[ Upstream commit 663a50ceac75c2208d2ad95365bc8382fd42f44d ]

shadow mm's pin count got increased in workload preparation phase, which is after workload scanning. it will get decreased in complete_current_workload() anyway after workload completion. Sometimes, if a workload meets a scanning error, its shadow mm pin count will not get increased but will get decreased in the end. This patch lets shadow mm's pin count not go below 0.

Fixes: 2707e4446688 ("drm/i915/gvt: vGPU graphics memory virtualization") Cc: zhenyuw@linux.intel.com Cc: stable@vger.kernel.org #4.14+ Signed-off-by: Yan Zhao yan.y.zhao@intel.com Signed-off-by: Zhenyu Wang zhenyuw@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/i915/gvt/gtt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 00aad8164dec..542f31ce108f 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1940,7 +1940,7 @@ void _intel_vgpu_mm_release(struct kref *mm_ref) */ void intel_vgpu_unpin_mm(struct intel_vgpu_mm *mm) { - atomic_dec(&mm->pincount); + atomic_dec_if_positive(&mm->pincount); }

/**

[ Upstream commit 1b704c4a1ba95574832e730f23817b651db2aa59 ]

After queue stopped, the wakeup mechanism may wake it up again when ring buffer usage is lower than a threshold. This may cause send path panic on NULL pointer when we stopped all tx queues in netvsc_detach and start removing the netvsc device.

This patch fix it by adding a tx_disable flag to prevent unwanted queue wakeup.

Fixes: 7b2ee50c0cd5 ("hv_netvsc: common detach logic") Reported-by: Mohammed Gamal mgamal@redhat.com Signed-off-by: Haiyang Zhang haiyangz@microsoft.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/hyperv/hyperv_net.h | 1 + drivers/net/hyperv/netvsc.c | 6 ++++-- drivers/net/hyperv/netvsc_drv.c | 32 ++++++++++++++++++++++++++------ 3 files changed, 31 insertions(+), 8 deletions(-)

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 42d284669b03..31d8d83c25ac 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -970,6 +970,7 @@ struct netvsc_device {

wait_queue_head_t wait_drain; bool destroy; + bool tx_disable; /* if true, do not wake up queue again */

/* Receive buffer allocated by us but manages by NetVSP */ void *recv_buf; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 1a942feab954..fb12b63439c6 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -110,6 +110,7 @@ static struct netvsc_device *alloc_net_device(void)

init_waitqueue_head(&net_device->wait_drain); net_device->destroy = false; + net_device->tx_disable = false;

net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT; net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT; @@ -716,7 +717,7 @@ static void netvsc_send_tx_complete(struct net_device *ndev, } else { struct netdev_queue *txq = netdev_get_tx_queue(ndev, q_idx);

- if (netif_tx_queue_stopped(txq) && + if (netif_tx_queue_stopped(txq) && !net_device->tx_disable && (hv_get_avail_to_write_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER || queue_sends < 1)) { netif_tx_wake_queue(txq); @@ -871,7 +872,8 @@ static inline int netvsc_send_pkt( } else if (ret == -EAGAIN) { netif_tx_stop_queue(txq); ndev_ctx->eth_stats.stop_queue++; - if (atomic_read(&nvchan->queue_sends) < 1) { + if (atomic_read(&nvchan->queue_sends) < 1 && + !net_device->tx_disable) { netif_tx_wake_queue(txq); ndev_ctx->eth_stats.wake_queue++; ret = -ENOSPC; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index c8320405c8f1..9d699bd5f715 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -109,6 +109,15 @@ static void netvsc_set_rx_mode(struct net_device *net) rcu_read_unlock(); }

+static void netvsc_tx_enable(struct netvsc_device *nvscdev, + struct net_device *ndev) +{ + nvscdev->tx_disable = false; + virt_wmb(); /* ensure queue wake up mechanism is on */ + + netif_tx_wake_all_queues(ndev); +} + static int netvsc_open(struct net_device *net) { struct net_device_context *ndev_ctx = netdev_priv(net); @@ -129,7 +138,7 @@ static int netvsc_open(struct net_device *net) rdev = nvdev->extension; if (!rdev->link_state) { netif_carrier_on(net); - netif_tx_wake_all_queues(net); + netvsc_tx_enable(nvdev, net); }

if (vf_netdev) { @@ -184,6 +193,17 @@ static int netvsc_wait_until_empty(struct netvsc_device *nvdev) } }

+static void netvsc_tx_disable(struct netvsc_device *nvscdev, + struct net_device *ndev) +{ + if (nvscdev) { + nvscdev->tx_disable = true; + virt_wmb(); /* ensure txq will not wake up after stop */ + } + + netif_tx_disable(ndev); +} + static int netvsc_close(struct net_device *net) { struct net_device_context *net_device_ctx = netdev_priv(net); @@ -192,7 +212,7 @@ static int netvsc_close(struct net_device *net) struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev); int ret;

- netif_tx_disable(net); + netvsc_tx_disable(nvdev, net);

/* No need to close rndis filter if it is removed already */ if (!nvdev) @@ -918,7 +938,7 @@ static int netvsc_detach(struct net_device *ndev,

/* If device was up (receiving) then shutdown */ if (netif_running(ndev)) { - netif_tx_disable(ndev); + netvsc_tx_disable(nvdev, ndev);

ret = rndis_filter_close(nvdev); if (ret) { @@ -1899,7 +1919,7 @@ static void netvsc_link_change(struct work_struct *w) if (rdev->link_state) { rdev->link_state = false; netif_carrier_on(net); - netif_tx_wake_all_queues(net); + netvsc_tx_enable(net_device, net); } else { notify = true; } @@ -1909,7 +1929,7 @@ static void netvsc_link_change(struct work_struct *w) if (!rdev->link_state) { rdev->link_state = true; netif_carrier_off(net); - netif_tx_stop_all_queues(net); + netvsc_tx_disable(net_device, net); } kfree(event); break; @@ -1918,7 +1938,7 @@ static void netvsc_link_change(struct work_struct *w) if (!rdev->link_state) { rdev->link_state = true; netif_carrier_off(net); - netif_tx_stop_all_queues(net); + netvsc_tx_disable(net_device, net); event->event = RNDIS_STATUS_MEDIA_CONNECT; spin_lock_irqsave(&ndev_ctx->lock, flags); list_add(&event->list, &ndev_ctx->reconfig_events);

[ Upstream commit b2e54b09a3d29c4db883b920274ca8dca4d9f04d ]

The device type for ip6 tunnels is set to ARPHRD_TUNNEL6. However, the ip4ip6_err function is expecting the device type of the tunnel to be ARPHRD_TUNNEL. Since the device types do not match, the function exits and the ICMP error packet is not sent to the originating host. Note that the device type for IPv4 tunnels is set to ARPHRD_TUNNEL.

Fix is to expect a tunnel device type of ARPHRD_TUNNEL6 instead. Now the tunnel device type matches and the ICMP error packet is sent to the originating host.

Signed-off-by: Sheena Mira-ato sheena.mira-ato@alliedtelesis.co.nz Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/ip6_tunnel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 0c6403cf8b52..ade1390c6348 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -627,7 +627,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->daddr, eiph->saddr, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0); - if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL) { + if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL6) { if (!IS_ERR(rt)) ip_rt_put(rt); goto out; @@ -636,7 +636,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } else { if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) || - skb_dst(skb2)->dev->type != ARPHRD_TUNNEL) + skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6) goto out; }

[ Upstream commit bb9bd814ebf04f579be466ba61fc922625508807 ]

ipip6 tunnels run iptunnel_pull_header on received skbs. This can determine the following use-after-free accessing iph pointer since the packet will be 'uncloned' running pskb_expand_head if it is a cloned gso skb (e.g if the packet has been sent though a veth device)

[ 706.369655] BUG: KASAN: use-after-free in ipip6_rcv+0x1678/0x16e0 [sit] [ 706.449056] Read of size 1 at addr ffffe01b6bd855f5 by task ksoftirqd/1/= [ 706.669494] Hardware name: HPE ProLiant m400 Server/ProLiant m400 Server, BIOS U02 08/19/2016 [ 706.771839] Call trace: [ 706.801159] dump_backtrace+0x0/0x2f8 [ 706.845079] show_stack+0x24/0x30 [ 706.884833] dump_stack+0xe0/0x11c [ 706.925629] print_address_description+0x68/0x260 [ 706.982070] kasan_report+0x178/0x340 [ 707.025995] __asan_report_load1_noabort+0x30/0x40 [ 707.083481] ipip6_rcv+0x1678/0x16e0 [sit] [ 707.132623] tunnel64_rcv+0xd4/0x200 [tunnel4] [ 707.185940] ip_local_deliver_finish+0x3b8/0x988 [ 707.241338] ip_local_deliver+0x144/0x470 [ 707.289436] ip_rcv_finish+0x43c/0x14b0 [ 707.335447] ip_rcv+0x628/0x1138 [ 707.374151] __netif_receive_skb_core+0x1670/0x2600 [ 707.432680] __netif_receive_skb+0x28/0x190 [ 707.482859] process_backlog+0x1d0/0x610 [ 707.529913] net_rx_action+0x37c/0xf68 [ 707.574882] __do_softirq+0x288/0x1018 [ 707.619852] run_ksoftirqd+0x70/0xa8 [ 707.662734] smpboot_thread_fn+0x3a4/0x9e8 [ 707.711875] kthread+0x2c8/0x350 [ 707.750583] ret_from_fork+0x10/0x18

