_SIZE); ilen = ctemplate[i].inlen; ret = crypto_comp_compress(tfm, ctemplate[i].input, @@ -1445,7 +1445,7 @@ static int test_comp(struct crypto_comp *tfm, int ilen; unsigned int dlen = COMP_BUF_SIZE; - memset(decomp_output, 0, sizeof(COMP_BUF_SIZE)); + memset(decomp_output, 0, COMP_BUF_SIZE); ilen = dtemplate[i].inlen; ret = crypto_comp_decompress(tfm, dtemplate[i].input, From 90d73768ddb6eac2df86c60072fbfe4d87e1d051 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Tue, 2 Oct 2018 11:38:35 +0900 Subject: [PATCH 024/299] printk: lock/unlock console only for new logbuf entries [ Upstream commit 3ac37a93fa9217e576bebfd4ba3e80edaaeb2289 ] Prior to commit 5c2992ee7fd8a29 ("printk: remove console flushing special cases for partial buffered lines") we would do console_cont_flush() for each pr_cont() to print cont fragments, so console_unlock() would actually print data: pr_cont(); console_lock(); console_unlock() console_cont_flush(); // print cont fragment ... pr_cont(); console_lock(); console_unlock() console_cont_flush(); // print cont fragment We don't do console_cont_flush() anymore, so when we do pr_cont() console_unlock() does nothing (unless we flushed the cont buffer): pr_cont(); console_lock(); console_unlock(); // noop ... pr_cont(); console_lock(); console_unlock(); // noop ... pr_cont(); cont_flush(); console_lock(); console_unlock(); // print data We also wakeup klogd purposelessly for pr_cont() output - un-flushed cont buffer is not stored in log_buf; there is nothing to pull. Thus we can console_lock()/console_unlock()/wake_up_klogd() only when we know that we log_store()-ed a message and there is something to print to the consoles/syslog. Link: http://lkml.kernel.org/r/20181002023836.4487-3-sergey.senozhatsky@gmail.com To: Steven Rostedt Cc: Andrew Morton Cc: Dmitriy Vyukov Cc: Tetsuo Handa Cc: Tejun Heo Cc: Peter Zijlstra Cc: LKML Cc: Sergey Senozhatsky Signed-off-by: Sergey Senozhatsky Signed-off-by: Petr Mladek Signed-off-by: Sasha Levin --- kernel/printk/printk.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index c7b3d5489937..59ceaed1aeed 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1901,8 +1901,9 @@ asmlinkage int vprintk_emit(int facility, int level, const char *fmt, va_list args) { int printed_len; - bool in_sched = false; + bool in_sched = false, pending_output; unsigned long flags; + u64 curr_log_seq; if (level == LOGLEVEL_SCHED) { level = LOGLEVEL_DEFAULT; @@ -1914,11 +1915,13 @@ asmlinkage int vprintk_emit(int facility, int level, /* This stops the holder of console_sem just where we want him */ logbuf_lock_irqsave(flags); + curr_log_seq = log_next_seq; printed_len = vprintk_store(facility, level, dict, dictlen, fmt, args); + pending_output = (curr_log_seq != log_next_seq); logbuf_unlock_irqrestore(flags); /* If called from the scheduler, we can not call up(). */ - if (!in_sched) { + if (!in_sched && pending_output) { /* * Disable preemption to avoid being preempted while holding * console_sem which would prevent anyone from printing to @@ -1935,7 +1938,8 @@ asmlinkage int vprintk_emit(int facility, int level, preempt_enable(); } - wake_up_klogd(); + if (pending_output) + wake_up_klogd(); return printed_len; } EXPORT_SYMBOL(vprintk_emit); From 4465a916eaa733c0dd369a108a4c0c349bfcc013 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Wed, 10 Oct 2018 20:33:08 +0900 Subject: [PATCH 025/299] printk: fix integer overflow in setup_log_buf() [ Upstream commit d2130e82e9454304e9b91ba9da551b5989af8c27 ] The way we calculate logbuf free space percentage overflows signed integer: int free; free = __LOG_BUF_LEN - log_next_idx; pr_info("early log buf free: %u(%u%%)\n", free, (free * 100) / __LOG_BUF_LEN); We support LOG_BUF_LEN of up to 1<<25 bytes. Since setup_log_buf() is called during early init, logbuf is mostly empty, so __LOG_BUF_LEN - log_next_idx is close to 1<<25. Thus when we multiply it by 100, we overflow signed integer value range: 100 is 2^6 + 2^5 + 2^2. Example, booting with LOG_BUF_LEN 1<<25 and log_buf_len=2G boot param: [ 0.075317] log_buf_len: -2147483648 bytes [ 0.075319] early log buf free: 33549896(-28%) Make "free" unsigned integer and use appropriate printk() specifier. Link: http://lkml.kernel.org/r/20181010113308.9337-1-sergey.senozhatsky@gmail.com To: Steven Rostedt Cc: linux-kernel@vger.kernel.org Cc: Sergey Senozhatsky Signed-off-by: Sergey Senozhatsky Signed-off-by: Petr Mladek Signed-off-by: Sasha Levin --- kernel/printk/printk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 59ceaed1aeed..845efadaf7ec 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1105,7 +1105,7 @@ void __init setup_log_buf(int early) { unsigned long flags; char *new_log_buf; - int free; + unsigned int free; if (log_buf != __log_buf) return; From ca71f9c8adc2f61246158a1bdc9cd5e21db52773 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 10 Oct 2018 17:13:13 +0200 Subject: [PATCH 026/299] pinctrl: madera: Fix uninitialized variable bug in madera_mux_set_mux [ Upstream commit 4fe81669df50889ff1072c030c59df5f1fa6534e ] There is a potential execution path in which variable *ret* is checked in an IF statement, and then its value is used to report an error at line 659 without being properly initialized previously: 659 if (ret) 660 dev_err(priv->dev, "Failed to write to 0x%x (%d)\n", reg, ret); Fix this by initializing variable *ret* to 0 in order to avoid unpredictable or unintended results. Addresses-Coverity-ID: 1471969 ("Uninitialized scalar variable") Fixes: 218d72a77b0b ("pinctrl: madera: Add driver for Cirrus Logic Madera codecs") Signed-off-by: Gustavo A. R. Silva Acked-by: Charles Keepax Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/cirrus/pinctrl-madera-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/cirrus/pinctrl-madera-core.c b/drivers/pinctrl/cirrus/pinctrl-madera-core.c index c4f4d904e4a6..618e04407ac8 100644 --- a/drivers/pinctrl/cirrus/pinctrl-madera-core.c +++ b/drivers/pinctrl/cirrus/pinctrl-madera-core.c @@ -608,7 +608,7 @@ static int madera_mux_set_mux(struct pinctrl_dev *pctldev, unsigned int n_chip_groups = priv->chip->n_pin_groups; const char *func_name = madera_mux_funcs[selector].name; unsigned int reg; - int i, ret; + int i, ret = 0; dev_dbg(priv->dev, "%s selecting %u (%s) for group %u (%s)\n", __func__, selector, func_name, group, From 26a4c6a562ceb419e42cd5b0fa05752b8ff3db60 Mon Sep 17 00:00:00 2001 From: Alan Douglas Date: Thu, 11 Oct 2018 17:15:54 +0100 Subject: [PATCH 027/299] PCI: cadence: Write MSI data with 32bits [ Upstream commit e81e36a96bb56f243b5ac1d114c37c086761595b ] According to the PCIe specification, although the MSI data is only 16bits, the upper 16bits should be written as 0. Use writel instead of writew when writing the MSI data to the host. Fixes: 37dddf14f1ae ("PCI: cadence: Add EndPoint Controller driver for Cadence PCIe controller") Signed-off-by: Alan Douglas Signed-off-by: Lorenzo Pieralisi Signed-off-by: Sasha Levin --- drivers/pci/controller/pcie-cadence-ep.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/controller/pcie-cadence-ep.c b/drivers/pci/controller/pcie-cadence-ep.c index 6692654798d4..c3a088910f48 100644 --- a/drivers/pci/controller/pcie-cadence-ep.c +++ b/drivers/pci/controller/pcie-cadence-ep.c @@ -355,7 +355,7 @@ static int cdns_pcie_ep_send_msi_irq(struct cdns_pcie_ep *ep, u8 fn, ep->irq_pci_addr = (pci_addr & ~pci_addr_mask); ep->irq_pci_fn = fn; } - writew(data, ep->irq_cpu_addr + (pci_addr & pci_addr_mask)); + writel(data, ep->irq_cpu_addr + (pci_addr & pci_addr_mask)); return 0; } From fa3fe5f442ab54662458489212c6c781c5408bd8 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 27 Sep 2018 15:30:25 +0100 Subject: [PATCH 028/299] gfs2: Fix marking bitmaps non-full [ Upstream commit ec23df2b0cf3e1620f5db77972b7fb735f267eff ] Reservations in gfs can span multiple gfs2_bitmaps (but they won't span multiple resource groups). When removing a reservation, we want to clear the GBF_FULL flags of all involved gfs2_bitmaps, not just that of the first bitmap. Signed-off-by: Andreas Gruenbacher Signed-off-by: Bob Peterson Reviewed-by: Steven Whitehouse Signed-off-by: Sasha Levin --- fs/gfs2/rgrp.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 63e5387c84d2..c94c4ac1ae78 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -642,7 +642,10 @@ static void __rs_deltree(struct gfs2_blkreserv *rs) RB_CLEAR_NODE(&rs->rs_node); if (rs->rs_free) { - struct gfs2_bitmap *bi = rbm_bi(&rs->rs_rbm); + u64 last_block = gfs2_rbm_to_block(&rs->rs_rbm) + + rs->rs_free - 1; + struct gfs2_rbm last_rbm = { .rgd = rs->rs_rbm.rgd, }; + struct gfs2_bitmap *start, *last; /* return reserved blocks to the rgrp */ BUG_ON(rs->rs_rbm.rgd->rd_reserved < rs->rs_free); @@ -653,7 +656,13 @@ static void __rs_deltree(struct gfs2_blkreserv *rs) it will force the number to be recalculated later. */ rgd->rd_extfail_pt += rs->rs_free; rs->rs_free = 0; - clear_bit(GBF_FULL, &bi->bi_flags); + if (gfs2_rbm_from_block(&last_rbm, last_block)) + return; + start = rbm_bi(&rs->rs_rbm); + last = rbm_bi(&last_rbm); + do + clear_bit(GBF_FULL, &start->bi_flags); + while (start++ != last); } } From 8d67a4ecb4735292427fc54fcb604328122aa0a6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 12 Sep 2018 20:53:46 -0400 Subject: [PATCH 029/299] pty: fix compat ioctls [ Upstream commit 50f45326afab723df529eca54095e2feac24da2d ] pointer-taking ones need compat_ptr(); int-taking one doesn't. Signed-off-by: Al Viro Signed-off-by: Sasha Levin --- drivers/tty/pty.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 678406e0948b..00099a8439d2 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -28,6 +28,7 @@ #include #include #include +#include #undef TTY_DEBUG_HANGUP #ifdef TTY_DEBUG_HANGUP @@ -488,6 +489,7 @@ static int pty_bsd_ioctl(struct tty_struct *tty, return -ENOIOCTLCMD; } +#ifdef CONFIG_COMPAT static long pty_bsd_compat_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { @@ -495,8 +497,11 @@ static long pty_bsd_compat_ioctl(struct tty_struct *tty, * PTY ioctls don't require any special translation between 32-bit and * 64-bit userspace, they are already compatible. */ - return pty_bsd_ioctl(tty, cmd, arg); + return pty_bsd_ioctl(tty, cmd, (unsigned long)compat_ptr(arg)); } +#else +#define pty_bsd_compat_ioctl NULL +#endif static int legacy_count = CONFIG_LEGACY_PTY_COUNT; /* @@ -676,6 +681,7 @@ static int pty_unix98_ioctl(struct tty_struct *tty, return -ENOIOCTLCMD; } +#ifdef CONFIG_COMPAT static long pty_unix98_compat_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { @@ -683,8 +689,12 @@ static long pty_unix98_compat_ioctl(struct tty_struct *tty, * PTY ioctls don't require any special translation between 32-bit and * 64-bit userspace, they are already compatible. */ - return pty_unix98_ioctl(tty, cmd, arg); + return pty_unix98_ioctl(tty, cmd, + cmd == TIOCSIG ? arg : (unsigned long)compat_ptr(arg)); } +#else +#define pty_unix98_compat_ioctl NULL +#endif /** * ptm_unix98_lookup - find a pty master From 93b943c0602f98999a274ec2c09a98771d54e134 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 12 Sep 2018 20:57:18 -0400 Subject: [PATCH 030/299] synclink_gt(): fix compat_ioctl() [ Upstream commit 27230e51349fde075598c1b59d15e1ff802f3f6e ] compat_ptr() for pointer-taking ones... Signed-off-by: Al Viro Signed-off-by: Sasha Levin --- drivers/tty/synclink_gt.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c index a94086597ebd..b88ecf102764 100644 --- a/drivers/tty/synclink_gt.c +++ b/drivers/tty/synclink_gt.c @@ -1186,14 +1186,13 @@ static long slgt_compat_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct slgt_info *info = tty->driver_data; - int rc = -ENOIOCTLCMD; + int rc; if (sanity_check(info, tty->name, "compat_ioctl")) return -ENODEV; DBGINFO(("%s compat_ioctl() cmd=%08X\n", info->device_name, cmd)); switch (cmd) { - case MGSL_IOCSPARAMS32: rc = set_params32(info, compat_ptr(arg)); break; @@ -1213,18 +1212,11 @@ static long slgt_compat_ioctl(struct tty_struct *tty, case MGSL_IOCWAITGPIO: case MGSL_IOCGXSYNC: case MGSL_IOCGXCTRL: - case MGSL_IOCSTXIDLE: - case MGSL_IOCTXENABLE: - case MGSL_IOCRXENABLE: - case MGSL_IOCTXABORT: - case TIOCMIWAIT: - case MGSL_IOCSIF: - case MGSL_IOCSXSYNC: - case MGSL_IOCSXCTRL: - rc = ioctl(tty, cmd, arg); + rc = ioctl(tty, cmd, (unsigned long)compat_ptr(arg)); break; + default: + rc = ioctl(tty, cmd, arg); } - DBGINFO(("%s compat_ioctl() cmd=%08X rc=%d\n", info->device_name, cmd, rc)); return rc; } From 4505cff2ef4a6df512bf329c02fc73ffbead23d6 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 1 Oct 2018 19:44:58 +0300 Subject: [PATCH 031/299] powerpc: Fix signedness bug in update_flash_db() [ Upstream commit 014704e6f54189a203cc14c7c0bb411b940241bc ] The "count < sizeof(struct os_area_db)" comparison is type promoted to size_t so negative values of "count" are treated as very high values and we accidentally return success instead of a negative error code. This doesn't really change runtime much but it fixes a static checker warning. Signed-off-by: Dan Carpenter Acked-by: Geoff Levand Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- arch/powerpc/platforms/ps3/os-area.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/ps3/os-area.c b/arch/powerpc/platforms/ps3/os-area.c index cdbfc5cfd6f3..f5387ad82279 100644 --- a/arch/powerpc/platforms/ps3/os-area.c +++ b/arch/powerpc/platforms/ps3/os-area.c @@ -664,7 +664,7 @@ static int update_flash_db(void) db_set_64(db, &os_area_db_id_rtc_diff, saved_params.rtc_diff); count = os_area_flash_write(db, sizeof(struct os_area_db), pos); - if (count < sizeof(struct os_area_db)) { + if (count < 0 || count < sizeof(struct os_area_db)) { pr_debug("%s: os_area_flash_write failed %zd\n", __func__, count); error = count < 0 ? count : -EIO; From 5346c840373348deb53bb2977ffb6b340770d201 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Wed, 10 Oct 2018 09:58:03 +1030 Subject: [PATCH 032/299] powerpc/boot: Fix opal console in boot wrapper [ Upstream commit 1a855eaccf353f7ed1d51a3d4b3af727ccbd81ca ] As of commit 10c77dba40ff ("powerpc/boot: Fix build failure in 32-bit boot wrapper") the opal code is hidden behind CONFIG_PPC64_BOOT_WRAPPER, but the boot wrapper avoids include/linux, so it does not get the normal Kconfig flags. We can drop the guard entirely as in commit f8e8e69cea49 ("powerpc/boot: Only build OPAL code when necessary") the makefile only includes opal.c in the build if CONFIG_PPC64_BOOT_WRAPPER is set. Fixes: 10c77dba40ff ("powerpc/boot: Fix build failure in 32-bit boot wrapper") Signed-off-by: Joel Stanley Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- arch/powerpc/boot/opal.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/arch/powerpc/boot/opal.c b/arch/powerpc/boot/opal.c index 0272570d02de..dfb199ef5b94 100644 --- a/arch/powerpc/boot/opal.c +++ b/arch/powerpc/boot/opal.c @@ -13,8 +13,6 @@ #include #include "../include/asm/opal-api.h" -#ifdef CONFIG_PPC64_BOOT_WRAPPER - /* Global OPAL struct used by opal-call.S */ struct opal { u64 base; @@ -101,9 +99,3 @@ int opal_console_init(void *devp, struct serial_console_data *scdp) return 0; } -#else -int opal_console_init(void *devp, struct serial_console_data *scdp) -{ - return -1; -} -#endif /* __powerpc64__ */ From 16e4657a1d2542dba2fce2c91ace742e2e47f6e7 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Wed, 10 Oct 2018 13:15:22 +1030 Subject: [PATCH 033/299] powerpc/boot: Disable vector instructions [ Upstream commit e8e132e6885962582784b6fa16a80d07ea739c0f ] This will avoid auto-vectorisation when building with higher optimisation levels. We don't know if the machine can support VSX and even if it's present it's probably not going to be enabled at this point in boot. These flag were both added prior to GCC 4.6 which is the minimum compiler version supported by upstream, thanks to Segher for the details. Signed-off-by: Joel Stanley Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- arch/powerpc/boot/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 25e3184f11f7..7d5ddf53750c 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -32,8 +32,8 @@ else endif BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ - -fno-strict-aliasing -Os -msoft-float -pipe \ - -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ + -fno-strict-aliasing -Os -msoft-float -mno-altivec -mno-vsx \ + -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ -D$(compress-y) ifdef CONFIG_PPC64_BOOT_WRAPPER From bd2a7e53cd6e246ff469761bddc21c04d8d3d9a8 Mon Sep 17 00:00:00 2001 From: Sam Bobroff Date: Wed, 12 Sep 2018 11:23:21 +1000 Subject: [PATCH 034/299] powerpc/eeh: Fix null deref for devices removed during EEH [ Upstream commit bcbe3730531239abd45ab6c6af4a18078b37dd47 ] If a device is removed during EEH processing (either by a driver's handler or as part of recovery), it can lead to a null dereference in eeh_pe_report_edev(). To handle this, skip devices that have been removed. Signed-off-by: Sam Bobroff Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- arch/powerpc/kernel/eeh_driver.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 110eba400de7..af1f3d5f9a0f 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -281,6 +281,10 @@ static void eeh_pe_report_edev(struct eeh_dev *edev, eeh_report_fn fn, struct pci_driver *driver; enum pci_ers_result new_result; + if (!edev->pdev) { + eeh_edev_info(edev, "no device"); + return; + } device_lock(&edev->pdev->dev); if (eeh_edev_actionable(edev)) { driver = eeh_pcid_get(edev->pdev); From 97aab1a43a2fbefdd863db2fd794bcf4a2edf273 Mon Sep 17 00:00:00 2001 From: Sam Bobroff Date: Wed, 12 Sep 2018 11:23:22 +1000 Subject: [PATCH 035/299] powerpc/eeh: Fix use of EEH_PE_KEEP on wrong field [ Upstream commit 473af09b56dc4be68e4af33220ceca6be67aa60d ] eeh_add_to_parent_pe() sometimes removes the EEH_PE_KEEP flag, but it incorrectly removes it from pe->type, instead of pe->state. However, rather than clearing it from the correct field, remove it. Inspection of the code shows that it can't ever have had any effect (even if it had been cleared from the correct field), because the field is never tested after it is cleared by the statement in question. The clear statement was added by commit 807a827d4e74 ("powerpc/eeh: Keep PE during hotplug"), but it didn't explain why it was necessary. Signed-off-by: Sam Bobroff Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- arch/powerpc/kernel/eeh_pe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 1b238ecc553e..210d239a9395 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -379,7 +379,7 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) while (parent) { if (!(parent->type & EEH_PE_INVALID)) break; - parent->type &= ~(EEH_PE_INVALID | EEH_PE_KEEP); + parent->type &= ~EEH_PE_INVALID; parent = parent->parent; } From b95998fb6c500790fc4f13ae5feadac72cfa4e1d Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 13 Oct 2018 13:28:43 +0300 Subject: [PATCH 036/299] EDAC, thunderx: Fix memory leak in thunderx_l2c_threaded_isr() [ Upstream commit d8c27ba86a2fd806d3957e5a9b30e66dfca2a61d ] Fix memory leak in L2c threaded interrupt handler. [ bp: Rewrite commit message. ] Fixes: 41003396f932 ("EDAC, thunderx: Add Cavium ThunderX EDAC driver") Signed-off-by: Dan Carpenter Signed-off-by: Borislav Petkov CC: David Daney CC: Jan Glauber CC: Mauro Carvalho Chehab CC: Sergey Temerkhanov CC: linux-edac Link: http://lkml.kernel.org/r/20181013102843.GG16086@mwanda Signed-off-by: Sasha Levin --- drivers/edac/thunderx_edac.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c index c009d94f40c5..34be60fe6892 100644 --- a/drivers/edac/thunderx_edac.c +++ b/drivers/edac/thunderx_edac.c @@ -1884,7 +1884,7 @@ static irqreturn_t thunderx_l2c_threaded_isr(int irq, void *irq_id) default: dev_err(&l2c->pdev->dev, "Unsupported device: %04x\n", l2c->pdev->device); - return IRQ_NONE; + goto err_free; } while (CIRC_CNT(l2c->ring_head, l2c->ring_tail, @@ -1906,7 +1906,7 @@ static irqreturn_t thunderx_l2c_threaded_isr(int irq, void *irq_id) l2c->ring_tail++; } - return IRQ_HANDLED; + ret = IRQ_HANDLED; err_free: kfree(other); From 8cb568162524e6585bdcc08170525b1ffa0cce53 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Mon, 8 Oct 2018 10:39:24 +0200 Subject: [PATCH 037/299] mt76: do not store aggregation sequence number for null-data frames [ Upstream commit 5155938d8a0fe0e0251435cae02539e81fb8e407 ] Fixes a rare corner case where a BlockAckReq might get the wrong sequence number. Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/tx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c index 20447fdce4c3..227e5ebfe3dc 100644 --- a/drivers/net/wireless/mediatek/mt76/tx.c +++ b/drivers/net/wireless/mediatek/mt76/tx.c @@ -148,7 +148,8 @@ mt76_check_agg_ssn(struct mt76_txq *mtxq, struct sk_buff *skb) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; - if (!ieee80211_is_data_qos(hdr->frame_control)) + if (!ieee80211_is_data_qos(hdr->frame_control) || + !ieee80211_is_data_present(hdr->frame_control)) return; mtxq->agg_ssn = le16_to_cpu(hdr->seq_ctrl) + 0x10; From 20e42ddf6c1d4a769a87009d758b9d904046dac9 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 9 Oct 2018 10:57:06 +0200 Subject: [PATCH 038/299] mt76x0: phy: fix restore phase in mt76x0_phy_recalibrate_after_assoc [ Upstream commit 4df942733fd26d9378a4a00619be348c771e0190 ] Fix restore value configured in MT_BBP(IBI, 9) register in mt76x0_phy_recalibrate_after_assoc routine. Fixes: 10de7a8b4ab9 ("mt76x0: phy files") Signed-off-by: Lorenzo Bianconi Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt76x0/phy.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c index 14e8c575f6c3..924c761f34fd 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c @@ -793,9 +793,8 @@ void mt76x0_phy_recalibrate_after_assoc(struct mt76x0_dev *dev) mt76_wr(dev, MT_TX_ALC_CFG_0, 0); usleep_range(500, 700); - reg_val = mt76_rr(dev, 0x2124); - reg_val &= 0xffffff7e; - mt76_wr(dev, 0x2124, reg_val); + reg_val = mt76_rr(dev, MT_BBP(IBI, 9)); + mt76_wr(dev, MT_BBP(IBI, 9), 0xffffff7e); mt76x0_mcu_calibrate(dev, MCU_CAL_RXDCOC, 0); @@ -806,7 +805,7 @@ void mt76x0_phy_recalibrate_after_assoc(struct mt76x0_dev *dev) mt76x0_mcu_calibrate(dev, MCU_CAL_RXIQ, is_5ghz); mt76x0_mcu_calibrate(dev, MCU_CAL_RX_GROUP_DELAY, is_5ghz); - mt76_wr(dev, 0x2124, reg_val); + mt76_wr(dev, MT_BBP(IBI, 9), reg_val); mt76_wr(dev, MT_TX_ALC_CFG_0, tx_alc); msleep(100); From 8111f99f7c4478370953f3d62ac298329e050d23 Mon Sep 17 00:00:00 2001 From: Ali MJ Al-Nasrawy Date: Wed, 3 Oct 2018 19:21:39 +0300 Subject: [PATCH 039/299] brcmsmac: AP mode: update beacon when TIM changes [ Upstream commit 2258ee58baa554609a3cc3996276e4276f537b6d ] Beacons are not updated to reflect TIM changes. This is not compliant with power-saving client stations as the beacons do not have valid TIM and can cause the network to stall at random occasions and to have highly variable latencies. Fix it by updating beacon templates on mac80211 set_tim callback. Addresses an issue described in: https://marc.info/?i=20180911163534.21312d08%20()%20manjaro Signed-off-by: Ali MJ Al-Nasrawy Signed-off-by: Kalle Valo Signed-off-by: Sasha Levin --- .../broadcom/brcm80211/brcmsmac/mac80211_if.c | 26 +++++++++++++++++++ .../broadcom/brcm80211/brcmsmac/main.h | 1 + 2 files changed, 27 insertions(+) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c index 6255fb6d97a7..81ff558046a8 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c @@ -502,6 +502,7 @@ brcms_ops_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) } spin_lock_bh(&wl->lock); + wl->wlc->vif = vif; wl->mute_tx = false; brcms_c_mute(wl->wlc, false); if (vif->type == NL80211_IFTYPE_STATION) @@ -519,6 +520,11 @@ brcms_ops_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) static void brcms_ops_remove_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { + struct brcms_info *wl = hw->priv; + + spin_lock_bh(&wl->lock); + wl->wlc->vif = NULL; + spin_unlock_bh(&wl->lock); } static int brcms_ops_config(struct ieee80211_hw *hw, u32 changed) @@ -937,6 +943,25 @@ static void brcms_ops_set_tsf(struct ieee80211_hw *hw, spin_unlock_bh(&wl->lock); } +static int brcms_ops_beacon_set_tim(struct ieee80211_hw *hw, + struct ieee80211_sta *sta, bool set) +{ + struct brcms_info *wl = hw->priv; + struct sk_buff *beacon = NULL; + u16 tim_offset = 0; + + spin_lock_bh(&wl->lock); + if (wl->wlc->vif) + beacon = ieee80211_beacon_get_tim(hw, wl->wlc->vif, + &tim_offset, NULL); + if (beacon) + brcms_c_set_new_beacon(wl->wlc, beacon, tim_offset, + wl->wlc->vif->bss_conf.dtim_period); + spin_unlock_bh(&wl->lock); + + return 0; +} + static const struct ieee80211_ops brcms_ops = { .tx = brcms_ops_tx, .start = brcms_ops_start, @@ -955,6 +980,7 @@ static const struct ieee80211_ops brcms_ops = { .flush = brcms_ops_flush, .get_tsf = brcms_ops_get_tsf, .set_tsf = brcms_ops_set_tsf, + .set_tim = brcms_ops_beacon_set_tim, }; void brcms_dpc(unsigned long data) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.h index c4d135cff04a..9f76b880814e 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.h @@ -563,6 +563,7 @@ struct brcms_c_info { struct wiphy *wiphy; struct scb pri_scb; + struct ieee80211_vif *vif; struct sk_buff *beacon; u16 beacon_tim_offset; From 17fbe3c91ad48eb43247cd372e5a0af73b8a6113 Mon Sep 17 00:00:00 2001 From: Rakesh Pillai Date: Tue, 2 Oct 2018 23:33:13 +0530 Subject: [PATCH 040/299] ath10k: set probe request oui during driver start [ Upstream commit f1157695c527d4ee949ac83f743f80107751a70c ] Currently the wmi command for setting probe request oui, needed for mac randomization, is sent during the mac register. At this time, during the driver init the wmi has already been detached. This can cause unexpected behavior since the firmware is already down and the wmi has been detached. Send the wmi command for setting probe request oui during the driver start. This will make sure that the firmware is started and wmi is initialized before we send this command. Tested HW: WCN3990 Tested FW: WLAN.HL.2.0-01188-QCAHLSWMTPLZ-1 Fixes: 60e1d0fb290197fe505dff6e4e3b7e4d258dbf60 Signed-off-by: Rakesh Pillai Signed-off-by: Kalle Valo Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath10k/mac.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index d3d33cc2adfd..613ca74f1b28 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -4686,6 +4686,14 @@ static int ath10k_start(struct ieee80211_hw *hw) goto err_core_stop; } + if (test_bit(WMI_SERVICE_SPOOF_MAC_SUPPORT, ar->wmi.svc_map)) { + ret = ath10k_wmi_scan_prob_req_oui(ar, ar->mac_addr); + if (ret) { + ath10k_err(ar, "failed to set prob req oui: %i\n", ret); + goto err_core_stop; + } + } + if (test_bit(WMI_SERVICE_ADAPTIVE_OCS, ar->wmi.svc_map)) { ret = ath10k_wmi_adaptive_qcs(ar, true); if (ret) { @@ -8551,12 +8559,6 @@ int ath10k_mac_register(struct ath10k *ar) } if (test_bit(WMI_SERVICE_SPOOF_MAC_SUPPORT, ar->wmi.svc_map)) { - ret = ath10k_wmi_scan_prob_req_oui(ar, ar->mac_addr); - if (ret) { - ath10k_err(ar, "failed to set prob req oui: %i\n", ret); - goto err_dfs_detector_exit; - } - ar->hw->wiphy->features |= NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR; } From 196b007ac0a6060f20ba9383dc6c98b827def052 Mon Sep 17 00:00:00 2001 From: Carl Huang Date: Thu, 11 Oct 2018 15:55:26 +0800 Subject: [PATCH 041/299] ath10k: allocate small size dma memory in ath10k_pci_diag_write_mem [ Upstream commit 0738b4998c6d1caf9ca2447b946709a7278c70f1 ] ath10k_pci_diag_write_mem may allocate big size of the dma memory based on the parameter nbytes. Take firmware diag download as example, the biggest size is about 500K. In some systems, the allocation is likely to fail because it can't acquire such a large contiguous dma memory. The fix is to allocate a small size dma memory. In the loop, driver copies the data to the allocated dma memory and writes to the destination until all the data is written. Tested with QCA6174 PCI with firmware-6.bin_WLAN.RM.4.4.1-00119-QCARMSWP-1, this also affects QCA9377 PCI. Signed-off-by: Carl Huang Reviewed-by: Brian Norris Signed-off-by: Kalle Valo Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath10k/pci.c | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c index 97fa5c74f2fe..50a801a5d4f1 100644 --- a/drivers/net/wireless/ath/ath10k/pci.c +++ b/drivers/net/wireless/ath/ath10k/pci.c @@ -1054,10 +1054,9 @@ int ath10k_pci_diag_write_mem(struct ath10k *ar, u32 address, struct ath10k_ce *ce = ath10k_ce_priv(ar); int ret = 0; u32 *buf; - unsigned int completed_nbytes, orig_nbytes, remaining_bytes; + unsigned int completed_nbytes, alloc_nbytes, remaining_bytes; struct ath10k_ce_pipe *ce_diag; void *data_buf = NULL; - u32 ce_data; /* Host buffer address in CE space */ dma_addr_t ce_data_base = 0; int i; @@ -1071,9 +1070,10 @@ int ath10k_pci_diag_write_mem(struct ath10k *ar, u32 address, * 1) 4-byte alignment * 2) Buffer in DMA-able space */ - orig_nbytes = nbytes; + alloc_nbytes = min_t(unsigned int, nbytes, DIAG_TRANSFER_LIMIT); + data_buf = (unsigned char *)dma_alloc_coherent(ar->dev, - orig_nbytes, + alloc_nbytes, &ce_data_base, GFP_ATOMIC); if (!data_buf) { @@ -1081,9 +1081,6 @@ int ath10k_pci_diag_write_mem(struct ath10k *ar, u32 address, goto done; } - /* Copy caller's data to allocated DMA buf */ - memcpy(data_buf, data, orig_nbytes); - /* * The address supplied by the caller is in the * Target CPU virtual address space. @@ -1096,12 +1093,14 @@ int ath10k_pci_diag_write_mem(struct ath10k *ar, u32 address, */ address = ath10k_pci_targ_cpu_to_ce_addr(ar, address); - remaining_bytes = orig_nbytes; - ce_data = ce_data_base; + remaining_bytes = nbytes; while (remaining_bytes) { /* FIXME: check cast */ nbytes = min_t(int, remaining_bytes, DIAG_TRANSFER_LIMIT); + /* Copy caller's data to allocated DMA buf */ + memcpy(data_buf, data, nbytes); + /* Set up to receive directly into Target(!) address */ ret = ce_diag->ops->ce_rx_post_buf(ce_diag, &address, address); if (ret != 0) @@ -1111,7 +1110,7 @@ int ath10k_pci_diag_write_mem(struct ath10k *ar, u32 address, * Request CE to send caller-supplied data that * was copied to bounce buffer to Target(!) address. */ - ret = ath10k_ce_send_nolock(ce_diag, NULL, (u32)ce_data, + ret = ath10k_ce_send_nolock(ce_diag, NULL, ce_data_base, nbytes, 0, 0); if (ret != 0) goto done; @@ -1152,12 +1151,12 @@ int ath10k_pci_diag_write_mem(struct ath10k *ar, u32 address, remaining_bytes -= nbytes; address += nbytes; - ce_data += nbytes; + data += nbytes; } done: if (data_buf) { - dma_free_coherent(ar->dev, orig_nbytes, data_buf, + dma_free_coherent(ar->dev, alloc_nbytes, data_buf, ce_data_base); } From 0c5c34c1aaf3651fc4271a642b70a39b3729a5bd Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 11 Oct 2018 14:56:14 -0600 Subject: [PATCH 042/299] skd: fixup usage of legacy IO API [ Upstream commit 6d1f9dfde7343c4ebfb8f84dcb333af571bb3b22 ] We need to be using the mq variant of request requeue here. Fixes: ca33dd92968b ("skd: Convert to blk-mq") Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/block/skd_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c index 87b9e7fbf062..27323fa23997 100644 --- a/drivers/block/skd_main.c +++ b/drivers/block/skd_main.c @@ -1416,7 +1416,7 @@ static void skd_resolve_req_exception(struct skd_device *skdev, case SKD_CHECK_STATUS_BUSY_IMMINENT: skd_log_skreq(skdev, skreq, "retry(busy)"); - blk_requeue_request(skdev->queue, req); + blk_mq_requeue_request(req, true); dev_info(&skdev->pdev->dev, "drive BUSY imminent\n"); skdev->state = SKD_DRVR_STATE_BUSY_IMMINENT; skdev->timer_countdown = SKD_TIMER_MINUTES(20); @@ -1426,7 +1426,7 @@ static void skd_resolve_req_exception(struct skd_device *skdev, case SKD_CHECK_STATUS_REQUEUE_REQUEST: if ((unsigned long) ++req->special < SKD_MAX_RETRIES) { skd_log_skreq(skdev, skreq, "retry"); - blk_requeue_request(skdev->queue, req); + blk_mq_requeue_request(req, true); break; } /* fall through */ From 2cd0b70c55b0e71f578134510107d002d52ee235 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 14 Oct 2018 13:20:48 -0600 Subject: [PATCH 043/299] cdrom: don't attempt to fiddle with cdo->capability [ Upstream commit 8f94004e2a51a3ea195cf3447eb5d5906f36d8b3 ] We can't modify cdo->capability as it is defined as a const. Change the modification hack to just WARN_ON_ONCE() if we hit any of the invalid combinations. This fixes a regression for pcd, which doesn't work after the constify patch. Fixes: 853fe1bf7554 ("cdrom: Make device operations read-only") Tested-by: Ondrej Zary Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/cdrom/cdrom.c | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 27a82a559ab9..933268b8d6a5 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -411,10 +411,10 @@ static int cdrom_get_disc_info(struct cdrom_device_info *cdi, * hack to have the capability flags defined const, while we can still * change it here without gcc complaining at every line. */ -#define ENSURE(call, bits) \ -do { \ - if (cdo->call == NULL) \ - *change_capability &= ~(bits); \ +#define ENSURE(cdo, call, bits) \ +do { \ + if (cdo->call == NULL) \ + WARN_ON_ONCE((cdo)->capability & (bits)); \ } while (0) /* @@ -590,7 +590,6 @@ int register_cdrom(struct cdrom_device_info *cdi) { static char banner_printed; const struct cdrom_device_ops *cdo = cdi->ops; - int *change_capability = (int *)&cdo->capability; /* hack */ cd_dbg(CD_OPEN, "entering register_cdrom\n"); @@ -602,16 +601,16 @@ int register_cdrom(struct cdrom_device_info *cdi) cdrom_sysctl_register(); } - ENSURE(drive_status, CDC_DRIVE_STATUS); + ENSURE(cdo, drive_status, CDC_DRIVE_STATUS); if (cdo->check_events == NULL && cdo->media_changed == NULL) - *change_capability = ~(CDC_MEDIA_CHANGED | CDC_SELECT_DISC); - ENSURE(tray_move, CDC_CLOSE_TRAY | CDC_OPEN_TRAY); - ENSURE(lock_door, CDC_LOCK); - ENSURE(select_speed, CDC_SELECT_SPEED); - ENSURE(get_last_session, CDC_MULTI_SESSION); - ENSURE(get_mcn, CDC_MCN); - ENSURE(reset, CDC_RESET); - ENSURE(generic_packet, CDC_GENERIC_PACKET); + WARN_ON_ONCE(cdo->capability & (CDC_MEDIA_CHANGED | CDC_SELECT_DISC)); + ENSURE(cdo, tray_move, CDC_CLOSE_TRAY | CDC_OPEN_TRAY); + ENSURE(cdo, lock_door, CDC_LOCK); + ENSURE(cdo, select_speed, CDC_SELECT_SPEED); + ENSURE(cdo, get_last_session, CDC_MULTI_SESSION); + ENSURE(cdo, get_mcn, CDC_MCN); + ENSURE(cdo, reset, CDC_RESET); + ENSURE(cdo, generic_packet, CDC_GENERIC_PACKET); cdi->mc_flags = 0; cdi->options = CDO_USE_FFLAGS; From e3fa491211c405ac5a3ce0c8171e2511ed847a92 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Fri, 12 Oct 2018 22:48:22 +0300 Subject: [PATCH 044/299] spi: sh-msiof: fix deferred probing [ Upstream commit f34c6e6257aa477cdfe7e9bbbecd3c5648ecda69 ] Since commit 9ec36cafe43b ("of/irq: do irq resolution in platform_get_irq") platform_get_irq() can return -EPROBE_DEFER. However, the driver overrides an error returned by that function with -ENOENT which breaks the deferred probing. Propagate upstream an error code returned by platform_get_irq() and remove the bogus "platform" from the error message, while at it... Fixes: 9ec36cafe43b ("of/irq: do irq resolution in platform_get_irq") Signed-off-by: Sergei Shtylyov Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-sh-msiof.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c index 101cd6aae2ea..30ea0a2068e0 100644 --- a/drivers/spi/spi-sh-msiof.c +++ b/drivers/spi/spi-sh-msiof.c @@ -1343,8 +1343,8 @@ static int sh_msiof_spi_probe(struct platform_device *pdev) i = platform_get_irq(pdev, 0); if (i < 0) { - dev_err(&pdev->dev, "cannot get platform IRQ\n"); - ret = -ENOENT; + dev_err(&pdev->dev, "cannot get IRQ\n"); + ret = i; goto err1; } From e2c158f5852295be92473b3b36b163e1935a97d2 Mon Sep 17 00:00:00 2001 From: Chaotian Jing Date: Sat, 13 Oct 2018 15:20:46 +0800 Subject: [PATCH 045/299] mmc: mediatek: fill the actual clock for mmc debugfs [ Upstream commit 56f6cbbed0463f1c78d602b17c315916cc1cd238 ] as the mmc core layer has the mmc->actual_clock, so fill it and drop msdc_host->sclk. Signed-off-by: Chaotian Jing Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/mtk-sd.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index f171cce5197d..621c914dc5c0 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -390,7 +390,6 @@ struct msdc_host { struct clk *src_clk_cg; /* msdc source clock control gate */ u32 mclk; /* mmc subsystem clock frequency */ u32 src_clk_freq; /* source clock frequency */ - u32 sclk; /* SD/MS bus clock frequency */ unsigned char timing; bool vqmmc_enabled; u32 latch_ck; @@ -635,10 +634,10 @@ static void msdc_set_timeout(struct msdc_host *host, u32 ns, u32 clks) host->timeout_ns = ns; host->timeout_clks = clks; - if (host->sclk == 0) { + if (host->mmc->actual_clock == 0) { timeout = 0; } else { - clk_ns = 1000000000UL / host->sclk; + clk_ns = 1000000000UL / host->mmc->actual_clock; timeout = (ns + clk_ns - 1) / clk_ns + clks; /* in 1048576 sclk cycle unit */ timeout = (timeout + (0x1 << 20) - 1) >> 20; @@ -683,6 +682,7 @@ static void msdc_set_mclk(struct msdc_host *host, unsigned char timing, u32 hz) if (!hz) { dev_dbg(host->dev, "set mclk to 0\n"); host->mclk = 0; + host->mmc->actual_clock = 0; sdr_clr_bits(host->base + MSDC_CFG, MSDC_CFG_CKPDN); return; } @@ -761,7 +761,7 @@ static void msdc_set_mclk(struct msdc_host *host, unsigned char timing, u32 hz) while (!(readl(host->base + MSDC_CFG) & MSDC_CFG_CKSTB)) cpu_relax(); sdr_set_bits(host->base + MSDC_CFG, MSDC_CFG_CKPDN); - host->sclk = sclk; + host->mmc->actual_clock = sclk; host->mclk = hz; host->timing = timing; /* need because clk changed. */ @@ -772,7 +772,7 @@ static void msdc_set_mclk(struct msdc_host *host, unsigned char timing, u32 hz) * mmc_select_hs400() will drop to 50Mhz and High speed mode, * tune result of hs200/200Mhz is not suitable for 50Mhz */ - if (host->sclk <= 52000000) { + if (host->mmc->actual_clock <= 52000000) { writel(host->def_tune_para.iocon, host->base + MSDC_IOCON); writel(host->def_tune_para.pad_tune, host->base + tune_reg); } else { @@ -787,7 +787,8 @@ static void msdc_set_mclk(struct msdc_host *host, unsigned char timing, u32 hz) sdr_set_field(host->base + tune_reg, MSDC_PAD_TUNE_CMDRRDLY, host->hs400_cmd_int_delay); - dev_dbg(host->dev, "sclk: %d, timing: %d\n", host->sclk, timing); + dev_dbg(host->dev, "sclk: %d, timing: %d\n", host->mmc->actual_clock, + timing); } static inline u32 msdc_cmd_find_resp(struct msdc_host *host, From dfffae314a0259452488917d3aa162b5291e6343 Mon Sep 17 00:00:00 2001 From: Chaotian Jing Date: Sat, 13 Oct 2018 15:20:47 +0800 Subject: [PATCH 046/299] mmc: mediatek: fix cannot receive new request when msdc_cmd_is_ready fail [ Upstream commit f38a9774ddde9d79b3487dd888edd8b8623552af ] when msdc_cmd_is_ready return fail, the req_timeout work has not been inited and cancel_delayed_work() will return false, then, the request return directly and never call mmc_request_done(). so need call mod_delayed_work() before msdc_cmd_is_ready() Signed-off-by: Chaotian Jing Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/mtk-sd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 621c914dc5c0..673f6a9616cd 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -1056,6 +1056,7 @@ static void msdc_start_command(struct msdc_host *host, WARN_ON(host->cmd); host->cmd = cmd; + mod_delayed_work(system_wq, &host->req_timeout, DAT_TIMEOUT); if (!msdc_cmd_is_ready(host, mrq, cmd)) return; @@ -1067,7 +1068,6 @@ static void msdc_start_command(struct msdc_host *host, cmd->error = 0; rawcmd = msdc_cmd_prepare_raw_cmd(host, mrq, cmd); - mod_delayed_work(system_wq, &host->req_timeout, DAT_TIMEOUT); sdr_set_bits(host->base + MSDC_INTEN, cmd_ints_mask); writel(cmd->arg, host->base + SDC_ARG); From 9325e8f4688ce4df65dc9c1b4698f75f3ab9a515 Mon Sep 17 00:00:00 2001 From: Honghui Zhang Date: Mon, 15 Oct 2018 16:08:53 +0800 Subject: [PATCH 047/299] PCI: mediatek: Fix class type for MT7622 to PCI_CLASS_BRIDGE_PCI [ Upstream commit a7f172ab6a8e755e60311f27512034b0441ef421 ] commit 101c92dc80c8 ("PCI: mediatek: Set up vendor ID and class type for MT7622") erroneously set the class type for MT7622 to PCI_CLASS_BRIDGE_HOST. The PCIe controller of MT7622 integrates a Root Port that has type 1 configuration space header and related bridge windows. The HW default value of this bridge's class type is invalid. Fix its class type and set it to PCI_CLASS_BRIDGE_PCI to match the hardware implementation. Fixes: 101c92dc80c8 ("PCI: mediatek: Set up vendor ID and class type for MT7622") Signed-off-by: Honghui Zhang [lorenzo.pieralisi@arm.com: reworked the commit log] Signed-off-by: Lorenzo Pieralisi Acked-by: Ryder Lee Signed-off-by: Sasha Levin --- drivers/pci/controller/pcie-mediatek.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index 0d100f56cb88..8d1364c31774 100644 --- a/drivers/pci/controller/pcie-mediatek.c +++ b/drivers/pci/controller/pcie-mediatek.c @@ -432,7 +432,7 @@ static int mtk_pcie_startup_port_v2(struct mtk_pcie_port *port) val = PCI_VENDOR_ID_MEDIATEK; writew(val, port->base + PCIE_CONF_VEND_ID); - val = PCI_CLASS_BRIDGE_HOST; + val = PCI_CLASS_BRIDGE_PCI; writew(val, port->base + PCIE_CONF_CLASS_ID); } From 1b49c453a5645f483cd6b7733919a36f9c492f98 Mon Sep 17 00:00:00 2001 From: Su Yue Date: Wed, 5 Sep 2018 11:07:33 +0800 Subject: [PATCH 048/299] btrfs: defrag: use btrfs_mod_outstanding_extents in cluster_pages_for_defrag [ Upstream commit 28c4a3e21ad030d7571ee9b1b246a5cbfd886627 ] Since commit 8b62f87bad9c ("Btrfs: rework outstanding_extents"), manual operations of outstanding_extent in btrfs_inode are replaced by btrfs_mod_outstanding_extents(). The one in cluster_pages_for_defrag seems to be lost, so replace it of btrfs_mod_outstanding_extents(). Fixes: 8b62f87bad9c ("Btrfs: rework outstanding_extents") Signed-off-by: Su Yue Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 7592beb53fc4..00ff4349b457 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1337,7 +1337,7 @@ again: if (i_done != page_cnt) { spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->outstanding_extents++; + btrfs_mod_outstanding_extents(BTRFS_I(inode), 1); spin_unlock(&BTRFS_I(inode)->lock); btrfs_delalloc_release_space(inode, data_reserved, start_index << PAGE_SHIFT, From cc08097f261966ad18071383f01c16f0ce1d839c Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Thu, 13 Sep 2018 11:35:10 +0300 Subject: [PATCH 049/299] btrfs: handle error of get_old_root [ Upstream commit 315bed43fea532650933e7bba316a7601d439edf ] In btrfs_search_old_slot get_old_root is always used with the assumption it cannot fail. However, this is not true in rare circumstance it can fail and return null. This will lead to null point dereference when the header is read. Fix this by checking the return value and properly handling NULL by setting ret to -EIO and returning gracefully. Coverity-id: 1087503 Signed-off-by: Nikolay Borisov Reviewed-by: Lu Fengqi Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/ctree.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 9fd383285f0e..fc764f350f05 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -3031,6 +3031,10 @@ int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key, again: b = get_old_root(root, time_seq); + if (!b) { + ret = -EIO; + goto done; + } level = btrfs_header_level(b); p->locks[level] = BTRFS_READ_LOCK; From a2204a2955544d140689a639a236a00ee69dd4ac Mon Sep 17 00:00:00 2001 From: Duncan Laurie Date: Fri, 12 Oct 2018 10:04:45 -0600 Subject: [PATCH 050/299] gsmi: Fix bug in append_to_eventlog sysfs handler [ Upstream commit 655603de68469adaff16842ac17a5aec9c9ce89b ] The sysfs handler should return the number of bytes consumed, which in the case of a successful write is the entire buffer. Also fix a bug where param.data_len was being set to (count - (2 * sizeof(u32))) instead of just (count - sizeof(u32)). The latter is correct because we skip over the leading u32 which is our param.type, but we were also incorrectly subtracting sizeof(u32) on the line where we were actually setting param.data_len: param.data_len = count - sizeof(u32); This meant that for our example event.kernel_software_watchdog with total length 10 bytes, param.data_len was just 2 prior to this change. To test, successfully append an event to the log with gsmi sysfs. This sample event is for a "Kernel Software Watchdog" > xxd -g 1 event.kernel_software_watchdog 0000000: 01 00 00 00 ad de 06 00 00 00 > cat event.kernel_software_watchdog > /sys/firmware/gsmi/append_to_eventlog > mosys eventlog list | tail -1 14 | 2012-06-25 10:14:14 | Kernl Event | Software Watchdog Signed-off-by: Duncan Laurie Reviewed-by: Vadim Bendebury Reviewed-by: Stefan Reinauer Signed-off-by: Furquan Shaikh Tested-by: Furquan Shaikh Reviewed-by: Aaron Durbin Reviewed-by: Justin TerAvest [zwisler: updated changelog for 2nd bug fix and upstream] Signed-off-by: Ross Zwisler Reviewed-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/firmware/google/gsmi.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/firmware/google/gsmi.c b/drivers/firmware/google/gsmi.c index c8f169bf2e27..62337be07afc 100644 --- a/drivers/firmware/google/gsmi.c +++ b/drivers/firmware/google/gsmi.c @@ -480,11 +480,10 @@ static ssize_t eventlog_write(struct file *filp, struct kobject *kobj, if (count < sizeof(u32)) return -EINVAL; param.type = *(u32 *)buf; - count -= sizeof(u32); buf += sizeof(u32); /* The remaining buffer is the data payload */ - if (count > gsmi_dev.data_buf->length) + if ((count - sizeof(u32)) > gsmi_dev.data_buf->length) return -EINVAL; param.data_len = count - sizeof(u32); @@ -504,7 +503,7 @@ static ssize_t eventlog_write(struct file *filp, struct kobject *kobj, spin_unlock_irqrestore(&gsmi_dev.lock, flags); - return rc; + return (rc == 0) ? count : rc; } From d11d985d0a8285cc308a61c2464ad68e8e1f4ff8 Mon Sep 17 00:00:00 2001 From: Wenwen Wang Date: Wed, 10 Oct 2018 18:38:28 -0500 Subject: [PATCH 051/299] misc: mic: fix a DMA pool free failure [ Upstream commit 6b995f4eec34745f6cb20d66d5277611f0b3c3fa ] In _scif_prog_signal(), the boolean variable 'x100' is used to indicate whether the MIC Coprocessor is X100. If 'x100' is true, the status descriptor will be used to write the value to the destination. Otherwise, a DMA pool will be allocated for this purpose. Specifically, if the DMA pool is allocated successfully, two memory addresses will be returned. One is for the CPU and the other is for the device to access the DMA pool. The former is stored to the variable 'status' and the latter is stored to the variable 'src'. After the allocation, the address in 'src' is saved to 'status->src_dma_addr', which is actually in the DMA pool, and 'src' is then modified. Later on, if an error occurs, the execution flow will transfer to the label 'dma_fail', which will check 'x100' and free up the allocated DMA pool if 'x100' is false. The point here is that 'status->src_dma_addr' is used for freeing up the DMA pool. As mentioned before, 'status->src_dma_addr' is in the DMA pool. And thus, the device is able to modify this data. This can potentially cause failures when freeing up the DMA pool because of the modified device address. This patch avoids the above issue by using the variable 'src' (with necessary calculation) to free up the DMA pool. Signed-off-by: Wenwen Wang Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/misc/mic/scif/scif_fence.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/mic/scif/scif_fence.c b/drivers/misc/mic/scif/scif_fence.c index cac3bcc308a7..7bb929f05d85 100644 --- a/drivers/misc/mic/scif/scif_fence.c +++ b/drivers/misc/mic/scif/scif_fence.c @@ -272,7 +272,7 @@ static int _scif_prog_signal(scif_epd_t epd, dma_addr_t dst, u64 val) dma_fail: if (!x100) dma_pool_free(ep->remote_dev->signal_pool, status, - status->src_dma_addr); + src - offsetof(struct scif_status, val)); alloc_fail: return err; } From 4ab1594e699ed2371e7ea9e6893b58e4038a40fc Mon Sep 17 00:00:00 2001 From: Julien Folly Date: Tue, 9 Oct 2018 19:47:45 +0200 Subject: [PATCH 052/299] w1: IAD Register is yet readable trough iad sys file. Fix snprintf (%u for unsigned, count for max size). [ Upstream commit 6eaafbb6998e999467cf78a76e155ee00e372b14 ] IAD Register is yet readable trough the "iad" sys file. A write to the "iad" sys file enables or disables the current measurement, but it was not possible to get the measured value by reading it. Fix: %u in snprintf for unsigned values (vdd and vad) Fix: Avoid possibles overflows (Usage of the 'count' variables) Signed-off-by: Julien Folly Acked-by: Evgeniy Polyakov Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/w1/slaves/w1_ds2438.c | 66 +++++++++++++++++++++++++++-------- 1 file changed, 52 insertions(+), 14 deletions(-) diff --git a/drivers/w1/slaves/w1_ds2438.c b/drivers/w1/slaves/w1_ds2438.c index bf641a191d07..7c4e33dbee4d 100644 --- a/drivers/w1/slaves/w1_ds2438.c +++ b/drivers/w1/slaves/w1_ds2438.c @@ -186,8 +186,8 @@ static int w1_ds2438_change_config_bit(struct w1_slave *sl, u8 mask, u8 value) return -1; } -static uint16_t w1_ds2438_get_voltage(struct w1_slave *sl, - int adc_input, uint16_t *voltage) +static int w1_ds2438_get_voltage(struct w1_slave *sl, + int adc_input, uint16_t *voltage) { unsigned int retries = W1_DS2438_RETRIES; u8 w1_buf[DS2438_PAGE_SIZE + 1 /*for CRC*/]; @@ -235,6 +235,25 @@ post_unlock: return ret; } +static int w1_ds2438_get_current(struct w1_slave *sl, int16_t *voltage) +{ + u8 w1_buf[DS2438_PAGE_SIZE + 1 /*for CRC*/]; + int ret; + + mutex_lock(&sl->master->bus_mutex); + + if (w1_ds2438_get_page(sl, 0, w1_buf) == 0) { + /* The voltage measured across current sense resistor RSENS. */ + *voltage = (((int16_t) w1_buf[DS2438_CURRENT_MSB]) << 8) | ((int16_t) w1_buf[DS2438_CURRENT_LSB]); + ret = 0; + } else + ret = -1; + + mutex_unlock(&sl->master->bus_mutex); + + return ret; +} + static ssize_t iad_write(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) @@ -257,6 +276,27 @@ static ssize_t iad_write(struct file *filp, struct kobject *kobj, return ret; } +static ssize_t iad_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, + loff_t off, size_t count) +{ + struct w1_slave *sl = kobj_to_w1_slave(kobj); + int ret; + int16_t voltage; + + if (off != 0) + return 0; + if (!buf) + return -EINVAL; + + if (w1_ds2438_get_current(sl, &voltage) == 0) { + ret = snprintf(buf, count, "%i\n", voltage); + } else + ret = -EIO; + + return ret; +} + static ssize_t page0_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) @@ -272,9 +312,13 @@ static ssize_t page0_read(struct file *filp, struct kobject *kobj, mutex_lock(&sl->master->bus_mutex); + /* Read no more than page0 size */ + if (count > DS2438_PAGE_SIZE) + count = DS2438_PAGE_SIZE; + if (w1_ds2438_get_page(sl, 0, w1_buf) == 0) { - memcpy(buf, &w1_buf, DS2438_PAGE_SIZE); - ret = DS2438_PAGE_SIZE; + memcpy(buf, &w1_buf, count); + ret = count; } else ret = -EIO; @@ -289,7 +333,6 @@ static ssize_t temperature_read(struct file *filp, struct kobject *kobj, { struct w1_slave *sl = kobj_to_w1_slave(kobj); int ret; - ssize_t c = PAGE_SIZE; int16_t temp; if (off != 0) @@ -298,8 +341,7 @@ static ssize_t temperature_read(struct file *filp, struct kobject *kobj, return -EINVAL; if (w1_ds2438_get_temperature(sl, &temp) == 0) { - c -= snprintf(buf + PAGE_SIZE - c, c, "%d\n", temp); - ret = PAGE_SIZE - c; + ret = snprintf(buf, count, "%i\n", temp); } else ret = -EIO; @@ -312,7 +354,6 @@ static ssize_t vad_read(struct file *filp, struct kobject *kobj, { struct w1_slave *sl = kobj_to_w1_slave(kobj); int ret; - ssize_t c = PAGE_SIZE; uint16_t voltage; if (off != 0) @@ -321,8 +362,7 @@ static ssize_t vad_read(struct file *filp, struct kobject *kobj, return -EINVAL; if (w1_ds2438_get_voltage(sl, DS2438_ADC_INPUT_VAD, &voltage) == 0) { - c -= snprintf(buf + PAGE_SIZE - c, c, "%d\n", voltage); - ret = PAGE_SIZE - c; + ret = snprintf(buf, count, "%u\n", voltage); } else ret = -EIO; @@ -335,7 +375,6 @@ static ssize_t vdd_read(struct file *filp, struct kobject *kobj, { struct w1_slave *sl = kobj_to_w1_slave(kobj); int ret; - ssize_t c = PAGE_SIZE; uint16_t voltage; if (off != 0) @@ -344,15 +383,14 @@ static ssize_t vdd_read(struct file *filp, struct kobject *kobj, return -EINVAL; if (w1_ds2438_get_voltage(sl, DS2438_ADC_INPUT_VDD, &voltage) == 0) { - c -= snprintf(buf + PAGE_SIZE - c, c, "%d\n", voltage); - ret = PAGE_SIZE - c; + ret = snprintf(buf, count, "%u\n", voltage); } else ret = -EIO; return ret; } -static BIN_ATTR(iad, S_IRUGO | S_IWUSR | S_IWGRP, NULL, iad_write, 1); +static BIN_ATTR(iad, S_IRUGO | S_IWUSR | S_IWGRP, iad_read, iad_write, 0); static BIN_ATTR_RO(page0, DS2438_PAGE_SIZE); static BIN_ATTR_RO(temperature, 0/* real length varies */); static BIN_ATTR_RO(vad, 0/* real length varies */); From 92ac0e3249746a852478af8c644aa81657c479ad Mon Sep 17 00:00:00 2001 From: Angelo Dureghello Date: Fri, 7 Sep 2018 14:44:25 +0200 Subject: [PATCH 053/299] m68k: fix command-line parsing when passed from u-boot [ Upstream commit 381fdd62c38344a771aed06adaf14aae65c47454 ] This patch fixes command_line array zero-terminated one byte over the end of the array, causing boot to hang. Signed-off-by: Angelo Dureghello Signed-off-by: Greg Ungerer Signed-off-by: Sasha Levin --- arch/m68k/kernel/uboot.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/m68k/kernel/uboot.c b/arch/m68k/kernel/uboot.c index b29c3b241e1b..107082877064 100644 --- a/arch/m68k/kernel/uboot.c +++ b/arch/m68k/kernel/uboot.c @@ -102,5 +102,5 @@ __init void process_uboot_commandline(char *commandp, int size) } parse_uboot_commandline(commandp, len); - commandp[size - 1] = 0; + commandp[len - 1] = 0; } From d10b7dd14a37dcc5c5fc21ad9119ad614f924f36 Mon Sep 17 00:00:00 2001 From: Luo Jiaxing Date: Mon, 24 Sep 2018 23:06:28 +0800 Subject: [PATCH 054/299] scsi: hisi_sas: Feed back linkrate(max/min) when re-attached [ Upstream commit 5a54691f874ab29ec82f08bc6936866a3ccdaa91 ] At directly attached situation, if the user modifies the sysfs interface of maximum_linkrate and minimum_linkrate to renegotiate the linkrate between SAS controller and target, the value of both files mentioned above should have change to user setting after renegotiate is over, but it remains unchanged. To fix this bug, maximum_linkrate and minimum_linkrate will be directly fed back to relevant sas_phy structure. Signed-off-by: Luo Jiaxing Signed-off-by: John Garry Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/hisi_sas/hisi_sas_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index fd9d82c9033d..e9747379384b 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -906,6 +906,9 @@ static void hisi_sas_phy_set_linkrate(struct hisi_hba *hisi_hba, int phy_no, _r.maximum_linkrate = max; _r.minimum_linkrate = min; + sas_phy->phy->maximum_linkrate = max; + sas_phy->phy->minimum_linkrate = min; + hisi_hba->hw->phy_disable(hisi_hba, phy_no); msleep(100); hisi_hba->hw->phy_set_linkrate(hisi_hba, phy_no, &_r); From 628cae51693a71ef71b0a54a4734d2817eb30976 Mon Sep 17 00:00:00 2001 From: Xiang Chen Date: Mon, 24 Sep 2018 23:06:30 +0800 Subject: [PATCH 055/299] scsi: hisi_sas: Fix the race between IO completion and timeout for SMP/internal IO [ Upstream commit 584f53fe5f529d877968c711a095923c1ed12307 ] If SMP/internal IO times out, we will possibly free the task immediately. However if the IO actually completes at the same time, the IO completion may refer to task which has been freed. So to solve the issue, flush the tasklet to finish IO completion before free'ing slot/task. Signed-off-by: Xiang Chen Signed-off-by: John Garry Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/hisi_sas/hisi_sas_main.c | 53 +++++++++++++++++++++++---- 1 file changed, 45 insertions(+), 8 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index e9747379384b..d4a2625a4423 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -955,8 +955,7 @@ static int hisi_sas_control_phy(struct asd_sas_phy *sas_phy, enum phy_func func, static void hisi_sas_task_done(struct sas_task *task) { - if (!del_timer(&task->slow_task->timer)) - return; + del_timer(&task->slow_task->timer); complete(&task->slow_task->completion); } @@ -965,13 +964,17 @@ static void hisi_sas_tmf_timedout(struct timer_list *t) struct sas_task_slow *slow = from_timer(slow, t, timer); struct sas_task *task = slow->task; unsigned long flags; + bool is_completed = true; spin_lock_irqsave(&task->task_state_lock, flags); - if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) + if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) { task->task_state_flags |= SAS_TASK_STATE_ABORTED; + is_completed = false; + } spin_unlock_irqrestore(&task->task_state_lock, flags); - complete(&task->slow_task->completion); + if (!is_completed) + complete(&task->slow_task->completion); } #define TASK_TIMEOUT 20 @@ -1022,10 +1025,18 @@ static int hisi_sas_exec_internal_tmf_task(struct domain_device *device, if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) { if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) { struct hisi_sas_slot *slot = task->lldd_task; + struct hisi_sas_cq *cq = + &hisi_hba->cq[slot->dlvry_queue]; dev_err(dev, "abort tmf: TMF task timeout and not done\n"); - if (slot) + if (slot) { + /* + * flush tasklet to avoid free'ing task + * before using task in IO completion + */ + tasklet_kill(&cq->tasklet); slot->task = NULL; + } goto ex_err; } else @@ -1401,6 +1412,17 @@ static int hisi_sas_abort_task(struct sas_task *task) spin_lock_irqsave(&task->task_state_lock, flags); if (task->task_state_flags & SAS_TASK_STATE_DONE) { + struct hisi_sas_slot *slot = task->lldd_task; + struct hisi_sas_cq *cq; + + if (slot) { + /* + * flush tasklet to avoid free'ing task + * before using task in IO completion + */ + cq = &hisi_hba->cq[slot->dlvry_queue]; + tasklet_kill(&cq->tasklet); + } spin_unlock_irqrestore(&task->task_state_lock, flags); rc = TMF_RESP_FUNC_COMPLETE; goto out; @@ -1456,12 +1478,19 @@ static int hisi_sas_abort_task(struct sas_task *task) /* SMP */ struct hisi_sas_slot *slot = task->lldd_task; u32 tag = slot->idx; + struct hisi_sas_cq *cq = &hisi_hba->cq[slot->dlvry_queue]; rc = hisi_sas_internal_task_abort(hisi_hba, device, HISI_SAS_INT_ABT_CMD, tag); if (((rc < 0) || (rc == TMF_RESP_FUNC_FAILED)) && - task->lldd_task) - hisi_sas_do_release_task(hisi_hba, task, slot); + task->lldd_task) { + /* + * flush tasklet to avoid free'ing task + * before using task in IO completion + */ + tasklet_kill(&cq->tasklet); + slot->task = NULL; + } } out: @@ -1827,9 +1856,17 @@ hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba, if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) { if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) { struct hisi_sas_slot *slot = task->lldd_task; + struct hisi_sas_cq *cq = + &hisi_hba->cq[slot->dlvry_queue]; - if (slot) + if (slot) { + /* + * flush tasklet to avoid free'ing task + * before using task in IO completion + */ + tasklet_kill(&cq->tasklet); slot->task = NULL; + } dev_err(dev, "internal task abort: timeout and not done.\n"); res = -EIO; goto exit; From bbeeadb7bab415bef91cdd8a86fbc9d1891cbaa1 Mon Sep 17 00:00:00 2001 From: Xiang Chen Date: Mon, 24 Sep 2018 23:06:31 +0800 Subject: [PATCH 056/299] scsi: hisi_sas: Free slot later in slot_complete_vx_hw() [ Upstream commit 3e178f3ecfcf91a258e832b0f0843a4cfd9059ac ] If an SSP/SMP IO times out, it may be actually in reality be simultaneously processing completion of the slot in slot_complete_vx_hw(). Then if the slot is freed in slot_complete_vx_hw() (this IPTT is freed and it may be re-used by other slot), and we may abort the wrong slot in hisi_sas_abort_task(). So to solve the issue, free the slot after the check of SAS_TASK_STATE_ABORTED in slot_complete_vx_hw(). Signed-off-by: Xiang Chen Signed-off-by: John Garry Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 2 +- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index 1c4ea58da1ae..c4774d63d5d0 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -2481,7 +2481,6 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) } out: - hisi_sas_slot_task_free(hisi_hba, task, slot); sts = ts->stat; spin_lock_irqsave(&task->task_state_lock, flags); if (task->task_state_flags & SAS_TASK_STATE_ABORTED) { @@ -2491,6 +2490,7 @@ out: } task->task_state_flags |= SAS_TASK_STATE_DONE; spin_unlock_irqrestore(&task->task_state_lock, flags); + hisi_sas_slot_task_free(hisi_hba, task, slot); if (!is_internal && (task->task_proto != SAS_PROTOCOL_SMP)) { spin_lock_irqsave(&device->done_lock, flags); diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 3922b17e2ea3..fb2a5969181b 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -1749,7 +1749,6 @@ slot_complete_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) } out: - hisi_sas_slot_task_free(hisi_hba, task, slot); sts = ts->stat; spin_lock_irqsave(&task->task_state_lock, flags); if (task->task_state_flags & SAS_TASK_STATE_ABORTED) { @@ -1759,6 +1758,7 @@ out: } task->task_state_flags |= SAS_TASK_STATE_DONE; spin_unlock_irqrestore(&task->task_state_lock, flags); + hisi_sas_slot_task_free(hisi_hba, task, slot); if (!is_internal && (task->task_proto != SAS_PROTOCOL_SMP)) { spin_lock_irqsave(&device->done_lock, flags); From 2f241e333f7b5cb7e5aca9a02c1775e800db9e2e Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Mon, 8 Oct 2018 03:27:55 -0700 Subject: [PATCH 057/299] RDMA/bnxt_re: Avoid NULL check after accessing the pointer [ Upstream commit eae4ad1b0c9a77ef0cbac212d58d46976eaacfc1 ] This is reported by smatch check. rcfw->creq_bar_reg_iomem is accessed in bnxt_qplib_rcfw_stop_irq and this variable check afterwards doesn't make sense. Also, rcfw->creq_bar_reg_iomem will never be NULL. So Removing this check. Reported-by: Dan Carpenter Fixes: 6e04b1035689 ("RDMA/bnxt_re: Fix broken RoCE driver due to recent L2 driver changes") Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/bnxt_re/qplib_rcfw.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 6637df77d236..8b3b5fdc19bb 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -614,13 +614,8 @@ void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw) bnxt_qplib_rcfw_stop_irq(rcfw, true); - if (rcfw->cmdq_bar_reg_iomem) - iounmap(rcfw->cmdq_bar_reg_iomem); - rcfw->cmdq_bar_reg_iomem = NULL; - - if (rcfw->creq_bar_reg_iomem) - iounmap(rcfw->creq_bar_reg_iomem); - rcfw->creq_bar_reg_iomem = NULL; + iounmap(rcfw->cmdq_bar_reg_iomem); + iounmap(rcfw->creq_bar_reg_iomem); indx = find_first_bit(rcfw->cmdq_bitmap, rcfw->bmap_size); if (indx != rcfw->bmap_size) @@ -629,6 +624,8 @@ void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw) kfree(rcfw->cmdq_bitmap); rcfw->bmap_size = 0; + rcfw->cmdq_bar_reg_iomem = NULL; + rcfw->creq_bar_reg_iomem = NULL; rcfw->aeq_handler = NULL; rcfw->vector = 0; } @@ -714,6 +711,8 @@ int bnxt_qplib_enable_rcfw_channel(struct pci_dev *pdev, dev_err(&rcfw->pdev->dev, "QPLIB: CREQ BAR region %d mapping failed", rcfw->creq_bar_reg); + iounmap(rcfw->cmdq_bar_reg_iomem); + rcfw->cmdq_bar_reg_iomem = NULL; return -ENOMEM; } rcfw->creq_qp_event_processed = 0; From b1bf1e424dcb619e6954355afa488a65b632a0c6 Mon Sep 17 00:00:00 2001 From: Devesh Sharma Date: Mon, 8 Oct 2018 03:28:01 -0700 Subject: [PATCH 058/299] RDMA/bnxt_re: Fix qp async event reporting [ Upstream commit 4c01f2e3a906a0d2d798be5751c331cf501bc129 ] Reports affiliated async event on the qp-async event channel instead of global event channel. Signed-off-by: Devesh Sharma Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/bnxt_re/main.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 22bd9784fa2e..7ffad368c5fa 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -989,12 +989,17 @@ static void bnxt_re_dispatch_event(struct ib_device *ibdev, struct ib_qp *qp, struct ib_event ib_event; ib_event.device = ibdev; - if (qp) + if (qp) { ib_event.element.qp = qp; - else + ib_event.event = event; + if (qp->event_handler) + qp->event_handler(&ib_event, qp->qp_context); + + } else { ib_event.element.port_num = port_num; - ib_event.event = event; - ib_dispatch_event(&ib_event); + ib_event.event = event; + ib_dispatch_event(&ib_event); + } } #define HWRM_QUEUE_PRI2COS_QCFG_INPUT_FLAGS_IVLAN 0x02 From fae3cf8874c38c40746dfe90ebcd674da72e88f8 Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Mon, 8 Oct 2018 03:28:04 -0700 Subject: [PATCH 059/299] RDMA/bnxt_re: Avoid resource leak in case the NQ registration fails [ Upstream commit 5df950994934814a8b91f0cf9f653842d2ba082d ] In case the NQ alloc/enable fails, free up the already allocated/enabled NQ before reporting failure. Also, track the alloc/enable using proper state checking. Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/bnxt_re/bnxt_re.h | 2 ++ drivers/infiniband/hw/bnxt_re/main.c | 31 ++++++++++++++++++------- 2 files changed, 24 insertions(+), 9 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h index 96f76896488d..802942adea8e 100644 --- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h +++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h @@ -120,6 +120,8 @@ struct bnxt_re_dev { #define BNXT_RE_FLAG_HAVE_L2_REF 3 #define BNXT_RE_FLAG_RCFW_CHANNEL_EN 4 #define BNXT_RE_FLAG_QOS_WORK_REG 5 +#define BNXT_RE_FLAG_RESOURCES_ALLOCATED 7 +#define BNXT_RE_FLAG_RESOURCES_INITIALIZED 8 #define BNXT_RE_FLAG_ISSUE_ROCE_STATS 29 struct net_device *netdev; unsigned int version, major, minor; diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 7ffad368c5fa..589b0d4677d5 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -864,10 +864,8 @@ static void bnxt_re_cleanup_res(struct bnxt_re_dev *rdev) { int i; - if (rdev->nq[0].hwq.max_elements) { - for (i = 1; i < rdev->num_msix; i++) - bnxt_qplib_disable_nq(&rdev->nq[i - 1]); - } + for (i = 1; i < rdev->num_msix; i++) + bnxt_qplib_disable_nq(&rdev->nq[i - 1]); if (rdev->qplib_res.rcfw) bnxt_qplib_cleanup_res(&rdev->qplib_res); @@ -876,6 +874,7 @@ static void bnxt_re_cleanup_res(struct bnxt_re_dev *rdev) static int bnxt_re_init_res(struct bnxt_re_dev *rdev) { int rc = 0, i; + int num_vec_enabled = 0; bnxt_qplib_init_res(&rdev->qplib_res); @@ -891,9 +890,13 @@ static int bnxt_re_init_res(struct bnxt_re_dev *rdev) "Failed to enable NQ with rc = 0x%x", rc); goto fail; } + num_vec_enabled++; } return 0; fail: + for (i = num_vec_enabled; i >= 0; i--) + bnxt_qplib_disable_nq(&rdev->nq[i]); + return rc; } @@ -925,6 +928,7 @@ static void bnxt_re_free_res(struct bnxt_re_dev *rdev) static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev) { int rc = 0, i; + int num_vec_created = 0; /* Configure and allocate resources for qplib */ rdev->qplib_res.rcfw = &rdev->rcfw; @@ -951,7 +955,7 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev) if (rc) { dev_err(rdev_to_dev(rdev), "Alloc Failed NQ%d rc:%#x", i, rc); - goto dealloc_dpi; + goto free_nq; } rc = bnxt_re_net_ring_alloc (rdev, rdev->nq[i].hwq.pbl[PBL_LVL_0].pg_map_arr, @@ -964,14 +968,17 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev) dev_err(rdev_to_dev(rdev), "Failed to allocate NQ fw id with rc = 0x%x", rc); + bnxt_qplib_free_nq(&rdev->nq[i]); goto free_nq; } + num_vec_created++; } return 0; free_nq: - for (i = 0; i < rdev->num_msix - 1; i++) + for (i = num_vec_created; i >= 0; i--) { + bnxt_re_net_ring_free(rdev, rdev->nq[i].ring_id); bnxt_qplib_free_nq(&rdev->nq[i]); -dealloc_dpi: + } bnxt_qplib_dealloc_dpi(&rdev->qplib_res, &rdev->qplib_res.dpi_tbl, &rdev->dpi_privileged); @@ -1206,8 +1213,11 @@ static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev) if (test_and_clear_bit(BNXT_RE_FLAG_QOS_WORK_REG, &rdev->flags)) cancel_delayed_work(&rdev->worker); - bnxt_re_cleanup_res(rdev); - bnxt_re_free_res(rdev); + if (test_and_clear_bit(BNXT_RE_FLAG_RESOURCES_INITIALIZED, + &rdev->flags)) + bnxt_re_cleanup_res(rdev); + if (test_and_clear_bit(BNXT_RE_FLAG_RESOURCES_ALLOCATED, &rdev->flags)) + bnxt_re_free_res(rdev); if (test_and_clear_bit(BNXT_RE_FLAG_RCFW_CHANNEL_EN, &rdev->flags)) { rc = bnxt_qplib_deinit_rcfw(&rdev->rcfw); @@ -1337,12 +1347,15 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev) pr_err("Failed to allocate resources: %#x\n", rc); goto fail; } + set_bit(BNXT_RE_FLAG_RESOURCES_ALLOCATED, &rdev->flags); rc = bnxt_re_init_res(rdev); if (rc) { pr_err("Failed to initialize resources: %#x\n", rc); goto fail; } + set_bit(BNXT_RE_FLAG_RESOURCES_INITIALIZED, &rdev->flags); + if (!rdev->is_virtfn) { rc = bnxt_re_setup_qos(rdev); if (rc) From ad78a958663aa7d37a41de5779f048e2334ecd09 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 16 Oct 2018 08:22:28 +0200 Subject: [PATCH 060/299] pinctrl: sunxi: Fix a memory leak in 'sunxi_pinctrl_build_state()' [ Upstream commit a93a676b079144009f55fff2ab0e34c3b7258c8a ] If 'krealloc()' fails, 'pctl->functions' is set to NULL. We should instead use a temp variable in order to be able to free the previously allocated memeory, in case of OOM. Signed-off-by: Christophe JAILLET Acked-by: Maxime Ripard Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/sunxi/pinctrl-sunxi.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index 26ebedc1f6d3..61aaaf58c599 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -1042,6 +1042,7 @@ static int sunxi_pinctrl_add_function(struct sunxi_pinctrl *pctl, static int sunxi_pinctrl_build_state(struct platform_device *pdev) { struct sunxi_pinctrl *pctl = platform_get_drvdata(pdev); + void *ptr; int i; /* @@ -1108,13 +1109,15 @@ static int sunxi_pinctrl_build_state(struct platform_device *pdev) } /* And now allocated and fill the array for real */ - pctl->functions = krealloc(pctl->functions, - pctl->nfunctions * sizeof(*pctl->functions), - GFP_KERNEL); - if (!pctl->functions) { + ptr = krealloc(pctl->functions, + pctl->nfunctions * sizeof(*pctl->functions), + GFP_KERNEL); + if (!ptr) { kfree(pctl->functions); + pctl->functions = NULL; return -ENOMEM; } + pctl->functions = ptr; for (i = 0; i < pctl->desc->npins; i++) { const struct sunxi_desc_pin *pin = pctl->desc->pins + i; From 4043bc0f634bf349da5612e87e189a6d71bad504 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 14 Oct 2018 17:12:02 +0200 Subject: [PATCH 061/299] pwm: lpss: Only set update bit if we are actually changing the settings [ Upstream commit 2153bbc12f77fb2203276befc0f0dddbfb023bb1 ] According to the datasheet the update bit must be set if the on-time-div or the base-unit changes. Now that we properly order device resume on Cherry Trail so that the GFX0 _PS0 method no longer exits with an error, we end up with a sequence of events where we are writing the same values twice in a row. First the _PS0 method restores the duty cycle of 0% the GPU driver set on suspend and then the GPU driver first updates just the enabled bit in the pwm_state from 0 to 1, causing us to write the same values again, before restoring the pre-suspend duty-cycle in a separate pwm_apply call. When writing the update bit the second time, without changing any of the values the update bit clears immediately / instantly, instead of staying 1 for a while as usual. After this the next setting of the update bit seems to be ignored, causing the restoring of the pre-suspend duty-cycle to not get applied. This makes the backlight come up with a 0% dutycycle after suspend/resume. Any further brightness changes after this do work. This commit moves the setting of the update bit into pwm_lpss_prepare() and only sets the bit if we have actually changed any of the values. This avoids the setting of the update bit the second time we configure the PWM to 0% dutycycle, this fixes the backlight coming up with 0% duty-cycle after a suspend/resume. Signed-off-by: Hans de Goede Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/pwm/pwm-lpss.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/pwm/pwm-lpss.c b/drivers/pwm/pwm-lpss.c index 4721a264bac2..1e69c1c9ec09 100644 --- a/drivers/pwm/pwm-lpss.c +++ b/drivers/pwm/pwm-lpss.c @@ -97,7 +97,7 @@ static void pwm_lpss_prepare(struct pwm_lpss_chip *lpwm, struct pwm_device *pwm, unsigned long long on_time_div; unsigned long c = lpwm->info->clk_rate, base_unit_range; unsigned long long base_unit, freq = NSEC_PER_SEC; - u32 ctrl; + u32 orig_ctrl, ctrl; do_div(freq, period_ns); @@ -114,13 +114,17 @@ static void pwm_lpss_prepare(struct pwm_lpss_chip *lpwm, struct pwm_device *pwm, do_div(on_time_div, period_ns); on_time_div = 255ULL - on_time_div; - ctrl = pwm_lpss_read(pwm); + orig_ctrl = ctrl = pwm_lpss_read(pwm); ctrl &= ~PWM_ON_TIME_DIV_MASK; ctrl &= ~(base_unit_range << PWM_BASE_UNIT_SHIFT); base_unit &= base_unit_range; ctrl |= (u32) base_unit << PWM_BASE_UNIT_SHIFT; ctrl |= on_time_div; - pwm_lpss_write(pwm, ctrl); + + if (orig_ctrl != ctrl) { + pwm_lpss_write(pwm, ctrl); + pwm_lpss_write(pwm, ctrl | PWM_SW_UPDATE); + } } static inline void pwm_lpss_cond_enable(struct pwm_device *pwm, bool cond) @@ -144,7 +148,6 @@ static int pwm_lpss_apply(struct pwm_chip *chip, struct pwm_device *pwm, return ret; } pwm_lpss_prepare(lpwm, pwm, state->duty_cycle, state->period); - pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE); pwm_lpss_cond_enable(pwm, lpwm->info->bypass == false); ret = pwm_lpss_wait_for_update(pwm); if (ret) { @@ -157,7 +160,6 @@ static int pwm_lpss_apply(struct pwm_chip *chip, struct pwm_device *pwm, if (ret) return ret; pwm_lpss_prepare(lpwm, pwm, state->duty_cycle, state->period); - pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE); return pwm_lpss_wait_for_update(pwm); } } else if (pwm_is_enabled(pwm)) { From 45f89cf0f329ac86e59ec18e163f6e5cb274dd49 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 11 Oct 2018 12:20:46 -0700 Subject: [PATCH 062/299] amiflop: clean up on errors during setup [ Upstream commit 53d0f8dbde89cf6c862c7a62e00c6123e02cba41 ] The error handling in fd_probe_drives() doesn't clean up at all. Fix it up in preparation for converting to blk-mq. While we're here, get rid of the commented out amiga_floppy_remove(). Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/block/amiflop.c | 84 ++++++++++++++++++++--------------------- 1 file changed, 40 insertions(+), 44 deletions(-) diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 3aaf6af3ec23..2158e130744e 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1701,11 +1701,41 @@ static const struct block_device_operations floppy_fops = { .check_events = amiga_check_events, }; +static struct gendisk *fd_alloc_disk(int drive) +{ + struct gendisk *disk; + + disk = alloc_disk(1); + if (!disk) + goto out; + + disk->queue = blk_init_queue(do_fd_request, &amiflop_lock); + if (IS_ERR(disk->queue)) { + disk->queue = NULL; + goto out_put_disk; + } + + unit[drive].trackbuf = kmalloc(FLOPPY_MAX_SECTORS * 512, GFP_KERNEL); + if (!unit[drive].trackbuf) + goto out_cleanup_queue; + + return disk; + +out_cleanup_queue: + blk_cleanup_queue(disk->queue); + disk->queue = NULL; +out_put_disk: + put_disk(disk); +out: + unit[drive].type->code = FD_NODRIVE; + return NULL; +} + static int __init fd_probe_drives(void) { int drive,drives,nomem; - printk(KERN_INFO "FD: probing units\nfound "); + pr_info("FD: probing units\nfound"); drives=0; nomem=0; for(drive=0;drivecode == FD_NODRIVE) continue; - disk = alloc_disk(1); + + disk = fd_alloc_disk(drive); if (!disk) { - unit[drive].type->code = FD_NODRIVE; + pr_cont(" no mem for fd%d", drive); + nomem = 1; continue; } unit[drive].gendisk = disk; - - disk->queue = blk_init_queue(do_fd_request, &amiflop_lock); - if (!disk->queue) { - unit[drive].type->code = FD_NODRIVE; - continue; - } - drives++; - if ((unit[drive].trackbuf = kmalloc(FLOPPY_MAX_SECTORS * 512, GFP_KERNEL)) == NULL) { - printk("no mem for "); - unit[drive].type = &drive_types[num_dr_types - 1]; /* FD_NODRIVE */ - drives--; - nomem = 1; - } - printk("fd%d ",drive); + + pr_cont(" fd%d",drive); disk->major = FLOPPY_MAJOR; disk->first_minor = drive; disk->fops = &floppy_fops; @@ -1744,11 +1764,11 @@ static int __init fd_probe_drives(void) } if ((drives > 0) || (nomem == 0)) { if (drives == 0) - printk("no drives"); - printk("\n"); + pr_cont(" no drives"); + pr_cont("\n"); return drives; } - printk("\n"); + pr_cont("\n"); return -ENOMEM; } @@ -1831,30 +1851,6 @@ out_blkdev: return ret; } -#if 0 /* not safe to unload */ -static int __exit amiga_floppy_remove(struct platform_device *pdev) -{ - int i; - - for( i = 0; i < FD_MAX_UNITS; i++) { - if (unit[i].type->code != FD_NODRIVE) { - struct request_queue *q = unit[i].gendisk->queue; - del_gendisk(unit[i].gendisk); - put_disk(unit[i].gendisk); - kfree(unit[i].trackbuf); - if (q) - blk_cleanup_queue(q); - } - } - blk_unregister_region(MKDEV(FLOPPY_MAJOR, 0), 256); - free_irq(IRQ_AMIGA_CIAA_TB, NULL); - free_irq(IRQ_AMIGA_DSKBLK, NULL); - custom.dmacon = DMAF_DISK; /* disable DMA */ - amiga_chip_free(raw_buf); - unregister_blkdev(FLOPPY_MAJOR, "fd"); -} -#endif - static struct platform_driver amiga_floppy_driver = { .driver = { .name = "amiga-floppy", From 073f454cc28ce791a236f9a02a48346d7041b0ee Mon Sep 17 00:00:00 2001 From: Rahul Verma Date: Tue, 16 Oct 2018 03:59:18 -0700 Subject: [PATCH 063/299] qed: Align local and global PTT to propagate through the APIs. [ Upstream commit 706d08913d1f68610c32b4a001026aa989878dd9 ] Align the use of local PTT to propagate through the qed_mcp* API's. Global ptt should not be used. Register access should be done through layers. Register address is mapped into a PTT, PF translation table. Several interface functions require a PTT to direct read/write into register. There is a pool of PTT maintained, and several PTT are used simultaneously to access device registers in different flows. Same PTT should not be used in flows that can run concurrently. To avoid running out of PTT resources, too many PTT should not be acquired without releasing them. Every PF has a global PTT, which is used throughout the life of PF, in most important flows for register access. Generic functions acquire the PTT locally and release after the use. This patch aligns the use of Global PTT and Local PTT accordingly. Signed-off-by: Rahul Verma Signed-off-by: Ariel Elior Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qed/qed.h | 2 +- drivers/net/ethernet/qlogic/qed/qed_main.c | 22 ++++++++++++++---- drivers/net/ethernet/qlogic/qed/qed_mcp.c | 27 ++++++++++------------ drivers/net/ethernet/qlogic/qed/qed_mcp.h | 5 ++-- drivers/net/ethernet/qlogic/qed/qed_vf.c | 2 +- 5 files changed, 35 insertions(+), 23 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index a60e1c8d470a..32e786a3952b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -914,7 +914,7 @@ u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc); /* Prototypes */ int qed_fill_dev_info(struct qed_dev *cdev, struct qed_dev_info *dev_info); -void qed_link_update(struct qed_hwfn *hwfn); +void qed_link_update(struct qed_hwfn *hwfn, struct qed_ptt *ptt); u32 qed_unzip_data(struct qed_hwfn *p_hwfn, u32 input_len, u8 *input_buf, u32 max_size, u8 *unzip_buf); diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 637687b766ff..049a83b40e46 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -1462,6 +1462,7 @@ static int qed_get_link_data(struct qed_hwfn *hwfn, } static void qed_fill_link(struct qed_hwfn *hwfn, + struct qed_ptt *ptt, struct qed_link_output *if_link) { struct qed_mcp_link_params params; @@ -1542,7 +1543,7 @@ static void qed_fill_link(struct qed_hwfn *hwfn, /* TODO - fill duplex properly */ if_link->duplex = DUPLEX_FULL; - qed_mcp_get_media_type(hwfn->cdev, &media_type); + qed_mcp_get_media_type(hwfn, ptt, &media_type); if_link->port = qed_get_port_type(media_type); if_link->autoneg = params.speed.autoneg; @@ -1598,21 +1599,34 @@ static void qed_fill_link(struct qed_hwfn *hwfn, static void qed_get_current_link(struct qed_dev *cdev, struct qed_link_output *if_link) { + struct qed_hwfn *hwfn; + struct qed_ptt *ptt; int i; - qed_fill_link(&cdev->hwfns[0], if_link); + hwfn = &cdev->hwfns[0]; + if (IS_PF(cdev)) { + ptt = qed_ptt_acquire(hwfn); + if (ptt) { + qed_fill_link(hwfn, ptt, if_link); + qed_ptt_release(hwfn, ptt); + } else { + DP_NOTICE(hwfn, "Failed to fill link; No PTT\n"); + } + } else { + qed_fill_link(hwfn, NULL, if_link); + } for_each_hwfn(cdev, i) qed_inform_vf_link_state(&cdev->hwfns[i]); } -void qed_link_update(struct qed_hwfn *hwfn) +void qed_link_update(struct qed_hwfn *hwfn, struct qed_ptt *ptt) { void *cookie = hwfn->cdev->ops_cookie; struct qed_common_cb_ops *op = hwfn->cdev->protocol_ops.common; struct qed_link_output if_link; - qed_fill_link(hwfn, &if_link); + qed_fill_link(hwfn, ptt, &if_link); qed_inform_vf_link_state(hwfn); if (IS_LEAD_HWFN(hwfn) && cookie) diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 58c7eb9d8e1b..938ace333af1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -1382,7 +1382,7 @@ static void qed_mcp_handle_link_change(struct qed_hwfn *p_hwfn, if (p_hwfn->mcp_info->capabilities & FW_MB_PARAM_FEATURE_SUPPORT_EEE) qed_mcp_read_eee_config(p_hwfn, p_ptt, p_link); - qed_link_update(p_hwfn); + qed_link_update(p_hwfn, p_ptt); out: spin_unlock_bh(&p_hwfn->mcp_info->link_lock); } @@ -1849,12 +1849,10 @@ int qed_mcp_get_mbi_ver(struct qed_hwfn *p_hwfn, return 0; } -int qed_mcp_get_media_type(struct qed_dev *cdev, u32 *p_media_type) +int qed_mcp_get_media_type(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *p_media_type) { - struct qed_hwfn *p_hwfn = &cdev->hwfns[0]; - struct qed_ptt *p_ptt; - - if (IS_VF(cdev)) + if (IS_VF(p_hwfn->cdev)) return -EINVAL; if (!qed_mcp_is_init(p_hwfn)) { @@ -1862,16 +1860,15 @@ int qed_mcp_get_media_type(struct qed_dev *cdev, u32 *p_media_type) return -EBUSY; } - *p_media_type = MEDIA_UNSPECIFIED; + if (!p_ptt) { + *p_media_type = MEDIA_UNSPECIFIED; + return -EINVAL; + } - p_ptt = qed_ptt_acquire(p_hwfn); - if (!p_ptt) - return -EBUSY; - - *p_media_type = qed_rd(p_hwfn, p_ptt, p_hwfn->mcp_info->port_addr + - offsetof(struct public_port, media_type)); - - qed_ptt_release(p_hwfn, p_ptt); + *p_media_type = qed_rd(p_hwfn, p_ptt, + p_hwfn->mcp_info->port_addr + + offsetof(struct public_port, + media_type)); return 0; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 85e6b3989e7a..80a6b5d1ff33 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -322,14 +322,15 @@ int qed_mcp_get_mbi_ver(struct qed_hwfn *p_hwfn, * @brief Get media type value of the port. * * @param cdev - qed dev pointer + * @param p_ptt * @param mfw_ver - media type value * * @return int - * 0 - Operation was successul. * -EBUSY - Operation failed */ -int qed_mcp_get_media_type(struct qed_dev *cdev, - u32 *media_type); +int qed_mcp_get_media_type(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *media_type); /** * @brief General function for sending commands to the MCP diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 6ab3fb008139..5dda547772c1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -1698,7 +1698,7 @@ static void qed_handle_bulletin_change(struct qed_hwfn *hwfn) ops->ports_update(cookie, vxlan_port, geneve_port); /* Always update link configuration according to bulletin */ - qed_link_update(hwfn); + qed_link_update(hwfn, NULL); } void qed_iov_vf_task(struct work_struct *work) From bfe01cddb81a58a1a24062a4d562496116f7c560 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 16 Oct 2018 11:12:23 +0200 Subject: [PATCH 064/299] scsi: ips: fix missing break in switch [ Upstream commit 5d25ff7a544889bc4b749fda31778d6a18dddbcb ] Add missing break statement in order to prevent the code from falling through to case TEST_UNIT_READY. Addresses-Coverity-ID: 1357338 ("Missing break in switch") Suggested-by: Martin K. Petersen Signed-off-by: Gustavo A. R. Silva Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/ips.