[ 707.811302] Allocated by task 16982: [ 707.854182] kasan_kmalloc.part.1+0x40/0x108 [ 707.905405] kasan_kmalloc+0xb4/0xc8 [ 707.948291] kasan_slab_alloc+0x14/0x20 [ 707.994309] __kmalloc_node_track_caller+0x158/0x5e0 [ 708.053902] __kmalloc_reserve.isra.8+0x54/0xe0 [ 708.108280] __alloc_skb+0xd8/0x400 [ 708.150139] sk_stream_alloc_skb+0xa4/0x638 [ 708.200346] tcp_sendmsg_locked+0x818/0x2b90 [ 708.251581] tcp_sendmsg+0x40/0x60 [ 708.292376] inet_sendmsg+0xf0/0x520 [ 708.335259] sock_sendmsg+0xac/0xf8 [ 708.377096] sock_write_iter+0x1c0/0x2c0 [ 708.424154] new_sync_write+0x358/0x4a8 [ 708.470162] __vfs_write+0xc4/0xf8 [ 708.510950] vfs_write+0x12c/0x3d0 [ 708.551739] ksys_write+0xcc/0x178 [ 708.592533] __arm64_sys_write+0x70/0xa0 [ 708.639593] el0_svc_handler+0x13c/0x298 [ 708.686646] el0_svc+0x8/0xc

[ 708.739019] Freed by task 17: [ 708.774597] __kasan_slab_free+0x114/0x228 [ 708.823736] kasan_slab_free+0x10/0x18 [ 708.868703] kfree+0x100/0x3d8 [ 708.905320] skb_free_head+0x7c/0x98 [ 708.948204] skb_release_data+0x320/0x490 [ 708.996301] pskb_expand_head+0x60c/0x970 [ 709.044399] __iptunnel_pull_header+0x3b8/0x5d0 [ 709.098770] ipip6_rcv+0x41c/0x16e0 [sit] [ 709.146873] tunnel64_rcv+0xd4/0x200 [tunnel4] [ 709.200195] ip_local_deliver_finish+0x3b8/0x988 [ 709.255596] ip_local_deliver+0x144/0x470 [ 709.303692] ip_rcv_finish+0x43c/0x14b0 [ 709.349705] ip_rcv+0x628/0x1138 [ 709.388413] __netif_receive_skb_core+0x1670/0x2600 [ 709.446943] __netif_receive_skb+0x28/0x190 [ 709.497120] process_backlog+0x1d0/0x610 [ 709.544169] net_rx_action+0x37c/0xf68 [ 709.589131] __do_softirq+0x288/0x1018

[ 709.651938] The buggy address belongs to the object at ffffe01b6bd85580 which belongs to the cache kmalloc-1024 of size 1024 [ 709.804356] The buggy address is located 117 bytes inside of 1024-byte region [ffffe01b6bd85580, ffffe01b6bd85980) [ 709.946340] The buggy address belongs to the page: [ 710.003824] page:ffff7ff806daf600 count:1 mapcount:0 mapping:ffffe01c4001f600 index:0x0 [ 710.099914] flags: 0xfffff8000000100(slab) [ 710.149059] raw: 0fffff8000000100 dead000000000100 dead000000000200 ffffe01c4001f600 [ 710.242011] raw: 0000000000000000 0000000000380038 00000001ffffffff 0000000000000000 [ 710.334966] page dumped because: kasan: bad access detected

Fix it resetting iph pointer after iptunnel_pull_header

Fixes: a09a4c8dd1ec ("tunnels: Remove encapsulation offloads on decap") Tested-by: Jianlin Shi jishi@redhat.com Signed-off-by: Lorenzo Bianconi lorenzo.bianconi@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/sit.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index de9aa5cb295c..8f6cf8e6b5c1 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -669,6 +669,10 @@ static int ipip6_rcv(struct sk_buff *skb) !net_eq(tunnel->net, dev_net(tunnel->dev)))) goto out;

+ /* skb can be uncloned in iptunnel_pull_header, so + * old iph is no longer valid + */ + iph = (const struct iphdr *)skb_mac_header(skb); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error)

[ Upstream commit 3d8830266ffc28c16032b859e38a0252e014b631 ]

NULL or ZERO_SIZE_PTR will be returned for zero sized memory request, and derefencing them will lead to a segfault

so it is unnecessory to call vzalloc for zero sized memory request and not call functions which maybe derefence the NULL allocated memory

this also fixes a possible memory leak if phy_ethtool_get_stats returns error, memory should be freed before exit

Signed-off-by: Li RongQing lirongqing@baidu.com Reviewed-by: Wang Li wangli39@baidu.com Reviewed-by: Michal Kubecek mkubecek@suse.cz Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/ethtool.c | 46 ++++++++++++++++++++++++++++++---------------- 1 file changed, 30 insertions(+), 16 deletions(-)

diff --git a/net/core/ethtool.c b/net/core/ethtool.c index aeabc4831fca..7cc97f43f138 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1863,11 +1863,16 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) WARN_ON_ONCE(!ret);

gstrings.len = ret; - data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN)); - if (gstrings.len && !data) - return -ENOMEM;

- __ethtool_get_strings(dev, gstrings.string_set, data); + if (gstrings.len) { + data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN)); + if (!data) + return -ENOMEM; + + __ethtool_get_strings(dev, gstrings.string_set, data); + } else { + data = NULL; + }

ret = -EFAULT; if (copy_to_user(useraddr, &gstrings, sizeof(gstrings))) @@ -1963,11 +1968,15 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) return -EFAULT;

stats.n_stats = n_stats; - data = vzalloc(array_size(n_stats, sizeof(u64))); - if (n_stats && !data) - return -ENOMEM;

- ops->get_ethtool_stats(dev, &stats, data); + if (n_stats) { + data = vzalloc(array_size(n_stats, sizeof(u64))); + if (!data) + return -ENOMEM; + ops->get_ethtool_stats(dev, &stats, data); + } else { + data = NULL; + }

ret = -EFAULT; if (copy_to_user(useraddr, &stats, sizeof(stats))) @@ -2007,16 +2016,21 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) return -EFAULT;

stats.n_stats = n_stats; - data = vzalloc(array_size(n_stats, sizeof(u64))); - if (n_stats && !data) - return -ENOMEM;

- if (dev->phydev && !ops->get_ethtool_phy_stats) { - ret = phy_ethtool_get_stats(dev->phydev, &stats, data); - if (ret < 0) - return ret; + if (n_stats) { + data = vzalloc(array_size(n_stats, sizeof(u64))); + if (!data) + return -ENOMEM; + + if (dev->phydev && !ops->get_ethtool_phy_stats) { + ret = phy_ethtool_get_stats(dev->phydev, &stats, data); + if (ret < 0) + goto out; + } else { + ops->get_ethtool_phy_stats(dev, &stats, data); + } } else { - ops->get_ethtool_phy_stats(dev, &stats, data); + data = NULL; }

ret = -EFAULT;

[ Upstream commit e8b26b2135dedc0284490bfeac06dfc4418d0105 ]

Delete initialization of high order entries in mr cache to decrease initial memory footprint. When required, the administrator can populate the entries with memory keys via the /sys interface.

This approach is very helpful to significantly reduce the per HW function memory footprint in virtualization environments such as SRIOV.

Fixes: 9603b61de1ee ("mlx5: Move pci device handling from mlx5_ib to mlx5_core") Signed-off-by: Artemy Kovalyov artemyko@mellanox.com Signed-off-by: Moni Shoua monis@mellanox.com Signed-off-by: Leon Romanovsky leonro@mellanox.com Reported-by: Shalom Toledo shalomt@mellanox.com Acked-by: Or Gerlitz ogerlitz@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/mellanox/mlx5/core/main.c | 20 ------------------- 1 file changed, 20 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 563ce3fedab4..0e820cf92f8a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -162,26 +162,6 @@ static struct mlx5_profile profile[] = { .size = 8, .limit = 4 }, - .mr_cache[16] = { - .size = 8, - .limit = 4 - }, - .mr_cache[17] = { - .size = 8, - .limit = 4 - }, - .mr_cache[18] = { - .size = 8, - .limit = 4 - }, - .mr_cache[19] = { - .size = 4, - .limit = 2 - }, - .mr_cache[20] = { - .size = 4, - .limit = 2 - }, }, };

[ Upstream commit cb66ddd156203daefb8d71158036b27b0e2caf63 ]

When it is to cleanup net namespace, rds_tcp_exit_net() will call rds_tcp_kill_sock(), if t_sock is NULL, it will not call rds_conn_destroy(), rds_conn_path_destroy() and rds_tcp_conn_free() to free connection, and the worker cp_conn_w is not stopped, afterwards the net is freed in net_drop_ns(); While cp_conn_w rds_connect_worker() will call rds_tcp_conn_path_connect() and reference 'net' which has already been freed.

In rds_tcp_conn_path_connect(), rds_tcp_set_callbacks() will set t_sock = sock before sock->ops->connect, but if connect() is failed, it will call rds_tcp_restore_callbacks() and set t_sock = NULL, if connect is always failed, rds_connect_worker() will try to reconnect all the time, so rds_tcp_kill_sock() will never to cancel worker cp_conn_w and free the connections.