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c index bd6ac6b5980a..fe587ef1741d 100644 --- a/drivers/scsi/ips.c +++ b/drivers/scsi/ips.c @@ -3485,6 +3485,7 @@ ips_send_cmd(ips_ha_t * ha, ips_scb_t * scb) case START_STOP: scb->scsi_cmd->result = DID_OK << 16; + break; case TEST_UNIT_READY: case INQUIRY: From cec14148c1a9ce23f404e01d56cb466b39dbe1c4 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 Oct 2018 15:19:09 -0700 Subject: [PATCH 065/299] nfp: bpf: protect against mis-initializing atomic counters [ Upstream commit 527db74b71ee5a279f818aae51f2c26b4e5c7648 ] Atomic operations on the NFP are currently always in big endian. The driver keeps track of regions of memory storing atomic values and byte swaps them accordingly. There are corner cases where the map values may be initialized before the driver knows they are used as atomic counters. This can happen either when the datapath is performing the update and the stack contents are unknown or when map is updated before the program which will use it for atomic values is loaded. To avoid situation where user initializes the value to 0 1 2 3 and then after loading a program which uses the word as an atomic counter starts reading 3 2 1 0 - only allow atomic counters to be initialized to endian-neutral values. For updates from the datapath the stack information may not be as precise, so just allow initializing such values to 0. Example code which would break: struct bpf_map_def SEC("maps") rxcnt = { .type = BPF_MAP_TYPE_HASH, .key_size = sizeof(__u32), .value_size = sizeof(__u64), .max_entries = 1, }; int xdp_prog1() { __u64 nonzeroval = 3; __u32 key = 0; __u64 *value; value = bpf_map_lookup_elem(&rxcnt, &key); if (!value) bpf_map_update_elem(&rxcnt, &key, &nonzeroval, BPF_ANY); else __sync_fetch_and_add(value, 1); return XDP_PASS; } $ offload bpftool map dump key: 00 00 00 00 value: 00 00 00 03 00 00 00 00 should be: $ offload bpftool map dump key: 00 00 00 00 value: 03 00 00 00 00 00 00 00 Reported-by: David Beckett Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- drivers/net/ethernet/netronome/nfp/bpf/main.h | 7 ++- .../net/ethernet/netronome/nfp/bpf/offload.c | 18 +++++- .../net/ethernet/netronome/nfp/bpf/verifier.c | 58 +++++++++++++++++-- 3 files changed, 76 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index dbd00982fd2b..2134045e14c3 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -206,6 +206,11 @@ enum nfp_bpf_map_use { NFP_MAP_USE_ATOMIC_CNT, }; +struct nfp_bpf_map_word { + unsigned char type :4; + unsigned char non_zero_update :1; +}; + /** * struct nfp_bpf_map - private per-map data attached to BPF maps for offload * @offmap: pointer to the offloaded BPF map @@ -219,7 +224,7 @@ struct nfp_bpf_map { struct nfp_app_bpf *bpf; u32 tid; struct list_head l; - enum nfp_bpf_map_use use_map[]; + struct nfp_bpf_map_word use_map[]; }; struct nfp_bpf_neutral_map { diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 1ccd6371a15b..6140e4650b71 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -299,10 +299,25 @@ static void nfp_map_bpf_byte_swap(struct nfp_bpf_map *nfp_map, void *value) unsigned int i; for (i = 0; i < DIV_ROUND_UP(nfp_map->offmap->map.value_size, 4); i++) - if (nfp_map->use_map[i] == NFP_MAP_USE_ATOMIC_CNT) + if (nfp_map->use_map[i].type == NFP_MAP_USE_ATOMIC_CNT) word[i] = (__force u32)cpu_to_be32(word[i]); } +/* Mark value as unsafely initialized in case it becomes atomic later + * and we didn't byte swap something non-byte swap neutral. + */ +static void +nfp_map_bpf_byte_swap_record(struct nfp_bpf_map *nfp_map, void *value) +{ + u32 *word = value; + unsigned int i; + + for (i = 0; i < DIV_ROUND_UP(nfp_map->offmap->map.value_size, 4); i++) + if (nfp_map->use_map[i].type == NFP_MAP_UNUSED && + word[i] != (__force u32)cpu_to_be32(word[i])) + nfp_map->use_map[i].non_zero_update = 1; +} + static int nfp_bpf_map_lookup_entry(struct bpf_offloaded_map *offmap, void *key, void *value) @@ -322,6 +337,7 @@ nfp_bpf_map_update_entry(struct bpf_offloaded_map *offmap, void *key, void *value, u64 flags) { nfp_map_bpf_byte_swap(offmap->dev_priv, value); + nfp_map_bpf_byte_swap_record(offmap->dev_priv, value); return nfp_bpf_ctrl_update_entry(offmap, key, value, flags); } diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c index a6e9248669e1..db7e186dae56 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c @@ -108,6 +108,46 @@ exit_set_location: nfp_prog->adjust_head_location = location; } +static bool nfp_bpf_map_update_value_ok(struct bpf_verifier_env *env) +{ + const struct bpf_reg_state *reg1 = cur_regs(env) + BPF_REG_1; + const struct bpf_reg_state *reg3 = cur_regs(env) + BPF_REG_3; + struct bpf_offloaded_map *offmap; + struct bpf_func_state *state; + struct nfp_bpf_map *nfp_map; + int off, i; + + state = env->cur_state->frame[reg3->frameno]; + + /* We need to record each time update happens with non-zero words, + * in case such word is used in atomic operations. + * Implicitly depend on nfp_bpf_stack_arg_ok(reg3) being run before. + */ + + offmap = map_to_offmap(reg1->map_ptr); + nfp_map = offmap->dev_priv; + off = reg3->off + reg3->var_off.value; + + for (i = 0; i < offmap->map.value_size; i++) { + struct bpf_stack_state *stack_entry; + unsigned int soff; + + soff = -(off + i) - 1; + stack_entry = &state->stack[soff / BPF_REG_SIZE]; + if (stack_entry->slot_type[soff % BPF_REG_SIZE] == STACK_ZERO) + continue; + + if (nfp_map->use_map[i / 4].type == NFP_MAP_USE_ATOMIC_CNT) { + pr_vlog(env, "value at offset %d/%d may be non-zero, bpf_map_update_elem() is required to initialize atomic counters to zero to avoid offload endian issues\n", + i, soff); + return false; + } + nfp_map->use_map[i / 4].non_zero_update = 1; + } + + return true; +} + static int nfp_bpf_stack_arg_ok(const char *fname, struct bpf_verifier_env *env, const struct bpf_reg_state *reg, @@ -198,7 +238,8 @@ nfp_bpf_check_call(struct nfp_prog *nfp_prog, struct bpf_verifier_env *env, bpf->helpers.map_update, reg1) || !nfp_bpf_stack_arg_ok("map_update", env, reg2, meta->func_id ? &meta->arg2 : NULL) || - !nfp_bpf_stack_arg_ok("map_update", env, reg3, NULL)) + !nfp_bpf_stack_arg_ok("map_update", env, reg3, NULL) || + !nfp_bpf_map_update_value_ok(env)) return -EOPNOTSUPP; break; @@ -376,15 +417,22 @@ nfp_bpf_map_mark_used_one(struct bpf_verifier_env *env, struct nfp_bpf_map *nfp_map, unsigned int off, enum nfp_bpf_map_use use) { - if (nfp_map->use_map[off / 4] != NFP_MAP_UNUSED && - nfp_map->use_map[off / 4] != use) { + if (nfp_map->use_map[off / 4].type != NFP_MAP_UNUSED && + nfp_map->use_map[off / 4].type != use) { pr_vlog(env, "map value use type conflict %s vs %s off: %u\n", - nfp_bpf_map_use_name(nfp_map->use_map[off / 4]), + nfp_bpf_map_use_name(nfp_map->use_map[off / 4].type), nfp_bpf_map_use_name(use), off); return -EOPNOTSUPP; } - nfp_map->use_map[off / 4] = use; + if (nfp_map->use_map[off / 4].non_zero_update && + use == NFP_MAP_USE_ATOMIC_CNT) { + pr_vlog(env, "atomic counter in map value may already be initialized to non-zero value off: %u\n", + off); + return -EOPNOTSUPP; + } + + nfp_map->use_map[off / 4].type = use; return 0; } From 9fe573d539a827d123ba7503cc8ac2301424d26b Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 26 Sep 2018 09:23:42 -0700 Subject: [PATCH 066/299] KVM: nVMX: reset cache/shadows when switching loaded VMCS [ Upstream commit b7031fd40fcc741b0f9b0c04c8d844e445858b84 ] Reset the vm_{entry,exit}_controls_shadow variables as well as the segment cache after loading a new VMCS in vmx_switch_vmcs(). The shadows/cache track VMCS data, i.e. they're stale every time we switch to a new VMCS regardless of reason. This fixes a bug where stale control shadows would be consumed after a nested VMExit due to a failed consistency check. Suggested-by: Jim Mattson Signed-off-by: Sean Christopherson Reviewed-by: Jim Mattson Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin --- arch/x86/kvm/vmx.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 1ab4bb3d6a04..fe7fdd666f09 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -11013,6 +11013,10 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) vmx->loaded_vmcs = vmcs; vmx_vcpu_load(vcpu, cpu); put_cpu(); + + vm_entry_controls_reset_shadow(vmx); + vm_exit_controls_reset_shadow(vmx); + vmx_segment_cache_clear(vmx); } /* @@ -12699,7 +12703,6 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); - vmx_segment_cache_clear(vmx); if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) vcpu->arch.tsc_offset += vmcs12->tsc_offset; @@ -13530,9 +13533,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, } vmx_switch_vmcs(vcpu, &vmx->vmcs01); - vm_entry_controls_reset_shadow(vmx); - vm_exit_controls_reset_shadow(vmx); - vmx_segment_cache_clear(vmx); /* Update any VMCS fields that might have changed while L2 ran */ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); From 7392aa08f8a4386c99d5c6506a79e2ccd5b4701f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 26 Sep 2018 09:23:46 -0700 Subject: [PATCH 067/299] KVM: nVMX: move check_vmentry_postreqs() call to nested_vmx_enter_non_root_mode() [ Upstream commit 7671ce21b13b9596163a29f4712cb2451a9b97dc ] In preparation of supporting checkpoint/restore for nested state, commit ca0bde28f2ed ("kvm: nVMX: Split VMCS checks from nested_vmx_run()") modified check_vmentry_postreqs() to only perform the guest EFER consistency checks when nested_run_pending is true. But, in the normal nested VMEntry flow, nested_run_pending is only set after check_vmentry_postreqs(), i.e. the consistency check is being skipped. Alternatively, nested_run_pending could be set prior to calling check_vmentry_postreqs() in nested_vmx_run(), but placing the consistency checks in nested_vmx_enter_non_root_mode() allows us to split prepare_vmcs02() and interleave the preparation with the consistency checks without having to change the call sites of nested_vmx_enter_non_root_mode(). In other words, the rest of the consistency check code in nested_vmx_run() will be joining the postreqs checks in future patches. Fixes: ca0bde28f2ed ("kvm: nVMX: Split VMCS checks from nested_vmx_run()") Signed-off-by: Sean Christopherson Cc: Jim Mattson Reviewed-by: Jim Mattson Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin --- arch/x86/kvm/vmx.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index fe7fdd666f09..bdf019f32211 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -12694,6 +12694,9 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu)) evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu); + if (from_vmentry && check_vmentry_postreqs(vcpu, vmcs12, exit_qual)) + return EXIT_REASON_INVALID_STATE; + enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) @@ -12836,13 +12839,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) */ skip_emulated_instruction(vcpu); - ret = check_vmentry_postreqs(vcpu, vmcs12, &exit_qual); - if (ret) { - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, exit_qual); - return 1; - } - /* * We're finally done with prerequisite checking, and can start with * the nested entry. From 5a487f40e717b99855be143497118de0452064d1 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Thu, 11 Oct 2018 19:40:43 +0200 Subject: [PATCH 068/299] KVM/x86: Fix invvpid and invept register operand size in 64-bit mode [ Upstream commit 5ebb272b2ea7e02911a03a893f8d922d49f9bb4a ] Register operand size of invvpid and invept instruction in 64-bit mode has always 64 bits. Adjust inline function argument type to reflect correct size. Signed-off-by: Uros Bizjak Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin --- arch/x86/kvm/vmx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index bdf019f32211..0b7559bf15ea 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2079,7 +2079,7 @@ static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr) return -1; } -static inline void __invvpid(int ext, u16 vpid, gva_t gva) +static inline void __invvpid(unsigned long ext, u16 vpid, gva_t gva) { struct { u64 vpid : 16; @@ -2094,7 +2094,7 @@ static inline void __invvpid(int ext, u16 vpid, gva_t gva) BUG_ON(error); } -static inline void __invept(int ext, u64 eptp, gpa_t gpa) +static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa) { struct { u64 eptp, gpa; From 6288f52ed258d688726a31e7206061fad4833994 Mon Sep 17 00:00:00 2001 From: Joseph Lo Date: Thu, 27 Sep 2018 10:32:03 +0800 Subject: [PATCH 069/299] clk: tegra: Fixes for MBIST work around [ Upstream commit a4dbbceeee3e0ba670875a147237d6566de78840 ] Fix some incorrect data in LVL2 offset and bit mask. Fixes: e403d0057343 ("clk: tegra: MBIST work around for Tegra210") Signed-off-by: Joseph Lo Signed-off-by: Peter De Schrijver Acked-by: Jon Hunter Acked-by: Peter De Schrijver Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/tegra/clk-tegra210.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c index 080bfa24863e..7264e9731034 100644 --- a/drivers/clk/tegra/clk-tegra210.c +++ b/drivers/clk/tegra/clk-tegra210.c @@ -2603,7 +2603,7 @@ static struct tegra210_domain_mbist_war tegra210_pg_mbist_war[] = { [TEGRA_POWERGATE_MPE] = { .handle_lvl2_ovr = tegra210_generic_mbist_war, .lvl2_offset = LVL2_CLK_GATE_OVRE, - .lvl2_mask = BIT(2), + .lvl2_mask = BIT(29), }, [TEGRA_POWERGATE_SOR] = { .handle_lvl2_ovr = tegra210_generic_mbist_war, @@ -2654,14 +2654,14 @@ static struct tegra210_domain_mbist_war tegra210_pg_mbist_war[] = { .num_clks = ARRAY_SIZE(nvdec_slcg_clkids), .clk_init_data = nvdec_slcg_clkids, .handle_lvl2_ovr = tegra210_generic_mbist_war, - .lvl2_offset = LVL2_CLK_GATE_OVRC, + .lvl2_offset = LVL2_CLK_GATE_OVRE, .lvl2_mask = BIT(9) | BIT(31), }, [TEGRA_POWERGATE_NVJPG] = { .num_clks = ARRAY_SIZE(nvjpg_slcg_clkids), .clk_init_data = nvjpg_slcg_clkids, .handle_lvl2_ovr = tegra210_generic_mbist_war, - .lvl2_offset = LVL2_CLK_GATE_OVRC, + .lvl2_offset = LVL2_CLK_GATE_OVRE, .lvl2_mask = BIT(9) | BIT(31), }, [TEGRA_POWERGATE_AUD] = { From 3a40068dc831b5e364b709613996754962e95cab Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 26 Sep 2018 17:11:50 -0700 Subject: [PATCH 070/299] scsi: isci: Use proper enumerated type in atapi_d2h_reg_frame_handler [ Upstream commit e9e9a103528c7e199ead6e5374c9c52cf16b5802 ] Clang warns when one enumerated type is implicitly converted to another. drivers/scsi/isci/request.c:1629:13: warning: implicit conversion from enumeration type 'enum sci_io_status' to different enumeration type 'enum sci_status' [-Wenum-conversion] status = SCI_IO_FAILURE_RESPONSE_VALID; ~ ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/scsi/isci/request.c:1631:12: warning: implicit conversion from enumeration type 'enum sci_io_status' to different enumeration type 'enum sci_status' [-Wenum-conversion] status = SCI_IO_FAILURE_RESPONSE_VALID; ~ ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~ status is of type sci_status but SCI_IO_FAILURE_RESPONSE_VALID is of type sci_io_status. Use SCI_FAILURE_IO_RESPONSE_VALID, which is from sci_status and has SCI_IO_FAILURE_RESPONSE_VALID's exact value since that is what SCI_IO_FAILURE_RESPONSE_VALID is mapped to in the isci.h file. Link: https://github.com/ClangBuiltLinux/linux/issues/153 Signed-off-by: Nathan Chancellor Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/isci/request.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c index ed197bc8e801..2f151708b59a 100644 --- a/drivers/scsi/isci/request.c +++ b/drivers/scsi/isci/request.c @@ -1626,9 +1626,9 @@ static enum sci_status atapi_d2h_reg_frame_handler(struct isci_request *ireq, if (status == SCI_SUCCESS) { if (ireq->stp.rsp.status & ATA_ERR) - status = SCI_IO_FAILURE_RESPONSE_VALID; + status = SCI_FAILURE_IO_RESPONSE_VALID; } else { - status = SCI_IO_FAILURE_RESPONSE_VALID; + status = SCI_FAILURE_IO_RESPONSE_VALID; } if (status != SCI_SUCCESS) { From f4bf2dc77826c0dfa98aed87ae829e0f070c2e61 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 26 Sep 2018 17:12:00 -0700 Subject: [PATCH 071/299] scsi: isci: Change sci_controller_start_task's return type to sci_status [ Upstream commit 362b5da3dfceada6e74ecdd7af3991bbe42c0c0f ] Clang warns when an enumerated type is implicitly converted to another. drivers/scsi/isci/request.c:3476:13: warning: implicit conversion from enumeration type 'enum sci_task_status' to different enumeration type 'enum sci_status' [-Wenum-conversion] status = sci_controller_start_task(ihost, ~ ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/scsi/isci/host.c:2744:10: warning: implicit conversion from enumeration type 'enum sci_status' to different enumeration type 'enum sci_task_status' [-Wenum-conversion] return SCI_SUCCESS; ~~~~~~ ^~~~~~~~~~~ drivers/scsi/isci/host.c:2753:9: warning: implicit conversion from enumeration type 'enum sci_status' to different enumeration type 'enum sci_task_status' [-Wenum-conversion] return status; ~~~~~~ ^~~~~~ Avoid all of these implicit conversion by just making sci_controller_start_task use sci_status. This silences Clang and has no functional change since sci_task_status has all of its values mapped to something in sci_status. Link: https://github.com/ClangBuiltLinux/linux/issues/153 Signed-off-by: Nathan Chancellor Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/isci/host.c | 8 ++++---- drivers/scsi/isci/host.h | 2 +- drivers/scsi/isci/task.c | 4 ++-- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/scsi/isci/host.c b/drivers/scsi/isci/host.c index 1ee3868ade07..7b5deae68d33 100644 --- a/drivers/scsi/isci/host.c +++ b/drivers/scsi/isci/host.c @@ -2717,9 +2717,9 @@ enum sci_status sci_controller_continue_io(struct isci_request *ireq) * the task management request. * @task_request: the handle to the task request object to start. */ -enum sci_task_status sci_controller_start_task(struct isci_host *ihost, - struct isci_remote_device *idev, - struct isci_request *ireq) +enum sci_status sci_controller_start_task(struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq) { enum sci_status status; @@ -2728,7 +2728,7 @@ enum sci_task_status sci_controller_start_task(struct isci_host *ihost, "%s: SCIC Controller starting task from invalid " "state\n", __func__); - return SCI_TASK_FAILURE_INVALID_STATE; + return SCI_FAILURE_INVALID_STATE; } status = sci_remote_device_start_task(ihost, idev, ireq); diff --git a/drivers/scsi/isci/host.h b/drivers/scsi/isci/host.h index b3539928073c..6bc3f022630a 100644 --- a/drivers/scsi/isci/host.h +++ b/drivers/scsi/isci/host.h @@ -489,7 +489,7 @@ enum sci_status sci_controller_start_io( struct isci_remote_device *idev, struct isci_request *ireq); -enum sci_task_status sci_controller_start_task( +enum sci_status sci_controller_start_task( struct isci_host *ihost, struct isci_remote_device *idev, struct isci_request *ireq); diff --git a/drivers/scsi/isci/task.c b/drivers/scsi/isci/task.c index 6dcaed0c1fc8..fb6eba331ac6 100644 --- a/drivers/scsi/isci/task.c +++ b/drivers/scsi/isci/task.c @@ -258,7 +258,7 @@ static int isci_task_execute_tmf(struct isci_host *ihost, struct isci_tmf *tmf, unsigned long timeout_ms) { DECLARE_COMPLETION_ONSTACK(completion); - enum sci_task_status status = SCI_TASK_FAILURE; + enum sci_status status = SCI_FAILURE; struct isci_request *ireq; int ret = TMF_RESP_FUNC_FAILED; unsigned long flags; @@ -301,7 +301,7 @@ static int isci_task_execute_tmf(struct isci_host *ihost, /* start the TMF io. */ status = sci_controller_start_task(ihost, idev, ireq); - if (status != SCI_TASK_SUCCESS) { + if (status != SCI_SUCCESS) { dev_dbg(&ihost->pdev->dev, "%s: start_io failed - status = 0x%x, request = %p\n", __func__, From 06815ae5e27f3dd6ab2f4c318f85e50c7d2dce37 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 27 Sep 2018 16:56:52 -0700 Subject: [PATCH 072/299] scsi: bfa: Avoid implicit enum conversion in bfad_im_post_vendor_event [ Upstream commit 761c830ec7b3d0674b3ad89cefd77a692634e305 ] Clang warns when one enumerated type is implicitly converted to another. drivers/scsi/bfa/bfa_fcs_lport.c:379:26: warning: implicit conversion from enumeration type 'enum bfa_lport_aen_event' to different enumeration type 'enum bfa_ioc_aen_event' [-Wenum-conversion] BFA_AEN_CAT_LPORT, event); ^~~~~ The root cause of these warnings is the bfad_im_post_vendor_event function, which expects a value from enum bfa_ioc_aen_event but there are multiple instances of values from enums bfa_port_aen_event, bfa_audit_aen_event, and bfa_lport_aen_event being used in this function. Given that this doesn't appear to be a problem since cat helps with differentiating the events, just change evt's type to int so that no conversion needs to happen and Clang won't warn. Update aen_type's type in bfa_aen_entry_s as members that hold enumerated types should be int. Link: https://github.com/ClangBuiltLinux/linux/issues/147 Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/bfa/bfa_defs_svc.h | 2 +- drivers/scsi/bfa/bfad_im.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/bfa/bfa_defs_svc.h b/drivers/scsi/bfa/bfa_defs_svc.h index 3d0c96a5c873..c19c26e0e405 100644 --- a/drivers/scsi/bfa/bfa_defs_svc.h +++ b/drivers/scsi/bfa/bfa_defs_svc.h @@ -1453,7 +1453,7 @@ union bfa_aen_data_u { struct bfa_aen_entry_s { struct list_head qe; enum bfa_aen_category aen_category; - u32 aen_type; + int aen_type; union bfa_aen_data_u aen_data; u64 aen_tv_sec; u64 aen_tv_usec; diff --git a/drivers/scsi/bfa/bfad_im.h b/drivers/scsi/bfa/bfad_im.h index e61ed8dad0b4..bd4ac187fd8e 100644 --- a/drivers/scsi/bfa/bfad_im.h +++ b/drivers/scsi/bfa/bfad_im.h @@ -143,7 +143,7 @@ struct bfad_im_s { static inline void bfad_im_post_vendor_event(struct bfa_aen_entry_s *entry, struct bfad_s *drv, int cnt, enum bfa_aen_category cat, - enum bfa_ioc_aen_event evt) + int evt) { struct timespec64 ts; From 5bbeb4fcf39a96caab99d22c612edb7239af4063 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 3 Oct 2018 18:06:15 -0700 Subject: [PATCH 073/299] scsi: iscsi_tcp: Explicitly cast param in iscsi_sw_tcp_host_get_param [ Upstream commit 20054597f169090109fc3f0dfa1a48583f4178a4 ] Clang warns when one enumerated type is implicitly converted to another. drivers/scsi/iscsi_tcp.c:803:15: warning: implicit conversion from enumeration type 'enum iscsi_host_param' to different enumeration type 'enum iscsi_param' [-Wenum-conversion] &addr, param, buf); ^~~~~ 1 warning generated. iscsi_conn_get_addr_param handles ISCSI_HOST_PARAM_IPADDRESS just fine so add an explicit cast to iscsi_param to make it clear to Clang that this is expected behavior. Link: https://github.com/ClangBuiltLinux/linux/issues/153 Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/iscsi_tcp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index b025a0b74341..23354f206533 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -800,7 +800,8 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, return rc; return iscsi_conn_get_addr_param((struct sockaddr_storage *) - &addr, param, buf); + &addr, + (enum iscsi_param)param, buf); default: return iscsi_host_get_param(shost, param, buf); } From 30ca1af4948123174d1b63bf6d6f967857a6a638 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 10 Oct 2018 14:40:07 -0700 Subject: [PATCH 074/299] crypto: ccree - avoid implicit enum conversion [ Upstream commit 18e732b8035d175181aae2ded127994cb01694f7 ] Clang warns when one enumerated type is implicitly converted to another and this happens in several locations in this driver, ultimately related to the set_cipher_{mode,config0} functions. set_cipher_mode expects a mode of type drv_cipher_mode and set_cipher_config0 expects a mode of type drv_crypto_direction. drivers/crypto/ccree/cc_ivgen.c:58:35: warning: implicit conversion from enumeration type 'enum cc_desc_direction' to different enumeration type 'enum drv_crypto_direction' [-Wenum-conversion] set_cipher_config0(&iv_seq[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT); drivers/crypto/ccree/cc_hash.c:99:28: warning: implicit conversion from enumeration type 'enum cc_hash_conf_pad' to different enumeration type 'enum drv_crypto_direction' [-Wenum-conversion] set_cipher_config0(desc, HASH_DIGEST_RESULT_LITTLE_ENDIAN); drivers/crypto/ccree/cc_aead.c:1643:30: warning: implicit conversion from enumeration type 'enum drv_hash_hw_mode' to different enumeration type 'enum drv_cipher_mode' [-Wenum-conversion] set_cipher_mode(&desc[idx], DRV_HASH_HW_GHASH); Since this fundamentally isn't a problem because these values just represent simple integers for a shift operation, make it clear to Clang that this is okay by making the mode parameter in both functions an int. Link: https://github.com/ClangBuiltLinux/linux/issues/46 Signed-off-by: Nathan Chancellor Acked-by: Gilad Ben-Yossef Reviewed-by: Nick Desaulniers Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/ccree/cc_hw_queue_defs.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/crypto/ccree/cc_hw_queue_defs.h b/drivers/crypto/ccree/cc_hw_queue_defs.h index a091ae57f902..45985b955d2c 100644 --- a/drivers/crypto/ccree/cc_hw_queue_defs.h +++ b/drivers/crypto/ccree/cc_hw_queue_defs.h @@ -449,8 +449,7 @@ static inline void set_flow_mode(struct cc_hw_desc *pdesc, * @pdesc: pointer HW descriptor struct * @mode: Any one of the modes defined in [CC7x-DESC] */ -static inline void set_cipher_mode(struct cc_hw_desc *pdesc, - enum drv_cipher_mode mode) +static inline void set_cipher_mode(struct cc_hw_desc *pdesc, int mode) { pdesc->word[4] |= FIELD_PREP(WORD4_CIPHER_MODE, mode); } @@ -461,8 +460,7 @@ static inline void set_cipher_mode(struct cc_hw_desc *pdesc, * @pdesc: pointer HW descriptor struct * @mode: Any one of the modes defined in [CC7x-DESC] */ -static inline void set_cipher_config0(struct cc_hw_desc *pdesc, - enum drv_crypto_direction mode) +static inline void set_cipher_config0(struct cc_hw_desc *pdesc, int mode) { pdesc->word[4] |= FIELD_PREP(WORD4_CIPHER_CONF0, mode); } From 2f1e4e65ba415908212d93d665a8338dad1aac8a Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 8 Oct 2018 14:28:52 -0700 Subject: [PATCH 075/299] nvmet: avoid integer overflow in the discard code [ Upstream commit 8eacd1bd21d6913ec27e6120e9a8733352e191d3 ] Although I'm not sure whether it is a good idea to support large discard commands, I think integer overflow for discard ranges larger than 4 GB should be avoided. This patch avoids that smatch reports the following: drivers/nvme/target/io-cmd-file.c:249:1 nvmet_file_execute_discard() warn: should '((range.nlb)) << req->ns->blksize_shift' be a 64 bit type? Fixes: d5eff33ee6f8 ("nvmet: add simple file backed ns support") Signed-off-by: Bart Van Assche Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/target/io-cmd-file.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 81a9dc5290a8..39d972e2595f 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -246,7 +246,8 @@ static void nvmet_file_execute_discard(struct nvmet_req *req) break; offset = le64_to_cpu(range.slba) << req->ns->blksize_shift; - len = le32_to_cpu(range.nlb) << req->ns->blksize_shift; + len = le32_to_cpu(range.nlb); + len <<= req->ns->blksize_shift; if (offset + len > req->ns->size) { ret = NVME_SC_LBA_RANGE | NVME_SC_DNR; break; From 4e4b97f59050f5ede5ef13b8db8d2fdf13aab136 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 10 Oct 2018 08:08:20 -0700 Subject: [PATCH 076/299] nvmet-fcloop: suppress a compiler warning [ Upstream commit 1216e9ef18b84f4fb5934792368fb01eb3540520 ] Building with W=1 enables the compiler warning -Wimplicit-fallthrough=3. That option does not recognize the fall-through comment in the fcloop driver. Add a fall-through comment that is recognized for -Wimplicit-fallthrough=3. This patch avoids that the compiler reports the following warning when building with W=1: drivers/nvme/target/fcloop.c:647:6: warning: this statement may fall through [-Wimplicit-fallthrough=] if (op == NVMET_FCOP_READDATA) ^ Signed-off-by: Bart Van Assche Reviewed-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/target/fcloop.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 5251689a1d9a..291f4121f516 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -648,6 +648,7 @@ fcloop_fcp_op(struct nvmet_fc_target_port *tgtport, break; /* Fall-Thru to RSP handling */ + /* FALLTHRU */ case NVMET_FCOP_RSP: if (fcpreq) { From 305c262fb8ee63d8343a258704eb72876cdca9c7 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 15 Oct 2018 10:19:06 -0600 Subject: [PATCH 077/299] nvme-pci: fix hot removal during error handling [ Upstream commit cb4bfda62afa25b4eee3d635d33fccdd9485dd7c ] A removal waits for the reset_work to complete. If a surprise removal occurs around the same time as an error triggered controller reset, and reset work happened to dispatch a command to the removed controller, the command won't be recovered since the timeout work doesn't do anything during error recovery. We wouldn't want to wait for timeout handling anyway, so this patch fixes this by disabling the controller and killing admin queues prior to syncing with the reset_work. Signed-off-by: Keith Busch Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/host/pci.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index a64a8bca0d5b..9479c0db08f6 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2583,13 +2583,12 @@ static void nvme_remove(struct pci_dev *pdev) struct nvme_dev *dev = pci_get_drvdata(pdev); nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING); - - cancel_work_sync(&dev->ctrl.reset_work); pci_set_drvdata(pdev, NULL); if (!pci_device_is_present(pdev)) { nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DEAD); nvme_dev_disable(dev, true); + nvme_dev_remove_admin(dev); } flush_work(&dev->ctrl.reset_work); From 6391dd5eb0ef9fe7367819e32640dc853e8fd0c0 Mon Sep 17 00:00:00 2001 From: Honghui Zhang Date: Mon, 15 Oct 2018 16:08:56 +0800 Subject: [PATCH 078/299] PCI: mediatek: Fixup MSI enablement logic by enabling MSI before clocks [ Upstream commit 3828d60fd2ef99f97a677c1f95af2ab3e65e2576 ] Commit 43e6409db64d ("PCI: mediatek: Add MSI support for MT2712 and MT7622") added MSI support but enabled MSI in the wrong place, at a step in the probe sequence where clocks were not still enabled. Fix this issue by calling mtk_pcie_enable_msi() in mtk_pcie_startup_port_v2() since clocks are enabled when mtk_pcie_startup_port_v2() is called. To avoid forward declaration of mtk_pcie_enable_msi(), move the mtk_pcie_startup_port_v2() function definition in the file. Fixes: 43e6409db64d ("PCI: mediatek: Add MSI support for MT2712 and MT7622") Signed-off-by: Honghui Zhang [lorenzo.pieralisi@arm.com: squashed commit and adapted log] Signed-off-by: Lorenzo Pieralisi Acked-by: Ryder Lee Signed-off-by: Sasha Levin --- drivers/pci/controller/pcie-mediatek.c | 143 +++++++++++++------------ 1 file changed, 72 insertions(+), 71 deletions(-) diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index 8d1364c31774..1bfbceb9f445 100644 --- a/drivers/pci/controller/pcie-mediatek.c +++ b/drivers/pci/controller/pcie-mediatek.c @@ -394,75 +394,6 @@ static struct pci_ops mtk_pcie_ops_v2 = { .write = mtk_pcie_config_write, }; -static int mtk_pcie_startup_port_v2(struct mtk_pcie_port *port) -{ - struct mtk_pcie *pcie = port->pcie; - struct resource *mem = &pcie->mem; - const struct mtk_pcie_soc *soc = port->pcie->soc; - u32 val; - size_t size; - int err; - - /* MT7622 platforms need to enable LTSSM and ASPM from PCIe subsys */ - if (pcie->base) { - val = readl(pcie->base + PCIE_SYS_CFG_V2); - val |= PCIE_CSR_LTSSM_EN(port->slot) | - PCIE_CSR_ASPM_L1_EN(port->slot); - writel(val, pcie->base + PCIE_SYS_CFG_V2); - } - - /* Assert all reset signals */ - writel(0, port->base + PCIE_RST_CTRL); - - /* - * Enable PCIe link down reset, if link status changed from link up to - * link down, this will reset MAC control registers and configuration - * space. - */ - writel(PCIE_LINKDOWN_RST_EN, port->base + PCIE_RST_CTRL); - - /* De-assert PHY, PE, PIPE, MAC and configuration reset */ - val = readl(port->base + PCIE_RST_CTRL); - val |= PCIE_PHY_RSTB | PCIE_PERSTB | PCIE_PIPE_SRSTB | - PCIE_MAC_SRSTB | PCIE_CRSTB; - writel(val, port->base + PCIE_RST_CTRL); - - /* Set up vendor ID and class code */ - if (soc->need_fix_class_id) { - val = PCI_VENDOR_ID_MEDIATEK; - writew(val, port->base + PCIE_CONF_VEND_ID); - - val = PCI_CLASS_BRIDGE_PCI; - writew(val, port->base + PCIE_CONF_CLASS_ID); - } - - /* 100ms timeout value should be enough for Gen1/2 training */ - err = readl_poll_timeout(port->base + PCIE_LINK_STATUS_V2, val, - !!(val & PCIE_PORT_LINKUP_V2), 20, - 100 * USEC_PER_MSEC); - if (err) - return -ETIMEDOUT; - - /* Set INTx mask */ - val = readl(port->base + PCIE_INT_MASK); - val &= ~INTX_MASK; - writel(val, port->base + PCIE_INT_MASK); - - /* Set AHB to PCIe translation windows */ - size = mem->end - mem->start; - val = lower_32_bits(mem->start) | AHB2PCIE_SIZE(fls(size)); - writel(val, port->base + PCIE_AHB_TRANS_BASE0_L); - - val = upper_32_bits(mem->start); - writel(val, port->base + PCIE_AHB_TRANS_BASE0_H); - - /* Set PCIe to AXI translation memory space.*/ - val = fls(0xffffffff) | WIN_ENABLE; - writel(val, port->base + PCIE_AXI_WINDOW0); - - return 0; -} - static void mtk_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { struct mtk_pcie_port *port = irq_data_get_irq_chip_data(data); @@ -639,8 +570,6 @@ static int mtk_pcie_init_irq_domain(struct mtk_pcie_port *port, ret = mtk_pcie_allocate_msi_domains(port); if (ret) return ret; - - mtk_pcie_enable_msi(port); } return 0; @@ -707,6 +636,78 @@ static int mtk_pcie_setup_irq(struct mtk_pcie_port *port, return 0; } +static int mtk_pcie_startup_port_v2(struct mtk_pcie_port *port) +{ + struct mtk_pcie *pcie = port->pcie; + struct resource *mem = &pcie->mem; + const struct mtk_pcie_soc *soc = port->pcie->soc; + u32 val; + size_t size; + int err; + + /* MT7622 platforms need to enable LTSSM and ASPM from PCIe subsys */ + if (pcie->base) { + val = readl(pcie->base + PCIE_SYS_CFG_V2); + val |= PCIE_CSR_LTSSM_EN(port->slot) | + PCIE_CSR_ASPM_L1_EN(port->slot); + writel(val, pcie->base + PCIE_SYS_CFG_V2); + } + + /* Assert all reset signals */ + writel(0, port->base + PCIE_RST_CTRL); + + /* + * Enable PCIe link down reset, if link status changed from link up to + * link down, this will reset MAC control registers and configuration + * space. + */ + writel(PCIE_LINKDOWN_RST_EN, port->base + PCIE_RST_CTRL); + + /* De-assert PHY, PE, PIPE, MAC and configuration reset */ + val = readl(port->base + PCIE_RST_CTRL); + val |= PCIE_PHY_RSTB | PCIE_PERSTB | PCIE_PIPE_SRSTB | + PCIE_MAC_SRSTB | PCIE_CRSTB; + writel(val, port->base + PCIE_RST_CTRL); + + /* Set up vendor ID and class code */ + if (soc->need_fix_class_id) { + val = PCI_VENDOR_ID_MEDIATEK; + writew(val, port->base + PCIE_CONF_VEND_ID); + + val = PCI_CLASS_BRIDGE_PCI; + writew(val, port->base + PCIE_CONF_CLASS_ID); + } + + /* 100ms timeout value should be enough for Gen1/2 training */ + err = readl_poll_timeout(port->base + PCIE_LINK_STATUS_V2, val, + !!(val & PCIE_PORT_LINKUP_V2), 20, + 100 * USEC_PER_MSEC); + if (err) + return -ETIMEDOUT; + + /* Set INTx mask */ + val = readl(port->base + PCIE_INT_MASK); + val &= ~INTX_MASK; + writel(val, port->base + PCIE_INT_MASK); + + if (IS_ENABLED(CONFIG_PCI_MSI)) + mtk_pcie_enable_msi(port); + + /* Set AHB to PCIe translation windows */ + size = mem->end - mem->start; + val = lower_32_bits(mem->start) | AHB2PCIE_SIZE(fls(size)); + writel(val, port->base + PCIE_AHB_TRANS_BASE0_L); + + val = upper_32_bits(mem->start); + writel(val, port->base + PCIE_AHB_TRANS_BASE0_H); + + /* Set PCIe to AXI translation memory space.*/ + val = fls(0xffffffff) | WIN_ENABLE; + writel(val, port->base + PCIE_AXI_WINDOW0); + + return 0; +} + static void __iomem *mtk_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, int where) { From f15b802890bbfe30cae63f5d05531467db2e75d4 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Mon, 10 Sep 2018 14:01:44 +0200 Subject: [PATCH 079/299] clk: mmp2: fix the clock id for sdh2_clk and sdh3_clk [ Upstream commit 4917fb90eec7c26dac1497ada3bd4a325f670fcc ] A typo that makes it impossible to get the correct clocks for MMP2_CLK_SDH2 and MMP2_CLK_SDH3. Signed-off-by: Lubomir Rintel Fixes: 1ec770d92a62 ("clk: mmp: add mmp2 DT support for clock driver") Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/mmp/clk-of-mmp2.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/mmp/clk-of-mmp2.c b/drivers/clk/mmp/clk-of-mmp2.c index 0fc75c395957..d083b860f083 100644 --- a/drivers/clk/mmp/clk-of-mmp2.c +++ b/drivers/clk/mmp/clk-of-mmp2.c @@ -227,8 +227,8 @@ static struct mmp_param_gate_clk apmu_gate_clks[] = { /* The gate clocks has mux parent. */ {MMP2_CLK_SDH0, "sdh0_clk", "sdh_mix_clk", CLK_SET_RATE_PARENT, APMU_SDH0, 0x1b, 0x1b, 0x0, 0, &sdh_lock}, {MMP2_CLK_SDH1, "sdh1_clk", "sdh_mix_clk", CLK_SET_RATE_PARENT, APMU_SDH1, 0x1b, 0x1b, 0x0, 0, &sdh_lock}, - {MMP2_CLK_SDH1, "sdh2_clk", "sdh_mix_clk", CLK_SET_RATE_PARENT, APMU_SDH2, 0x1b, 0x1b, 0x0, 0, &sdh_lock}, - {MMP2_CLK_SDH1, "sdh3_clk", "sdh_mix_clk", CLK_SET_RATE_PARENT, APMU_SDH3, 0x1b, 0x1b, 0x0, 0, &sdh_lock}, + {MMP2_CLK_SDH2, "sdh2_clk", "sdh_mix_clk", CLK_SET_RATE_PARENT, APMU_SDH2, 0x1b, 0x1b, 0x0, 0, &sdh_lock}, + {MMP2_CLK_SDH3, "sdh3_clk", "sdh_mix_clk", CLK_SET_RATE_PARENT, APMU_SDH3, 0x1b, 0x1b, 0x0, 0, &sdh_lock}, {MMP2_CLK_DISP0, "disp0_clk", "disp0_div", CLK_SET_RATE_PARENT, APMU_DISP0, 0x1b, 0x1b, 0x0, 0, &disp0_lock}, {MMP2_CLK_DISP0_SPHY, "disp0_sphy_clk", "disp0_sphy_div", CLK_SET_RATE_PARENT, APMU_DISP0, 0x1024, 0x1024, 0x0, 0, &disp0_lock}, {MMP2_CLK_DISP1, "disp1_clk", "disp1_div", CLK_SET_RATE_PARENT, APMU_DISP1, 0x1b, 0x1b, 0x0, 0, &disp1_lock}, From f1f1002a998749efca04627a2aca3e09fe96bd48 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Tue, 16 Oct 2018 16:21:39 +0200 Subject: [PATCH 080/299] clk: at91: audio-pll: fix audio pmc type [ Upstream commit 7fa75007b7d7421aea59ff2b12ab1bd65a5abfa6 ] The allocation for the audio pmc is using the size of struct clk_audio_pad instead of struct clk_audio_pmc. This works fine because the former is larger than the latter but it is safer to be correct. Fixes: ("0865805d82d4 clk: at91: add audio pll clock drivers") Signed-off-by: Alexandre Belloni Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/at91/clk-audio-pll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/at91/clk-audio-pll.c b/drivers/clk/at91/clk-audio-pll.c index da7bafcfbe70..b3eaf654fac9 100644 --- a/drivers/clk/at91/clk-audio-pll.c +++ b/drivers/clk/at91/clk-audio-pll.c @@ -509,7 +509,7 @@ static void __init of_sama5d2_clk_audio_pll_pad_setup(struct device_node *np) static void __init of_sama5d2_clk_audio_pll_pmc_setup(struct device_node *np) { - struct clk_audio_pad *apmc_ck; + struct clk_audio_pmc *apmc_ck; struct clk_init_data init = {}; apmc_ck = kzalloc(sizeof(*apmc_ck), GFP_KERNEL); From 95655b10529d2b9beee913088b762df0146238be Mon Sep 17 00:00:00 2001 From: Marcel Ziswiler Date: Tue, 16 Oct 2018 12:47:29 +0200 Subject: [PATCH 081/299] ASoC: tegra_sgtl5000: fix device_node refcounting [ Upstream commit a85227da2dcc291b762c8482a505bc7d0d2d4b07 ] Similar to the following: commit 4321723648b0 ("ASoC: tegra_alc5632: fix device_node refcounting") commit 7c5dfd549617 ("ASoC: tegra: fix device_node refcounting") Signed-off-by: Marcel Ziswiler Acked-by: Jon Hunter Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/tegra/tegra_sgtl5000.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/sound/soc/tegra/tegra_sgtl5000.c b/sound/soc/tegra/tegra_sgtl5000.c index 45a4aa9d2a47..901457da25ec 100644 --- a/sound/soc/tegra/tegra_sgtl5000.c +++ b/sound/soc/tegra/tegra_sgtl5000.c @@ -149,14 +149,14 @@ static int tegra_sgtl5000_driver_probe(struct platform_device *pdev) dev_err(&pdev->dev, "Property 'nvidia,i2s-controller' missing/invalid\n"); ret = -EINVAL; - goto err; + goto err_put_codec_of_node; } tegra_sgtl5000_dai.platform_of_node = tegra_sgtl5000_dai.cpu_of_node; ret = tegra_asoc_utils_init(&machine->util_data, &pdev->dev); if (ret) - goto err; + goto err_put_cpu_of_node; ret = snd_soc_register_card(card); if (ret) { @@ -169,6 +169,13 @@ static int tegra_sgtl5000_driver_probe(struct platform_device *pdev) err_fini_utils: tegra_asoc_utils_fini(&machine->util_data); +err_put_cpu_of_node: + of_node_put(tegra_sgtl5000_dai.cpu_of_node); + tegra_sgtl5000_dai.cpu_of_node = NULL; + tegra_sgtl5000_dai.platform_of_node = NULL; +err_put_codec_of_node: + of_node_put(tegra_sgtl5000_dai.codec_of_node); + tegra_sgtl5000_dai.codec_of_node = NULL; err: return ret; } @@ -183,6 +190,12 @@ static int tegra_sgtl5000_driver_remove(struct platform_device *pdev) tegra_asoc_utils_fini(&machine->util_data); + of_node_put(tegra_sgtl5000_dai.cpu_of_node); + tegra_sgtl5000_dai.cpu_of_node = NULL; + tegra_sgtl5000_dai.platform_of_node = NULL; + of_node_put(tegra_sgtl5000_dai.codec_of_node); + tegra_sgtl5000_dai.codec_of_node = NULL; + return ret; } From e95ec662b1267022143ae03afdcc65715a76dc89 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Oct 2018 16:17:14 +0200 Subject: [PATCH 082/299] scsi: dc395x: fix dma API usage in srb_done [ Upstream commit 3a5bd7021184dec2946f2a4d7a8943f8a5713e52 ] We can't just transfer ownership to the CPU and then unmap, as this will break with swiotlb. Instead unmap the command and sense buffer a little earlier in the I/O completion handler and get rid of the pci_dma_sync_sg_for_cpu call entirely. Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/dc395x.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/dc395x.c b/drivers/scsi/dc395x.c index 1ed2cd82129d..08161df64ead 100644 --- a/drivers/scsi/dc395x.c +++ b/drivers/scsi/dc395x.c @@ -3447,14 +3447,12 @@ static void srb_done(struct AdapterCtlBlk *acb, struct DeviceCtlBlk *dcb, } } - if (dir != PCI_DMA_NONE && scsi_sg_count(cmd)) - pci_dma_sync_sg_for_cpu(acb->dev, scsi_sglist(cmd), - scsi_sg_count(cmd), dir); - ckc_only = 0; /* Check Error Conditions */ ckc_e: + pci_unmap_srb(acb, srb); + if (cmd->cmnd[0] == INQUIRY) { unsigned char *base = NULL; struct ScsiInqData *ptr; @@ -3507,7 +3505,6 @@ static void srb_done(struct AdapterCtlBlk *acb, struct DeviceCtlBlk *dcb, cmd, cmd->result); srb_free_insert(acb, srb); } - pci_unmap_srb(acb, srb); cmd->scsi_done(cmd); waiting_process_next(acb); From 1f13afca914fcd80f07c80ab36ccc6b6005460ed Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Oct 2018 16:17:15 +0200 Subject: [PATCH 083/299] scsi: dc395x: fix DMA API usage in sg_update_list [ Upstream commit 6c404a68bf83b4135a8a9aa1c388ebdf98e8ba7f ] We need to transfer device ownership to the CPU before we can manipulate the mapped data. Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/dc395x.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/scsi/dc395x.c b/drivers/scsi/dc395x.c index 08161df64ead..3943347ec3c7 100644 --- a/drivers/scsi/dc395x.c +++ b/drivers/scsi/dc395x.c @@ -1969,6 +1969,11 @@ static void sg_update_list(struct ScsiReqBlk *srb, u32 left) xferred -= psge->length; } else { /* Partial SG entry done */ + pci_dma_sync_single_for_cpu(srb->dcb-> + acb->dev, + srb->sg_bus_addr, + SEGMENTX_LEN, + PCI_DMA_TODEVICE); psge->length -= xferred; psge->address += xferred; srb->sg_index = idx; From 274726bcf5bac48ecc825a5c228fd5a630f932ac Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Tue, 16 Oct 2018 16:31:25 +1100 Subject: [PATCH 084/299] scsi: zorro_esp: Limit DMA transfers to 65535 bytes [ Upstream commit b7ded0e8b0d11b6df1c4e5aa23a26e6629c21985 ] The core driver, esp_scsi, does not use the ESP_CONFIG2_FENAB bit, so the chip's Transfer Counter register is only 16 bits wide (not 24). A larger transfer cannot work and will theoretically result in a failed command and a "DMA length is zero" error. Fixes: 3109e5ae0311 ("scsi: zorro_esp: New driver for Amiga Zorro NCR53C9x boards") Signed-off-by: Finn Thain Cc: Michael Schmitz Tested-by: Michael Schmitz Reviewed-by: Michael Schmitz Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/zorro_esp.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/scsi/zorro_esp.c b/drivers/scsi/zorro_esp.c index bb70882e6b56..be79127db594 100644 --- a/drivers/scsi/zorro_esp.c +++ b/drivers/scsi/zorro_esp.c @@ -245,7 +245,7 @@ static int fastlane_esp_irq_pending(struct esp *esp) static u32 zorro_esp_dma_length_limit(struct esp *esp, u32 dma_addr, u32 dma_len) { - return dma_len > 0xFFFFFF ? 0xFFFFFF : dma_len; + return dma_len > 0xFFFF ? 0xFFFF : dma_len; } static void zorro_esp_reset_dma(struct esp *esp) @@ -484,7 +484,6 @@ static void zorro_esp_send_blz1230_dma_cmd(struct esp *esp, u32 addr, scsi_esp_cmd(esp, ESP_CMD_DMA); zorro_esp_write8(esp, (esp_count >> 0) & 0xff, ESP_TCLOW); zorro_esp_write8(esp, (esp_count >> 8) & 0xff, ESP_TCMED); - zorro_esp_write8(esp, (esp_count >> 16) & 0xff, ESP_TCHI); scsi_esp_cmd(esp, cmd); } @@ -529,7 +528,6 @@ static void zorro_esp_send_blz1230II_dma_cmd(struct esp *esp, u32 addr, scsi_esp_cmd(esp, ESP_CMD_DMA); zorro_esp_write8(esp, (esp_count >> 0) & 0xff, ESP_TCLOW); zorro_esp_write8(esp, (esp_count >> 8) & 0xff, ESP_TCMED); - zorro_esp_write8(esp, (esp_count >> 16) & 0xff, ESP_TCHI); scsi_esp_cmd(esp, cmd); } @@ -574,7 +572,6 @@ static void zorro_esp_send_blz2060_dma_cmd(struct esp *esp, u32 addr, scsi_esp_cmd(esp, ESP_CMD_DMA); zorro_esp_write8(esp, (esp_count >> 0) & 0xff, ESP_TCLOW); zorro_esp_write8(esp, (esp_count >> 8) & 0xff, ESP_TCMED); - zorro_esp_write8(esp, (esp_count >> 16) & 0xff, ESP_TCHI); scsi_esp_cmd(esp, cmd); } @@ -599,7 +596,6 @@ static void zorro_esp_send_cyber_dma_cmd(struct esp *esp, u32 addr, zorro_esp_write8(esp, (esp_count >> 0) & 0xff, ESP_TCLOW); zorro_esp_write8(esp, (esp_count >> 8) & 0xff, ESP_TCMED); - zorro_esp_write8(esp, (esp_count >> 16) & 0xff, ESP_TCHI); if (write) { /* DMA receive */ @@ -649,7 +645,6 @@ static void zorro_esp_send_cyberII_dma_cmd(struct esp *esp, u32 addr, zorro_esp_write8(esp, (esp_count >> 0) & 0xff, ESP_TCLOW); zorro_esp_write8(esp, (esp_count >> 8) & 0xff, ESP_TCMED); - zorro_esp_write8(esp, (esp_count >> 16) & 0xff, ESP_TCHI); if (write) { /* DMA receive */ @@ -691,7 +686,6 @@ static void zorro_esp_send_fastlane_dma_cmd(struct esp *esp, u32 addr, zorro_esp_write8(esp, (esp_count >> 0) & 0xff, ESP_TCLOW); zorro_esp_write8(esp, (esp_count >> 8) & 0xff, ESP_TCMED); - zorro_esp_write8(esp, (esp_count >> 16) & 0xff, ESP_TCHI); if (write) { /* DMA receive */ From 5e110ec2d924171458f4099c53b04b7e30ffa929 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Sat, 13 Oct 2018 14:40:31 +0200 Subject: [PATCH 085/299] net: dsa: mv88e6xxx: Fix 88E6141/6341 2500mbps SERDES speed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 26422340da467538cd65eaa9c65538039ee99c8c ] This is a fix for the port_set_speed method for the Topaz family. Currently the same method is used as for the Peridot family, but this is wrong for the SERDES port. On Topaz, the SERDES port is port 5, not 9 and 10 as in Peridot. Moreover setting alt_bit on Topaz only makes sense for port 0 (for (differentiating 100mbps vs 200mbps). The SERDES port does not support more than 2500mbps, so alt_bit does not make any difference. Signed-off-by: Marek Behún Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/mv88e6xxx/chip.c | 4 ++-- drivers/net/dsa/mv88e6xxx/port.c | 25 +++++++++++++++++++++++-- drivers/net/dsa/mv88e6xxx/port.h | 1 + 3 files changed, 26 insertions(+), 4 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index d075f0f7a3de..411ae9961bf4 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3028,7 +3028,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .port_set_link = mv88e6xxx_port_set_link, .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, - .port_set_speed = mv88e6390_port_set_speed, + .port_set_speed = mv88e6341_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_egress_floods = mv88e6352_port_set_egress_floods, @@ -3649,7 +3649,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .port_set_link = mv88e6xxx_port_set_link, .port_set_duplex = mv88e6xxx_port_set_duplex, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, - .port_set_speed = mv88e6390_port_set_speed, + .port_set_speed = mv88e6341_port_set_speed, .port_tag_remap = mv88e6095_port_tag_remap, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_egress_floods = mv88e6352_port_set_egress_floods, diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index fdeddbfa829d..2f16a310c110 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -228,8 +228,11 @@ static int mv88e6xxx_port_set_speed(struct mv88e6xxx_chip *chip, int port, ctrl = MV88E6XXX_PORT_MAC_CTL_SPEED_1000; break; case 2500: - ctrl = MV88E6390_PORT_MAC_CTL_SPEED_10000 | - MV88E6390_PORT_MAC_CTL_ALTSPEED; + if (alt_bit) + ctrl = MV88E6390_PORT_MAC_CTL_SPEED_10000 | + MV88E6390_PORT_MAC_CTL_ALTSPEED; + else + ctrl = MV88E6390_PORT_MAC_CTL_SPEED_10000; break; case 10000: /* all bits set, fall through... */ @@ -291,6 +294,24 @@ int mv88e6185_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed) return mv88e6xxx_port_set_speed(chip, port, speed, false, false); } +/* Support 10, 100, 200, 1000, 2500 Mbps (e.g. 88E6341) */ +int mv88e6341_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed) +{ + if (speed == SPEED_MAX) + speed = port < 5 ? 1000 : 2500; + + if (speed > 2500) + return -EOPNOTSUPP; + + if (speed == 200 && port != 0) + return -EOPNOTSUPP; + + if (speed == 2500 && port < 5) + return -EOPNOTSUPP; + + return mv88e6xxx_port_set_speed(chip, port, speed, !port, true); +} + /* Support 10, 100, 200, 1000 Mbps (e.g. 88E6352 family) */ int mv88e6352_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed) { diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index 95b59f5eb393..cbb64a7683e2 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -280,6 +280,7 @@ int mv88e6xxx_port_set_duplex(struct mv88e6xxx_chip *chip, int port, int dup); int mv88e6065_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed); int mv88e6185_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed); +int mv88e6341_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed); int mv88e6352_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed); int mv88e6390_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed); int mv88e6390x_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed); From 7ac437558e4a68f0127cba24bad6f98cff5c736f Mon Sep 17 00:00:00 2001 From: Kyeongdon Kim Date: Tue, 16 Oct 2018 14:57:26 +0900 Subject: [PATCH 086/299] net: fix warning in af_unix [ Upstream commit 33c4368ee2589c165aebd8d388cbd91e9adb9688 ] This fixes the "'hash' may be used uninitialized in this function" net/unix/af_unix.c:1041:20: warning: 'hash' may be used uninitialized in this function [-Wmaybe-uninitialized] addr->hash = hash ^ sk->sk_type; Signed-off-by: Kyeongdon Kim Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/unix/af_unix.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 231b6c032d2c..d2d6ff0c6265 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -225,6 +225,8 @@ static inline void unix_release_addr(struct unix_address *addr) static int unix_mkname(struct sockaddr_un *sunaddr, int len, unsigned int *hashp) { + *hashp = 0; + if (len <= sizeof(short) || len > sizeof(*sunaddr)) return -EINVAL; if (!sunaddr || sunaddr->sun_family != AF_UNIX) From e0e8d83e4878692a4915a29524573e05dd59e117 Mon Sep 17 00:00:00 2001 From: Netanel Belgazal Date: Wed, 17 Oct 2018 10:04:21 +0000 Subject: [PATCH 087/299] net: ena: Fix Kconfig dependency on X86 [ Upstream commit 8c590f9776386b8f697fd0b7ed6142ae6e3de79e ] The Kconfig limitation of X86 is to too wide. The ENA driver only requires a little endian dependency. Change the dependency to be on little endian CPU. Signed-off-by: Netanel Belgazal Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/amazon/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/amazon/Kconfig b/drivers/net/ethernet/amazon/Kconfig index 99b30353541a..9e87d7b8360f 100644 --- a/drivers/net/ethernet/amazon/Kconfig +++ b/drivers/net/ethernet/amazon/Kconfig @@ -17,7 +17,7 @@ if NET_VENDOR_AMAZON config ENA_ETHERNET tristate "Elastic Network Adapter (ENA) support" - depends on (PCI_MSI && X86) + depends on PCI_MSI && !CPU_BIG_ENDIAN ---help--- This driver supports Elastic Network Adapter (ENA)" From bb64349b6f5635d8688d186b06b4b2b24c0310a4 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 18 Oct 2018 17:21:29 +1100 Subject: [PATCH 088/299] xfs: fix use-after-free race in xfs_buf_rele [ Upstream commit 37fd1678245f7a5898c1b05128bc481fb403c290 ] When looking at a 4.18 based KASAN use after free report, I noticed that racing xfs_buf_rele() may race on dropping the last reference to the buffer and taking the buffer lock. This was the symptom displayed by the KASAN report, but the actual issue that was reported had already been fixed in 4.19-rc1 by commit e339dd8d8b04 ("xfs: use sync buffer I/O for sync delwri queue submission"). Despite this, I think there is still an issue with xfs_buf_rele() in this code: release = atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock); spin_lock(&bp->b_lock); if (!release) { ..... If two threads race on the b_lock after both dropping a reference and one getting dropping the last reference so release = true, we end up with: CPU 0 CPU 1 atomic_dec_and_lock() atomic_dec_and_lock() spin_lock(&bp->b_lock) spin_lock(&bp->b_lock) b_lru_ref = 0> freebuf = true spin_unlock(&bp->b_lock) xfs_buf_free(bp) spin_unlock(&bp->b_lock) IOWs, we can't safely take bp->b_lock after dropping the hold reference because the buffer may go away at any time after we drop that reference. However, this can be fixed simply by taking the bp->b_lock before we drop the reference. It is safe to nest the pag_buf_lock inside bp->b_lock as the pag_buf_lock is only used to serialise against lookup in xfs_buf_find() and no other locks are held over or under the pag_buf_lock there. Make this clear by documenting the buffer lock orders at the top of the file. Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Reviewed-by: Carlos Maiolino Signed-off-by: Sasha Levin --- fs/xfs/xfs_buf.c | 38 +++++++++++++++++++++++++++++++++++++- 1 file changed, 37 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index e839907e8492..f4a89c94c931 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -37,6 +37,32 @@ static kmem_zone_t *xfs_buf_zone; #define xb_to_gfp(flags) \ ((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : GFP_NOFS) | __GFP_NOWARN) +/* + * Locking orders + * + * xfs_buf_ioacct_inc: + * xfs_buf_ioacct_dec: + * b_sema (caller holds) + * b_lock + * + * xfs_buf_stale: + * b_sema (caller holds) + * b_lock + * lru_lock + * + * xfs_buf_rele: + * b_lock + * pag_buf_lock + * lru_lock + * + * xfs_buftarg_wait_rele + * lru_lock + * b_lock (trylock due to inversion) + * + * xfs_buftarg_isolate + * lru_lock + * b_lock (trylock due to inversion) + */ static inline int xfs_buf_is_vmapped( @@ -1006,8 +1032,18 @@ xfs_buf_rele( ASSERT(atomic_read(&bp->b_hold) > 0); - release = atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock); + /* + * We grab the b_lock here first to serialise racing xfs_buf_rele() + * calls. The pag_buf_lock being taken on the last reference only + * serialises against racing lookups in xfs_buf_find(). IOWs, the second + * to last reference we drop here is not serialised against the last + * reference until we take bp->b_lock. Hence if we don't grab b_lock + * first, the last "release" reference can win the race to the lock and + * free the buffer before the second-to-last reference is processed, + * leading to a use-after-free scenario. + */ spin_lock(&bp->b_lock); + release = atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock); if (!release) { /* * Drop the in-flight state if the buffer is already on the LRU From f0f842a1a9f98a637e20171828f3279b1def4083 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Thu, 18 Oct 2018 17:21:49 +1100 Subject: [PATCH 089/299] xfs: clear ail delwri queued bufs on unmount of shutdown fs [ Upstream commit efc3289cf8d39c34502a7cc9695ca2fa125aad0c ] In the typical unmount case, the AIL is forced out by the unmount sequence before the xfsaild task is stopped. Since AIL items are removed on writeback completion, this means that the AIL ->ail_buf_list delwri queue has been drained. This is not always true in the shutdown case, however. It's possible for buffers to sit on a delwri queue for a period of time across submission attempts if said items are locked or have been relogged and pinned since first added to the queue. If the attempt to log such an item results in a log I/O error, the error processing can shutdown the fs, remove the item from the AIL, stale the buffer (dropping the LRU reference) and clear its delwri queue state. The latter bit means the buffer will be released from a delwri queue on the next submission attempt, but this might never occur if the filesystem has shutdown and the AIL is empty. This means that such buffers are held indefinitely by the AIL delwri queue across destruction of the AIL. Aside from being a memory leak, these buffers can also hold references to in-core perag structures. The latter problem manifests as a generic/475 failure, reproducing the following asserts at unmount time: XFS: Assertion failed: atomic_read(&pag->pag_ref) == 0, file: fs/xfs/xfs_mount.c, line: 151 XFS: Assertion failed: atomic_read(&pag->pag_ref) == 0, file: fs/xfs/xfs_mount.c, line: 132 To prevent this problem, clear the AIL delwri queue as a final step before xfsaild() exit. The !empty state should never occur in the normal case, so add an assert to catch unexpected problems going forward. [dgc: add comment explaining need for xfs_buf_delwri_cancel() after calling xfs_buf_delwri_submit_nowait().] Signed-off-by: Brian Foster Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner Signed-off-by: Sasha Levin --- fs/xfs/xfs_buf.c | 7 +++++++ fs/xfs/xfs_trans_ail.c | 28 ++++++++++++++++++++++------ 2 files changed, 29 insertions(+), 6 deletions(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index f4a89c94c931..e36124546d0d 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -2025,6 +2025,13 @@ xfs_buf_delwri_submit_buffers( * is only safely useable for callers that can track I/O completion by higher * level means, e.g. AIL pushing as the @buffer_list is consumed in this * function. + * + * Note: this function will skip buffers it would block on, and in doing so + * leaves them on @buffer_list so they can be retried on a later pass. As such, + * it is up to the caller to ensure that the buffer list is fully submitted or + * cancelled appropriately when they are finished with the list. Failure to + * cancel or resubmit the list until it is empty will result in leaked buffers + * at unmount time. */ int xfs_buf_delwri_submit_nowait( diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 55326f971cb3..d3a4e89bf4a0 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -531,17 +531,33 @@ xfsaild( set_current_state(TASK_INTERRUPTIBLE); /* - * Check kthread_should_stop() after we set the task state - * to guarantee that we either see the stop bit and exit or - * the task state is reset to runnable such that it's not - * scheduled out indefinitely and detects the stop bit at - * next iteration. - * + * Check kthread_should_stop() after we set the task state to + * guarantee that we either see the stop bit and exit or the + * task state is reset to runnable such that it's not scheduled + * out indefinitely and detects the stop bit at next iteration. * A memory barrier is included in above task state set to * serialize again kthread_stop(). */ if (kthread_should_stop()) { __set_current_state(TASK_RUNNING); + + /* + * The caller forces out the AIL before stopping the + * thread in the common case, which means the delwri + * queue is drained. In the shutdown case, the queue may + * still hold relogged buffers that haven't been + * submitted because they were pinned since added to the + * queue. + * + * Log I/O error processing stales the underlying buffer + * and clears the delwri state, expecting the buf to be + * removed on the next submission attempt. That won't + * happen if we're shutting down, so this is the last + * opportunity to release such buffers from the queue. + */ + ASSERT(list_empty(&ailp->ail_buf_list) || + XFS_FORCED_SHUTDOWN(ailp->ail_mount)); + xfs_buf_delwri_cancel(&ailp->ail_buf_list); break; } From cb6a3096ec2f97a3ab59daeda91866a7e29c0255 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 17 Oct 2018 16:59:51 -0400 Subject: [PATCH 090/299] kprobes, x86/ptrace.h: Make regs_get_kernel_stack_nth() not fault on bad stack [ Upstream commit c2712b858187f5bcd7b042fe4daa3ba3a12635c0 ] Andy had some concerns about using regs_get_kernel_stack_nth() in a new function regs_get_kernel_argument() as if there's any error in the stack code, it could cause a bad memory access. To be on the safe side, call probe_kernel_read() on the stack address to be extra careful in accessing the memory. A helper function, regs_get_kernel_stack_nth_addr(), was added to just return the stack address (or NULL if not on the stack), that will be used to find the address (and could be used by other functions) and read the address with kernel_probe_read(). Requested-by: Andy Lutomirski Signed-off-by: Steven Rostedt (VMware) Reviewed-by: Joel Fernandes (Google) Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20181017165951.09119177@gandalf.local.home Signed-off-by: Ingo Molnar Signed-off-by: Sasha Levin --- arch/x86/include/asm/ptrace.h | 42 +++++++++++++++++++++++++++++------ 1 file changed, 35 insertions(+), 7 deletions(-) diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 6de1fd3d0097..ee696efec99f 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -236,24 +236,52 @@ static inline int regs_within_kernel_stack(struct pt_regs *regs, (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))); } +/** + * regs_get_kernel_stack_nth_addr() - get the address of the Nth entry on stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns the address of the @n th entry of the + * kernel stack which is specified by @regs. If the @n th entry is NOT in + * the kernel stack, this returns NULL. + */ +static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs, unsigned int n) +{ + unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); + + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return addr; + else + return NULL; +} + +/* To avoid include hell, we can't include uaccess.h */ +extern long probe_kernel_read(void *dst, const void *src, size_t size); + /** * regs_get_kernel_stack_nth() - get Nth entry of the stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which - * is specified by @regs. If the @n th entry is NOT in the kernel stack, + * is specified by @regs. If the @n th entry is NOT in the kernel stack * this returns 0. */ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) { - unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); - addr += n; - if (regs_within_kernel_stack(regs, (unsigned long)addr)) - return *addr; - else - return 0; + unsigned long *addr; + unsigned long val; + long ret; + + addr = regs_get_kernel_stack_nth_addr(regs, n); + if (addr) { + ret = probe_kernel_read(&val, addr, sizeof(val)); + if (!ret) + return val; + } + return 0; } #define arch_has_single_step() (1) From cf800f2b630b4f7b16a808b0f1f33ad810c6ebad Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 17 Oct 2018 10:59:28 +0200 Subject: [PATCH 091/299] ACPI / scan: Create platform device for INT33FE ACPI nodes [ Upstream commit 589edb56b424876cbbf61547b987a1f57d7ea99d ] Bay and Cherry Trail devices with a Dollar Cove or Whiskey Cove PMIC have an ACPI node with a HID of INT33FE which is a "virtual" battery device implementing a standard ACPI battery interface which depends upon a proprietary, undocument OpRegion called BMOP. Since we do have docs for the actual fuel-gauges used on these boards we instead use native fuel-gauge drivers talking directly to the fuel-gauge ICs on boards which rely on this INT33FE device for their battery monitoring. On boards with a Dollar Cove PMIC the INT33FE device's resources (_CRS) describe a non-existing I2C client at address 0x6b with a bus-speed of 100KHz. This is a problem on some boards since there are actual devices on that same bus which need a speed of 400KHz to function properly. This commit adds the INT33FE HID to the list of devices with I2C resources which should be enumerated as a platform-device rather then letting the i2c-core instantiate an i2c-client matching the first I2C resource, so that its bus-speed will not influence the max speed of the I2C bus. This fixes e.g. the touchscreen not working on the Teclast X98 II Plus. The INT33FE device on boards with a Whiskey Cove PMIC is somewhat special. Its first I2C resource is for a secondary I2C address of the PMIC itself, which is already described in an ACPI device with an INT34D3 HID. But it has 3 more I2C resources describing 3 other chips for which we do need to instantiate I2C clients and which need device-connections added between them for things to work properly. This special case is handled by the drivers/platform/x86/intel_cht_int33fe.c code. Before this commit that code was binding to the i2c-client instantiated for the secondary I2C address of the PMIC, since we now instantiate a platform device for the INT33FE device instead, this commit also changes the intel_cht_int33fe driver from an i2c driver to a platform driver. This also brings the intel_cht_int33fe drv inline with how we instantiate multiple i2c clients from a single ACPI device in other cases, as done by the drivers/platform/x86/i2c-multi-instantiate.c code. Reported-and-tested-by: Alexander Meiler Signed-off-by: Hans de Goede Acked-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/scan.c | 1 + drivers/platform/x86/intel_cht_int33fe.c | 24 +++++++++--------------- 2 files changed, 10 insertions(+), 15 deletions(-) diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index e1b6231cfa1c..1dcc48b9d33c 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1550,6 +1550,7 @@ static bool acpi_device_enumeration_by_parent(struct acpi_device *device) */ static const struct acpi_device_id i2c_multi_instantiate_ids[] = { {"BSG1160", }, + {"INT33FE", }, {} }; diff --git a/drivers/platform/x86/intel_cht_int33fe.c b/drivers/platform/x86/intel_cht_int33fe.c index a26f410800c2..f40b1c192106 100644 --- a/drivers/platform/x86/intel_cht_int33fe.c +++ b/drivers/platform/x86/intel_cht_int33fe.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -88,9 +89,9 @@ static const struct property_entry fusb302_props[] = { { } }; -static int cht_int33fe_probe(struct i2c_client *client) +static int cht_int33fe_probe(struct platform_device *pdev) { - struct device *dev = &client->dev; + struct device *dev = &pdev->dev; struct i2c_board_info board_info; struct cht_int33fe_data *data; struct i2c_client *max17047; @@ -207,7 +208,7 @@ static int cht_int33fe_probe(struct i2c_client *client) if (!data->pi3usb30532) goto out_unregister_fusb302; - i2c_set_clientdata(client, data); + platform_set_drvdata(pdev, data); return 0; @@ -223,9 +224,9 @@ out_unregister_max17047: return -EPROBE_DEFER; /* Wait for the i2c-adapter to load */ } -static int cht_int33fe_remove(struct i2c_client *i2c) +static int cht_int33fe_remove(struct platform_device *pdev) { - struct cht_int33fe_data *data = i2c_get_clientdata(i2c); + struct cht_int33fe_data *data = platform_get_drvdata(pdev); i2c_unregister_device(data->pi3usb30532); i2c_unregister_device(data->fusb302); @@ -237,29 +238,22 @@ static int cht_int33fe_remove(struct i2c_client *i2c) return 0; } -static const struct i2c_device_id cht_int33fe_i2c_id[] = { - { } -}; -MODULE_DEVICE_TABLE(i2c, cht_int33fe_i2c_id); - static const struct acpi_device_id cht_int33fe_acpi_ids[] = { { "INT33FE", }, { } }; MODULE_DEVICE_TABLE(acpi, cht_int33fe_acpi_ids); -static struct i2c_driver cht_int33fe_driver = { +static struct platform_driver cht_int33fe_driver = { .driver = { .name = "Intel Cherry Trail ACPI INT33FE driver", .acpi_match_table = ACPI_PTR(cht_int33fe_acpi_ids), }, - .probe_new = cht_int33fe_probe, + .probe = cht_int33fe_probe, .remove = cht_int33fe_remove, - .id_table = cht_int33fe_i2c_id, - .disable_i2c_core_irq_mapping = true, }; -module_i2c_driver(cht_int33fe_driver); +module_platform_driver(cht_int33fe_driver); MODULE_DESCRIPTION("Intel Cherry Trail ACPI INT33FE pseudo device driver"); MODULE_AUTHOR("Hans de Goede "); From 46729b27706a381193c8dbf911e7d0a7004f770a Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 3 Oct 2018 16:38:15 +0200 Subject: [PATCH 092/299] PM / Domains: Deal with multiple states but no governor in genpd [ Upstream commit 2c9b7f8772033cc8bafbd4eefe2ca605bf3eb094 ] A caller of pm_genpd_init() that provides some states for the genpd via the ->states pointer in the struct generic_pm_domain, should also provide a governor. This because it's the job of the governor to pick a state that satisfies the constraints. Therefore, let's print a warning to inform the user about such bogus configuration and avoid to bail out, by instead picking the shallowest state before genpd invokes the ->power_off() callback. Signed-off-by: Ulf Hansson Reviewed-by: Lina Iyer Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/base/power/domain.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index bf5be0bfaf77..52c292d0908a 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -467,6 +467,10 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on, return -EAGAIN; } + /* Default to shallowest state. */ + if (!genpd->gov) + genpd->state_idx = 0; + if (genpd->power_off) { int ret; @@ -1686,6 +1690,8 @@ int pm_genpd_init(struct generic_pm_domain *genpd, ret = genpd_set_default_power_state(genpd); if (ret) return ret; + } else if (!gov) { + pr_warn("%s : no governor for states\n", genpd->name); } device_initialize(&genpd->dev); From 86f63146f8861b00dbb4c2c2def8edae4c44b6f1 Mon Sep 17 00:00:00 2001 From: Philipp Klocke Date: Thu, 18 Oct 2018 12:33:02 +0200 Subject: [PATCH 093/299] ALSA: i2c/cs8427: Fix int to char conversion [ Upstream commit eb7ebfa3c1989aa8e59d5e68ab3cddd7df1bfb27 ] Compiling with clang yields the following warning: sound/i2c/cs8427.c:140:31: warning: implicit conversion from 'int' to 'char' changes value from 160 to -96 [-Wconstant-conversion] data[0] = CS8427_REG_AUTOINC | CS8427_REG_CORU_DATABUF; ~ ~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~ Because CS8427_REG_AUTOINC is defined as 128, it is too big for a char field. So change data from char to unsigned char, that it can hold the value. This patch does not change the generated code. Signed-off-by: Philipp Klocke Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/i2c/cs8427.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/i2c/cs8427.c b/sound/i2c/cs8427.c index 2647309bc675..8afa2f888466 100644 --- a/sound/i2c/cs8427.c +++ b/sound/i2c/cs8427.c @@ -118,7 +118,7 @@ static int snd_cs8427_send_corudata(struct snd_i2c_device *device, struct cs8427 *chip = device->private_data; char *hw_data = udata ? chip->playback.hw_udata : chip->playback.hw_status; - char data[32]; + unsigned char data[32]; int err, idx; if (!memcmp(hw_data, ndata, count)) From b0f69ccfff3a353d08ee2aa5bb3a39f701d2482d Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 15 Oct 2018 11:18:49 +1100 Subject: [PATCH 094/299] macintosh/windfarm_smu_sat: Fix debug output [ Upstream commit fc0c8b36d379a046525eacb9c3323ca635283757 ] There's some antiquated debug output that's trying to do a hand-made hexdump and turning into horrible 1-byte-per-line output these days. Use print_hex_dump() instead Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- drivers/macintosh/windfarm_smu_sat.c | 25 +++++++------------------ 1 file changed, 7 insertions(+), 18 deletions(-) diff --git a/drivers/macintosh/windfarm_smu_sat.c b/drivers/macintosh/windfarm_smu_sat.c index da7f4fc1a51d..a0f61eb853c5 100644 --- a/drivers/macintosh/windfarm_smu_sat.c +++ b/drivers/macintosh/windfarm_smu_sat.c @@ -22,14 +22,6 @@ #define VERSION "1.0" -#define DEBUG - -#ifdef DEBUG -#define DBG(args...) printk(args) -#else -#define DBG(args...) do { } while(0) -#endif - /* If the cache is older than 800ms we'll refetch it */ #define MAX_AGE msecs_to_jiffies(800) @@ -106,13 +98,10 @@ struct smu_sdbp_header *smu_sat_get_sdb_partition(unsigned int sat_id, int id, buf[i+2] = data[3]; buf[i+3] = data[2]; } -#ifdef DEBUG - DBG(KERN_DEBUG "sat %d partition %x:", sat_id, id); - for (i = 0; i < len; ++i) - DBG(" %x", buf[i]); - DBG("\n"); -#endif + printk(KERN_DEBUG "sat %d partition %x:", sat_id, id); + print_hex_dump(KERN_DEBUG, " ", DUMP_PREFIX_OFFSET, + 16, 1, buf, len, false); if (size) *size = len; return (struct smu_sdbp_header *) buf; @@ -132,13 +121,13 @@ static int wf_sat_read_cache(struct wf_sat *sat) if (err < 0) return err; sat->last_read = jiffies; + #ifdef LOTSA_DEBUG { int i; - DBG(KERN_DEBUG "wf_sat_get: data is"); - for (i = 0; i < 16; ++i) - DBG(" %.2x", sat->cache[i]); - DBG("\n"); + printk(KERN_DEBUG "wf_sat_get: data is"); + print_hex_dump(KERN_DEBUG, " ", DUMP_PREFIX_OFFSET, + 16, 1, sat->cache, 16, false); } #endif return 0; From 80a23f70d546a6fc74561ce7f9e4e65cb6580791 Mon Sep 17 00:00:00 2001 From: Jon Derrick Date: Mon, 15 Oct 2018 18:48:07 -0600 Subject: [PATCH 095/299] PCI: vmd: Detach resources after stopping root bus [ Upstream commit dc8af3a827df6d4bb925d3b81b7ec94a7cce9482 ] The VMD removal path calls pci_stop_root_busi(), which tears down the pcie tree, including detaching all of the attached drivers. During driver detachment, devices may use pci_release_region() to release resources. This path relies on the resource being accessible in resource tree. By detaching the child domain from the parent resource domain prior to stopping the bus, we are preventing the list traversal from finding the resource to be freed. If we instead detach the resource after stopping the bus, we will have properly freed the resource and detaching is simply accounting at that point. Without this order, the resource is never freed and is orphaned on VMD removal, leading to a warning: [ 181.940162] Trying to free nonexistent resource Fixes: 2c2c5c5cd213 ("x86/PCI: VMD: Attach VMD resources to parent domain's resource tree") Signed-off-by: Jon Derrick [lorenzo.pieralisi@arm.com: updated commit log] Signed-off-by: Lorenzo Pieralisi Reviewed-by: Keith Busch Signed-off-by: Sasha Levin --- drivers/pci/controller/vmd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 65eaa6b61868..ab36e5ca1aca 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -818,12 +818,12 @@ static void vmd_remove(struct pci_dev *dev) { struct vmd_dev *vmd = pci_get_drvdata(dev); - vmd_detach_resources(vmd); sysfs_remove_link(&vmd->dev->dev.kobj, "domain"); pci_stop_root_bus(vmd->bus); pci_remove_root_bus(vmd->bus); vmd_cleanup_srcu(vmd); vmd_teardown_dma_ops(vmd); + vmd_detach_resources(vmd); irq_domain_remove(vmd->irq_domain); } From 283d9618e22b7ff43ac6fc16c35f3c4d24fbb733 Mon Sep 17 00:00:00 2001 From: Mattias Jacobsson <2pi@mok.nu> Date: Tue, 16 Oct 2018 14:20:08 +0200 Subject: [PATCH 096/299] USB: misc: appledisplay: fix backlight update_status return code [ Upstream commit 090158555ff8d194a98616034100b16697dd80d0 ] Upon success the update_status handler returns a positive number corresponding to the number of bytes transferred by usb_control_msg. However the return code of the update_status handler should indicate if an error occurred(negative) or how many bytes of the user's input to sysfs that was consumed. Return code zero indicates all bytes were consumed. The bug can for example result in the update_status handler being called twice, the second time with only the "unconsumed" part of the user's input to sysfs. Effectively setting an incorrect brightness. Change the update_status handler to return zero for all successful transactions and forward usb_control_msg's error code upon failure. Signed-off-by: Mattias Jacobsson <2pi@mok.nu> Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/misc/appledisplay.