Therefore, the condition !tc->t_sock is not needed if it is going to do cleanup_net->rds_tcp_exit_net->rds_tcp_kill_sock, because tc->t_sock is always NULL, and there is on other path to cancel cp_conn_w and free connection. So this patch is to fix this.

rds_tcp_kill_sock(): ... if (net != c_net || !tc->t_sock) ... Acked-by: Santosh Shilimkar santosh.shilimkar@oracle.com

================================================================== BUG: KASAN: use-after-free in inet_create+0xbcc/0xd28 net/ipv4/af_inet.c:340 Read of size 4 at addr ffff8003496a4684 by task kworker/u8:4/3721

CPU: 3 PID: 3721 Comm: kworker/u8:4 Not tainted 5.1.0 #11 Hardware name: linux,dummy-virt (DT) Workqueue: krdsd rds_connect_worker Call trace: dump_backtrace+0x0/0x3c0 arch/arm64/kernel/time.c:53 show_stack+0x28/0x38 arch/arm64/kernel/traps.c:152 __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x120/0x188 lib/dump_stack.c:113 print_address_description+0x68/0x278 mm/kasan/report.c:253 kasan_report_error mm/kasan/report.c:351 [inline] kasan_report+0x21c/0x348 mm/kasan/report.c:409 __asan_report_load4_noabort+0x30/0x40 mm/kasan/report.c:429 inet_create+0xbcc/0xd28 net/ipv4/af_inet.c:340 __sock_create+0x4f8/0x770 net/socket.c:1276 sock_create_kern+0x50/0x68 net/socket.c:1322 rds_tcp_conn_path_connect+0x2b4/0x690 net/rds/tcp_connect.c:114 rds_connect_worker+0x108/0x1d0 net/rds/threads.c:175 process_one_work+0x6e8/0x1700 kernel/workqueue.c:2153 worker_thread+0x3b0/0xdd0 kernel/workqueue.c:2296 kthread+0x2f0/0x378 kernel/kthread.c:255 ret_from_fork+0x10/0x18 arch/arm64/kernel/entry.S:1117

Allocated by task 687: save_stack mm/kasan/kasan.c:448 [inline] set_track mm/kasan/kasan.c:460 [inline] kasan_kmalloc+0xd4/0x180 mm/kasan/kasan.c:553 kasan_slab_alloc+0x14/0x20 mm/kasan/kasan.c:490 slab_post_alloc_hook mm/slab.h:444 [inline] slab_alloc_node mm/slub.c:2705 [inline] slab_alloc mm/slub.c:2713 [inline] kmem_cache_alloc+0x14c/0x388 mm/slub.c:2718 kmem_cache_zalloc include/linux/slab.h:697 [inline] net_alloc net/core/net_namespace.c:384 [inline] copy_net_ns+0xc4/0x2d0 net/core/net_namespace.c:424 create_new_namespaces+0x300/0x658 kernel/nsproxy.c:107 unshare_nsproxy_namespaces+0xa0/0x198 kernel/nsproxy.c:206 ksys_unshare+0x340/0x628 kernel/fork.c:2577 __do_sys_unshare kernel/fork.c:2645 [inline] __se_sys_unshare kernel/fork.c:2643 [inline] __arm64_sys_unshare+0x38/0x58 kernel/fork.c:2643 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall arch/arm64/kernel/syscall.c:47 [inline] el0_svc_common+0x168/0x390 arch/arm64/kernel/syscall.c:83 el0_svc_handler+0x60/0xd0 arch/arm64/kernel/syscall.c:129 el0_svc+0x8/0xc arch/arm64/kernel/entry.S:960

Freed by task 264: save_stack mm/kasan/kasan.c:448 [inline] set_track mm/kasan/kasan.c:460 [inline] __kasan_slab_free+0x114/0x220 mm/kasan/kasan.c:521 kasan_slab_free+0x10/0x18 mm/kasan/kasan.c:528 slab_free_hook mm/slub.c:1370 [inline] slab_free_freelist_hook mm/slub.c:1397 [inline] slab_free mm/slub.c:2952 [inline] kmem_cache_free+0xb8/0x3a8 mm/slub.c:2968 net_free net/core/net_namespace.c:400 [inline] net_drop_ns.part.6+0x78/0x90 net/core/net_namespace.c:407 net_drop_ns net/core/net_namespace.c:406 [inline] cleanup_net+0x53c/0x6d8 net/core/net_namespace.c:569 process_one_work+0x6e8/0x1700 kernel/workqueue.c:2153 worker_thread+0x3b0/0xdd0 kernel/workqueue.c:2296 kthread+0x2f0/0x378 kernel/kthread.c:255 ret_from_fork+0x10/0x18 arch/arm64/kernel/entry.S:1117

The buggy address belongs to the object at ffff8003496a3f80 which belongs to the cache net_namespace of size 7872 The buggy address is located 1796 bytes inside of 7872-byte region [ffff8003496a3f80, ffff8003496a5e40) The buggy address belongs to the page: page:ffff7e000d25a800 count:1 mapcount:0 mapping:ffff80036ce4b000 index:0x0 compound_mapcount: 0 flags: 0xffffe0000008100(slab|head) raw: 0ffffe0000008100 dead000000000100 dead000000000200 ffff80036ce4b000 raw: 0000000000000000 0000000080040004 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected

Memory state around the buggy address: ffff8003496a4580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8003496a4600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

ffff8003496a4680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

^ ffff8003496a4700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8003496a4780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ==================================================================

Fixes: 467fa15356ac("RDS-TCP: Support multiple RDS-TCP listen endpoints, one per netns.") Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Mao Wenan maowenan@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/rds/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/tcp.c b/net/rds/tcp.c index b9bbcf3d6c63..18bb522df282 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -600,7 +600,7 @@ static void rds_tcp_kill_sock(struct net *net) list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) { struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);

- if (net != c_net || !tc->t_sock) + if (net != c_net) continue; if (!list_has_conn(&tmp_list, tc->t_cpath->cp_conn)) { list_move_tail(&tc->t_tcp_node, &tmp_list);

[ Upstream commit 0db6f8befc32c68bb13d7ffbb2e563c79e913e13 ]

It returned always NULL, thus it was never possible to get the filter.

Example: $ ip link add foo type dummy $ ip link add bar type dummy $ tc qdisc add dev foo clsact $ tc filter add dev foo protocol all pref 1 ingress handle 1234 \ matchall action mirred ingress mirror dev bar

Before the patch: $ tc filter get dev foo protocol all pref 1 ingress handle 1234 matchall Error: Specified filter handle not found. We have an error talking to the kernel

After: $ tc filter get dev foo protocol all pref 1 ingress handle 1234 matchall filter ingress protocol all pref 1 matchall chain 0 handle 0x4d2 not_in_hw action order 1: mirred (Ingress Mirror to device bar) pipe index 1 ref 1 bind 1

CC: Yotam Gigi yotamg@mellanox.com CC: Jiri Pirko jiri@mellanox.com Fixes: fd62d9f5c575 ("net/sched: matchall: Fix configuration race") Signed-off-by: Nicolas Dichtel nicolas.dichtel@6wind.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/cls_matchall.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 856fa79d4ffd..621bc1d5b057 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -126,6 +126,11 @@ static void mall_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)

static void *mall_get(struct tcf_proto *tp, u32 handle) { + struct cls_mall_head *head = rtnl_dereference(tp->root); + + if (head && head->handle == handle) + return head; + return NULL; }

[ Upstream commit 6289d0facd9ebce4cc83e5da39e15643ee998dc5 ]

This is a Qualcomm based device with a QMI function on interface 4. It is mode switched from 2020:2030 using a standard eject message.

T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 6 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=2020 ProdID=2031 Rev= 2.32 S: Manufacturer=Mobile Connect S: Product=Mobile Connect S: SerialNumber=0123456789ABCDEF C:* #Ifs= 6 Cfg#= 1 Atr=80 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) E: Ad=89(I) Atr=03(Int.) MxPS= 8 Ivl=32ms E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=(none) E: Ad=8a(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=125us

Signed-off-by: Bjørn Mork bjorn@mork.no Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 74bebbdb4b15..9195f3476b1d 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1203,6 +1203,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x19d2, 0x2002, 4)}, /* ZTE (Vodafone) K3765-Z */ {QMI_FIXED_INTF(0x2001, 0x7e19, 4)}, /* D-Link DWM-221 B1 */ {QMI_FIXED_INTF(0x2001, 0x7e35, 4)}, /* D-Link DWM-222 */ + {QMI_FIXED_INTF(0x2020, 0x2031, 4)}, /* Olicard 600 */ {QMI_FIXED_INTF(0x2020, 0x2033, 4)}, /* BroadMobi BM806U */ {QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */ {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */

[ Upstream commit 09279e615c81ce55e04835970601ae286e3facbe ]

Syzbot report a kernel-infoleak:

BUG: KMSAN: kernel-infoleak in _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32 Call Trace: _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32 copy_to_user include/linux/uaccess.h:174 [inline] sctp_getsockopt_peer_addrs net/sctp/socket.c:5911 [inline] sctp_getsockopt+0x1668e/0x17f70 net/sctp/socket.c:7562 ... Uninit was stored to memory at: sctp_transport_init net/sctp/transport.c:61 [inline] sctp_transport_new+0x16d/0x9a0 net/sctp/transport.c:115 sctp_assoc_add_peer+0x532/0x1f70 net/sctp/associola.c:637 sctp_process_param net/sctp/sm_make_chunk.c:2548 [inline] sctp_process_init+0x1a1b/0x3ed0 net/sctp/sm_make_chunk.c:2361 ... Bytes 8-15 of 16 are uninitialized

It was caused by that th _pad field (the 8-15 bytes) of a v4 addr (saved in struct sockaddr_in) wasn't initialized, but directly copied to user memory in sctp_getsockopt_peer_addrs().

So fix it by calling memset(addr->v4.sin_zero, 0, 8) to initialize _pad of sockaddr_in before copying it to user memory in sctp_v4_addr_to_user(), as sctp_v6_addr_to_user() does.

Reported-by: syzbot+86b5c7c236a22616a72f@syzkaller.appspotmail.com Signed-off-by: Xin Long lucien.xin@gmail.com Tested-by: Alexander Potapenko glider@google.com Acked-by: Neil Horman nhorman@tuxdriver.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sctp/protocol.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 1c9f079e8a50..d97b2b4b7a8b 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -600,6 +600,7 @@ static struct sock *sctp_v4_create_accept_sk(struct sock *sk, static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr) { /* No address mapping for V4 sockets */ + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); return sizeof(struct sockaddr_in); }

[ Upstream commit b506bc975f60f06e13e74adb35e708a23dc4e87c ]

When tcp_sk_init() failed in inet_ctl_sock_create(), 'net->ipv4.tcp_congestion_control' will be left uninitialized, but tcp_sk_exit() hasn't check for that.