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/usb/misc/appledisplay.c b/drivers/usb/misc/appledisplay.c index 1c6da8d6cccf..39ca31b4de46 100644 --- a/drivers/usb/misc/appledisplay.c +++ b/drivers/usb/misc/appledisplay.c @@ -148,8 +148,11 @@ static int appledisplay_bl_update_status(struct backlight_device *bd) pdata->msgdata, 2, ACD_USB_TIMEOUT); mutex_unlock(&pdata->sysfslock); - - return retval; + + if (retval < 0) + return retval; + else + return 0; } static int appledisplay_bl_get_brightness(struct backlight_device *bd) From 1f7f2a0666a31d824e98e54220bba96f5ac2f4ee Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 16 Oct 2018 19:03:43 +0100 Subject: [PATCH 097/299] usbip: tools: fix atoi() on non-null terminated string [ Upstream commit e325808c0051b16729ffd472ff887c6cae5c6317 ] Currently the call to atoi is being passed a single char string that is not null terminated, so there is a potential read overrun along the stack when parsing for an integer value. Fix this by instead using a 2 char string that is initialized to all zeros to ensure that a 1 char read into the string is always terminated with a \0. Detected by cppcheck: "Invalid atoi() argument nr 1. A nul-terminated string is required." Fixes: 3391ba0e2792 ("usbip: tools: Extract generic code to be shared with vudc backend") Signed-off-by: Colin Ian King Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- tools/usb/usbip/libsrc/usbip_host_common.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/usb/usbip/libsrc/usbip_host_common.c b/tools/usb/usbip/libsrc/usbip_host_common.c index dc93fadbee96..d79c7581b175 100644 --- a/tools/usb/usbip/libsrc/usbip_host_common.c +++ b/tools/usb/usbip/libsrc/usbip_host_common.c @@ -43,7 +43,7 @@ static int32_t read_attr_usbip_status(struct usbip_usb_device *udev) int size; int fd; int length; - char status; + char status[2] = { 0 }; int value = 0; size = snprintf(status_attr_path, sizeof(status_attr_path), @@ -61,14 +61,14 @@ static int32_t read_attr_usbip_status(struct usbip_usb_device *udev) return -1; } - length = read(fd, &status, 1); + length = read(fd, status, 1); if (length < 0) { err("error reading attribute %s", status_attr_path); close(fd); return -1; } - value = atoi(&status); + value = atoi(status); return value; } From 4de506d51177d8ad2a48a212408c494c67efbd15 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 17 Oct 2018 03:07:51 +0800 Subject: [PATCH 098/299] sctp: use sk_wmem_queued to check for writable space [ Upstream commit cd305c74b0f8b49748a79a8f67fc8e5e3e0c4794 ] sk->sk_wmem_queued is used to count the size of chunks in out queue while sk->sk_wmem_alloc is for counting the size of chunks has been sent. sctp is increasing both of them before enqueuing the chunks, and using sk->sk_wmem_alloc to check for writable space. However, sk_wmem_alloc is also increased by 1 for the skb allocked for sending in sctp_packet_transmit() but it will not wake up the waiters when sk_wmem_alloc is decreased in this skb's destructor. If msg size is equal to sk_sndbuf and sendmsg is waiting for sndbuf, the check 'msg_len <= sctp_wspace(asoc)' in sctp_wait_for_sndbuf() will keep waiting if there's a skb allocked in sctp_packet_transmit, and later even if this skb got freed, the waiting thread will never get waked up. This issue has been there since very beginning, so we change to use sk->sk_wmem_queued to check for writable space as sk_wmem_queued is not increased for the skb allocked for sending, also as TCP does. SOCK_SNDBUF_LOCK check is also removed here as it's for tx buf auto tuning which I will add in another patch. Signed-off-by: Xin Long Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sctp/socket.c | 38 +++++++++----------------------------- 1 file changed, 9 insertions(+), 29 deletions(-) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c76631552722..e7a11cd7633f 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -83,7 +83,7 @@ #include /* Forward declarations for internal helper functions. */ -static int sctp_writeable(struct sock *sk); +static bool sctp_writeable(struct sock *sk); static void sctp_wfree(struct sk_buff *skb); static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, size_t msg_len); @@ -119,25 +119,10 @@ static void sctp_enter_memory_pressure(struct sock *sk) /* Get the sndbuf space available at the time on the association. */ static inline int sctp_wspace(struct sctp_association *asoc) { - int amt; + struct sock *sk = asoc->base.sk; - if (asoc->ep->sndbuf_policy) - amt = asoc->sndbuf_used; - else - amt = sk_wmem_alloc_get(asoc->base.sk); - - if (amt >= asoc->base.sk->sk_sndbuf) { - if (asoc->base.sk->sk_userlocks & SOCK_SNDBUF_LOCK) - amt = 0; - else { - amt = sk_stream_wspace(asoc->base.sk); - if (amt < 0) - amt = 0; - } - } else { - amt = asoc->base.sk->sk_sndbuf - amt; - } - return amt; + return asoc->ep->sndbuf_policy ? sk->sk_sndbuf - asoc->sndbuf_used + : sk_stream_wspace(sk); } /* Increment the used sndbuf space count of the corresponding association by @@ -1928,10 +1913,10 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, asoc->pmtu_pending = 0; } - if (sctp_wspace(asoc) < msg_len) + if (sctp_wspace(asoc) < (int)msg_len) sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc)); - if (!sctp_wspace(asoc)) { + if (sctp_wspace(asoc) <= 0) { timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); if (err) @@ -8516,7 +8501,7 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, goto do_error; if (signal_pending(current)) goto do_interrupted; - if (msg_len <= sctp_wspace(asoc)) + if ((int)msg_len <= sctp_wspace(asoc)) break; /* Let another process have a go. Since we are going @@ -8591,14 +8576,9 @@ void sctp_write_space(struct sock *sk) * UDP-style sockets or TCP-style sockets, this code should work. * - Daisy */ -static int sctp_writeable(struct sock *sk) +static bool sctp_writeable(struct sock *sk) { - int amt = 0; - - amt = sk->sk_sndbuf - sk_wmem_alloc_get(sk); - if (amt < 0) - amt = 0; - return amt; + return sk->sk_sndbuf > sk->sk_wmem_queued; } /* Wait for an association to go into ESTABLISHED state. If timeout is 0, From 56b8b18321223aa3574856f17457539e8c117726 Mon Sep 17 00:00:00 2001 From: Heinz Mauelshagen Date: Fri, 12 Oct 2018 20:24:25 +0200 Subject: [PATCH 099/299] dm raid: avoid bitmap with raid4/5/6 journal device [ Upstream commit d857ad75edf3c0066fcd920746f9dc75382b3324 ] With raid4/5/6, journal device and write intent bitmap are mutually exclusive. Signed-off-by: Heinz Mauelshagen Signed-off-by: Mike Snitzer Signed-off-by: Sasha Levin --- drivers/md/dm-raid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index b78a8a4d061c..6c9b54288261 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -2475,7 +2475,7 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev) } /* Enable bitmap creation for RAID levels != 0 */ - mddev->bitmap_info.offset = rt_is_raid0(rs->raid_type) ? 0 : to_sector(4096); + mddev->bitmap_info.offset = (rt_is_raid0(rs->raid_type) || rs->journal_dev.dev) ? 0 : to_sector(4096); mddev->bitmap_info.default_offset = mddev->bitmap_info.offset; if (!test_and_clear_bit(FirstUse, &rdev->flags)) { From a0ec7f6eabe88eb72acfef786c706c453fef6872 Mon Sep 17 00:00:00 2001 From: Peng Hao Date: Thu, 18 Oct 2018 23:18:36 +0800 Subject: [PATCH 100/299] selftests/bpf: fix file resource leak in load_kallsyms [ Upstream commit 1bd70d2eba9d90eb787634361f0f6fa2c86b3f6d ] FILE pointer variable f is opened but never closed. Signed-off-by: Peng Hao Signed-off-by: Daniel Borkmann Signed-off-by: Sasha Levin --- tools/testing/selftests/bpf/trace_helpers.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index cf156b353679..82922f13dcd3 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -41,6 +41,7 @@ int load_kallsyms(void) syms[i].name = strdup(func); i++; } + fclose(f); sym_cnt = i; qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp); return 0; From 7983dea8c368c396c2e246885336496c67573300 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 18 Oct 2018 17:03:56 -0400 Subject: [PATCH 101/299] SUNRPC: Fix a compile warning for cmpxchg64() [ Upstream commit e732f4485a150492b286f3efc06f9b34dd6b9995 ] Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- net/sunrpc/auth_gss/gss_krb5_seal.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c index eaad9bc7a0bd..e1f0571843c8 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seal.c +++ b/net/sunrpc/auth_gss/gss_krb5_seal.c @@ -63,6 +63,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH From f9304c6277ededc5dad10c9f22f05bbb1c7f07c3 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 18 Oct 2018 15:27:02 -0400 Subject: [PATCH 102/299] sunrpc: safely reallow resvport min/max inversion [ Upstream commit 826799e66e8683e5698e140bb9ef69afc8c0014e ] Commits ffb6ca33b04b and e08ea3a96fc7 prevent setting xprt_min_resvport greater than xprt_max_resvport, but may also break simple code that sets one parameter then the other, if the new range does not overlap the old. Also it looks racy to me, unless there's some serialization I'm not seeing. Granted it would probably require malicious privileged processes (unless there's a chance these might eventually be settable in unprivileged containers), but still it seems better not to let userspace panic the kernel. Simpler seems to be to allow setting the parameters to whatever you want but interpret xprt_min_resvport > xprt_max_resvport as the empty range. Fixes: ffb6ca33b04b "sunrpc: Prevent resvport min/max inversion..." Fixes: e08ea3a96fc7 "sunrpc: Prevent rexvport min/max inversion..." Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- net/sunrpc/xprtsock.c | 34 ++++++++++++++++++---------------- 1 file changed, 18 insertions(+), 16 deletions(-) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index c0d7875a64ff..9dc059dea689 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -129,7 +129,7 @@ static struct ctl_table xs_tunables_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &xprt_min_resvport_limit, - .extra2 = &xprt_max_resvport + .extra2 = &xprt_max_resvport_limit }, { .procname = "max_resvport", @@ -137,7 +137,7 @@ static struct ctl_table xs_tunables_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &xprt_min_resvport, + .extra1 = &xprt_min_resvport_limit, .extra2 = &xprt_max_resvport_limit }, { @@ -1776,11 +1776,17 @@ static void xs_udp_timer(struct rpc_xprt *xprt, struct rpc_task *task) spin_unlock_bh(&xprt->transport_lock); } -static unsigned short xs_get_random_port(void) +static int xs_get_random_port(void) { - unsigned short range = xprt_max_resvport - xprt_min_resvport + 1; - unsigned short rand = (unsigned short) prandom_u32() % range; - return rand + xprt_min_resvport; + unsigned short min = xprt_min_resvport, max = xprt_max_resvport; + unsigned short range; + unsigned short rand; + + if (max < min) + return -EADDRINUSE; + range = max - min + 1; + rand = (unsigned short) prandom_u32() % range; + return rand + min; } /** @@ -1836,9 +1842,9 @@ static void xs_set_srcport(struct sock_xprt *transport, struct socket *sock) transport->srcport = xs_sock_getport(sock); } -static unsigned short xs_get_srcport(struct sock_xprt *transport) +static int xs_get_srcport(struct sock_xprt *transport) { - unsigned short port = transport->srcport; + int port = transport->srcport; if (port == 0 && transport->xprt.resvport) port = xs_get_random_port(); @@ -1859,7 +1865,7 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock) { struct sockaddr_storage myaddr; int err, nloop = 0; - unsigned short port = xs_get_srcport(transport); + int port = xs_get_srcport(transport); unsigned short last; /* @@ -1877,8 +1883,8 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock) * transport->xprt.resvport == 1) xs_get_srcport above will * ensure that port is non-zero and we will bind as needed. */ - if (port == 0) - return 0; + if (port <= 0) + return port; memcpy(&myaddr, &transport->srcaddr, transport->xprt.addrlen); do { @@ -3319,12 +3325,8 @@ static int param_set_uint_minmax(const char *val, static int param_set_portnr(const char *val, const struct kernel_param *kp) { - if (kp->arg == &xprt_min_resvport) - return param_set_uint_minmax(val, kp, - RPC_MIN_RESVPORT, - xprt_max_resvport); return param_set_uint_minmax(val, kp, - xprt_min_resvport, + RPC_MIN_RESVPORT, RPC_MAX_RESVPORT); } From 641f1f798c80e0e93126a1b4fd91667c5a0918da Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 17 Oct 2018 11:04:19 -0700 Subject: [PATCH 103/299] atm: zatm: Fix empty body Clang warnings [ Upstream commit 64b9d16e2d02ca6e5dc8fcd30cfd52b0ecaaa8f4 ] Clang warns: drivers/atm/zatm.c:513:7: error: while loop has empty body [-Werror,-Wempty-body] zwait; ^ drivers/atm/zatm.c:513:7: note: put the semicolon on a separate line to silence this warning Get rid of this warning by using an empty do-while loop. While we're at it, add parentheses to make it clear that this is a function-like macro. Link: https://github.com/ClangBuiltLinux/linux/issues/42 Suggested-by: Masahiro Yamada Signed-off-by: Nathan Chancellor Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/atm/zatm.c | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c index e89146ddede6..d5c76b50d357 100644 --- a/drivers/atm/zatm.c +++ b/drivers/atm/zatm.c @@ -126,7 +126,7 @@ static unsigned long dummy[2] = {0,0}; #define zin_n(r) inl(zatm_dev->base+r*4) #define zin(r) inl(zatm_dev->base+uPD98401_##r*4) #define zout(v,r) outl(v,zatm_dev->base+uPD98401_##r*4) -#define zwait while (zin(CMR) & uPD98401_BUSY) +#define zwait() do {} while (zin(CMR) & uPD98401_BUSY) /* RX0, RX1, TX0, TX1 */ static const int mbx_entries[NR_MBX] = { 1024,1024,1024,1024 }; @@ -140,7 +140,7 @@ static const int mbx_esize[NR_MBX] = { 16,16,4,4 }; /* entry size in bytes */ static void zpokel(struct zatm_dev *zatm_dev,u32 value,u32 addr) { - zwait; + zwait(); zout(value,CER); zout(uPD98401_IND_ACC | uPD98401_IA_BALL | (uPD98401_IA_TGT_CM << uPD98401_IA_TGT_SHIFT) | addr,CMR); @@ -149,10 +149,10 @@ static void zpokel(struct zatm_dev *zatm_dev,u32 value,u32 addr) static u32 zpeekl(struct zatm_dev *zatm_dev,u32 addr) { - zwait; + zwait(); zout(uPD98401_IND_ACC | uPD98401_IA_BALL | uPD98401_IA_RW | (uPD98401_IA_TGT_CM << uPD98401_IA_TGT_SHIFT) | addr,CMR); - zwait; + zwait(); return zin(CER); } @@ -241,7 +241,7 @@ static void refill_pool(struct atm_dev *dev,int pool) } if (first) { spin_lock_irqsave(&zatm_dev->lock, flags); - zwait; + zwait(); zout(virt_to_bus(first),CER); zout(uPD98401_ADD_BAT | (pool << uPD98401_POOL_SHIFT) | count, CMR); @@ -508,9 +508,9 @@ static int open_rx_first(struct atm_vcc *vcc) } if (zatm_vcc->pool < 0) return -EMSGSIZE; spin_lock_irqsave(&zatm_dev->lock, flags); - zwait; + zwait(); zout(uPD98401_OPEN_CHAN,CMR); - zwait; + zwait(); DPRINTK("0x%x 0x%x\n",zin(CMR),zin(CER)); chan = (zin(CMR) & uPD98401_CHAN_ADDR) >> uPD98401_CHAN_ADDR_SHIFT; spin_unlock_irqrestore(&zatm_dev->lock, flags); @@ -571,21 +571,21 @@ static void close_rx(struct atm_vcc *vcc) pos = vcc->vci >> 1; shift = (1-(vcc->vci & 1)) << 4; zpokel(zatm_dev,zpeekl(zatm_dev,pos) & ~(0xffff << shift),pos); - zwait; + zwait(); zout(uPD98401_NOP,CMR); - zwait; + zwait(); zout(uPD98401_NOP,CMR); spin_unlock_irqrestore(&zatm_dev->lock, flags); } spin_lock_irqsave(&zatm_dev->lock, flags); - zwait; + zwait(); zout(uPD98401_DEACT_CHAN | uPD98401_CHAN_RT | (zatm_vcc->rx_chan << uPD98401_CHAN_ADDR_SHIFT),CMR); - zwait; + zwait(); udelay(10); /* why oh why ... ? */ zout(uPD98401_CLOSE_CHAN | uPD98401_CHAN_RT | (zatm_vcc->rx_chan << uPD98401_CHAN_ADDR_SHIFT),CMR); - zwait; + zwait(); if (!(zin(CMR) & uPD98401_CHAN_ADDR)) printk(KERN_CRIT DEV_LABEL "(itf %d): can't close RX channel " "%d\n",vcc->dev->number,zatm_vcc->rx_chan); @@ -699,7 +699,7 @@ printk("NONONONOO!!!!\n"); skb_queue_tail(&zatm_vcc->tx_queue,skb); DPRINTK("QRP=0x%08lx\n",zpeekl(zatm_dev,zatm_vcc->tx_chan*VC_SIZE/4+ uPD98401_TXVC_QRP)); - zwait; + zwait(); zout(uPD98401_TX_READY | (zatm_vcc->tx_chan << uPD98401_CHAN_ADDR_SHIFT),CMR); spin_unlock_irqrestore(&zatm_dev->lock, flags); @@ -891,12 +891,12 @@ static void close_tx(struct atm_vcc *vcc) } spin_lock_irqsave(&zatm_dev->lock, flags); #if 0 - zwait; + zwait(); zout(uPD98401_DEACT_CHAN | (chan << uPD98401_CHAN_ADDR_SHIFT),CMR); #endif - zwait; + zwait(); zout(uPD98401_CLOSE_CHAN | (chan << uPD98401_CHAN_ADDR_SHIFT),CMR); - zwait; + zwait(); if (!(zin(CMR) & uPD98401_CHAN_ADDR)) printk(KERN_CRIT DEV_LABEL "(itf %d): can't close TX channel " "%d\n",vcc->dev->number,chan); @@ -926,9 +926,9 @@ static int open_tx_first(struct atm_vcc *vcc) zatm_vcc->tx_chan = 0; if (vcc->qos.txtp.traffic_class == ATM_NONE) return 0; spin_lock_irqsave(&zatm_dev->lock, flags); - zwait; + zwait(); zout(uPD98401_OPEN_CHAN,CMR); - zwait; + zwait(); DPRINTK("0x%x 0x%x\n",zin(CMR),zin(CER)); chan = (zin(CMR) & uPD98401_CHAN_ADDR) >> uPD98401_CHAN_ADDR_SHIFT; spin_unlock_irqrestore(&zatm_dev->lock, flags); @@ -1557,7 +1557,7 @@ static void zatm_phy_put(struct atm_dev *dev,unsigned char value, struct zatm_dev *zatm_dev; zatm_dev = ZATM_DEV(dev); - zwait; + zwait(); zout(value,CER); zout(uPD98401_IND_ACC | uPD98401_IA_B0 | (uPD98401_IA_TGT_PHY << uPD98401_IA_TGT_SHIFT) | addr,CMR); @@ -1569,10 +1569,10 @@ static unsigned char zatm_phy_get(struct atm_dev *dev,unsigned long addr) struct zatm_dev *zatm_dev; zatm_dev = ZATM_DEV(dev); - zwait; + zwait(); zout(uPD98401_IND_ACC | uPD98401_IA_B0 | uPD98401_IA_RW | (uPD98401_IA_TGT_PHY << uPD98401_IA_TGT_SHIFT) | addr,CMR); - zwait; + zwait(); return zin(CER) & 0xff; } From 9b572e8bc0385c05009b173f0385ee7d1fb45583 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Mon, 15 Oct 2018 14:39:29 +0100 Subject: [PATCH 104/299] s390/perf: Return error when debug_register fails [ Upstream commit ec0c0bb489727de0d4dca6a00be6970ab8a3b30a ] Return an error when the function debug_register() fails allocating the debug handle. Also remove the registered debug handle when the initialization fails later on. Signed-off-by: Thomas Richter Reviewed-by: Hendrik Brueckner Signed-off-by: Martin Schwidefsky Signed-off-by: Sasha Levin --- arch/s390/kernel/perf_cpum_sf.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 44404836e9d1..df92c2af99b6 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -2045,14 +2045,17 @@ static int __init init_cpum_sampling_pmu(void) } sfdbg = debug_register(KMSG_COMPONENT, 2, 1, 80); - if (!sfdbg) + if (!sfdbg) { pr_err("Registering for s390dbf failed\n"); + return -ENOMEM; + } debug_register_view(sfdbg, &debug_sprintf_view); err = register_external_irq(EXT_IRQ_MEASURE_ALERT, cpumf_measurement_alert); if (err) { pr_cpumsf_err(RS_INIT_FAILURE_ALRT); + debug_unregister(sfdbg); goto out; } @@ -2061,6 +2064,7 @@ static int __init init_cpum_sampling_pmu(void) pr_cpumsf_err(RS_INIT_FAILURE_PERF); unregister_external_irq(EXT_IRQ_MEASURE_ALERT, cpumf_measurement_alert); + debug_unregister(sfdbg); goto out; } From ad9a4e963c9270370934ad93c5760c26a521b058 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 12 Apr 2018 10:38:08 +0200 Subject: [PATCH 105/299] swiotlb: do not panic on mapping failures [ Upstream commit 8088546832aa2c0d8f99dd56edf6384f8a9b63b3 ] All properly written drivers now have error handling in the dma_map_single / dma_map_page callers. As swiotlb_tbl_map_single already prints a useful warning when running out of swiotlb pool space we can also remove swiotlb_full entirely as it serves no purpose now. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy Signed-off-by: Sasha Levin --- kernel/dma/swiotlb.c | 33 +-------------------------------- 1 file changed, 1 insertion(+), 32 deletions(-) diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 4f8a6dbf0b60..2a8c41f12d45 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -761,34 +761,6 @@ static bool swiotlb_free_buffer(struct device *dev, size_t size, return true; } -static void -swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir, - int do_panic) -{ - if (swiotlb_force == SWIOTLB_NO_FORCE) - return; - - /* - * Ran out of IOMMU space for this operation. This is very bad. - * Unfortunately the drivers cannot handle this operation properly. - * unless they check for dma_mapping_error (most don't) - * When the mapping is small enough return a static buffer to limit - * the damage, or panic when the transfer is too big. - */ - dev_err_ratelimited(dev, "DMA: Out of SW-IOMMU space for %zu bytes\n", - size); - - if (size <= io_tlb_overflow || !do_panic) - return; - - if (dir == DMA_BIDIRECTIONAL) - panic("DMA: Random memory could be DMA accessed\n"); - if (dir == DMA_FROM_DEVICE) - panic("DMA: Random memory could be DMA written\n"); - if (dir == DMA_TO_DEVICE) - panic("DMA: Random memory could be DMA read\n"); -} - /* * Map a single buffer of the indicated size for DMA in streaming mode. The * physical address to use is returned. @@ -817,10 +789,8 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, /* Oh well, have to allocate and map a bounce buffer. */ map = map_single(dev, phys, size, dir, attrs); - if (map == SWIOTLB_MAP_ERROR) { - swiotlb_full(dev, size, dir, 1); + if (map == SWIOTLB_MAP_ERROR) return __phys_to_dma(dev, io_tlb_overflow_buffer); - } dev_addr = __phys_to_dma(dev, map); @@ -954,7 +924,6 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, if (map == SWIOTLB_MAP_ERROR) { /* Don't panic here, we expect map_sg users to do proper error handling. */ - swiotlb_full(hwdev, sg->length, dir, 0); attrs |= DMA_ATTR_SKIP_CPU_SYNC; swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir, attrs); From b6e44f7439510a0058afed5779ed9640a802e0e9 Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Mon, 15 Oct 2018 12:08:28 +0530 Subject: [PATCH 106/299] spi: omap2-mcspi: Set FIFO DMA trigger level to word length [ Upstream commit b682cffa3ac6d9d9e16e9b413c45caee3b391fab ] McSPI has 32 byte FIFO in Transmit-Receive mode. Current code tries to configuration FIFO watermark level for DMA trigger to be GCD of transfer length and max FIFO size which would mean trigger level may be set to 32 for transmit-receive mode if length is aligned. This does not work in case of SPI slave mode where FIFO always needs to have data ready whenever master starts the clock. With DMA trigger size of 32 there will be a small window during slave TX where DMA is still putting data into FIFO but master would have started clock for next byte, resulting in shifting out of stale data. Similarly, on Slave RX side there may be RX FIFO overflow Fix this by setting FIFO watermark for DMA trigger to word length. This means DMA is triggered as soon as FIFO has space for word length bytes and DMA would make sure FIFO is almost always full therefore improving FIFO occupancy in both master and slave mode. Signed-off-by: Vignesh R Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-omap2-mcspi.c | 26 +++++++------------------- 1 file changed, 7 insertions(+), 19 deletions(-) diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index e2be7da74343..f50cb8a4b413 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -299,7 +299,7 @@ static void omap2_mcspi_set_fifo(const struct spi_device *spi, struct omap2_mcspi_cs *cs = spi->controller_state; struct omap2_mcspi *mcspi; unsigned int wcnt; - int max_fifo_depth, fifo_depth, bytes_per_word; + int max_fifo_depth, bytes_per_word; u32 chconf, xferlevel; mcspi = spi_master_get_devdata(master); @@ -315,10 +315,6 @@ static void omap2_mcspi_set_fifo(const struct spi_device *spi, else max_fifo_depth = OMAP2_MCSPI_MAX_FIFODEPTH; - fifo_depth = gcd(t->len, max_fifo_depth); - if (fifo_depth < 2 || fifo_depth % bytes_per_word != 0) - goto disable_fifo; - wcnt = t->len / bytes_per_word; if (wcnt > OMAP2_MCSPI_MAX_FIFOWCNT) goto disable_fifo; @@ -326,16 +322,17 @@ static void omap2_mcspi_set_fifo(const struct spi_device *spi, xferlevel = wcnt << 16; if (t->rx_buf != NULL) { chconf |= OMAP2_MCSPI_CHCONF_FFER; - xferlevel |= (fifo_depth - 1) << 8; + xferlevel |= (bytes_per_word - 1) << 8; } + if (t->tx_buf != NULL) { chconf |= OMAP2_MCSPI_CHCONF_FFET; - xferlevel |= fifo_depth - 1; + xferlevel |= bytes_per_word - 1; } mcspi_write_reg(master, OMAP2_MCSPI_XFERLEVEL, xferlevel); mcspi_write_chconf0(spi, chconf); - mcspi->fifo_depth = fifo_depth; + mcspi->fifo_depth = max_fifo_depth; return; } @@ -585,7 +582,6 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer) struct dma_slave_config cfg; enum dma_slave_buswidth width; unsigned es; - u32 burst; void __iomem *chstat_reg; void __iomem *irqstat_reg; int wait_res; @@ -605,22 +601,14 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer) } count = xfer->len; - burst = 1; - - if (mcspi->fifo_depth > 0) { - if (count > mcspi->fifo_depth) - burst = mcspi->fifo_depth / es; - else - burst = count / es; - } memset(&cfg, 0, sizeof(cfg)); cfg.src_addr = cs->phys + OMAP2_MCSPI_RX0; cfg.dst_addr = cs->phys + OMAP2_MCSPI_TX0; cfg.src_addr_width = width; cfg.dst_addr_width = width; - cfg.src_maxburst = burst; - cfg.dst_maxburst = burst; + cfg.src_maxburst = es; + cfg.dst_maxburst = es; rx = xfer->rx_buf; tx = xfer->tx_buf; From 3d02e3bb3cfe1a9289b1ee27dec2f6d1248d48bd Mon Sep 17 00:00:00 2001 From: Jithu Joseph Date: Fri, 12 Oct 2018 15:51:01 -0700 Subject: [PATCH 107/299] x86/intel_rdt: Prevent pseudo-locking from using stale pointers [ Upstream commit b61b8bba18fe2b63d38fdaf9b83de25e2d787dfe ] When the last CPU in an rdt_domain goes offline, its rdt_domain struct gets freed. Current pseudo-locking code is unaware of this scenario and tries to dereference the freed structure in a few places. Add checks to prevent pseudo-locking code from doing this. While further work is needed to seamlessly restore resource groups (not just pseudo-locking) to their configuration when the domain is brought back online, the immediate issue of invalid pointers is addressed here. Fixes: f4e80d67a5274 ("x86/intel_rdt: Resctrl files reflect pseudo-locked information") Fixes: 443810fe61605 ("x86/intel_rdt: Create debugfs files for pseudo-locking testing") Fixes: 746e08590b864 ("x86/intel_rdt: Create character device exposing pseudo-locked region") Fixes: 33dc3e410a0d9 ("x86/intel_rdt: Make CPU information accessible for pseudo-locked regions") Signed-off-by: Jithu Joseph Signed-off-by: Reinette Chatre Signed-off-by: Thomas Gleixner Cc: fenghua.yu@intel.com Cc: tony.luck@intel.com Cc: gavin.hindman@intel.com Cc: hpa@zytor.com Link: https://lkml.kernel.org/r/231f742dbb7b00a31cc104416860e27dba6b072d.1539384145.git.reinette.chatre@intel.com Signed-off-by: Sasha Levin --- arch/x86/kernel/cpu/intel_rdt.c | 7 ++++ arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c | 12 +++++-- arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 10 ++++++ arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 38 +++++++++++++++------ 4 files changed, 55 insertions(+), 12 deletions(-) diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index cc43c5abd187..b99a04da70f6 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -610,6 +610,13 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cancel_delayed_work(&d->cqm_limbo); } + /* + * rdt_domain "d" is going to be freed below, so clear + * its pointer from pseudo_lock_region struct. + */ + if (d->plr) + d->plr->d = NULL; + kfree(d->ctrl_val); kfree(d->mbps_val); kfree(d->rmid_busy_llc); diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index 968ace3c6d73..c8b72aff55e0 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -408,8 +408,16 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, for_each_alloc_enabled_rdt_resource(r) seq_printf(s, "%s:uninitialized\n", r->name); } else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { - seq_printf(s, "%s:%d=%x\n", rdtgrp->plr->r->name, - rdtgrp->plr->d->id, rdtgrp->plr->cbm); + if (!rdtgrp->plr->d) { + rdt_last_cmd_clear(); + rdt_last_cmd_puts("Cache domain offline\n"); + ret = -ENODEV; + } else { + seq_printf(s, "%s:%d=%x\n", + rdtgrp->plr->r->name, + rdtgrp->plr->d->id, + rdtgrp->plr->cbm); + } } else { closid = rdtgrp->closid; for_each_alloc_enabled_rdt_resource(r) { diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c index 912d53939f4f..a999a58ca331 100644 --- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c +++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c @@ -1116,6 +1116,11 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel) goto out; } + if (!plr->d) { + ret = -ENODEV; + goto out; + } + plr->thread_done = 0; cpu = cpumask_first(&plr->d->cpu_mask); if (!cpu_online(cpu)) { @@ -1429,6 +1434,11 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma) plr = rdtgrp->plr; + if (!plr->d) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + /* * Task is required to run with affinity to the cpus associated * with the pseudo-locked region. If this is not the case the task diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index ad64031e82dc..a2d7e6646cce 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -268,17 +268,27 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { struct rdtgroup *rdtgrp; + struct cpumask *mask; int ret = 0; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (rdtgrp) { - if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) - seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", - cpumask_pr_args(&rdtgrp->plr->d->cpu_mask)); - else + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + if (!rdtgrp->plr->d) { + rdt_last_cmd_clear(); + rdt_last_cmd_puts("Cache domain offline\n"); + ret = -ENODEV; + } else { + mask = &rdtgrp->plr->d->cpu_mask; + seq_printf(s, is_cpu_list(of) ? + "%*pbl\n" : "%*pb\n", + cpumask_pr_args(mask)); + } + } else { seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", cpumask_pr_args(&rdtgrp->cpu_mask)); + } } else { ret = -ENOENT; } @@ -1286,6 +1296,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, struct rdt_resource *r; struct rdt_domain *d; unsigned int size; + int ret = 0; bool sep; u32 ctrl; @@ -1296,11 +1307,18 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, } if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { - seq_printf(s, "%*s:", max_name_width, rdtgrp->plr->r->name); - size = rdtgroup_cbm_to_size(rdtgrp->plr->r, - rdtgrp->plr->d, - rdtgrp->plr->cbm); - seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size); + if (!rdtgrp->plr->d) { + rdt_last_cmd_clear(); + rdt_last_cmd_puts("Cache domain offline\n"); + ret = -ENODEV; + } else { + seq_printf(s, "%*s:", max_name_width, + rdtgrp->plr->r->name); + size = rdtgroup_cbm_to_size(rdtgrp->plr->r, + rdtgrp->plr->d, + rdtgrp->plr->cbm); + seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size); + } goto out; } @@ -1330,7 +1348,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, out: rdtgroup_kn_unlock(of->kn); - return 0; + return ret; } /* rdtgroup information files for one cache resource. */ From ff6618e06cb4548b8ceaed1855ee39976a1f4aaf Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 19 Oct 2018 10:52:52 -0700 Subject: [PATCH 108/299] sparc: Fix parport build warnings. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 46b8306480fb424abd525acc1763da1c63a27d8a ] If PARPORT_PC_FIFO is not enabled, do not provide the dma lock macros and lock definition. Otherwise: ./arch/sparc/include/asm/parport.h:24:24: warning: ‘dma_spin_lock’ defined but not used [-Wunused-variable] static DEFINE_SPINLOCK(dma_spin_lock); ^~~~~~~~~~~~~ ./include/linux/spinlock_types.h:81:39: note: in definition of macro ‘DEFINE_SPINLOCK’ #define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- arch/sparc/include/asm/parport.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/sparc/include/asm/parport.h b/arch/sparc/include/asm/parport.h index 05df5f043053..3c5a1c620f0f 100644 --- a/arch/sparc/include/asm/parport.h +++ b/arch/sparc/include/asm/parport.h @@ -21,6 +21,7 @@ */ #define HAS_DMA +#ifdef CONFIG_PARPORT_PC_FIFO static DEFINE_SPINLOCK(dma_spin_lock); #define claim_dma_lock() \ @@ -31,6 +32,7 @@ static DEFINE_SPINLOCK(dma_spin_lock); #define release_dma_lock(__flags) \ spin_unlock_irqrestore(&dma_spin_lock, __flags); +#endif static struct sparc_ebus_info { struct ebus_dma_info info; From 9ed143cf730d6a13415da0a6a3456560bb4bc6cf Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 18 Oct 2018 18:59:39 +0200 Subject: [PATCH 109/299] scsi: hisi_sas: Fix NULL pointer dereference [ Upstream commit f4445bb93d82a984657b469e63118c2794a4c3d3 ] There is a NULL pointer dereference in case *slot* happens to be NULL at lines 1053 and 1878: struct hisi_sas_cq *cq = &hisi_hba->cq[slot->dlvry_queue]; Notice that *slot* is being NULL checked at lines 1057 and 1881: if (slot), which implies it may be NULL. Fix this by placing the declaration and definition of variable cq, which contains the pointer dereference slot->dlvry_queue, after slot has been properly NULL checked. Addresses-Coverity-ID: 1474515 ("Dereference before null check") Addresses-Coverity-ID: 1474520 ("Dereference before null check") Fixes: 584f53fe5f52 ("scsi: hisi_sas: Fix the race between IO completion and timeout for SMP/internal IO") Signed-off-by: Gustavo A. R. Silva Reviewed-by: Xiang Chen Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/hisi_sas/hisi_sas_main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index d4a2625a4423..f478d1f50dfc 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -1025,11 +1025,11 @@ static int hisi_sas_exec_internal_tmf_task(struct domain_device *device, if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) { if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) { struct hisi_sas_slot *slot = task->lldd_task; - struct hisi_sas_cq *cq = - &hisi_hba->cq[slot->dlvry_queue]; dev_err(dev, "abort tmf: TMF task timeout and not done\n"); if (slot) { + struct hisi_sas_cq *cq = + &hisi_hba->cq[slot->dlvry_queue]; /* * flush tasklet to avoid free'ing task * before using task in IO completion @@ -1856,10 +1856,10 @@ hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba, if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) { if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) { struct hisi_sas_slot *slot = task->lldd_task; - struct hisi_sas_cq *cq = - &hisi_hba->cq[slot->dlvry_queue]; if (slot) { + struct hisi_sas_cq *cq = + &hisi_hba->cq[slot->dlvry_queue]; /* * flush tasklet to avoid free'ing task * before using task in IO completion From ee35e01b0f08affff2c03dbd1c1f11bababf908e Mon Sep 17 00:00:00 2001 From: Aravinda Prasad Date: Tue, 16 Oct 2018 17:20:05 +0530 Subject: [PATCH 110/299] powerpc/pseries: Export raw per-CPU VPA data via debugfs [ Upstream commit c6c26fb55e8e4b3fc376be5611685990a17de27a ] This patch exports the raw per-CPU VPA data via debugfs. A per-CPU file is created which exports the VPA data of that CPU to help debug some of the VPA related issues or to analyze the per-CPU VPA related statistics. v3: Removed offline CPU check. v2: Included offline CPU check and other review comments. Signed-off-by: Aravinda Prasad Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- arch/powerpc/platforms/pseries/lpar.c | 54 +++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index ea602f7f97ce..49e3a88b6a0c 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -48,6 +48,7 @@ #include #include #include +#include #include "pseries.h" @@ -1032,3 +1033,56 @@ static int __init reserve_vrma_context_id(void) return 0; } machine_device_initcall(pseries, reserve_vrma_context_id); + +#ifdef CONFIG_DEBUG_FS +/* debugfs file interface for vpa data */ +static ssize_t vpa_file_read(struct file *filp, char __user *buf, size_t len, + loff_t *pos) +{ + int cpu = (long)filp->private_data; + struct lppaca *lppaca = &lppaca_of(cpu); + + return simple_read_from_buffer(buf, len, pos, lppaca, + sizeof(struct lppaca)); +} + +static const struct file_operations vpa_fops = { + .open = simple_open, + .read = vpa_file_read, + .llseek = default_llseek, +}; + +static int __init vpa_debugfs_init(void) +{ + char name[16]; + long i; + static struct dentry *vpa_dir; + + if (!firmware_has_feature(FW_FEATURE_SPLPAR)) + return 0; + + vpa_dir = debugfs_create_dir("vpa", powerpc_debugfs_root); + if (!vpa_dir) { + pr_warn("%s: can't create vpa root dir\n", __func__); + return -ENOMEM; + } + + /* set up the per-cpu vpa file*/ + for_each_possible_cpu(i) { + struct dentry *d; + + sprintf(name, "cpu-%ld", i); + + d = debugfs_create_file(name, 0400, vpa_dir, (void *)i, + &vpa_fops); + if (!d) { + pr_warn("%s: can't create per-cpu vpa file\n", + __func__); + return -ENOMEM; + } + } + + return 0; +} +machine_arch_initcall(pseries, vpa_debugfs_init); +#endif /* CONFIG_DEBUG_FS */ From 434551e9fd4485b18df07c8566fb2df59105dcc0 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 10 Aug 2018 22:29:26 +1000 Subject: [PATCH 111/299] powerpc/mm/radix: Fix off-by-one in split mapping logic [ Upstream commit 5c6499b7041b43807dfaeda28aa87fc0e62558f7 ] When we have CONFIG_STRICT_KERNEL_RWX enabled, we try to split the kernel linear (1:1) mapping so that the kernel text is in a separate page to kernel data, so we can mark the former read-only. We could achieve that just by always using 64K pages for the linear mapping, but we try to be smarter. Instead we use huge pages when possible, and only switch to smaller pages when necessary. However we have an off-by-one bug in that logic, which causes us to calculate the wrong boundary between text and data. For example with the end of the kernel text at 16M we see: radix-mmu: Mapped 0x0000000000000000-0x0000000001200000 with 64.0 KiB pages radix-mmu: Mapped 0x0000000001200000-0x0000000040000000 with 2.00 MiB pages radix-mmu: Mapped 0x0000000040000000-0x0000000100000000 with 1.00 GiB pages ie. we mapped from 0 to 18M with 64K pages, even though the boundary between text and data is at 16M. With the fix we see we're correctly hitting the 16M boundary: radix-mmu: Mapped 0x0000000000000000-0x0000000001000000 with 64.0 KiB pages radix-mmu: Mapped 0x0000000001000000-0x0000000040000000 with 2.00 MiB pages radix-mmu: Mapped 0x0000000040000000-0x0000000100000000 with 1.00 GiB pages Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- arch/powerpc/mm/pgtable-radix.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 3ea4c1f107d7..24a2eadc8c21 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -294,14 +294,14 @@ retry: } if (split_text_mapping && (mapping_size == PUD_SIZE) && - (addr <= __pa_symbol(__init_begin)) && + (addr < __pa_symbol(__init_begin)) && (addr + mapping_size) >= __pa_symbol(_stext)) { max_mapping_size = PMD_SIZE; goto retry; } if (split_text_mapping && (mapping_size == PMD_SIZE) && - (addr <= __pa_symbol(__init_begin)) && + (addr < __pa_symbol(__init_begin)) && (addr + mapping_size) >= __pa_symbol(_stext)) { mapping_size = PAGE_SIZE; psize = mmu_virtual_psize; From b499fa070ee4827931c443811a08cced55f8f00a Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 14 Aug 2018 20:48:22 +1000 Subject: [PATCH 112/299] powerpc/mm/radix: Fix overuse of small pages in splitting logic [ Upstream commit 3b5657ed5b4e27ccf593a41ff3c5aa27dae8df18 ] When we have CONFIG_STRICT_KERNEL_RWX enabled, we want to split the linear mapping at the text/data boundary so we can map the kernel text read only. But the current logic uses small pages for the entire text section, regardless of whether a larger page size would fit. eg. with the boundary at 16M we could use 2M pages, but instead we use 64K pages up to the 16M boundary: Mapped 0x0000000000000000-0x0000000001000000 with 64.0 KiB pages Mapped 0x0000000001000000-0x0000000040000000 with 2.00 MiB pages Mapped 0x0000000040000000-0x0000000100000000 with 1.00 GiB pages This is because the test is checking if addr is < __init_begin and addr + mapping_size is >= _stext. But that is true for all pages between _stext and __init_begin. Instead what we want to check is if we are crossing the text/data boundary, which is at __init_begin. With that fixed we see: Mapped 0x0000000000000000-0x0000000000e00000 with 2.00 MiB pages Mapped 0x0000000000e00000-0x0000000001000000 with 64.0 KiB pages Mapped 0x0000000001000000-0x0000000040000000 with 2.00 MiB pages Mapped 0x0000000040000000-0x0000000100000000 with 1.00 GiB pages ie. we're correctly using 2MB pages below __init_begin, but we still drop down to 64K pages unnecessarily at the boundary. Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- arch/powerpc/mm/pgtable-radix.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 24a2eadc8c21..b387c7b917b7 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -295,14 +295,14 @@ retry: if (split_text_mapping && (mapping_size == PUD_SIZE) && (addr < __pa_symbol(__init_begin)) && - (addr + mapping_size) >= __pa_symbol(_stext)) { + (addr + mapping_size) >= __pa_symbol(__init_begin)) { max_mapping_size = PMD_SIZE; goto retry; } if (split_text_mapping && (mapping_size == PMD_SIZE) && (addr < __pa_symbol(__init_begin)) && - (addr + mapping_size) >= __pa_symbol(_stext)) { + (addr + mapping_size) >= __pa_symbol(__init_begin)) { mapping_size = PAGE_SIZE; psize = mmu_virtual_psize; } From b43c5287f6bca1bfaef43326130515c1256856ff Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 14 Aug 2018 21:05:20 +1000 Subject: [PATCH 113/299] powerpc/mm/radix: Fix small page at boundary when splitting [ Upstream commit 81d1b54dec95209ab5e5be2cf37182885f998753 ] When we have CONFIG_STRICT_KERNEL_RWX enabled, we want to split the linear mapping at the text/data boundary so we can map the kernel text read only. Currently we always use a small page at the text/data boundary, even when that's not necessary: Mapped 0x0000000000000000-0x0000000000e00000 with 2.00 MiB pages Mapped 0x0000000000e00000-0x0000000001000000 with 64.0 KiB pages Mapped 0x0000000001000000-0x0000000040000000 with 2.00 MiB pages This is because the check that the mapping crosses the __init_begin boundary is too strict, it also returns true when we map exactly up to the boundary. So fix it to check that the mapping would actually map past __init_begin, and with that we see: Mapped 0x0000000000000000-0x0000000040000000 with 2.00 MiB pages Mapped 0x0000000040000000-0x0000000100000000 with 1.00 GiB pages Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- arch/powerpc/mm/pgtable-radix.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index b387c7b917b7..69caeb5bccb2 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -295,14 +295,14 @@ retry: if (split_text_mapping && (mapping_size == PUD_SIZE) && (addr < __pa_symbol(__init_begin)) && - (addr + mapping_size) >= __pa_symbol(__init_begin)) { + (addr + mapping_size) > __pa_symbol(__init_begin)) { max_mapping_size = PMD_SIZE; goto retry; } if (split_text_mapping && (mapping_size == PMD_SIZE) && (addr < __pa_symbol(__init_begin)) && - (addr + mapping_size) >= __pa_symbol(__init_begin)) { + (addr + mapping_size) > __pa_symbol(__init_begin)) { mapping_size = PAGE_SIZE; psize = mmu_virtual_psize; } From 3173e226ca412a80267f471ce173e326895198df Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 28 Aug 2018 18:11:27 +1000 Subject: [PATCH 114/299] powerpc/64s/radix: Fix radix__flush_tlb_collapsed_pmd double flushing pmd [ Upstream commit dd76ff5af35350fd6d5bb5b069e73b6017f66893 ] Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- arch/powerpc/mm/tlb-radix.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 796ff5de26d0..1749f15fc070 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -1072,7 +1072,6 @@ void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr) goto local; } _tlbie_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true); - goto local; } else { local: _tlbiel_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true); From 570c05378d971ab29e6e67500c8b0e6fdd19dc93 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Sat, 20 Oct 2018 22:58:44 +0100 Subject: [PATCH 115/299] selftests/bpf: fix return value comparison for tests in test_libbpf.sh [ Upstream commit c5fa5d602221362f8341ecd9e32d83194abf5bd9 ] The return value for each test in test_libbpf.sh is compared with if (( $? == 0 )) ; then ... This works well with bash, but not with dash, that /bin/sh is aliased to on some systems (such as Ubuntu). Let's replace this comparison by something that works on both shells. Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- tools/testing/selftests/bpf/test_libbpf.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/test_libbpf.sh b/tools/testing/selftests/bpf/test_libbpf.sh index 8b1bc96d8e0c..2989b2e2d856 100755 --- a/tools/testing/selftests/bpf/test_libbpf.sh +++ b/tools/testing/selftests/bpf/test_libbpf.sh @@ -6,7 +6,7 @@ export TESTNAME=test_libbpf # Determine selftest success via shell exit code exit_handler() { - if (( $? == 0 )); then + if [ $? -eq 0 ]; then echo "selftests: $TESTNAME [PASS]"; else echo "$TESTNAME: failed at file $LAST_LOADED" 1>&2 From 083757d848597e5e33528c931751ceb8a98bc6c0 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Sat, 20 Oct 2018 23:01:50 +0100 Subject: [PATCH 116/299] tools: bpftool: fix completion for "bpftool map update" [ Upstream commit fe8ecccc10b3adc071de05ca7af728ca1a4ac9aa ] When trying to complete "bpftool map update" commands, the call to printf would print an error message that would show on the command line if no map is found to complete the command line. Fix it by making sure we have map ids to complete the line with, before we try to print something. Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Daniel Borkmann Signed-off-by: Sasha Levin --- tools/bpf/bpftool/bash-completion/bpftool | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 598066c40191..c2b6b2176f3b 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -143,7 +143,7 @@ _bpftool_map_update_map_type() local type type=$(bpftool -jp map show $keyword $ref | \ command sed -n 's/.*"type": "\(.*\)",$/\1/p') - printf $type + [[ -n $type ]] && printf $type } _bpftool_map_update_get_id() From 146fb4b0d4fe8a35e3cc28cd7a9fa69a5d1ee8ab Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Fri, 28 Sep 2018 09:10:29 +0800 Subject: [PATCH 117/299] ceph: fix dentry leak in ceph_readdir_prepopulate [ Upstream commit c58f450bd61511d897efc2ea472c69630635b557 ] Signed-off-by: "Yan, Zheng" Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov Signed-off-by: Sasha Levin --- fs/ceph/inode.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index acb70a6a82f0..1e438e0faf77 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1694,7 +1694,6 @@ retry_lookup: if (IS_ERR(realdn)) { err = PTR_ERR(realdn); d_drop(dn); - dn = NULL; goto next_item; } dn = realdn; From 8112f3d4ed036ca5caacecad23e31e805fb93ec6 Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Tue, 9 Oct 2018 18:54:28 +0100 Subject: [PATCH 118/299] ceph: only allow punch hole mode in fallocate [ Upstream commit bddff633ab7bc60a18a86ac8b322695b6f8594d0 ] Current implementation of cephfs fallocate isn't correct as it doesn't really reserve the space in the cluster, which means that a subsequent call to a write may actually fail due to lack of space. In fact, it is currently possible to fallocate an amount space that is larger than the free space in the cluster. It has behaved this way since the initial commit ad7a60de882a ("ceph: punch hole support"). Since there's no easy solution to fix this at the moment, this patch simply removes support for all fallocate operations but FALLOC_FL_PUNCH_HOLE (which implies FALLOC_FL_KEEP_SIZE). Link: https://tracker.ceph.com/issues/36317 Signed-off-by: Luis Henriques Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov Signed-off-by: Sasha Levin --- fs/ceph/file.c | 45 +++++++++------------------------------------ 1 file changed, 9 insertions(+), 36 deletions(-) diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 92ab20433682..91a7ad259bcf 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1735,7 +1735,6 @@ static long ceph_fallocate(struct file *file, int mode, struct ceph_file_info *fi = file->private_data; struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_fs_client *fsc = ceph_inode_to_client(inode); struct ceph_cap_flush *prealloc_cf; int want, got = 0; int dirty; @@ -1743,10 +1742,7 @@ static long ceph_fallocate(struct file *file, int mode, loff_t endoff = 0; loff_t size; - if ((offset + length) > max(i_size_read(inode), fsc->max_file_size)) - return -EFBIG; - - if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + if (mode != (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) return -EOPNOTSUPP; if (!S_ISREG(inode->i_mode)) @@ -1763,18 +1759,6 @@ static long ceph_fallocate(struct file *file, int mode, goto unlock; } - if (!(mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE)) && - ceph_quota_is_max_bytes_exceeded(inode, offset + length)) { - ret = -EDQUOT; - goto unlock; - } - - if (ceph_osdmap_flag(&fsc->client->osdc, CEPH_OSDMAP_FULL) && - !(mode & FALLOC_FL_PUNCH_HOLE)) { - ret = -ENOSPC; - goto unlock; - } - if (ci->i_inline_version != CEPH_INLINE_NONE) { ret = ceph_uninline_data(file, NULL); if (ret < 0) @@ -1782,12 +1766,12 @@ static long ceph_fallocate(struct file *file, int mode, } size = i_size_read(inode); - if (!(mode & FALLOC_FL_KEEP_SIZE)) { - endoff = offset + length; - ret = inode_newsize_ok(inode, endoff); - if (ret) - goto unlock; - } + + /* Are we punching a hole beyond EOF? */ + if (offset >= size) + goto unlock; + if ((offset + length) > size) + length = size - offset; if (fi->fmode & CEPH_FILE_MODE_LAZY) want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO; @@ -1798,16 +1782,8 @@ static long ceph_fallocate(struct file *file, int mode, if (ret < 0) goto unlock; - if (mode & FALLOC_FL_PUNCH_HOLE) { - if (offset < size) - ceph_zero_pagecache_range(inode, offset, length); - ret = ceph_zero_objects(inode, offset, length); - } else if (endoff > size) { - truncate_pagecache_range(inode, size, -1); - if (ceph_inode_set_size(inode, endoff)) - ceph_check_caps(ceph_inode(inode), - CHECK_CAPS_AUTHONLY, NULL); - } + ceph_zero_pagecache_range(inode, offset, length); + ret = ceph_zero_objects(inode, offset, length); if (!ret) { spin_lock(&ci->i_ceph_lock); @@ -1817,9 +1793,6 @@ static long ceph_fallocate(struct file *file, int mode, spin_unlock(&ci->i_ceph_lock); if (dirty) __mark_inode_dirty(inode, dirty); - if ((endoff > size) && - ceph_quota_is_max_bytes_approaching(inode, endoff)) - ceph_check_caps(ci, CHECK_CAPS_NODELAY, NULL); } ceph_put_cap_refs(ci, got); From 829aa617bf6e061964a724d48a2cb892752fa5ef Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 19 Oct 2018 13:43:45 -0700 Subject: [PATCH 119/299] rtc: s35390a: Change buf's type to u8 in s35390a_init [ Upstream commit ef0f02fd69a02b50e468a4ddbe33e3d81671e248 ] Clang warns: drivers/rtc/rtc-s35390a.c:124:27: warning: implicit conversion from 'int' to 'char' changes value from 192 to -64 [-Wconstant-conversion] buf = S35390A_FLAG_RESET | S35390A_FLAG_24H; ~ ~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~ 1 warning generated. Update buf to be an unsigned 8-bit integer, which matches the buf member in struct i2c_msg. https://github.com/ClangBuiltLinux/linux/issues/145 Signed-off-by: Nathan Chancellor Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/rtc/rtc-s35390a.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-s35390a.c b/drivers/rtc/rtc-s35390a.c index 77feb603cd4c..3c64dbb08109 100644 --- a/drivers/rtc/rtc-s35390a.c +++ b/drivers/rtc/rtc-s35390a.c @@ -108,7 +108,7 @@ static int s35390a_get_reg(struct s35390a *s35390a, int reg, char *buf, int len) static int s35390a_init(struct s35390a *s35390a) { - char buf; + u8 buf; int ret; unsigned initcount = 0; From bb925b9bece25e3c53fb06dc0cbcc4f3e40b196e Mon Sep 17 00:00:00 2001 From: Vincent Chen Date: Tue, 2 Oct 2018 16:52:31 +0800 Subject: [PATCH 120/299] RISC-V: Avoid corrupting the upper 32-bit of phys_addr_t in ioremap [ Upstream commit 827a438156e4c423b6875a092e272933952a2910 ] For 32bit, the upper 32-bit of phys_addr_t will be flushed to zero after AND with PAGE_MASK because the data type of PAGE_MASK is unsigned long. To fix this problem, the page alignment is done by subtracting the page offset instead of AND with PAGE_MASK. Signed-off-by: Vincent Chen Reviewed-by: Christoph Hellwig Signed-off-by: Palmer Dabbelt Signed-off-by: Sasha Levin --- arch/riscv/mm/ioremap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/mm/ioremap.c b/arch/riscv/mm/ioremap.c index 70ef2724cdf6..bd2f2db557cc 100644 --- a/arch/riscv/mm/ioremap.c +++ b/arch/riscv/mm/ioremap.c @@ -42,7 +42,7 @@ static void __iomem *__ioremap_caller(phys_addr_t addr, size_t size, /* Page-align mappings */ offset = addr & (~PAGE_MASK); - addr &= PAGE_MASK; + addr -= offset; size = PAGE_ALIGN(size + offset); area = get_vm_area_caller(size, VM_IOREMAP, caller); From 733fddc346515d1d44c577efa7d36cb02fb57a3f Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 19 Sep 2018 13:35:00 +0300 Subject: [PATCH 121/299] thermal: armada: fix a test in probe() [ Upstream commit d1d2c290b3c04b65fa6132eeebe50a070746d8f6 ] The platform_get_resource() function doesn't return error pointers, it returns NULL on error. Fixes: 3d4e51844a4e ("thermal: armada: convert driver to syscon register accesses") Signed-off-by: Dan Carpenter Reviewed-by: Miquel Raynal Signed-off-by: Eduardo Valentin Signed-off-by: Sasha Levin --- drivers/thermal/armada_thermal.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c index e16b3cb1808c..1c9830b2c84d 100644 --- a/drivers/thermal/armada_thermal.c +++ b/drivers/thermal/armada_thermal.c @@ -526,8 +526,8 @@ static int armada_thermal_probe_legacy(struct platform_device *pdev, /* First memory region points towards the status register */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (IS_ERR(res)) - return PTR_ERR(res); + if (!res) + return -EIO; /* * Edit the resource start address and length to map over all the From e7f81efae3b5c90684a83dc95aab1ba5c8c7b7cf Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Fri, 27 Jul 2018 18:15:16 +0800 Subject: [PATCH 122/299] f2fs: fix to spread clear_cold_data() [ Upstream commit 2baf07818549c8bb8d7b3437e889b86eab56d38e ] We need to drop PG_checked flag on page as well when we clear PG_uptodate flag, in order to avoid treating the page as GCing one later. Signed-off-by: Weichao Guo Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/data.c | 8 +++++++- fs/f2fs/dir.c | 1 + fs/f2fs/segment.c | 4 +++- 3 files changed, 11 insertions(+), 2 deletions(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 3a2fd6676966..a7436ad19458 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1782,6 +1782,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio) /* This page is already truncated */ if (fio->old_blkaddr == NULL_ADDR) { ClearPageUptodate(page); + clear_cold_data(page); goto out_writepage; } got_it: @@ -1957,8 +1958,10 @@ done: out: inode_dec_dirty_pages(inode); - if (err) + if (err) { ClearPageUptodate(page); + clear_cold_data(page); + } if (wbc->for_reclaim) { f2fs_submit_merged_write_cond(sbi, inode, 0, page->index, DATA); @@ -2573,6 +2576,8 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset, } } + clear_cold_data(page); + /* This is atomic written page, keep Private */ if (IS_ATOMIC_WRITTEN_PAGE(page)) return f2fs_drop_inmem_page(inode, page); @@ -2591,6 +2596,7 @@ int f2fs_release_page(struct page *page, gfp_t wait) if (IS_ATOMIC_WRITTEN_PAGE(page)) return 0; + clear_cold_data(page); set_page_private(page, 0); ClearPagePrivate(page); return 1; diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index ecc3a4e2be96..cd611a57d04d 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -733,6 +733,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, clear_page_dirty_for_io(page); ClearPagePrivate(page); ClearPageUptodate(page); + clear_cold_data(page); inode_dec_dirty_pages(dir); f2fs_remove_dirty_inode(dir); } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index d78009694f3f..43a07514c357 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -277,8 +277,10 @@ retry: } next: /* we don't need to invalidate this in the sccessful status */ - if (drop || recover) + if (drop || recover) { ClearPageUptodate(page); + clear_cold_data(page); + } set_page_private(page, 0); ClearPagePrivate(page); f2fs_put_page(page, 1); From 074af1668038e5743bddb413681e345d632e7a97 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Sun, 7 Oct 2018 19:06:15 +0800 Subject: [PATCH 123/299] f2fs: spread f2fs_set_inode_flags() [ Upstream commit 9149a5eb606152df158eb7d7da5a34e84b574189 ] This patch changes codes as below: - use f2fs_set_inode_flags() to update i_flags atomically to avoid potential race. - synchronize F2FS_I(inode)->i_flags to inode->i_flags in f2fs_new_inode(). - use f2fs_set_inode_flags() to simply codes in f2fs_quota_{on,off}. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/f2fs.h | 2 +- fs/f2fs/namei.c | 2 ++ fs/f2fs/super.c | 5 ++--- 3 files changed, 5 insertions(+), 4 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 2dc49a541907..34e48bcf5087 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3388,7 +3388,7 @@ static inline void f2fs_set_encrypted_inode(struct inode *inode) { #ifdef CONFIG_F2FS_FS_ENCRYPTION file_set_encrypt(inode); - inode->i_flags |= S_ENCRYPTED; + f2fs_set_inode_flags(inode); #endif } diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 1f67e389169f..6b23dcbf52f4 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -124,6 +124,8 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL) set_inode_flag(inode, FI_PROJ_INHERIT); + f2fs_set_inode_flags(inode); + trace_f2fs_new_inode(inode, 0); return inode; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 15779123d089..7a9cc64f5ca3 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1837,8 +1837,7 @@ static int f2fs_quota_on(struct super_block *sb, int type, int format_id, inode_lock(inode); F2FS_I(inode)->i_flags |= F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL; - inode_set_flags(inode, S_NOATIME | S_IMMUTABLE, - S_NOATIME | S_IMMUTABLE); + f2fs_set_inode_flags(inode); inode_unlock(inode); f2fs_mark_inode_dirty_sync(inode, false); @@ -1863,7 +1862,7 @@ static int f2fs_quota_off(struct super_block *sb, int type) inode_lock(inode); F2FS_I(inode)->i_flags &= ~(F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL); - inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE); + f2fs_set_inode_flags(inode); inode_unlock(inode); f2fs_mark_inode_dirty_sync(inode, false); out_put: From 321c40dce58185672882e9250ce333eec1f91886 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 19 Oct 2018 11:00:30 -0700 Subject: [PATCH 124/299] mISDN: Fix type of switch control variable in ctrl_teimanager [ Upstream commit aeb5e02aca91522733eb1db595ac607d30c87767 ] Clang warns (trimmed for brevity): drivers/isdn/mISDN/tei.c:1193:7: warning: overflow converting case value to switch condition type (2147764552 to 18446744071562348872) [-Wswitch] case IMHOLD_L1: ^ drivers/isdn/mISDN/tei.c:1187:7: warning: overflow converting case value to switch condition type (2147764550 to 18446744071562348870) [-Wswitch] case IMCLEAR_L2: ^ 2 warnings generated. The root cause is that the _IOC macro can generate really large numbers, which don't find into type int. My research into how GCC and Clang are handling this at a low level didn't prove fruitful and surveying the kernel tree shows that aside from here and a few places in the scsi subsystem, everything that uses _IOC is at least of type 'unsigned int'. Make that change here because as nothing in this function cares about the signedness of the variable and it removes ambiguity, which is never good when dealing with compilers. While we're here, remove the unnecessary local variable ret (just return -EINVAL and 0 directly). Link: https://github.com/ClangBuiltLinux/linux/issues/67 Signed-off-by: Nathan Chancellor Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/isdn/mISDN/tei.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/isdn/mISDN/tei.c b/drivers/isdn/mISDN/tei.c index 12d9e5f4beb1..58635b5f296f 100644 --- a/drivers/isdn/mISDN/tei.c +++ b/drivers/isdn/mISDN/tei.c @@ -1180,8 +1180,7 @@ static int ctrl_teimanager(struct manager *mgr, void *arg) { /* currently we only have one option */ - int *val = (int *)arg; - int ret = 0; + unsigned int *val = (unsigned int *)arg; switch (val[0]) { case IMCLEAR_L2: @@ -1197,9 +1196,9 @@ ctrl_teimanager(struct manager *mgr, void *arg) test_and_clear_bit(OPTION_L1_HOLD, &mgr->options); break; default: - ret = -EINVAL; + return -EINVAL; } - return ret; + return 0; } /* This function does create a L2 for fixed TEI in NT Mode */ From 7c011435110f150abba12ab187c131fa902e2520 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 19 Oct 2018 23:11:11 +0300 Subject: [PATCH 125/299] qlcnic: fix a return in qlcnic_dcb_get_capability() [ Upstream commit c94f026fb742b2d3199422751dbc4f6fc0e753d8 ] These functions are supposed to return one on failure and zero on success. Returning a zero here could cause uninitialized variable bugs in several of the callers. For example: drivers/scsi/cxgbi/cxgb4i/cxgb4i.c:1660 get_iscsi_dcb_priority() error: uninitialized symbol 'caps'. Fixes: 48365e485275 ("qlcnic: dcb: Add support for CEE Netlink interface.") Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c index 4b76c69fe86d..834208e55f7b 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c @@ -883,7 +883,7 @@ static u8 qlcnic_dcb_get_capability(struct net_device *netdev, int capid, struct qlcnic_adapter *adapter = netdev_priv(netdev); if (!test_bit(QLCNIC_DCB_STATE, &adapter->dcb->state)) - return 0; + return 1; switch (capid) { case DCB_CAP_ATTR_PG: From e79d230832d02e4783df5fc62ad7c8752fe846c4 Mon Sep 17 00:00:00 2001 From: Ivan Khoronzhuk Date: Mon, 22 Oct 2018 21:51:36 +0300 Subject: [PATCH 126/299] net: ethernet: ti: cpsw: unsync mcast entries while switch promisc mode [ Upstream commit 9737cc99dd14b5b8b9d267618a6061feade8ea68 ] After flushing all mcast entries from the table, the ones contained in mc list of ndev are not restored when promisc mode is toggled off, because they are considered as synched with ALE, thus, in order to restore them after promisc mode - reset syncing info. This fix touches only switch mode devices, including single port boards like Beagle Bone. Fixes: commit 5da1948969bc ("net: ethernet: ti: cpsw: fix lost of mcast packets while rx_mode update") Signed-off-by: Ivan Khoronzhuk Reviewed-by: Grygorii Strashko Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/ti/cpsw.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 1afed85550c0..8417d4c17844 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -642,6 +642,7 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable) /* Clear all mcast from ALE */ cpsw_ale_flush_multicast(ale, ALE_ALL_PORTS, -1); + __dev_mc_unsync(ndev, NULL); /* Flood All Unicast Packets to Host port */ cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 1); From 02c9ec11860f217006bc04c16d960cdba8de1c23 Mon Sep 17 00:00:00 2001 From: Sapthagiri Baratam Date: Tue, 21 Aug 2018 19:52:44 +0530 Subject: [PATCH 127/299] mfd: arizona: Correct calling of runtime_put_sync [ Upstream commit 6b269a41a4520f7eb639e61a45ebbb9c9267d5e0 ] Don't call runtime_put_sync when clk32k_ref is ARIZONA_32KZ_MCLK2 as there is no corresponding runtime_get_sync call. MCLK1 is not in the AoD power domain so if it is used as 32kHz clock source we need to hold a runtime PM reference to keep the device from going into low power mode. Fixes: cdd8da8cc66b ("mfd: arizona: Add gating of external MCLKn clocks") Signed-off-by: Sapthagiri Baratam Acked-by: Charles Keepax Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/mfd/arizona-core.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c index 47d6d40f41cd..a4403a57ddc8 100644 --- a/drivers/mfd/arizona-core.c +++ b/drivers/mfd/arizona-core.c @@ -52,8 +52,10 @@ int arizona_clk32k_enable(struct arizona *arizona) if (ret != 0) goto err_ref; ret = clk_prepare_enable(arizona->mclk[ARIZONA_MCLK1]); - if (ret != 0) - goto err_pm; + if (ret != 0) { + pm_runtime_put_sync(arizona->dev); + goto err_ref; + } break; case ARIZONA_32KZ_MCLK2: ret = clk_prepare_enable(arizona->mclk[ARIZONA_MCLK2]); @@ -67,8 +69,6 @@ int arizona_clk32k_enable(struct arizona *arizona) ARIZONA_CLK_32K_ENA); } -err_pm: - pm_runtime_put_sync(arizona->dev); err_ref: if (ret != 0) arizona->clk32k_ref--; From dd72391c9a5380a96351e9dba7a0a7cf7fd23a39 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Tue, 28 Aug 2018 17:02:40 -0300 Subject: [PATCH 128/299] mfd: mc13xxx-core: Fix PMIC shutdown when reading ADC values [ Upstream commit 55143439b7b501882bea9d95a54adfe00ffc79a3 ] When trying to read any MC13892 ADC channel on a imx51-babbage board: The MC13892 PMIC shutdowns completely. After debugging this issue and comparing the MC13892 and MC13783 initializations done in the vendor kernel, it was noticed that the CHRGRAWDIV bit of the ADC0 register was not being set. This bit is set by default after power on, but the driver was clearing it. After setting this bit it is possible to read the ADC values correctly. Signed-off-by: Fabio Estevam Tested-by: Chris Healy Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/mfd/mc13xxx-core.c | 3 ++- include/linux/mfd/mc13xxx.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mfd/mc13xxx-core.c b/drivers/mfd/mc13xxx-core.c index 234febfe6398..d0bf50e3568d 100644 --- a/drivers/mfd/mc13xxx-core.c +++ b/drivers/mfd/mc13xxx-core.c @@ -278,7 +278,8 @@ int mc13xxx_adc_do_conversion(struct mc13xxx *mc13xxx, unsigned int mode, if (ret) goto out; - adc0 = MC13XXX_ADC0_ADINC1 | MC13XXX_ADC0_ADINC2; + adc0 = MC13XXX_ADC0_ADINC1 | MC13XXX_ADC0_ADINC2 | + MC13XXX_ADC0_CHRGRAWDIV; adc1 = MC13XXX_ADC1_ADEN | MC13XXX_ADC1_ADTRIGIGN | MC13XXX_ADC1_ASC; /* diff --git a/include/linux/mfd/mc13xxx.h b/include/linux/mfd/mc13xxx.h index 54a3cd808f9e..2ad9bdc0a5ec 100644 --- a/include/linux/mfd/mc13xxx.h +++ b/include/linux/mfd/mc13xxx.h @@ -249,6 +249,7 @@ struct mc13xxx_platform_data { #define MC13XXX_ADC0_TSMOD0 (1 << 12) #define MC13XXX_ADC0_TSMOD1 (1 << 13) #define MC13XXX_ADC0_TSMOD2 (1 << 14) +#define MC13XXX_ADC0_CHRGRAWDIV (1 << 15) #define MC13XXX_ADC0_ADINC1 (1 << 16) #define MC13XXX_ADC0_ADINC2 (1 << 17) From 5a04242e8c2357dfb3dd0af4dbca24c5e0aa774a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Aug 2018 19:52:52 +0300 Subject: [PATCH 129/299] mfd: intel_soc_pmic_bxtwc: Chain power button IRQs as well [ Upstream commit 9f8ddee1dab836ca758ca8fc555ab5a3aaa5d3fd ] Power button IRQ actually has a second level of interrupts to distinguish between UI and POWER buttons. Moreover, current implementation looks awkward in approach to handle second level IRQs by first level related IRQ chip. To address above issues, split power button IRQ to be chained as well. Signed-off-by: Andy Shevchenko Reviewed-by: Mika Westerberg Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/mfd/intel_soc_pmic_bxtwc.c | 41 ++++++++++++++++++++++-------- include/linux/mfd/intel_soc_pmic.h | 1 + 2 files changed, 32 insertions(+), 10 deletions(-) diff --git a/drivers/mfd/intel_soc_pmic_bxtwc.c b/drivers/mfd/intel_soc_pmic_bxtwc.c index 15bc052704a6..9ca1f8c015de 100644 --- a/drivers/mfd/intel_soc_pmic_bxtwc.c +++ b/drivers/mfd/intel_soc_pmic_bxtwc.c @@ -31,8 +31,8 @@ /* Interrupt Status Registers */ #define BXTWC_IRQLVL1 0x4E02 -#define BXTWC_PWRBTNIRQ 0x4E03 +#define BXTWC_PWRBTNIRQ 0x4E03 #define BXTWC_THRM0IRQ 0x4E04 #define BXTWC_THRM1IRQ 0x4E05 #define BXTWC_THRM2IRQ 0x4E06 @@ -47,10 +47,9 @@ /* Interrupt MASK Registers */ #define BXTWC_MIRQLVL1 0x4E0E -#define BXTWC_MPWRTNIRQ 0x4E0F - #define BXTWC_MIRQLVL1_MCHGR BIT(5) +#define BXTWC_MPWRBTNIRQ 0x4E0F #define BXTWC_MTHRM0IRQ 0x4E12 #define BXTWC_MTHRM1IRQ 0x4E13 #define BXTWC_MTHRM2IRQ 0x4E14 @@ -66,9 +65,7 @@ /* Whiskey Cove PMIC share same ACPI ID between different platforms */ #define BROXTON_PMIC_WC_HRV 4 -/* Manage in two IRQ chips since mask registers are not consecutive */ enum bxtwc_irqs { - /* Level 1 */ BXTWC_PWRBTN_LVL1_IRQ = 0, BXTWC_TMU_LVL1_IRQ, BXTWC_THRM_LVL1_IRQ, @@ -77,9 +74,11 @@ enum bxtwc_irqs { BXTWC_CHGR_LVL1_IRQ, BXTWC_GPIO_LVL1_IRQ, BXTWC_CRIT_LVL1_IRQ, +}; - /* Level 2 */ - BXTWC_PWRBTN_IRQ, +enum bxtwc_irqs_pwrbtn { + BXTWC_PWRBTN_IRQ = 0, + BXTWC_UIBTN_IRQ, }; enum bxtwc_irqs_bcu { @@ -113,7 +112,10 @@ static const struct regmap_irq bxtwc_regmap_irqs[] = { REGMAP_IRQ_REG(BXTWC_CHGR_LVL1_IRQ, 0, BIT(5)), REGMAP_IRQ_REG(BXTWC_GPIO_LVL1_IRQ, 0, BIT(6)), REGMAP_IRQ_REG(BXTWC_CRIT_LVL1_IRQ, 0, BIT(7)), - REGMAP_IRQ_REG(BXTWC_PWRBTN_IRQ, 1, 0x03), +}; + +static const struct regmap_irq bxtwc_regmap_irqs_pwrbtn[] = { + REGMAP_IRQ_REG(BXTWC_PWRBTN_IRQ, 0, 0x01), }; static const struct regmap_irq bxtwc_regmap_irqs_bcu[] = { @@ -125,7 +127,7 @@ static const struct regmap_irq bxtwc_regmap_irqs_adc[] = { }; static const struct regmap_irq bxtwc_regmap_irqs_chgr[] = { - REGMAP_IRQ_REG(BXTWC_USBC_IRQ, 0, BIT(5)), + REGMAP_IRQ_REG(BXTWC_USBC_IRQ, 0, 0x20), REGMAP_IRQ_REG(BXTWC_CHGR0_IRQ, 0, 0x1f), REGMAP_IRQ_REG(BXTWC_CHGR1_IRQ, 1, 0x1f), }; @@ -144,7 +146,16 @@ static struct regmap_irq_chip bxtwc_regmap_irq_chip = { .mask_base = BXTWC_MIRQLVL1, .irqs = bxtwc_regmap_irqs, .num_irqs = ARRAY_SIZE(bxtwc_regmap_irqs), - .num_regs = 2, + .num_regs = 1, +}; + +static struct regmap_irq_chip bxtwc_regmap_irq_chip_pwrbtn = { + .name = "bxtwc_irq_chip_pwrbtn", + .status_base = BXTWC_PWRBTNIRQ, + .mask_base = BXTWC_MPWRBTNIRQ, + .irqs = bxtwc_regmap_irqs_pwrbtn, + .num_irqs = ARRAY_SIZE(bxtwc_regmap_irqs_pwrbtn), + .num_regs = 1, }; static struct regmap_irq_chip bxtwc_regmap_irq_chip_tmu = { @@ -472,6 +483,16 @@ static int bxtwc_probe(struct platform_device *pdev) return ret; } + ret = bxtwc_add_chained_irq_chip(pmic, pmic->irq_chip_data, + BXTWC_PWRBTN_LVL1_IRQ, + IRQF_ONESHOT, + &bxtwc_regmap_irq_chip_pwrbtn, + &pmic->irq_chip_data_pwrbtn); + if (ret) { + dev_err(&pdev->dev, "Failed to add PWRBTN IRQ chip\n"); + return ret; + } + ret = bxtwc_add_chained_irq_chip(pmic, pmic->irq_chip_data, BXTWC_TMU_LVL1_IRQ, IRQF_ONESHOT, diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index 5aacdb017a9f..806a4f095312 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -25,6 +25,7 @@ struct intel_soc_pmic { int irq; struct regmap *regmap; struct regmap_irq_chip_data *irq_chip_data; + struct regmap_irq_chip_data *irq_chip_data_pwrbtn; struct regmap_irq_chip_data *irq_chip_data_tmu; struct regmap_irq_chip_data *irq_chip_data_bcu; struct regmap_irq_chip_data *irq_chip_data_adc; From 0a6fa6119ab178a50dfb8c82921bac54b2982d56 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 5 Sep 2018 13:54:07 +0200 Subject: [PATCH 130/299] mfd: max8997: Enale irq-wakeup unconditionally [ Upstream commit efddff27c886e729a7f84a7205bd84d7d4af7336 ] IRQ wake up support for MAX8997 driver was initially configured by respective property in pdata. However, after the driver conversion to device-tree, setting it was left as 'todo'. Nowadays most of other PMIC MFD drivers initialized from device-tree assume that they can be an irq wakeup source, so enable it also for MAX8997. This fixes support for wakeup from MAX8997 RTC alarm. Signed-off-by: Marek Szyprowski Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/mfd/max8997.c | 8 +------- include/linux/mfd/max8997.h | 1 - 2 files changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/mfd/max8997.c b/drivers/mfd/max8997.c index 3f554c447521..d1495d76bf2c 100644 --- a/drivers/mfd/max8997.c +++ b/drivers/mfd/max8997.c @@ -153,12 +153,6 @@ static struct max8997_platform_data *max8997_i2c_parse_dt_pdata( pd->ono = irq_of_parse_and_map(dev->of_node, 1); - /* - * ToDo: the 'wakeup' member in the platform data is more of a linux - * specfic information. Hence, there is no binding for that yet and - * not parsed here. - */ - return pd; } @@ -246,7 +240,7 @@ static int max8997_i2c_probe(struct i2c_client *i2c, */ /* MAX8997 has a power button input. */ - device_init_wakeup(max8997->dev, pdata->wakeup); + device_init_wakeup(max8997->dev, true); return ret; diff --git a/include/linux/mfd/max8997.h b/include/linux/mfd/max8997.h index cf815577bd68..3ae1fe743bc3 100644 --- a/include/linux/mfd/max8997.h +++ b/include/linux/mfd/max8997.h @@ -178,7 +178,6 @@ struct max8997_led_platform_data { struct max8997_platform_data { /* IRQ */ int ono; - int wakeup; /* ---- PMIC ---- */ struct max8997_regulator_data *regulators; From c5621fbd656077c2d888d341059ce5a180c906bd Mon Sep 17 00:00:00 2001 From: Masahisa Kojima Date: Tue, 23 Oct 2018 20:24:26 +0900 Subject: [PATCH 131/299] net: socionext: Stop PHY before resetting netsec [ Upstream commit 8e850f25b5812aefedec6732732eb10e7b47cb5c ] In ndo_stop, driver resets the netsec ethernet controller IP. When the netsec IP is reset, HW running mode turns to NRM mode and driver has to wait until this mode transition completes. But mode transition to NRM will not complete if the PHY is in normal operation state. Netsec IP requires PHY is in power down state when it is reset. This modification stops the PHY before resetting netsec. Together with this modification, phy_addr is stored in netsec_priv structure because ndev->phydev is not yet ready in ndo_init. Fixes: 533dd11a12f6 ("net: socionext: Add Synquacer NetSec driver") Signed-off-by: Masahisa Kojima Signed-off-by: Yoshitoyo Osaki Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/socionext/netsec.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index d2caeb9edc04..28d582c18afb 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -274,6 +274,7 @@ struct netsec_priv { struct clk *clk; u32 msg_enable; u32 freq; + u32 phy_addr; bool rx_cksum_offload_flag; }; @@ -1346,11 +1347,11 @@ static int netsec_netdev_stop(struct net_device *ndev) netsec_uninit_pkt_dring(priv, NETSEC_RING_TX); netsec_uninit_pkt_dring(priv, NETSEC_RING_RX); - ret = netsec_reset_hardware(priv, false); - phy_stop(ndev->phydev); phy_disconnect(ndev->phydev); + ret = netsec_reset_hardware(priv, false); + pm_runtime_put_sync(priv->dev); return ret; @@ -1360,6 +1361,7 @@ static int netsec_netdev_init(struct net_device *ndev) { struct netsec_priv *priv = netdev_priv(ndev); int ret; + u16 data; ret = netsec_alloc_dring(priv, NETSEC_RING_TX); if (ret) @@ -1369,6 +1371,11 @@ static int netsec_netdev_init(struct net_device *ndev) if (ret) goto err1; + /* set phy power down */ + data = netsec_phy_read(priv->mii_bus, priv->phy_addr, MII_BMCR) | + BMCR_PDOWN; + netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR, data); + ret = netsec_reset_hardware(priv, true); if (ret) goto err2; @@ -1418,7 +1425,7 @@ static const struct net_device_ops netsec_netdev_ops = { }; static int netsec_of_probe(struct platform_device *pdev, - struct netsec_priv *priv) + struct netsec_priv *priv, u32 *phy_addr) { priv->phy_np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); if (!priv->phy_np) { @@ -1426,6 +1433,8 @@ static int netsec_of_probe(struct platform_device *pdev, return -EINVAL; } + *phy_addr = of_mdio_parse_addr(&pdev->dev, priv->phy_np); + priv->clk = devm_clk_get(&pdev->dev, NULL); /* get by 'phy_ref_clk' */ if (IS_ERR(priv->clk)) { dev_err(&pdev->dev, "phy_ref_clk not found\n"); @@ -1626,12 +1635,14 @@ static int netsec_probe(struct platform_device *pdev) } if (dev_of_node(&pdev->dev)) - ret = netsec_of_probe(pdev, priv); + ret = netsec_of_probe(pdev, priv, &phy_addr); else ret = netsec_acpi_probe(pdev, priv, &phy_addr); if (ret) goto free_ndev; + priv->phy_addr = phy_addr; + if (!priv->freq) { dev_err(&pdev->dev, "missing PHY reference clock frequency\n"); ret = -ENODEV; From 6c2075f792c6bf10809577bec6cf8d0d347ba056 Mon Sep 17 00:00:00 2001 From: Garry McNulty Date: Wed, 3 Oct 2018 20:51:21 +0100 Subject: [PATCH 132/299] fs/cifs: fix uninitialised variable warnings [ Upstream commit ef2298a06d012973bbc592b86fe5ff730d4d0c63 ] In some error conditions, resp_buftype can be passed uninitialised to free_rsp_buf(), potentially resulting in a spurious debug message. If resp_buftype randomly had the value 1 (CIFS_SMALL_BUFFER) then this would log a debug message. The rsp pointer is initialised to NULL so there is no other side-effect. Detected by CoverityScan, CID 1438585 ("Uninitialized scalar variable") Detected by CoverityScan, CID 1438667 ("Uninitialized scalar variable") Detected by CoverityScan, CID 1438764 ("Uninitialized scalar variable") Signed-off-by: Garry McNulty Signed-off-by: Steve French Reviewed-by: Aurelien Aptel Signed-off-by: Sasha Levin --- fs/cifs/smb2pdu.