This patch add checking on 'net->ipv4.tcp_congestion_control' in tcp_sk_exit() to prevent NULL-ptr dereference.

Fixes: 6670e1524477 ("tcp: Namespace-ify sysctl_tcp_default_congestion_control") Signed-off-by: Dust Li dust.li@linux.alibaba.com Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_ipv4.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 30fdf891940b..11101cf8693b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2490,7 +2490,8 @@ static void __net_exit tcp_sk_exit(struct net *net) { int cpu;

- module_put(net->ipv4.tcp_congestion_control->owner); + if (net->ipv4.tcp_congestion_control) + module_put(net->ipv4.tcp_congestion_control->owner);

for_each_possible_cpu(cpu) inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));

[ Upstream commit bc87a0036826a37b43489b029af8143bd07c6cca ]

Previously, a false positive would be caught if the TIRs list is empty, since the err value was initialized to -ENOMEM, and was only updated if a TIR is refreshed. This is resolved by initializing the err value to zero.

Fixes: b676f653896a ("net/mlx5e: Refactor refresh TIRs") Signed-off-by: Gavi Teitz gavi@mellanox.com Reviewed-by: Roi Dayan roid@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index db3278cc052b..1e28866e3924 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -141,15 +141,17 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb) { struct mlx5_core_dev *mdev = priv->mdev; struct mlx5e_tir *tir; - int err = -ENOMEM; + int err = 0; u32 tirn = 0; int inlen; void *in;

inlen = MLX5_ST_SZ_BYTES(modify_tir_in); in = kvzalloc(inlen, GFP_KERNEL); - if (!in) + if (!in) { + err = -ENOMEM; goto out; + }

if (enable_uc_lb) MLX5_SET(modify_tir_in, in, ctx.self_lb_block,

[ Upstream commit c8ba5b91a04e3e2643e48501c114108802f21cda ]

dev_queue_xmit() may return error codes as well as netdev_tx_t, and it always consumes the skb. Make sure we always return a correct netdev_tx_t value.

Fixes: eadfa4c3be99 ("nfp: add stats and xmit helpers for representors") Signed-off-by: Jakub Kicinski jakub.kicinski@netronome.com Reviewed-by: John Hurley john.hurley@netronome.com Reviewed-by: Simon Horman simon.horman@netronome.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index 18a09cdcd9c6..e0d73b385563 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -225,7 +225,7 @@ static netdev_tx_t nfp_repr_xmit(struct sk_buff *skb, struct net_device *netdev) ret = dev_queue_xmit(skb); nfp_repr_inc_tx_stats(netdev, len, ret);

- return ret; + return NETDEV_TX_OK; }

static int nfp_repr_stop(struct net_device *netdev)

[ Upstream commit a1b0e4e684e9c300b9e759b46cb7a0147e61ddff ]

There is logic to check that the RX/TPA consumer index is the expected index to work around a hardware problem. However, the potentially bad consumer index is first used to index into an array to reference an entry. This can potentially crash if the bad consumer index is beyond legal range. Improve the logic to use the consumer index for dereferencing after the validity check and log an error message.

Fixes: fa7e28127a5a ("bnxt_en: Add workaround to detect bad opaque in rx completion (part 2)") Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 0bd93bb7d1a2..a8abb47178be 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1092,6 +1092,8 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, tpa_info = &rxr->rx_tpa[agg_id];

if (unlikely(cons != rxr->rx_next_cons)) { + netdev_warn(bp->dev, "TPA cons %x != expected cons %x\n", + cons, rxr->rx_next_cons); bnxt_sched_reset(bp, rxr); return; } @@ -1544,15 +1546,17 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons, }

cons = rxcmp->rx_cmp_opaque; - rx_buf = &rxr->rx_buf_ring[cons]; - data = rx_buf->data; - data_ptr = rx_buf->data_ptr; if (unlikely(cons != rxr->rx_next_cons)) { int rc1 = bnxt_discard_rx(bp, bnapi, raw_cons, rxcmp);

+ netdev_warn(bp->dev, "RX cons %x != expected cons %x\n", + cons, rxr->rx_next_cons); bnxt_sched_reset(bp, rxr); return rc1; } + rx_buf = &rxr->rx_buf_ring[cons]; + data = rx_buf->data; + data_ptr = rx_buf->data_ptr; prefetch(data_ptr);

misc = le32_to_cpu(rxcmp->rx_cmp_misc_v1);

[ Upstream commit 492b67e28ee5f2a2522fb72e3d3bcb990e461514 ]

erspan tunnels run __iptunnel_pull_header on received skbs to remove gre and erspan headers. This can determine a possible use-after-free accessing pkt_md pointer in erspan_rcv since the packet will be 'uncloned' running pskb_expand_head if it is a cloned gso skb (e.g if the packet has been sent though a veth device). Fix it resetting pkt_md pointer after __iptunnel_pull_header

Fixes: 1d7e2ed22f8d ("net: erspan: refactor existing erspan code") Signed-off-by: Lorenzo Bianconi lorenzo.bianconi@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/ip_gre.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index f199945f6e4a..3c734832bb7c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -260,7 +260,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct net *net = dev_net(skb->dev); struct metadata_dst *tun_dst = NULL; struct erspan_base_hdr *ershdr; - struct erspan_metadata *pkt_md; struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; const struct iphdr *iph; @@ -283,9 +282,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (unlikely(!pskb_may_pull(skb, len))) return PACKET_REJECT;

- ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); - pkt_md = (struct erspan_metadata *)(ershdr + 1); - if (__iptunnel_pull_header(skb, len, htons(ETH_P_TEB), @@ -293,8 +289,9 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, goto drop;

if (tunnel->collect_md) { + struct erspan_metadata *pkt_md, *md; struct ip_tunnel_info *info; - struct erspan_metadata *md; + unsigned char *gh; __be64 tun_id; __be16 flags;

@@ -307,6 +304,14 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (!tun_dst) return PACKET_REJECT;

+ /* skb can be uncloned in __iptunnel_pull_header, so + * old pkt_md is no longer valid and we need to reset + * it + */ + gh = skb_network_header(skb) + + skb_network_header_len(skb); + pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len + + sizeof(*ershdr)); md = ip_tunnel_info_opts(&tun_dst->u.tun_info); md->version = ver; md2 = &md->u.md2;

[ Upstream commit 9a5a90d167b0e5fe3d47af16b68fd09ce64085cd ]

__netif_receive_skb_list_ptype() leaves skb->next poisoned before passing it to pt_prev->func handler, what may produce (in certain cases, e.g. DSA setup) crashes like:

[ 88.606777] CPU 0 Unable to handle kernel paging request at virtual address 0000000e, epc == 80687078, ra == 8052cc7c [ 88.618666] Oops[#1]: [ 88.621196] CPU: 0 PID: 0 Comm: swapper Not tainted 5.1.0-rc2-dlink-00206-g4192a172-dirty #1473 [ 88.630885] $ 0 : 00000000 10000400 00000002 864d7850 [ 88.636709] $ 4 : 87c0ddf0 864d7800 87c0ddf0 00000000 [ 88.642526] $ 8 : 00000000 49600000 00000001 00000001 [ 88.648342] $12 : 00000000 c288617b dadbee27 25d17c41 [ 88.654159] $16 : 87c0ddf0 85cff080 80790000 fffffffd [ 88.659975] $20 : 80797b20 ffffffff 00000001 864d7800 [ 88.665793] $24 : 00000000 8011e658 [ 88.671609] $28 : 80790000 87c0dbc0 87cabf00 8052cc7c [ 88.677427] Hi : 00000003 [ 88.680622] Lo : 7b5b4220 [ 88.683840] epc : 80687078 vlan_dev_hard_start_xmit+0x1c/0x1a0 [ 88.690532] ra : 8052cc7c dev_hard_start_xmit+0xac/0x188 [ 88.696734] Status: 10000404 IEp [ 88.700422] Cause : 50000008 (ExcCode 02) [ 88.704874] BadVA : 0000000e [ 88.708069] PrId : 0001a120 (MIPS interAptiv (multi)) [ 88.713005] Modules linked in: [ 88.716407] Process swapper (pid: 0, threadinfo=(ptrval), task=(ptrval), tls=00000000) [ 88.725219] Stack : 85f61c28 00000000 0000000e 80780000 87c0ddf0 85cff080 80790000 8052cc7c [ 88.734529] 87cabf00 00000000 00000001 85f5fb40 807b0000 864d7850 87cabf00 807d0000 [ 88.743839] 864d7800 8655f600 00000000 85cff080 87c1c000 0000006a 00000000 8052d96c [ 88.753149] 807a0000 8057adb8 87c0dcc8 87c0dc50 85cfff08 00000558 87cabf00 85f58c50 [ 88.762460] 00000002 85f58c00 864d7800 80543308 fffffff4 00000001 85f58c00 864d7800 [ 88.771770] ... [ 88.774483] Call Trace: [ 88.777199] [<80687078>] vlan_dev_hard_start_xmit+0x1c/0x1a0 [ 88.783504] [<8052cc7c>] dev_hard_start_xmit+0xac/0x188 [ 88.789326] [<8052d96c>] __dev_queue_xmit+0x6e8/0x7d4 [ 88.794955] [<805a8640>] ip_finish_output2+0x238/0x4d0 [ 88.800677] [<805ab6a0>] ip_output+0xc8/0x140 [ 88.805526] [<805a68f4>] ip_forward+0x364/0x560 [ 88.810567] [<805a4ff8>] ip_rcv+0x48/0xe4 [ 88.815030] [<80528d44>] __netif_receive_skb_one_core+0x44/0x58 [ 88.821635] [<8067f220>] dsa_switch_rcv+0x108/0x1ac [ 88.827067] [<80528f80>] __netif_receive_skb_list_core+0x228/0x26c [ 88.833951] [<8052ed84>] netif_receive_skb_list+0x1d4/0x394 [ 88.840160] [<80355a88>] lunar_rx_poll+0x38c/0x828 [ 88.845496] [<8052fa78>] net_rx_action+0x14c/0x3cc [ 88.850835] [<806ad300>] __do_softirq+0x178/0x338 [ 88.856077] [<8012a2d4>] irq_exit+0xbc/0x100 [ 88.860846] [<802f8b70>] plat_irq_dispatch+0xc0/0x144 [ 88.866477] [<80105974>] handle_int+0x14c/0x158 [ 88.871516] [<806acfb0>] r4k_wait+0x30/0x40 [ 88.876462] Code: afb10014 8c8200a0 00803025 <9443000c> 94a20468 00000000 10620042 00a08025 9605046a [ 88.887332] [ 88.888982] ---[ end trace eb863d007da11cf1 ]--- [ 88.894122] Kernel panic - not syncing: Fatal exception in interrupt [ 88.901202] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

Fix this by pulling skb off the sublist and zeroing skb->next pointer before calling ptype callback.