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index b1f5d0d28335..9194f17675c8 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2283,7 +2283,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, struct cifs_ses *ses = tcon->ses; struct kvec iov[SMB2_CREATE_IOV_SIZE]; struct kvec rsp_iov = {NULL, 0}; - int resp_buftype; + int resp_buftype = CIFS_NO_BUFFER; int rc = 0; int flags = 0; @@ -2570,7 +2570,7 @@ SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_ses *ses = tcon->ses; struct kvec iov[1]; struct kvec rsp_iov; - int resp_buftype; + int resp_buftype = CIFS_NO_BUFFER; int rc = 0; cifs_dbg(FYI, "Close\n"); @@ -2723,7 +2723,7 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon, struct kvec iov[1]; struct kvec rsp_iov; int rc = 0; - int resp_buftype; + int resp_buftype = CIFS_NO_BUFFER; struct cifs_ses *ses = tcon->ses; int flags = 0; From adcb6d9ff121bcff8365ab42321d71fbed4725ea Mon Sep 17 00:00:00 2001 From: Keiji Hayashibara Date: Wed, 24 Oct 2018 18:34:29 +0900 Subject: [PATCH 133/299] spi: uniphier: fix incorrect property items [ Upstream commit 3511ba7d4ca6f39e2d060bb94e42a41ad1fee7bf ] This commit fixes incorrect property because it was different from the actual. The parameters of '#address-cells' and '#size-cells' were removed, and 'interrupts', 'pinctrl-names' and 'pinctrl-0' were added. Fixes: 4dcd5c2781f3 ("spi: add DT bindings for UniPhier SPI controller") Signed-off-by: Keiji Hayashibara Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- .../devicetree/bindings/spi/spi-uniphier.txt | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/Documentation/devicetree/bindings/spi/spi-uniphier.txt b/Documentation/devicetree/bindings/spi/spi-uniphier.txt index 504a4ecfc7b1..b04e66a52de5 100644 --- a/Documentation/devicetree/bindings/spi/spi-uniphier.txt +++ b/Documentation/devicetree/bindings/spi/spi-uniphier.txt @@ -5,18 +5,20 @@ UniPhier SoCs have SCSSI which supports SPI single channel. Required properties: - compatible: should be "socionext,uniphier-scssi" - reg: address and length of the spi master registers - - #address-cells: must be <1>, see spi-bus.txt - - #size-cells: must be <0>, see spi-bus.txt - - clocks: A phandle to the clock for the device. - - resets: A phandle to the reset control for the device. + - interrupts: a single interrupt specifier + - pinctrl-names: should be "default" + - pinctrl-0: pin control state for the default mode + - clocks: a phandle to the clock for the device + - resets: a phandle to the reset control for the device Example: spi0: spi@54006000 { compatible = "socionext,uniphier-scssi"; reg = <0x54006000 0x100>; - #address-cells = <1>; - #size-cells = <0>; + interrupts = <0 39 4>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_spi0>; clocks = <&peri_clk 11>; resets = <&peri_rst 11>; }; From 58ceffabad41aaab4dcf68490b10133344a2377e Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 30 Aug 2018 23:16:13 +0900 Subject: [PATCH 134/299] selftests/ftrace: Fix to test kprobe $comm arg only if available [ Upstream commit 2452c96e617a0ff6fb2692e55217a3fa57a7322c ] Test $comm in kprobe-event argument syntax testcase only if it is supported on the kernel because $comm has been introduced 4.8 kernel. So on older stable kernel, it should be skipped. Signed-off-by: Masami Hiramatsu Signed-off-by: Shuah Khan (Samsung OSG) Signed-off-by: Sasha Levin --- .../selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc index d026ff4e562f..92ffb3bd33d8 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc @@ -78,8 +78,11 @@ test_badarg "\$stackp" "\$stack0+10" "\$stack1-10" echo "r ${PROBEFUNC} \$retval" > kprobe_events ! echo "p ${PROBEFUNC} \$retval" > kprobe_events +# $comm was introduced in 4.8, older kernels reject it. +if grep -A1 "fetcharg:" README | grep -q '\$comm' ; then : "Comm access" test_goodarg "\$comm" +fi : "Indirect memory access" test_goodarg "+0(${GOODREG})" "-0(${GOODREG})" "+10(\$stack)" \ From 74685702363cc13dac2915bf47b49fa18627c666 Mon Sep 17 00:00:00 2001 From: "Shuah Khan (Samsung OSG)" Date: Wed, 26 Sep 2018 13:07:11 -0600 Subject: [PATCH 135/299] selftests: watchdog: fix message when /dev/watchdog open fails [ Upstream commit 9a244229a4b850b11952a0df79607c69b18fd8df ] When /dev/watchdog open fails, watchdog exits with "watchdog not enabled" message. This is incorrect when open fails due to insufficient privilege. Fix message to clearly state the reason when open fails with EACCESS when a non-root user runs it. Signed-off-by: Shuah Khan (Samsung OSG) Signed-off-by: Sasha Levin --- tools/testing/selftests/watchdog/watchdog-test.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c index 6e290874b70e..e029e2017280 100644 --- a/tools/testing/selftests/watchdog/watchdog-test.c +++ b/tools/testing/selftests/watchdog/watchdog-test.c @@ -89,7 +89,13 @@ int main(int argc, char *argv[]) fd = open("/dev/watchdog", O_WRONLY); if (fd == -1) { - printf("Watchdog device not enabled.\n"); + if (errno == ENOENT) + printf("Watchdog device not enabled.\n"); + else if (errno == EACCES) + printf("Run watchdog as root.\n"); + else + printf("Watchdog device open failed %s\n", + strerror(errno)); exit(-1); } From 5802cb25de861943f88e96eb43a9aaf42544fb5b Mon Sep 17 00:00:00 2001 From: Jerry Hoemann Date: Wed, 26 Sep 2018 15:23:08 -0600 Subject: [PATCH 136/299] selftests: watchdog: Fix error message. [ Upstream commit 04d5e4bd37516ad60854eb74592c7dbddd75d277 ] Printf's say errno but print the string version of error. Make consistent. Signed-off-by: Jerry Hoemann Signed-off-by: Shuah Khan (Samsung OSG) Signed-off-by: Sasha Levin --- tools/testing/selftests/watchdog/watchdog-test.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c index e029e2017280..f1c6e025cbe5 100644 --- a/tools/testing/selftests/watchdog/watchdog-test.c +++ b/tools/testing/selftests/watchdog/watchdog-test.c @@ -109,7 +109,7 @@ int main(int argc, char *argv[]) printf("Last boot is caused by: %s.\n", (flags != 0) ? "Watchdog" : "Power-On-Reset"); else - printf("WDIOC_GETBOOTSTATUS errno '%s'\n", strerror(errno)); + printf("WDIOC_GETBOOTSTATUS error '%s'\n", strerror(errno)); break; case 'd': flags = WDIOS_DISABLECARD; @@ -117,7 +117,7 @@ int main(int argc, char *argv[]) if (!ret) printf("Watchdog card disabled.\n"); else - printf("WDIOS_DISABLECARD errno '%s'\n", strerror(errno)); + printf("WDIOS_DISABLECARD error '%s'\n", strerror(errno)); break; case 'e': flags = WDIOS_ENABLECARD; @@ -125,7 +125,7 @@ int main(int argc, char *argv[]) if (!ret) printf("Watchdog card enabled.\n"); else - printf("WDIOS_ENABLECARD errno '%s'\n", strerror(errno)); + printf("WDIOS_ENABLECARD error '%s'\n", strerror(errno)); break; case 'p': ping_rate = strtoul(optarg, NULL, 0); @@ -139,7 +139,7 @@ int main(int argc, char *argv[]) if (!ret) printf("Watchdog timeout set to %u seconds.\n", flags); else - printf("WDIOC_SETTIMEOUT errno '%s'\n", strerror(errno)); + printf("WDIOC_SETTIMEOUT error '%s'\n", strerror(errno)); break; default: usage(argv[0]); From c62be4108883a7aee896e4e1417a1e00cf0bb89a Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Tue, 16 Oct 2018 16:13:46 +0200 Subject: [PATCH 137/299] selftests: kvm: Fix -Wformat warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit fb363e2d20351e1d16629df19e7bce1a31b3227a ] Fixes the following warnings: dirty_log_test.c: In function ‘help’: dirty_log_test.c:216:9: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘int’ [-Wformat=] printf(" -i: specify iteration counts (default: %"PRIu64")\n", ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from include/test_util.h:18:0, from dirty_log_test.c:16: /usr/include/inttypes.h:105:34: note: format string is defined here # define PRIu64 __PRI64_PREFIX "u" dirty_log_test.c:218:9: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘int’ [-Wformat=] printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n", ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from include/test_util.h:18:0, from dirty_log_test.c:16: /usr/include/inttypes.h:105:34: note: format string is defined here # define PRIu64 __PRI64_PREFIX "u" Signed-off-by: Andrea Parri Signed-off-by: Shuah Khan (Samsung OSG) Signed-off-by: Sasha Levin --- tools/testing/selftests/kvm/dirty_log_test.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 0c2cdc105f96..a9c4b5e21d7e 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -31,9 +31,9 @@ /* How many pages to dirty for each guest loop */ #define TEST_PAGES_PER_LOOP 1024 /* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */ -#define TEST_HOST_LOOP_N 32 +#define TEST_HOST_LOOP_N 32UL /* Interval for each host loop (ms) */ -#define TEST_HOST_LOOP_INTERVAL 10 +#define TEST_HOST_LOOP_INTERVAL 10UL /* * Guest variables. We use these variables to share data between host From 51aa1a10fbac2faabcee67b882ca5bf8129cb1bb Mon Sep 17 00:00:00 2001 From: Peng Hao Date: Fri, 12 Oct 2018 03:53:50 +0800 Subject: [PATCH 138/299] selftests: fix warning: "_GNU_SOURCE" redefined [ Upstream commit 0387662d1b6c5ad2950d8e94d5e380af3f15c05c ] Makefile contains -D_GNU_SOURCE. remove define "_GNU_SOURCE" in c files. Signed-off-by: Peng Hao Signed-off-by: Shuah Khan (Samsung OSG) Signed-off-by: Sasha Levin --- tools/testing/selftests/proc/fd-001-lookup.c | 2 +- tools/testing/selftests/proc/fd-003-kthread.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/proc/fd-001-lookup.c b/tools/testing/selftests/proc/fd-001-lookup.c index a2010dfb2110..60d7948e7124 100644 --- a/tools/testing/selftests/proc/fd-001-lookup.c +++ b/tools/testing/selftests/proc/fd-001-lookup.c @@ -14,7 +14,7 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ // Test /proc/*/fd lookup. -#define _GNU_SOURCE + #undef NDEBUG #include #include diff --git a/tools/testing/selftests/proc/fd-003-kthread.c b/tools/testing/selftests/proc/fd-003-kthread.c index 1d659d55368c..dc591f97b63d 100644 --- a/tools/testing/selftests/proc/fd-003-kthread.c +++ b/tools/testing/selftests/proc/fd-003-kthread.c @@ -14,7 +14,7 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ // Test that /proc/$KERNEL_THREAD/fd/ is empty. -#define _GNU_SOURCE + #undef NDEBUG #include #include From 436e610bf195a59a9d5b1c47a75a8ebdd1f250bb Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Wed, 3 Oct 2018 23:47:34 +0300 Subject: [PATCH 139/299] thermal: rcar_thermal: fix duplicate IRQ request [ Upstream commit df016bbba63743bbef9ff5c6c282561211dd72cc ] The driver on R8A77995 requests the same IRQ twice since platform_get_resource() is always called for the 1st IRQ resource. Fixes: 1969d9dc2079 ("thermal: rcar_thermal: add r8a77995 support") Signed-off-by: Sergei Shtylyov Reviewed-by: Geert Uytterhoeven Reviewed-by: Simon Horman Reviewed-by: Daniel Lezcano Signed-off-by: Eduardo Valentin Signed-off-by: Sasha Levin --- drivers/thermal/rcar_thermal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c index 8df2ce94c28d..edaa4058686b 100644 --- a/drivers/thermal/rcar_thermal.c +++ b/drivers/thermal/rcar_thermal.c @@ -493,7 +493,7 @@ static int rcar_thermal_probe(struct platform_device *pdev) pm_runtime_get_sync(dev); for (i = 0; i < chip->nirqs; i++) { - irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + irq = platform_get_resource(pdev, IORESOURCE_IRQ, i); if (!irq) continue; if (!common->base) { From 3681b901e94a18e9fbe505f4c7f34536c931ce92 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 12 Oct 2018 09:20:15 +0200 Subject: [PATCH 140/299] thermal: rcar_thermal: Prevent hardware access during system suspend MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 3a31386217628ffe2491695be2db933c25dde785 ] On r8a7791/koelsch, sometimes the following message is printed during system suspend: rcar_thermal e61f0000.thermal: thermal sensor was broken This happens if the workqueue runs while the device is already suspended. Fix this by using the freezable system workqueue instead, cfr. commit 51e20d0e3a60cf46 ("thermal: Prevent polling from happening during system suspend"). Fixes: e0a5172e9eec7f0d ("thermal: rcar: add interrupt support") Signed-off-by: Geert Uytterhoeven Reviewed-by: Niklas Söderlund Signed-off-by: Eduardo Valentin Signed-off-by: Sasha Levin --- drivers/thermal/rcar_thermal.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c index edaa4058686b..4dc30e7890f6 100644 --- a/drivers/thermal/rcar_thermal.c +++ b/drivers/thermal/rcar_thermal.c @@ -434,8 +434,8 @@ static irqreturn_t rcar_thermal_irq(int irq, void *data) rcar_thermal_for_each_priv(priv, common) { if (rcar_thermal_had_changed(priv, status)) { rcar_thermal_irq_disable(priv); - schedule_delayed_work(&priv->work, - msecs_to_jiffies(300)); + queue_delayed_work(system_freezable_wq, &priv->work, + msecs_to_jiffies(300)); } } From 7b557dbdc51947b92dcfe8f13d6fd59d2353d2d9 Mon Sep 17 00:00:00 2001 From: Tristram Ha Date: Wed, 24 Oct 2018 14:51:23 -0700 Subject: [PATCH 141/299] net: ethernet: cadence: fix socket buffer corruption problem [ Upstream commit 899ecaedd15599c22553d158f53b127cc1632dc2 ] Socket buffer is not re-created when headroom is 2 and tailroom is 1. Signed-off-by: Tristram Ha Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/cadence/macb_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 74eeb3a985bf..f175b20ac510 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1721,7 +1721,7 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) padlen = 0; /* No room for FCS, need to reallocate skb. */ else - padlen = ETH_FCS_LEN - tailroom; + padlen = ETH_FCS_LEN; } else { /* Add room for FCS. */ padlen += ETH_FCS_LEN; From 8044e741eee42db4a08f1d284144ef2d482996be Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Wed, 24 Oct 2018 20:15:17 +0900 Subject: [PATCH 142/299] bpf: devmap: fix wrong interface selection in notifier_call [ Upstream commit f592f804831f1cf9d1f9966f58c80f150e6829b5 ] The dev_map_notification() removes interface in devmap if unregistering interface's ifindex is same. But only checking ifindex is not enough because other netns can have same ifindex. so that wrong interface selection could occurred. Hence netdev pointer comparison code is added. v2: compare netdev pointer instead of using net_eq() (Daniel Borkmann) v1: Initial patch Fixes: 2ddf71e23cc2 ("net: add notifier hooks for devmap bpf map") Signed-off-by: Taehee Yoo Acked-by: Song Liu Signed-off-by: Daniel Borkmann Signed-off-by: Sasha Levin --- kernel/bpf/devmap.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index fc500ca464d0..1defea4b2755 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -520,8 +520,7 @@ static int dev_map_notification(struct notifier_block *notifier, struct bpf_dtab_netdev *dev, *odev; dev = READ_ONCE(dtab->netdev_map[i]); - if (!dev || - dev->dev->ifindex != netdev->ifindex) + if (!dev || netdev != dev->dev) continue; odev = cmpxchg(&dtab->netdev_map[i], dev, NULL); if (dev == odev) From 54299e1cf3793df8fe266dac00f7083b1378b08f Mon Sep 17 00:00:00 2001 From: Martin Lau Date: Wed, 24 Oct 2018 20:42:25 +0000 Subject: [PATCH 143/299] bpf, btf: fix a missing check bug in btf_parse [ Upstream commit 4a6998aff82a20a1aece86a186d8e5263f8b2315 ] Wenwen Wang reported: In btf_parse(), the header of the user-space btf data 'btf_data' is firstly parsed and verified through btf_parse_hdr(). In btf_parse_hdr(), the header is copied from user-space 'btf_data' to kernel-space 'btf->hdr' and then verified. If no error happens during the verification process, the whole data of 'btf_data', including the header, is then copied to 'data' in btf_parse(). It is obvious that the header is copied twice here. More importantly, no check is enforced after the second copy to make sure the headers obtained in these two copies are same. Given that 'btf_data' resides in the user space, a malicious user can race to modify the header between these two copies. By doing so, the user can inject inconsistent data, which can cause undefined behavior of the kernel and introduce potential security risk. This issue is similar to the one fixed in commit 8af03d1ae2e1 ("bpf: btf: Fix a missing check bug"). To fix it, this patch copies the user 'btf_data' *before* parsing / verifying the BTF header. Fixes: 69b693f0aefa ("bpf: btf: Introduce BPF Type Format (BTF)") Signed-off-by: Martin KaFai Lau Co-developed-by: Wenwen Wang Acked-by: Song Liu Signed-off-by: Daniel Borkmann Signed-off-by: Sasha Levin --- kernel/bpf/btf.c | 55 ++++++++++++++++++++++-------------------------- 1 file changed, 25 insertions(+), 30 deletions(-) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 378cef70341c..cfa27b7d1168 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -2067,50 +2067,44 @@ static int btf_check_sec_info(struct btf_verifier_env *env, return 0; } -static int btf_parse_hdr(struct btf_verifier_env *env, void __user *btf_data, - u32 btf_data_size) +static int btf_parse_hdr(struct btf_verifier_env *env) { + u32 hdr_len, hdr_copy, btf_data_size; const struct btf_header *hdr; - u32 hdr_len, hdr_copy; - /* - * Minimal part of the "struct btf_header" that - * contains the hdr_len. - */ - struct btf_min_header { - u16 magic; - u8 version; - u8 flags; - u32 hdr_len; - } __user *min_hdr; struct btf *btf; int err; btf = env->btf; - min_hdr = btf_data; + btf_data_size = btf->data_size; - if (btf_data_size < sizeof(*min_hdr)) { + if (btf_data_size < + offsetof(struct btf_header, hdr_len) + sizeof(hdr->hdr_len)) { btf_verifier_log(env, "hdr_len not found"); return -EINVAL; } - if (get_user(hdr_len, &min_hdr->hdr_len)) - return -EFAULT; - + hdr = btf->data; + hdr_len = hdr->hdr_len; if (btf_data_size < hdr_len) { btf_verifier_log(env, "btf_header not found"); return -EINVAL; } - err = bpf_check_uarg_tail_zero(btf_data, sizeof(btf->hdr), hdr_len); - if (err) { - if (err == -E2BIG) - btf_verifier_log(env, "Unsupported btf_header"); - return err; + /* Ensure the unsupported header fields are zero */ + if (hdr_len > sizeof(btf->hdr)) { + u8 *expected_zero = btf->data + sizeof(btf->hdr); + u8 *end = btf->data + hdr_len; + + for (; expected_zero < end; expected_zero++) { + if (*expected_zero) { + btf_verifier_log(env, "Unsupported btf_header"); + return -E2BIG; + } + } } hdr_copy = min_t(u32, hdr_len, sizeof(btf->hdr)); - if (copy_from_user(&btf->hdr, btf_data, hdr_copy)) - return -EFAULT; + memcpy(&btf->hdr, btf->data, hdr_copy); hdr = &btf->hdr; @@ -2186,10 +2180,6 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, } env->btf = btf; - err = btf_parse_hdr(env, btf_data, btf_data_size); - if (err) - goto errout; - data = kvmalloc(btf_data_size, GFP_KERNEL | __GFP_NOWARN); if (!data) { err = -ENOMEM; @@ -2198,13 +2188,18 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, btf->data = data; btf->data_size = btf_data_size; - btf->nohdr_data = btf->data + btf->hdr.hdr_len; if (copy_from_user(data, btf_data, btf_data_size)) { err = -EFAULT; goto errout; } + err = btf_parse_hdr(env); + if (err) + goto errout; + + btf->nohdr_data = btf->data + btf->hdr.hdr_len; + err = btf_parse_str_sec(env); if (err) goto errout; From 4e4cad4365e0e2458c0ae48b2a9c8c0f0207f31f Mon Sep 17 00:00:00 2001 From: Felipe Rechia Date: Wed, 24 Oct 2018 10:57:22 -0300 Subject: [PATCH 144/299] powerpc/process: Fix flush_all_to_thread for SPE [ Upstream commit e901378578c62202594cba0f6c076f3df365ec91 ] Fix a bug introduced by the creation of flush_all_to_thread() for processors that have SPE (Signal Processing Engine) and use it to compute floating-point operations. >From userspace perspective, the problem was seen in attempts of computing floating-point operations which should generate exceptions. For example: fork(); float x = 0.0 / 0.0; isnan(x); // forked process returns False (should be True) The operation above also should always cause the SPEFSCR FINV bit to be set. However, the SPE floating-point exceptions were turned off after a fork(). Kernel versions prior to the bug used flush_spe_to_thread(), which first saves SPEFSCR register values in tsk->thread and then calls giveup_spe(tsk). After commit 579e633e764e, the save_all() function was called first to giveup_spe(), and then the SPEFSCR register values were saved in tsk->thread. This would save the SPEFSCR register values after disabling SPE for that thread, causing the bug described above. Fixes 579e633e764e ("powerpc: create flush_all_to_thread()") Signed-off-by: Felipe Rechia Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- arch/powerpc/kernel/process.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 909c9407e392..02b69a68139c 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -575,12 +575,11 @@ void flush_all_to_thread(struct task_struct *tsk) if (tsk->thread.regs) { preempt_disable(); BUG_ON(tsk != current); - save_all(tsk); - #ifdef CONFIG_SPE if (tsk->thread.regs->msr & MSR_SPE) tsk->thread.spefscr = mfspr(SPRN_SPEFSCR); #endif + save_all(tsk); preempt_enable(); } From b84e965c7edb55405956dbbec93a0754a97c4526 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 26 Oct 2018 15:39:49 -0700 Subject: [PATCH 145/299] sparc64: Rework xchg() definition to avoid warnings. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 6c2fc9cddc1ffdef8ada1dc8404e5affae849953 ] Such as: fs/ocfs2/file.c: In function ‘ocfs2_file_write_iter’: ./arch/sparc/include/asm/cmpxchg_64.h:55:22: warning: value computed is not used [-Wunused-value] #define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr)))) and drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c: In function ‘ixgbevf_xdp_setup’: ./arch/sparc/include/asm/cmpxchg_64.h:55:22: warning: value computed is not used [-Wunused-value] #define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr)))) Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- arch/sparc/include/asm/cmpxchg_64.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h index f71ef3729888..316faa0130ba 100644 --- a/arch/sparc/include/asm/cmpxchg_64.h +++ b/arch/sparc/include/asm/cmpxchg_64.h @@ -52,7 +52,12 @@ static inline unsigned long xchg64(__volatile__ unsigned long *m, unsigned long return val; } -#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr)))) +#define xchg(ptr,x) \ +({ __typeof__(*(ptr)) __ret; \ + __ret = (__typeof__(*(ptr))) \ + __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))); \ + __ret; \ +}) void __xchg_called_with_bad_pointer(void); From 99b3146b799ab983b1b639334dd0a2eba40844ca Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 26 Oct 2018 15:02:30 -0700 Subject: [PATCH 146/299] arm64: lib: use C string functions with KASAN enabled [ Upstream commit 19a2ca0fb560fd7be7b5293c6b652c6d6078dcde ] ARM64 has asm implementation of memchr(), memcmp(), str[r]chr(), str[n]cmp(), str[n]len(). KASAN don't see memory accesses in asm code, thus it can potentially miss many bugs. Ifdef out __HAVE_ARCH_* defines of these functions when KASAN is enabled, so the generic implementations from lib/string.c will be used. We can't just remove the asm functions because efistub uses them. And we can't have two non-weak functions either, so declare the asm functions as weak. Link: http://lkml.kernel.org/r/20180920135631.23833-2-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin Reported-by: Kyeongdon Kim Cc: Alexander Potapenko Cc: Ard Biesheuvel Cc: Dmitry Vyukov Cc: Mark Rutland Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- arch/arm64/include/asm/string.h | 14 ++++++++------ arch/arm64/kernel/arm64ksyms.c | 7 +++++-- arch/arm64/lib/memchr.S | 2 +- arch/arm64/lib/memcmp.S | 2 +- arch/arm64/lib/strchr.S | 2 +- arch/arm64/lib/strcmp.S | 2 +- arch/arm64/lib/strlen.S | 2 +- arch/arm64/lib/strncmp.S | 2 +- arch/arm64/lib/strnlen.S | 2 +- arch/arm64/lib/strrchr.S | 2 +- 10 files changed, 21 insertions(+), 16 deletions(-) diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h index dd95d33a5bd5..03a6c256b7ec 100644 --- a/arch/arm64/include/asm/string.h +++ b/arch/arm64/include/asm/string.h @@ -16,6 +16,7 @@ #ifndef __ASM_STRING_H #define __ASM_STRING_H +#ifndef CONFIG_KASAN #define __HAVE_ARCH_STRRCHR extern char *strrchr(const char *, int c); @@ -34,6 +35,13 @@ extern __kernel_size_t strlen(const char *); #define __HAVE_ARCH_STRNLEN extern __kernel_size_t strnlen(const char *, __kernel_size_t); +#define __HAVE_ARCH_MEMCMP +extern int memcmp(const void *, const void *, size_t); + +#define __HAVE_ARCH_MEMCHR +extern void *memchr(const void *, int, __kernel_size_t); +#endif + #define __HAVE_ARCH_MEMCPY extern void *memcpy(void *, const void *, __kernel_size_t); extern void *__memcpy(void *, const void *, __kernel_size_t); @@ -42,16 +50,10 @@ extern void *__memcpy(void *, const void *, __kernel_size_t); extern void *memmove(void *, const void *, __kernel_size_t); extern void *__memmove(void *, const void *, __kernel_size_t); -#define __HAVE_ARCH_MEMCHR -extern void *memchr(const void *, int, __kernel_size_t); - #define __HAVE_ARCH_MEMSET extern void *memset(void *, int, __kernel_size_t); extern void *__memset(void *, int, __kernel_size_t); -#define __HAVE_ARCH_MEMCMP -extern int memcmp(const void *, const void *, size_t); - #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE #define __HAVE_ARCH_MEMCPY_FLUSHCACHE void memcpy_flushcache(void *dst, const void *src, size_t cnt); diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c index d894a20b70b2..72f63a59b008 100644 --- a/arch/arm64/kernel/arm64ksyms.c +++ b/arch/arm64/kernel/arm64ksyms.c @@ -44,20 +44,23 @@ EXPORT_SYMBOL(__arch_copy_in_user); EXPORT_SYMBOL(memstart_addr); /* string / mem functions */ +#ifndef CONFIG_KASAN EXPORT_SYMBOL(strchr); EXPORT_SYMBOL(strrchr); EXPORT_SYMBOL(strcmp); EXPORT_SYMBOL(strncmp); EXPORT_SYMBOL(strlen); EXPORT_SYMBOL(strnlen); +EXPORT_SYMBOL(memcmp); +EXPORT_SYMBOL(memchr); +#endif + EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(__memset); EXPORT_SYMBOL(__memcpy); EXPORT_SYMBOL(__memmove); -EXPORT_SYMBOL(memchr); -EXPORT_SYMBOL(memcmp); /* atomic bitops */ EXPORT_SYMBOL(set_bit); diff --git a/arch/arm64/lib/memchr.S b/arch/arm64/lib/memchr.S index 4444c1d25f4b..0f164a4baf52 100644 --- a/arch/arm64/lib/memchr.S +++ b/arch/arm64/lib/memchr.S @@ -30,7 +30,7 @@ * Returns: * x0 - address of first occurrence of 'c' or 0 */ -ENTRY(memchr) +WEAK(memchr) and w1, w1, #0xff 1: subs x2, x2, #1 b.mi 2f diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S index 2a4e239bd17a..fb295f52e9f8 100644 --- a/arch/arm64/lib/memcmp.S +++ b/arch/arm64/lib/memcmp.S @@ -58,7 +58,7 @@ pos .req x11 limit_wd .req x12 mask .req x13 -ENTRY(memcmp) +WEAK(memcmp) cbz limit, .Lret0 eor tmp1, src1, src2 tst tmp1, #7 diff --git a/arch/arm64/lib/strchr.S b/arch/arm64/lib/strchr.S index dae0cf5591f9..7c83091d1bcd 100644 --- a/arch/arm64/lib/strchr.S +++ b/arch/arm64/lib/strchr.S @@ -29,7 +29,7 @@ * Returns: * x0 - address of first occurrence of 'c' or 0 */ -ENTRY(strchr) +WEAK(strchr) and w1, w1, #0xff 1: ldrb w2, [x0], #1 cmp w2, w1 diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S index 471fe61760ef..7d5d15398bfb 100644 --- a/arch/arm64/lib/strcmp.S +++ b/arch/arm64/lib/strcmp.S @@ -60,7 +60,7 @@ tmp3 .req x9 zeroones .req x10 pos .req x11 -ENTRY(strcmp) +WEAK(strcmp) eor tmp1, src1, src2 mov zeroones, #REP8_01 tst tmp1, #7 diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S index 55ccc8e24c08..8e0b14205dcb 100644 --- a/arch/arm64/lib/strlen.S +++ b/arch/arm64/lib/strlen.S @@ -56,7 +56,7 @@ pos .req x12 #define REP8_7f 0x7f7f7f7f7f7f7f7f #define REP8_80 0x8080808080808080 -ENTRY(strlen) +WEAK(strlen) mov zeroones, #REP8_01 bic src, srcin, #15 ands tmp1, srcin, #15 diff --git a/arch/arm64/lib/strncmp.S b/arch/arm64/lib/strncmp.S index e267044761c6..66bd145935d9 100644 --- a/arch/arm64/lib/strncmp.S +++ b/arch/arm64/lib/strncmp.S @@ -64,7 +64,7 @@ limit_wd .req x13 mask .req x14 endloop .req x15 -ENTRY(strncmp) +WEAK(strncmp) cbz limit, .Lret0 eor tmp1, src1, src2 mov zeroones, #REP8_01 diff --git a/arch/arm64/lib/strnlen.S b/arch/arm64/lib/strnlen.S index eae38da6e0bb..355be04441fe 100644 --- a/arch/arm64/lib/strnlen.S +++ b/arch/arm64/lib/strnlen.S @@ -59,7 +59,7 @@ limit_wd .req x14 #define REP8_7f 0x7f7f7f7f7f7f7f7f #define REP8_80 0x8080808080808080 -ENTRY(strnlen) +WEAK(strnlen) cbz limit, .Lhit_limit mov zeroones, #REP8_01 bic src, srcin, #15 diff --git a/arch/arm64/lib/strrchr.S b/arch/arm64/lib/strrchr.S index f8e2784d5752..ea84924d5990 100644 --- a/arch/arm64/lib/strrchr.S +++ b/arch/arm64/lib/strrchr.S @@ -29,7 +29,7 @@ * Returns: * x0 - address of last occurrence of 'c' or 0 */ -ENTRY(strrchr) +WEAK(strrchr) mov x3, #0 and w1, w1, #0xff 1: ldrb w2, [x0], #1 From bcba80f38a003f0cfcebb8502ab81cb043a68977 Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Fri, 26 Oct 2018 15:02:52 -0700 Subject: [PATCH 147/299] fs/ocfs2/dlm/dlmdebug.c: fix a sleep-in-atomic-context bug in dlm_print_one_mle() [ Upstream commit 999865764f5f128896402572b439269acb471022 ] The kernel module may sleep with holding a spinlock. The function call paths (from bottom to top) in Linux-4.16 are: [FUNC] get_zeroed_page(GFP_NOFS) fs/ocfs2/dlm/dlmdebug.c, 332: get_zeroed_page in dlm_print_one_mle fs/ocfs2/dlm/dlmmaster.c, 240: dlm_print_one_mle in __dlm_put_mle fs/ocfs2/dlm/dlmmaster.c, 255: __dlm_put_mle in dlm_put_mle fs/ocfs2/dlm/dlmmaster.c, 254: spin_lock in dlm_put_ml [FUNC] get_zeroed_page(GFP_NOFS) fs/ocfs2/dlm/dlmdebug.c, 332: get_zeroed_page in dlm_print_one_mle fs/ocfs2/dlm/dlmmaster.c, 240: dlm_print_one_mle in __dlm_put_mle fs/ocfs2/dlm/dlmmaster.c, 222: __dlm_put_mle in dlm_put_mle_inuse fs/ocfs2/dlm/dlmmaster.c, 219: spin_lock in dlm_put_mle_inuse To fix this bug, GFP_NOFS is replaced with GFP_ATOMIC. This bug is found by my static analysis tool DSAC. Link: http://lkml.kernel.org/r/20180901112528.27025-1-baijiaju1990@gmail.com Signed-off-by: Jia-Ju Bai Reviewed-by: Andrew Morton Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Joseph Qi Cc: Changwei Ge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/ocfs2/dlm/dlmdebug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index 9b984cae4c4e..1d6dc8422899 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -329,7 +329,7 @@ void dlm_print_one_mle(struct dlm_master_list_entry *mle) { char *buf; - buf = (char *) get_zeroed_page(GFP_NOFS); + buf = (char *) get_zeroed_page(GFP_ATOMIC); if (buf) { dump_mle(mle, buf, PAGE_SIZE - 1); free_page((unsigned long)buf); From 2d9d6c099eaf91523c7f73ec84c523afd196b18f Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 26 Oct 2018 15:09:45 -0700 Subject: [PATCH 148/299] mm/page-writeback.c: fix range_cyclic writeback vs writepages deadlock [ Upstream commit 64081362e8ff4587b4554087f3cfc73d3e0a4cd7 ] We've recently seen a workload on XFS filesystems with a repeatable deadlock between background writeback and a multi-process application doing concurrent writes and fsyncs to a small range of a file. range_cyclic writeback Process 1 Process 2 xfs_vm_writepages write_cache_pages writeback_index = 2 cycled = 0 .... find page 2 dirty lock Page 2 ->writepage page 2 writeback page 2 clean page 2 added to bio no more pages write() locks page 1 dirties page 1 locks page 2 dirties page 1 fsync() .... xfs_vm_writepages write_cache_pages start index 0 find page 1 towrite lock Page 1 ->writepage page 1 writeback page 1 clean page 1 added to bio find page 2 towrite lock Page 2 page 2 is writeback write() locks page 1 dirties page 1 fsync() .... xfs_vm_writepages write_cache_pages start index 0 !done && !cycled sets index to 0, restarts lookup find page 1 dirty find page 1 towrite lock Page 1 page 1 is writeback lock Page 1 DEADLOCK because: - process 1 needs page 2 writeback to complete to make enough progress to issue IO pending for page 1 - writeback needs page 1 writeback to complete so process 2 can progress and unlock the page it is blocked on, then it can issue the IO pending for page 2 - process 2 can't make progress until process 1 issues IO for page 1 The underlying cause of the problem here is that range_cyclic writeback is processing pages in descending index order as we hold higher index pages in a structure controlled from above write_cache_pages(). The write_cache_pages() caller needs to be able to submit these pages for IO before write_cache_pages restarts writeback at mapping index 0 to avoid wcp inverting the page lock/writeback wait order. generic_writepages() is not susceptible to this bug as it has no private context held across write_cache_pages() - filesystems using this infrastructure always submit pages in ->writepage immediately and so there is no problem with range_cyclic going back to mapping index 0. However: mpage_writepages() has a private bio context, exofs_writepages() has page_collect fuse_writepages() has fuse_fill_wb_data nfs_writepages() has nfs_pageio_descriptor xfs_vm_writepages() has xfs_writepage_ctx All of these ->writepages implementations can hold pages under writeback in their private structures until write_cache_pages() returns, and hence they are all susceptible to this deadlock. Also worth noting is that ext4 has it's own bastardised version of write_cache_pages() and so it /may/ have an equivalent deadlock. I looked at the code long enough to understand that it has a similar retry loop for range_cyclic writeback reaching the end of the file and then promptly ran away before my eyes bled too much. I'll leave it for the ext4 developers to determine if their code is actually has this deadlock and how to fix it if it has. There's a few ways I can see avoid this deadlock. There's probably more, but these are the first I've though of: 1. get rid of range_cyclic altogether 2. range_cyclic always stops at EOF, and we start again from writeback index 0 on the next call into write_cache_pages() 2a. wcp also returns EAGAIN to ->writepages implementations to indicate range cyclic has hit EOF. writepages implementations can then flush the current context and call wpc again to continue. i.e. lift the retry into the ->writepages implementation 3. range_cyclic uses trylock_page() rather than lock_page(), and it skips pages it can't lock without blocking. It will already do this for pages under writeback, so this seems like a no-brainer 3a. all non-WB_SYNC_ALL writeback uses trylock_page() to avoid blocking as per pages under writeback. I don't think #1 is an option - range_cyclic prevents frequently dirtied lower file offset from starving background writeback of rarely touched higher file offsets. #2 is simple, and I don't think it will have any impact on performance as going back to the start of the file implies an immediate seek. We'll have exactly the same number of seeks if we switch writeback to another inode, and then come back to this one later and restart from index 0. #2a is pretty much "status quo without the deadlock". Moving the retry loop up into the wcp caller means we can issue IO on the pending pages before calling wcp again, and so avoid locking or waiting on pages in the wrong order. I'm not convinced we need to do this given that we get the same thing from #2 on the next writeback call from the writeback infrastructure. #3 is really just a band-aid - it doesn't fix the access/wait inversion problem, just prevents it from becoming a deadlock situation. I'd prefer we fix the inversion, not sweep it under the carpet like this. #3a is really an optimisation that just so happens to include the band-aid fix of #3. So it seems that the simplest way to fix this issue is to implement solution #2 Link: http://lkml.kernel.org/r/20181005054526.21507-1-david@fromorbit.com Signed-off-by: Dave Chinner Reviewed-by: Jan Kara Cc: Nicholas Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- mm/page-writeback.c | 33 +++++++++++++++------------------ 1 file changed, 15 insertions(+), 18 deletions(-) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index ea4fd3af3b4b..43df0c52e1cc 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2149,6 +2149,13 @@ EXPORT_SYMBOL(tag_pages_for_writeback); * not miss some pages (e.g., because some other process has cleared TOWRITE * tag we set). The rule we follow is that TOWRITE tag can be cleared only * by the process clearing the DIRTY tag (and submitting the page for IO). + * + * To avoid deadlocks between range_cyclic writeback and callers that hold + * pages in PageWriteback to aggregate IO until write_cache_pages() returns, + * we do not loop back to the start of the file. Doing so causes a page + * lock/page writeback access order inversion - we should only ever lock + * multiple pages in ascending page->index order, and looping back to the start + * of the file violates that rule and causes deadlocks. */ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, @@ -2163,7 +2170,6 @@ int write_cache_pages(struct address_space *mapping, pgoff_t index; pgoff_t end; /* Inclusive */ pgoff_t done_index; - int cycled; int range_whole = 0; int tag; @@ -2171,23 +2177,17 @@ int write_cache_pages(struct address_space *mapping, if (wbc->range_cyclic) { writeback_index = mapping->writeback_index; /* prev offset */ index = writeback_index; - if (index == 0) - cycled = 1; - else - cycled = 0; end = -1; } else { index = wbc->range_start >> PAGE_SHIFT; end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; - cycled = 1; /* ignore range_cyclic tests */ } if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag = PAGECACHE_TAG_TOWRITE; else tag = PAGECACHE_TAG_DIRTY; -retry: if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag_pages_for_writeback(mapping, index, end); done_index = index; @@ -2279,17 +2279,14 @@ continue_unlock: pagevec_release(&pvec); cond_resched(); } - if (!cycled && !done) { - /* - * range_cyclic: - * We hit the last page and there is more work to be done: wrap - * back to the start of the file - */ - cycled = 1; - index = 0; - end = writeback_index - 1; - goto retry; - } + + /* + * If we hit the last page and there is more work to be done: wrap + * back the index back to the start of the file for the next + * time we are called. + */ + if (wbc->range_cyclic && !done) + done_index = 0; if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = done_index; From ac1cad79bcad463ff2c886abf613dd0bc273ac3f Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 26 Oct 2018 15:09:59 -0700 Subject: [PATCH 149/299] tools/testing/selftests/vm/gup_benchmark.c: fix 'write' flag usage [ Upstream commit 319e0bec1aecb36c5ac6d23812af487ff2c8f47f ] If the '-w' parameter was provided, the benchmark would exit due to a mssing 'break'. Link: http://lkml.kernel.org/r/20181010195605.10689-3-keith.busch@intel.com Signed-off-by: Keith Busch Acked-by: Kirill A. Shutemov Reviewed-by: Andrew Morton Cc: Dave Hansen Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- tools/testing/selftests/vm/gup_benchmark.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c index 9601bc24454d..17da711f26af 100644 --- a/tools/testing/selftests/vm/gup_benchmark.c +++ b/tools/testing/selftests/vm/gup_benchmark.c @@ -51,6 +51,7 @@ int main(int argc, char **argv) break; case 'w': write = 1; + break; default: return -1; } From 4291e97c69f658d3d6ba1720d3c2fc820a1721aa Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 26 Oct 2018 15:10:36 -0700 Subject: [PATCH 150/299] mm: thp: fix MADV_DONTNEED vs migrate_misplaced_transhuge_page race condition [ Upstream commit d7c3393413fe7e7dc54498ea200ea94742d61e18 ] Patch series "migrate_misplaced_transhuge_page race conditions". Aaron found a new instance of the THP MADV_DONTNEED race against pmdp_clear_flush* variants, that was apparently left unfixed. While looking into the race found by Aaron, I may have found two more issues in migrate_misplaced_transhuge_page. These race conditions would not cause kernel instability, but they'd corrupt userland data or leave data non zero after MADV_DONTNEED. I did only minor testing, and I don't expect to be able to reproduce this (especially the lack of ->invalidate_range before migrate_page_copy, requires the latest iommu hardware or infiniband to reproduce). The last patch is noop for x86 and it needs further review from maintainers of archs that implement flush_cache_range() (not in CC yet). To avoid confusion, it's not the first patch that introduces the bug fixed in the second patch, even before removing the pmdp_huge_clear_flush_notify, that _notify suffix was called after migrate_page_copy already run. This patch (of 3): This is a corollary of ced108037c2aa ("thp: fix MADV_DONTNEED vs. numa balancing race"), 58ceeb6bec8 ("thp: fix MADV_DONTNEED vs. MADV_FREE race") and 5b7abeae3af8c ("thp: fix MADV_DONTNEED vs clear soft dirty race). When the above three fixes where posted Dave asked https://lkml.kernel.org/r/929b3844-aec2-0111-fef7-8002f9d4e2b9@intel.com but apparently this was missed. The pmdp_clear_flush* in migrate_misplaced_transhuge_page() was introduced in a54a407fbf7 ("mm: Close races between THP migration and PMD numa clearing"). The important part of such commit is only the part where the page lock is not released until the first do_huge_pmd_numa_page() finished disarming the pagenuma/protnone. The addition of pmdp_clear_flush() wasn't beneficial to such commit and there's no commentary about such an addition either. I guess the pmdp_clear_flush() in such commit was added just in case for safety, but it ended up introducing the MADV_DONTNEED race condition found by Aaron. At that point in time nobody thought of such kind of MADV_DONTNEED race conditions yet (they were fixed later) so the code may have looked more robust by adding the pmdp_clear_flush(). This specific race condition won't destabilize the kernel, but it can confuse userland because after MADV_DONTNEED the memory won't be zeroed out. This also optimizes the code and removes a superfluous TLB flush. [akpm@linux-foundation.org: reflow comment to 80 cols, fix grammar and typo (beacuse)] Link: http://lkml.kernel.org/r/20181013002430.698-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Reported-by: Aaron Tomlin Acked-by: Mel Gorman Acked-by: Kirill A. Shutemov Cc: Jerome Glisse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- mm/migrate.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/mm/migrate.c b/mm/migrate.c index 0c48191a9036..4d3588c01203 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2048,15 +2048,26 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); /* - * Clear the old entry under pagetable lock and establish the new PTE. - * Any parallel GUP will either observe the old page blocking on the - * page lock, block on the page table lock or observe the new page. - * The SetPageUptodate on the new page and page_add_new_anon_rmap - * guarantee the copy is visible before the pagetable update. + * Overwrite the old entry under pagetable lock and establish + * the new PTE. Any parallel GUP will either observe the old + * page blocking on the page lock, block on the page table + * lock or observe the new page. The SetPageUptodate on the + * new page and page_add_new_anon_rmap guarantee the copy is + * visible before the pagetable update. */ flush_cache_range(vma, mmun_start, mmun_end); page_add_anon_rmap(new_page, vma, mmun_start, true); - pmdp_huge_clear_flush_notify(vma, mmun_start, pmd); + /* + * At this point the pmd is numa/protnone (i.e. non present) and the TLB + * has already been flushed globally. So no TLB can be currently + * caching this non present pmd mapping. There's no need to clear the + * pmd before doing set_pmd_at(), nor to flush the TLB after + * set_pmd_at(). Clearing the pmd here would introduce a race + * condition against MADV_DONTNEED, because MADV_DONTNEED only holds the + * mmap_sem for reading. If the pmd is set to NULL at any given time, + * MADV_DONTNEED won't wait on the pmd lock and it'll skip clearing this + * pmd. + */ set_pmd_at(mm, mmun_start, pmd, entry); update_mmu_cache_pmd(vma, address, &entry); @@ -2070,7 +2081,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, * No need to double call mmu_notifier->invalidate_range() callback as * the above pmdp_huge_clear_flush_notify() did already call it. */ - mmu_notifier_invalidate_range_only_end(mm, mmun_start, mmun_end); + mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); /* Take an "isolate" reference and put new page on the LRU. */ get_page(new_page); From f5bdad7106fc509f27a627a94671ef2dd7136021 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Sun, 28 Oct 2018 09:33:09 +0100 Subject: [PATCH 151/299] macsec: update operstate when lower device changes [ Upstream commit e6ac075882b2afcdf2d5ab328ce4ab42a1eb9593 ] Like all other virtual devices (macvlan, vlan), the operstate of a macsec device should match the state of its lower device. This is done by calling netif_stacked_transfer_operstate from its netdevice notifier. We also need to call netif_stacked_transfer_operstate when a new macsec device is created, so that its operstate is set properly. This is only relevant when we try to bring the device up directly when we create it. Radu Rendec proposed a similar patch, inspired from the 802.1q driver, that included changing the administrative state of the macsec device, instead of just the operstate. This version is similar to what the macvlan driver does, and updates only the operstate. Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Reported-by: Radu Rendec Reported-by: Patrick Talbert Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/macsec.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 05115fb0c97a..50acd8c9d7f5 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3305,6 +3305,9 @@ static int macsec_newlink(struct net *net, struct net_device *dev, if (err < 0) goto del_dev; + netif_stacked_transfer_operstate(real_dev, dev); + linkwatch_fire_event(dev); + macsec_generation++; return 0; @@ -3489,6 +3492,20 @@ static int macsec_notify(struct notifier_block *this, unsigned long event, return NOTIFY_DONE; switch (event) { + case NETDEV_DOWN: + case NETDEV_UP: + case NETDEV_CHANGE: { + struct macsec_dev *m, *n; + struct macsec_rxh_data *rxd; + + rxd = macsec_data_rtnl(real_dev); + list_for_each_entry_safe(m, n, &rxd->secys, secys) { + struct net_device *dev = m->secy.netdev; + + netif_stacked_transfer_operstate(real_dev, dev); + } + break; + } case NETDEV_UNREGISTER: { struct macsec_dev *m, *n; struct macsec_rxh_data *rxd; From b948d56951be8e8fe169c608cf384f5303ae4d0c Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Sun, 28 Oct 2018 09:33:10 +0100 Subject: [PATCH 152/299] macsec: let the administrator set UP state even if lowerdev is down [ Upstream commit 07bddef9839378bd6f95b393cf24c420529b4ef1 ] Currently, the kernel doesn't let the administrator set a macsec device up unless its lower device is currently up. This is inconsistent, as a macsec device that is up won't automatically go down when its lower device goes down. Now that linkstate propagation works, there's really no reason for this limitation, so let's remove it. Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Reported-by: Radu Rendec Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/macsec.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 50acd8c9d7f5..10a8ef2d025a 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2813,9 +2813,6 @@ static int macsec_dev_open(struct net_device *dev) struct net_device *real_dev = macsec->real_dev; int err; - if (!(real_dev->flags & IFF_UP)) - return -ENETDOWN; - err = dev_uc_add(real_dev, dev->dev_addr); if (err < 0) return err; From 10807b374663291a3571ba3092a1e2d3ffb7b2b9 Mon Sep 17 00:00:00 2001 From: Jianchao Wang Date: Sat, 27 Oct 2018 19:52:14 +0800 Subject: [PATCH 153/299] block: fix the DISCARD request merge [ Upstream commit 69840466086d2248898020a08dda52732686c4e6 ] There are two cases when handle DISCARD merge. If max_discard_segments == 1, the bios/requests need to be contiguous to merge. If max_discard_segments > 1, it takes every bio as a range and different range needn't to be contiguous. But now, attempt_merge screws this up. It always consider contiguity for DISCARD for the case max_discard_segments > 1 and cannot merge contiguous DISCARD for the case max_discard_segments == 1, because rq_attempt_discard_merge always returns false in this case. This patch fixes both of the two cases above. Reviewed-by: Christoph Hellwig Reviewed-by: Ming Lei Signed-off-by: Jianchao Wang Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/blk-merge.c | 46 ++++++++++++++++++++++++++++++++++++---------- 1 file changed, 36 insertions(+), 10 deletions(-) diff --git a/block/blk-merge.c b/block/blk-merge.c index 2e042190a4f1..1dced51de1c6 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -669,6 +669,31 @@ static void blk_account_io_merge(struct request *req) part_stat_unlock(); } } +/* + * Two cases of handling DISCARD merge: + * If max_discard_segments > 1, the driver takes every bio + * as a range and send them to controller together. The ranges + * needn't to be contiguous. + * Otherwise, the bios/requests will be handled as same as + * others which should be contiguous. + */ +static inline bool blk_discard_mergable(struct request *req) +{ + if (req_op(req) == REQ_OP_DISCARD && + queue_max_discard_segments(req->q) > 1) + return true; + return false; +} + +enum elv_merge blk_try_req_merge(struct request *req, struct request *next) +{ + if (blk_discard_mergable(req)) + return ELEVATOR_DISCARD_MERGE; + else if (blk_rq_pos(req) + blk_rq_sectors(req) == blk_rq_pos(next)) + return ELEVATOR_BACK_MERGE; + + return ELEVATOR_NO_MERGE; +} /* * For non-mq, this has to be called with the request spinlock acquired. @@ -686,12 +711,6 @@ static struct request *attempt_merge(struct request_queue *q, if (req_op(req) != req_op(next)) return NULL; - /* - * not contiguous - */ - if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next)) - return NULL; - if (rq_data_dir(req) != rq_data_dir(next) || req->rq_disk != next->rq_disk || req_no_special_merge(next)) @@ -715,11 +734,19 @@ static struct request *attempt_merge(struct request_queue *q, * counts here. Handle DISCARDs separately, as they * have separate settings. */ - if (req_op(req) == REQ_OP_DISCARD) { + + switch (blk_try_req_merge(req, next)) { + case ELEVATOR_DISCARD_MERGE: if (!req_attempt_discard_merge(q, req, next)) return NULL; - } else if (!ll_merge_requests_fn(q, req, next)) + break; + case ELEVATOR_BACK_MERGE: + if (!ll_merge_requests_fn(q, req, next)) + return NULL; + break; + default: return NULL; + } /* * If failfast settings disagree or any of the two is already @@ -843,8 +870,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) enum elv_merge blk_try_merge(struct request *rq, struct bio *bio) { - if (req_op(rq) == REQ_OP_DISCARD && - queue_max_discard_segments(rq->q) > 1) + if (blk_discard_mergable(rq)) return ELEVATOR_DISCARD_MERGE; else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector) return ELEVATOR_BACK_MERGE; From 1466eae37a9f867674dceba9c7f17d7e8167456d Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 16 Oct 2018 12:01:47 +0900 Subject: [PATCH 154/299] i2c: uniphier-f: make driver robust against concurrency [ Upstream commit f1fdcbbdf45d9609f3d4063b67e9ea941ba3a58f ] This is unlikely to happen, but it is possible for a CPU to enter the interrupt handler just after wait_for_completion_timeout() has expired. If this happens, the hardware is accessed from multiple contexts concurrently. Disable the IRQ after wait_for_completion_timeout(), and do nothing from the handler when the IRQ is disabled. Fixes: 6a62974b667f ("i2c: uniphier_f: add UniPhier FIFO-builtin I2C driver") Signed-off-by: Masahiro Yamada Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-uniphier-f.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-uniphier-f.c b/drivers/i2c/busses/i2c-uniphier-f.c index bc26ec822e26..b9a0690b4fd7 100644 --- a/drivers/i2c/busses/i2c-uniphier-f.c +++ b/drivers/i2c/busses/i2c-uniphier-f.c @@ -98,6 +98,7 @@ struct uniphier_fi2c_priv { unsigned int flags; unsigned int busy_cnt; unsigned int clk_cycle; + spinlock_t lock; /* IRQ synchronization */ }; static void uniphier_fi2c_fill_txfifo(struct uniphier_fi2c_priv *priv, @@ -162,7 +163,10 @@ static irqreturn_t uniphier_fi2c_interrupt(int irq, void *dev_id) struct uniphier_fi2c_priv *priv = dev_id; u32 irq_status; + spin_lock(&priv->lock); + irq_status = readl(priv->membase + UNIPHIER_FI2C_INT); + irq_status &= priv->enabled_irqs; dev_dbg(&priv->adap.dev, "interrupt: enabled_irqs=%04x, irq_status=%04x\n", @@ -230,6 +234,8 @@ static irqreturn_t uniphier_fi2c_interrupt(int irq, void *dev_id) goto handled; } + spin_unlock(&priv->lock); + return IRQ_NONE; data_done: @@ -246,6 +252,8 @@ complete: handled: uniphier_fi2c_clear_irqs(priv); + spin_unlock(&priv->lock); + return IRQ_HANDLED; } @@ -311,7 +319,7 @@ static int uniphier_fi2c_master_xfer_one(struct i2c_adapter *adap, { struct uniphier_fi2c_priv *priv = i2c_get_adapdata(adap); bool is_read = msg->flags & I2C_M_RD; - unsigned long time_left; + unsigned long time_left, flags; dev_dbg(&adap->dev, "%s: addr=0x%02x, len=%d, stop=%d\n", is_read ? "receive" : "transmit", msg->addr, msg->len, stop); @@ -342,6 +350,12 @@ static int uniphier_fi2c_master_xfer_one(struct i2c_adapter *adap, priv->membase + UNIPHIER_FI2C_CR); time_left = wait_for_completion_timeout(&priv->comp, adap->timeout); + + spin_lock_irqsave(&priv->lock, flags); + priv->enabled_irqs = 0; + uniphier_fi2c_set_irqs(priv); + spin_unlock_irqrestore(&priv->lock, flags); + if (!time_left) { dev_err(&adap->dev, "transaction timeout.\n"); uniphier_fi2c_recover(priv); @@ -546,6 +560,7 @@ static int uniphier_fi2c_probe(struct platform_device *pdev) priv->clk_cycle = clk_rate / bus_speed; init_completion(&priv->comp); + spin_lock_init(&priv->lock); priv->adap.owner = THIS_MODULE; priv->adap.algo = &uniphier_fi2c_algo; priv->adap.dev.parent = dev; From a118403a5ecce1ba8da834bf1de501402851bc9b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 16 Oct 2018 12:01:48 +0900 Subject: [PATCH 155/299] i2c: uniphier-f: fix occasional timeout error [ Upstream commit 39226aaa85f002d695e3cafade3309e12ffdaecd ] Currently, a timeout error could happen at a repeated START condition. For a (non-repeated) START condition, the controller starts sending data when the UNIPHIER_FI2C_CR_STA bit is set. However, for a repeated START condition, the hardware starts running when the slave address is written to the TX FIFO - the write to the UNIPHIER_FI2C_CR register is actually unneeded. Because the hardware is already running before the IRQ is enabled for a repeated START, the driver may miss the IRQ event. In most cases, this problem does not show up since modern CPUs are much faster than the I2C transfer. However, it is still possible that a context switch happens after the controller starts, but before the IRQ register is set up. To fix this, - Do not write UNIPHIER_FI2C_CR for repeated START conditions. - Enable IRQ *before* writing the slave address to the TX FIFO. - Disable IRQ for the current CPU while queuing up the TX FIFO; If the CPU is interrupted by some task, the interrupt handler might be invoked due to the empty TX FIFO before completing the setup. Fixes: 6a62974b667f ("i2c: uniphier_f: add UniPhier FIFO-builtin I2C driver") Signed-off-by: Masahiro Yamada Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-uniphier-f.c | 33 ++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 8 deletions(-) diff --git a/drivers/i2c/busses/i2c-uniphier-f.c b/drivers/i2c/busses/i2c-uniphier-f.c index b9a0690b4fd7..bbd5b137aa21 100644 --- a/drivers/i2c/busses/i2c-uniphier-f.c +++ b/drivers/i2c/busses/i2c-uniphier-f.c @@ -260,6 +260,8 @@ handled: static void uniphier_fi2c_tx_init(struct uniphier_fi2c_priv *priv, u16 addr) { priv->enabled_irqs |= UNIPHIER_FI2C_INT_TE; + uniphier_fi2c_set_irqs(priv); + /* do not use TX byte counter */ writel(0, priv->membase + UNIPHIER_FI2C_TBC); /* set slave address */ @@ -292,6 +294,8 @@ static void uniphier_fi2c_rx_init(struct uniphier_fi2c_priv *priv, u16 addr) priv->enabled_irqs |= UNIPHIER_FI2C_INT_RF; } + uniphier_fi2c_set_irqs(priv); + /* set slave address with RD bit */ writel(UNIPHIER_FI2C_DTTX_CMD | UNIPHIER_FI2C_DTTX_RD | addr << 1, priv->membase + UNIPHIER_FI2C_DTTX); @@ -315,14 +319,16 @@ static void uniphier_fi2c_recover(struct uniphier_fi2c_priv *priv) } static int uniphier_fi2c_master_xfer_one(struct i2c_adapter *adap, - struct i2c_msg *msg, bool stop) + struct i2c_msg *msg, bool repeat, + bool stop) { struct uniphier_fi2c_priv *priv = i2c_get_adapdata(adap); bool is_read = msg->flags & I2C_M_RD; unsigned long time_left, flags; - dev_dbg(&adap->dev, "%s: addr=0x%02x, len=%d, stop=%d\n", - is_read ? "receive" : "transmit", msg->addr, msg->len, stop); + dev_dbg(&adap->dev, "%s: addr=0x%02x, len=%d, repeat=%d, stop=%d\n", + is_read ? "receive" : "transmit", msg->addr, msg->len, + repeat, stop); priv->len = msg->len; priv->buf = msg->buf; @@ -338,16 +344,24 @@ static int uniphier_fi2c_master_xfer_one(struct i2c_adapter *adap, writel(UNIPHIER_FI2C_RST_TBRST | UNIPHIER_FI2C_RST_RBRST, priv->membase + UNIPHIER_FI2C_RST); /* reset TX/RX FIFO */ + spin_lock_irqsave(&priv->lock, flags); + if (is_read) uniphier_fi2c_rx_init(priv, msg->addr); else uniphier_fi2c_tx_init(priv, msg->addr); - uniphier_fi2c_set_irqs(priv); - dev_dbg(&adap->dev, "start condition\n"); - writel(UNIPHIER_FI2C_CR_MST | UNIPHIER_FI2C_CR_STA, - priv->membase + UNIPHIER_FI2C_CR); + /* + * For a repeated START condition, writing a slave address to the FIFO + * kicks the controller. So, the UNIPHIER_FI2C_CR register should be + * written only for a non-repeated START condition. + */ + if (!repeat) + writel(UNIPHIER_FI2C_CR_MST | UNIPHIER_FI2C_CR_STA, + priv->membase + UNIPHIER_FI2C_CR); + + spin_unlock_irqrestore(&priv->lock, flags); time_left = wait_for_completion_timeout(&priv->comp, adap->timeout); @@ -408,6 +422,7 @@ static int uniphier_fi2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) { struct i2c_msg *msg, *emsg = msgs + num; + bool repeat = false; int ret; ret = uniphier_fi2c_check_bus_busy(adap); @@ -418,9 +433,11 @@ static int uniphier_fi2c_master_xfer(struct i2c_adapter *adap, /* Emit STOP if it is the last message or I2C_M_STOP is set. */ bool stop = (msg + 1 == emsg) || (msg->flags & I2C_M_STOP); - ret = uniphier_fi2c_master_xfer_one(adap, msg, stop); + ret = uniphier_fi2c_master_xfer_one(adap, msg, repeat, stop); if (ret) return ret; + + repeat = !stop; } return num; From a17e3bbfb97c3ff7fa297f5193c1310faf6b749f Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 16 Oct 2018 12:01:49 +0900 Subject: [PATCH 156/299] i2c: uniphier-f: fix race condition when IRQ is cleared [ Upstream commit eaba68785c2d24ebf1f0d46c24e11b79cc2f94c7 ] The current IRQ handler clears all the IRQ status bits when it bails out. This is dangerous because it might clear away the status bits that have just been set while processing the current handler. If this happens, the IRQ event for the latest transfer is lost forever. The IRQ status bits must be cleared *before* the next transfer is kicked. Fixes: 6a62974b667f ("i2c: uniphier_f: add UniPhier FIFO-builtin I2C driver") Signed-off-by: Masahiro Yamada Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-uniphier-f.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/i2c/busses/i2c-uniphier-f.c b/drivers/i2c/busses/i2c-uniphier-f.c index bbd5b137aa21..928ea9930d17 100644 --- a/drivers/i2c/busses/i2c-uniphier-f.c +++ b/drivers/i2c/busses/i2c-uniphier-f.c @@ -143,9 +143,10 @@ static void uniphier_fi2c_set_irqs(struct uniphier_fi2c_priv *priv) writel(priv->enabled_irqs, priv->membase + UNIPHIER_FI2C_IE); } -static void uniphier_fi2c_clear_irqs(struct uniphier_fi2c_priv *priv) +static void uniphier_fi2c_clear_irqs(struct uniphier_fi2c_priv *priv, + u32 mask) { - writel(-1, priv->membase + UNIPHIER_FI2C_IC); + writel(mask, priv->membase + UNIPHIER_FI2C_IC); } static void uniphier_fi2c_stop(struct uniphier_fi2c_priv *priv) @@ -172,6 +173,8 @@ static irqreturn_t uniphier_fi2c_interrupt(int irq, void *dev_id) "interrupt: enabled_irqs=%04x, irq_status=%04x\n", priv->enabled_irqs, irq_status); + uniphier_fi2c_clear_irqs(priv, irq_status); + if (irq_status & UNIPHIER_FI2C_INT_STOP) goto complete; @@ -250,8 +253,6 @@ complete: } handled: - uniphier_fi2c_clear_irqs(priv); - spin_unlock(&priv->lock); return IRQ_HANDLED; @@ -340,7 +341,7 @@ static int uniphier_fi2c_master_xfer_one(struct i2c_adapter *adap, priv->flags |= UNIPHIER_FI2C_STOP; reinit_completion(&priv->comp); - uniphier_fi2c_clear_irqs(priv); + uniphier_fi2c_clear_irqs(priv, U32_MAX); writel(UNIPHIER_FI2C_RST_TBRST | UNIPHIER_FI2C_RST_RBRST, priv->membase + UNIPHIER_FI2C_RST); /* reset TX/RX FIFO */ From cdc45f2047750b511409c1c7b6b7725d902d79a4 Mon Sep 17 00:00:00 2001 From: Anton Ivanov Date: Tue, 25 Sep 2018 08:47:13 +0100 Subject: [PATCH 157/299] um: Make line/tty semantics use true write IRQ [ Upstream commit 917e2fd2c53eb3c4162f5397555cbd394390d4bc ] This fixes a long standing bug where large amounts of output could freeze the tty (most commonly seen on stdio console). While the bug has always been there it became more pronounced after moving to the new interrupt controller. The line semantics are now changed to have true IRQ write semantics which should further improve the tty/line subsystem stability and performance Signed-off-by: Anton Ivanov Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- arch/um/drivers/line.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index 8d80b27502e6..7e524efed584 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -261,7 +261,7 @@ static irqreturn_t line_write_interrupt(int irq, void *data) if (err == 0) { spin_unlock(&line->lock); return IRQ_NONE; - } else if (err < 0) { + } else if ((err < 0) && (err != -EAGAIN)) { line->head = line->buffer; line->tail = line->buffer; } @@ -284,7 +284,7 @@ int line_setup_irq(int fd, int input, int output, struct line *line, void *data) if (err) return err; if (output) - err = um_request_irq(driver->write_irq, fd, IRQ_NONE, + err = um_request_irq(driver->write_irq, fd, IRQ_WRITE, line_write_interrupt, IRQF_SHARED, driver->write_irq_name, data); return err; From 691bd94c15b107de103650d0656822fa9b639fa6 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:40:55 +1100 Subject: [PATCH 158/299] vfs: avoid problematic remapping requests into partial EOF block [ Upstream commit 07d19dc9fbe9128378b9e226abe886fd8fd473df ] A deduplication data corruption is exposed in XFS and btrfs. It is caused by extending the block match range to include the partial EOF block, but then allowing unknown data beyond EOF to be considered a "match" to data in the destination file because the comparison is only made to the end of the source file. This corrupts the destination file when the source extent is shared with it. The VFS remapping prep functions only support whole block dedupe, but we still need to appear to support whole file dedupe correctly. Hence if the dedupe request includes the last block of the souce file, don't include it in the actual dedupe operation. If the rest of the range dedupes successfully, then reject the entire request. A subsequent patch will enable us to shorten dedupe requests correctly. When reflinking sub-file ranges, a data corruption can occur when the source file range includes a partial EOF block. This shares the unknown data beyond EOF into the second file at a position inside EOF, exposing stale data in the second file. If the reflink request includes the last block of the souce file, only proceed with the reflink operation if it lands at or past the destination file's current EOF. If it lands within the destination file EOF, reject the entire request with -EINVAL and make the caller go the hard way. A subsequent patch will enable us to shorten reflink requests correctly. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner Signed-off-by: Sasha Levin --- fs/read_write.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/fs/read_write.c b/fs/read_write.c index 5fb5ee5b8cd7..2195380620d0 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1715,6 +1715,34 @@ static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write) return security_file_permission(file, write ? MAY_WRITE : MAY_READ); } +/* + * Ensure that we don't remap a partial EOF block in the middle of something + * else. Assume that the offsets have already been checked for block + * alignment. + * + * For deduplication we always scale down to the previous block because we + * can't meaningfully compare post-EOF contents. + * + * For clone we only link a partial EOF block above the destination file's EOF. + */ +static int generic_remap_check_len(struct inode *inode_in, + struct inode *inode_out, + loff_t pos_out, + u64 *len, + bool is_dedupe) +{ + u64 blkmask = i_blocksize(inode_in) - 1; + + if ((*len & blkmask) == 0) + return 0; + + if (is_dedupe) + *len &= ~blkmask; + else if (pos_out + *len < i_size_read(inode_out)) + return -EINVAL; + + return 0; +} /* * Check that the two inodes are eligible for cloning, the ranges make @@ -1821,6 +1849,11 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, return -EBADE; } + ret = generic_remap_check_len(inode_in, inode_out, pos_out, len, + is_dedupe); + if (ret) + return ret; + return 1; } EXPORT_SYMBOL(vfs_clone_file_prep_inodes); From 32d7474b7a08f432191c9781a05f6ba3585f0db9 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 26 Oct 2018 11:30:35 +0800 Subject: [PATCH 159/299] ipv4/igmp: fix v1/v2 switchback timeout based on rfc3376, 8.12 [ Upstream commit 966c37f2d77eb44d47af8e919267b1ba675b2eca ] Similiar with ipv6 mcast commit 89225d1ce6af3 ("net: ipv6: mld: fix v1/v2 switchback timeout to rfc3810, 9.12.") i) RFC3376 8.12. Older Version Querier Present Timeout says: The Older Version Querier Interval is the time-out for transitioning a host back to IGMPv3 mode once an older version query is heard. When an older version query is received, hosts set their Older Version Querier Present Timer to Older Version Querier Interval. This value MUST be ((the Robustness Variable) times (the Query Interval in the last Query received)) plus (one Query Response Interval). Currently we only use a hardcode value IGMP_V1/v2_ROUTER_PRESENT_TIMEOUT. Fix it by adding two new items mr_qi(Query Interval) and mr_qri(Query Response Interval) in struct in_device. Now we can calculate the switchback time via (mr_qrv * mr_qi) + mr_qri. We need update these values when receive IGMPv3 queries. Reported-by: Ying Xu Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/linux/inetdevice.h | 4 ++- net/ipv4/igmp.c | 55 +++++++++++++++++++++++++------------- 2 files changed, 40 insertions(+), 19 deletions(-) diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index c759d1cbcedd..a64f21a97369 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -37,7 +37,9 @@ struct in_device { unsigned long mr_v1_seen; unsigned long mr_v2_seen; unsigned long mr_maxdelay; - unsigned char mr_qrv; + unsigned long mr_qi; /* Query Interval */ + unsigned long mr_qri; /* Query Response Interval */ + unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; unsigned char mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index b2240b7f225d..523d26f5e22e 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -111,13 +111,10 @@ #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ -#define IGMP_V1_ROUTER_PRESENT_TIMEOUT (400*HZ) -#define IGMP_V2_ROUTER_PRESENT_TIMEOUT (400*HZ) #define IGMP_V2_UNSOLICITED_REPORT_INTERVAL (10*HZ) #define IGMP_V3_UNSOLICITED_REPORT_INTERVAL (1*HZ) +#define IGMP_QUERY_INTERVAL (125*HZ) #define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ) -#define IGMP_QUERY_ROBUSTNESS_VARIABLE 2 - #define IGMP_INITIAL_REPORT_DELAY (1) @@ -953,13 +950,15 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, max_delay = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_v1_seen = jiffies + - IGMP_V1_ROUTER_PRESENT_TIMEOUT; + (in_dev->mr_qrv * in_dev->mr_qi) + + in_dev->mr_qri; group = 0; } else { /* v2 router present */ max_delay = ih->code*(HZ/IGMP_TIMER_SCALE); in_dev->mr_v2_seen = jiffies + - IGMP_V2_ROUTER_PRESENT_TIMEOUT; + (in_dev->mr_qrv * in_dev->mr_qi) + + in_dev->mr_qri; } /* cancel the interface change timer */ in_dev->mr_ifc_count = 0; @@ -999,8 +998,21 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ in_dev->mr_maxdelay = max_delay; - if (ih3->qrv) - in_dev->mr_qrv = ih3->qrv; + + /* RFC3376, 4.1.6. QRV and 4.1.7. QQIC, when the most recently + * received value was zero, use the default or statically + * configured value. + */ + in_dev->mr_qrv = ih3->qrv ?: net->ipv4.sysctl_igmp_qrv; + in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL; + + /* RFC3376, 8.3. Query Response Interval: + * The number of seconds represented by the [Query Response + * Interval] must be less than the [Query Interval]. + */ + if (in_dev->mr_qri >= in_dev->mr_qi) + in_dev->mr_qri = (in_dev->mr_qi/HZ - 1)*HZ; + if (!group) { /* general query */ if (ih3->nsrcs) return true; /* no sources allowed */ @@ -1738,18 +1750,30 @@ void ip_mc_down(struct in_device *in_dev) ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS); } +#ifdef CONFIG_IP_MULTICAST +static void ip_mc_reset(struct in_device *in_dev) +{ + struct net *net = dev_net(in_dev->dev); + + in_dev->mr_qi = IGMP_QUERY_INTERVAL; + in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL; + in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; +} +#else +static void ip_mc_reset(struct in_device *in_dev) +{ +} +#endif + void ip_mc_init_dev(struct in_device *in_dev) { -#ifdef CONFIG_IP_MULTICAST - struct net *net = dev_net(in_dev->dev); -#endif ASSERT_RTNL(); #ifdef CONFIG_IP_MULTICAST timer_setup(&in_dev->mr_gq_timer, igmp_gq_timer_expire, 0); timer_setup(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, 0); - in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; #endif + ip_mc_reset(in_dev); spin_lock_init(&in_dev->mc_tomb_lock); } @@ -1759,15 +1783,10 @@ void ip_mc_init_dev(struct in_device *in_dev) void ip_mc_up(struct in_device *in_dev) { struct ip_mc_list *pmc; -#ifdef CONFIG_IP_MULTICAST - struct net *net = dev_net(in_dev->dev); -#endif ASSERT_RTNL(); -#ifdef CONFIG_IP_MULTICAST - in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; -#endif + ip_mc_reset(in_dev); ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); for_each_pmc_rtnl(in_dev, pmc) { From 57aab8f0a33d5eab59d2108de0644f209941f39e Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Wed, 31 Oct 2018 11:39:34 +1030 Subject: [PATCH 160/299] powerpc/xmon: Relax frame size for clang [ Upstream commit 9c87156cce5a63735d1218f0096a65c50a7a32aa ] When building with clang (8 trunk, 7.0 release) the frame size limit is hit: arch/powerpc/xmon/xmon.c:452:12: warning: stack frame size of 2576 bytes in function 'xmon_core' [-Wframe-larger-than=] Some investigation by Naveen indicates this is due to clang saving the addresses to printf format strings on the stack. While this issue is investigated, bump up the frame size limit for xmon when building with clang. Link: https://github.com/ClangBuiltLinux/linux/issues/252 Signed-off-by: Joel Stanley Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- arch/powerpc/xmon/Makefile | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile index 9d7d8e6d705c..9ba44e190e5e 100644 --- a/arch/powerpc/xmon/Makefile +++ b/arch/powerpc/xmon/Makefile @@ -13,6 +13,12 @@ UBSAN_SANITIZE := n ORIG_CFLAGS := $(KBUILD_CFLAGS) KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS)) +ifdef CONFIG_CC_IS_CLANG +# clang stores addresses on the stack causing the frame size to blow +# out. See https://github.com/ClangBuiltLinux/linux/issues/252 +KBUILD_CFLAGS += -Wframe-larger-than=4096 +endif + ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) obj-y += xmon.o nonstdio.o spr_access.o From f74f406bbd0b29d58237a5d14d6cff69e00cf511 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Mon, 29 Oct 2018 22:23:49 +1100 Subject: [PATCH 161/299] selftests/powerpc/ptrace: Fix out-of-tree build [ Upstream commit c39b79082a38a4f8c801790edecbbb4d62ed2992 ] We should use TEST_GEN_PROGS, not TEST_PROGS. That tells the selftests makefile (lib.mk) that those tests are generated (built), and so it adds the $(OUTPUT) prefix for us, making the out-of-tree build work correctly. It also means we don't need our own clean rule, lib.mk does it. We also have to update the ptrace-pkey and core-pkey rules to use $(OUTPUT). Signed-off-by: Joel Stanley Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- tools/testing/selftests/powerpc/ptrace/Makefile | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile index 923d531265f8..9f9423430059 100644 --- a/tools/testing/selftests/powerpc/ptrace/Makefile +++ b/tools/testing/selftests/powerpc/ptrace/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \ +TEST_GEN_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \ ptrace-tar ptrace-tm-tar ptrace-tm-spd-tar ptrace-vsx ptrace-tm-vsx \ ptrace-tm-spd-vsx ptrace-tm-spr ptrace-hwbreak ptrace-pkey core-pkey \ perf-hwbreak @@ -7,14 +7,9 @@ TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \ top_srcdir = ../../../../.. include ../../lib.mk -all: $(TEST_PROGS) - CFLAGS += -m64 -I../../../../../usr/include -I../tm -mhtm -fno-pie -ptrace-pkey core-pkey: child.h -ptrace-pkey core-pkey: LDLIBS += -pthread +$(OUTPUT)/ptrace-pkey $(OUTPUT)/core-pkey: child.h +$(OUTPUT)/ptrace-pkey $(OUTPUT)/core-pkey: LDLIBS += -pthread -$(TEST_PROGS): ../harness.c ../utils.c ../lib/reg.S ptrace.h - -clean: - rm -f $(TEST_PROGS) *.o +$(TEST_GEN_PROGS): ../harness.c ../utils.c ../lib/reg.S ptrace.h From a4a660f7abd984c733b4a6599ef22031e2398146 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Mon, 29 Oct 2018 22:23:50 +1100 Subject: [PATCH 162/299] selftests/powerpc/signal: Fix out-of-tree build [ Upstream commit 27825349d7b238533a47e3d98b8bb0efd886b752 ] We should use TEST_GEN_PROGS, not TEST_PROGS. That tells the selftests makefile (lib.mk) that those tests are generated (built), and so it adds the $(OUTPUT) prefix for us, making the out-of-tree build work correctly. It also means we don't need our own clean rule, lib.mk does it. We also have to update the signal_tm rule to use $(OUTPUT). Signed-off-by: Joel Stanley Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- tools/testing/selftests/powerpc/signal/Makefile | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile index 1fca25c6ace0..209a958dca12 100644 --- a/tools/testing/selftests/powerpc/signal/Makefile +++ b/tools/testing/selftests/powerpc/signal/Makefile @@ -1,15 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 -TEST_PROGS := signal signal_tm - -all: $(TEST_PROGS) - -$(TEST_PROGS): ../harness.c ../utils.c signal.S +TEST_GEN_PROGS := signal signal_tm CFLAGS += -maltivec -signal_tm: CFLAGS += -mhtm +$(OUTPUT)/signal_tm: CFLAGS += -mhtm top_srcdir = ../../../../.. include ../../lib.mk -clean: - rm -f $(TEST_PROGS) *.o +$(TEST_GEN_PROGS): ../harness.c ../utils.c signal.S From 024cd793bbe1f3a0417f8b1f7a44fe9efc7a0f02 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 29 Oct 2018 22:23:52 +1100 Subject: [PATCH 163/299] selftests/powerpc/switch_endian: Fix out-of-tree build [ Upstream commit 266bac361d5677e61a6815bd29abeb3bdced2b07 ] For the out-of-tree build to work we need to tell switch_endian_test to look for check-reversed.S in $(OUTPUT). Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- tools/testing/selftests/powerpc/switch_endian/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/powerpc/switch_endian/Makefile b/tools/testing/selftests/powerpc/switch_endian/Makefile index fcd2dcb8972b..bdc081afedb0 100644 --- a/tools/testing/selftests/powerpc/switch_endian/Makefile +++ b/tools/testing/selftests/powerpc/switch_endian/Makefile @@ -8,6 +8,7 @@ EXTRA_CLEAN = $(OUTPUT)/*.o $(OUTPUT)/check-reversed.S top_srcdir = ../../../../.. include ../../lib.mk +$(OUTPUT)/switch_endian_test: ASFLAGS += -I $(OUTPUT) $(OUTPUT)/switch_endian_test: $(OUTPUT)/check-reversed.S $(OUTPUT)/check-reversed.o: $(OUTPUT)/check.o From a125df22d134c341a1e7a998958ecaa2969256cd Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 29 Oct 2018 22:23:53 +1100 Subject: [PATCH 164/299] selftests/powerpc/cache_shape: Fix out-of-tree build [ Upstream commit 69f8117f17b332a68cd8f4bf8c2d0d3d5b84efc5 ] Use TEST_GEN_PROGS and don't redefine all, this makes the out-of-tree build work. We need to move the extra dependencies below the include of lib.mk, because it adds the $(OUTPUT) prefix if it's defined. We can also drop the clean rule, lib.mk does it for us. Signed-off-by: Michael Ellerman Signed-off-by: Sasha Levin --- tools/testing/selftests/powerpc/cache_shape/Makefile | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/powerpc/cache_shape/Makefile b/tools/testing/selftests/powerpc/cache_shape/Makefile index ede4d3dae750..689f6c8ebcd8 100644 --- a/tools/testing/selftests/powerpc/cache_shape/Makefile +++ b/tools/testing/selftests/powerpc/cache_shape/Makefile @@ -1,12 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 -TEST_PROGS := cache_shape - -all: $(TEST_PROGS) - -$(TEST_PROGS): ../harness.c ../utils.c +TEST_GEN_PROGS := cache_shape top_srcdir = ../../../../.. include ../../lib.mk -clean: - rm -f $(TEST_PROGS) *.o +$(TEST_GEN_PROGS): ../harness.c ../utils.c From 9663d294ae28ccd970bd0f1e8abbd8d7eb630943 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 24 Oct 2018 21:18:09 +0800 Subject: [PATCH 165/299] block: call rq_qos_exit() after queue is frozen [ Upstream commit c57cdf7a9e51d97a43e29b8f4a04157875104000 ] rq_qos_exit() removes the current q->rq_qos, this action has to be done after queue is frozen, otherwise the IO queue path may never be waken up, then IO hang is caused. So fixes this issue by moving rq_qos_exit() after queue is frozen. Cc: Josef Bacik Signed-off-by: Ming Lei Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/blk-core.c | 3 +++ block/blk-sysfs.c | 2 -- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index 074ae9376189..ea33d6abdcfc 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -784,6 +784,9 @@ void blk_cleanup_queue(struct request_queue *q) * prevent that q->request_fn() gets invoked after draining finished. */ blk_freeze_queue(q); + + rq_qos_exit(q); + spin_lock_irq(lock); queue_flag_set(QUEUE_FLAG_DEAD, q); spin_unlock_irq(lock); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index bab47a17b96f..8286640d4d66 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -997,8 +997,6 @@ void blk_unregister_queue(struct gendisk *disk) kobject_del(&q->kobj); blk_trace_remove_sysfs(disk_to_dev(disk)); - rq_qos_exit(q); - mutex_lock(&q->sysfs_lock); if (q->request_fn || (q->mq_ops && q->elevator)) elv_unregister_queue(q); From 30598425aecc7af38f8786db3ab5317e07430db2 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 30 Oct 2018 15:04:32 -0700 Subject: [PATCH 166/299] mm/gup_benchmark.c: prevent integer overflow in ioctl [ Upstream commit 4b408c74ee5a0b74fc9265c2fe39b0e7dec7c056 ] The concern here is that "gup->size" is a u64 and "nr_pages" is unsigned long. On 32 bit systems we could trick the kernel into allocating fewer pages than expected. Link: http://lkml.kernel.org/r/20181025061546.hnhkv33diogf2uis@kili.mountain Fixes: 64c349f4ae78 ("mm: add infrastructure for get_user_pages_fast() benchmarking") Signed-off-by: Dan Carpenter Acked-by: Kirill A. Shutemov Reviewed-by: Andrew Morton Cc: Stephen Rothwell Cc: Keith Busch Cc: "Michael S. Tsirkin" Cc: Kees Cook Cc: YueHaibing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- mm/gup_benchmark.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c index 7405c9d89d65..7e6f2d2dafb5 100644 --- a/mm/gup_benchmark.c +++ b/mm/gup_benchmark.c @@ -23,6 +23,9 @@ static int __gup_benchmark_ioctl(unsigned int cmd, int nr; struct page **pages; + if (gup->size > ULONG_MAX) + return -EINVAL; + nr_pages = gup->size / PAGE_SIZE; pages = kvcalloc(nr_pages, sizeof(void *), GFP_KERNEL); if (!pages) From 8deaaf77ce2efb3f314c97fa2e1f73eb6899d8c3 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 30 Oct 2018 15:04:59 -0700 Subject: [PATCH 167/299] linux/bitmap.h: handle constant zero-size bitmaps correctly [ Upstream commit 7275b097851a5e2e0dd4da039c7e96b59ac5314e ] The static inlines in bitmap.h do not handle a compile-time constant nbits==0 correctly (they dereference the passed src or dst pointers, despite only 0 words being valid to access). I had the 0-day buildbot chew on a patch [1] that would cause build failures for such cases without complaining, suggesting that we don't have any such users currently, at least for the 70 .config/arch combinations that was built. Should any turn up, make sure they use the out-of-line versions, which do handle nbits==0 correctly. This is of course not the most efficient, but it's much less churn than teaching all the static inlines an "if (zero_const_nbits())", and since we don't have any current instances, this doesn't affect existing code at all. [1] lkml.kernel.org/r/20180815085539.27485-1-linux@rasmusvillemoes.dk Link: http://lkml.kernel.org/r/20180818131623.8755-3-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Reviewed-by: Andy Shevchenko Cc: Yury Norov Cc: Rasmus Villemoes Cc: Sudeep Holla Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- include/linux/bitmap.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index acf5e8df3504..a9805bacbd7c 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -204,8 +204,13 @@ extern int bitmap_print_to_pagebuf(bool list, char *buf, #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) +/* + * The static inlines below do not handle constant nbits==0 correctly, + * so make such users (should any ever turn up) call the out-of-line + * versions. + */ #define small_const_nbits(nbits) \ - (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG) + (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG && (nbits) > 0) static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { From 1d58349459450f04cbd82e5f3bdd8c4e3699433b Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 30 Oct 2018 15:05:07 -0700 Subject: [PATCH 168/299] linux/bitmap.h: fix type of nbits in bitmap_shift_right() [ Upstream commit d9873969fa8725dc6a5a21ab788c057fd8719751 ] Most other bitmap API, including the OOL version __bitmap_shift_right, take unsigned nbits. This was accidentally left out from 2fbad29917c98. Link: http://lkml.kernel.org/r/20180818131623.8755-5-linux@rasmusvillemoes.dk Fixes: 2fbad29917c98 ("lib: bitmap: change bitmap_shift_right to take unsigned parameters") Signed-off-by: Rasmus Villemoes Reported-by: Yury Norov Reviewed-by: Andy Shevchenko Cc: Rasmus Villemoes Cc: Sudeep Holla Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- include/linux/bitmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index a9805bacbd7c..b71a033c781e 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -403,7 +403,7 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, } static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, - unsigned int shift, int nbits) + unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift; From 08751e477f0eacf90a72df15dbda94f95c794fda Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 30 Oct 2018 15:05:14 -0700 Subject: [PATCH 169/299] lib/bitmap.c: fix remaining space computation in bitmap_print_to_pagebuf [ Upstream commit ce1091d471107dbf6f91db66a480a25950c9b9ff ] For various alignments of buf, the current expression computes 4096 ok 4095 ok 8190 8189 ... 4097 i.e., if the caller has already written two bytes into the page buffer, len is 8190 rather than 4094, because PTR_ALIGN aligns up to the next boundary. So if the printed version of the bitmap is huge, scnprintf() ends up writing beyond the page boundary. I don't think any current callers actually write anything before bitmap_print_to_pagebuf, but the API seems to be designed to allow it. [akpm@linux-foundation.org: use offset_in_page(), per Andy] [akpm@linux-foundation.org: include mm.h for offset_in_page()] Link: http://lkml.kernel.org/r/20180818131623.8755-7-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Reviewed-by: Andy Shevchenko Cc: Yury Norov Cc: Rasmus Villemoes Cc: Sudeep Holla Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- lib/bitmap.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/lib/bitmap.c b/lib/bitmap.c index 2fd07f6df0b8..c4ca9ceb09fe 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -466,14 +467,15 @@ EXPORT_SYMBOL(bitmap_parse_user); * ranges if list is specified or hex digits grouped into comma-separated * sets of 8 digits/set. Returns the number of characters written to buf. * - * It is assumed that @buf is a pointer into a PAGE_SIZE area and that - * sufficient storage remains at @buf to accommodate the - * bitmap_print_to_pagebuf() output. + * It is assumed that @buf is a pointer into a PAGE_SIZE, page-aligned + * area and that sufficient storage remains at @buf to accommodate the + * bitmap_print_to_pagebuf() output. Returns the number of characters + * actually printed to @buf, excluding terminating '\0'. */ int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits) { - ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf; + ptrdiff_t len = PAGE_SIZE - offset_in_page(buf); int n = 0; if (len > 1) From 1df96949ebfb210c9cc56c90e4159121d3c470c3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ernesto=20A=2E=20Fern=C3=A1ndez?= Date: Tue, 30 Oct 2018 15:06:04 -0700 Subject: [PATCH 170/299] hfsplus: fix BUG on bnode parent update MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 19a9d0f1acf75e8be8cfba19c1a34e941846fa2b ] Creating, renaming or deleting a file may hit BUG_ON() if the first record of both a leaf node and its parent are changed, and if this forces the parent to be split. This bug is triggered by xfstests generic/027, somewhat rarely; here is a more reliable reproducer: truncate -s 50M fs.iso mkfs.hfsplus fs.iso mount fs.iso /mnt i=1000 while [ $i -le 2400 ]; do touch /mnt/$i &>/dev/null ((++i)) done i=2400 while [ $i -ge 1000 ]; do mv /mnt/$i /mnt/$(perl -e "print $i x61") &>/dev/null ((--i)) done The issue is that a newly created bnode is being put twice. Reset new_node to NULL in hfs_brec_update_parent() before reaching goto again. Link: http://lkml.kernel.org/r/5ee1db09b60373a15890f6a7c835d00e76bf601d.1535682461.git.ernesto.mnd.fernandez@gmail.com Signed-off-by: Ernesto A. Fernández Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/hfsplus/brec.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c index aa17a392b414..1918544a7871 100644 --- a/fs/hfsplus/brec.c +++ b/fs/hfsplus/brec.c @@ -449,6 +449,7 @@ skip: /* restore search_key */ hfs_bnode_read_key(node, fd->search_key, 14); } + new_node = NULL; } if (!rec && node->parent) From 7beaf6105e2e14a421a5ccb1d01fb730ea61d8c3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ernesto=20A=2E=20Fern=C3=A1ndez?= Date: Tue, 30 Oct 2018 15:06:11 -0700 Subject: [PATCH 171/299] hfs: fix BUG on bnode parent update MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ef75bcc5763d130451a99825f247d301088b790b ] hfs_brec_update_parent() may hit BUG_ON() if the first record of both a leaf node and its parent are changed, and if this forces the parent to be split. It is not possible for this to happen on a valid hfs filesystem because the index nodes have fixed length keys. For reasons I ignore, the hfs module does have support for a number of hfsplus features. A corrupt btree header may report variable length keys and trigger this BUG, so it's better to fix it. Link: http://lkml.kernel.org/r/cf9b02d57f806217a2b1bf5db8c3e39730d8f603.1535682463.git.ernesto.mnd.fernandez@gmail.com Signed-off-by: Ernesto A. Fernández Reviewed-by: Andrew Morton Cc: Christoph Hellwig Cc: Viacheslav Dubeyko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/hfs/brec.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/hfs/brec.c b/fs/hfs/brec.c index da25c49203cc..896396554bcc 100644 --- a/fs/hfs/brec.c +++ b/fs/hfs/brec.c @@ -445,6 +445,7 @@ skip: /* restore search_key */ hfs_bnode_read_key(node, fd->search_key, 14); } + new_node = NULL; } if (!rec && node->parent) From 0b54b59d8541ec9ca6160c77633bf8e11edfaaac Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ernesto=20A=2E=20Fern=C3=A1ndez?= Date: Tue, 30 Oct 2018 15:06:14 -0700 Subject: [PATCH 172/299] hfsplus: prevent btree data loss on ENOSPC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit d92915c35bfaf763d78bf1d5ac7f183420e3bd99 ] Inserting or deleting a record in a btree may require splitting several of its nodes. If we hit ENOSPC halfway through, the new nodes will be left orphaned and their records will be lost. This could mean lost inodes, extents or xattrs. Henceforth, check the available disk space before making any changes. This still leaves the potential problem of corruption on ENOMEM. The patch can be tested with xfstests generic/027. Link: http://lkml.kernel.org/r/4596eef22fbda137b4ffa0272d92f0da15364421.1536269129.git.ernesto.mnd.fernandez@gmail.com Signed-off-by: Ernesto A. Fernández Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/hfsplus/attributes.c | 10 ++++++++ fs/hfsplus/btree.c | 52 +++++++++++++++++++++++++---------------- fs/hfsplus/catalog.c | 24 +++++++++++++++++++ fs/hfsplus/extents.c | 4 ++++ fs/hfsplus/hfsplus_fs.h | 2 ++ 5 files changed, 72 insertions(+), 20 deletions(-) diff --git a/fs/hfsplus/attributes.c b/fs/hfsplus/attributes.c index 2bab6b3cdba4..e6d554476db4 100644 --- a/fs/hfsplus/attributes.c +++ b/fs/hfsplus/attributes.c @@ -217,6 +217,11 @@ int hfsplus_create_attr(struct inode *inode, if (err) goto failed_init_create_attr; + /* Fail early and avoid ENOSPC during the btree operation */ + err = hfs_bmap_reserve(fd.tree, fd.tree->depth + 1); + if (err) + goto failed_create_attr; + if (name) { err = hfsplus_attr_build_key(sb, fd.search_key, inode->i_ino, name); @@ -313,6 +318,11 @@ int hfsplus_delete_attr(struct inode *inode, const char *name) if (err) return err; + /* Fail early and avoid ENOSPC during the btree operation */ + err = hfs_bmap_reserve(fd.tree, fd.tree->depth); + if (err) + goto out; + if (name) { err = hfsplus_attr_build_key(sb, fd.search_key, inode->i_ino, name); diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c index 3de3bc4918b5..66774f4cb4fd 100644 --- a/fs/hfsplus/btree.c +++ b/fs/hfsplus/btree.c @@ -342,6 +342,34 @@ static struct hfs_bnode *hfs_bmap_new_bmap(struct hfs_bnode *prev, u32 idx) return node; } +/* Make sure @tree has enough space for the @rsvd_nodes */ +int hfs_bmap_reserve(struct hfs_btree *tree, int rsvd_nodes) +{ + struct inode *inode = tree->inode; + struct hfsplus_inode_info *hip = HFSPLUS_I(inode); + u32 count; + int res; + + if (rsvd_nodes <= 0) + return 0; + + while (tree->free_nodes < rsvd_nodes) { + res = hfsplus_file_extend(inode, hfs_bnode_need_zeroout(tree)); + if (res) + return res; + hip->phys_size = inode->i_size = + (loff_t)hip->alloc_blocks << + HFSPLUS_SB(tree->sb)->alloc_blksz_shift; + hip->fs_blocks = + hip->alloc_blocks << HFSPLUS_SB(tree->sb)->fs_shift; + inode_set_bytes(inode, inode->i_size); + count = inode->i_size >> tree->node_size_shift; + tree->free_nodes += count - tree->node_count; + tree->node_count = count; + } + return 0; +} + struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) { struct hfs_bnode *node, *next_node; @@ -351,27 +379,11 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) u16 off16; u16 len; u8 *data, byte, m; - int i; + int i, res; - while (!tree->free_nodes) { - struct inode *inode = tree->inode; - struct hfsplus_inode_info *hip = HFSPLUS_I(inode); - u32 count; - int res; - - res = hfsplus_file_extend(inode, hfs_bnode_need_zeroout(tree)); - if (res) - return ERR_PTR(res); - hip->phys_size = inode->i_size = - (loff_t)hip->alloc_blocks << - HFSPLUS_SB(tree->sb)->alloc_blksz_shift; - hip->fs_blocks = - hip->alloc_blocks << HFSPLUS_SB(tree->sb)->fs_shift; - inode_set_bytes(inode, inode->i_size); - count = inode->i_size >> tree->node_size_shift; - tree->free_nodes = count - tree->node_count; - tree->node_count = count; - } + res = hfs_bmap_reserve(tree, 1); + if (res) + return ERR_PTR(res); nidx = 0; node = hfs_bnode_find(tree, nidx); diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c index a196369ba779..35472cba750e 100644 --- a/fs/hfsplus/catalog.c +++ b/fs/hfsplus/catalog.c @@ -265,6 +265,14 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, if (err) return err; + /* + * Fail early and avoid ENOSPC during the btree operations. We may + * have to split the root node at most once. + */ + err = hfs_bmap_reserve(fd.tree, 2 * fd.tree->depth); + if (err) + goto err2; + hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid); entry_size = hfsplus_fill_cat_thread(sb, &entry, S_ISDIR(inode->i_mode) ? @@ -333,6 +341,14 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, const struct qstr *str) if (err) return err; + /* + * Fail early and avoid ENOSPC during the btree operations. We may + * have to split the root node at most once. + */ + err = hfs_bmap_reserve(fd.tree, 2 * (int)fd.tree->depth - 2); + if (err) + goto out; + if (!str) { int len; @@ -433,6 +449,14 @@ int hfsplus_rename_cat(u32 cnid, return err; dst_fd = src_fd; + /* + * Fail early and avoid ENOSPC during the btree operations. We may + * have to split the root node at most twice. + */ + err = hfs_bmap_reserve(src_fd.tree, 4 * (int)src_fd.tree->depth - 1); + if (err) + goto out; + /* find the old dir entry and read the data */ err = hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name); diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index 8e0f59767694..8a8893d522ef 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -100,6 +100,10 @@ static int __hfsplus_ext_write_extent(struct inode *inode, if (hip->extent_state & HFSPLUS_EXT_NEW) { if (res != -ENOENT) return res; + /* Fail early and avoid ENOSPC during the btree operation */ + res = hfs_bmap_reserve(fd->tree, fd->tree->depth + 1); + if (res) + return res; hfs_brec_insert(fd, hip->cached_extents, sizeof(hfsplus_extent_rec)); hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW); diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 8e039435958a..dd7ad9f13e3a 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -311,6 +311,7 @@ static inline unsigned short hfsplus_min_io_size(struct super_block *sb) #define hfs_btree_open hfsplus_btree_open #define hfs_btree_close hfsplus_btree_close #define hfs_btree_write hfsplus_btree_write +#define hfs_bmap_reserve hfsplus_bmap_reserve #define hfs_bmap_alloc hfsplus_bmap_alloc #define hfs_bmap_free hfsplus_bmap_free #define hfs_bnode_read hfsplus_bnode_read @@ -395,6 +396,7 @@ u32 hfsplus_calc_btree_clump_size(u32 block_size, u32 node_size, u64 sectors, struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id); void hfs_btree_close(struct hfs_btree *tree); int hfs_btree_write(struct hfs_btree *tree); +int hfs_bmap_reserve(struct hfs_btree *tree, int rsvd_nodes); struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree); void hfs_bmap_free(struct hfs_bnode *node); From 8687d57d247a4d7a217fcf324b34c5ded887c21a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ernesto=20A=2E=20Fern=C3=A1ndez?= Date: Tue, 30 Oct 2018 15:06:17 -0700 Subject: [PATCH 173/299] hfs: prevent btree data loss on ENOSPC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 54640c7502e5ed41fbf4eedd499e85f9acc9698f ] Inserting a new record in a btree may require splitting several of its nodes. If we hit ENOSPC halfway through, the new nodes will be left orphaned and their records will be lost. This could mean lost inodes or extents. Henceforth, check the available disk space before making any changes. This still leaves the potential problem of corruption on ENOMEM. There is no need to reserve space before deleting a catalog record, as we do for hfsplus. This difference is because hfs index nodes have fixed length keys. Link: http://lkml.kernel.org/r/ab5fc8a7d5ffccfd5f27b1cf2cb4ceb6c110da74.1536269131.git.ernesto.mnd.fernandez@gmail.com Signed-off-by: Ernesto A. Fernández Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/hfs/btree.c | 47 ++++++++++++++++++++++++++++------------------- fs/hfs/btree.h | 1 + fs/hfs/catalog.c | 16 ++++++++++++++++ fs/hfs/extent.c | 4 ++++ 4 files changed, 49 insertions(+), 19 deletions(-) diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c index 9bdff5e40626..19017d296173 100644 --- a/fs/hfs/btree.c +++ b/fs/hfs/btree.c @@ -220,6 +220,30 @@ static struct hfs_bnode *hfs_bmap_new_bmap(struct hfs_bnode *prev, u32 idx) return node; } +/* Make sure @tree has enough space for the @rsvd_nodes */ +int hfs_bmap_reserve(struct hfs_btree *tree, int rsvd_nodes) +{ + struct inode *inode = tree->inode; + u32 count; + int res; + + while (tree->free_nodes < rsvd_nodes) { + res = hfs_extend_file(inode); + if (res) + return res; + HFS_I(inode)->phys_size = inode->i_size = + (loff_t)HFS_I(inode)->alloc_blocks * + HFS_SB(tree->sb)->alloc_blksz; + HFS_I(inode)->fs_blocks = inode->i_size >> + tree->sb->s_blocksize_bits; + inode_set_bytes(inode, inode->i_size); + count = inode->i_size >> tree->node_size_shift; + tree->free_nodes += count - tree->node_count; + tree->node_count = count; + } + return 0; +} + struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) { struct hfs_bnode *node, *next_node; @@ -229,26 +253,11 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) u16 off16; u16 len; u8 *data, byte, m; - int i; + int i, res; - while (!tree->free_nodes) { - struct inode *inode = tree->inode; - u32 count; - int res; - - res = hfs_extend_file(inode); - if (res) - return ERR_PTR(res); - HFS_I(inode)->phys_size = inode->i_size = - (loff_t)HFS_I(inode)->alloc_blocks * - HFS_SB(tree->sb)->alloc_blksz; - HFS_I(inode)->fs_blocks = inode->i_size >> - tree->sb->s_blocksize_bits; - inode_set_bytes(inode, inode->i_size); - count = inode->i_size >> tree->node_size_shift; - tree->free_nodes = count - tree->node_count; - tree->node_count = count; - } + res = hfs_bmap_reserve(tree, 1); + if (res) + return ERR_PTR(res); nidx = 0; node = hfs_bnode_find(tree, nidx); diff --git a/fs/hfs/btree.h b/fs/hfs/btree.h index c8b252dbb26c..dcc2aab1b2c4 100644 --- a/fs/hfs/btree.h +++ b/fs/hfs/btree.h @@ -82,6 +82,7 @@ struct hfs_find_data { extern struct hfs_btree *hfs_btree_open(struct super_block *, u32, btree_keycmp); extern void hfs_btree_close(struct hfs_btree *); extern void hfs_btree_write(struct hfs_btree *); +extern int hfs_bmap_reserve(struct hfs_btree *, int); extern struct hfs_bnode * hfs_bmap_alloc(struct hfs_btree *); extern void hfs_bmap_free(struct hfs_bnode *node); diff --git a/fs/hfs/catalog.c b/fs/hfs/catalog.c index 8a66405b0f8b..d365bf0b8c77 100644 --- a/fs/hfs/catalog.c +++ b/fs/hfs/catalog.c @@ -97,6 +97,14 @@ int hfs_cat_create(u32 cnid, struct inode *dir, const struct qstr *str, struct i if (err) return err; + /* + * Fail early and avoid ENOSPC during the btree operations. We may + * have to split the root node at most once. + */ + err = hfs_bmap_reserve(fd.tree, 2 * fd.tree->depth); + if (err) + goto err2; + hfs_cat_build_key(sb, fd.search_key, cnid, NULL); entry_size = hfs_cat_build_thread(sb, &entry, S_ISDIR(inode->i_mode) ? HFS_CDR_THD : HFS_CDR_FTH, @@ -295,6 +303,14 @@ int hfs_cat_move(u32 cnid, struct inode *src_dir, const struct qstr *src_name, return err; dst_fd = src_fd; + /* + * Fail early and avoid ENOSPC during the btree operations. We may + * have to split the root node at most once. + */ + err = hfs_bmap_reserve(src_fd.tree, 2 * src_fd.tree->depth); + if (err) + goto out; + /* find the old dir entry and read the data */ hfs_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name); err = hfs_brec_find(&src_fd); diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c index 5d0182654580..0c638c612152 100644 --- a/fs/hfs/extent.c +++ b/fs/hfs/extent.c @@ -117,6 +117,10 @@ static int __hfs_ext_write_extent(struct inode *inode, struct hfs_find_data *fd) if (HFS_I(inode)->flags & HFS_FLG_EXT_NEW) { if (res != -ENOENT) return res; + /* Fail early and avoid ENOSPC during the btree operation */ + res = hfs_bmap_reserve(fd->tree, fd->tree->depth + 1); + if (res) + return res; hfs_brec_insert(fd, HFS_I(inode)->cached_extents, sizeof(hfs_extent_rec)); HFS_I(inode)->flags &= ~(HFS_FLG_EXT_DIRTY|HFS_FLG_EXT_NEW); } else { From 550da9ee35fd904b3814da10236802a555c13f2c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ernesto=20A=2E=20Fern=C3=A1ndez?= Date: Tue, 30 Oct 2018 15:06:21 -0700 Subject: [PATCH 174/299] hfsplus: fix return value of hfsplus_get_block() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 839c3a6a5e1fbc8542d581911b35b2cb5cd29304 ] Direct writes to empty inodes fail with EIO. The generic direct-io code is in part to blame (a patch has been submitted as "direct-io: allow direct writes to empty inodes"), but hfsplus is worse affected than the other filesystems because the fallback to buffered I/O doesn't happen. The problem is the return value of hfsplus_get_block() when called with !create. Change it to be more consistent with the other modules. Link: http://lkml.kernel.org/r/2cd1301404ec7cf1e39c8f11a01a4302f1460ad6.1539195310.git.ernesto.mnd.fernandez@gmail.com Signed-off-by: Ernesto A. Fernández Reviewed-by: Vyacheslav Dubeyko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/hfsplus/extents.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index 8a8893d522ef..a930ddd15681 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -237,7 +237,9 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock, ablock = iblock >> sbi->fs_shift; if (iblock >= hip->fs_blocks) { - if (iblock > hip->fs_blocks || !create) + if (!create) + return 0; + if (iblock > hip->fs_blocks) return -EIO; if (ablock >= hip->alloc_blocks) { res = hfsplus_file_extend(inode, false); From 38e7b916daa2d9c4161a2e46148693b2374c0296 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ernesto=20A=2E=20Fern=C3=A1ndez?= Date: Tue, 30 Oct 2018 15:06:24 -0700 Subject: [PATCH 175/299] hfs: fix return value of hfs_get_block() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 1267a07be5ebbff2d2739290f3d043ae137c15b4 ] Direct writes to empty inodes fail with EIO. The generic direct-io code is in part to blame (a patch has been submitted as "direct-io: allow direct writes to empty inodes"), but hfs is worse affected than the other filesystems because the fallback to buffered I/O doesn't happen. The problem is the return value of hfs_get_block() when called with !create. Change it to be more consistent with the other modules. Link: http://lkml.kernel.org/r/4538ab8c35ea37338490525f0f24cbc37227528c.1539195310.git.ernesto.mnd.fernandez@gmail.com Signed-off-by: Ernesto A. Fernández Reviewed-by: Vyacheslav Dubeyko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/hfs/extent.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c index 0c638c612152..5f1ff97a3b98 100644 --- a/fs/hfs/extent.c +++ b/fs/hfs/extent.c @@ -345,7 +345,9 @@ int hfs_get_block(struct inode *inode, sector_t block, ablock = (u32)block / HFS_SB(sb)->fs_div; if (block >= HFS_I(inode)->fs_blocks) { - if (block > HFS_I(inode)->fs_blocks || !create) + if (!create) + return 0; + if (block > HFS_I(inode)->fs_blocks) return -EIO; if (ablock >= HFS_I(inode)->alloc_blocks) { res = hfs_extend_file(inode); From 0013adceb5211fce175c0bd30b4ebc81c265d97f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ernesto=20A=2E=20Fern=C3=A1ndez?= Date: Tue, 30 Oct 2018 15:06:27 -0700 Subject: [PATCH 176/299] hfsplus: update timestamps on truncate() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit dc8844aada735890a6de109bef327f5df36a982e ] The vfs takes care of updating ctime and mtime on ftruncate(), but on truncate() it must be done by the module. This patch can be tested with xfstests generic/313. Link: http://lkml.kernel.org/r/9beb0913eea37288599e8e1b7cec8768fb52d1b8.1539316825.git.ernesto.mnd.fernandez@gmail.com Signed-off-by: Ernesto A. Fernández Reviewed-by: Vyacheslav Dubeyko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/hfsplus/inode.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 8e9427a42b81..d7ab9d8c4b67 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -261,6 +261,7 @@ static int hfsplus_setattr(struct dentry *dentry, struct iattr *attr) } truncate_setsize(inode, attr->ia_size); hfsplus_file_truncate(inode); + inode->i_mtime = inode->i_ctime = current_time(inode); } setattr_copy(inode, attr); From a9f38975eb981ff59ef3e943274a723c837da422 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ernesto=20A=2E=20Fern=C3=A1ndez?= Date: Tue, 30 Oct 2018 15:06:31 -0700 Subject: [PATCH 177/299] hfs: update timestamp on truncate() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8cd3cb5061730af085a3f9890a3352f162b4e20c ] The vfs takes care of updating mtime on ftruncate(), but on truncate() it must be done by the module. Link: http://lkml.kernel.org/r/e1611eda2985b672ed2d8677350b4ad8c2d07e8a.1539316825.git.ernesto.mnd.fernandez@gmail.com Signed-off-by: Ernesto A. Fernández Reviewed-by: Vyacheslav Dubeyko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/hfs/inode.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index a2dfa1b2a89c..da243c84e93b 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -642,6 +642,8 @@ int hfs_inode_setattr(struct dentry *dentry, struct iattr * attr) truncate_setsize(inode, attr->ia_size); hfs_file_truncate(inode); + inode->i_atime = inode->i_mtime = inode->i_ctime = + current_time(inode); } setattr_copy(inode, attr); From 1914e5edd81131c3b7f6621f4c12832997dd2c93 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 30 Oct 2018 15:06:35 -0700 Subject: [PATCH 178/299] fs/hfs/extent.c: fix array out of bounds read of array extent [ Upstream commit 6c9a3f843a29d6894dfc40df338b91dbd78f0ae3 ] Currently extent and index i are both being incremented causing an array out of bounds read on extent[i]. Fix this by removing the extraneous increment of extent. Ernesto said: : This is only triggered when deleting a file with a resource fork. I : may be wrong because the documentation isn't clear, but I don't think : you can create those under linux. So I guess nobody was testing them. : : > A disk space leak, perhaps? : : That's what it looks like in general. hfs_free_extents() won't do : anything if the block count doesn't add up, and the error will be : ignored. Now, if the block count randomly does add up, we could see : some corruption. Detected by CoverityScan, CID#711541 ("Out of bounds read") Link: http://lkml.kernel.org/r/20180831140538.31566-1-colin.king@canonical.com Signed-off-by: Colin Ian King Reviewed-by: Ernesto A. Fernndez Cc: David Howells Cc: Al Viro Cc: Hin-Tak Leung Cc: Vyacheslav Dubeyko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/hfs/extent.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c index 5f1ff97a3b98..263d5028d9d1 100644 --- a/fs/hfs/extent.c +++ b/fs/hfs/extent.c @@ -304,7 +304,7 @@ int hfs_free_fork(struct super_block *sb, struct hfs_cat_file *file, int type) return 0; blocks = 0; - for (i = 0; i < 3; extent++, i++) + for (i = 0; i < 3; i++) blocks += be16_to_cpu(extent[i].count); res = hfs_free_extents(sb, extent, blocks, blocks); From 023c071f101c6ab7640c37445f1ea8f8013d3f16 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 30 Oct 2018 15:07:13 -0700 Subject: [PATCH 179/299] kernel/panic.c: do not append newline to the stack protector panic string [ Upstream commit 95c4fb78fb23081472465ca20d5d31c4b780ed82 ] ... because panic() itself already does this. Otherwise you have line-broken trailer: [ 1.836965] ---[ end Kernel panic - not syncing: stack-protector: Kernel stack is corrupted in: pgd_alloc+0x29e/0x2a0 [ 1.836965] ]--- Link: http://lkml.kernel.org/r/20181008202901.7894-1-bp@alien8.de Signed-off-by: Borislav Petkov Acked-by: Kees Cook Cc: Masahiro Yamada Cc: "Steven Rostedt (VMware)" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- kernel/panic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/panic.c b/kernel/panic.c index 72e001e3753e..8138a676fb7d 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -636,7 +636,7 @@ device_initcall(register_warn_debugfs); */ __visible void __stack_chk_fail(void) { - panic("stack-protector: Kernel stack is corrupted in: %pB\n", + panic("stack-protector: Kernel stack is corrupted in: %pB", __builtin_return_address(0)); } EXPORT_SYMBOL(__stack_chk_fail); From 02735d5987b949f290ba65d491a714bba38de905 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 30 Oct 2018 15:10:24 -0700 Subject: [PATCH 180/299] mm/memory_hotplug: make add_memory() take the device_hotplug_lock [ Upstream commit 8df1d0e4a265f25dc1e7e7624ccdbcb4a6630c89 ] add_memory() currently does not take the device_hotplug_lock, however is aleady called under the lock from arch/powerpc/platforms/pseries/hotplug-memory.c drivers/acpi/acpi_memhotplug.c to synchronize against CPU hot-remove and similar. In general, we should hold the device_hotplug_lock when adding memory to synchronize against online/offline request (e.g. from user space) - which already resulted in lock inversions due to device_lock() and mem_hotplug_lock - see 30467e0b3be ("mm, hotplug: fix concurrent memory hot-add deadlock"). add_memory()/add_memory_resource() will create memory block devices, so this really feels like the right thing to do. Holding the device_hotplug_lock makes sure that a memory block device can really only be accessed (e.g. via .online/.state) from user space, once the memory has been fully added to the system. The lock is not held yet in drivers/xen/balloon.c arch/powerpc/platforms/powernv/memtrace.c drivers/s390/char/sclp_cmd.c drivers/hv/hv_balloon.c So, let's either use the locked variants or take the lock. Don't export add_memory_resource(), as it once was exported to be used by XEN, which is never built as a module. If somebody requires it, we also have to export a locked variant (as device_hotplug_lock is never exported). Link: http://lkml.kernel.org/r/20180925091457.28651-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Reviewed-by: Rafael J. Wysocki Reviewed-by: Rashmica Gupta Reviewed-by: Oscar Salvador Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Greg Kroah-Hartman Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Nathan Fontenot Cc: John Allen Cc: Michal Hocko Cc: Dan Williams Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Mathieu Malaterre Cc: Pavel Tatashin Cc: YASUAKI ISHIMATSU Cc: Balbir Singh Cc: Haiyang Zhang Cc: Heiko Carstens Cc: Jonathan Corbet Cc: Kate Stewart Cc: "K. Y. Srinivasan" Cc: Martin Schwidefsky Cc: Michael Neuling Cc: Philippe Ombredanne Cc: Stephen Hemminger Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- .../platforms/pseries/hotplug-memory.c | 2 +- drivers/acpi/acpi_memhotplug.c | 2 +- drivers/base/memory.c | 9 ++++++-- drivers/xen/balloon.c | 3 +++ include/linux/memory_hotplug.h | 1 + mm/memory_hotplug.c | 22 ++++++++++++++++--- 6 files changed, 32 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 2f166136bb50..d93ff494e778 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -676,7 +676,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) nid = memory_add_physaddr_to_nid(lmb->base_addr); /* Add the memory */ - rc = add_memory(nid, lmb->base_addr, block_sz); + rc = __add_memory(nid, lmb->base_addr, block_sz); if (rc) { invalidate_lmb_associativity_index(lmb); return rc; diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c index 6b0d3ef7309c..2ccfbb61ca89 100644 --- a/drivers/acpi/acpi_memhotplug.c +++ b/drivers/acpi/acpi_memhotplug.c @@ -228,7 +228,7 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device) if (node < 0) node = memory_add_physaddr_to_nid(info->start_addr); - result = add_memory(node, info->start_addr, info->length); + result = __add_memory(node, info->start_addr, info->length); /* * If the memory block has been used by the kernel, add_memory() diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 85ee64d0a44e..07901cacfec6 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -519,15 +519,20 @@ memory_probe_store(struct device *dev, struct device_attribute *attr, if (phys_addr & ((pages_per_block << PAGE_SHIFT) - 1)) return -EINVAL; + ret = lock_device_hotplug_sysfs(); + if (ret) + goto out; + nid = memory_add_physaddr_to_nid(phys_addr); - ret = add_memory(nid, phys_addr, - MIN_MEMORY_BLOCK_SIZE * sections_per_block); + ret = __add_memory(nid, phys_addr, + MIN_MEMORY_BLOCK_SIZE * sections_per_block); if (ret) goto out; ret = count; out: + unlock_device_hotplug(); return ret; } diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index d4e8b717ce2b..747a15acbce3 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -350,7 +350,10 @@ static enum bp_state reserve_additional_memory(void) * callers drop the mutex before trying again. */ mutex_unlock(&balloon_mutex); + /* add_memory_resource() requires the device_hotplug lock */ + lock_device_hotplug(); rc = add_memory_resource(nid, resource, memhp_auto_online); + unlock_device_hotplug(); mutex_lock(&balloon_mutex); if (rc) { diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 34a28227068d..16487052017d 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -322,6 +322,7 @@ static inline void remove_memory(int nid, u64 start, u64 size) {} extern void __ref free_area_init_core_hotplug(int nid); extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)); +extern int __add_memory(int nid, u64 start, u64 size); extern int add_memory(int nid, u64 start, u64 size); extern int add_memory_resource(int nid, struct resource *resource, bool online); extern int arch_add_memory(int nid, u64 start, u64 size, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 7965112eb063..0db85bffa389 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1077,7 +1077,12 @@ static int online_memory_block(struct memory_block *mem, void *arg) return device_online(&mem->dev); } -/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ +/* + * NOTE: The caller must call lock_device_hotplug() to serialize hotplug + * and online/offline operations (triggered e.g. by sysfs). + * + * we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG + */ int __ref add_memory_resource(int nid, struct resource *res, bool online) { u64 start, size; @@ -1146,9 +1151,9 @@ out: mem_hotplug_done(); return ret; } -EXPORT_SYMBOL_GPL(add_memory_resource); -int __ref add_memory(int nid, u64 start, u64 size) +/* requires device_hotplug_lock, see add_memory_resource() */ +int __ref __add_memory(int nid, u64 start, u64 size) { struct resource *res; int ret; @@ -1162,6 +1167,17 @@ int __ref add_memory(int nid, u64 start, u64 size) release_memory_resource(res); return ret; } + +int add_memory(int nid, u64 start, u64 size) +{ + int rc; + + lock_device_hotplug(); + rc = __add_memory(nid, start, size); + unlock_device_hotplug(); + + return rc; +} EXPORT_SYMBOL_GPL(add_memory); #ifdef CONFIG_MEMORY_HOTREMOVE From 17523d7a1cc8c4dd79b078d8724c2af5ad2f3a4e Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 30 Oct 2018 15:10:29 -0700 Subject: [PATCH 181/299] mm/memory_hotplug: fix online/offline_pages called w.o. mem_hotplug_lock [ Upstream commit 381eab4a6ee81266f8dddc62e57376c7e584e5b8 ] There seem to be some problems as result of 30467e0b3be ("mm, hotplug: fix concurrent memory hot-add deadlock"), which tried to fix a possible lock inversion reported and discussed in [1] due to the two locks a) device_lock() b) mem_hotplug_lock While add_memory() first takes b), followed by a) during bus_probe_device(), onlining of memory from user space first took a), followed by b), exposing a possible deadlock. In [1], and it was decided to not make use of device_hotplug_lock, but rather to enforce a locking order. The problems I spotted related to this: 1. Memory block device attributes: While .state first calls mem_hotplug_begin() and the calls device_online() - which takes device_lock() - .online does no longer call mem_hotplug_begin(), so effectively calls online_pages() without mem_hotplug_lock. 2. device_online() should be called under device_hotplug_lock, however onlining memory during add_memory() does not take care of that. In addition, I think there is also something wrong about the locking in 3. arch/powerpc/platforms/powernv/memtrace.c calls offline_pages() without locks. This was introduced after 30467e0b3be. And skimming over the code, I assume it could need some more care in regards to locking (e.g. device_online() called without device_hotplug_lock. This will be addressed in the following patches. Now that we hold the device_hotplug_lock when - adding memory (e.g. via add_memory()/add_memory_resource()) - removing memory (e.g. via remove_memory()) - device_online()/device_offline() We can move mem_hotplug_lock usage back into online_pages()/offline_pages(). Why is mem_hotplug_lock still needed? Essentially to make get_online_mems()/put_online_mems() be very fast (relying on device_hotplug_lock would be very slow), and to serialize against addition of memory that does not create memory block devices (hmm). [1] http://driverdev.linuxdriverproject.org/pipermail/ driverdev-devel/ 2015-February/065324.html This patch is partly based on a patch by Vitaly Kuznetsov. Link: http://lkml.kernel.org/r/20180925091457.28651-4-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Reviewed-by: Rashmica Gupta Reviewed-by: Oscar Salvador Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Greg Kroah-Hartman Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Rashmica Gupta Cc: Michael Neuling Cc: Balbir Singh Cc: Kate Stewart Cc: Thomas Gleixner Cc: Philippe Ombredanne Cc: Pavel Tatashin Cc: Vlastimil Babka Cc: Dan Williams Cc: Oscar Salvador Cc: YASUAKI ISHIMATSU Cc: Mathieu Malaterre Cc: John Allen Cc: Jonathan Corbet Cc: Joonsoo Kim Cc: Nathan Fontenot Cc: Rafael J. Wysocki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- drivers/base/memory.c | 13 +------------ mm/memory_hotplug.c | 28 ++++++++++++++++++++-------- 2 files changed, 21 insertions(+), 20 deletions(-) diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 07901cacfec6..0f8e77f78cc8 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -228,7 +228,6 @@ static bool pages_correctly_probed(unsigned long start_pfn) /* * MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is * OK to have direct references to sparsemem variables in here. - * Must already be protected by mem_hotplug_begin(). */ static int memory_block_action(unsigned long phys_index, unsigned long action, int online_type) @@ -294,7 +293,6 @@ static int memory_subsys_online(struct device *dev) if (mem->online_type < 0) mem->online_type = MMOP_ONLINE_KEEP; - /* Already under protection of mem_hotplug_begin() */ ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE); /* clear online_type */ @@ -341,19 +339,11 @@ store_mem_state(struct device *dev, goto err; } - /* - * Memory hotplug needs to hold mem_hotplug_begin() for probe to find - * the correct memory block to online before doing device_online(dev), - * which will take dev->mutex. Take the lock early to prevent an - * inversion, memory_subsys_online() callbacks will be implemented by - * assuming it's already protected. - */ - mem_hotplug_begin(); - switch (online_type) { case MMOP_ONLINE_KERNEL: case MMOP_ONLINE_MOVABLE: case MMOP_ONLINE_KEEP: + /* mem->online_type is protected by device_hotplug_lock */ mem->online_type = online_type; ret = device_online(&mem->dev); break; @@ -364,7 +354,6 @@ store_mem_state(struct device *dev, ret = -EINVAL; /* should never happen */ } - mem_hotplug_done(); err: unlock_device_hotplug(); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0db85bffa389..3a0a87e7c40a 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -846,7 +846,6 @@ static struct zone * __meminit move_pfn_range(int online_type, int nid, return zone; } -/* Must be protected by mem_hotplug_begin() or a device_lock */ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type) { unsigned long flags; @@ -858,6 +857,8 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ struct memory_notify arg; struct memory_block *mem; + mem_hotplug_begin(); + /* * We can't use pfn_to_nid() because nid might be stored in struct page * which is not yet initialized. Instead, we find nid from memory block. @@ -923,6 +924,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ if (onlined_pages) memory_notify(MEM_ONLINE, &arg); + mem_hotplug_done(); return 0; failed_addition: @@ -930,6 +932,7 @@ failed_addition: (unsigned long long) pfn << PAGE_SHIFT, (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); + mem_hotplug_done(); return ret; } #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ @@ -1134,20 +1137,20 @@ int __ref add_memory_resource(int nid, struct resource *res, bool online) /* create new memmap entry */ firmware_map_add_hotplug(start, start + size, "System RAM"); + /* device_online() will take the lock when calling online_pages() */ + mem_hotplug_done(); + /* online pages if requested */ if (online) walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL, online_memory_block); - goto out; - + return ret; error: /* rollback pgdat allocation and others */ if (new_node) rollback_node_hotadd(nid); memblock_remove(start, size); - -out: mem_hotplug_done(); return ret; } @@ -1614,10 +1617,16 @@ static int __ref __offline_pages(unsigned long start_pfn, return -EINVAL; if (!IS_ALIGNED(end_pfn, pageblock_nr_pages)) return -EINVAL; + + mem_hotplug_begin(); + /* This makes hotplug much easier...and readable. we assume this for now. .*/ - if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) + if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, + &valid_end)) { + mem_hotplug_done(); return -EINVAL; + } zone = page_zone(pfn_to_page(valid_start)); node = zone_to_nid(zone); @@ -1626,8 +1635,10 @@ static int __ref __offline_pages(unsigned long start_pfn, /* set above range as isolated */ ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE, true); - if (ret) + if (ret) { + mem_hotplug_done(); return ret; + } arg.start_pfn = start_pfn; arg.nr_pages = nr_pages; @@ -1698,6 +1709,7 @@ repeat: writeback_set_ratelimit(); memory_notify(MEM_OFFLINE, &arg); + mem_hotplug_done(); return 0; failed_removal: @@ -1707,10 +1719,10 @@ failed_removal: memory_notify(MEM_CANCEL_OFFLINE, &arg); /* pushback to free area */ undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); + mem_hotplug_done(); return ret; } -/* Must be protected by mem_hotplug_begin() or a device_lock */ int offline_pages(unsigned long start_pfn, unsigned long nr_pages) { return __offline_pages(start_pfn, start_pfn + nr_pages); From 3081ae5e378f4ec1860b14457b03fe94e65374e7 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 30 Oct 2018 15:10:33 -0700 Subject: [PATCH 182/299] powerpc/powernv: hold device_hotplug_lock when calling device_online() [ Upstream commit cec1680591d6d5b10ecc10f370210089416e98af ] device_online() should be called with device_hotplug_lock() held. Link: http://lkml.kernel.org/r/20180925091457.28651-5-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Reviewed-by: Rashmica Gupta Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Rashmica Gupta Cc: Balbir Singh Cc: Michael Neuling Cc: Boris Ostrovsky Cc: Dan Williams Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Heiko Carstens Cc: John Allen Cc: Jonathan Corbet Cc: Joonsoo Kim Cc: Juergen Gross Cc: Kate Stewart Cc: "K. Y. Srinivasan" Cc: Len Brown Cc: Martin Schwidefsky Cc: Mathieu Malaterre Cc: Michal Hocko Cc: Nathan Fontenot Cc: Oscar Salvador Cc: Philippe Ombredanne Cc: Rafael J. Wysocki Cc: "Rafael J. Wysocki" Cc: Stephen Hemminger Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: YASUAKI ISHIMATSU Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- arch/powerpc/platforms/powernv/memtrace.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index 232bf5987f91..dd3cc4632b9a 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -244,9 +244,11 @@ static int memtrace_online(void) * we need to online the memory ourselves. */ if (!memhp_auto_online) { + lock_device_hotplug(); walk_memory_range(PFN_DOWN(ent->start), PFN_UP(ent->start + ent->size - 1), NULL, online_mem_block); + unlock_device_hotplug(); } /* From 2fed73906e97b57804c7e344838e88c1a1cc2b94 Mon Sep 17 00:00:00 2001 From: Miroslav Lichvar Date: Fri, 12 Oct 2018 13:13:39 +0200 Subject: [PATCH 183/299] igb: shorten maximum PHC timecounter update interval [ Upstream commit 094bf4d0e9657f6ea1ee3d7e07ce3970796949ce ] The timecounter needs to be updated at least once per ~550 seconds in order to avoid a 40-bit SYSTIM timestamp to be misinterpreted as an old timestamp. Since commit 500462a9d ("timers: Switch to a non-cascading wheel"), scheduling of delayed work seems to be less accurate and a requested delay of 540 seconds may actually be longer than 550 seconds. Shorten the delay to 480 seconds to be sure the timecounter is updated in time. This fixes an issue with HW timestamps on 82580/I350/I354 being off by ~1100 seconds for few seconds every ~9 minutes. Cc: Jacob Keller Cc: Richard Cochran Cc: Thomas Gleixner Signed-off-by: Miroslav Lichvar Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igb/igb_ptp.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 9f4d700e09df..29ced6b74d36 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -51,9 +51,15 @@ * * The 40 bit 82580 SYSTIM overflows every * 2^40 * 10^-9 / 60 = 18.3 minutes. + * + * SYSTIM is converted to real time using a timecounter. As + * timecounter_cyc2time() allows old timestamps, the timecounter + * needs to be updated at least once per half of the SYSTIM interval. + * Scheduling of delayed work is not very accurate, so we aim for 8 + * minutes to be sure the actual interval is shorter than 9.16 minutes. */ -#define IGB_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 9) +#define IGB_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 8) #define IGB_PTP_TX_TIMEOUT (HZ * 15) #define INCPERIOD_82576 BIT(E1000_TIMINCA_16NS_SHIFT) #define INCVALUE_82576_MASK GENMASK(E1000_TIMINCA_16NS_SHIFT - 1, 0) From 3d9bc014c519fc2fb755bb397a07332010d520ab Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 15 Oct 2018 12:18:28 -0700 Subject: [PATCH 184/299] fm10k: ensure completer aborts are marked as non-fatal after a resume [ Upstream commit e330af788998b0de4da4f5bd7ddd087507999800 ] VF drivers can trigger PCIe completer aborts any time they read a queue that they don't own. Even in nominal circumstances, it is not possible to prevent the VF driver from reading queues it doesn't own. VF drivers may attempt to read queues it previously owned, but which it no longer does due to a PF reset. Normally these completer aborts aren't an issue. However, on some platforms these trigger machine check errors. This is true even if we lower their severity from fatal to non-fatal. Indeed, we already have code for lowering the severity. We could attempt to mask these errors conditionally around resets, which is the most common time they would occur. However this would essentially be a race between the PF and VF drivers, and we may still occasionally see machine check exceptions on these strictly configured platforms. Instead, mask the errors entirely any time we resume VFs. By doing so, we prevent the completer aborts from being sent to the parent PCIe device, and thus these strict platforms will not upgrade them into machine check errors. Additionally, we don't lose any information by masking these errors, because we'll still report VFs which attempt to access queues via the FUM_BAD_VF_QACCESS errors. Without this change, on platforms where completer aborts cause machine check exceptions, the VF reading queues it doesn't own could crash the host system. Masking the completer abort prevents this, so we should mask it for good, and not just around a PCIe reset. Otherwise malicious or misconfigured VFs could cause the host system to crash. Because we are masking the error entirely, there is little reason to also keep setting the severity bit, so that code is also removed. Signed-off-by: Jacob Keller Signed-off-by: Jeff Kirsher Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/fm10k/fm10k_iov.c | 48 ++++++++++++-------- 1 file changed, 28 insertions(+), 20 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index e707d717012f..618032612f52 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -302,6 +302,28 @@ void fm10k_iov_suspend(struct pci_dev *pdev) } } +static void fm10k_mask_aer_comp_abort(struct pci_dev *pdev) +{ + u32 err_mask; + int pos; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); + if (!pos) + return; + + /* Mask the completion abort bit in the ERR_UNCOR_MASK register, + * preventing the device from reporting these errors to the upstream + * PCIe root device. This avoids bringing down platforms which upgrade + * non-fatal completer aborts into machine check exceptions. Completer + * aborts can occur whenever a VF reads a queue it doesn't own. + */ + pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, &err_mask); + err_mask |= PCI_ERR_UNC_COMP_ABORT; + pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, err_mask); + + mmiowb(); +} + int fm10k_iov_resume(struct pci_dev *pdev) { struct fm10k_intfc *interface = pci_get_drvdata(pdev); @@ -317,6 +339,12 @@ int fm10k_iov_resume(struct pci_dev *pdev) if (!iov_data) return -ENOMEM; + /* Lower severity of completer abort error reporting as + * the VFs can trigger this any time they read a queue + * that they don't own. + */ + fm10k_mask_aer_comp_abort(pdev); + /* allocate hardware resources for the VFs */ hw->iov.ops.assign_resources(hw, num_vfs, num_vfs); @@ -460,20 +488,6 @@ void fm10k_iov_disable(struct pci_dev *pdev) fm10k_iov_free_data(pdev); } -static void fm10k_disable_aer_comp_abort(struct pci_dev *pdev) -{ - u32 err_sev; - int pos; - - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); - if (!pos) - return; - - pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, &err_sev); - err_sev &= ~PCI_ERR_UNC_COMP_ABORT; - pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, err_sev); -} - int fm10k_iov_configure(struct pci_dev *pdev, int num_vfs) { int current_vfs = pci_num_vf(pdev); @@ -495,12 +509,6 @@ int fm10k_iov_configure(struct pci_dev *pdev, int num_vfs) /* allocate VFs if not already allocated */ if (num_vfs && num_vfs != current_vfs) { - /* Disable completer abort error reporting as - * the VFs can trigger this any time they read a queue - * that they don't own. - */ - fm10k_disable_aer_comp_abort(pdev); - err = pci_enable_sriov(pdev, num_vfs); if (err) { dev_err(&pdev->dev, From b0465d06d4c6bedde945864cc10cdf7a1da1f034 Mon Sep 17 00:00:00 2001 From: Huazhong Tan Date: Tue, 30 Oct 2018 21:50:44 +0800 Subject: [PATCH 185/299] net: hns3: bugfix for buffer not free problem during resetting [ Upstream commit 73b907a083b8a8c1c62cb494bc9fbe6ae086c460 ] When hns3_get_ring_config()/hns3_queue_to_ring()/ hns3_get_vector_ring_chain() failed during resetting, the allocated memory has not been freed before these three functions return. So this patch adds error handler in these functions to fix it. Fixes: 76ad4f0ee747 ("net: hns3: Add support of HNS3 Ethernet Driver for hip08 SoC") Signed-off-by: Huazhong Tan Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- .../net/ethernet/hisilicon/hns3/hns3_enet.c | 24 ++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index e11a7de20b8f..3708f149d0a6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2547,7 +2547,7 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, chain = devm_kzalloc(&pdev->dev, sizeof(*chain), GFP_KERNEL); if (!chain) - return -ENOMEM; + goto err_free_chain; cur_chain->next = chain; chain->tqp_index = tx_ring->tqp->tqp_index; @@ -2577,7 +2577,7 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, while (rx_ring) { chain = devm_kzalloc(&pdev->dev, sizeof(*chain), GFP_KERNEL); if (!chain) - return -ENOMEM; + goto err_free_chain; cur_chain->next = chain; chain->tqp_index = rx_ring->tqp->tqp_index; @@ -2592,6 +2592,16 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, } return 0; + +err_free_chain: + cur_chain = head->next; + while (cur_chain) { + chain = cur_chain->next; + devm_kfree(&pdev->dev, chain); + cur_chain = chain; + } + + return -ENOMEM; } static void hns3_free_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, @@ -2836,8 +2846,10 @@ static int hns3_queue_to_ring(struct hnae3_queue *tqp, return ret; ret = hns3_ring_get_cfg(tqp, priv, HNAE3_RING_TYPE_RX); - if (ret) + if (ret) { + devm_kfree(priv->dev, priv->ring_data[tqp->tqp_index].ring); return ret; + } return 0; } @@ -2864,6 +2876,12 @@ static int hns3_get_ring_config(struct hns3_nic_priv *priv) return 0; err: + while (i--) { + devm_kfree(priv->dev, priv->ring_data[i].ring); + devm_kfree(priv->dev, + priv->ring_data[i + h->kinfo.num_tqps].ring); + } + devm_kfree(&pdev->dev, priv->ring_data); return ret; } From e3345108409c720bbce563d02443bc85431dab09 Mon Sep 17 00:00:00 2001 From: Huazhong Tan Date: Tue, 30 Oct 2018 21:50:45 +0800 Subject: [PATCH 186/299] net: hns3: bugfix for reporting unknown vector0 interrupt repeatly problem [ Upstream commit 0d4411408a7fb9aad0645f23911d9bfdd2ce3177 ] The current driver supports handling two vector0 interrupts, reset and mailbox. When the hardware reports an interrupt of another type of interrupt source, if the driver does not process the interrupt, but enables the interrupt, the hardware will repeatedly report the unknown interrupt. Therefore, the driver enables the vector0 interrupt after clearing the known type of interrupt source. Other conditions are not enabled. Fixes: cd8c5c269b1d ("net: hns3: Fix for hclge_reset running repeatly problem") Signed-off-by: Huazhong Tan Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index b04df79f393f..f8cc8d1f0b20 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2574,7 +2574,7 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data) } /* clear the source of interrupt if it is not cause by reset */ - if (event_cause != HCLGE_VECTOR0_EVENT_RST) { + if (event_cause == HCLGE_VECTOR0_EVENT_MBX) { hclge_clear_event_cause(hdev, event_cause, clearval); hclge_enable_vector(&hdev->misc_vector, true); } From 12eeb72afac226d9cb4c5555ebbcfebcc57f76f9 Mon Sep 17 00:00:00 2001 From: Huazhong Tan Date: Tue, 30 Oct 2018 21:50:48 +0800 Subject: [PATCH 187/299] net: hns3: bugfix for is_valid_csq_clean_head() [ Upstream commit 6d71ec6cbf74ac9c2823ef751b1baa5b889bb3ac ] The HEAD pointer of the hardware command queue maybe equal to the command queue's next_to_use in the driver, so that does not belong to the invalid HEAD pointer, since the hardware may not process the command in time, causing the HEAD pointer to be too late to update. The variables' name in this function is unreadable, so give them a more readable one. Fixes: 3ff504908f95 ("net: hns3: fix a dead loop in hclge_cmd_csq_clean") Signed-off-by: Huazhong Tan Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index 68026a5ad7e7..690f62ed87dc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -24,15 +24,15 @@ static int hclge_ring_space(struct hclge_cmq_ring *ring) return ring->desc_num - used - 1; } -static int is_valid_csq_clean_head(struct hclge_cmq_ring *ring, int h) +static int is_valid_csq_clean_head(struct hclge_cmq_ring *ring, int head) { - int u = ring->next_to_use; - int c = ring->next_to_clean; + int ntu = ring->next_to_use; + int ntc = ring->next_to_clean; - if (unlikely(h >= ring->desc_num)) - return 0; + if (ntu > ntc) + return head >= ntc && head <= ntu; - return u > c ? (h > c && h <= u) : (h > c || h <= u); + return head >= ntc || head <= ntu; } static int hclge_alloc_cmd_desc(struct hclge_cmq_ring *ring) From 8dbecf6c2f1737249701522e93c7952083a12826 Mon Sep 17 00:00:00 2001 From: Huazhong Tan Date: Tue, 30 Oct 2018 21:50:49 +0800 Subject: [PATCH 188/299] net: hns3: bugfix for hclge_mdio_write and hclge_mdio_read [ Upstream commit 1c12493809924deda6c0834cb2f2c5a6dc786390 ] When there is a PHY, the driver needs to complete some operations through MDIO during reset reinitialization, so HCLGE_STATE_CMD_DISABLE is more suitable than HCLGE_STATE_RST_HANDLING to prevent the MDIO operation from being sent during the hardware reset. Fixes: b50ae26c57cb ("net: hns3: never send command queue message to IMP when reset) Signed-off-by: Huazhong Tan Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index 398971a062f4..03491e8ebb73 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -54,7 +54,7 @@ static int hclge_mdio_write(struct mii_bus *bus, int phyid, int regnum, struct hclge_desc desc; int ret; - if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) + if (test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) return 0; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MDIO_CONFIG, false); @@ -92,7 +92,7 @@ static int hclge_mdio_read(struct mii_bus *bus, int phyid, int regnum) struct hclge_desc desc; int ret; - if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) + if (test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) return 0; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MDIO_CONFIG, true); From 3bd4422af874152e95c743f71b86d57fc0a0d4d8 Mon Sep 17 00:00:00 2001 From: Jon Mason Date: Mon, 11 Jun 2018 16:13:12 -0400 Subject: [PATCH 189/299] ntb_netdev: fix sleep time mismatch [ Upstream commit a861594b1b7ffd630f335b351c4e9f938feadb8e ] The tx_time should be in usecs (according to the comment above the variable), but the setting of the timer during the rearming is done in msecs. Change it to match the expected units. Fixes: e74bfeedad08 ("NTB: Add flow control to the ntb_netdev") Suggested-by: Gerd W. Haeussler Signed-off-by: Jon Mason Acked-by: Dave Jiang Signed-off-by: Sasha Levin --- drivers/net/ntb_netdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index b12023bc2cab..df8d49ad48c3 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -236,7 +236,7 @@ static void ntb_netdev_tx_timer(struct timer_list *t) struct net_device *ndev = dev->ndev; if (ntb_transport_tx_free_entry(dev->qp) < tx_stop) { - mod_timer(&dev->tx_timer, jiffies + msecs_to_jiffies(tx_time)); + mod_timer(&dev->tx_timer, jiffies + usecs_to_jiffies(tx_time)); } else { /* Make sure anybody stopping the queue after this sees the new * value of ntb_transport_tx_free_entry() From ad8298fccd706b6c5fd23c20c77a1d38ecb34609 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Tue, 28 Aug 2018 17:13:59 -0700 Subject: [PATCH 190/299] ntb: intel: fix return value for ndev_vec_mask() [ Upstream commit 7756e2b5d68c36e170a111dceea22f7365f83256 ] ndev_vec_mask() should be returning u64 mask value instead of int. Otherwise the mask value returned can be incorrect for larger vectors. Fixes: e26a5843f7f5 ("NTB: Split ntb_hw_intel and ntb_transport drivers") Signed-off-by: Dave Jiang Tested-by: Lucas Van Signed-off-by: Jon Mason Signed-off-by: Sasha Levin --- drivers/ntb/hw/intel/ntb_hw_gen1.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ntb/hw/intel/ntb_hw_gen1.c b/drivers/ntb/hw/intel/ntb_hw_gen1.c index 6aa573227279..2ad263f708da 100644 --- a/drivers/ntb/hw/intel/ntb_hw_gen1.c +++ b/drivers/ntb/hw/intel/ntb_hw_gen1.c @@ -265,7 +265,7 @@ static inline int ndev_db_clear_mask(struct intel_ntb_dev *ndev, u64 db_bits, return 0; } -static inline int ndev_vec_mask(struct intel_ntb_dev *ndev, int db_vector) +static inline u64 ndev_vec_mask(struct intel_ntb_dev *ndev, int db_vector) { u64 shift, mask; From 0bbb8382db4c8c7d1b0dc894f3364719d91dbf7e Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Thu, 1 Nov 2018 00:35:05 +0000 Subject: [PATCH 191/299] irq/matrix: Fix memory overallocation [ Upstream commit 57f01796f14fecf00d330fe39c8d2477ced9cd79 ] IRQ_MATRIX_SIZE is the number of longs needed for a bitmap, multiplied by the size of a long, yielding a byte count. But it is used to size an array of longs, which is way more memory than is needed. Change IRQ_MATRIX_SIZE so it is just the number of longs needed and the arrays come out the correct size. Fixes: 2f75d9e1c905 ("genirq: Implement bitmap matrix allocator") Signed-off-by: Michael Kelley Signed-off-by: Thomas Gleixner Cc: KY Srinivasan Link: https://lkml.kernel.org/r/1541032428-10392-1-git-send-email-mikelley@microsoft.com Signed-off-by: Sasha Levin --- kernel/irq/matrix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index 92337703ca9f..30cc217b8631 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -8,7 +8,7 @@ #include #include -#define IRQ_MATRIX_SIZE (BITS_TO_LONGS(IRQ_MATRIX_BITS) * sizeof(unsigned long)) +#define IRQ_MATRIX_SIZE (BITS_TO_LONGS(IRQ_MATRIX_BITS)) struct cpumap { unsigned int available; From fa7f1bce27c064c204d942cc31c31a4c4cef451a Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 31 Oct 2018 13:15:29 -0600 Subject: [PATCH 192/299] nvme-pci: fix conflicting p2p resource adds [ Upstream commit 9fe5c59ff6a1e5e26a39b75489a1420e7eaaf0b1 ] The nvme pci driver had been adding its CMB resource to the P2P DMA subsystem everytime on on a controller reset. This results in the following warning: ------------[ cut here ]------------ nvme 0000:00:03.0: Conflicting mapping in same section WARNING: CPU: 7 PID: 81 at kernel/memremap.c:155 devm_memremap_pages+0xa6/0x380 ... Call Trace: pci_p2pdma_add_resource+0x153/0x370 nvme_reset_work+0x28c/0x17b1 [nvme] ? add_timer+0x107/0x1e0 ? dequeue_entity+0x81/0x660 ? dequeue_entity+0x3b0/0x660 ? pick_next_task_fair+0xaf/0x610 ? __switch_to+0xbc/0x410 process_one_work+0x1cf/0x350 worker_thread+0x215/0x3d0 ? process_one_work+0x350/0x350 kthread+0x107/0x120 ? kthread_park+0x80/0x80 ret_from_fork+0x1f/0x30 ---[ end trace f7ea76ac6ee72727 ]--- nvme nvme0: failed to register the CMB This patch fixes this by registering the CMB with P2P only once. Signed-off-by: Keith Busch Reviewed-by: Logan Gunthorpe Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/nvme/host/pci.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 9479c0db08f6..124f41157173 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1652,6 +1652,9 @@ static void nvme_map_cmb(struct nvme_dev *dev) struct pci_dev *pdev = to_pci_dev(dev->dev); int bar; + if (dev->cmb_size) + return; + dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ); if (!dev->cmbsz) return; @@ -2136,7 +2139,6 @@ static void nvme_pci_disable(struct nvme_dev *dev) { struct pci_dev *pdev = to_pci_dev(dev->dev); - nvme_release_cmb(dev); pci_free_irq_vectors(pdev); if (pci_is_enabled(pdev)) { @@ -2595,6 +2597,7 @@ static void nvme_remove(struct pci_dev *pdev) nvme_stop_ctrl(&dev->ctrl); nvme_remove_namespaces(&dev->ctrl); nvme_dev_disable(dev, true); + nvme_release_cmb(dev); nvme_free_host_mem(dev); nvme_dev_remove_admin(dev); nvme_free_queues(dev, 0); From b167fee4e45d51d69c68dcd0a3495e576e7d6190 Mon Sep 17 00:00:00 2001 From: Victor Kamensky Date: Tue, 30 Oct 2018 16:37:10 -0700 Subject: [PATCH 193/299] arm64: makefile fix build of .i file in external module case [ Upstream commit 98356eb0ae499c63e78073ccedd9a5fc5c563288 ] After 'a66649dab350 arm64: fix vdso-offsets.h dependency' if one will try to build .i file in case of external kernel module, build fails complaining that prepare0 target is missing. This issue came up with SystemTap when it tries to build variety of .i files for its own generated kernel modules trying to figure given kernel features/capabilities. The issue is that prepare0 is defined in top level Makefile only if KBUILD_EXTMOD is not defined. .i file rule depends on prepare and in case KBUILD_EXTMOD defined top level Makefile contains empty rule for prepare. But after mentioned commit arch/arm64/Makefile would introduce dependency on prepare0 through its own prepare target. Fix it to put proper ifdef KBUILD_EXTMOD around code introduced by mentioned commit. It matches what top level Makefile does. Acked-by: Kevin Brodsky Signed-off-by: Victor Kamensky Signed-off-by: Catalin Marinas Signed-off-by: Sasha Levin --- arch/arm64/Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 5d8787f0ca5f..9a5e28141211 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -148,6 +148,7 @@ archclean: $(Q)$(MAKE) $(clean)=$(boot) $(Q)$(MAKE) $(clean)=$(boot)/dts +ifeq ($(KBUILD_EXTMOD),) # We need to generate vdso-offsets.h before compiling certain files in kernel/. # In order to do that, we should use the archprepare target, but we can't since # asm-offsets.h is included in some files used to generate vdso-offsets.h, and @@ -157,6 +158,7 @@ archclean: prepare: vdso_prepare vdso_prepare: prepare0 $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso include/generated/vdso-offsets.h +endif define archhelp echo '* Image.gz - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)' From 08f07d9f5b17c5d1e0c4bafb75840e4f7ad6b764 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Tue, 7 Aug 2018 20:22:28 -0400 Subject: [PATCH 194/299] tools/power turbosat: fix AMD APIC-id output [ Upstream commit 3404155190ce09a1e5d8407e968fc19aac4493e3 ] turbostat recently gained a feature adding APIC and X2APIC columns. While they are disabled by-default, they are enabled with --debug or when explicitly requested, eg. $ sudo turbostat --quiet --show Package,Node,Core,CPU,APIC,X2APIC date But these columns erroneously showed zeros on AMD hardware. This patch corrects the APIC and X2APIC [sic] columns on AMD. Signed-off-by: Len Brown Signed-off-by: Sasha Levin --- tools/power/x86/turbostat/turbostat.c | 97 +++++++++++++++++---------- 1 file changed, 62 insertions(+), 35 deletions(-) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 823bbc741ad7..02d123871ef9 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -1,6 +1,6 @@ /* * turbostat -- show CPU frequency and C-state residency - * on modern Intel turbo-capable processors. + * on modern Intel and AMD processors. * * Copyright (c) 2013 Intel Corporation. * Len Brown @@ -71,6 +71,8 @@ unsigned int do_irtl_snb; unsigned int do_irtl_hsw; unsigned int units = 1000000; /* MHz etc */ unsigned int genuine_intel; +unsigned int authentic_amd; +unsigned int max_level, max_extended_level; unsigned int has_invariant_tsc; unsigned int do_nhm_platform_info; unsigned int no_MSR_MISC_PWR_MGMT; @@ -1667,30 +1669,51 @@ int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp) void get_apic_id(struct thread_data *t) { - unsigned int eax, ebx, ecx, edx, max_level; + unsigned int eax, ebx, ecx, edx; - eax = ebx = ecx = edx = 0; + if (DO_BIC(BIC_APIC)) { + eax = ebx = ecx = edx = 0; + __cpuid(1, eax, ebx, ecx, edx); + + t->apic_id = (ebx >> 24) & 0xff; + } + + if (!DO_BIC(BIC_X2APIC)) + return; + + if (authentic_amd) { + unsigned int topology_extensions; + + if (max_extended_level < 0x8000001e) + return; + + eax = ebx = ecx = edx = 0; + __cpuid(0x80000001, eax, ebx, ecx, edx); + topology_extensions = ecx & (1 << 22); + + if (topology_extensions == 0) + return; + + eax = ebx = ecx = edx = 0; + __cpuid(0x8000001e, eax, ebx, ecx, edx); + + t->x2apic_id = eax; + return; + } if (!genuine_intel) return; - __cpuid(0, max_level, ebx, ecx, edx); - - __cpuid(1, eax, ebx, ecx, edx); - t->apic_id = (ebx >> 24) & 0xf; - if (max_level < 0xb) return; - if (!DO_BIC(BIC_X2APIC)) - return; - ecx = 0; __cpuid(0xb, eax, ebx, ecx, edx); t->x2apic_id = edx; - if (debug && (t->apic_id != t->x2apic_id)) - fprintf(outf, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id); + if (debug && (t->apic_id != (t->x2apic_id & 0xff))) + fprintf(outf, "cpu%d: BIOS BUG: apic 0x%x x2apic 0x%x\n", + t->cpu_id, t->apic_id, t->x2apic_id); } /* @@ -4439,16 +4462,18 @@ void decode_c6_demotion_policy_msr(void) void process_cpuid() { - unsigned int eax, ebx, ecx, edx, max_level, max_extended_level; - unsigned int fms, family, model, stepping; + unsigned int eax, ebx, ecx, edx; + unsigned int fms, family, model, stepping, ecx_flags, edx_flags; unsigned int has_turbo; eax = ebx = ecx = edx = 0; __cpuid(0, max_level, ebx, ecx, edx); - if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e) + if (ebx == 0x756e6547 && ecx == 0x6c65746e && edx == 0x49656e69) genuine_intel = 1; + else if (ebx == 0x68747541 && ecx == 0x444d4163 && edx == 0x69746e65) + authentic_amd = 1; if (!quiet) fprintf(outf, "CPUID(0): %.4s%.4s%.4s ", @@ -4462,25 +4487,8 @@ void process_cpuid() family += (fms >> 20) & 0xff; if (family >= 6) model += ((fms >> 16) & 0xf) << 4; - - if (!quiet) { - fprintf(outf, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n", - max_level, family, model, stepping, family, model, stepping); - fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s %s\n", - ecx & (1 << 0) ? "SSE3" : "-", - ecx & (1 << 3) ? "MONITOR" : "-", - ecx & (1 << 6) ? "SMX" : "-", - ecx & (1 << 7) ? "EIST" : "-", - ecx & (1 << 8) ? "TM2" : "-", - edx & (1 << 4) ? "TSC" : "-", - edx & (1 << 5) ? "MSR" : "-", - edx & (1 << 22) ? "ACPI-TM" : "-", - edx & (1 << 28) ? "HT" : "-", - edx & (1 << 29) ? "TM" : "-"); - } - - if (!(edx & (1 << 5))) - errx(1, "CPUID: no MSR"); + ecx_flags = ecx; + edx_flags = edx; /* * check max extended function levels of CPUID. @@ -4490,6 +4498,25 @@ void process_cpuid() ebx = ecx = edx = 0; __cpuid(0x80000000, max_extended_level, ebx, ecx, edx); + if (!quiet) { + fprintf(outf, "0x%x CPUID levels; 0x%x xlevels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n", + max_level, max_extended_level, family, model, stepping, family, model, stepping); + fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s %s\n", + ecx_flags & (1 << 0) ? "SSE3" : "-", + ecx_flags & (1 << 3) ? "MONITOR" : "-", + ecx_flags & (1 << 6) ? "SMX" : "-", + ecx_flags & (1 << 7) ? "EIST" : "-", + ecx_flags & (1 << 8) ? "TM2" : "-", + edx_flags & (1 << 4) ? "TSC" : "-", + edx_flags & (1 << 5) ? "MSR" : "-", + edx_flags & (1 << 22) ? "ACPI-TM" : "-", + edx_flags & (1 << 28) ? "HT" : "-", + edx_flags & (1 << 29) ? "TM" : "-"); + } + + if (!(edx_flags & (1 << 5))) + errx(1, "CPUID: no MSR"); + if (max_extended_level >= 0x80000007) { /* From 6a2245d828e4627df8927957b30602a04d9c2f07 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 2 Nov 2018 15:47:49 -0700 Subject: [PATCH 195/299] mm: handle no memcg case in memcg_kmem_charge() properly [ Upstream commit e68599a3c3ad0f3171a7cb4e48aa6f9a69381902 ] Mike Galbraith reported a regression caused by the commit 9b6f7e163cd0 ("mm: rework memcg kernel stack accounting") on a system with "cgroup_disable=memory" boot option: the system panics with the following stack trace: BUG: unable to handle kernel NULL pointer dereference at 00000000000000f8 PGD 0 P4D 0 Oops: 0002 [#1] PREEMPT SMP PTI CPU: 0 PID: 1 Comm: systemd Not tainted 4.19.0-preempt+ #410 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20180531_142017-buildhw-08.phx2.fed4 RIP: 0010:page_counter_try_charge+0x22/0xc0 Code: 41 5d c3 c3 0f 1f 40 00 0f 1f 44 00 00 48 85 ff 0f 84 a7 00 00 00 41 56 48 89 f8 49 89 fe 49 Call Trace: try_charge+0xcb/0x780 memcg_kmem_charge_memcg+0x28/0x80 memcg_kmem_charge+0x8b/0x1d0 copy_process.part.41+0x1ca/0x2070 _do_fork+0xd7/0x3d0 do_syscall_64+0x5a/0x180 entry_SYSCALL_64_after_hwframe+0x49/0xbe The problem occurs because get_mem_cgroup_from_current() returns the NULL pointer if memory controller is disabled. Let's check if this is a case at the beginning of memcg_kmem_charge() and just return 0 if mem_cgroup_disabled() returns true. This is how we handle this case in many other places in the memory controller code. Link: http://lkml.kernel.org/r/20181029215123.17830-1-guro@fb.com Fixes: 9b6f7e163cd0 ("mm: rework memcg kernel stack accounting") Signed-off-by: Roman Gushchin Reported-by: Mike Galbraith Acked-by: Rik van Riel Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Vladimir Davydov Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5af38d8a9afd..3a3d109dce21 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2678,7 +2678,7 @@ int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) struct mem_cgroup *memcg; int ret = 0; - if (memcg_kmem_bypass()) + if (mem_cgroup_disabled() || memcg_kmem_bypass()) return 0; memcg = get_mem_cgroup_from_current(); From abc7968b86b1d09e1798341760197f6d1e9071f5 Mon Sep 17 00:00:00 2001 From: Guozhonghua Date: Fri, 2 Nov 2018 15:48:07 -0700 Subject: [PATCH 196/299] ocfs2: without quota support, avoid calling quota recovery [ Upstream commit 21158ca85b73ddd0088076a5209cfd040513a8b5 ] During one dead node's recovery by other node, quota recovery work will be queued. We should avoid calling quota when it is not supported, so check the quota flags. Link: http://lkml.kernel.org/r/71604351584F6A4EBAE558C676F37CA401071AC9FB@H3CMLB12-EX.srv.huawei-3com.com Signed-off-by: guozhonghua Reviewed-by: Jan Kara Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Joseph Qi Cc: Changwei Ge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/ocfs2/journal.c | 51 ++++++++++++++++++++++++++++++---------------- 1 file changed, 34 insertions(+), 17 deletions(-) diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index c492cbb2410f..babb0ec76d67 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1379,15 +1379,23 @@ static int __ocfs2_recovery_thread(void *arg) int rm_quota_used = 0, i; struct ocfs2_quota_recovery *qrec; + /* Whether the quota supported. */ + int quota_enabled = OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, + OCFS2_FEATURE_RO_COMPAT_USRQUOTA) + || OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, + OCFS2_FEATURE_RO_COMPAT_GRPQUOTA); + status = ocfs2_wait_on_mount(osb); if (status < 0) { goto bail; } - rm_quota = kcalloc(osb->max_slots, sizeof(int), GFP_NOFS); - if (!rm_quota) { - status = -ENOMEM; - goto bail; + if (quota_enabled) { + rm_quota = kcalloc(osb->max_slots, sizeof(int), GFP_NOFS); + if (!rm_quota) { + status = -ENOMEM; + goto bail; + } } restart: status = ocfs2_super_lock(osb, 1); @@ -1423,9 +1431,14 @@ restart: * then quota usage would be out of sync until some node takes * the slot. So we remember which nodes need quota recovery * and when everything else is done, we recover quotas. */ - for (i = 0; i < rm_quota_used && rm_quota[i] != slot_num; i++); - if (i == rm_quota_used) - rm_quota[rm_quota_used++] = slot_num; + if (quota_enabled) { + for (i = 0; i < rm_quota_used + && rm_quota[i] != slot_num; i++) + ; + + if (i == rm_quota_used) + rm_quota[rm_quota_used++] = slot_num; + } status = ocfs2_recover_node(osb, node_num, slot_num); skip_recovery: @@ -1453,16 +1466,19 @@ skip_recovery: /* Now it is right time to recover quotas... We have to do this under * superblock lock so that no one can start using the slot (and crash) * before we recover it */ - for (i = 0; i < rm_quota_used; i++) { - qrec = ocfs2_begin_quota_recovery(osb, rm_quota[i]); - if (IS_ERR(qrec)) { - status = PTR_ERR(qrec); - mlog_errno(status); - continue; + if (quota_enabled) { + for (i = 0; i < rm_quota_used; i++) { + qrec = ocfs2_begin_quota_recovery(osb, rm_quota[i]); + if (IS_ERR(qrec)) { + status = PTR_ERR(qrec); + mlog_errno(status); + continue; + } + ocfs2_queue_recovery_completion(osb->journal, + rm_quota[i], + NULL, NULL, qrec, + ORPHAN_NEED_TRUNCATE); } - ocfs2_queue_recovery_completion(osb->journal, rm_quota[i], - NULL, NULL, qrec, - ORPHAN_NEED_TRUNCATE); } ocfs2_super_unlock(osb, 1); @@ -1484,7 +1500,8 @@ bail: mutex_unlock(&osb->recovery_lock); - kfree(rm_quota); + if (quota_enabled) + kfree(rm_quota); /* no one is callint kthread_stop() for us so the kthread() api * requires that we call do_exit(). And it isn't exported, but From 6fd469d06eb840462329b60239b5f235cee9e925 Mon Sep 17 00:00:00 2001 From: Changwei Ge Date: Fri, 2 Nov 2018 15:48:11 -0700 Subject: [PATCH 197/299] ocfs2: don't use iocb when EIOCBQUEUED returns [ Upstream commit 9e985787750db8aae87f02b67e908f28ac4d6b83 ] When -EIOCBQUEUED returns, it means that aio_complete() will be called from dio_complete(), which is an asynchronous progress against write_iter. Generally, IO is a very slow progress than executing instruction, but we still can't take the risk to access a freed iocb. And we do face a BUG crash issue. Using the crash tool, iocb is obviously freed already. crash> struct -x kiocb ffff881a350f5900 struct kiocb { ki_filp = 0xffff881a350f5a80, ki_pos = 0x0, ki_complete = 0x0, private = 0x0, ki_flags = 0x0 } And the backtrace shows: ocfs2_file_write_iter+0xcaa/0xd00 [ocfs2] aio_run_iocb+0x229/0x2f0 do_io_submit+0x291/0x540 SyS_io_submit+0x10/0x20 system_call_fastpath+0x16/0x75 Link: http://lkml.kernel.org/r/1523361653-14439-1-git-send-email-ge.changwei@h3c.com Signed-off-by: Changwei Ge Reviewed-by: Andrew Morton Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Joseph Qi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/ocfs2/file.