Fixes: 88eb1944e18c ("net: core: propagate SKB lists through packet_type lookup") Reviewed-by: Edward Cree ecree@solarflare.com Signed-off-by: Alexander Lobakin alobakin@dlink.ru Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/dev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c index 5c8c0a572ee9..d47554307a6d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4959,8 +4959,10 @@ static inline void __netif_receive_skb_list_ptype(struct list_head *head, if (pt_prev->list_func != NULL) pt_prev->list_func(head, pt_prev, orig_dev); else - list_for_each_entry_safe(skb, next, head, list) + list_for_each_entry_safe(skb, next, head, list) { + skb_list_del_init(skb); pt_prev->func(skb, skb->dev, pt_prev, orig_dev); + } }

static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc)

[ Upstream commit 8e949363f017e2011464812a714fb29710fb95b4 ]

idr_find() can return a NULL value to 'flow' which is used without a check. The patch adds a check to avoid potential NULL pointer dereference.

In case of mlx5_fpga_sbu_conn_sendmsg() failure, free buf allocated using kzalloc.

Fixes: ab412e1dd7db ("net/mlx5: Accel, add TLS rx offload routines") Signed-off-by: Aditya Pakki pakki001@umn.edu Reviewed-by: Yuval Shaia yuval.shaia@oracle.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c index 5cf5f2a9d51f..8de64e88c670 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c @@ -217,15 +217,21 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq, void *cmd; int ret;

+ rcu_read_lock(); + flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle)); + rcu_read_unlock(); + + if (!flow) { + WARN_ONCE(1, "Received NULL pointer for handle\n"); + return -EINVAL; + } + buf = kzalloc(size, GFP_ATOMIC); if (!buf) return -ENOMEM;

cmd = (buf + 1);

- rcu_read_lock(); - flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle)); - rcu_read_unlock(); mlx5_fpga_tls_flow_to_cmd(flow, cmd);

MLX5_SET(tls_cmd, cmd, swid, ntohl(handle)); @@ -238,6 +244,8 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq, buf->complete = mlx_tls_kfree_complete;

ret = mlx5_fpga_sbu_conn_sendmsg(mdev->fpga->tls->conn, buf); + if (ret < 0) + kfree(buf);

return ret; }

[ Upstream commit e28408e98bced123038857b6e3c81fa12a2e3e68 ]

Set xon = xoff - netdev's max_mtu. netdev's max_mtu will give enough time for the pause frame to arrive at the sender.

Fixes: 0696d60853d5 ("net/mlx5e: Receive buffer configuration") Signed-off-by: Huy Nguyen huyn@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../mellanox/mlx5/core/en/port_buffer.c | 28 +++++++++++-------- 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index f00de0c987cd..4ab0d030b544 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -143,7 +143,7 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu) }

static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, - u32 xoff, unsigned int mtu) + u32 xoff, unsigned int max_mtu) { int i;

@@ -155,11 +155,12 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, }

if (port_buffer->buffer[i].size < - (xoff + mtu + (1 << MLX5E_BUFFER_CELL_SHIFT))) + (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT))) return -ENOMEM;

port_buffer->buffer[i].xoff = port_buffer->buffer[i].size - xoff; - port_buffer->buffer[i].xon = port_buffer->buffer[i].xoff - mtu; + port_buffer->buffer[i].xon = + port_buffer->buffer[i].xoff - max_mtu; }

return 0; @@ -167,7 +168,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,

/** * update_buffer_lossy() - * mtu: device's MTU + * max_mtu: netdev's max_mtu * pfc_en: <input> current pfc configuration * buffer: <input> current prio to buffer mapping * xoff: <input> xoff value @@ -184,7 +185,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, * Return 0 if no error. * Set change to true if buffer configuration is modified. */ -static int update_buffer_lossy(unsigned int mtu, +static int update_buffer_lossy(unsigned int max_mtu, u8 pfc_en, u8 *buffer, u32 xoff, struct mlx5e_port_buffer *port_buffer, bool *change) @@ -221,7 +222,7 @@ static int update_buffer_lossy(unsigned int mtu, }

if (changed) { - err = update_xoff_threshold(port_buffer, xoff, mtu); + err = update_xoff_threshold(port_buffer, xoff, max_mtu); if (err) return err;

@@ -231,6 +232,7 @@ static int update_buffer_lossy(unsigned int mtu, return 0; }

+#define MINIMUM_MAX_MTU 9216 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, u32 change, unsigned int mtu, struct ieee_pfc *pfc, @@ -242,12 +244,14 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, bool update_prio2buffer = false; u8 buffer[MLX5E_MAX_PRIORITY]; bool update_buffer = false; + unsigned int max_mtu; u32 total_used = 0; u8 curr_pfc_en; int err; int i;

mlx5e_dbg(HW, priv, "%s: change=%x\n", __func__, change); + max_mtu = max_t(unsigned int, priv->netdev->max_mtu, MINIMUM_MAX_MTU);

err = mlx5e_port_query_buffer(priv, &port_buffer); if (err) @@ -255,7 +259,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,

if (change & MLX5E_PORT_BUFFER_CABLE_LEN) { update_buffer = true; - err = update_xoff_threshold(&port_buffer, xoff, mtu); + err = update_xoff_threshold(&port_buffer, xoff, max_mtu); if (err) return err; } @@ -265,7 +269,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (err) return err;

- err = update_buffer_lossy(mtu, pfc->pfc_en, buffer, xoff, + err = update_buffer_lossy(max_mtu, pfc->pfc_en, buffer, xoff, &port_buffer, &update_buffer); if (err) return err; @@ -277,8 +281,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (err) return err;

- err = update_buffer_lossy(mtu, curr_pfc_en, prio2buffer, xoff, - &port_buffer, &update_buffer); + err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer, + xoff, &port_buffer, &update_buffer); if (err) return err; } @@ -302,7 +306,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, return -EINVAL;

update_buffer = true; - err = update_xoff_threshold(&port_buffer, xoff, mtu); + err = update_xoff_threshold(&port_buffer, xoff, max_mtu); if (err) return err; } @@ -310,7 +314,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, /* Need to update buffer configuration if xoff value is changed */ if (!update_buffer && xoff != priv->dcbx.xoff) { update_buffer = true; - err = update_xoff_threshold(&port_buffer, xoff, mtu); + err = update_xoff_threshold(&port_buffer, xoff, max_mtu); if (err) return err; }

commit ad15006cc78459d059af56729c4d9bed7c7fd860 upstream.

This causes an issue when trying to build with `make LD=ld.lld` if ld.lld and the rest of your cross tools aren't in the same directory (ex. /usr/local/bin) (as is the case for Android's build system), as the GCC_TOOLCHAIN_DIR then gets set based on `which $(LD)` which will point where LLVM tools are, not GCC/binutils tools are located.

Instead, select the GCC_TOOLCHAIN_DIR based on another tool provided by binutils for which LLVM does not provide a substitute for, such as elfedit.

Fixes: 785f11aa595b ("kbuild: Add better clang cross build support") Link: https://github.com/ClangBuiltLinux/linux/issues/341 Suggested-by: Nathan Chancellor natechancellor@gmail.com Reviewed-by: Nathan Chancellor natechancellor@gmail.com Tested-by: Nathan Chancellor natechancellor@gmail.com Signed-off-by: Nick Desaulniers ndesaulniers@google.com Signed-off-by: Masahiro Yamada yamada.masahiro@socionext.com Signed-off-by: Nathan Chancellor natechancellor@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile index 8fdfe0af5862..c07f25e2e11b 100644 --- a/Makefile +++ b/Makefile @@ -483,7 +483,7 @@ endif ifeq ($(cc-name),clang) ifneq ($(CROSS_COMPILE),) CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%)) -GCC_TOOLCHAIN_DIR := $(dir $(shell which $(LD))) +GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit)) CLANG_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR) GCC_TOOLCHAIN := $(realpath $(GCC_TOOLCHAIN_DIR)/..) endif

[ Upstream commit 5f074f3e192f10c9fade898b9b3b8812e3d83342 ]

A recent optimization in Clang (r355672) lowers comparisons of the return value of memcmp against zero to comparisons of the return value of bcmp against zero. This helps some platforms that implement bcmp more efficiently than memcmp. glibc simply aliases bcmp to memcmp, but an optimized implementation is in the works.

This results in linkage failures for all targets with Clang due to the undefined symbol. For now, just implement bcmp as a tailcail to memcmp to unbreak the build. This routine can be further optimized in the future.

Other ideas discussed:

* A weak alias was discussed, but breaks for architectures that define their own implementations of memcmp since aliases to declarations are not permitted (only definitions). Arch-specific memcmp implementations typically declare memcmp in C headers, but implement them in assembly.

* -ffreestanding also is used sporadically throughout the kernel.

* -fno-builtin-bcmp doesn't work when doing LTO.

Link: https://bugs.llvm.org/show_bug.cgi?id=41035 Link: https://code.woboq.org/userspace/glibc/string/memcmp.c.html#bcmp Link: https://github.com/llvm/llvm-project/commit/8e16d73346f8091461319a7dfc4ddd18... Link: https://github.com/ClangBuiltLinux/linux/issues/416 Link: http://lkml.kernel.org/r/20190313211335.165605-1-ndesaulniers@google.com Signed-off-by: Nick Desaulniers ndesaulniers@google.com Reported-by: Nathan Chancellor natechancellor@gmail.com Reported-by: Adhemerval Zanella adhemerval.zanella@linaro.org Suggested-by: Arnd Bergmann arnd@arndb.de Suggested-by: James Y Knight jyknight@google.com Suggested-by: Masahiro Yamada yamada.masahiro@socionext.com Suggested-by: Nathan Chancellor natechancellor@gmail.com Suggested-by: Rasmus Villemoes linux@rasmusvillemoes.dk Acked-by: Steven Rostedt (VMware) rostedt@goodmis.org Reviewed-by: Nathan Chancellor natechancellor@gmail.com Tested-by: Nathan Chancellor natechancellor@gmail.com Reviewed-by: Masahiro Yamada yamada.masahiro@socionext.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Cc: David Laight David.Laight@ACULAB.COM Cc: Rasmus Villemoes linux@rasmusvillemoes.dk Cc: Namhyung Kim namhyung@kernel.org Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Dan Williams dan.j.williams@intel.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/string.h | 3 +++ lib/string.c | 20 ++++++++++++++++++++ 2 files changed, 23 insertions(+)

diff --git a/include/linux/string.h b/include/linux/string.h index 4a5a0eb7df51..f58e1ef76572 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -143,6 +143,9 @@ extern void * memscan(void *,int,__kernel_size_t); #ifndef __HAVE_ARCH_MEMCMP extern int memcmp(const void *,const void *,__kernel_size_t); #endif +#ifndef __HAVE_ARCH_BCMP +extern int bcmp(const void *,const void *,__kernel_size_t); +#endif #ifndef __HAVE_ARCH_MEMCHR extern void * memchr(const void *,int,__kernel_size_t); #endif diff --git a/lib/string.c b/lib/string.c index 2c0900a5d51a..72125fd5b4a6 100644 --- a/lib/string.c +++ b/lib/string.c @@ -865,6 +865,26 @@ __visible int memcmp(const void *cs, const void *ct, size_t count) EXPORT_SYMBOL(memcmp); #endif

+#ifndef __HAVE_ARCH_BCMP +/** + * bcmp - returns 0 if and only if the buffers have identical contents. + * @a: pointer to first buffer. + * @b: pointer to second buffer. + * @len: size of buffers. + * + * The sign or magnitude of a non-zero return value has no particular + * meaning, and architectures may implement their own more efficient bcmp(). So + * while this particular implementation is a simple (tail) call to memcmp, do + * not rely on anything but whether the return value is zero or non-zero. + */ +#undef bcmp +int bcmp(const void *a, const void *b, size_t len) +{ + return memcmp(a, b, len); +} +EXPORT_SYMBOL(bcmp); +#endif + #ifndef __HAVE_ARCH_MEMSCAN /** * memscan - Find a character in an area of memory.

commit 8866df9264a34e675b4ee8a151db819b87cce2d3 upstream

Otherwise, we hit a NULL pointer deference since handlers always assume default timeout policy is passed.

netlink: 24 bytes leftover after parsing attributes in process `syz-executor2'. kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 9575 Comm: syz-executor1 Not tainted 4.19.0+ #312 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:icmp_timeout_obj_to_nlattr+0x77/0x170 net/netfilter/nf_conntrack_proto_icmp.c:297

Fixes: c779e849608a ("netfilter: conntrack: remove get_timeout() indirection") Reported-by: Eric Dumazet eric.dumazet@gmail.com Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Zubin Mithra zsm@chromium.org Signed-off-by: Sasha Levin (Microsoft) sashal@kernel.org --- net/netfilter/nfnetlink_cttimeout.c | 46 +++++++++++++++++++++++++---- 1 file changed, 40 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index a30f8ba4b89a..1dc4ea327cbe 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -392,7 +392,8 @@ err: static int cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, - const struct nf_conntrack_l4proto *l4proto) + const struct nf_conntrack_l4proto *l4proto, + const unsigned int *timeouts) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; @@ -421,7 +422,7 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, if (!nest_parms) goto nla_put_failure;

- ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, NULL); + ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, timeouts); if (ret < 0) goto nla_put_failure;

@@ -444,6 +445,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, struct netlink_ext_ack *extack) { const struct nf_conntrack_l4proto *l4proto; + unsigned int *timeouts = NULL; struct sk_buff *skb2; int ret, err; __u16 l3num; @@ -456,12 +458,44 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); l4proto = nf_ct_l4proto_find_get(l3num, l4num);

- /* This protocol is not supported, skip. */ - if (l4proto->l4proto != l4num) { - err = -EOPNOTSUPP; + err = -EOPNOTSUPP; + if (l4proto->l4proto != l4num) goto err; + + switch (l4proto->l4proto) { + case IPPROTO_ICMP: + timeouts = &net->ct.nf_ct_proto.icmp.timeout; + break; + case IPPROTO_TCP: + timeouts = net->ct.nf_ct_proto.tcp.timeouts; + break; + case IPPROTO_UDP: + timeouts = net->ct.nf_ct_proto.udp.timeouts; + break; + case IPPROTO_DCCP: +#ifdef CONFIG_NF_CT_PROTO_DCCP + timeouts = net->ct.nf_ct_proto.dccp.dccp_timeout; +#endif + break; + case IPPROTO_ICMPV6: + timeouts = &net->ct.nf_ct_proto.icmpv6.timeout; + break; + case IPPROTO_SCTP: +#ifdef CONFIG_NF_CT_PROTO_SCTP + timeouts = net->ct.nf_ct_proto.sctp.timeouts; +#endif + break; + case 255: + timeouts = &net->ct.nf_ct_proto.generic.timeout; + break; + default: + WARN_ON_ONCE(1); + break; }

+ if (!timeouts) + goto err; + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) { err = -ENOMEM; @@ -472,7 +506,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_DEFAULT_SET, - l4proto); + l4proto, timeouts); if (ret <= 0) { kfree_skb(skb2); err = -ENOMEM;

[ Upstream commit c8a43c18a97845e7f94ed7d181c11f41964976a2 ]

When KASLR is enabled (CONFIG_RANDOMIZE_BASE=y), the top 4K of kernel virtual address space may be mapped to physical addresses despite being reserved for ERR_PTR values.

Fix the randomization of the linear region so that we avoid mapping the last page of the virtual address space.

Cc: Ard Biesheuvel ard.biesheuvel@linaro.org Signed-off-by: liyueyi liyueyi@live.com [will: rewrote commit message; merged in suggestion from Ard] Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Sasha Levin (Microsoft) sashal@kernel.org --- arch/arm64/mm/init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 787e27964ab9..774c3e17c798 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -450,7 +450,7 @@ void __init arm64_memblock_init(void) * memory spans, randomize the linear region as well. */ if (memstart_offset_seed > 0 && range >= ARM64_MEMSTART_ALIGN) { - range = range / ARM64_MEMSTART_ALIGN + 1; + range /= ARM64_MEMSTART_ALIGN; memstart_addr -= ARM64_MEMSTART_ALIGN * ((range * memstart_offset_seed) >> 16); }

From: Greg Kroah-Hartman gregkh@linuxfoundation.org

commit 7c0cca7c847e6e019d67b7d793efbbe3b947d004 upstream.

By default, the kernel will automatically load the module of any line dicipline that is asked for. As this sometimes isn't the safest thing to do, provide a sysctl to disable this feature.

By default, we set this to 'y' as that is the historical way that Linux has worked, and we do not want to break working systems. But in the future, perhaps this can default to 'n' to prevent this functionality.

Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Reviewed-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/tty/Kconfig | 24 ++++++++++++++++++++++++ drivers/tty/tty_io.c | 3 +++ drivers/tty/tty_ldisc.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 74 insertions(+)

--- a/drivers/tty/Kconfig +++ b/drivers/tty/Kconfig @@ -441,4 +441,28 @@ config VCC depends on SUN_LDOMS help Support for Sun logical domain consoles. + +config LDISC_AUTOLOAD + bool "Automatically load TTY Line Disciplines" + default y + help + Historically the kernel has always automatically loaded any + line discipline that is in a kernel module when a user asks + for it to be loaded with the TIOCSETD ioctl, or through other + means. This is not always the best thing to do on systems + where you know you will not be using some of the more + "ancient" line disciplines, so prevent the kernel from doing + this unless the request is coming from a process with the + CAP_SYS_MODULE permissions. + + Say 'Y' here if you trust your userspace users to do the right + thing, or if you have only provided the line disciplines that + you know you will be using, or if you wish to continue to use + the traditional method of on-demand loading of these modules + by any user. + + This functionality can be changed at runtime with the + dev.tty.ldisc_autoload sysctl, this configuration option will + only set the default value of this functionality. + endif # TTY --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -512,6 +512,8 @@ static const struct file_operations hung static DEFINE_SPINLOCK(redirect_lock); static struct file *redirect;