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index a847fe52c56e..a3e077fcfeb9 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2389,7 +2389,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb, written = __generic_file_write_iter(iocb, from); /* buffered aio wouldn't have proper lock coverage today */ - BUG_ON(written == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT)); + BUG_ON(written == -EIOCBQUEUED && !direct_io); /* * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io @@ -2509,7 +2509,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb, trace_generic_file_read_iter_ret(ret); /* buffered aio wouldn't have proper lock coverage today */ - BUG_ON(ret == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT)); + BUG_ON(ret == -EIOCBQUEUED && !direct_io); /* see ocfs2_file_write_iter */ if (ret == -EIOCBQUEUED || !ocfs2_iocb_is_rw_locked(iocb)) { From 6c150df9c2e80b5cf86f5a0d98beb7390ad63bfc Mon Sep 17 00:00:00 2001 From: Changwei Ge Date: Fri, 2 Nov 2018 15:48:19 -0700 Subject: [PATCH 198/299] ocfs2: don't put and assigning null to bh allocated outside [ Upstream commit cf76c78595ca87548ca5e45c862ac9e0949c4687 ] ocfs2_read_blocks() and ocfs2_read_blocks_sync() are both used to read several blocks from disk. Currently, the input argument *bhs* can be NULL or NOT. It depends on the caller's behavior. If the function fails in reading blocks from disk, the corresponding bh will be assigned to NULL and put. Obviously, above process for non-NULL input bh is not appropriate. Because the caller doesn't even know its bhs are put and re-assigned. If buffer head is managed by caller, ocfs2_read_blocks and ocfs2_read_blocks_sync() should not evaluate it to NULL. It will cause caller accessing illegal memory, thus crash. Link: http://lkml.kernel.org/r/HK2PR06MB045285E0F4FBB561F9F2F9B3D5680@HK2PR06MB0452.apcprd06.prod.outlook.com Signed-off-by: Changwei Ge Reviewed-by: Guozhonghua Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Joseph Qi Cc: Changwei Ge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/ocfs2/buffer_head_io.c | 77 ++++++++++++++++++++++++++++++--------- 1 file changed, 59 insertions(+), 18 deletions(-) diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index 9f8250df99f1..f9b84f7a3e4b 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -99,25 +99,34 @@ out: return ret; } +/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it + * will be easier to handle read failure. + */ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, unsigned int nr, struct buffer_head *bhs[]) { int status = 0; unsigned int i; struct buffer_head *bh; + int new_bh = 0; trace_ocfs2_read_blocks_sync((unsigned long long)block, nr); if (!nr) goto bail; + /* Don't put buffer head and re-assign it to NULL if it is allocated + * outside since the caller can't be aware of this alternation! + */ + new_bh = (bhs[0] == NULL); + for (i = 0 ; i < nr ; i++) { if (bhs[i] == NULL) { bhs[i] = sb_getblk(osb->sb, block++); if (bhs[i] == NULL) { status = -ENOMEM; mlog_errno(status); - goto bail; + break; } } bh = bhs[i]; @@ -157,9 +166,26 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, submit_bh(REQ_OP_READ, 0, bh); } +read_failure: for (i = nr; i > 0; i--) { bh = bhs[i - 1]; + if (unlikely(status)) { + if (new_bh && bh) { + /* If middle bh fails, let previous bh + * finish its read and then put it to + * aovoid bh leak + */ + if (!buffer_jbd(bh)) + wait_on_buffer(bh); + put_bh(bh); + bhs[i - 1] = NULL; + } else if (bh && buffer_uptodate(bh)) { + clear_buffer_uptodate(bh); + } + continue; + } + /* No need to wait on the buffer if it's managed by JBD. */ if (!buffer_jbd(bh)) wait_on_buffer(bh); @@ -169,8 +195,7 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, * so we can safely record this and loop back * to cleanup the other buffers. */ status = -EIO; - put_bh(bh); - bhs[i - 1] = NULL; + goto read_failure; } } @@ -178,6 +203,9 @@ bail: return status; } +/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it + * will be easier to handle read failure. + */ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, struct buffer_head *bhs[], int flags, int (*validate)(struct super_block *sb, @@ -187,6 +215,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, int i, ignore_cache = 0; struct buffer_head *bh; struct super_block *sb = ocfs2_metadata_cache_get_super(ci); + int new_bh = 0; trace_ocfs2_read_blocks_begin(ci, (unsigned long long)block, nr, flags); @@ -212,6 +241,11 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, goto bail; } + /* Don't put buffer head and re-assign it to NULL if it is allocated + * outside since the caller can't be aware of this alternation! + */ + new_bh = (bhs[0] == NULL); + ocfs2_metadata_cache_io_lock(ci); for (i = 0 ; i < nr ; i++) { if (bhs[i] == NULL) { @@ -220,7 +254,8 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, ocfs2_metadata_cache_io_unlock(ci); status = -ENOMEM; mlog_errno(status); - goto bail; + /* Don't forget to put previous bh! */ + break; } } bh = bhs[i]; @@ -314,16 +349,27 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, } } - status = 0; - +read_failure: for (i = (nr - 1); i >= 0; i--) { bh = bhs[i]; if (!(flags & OCFS2_BH_READAHEAD)) { - if (status) { - /* Clear the rest of the buffers on error */ - put_bh(bh); - bhs[i] = NULL; + if (unlikely(status)) { + /* Clear the buffers on error including those + * ever succeeded in reading + */ + if (new_bh && bh) { + /* If middle bh fails, let previous bh + * finish its read and then put it to + * aovoid bh leak + */ + if (!buffer_jbd(bh)) + wait_on_buffer(bh); + put_bh(bh); + bhs[i] = NULL; + } else if (bh && buffer_uptodate(bh)) { + clear_buffer_uptodate(bh); + } continue; } /* We know this can't have changed as we hold the @@ -341,9 +387,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, * uptodate. */ status = -EIO; clear_buffer_needs_validate(bh); - put_bh(bh); - bhs[i] = NULL; - continue; + goto read_failure; } if (buffer_needs_validate(bh)) { @@ -353,11 +397,8 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, BUG_ON(buffer_jbd(bh)); clear_buffer_needs_validate(bh); status = validate(sb, bh); - if (status) { - put_bh(bh); - bhs[i] = NULL; - continue; - } + if (status) + goto read_failure; } } From 0d3b9ac2844fd0fe3eb2b19592aaced0abb0d6bb Mon Sep 17 00:00:00 2001 From: Larry Chen Date: Fri, 2 Nov 2018 15:48:27 -0700 Subject: [PATCH 199/299] ocfs2: fix clusters leak in ocfs2_defrag_extent() [ Upstream commit 6194ae4242dec0c9d604bc05df83aa9260a899e4 ] ocfs2_defrag_extent() might leak allocated clusters. When the file system has insufficient space, the number of claimed clusters might be less than the caller wants. If that happens, the original code might directly commit the transaction without returning clusters. This patch is based on code in ocfs2_add_clusters_in_btree(). [akpm@linux-foundation.org: include localalloc.h, reduce scope of data_ac] Link: http://lkml.kernel.org/r/20180904041621.16874-3-lchen@suse.com Signed-off-by: Larry Chen Reviewed-by: Andrew Morton Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Joseph Qi Cc: Changwei Ge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/ocfs2/move_extents.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index f55f82ca3425..1565dd8e8856 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -25,6 +25,7 @@ #include "ocfs2_ioctl.h" #include "alloc.h" +#include "localalloc.h" #include "aops.h" #include "dlmglue.h" #include "extent_map.h" @@ -222,6 +223,7 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, struct ocfs2_refcount_tree *ref_tree = NULL; u32 new_phys_cpos, new_len; u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos); + int need_free = 0; if ((ext_flags & OCFS2_EXT_REFCOUNTED) && *len) { BUG_ON(!ocfs2_is_refcount_inode(inode)); @@ -312,6 +314,7 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, if (!partial) { context->range->me_flags &= ~OCFS2_MOVE_EXT_FL_COMPLETE; ret = -ENOSPC; + need_free = 1; goto out_commit; } } @@ -336,6 +339,20 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, mlog_errno(ret); out_commit: + if (need_free && context->data_ac) { + struct ocfs2_alloc_context *data_ac = context->data_ac; + + if (context->data_ac->ac_which == OCFS2_AC_USE_LOCAL) + ocfs2_free_local_alloc_bits(osb, handle, data_ac, + new_phys_cpos, new_len); + else + ocfs2_free_clusters(handle, + data_ac->ac_inode, + data_ac->ac_bh, + ocfs2_clusters_to_blocks(osb->sb, new_phys_cpos), + new_len); + } + ocfs2_commit_trans(osb, handle); out_unlock_mutex: From f9fca78e6cf2a44504dac45761c5195973f49c29 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 31 Oct 2018 08:39:13 -0700 Subject: [PATCH 200/299] net: do not abort bulk send on BQL status [ Upstream commit fe60faa5063822f2d555f4f326c7dd72a60929bf ] Before calling dev_hard_start_xmit(), upper layers tried to cook optimal skb list based on BQL budget. Problem is that GSO packets can end up comsuming more than the BQL budget. Breaking the loop is not useful, since requeued packets are ahead of any packets still in the qdisc. It is also more expensive, since next TX completion will push these packets later, while skbs are not in cpu caches. It is also a behavior difference with TSO packets, that can break the BQL limit by a large amount. Note that drivers should use __netdev_tx_sent_queue() in order to have optimal xmit_more support, and avoid useless atomic operations as shown in the following patch. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/dev.c b/net/core/dev.c index e96c88b1465d..91179febdeee 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3277,7 +3277,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *de } skb = next; - if (netif_xmit_stopped(txq) && skb) { + if (netif_tx_queue_stopped(txq) && skb) { rc = NETDEV_TX_BUSY; break; } From ed023646c2cf2366d0d31beef688227b0a2bc15f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 2 Nov 2018 14:22:25 +0100 Subject: [PATCH 201/299] sched/topology: Fix off by one bug [ Upstream commit 993f0b0510dad98b4e6e39506834dab0d13fd539 ] With the addition of the NUMA identity level, we increased @level by one and will run off the end of the array in the distance sort loop. Fixed: 051f3ca02e46 ("sched/topology: Introduce NUMA identity node sched domain") Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar Signed-off-by: Sasha Levin --- kernel/sched/topology.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index c0a751464971..74b694392f2f 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1329,7 +1329,7 @@ void sched_init_numa(void) int level = 0; int i, j, k; - sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL); + sched_domains_numa_distance = kzalloc(sizeof(int) * (nr_node_ids + 1), GFP_KERNEL); if (!sched_domains_numa_distance) return; From 31bced01fe77f5164201190bb488f09575000c1d Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 26 Sep 2018 16:12:07 +0100 Subject: [PATCH 202/299] sched/fair: Don't increase sd->balance_interval on newidle balance [ Upstream commit 3f130a37c442d5c4d66531b240ebe9abfef426b5 ] When load_balance() fails to move some load because of task affinity, we end up increasing sd->balance_interval to delay the next periodic balance in the hopes that next time we look, that annoying pinned task(s) will be gone. However, idle_balance() pays no attention to sd->balance_interval, yet it will still lead to an increase in balance_interval in case of pinned tasks. If we're going through several newidle balances (e.g. we have a periodic task), this can lead to a huge increase of the balance_interval in a very small amount of time. To prevent that, don't increase the balance interval when going through a newidle balance. This is a similar approach to what is done in commit 58b26c4c0257 ("sched: Increment cache_nice_tries only on periodic lb"), where we disregard newidle balance and rely on periodic balance for more stable results. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Cc: Dietmar.Eggemann@arm.com Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: patrick.bellasi@arm.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1537974727-30788-2-git-send-email-valentin.schneider@arm.com Signed-off-by: Ingo Molnar Signed-off-by: Sasha Levin --- kernel/sched/fair.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index e5e8f6721872..f77fcd37b226 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8819,13 +8819,22 @@ out_all_pinned: sd->nr_balance_failed = 0; out_one_pinned: + ld_moved = 0; + + /* + * idle_balance() disregards balance intervals, so we could repeatedly + * reach this code, which would lead to balance_interval skyrocketting + * in a short amount of time. Skip the balance_interval increase logic + * to avoid that. + */ + if (env.idle == CPU_NEWLY_IDLE) + goto out; + /* tune up the balancing interval */ if (((env.flags & LBF_ALL_PINNED) && sd->balance_interval < MAX_PINNED_INTERVAL) || (sd->balance_interval < sd->max_interval)) sd->balance_interval *= 2; - - ld_moved = 0; out: return ld_moved; } From 465073e44fda4982af05fb2d518ef5ce99b1fbe6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 2 Nov 2018 16:36:55 +0100 Subject: [PATCH 203/299] openvswitch: fix linking without CONFIG_NF_CONNTRACK_LABELS [ Upstream commit a277d516de5f498c91d91189717ef7e01102ad27 ] When CONFIG_CC_OPTIMIZE_FOR_DEBUGGING is enabled, the compiler fails to optimize out a dead code path, which leads to a link failure: net/openvswitch/conntrack.o: In function `ovs_ct_set_labels': conntrack.c:(.text+0x2e60): undefined reference to `nf_connlabels_replace' In this configuration, we can take a shortcut, and completely remove the contrack label code. This may also help the regular optimization. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/openvswitch/conntrack.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 35ae64cbef33..46aa1aa51db4 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1199,7 +1199,8 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, &info->labels.mask); if (err) return err; - } else if (labels_nonzero(&info->labels.mask)) { + } else if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && + labels_nonzero(&info->labels.mask)) { err = ovs_ct_set_labels(ct, key, &info->labels.value, &info->labels.mask); if (err) From a2e6fe1f647f45ec3ad14922f05b34b8c4afd211 Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Mon, 8 Oct 2018 15:28:01 +0000 Subject: [PATCH 204/299] ARM: dts: imx6sx-sdb: Fix enet phy regulator [ Upstream commit 1ad9fb750a104f51851c092edd7b3553f0218428 ] Bindings for "fixed-regulator" only explicitly support "gpio" property, not "gpios". Fix by correcting the property name. The enet PHYs on imx6sx-sdb needs to be explicitly reset after a power cycle, this can be handled by the phy-reset-gpios property. Sadly this is not handled on suspend: the fec driver turns phy-supply off but doesn't assert phy-reset-gpios again on resume. Since additional phy-level work is required to support powering off the phy in suspend fix the problem by just marking the regulator as "boot-on" "always-on" so that it's never turned off. This behavior is equivalent to older releases. Keep the phy-reset-gpios property on fec anyway because it is a correct description of board design. This issue was exposed by commit efdfeb079cc3 ("regulator: fixed: Convert to use GPIO descriptor only") which causes the "gpios" property to also be parsed. Before that commit the "gpios" property had no effect, PHY reset was only handled in the the bootloader. This fixes linux-next boot failures previously reported here: https://lore.kernel.org/patchwork/patch/982437/#1177900 https://lore.kernel.org/patchwork/patch/994091/#1178304 Signed-off-by: Leonard Crestez Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx6sx-sdb.dtsi | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi index f8f31872fa14..d6d517e4922f 100644 --- a/arch/arm/boot/dts/imx6sx-sdb.dtsi +++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi @@ -115,7 +115,9 @@ regulator-name = "enet_3v3"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; - gpios = <&gpio2 6 GPIO_ACTIVE_LOW>; + gpio = <&gpio2 6 GPIO_ACTIVE_LOW>; + regulator-boot-on; + regulator-always-on; }; reg_pcie_gpio: regulator-pcie-gpio { @@ -178,6 +180,7 @@ phy-supply = <®_enet_3v3>; phy-mode = "rgmii"; phy-handle = <ðphy1>; + phy-reset-gpios = <&gpio2 7 GPIO_ACTIVE_LOW>; status = "okay"; mdio { @@ -371,6 +374,8 @@ MX6SX_PAD_RGMII1_RD3__ENET1_RX_DATA_3 0x3081 MX6SX_PAD_RGMII1_RX_CTL__ENET1_RX_EN 0x3081 MX6SX_PAD_ENET2_RX_CLK__ENET2_REF_CLK_25M 0x91 + /* phy reset */ + MX6SX_PAD_ENET2_CRS__GPIO2_IO_7 0x10b0 >; }; From 9cdfff0a5e61b0eed6f8a81f178939f06dc5b65b Mon Sep 17 00:00:00 2001 From: Icenowy Zheng Date: Thu, 18 Oct 2018 15:07:29 +0800 Subject: [PATCH 205/299] clk: sunxi-ng: enable so-said LDOs for A64 SoC's pll-mipi clock [ Upstream commit 859783d1390035e29ba850963bded2b4ffdf43b5 ] In the user manual of A64 SoC, the bit 22 and 23 of pll-mipi control register is called "LDO{1,2}_EN", and according to the BSP source code from Allwinner , the LDOs are enabled during the clock's enabling process. The clock failed to generate output if the two LDOs are not enabled. Add the two bits to the clock's gate bits, so that the LDOs are enabled when the PLL is enabled. Fixes: c6a0637460c2 ("clk: sunxi-ng: Add A64 clocks") Signed-off-by: Icenowy Zheng Signed-off-by: Maxime Ripard Signed-off-by: Sasha Levin --- drivers/clk/sunxi-ng/ccu-sun50i-a64.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c index ee9c12cf3f08..2a6098179921 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c @@ -158,7 +158,12 @@ static SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK(pll_gpu_clk, "pll-gpu", #define SUN50I_A64_PLL_MIPI_REG 0x040 static struct ccu_nkm pll_mipi_clk = { - .enable = BIT(31), + /* + * The bit 23 and 22 are called "LDO{1,2}_EN" on the SoC's + * user manual, and by experiments the PLL doesn't work without + * these bits toggled. + */ + .enable = BIT(31) | BIT(23) | BIT(22), .lock = BIT(28), .n = _SUNXI_CCU_MULT(8, 4), .k = _SUNXI_CCU_MULT_MIN(4, 2, 2), From 5dc441fbef91a8d05c0917942692d3c06d255e73 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 27 Sep 2018 12:27:11 -0700 Subject: [PATCH 206/299] soc: bcm: brcmstb: Fix re-entry point with a THUMB2_KERNEL [ Upstream commit fb14ada11d62fb849fc357a25ef8016ba438ba10 ] When the kernel is built with CONFIG_THUMB2_KERNEL we would set the kernel's resume entry point to be a function that is already built as Thumb-2 code while the boot agent doing the resume is in ARM mode, so this does not work. There is a header label defined: cpu_resume_arm which we can use to do the switching for us. Fixes: 0b741b8234c8 ("soc: bcm: brcmstb: Add support for S2/S3/S5 suspend states (ARM)") Signed-off-by: Florian Fainelli Signed-off-by: Sasha Levin --- drivers/soc/bcm/brcmstb/pm/pm-arm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soc/bcm/brcmstb/pm/pm-arm.c b/drivers/soc/bcm/brcmstb/pm/pm-arm.c index a5577dd5eb08..8ee06347447c 100644 --- a/drivers/soc/bcm/brcmstb/pm/pm-arm.c +++ b/drivers/soc/bcm/brcmstb/pm/pm-arm.c @@ -404,7 +404,7 @@ noinline int brcmstb_pm_s3_finish(void) { struct brcmstb_s3_params *params = ctrl.s3_params; dma_addr_t params_pa = ctrl.s3_params_pa; - phys_addr_t reentry = virt_to_phys(&cpu_resume); + phys_addr_t reentry = virt_to_phys(&cpu_resume_arm); enum bsp_initiate_command cmd; u32 flags; From 3c69a033b416cdebf455787f51750e3ab0c12718 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 10 Oct 2018 16:22:57 -0400 Subject: [PATCH 207/299] audit: print empty EXECVE args [ Upstream commit ea956d8be91edc702a98b7fe1f9463e7ca8c42ab ] Empty executable arguments were being skipped when printing out the list of arguments in an EXECVE record, making it appear they were somehow lost. Include empty arguments as an itemized empty string. Reproducer: autrace /bin/ls "" "/etc" ausearch --start recent -m execve -i | grep EXECVE type=EXECVE msg=audit(10/03/2018 13:04:03.208:1391) : argc=3 a0=/bin/ls a2=/etc With fix: type=EXECVE msg=audit(10/03/2018 21:51:38.290:194) : argc=3 a0=/bin/ls a1= a2=/etc type=EXECVE msg=audit(1538617898.290:194): argc=3 a0="/bin/ls" a1="" a2="/etc" Passes audit-testsuite. GH issue tracker at https://github.com/linux-audit/audit-kernel/issues/99 Signed-off-by: Richard Guy Briggs [PM: cleaned up the commit metadata] Signed-off-by: Paul Moore Signed-off-by: Sasha Levin --- kernel/auditsc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/auditsc.c b/kernel/auditsc.c index b2d1f043f17f..1513873e23bd 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1107,7 +1107,7 @@ static void audit_log_execve_info(struct audit_context *context, } /* write as much as we can to the audit log */ - if (len_buf > 0) { + if (len_buf >= 0) { /* NOTE: some magic numbers here - basically if we * can't fit a reasonable amount of data into the * existing audit buffer, flush it and start with From 811c8141d663e399f9413eba23eb046c98b16665 Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Sun, 4 Nov 2018 22:37:15 -0800 Subject: [PATCH 208/299] sock_diag: fix autoloading of the raw_diag module [ Upstream commit c34c1287778b080ed692c0a46a8e345206cc29e6 ] IPPROTO_RAW isn't registred as an inet protocol, so inet_protos[protocol] is always NULL for it. Cc: Cyrill Gorcunov Cc: Xin Long Fixes: bf2ae2e4bf93 ("sock_diag: request _diag module only when the family or proto has been registered") Signed-off-by: Andrei Vagin Reviewed-by: Cyrill Gorcunov Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/core/sock.c b/net/core/sock.c index 6c1107821776..ba4f843cdd1d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3347,6 +3347,7 @@ int sock_load_diag_module(int family, int protocol) #ifdef CONFIG_INET if (family == AF_INET && + protocol != IPPROTO_RAW && !rcu_access_pointer(inet_protos[protocol])) return -ENOENT; #endif From e6c6c0439a936e7fadc6a861cfa53ee61e43dae0 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Nov 2018 22:31:41 +0900 Subject: [PATCH 209/299] net: bpfilter: fix iptables failure if bpfilter_umh is disabled [ Upstream commit 97adaddaa6db7a8af81b9b11e30cbe3628cd6700 ] When iptables command is executed, ip_{set/get}sockopt() try to upload bpfilter.ko if bpfilter is enabled. if it couldn't find bpfilter.ko, command is failed. bpfilter.ko is generated if CONFIG_BPFILTER_UMH is enabled. ip_{set/get}sockopt() only checks CONFIG_BPFILTER. So that if CONFIG_BPFILTER is enabled and CONFIG_BPFILTER_UMH is disabled, iptables command is always failed. test config: CONFIG_BPFILTER=y # CONFIG_BPFILTER_UMH is not set test command: %iptables -L iptables: No chain/target/match by that name. Fixes: d2ba09c17a06 ("net: add skeleton of bpfilter kernel module") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv4/ip_sockglue.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index b7a26120d552..82f341e84fae 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1244,7 +1244,7 @@ int ip_setsockopt(struct sock *sk, int level, return -ENOPROTOOPT; err = do_ip_setsockopt(sk, level, optname, optval, optlen); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_SET_REPLACE && optname < BPFILTER_IPT_SET_MAX) err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen); @@ -1557,7 +1557,7 @@ int ip_getsockopt(struct sock *sk, int level, int err; err = do_ip_getsockopt(sk, level, optname, optval, optlen, 0); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_GET_INFO && optname < BPFILTER_IPT_GET_MAX) err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); @@ -1594,7 +1594,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, err = do_ip_getsockopt(sk, level, optname, optval, optlen, MSG_CMSG_COMPAT); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_GET_INFO && optname < BPFILTER_IPT_GET_MAX) err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); From 3ee72f30c1636c57c9fe0dbd925d25ecb10a9ff8 Mon Sep 17 00:00:00 2001 From: Nickhu Date: Thu, 25 Oct 2018 10:24:14 +0800 Subject: [PATCH 210/299] nds32: Fix bug in bitfield.h [ Upstream commit 9aaafac8cffa1c1edb66e19a63841b7c86be07ca ] There two bitfield bug for perfomance counter in bitfield.h: PFM_CTL_offSEL1 21 --> 16 PFM_CTL_offSEL2 27 --> 22 This commit fix it. Signed-off-by: Nickhu Acked-by: Greentime Hu Signed-off-by: Greentime Hu Signed-off-by: Sasha Levin --- arch/nds32/include/asm/bitfield.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/nds32/include/asm/bitfield.h b/arch/nds32/include/asm/bitfield.h index 8e84fc385b94..19b2841219ad 100644 --- a/arch/nds32/include/asm/bitfield.h +++ b/arch/nds32/include/asm/bitfield.h @@ -692,8 +692,8 @@ #define PFM_CTL_offKU1 13 /* Enable user mode event counting for PFMC1 */ #define PFM_CTL_offKU2 14 /* Enable user mode event counting for PFMC2 */ #define PFM_CTL_offSEL0 15 /* The event selection for PFMC0 */ -#define PFM_CTL_offSEL1 21 /* The event selection for PFMC1 */ -#define PFM_CTL_offSEL2 27 /* The event selection for PFMC2 */ +#define PFM_CTL_offSEL1 16 /* The event selection for PFMC1 */ +#define PFM_CTL_offSEL2 22 /* The event selection for PFMC2 */ /* bit 28:31 reserved */ #define PFM_CTL_mskEN0 ( 0x01 << PFM_CTL_offEN0 ) From 4a035f2643c6b05bbd029e1f509f8e3843a93552 Mon Sep 17 00:00:00 2001 From: Chiranjeevi Rapolu Date: Fri, 26 Oct 2018 11:34:30 -0400 Subject: [PATCH 211/299] media: ov13858: Check for possible null pointer [ Upstream commit 35629182eb8f931b0de6ed38c0efac58e922c801 ] Check for possible null pointer to avoid crash. Signed-off-by: Chiranjeevi Rapolu Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov13858.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/media/i2c/ov13858.c b/drivers/media/i2c/ov13858.c index 0e7a85c4996c..afd66d243403 100644 --- a/drivers/media/i2c/ov13858.c +++ b/drivers/media/i2c/ov13858.c @@ -1612,7 +1612,8 @@ static int ov13858_init_controls(struct ov13858 *ov13858) OV13858_NUM_OF_LINK_FREQS - 1, 0, link_freq_menu_items); - ov13858->link_freq->flags |= V4L2_CTRL_FLAG_READ_ONLY; + if (ov13858->link_freq) + ov13858->link_freq->flags |= V4L2_CTRL_FLAG_READ_ONLY; pixel_rate_max = link_freq_to_pixel_rate(link_freq_menu_items[0]); pixel_rate_min = link_freq_to_pixel_rate(link_freq_menu_items[1]); @@ -1635,7 +1636,8 @@ static int ov13858_init_controls(struct ov13858 *ov13858) ov13858->hblank = v4l2_ctrl_new_std( ctrl_hdlr, &ov13858_ctrl_ops, V4L2_CID_HBLANK, hblank, hblank, 1, hblank); - ov13858->hblank->flags |= V4L2_CTRL_FLAG_READ_ONLY; + if (ov13858->hblank) + ov13858->hblank->flags |= V4L2_CTRL_FLAG_READ_ONLY; exposure_max = mode->vts_def - 8; ov13858->exposure = v4l2_ctrl_new_std( From ea136e61e4df85f53c7fce53d2273c579cf6db9f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 3 Nov 2018 16:39:28 +0100 Subject: [PATCH 212/299] btrfs: avoid link error with CONFIG_NO_AUTO_INLINE [ Upstream commit 7e17916b35797396f681a3270245fd29c1e4c250 ] Note: this patch fixes a problem in a feature outside of btrfs ("kernel hacking: add a config option to disable compiler auto-inlining") and is applied ahead of time due to cross-subsystem dependencies. On 32-bit ARM with gcc-8, I see a link error with the addition of the CONFIG_NO_AUTO_INLINE option: fs/btrfs/super.o: In function `btrfs_statfs': super.c:(.text+0x67b8): undefined reference to `__aeabi_uldivmod' super.c:(.text+0x67fc): undefined reference to `__aeabi_uldivmod' super.c:(.text+0x6858): undefined reference to `__aeabi_uldivmod' super.c:(.text+0x6920): undefined reference to `__aeabi_uldivmod' super.c:(.text+0x693c): undefined reference to `__aeabi_uldivmod' fs/btrfs/super.o:super.c:(.text+0x6958): more undefined references to `__aeabi_uldivmod' follow So far this is the only file that shows the behavior, so I'd propose to just work around it by marking the functions as 'static inline' that normally get inlined here. The reference to __aeabi_uldivmod comes from a div_u64() which has an optimization for a constant division that uses a straight '/' operator when the result should be known to the compiler. My interpretation is that as we turn off inlining, gcc still expects the result to be constant but fails to use that constant value. Link: https://lkml.kernel.org/r/20181103153941.1881966-1-arnd@arndb.de Reviewed-by: Nikolay Borisov Reviewed-by: Changbin Du Signed-off-by: Arnd Bergmann [ add the note ] Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/super.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 8888337a95b6..ddbad8d50949 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1919,7 +1919,7 @@ restore: } /* Used to sort the devices by max_avail(descending sort) */ -static int btrfs_cmp_device_free_bytes(const void *dev_info1, +static inline int btrfs_cmp_device_free_bytes(const void *dev_info1, const void *dev_info2) { if (((struct btrfs_device_info *)dev_info1)->max_avail > @@ -1948,8 +1948,8 @@ static inline void btrfs_descending_sort_devices( * The helper to calc the free space on the devices that can be used to store * file data. */ -static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, - u64 *free_bytes) +static inline int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, + u64 *free_bytes) { struct btrfs_device_info *devices_info; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; From aa2112d571521b68cfdb82d399a517041e9c4b7c Mon Sep 17 00:00:00 2001 From: Ahmad Masri Date: Wed, 31 Oct 2018 10:52:18 +0200 Subject: [PATCH 213/299] wil6210: fix debugfs memory access alignment [ Upstream commit 84ec040d0fb25197584d28a0dedc355503cd19b9 ] All wil6210 device memory access should be 4 bytes aligned. In io blob wil6210 did not force alignment for read function, this caused alignment fault on some platforms. Fixing that by accessing all 4 lower bytes and return to host the requested data. Signed-off-by: Ahmad Masri Signed-off-by: Maya Erez Signed-off-by: Kalle Valo Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/wil6210/debugfs.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c index ceace95b1595..44296c015925 100644 --- a/drivers/net/wireless/ath/wil6210/debugfs.c +++ b/drivers/net/wireless/ath/wil6210/debugfs.c @@ -662,10 +662,10 @@ static ssize_t wil_read_file_ioblob(struct file *file, char __user *user_buf, enum { max_count = 4096 }; struct wil_blob_wrapper *wil_blob = file->private_data; struct wil6210_priv *wil = wil_blob->wil; - loff_t pos = *ppos; + loff_t aligned_pos, pos = *ppos; size_t available = wil_blob->blob.size; void *buf; - size_t ret; + size_t unaligned_bytes, aligned_count, ret; int rc; if (test_bit(wil_status_suspending, wil_blob->wil->status) || @@ -683,7 +683,12 @@ static ssize_t wil_read_file_ioblob(struct file *file, char __user *user_buf, if (count > max_count) count = max_count; - buf = kmalloc(count, GFP_KERNEL); + /* set pos to 4 bytes aligned */ + unaligned_bytes = pos % 4; + aligned_pos = pos - unaligned_bytes; + aligned_count = count + unaligned_bytes; + + buf = kmalloc(aligned_count, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -694,9 +699,9 @@ static ssize_t wil_read_file_ioblob(struct file *file, char __user *user_buf, } wil_memcpy_fromio_32(buf, (const void __iomem *) - wil_blob->blob.data + pos, count); + wil_blob->blob.data + aligned_pos, aligned_count); - ret = copy_to_user(user_buf, buf, count); + ret = copy_to_user(user_buf, buf + unaligned_bytes, count); wil_pm_runtime_put(wil); From 0e1304ae42c2174a5056fec0aa03ffa09776b1f2 Mon Sep 17 00:00:00 2001 From: Maya Erez Date: Wed, 31 Oct 2018 10:52:19 +0200 Subject: [PATCH 214/299] wil6210: fix L2 RX status handling [ Upstream commit 04de15010aa42a92add66b159e3ae44b4287390f ] L2 RX status errors should not be treated as a bitmap and the actual error values should be checked. Print L2 errors as wil_err_ratelimited for easier debugging when such errors occurs. Signed-off-by: Maya Erez Signed-off-by: Kalle Valo Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/wil6210/txrx_edma.c | 23 ++++++++++---------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c index 409a6fa8b6c8..5fa8d6ad6648 100644 --- a/drivers/net/wireless/ath/wil6210/txrx_edma.c +++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c @@ -808,23 +808,24 @@ static int wil_rx_error_check_edma(struct wil6210_priv *wil, wil_dbg_txrx(wil, "L2 RX error, l2_rx_status=0x%x\n", l2_rx_status); /* Due to HW issue, KEY error will trigger a MIC error */ - if (l2_rx_status & WIL_RX_EDMA_ERROR_MIC) { - wil_dbg_txrx(wil, - "L2 MIC/KEY error, dropping packet\n"); + if (l2_rx_status == WIL_RX_EDMA_ERROR_MIC) { + wil_err_ratelimited(wil, + "L2 MIC/KEY error, dropping packet\n"); stats->rx_mic_error++; } - if (l2_rx_status & WIL_RX_EDMA_ERROR_KEY) { - wil_dbg_txrx(wil, "L2 KEY error, dropping packet\n"); + if (l2_rx_status == WIL_RX_EDMA_ERROR_KEY) { + wil_err_ratelimited(wil, + "L2 KEY error, dropping packet\n"); stats->rx_key_error++; } - if (l2_rx_status & WIL_RX_EDMA_ERROR_REPLAY) { - wil_dbg_txrx(wil, - "L2 REPLAY error, dropping packet\n"); + if (l2_rx_status == WIL_RX_EDMA_ERROR_REPLAY) { + wil_err_ratelimited(wil, + "L2 REPLAY error, dropping packet\n"); stats->rx_replay++; } - if (l2_rx_status & WIL_RX_EDMA_ERROR_AMSDU) { - wil_dbg_txrx(wil, - "L2 AMSDU error, dropping packet\n"); + if (l2_rx_status == WIL_RX_EDMA_ERROR_AMSDU) { + wil_err_ratelimited(wil, + "L2 AMSDU error, dropping packet\n"); stats->rx_amsdu_error++; } return -EFAULT; From ccb2390e89330d3a562c816408d571975dc8ae5e Mon Sep 17 00:00:00 2001 From: Maya Erez Date: Wed, 31 Oct 2018 10:52:20 +0200 Subject: [PATCH 215/299] wil6210: fix RGF_CAF_ICR address for Talyn-MB [ Upstream commit 7c69709f8ed27197b16aa1c3f9b0744402b2fa02 ] RGF_CAF_ICR register location has changed in Talyn-MB. Add RGF_CAF_ICR_TALYN_MB to support the new address. Signed-off-by: Maya Erez Signed-off-by: Kalle Valo Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/wil6210/main.c | 11 +++++++++-- drivers/net/wireless/ath/wil6210/wil6210.h | 1 + 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c index 920cb233f4db..10673fa9388e 100644 --- a/drivers/net/wireless/ath/wil6210/main.c +++ b/drivers/net/wireless/ath/wil6210/main.c @@ -1397,8 +1397,15 @@ static void wil_pre_fw_config(struct wil6210_priv *wil) wil6210_clear_irq(wil); /* CAF_ICR - clear and mask */ /* it is W1C, clear by writing back same value */ - wil_s(wil, RGF_CAF_ICR + offsetof(struct RGF_ICR, ICR), 0); - wil_w(wil, RGF_CAF_ICR + offsetof(struct RGF_ICR, IMV), ~0); + if (wil->hw_version < HW_VER_TALYN_MB) { + wil_s(wil, RGF_CAF_ICR + offsetof(struct RGF_ICR, ICR), 0); + wil_w(wil, RGF_CAF_ICR + offsetof(struct RGF_ICR, IMV), ~0); + } else { + wil_s(wil, + RGF_CAF_ICR_TALYN_MB + offsetof(struct RGF_ICR, ICR), 0); + wil_w(wil, RGF_CAF_ICR_TALYN_MB + + offsetof(struct RGF_ICR, IMV), ~0); + } /* clear PAL_UNIT_ICR (potential D0->D3 leftover) * In Talyn-MB host cannot access this register due to * access control, hence PAL_UNIT_ICR is cleared by the FW diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h index 17c294b1ead1..75fe1a3b7046 100644 --- a/drivers/net/wireless/ath/wil6210/wil6210.h +++ b/drivers/net/wireless/ath/wil6210/wil6210.h @@ -319,6 +319,7 @@ struct RGF_ICR { /* MAC timer, usec, for packet lifetime */ #define RGF_MAC_MTRL_COUNTER_0 (0x886aa8) +#define RGF_CAF_ICR_TALYN_MB (0x8893d4) /* struct RGF_ICR */ #define RGF_CAF_ICR (0x88946c) /* struct RGF_ICR */ #define RGF_CAF_OSC_CONTROL (0x88afa4) #define BIT_CAF_OSC_XTAL_EN BIT(0) From c262dc0655dfdd1d61298a132027159d87e80407 Mon Sep 17 00:00:00 2001 From: Lior David Date: Wed, 31 Oct 2018 10:52:24 +0200 Subject: [PATCH 216/299] wil6210: fix locking in wmi_call [ Upstream commit dc57731dbd535880fe6ced31c229262c34df7d64 ] Switch from spin_lock to spin_lock_irqsave, because wmi_ev_lock is used inside interrupt handler. Signed-off-by: Lior David Signed-off-by: Maya Erez Signed-off-by: Kalle Valo Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/wil6210/wmi.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c index 2010f771478d..8a603432f531 100644 --- a/drivers/net/wireless/ath/wil6210/wmi.c +++ b/drivers/net/wireless/ath/wil6210/wmi.c @@ -1639,16 +1639,17 @@ int wmi_call(struct wil6210_priv *wil, u16 cmdid, u8 mid, void *buf, u16 len, { int rc; unsigned long remain; + ulong flags; mutex_lock(&wil->wmi_mutex); - spin_lock(&wil->wmi_ev_lock); + spin_lock_irqsave(&wil->wmi_ev_lock, flags); wil->reply_id = reply_id; wil->reply_mid = mid; wil->reply_buf = reply; wil->reply_size = reply_size; reinit_completion(&wil->wmi_call); - spin_unlock(&wil->wmi_ev_lock); + spin_unlock_irqrestore(&wil->wmi_ev_lock, flags); rc = __wmi_send(wil, cmdid, mid, buf, len); if (rc) @@ -1668,12 +1669,12 @@ int wmi_call(struct wil6210_priv *wil, u16 cmdid, u8 mid, void *buf, u16 len, } out: - spin_lock(&wil->wmi_ev_lock); + spin_lock_irqsave(&wil->wmi_ev_lock, flags); wil->reply_id = 0; wil->reply_mid = U8_MAX; wil->reply_buf = NULL; wil->reply_size = 0; - spin_unlock(&wil->wmi_ev_lock); + spin_unlock_irqrestore(&wil->wmi_ev_lock, flags); mutex_unlock(&wil->wmi_mutex); From c68a499448e139192ca0b45dbe05ca47463a376d Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Mon, 5 Nov 2018 14:35:22 +0200 Subject: [PATCH 217/299] ath10k: snoc: fix unbalanced clock error handling [ Upstream commit 82e60d920e8ad70cd9a280ab156566755f1fe4aa ] Similar to regulator error handling, we should only start tearing down the 'i - 1' clock when clock 'i' fails to enable. Otherwise, we might end up with an unbalanced clock, where we never successfully enabled the clock, but we try to disable it anyway. Fixes: a6a793f98786 ("ath10k: vote for hardware resources for WCN3990") Signed-off-by: Brian Norris Reviewed-by: Douglas Anderson Signed-off-by: Kalle Valo Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath10k/snoc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c index fa1843a7e0fd..e2d78f77edb7 100644 --- a/drivers/net/wireless/ath/ath10k/snoc.c +++ b/drivers/net/wireless/ath/ath10k/snoc.c @@ -1190,7 +1190,7 @@ static int ath10k_wcn3990_clk_init(struct ath10k *ar) return 0; err_clock_config: - for (; i >= 0; i--) { + for (i = i - 1; i >= 0; i--) { clk_info = &ar_snoc->clk[i]; if (!clk_info->handle) From 06ed77066838a07a0126c4d09fc843d1a692c419 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 16 Oct 2018 09:39:40 +0200 Subject: [PATCH 218/299] wlcore: Fix the return value in case of error in 'wlcore_vendor_cmd_smart_config_start()' [ Upstream commit 3419348a97bcc256238101129d69b600ceb5cc70 ] We return 0 unconditionally at the end of 'wlcore_vendor_cmd_smart_config_start()'. However, 'ret' is set to some error codes in several error handling paths and we already return some error codes at the beginning of the function. Return 'ret' instead to propagate the error code. Fixes: 80ff8063e87c ("wlcore: handle smart config vendor commands") Signed-off-by: Christophe JAILLET Signed-off-by: Kalle Valo Signed-off-by: Sasha Levin --- drivers/net/wireless/ti/wlcore/vendor_cmd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/ti/wlcore/vendor_cmd.c b/drivers/net/wireless/ti/wlcore/vendor_cmd.c index dbe78d8491ef..7f34ec077ee5 100644 --- a/drivers/net/wireless/ti/wlcore/vendor_cmd.c +++ b/drivers/net/wireless/ti/wlcore/vendor_cmd.c @@ -70,7 +70,7 @@ wlcore_vendor_cmd_smart_config_start(struct wiphy *wiphy, out: mutex_unlock(&wl->mutex); - return 0; + return ret; } static int From bdb61fa50b708a45f21095f586fdd08921f3cf50 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 22 Oct 2018 13:51:03 +0200 Subject: [PATCH 219/299] rtl8xxxu: Fix missing break in switch [ Upstream commit 307b00c5e695857ca92fc6a4b8ab6c48f988a1b1 ] Add missing break statement in order to prevent the code from falling through to the default case. Fixes: 26f1fad29ad9 ("New driver: rtl8xxxu (mac80211)") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Kalle Valo Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index 505ab1b055ff..2b4fcdf4ec5b 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -5691,6 +5691,7 @@ static int rtl8xxxu_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, break; case WLAN_CIPHER_SUITE_TKIP: key->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIC; + break; default: return -EOPNOTSUPP; } From fad934bb2e476d90957af95c8d51ede3bbfca4c9 Mon Sep 17 00:00:00 2001 From: Ali MJ Al-Nasrawy Date: Tue, 23 Oct 2018 19:12:35 +0300 Subject: [PATCH 220/299] brcmsmac: never log "tid x is not agg'able" by default [ Upstream commit 96fca788e5788b7ea3b0050eb35a343637e0a465 ] This message greatly spams the log under heavy Tx of frames with BK access class which is especially true when operating as AP. It is also not informative as the "agg'ablity" of TIDs are set once and never change. Fix this by logging only in debug mode. Signed-off-by: Ali MJ Al-Nasrawy Signed-off-by: Kalle Valo Signed-off-by: Sasha Levin --- .../net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c index 81ff558046a8..6188275b17e5 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c @@ -846,8 +846,8 @@ brcms_ops_ampdu_action(struct ieee80211_hw *hw, status = brcms_c_aggregatable(wl->wlc, tid); spin_unlock_bh(&wl->lock); if (!status) { - brcms_err(wl->wlc->hw->d11core, - "START: tid %d is not agg\'able\n", tid); + brcms_dbg_ht(wl->wlc->hw->d11core, + "START: tid %d is not agg\'able\n", tid); return -EINVAL; } ieee80211_start_tx_ba_cb_irqsafe(vif, sta->addr, tid); From 13d434fed1a2ce7c11b1c3a95a1c20c86b2bf8a7 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 24 Oct 2018 11:33:34 +0300 Subject: [PATCH 221/299] wireless: airo: potential buffer overflow in sprintf() [ Upstream commit 3d39e1bb1c88f32820c5f9271f2c8c2fb9a52bac ] It looks like we wanted to print a maximum of BSSList_rid.ssidLen bytes of the ssid, but we accidentally use "%*s" (width) instead of "%.*s" (precision) so if the ssid doesn't have a NUL terminator this could lead to an overflow. Static analysis. Not tested. Fixes: e174961ca1a0 ("net: convert print_mac to %pM") Signed-off-by: Dan Carpenter Signed-off-by: Kalle Valo Signed-off-by: Sasha Levin --- drivers/net/wireless/cisco/airo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c index 04dd7a936593..5512c7f73fce 100644 --- a/drivers/net/wireless/cisco/airo.c +++ b/drivers/net/wireless/cisco/airo.c @@ -5462,7 +5462,7 @@ static int proc_BSSList_open( struct inode *inode, struct file *file ) { we have to add a spin lock... */ rc = readBSSListRid(ai, doLoseSync, &BSSList_rid); while(rc == 0 && BSSList_rid.index != cpu_to_le16(0xffff)) { - ptr += sprintf(ptr, "%pM %*s rssi = %d", + ptr += sprintf(ptr, "%pM %.*s rssi = %d", BSSList_rid.bssid, (int)BSSList_rid.ssidLen, BSSList_rid.ssid, From 2ac94b9e902fa2abe9de0c9b8262fb9e147f4b3a Mon Sep 17 00:00:00 2001 From: Shaokun Zhang Date: Mon, 5 Nov 2018 19:25:30 +0800 Subject: [PATCH 222/299] rtlwifi: rtl8192de: Fix misleading REG_MCUFWDL information [ Upstream commit 7d129adff3afbd3a449bc3593f2064ac546d58d3 ] RT_TRACE shows REG_MCUFWDL value as a decimal value with a '0x' prefix, which is somewhat misleading. Fix it to print hexadecimal, as was intended. Cc: Ping-Ke Shih Cc: Kalle Valo Signed-off-by: Shaokun Zhang Acked-by: Ping-Ke Shih Signed-off-by: Kalle Valo Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c index 85cedd083d2b..75bfa9dfef4a 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c @@ -173,7 +173,7 @@ static int _rtl92d_fw_init(struct ieee80211_hw *hw) rtl_read_byte(rtlpriv, FW_MAC1_READY)); } RT_TRACE(rtlpriv, COMP_FW, DBG_DMESG, - "Polling FW ready fail!! REG_MCUFWDL:0x%08ul\n", + "Polling FW ready fail!! REG_MCUFWDL:0x%08x\n", rtl_read_dword(rtlpriv, REG_MCUFWDL)); return -1; } From 5f2dc610eb281af3f9f19e39b5ddb07598f033be Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 6 Nov 2018 15:15:16 -0800 Subject: [PATCH 223/299] net: dsa: bcm_sf2: Turn on PHY to allow successful registration [ Upstream commit c04a17d2a9ccf1eaba1c5a56f83e997540a70556 ] We are binding to the PHY using the SF2 slave MDIO bus that we create, binding involves reading the PHY's MII_PHYSID1/2 which won't be possible if the PHY is turned off. Temporarily turn it on/off for the bus probing to succeeed. This fixes unbind/bind problems where the port connecting to that PHY would be in error since it could not connect to it. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/bcm_sf2.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index ca3655d28e00..17cec68e56b4 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1099,12 +1099,16 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) return ret; } + bcm_sf2_gphy_enable_set(priv->dev->ds, true); + ret = bcm_sf2_mdio_register(ds); if (ret) { pr_err("failed to register MDIO bus\n"); return ret; } + bcm_sf2_gphy_enable_set(priv->dev->ds, false); + ret = bcm_sf2_cfp_rst(priv); if (ret) { pr_err("failed to reset CFP\n"); From 5553e2bdcb02bd0d9cb2c4115910fbc46a96b58b Mon Sep 17 00:00:00 2001 From: Suganath Prabu Date: Wed, 31 Oct 2018 18:53:36 +0530 Subject: [PATCH 224/299] scsi: mpt3sas: Fix Sync cache command failure during driver unload [ Upstream commit 9029a72500b95578a35877a43473b82cb0386c53 ] This is to fix SYNC CACHE and START STOP command failures with DID_NO_CONNECT during driver unload. In driver's IO submission patch (i.e. in driver's .queuecommand()) driver won't allow any SCSI commands to the IOC when ioc->remove_host flag is set and hence SYNC CACHE commands which are issued to the target drives (where write cache is enabled) during driver unload time is failed with DID_NO_CONNECT status. Now modified the driver to allow SYNC CACHE and START STOP commands to IOC, even when remove_host flag is set. Signed-off-by: Suganath Prabu Reviewed-by: Bjorn Helgaas Reviewed-by: Andy Shevchenko Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 36 +++++++++++++++++++++++++++- 1 file changed, 35 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 73d661a0ecbb..d3c944d99703 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -3791,6 +3791,40 @@ _scsih_tm_tr_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, return _scsih_check_for_pending_tm(ioc, smid); } +/** _scsih_allow_scmd_to_device - check whether scmd needs to + * issue to IOC or not. + * @ioc: per adapter object + * @scmd: pointer to scsi command object + * + * Returns true if scmd can be issued to IOC otherwise returns false. + */ +inline bool _scsih_allow_scmd_to_device(struct MPT3SAS_ADAPTER *ioc, + struct scsi_cmnd *scmd) +{ + + if (ioc->pci_error_recovery) + return false; + + if (ioc->hba_mpi_version_belonged == MPI2_VERSION) { + if (ioc->remove_host) + return false; + + return true; + } + + if (ioc->remove_host) { + + switch (scmd->cmnd[0]) { + case SYNCHRONIZE_CACHE: + case START_STOP: + return true; + default: + return false; + } + } + + return true; +} /** * _scsih_sas_control_complete - completion routine @@ -4623,7 +4657,7 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd) return 0; } - if (ioc->pci_error_recovery || ioc->remove_host) { + if (!(_scsih_allow_scmd_to_device(ioc, scmd))) { scmd->result = DID_NO_CONNECT << 16; scmd->scsi_done(scmd); return 0; From 80224e3b08ffe85eb990af78e7e3532d779e7be4 Mon Sep 17 00:00:00 2001 From: Suganath Prabu Date: Wed, 31 Oct 2018 18:53:37 +0530 Subject: [PATCH 225/299] scsi: mpt3sas: Don't modify EEDPTagMode field setting on SAS3.5 HBA devices [ Upstream commit 6cd1bc7b9b5075d395ba0120923903873fc7ea0e ] If EEDPTagMode field in manufacturing page11 is set then unset it. This is needed to fix a hardware bug only in SAS3/SAS2 cards. So, skipping EEDPTagMode changes in Manufacturing page11 for SAS 3.5 controllers. Signed-off-by: Suganath Prabu Reviewed-by: Bjorn Helgaas Reviewed-by: Andy Shevchenko Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/mpt3sas/mpt3sas_base.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index d2ab52026014..2c556c7fcf0d 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -4117,7 +4117,7 @@ _base_static_config_pages(struct MPT3SAS_ADAPTER *ioc) * flag unset in NVDATA. */ mpt3sas_config_get_manufacturing_pg11(ioc, &mpi_reply, &ioc->manu_pg11); - if (ioc->manu_pg11.EEDPTagMode == 0) { + if (!ioc->is_gen35_ioc && ioc->manu_pg11.EEDPTagMode == 0) { pr_err("%s: overriding NVDATA EEDPTagMode setting\n", ioc->name); ioc->manu_pg11.EEDPTagMode &= ~0x3; From ff997bf13c1e732139ec5b5d1eda998cf3b50320 Mon Sep 17 00:00:00 2001 From: Suganath Prabu Date: Wed, 31 Oct 2018 18:53:38 +0530 Subject: [PATCH 226/299] scsi: mpt3sas: Fix driver modifying persistent data in Manufacturing page11 [ Upstream commit 97f35194093362a63b33caba2485521ddabe2c95 ] Currently driver is modifying both current & NVRAM/persistent data in Manufacturing page11. Driver should change only current copy of Manufacturing page11. It should not modify the persistent data. So removed the section of code where driver is modifying the persistent data of Manufacturing page11. Signed-off-by: Suganath Prabu Reviewed-by: Bjorn Helgaas Reviewed-by: Andy Shevchenko Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/mpt3sas/mpt3sas_config.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_config.c b/drivers/scsi/mpt3sas/mpt3sas_config.c index d29a2dcc7d0e..9b01c5a7aebd 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_config.c +++ b/drivers/scsi/mpt3sas/mpt3sas_config.c @@ -692,10 +692,6 @@ mpt3sas_config_set_manufacturing_pg11(struct MPT3SAS_ADAPTER *ioc, r = _config_request(ioc, &mpi_request, mpi_reply, MPT3_CONFIG_PAGE_DEFAULT_TIMEOUT, config_page, sizeof(*config_page)); - mpi_request.Action = MPI2_CONFIG_ACTION_PAGE_WRITE_NVRAM; - r = _config_request(ioc, &mpi_request, mpi_reply, - MPT3_CONFIG_PAGE_DEFAULT_TIMEOUT, config_page, - sizeof(*config_page)); out: return r; } From 83e679606e78210a30f5f3906f8b8f64391f062b Mon Sep 17 00:00:00 2001 From: Shivasharan S Date: Tue, 16 Oct 2018 23:37:41 -0700 Subject: [PATCH 227/299] scsi: megaraid_sas: Fix msleep granularity [ Upstream commit 9155cf30a3c4ef97e225d6daddf9bd4b173267e8 ] In megasas_transition_to_ready() driver waits 180seconds for controller to change FW state. Here we are calling msleep(1) in a loop for this. As explained in timers-howto.txt, msleep(1) will actually sleep longer than 1ms. If a faulty controller is connected, we will end up waiting for much more than 180 seconds causing unnecessary delays during load. Change the granularity of msleep() call from 1ms to 1000ms. Signed-off-by: Shivasharan S Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/megaraid/megaraid_sas_base.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index bc37666f998e..2f94ab9c2354 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -3894,12 +3894,12 @@ megasas_transition_to_ready(struct megasas_instance *instance, int ocr) /* * The cur_state should not last for more than max_wait secs */ - for (i = 0; i < (max_wait * 1000); i++) { + for (i = 0; i < max_wait; i++) { curr_abs_state = instance->instancet-> read_fw_status_reg(instance->reg_set); if (abs_state == curr_abs_state) { - msleep(1); + msleep(1000); } else break; } From e6d0262e1628e5d61d936a9e15ec5919a2abacbe Mon Sep 17 00:00:00 2001 From: Shivasharan S Date: Tue, 16 Oct 2018 23:37:44 -0700 Subject: [PATCH 228/299] scsi: megaraid_sas: Fix goto labels in error handling [ Upstream commit 8a25fa17b6ed6e6c8101e9c68a10ae68a9025f2c ] During init, if pci_alloc_irq_vectors() fails, the driver has not yet setup the IRQs. Fix the goto labels and error handling for this case. Signed-off-by: Shivasharan S Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/megaraid/megaraid_sas_base.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 2f94ab9c2354..2f31d266339f 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -5410,7 +5410,7 @@ static int megasas_init_fw(struct megasas_instance *instance) if (!instance->msix_vectors) { i = pci_alloc_irq_vectors(instance->pdev, 1, 1, PCI_IRQ_LEGACY); if (i < 0) - goto fail_setup_irqs; + goto fail_init_adapter; } megasas_setup_reply_map(instance); @@ -5619,9 +5619,8 @@ static int megasas_init_fw(struct megasas_instance *instance) fail_get_ld_pd_list: instance->instancet->disable_intr(instance); -fail_init_adapter: megasas_destroy_irqs(instance); -fail_setup_irqs: +fail_init_adapter: if (instance->msix_vectors) pci_free_irq_vectors(instance->pdev); instance->msix_vectors = 0; From 05678af01a337a242da9744b15255cd6f08a436c Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 23 Oct 2018 13:41:06 -0700 Subject: [PATCH 229/299] scsi: lpfc: fcoe: Fix link down issue after 1000+ link bounces [ Upstream commit 036cad1f1ac9ce03e2db94b8460f98eaf1e1ee4c ] On FCoE adapters, when running link bounce test in a loop, initiator failed to login with switch switch and required driver reload to recover. Switch reached a point where all subsequent FLOGIs would be LS_RJT'd. Further testing showed the condition to be related to not performing FCF discovery between FLOGI's. Fix by monitoring FLOGI failures and once a repeated error is seen repeat FCF discovery. Signed-off-by: Dick Kennedy Signed-off-by: James Smart Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/lpfc/lpfc_els.c | 2 ++ drivers/scsi/lpfc/lpfc_hbadisc.c | 20 ++++++++++++++++++++ drivers/scsi/lpfc/lpfc_init.c | 2 +- drivers/scsi/lpfc/lpfc_sli.c | 11 ++--------- drivers/scsi/lpfc/lpfc_sli4.h | 1 + 5 files changed, 26 insertions(+), 10 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index f3c6801c0b31..8bf916b9a987 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -1157,6 +1157,7 @@ stop_rr_fcf_flogi: phba->fcf.fcf_flag &= ~FCF_DISCOVERY; phba->hba_flag &= ~(FCF_RR_INPROG | HBA_DEVLOSS_TMO); spin_unlock_irq(&phba->hbalock); + phba->fcf.fcf_redisc_attempted = 0; /* reset */ goto out; } if (!rc) { @@ -1171,6 +1172,7 @@ stop_rr_fcf_flogi: phba->fcf.fcf_flag &= ~FCF_DISCOVERY; phba->hba_flag &= ~(FCF_RR_INPROG | HBA_DEVLOSS_TMO); spin_unlock_irq(&phba->hbalock); + phba->fcf.fcf_redisc_attempted = 0; /* reset */ goto out; } } diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index db183d1f34ab..0d19e5f6b3bc 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -1997,6 +1997,26 @@ int lpfc_sli4_fcf_rr_next_proc(struct lpfc_vport *vport, uint16_t fcf_index) "failover and change port state:x%x/x%x\n", phba->pport->port_state, LPFC_VPORT_UNKNOWN); phba->pport->port_state = LPFC_VPORT_UNKNOWN; + + if (!phba->fcf.fcf_redisc_attempted) { + lpfc_unregister_fcf(phba); + + rc = lpfc_sli4_redisc_fcf_table(phba); + if (!rc) { + lpfc_printf_log(phba, KERN_INFO, LOG_FIP, + "3195 Rediscover FCF table\n"); + phba->fcf.fcf_redisc_attempted = 1; + lpfc_sli4_clear_fcf_rr_bmask(phba); + } else { + lpfc_printf_log(phba, KERN_WARNING, LOG_FIP, + "3196 Rediscover FCF table " + "failed. Status:x%x\n", rc); + } + } else { + lpfc_printf_log(phba, KERN_WARNING, LOG_FIP, + "3197 Already rediscover FCF table " + "attempted. No more retry\n"); + } goto stop_flogi_current_fcf; } else { lpfc_printf_log(phba, KERN_INFO, LOG_FIP | LOG_ELS, diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 9acb5b44ce4c..a7d3e532e0f5 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -5044,7 +5044,7 @@ lpfc_sli4_async_fip_evt(struct lpfc_hba *phba, break; } /* If fast FCF failover rescan event is pending, do nothing */ - if (phba->fcf.fcf_flag & FCF_REDISC_EVT) { + if (phba->fcf.fcf_flag & (FCF_REDISC_EVT | FCF_REDISC_PEND)) { spin_unlock_irq(&phba->hbalock); break; } diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index e704297618e0..3361ae75578f 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -18431,15 +18431,8 @@ next_priority: goto initial_priority; lpfc_printf_log(phba, KERN_WARNING, LOG_FIP, "2844 No roundrobin failover FCF available\n"); - if (next_fcf_index >= LPFC_SLI4_FCF_TBL_INDX_MAX) - return LPFC_FCOE_FCF_NEXT_NONE; - else { - lpfc_printf_log(phba, KERN_WARNING, LOG_FIP, - "3063 Only FCF available idx %d, flag %x\n", - next_fcf_index, - phba->fcf.fcf_pri[next_fcf_index].fcf_rec.flag); - return next_fcf_index; - } + + return LPFC_FCOE_FCF_NEXT_NONE; } if (next_fcf_index < LPFC_SLI4_FCF_TBL_INDX_MAX && diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h index 399c0015c546..3dcc6615a23b 100644 --- a/drivers/scsi/lpfc/lpfc_sli4.h +++ b/drivers/scsi/lpfc/lpfc_sli4.h @@ -279,6 +279,7 @@ struct lpfc_fcf { #define FCF_REDISC_EVT 0x100 /* FCF rediscovery event to worker thread */ #define FCF_REDISC_FOV 0x200 /* Post FCF rediscovery fast failover */ #define FCF_REDISC_PROG (FCF_REDISC_PEND | FCF_REDISC_EVT) + uint16_t fcf_redisc_attempted; uint32_t addr_mode; uint32_t eligible_fcf_cnt; struct lpfc_fcf_rec current_rec; From a391709b636e9b78cf28494f38e42a30c37294f5 Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 23 Oct 2018 13:41:08 -0700 Subject: [PATCH 230/299] scsi: lpfc: Fix odd recovery in duplicate FLOGIs in point-to-point [ Upstream commit d496b9a7246cb9813da1fe49e14edbbbf8e232d5 ] Testing a point-to-point topology and a case of re-FLOGI without intervening link bouncing, showed an odd interaction with firmware and a resulting scenario where the driver no longer probed after accepting the new FLOGI. Work around the firmware issue by issuing a link bounce if a FLOGI is received after the link is already up and FLOGI's accepted. While debugging the issue, realized that some debug traces should be clarified to help in the future. Signed-off-by: Dick Kennedy Signed-off-by: James Smart Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/lpfc/lpfc.h | 1 + drivers/scsi/lpfc/lpfc_els.c | 66 ++++++++++++++++++++++++++------ drivers/scsi/lpfc/lpfc_hbadisc.c | 9 +++++ 3 files changed, 64 insertions(+), 12 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index 43732e8d1347..ebcfcbb8b4cc 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -490,6 +490,7 @@ struct lpfc_vport { struct nvme_fc_local_port *localport; uint8_t nvmei_support; /* driver supports NVME Initiator */ uint32_t last_fcp_wqidx; + uint32_t rcv_flogi_cnt; /* How many unsol FLOGIs ACK'd. */ }; struct hbq_s { diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 8bf916b9a987..e263a486b1c6 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -1057,9 +1057,9 @@ stop_rr_fcf_flogi: goto flogifail; lpfc_printf_vlog(vport, KERN_WARNING, LOG_ELS, - "0150 FLOGI failure Status:x%x/x%x TMO:x%x\n", + "0150 FLOGI failure Status:x%x/x%x xri x%x TMO:x%x\n", irsp->ulpStatus, irsp->un.ulpWord[4], - irsp->ulpTimeout); + cmdiocb->sli4_xritag, irsp->ulpTimeout); /* FLOGI failed, so there is no fabric */ spin_lock_irq(shost->host_lock); @@ -1113,7 +1113,8 @@ stop_rr_fcf_flogi: /* FLOGI completes successfully */ lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS, "0101 FLOGI completes successfully, I/O tag:x%x, " - "Data: x%x x%x x%x x%x x%x x%x\n", cmdiocb->iotag, + "xri x%x Data: x%x x%x x%x x%x x%x %x\n", + cmdiocb->iotag, cmdiocb->sli4_xritag, irsp->un.ulpWord[4], sp->cmn.e_d_tov, sp->cmn.w2.r_a_tov, sp->cmn.edtovResolution, vport->port_state, vport->fc_flag); @@ -4266,14 +4267,6 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag, default: return 1; } - /* Xmit ELS ACC response tag */ - lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS, - "0128 Xmit ELS ACC response tag x%x, XRI: x%x, " - "DID: x%x, nlp_flag: x%x nlp_state: x%x RPI: x%x " - "fc_flag x%x\n", - elsiocb->iotag, elsiocb->iocb.ulpContext, - ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state, - ndlp->nlp_rpi, vport->fc_flag); if (ndlp->nlp_flag & NLP_LOGO_ACC) { spin_lock_irq(shost->host_lock); if (!(ndlp->nlp_flag & NLP_RPI_REGISTERED || @@ -4442,6 +4435,15 @@ lpfc_els_rsp_adisc_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb, lpfc_els_free_iocb(phba, elsiocb); return 1; } + + /* Xmit ELS ACC response tag */ + lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS, + "0128 Xmit ELS ACC response Status: x%x, IoTag: x%x, " + "XRI: x%x, DID: x%x, nlp_flag: x%x nlp_state: x%x " + "RPI: x%x, fc_flag x%x\n", + rc, elsiocb->iotag, elsiocb->sli4_xritag, + ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state, + ndlp->nlp_rpi, vport->fc_flag); return 0; } @@ -6452,6 +6454,11 @@ lpfc_els_rcv_flogi(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb, port_state = vport->port_state; vport->fc_flag |= FC_PT2PT; vport->fc_flag &= ~(FC_FABRIC | FC_PUBLIC_LOOP); + + /* Acking an unsol FLOGI. Count 1 for link bounce + * work-around. + */ + vport->rcv_flogi_cnt++; spin_unlock_irq(shost->host_lock); lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS, "3311 Rcv Flogi PS x%x new PS x%x " @@ -7849,8 +7856,9 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, struct ls_rjt stat; uint32_t *payload; uint32_t cmd, did, newnode; - uint8_t rjt_exp, rjt_err = 0; + uint8_t rjt_exp, rjt_err = 0, init_link = 0; IOCB_t *icmd = &elsiocb->iocb; + LPFC_MBOXQ_t *mbox; if (!vport || !(elsiocb->context2)) goto dropit; @@ -7999,6 +8007,19 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, did, vport->port_state, ndlp->nlp_flag); phba->fc_stat.elsRcvFLOGI++; + + /* If the driver believes fabric discovery is done and is ready, + * bounce the link. There is some descrepancy. + */ + if (vport->port_state >= LPFC_LOCAL_CFG_LINK && + vport->fc_flag & FC_PT2PT && + vport->rcv_flogi_cnt >= 1) { + rjt_err = LSRJT_LOGICAL_BSY; + rjt_exp = LSEXP_NOTHING_MORE; + init_link++; + goto lsrjt; + } + lpfc_els_rcv_flogi(vport, elsiocb, ndlp); if (newnode) lpfc_nlp_put(ndlp); @@ -8227,6 +8248,27 @@ lsrjt: lpfc_nlp_put(elsiocb->context1); elsiocb->context1 = NULL; + + /* Special case. Driver received an unsolicited command that + * unsupportable given the driver's current state. Reset the + * link and start over. + */ + if (init_link) { + mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); + if (!mbox) + return; + lpfc_linkdown(phba); + lpfc_init_link(phba, mbox, + phba->cfg_topology, + phba->cfg_link_speed); + mbox->u.mb.un.varInitLnk.lipsr_AL_PA = 0; + mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl; + mbox->vport = vport; + if (lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT) == + MBX_NOT_FINISHED) + mempool_free(mbox, phba->mbox_mem_pool); + } + return; dropit: diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 0d19e5f6b3bc..68f223882d96 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -952,6 +952,7 @@ lpfc_linkdown(struct lpfc_hba *phba) } spin_lock_irq(shost->host_lock); phba->pport->fc_flag &= ~(FC_PT2PT | FC_PT2PT_PLOGI); + phba->pport->rcv_flogi_cnt = 0; spin_unlock_irq(shost->host_lock); } return 0; @@ -1023,6 +1024,7 @@ lpfc_linkup(struct lpfc_hba *phba) { struct lpfc_vport **vports; int i; + struct Scsi_Host *shost = lpfc_shost_from_vport(phba->pport); phba->link_state = LPFC_LINK_UP; @@ -1036,6 +1038,13 @@ lpfc_linkup(struct lpfc_hba *phba) lpfc_linkup_port(vports[i]); lpfc_destroy_vport_work_array(phba, vports); + /* Clear the pport flogi counter in case the link down was + * absorbed without an ACQE. No lock here - in worker thread + * and discovery is synchronized. + */ + spin_lock_irq(shost->host_lock); + phba->pport->rcv_flogi_cnt = 0; + spin_unlock_irq(shost->host_lock); return 0; } From 5e989b6cad68f64512bfab2d04df48a47f5c24d2 Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 23 Oct 2018 13:41:09 -0700 Subject: [PATCH 231/299] scsi: lpfc: Correct loss of fc4 type on remote port address change [ Upstream commit d83ca3ea833d7a66d49225e4191c4e37cab8f079 ] An address change for a remote port cause PRLI for the wrong protocol to be sent. The node copy done in the discovery code skipped copying the fc4 protocols supported as well. Fix the copy logic for the address change. Beefed up log messages in this area as well. Signed-off-by: Dick Kennedy Signed-off-by: James Smart Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/lpfc/lpfc_els.c | 27 +++++++++++++++++++++++---- drivers/scsi/lpfc/lpfc_nportdisc.c | 5 +++-- 2 files changed, 26 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index e263a486b1c6..222fa9b7f478 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -1556,8 +1556,10 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp, */ new_ndlp = lpfc_findnode_wwpn(vport, &sp->portName); + /* return immediately if the WWPN matches ndlp */ if (new_ndlp == ndlp && NLP_CHK_NODE_ACT(new_ndlp)) return ndlp; + if (phba->sli_rev == LPFC_SLI_REV4) { active_rrqs_xri_bitmap = mempool_alloc(phba->active_rrq_pool, GFP_KERNEL); @@ -1566,9 +1568,13 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp, phba->cfg_rrq_xri_bitmap_sz); } - lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS, - "3178 PLOGI confirm: ndlp %p x%x: new_ndlp %p\n", - ndlp, ndlp->nlp_DID, new_ndlp); + lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS | LOG_NODE, + "3178 PLOGI confirm: ndlp x%x x%x x%x: " + "new_ndlp x%x x%x x%x\n", + ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_fc4_type, + (new_ndlp ? new_ndlp->nlp_DID : 0), + (new_ndlp ? new_ndlp->nlp_flag : 0), + (new_ndlp ? new_ndlp->nlp_fc4_type : 0)); if (!new_ndlp) { rc = memcmp(&ndlp->nlp_portname, name, @@ -1617,6 +1623,14 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp, phba->cfg_rrq_xri_bitmap_sz); } + /* At this point in this routine, we know new_ndlp will be + * returned. however, any previous GID_FTs that were done + * would have updated nlp_fc4_type in ndlp, so we must ensure + * new_ndlp has the right value. + */ + if (vport->fc_flag & FC_FABRIC) + new_ndlp->nlp_fc4_type = ndlp->nlp_fc4_type; + lpfc_unreg_rpi(vport, new_ndlp); new_ndlp->nlp_DID = ndlp->nlp_DID; new_ndlp->nlp_prev_state = ndlp->nlp_prev_state; @@ -1666,7 +1680,6 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp, if (ndlp->nrport) { ndlp->nrport = NULL; lpfc_nlp_put(ndlp); - new_ndlp->nlp_fc4_type = ndlp->nlp_fc4_type; } /* We shall actually free the ndlp with both nlp_DID and @@ -1740,6 +1753,12 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp, active_rrqs_xri_bitmap) mempool_free(active_rrqs_xri_bitmap, phba->active_rrq_pool); + + lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS | LOG_NODE, + "3173 PLOGI confirm exit: new_ndlp x%x x%x x%x\n", + new_ndlp->nlp_DID, new_ndlp->nlp_flag, + new_ndlp->nlp_fc4_type); + return new_ndlp; } diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c index c15f3265eefe..bd8dc6a2243c 100644 --- a/drivers/scsi/lpfc/lpfc_nportdisc.c +++ b/drivers/scsi/lpfc/lpfc_nportdisc.c @@ -2868,8 +2868,9 @@ lpfc_disc_state_machine(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, /* DSM in event on NPort in state */ lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, "0211 DSM in event x%x on NPort x%x in " - "state %d Data: x%x\n", - evt, ndlp->nlp_DID, cur_state, ndlp->nlp_flag); + "state %d Data: x%x x%x\n", + evt, ndlp->nlp_DID, cur_state, + ndlp->nlp_flag, ndlp->nlp_fc4_type); lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_DSM, "DSM in: evt:%d ste:%d did:x%x", From 30fc13ae88b2b6a40c130f243284ee030591a658 Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Mon, 1 Oct 2018 12:45:01 -0700 Subject: [PATCH 232/299] usb: typec: tcpm: charge current handling for sink during hard reset [ Upstream commit 157c0f2f641a9938382b092c64548ebdabfe25e0 ] During the initial connect to a non-pd port, sink would hard reset twice before deeming that the port partner is non-pd. TCPM sets the the charge path to false during the hard reset. This causes unnecessary connects/disconnects of charge path and makes port take longer to charge from the non-pd ports. Avoid this by not setting the charge path to false unless the partner has already identified to be pd capable. When partner is a pd port, set the charge path to false in SNK_HARD_RESET_SINK_OFF. Set the current limits to default value based of CC pull up and resume the charge path when port enters SNK_HARD_RESET_SINK_ON. Signed-off-by: Badhri Jagan Sridharan Reviewed-by: Rob Herring Reviewed-by: Heikki Krogerus -------- Changes in V3: Rebase on top of usb-next Changes in V2: Based on feedback of jackp@codeaurora.org - vsafe_5v_hard_reset flag from tcpc_config is removed - Patch only differentiates between pd port partner and non-pd port partner V1 version of the patch is here: https://lkml.org/lkml/2018/9/14/11 Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/typec/tcpm.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/usb/typec/tcpm.c b/drivers/usb/typec/tcpm.c index 819ae3b2bd7e..39cf19001239 100644 --- a/drivers/usb/typec/tcpm.c +++ b/drivers/usb/typec/tcpm.c @@ -3322,7 +3322,8 @@ static void run_state_machine(struct tcpm_port *port) case SNK_HARD_RESET_SINK_OFF: memset(&port->pps_data, 0, sizeof(port->pps_data)); tcpm_set_vconn(port, false); - tcpm_set_charge(port, false); + if (port->pd_capable) + tcpm_set_charge(port, false); tcpm_set_roles(port, port->self_powered, TYPEC_SINK, TYPEC_DEVICE); /* @@ -3354,6 +3355,12 @@ static void run_state_machine(struct tcpm_port *port) * Similar, dual-mode ports in source mode should transition * to PE_SNK_Transition_to_default. */ + if (port->pd_capable) { + tcpm_set_current_limit(port, + tcpm_get_current_limit(port), + 5000); + tcpm_set_charge(port, true); + } tcpm_set_attached_state(port, true); tcpm_set_state(port, SNK_STARTUP, 0); break; From afb4717ab81b5aca60cd9836788cb6e2e6a1bcba Mon Sep 17 00:00:00 2001 From: Tycho Andersen Date: Fri, 2 Nov 2018 14:18:20 -0600 Subject: [PATCH 233/299] dlm: fix invalid free [ Upstream commit d968b4e240cfe39d39d80483bac8bca8716fd93c ] dlm_config_nodes() does not allocate nodes on failure, so we should not free() nodes when it fails. Signed-off-by: Tycho Andersen Signed-off-by: David Teigland Signed-off-by: Sasha Levin --- fs/dlm/member.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/dlm/member.c b/fs/dlm/member.c index 3fda3832cf6a..cad6d85911a8 100644 --- a/fs/dlm/member.c +++ b/fs/dlm/member.c @@ -680,7 +680,7 @@ int dlm_ls_start(struct dlm_ls *ls) error = dlm_config_nodes(ls->ls_name, &nodes, &count); if (error < 0) - goto fail; + goto fail_rv; spin_lock(&ls->ls_recover_lock); @@ -712,8 +712,9 @@ int dlm_ls_start(struct dlm_ls *ls) return 0; fail: - kfree(rv); kfree(nodes); + fail_rv: + kfree(rv); return error; } From 5c2a3997ae5b7d14431eda830bfd0d4d727a7ec9 Mon Sep 17 00:00:00 2001 From: Tycho Andersen Date: Fri, 2 Nov 2018 14:18:22 -0600 Subject: [PATCH 234/299] dlm: don't leak kernel pointer to userspace [ Upstream commit 9de30f3f7f4d31037cfbb7c787e1089c1944b3a7 ] In copy_result_to_user(), we first create a struct dlm_lock_result, which contains a struct dlm_lksb, the last member of which is a pointer to the lvb. Unfortunately, we copy the entire struct dlm_lksb to the result struct, which is then copied to userspace at the end of the function, leaking the contents of sb_lvbptr, which is a valid kernel pointer in some cases (indeed, later in the same function the data it points to is copied to userspace). It is an error to leak kernel pointers to userspace, as it undermines KASLR protections (see e.g. 65eea8edc31 ("floppy: Do not copy a kernel pointer to user memory in FDGETPRM ioctl") for another example of this). Signed-off-by: Tycho Andersen Signed-off-by: David Teigland Signed-off-by: Sasha Levin --- fs/dlm/user.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 2a669390cd7f..13f29409600b 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -702,7 +702,7 @@ static int copy_result_to_user(struct dlm_user_args *ua, int compat, result.version[0] = DLM_DEVICE_VERSION_MAJOR; result.version[1] = DLM_DEVICE_VERSION_MINOR; result.version[2] = DLM_DEVICE_VERSION_PATCH; - memcpy(&result.lksb, &ua->lksb, sizeof(struct dlm_lksb)); + memcpy(&result.lksb, &ua->lksb, offsetof(struct dlm_lksb, sb_lvbptr)); result.user_lksb = ua->user_lksb; /* FIXME: dlm1 provides for the user's bastparam/addr to not be updated From 91c5f99d131ed3b231aaef7d4ed6799085b095a3 Mon Sep 17 00:00:00 2001 From: Mike Manning Date: Wed, 7 Nov 2018 15:36:07 +0000 Subject: [PATCH 235/299] vrf: mark skb for multicast or link-local as enslaved to VRF [ Upstream commit 6f12fa775530195a501fb090d092c637f32d0cc5 ] The skb for packets that are multicast or to a link-local address are not marked as being enslaved to a VRF, if they are received on a socket bound to the VRF. This is needed for ND and it is preferable for the kernel not to have to deal with the additional use-cases if ll or mcast packets are handled as enslaved. However, this does not allow service instances listening on unbound and bound to VRF sockets to distinguish the VRF used, if packets are sent as multicast or to a link-local address. The fix is for the VRF driver to also mark these skb as being enslaved to the VRF. Signed-off-by: Mike Manning Reviewed-by: David Ahern Tested-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/vrf.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 9f895083bc0a..7f5ee6bb4430 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -993,24 +993,23 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { int orig_iif = skb->skb_iif; - bool need_strict; + bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr); + bool is_ndisc = ipv6_ndisc_frame(skb); - /* loopback traffic; do not push through packet taps again. - * Reset pkt_type for upper layers to process skb + /* loopback, multicast & non-ND link-local traffic; do not push through + * packet taps again. Reset pkt_type for upper layers to process skb */ - if (skb->pkt_type == PACKET_LOOPBACK) { + if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) { skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IP6CB(skb)->flags |= IP6SKB_L3SLAVE; - skb->pkt_type = PACKET_HOST; + if (skb->pkt_type == PACKET_LOOPBACK) + skb->pkt_type = PACKET_HOST; goto out; } - /* if packet is NDISC or addressed to multicast or link-local - * then keep the ingress interface - */ - need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr); - if (!ipv6_ndisc_frame(skb) && !need_strict) { + /* if packet is NDISC then keep the ingress interface */ + if (!is_ndisc) { vrf_rx_stats(vrf_dev, skb->len); skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; From d15b8b691725a432130358d198e909ccb48b403b Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Sun, 21 Oct 2018 21:30:50 +0300 Subject: [PATCH 236/299] clk: tegra20: Turn EMC clock gate into divider [ Upstream commit 514fddba845ed3a1b17e01e99cb3a2a52256a88a ] Kernel should never gate the EMC clock as it causes immediate lockup, so removing clk-gate functionality doesn't affect anything. Turning EMC clk gate into divider allows to implement glitch-less EMC scaling, avoiding reparenting to a backup clock. Signed-off-by: Dmitry Osipenko Acked-by: Peter De Schrijver Acked-by: Stephen Boyd Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/clk/tegra/clk-tegra20.c | 36 ++++++++++++++++++++++++--------- 1 file changed, 26 insertions(+), 10 deletions(-) diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c index cc857d4d4a86..68551effb5ca 100644 --- a/drivers/clk/tegra/clk-tegra20.c +++ b/drivers/clk/tegra/clk-tegra20.c @@ -578,7 +578,6 @@ static struct tegra_clk tegra20_clks[tegra_clk_max] __initdata = { [tegra_clk_afi] = { .dt_id = TEGRA20_CLK_AFI, .present = true }, [tegra_clk_fuse] = { .dt_id = TEGRA20_CLK_FUSE, .present = true }, [tegra_clk_kfuse] = { .dt_id = TEGRA20_CLK_KFUSE, .present = true }, - [tegra_clk_emc] = { .dt_id = TEGRA20_CLK_EMC, .present = true }, }; static unsigned long tegra20_clk_measure_input_freq(void) @@ -799,6 +798,31 @@ static struct tegra_periph_init_data tegra_periph_nodiv_clk_list[] = { TEGRA_INIT_DATA_NODIV("disp2", mux_pllpdc_clkm, CLK_SOURCE_DISP2, 30, 2, 26, 0, TEGRA20_CLK_DISP2), }; +static void __init tegra20_emc_clk_init(void) +{ + struct clk *clk; + + clk = clk_register_mux(NULL, "emc_mux", mux_pllmcp_clkm, + ARRAY_SIZE(mux_pllmcp_clkm), + CLK_SET_RATE_NO_REPARENT, + clk_base + CLK_SOURCE_EMC, + 30, 2, 0, &emc_lock); + + clk = tegra_clk_register_mc("mc", "emc_mux", clk_base + CLK_SOURCE_EMC, + &emc_lock); + clks[TEGRA20_CLK_MC] = clk; + + /* + * Note that 'emc_mux' source and 'emc' rate shouldn't be changed at + * the same time due to a HW bug, this won't happen because we're + * defining 'emc_mux' and 'emc' as distinct clocks. + */ + clk = tegra_clk_register_divider("emc", "emc_mux", + clk_base + CLK_SOURCE_EMC, CLK_IS_CRITICAL, + TEGRA_DIVIDER_INT, 0, 8, 1, &emc_lock); + clks[TEGRA20_CLK_EMC] = clk; +} + static void __init tegra20_periph_clk_init(void) { struct tegra_periph_init_data *data; @@ -812,15 +836,7 @@ static void __init tegra20_periph_clk_init(void) clks[TEGRA20_CLK_AC97] = clk; /* emc */ - clk = clk_register_mux(NULL, "emc_mux", mux_pllmcp_clkm, - ARRAY_SIZE(mux_pllmcp_clkm), - CLK_SET_RATE_NO_REPARENT, - clk_base + CLK_SOURCE_EMC, - 30, 2, 0, &emc_lock); - - clk = tegra_clk_register_mc("mc", "emc_mux", clk_base + CLK_SOURCE_EMC, - &emc_lock); - clks[TEGRA20_CLK_MC] = clk; + tegra20_emc_clk_init(); /* dsi */ clk = tegra_clk_register_periph_gate("dsi", "pll_d", 0, clk_base, 0, From 1d6a0dd6aa535e3c5d9d840e3d0cff55cefabaa8 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 5 Nov 2018 09:43:52 -0800 Subject: [PATCH 237/299] ACPICA: Use %d for signed int print formatting instead of %u [ Upstream commit f8ddf49b420112e28bdd23d7ad52d7991a0ccbe3 ] Fix warnings found using static analysis with cppcheck, use %d printf format specifier for signed ints rather than %u Signed-off-by: Colin Ian King Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- tools/power/acpi/tools/acpidump/apmain.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c index db213171f8d9..2d9b94b631cb 100644 --- a/tools/power/acpi/tools/acpidump/apmain.c +++ b/tools/power/acpi/tools/acpidump/apmain.c @@ -106,7 +106,7 @@ static int ap_insert_action(char *argument, u32 to_be_done) current_action++; if (current_action > AP_MAX_ACTIONS) { - fprintf(stderr, "Too many table options (max %u)\n", + fprintf(stderr, "Too many table options (max %d)\n", AP_MAX_ACTIONS); return (-1); } From 1303c938c95377895deafce6067dd433c814f94f Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 8 Nov 2018 02:08:43 +0000 Subject: [PATCH 238/299] net: bcmgenet: return correct value 'ret' from bcmgenet_power_down [ Upstream commit 0db55093b56618088b9a1d445eb6e43b311bea33 ] Fixes gcc '-Wunused-but-set-variable' warning: drivers/net/ethernet/broadcom/genet/bcmgenet.c: In function 'bcmgenet_power_down': drivers/net/ethernet/broadcom/genet/bcmgenet.c:1136:6: warning: variable 'ret' set but not used [-Wunused-but-set-variable] bcmgenet_power_down should return 'ret' instead of 0. Fixes: ca8cf341903f ("net: bcmgenet: propagate errors from bcmgenet_power_down") Signed-off-by: YueHaibing Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index bb60104b4f80..338d22380434 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1169,7 +1169,7 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv, break; } - return 0; + return ret; } static void bcmgenet_power_up(struct bcmgenet_priv *priv, From e4547e02854776bd8270a7493a5e9f40e77c7ce4 Mon Sep 17 00:00:00 2001 From: Frank Rowand Date: Fri, 12 Oct 2018 19:38:26 -0700 Subject: [PATCH 239/299] of: unittest: allow base devicetree to have symbol metadata [ Upstream commit 5babefb7f7ab1f23861336d511cc666fa45ede82 ] The overlay metadata nodes in the FDT created from testcases.dts are not handled properly. The __fixups__ and __local_fixups__ node were added to the live devicetree, but should not be. Only the first property in the /__symbols__ node was added to the live devicetree if the live devicetree already contained a /__symbols node. All of the node's properties must be added. Tested-by: Alan Tull Signed-off-by: Frank Rowand Signed-off-by: Sasha Levin --- drivers/of/unittest.c | 43 +++++++++++++++++++++++++++++++++++-------- 1 file changed, 35 insertions(+), 8 deletions(-) diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index bac4b4bbc33d..e8997cdb228c 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -1067,20 +1067,44 @@ static void __init of_unittest_platform_populate(void) * of np into dup node (present in live tree) and * updates parent of children of np to dup. * - * @np: node already present in live tree + * @np: node whose properties are being added to the live tree * @dup: node present in live tree to be updated */ static void update_node_properties(struct device_node *np, struct device_node *dup) { struct property *prop; + struct property *save_next; struct device_node *child; - - for_each_property_of_node(np, prop) - of_add_property(dup, prop); + int ret; for_each_child_of_node(np, child) child->parent = dup; + + /* + * "unittest internal error: unable to add testdata property" + * + * If this message reports a property in node '/__symbols__' then + * the respective unittest overlay contains a label that has the + * same name as a label in the live devicetree. The label will + * be in the live devicetree only if the devicetree source was + * compiled with the '-@' option. If you encounter this error, + * please consider renaming __all__ of the labels in the unittest + * overlay dts files with an odd prefix that is unlikely to be + * used in a real devicetree. + */ + + /* + * open code for_each_property_of_node() because of_add_property() + * sets prop->next to NULL + */ + for (prop = np->properties; prop != NULL; prop = save_next) { + save_next = prop->next; + ret = of_add_property(dup, prop); + if (ret) + pr_err("unittest internal error: unable to add testdata property %pOF/%s", + np, prop->name); + } } /** @@ -1089,18 +1113,23 @@ static void update_node_properties(struct device_node *np, * * @np: Node to attach to live tree */ -static int attach_node_and_children(struct device_node *np) +static void attach_node_and_children(struct device_node *np) { struct device_node *next, *dup, *child; unsigned long flags; const char *full_name; full_name = kasprintf(GFP_KERNEL, "%pOF", np); + + if (!strcmp(full_name, "/__local_fixups__") || + !strcmp(full_name, "/__fixups__")) + return; + dup = of_find_node_by_path(full_name); kfree(full_name); if (dup) { update_node_properties(np, dup); - return 0; + return; } child = np->child; @@ -1121,8 +1150,6 @@ static int attach_node_and_children(struct device_node *np) attach_node_and_children(child); child = next; } - - return 0; } /** From 367e64ce11fc59fc51b41a8f0f2ba4b5daa23a17 Mon Sep 17 00:00:00 2001 From: Frank Rowand Date: Thu, 4 Oct 2018 20:40:21 -0700 Subject: [PATCH 240/299] of: unittest: initialize args before calling of_*parse_*() [ Upstream commit eeb07c573ec307c53fe2f6ac6d8d11c261f64006 ] Callers of of_irq_parse_one() blindly use the pointer args.np without checking whether of_irq_parse_one() had an error and thus did not set the value of args.np. Initialize args to zero so that using the format "%pOF" to show the value of args.np will show "(null)" when of_irq_parse_one() has an error. This prevents the dereference of a random value. Make the same fix for callers of of_parse_phandle_with_args() and of_parse_phandle_with_args_map(). Reported-by: Guenter Roeck Tested-by: Alan Tull Signed-off-by: Frank Rowand Signed-off-by: Sasha Levin --- drivers/of/unittest.