+extern void tty_sysctl_init(void); + /** * tty_wakeup - request more data * @tty: terminal @@ -3340,6 +3342,7 @@ void console_sysfs_notify(void) */ int __init tty_init(void) { + tty_sysctl_init(); cdev_init(&tty_cdev, &tty_fops); if (cdev_add(&tty_cdev, MKDEV(TTYAUX_MAJOR, 0), 1) || register_chrdev_region(MKDEV(TTYAUX_MAJOR, 0), 1, "/dev/tty") < 0) --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -156,6 +156,13 @@ static void put_ldops(struct tty_ldisc_o * takes tty_ldiscs_lock to guard against ldisc races */

+#if defined(CONFIG_LDISC_AUTOLOAD) + #define INITIAL_AUTOLOAD_STATE 1 +#else + #define INITIAL_AUTOLOAD_STATE 0 +#endif +static int tty_ldisc_autoload = INITIAL_AUTOLOAD_STATE; + static struct tty_ldisc *tty_ldisc_get(struct tty_struct *tty, int disc) { struct tty_ldisc *ld; @@ -170,6 +177,8 @@ static struct tty_ldisc *tty_ldisc_get(s */ ldops = get_ldops(disc); if (IS_ERR(ldops)) { + if (!capable(CAP_SYS_MODULE) && !tty_ldisc_autoload) + return ERR_PTR(-EPERM); request_module("tty-ldisc-%d", disc); ldops = get_ldops(disc); if (IS_ERR(ldops)) @@ -829,3 +838,41 @@ void tty_ldisc_deinit(struct tty_struct tty_ldisc_put(tty->ldisc); tty->ldisc = NULL; } + +static int zero; +static int one = 1; +static struct ctl_table tty_table[] = { + { + .procname = "ldisc_autoload", + .data = &tty_ldisc_autoload, + .maxlen = sizeof(tty_ldisc_autoload), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &one, + }, + { } +}; + +static struct ctl_table tty_dir_table[] = { + { + .procname = "tty", + .mode = 0555, + .child = tty_table, + }, + { } +}; + +static struct ctl_table tty_root_table[] = { + { + .procname = "dev", + .mode = 0555, + .child = tty_dir_table, + }, + { } +}; + +void tty_sysctl_init(void) +{ + register_sysctl_table(tty_root_table); +}

From: Furquan Shaikh furquan@google.com

commit c8b1917c8987a6fa3695d479b4d60fbbbc3e537b upstream.

Commit 18996f2db918 ("ACPICA: Events: Stop unconditionally clearing ACPI IRQs during suspend/resume") was added to stop clearing event status bits unconditionally in the system-wide suspend and resume paths. This was done because of an issue with a laptop lid appaering to be closed even when it was used to wake up the system from suspend (see https://bugzilla.kernel.org/show_bug.cgi?id=196249), which happened because event status bits were cleared unconditionally on system resume. Though this change fixed the issue in the resume path, it introduced regressions in a few suspend paths.

First regression was reported and fixed in the S5 entry path by commit fa85015c0d95 ("ACPICA: Clear status of all events when entering S5"). Next regression was reported and fixed for all legacy sleep paths by commit f317c7dc12b7 ("ACPICA: Clear status of all events when entering sleep states"). However, there still is a suspend-to-idle regression, since suspend-to-idle does not follow the legacy sleep paths.

In the suspend-to-idle case, wakeup is enabled as part of device suspend. If the status bits of wakeup GPEs are set when they are enabled, it causes a premature system wakeup to occur.

To address that problem, partially revert commit 18996f2db918 to restore GPE status bits clearing before the GPE is enabled in acpi_ev_enable_gpe().

Fixes: 18996f2db918 ("ACPICA: Events: Stop unconditionally clearing ACPI IRQs during suspend/resume") Signed-off-by: Furquan Shaikh furquan@google.com Cc: 4.17+ stable@vger.kernel.org # 4.17+ [ rjw: Subject & changelog ] Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/acpi/acpica/evgpe.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/drivers/acpi/acpica/evgpe.c +++ b/drivers/acpi/acpica/evgpe.c @@ -81,8 +81,12 @@ acpi_status acpi_ev_enable_gpe(struct ac

ACPI_FUNCTION_TRACE(ev_enable_gpe);

- /* Enable the requested GPE */ + /* Clear the GPE status */ + status = acpi_hw_clear_gpe(gpe_event_info); + if (ACPI_FAILURE(status)) + return_ACPI_STATUS(status);

+ /* Enable the requested GPE */ status = acpi_hw_low_set_gpe(gpe_event_info, ACPI_GPE_ENABLE); return_ACPI_STATUS(status); }

From: Zubin Mithra zsm@chromium.org

commit 212ac181c158c09038c474ba68068be49caecebb upstream.

When ioctl calls are made with non-null-terminated userspace strings, strlcpy causes an OOB-read from within strlen. Fix by changing to use strscpy instead.

Signed-off-by: Zubin Mithra zsm@chromium.org Reviewed-by: Guenter Roeck groeck@chromium.org Cc: stable@vger.kernel.org Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/core/seq/seq_clientmgr.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1252,7 +1252,7 @@ static int snd_seq_ioctl_set_client_info

/* fill the info fields */ if (client_info->name[0]) - strlcpy(client->name, client_info->name, sizeof(client->name)); + strscpy(client->name, client_info->name, sizeof(client->name));

client->filter = client_info->filter; client->event_lost = client_info->event_lost; @@ -1530,7 +1530,7 @@ static int snd_seq_ioctl_create_queue(st /* set queue name */ if (!info->name[0]) snprintf(info->name, sizeof(info->name), "Queue-%d", q->queue); - strlcpy(q->name, info->name, sizeof(q->name)); + strscpy(q->name, info->name, sizeof(q->name)); snd_use_lock_free(&q->use_lock);

return 0; @@ -1592,7 +1592,7 @@ static int snd_seq_ioctl_set_queue_info( queuefree(q); return -EPERM; } - strlcpy(q->name, info->name, sizeof(q->name)); + strscpy(q->name, info->name, sizeof(q->name)); queuefree(q);

return 0;

From: Richard Sailer rs@tuxedocomputers.com

commit 80690a276f444a68a332136d98bfea1c338bc263 upstream.

This adds a SND_PCI_QUIRK(...) line for the Tuxedo XC 1509.

The Tuxedo XC 1509 and the System76 oryp5 are the same barebone notebooks manufactured by Clevo. To name the fixups both use after the actual underlying hardware, this patch also changes System76_orpy5 to clevo_pb51ed in 2 enum symbols and one function name, matching the other pci_quirk entries which are also named after the device ODM.

Fixes: 7f665b1c3283 ("ALSA: hda/realtek - Headset microphone and internal speaker support for System76 oryp5") Signed-off-by: Richard Sailer rs@tuxedocomputers.com Cc: stable@vger.kernel.org Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/pci/hda/patch_realtek.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -1864,8 +1864,8 @@ enum { ALC887_FIXUP_BASS_CHMAP, ALC1220_FIXUP_GB_DUAL_CODECS, ALC1220_FIXUP_CLEVO_P950, - ALC1220_FIXUP_SYSTEM76_ORYP5, - ALC1220_FIXUP_SYSTEM76_ORYP5_PINS, + ALC1220_FIXUP_CLEVO_PB51ED, + ALC1220_FIXUP_CLEVO_PB51ED_PINS, };

static void alc889_fixup_coef(struct hda_codec *codec, @@ -2070,7 +2070,7 @@ static void alc1220_fixup_clevo_p950(str static void alc_fixup_headset_mode_no_hp_mic(struct hda_codec *codec, const struct hda_fixup *fix, int action);

-static void alc1220_fixup_system76_oryp5(struct hda_codec *codec, +static void alc1220_fixup_clevo_pb51ed(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -2322,18 +2322,18 @@ static const struct hda_fixup alc882_fix .type = HDA_FIXUP_FUNC, .v.func = alc1220_fixup_clevo_p950, }, - [ALC1220_FIXUP_SYSTEM76_ORYP5] = { + [ALC1220_FIXUP_CLEVO_PB51ED] = { .type = HDA_FIXUP_FUNC, - .v.func = alc1220_fixup_system76_oryp5, + .v.func = alc1220_fixup_clevo_pb51ed, }, - [ALC1220_FIXUP_SYSTEM76_ORYP5_PINS] = { + [ALC1220_FIXUP_CLEVO_PB51ED_PINS] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { { 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */ {} }, .chained = true, - .chain_id = ALC1220_FIXUP_SYSTEM76_ORYP5, + .chain_id = ALC1220_FIXUP_CLEVO_PB51ED, }, };

@@ -2411,8 +2411,9 @@ static const struct snd_pci_quirk alc882 SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950), - SND_PCI_QUIRK(0x1558, 0x96e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_SYSTEM76_ORYP5_PINS), - SND_PCI_QUIRK(0x1558, 0x97e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_SYSTEM76_ORYP5_PINS), + SND_PCI_QUIRK(0x1558, 0x96e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x97e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x65d1, "Tuxedo Book XC1509", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD), SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", ALC882_FIXUP_LENOVO_Y530),

From: Aneesh Kumar K.V aneesh.kumar@linux.ibm.com

commit c6f3c5ee40c10bb65725047a220570f718507001 upstream.

With some architectures like ppc64, set_pmd_at() cannot cope with a situation where there is already some (different) valid entry present.

Use pmdp_set_access_flags() instead to modify the pfn which is built to deal with modifying existing PMD entries.

This is similar to commit cae85cb8add3 ("mm/memory.c: fix modifying of page protection by insert_pfn()")

We also do similar update w.r.t insert_pfn_pud eventhough ppc64 don't support pud pfn entries now.