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index e8997cdb228c..68f52966bbc0 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -375,6 +375,7 @@ static void __init of_unittest_parse_phandle_with_args(void) for (i = 0; i < 8; i++) { bool passed = true; + memset(&args, 0, sizeof(args)); rc = of_parse_phandle_with_args(np, "phandle-list", "#phandle-cells", i, &args); @@ -428,6 +429,7 @@ static void __init of_unittest_parse_phandle_with_args(void) } /* Check for missing list property */ + memset(&args, 0, sizeof(args)); rc = of_parse_phandle_with_args(np, "phandle-list-missing", "#phandle-cells", 0, &args); unittest(rc == -ENOENT, "expected:%i got:%i\n", -ENOENT, rc); @@ -436,6 +438,7 @@ static void __init of_unittest_parse_phandle_with_args(void) unittest(rc == -ENOENT, "expected:%i got:%i\n", -ENOENT, rc); /* Check for missing cells property */ + memset(&args, 0, sizeof(args)); rc = of_parse_phandle_with_args(np, "phandle-list", "#phandle-cells-missing", 0, &args); unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); @@ -444,6 +447,7 @@ static void __init of_unittest_parse_phandle_with_args(void) unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); /* Check for bad phandle in list */ + memset(&args, 0, sizeof(args)); rc = of_parse_phandle_with_args(np, "phandle-list-bad-phandle", "#phandle-cells", 0, &args); unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); @@ -452,6 +456,7 @@ static void __init of_unittest_parse_phandle_with_args(void) unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); /* Check for incorrectly formed argument list */ + memset(&args, 0, sizeof(args)); rc = of_parse_phandle_with_args(np, "phandle-list-bad-args", "#phandle-cells", 1, &args); unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); @@ -502,6 +507,7 @@ static void __init of_unittest_parse_phandle_with_args_map(void) for (i = 0; i < 8; i++) { bool passed = true; + memset(&args, 0, sizeof(args)); rc = of_parse_phandle_with_args_map(np, "phandle-list", "phandle", i, &args); @@ -559,21 +565,25 @@ static void __init of_unittest_parse_phandle_with_args_map(void) } /* Check for missing list property */ + memset(&args, 0, sizeof(args)); rc = of_parse_phandle_with_args_map(np, "phandle-list-missing", "phandle", 0, &args); unittest(rc == -ENOENT, "expected:%i got:%i\n", -ENOENT, rc); /* Check for missing cells,map,mask property */ + memset(&args, 0, sizeof(args)); rc = of_parse_phandle_with_args_map(np, "phandle-list", "phandle-missing", 0, &args); unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); /* Check for bad phandle in list */ + memset(&args, 0, sizeof(args)); rc = of_parse_phandle_with_args_map(np, "phandle-list-bad-phandle", "phandle", 0, &args); unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); /* Check for incorrectly formed argument list */ + memset(&args, 0, sizeof(args)); rc = of_parse_phandle_with_args_map(np, "phandle-list-bad-args", "phandle", 1, &args); unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); @@ -783,7 +793,7 @@ static void __init of_unittest_parse_interrupts(void) for (i = 0; i < 4; i++) { bool passed = true; - args.args_count = 0; + memset(&args, 0, sizeof(args)); rc = of_irq_parse_one(np, i, &args); passed &= !rc; @@ -804,7 +814,7 @@ static void __init of_unittest_parse_interrupts(void) for (i = 0; i < 4; i++) { bool passed = true; - args.args_count = 0; + memset(&args, 0, sizeof(args)); rc = of_irq_parse_one(np, i, &args); /* Test the values from tests-phandle.dtsi */ @@ -860,6 +870,7 @@ static void __init of_unittest_parse_interrupts_extended(void) for (i = 0; i < 7; i++) { bool passed = true; + memset(&args, 0, sizeof(args)); rc = of_irq_parse_one(np, i, &args); /* Test the values from tests-phandle.dtsi */ From ee7d2473812be2fbadc419764eb580478f9f31ff Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Thu, 8 Nov 2018 11:52:27 +0000 Subject: [PATCH 241/299] tools: bpftool: pass an argument to silence open_obj_pinned() [ Upstream commit f120919f9905a2cad9dea792a28a11fb623f72c1 ] Function open_obj_pinned() prints error messages when it fails to open a link in the BPF virtual file system. However, in some occasions it is not desirable to print an error, for example when we parse all links under the bpffs root, and the error is due to some paths actually being symbolic links. Example output: # ls -l /sys/fs/bpf/ lrwxrwxrwx 1 root root 0 Oct 18 19:00 ip -> /sys/fs/bpf/tc/ drwx------ 3 root root 0 Oct 18 19:00 tc lrwxrwxrwx 1 root root 0 Oct 18 19:00 xdp -> /sys/fs/bpf/tc/ # bpftool --bpffs prog show Error: bpf obj get (/sys/fs/bpf): Permission denied Error: bpf obj get (/sys/fs/bpf): Permission denied # strace -e bpf bpftool --bpffs prog show bpf(BPF_OBJ_GET, {pathname="/sys/fs/bpf/ip", bpf_fd=0}, 72) = -1 EACCES (Permission denied) Error: bpf obj get (/sys/fs/bpf): Permission denied bpf(BPF_OBJ_GET, {pathname="/sys/fs/bpf/xdp", bpf_fd=0}, 72) = -1 EACCES (Permission denied) Error: bpf obj get (/sys/fs/bpf): Permission denied ... To fix it, pass a bool as a second argument to the function, and prevent it from printing an error when the argument is set to true. Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Daniel Borkmann Signed-off-by: Sasha Levin --- tools/bpf/bpftool/common.c | 15 ++++++++------- tools/bpf/bpftool/main.h | 2 +- 2 files changed, 9 insertions(+), 8 deletions(-) diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index be7aebff0c1e..158469f57461 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -130,16 +130,17 @@ static int mnt_bpffs(const char *target, char *buff, size_t bufflen) return 0; } -int open_obj_pinned(char *path) +int open_obj_pinned(char *path, bool quiet) { int fd; fd = bpf_obj_get(path); if (fd < 0) { - p_err("bpf obj get (%s): %s", path, - errno == EACCES && !is_bpffs(dirname(path)) ? - "directory not in bpf file system (bpffs)" : - strerror(errno)); + if (!quiet) + p_err("bpf obj get (%s): %s", path, + errno == EACCES && !is_bpffs(dirname(path)) ? + "directory not in bpf file system (bpffs)" : + strerror(errno)); return -1; } @@ -151,7 +152,7 @@ int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type) enum bpf_obj_type type; int fd; - fd = open_obj_pinned(path); + fd = open_obj_pinned(path, false); if (fd < 0) return -1; @@ -384,7 +385,7 @@ int build_pinned_obj_table(struct pinned_obj_table *tab, while ((ftse = fts_read(fts))) { if (!(ftse->fts_info & FTS_F)) continue; - fd = open_obj_pinned(ftse->fts_path); + fd = open_obj_pinned(ftse->fts_path, true); if (fd < 0) continue; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 238e734d75b3..057a227bdb9f 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -126,7 +126,7 @@ int cmd_select(const struct cmd *cmds, int argc, char **argv, int get_fd_type(int fd); const char *get_fd_type_name(enum bpf_obj_type type); char *get_fdinfo(int fd, const char *key); -int open_obj_pinned(char *path); +int open_obj_pinned(char *path, bool quiet); int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type); int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)); int do_pin_fd(int fd, const char *name); From c24fe7807320ca9e881ee30e1a54b71b2c05ee1e Mon Sep 17 00:00:00 2001 From: Sriram R Date: Fri, 19 Oct 2018 14:42:59 +0530 Subject: [PATCH 242/299] cfg80211: Prevent regulatory restore during STA disconnect in concurrent interfaces [ Upstream commit 113f3aaa81bd56aba02659786ed65cbd9cb9a6fc ] Currently when an AP and STA interfaces are active in the same or different radios, regulatory settings are restored whenever the STA disconnects. This restores all channel information including dfs states in all radios. For example, if an AP interface is active in one radio and STA in another, when radar is detected on the AP interface, the dfs state of the channel will be changed to UNAVAILABLE. But when the STA interface disconnects, this issues a regulatory disconnect hint which restores all regulatory settings in all the radios attached and thereby losing the stored dfs state on the other radio where the channel was marked as unavailable earlier. Hence prevent such regulatory restore whenever another active beaconing interface is present in the same or other radios. Signed-off-by: Sriram R Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/wireless/sme.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/wireless/sme.c b/net/wireless/sme.c index d536b07582f8..c7047c7b4e80 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -642,11 +642,15 @@ static bool cfg80211_is_all_idle(void) * All devices must be idle as otherwise if you are actively * scanning some new beacon hints could be learned and would * count as new regulatory hints. + * Also if there is any other active beaconing interface we + * need not issue a disconnect hint and reset any info such + * as chan dfs state, etc. */ list_for_each_entry(rdev, &cfg80211_rdev_list, list) { list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { wdev_lock(wdev); - if (wdev->conn || wdev->current_bss) + if (wdev->conn || wdev->current_bss || + cfg80211_beaconing_iface_active(wdev)) is_all_idle = false; wdev_unlock(wdev); } From bad4da12b7977e562e48ceee914d290e66768396 Mon Sep 17 00:00:00 2001 From: Brian Masney Date: Wed, 31 Oct 2018 20:11:47 -0400 Subject: [PATCH 243/299] pinctrl: qcom: spmi-gpio: fix gpio-hog related boot issues [ Upstream commit 149a96047237574b756d872007c006acd0cc6687 ] When attempting to setup up a gpio hog, device probing would repeatedly fail with -EPROBE_DEFERED errors. It was caused by a circular dependency between the gpio and pinctrl frameworks. If the gpio-ranges property is present in device tree, then the gpio framework will handle the gpio pin registration and eliminate the circular dependency. See Christian Lamparter's commit a86caa9ba5d7 ("pinctrl: msm: fix gpio-hog related boot issues") for a detailed commit message that explains the issue in much more detail. The code comment in this commit came from Christian's commit. Signed-off-by: Brian Masney Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/qcom/pinctrl-spmi-gpio.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c index cf82db78e69e..0c30f5eb4c71 100644 --- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c @@ -1028,10 +1028,23 @@ static int pmic_gpio_probe(struct platform_device *pdev) return ret; } - ret = gpiochip_add_pin_range(&state->chip, dev_name(dev), 0, 0, npins); - if (ret) { - dev_err(dev, "failed to add pin range\n"); - goto err_range; + /* + * For DeviceTree-supported systems, the gpio core checks the + * pinctrl's device node for the "gpio-ranges" property. + * If it is present, it takes care of adding the pin ranges + * for the driver. In this case the driver can skip ahead. + * + * In order to remain compatible with older, existing DeviceTree + * files which don't set the "gpio-ranges" property or systems that + * utilize ACPI the driver has to call gpiochip_add_pin_range(). + */ + if (!of_property_read_bool(dev->of_node, "gpio-ranges")) { + ret = gpiochip_add_pin_range(&state->chip, dev_name(dev), 0, 0, + npins); + if (ret) { + dev_err(dev, "failed to add pin range\n"); + goto err_range; + } } return 0; From 5efa36e7f04abffe4f6553e6a5b3a6593bec10e7 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 31 Oct 2018 17:46:54 -0700 Subject: [PATCH 244/299] pinctrl: bcm2835: Use define directive for BCM2835_PINCONF_PARAM_PULL [ Upstream commit b40ac08ff886302a6aa457fd72e94a969f50e245 ] Clang warns when one enumerated type is implicitly converted to another: drivers/pinctrl/bcm/pinctrl-bcm2835.c:707:40: warning: implicit conversion from enumeration type 'enum bcm2835_pinconf_param' to different enumeration type 'enum pin_config_param' [-Wenum-conversion] configs[0] = pinconf_to_config_packed(BCM2835_PINCONF_PARAM_PULL, pull); ~~~~~~~~~~~~~~~~~~~~~~~~ ^~~~~~~~~~~~~~~~~~~~~~~~~~ 1 warning generated. It is expected that pinctrl drivers can extend pin_config_param because of the gap between PIN_CONFIG_END and PIN_CONFIG_MAX so this conversion isn't an issue. Most drivers that take advantage of this define the PIN_CONFIG variables as constants, rather than enumerated values. Do the same thing here so that Clang no longer warns. Signed-off-by: Nathan Chancellor Acked-by: Stefan Wahren Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/bcm/pinctrl-bcm2835.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c index 08925d24180b..1bd3c10ce189 100644 --- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c +++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c @@ -72,10 +72,8 @@ #define GPIO_REG_OFFSET(p) ((p) / 32) #define GPIO_REG_SHIFT(p) ((p) % 32) -enum bcm2835_pinconf_param { - /* argument: bcm2835_pinconf_pull */ - BCM2835_PINCONF_PARAM_PULL = (PIN_CONFIG_END + 1), -}; +/* argument: bcm2835_pinconf_pull */ +#define BCM2835_PINCONF_PARAM_PULL (PIN_CONFIG_END + 1) struct bcm2835_pinctrl { struct device *dev; From 0858006cda38ef89c0263d081077ef7f21b53ca1 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 1 Nov 2018 08:00:08 -0700 Subject: [PATCH 245/299] pinctrl: lpc18xx: Use define directive for PIN_CONFIG_GPIO_PIN_INT [ Upstream commit f24bfb39975c241374cadebbd037c17960cf1412 ] Clang warns when one enumerated type is implicitly converted to another: drivers/pinctrl/pinctrl-lpc18xx.c:643:29: warning: implicit conversion from enumeration type 'enum lpc18xx_pin_config_param' to different enumeration type 'enum pin_config_param' [-Wenum-conversion] {"nxp,gpio-pin-interrupt", PIN_CONFIG_GPIO_PIN_INT, 0}, ~ ^~~~~~~~~~~~~~~~~~~~~~~ drivers/pinctrl/pinctrl-lpc18xx.c:648:12: warning: implicit conversion from enumeration type 'enum lpc18xx_pin_config_param' to different enumeration type 'enum pin_config_param' [-Wenum-conversion] PCONFDUMP(PIN_CONFIG_GPIO_PIN_INT, "gpio pin int", NULL, true), ~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/pinctrl/pinconf-generic.h:163:11: note: expanded from macro 'PCONFDUMP' .param = a, .display = b, .format = c, .has_arg = d \ ^ 2 warnings generated. It is expected that pinctrl drivers can extend pin_config_param because of the gap between PIN_CONFIG_END and PIN_CONFIG_MAX so this conversion isn't an issue. Most drivers that take advantage of this define the PIN_CONFIG variables as constants, rather than enumerated values. Do the same thing here so that Clang no longer warns. Link: https://github.com/ClangBuiltLinux/linux/issues/140 Signed-off-by: Nathan Chancellor Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-lpc18xx.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/pinctrl/pinctrl-lpc18xx.c b/drivers/pinctrl/pinctrl-lpc18xx.c index 190f17e4bbda..1d3b88e6ab86 100644 --- a/drivers/pinctrl/pinctrl-lpc18xx.c +++ b/drivers/pinctrl/pinctrl-lpc18xx.c @@ -630,14 +630,8 @@ static const struct pinctrl_pin_desc lpc18xx_pins[] = { LPC18XX_PIN(i2c0_sda, PIN_I2C0_SDA), }; -/** - * enum lpc18xx_pin_config_param - possible pin configuration parameters - * @PIN_CONFIG_GPIO_PIN_INT: route gpio to the gpio pin interrupt - * controller. - */ -enum lpc18xx_pin_config_param { - PIN_CONFIG_GPIO_PIN_INT = PIN_CONFIG_END + 1, -}; +/* PIN_CONFIG_GPIO_PIN_INT: route gpio to the gpio pin interrupt controller */ +#define PIN_CONFIG_GPIO_PIN_INT (PIN_CONFIG_END + 1) static const struct pinconf_generic_params lpc18xx_params[] = { {"nxp,gpio-pin-interrupt", PIN_CONFIG_GPIO_PIN_INT, 0}, From c0418c4a61aa52bf46c234ccc6a067ae0ddbd3ce Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 7 Nov 2018 01:56:40 -0700 Subject: [PATCH 246/299] pinctrl: zynq: Use define directive for PIN_CONFIG_IO_STANDARD [ Upstream commit cd8a145a066a1a3beb0ae615c7cb2ee4217418d7 ] Clang warns when one enumerated type is implicitly converted to another: drivers/pinctrl/pinctrl-zynq.c:985:18: warning: implicit conversion from enumeration type 'enum zynq_pin_config_param' to different enumeration type 'enum pin_config_param' [-Wenum-conversion] {"io-standard", PIN_CONFIG_IOSTANDARD, zynq_iostd_lvcmos18}, ~ ^~~~~~~~~~~~~~~~~~~~~ drivers/pinctrl/pinctrl-zynq.c:990:16: warning: implicit conversion from enumeration type 'enum zynq_pin_config_param' to different enumeration type 'enum pin_config_param' [-Wenum-conversion] = { PCONFDUMP(PIN_CONFIG_IOSTANDARD, "IO-standard", NULL, true), ~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/pinctrl/pinconf-generic.h:163:11: note: expanded from macro 'PCONFDUMP' .param = a, .display = b, .format = c, .has_arg = d \ ^ 2 warnings generated. It is expected that pinctrl drivers can extend pin_config_param because of the gap between PIN_CONFIG_END and PIN_CONFIG_MAX so this conversion isn't an issue. Most drivers that take advantage of this define the PIN_CONFIG variables as constants, rather than enumerated values. Do the same thing here so that Clang no longer warns. Signed-off-by: Nathan Chancellor Acked-by: Michal Simek Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-zynq.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/pinctrl/pinctrl-zynq.c b/drivers/pinctrl/pinctrl-zynq.c index a0daf27042bd..90fd37e8207b 100644 --- a/drivers/pinctrl/pinctrl-zynq.c +++ b/drivers/pinctrl/pinctrl-zynq.c @@ -971,15 +971,12 @@ enum zynq_io_standards { zynq_iostd_max }; -/** - * enum zynq_pin_config_param - possible pin configuration parameters - * @PIN_CONFIG_IOSTANDARD: if the pin can select an IO standard, the argument to +/* + * PIN_CONFIG_IOSTANDARD: if the pin can select an IO standard, the argument to * this parameter (on a custom format) tells the driver which alternative * IO standard to use. */ -enum zynq_pin_config_param { - PIN_CONFIG_IOSTANDARD = PIN_CONFIG_END + 1, -}; +#define PIN_CONFIG_IOSTANDARD (PIN_CONFIG_END + 1) static const struct pinconf_generic_params zynq_dt_params[] = { {"io-standard", PIN_CONFIG_IOSTANDARD, zynq_iostd_lvcmos18}, From 597a37d01b69671088d70fffffcfd38f10a1cda7 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Wed, 17 Oct 2018 13:10:54 +0530 Subject: [PATCH 247/299] PCI: keystone: Use quirk to limit MRRS for K2G [ Upstream commit 148e340c0696369fadbbddc8f4bef801ed247d71 ] PCI controller in K2G also has a limitation that memory read request size (MRRS) must not exceed 256 bytes. Use the quirk to limit MRRS (added for K2HK, K2L and K2E) for K2G as well. Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pci-keystone.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c index 5e199e7d2d4f..765357b87ff6 100644 --- a/drivers/pci/controller/dwc/pci-keystone.c +++ b/drivers/pci/controller/dwc/pci-keystone.c @@ -36,6 +36,7 @@ #define PCIE_RC_K2HK 0xb008 #define PCIE_RC_K2E 0xb009 #define PCIE_RC_K2L 0xb00a +#define PCIE_RC_K2G 0xb00b #define to_keystone_pcie(x) dev_get_drvdata((x)->dev) @@ -50,6 +51,8 @@ static void quirk_limit_mrrs(struct pci_dev *dev) .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, }, { PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2L), .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, }, + { PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2G), + .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, }, { 0, }, }; From 1b0f1b2dde066c8dd78c9df9e33c82eecf572dcc Mon Sep 17 00:00:00 2001 From: Igor Konopko Date: Fri, 23 Nov 2018 16:58:10 +0100 Subject: [PATCH 248/299] nvme-pci: fix surprise removal [ Upstream commit 751a0cc0cd3a0d51e6aaf6fd3b8bd31f4ecfaf3e ] When a PCIe NVMe device is not present, nvme_dev_remove_admin() calls blk_cleanup_queue() on the admin queue, which frees the hctx for that queue. Moments later, on the same path nvme_kill_queues() calls blk_mq_unquiesce_queue() on admin queue and tries to access hctx of it, which leads to following OOPS: Oops: 0000 [#1] SMP PTI RIP: 0010:sbitmap_any_bit_set+0xb/0x40 Call Trace: blk_mq_run_hw_queue+0xd5/0x150 blk_mq_run_hw_queues+0x3a/0x50 nvme_kill_queues+0x26/0x50 nvme_remove_namespaces+0xb2/0xc0 nvme_remove+0x60/0x140 pci_device_remove+0x3b/0xb0 Fixes: cb4bfda62afa2 ("nvme-pci: fix hot removal during error handling") Signed-off-by: Igor Konopko Reviewed-by: Keith Busch Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/host/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 5d0f99bcc987..44da9fe5b27b 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3647,7 +3647,7 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) down_read(&ctrl->namespaces_rwsem); /* Forcibly unquiesce queues to avoid blocking dispatch */ - if (ctrl->admin_q) + if (ctrl->admin_q && !blk_queue_dying(ctrl->admin_q)) blk_mq_unquiesce_queue(ctrl->admin_q); list_for_each_entry(ns, &ctrl->namespaces, list) From 1efa17ab9cb830119b5f456b5f0a37aa3f44adbe Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Tue, 15 Jan 2019 12:28:32 +0530 Subject: [PATCH 249/299] spi: omap2-mcspi: Fix DMA and FIFO event trigger size mismatch [ Upstream commit baf8b9f8d260c55a86405f70a384c29cda888476 ] Commit b682cffa3ac6 ("spi: omap2-mcspi: Set FIFO DMA trigger level to word length") broke SPI transfers where bits_per_word != 8. This is because of mimsatch between McSPI FIFO level event trigger size (SPI word length) and DMA request size(word length * maxburst). This leads to data corruption, lockup and errors like: spi1.0: EOW timed out Fix this by setting DMA maxburst size to 1 so that McSPI FIFO level event trigger size matches DMA request size. Fixes: b682cffa3ac6 ("spi: omap2-mcspi: Set FIFO DMA trigger level to word length") Cc: stable@vger.kernel.org Reported-by: David Lechner Tested-by: David Lechner Signed-off-by: Vignesh R Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-omap2-mcspi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index f50cb8a4b413..eb2d2de172af 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -607,8 +607,8 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer) cfg.dst_addr = cs->phys + OMAP2_MCSPI_TX0; cfg.src_addr_width = width; cfg.dst_addr_width = width; - cfg.src_maxburst = es; - cfg.dst_maxburst = es; + cfg.src_maxburst = 1; + cfg.dst_maxburst = 1; rx = xfer->rx_buf; tx = xfer->tx_buf; From 896f7398152baf02aec8696cd8141d76946b0eb2 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 6 Dec 2018 12:55:25 +0900 Subject: [PATCH 250/299] i2c: uniphier-f: fix timeout error after reading 8 bytes [ Upstream commit c2a653deaa81f5a750c0dfcbaf9f8e5195cbe4a5 ] I was totally screwed up in commit eaba68785c2d ("i2c: uniphier-f: fix race condition when IRQ is cleared"). Since that commit, if the number of read bytes is multiple of the FIFO size (8, 16, 24... bytes), the STOP condition could be issued twice, depending on the timing. If this happens, the controller will go wrong, resulting in the timeout error. It was more than 3 years ago when I wrote this driver, so my memory about this hardware was vague. Please let me correct the description in the commit log of eaba68785c2d. Clearing the IRQ status on exiting the IRQ handler is absolutely fine. This controller makes a pause while any IRQ status is asserted. If the IRQ status is cleared first, the hardware may start the next transaction before the IRQ handler finishes what it supposed to do. This partially reverts the bad commit with clear comments so that I will never repeat this mistake. I also investigated what is happening at the last moment of the read mode. The UNIPHIER_FI2C_INT_RF interrupt is asserted a bit earlier (by half a period of the clock cycle) than UNIPHIER_FI2C_INT_RB. I consulted a hardware engineer, and I got the following information: UNIPHIER_FI2C_INT_RF asserted at the falling edge of SCL at the 8th bit. UNIPHIER_FI2C_INT_RB asserted at the rising edge of SCL at the 9th (ACK) bit. In order to avoid calling uniphier_fi2c_stop() twice, check the latter interrupt. I also commented this because it is obscure hardware internal. Fixes: eaba68785c2d ("i2c: uniphier-f: fix race condition when IRQ is cleared") Signed-off-by: Masahiro Yamada Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-uniphier-f.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/drivers/i2c/busses/i2c-uniphier-f.c b/drivers/i2c/busses/i2c-uniphier-f.c index 928ea9930d17..dd0687e36a47 100644 --- a/drivers/i2c/busses/i2c-uniphier-f.c +++ b/drivers/i2c/busses/i2c-uniphier-f.c @@ -173,8 +173,6 @@ static irqreturn_t uniphier_fi2c_interrupt(int irq, void *dev_id) "interrupt: enabled_irqs=%04x, irq_status=%04x\n", priv->enabled_irqs, irq_status); - uniphier_fi2c_clear_irqs(priv, irq_status); - if (irq_status & UNIPHIER_FI2C_INT_STOP) goto complete; @@ -214,7 +212,13 @@ static irqreturn_t uniphier_fi2c_interrupt(int irq, void *dev_id) if (irq_status & (UNIPHIER_FI2C_INT_RF | UNIPHIER_FI2C_INT_RB)) { uniphier_fi2c_drain_rxfifo(priv); - if (!priv->len) + /* + * If the number of bytes to read is multiple of the FIFO size + * (msg->len == 8, 16, 24, ...), the INT_RF bit is set a little + * earlier than INT_RB. We wait for INT_RB to confirm the + * completion of the current message. + */ + if (!priv->len && (irq_status & UNIPHIER_FI2C_INT_RB)) goto data_done; if (unlikely(priv->flags & UNIPHIER_FI2C_MANUAL_NACK)) { @@ -253,6 +257,13 @@ complete: } handled: + /* + * This controller makes a pause while any bit of the IRQ status is + * asserted. Clear the asserted bit to kick the controller just before + * exiting the handler. + */ + uniphier_fi2c_clear_irqs(priv, irq_status); + spin_unlock(&priv->lock); return IRQ_HANDLED; From 091ed093c9c8a1c4c0243924131c8344383aeec3 Mon Sep 17 00:00:00 2001 From: zhong jiang Date: Mon, 8 Apr 2019 12:07:17 +0800 Subject: [PATCH 251/299] mm/memory_hotplug: Do not unlock when fails to take the device_hotplug_lock [ Upstream commit d2ab99403ee00d8014e651728a4702ea1ae5e52c ] When adding the memory by probing memory block in sysfs interface, there is an obvious issue that we will unlock the device_hotplug_lock when fails to takes it. That issue was introduced in Commit 8df1d0e4a265 ("mm/memory_hotplug: make add_memory() take the device_hotplug_lock") We should drop out in time when fails to take the device_hotplug_lock. Fixes: 8df1d0e4a265 ("mm/memory_hotplug: make add_memory() take the device_hotplug_lock") Reported-by: Yang yingliang Signed-off-by: zhong jiang Reviewed-by: Oscar Salvador Reviewed-by: David Hildenbrand Acked-by: Michal Hocko Cc: stable Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/base/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 0f8e77f78cc8..ac1574a69610 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -510,7 +510,7 @@ memory_probe_store(struct device *dev, struct device_attribute *attr, ret = lock_device_hotplug_sysfs(); if (ret) - goto out; + return ret; nid = memory_add_physaddr_to_nid(phys_addr); ret = __add_memory(nid, phys_addr, From 2b3541ffdd05198b329d21920a0f606009a1058b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 12 Dec 2018 15:27:38 -0800 Subject: [PATCH 252/299] ipv6: Fix handling of LLA with VRF and sockets bound to VRF [ Upstream commit c2027d1e17582903e368abf5d4838b22a98f2b7b ] A recent commit allows sockets bound to a VRF to receive ipv6 link local packets. However, it only works for UDP and worse TCP connection attempts to the LLA with the only listener bound to the VRF just hang where as before the client gets a reset and connection refused. Fix by adjusting ir_iif for LL addresses and packets received through a device enslaved to a VRF. Fixes: 6f12fa775530 ("vrf: mark skb for multicast or link-local as enslaved to VRF") Reported-by: Donald Sharp Cc: Mike Manning Signed-off-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv6/tcp_ipv6.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e7cdfa92c382..9a117a79af65 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -734,6 +734,7 @@ static void tcp_v6_init_req(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb) { + bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); struct inet_request_sock *ireq = inet_rsk(req); const struct ipv6_pinfo *np = inet6_sk(sk_listener); @@ -741,7 +742,7 @@ static void tcp_v6_init_req(struct request_sock *req, ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; /* So that link locals have meaning */ - if (!sk_listener->sk_bound_dev_if && + if ((!sk_listener->sk_bound_dev_if || l3_slave) && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = tcp_v6_iif(skb); From 16a300fb1dbb119023275798bbd749c3a3a54d18 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 1 Feb 2019 11:09:54 +0100 Subject: [PATCH 253/299] cfg80211: call disconnect_wk when AP stops [ Upstream commit e005bd7ddea06784c1eb91ac5bb6b171a94f3b05 ] Since we now prevent regulatory restore during STA disconnect if concurrent AP interfaces are active, we need to reschedule this check when the AP state changes. This fixes never doing a restore when an AP is the last interface to stop. Or to put it another way: we need to re-check after anything we check here changes. Cc: stable@vger.kernel.org Fixes: 113f3aaa81bd ("cfg80211: Prevent regulatory restore during STA disconnect in concurrent interfaces") Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/wireless/ap.c | 2 ++ net/wireless/core.h | 2 ++ net/wireless/sme.c | 2 +- 3 files changed, 5 insertions(+), 1 deletion(-) diff --git a/net/wireless/ap.c b/net/wireless/ap.c index 882d97bdc6bf..550ac9d827fe 100644 --- a/net/wireless/ap.c +++ b/net/wireless/ap.c @@ -41,6 +41,8 @@ int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, cfg80211_sched_dfs_chan_update(rdev); } + schedule_work(&cfg80211_disconnect_work); + return err; } diff --git a/net/wireless/core.h b/net/wireless/core.h index 7f52ef569320..f5d58652108d 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -430,6 +430,8 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev); bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range, u32 center_freq_khz, u32 bw_khz); +extern struct work_struct cfg80211_disconnect_work; + /** * cfg80211_chandef_dfs_usable - checks if chandef is DFS usable * @wiphy: the wiphy to validate against diff --git a/net/wireless/sme.c b/net/wireless/sme.c index c7047c7b4e80..07c2196e9d57 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -667,7 +667,7 @@ static void disconnect_work(struct work_struct *work) rtnl_unlock(); } -static DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); +DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); /* From 006360ec33d9387610f641c633aef0e523753b8d Mon Sep 17 00:00:00 2001 From: Vinayak Menon Date: Fri, 15 Nov 2019 17:35:00 -0800 Subject: [PATCH 254/299] mm/page_io.c: do not free shared swap slots [ Upstream commit 5df373e95689b9519b8557da7c5bd0db0856d776 ] The following race is observed due to which a processes faulting on a swap entry, finds the page neither in swapcache nor swap. This causes zram to give a zero filled page that gets mapped to the process, resulting in a user space crash later. Consider parent and child processes Pa and Pb sharing the same swap slot with swap_count 2. Swap is on zram with SWP_SYNCHRONOUS_IO set. Virtual address 'VA' of Pa and Pb points to the shared swap entry. Pa Pb fault on VA fault on VA do_swap_page do_swap_page lookup_swap_cache fails lookup_swap_cache fails Pb scheduled out swapin_readahead (deletes zram entry) swap_free (makes swap_count 1) Pb scheduled in swap_readpage (swap_count == 1) Takes SWP_SYNCHRONOUS_IO path zram enrty absent zram gives a zero filled page Fix this by making sure that swap slot is freed only when swap count drops down to one. Link: http://lkml.kernel.org/r/1571743294-14285-1-git-send-email-vinmenon@codeaurora.org Fixes: aa8d22a11da9 ("mm: swap: SWP_SYNCHRONOUS_IO: skip swapcache only if swapped page has no other reference") Signed-off-by: Vinayak Menon Suggested-by: Minchan Kim Acked-by: Minchan Kim Cc: Michal Hocko Cc: Hugh Dickins Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- mm/page_io.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/mm/page_io.c b/mm/page_io.c index aafd19ec1db4..08d2eae58fce 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -76,6 +76,7 @@ static void swap_slot_free_notify(struct page *page) { struct swap_info_struct *sis; struct gendisk *disk; + swp_entry_t entry; /* * There is no guarantee that the page is in swap cache - the software @@ -107,11 +108,11 @@ static void swap_slot_free_notify(struct page *page) * we again wish to reclaim it. */ disk = sis->bdev->bd_disk; - if (disk->fops->swap_slot_free_notify) { - swp_entry_t entry; + entry.val = page_private(page); + if (disk->fops->swap_slot_free_notify && + __swap_count(sis, entry) == 1) { unsigned long offset; - entry.val = page_private(page); offset = swp_offset(entry); SetPageDirty(page); From 03bf4876a5935ab48e4dbf56ebdffd25e44378a5 Mon Sep 17 00:00:00 2001 From: Tomas Bortoli Date: Fri, 1 Nov 2019 21:42:44 +0100 Subject: [PATCH 255/299] Bluetooth: Fix invalid-free in bcsp_close() commit cf94da6f502d8caecabd56b194541c873c8a7a3c upstream. Syzbot reported an invalid-free that I introduced fixing a memleak. bcsp_recv() also frees bcsp->rx_skb but never nullifies its value. Nullify bcsp->rx_skb every time it is freed. Signed-off-by: Tomas Bortoli Reported-by: syzbot+a0d209a4676664613e76@syzkaller.appspotmail.com Signed-off-by: Marcel Holtmann Cc: Alexander Potapenko Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/hci_bcsp.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/bluetooth/hci_bcsp.c b/drivers/bluetooth/hci_bcsp.c index 66fe1e6dc631..27829273f3c9 100644 --- a/drivers/bluetooth/hci_bcsp.c +++ b/drivers/bluetooth/hci_bcsp.c @@ -606,6 +606,7 @@ static int bcsp_recv(struct hci_uart *hu, const void *data, int count) if (*ptr == 0xc0) { BT_ERR("Short BCSP packet"); kfree_skb(bcsp->rx_skb); + bcsp->rx_skb = NULL; bcsp->rx_state = BCSP_W4_PKT_START; bcsp->rx_count = 0; } else @@ -621,6 +622,7 @@ static int bcsp_recv(struct hci_uart *hu, const void *data, int count) bcsp->rx_skb->data[2])) != bcsp->rx_skb->data[3]) { BT_ERR("Error in BCSP hdr checksum"); kfree_skb(bcsp->rx_skb); + bcsp->rx_skb = NULL; bcsp->rx_state = BCSP_W4_PKT_DELIMITER; bcsp->rx_count = 0; continue; @@ -645,6 +647,7 @@ static int bcsp_recv(struct hci_uart *hu, const void *data, int count) bscp_get_crc(bcsp)); kfree_skb(bcsp->rx_skb); + bcsp->rx_skb = NULL; bcsp->rx_state = BCSP_W4_PKT_DELIMITER; bcsp->rx_count = 0; continue; From 4ae7392ab6f457b8d695df271d9344f54a326077 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 11 Nov 2019 14:12:27 -0800 Subject: [PATCH 256/299] KVM: MMU: Do not treat ZONE_DEVICE pages as being reserved commit a78986aae9b2988f8493f9f65a587ee433e83bc3 upstream. Explicitly exempt ZONE_DEVICE pages from kvm_is_reserved_pfn() and instead manually handle ZONE_DEVICE on a case-by-case basis. For things like page refcounts, KVM needs to treat ZONE_DEVICE pages like normal pages, e.g. put pages grabbed via gup(). But for flows such as setting A/D bits or shifting refcounts for transparent huge pages, KVM needs to to avoid processing ZONE_DEVICE pages as the flows in question lack the underlying machinery for proper handling of ZONE_DEVICE pages. This fixes a hang reported by Adam Borowski[*] in dev_pagemap_cleanup() when running a KVM guest backed with /dev/dax memory, as KVM straight up doesn't put any references to ZONE_DEVICE pages acquired by gup(). Note, Dan Williams proposed an alternative solution of doing put_page() on ZONE_DEVICE pages immediately after gup() in order to simplify the auditing needed to ensure is_zone_device_page() is called if and only if the backing device is pinned (via gup()). But that approach would break kvm_vcpu_{un}map() as KVM requires the page to be pinned from map() 'til unmap() when accessing guest memory, unlike KVM's secondary MMU, which coordinates with mmu_notifier invalidations to avoid creating stale page references, i.e. doesn't rely on pages being pinned. [*] http://lkml.kernel.org/r/20190919115547.GA17963@angband.pl Reported-by: Adam Borowski Analyzed-by: David Hildenbrand Acked-by: Dan Williams Cc: stable@vger.kernel.org Fixes: 3565fce3a659 ("mm, x86: get_user_pages() for dax mappings") Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini [sean: backport to 4.x; resolve conflict in mmu.c] Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/mmu.c | 8 ++++---- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 26 +++++++++++++++++++++++--- 3 files changed, 28 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d7db7608de5f..eddf91a0e363 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3261,7 +3261,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, * here. */ if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) && - level == PT_PAGE_TABLE_LEVEL && + !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL && PageTransCompoundMap(pfn_to_page(pfn)) && !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) { unsigned long mask; @@ -5709,9 +5709,9 @@ restart: * the guest, and the guest page table is using 4K page size * mapping if the indirect sp has level = 1. */ - if (sp->role.direct && - !kvm_is_reserved_pfn(pfn) && - PageTransCompoundMap(pfn_to_page(pfn))) { + if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && + !kvm_is_zone_device_pfn(pfn) && + PageTransCompoundMap(pfn_to_page(pfn))) { drop_spte(kvm, sptep); need_tlb_flush = 1; goto restart; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 96207939d862..748016ae01e3 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -911,6 +911,7 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); bool kvm_is_reserved_pfn(kvm_pfn_t pfn); +bool kvm_is_zone_device_pfn(kvm_pfn_t pfn); struct kvm_irq_ack_notifier { struct hlist_node link; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 7a0d86d52230..df3fc0f214ec 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -147,10 +147,30 @@ __weak int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, return 0; } +bool kvm_is_zone_device_pfn(kvm_pfn_t pfn) +{ + /* + * The metadata used by is_zone_device_page() to determine whether or + * not a page is ZONE_DEVICE is guaranteed to be valid if and only if + * the device has been pinned, e.g. by get_user_pages(). WARN if the + * page_count() is zero to help detect bad usage of this helper. + */ + if (!pfn_valid(pfn) || WARN_ON_ONCE(!page_count(pfn_to_page(pfn)))) + return false; + + return is_zone_device_page(pfn_to_page(pfn)); +} + bool kvm_is_reserved_pfn(kvm_pfn_t pfn) { + /* + * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting + * perspective they are "normal" pages, albeit with slightly different + * usage rules. + */ if (pfn_valid(pfn)) - return PageReserved(pfn_to_page(pfn)); + return PageReserved(pfn_to_page(pfn)) && + !kvm_is_zone_device_pfn(pfn); return true; } @@ -1727,7 +1747,7 @@ EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty); void kvm_set_pfn_dirty(kvm_pfn_t pfn) { - if (!kvm_is_reserved_pfn(pfn)) { + if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) { struct page *page = pfn_to_page(pfn); if (!PageReserved(page)) @@ -1738,7 +1758,7 @@ EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty); void kvm_set_pfn_accessed(kvm_pfn_t pfn) { - if (!kvm_is_reserved_pfn(pfn)) + if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) mark_page_accessed(pfn_to_page(pfn)); } EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed); From f0cfe98332d650f31b462207d63c496b4cedaee2 Mon Sep 17 00:00:00 2001 From: Hui Peng Date: Sat, 19 Oct 2019 14:42:23 +0300 Subject: [PATCH 257/299] ath10k: Fix a NULL-ptr-deref bug in ath10k_usb_alloc_urb_from_pipe commit bfd6e6e6c5d2ee43a3d9902b36e01fc7527ebb27 upstream. The `ar_usb` field of `ath10k_usb_pipe_usb_pipe` objects are initialized to point to the containing `ath10k_usb` object according to endpoint descriptors read from the device side, as shown below in `ath10k_usb_setup_pipe_resources`: for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { endpoint = &iface_desc->endpoint[i].desc; // get the address from endpoint descriptor pipe_num = ath10k_usb_get_logical_pipe_num(ar_usb, endpoint->bEndpointAddress, &urbcount); ...... // select the pipe object pipe = &ar_usb->pipes[pipe_num]; // initialize the ar_usb field pipe->ar_usb = ar_usb; } The driver assumes that the addresses reported in endpoint descriptors from device side to be complete. If a device is malicious and does not report complete addresses, it may trigger NULL-ptr-deref `ath10k_usb_alloc_urb_from_pipe` and `ath10k_usb_free_urb_to_pipe`. This patch fixes the bug by preventing potential NULL-ptr-deref. Signed-off-by: Hui Peng Reported-by: Hui Peng Reported-by: Mathias Payer Reviewed-by: Greg Kroah-Hartman [groeck: Add driver tag to subject, fix build warning] Signed-off-by: Guenter Roeck Signed-off-by: Kalle Valo Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/ath/ath10k/usb.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/wireless/ath/ath10k/usb.c b/drivers/net/wireless/ath/ath10k/usb.c index f09a4ad2e9de..f9c79e21ab22 100644 --- a/drivers/net/wireless/ath/ath10k/usb.c +++ b/drivers/net/wireless/ath/ath10k/usb.c @@ -49,6 +49,10 @@ ath10k_usb_alloc_urb_from_pipe(struct ath10k_usb_pipe *pipe) struct ath10k_urb_context *urb_context = NULL; unsigned long flags; + /* bail if this pipe is not initialized */ + if (!pipe->ar_usb) + return NULL; + spin_lock_irqsave(&pipe->ar_usb->cs_lock, flags); if (!list_empty(&pipe->urb_list_head)) { urb_context = list_first_entry(&pipe->urb_list_head, @@ -66,6 +70,10 @@ static void ath10k_usb_free_urb_to_pipe(struct ath10k_usb_pipe *pipe, { unsigned long flags; + /* bail if this pipe is not initialized */ + if (!pipe->ar_usb) + return; + spin_lock_irqsave(&pipe->ar_usb->cs_lock, flags); pipe->urb_cnt++; From f8dc0350d32bc4c7c3b27698bbde319ca1e632a3 Mon Sep 17 00:00:00 2001 From: Denis Efremov Date: Fri, 27 Sep 2019 01:56:04 +0300 Subject: [PATCH 258/299] ath9k_hw: fix uninitialized variable data commit 80e84f36412e0c5172447b6947068dca0d04ee82 upstream. Currently, data variable in ar9003_hw_thermo_cal_apply() could be uninitialized if ar9300_otp_read_word() will fail to read the value. Initialize data variable with 0 to prevent an undefined behavior. This will be enough to handle error case when ar9300_otp_read_word() fails. Fixes: 80fe43f2bbd5 ("ath9k_hw: Read and configure thermocal for AR9462") Cc: Rajkumar Manoharan Cc: John W. Linville Cc: Kalle Valo Cc: "David S. Miller" Cc: stable@vger.kernel.org Signed-off-by: Denis Efremov Signed-off-by: Kalle Valo Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/ath/ath9k/ar9003_eeprom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c index f019a20e5a1f..983e1abbd9e4 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c @@ -4183,7 +4183,7 @@ static void ar9003_hw_thermometer_apply(struct ath_hw *ah) static void ar9003_hw_thermo_cal_apply(struct ath_hw *ah) { - u32 data, ko, kg; + u32 data = 0, ko, kg; if (!AR_SREV_9462_20_OR_LATER(ah)) return; From a268d985f08935f565937cf36f0c1a1e0ca04ad3 Mon Sep 17 00:00:00 2001 From: John Pittman Date: Mon, 11 Nov 2019 16:43:20 -0800 Subject: [PATCH 259/299] md/raid10: prevent access of uninitialized resync_pages offset commit 45422b704db392a6d79d07ee3e3670b11048bd53 upstream. Due to unneeded multiplication in the out_free_pages portion of r10buf_pool_alloc(), when using a 3-copy raid10 layout, it is possible to access a resync_pages offset that has not been initialized. This access translates into a crash of the system within resync_free_pages() while passing a bad pointer to put_page(). Remove the multiplication, preventing access to the uninitialized area. Fixes: f0250618361db ("md: raid10: don't use bio's vec table to manage resync pages") Cc: stable@vger.kernel.org # 4.12+ Signed-off-by: John Pittman Suggested-by: David Jeffery Reviewed-by: Laurence Oberman Signed-off-by: Song Liu Signed-off-by: Greg Kroah-Hartman --- drivers/md/raid10.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 25e97de36717..4cf3d8ad0b4a 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -229,7 +229,7 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data) out_free_pages: while (--j >= 0) - resync_free_pages(&rps[j * 2]); + resync_free_pages(&rps[j]); j = 0; out_free_bio: From 5779cbc98369aec83eef8fd2fbe2ff04b27196d1 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 21 Nov 2019 17:53:56 -0800 Subject: [PATCH 260/299] mm/memory_hotplug: don't access uninitialized memmaps in shrink_zone_span() commit 7ce700bf11b5e2cb84e4352bbdf2123a7a239c84 upstream. Let's limit shrinking to !ZONE_DEVICE so we can fix the current code. We should never try to touch the memmap of offline sections where we could have uninitialized memmaps and could trigger BUGs when calling page_to_nid() on poisoned pages. There is no reliable way to distinguish an uninitialized memmap from an initialized memmap that belongs to ZONE_DEVICE, as we don't have anything like SECTION_IS_ONLINE we can use similar to pfn_to_online_section() for !ZONE_DEVICE memory. E.g., set_zone_contiguous() similarly relies on pfn_to_online_section() and will therefore never set a ZONE_DEVICE zone consecutive. Stopping to shrink the ZONE_DEVICE therefore results in no observable changes, besides /proc/zoneinfo indicating different boundaries - something we can totally live with. Before commit d0dc12e86b31 ("mm/memory_hotplug: optimize memory hotplug"), the memmap was initialized with 0 and the node with the right value. So the zone might be wrong but not garbage. After that commit, both the zone and the node will be garbage when touching uninitialized memmaps. Toshiki reported a BUG (race between delayed initialization of ZONE_DEVICE memmaps without holding the memory hotplug lock and concurrent zone shrinking). https://lkml.org/lkml/2019/11/14/1040 "Iteration of create and destroy namespace causes the panic as below: kernel BUG at mm/page_alloc.c:535! CPU: 7 PID: 2766 Comm: ndctl Not tainted 5.4.0-rc4 #6 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.0-0-g63451fca13-prebuilt.qemu-project.org 04/01/2014 RIP: 0010:set_pfnblock_flags_mask+0x95/0xf0 Call Trace: memmap_init_zone_device+0x165/0x17c memremap_pages+0x4c1/0x540 devm_memremap_pages+0x1d/0x60 pmem_attach_disk+0x16b/0x600 [nd_pmem] nvdimm_bus_probe+0x69/0x1c0 really_probe+0x1c2/0x3e0 driver_probe_device+0xb4/0x100 device_driver_attach+0x4f/0x60 bind_store+0xc9/0x110 kernfs_fop_write+0x116/0x190 vfs_write+0xa5/0x1a0 ksys_write+0x59/0xd0 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 While creating a namespace and initializing memmap, if you destroy the namespace and shrink the zone, it will initialize the memmap outside the zone and trigger VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page) in set_pfnblock_flags_mask()." This BUG is also mitigated by this commit, where we for now stop to shrink the ZONE_DEVICE zone until we can do it in a safe and clean way. Link: http://lkml.kernel.org/r/20191006085646.5768-5-david@redhat.com Fixes: f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online") [visible after d0dc12e86b319] Signed-off-by: David Hildenbrand Reported-by: Aneesh Kumar K.V Reported-by: Toshiki Fukasawa Cc: Oscar Salvador Cc: David Hildenbrand Cc: Michal Hocko Cc: Pavel Tatashin Cc: Dan Williams Cc: Alexander Duyck Cc: Alexander Potapenko Cc: Andy Lutomirski Cc: Anshuman Khandual Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Damian Tometzki Cc: Dave Hansen Cc: Fenghua Yu Cc: Gerald Schaefer Cc: Greg Kroah-Hartman Cc: Halil Pasic Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Ira Weiny Cc: Jason Gunthorpe Cc: Jun Yao Cc: Logan Gunthorpe Cc: Mark Rutland Cc: Masahiro Yamada Cc: "Matthew Wilcox (Oracle)" Cc: Mel Gorman Cc: Michael Ellerman Cc: Mike Rapoport Cc: Pankaj Gupta Cc: Paul Mackerras Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Qian Cai Cc: Rich Felker Cc: Robin Murphy Cc: Steve Capper Cc: Thomas Gleixner Cc: Tom Lendacky Cc: Tony Luck Cc: Vasily Gorbik Cc: Vlastimil Babka Cc: Wei Yang Cc: Wei Yang Cc: Will Deacon Cc: Yoshinori Sato Cc: Yu Zhao Cc: [4.13+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: David Hildenbrand Signed-off-by: Greg Kroah-Hartman --- mm/memory_hotplug.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 3a0a87e7c40a..413f6709039a 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -321,12 +321,8 @@ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { - struct mem_section *ms; - for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SECTION) { - ms = __pfn_to_section(start_pfn); - - if (unlikely(!valid_section(ms))) + if (unlikely(!pfn_to_online_page(start_pfn))) continue; if (unlikely(pfn_to_nid(start_pfn) != nid)) @@ -346,15 +342,12 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { - struct mem_section *ms; unsigned long pfn; /* pfn is the end pfn of a memory section. */ pfn = end_pfn - 1; for (; pfn >= start_pfn; pfn -= PAGES_PER_SECTION) { - ms = __pfn_to_section(pfn); - - if (unlikely(!valid_section(ms))) + if (unlikely(!pfn_to_online_page(pfn))) continue; if (unlikely(pfn_to_nid(pfn) != nid)) @@ -376,7 +369,6 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, unsigned long z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */ unsigned long zone_end_pfn = z; unsigned long pfn; - struct mem_section *ms; int nid = zone_to_nid(zone); zone_span_writelock(zone); @@ -414,9 +406,7 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, */ pfn = zone_start_pfn; for (; pfn < zone_end_pfn; pfn += PAGES_PER_SECTION) { - ms = __pfn_to_section(pfn); - - if (unlikely(!valid_section(ms))) + if (unlikely(!pfn_to_online_page(pfn))) continue; if (page_zone(pfn_to_page(pfn)) != zone) @@ -472,6 +462,16 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn) int nr_pages = PAGES_PER_SECTION; unsigned long flags; +#ifdef CONFIG_ZONE_DEVICE + /* + * Zone shrinking code cannot properly deal with ZONE_DEVICE. So + * we will not try to shrink the zones - which is okay as + * set_zone_contiguous() cannot deal with ZONE_DEVICE either way. + */ + if (zone_idx(zone) == ZONE_DEVICE) + return; +#endif + pgdat_resize_lock(zone->zone_pgdat, &flags); shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); update_pgdat_span(pgdat); From 87997a7800a1c0d206ff84cbb3b6fd2fc0eb561e Mon Sep 17 00:00:00 2001 From: Max Uvarov Date: Tue, 28 May 2019 13:00:49 +0300 Subject: [PATCH 261/299] net: phy: dp83867: fix speed 10 in sgmii mode commit 333061b924539c0de081339643f45514f5f1c1e6 upstream. For supporting 10Mps speed in SGMII mode DP83867_10M_SGMII_RATE_ADAPT bit of DP83867_10M_SGMII_CFG register has to be cleared by software. That does not affect speeds 100 and 1000 so can be done on init. Signed-off-by: Max Uvarov Cc: Heiner Kallweit Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller [ adapted for kernels without phy_modify_mmd ] Signed-off-by: Adrian Bunk Signed-off-by: Greg Kroah-Hartman --- drivers/net/phy/dp83867.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index e4bf9e7d7583..8c9df863491b 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -37,6 +37,8 @@ #define DP83867_STRAP_STS1 0x006E #define DP83867_RGMIIDCTL 0x0086 #define DP83867_IO_MUX_CFG 0x0170 +#define DP83867_10M_SGMII_CFG 0x016F +#define DP83867_10M_SGMII_RATE_ADAPT_MASK BIT(7) #define DP83867_SW_RESET BIT(15) #define DP83867_SW_RESTART BIT(14) @@ -294,6 +296,23 @@ static int dp83867_config_init(struct phy_device *phydev) } } + if (phydev->interface == PHY_INTERFACE_MODE_SGMII) { + /* For support SPEED_10 in SGMII mode + * DP83867_10M_SGMII_RATE_ADAPT bit + * has to be cleared by software. That + * does not affect SPEED_100 and + * SPEED_1000. + */ + val = phy_read_mmd(phydev, DP83867_DEVADDR, + DP83867_10M_SGMII_CFG); + val &= ~DP83867_10M_SGMII_RATE_ADAPT_MASK; + ret = phy_write_mmd(phydev, DP83867_DEVADDR, + DP83867_10M_SGMII_CFG, val); + + if (ret) + return ret; + } + /* Enable Interrupt output INT_OE in CFG3 register */ if (phy_interrupt_is_valid(phydev)) { val = phy_read(phydev, DP83867_CFG3); From 36bef080b55f9264d587085d9b00d658d4eafa22 Mon Sep 17 00:00:00 2001 From: Max Uvarov Date: Tue, 28 May 2019 13:00:50 +0300 Subject: [PATCH 262/299] net: phy: dp83867: increase SGMII autoneg timer duration commit 1a97a477e666cbdededab93bd3754e508f0c09d7 upstream. After reset SGMII Autoneg timer is set to 2us (bits 6 and 5 are 01). That is not enough to finalize autonegatiation on some devices. Increase this timer duration to maximum supported 16ms. Signed-off-by: Max Uvarov Cc: Heiner Kallweit Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller [ adapted for kernels without phy_modify_mmd ] Signed-off-by: Adrian Bunk Signed-off-by: Greg Kroah-Hartman --- drivers/net/phy/dp83867.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 8c9df863491b..eeadfde15940 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -33,6 +33,12 @@ /* Extended Registers */ #define DP83867_CFG4 0x0031 +#define DP83867_CFG4_SGMII_ANEG_MASK (BIT(5) | BIT(6)) +#define DP83867_CFG4_SGMII_ANEG_TIMER_11MS (3 << 5) +#define DP83867_CFG4_SGMII_ANEG_TIMER_800US (2 << 5) +#define DP83867_CFG4_SGMII_ANEG_TIMER_2US (1 << 5) +#define DP83867_CFG4_SGMII_ANEG_TIMER_16MS (0 << 5) + #define DP83867_RGMIICTL 0x0032 #define DP83867_STRAP_STS1 0x006E #define DP83867_RGMIIDCTL 0x0086 @@ -311,6 +317,18 @@ static int dp83867_config_init(struct phy_device *phydev) if (ret) return ret; + + /* After reset SGMII Autoneg timer is set to 2us (bits 6 and 5 + * are 01). That is not enough to finalize autoneg on some + * devices. Increase this timer duration to maximum 16ms. + */ + val = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4); + val &= ~DP83867_CFG4_SGMII_ANEG_MASK; + val |= DP83867_CFG4_SGMII_ANEG_TIMER_16MS; + ret = phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4, val); + + if (ret) + return ret; } /* Enable Interrupt output INT_OE in CFG3 register */ From 046f0fcf7397fa0b6c7925d1f4fd3fe69af2278a Mon Sep 17 00:00:00 2001 From: Gang He Date: Fri, 2 Nov 2018 15:48:03 -0700 Subject: [PATCH 263/299] ocfs2: remove ocfs2_is_o2cb_active() commit a634644751c46238df58bbfe992e30c1668388db upstream. Remove ocfs2_is_o2cb_active(). We have similar functions to identify which cluster stack is being used via osb->osb_cluster_stack. Secondly, the current implementation of ocfs2_is_o2cb_active() is not totally safe. Based on the design of stackglue, we need to get ocfs2_stack_lock before using ocfs2_stack related data structures, and that active_stack pointer can be NULL in the case of mount failure. Link: http://lkml.kernel.org/r/1495441079-11708-1-git-send-email-ghe@suse.com Signed-off-by: Gang He Reviewed-by: Joseph Qi Reviewed-by: Eric Ren Acked-by: Changwei Ge Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Lee Jones Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/dlmglue.c | 2 +- fs/ocfs2/stackglue.c | 6 ------ fs/ocfs2/stackglue.h | 3 --- 3 files changed, 1 insertion(+), 10 deletions(-) diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 933aac5da193..178cb9e6772a 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3603,7 +3603,7 @@ static int ocfs2_downconvert_lock(struct ocfs2_super *osb, * we can recover correctly from node failure. Otherwise, we may get * invalid LVB in LKB, but without DLM_SBF_VALNOTVALID being set. */ - if (!ocfs2_is_o2cb_active() && + if (ocfs2_userspace_stack(osb) && lockres->l_ops->flags & LOCK_TYPE_USES_LVB) lvb = 1; diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index d6c350ba25b9..c4b029c43464 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -48,12 +48,6 @@ static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl"; */ static struct ocfs2_stack_plugin *active_stack; -inline int ocfs2_is_o2cb_active(void) -{ - return !strcmp(active_stack->sp_name, OCFS2_STACK_PLUGIN_O2CB); -} -EXPORT_SYMBOL_GPL(ocfs2_is_o2cb_active); - static struct ocfs2_stack_plugin *ocfs2_stack_lookup(const char *name) { struct ocfs2_stack_plugin *p; diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h index e3036e1790e8..f2dce10fae54 100644 --- a/fs/ocfs2/stackglue.h +++ b/fs/ocfs2/stackglue.h @@ -298,9 +298,6 @@ void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_p int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin); void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin); -/* In ocfs2_downconvert_lock(), we need to know which stack we are using */ -int ocfs2_is_o2cb_active(void); - extern struct kset *ocfs2_kset; #endif /* STACKGLUE_H */ From e02f1448282b9e83250c25d47fc09e618fdca524 Mon Sep 17 00:00:00 2001 From: Chester Lin Date: Fri, 30 Aug 2019 14:30:07 +0100 Subject: [PATCH 264/299] ARM: 8904/1: skip nomap memblocks while finding the lowmem/highmem boundary commit 1d31999cf04c21709f72ceb17e65b54a401330da upstream. adjust_lowmem_bounds() checks every memblocks in order to find the boundary between lowmem and highmem. However some memblocks could be marked as NOMAP so they are not used by kernel, which should be skipped while calculating the boundary. Signed-off-by: Chester Lin Reviewed-by: Mike Rapoport Signed-off-by: Russell King Signed-off-by: Lee Jones Signed-off-by: Greg Kroah-Hartman --- arch/arm/mm/mmu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 70e560cf8ca0..d8cbe772f690 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1195,6 +1195,9 @@ void __init adjust_lowmem_bounds(void) phys_addr_t block_start = reg->base; phys_addr_t block_end = reg->base + reg->size; + if (memblock_is_nomap(reg)) + continue; + if (reg->base < vmalloc_limit) { if (block_end > lowmem_limit) /* From 99b933bbc7b05cebf99b032a80efae5ecc41888c Mon Sep 17 00:00:00 2001 From: Alexey Brodkin Date: Tue, 22 Oct 2019 17:04:11 +0300 Subject: [PATCH 265/299] ARC: perf: Accommodate big-endian CPU commit 5effc09c4907901f0e71e68e5f2e14211d9a203f upstream. 8-letter strings representing ARC perf events are stores in two 32-bit registers as ASCII characters like that: "IJMP", "IALL", "IJMPTAK" etc. And the same order of bytes in the word is used regardless CPU endianness. Which means in case of big-endian CPU core we need to swap bytes to get the same order as if it was on little-endian CPU. Otherwise we're seeing the following error message on boot: ------------------------->8---------------------- ARC perf : 8 counters (32 bits), 40 conditions, [overflow IRQ support] sysfs: cannot create duplicate filename '/devices/arc_pct/events/pmji' CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.2.18 #3 Stack Trace: arc_unwind_core+0xd4/0xfc dump_stack+0x64/0x80 sysfs_warn_dup+0x46/0x58 sysfs_add_file_mode_ns+0xb2/0x168 create_files+0x70/0x2a0 ------------[ cut here ]------------ WARNING: CPU: 0 PID: 1 at kernel/events/core.c:12144 perf_event_sysfs_init+0x70/0xa0 Failed to register pmu: arc_pct, reason -17 Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.2.18 #3 Stack Trace: arc_unwind_core+0xd4/0xfc dump_stack+0x64/0x80 __warn+0x9c/0xd4 warn_slowpath_fmt+0x22/0x2c perf_event_sysfs_init+0x70/0xa0 ---[ end trace a75fb9a9837bd1ec ]--- ------------------------->8---------------------- What happens here we're trying to register more than one raw perf event with the same name "PMJI". Why? Because ARC perf events are 4 to 8 letters and encoded into two 32-bit words. In this particular case we deal with 2 events: * "IJMP____" which counts all jump & branch instructions * "IJMPC___" which counts only conditional jumps & branches Those strings are split in two 32-bit words this way "IJMP" + "____" & "IJMP" + "C___" correspondingly. Now if we read them swapped due to CPU core being big-endian then we read "PMJI" + "____" & "PMJI" + "___C". And since we interpret read array of ASCII letters as a null-terminated string on big-endian CPU we end up with 2 events of the same name "PMJI". Signed-off-by: Alexey Brodkin Cc: stable@vger.kernel.org Signed-off-by: Vineet Gupta Signed-off-by: Greg Kroah-Hartman --- arch/arc/kernel/perf_event.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 8aec462d90fb..30f66b123541 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -490,8 +490,8 @@ static int arc_pmu_device_probe(struct platform_device *pdev) /* loop thru all available h/w condition indexes */ for (j = 0; j < cc_bcr.c; j++) { write_aux_reg(ARC_REG_CC_INDEX, j); - cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0); - cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1); + cc_name.indiv.word0 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME0)); + cc_name.indiv.word1 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME1)); /* See if it has been mapped to a perf event_id */ for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) { From ed7312096a1f253dc8cf3cca1c838bbdeefbf067 Mon Sep 17 00:00:00 2001 From: Alexander Kapshuk Date: Tue, 24 Sep 2019 07:46:59 +0300 Subject: [PATCH 266/299] x86/insn: Fix awk regexp warnings commit 700c1018b86d0d4b3f1f2d459708c0cdf42b521d upstream. gawk 5.0.1 generates the following regexp warnings: GEN /home/sasha/torvalds/tools/objtool/arch/x86/lib/inat-tables.c awk: ../arch/x86/tools/gen-insn-attr-x86.awk:260: warning: regexp escape sequence `\:' is not a known regexp operator awk: ../arch/x86/tools/gen-insn-attr-x86.awk:350: (FILENAME=../arch/x86/lib/x86-opcode-map.txt FNR=41) warning: regexp escape sequence `\&' is not a known regexp operator Ealier versions of gawk are not known to generate these warnings. The gawk manual referenced below does not list characters ':' and '&' as needing escaping, so 'unescape' them. See https://www.gnu.org/software/gawk/manual/html_node/Escape-Sequences.html for more info. Running diff on the output generated by the script before and after applying the patch reported no differences. [ bp: Massage commit message. ] [ Caught the respective tools header discrepancy. ] Reported-by: kbuild test robot Signed-off-by: Alexander Kapshuk Signed-off-by: Borislav Petkov Acked-by: Masami Hiramatsu Cc: "H. Peter Anvin" Cc: "Peter Zijlstra (Intel)" Cc: Arnaldo Carvalho de Melo Cc: Ingo Molnar Cc: Josh Poimboeuf Cc: Thomas Gleixner Cc: x86-ml Link: https://lkml.kernel.org/r/20190924044659.3785-1-alexander.kapshuk@gmail.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/tools/gen-insn-attr-x86.awk | 4 ++-- tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk index b02a36b2c14f..a42015b305f4 100644 --- a/arch/x86/tools/gen-insn-attr-x86.awk +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -69,7 +69,7 @@ BEGIN { lprefix1_expr = "\\((66|!F3)\\)" lprefix2_expr = "\\(F3\\)" - lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)" + lprefix3_expr = "\\((F2|!F3|66&F2)\\)" lprefix_expr = "\\((66|F2|F3)\\)" max_lprefix = 4 @@ -257,7 +257,7 @@ function convert_operands(count,opnd, i,j,imm,mod) return add_flags(imm, mod) } -/^[0-9a-f]+\:/ { +/^[0-9a-f]+:/ { if (NR == 1) next # get index diff --git a/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk b/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk index b02a36b2c14f..a42015b305f4 100644 --- a/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk +++ b/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk @@ -69,7 +69,7 @@ BEGIN { lprefix1_expr = "\\((66|!F3)\\)" lprefix2_expr = "\\(F3\\)" - lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)" + lprefix3_expr = "\\((F2|!F3|66&F2)\\)" lprefix_expr = "\\((66|F2|F3)\\)" max_lprefix = 4 @@ -257,7 +257,7 @@ function convert_operands(count,opnd, i,j,imm,mod) return add_flags(imm, mod) } -/^[0-9a-f]+\:/ { +/^[0-9a-f]+:/ { if (NR == 1) next # get index From 0af5ae268e24e265494ea4e91119ddd241744195 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 15 Nov 2019 11:14:44 -0500 Subject: [PATCH 267/299] x86/speculation: Fix incorrect MDS/TAA mitigation status commit 64870ed1b12e235cfca3f6c6da75b542c973ff78 upstream. For MDS vulnerable processors with TSX support, enabling either MDS or TAA mitigations will enable the use of VERW to flush internal processor buffers at the right code path. IOW, they are either both mitigated or both not. However, if the command line options are inconsistent, the vulnerabilites sysfs files may not report the mitigation status correctly. For example, with only the "mds=off" option: vulnerabilities/mds:Vulnerable; SMT vulnerable vulnerabilities/tsx_async_abort:Mitigation: Clear CPU buffers; SMT vulnerable The mds vulnerabilities file has wrong status in this case. Similarly, the taa vulnerability file will be wrong with mds mitigation on, but taa off. Change taa_select_mitigation() to sync up the two mitigation status and have them turned off if both "mds=off" and "tsx_async_abort=off" are present. Update documentation to emphasize the fact that both "mds=off" and "tsx_async_abort=off" have to be specified together for processors that are affected by both TAA and MDS to be effective. [ bp: Massage and add kernel-parameters.txt change too. ] Fixes: 1b42f017415b ("x86/speculation/taa: Add mitigation for TSX Async Abort") Signed-off-by: Waiman Long Signed-off-by: Borislav Petkov Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jiri Kosina Cc: Jonathan Corbet Cc: Josh Poimboeuf Cc: linux-doc@vger.kernel.org Cc: Mark Gross Cc: Cc: Pawan Gupta Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tim Chen Cc: Tony Luck Cc: Tyler Hicks Cc: x86-ml Link: https://lkml.kernel.org/r/20191115161445.30809-2-longman@redhat.com Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/hw-vuln/mds.rst | 7 +++++-- .../admin-guide/hw-vuln/tsx_async_abort.rst | 5 ++++- Documentation/admin-guide/kernel-parameters.txt | 11 +++++++++++ arch/x86/kernel/cpu/bugs.c | 17 +++++++++++++++-- 4 files changed, 35 insertions(+), 5 deletions(-) diff --git a/Documentation/admin-guide/hw-vuln/mds.rst b/Documentation/admin-guide/hw-vuln/mds.rst index e3a796c0d3a2..2d19c9f4c1fe 100644 --- a/Documentation/admin-guide/hw-vuln/mds.rst +++ b/Documentation/admin-guide/hw-vuln/mds.rst @@ -265,8 +265,11 @@ time with the option "mds=". The valid arguments for this option are: ============ ============================================================= -Not specifying this option is equivalent to "mds=full". - +Not specifying this option is equivalent to "mds=full". For processors +that are affected by both TAA (TSX Asynchronous Abort) and MDS, +specifying just "mds=off" without an accompanying "tsx_async_abort=off" +will have no effect as the same mitigation is used for both +vulnerabilities. Mitigation selection guide -------------------------- diff --git a/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst b/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst index fddbd7579c53..af6865b822d2 100644 --- a/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst +++ b/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst @@ -174,7 +174,10 @@ the option "tsx_async_abort=". The valid arguments for this option are: CPU is not vulnerable to cross-thread TAA attacks. ============ ============================================================= -Not specifying this option is equivalent to "tsx_async_abort=full". +Not specifying this option is equivalent to "tsx_async_abort=full". For +processors that are affected by both TAA and MDS, specifying just +"tsx_async_abort=off" without an accompanying "mds=off" will have no +effect as the same mitigation is used for both vulnerabilities. The kernel command line also allows to control the TSX feature using the parameter "tsx=" on CPUs which support TSX control. MSR_IA32_TSX_CTRL is used diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 475ed980b25b..ce1af89dbbb8 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2359,6 +2359,12 @@ SMT on vulnerable CPUs off - Unconditionally disable MDS mitigation + On TAA-affected machines, mds=off can be prevented by + an active TAA mitigation as both vulnerabilities are + mitigated with the same mechanism so in order to disable + this mitigation, you need to specify tsx_async_abort=off + too. + Not specifying this option is equivalent to mds=full. @@ -4773,6 +4779,11 @@ vulnerable to cross-thread TAA attacks. off - Unconditionally disable TAA mitigation + On MDS-affected machines, tsx_async_abort=off can be + prevented by an active MDS mitigation as both vulnerabilities + are mitigated with the same mechanism so in order to disable + this mitigation, you need to specify mds=off too. + Not specifying this option is equivalent to tsx_async_abort=full. On CPUs which are MDS affected and deploy MDS mitigation, TAA mitigation is not diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 4684ad7ba793..21480e917f27 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -304,8 +304,12 @@ static void __init taa_select_mitigation(void) return; } - /* TAA mitigation is turned off on the cmdline (tsx_async_abort=off) */ - if (taa_mitigation == TAA_MITIGATION_OFF) + /* + * TAA mitigation via VERW is turned off if both + * tsx_async_abort=off and mds=off are specified. + */ + if (taa_mitigation == TAA_MITIGATION_OFF && + mds_mitigation == MDS_MITIGATION_OFF) goto out; if (boot_cpu_has(X86_FEATURE_MD_CLEAR)) @@ -339,6 +343,15 @@ static void __init taa_select_mitigation(void) if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); + /* + * Update MDS mitigation, if necessary, as the mds_user_clear is + * now enabled for TAA mitigation. + */ + if (mds_mitigation == MDS_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_MDS)) { + mds_mitigation = MDS_MITIGATION_FULL; + mds_select_mitigation(); + } out: pr_info("%s\n", taa_strings[taa_mitigation]); } From ed7a3dde0aa224051c6455fce3755bf48c062178 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 15 Nov 2019 11:14:45 -0500 Subject: [PATCH 268/299] x86/speculation: Fix redundant MDS mitigation message commit cd5a2aa89e847bdda7b62029d94e95488d73f6b2 upstream. Since MDS and TAA mitigations are inter-related for processors that are affected by both vulnerabilities, the followiing confusing messages can be printed in the kernel log: MDS: Vulnerable MDS: Mitigation: Clear CPU buffers To avoid the first incorrect message, defer the printing of MDS mitigation after the TAA mitigation selection has been done. However, that has the side effect of printing TAA mitigation first before MDS mitigation. [ bp: Check box is affected/mitigations are disabled first before printing and massage. ] Suggested-by: Pawan Gupta Signed-off-by: Waiman Long Signed-off-by: Borislav Petkov Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Josh Poimboeuf Cc: Mark Gross Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tim Chen Cc: Tony Luck Cc: Tyler Hicks Cc: x86-ml Link: https://lkml.kernel.org/r/20191115161445.30809-3-longman@redhat.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/bugs.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 21480e917f27..2d23a448e72d 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -39,6 +39,7 @@ static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); +static void __init mds_print_mitigation(void); static void __init taa_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ @@ -108,6 +109,12 @@ void __init check_bugs(void) mds_select_mitigation(); taa_select_mitigation(); + /* + * As MDS and TAA mitigations are inter-related, print MDS + * mitigation until after TAA mitigation selection is done. + */ + mds_print_mitigation(); + arch_smt_update(); #ifdef CONFIG_X86_32 @@ -245,6 +252,12 @@ static void __init mds_select_mitigation(void) (mds_nosmt || cpu_mitigations_auto_nosmt())) cpu_smt_disable(false); } +} + +static void __init mds_print_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) + return; pr_info("%s\n", mds_strings[mds_mitigation]); } From 344966da99c962bea479298e4d3744e0c6a513f1 Mon Sep 17 00:00:00 2001 From: Navid Emamdoost Date: Mon, 23 Sep 2019 15:09:58 -0500 Subject: [PATCH 269/299] nbd: prevent memory leak commit 03bf73c315edca28f47451913177e14cd040a216 upstream. In nbd_add_socket when krealloc succeeds, if nsock's allocation fail the reallocted memory is leak. The correct behaviour should be assigning the reallocted memory to config->socks right after success. Reviewed-by: Josef Bacik Signed-off-by: Navid Emamdoost Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/nbd.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index d76840873420..996b1ef5f076 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -984,14 +984,15 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, sockfd_put(sock); return -ENOMEM; } + + config->socks = socks; + nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL); if (!nsock) { sockfd_put(sock); return -ENOMEM; } - config->socks = socks; - nsock->fallback_index = -1; nsock->dead = false; mutex_init(&nsock->tx_lock); From d3f8c58d701caa5fb18fcea8ff93946b747b8d8a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Apr 2018 16:31:07 +0200 Subject: [PATCH 270/299] y2038: futex: Move compat implementation into futex.c commit 04e7712f4460585e5eed5b853fd8b82a9943958f upstream. We are going to share the compat_sys_futex() handler between 64-bit architectures and 32-bit architectures that need to deal with both 32-bit and 64-bit time_t, and this is easier if both entry points are in the same file. In fact, most other system call handlers do the same thing these days, so let's follow the trend here and merge all of futex_compat.c into futex.c. In the process, a few minor changes have to be done to make sure everything still makes sense: handle_futex_death() and futex_cmpxchg_enabled() become local symbol, and the compat version of the fetch_robust_entry() function gets renamed to compat_fetch_robust_entry() to avoid a symbol clash. This is intended as a purely cosmetic patch, no behavior should change. Signed-off-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- include/linux/futex.h | 8 -- kernel/Makefile | 3 - kernel/futex.c | 195 +++++++++++++++++++++++++++++++++++++++- kernel/futex_compat.c | 202 ------------------------------------------ 4 files changed, 192 insertions(+), 216 deletions(-) delete mode 100644 kernel/futex_compat.c diff --git a/include/linux/futex.h b/include/linux/futex.h index 821ae502d3d8..ccaef0097785 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -9,9 +9,6 @@ struct inode; struct mm_struct; struct task_struct; -extern int -handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi); - /* * Futexes are matched on equal values of this key. * The key type depends on whether it's a shared or private mapping. @@ -55,11 +52,6 @@ extern void exit_robust_list(struct task_struct *curr); long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3); -#ifdef CONFIG_HAVE_FUTEX_CMPXCHG -#define futex_cmpxchg_enabled 1 -#else -extern int futex_cmpxchg_enabled; -#endif #else static inline void exit_robust_list(struct task_struct *curr) { diff --git a/kernel/Makefile b/kernel/Makefile index df5e3ca30acd..ad4b324d8906 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -50,9 +50,6 @@ obj-$(CONFIG_PROFILING) += profile.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ obj-$(CONFIG_FUTEX) += futex.o -ifeq ($(CONFIG_COMPAT),y) -obj-$(CONFIG_FUTEX) += futex_compat.o -endif obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o obj-$(CONFIG_SMP) += smp.o ifneq ($(CONFIG_SMP),y) diff --git a/kernel/futex.c b/kernel/futex.c index afdc5eadce6e..dd12c3369aba 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -44,6 +44,7 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include #include #include #include @@ -173,8 +174,10 @@ * double_lock_hb() and double_unlock_hb(), respectively. */ -#ifndef CONFIG_HAVE_FUTEX_CMPXCHG -int __read_mostly futex_cmpxchg_enabled; +#ifdef CONFIG_HAVE_FUTEX_CMPXCHG +#define futex_cmpxchg_enabled 1 +#else +static int __read_mostly futex_cmpxchg_enabled; #endif /* @@ -3458,7 +3461,7 @@ err_unlock: * Process a futex-list entry, check whether it's owned by the * dying task, and do notification if so: */ -int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi) +static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi) { u32 uval, uninitialized_var(nval), mval; int err; @@ -3707,6 +3710,192 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); } +#ifdef CONFIG_COMPAT +/* + * Fetch a robust-list pointer. Bit 0 signals PI futexes: + */ +static inline int +compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, + compat_uptr_t __user *head, unsigned int *pi) +{ + if (get_user(*uentry, head)) + return -EFAULT; + + *entry = compat_ptr((*uentry) & ~1); + *pi = (unsigned int)(*uentry) & 1; + + return 0; +} + +static void __user *futex_uaddr(struct robust_list __user *entry, + compat_long_t futex_offset) +{ + compat_uptr_t base = ptr_to_compat(entry); + void __user *uaddr = compat_ptr(base + futex_offset); + + return uaddr; +} + +/* + * Walk curr->robust_list (very carefully, it's a userspace list!) + * and mark any locks found there dead, and notify any waiters. + * + * We silently return on any sign of list-walking problem. + */ +void compat_exit_robust_list(struct task_struct *curr) +{ + struct compat_robust_list_head __user *head = curr->compat_robust_list; + struct robust_list __user *entry, *next_entry, *pending; + unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; + unsigned int uninitialized_var(next_pi); + compat_uptr_t uentry, next_uentry, upending; + compat_long_t futex_offset; + int rc; + + if (!futex_cmpxchg_enabled) + return; + + /* + * Fetch the list head (which was registered earlier, via + * sys_set_robust_list()): + */ + if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) + return; + /* + * Fetch the relative futex offset: + */ + if (get_user(futex_offset, &head->futex_offset)) + return; + /* + * Fetch any possibly pending lock-add first, and handle it + * if it exists: + */ + if (compat_fetch_robust_entry(&upending, &pending, + &head->list_op_pending, &pip)) + return; + + next_entry = NULL; /* avoid warning with gcc */ + while (entry != (struct robust_list __user *) &head->list) { + /* + * Fetch the next entry in the list before calling + * handle_futex_death: + */ + rc = compat_fetch_robust_entry(&next_uentry, &next_entry, + (compat_uptr_t __user *)&entry->next, &next_pi); + /* + * A pending lock might already be on the list, so + * dont process it twice: + */ + if (entry != pending) { + void __user *uaddr = futex_uaddr(entry, futex_offset); + + if (handle_futex_death(uaddr, curr, pi)) + return; + } + if (rc) + return; + uentry = next_uentry; + entry = next_entry; + pi = next_pi; + /* + * Avoid excessively long or circular lists: + */ + if (!--limit) + break; + + cond_resched(); + } + if (pending) { + void __user *uaddr = futex_uaddr(pending, futex_offset); + + handle_futex_death(uaddr, curr, pip); + } +} + +COMPAT_SYSCALL_DEFINE2(set_robust_list, + struct compat_robust_list_head __user *, head, + compat_size_t, len) +{ + if (!futex_cmpxchg_enabled) + return -ENOSYS; + + if (unlikely(len != sizeof(*head))) + return -EINVAL; + + current->compat_robust_list = head; + + return 0; +} + +COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, + compat_uptr_t __user *, head_ptr, + compat_size_t __user *, len_ptr) +{ + struct compat_robust_list_head __user *head; + unsigned long ret; + struct task_struct *p; + + if (!futex_cmpxchg_enabled) + return -ENOSYS; + + rcu_read_lock(); + + ret = -ESRCH; + if (!pid) + p = current; + else { + p = find_task_by_vpid(pid); + if (!p) + goto err_unlock; + } + + ret = -EPERM; + if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) + goto err_unlock; + + head = p->compat_robust_list; + rcu_read_unlock(); + + if (put_user(sizeof(*head), len_ptr)) + return -EFAULT; + return put_user(ptr_to_compat(head), head_ptr); + +err_unlock: + rcu_read_unlock(); + + return ret; +} + +COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, + struct old_timespec32 __user *, utime, u32 __user *, uaddr2, + u32, val3) +{ + struct timespec ts; + ktime_t t, *tp = NULL; + int val2 = 0; + int cmd = op & FUTEX_CMD_MASK; + + if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || + cmd == FUTEX_WAIT_BITSET || + cmd == FUTEX_WAIT_REQUEUE_PI)) { + if (compat_get_timespec(&ts, utime)) + return -EFAULT; + if (!timespec_valid(&ts)) + return -EINVAL; + + t = timespec_to_ktime(ts); + if (cmd == FUTEX_WAIT) + t = ktime_add_safe(ktime_get(), t); + tp = &t; + } + if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE || + cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP) + val2 = (int) (unsigned long) utime; + + return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); +} +#endif /* CONFIG_COMPAT */ + static void __init futex_detect_cmpxchg(void) { #ifndef CONFIG_HAVE_FUTEX_CMPXCHG diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c deleted file mode 100644 index 83f830acbb5f..000000000000 --- a/kernel/futex_compat.c +++ /dev/null @@ -1,202 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * linux/kernel/futex_compat.c - * - * Futex compatibililty routines. - * - * Copyright 2006, Red Hat, Inc., Ingo Molnar - */ - -#include -#include -#include -#include -#include -#include - -#include - - -/* - * Fetch a robust-list pointer. Bit 0 signals PI futexes: - */ -static inline int -fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, - compat_uptr_t __user *head, unsigned int *pi) -{ - if (get_user(*uentry, head)) - return -EFAULT; - - *entry = compat_ptr((*uentry) & ~1); - *pi = (unsigned int)(*uentry) & 1; - - return 0; -} - -static void __user *futex_uaddr(struct robust_list __user *entry, - compat_long_t futex_offset) -{ - compat_uptr_t base = ptr_to_compat(entry); - void __user *uaddr = compat_ptr(base + futex_offset); - - return uaddr; -} - -/* - * Walk curr->robust_list (very carefully, it's a userspace list!) - * and mark any locks found there dead, and notify any waiters. - * - * We silently return on any sign of list-walking problem. - */ -void compat_exit_robust_list(struct task_struct *curr) -{ - struct compat_robust_list_head __user *head = curr->compat_robust_list; - struct robust_list __user *entry, *next_entry, *pending; - unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; - unsigned int uninitialized_var(next_pi); - compat_uptr_t uentry, next_uentry, upending; - compat_long_t futex_offset; - int rc; - - if (!futex_cmpxchg_enabled) - return; - - /* - * Fetch the list head (which was registered earlier, via - * sys_set_robust_list()): - */ - if (fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) - return; - /* - * Fetch the relative futex offset: - */ - if (get_user(futex_offset, &head->futex_offset)) - return; - /* - * Fetch any possibly pending lock-add first, and handle it - * if it exists: - */ - if (fetch_robust_entry(&upending, &pending, - &head->list_op_pending, &pip)) - return; - - next_entry = NULL; /* avoid warning with gcc */ - while (entry != (struct robust_list __user *) &head->list) { - /* - * Fetch the next entry in the list before calling - * handle_futex_death: - */ - rc = fetch_robust_entry(&next_uentry, &next_entry, - (compat_uptr_t __user *)&entry->next, &next_pi); - /* - * A pending lock might already be on the list, so - * dont process it twice: - */ - if (entry != pending) { - void __user *uaddr = futex_uaddr(entry, futex_offset); - - if (handle_futex_death(uaddr, curr, pi)) - return; - } - if (rc) - return; - uentry = next_uentry; - entry = next_entry; - pi = next_pi; - /* - * Avoid excessively long or circular lists: - */ - if (!--limit) - break; - - cond_resched(); - } - if (pending) { - void __user *uaddr = futex_uaddr(pending, futex_offset); - - handle_futex_death(uaddr, curr, pip); - } -} - -COMPAT_SYSCALL_DEFINE2(set_robust_list, - struct compat_robust_list_head __user *, head, - compat_size_t, len) -{ - if (!futex_cmpxchg_enabled) - return -ENOSYS; - - if (unlikely(len != sizeof(*head))) - return -EINVAL; - - current->compat_robust_list = head; - - return 0; -} - -COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, - compat_uptr_t __user *, head_ptr, - compat_size_t __user *, len_ptr) -{ - struct compat_robust_list_head __user *head; - unsigned long ret; - struct task_struct *p; - - if (!futex_cmpxchg_enabled) - return -ENOSYS; - - rcu_read_lock(); - - ret = -ESRCH; - if (!pid) - p = current; - else { - p = find_task_by_vpid(pid); - if (!p) - goto err_unlock; - } - - ret = -EPERM; - if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) - goto err_unlock; - - head = p->compat_robust_list; - rcu_read_unlock(); - - if (put_user(sizeof(*head), len_ptr)) - return -EFAULT; - return put_user(ptr_to_compat(head), head_ptr); - -err_unlock: - rcu_read_unlock(); - - return ret; -} - -COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, - struct compat_timespec __user *, utime, u32 __user *, uaddr2, - u32, val3) -{ - struct timespec ts; - ktime_t t, *tp = NULL; - int val2 = 0; - int cmd = op & FUTEX_CMD_MASK; - - if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || - cmd == FUTEX_WAIT_BITSET || - cmd == FUTEX_WAIT_REQUEUE_PI)) { - if (compat_get_timespec(&ts, utime)) - return -EFAULT; - if (!timespec_valid(&ts)) - return -EINVAL; - - t = timespec_to_ktime(ts); - if (cmd == FUTEX_WAIT) - t = ktime_add_safe(ktime_get(), t); - tp = &t; - } - if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE || - cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP) - val2 = (int) (unsigned long) utime; - - return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); -} From 2819f4030f43057238992a4adcd950d7c95aff65 Mon Sep 17 00:00:00 2001 From: Yang Tao Date: Wed, 6 Nov 2019 22:55:35 +0100 Subject: [PATCH 271/299] futex: Prevent robust futex exit race commit ca16d5bee59807bf04deaab0a8eccecd5061528c upstream. Robust futexes utilize the robust_list mechanism to allow the kernel to release futexes which are held when a task exits. The exit can be voluntary or caused by a signal or fault. This prevents that waiters block forever. The futex operations in user space store a pointer to the futex they are either locking or unlocking in the op_pending member of the per task robust list. After a lock operation has succeeded the futex is queued in the robust list linked list and the op_pending pointer is cleared. After an unlock operation has succeeded the futex is removed from the robust list linked list and the op_pending pointer is cleared. The robust list exit code checks for the pending operation and any futex which is queued in the linked list. It carefully checks whether the futex value is the TID of the exiting task. If so, it sets the OWNER_DIED bit and tries to wake up a potential waiter. This is race free for the lock operation but unlock has two race scenarios where waiters might not be woken up. These issues can be observed with regular robust pthread mutexes. PI aware pthread mutexes are not affected. (1) Unlocking task is killed after unlocking the futex value in user space before being able to wake a waiter. pthread_mutex_unlock() | V atomic_exchange_rel (&mutex->__data.__lock, 0) <------------------------killed lll_futex_wake () | | |(__lock = 0) |(enter kernel) | V do_exit() exit_mm() mm_release() exit_robust_list() handle_futex_death() | |(__lock = 0) |(uval = 0) | V if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr)) return 0; The sanity check which ensures that the user space futex is owned by the exiting task prevents the wakeup of waiters which in consequence block infinitely. (2) Waiting task is killed after a wakeup and before it can acquire the futex in user space. OWNER WAITER futex_wait() pthread_mutex_unlock() | | | |(__lock = 0) | | | V | futex_wake() ------------> wakeup() | |(return to userspace) |(__lock = 0) | V oldval = mutex->__data.__lock <-----------------killed atomic_compare_and_exchange_val_acq (&mutex->__data.__lock, | id | assume_other_futex_waiters, 0) | | | (enter kernel)| | V do_exit() | | V handle_futex_death() | |(__lock = 0) |(uval = 0) | V if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr)) return 0; The sanity check which ensures that the user space futex is owned by the exiting task prevents the wakeup of waiters, which seems to be correct as the exiting task does not own the futex value, but the consequence is that other waiters wont be woken up and block infinitely. In both scenarios the following conditions are true: - task->robust_list->list_op_pending != NULL - user space futex value == 0 - Regular futex (not PI) If these conditions are met then it is reasonably safe to wake up a potential waiter in order to prevent the above problems. As this might be a false positive it can cause spurious wakeups, but the waiter side has to handle other types of unrelated wakeups, e.g. signals gracefully anyway. So such a spurious wakeup will not affect the correctness of these operations. This workaround must not touch the user space futex value and cannot set the OWNER_DIED bit because the lock value is 0, i.e. uncontended. Setting OWNER_DIED in this case would result in inconsistent state and subsequently in malfunction of the owner died handling in user space. The rest of the user space state is still consistent as no other task can observe the list_op_pending entry in the exiting tasks robust list. The eventually woken up waiter will observe the uncontended lock value and take it over. [ tglx: Massaged changelog and comment. Made the return explicit and not depend on the subsequent check and added constants to hand into handle_futex_death() instead of plain numbers. Fixed a few coding style issues. ] Fixes: 0771dfefc9e5 ("[PATCH] lightweight robust futexes: core") Signed-off-by: Yang Tao Signed-off-by: Yi Wang Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Acked-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1573010582-35297-1-git-send-email-wang.yi59@zte.com.cn Link: https://lkml.kernel.org/r/20191106224555.943191378@linutronix.de Signed-off-by: Greg Kroah-Hartman --- kernel/futex.c | 58 ++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 51 insertions(+), 7 deletions(-) diff --git a/kernel/futex.c b/kernel/futex.c index dd12c3369aba..e75ad30aa7bc 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -3457,11 +3457,16 @@ err_unlock: return ret; } +/* Constants for the pending_op argument of handle_futex_death */ +#define HANDLE_DEATH_PENDING true +#define HANDLE_DEATH_LIST false + /* * Process a futex-list entry, check whether it's owned by the * dying task, and do notification if so: */ -static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi) +static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, + bool pi, bool pending_op) { u32 uval, uninitialized_var(nval), mval; int err; @@ -3474,6 +3479,42 @@ retry: if (get_user(uval, uaddr)) return -1; + /* + * Special case for regular (non PI) futexes. The unlock path in + * user space has two race scenarios: + * + * 1. The unlock path releases the user space futex value and + * before it can execute the futex() syscall to wake up + * waiters it is killed. + * + * 2. A woken up waiter is killed before it can acquire the + * futex in user space. + * + * In both cases the TID validation below prevents a wakeup of + * potential waiters which can cause these waiters to block + * forever. + * + * In both cases the following conditions are met: + * + * 1) task->robust_list->list_op_pending != NULL + * @pending_op == true + * 2) User space futex value == 0 + * 3) Regular futex: @pi == false + * + * If these conditions are met, it is safe to attempt waking up a + * potential waiter without touching the user space futex value and + * trying to set the OWNER_DIED bit. The user space futex value is + * uncontended and the rest of the user space mutex state is + * consistent, so a woken waiter will just take over the + * uncontended futex. Setting the OWNER_DIED bit would create + * inconsistent state and malfunction of the user space owner died + * handling. + */ + if (pending_op && !pi && !uval) { + futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); + return 0; + } + if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr)) return 0; @@ -3593,10 +3634,11 @@ void exit_robust_list(struct task_struct *curr) * A pending lock might already be on the list, so * don't process it twice: */ - if (entry != pending) + if (entry != pending) { if (handle_futex_death((void __user *)entry + futex_offset, - curr, pi)) + curr, pi, HANDLE_DEATH_LIST)) return; + } if (rc) return; entry = next_entry; @@ -3610,9 +3652,10 @@ void exit_robust_list(struct task_struct *curr) cond_resched(); } - if (pending) + if (pending) { handle_futex_death((void __user *)pending + futex_offset, - curr, pip); + curr, pip, HANDLE_DEATH_PENDING); + } } long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, @@ -3789,7 +3832,8 @@ void compat_exit_robust_list(struct task_struct *curr) if (entry != pending) { void __user *uaddr = futex_uaddr(entry, futex_offset); - if (handle_futex_death(uaddr, curr, pi)) + if (handle_futex_death(uaddr, curr, pi, + HANDLE_DEATH_LIST)) return; } if (rc) @@ -3808,7 +3852,7 @@ void compat_exit_robust_list(struct task_struct *curr) if (pending) { void __user *uaddr = futex_uaddr(pending, futex_offset); - handle_futex_death(uaddr, curr, pip); + handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING); } } From 3510fb7947d5a7ca662178efe4f8d3712bb85177 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 22 Nov 2019 12:28:40 +0100 Subject: [PATCH 272/299] ALSA: usb-audio: Fix NULL dereference at parsing BADD commit 9435f2bb66874a0c4dd25e7c978957a7ca2c93b1 upstream. snd_usb_mixer_controls_badd() that parses UAC3 BADD profiles misses a NULL check for the given interfaces. When a malformed USB descriptor is passed, this may lead to an Oops, as spotted by syzkaller. Skip the iteration if the interface doesn't exist for avoiding the crash. Fixes: 17156f23e93c ("ALSA: usb: add UAC3 BADD profiles support") Reported-by: syzbot+a36ab65c6653d7ccdd62@syzkaller.appspotmail.com Suggested-by: Dan Carpenter Cc: Link: https://lore.kernel.org/r/20191122112840.24797-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/mixer.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 726cbd63a0c7..d7778f2bcbf8 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -2949,6 +2949,9 @@ static int snd_usb_mixer_controls_badd(struct usb_mixer_interface *mixer, continue; iface = usb_ifnum_to_if(dev, intf); + if (!iface) + continue; + num = iface->num_altsetting; if (num < 2) From af8071f50f4627fc68ad5f662f200a043dd68472 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Thu, 21 Nov 2019 11:37:10 +0100 Subject: [PATCH 273/299] nfc: port100: handle command failure cleanly commit 5f9f0b11f0816b35867f2cf71e54d95f53f03902 upstream. If starting the transfer of a command suceeds but the transfer for the reply fails, it is not enough to initiate killing the transfer for the command may still be running. You need to wait for the killing to finish before you can reuse URB and buffer. Reported-and-tested-by: syzbot+711468aa5c3a1eabf863@syzkaller.appspotmail.com Signed-off-by: Oliver Neukum Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/nfc/port100.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c index bb43cebda9dc..60ae382f50da 100644 --- a/drivers/nfc/port100.c +++ b/drivers/nfc/port100.c @@ -792,7 +792,7 @@ static int port100_send_frame_async(struct port100 *dev, struct sk_buff *out, rc = port100_submit_urb_for_ack(dev, GFP_KERNEL); if (rc) - usb_unlink_urb(dev->out_urb); + usb_kill_urb(dev->out_urb); exit: mutex_unlock(&dev->out_urb_lock); From b73b28b1b2cbc345cbe24d98b0997ec599bf4d06 Mon Sep 17 00:00:00 2001 From: Vandana BN Date: Mon, 9 Sep 2019 06:43:31 -0300 Subject: [PATCH 274/299] media: vivid: Set vid_cap_streaming and vid_out_streaming to true commit b4add02d2236fd5f568db141cfd8eb4290972eb3 upstream. When vbi stream is started, followed by video streaming, the vid_cap_streaming and vid_out_streaming were not being set to true, which would cause the video stream to stop when vbi stream is stopped. This patch allows to set vid_cap_streaming and vid_out_streaming to true. According to Hans Verkuil it appears that these 'if (dev->kthread_vid_cap)' checks are a left-over from the original vivid development and should never have been there. Signed-off-by: Vandana BN Cc: # for v3.18 and up Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/vivid/vivid-vid-cap.c | 3 --- drivers/media/platform/vivid/vivid-vid-out.c | 3 --- 2 files changed, 6 deletions(-) diff --git a/drivers/media/platform/vivid/vivid-vid-cap.c b/drivers/media/platform/vivid/vivid-vid-cap.c index 2e273f4dfc29..c58ae489f39c 100644 --- a/drivers/media/platform/vivid/vivid-vid-cap.c +++ b/drivers/media/platform/vivid/vivid-vid-cap.c @@ -222,9 +222,6 @@ static int vid_cap_start_streaming(struct vb2_queue *vq, unsigned count) if (vb2_is_streaming(&dev->vb_vid_out_q)) dev->can_loop_video = vivid_vid_can_loop(dev); - if (dev->kthread_vid_cap) - return 0; - dev->vid_cap_seq_count = 0; dprintk(dev, 1, "%s\n", __func__); for (i = 0; i < VIDEO_MAX_FRAME; i++) diff --git a/drivers/media/platform/vivid/vivid-vid-out.c b/drivers/media/platform/vivid/vivid-vid-out.c index 50248e2176a0..0f909500a0b8 100644 --- a/drivers/media/platform/vivid/vivid-vid-out.c +++ b/drivers/media/platform/vivid/vivid-vid-out.c @@ -146,9 +146,6 @@ static int vid_out_start_streaming(struct vb2_queue *vq, unsigned count) if (vb2_is_streaming(&dev->vb_vid_cap_q)) dev->can_loop_video = vivid_vid_can_loop(dev); - if (dev->kthread_vid_out) - return 0; - dev->vid_out_seq_count = 0; dprintk(dev, 1, "%s\n", __func__); if (dev->start_streaming_error) { From 467052f6ea5a51524992e43f02b543550495c391 Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Sun, 3 Nov 2019 23:17:19 +0100 Subject: [PATCH 275/299] media: vivid: Fix wrong locking that causes race conditions on streaming stop commit 6dcd5d7a7a29c1e4b8016a06aed78cd650cd8c27 upstream. There is the same incorrect approach to locking implemented in vivid_stop_generating_vid_cap(), vivid_stop_generating_vid_out() and sdr_cap_stop_streaming(). These functions are called during streaming stopping with vivid_dev.mutex locked. And they all do the same mistake while stopping their kthreads, which need to lock this mutex as well. See the example from vivid_stop_generating_vid_cap(): /* shutdown control thread */ vivid_grab_controls(dev, false); mutex_unlock(&dev->mutex); kthread_stop(dev->kthread_vid_cap); dev->kthread_vid_cap = NULL; mutex_lock(&dev->mutex); But when this mutex is unlocked, another vb2_fop_read() can lock it instead of vivid_thread_vid_cap() and manipulate the buffer queue. That causes a use-after-free access later. To fix those issues let's: 1. avoid unlocking the mutex in vivid_stop_generating_vid_cap(), vivid_stop_generating_vid_out() and sdr_cap_stop_streaming(); 2. use mutex_trylock() with schedule_timeout_uninterruptible() in the loops of the vivid kthread handlers. Signed-off-by: Alexander Popov Acked-by: Linus Torvalds Tested-by: Hans Verkuil Signed-off-by: Hans Verkuil Cc: # for v3.18 and up Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/vivid/vivid-kthread-cap.c | 8 +++++--- drivers/media/platform/vivid/vivid-kthread-out.c | 8 +++++--- drivers/media/platform/vivid/vivid-sdr-cap.c | 8 +++++--- 3 files changed, 15 insertions(+), 9 deletions(-) diff --git a/drivers/media/platform/vivid/vivid-kthread-cap.c b/drivers/media/platform/vivid/vivid-kthread-cap.c index 2a92e5aac9ed..ac17883a054f 100644 --- a/drivers/media/platform/vivid/vivid-kthread-cap.c +++ b/drivers/media/platform/vivid/vivid-kthread-cap.c @@ -765,7 +765,11 @@ static int vivid_thread_vid_cap(void *data) if (kthread_should_stop()) break; - mutex_lock(&dev->mutex); + if (!mutex_trylock(&dev->mutex)) { + schedule_timeout_uninterruptible(1); + continue; + } + cur_jiffies = jiffies; if (dev->cap_seq_resync) { dev->jiffies_vid_cap = cur_jiffies; @@ -918,8 +922,6 @@ void vivid_stop_generating_vid_cap(struct vivid_dev *dev, bool *pstreaming) /* shutdown control thread */ vivid_grab_controls(dev, false); - mutex_unlock(&dev->mutex); kthread_stop(dev->kthread_vid_cap); dev->kthread_vid_cap = NULL; - mutex_lock(&dev->mutex); } diff --git a/drivers/media/platform/vivid/vivid-kthread-out.c b/drivers/media/platform/vivid/vivid-kthread-out.c index 488590594150..c5f466a73312 100644 --- a/drivers/media/platform/vivid/vivid-kthread-out.c +++ b/drivers/media/platform/vivid/vivid-kthread-out.c @@ -135,7 +135,11 @@ static int vivid_thread_vid_out(void *data) if (kthread_should_stop()) break; - mutex_lock(&dev->mutex); + if (!mutex_trylock(&dev->mutex)) { + schedule_timeout_uninterruptible(1); + continue; + } + cur_jiffies = jiffies; if (dev->out_seq_resync) { dev->jiffies_vid_out = cur_jiffies; @@ -289,8 +293,6 @@ void vivid_stop_generating_vid_out(struct vivid_dev *dev, bool *pstreaming) /* shutdown control thread */ vivid_grab_controls(dev, false); - mutex_unlock(&dev->mutex); kthread_stop(dev->kthread_vid_out); dev->kthread_vid_out = NULL; - mutex_lock(&dev->mutex); } diff --git a/drivers/media/platform/vivid/vivid-sdr-cap.c b/drivers/media/platform/vivid/vivid-sdr-cap.c index cfb7cb4d37a8..e1794f8689d4 100644 --- a/drivers/media/platform/vivid/vivid-sdr-cap.c +++ b/drivers/media/platform/vivid/vivid-sdr-cap.c @@ -137,7 +137,11 @@ static int vivid_thread_sdr_cap(void *data) if (kthread_should_stop()) break; - mutex_lock(&dev->mutex); + if (!mutex_trylock(&dev->mutex)) { + schedule_timeout_uninterruptible(1); + continue; + } + cur_jiffies = jiffies; if (dev->sdr_cap_seq_resync) { dev->jiffies_sdr_cap = cur_jiffies; @@ -297,10 +301,8 @@ static void sdr_cap_stop_streaming(struct vb2_queue *vq) } /* shutdown control thread */ - mutex_unlock(&dev->mutex); kthread_stop(dev->kthread_sdr_cap); dev->kthread_sdr_cap = NULL; - mutex_lock(&dev->mutex); } const struct vb2_ops vivid_sdr_cap_qops = { From f217cef919dacaab257df22355ae6d275c126f61 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 7 Oct 2019 12:09:53 -0300 Subject: [PATCH 276/299] media: usbvision: Fix races among open, close, and disconnect commit 9e08117c9d4efc1e1bc6fce83dab856d9fd284b6 upstream. Visual inspection of the usbvision driver shows that it suffers from three races between its open, close, and disconnect handlers. In particular, the driver is careful to update its usbvision->user and usbvision->remove_pending flags while holding the private mutex, but: usbvision_v4l2_close() and usbvision_radio_close() don't hold the mutex while they check the value of usbvision->remove_pending; usbvision_disconnect() doesn't hold the mutex while checking the value of usbvision->user; and also, usbvision_v4l2_open() and usbvision_radio_open() don't check whether the device has been unplugged before allowing the user to open the device files. Each of these can potentially lead to usbvision_release() being called twice and use-after-free errors. This patch fixes the races by reading the flags while the mutex is still held and checking for pending removes before allowing an open to succeed. Signed-off-by: Alan Stern CC: Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/usb/usbvision/usbvision-video.c | 21 ++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/drivers/media/usb/usbvision/usbvision-video.c b/drivers/media/usb/usbvision/usbvision-video.c index f29d1bef0293..cce29b604f4a 100644 --- a/drivers/media/usb/usbvision/usbvision-video.c +++ b/drivers/media/usb/usbvision/usbvision-video.c @@ -327,6 +327,10 @@ static int usbvision_v4l2_open(struct file *file) if (mutex_lock_interruptible(&usbvision->v4l2_lock)) return -ERESTARTSYS; + if (usbvision->remove_pending) { + err_code = -ENODEV; + goto unlock; + } if (usbvision->user) { err_code = -EBUSY; } else { @@ -390,6 +394,7 @@ unlock: static int usbvision_v4l2_close(struct file *file) { struct usb_usbvision *usbvision = video_drvdata(file); + int r; PDEBUG(DBG_IO, "close"); @@ -404,9 +409,10 @@ static int usbvision_v4l2_close(struct file *file) usbvision_scratch_free(usbvision); usbvision->user--; + r = usbvision->remove_pending; mutex_unlock(&usbvision->v4l2_lock); - if (usbvision->remove_pending) { + if (r) { printk(KERN_INFO "%s: Final disconnect\n", __func__); usbvision_release(usbvision); return 0; @@ -1090,6 +1096,11 @@ static int usbvision_radio_open(struct file *file) if (mutex_lock_interruptible(&usbvision->v4l2_lock)) return -ERESTARTSYS; + + if (usbvision->remove_pending) { + err_code = -ENODEV; + goto out; + } err_code = v4l2_fh_open(file); if (err_code) goto out; @@ -1122,6 +1133,7 @@ out: static int usbvision_radio_close(struct file *file) { struct usb_usbvision *usbvision = video_drvdata(file); + int r; PDEBUG(DBG_IO, ""); @@ -1134,9 +1146,10 @@ static int usbvision_radio_close(struct file *file) usbvision_audio_off(usbvision); usbvision->radio = 0; usbvision->user--; + r = usbvision->remove_pending; mutex_unlock(&usbvision->v4l2_lock); - if (usbvision->remove_pending) { + if (r) { printk(KERN_INFO "%s: Final disconnect\n", __func__); v4l2_fh_release(file); usbvision_release(usbvision); @@ -1562,6 +1575,7 @@ err_usb: static void usbvision_disconnect(struct usb_interface *intf) { struct usb_usbvision *usbvision = to_usbvision(usb_get_intfdata(intf)); + int u; PDEBUG(DBG_PROBE, ""); @@ -1578,13 +1592,14 @@ static void usbvision_disconnect(struct usb_interface *intf) v4l2_device_disconnect(&usbvision->v4l2_dev); usbvision_i2c_unregister(usbvision); usbvision->remove_pending = 1; /* Now all ISO data will be ignored */ + u = usbvision->user; usb_put_dev(usbvision->dev); usbvision->dev = NULL; /* USB device is no more */ mutex_unlock(&usbvision->v4l2_lock); - if (usbvision->user) { + if (u) { printk(KERN_INFO "%s: In use, disconnect pending\n", __func__); wake_up_interruptible(&usbvision->wait_frame); From 61e73cf57ed81f63ccce6209f16568578953a3ef Mon Sep 17 00:00:00 2001 From: Kai Shen Date: Thu, 7 Nov 2019 05:08:17 +0000 Subject: [PATCH 277/299] cpufreq: Add NULL checks to show() and store() methods of cpufreq commit e6e8df07268c1f75dd9215536e2ce4587b70f977 upstream. Add NULL checks to show() and store() in cpufreq.c to avoid attempts to invoke a NULL callback. Though some interfaces of cpufreq are set as read-only, users can still get write permission using chmod which can lead to a kernel crash, as follows: chmod +w /sys/devices/system/cpu/cpu0/cpufreq/scaling_cur_freq echo 1 > /sys/devices/system/cpu/cpu0/cpufreq/scaling_cur_freq This bug was found in linux 4.19. Signed-off-by: Kai Shen Reported-by: Feilong Lin Reviewed-by: Feilong Lin Acked-by: Viresh Kumar [ rjw: Subject & changelog ] Cc: All applicable Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- drivers/cpufreq/cpufreq.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index ace5ec65e36f..9d8d64f706e0 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -909,6 +909,9 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf) struct freq_attr *fattr = to_attr(attr); ssize_t ret; + if (!fattr->show) + return -EIO; + down_read(&policy->rwsem); ret = fattr->show(policy, buf); up_read(&policy->rwsem); @@ -923,6 +926,9 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, struct freq_attr *fattr = to_attr(attr); ssize_t ret = -EINVAL; + if (!fattr->store) + return -EIO; + /* * cpus_read_trylock() is used here to work around a circular lock * dependency problem with respect to the cpufreq_register_driver(). From 56be9f1b8733395caf570a80aa97d30e1fc61c28 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Mon, 29 Jul 2019 23:14:55 -0300 Subject: [PATCH 278/299] media: uvcvideo: Fix error path in control parsing failure commit 8c279e9394cade640ed86ec6c6645a0e7df5e0b6 upstream. When parsing the UVC control descriptors fails, the error path tries to cleanup a media device that hasn't been initialised, potentially resulting in a crash. Fix this by initialising the media device before the error handling path can be reached. Fixes: 5a254d751e52 ("[media] uvcvideo: Register a v4l2_device") Reported-by: syzbot+c86454eb3af9e8a4da20@syzkaller.appspotmail.com Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/usb/uvc/uvc_driver.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index c3ddbf6c202a..cf4feff2a48c 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -2124,6 +2124,20 @@ static int uvc_probe(struct usb_interface *intf, sizeof(dev->name) - len); } + /* Initialize the media device. */ +#ifdef CONFIG_MEDIA_CONTROLLER + dev->mdev.dev = &intf->dev; + strscpy(dev->mdev.model, dev->name, sizeof(dev->mdev.model)); + if (udev->serial) + strscpy(dev->mdev.serial, udev->serial, + sizeof(dev->mdev.serial)); + usb_make_path(udev, dev->mdev.bus_info, sizeof(dev->mdev.bus_info)); + dev->mdev.hw_revision = le16_to_cpu(udev->descriptor.bcdDevice); + media_device_init(&dev->mdev); + + dev->vdev.mdev = &dev->mdev; +#endif + /* Parse the Video Class control descriptor. */ if (uvc_parse_control(dev) < 0) { uvc_trace(UVC_TRACE_PROBE, "Unable to parse UVC " @@ -2144,19 +2158,7 @@ static int uvc_probe(struct usb_interface *intf, "linux-uvc-devel mailing list.\n"); } - /* Initialize the media device and register the V4L2 device. */ -#ifdef CONFIG_MEDIA_CONTROLLER - dev->mdev.dev = &intf->dev; - strlcpy(dev->mdev.model, dev->name, sizeof(dev->mdev.model)); - if (udev->serial) - strlcpy(dev->mdev.serial, udev->serial, - sizeof(dev->mdev.serial)); - strcpy(dev->mdev.bus_info, udev->devpath); - dev->mdev.hw_revision = le16_to_cpu(udev->descriptor.bcdDevice); - media_device_init(&dev->mdev); - - dev->vdev.mdev = &dev->mdev; -#endif + /* Register the V4L2 device. */ if (v4l2_device_register(&intf->dev, &dev->vdev) < 0) goto error; From 8b42c263ec1a348bf098e6255407486c1bf17ece Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Tue, 30 Jul 2019 09:48:27 +0200 Subject: [PATCH 279/299] media: b2c2-flexcop-usb: add sanity checking commit 1b976fc6d684e3282914cdbe7a8d68fdce19095c upstream. The driver needs an isochronous endpoint to be present. It will oops in its absence. Add checking for it. Reported-by: syzbot+d93dff37e6a89431c158@syzkaller.appspotmail.com Signed-off-by: Oliver Neukum Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/usb/b2c2/flexcop-usb.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/media/usb/b2c2/flexcop-usb.c b/drivers/media/usb/b2c2/flexcop-usb.c index a8f3169e30b3..ac4fddfd0a43 100644 --- a/drivers/media/usb/b2c2/flexcop-usb.c +++ b/drivers/media/usb/b2c2/flexcop-usb.c @@ -537,6 +537,9 @@ static int flexcop_usb_probe(struct usb_interface *intf, struct flexcop_device *fc = NULL; int ret; + if (intf->cur_altsetting->desc.bNumEndpoints < 1) + return -ENODEV; + if ((fc = flexcop_device_kmalloc(sizeof(struct flexcop_usb))) == NULL) { err("out of memory\n"); return -ENOMEM; From 94a94b605916a3c1f2e54cde475434281d7b7205 Mon Sep 17 00:00:00 2001 From: Vito Caputo Date: Sun, 13 Oct 2019 23:08:45 -0300 Subject: [PATCH 280/299] media: cxusb: detect cxusb_ctrl_msg error in query commit ca8f245f284eeffa56f3b7a5eb6fc503159ee028 upstream. Don't use uninitialized ircode[] in cxusb_rc_query() when cxusb_ctrl_msg() fails to populate its contents. syzbot reported: dvb-usb: bulk message failed: -22 (1/-30591) ===================================================== BUG: KMSAN: uninit-value in ir_lookup_by_scancode drivers/media/rc/rc-main.c:494 [inline] BUG: KMSAN: uninit-value in rc_g_keycode_from_table drivers/media/rc/rc-main.c:582 [inline] BUG: KMSAN: uninit-value in rc_keydown+0x1a6/0x6f0 drivers/media/rc/rc-main.c:816 CPU: 1 PID: 11436 Comm: kworker/1:2 Not tainted 5.3.0-rc7+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: events dvb_usb_read_remote_control Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x191/0x1f0 lib/dump_stack.c:113 kmsan_report+0x13a/0x2b0 mm/kmsan/kmsan_report.c:108 __msan_warning+0x73/0xe0 mm/kmsan/kmsan_instr.c:250 bsearch+0x1dd/0x250 lib/bsearch.c:41 ir_lookup_by_scancode drivers/media/rc/rc-main.c:494 [inline] rc_g_keycode_from_table drivers/media/rc/rc-main.c:582 [inline] rc_keydown+0x1a6/0x6f0 drivers/media/rc/rc-main.c:816 cxusb_rc_query+0x2e1/0x360 drivers/media/usb/dvb-usb/cxusb.c:548 dvb_usb_read_remote_control+0xf9/0x290 drivers/media/usb/dvb-usb/dvb-usb-remote.c:261 process_one_work+0x1572/0x1ef0 kernel/workqueue.c:2269 worker_thread+0x111b/0x2460 kernel/workqueue.c:2415 kthread+0x4b5/0x4f0 kernel/kthread.c:256 ret_from_fork+0x35/0x40 arch/x86/entry/entry_64.S:355 Uninit was stored to memory at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:150 [inline] kmsan_internal_chain_origin+0xd2/0x170 mm/kmsan/kmsan.c:314 __msan_chain_origin+0x6b/0xe0 mm/kmsan/kmsan_instr.c:184 rc_g_keycode_from_table drivers/media/rc/rc-main.c:583 [inline] rc_keydown+0x2c4/0x6f0 drivers/media/rc/rc-main.c:816 cxusb_rc_query+0x2e1/0x360 drivers/media/usb/dvb-usb/cxusb.c:548 dvb_usb_read_remote_control+0xf9/0x290 drivers/media/usb/dvb-usb/dvb-usb-remote.c:261 process_one_work+0x1572/0x1ef0 kernel/workqueue.c:2269 worker_thread+0x111b/0x2460 kernel/workqueue.c:2415 kthread+0x4b5/0x4f0 kernel/kthread.c:256 ret_from_fork+0x35/0x40 arch/x86/entry/entry_64.S:355 Local variable description: ----ircode@cxusb_rc_query Variable was created at: cxusb_rc_query+0x4d/0x360 drivers/media/usb/dvb-usb/cxusb.c:543 dvb_usb_read_remote_control+0xf9/0x290 drivers/media/usb/dvb-usb/dvb-usb-remote.c:261 Signed-off-by: Vito Caputo Reported-by: syzbot Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/usb/dvb-usb/cxusb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/media/usb/dvb-usb/cxusb.c b/drivers/media/usb/dvb-usb/cxusb.c index 5b51ed7d6243..5400ec99986f 100644 --- a/drivers/media/usb/dvb-usb/cxusb.c +++ b/drivers/media/usb/dvb-usb/cxusb.c @@ -457,7 +457,8 @@ static int cxusb_rc_query(struct dvb_usb_device *d) { u8 ircode[4]; - cxusb_ctrl_msg(d, CMD_GET_IR_CODE, NULL, 0, ircode, 4); + if (cxusb_ctrl_msg(d, CMD_GET_IR_CODE, NULL, 0, ircode, 4) < 0) + return 0; if (ircode[2] || ircode[3]) rc_keydown(d->rc_dev, RC_PROTO_NEC, From 78260a294c04952758f9367f6d92ab129dd8fffb Mon Sep 17 00:00:00 2001 From: Sean Young Date: Wed, 16 Oct 2019 14:19:15 -0300 Subject: [PATCH 281/299] media: imon: invalid dereference in imon_touch_event commit f3f5ba42c58d56d50f539854d8cc188944e96087 upstream. The touch timer is set up in intf1. If the second interface does not exist, the timer and touch input device are not setup and we get the following error, when touch events are reported via intf0. kernel BUG at kernel/time/timer.c:956! invalid opcode: 0000 [#1] SMP KASAN CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc1+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__mod_timer kernel/time/timer.c:956 [inline] RIP: 0010:__mod_timer kernel/time/timer.c:949 [inline] RIP: 0010:mod_timer+0x5a2/0xb50 kernel/time/timer.c:1100 Code: 45 10 c7 44 24 14 ff ff ff ff 48 89 44 24 08 48 8d 45 20 48 c7 44 24 18 00 00 00 00 48 89 04 24 e9 5a fc ff ff e8 ae ce 0e 00 <0f> 0b e8 a7 ce 0e 00 4c 89 74 24 20 e9 37 fe ff ff e8 98 ce 0e 00 RSP: 0018:ffff8881db209930 EFLAGS: 00010006 RAX: ffffffff86c2b200 RBX: 00000000ffffa688 RCX: ffffffff83efc583 RDX: 0000000000000100 RSI: ffffffff812f4d82 RDI: ffff8881d2356200 RBP: ffff8881d23561e8 R08: ffffffff86c2b200 R09: ffffed103a46abeb R10: ffffed103a46abea R11: ffff8881d2355f53 R12: dffffc0000000000 R13: 1ffff1103b64132d R14: ffff8881d2355f50 R15: 0000000000000006 FS: 0000000000000000(0000) GS:ffff8881db200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f75e2799000 CR3: 00000001d3b07000 CR4: 00000000001406f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: imon_touch_event drivers/media/rc/imon.c:1348 [inline] imon_incoming_packet.isra.0+0x2546/0x2f10 drivers/media/rc/imon.c:1603 usb_rx_callback_intf0+0x151/0x1e0 drivers/media/rc/imon.c:1734 __usb_hcd_giveback_urb+0x1f2/0x470 drivers/usb/core/hcd.c:1654 usb_hcd_giveback_urb+0x368/0x420 drivers/usb/core/hcd.c:1719 dummy_timer+0x120f/0x2fa2 drivers/usb/gadget/udc/dummy_hcd.c:1965 call_timer_fn+0x179/0x650 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0x5e3/0x1490 kernel/time/timer.c:1786 __do_softirq+0x221/0x912 kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0x178/0x1a0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0x12f/0x500 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 RIP: 0010:default_idle+0x28/0x2e0 arch/x86/kernel/process.c:581 Code: 90 90 41 56 41 55 65 44 8b 2d 44 3a 8f 7a 41 54 55 53 0f 1f 44 00 00 e8 36 ee d0 fb e9 07 00 00 00 0f 00 2d fa dd 4f 00 fb f4 <65> 44 8b 2d 20 3a 8f 7a 0f 1f 44 00 00 5b 5d 41 5c 41 5d 41 5e c3 RSP: 0018:ffffffff86c07da8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: 0000000000000007 RBX: ffffffff86c2b200 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000006 RDI: ffffffff86c2ba4c RBP: fffffbfff0d85640 R08: ffffffff86c2b200 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x3b6/0x500 kernel/sched/idle.c:263 cpu_startup_entry+0x14/0x20 kernel/sched/idle.c:355 start_kernel+0x82a/0x864 init/main.c:784 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241 Modules linked in: Reported-by: syzbot+f49d12d34f2321cf4df2@syzkaller.appspotmail.com Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/rc/imon.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/media/rc/imon.c b/drivers/media/rc/imon.c index f23a220352f7..6b10363fb6f0 100644 --- a/drivers/media/rc/imon.c +++ b/drivers/media/rc/imon.c @@ -1607,8 +1607,7 @@ static void imon_incoming_packet(struct imon_context *ictx, spin_unlock_irqrestore(&ictx->kc_lock, flags); /* send touchscreen events through input subsystem if touchpad data */ - if (ictx->display_type == IMON_DISPLAY_TYPE_VGA && len == 8 && - buf[7] == 0x86) { + if (ictx->touch && len == 8 && buf[7] == 0x86) { imon_touch_event(ictx, buf); return; From 5d0b56f6725d93e750ec9a5a99222294fc631004 Mon Sep 17 00:00:00 2001 From: Halil Pasic Date: Thu, 14 Nov 2019 13:46:46 +0100 Subject: [PATCH 282/299] virtio_ring: fix return code on DMA mapping fails [ Upstream commit f7728002c1c7bfa787b276a31c3ef458739b8e7c ] Commit 780bc7903a32 ("virtio_ring: Support DMA APIs") makes virtqueue_add() return -EIO when we fail to map our I/O buffers. This is a very realistic scenario for guests with encrypted memory, as swiotlb may run out of space, depending on it's size and the I/O load. The virtio-blk driver interprets -EIO form virtqueue_add() as an IO error, despite the fact that swiotlb full is in absence of bugs a recoverable condition. Let us change the return code to -ENOMEM, and make the block layer recover form these failures when virtio-blk encounters the condition described above. Cc: stable@vger.kernel.org Fixes: 780bc7903a32 ("virtio_ring: Support DMA APIs") Signed-off-by: Halil Pasic Tested-by: Michael Mueller Signed-off-by: Michael S. Tsirkin Signed-off-by: Sasha Levin --- drivers/virtio/virtio_ring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 9529e28e1822..6228b48d1e12 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -431,7 +431,7 @@ unmap_release: kfree(desc); END_USE(vq); - return -EIO; + return -ENOMEM; } /** From e70448b92253c6b20a95b852147a7ff4b97f1c34 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Tue, 12 Nov 2019 16:49:39 +0100 Subject: [PATCH 283/299] USBIP: add config dependency for SGL_ALLOC commit 1ec13abac58b6f24e32f0d3081ef4e7456e62ed8 upstream. USBIP uses lib/scatterlist.h Hence it needs to set CONFIG_SGL_ALLOC Signed-off-by: Oliver Neukum Cc: stable Acked-by: Shuah Khan Link: https://lore.kernel.org/r/20191112154939.21217-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/usbip/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/usbip/Kconfig b/drivers/usb/usbip/Kconfig index a20b65cb6678..8276a20ecea7 100644 --- a/drivers/usb/usbip/Kconfig +++ b/drivers/usb/usbip/Kconfig @@ -2,6 +2,7 @@ config USBIP_CORE tristate "USB/IP support" depends on NET select USB_COMMON + select SGL_ALLOC ---help--- This enables pushing USB packets over IP to allow remote machines direct access to USB devices. It provides the From 375b26a8648188957e2f3119c6cf078d3275bd74 Mon Sep 17 00:00:00 2001 From: Hewenliang Date: Fri, 25 Oct 2019 00:35:15 -0400 Subject: [PATCH 284/299] usbip: tools: fix fd leakage in the function of read_attr_usbip_status commit 26a4d4c00f85cb844dd11dd35e848b079c2f5e8f upstream. We should close the fd before the return of read_attr_usbip_status. Fixes: 3391ba0e2792 ("usbip: tools: Extract generic code to be shared with vudc backend") Signed-off-by: Hewenliang Cc: stable Link: https://lore.kernel.org/r/20191025043515.20053-1-hewenliang4@huawei.com Signed-off-by: Greg Kroah-Hartman --- tools/usb/usbip/libsrc/usbip_host_common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/usb/usbip/libsrc/usbip_host_common.c b/tools/usb/usbip/libsrc/usbip_host_common.c index d79c7581b175..b0f7489d069d 100644 --- a/tools/usb/usbip/libsrc/usbip_host_common.c +++ b/tools/usb/usbip/libsrc/usbip_host_common.c @@ -69,7 +69,7 @@ static int32_t read_attr_usbip_status(struct usbip_usb_device *udev) } value = atoi(status); - + close(fd); return value; } From 61f6a3fac394fb4f2325196d8fb4cd2b6c8a3ac7 Mon Sep 17 00:00:00 2001 From: Suwan Kim Date: Mon, 11 Nov 2019 23:10:35 +0900 Subject: [PATCH 285/299] usbip: Fix uninitialized symbol 'nents' in stub_recv_cmd_submit() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 2a9125317b247f2cf35c196f968906dcf062ae2d upstream. Smatch reported that nents is not initialized and used in stub_recv_cmd_submit(). nents is currently initialized by sgl_alloc() and used to allocate multiple URBs when host controller doesn't support scatter-gather DMA. The use of uninitialized nents means that buf_len is zero and use_sg is true. But buffer length should not be zero when an URB uses scatter-gather DMA. To prevent this situation, add the conditional that checks buf_len and use_sg. And move the use of nents right after the sgl_alloc() to avoid the use of uninitialized nents. If the error occurs, it adds SDEV_EVENT_ERROR_MALLOC and stub_priv will be released by stub event handler and connection will be shut down. Fixes: ea44d190764b ("usbip: Implement SG support to vhci-hcd and stub driver") Reported-by: kbuild test robot Reported-by: Dan Carpenter Signed-off-by: Suwan Kim Acked-by: Shuah Khan Cc: stable Link: https://lore.kernel.org/r/20191111141035.27788-1-suwan.kim027@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/usbip/stub_rx.c | 50 ++++++++++++++++++++++++------------- 1 file changed, 32 insertions(+), 18 deletions(-) diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c index 75d8756c6d27..8c55cd833098 100644 --- a/drivers/usb/usbip/stub_rx.c +++ b/drivers/usb/usbip/stub_rx.c @@ -470,18 +470,50 @@ static void stub_recv_cmd_submit(struct stub_device *sdev, if (pipe == -1) return; + /* + * Smatch reported the error case where use_sg is true and buf_len is 0. + * In this case, It adds SDEV_EVENT_ERROR_MALLOC and stub_priv will be + * released by stub event handler and connection will be shut down. + */ priv = stub_priv_alloc(sdev, pdu); if (!priv) return; buf_len = (unsigned long long)pdu->u.cmd_submit.transfer_buffer_length; + if (use_sg && !buf_len) { + dev_err(&udev->dev, "sg buffer with zero length\n"); + goto err_malloc; + } + /* allocate urb transfer buffer, if needed */ if (buf_len) { if (use_sg) { sgl = sgl_alloc(buf_len, GFP_KERNEL, &nents); if (!sgl) goto err_malloc; + + /* Check if the server's HCD supports SG */ + if (!udev->bus->sg_tablesize) { + /* + * If the server's HCD doesn't support SG, break + * a single SG request into several URBs and map + * each SG list entry to corresponding URB + * buffer. The previously allocated SG list is + * stored in priv->sgl (If the server's HCD + * support SG, SG list is stored only in + * urb->sg) and it is used as an indicator that + * the server split single SG request into + * several URBs. Later, priv->sgl is used by + * stub_complete() and stub_send_ret_submit() to + * reassemble the divied URBs. + */ + support_sg = 0; + num_urbs = nents; + priv->completed_urbs = 0; + pdu->u.cmd_submit.transfer_flags &= + ~URB_DMA_MAP_SG; + } } else { buffer = kzalloc(buf_len, GFP_KERNEL); if (!buffer) @@ -489,24 +521,6 @@ static void stub_recv_cmd_submit(struct stub_device *sdev, } } - /* Check if the server's HCD supports SG */ - if (use_sg && !udev->bus->sg_tablesize) { - /* - * If the server's HCD doesn't support SG, break a single SG - * request into several URBs and map each SG list entry to - * corresponding URB buffer. The previously allocated SG - * list is stored in priv->sgl (If the server's HCD support SG, - * SG list is stored only in urb->sg) and it is used as an - * indicator that the server split single SG request into - * several URBs. Later, priv->sgl is used by stub_complete() and - * stub_send_ret_submit() to reassemble the divied URBs. - */ - support_sg = 0; - num_urbs = nents; - priv->completed_urbs = 0; - pdu->u.cmd_submit.transfer_flags &= ~URB_DMA_MAP_SG; - } - /* allocate urb array */ priv->num_urbs = num_urbs; priv->urbs = kmalloc_array(num_urbs, sizeof(*priv->urbs), GFP_KERNEL); From a18675e5d5f7addca7042d77c4763c26c5e8b1e8 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 18 Nov 2019 10:21:19 +0100 Subject: [PATCH 286/299] usb-serial: cp201x: support Mark-10 digital force gauge commit 347bc8cb26388791c5881a3775cb14a3f765a674 upstream. Add support for the Mark-10 digital force gauge device to the cp201x driver. Based on a report and a larger patch from Joel Jennings Reported-by: Joel Jennings Cc: stable Acked-by: Johan Hovold Link: https://lore.kernel.org/r/20191118092119.GA153852@kroah.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/cp210x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index e732949f6567..7ae121567098 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -125,6 +125,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */ { USB_DEVICE(0x10C4, 0x8382) }, /* Cygnal Integrated Products, Inc. */ { USB_DEVICE(0x10C4, 0x83A8) }, /* Amber Wireless AMB2560 */ + { USB_DEVICE(0x10C4, 0x83AA) }, /* Mark-10 Digital Force Gauge */ { USB_DEVICE(0x10C4, 0x83D8) }, /* DekTec DTA Plus VHF/UHF Booster/Attenuator */ { USB_DEVICE(0x10C4, 0x8411) }, /* Kyocera GPS Module */ { USB_DEVICE(0x10C4, 0x8418) }, /* IRZ Automation Teleport SG-10 GSM/GPRS Modem */ From 0439d6b901872933da7003413e1bae327c225717 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Thu, 7 Nov 2019 15:28:55 +0100 Subject: [PATCH 287/299] USB: chaoskey: fix error case of a timeout commit 92aa5986f4f7b5a8bf282ca0f50967f4326559f5 upstream. In case of a timeout or if a signal aborts a read communication with the device needs to be ended lest we overwrite an active URB the next time we do IO to the device, as the URB may still be active. Signed-off-by: Oliver Neukum Cc: stable Link: https://lore.kernel.org/r/20191107142856.16774-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/misc/chaoskey.c | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) diff --git a/drivers/usb/misc/chaoskey.c b/drivers/usb/misc/chaoskey.c index 34e6cd6f40d3..87067c3d6109 100644 --- a/drivers/usb/misc/chaoskey.c +++ b/drivers/usb/misc/chaoskey.c @@ -384,13 +384,17 @@ static int _chaoskey_fill(struct chaoskey *dev) !dev->reading, (started ? NAK_TIMEOUT : ALEA_FIRST_TIMEOUT) ); - if (result < 0) + if (result < 0) { + usb_kill_urb(dev->urb); goto out; + } - if (result == 0) + if (result == 0) { result = -ETIMEDOUT; - else + usb_kill_urb(dev->urb); + } else { result = dev->valid; + } out: /* Let the device go back to sleep eventually */ usb_autopm_put_interface(dev->interface); @@ -526,7 +530,21 @@ static int chaoskey_suspend(struct usb_interface *interface, static int chaoskey_resume(struct usb_interface *interface) { + struct chaoskey *dev; + struct usb_device *udev = interface_to_usbdev(interface); + usb_dbg(interface, "resume"); + dev = usb_get_intfdata(interface); + + /* + * We may have lost power. + * In that case the device that needs a long time + * for the first requests needs an extended timeout + * again + */ + if (le16_to_cpu(udev->descriptor.idVendor) == ALEA_VENDOR_ID) + dev->reads_started = false; + return 0; } #else From 356440a79b6b2faf796a65b9915b0882e9f1f73b Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Wed, 6 Nov 2019 13:49:01 +0100 Subject: [PATCH 288/299] appledisplay: fix error handling in the scheduled work commit 91feb01596e5efc0cc922cc73f5583114dccf4d2 upstream. The work item can operate on 1. stale memory left over from the last transfer the actual length of the data transfered needs to be checked 2. memory already freed the error handling in appledisplay_probe() needs to cancel the work in that case Reported-and-tested-by: syzbot+495dab1f175edc9c2f13@syzkaller.appspotmail.com Signed-off-by: Oliver Neukum Cc: stable Link: https://lore.kernel.org/r/20191106124902.7765-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/misc/appledisplay.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/usb/misc/appledisplay.c b/drivers/usb/misc/appledisplay.c index 39ca31b4de46..718d692b07ac 100644 --- a/drivers/usb/misc/appledisplay.c +++ b/drivers/usb/misc/appledisplay.c @@ -170,7 +170,12 @@ static int appledisplay_bl_get_brightness(struct backlight_device *bd) 0, pdata->msgdata, 2, ACD_USB_TIMEOUT); - brightness = pdata->msgdata[1]; + if (retval < 2) { + if (retval >= 0) + retval = -EMSGSIZE; + } else { + brightness = pdata->msgdata[1]; + } mutex_unlock(&pdata->sysfslock); if (retval < 0) @@ -305,6 +310,7 @@ error: if (pdata) { if (pdata->urb) { usb_kill_urb(pdata->urb); + cancel_delayed_work_sync(&pdata->work); if (pdata->urbdata) usb_free_coherent(pdata->udev, ACD_URB_BUFFER_LEN, pdata->urbdata, pdata->urb->transfer_dma); From 84743898d60bd9ac8a3ad0cac53aa01d508175bb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pavel=20L=C3=B6bl?= Date: Fri, 1 Nov 2019 08:01:50 +0100 Subject: [PATCH 289/299] USB: serial: mos7840: add USB ID to support Moxa UPort 2210 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit e696d00e65e81d46e911f24b12e441037bf11b38 upstream. Add USB ID for MOXA UPort 2210. This device contains mos7820 but it passes GPIO0 check implemented by driver and it's detected as mos7840. Hence product id check is added to force mos7820 mode. Signed-off-by: Pavel Löbl Cc: stable [ johan: rename id defines and add vendor-id check ] Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/mos7840.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c index b42bad85097a..c1c0f6023d96 100644 --- a/drivers/usb/serial/mos7840.c +++ b/drivers/usb/serial/mos7840.c @@ -118,11 +118,15 @@ /* This driver also supports * ATEN UC2324 device using Moschip MCS7840 * ATEN UC2322 device using Moschip MCS7820 + * MOXA UPort 2210 device using Moschip MCS7820 */ #define USB_VENDOR_ID_ATENINTL 0x0557 #define ATENINTL_DEVICE_ID_UC2324 0x2011 #define ATENINTL_DEVICE_ID_UC2322 0x7820 +#define USB_VENDOR_ID_MOXA 0x110a +#define MOXA_DEVICE_ID_2210 0x2210 + /* Interrupt Routine Defines */ #define SERIAL_IIR_RLS 0x06 @@ -193,6 +197,7 @@ static const struct usb_device_id id_table[] = { {USB_DEVICE(USB_VENDOR_ID_BANDB, BANDB_DEVICE_ID_USOPTL2_4)}, {USB_DEVICE(USB_VENDOR_ID_ATENINTL, ATENINTL_DEVICE_ID_UC2324)}, {USB_DEVICE(USB_VENDOR_ID_ATENINTL, ATENINTL_DEVICE_ID_UC2322)}, + {USB_DEVICE(USB_VENDOR_ID_MOXA, MOXA_DEVICE_ID_2210)}, {} /* terminating entry */ }; MODULE_DEVICE_TABLE(usb, id_table); @@ -2053,6 +2058,7 @@ static int mos7840_probe(struct usb_serial *serial, const struct usb_device_id *id) { u16 product = le16_to_cpu(serial->dev->descriptor.idProduct); + u16 vid = le16_to_cpu(serial->dev->descriptor.idVendor); u8 *buf; int device_type; @@ -2062,6 +2068,11 @@ static int mos7840_probe(struct usb_serial *serial, goto out; } + if (vid == USB_VENDOR_ID_MOXA && product == MOXA_DEVICE_ID_2210) { + device_type = MOSCHIP_DEVICE_ID_7820; + goto out; + } + buf = kzalloc(VENDOR_READ_LENGTH, GFP_KERNEL); if (!buf) return -ENOMEM; From abbda35d6a6e9449fcf8c40a8a79cfc208a3a127 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 7 Nov 2019 14:21:18 +0100 Subject: [PATCH 290/299] USB: serial: mos7720: fix remote wakeup commit ea422312a462696093b5db59d294439796cba4ad upstream. The driver was setting the device remote-wakeup feature during probe in violation of the USB specification (which says it should only be set just prior to suspending the device). This could potentially waste power during suspend as well as lead to spurious wakeups. Note that USB core would clear the remote-wakeup feature at first resume. Fixes: 0f64478cbc7a ("USB: add USB serial mos7720 driver") Cc: stable # 2.6.19 Reviewed-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/mos7720.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c index e8f275a0326d..c0232b67a40f 100644 --- a/drivers/usb/serial/mos7720.c +++ b/drivers/usb/serial/mos7720.c @@ -1894,10 +1894,6 @@ static int mos7720_startup(struct usb_serial *serial) product = le16_to_cpu(serial->dev->descriptor.idProduct); dev = serial->dev; - /* setting configuration feature to one */ - usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0), - (__u8)0x03, 0x00, 0x01, 0x00, NULL, 0x00, 5000); - if (product == MOSCHIP_DEVICE_ID_7715) { struct urb *urb = serial->port[0]->interrupt_in_urb; From 3349ed266ae22ea9571343b996ffed7fcf500244 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 7 Nov 2019 14:21:19 +0100 Subject: [PATCH 291/299] USB: serial: mos7840: fix remote wakeup commit 92fe35fb9c70a00d8fbbf5bd6172c921dd9c7815 upstream. The driver was setting the device remote-wakeup feature during probe in violation of the USB specification (which says it should only be set just prior to suspending the device). This could potentially waste power during suspend as well as lead to spurious wakeups. Note that USB core would clear the remote-wakeup feature at first resume. Fixes: 3f5429746d91 ("USB: Moschip 7840 USB-Serial Driver") Cc: stable # 2.6.19 Reviewed-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/mos7840.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c index c1c0f6023d96..4a7bd26841af 100644 --- a/drivers/usb/serial/mos7840.c +++ b/drivers/usb/serial/mos7840.c @@ -2325,11 +2325,6 @@ out: goto error; } else dev_dbg(&port->dev, "ZLP_REG5 Writing success status%d\n", status); - - /* setting configuration feature to one */ - usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0), - 0x03, 0x00, 0x01, 0x00, NULL, 0x00, - MOS_WDR_TIMEOUT); } return 0; error: From 62aca6645c084de24c3e594d7ecac0a8cfc08d6e Mon Sep 17 00:00:00 2001 From: Aleksander Morgado Date: Thu, 7 Nov 2019 11:55:08 +0100 Subject: [PATCH 292/299] USB: serial: option: add support for DW5821e with eSIM support commit 957c31ea082e3fe5196f46d5b04018b10de47400 upstream. The device exposes AT, NMEA and DIAG ports in both USB configurations. Exactly same layout as the default DW5821e module, just a different vid/pid. P: Vendor=413c ProdID=81e0 Rev=03.18 S: Manufacturer=Dell Inc. S: Product=DW5821e-eSIM Snapdragon X20 LTE S: SerialNumber=0123456789ABCDEF C: #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#=0x0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I: If#=0x1 Alt= 0 #EPs= 1 Cls=03(HID ) Sub=00 Prot=00 Driver=usbhid I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option P: Vendor=413c ProdID=81e0 Rev=03.18 S: Manufacturer=Dell Inc. S: Product=DW5821e-eSIM Snapdragon X20 LTE S: SerialNumber=0123456789ABCDEF C: #Ifs= 7 Cfg#= 2 Atr=a0 MxPwr=500mA I: If#=0x0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim I: If#=0x1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#=0x6 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) Signed-off-by: Aleksander Morgado Cc: stable Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 3cc659a62782..8eed4868554b 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -197,6 +197,7 @@ static void option_instat_callback(struct urb *urb); #define DELL_PRODUCT_5804_MINICARD_ATT 0x819b /* Novatel E371 */ #define DELL_PRODUCT_5821E 0x81d7 +#define DELL_PRODUCT_5821E_ESIM 0x81e0 #define KYOCERA_VENDOR_ID 0x0c88 #define KYOCERA_PRODUCT_KPC650 0x17da @@ -1044,6 +1045,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(DELL_VENDOR_ID, DELL_PRODUCT_5804_MINICARD_ATT, 0xff, 0xff, 0xff) }, { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5821E), .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5821E_ESIM), + .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_E100A) }, /* ADU-E100, ADU-310 */ { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_500A) }, { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_620UW) }, From 4101916e9f08a692000c0052ce2ca86305ff9b55 Mon Sep 17 00:00:00 2001 From: Aleksander Morgado Date: Wed, 13 Nov 2019 11:14:05 +0100 Subject: [PATCH 293/299] USB: serial: option: add support for Foxconn T77W968 LTE modules commit f0797095423e6ea3b4be61134ee353c7f504d440 upstream. These are the Foxconn-branded variants of the Dell DW5821e modules, same USB layout as those. The device exposes AT, NMEA and DIAG ports in both USB configurations. P: Vendor=0489 ProdID=e0b4 Rev=03.18 S: Manufacturer=FII S: Product=T77W968 LTE S: SerialNumber=0123456789ABCDEF C: #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#=0x0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I: If#=0x1 Alt= 0 #EPs= 1 Cls=03(HID ) Sub=00 Prot=00 Driver=usbhid I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option P: Vendor=0489 ProdID=e0b4 Rev=03.18 S: Manufacturer=FII S: Product=T77W968 LTE S: SerialNumber=0123456789ABCDEF C: #Ifs= 7 Cfg#= 2 Atr=a0 MxPwr=500mA I: If#=0x0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim I: If#=0x1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#=0x6 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) Signed-off-by: Aleksander Morgado [ johan: drop id defines ] Cc: stable Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 8eed4868554b..2905274e3626 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1993,6 +1993,10 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0xa31d, 0xff, 0x06, 0x13) }, { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0xa31d, 0xff, 0x06, 0x14) }, { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0xa31d, 0xff, 0x06, 0x1b) }, + { USB_DEVICE(0x0489, 0xe0b4), /* Foxconn T77W968 */ + .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, + { USB_DEVICE(0x0489, 0xe0b5), /* Foxconn T77W968 ESIM */ + .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 */ .driver_info = RSVD(4) | RSVD(5) | RSVD(6) }, { USB_DEVICE(0x2cb7, 0x0104), /* Fibocom NL678 series */ From b7e2a040d9fcaddcd665b593f31f0f5df8bbc1f3 Mon Sep 17 00:00:00 2001 From: Bernd Porr Date: Mon, 18 Nov 2019 23:07:59 +0000 Subject: [PATCH 294/299] staging: comedi: usbduxfast: usbduxfast_ai_cmdtest rounding error commit 5618332e5b955b4bff06d0b88146b971c8dd7b32 upstream. The userspace comedilib function 'get_cmd_generic_timed' fills the cmd structure with an informed guess and then calls the function 'usbduxfast_ai_cmdtest' in this driver repeatedly while 'usbduxfast_ai_cmdtest' is modifying the cmd struct until it no longer changes. However, because of rounding errors this never converged because 'steps = (cmd->convert_arg * 30) / 1000' and then back to 'cmd->convert_arg = (steps * 1000) / 30' won't be the same because of rounding errors. 'Steps' should only be converted back to the 'convert_arg' if 'steps' has actually been modified. In addition the case of steps being 0 wasn't checked which is also now done. Signed-off-by: Bernd Porr Cc: # 4.4+ Reviewed-by: Ian Abbott Link: https://lore.kernel.org/r/20191118230759.1727-1-mail@berndporr.me.uk Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/usbduxfast.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/drivers/staging/comedi/drivers/usbduxfast.c b/drivers/staging/comedi/drivers/usbduxfast.c index e18c0723b760..0d38589c2600 100644 --- a/drivers/staging/comedi/drivers/usbduxfast.c +++ b/drivers/staging/comedi/drivers/usbduxfast.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0+ /* - * Copyright (C) 2004-2014 Bernd Porr, mail@berndporr.me.uk + * Copyright (C) 2004-2019 Bernd Porr, mail@berndporr.me.uk */ /* @@ -8,7 +8,7 @@ * Description: University of Stirling USB DAQ & INCITE Technology Limited * Devices: [ITL] USB-DUX-FAST (usbduxfast) * Author: Bernd Porr - * Updated: 10 Oct 2014 + * Updated: 16 Nov 2019 * Status: stable */ @@ -22,6 +22,7 @@ * * * Revision history: + * 1.0: Fixed a rounding error in usbduxfast_ai_cmdtest * 0.9: Dropping the first data packet which seems to be from the last transfer. * Buffer overflows in the FX2 are handed over to comedi. * 0.92: Dropping now 4 packets. The quad buffer has to be emptied. @@ -350,6 +351,7 @@ static int usbduxfast_ai_cmdtest(struct comedi_device *dev, struct comedi_cmd *cmd) { int err = 0; + int err2 = 0; unsigned int steps; unsigned int arg; @@ -399,11 +401,16 @@ static int usbduxfast_ai_cmdtest(struct comedi_device *dev, */ steps = (cmd->convert_arg * 30) / 1000; if (cmd->chanlist_len != 1) - err |= comedi_check_trigger_arg_min(&steps, - MIN_SAMPLING_PERIOD); - err |= comedi_check_trigger_arg_max(&steps, MAX_SAMPLING_PERIOD); - arg = (steps * 1000) / 30; - err |= comedi_check_trigger_arg_is(&cmd->convert_arg, arg); + err2 |= comedi_check_trigger_arg_min(&steps, + MIN_SAMPLING_PERIOD); + else + err2 |= comedi_check_trigger_arg_min(&steps, 1); + err2 |= comedi_check_trigger_arg_max(&steps, MAX_SAMPLING_PERIOD); + if (err2) { + err |= err2; + arg = (steps * 1000) / 30; + err |= comedi_check_trigger_arg_is(&cmd->convert_arg, arg); + } if (cmd->stop_src == TRIG_COUNT) err |= comedi_check_trigger_arg_min(&cmd->stop_arg, 1); From 19d98b4d55b044b0d3902d70b3bec0ea9f652cd9 Mon Sep 17 00:00:00 2001 From: "Christopher M. Riedl" Date: Thu, 23 May 2019 21:46:48 -0500 Subject: [PATCH 295/299] powerpc/64s: support nospectre_v2 cmdline option commit d8f0e0b073e1ec52a05f0c2a56318b47387d2f10 upstream. Add support for disabling the kernel implemented spectre v2 mitigation (count cache flush on context switch) via the nospectre_v2 and mitigations=off cmdline options. Suggested-by: Michael Ellerman Signed-off-by: Christopher M. Riedl Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190524024647.381-1-cmr@informatik.wtf Signed-off-by: Daniel Axtens Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/kernel/security.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index 70568ccbd9fd..8cc8b0de12d2 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -28,7 +28,7 @@ static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NO bool barrier_nospec_enabled; static bool no_nospec; static bool btb_flush_enabled; -#ifdef CONFIG_PPC_FSL_BOOK3E +#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64) static bool no_spectrev2; #endif @@ -106,7 +106,7 @@ static __init int barrier_nospec_debugfs_init(void) device_initcall(barrier_nospec_debugfs_init); #endif /* CONFIG_DEBUG_FS */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64) static int __init handle_nospectre_v2(char *p) { no_spectrev2 = true; @@ -114,6 +114,9 @@ static int __init handle_nospectre_v2(char *p) return 0; } early_param("nospectre_v2", handle_nospectre_v2); +#endif /* CONFIG_PPC_FSL_BOOK3E || CONFIG_PPC_BOOK3S_64 */ + +#ifdef CONFIG_PPC_FSL_BOOK3E void setup_spectre_v2(void) { if (no_spectrev2 || cpu_mitigations_off()) @@ -391,7 +394,17 @@ static void toggle_count_cache_flush(bool enable) void setup_count_cache_flush(void) { - toggle_count_cache_flush(true); + bool enable = true; + + if (no_spectrev2 || cpu_mitigations_off()) { + if (security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED) || + security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED)) + pr_warn("Spectre v2 mitigations not under software control, can't disable\n"); + + enable = false; + } + + toggle_count_cache_flush(enable); } #ifdef CONFIG_DEBUG_FS From 0a60d4bddc0ba6a7e06d10efa59f7861837860b0 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 13 Nov 2019 21:05:41 +1100 Subject: [PATCH 296/299] powerpc/book3s64: Fix link stack flush on context switch commit 39e72bf96f5847ba87cc5bd7a3ce0fed813dc9ad upstream. In commit ee13cb249fab ("powerpc/64s: Add support for software count cache flush"), I added support for software to flush the count cache (indirect branch cache) on context switch if firmware told us that was the required mitigation for Spectre v2. As part of that code we also added a software flush of the link stack (return address stack), which protects against Spectre-RSB between user processes. That is all correct for CPUs that activate that mitigation, which is currently Power9 Nimbus DD2.3. What I got wrong is that on older CPUs, where firmware has disabled the count cache, we also need to flush the link stack on context switch. To fix it we create a new feature bit which is not set by firmware, which tells us we need to flush the link stack. We set that when firmware tells us that either of the existing Spectre v2 mitigations are enabled. Then we adjust the patching code so that if we see that feature bit we enable the link stack flush. If we're also told to flush the count cache in software then we fall through and do that also. On the older CPUs we don't need to do do the software count cache flush, firmware has disabled it, so in that case we patch in an early return after the link stack flush. The naming of some of the functions is awkward after this patch, because they're called "count cache" but they also do link stack. But we'll fix that up in a later commit to ease backporting. This is the fix for CVE-2019-18660. Reported-by: Anthony Steinhauser Fixes: ee13cb249fab ("powerpc/64s: Add support for software count cache flush") Cc: stable@vger.kernel.org # v4.4+ Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/include/asm/asm-prototypes.h | 1 + arch/powerpc/include/asm/security_features.h | 3 ++ arch/powerpc/kernel/entry_64.S | 6 +++ arch/powerpc/kernel/security.c | 48 ++++++++++++++++++-- 4 files changed, 54 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index e398173ae67d..00c2b37d8470 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -146,6 +146,7 @@ void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); /* Patch sites */ extern s32 patch__call_flush_count_cache; extern s32 patch__flush_count_cache_return; +extern s32 patch__flush_link_stack_return; extern s32 patch__memset_nocache, patch__memcpy_nocache; extern long flush_count_cache; diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index 759597bf0fd8..ccf44c135389 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -81,6 +81,9 @@ static inline bool security_ftr_enabled(unsigned long feature) // Software required to flush count cache on context switch #define SEC_FTR_FLUSH_COUNT_CACHE 0x0000000000000400ull +// Software required to flush link stack on context switch +#define SEC_FTR_FLUSH_LINK_STACK 0x0000000000001000ull + // Features enabled by default #define SEC_FTR_DEFAULT \ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 7a46e0e57a36..58b50967b3e5 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -533,6 +533,7 @@ flush_count_cache: /* Save LR into r9 */ mflr r9 + // Flush the link stack .rept 64 bl .+4 .endr @@ -542,6 +543,11 @@ flush_count_cache: .balign 32 /* Restore LR */ 1: mtlr r9 + + // If we're just flushing the link stack, return here +3: nop + patch_site 3b patch__flush_link_stack_return + li r9,0x7fff mtctr r9 diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index 8cc8b0de12d2..6e54a25f398b 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -24,6 +24,7 @@ enum count_cache_flush_type { COUNT_CACHE_FLUSH_HW = 0x4, }; static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; +static bool link_stack_flush_enabled; bool barrier_nospec_enabled; static bool no_nospec; @@ -204,11 +205,19 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c if (ccd) seq_buf_printf(&s, "Indirect branch cache disabled"); + + if (link_stack_flush_enabled) + seq_buf_printf(&s, ", Software link stack flush"); + } else if (count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) { seq_buf_printf(&s, "Mitigation: Software count cache flush"); if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW) seq_buf_printf(&s, " (hardware accelerated)"); + + if (link_stack_flush_enabled) + seq_buf_printf(&s, ", Software link stack flush"); + } else if (btb_flush_enabled) { seq_buf_printf(&s, "Mitigation: Branch predictor state flush"); } else { @@ -369,18 +378,40 @@ static __init int stf_barrier_debugfs_init(void) device_initcall(stf_barrier_debugfs_init); #endif /* CONFIG_DEBUG_FS */ +static void no_count_cache_flush(void) +{ + count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; + pr_info("count-cache-flush: software flush disabled.\n"); +} + static void toggle_count_cache_flush(bool enable) { - if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) { + if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE) && + !security_ftr_enabled(SEC_FTR_FLUSH_LINK_STACK)) + enable = false; + + if (!enable) { patch_instruction_site(&patch__call_flush_count_cache, PPC_INST_NOP); - count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; - pr_info("count-cache-flush: software flush disabled.\n"); + pr_info("link-stack-flush: software flush disabled.\n"); + link_stack_flush_enabled = false; + no_count_cache_flush(); return; } + // This enables the branch from _switch to flush_count_cache patch_branch_site(&patch__call_flush_count_cache, (u64)&flush_count_cache, BRANCH_SET_LINK); + pr_info("link-stack-flush: software flush enabled.\n"); + link_stack_flush_enabled = true; + + // If we just need to flush the link stack, patch an early return + if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) { + patch_instruction_site(&patch__flush_link_stack_return, PPC_INST_BLR); + no_count_cache_flush(); + return; + } + if (!security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) { count_cache_flush_type = COUNT_CACHE_FLUSH_SW; pr_info("count-cache-flush: full software flush sequence enabled.\n"); @@ -399,11 +430,20 @@ void setup_count_cache_flush(void) if (no_spectrev2 || cpu_mitigations_off()) { if (security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED) || security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED)) - pr_warn("Spectre v2 mitigations not under software control, can't disable\n"); + pr_warn("Spectre v2 mitigations not fully under software control, can't disable\n"); enable = false; } + /* + * There's no firmware feature flag/hypervisor bit to tell us we need to + * flush the link stack on context switch. So we set it here if we see + * either of the Spectre v2 mitigations that aim to protect userspace. + */ + if (security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED) || + security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) + security_ftr_set(SEC_FTR_FLUSH_LINK_STACK); + toggle_count_cache_flush(enable); } From 345712c95eec44bf414782b33e6d5a550fe62b3b Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 13 Nov 2019 21:05:44 +1100 Subject: [PATCH 297/299] KVM: PPC: Book3S HV: Flush link stack on guest exit to host kernel commit af2e8c68b9c5403f77096969c516f742f5bb29e0 upstream. On some systems that are vulnerable to Spectre v2, it is up to software to flush the link stack (return address stack), in order to protect against Spectre-RSB. When exiting from a guest we do some house keeping and then potentially exit to C code which is several stack frames deep in the host kernel. We will then execute a series of returns without preceeding calls, opening up the possiblity that the guest could have poisoned the link stack, and direct speculative execution of the host to a gadget of some sort. To prevent this we add a flush of the link stack on exit from a guest. Signed-off-by: Michael Ellerman [dja: straightforward backport to v4.19] Signed-off-by: Daniel Axtens Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/include/asm/asm-prototypes.h | 2 ++ arch/powerpc/kernel/security.c | 9 ++++++++ arch/powerpc/kvm/book3s_hv_rmhandlers.S | 28 +++++++++++++++++++++++ 3 files changed, 39 insertions(+) diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 00c2b37d8470..d0609c116e4f 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -147,8 +147,10 @@ void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); extern s32 patch__call_flush_count_cache; extern s32 patch__flush_count_cache_return; extern s32 patch__flush_link_stack_return; +extern s32 patch__call_kvm_flush_link_stack; extern s32 patch__memset_nocache, patch__memcpy_nocache; extern long flush_count_cache; +extern long kvm_flush_link_stack; #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */ diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index 6e54a25f398b..a5c5940d970a 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -392,6 +392,9 @@ static void toggle_count_cache_flush(bool enable) if (!enable) { patch_instruction_site(&patch__call_flush_count_cache, PPC_INST_NOP); +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + patch_instruction_site(&patch__call_kvm_flush_link_stack, PPC_INST_NOP); +#endif pr_info("link-stack-flush: software flush disabled.\n"); link_stack_flush_enabled = false; no_count_cache_flush(); @@ -402,6 +405,12 @@ static void toggle_count_cache_flush(bool enable) patch_branch_site(&patch__call_flush_count_cache, (u64)&flush_count_cache, BRANCH_SET_LINK); +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + // This enables the branch from guest_exit_cont to kvm_flush_link_stack + patch_branch_site(&patch__call_kvm_flush_link_stack, + (u64)&kvm_flush_link_stack, BRANCH_SET_LINK); +#endif + pr_info("link-stack-flush: software flush enabled.\n"); link_stack_flush_enabled = true; diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index f1878e13dd56..7fe3077a1ef6 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -18,6 +18,7 @@ */ #include +#include #include #include #include @@ -1559,6 +1560,10 @@ mc_cont: 1: #endif /* CONFIG_KVM_XICS */ + /* Possibly flush the link stack here. */ +1: nop + patch_site 1b patch__call_kvm_flush_link_stack + /* For hash guest, read the guest SLB and save it away */ ld r5, VCPU_KVM(r9) lbz r0, KVM_RADIX(r5) @@ -2107,6 +2112,29 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) mtlr r0 blr +.balign 32 +.global kvm_flush_link_stack +kvm_flush_link_stack: + /* Save LR into r0 */ + mflr r0 + + /* Flush the link stack. On Power8 it's up to 32 entries in size. */ + .rept 32 + bl .+4 + .endr + + /* And on Power9 it's up to 64. */ +BEGIN_FTR_SECTION + .rept 32 + bl .+4 + .endr +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + + /* Restore LR */ + mtlr r0 + blr + + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM /* * Softpatch interrupt for transactional memory emulation cases From 6938a9da7ff8f25fc6a445d4b7510776b00bb386 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Fri, 21 Jun 2019 18:39:49 -0300 Subject: [PATCH 298/299] PM / devfreq: Fix kernel oops on governor module load commit 7544fd7f384591038646d3cd9efb311ab4509e24 upstream. A bit unexpectedly (but still documented), request_module may return a positive value, in case of a modprobe error. This is currently causing issues in the devfreq framework. When a request_module exits with a positive value, we currently return that via ERR_PTR. However, because the value is positive, it's not a ERR_VALUE proper, and is therefore treated as a valid struct devfreq_governor pointer, leading to a kernel oops. Fix this by returning -EINVAL if request_module returns a positive value. Fixes: b53b0128052ff ("PM / devfreq: Fix static checker warning in try_then_request_governor") Signed-off-by: Ezequiel Garcia Reviewed-by: Chanwoo Choi Signed-off-by: MyungJoo Ham Cc: Nobuhiro Iwamatsu Signed-off-by: Greg Kroah-Hartman --- drivers/devfreq/devfreq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index e2ab46bfa666..d350253d161a 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -257,7 +257,7 @@ static struct devfreq_governor *try_then_request_governor(const char *name) /* Restore previous state before return */ mutex_lock(&devfreq_list_lock); if (err) - return ERR_PTR(err); + return (err < 0) ? ERR_PTR(err) : ERR_PTR(-EINVAL); governor = find_devfreq_governor(name); } From 174651bdf802a2139065e8e31ce950e2f3fc4a94 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 1 Dec 2019 09:17:47 +0100 Subject: [PATCH 299/299] Linux 4.19.87 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index feb0568e9535..9240f36099de 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 19 -SUBLEVEL = 86 +SUBLEVEL = 87 EXTRAVERSION = NAME = "People's Front"