Without this patch we also see the below message in kernel log "BUG: non-zero pgtables_bytes on freeing mm:"

Link: http://lkml.kernel.org/r/20190402115125.18803-1-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V aneesh.kumar@linux.ibm.com Reported-by: Chandan Rajendra chandan@linux.ibm.com Reviewed-by: Jan Kara jack@suse.cz Cc: Dan Williams dan.j.williams@intel.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- mm/huge_memory.c | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+)

--- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -734,6 +734,21 @@ static void insert_pfn_pmd(struct vm_are spinlock_t *ptl;

ptl = pmd_lock(mm, pmd); + if (!pmd_none(*pmd)) { + if (write) { + if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) { + WARN_ON_ONCE(!is_huge_zero_pmd(*pmd)); + goto out_unlock; + } + entry = pmd_mkyoung(*pmd); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + if (pmdp_set_access_flags(vma, addr, pmd, entry, 1)) + update_mmu_cache_pmd(vma, addr, pmd); + } + + goto out_unlock; + } + entry = pmd_mkhuge(pfn_t_pmd(pfn, prot)); if (pfn_t_devmap(pfn)) entry = pmd_mkdevmap(entry); @@ -745,11 +760,16 @@ static void insert_pfn_pmd(struct vm_are if (pgtable) { pgtable_trans_huge_deposit(mm, pmd, pgtable); mm_inc_nr_ptes(mm); + pgtable = NULL; }

set_pmd_at(mm, addr, pmd, entry); update_mmu_cache_pmd(vma, addr, pmd); + +out_unlock: spin_unlock(ptl); + if (pgtable) + pte_free(mm, pgtable); }

vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, @@ -800,6 +820,20 @@ static void insert_pfn_pud(struct vm_are spinlock_t *ptl;

ptl = pud_lock(mm, pud); + if (!pud_none(*pud)) { + if (write) { + if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) { + WARN_ON_ONCE(!is_huge_zero_pud(*pud)); + goto out_unlock; + } + entry = pud_mkyoung(*pud); + entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma); + if (pudp_set_access_flags(vma, addr, pud, entry, 1)) + update_mmu_cache_pud(vma, addr, pud); + } + goto out_unlock; + } + entry = pud_mkhuge(pfn_t_pud(pfn, prot)); if (pfn_t_devmap(pfn)) entry = pud_mkdevmap(entry); @@ -809,6 +843,8 @@ static void insert_pfn_pud(struct vm_are } set_pud_at(mm, addr, pud, entry); update_mmu_cache_pud(vma, addr, pud); + +out_unlock: spin_unlock(ptl); }

From: Helge Deller deller@gmx.de

commit d006e95b5561f708d0385e9677ffe2c46f2ae345 upstream.

While adding LASI support to QEMU, I noticed that the QEMU detection in the kernel happens much too late. For example, when a LASI chip is found by the kernel, it registers the LASI LED driver as well. But when we run on QEMU it makes sense to avoid spending unnecessary CPU cycles, so we need to access the running_on_QEMU flag earlier than before.

This patch now makes the QEMU detection the fist task of the Linux kernel by moving it to where the kernel enters the C-coding.

Fixes: 310d82784fb4 ("parisc: qemu idle sleep support") Signed-off-by: Helge Deller deller@gmx.de Cc: stable@vger.kernel.org # v4.14+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/parisc/kernel/process.c | 6 ------ arch/parisc/kernel/setup.c | 3 +++ 2 files changed, 3 insertions(+), 6 deletions(-)

--- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -210,12 +210,6 @@ void __cpuidle arch_cpu_idle(void)

static int __init parisc_idle_init(void) { - const char *marker; - - /* check QEMU/SeaBIOS marker in PAGE0 */ - marker = (char *) &PAGE0->pad0; - running_on_qemu = (memcmp(marker, "SeaBIOS", 8) == 0); - if (!running_on_qemu) cpu_idle_poll_ctrl(1);

--- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -399,6 +399,9 @@ void __init start_parisc(void) int ret, cpunum; struct pdc_coproc_cfg coproc_cfg;

+ /* check QEMU/SeaBIOS marker in PAGE0 */ + running_on_qemu = (memcmp(&PAGE0->pad0, "SeaBIOS", 8) == 0); + cpunum = smp_processor_id();

init_cpu_topology();

From: Sven Schnelle svens@stackframe.org

commit f324fa58327791b2696628b31480e7e21c745706 upstream.

When setting the instruction pointer on PA-RISC we also need to set the back of the instruction queue to the new offset, otherwise we will execute on instruction from the new location, and jumping back to the old location stored in iaoq_b.

Signed-off-by: Sven Schnelle svens@stackframe.org Signed-off-by: Helge Deller deller@gmx.de Fixes: 75ebedf1d263 ("parisc: Add HAVE_REGS_AND_STACK_ACCESS_API feature") Cc: stable@vger.kernel.org # 4.19+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/parisc/include/asm/ptrace.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/arch/parisc/include/asm/ptrace.h +++ b/arch/parisc/include/asm/ptrace.h @@ -28,7 +28,8 @@ static inline unsigned long regs_return_ static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { - regs->iaoq[0] = val; + regs->iaoq[0] = val; + regs->iaoq[1] = val + 4; }

/* Query offset/name of register from its name/offset */

From: Yan Zhao yan.y.zhao@intel.com

commit dade58ed5af6365ac50ff4259c2a0bf31219e285 upstream.

in workload creation routine, if any failure occurs, do not queue this workload for delivery. if this failure is fatal, enter into failsafe mode.

Fixes: 6d76303553ba ("drm/i915/gvt: Move common vGPU workload creation into scheduler.c") Cc: stable@vger.kernel.org #4.19+ Cc: zhenyuw@linux.intel.com Signed-off-by: Yan Zhao yan.y.zhao@intel.com Signed-off-by: Zhenyu Wang zhenyuw@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/gpu/drm/i915/gvt/scheduler.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -1389,8 +1389,9 @@ intel_vgpu_create_workload(struct intel_ intel_runtime_pm_put(dev_priv); }

- if (ret && (vgpu_is_vm_unhealthy(ret))) { - enter_failsafe_mode(vgpu, GVT_FAILSAFE_GUEST_ERR); + if (ret) { + if (vgpu_is_vm_unhealthy(ret)) + enter_failsafe_mode(vgpu, GVT_FAILSAFE_GUEST_ERR); intel_vgpu_destroy_workload(workload); return ERR_PTR(ret); }

From: David Rientjes rientjes@google.com

commit ede885ecb2cdf8a8dd5367702e3d964ec846a2d5 upstream.

get_num_contig_pages() could potentially overflow int so make its type consistent with its usage.

Reported-by: Cfir Cohen cfir@google.com Cc: stable@vger.kernel.org Signed-off-by: David Rientjes rientjes@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kvm/svm.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

--- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -6398,11 +6398,11 @@ e_free: return ret; }

-static int get_num_contig_pages(int idx, struct page **inpages, - unsigned long npages) +static unsigned long get_num_contig_pages(unsigned long idx, + struct page **inpages, unsigned long npages) { unsigned long paddr, next_paddr; - int i = idx + 1, pages = 1; + unsigned long i = idx + 1, pages = 1;

/* find the number of contiguous pages starting from idx */ paddr = __sme_page_pa(inpages[idx]); @@ -6421,12 +6421,12 @@ static int get_num_contig_pages(int idx,

static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) { - unsigned long vaddr, vaddr_end, next_vaddr, npages, size; + unsigned long vaddr, vaddr_end, next_vaddr, npages, pages, size, i; struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct kvm_sev_launch_update_data params; struct sev_data_launch_update_data *data; struct page **inpages; - int i, ret, pages; + int ret;

if (!sev_guest(kvm)) return -ENOTTY;

From: Greg Thelen gthelen@google.com

commit 0b3d6e6f2dd0a7b697b1aa8c167265908940624b upstream.

Since commit a983b5ebee57 ("mm: memcontrol: fix excessive complexity in memory.stat reporting") memcg dirty and writeback counters are managed as:

1) per-memcg per-cpu values in range of [-32..32]

2) per-memcg atomic counter

When a per-cpu counter cannot fit in [-32..32] it's flushed to the atomic. Stat readers only check the atomic. Thus readers such as balance_dirty_pages() may see a nontrivial error margin: 32 pages per cpu.

Assuming 100 cpus: 4k x86 page_size: 13 MiB error per memcg 64k ppc page_size: 200 MiB error per memcg

Considering that dirty+writeback are used together for some decisions the errors double.

This inaccuracy can lead to undeserved oom kills. One nasty case is when all per-cpu counters hold positive values offsetting an atomic negative value (i.e. per_cpu[*]=32, atomic=n_cpu*-32). balance_dirty_pages() only consults the atomic and does not consider throttling the next n_cpu*32 dirty pages. If the file_lru is in the 13..200 MiB range then there's absolutely no dirty throttling, which burdens vmscan with only dirty+writeback pages thus resorting to oom kill.

It could be argued that tiny containers are not supported, but it's more subtle. It's the amount the space available for file lru that matters. If a container has memory.max-200MiB of non reclaimable memory, then it will also suffer such oom kills on a 100 cpu machine.

The following test reliably ooms without this patch. This patch avoids oom kills.

$ cat test mount -t cgroup2 none /dev/cgroup cd /dev/cgroup echo +io +memory > cgroup.subtree_control mkdir test cd test echo 10M > memory.max (echo $BASHPID > cgroup.procs && exec /memcg-writeback-stress /foo) (echo $BASHPID > cgroup.procs && exec dd if=/dev/zero of=/foo bs=2M count=100)

$ cat memcg-writeback-stress.c /* * Dirty pages from all but one cpu. * Clean pages from the non dirtying cpu. * This is to stress per cpu counter imbalance. * On a 100 cpu machine: * - per memcg per cpu dirty count is 32 pages for each of 99 cpus * - per memcg atomic is -99*32 pages * - thus the complete dirty limit: sum of all counters 0 * - balance_dirty_pages() only sees atomic count -99*32 pages, which * it max()s to 0. * - So a workload can dirty -99*32 pages before balance_dirty_pages() * cares. */ #define _GNU_SOURCE #include <err.h> #include <fcntl.h> #include <sched.h> #include <stdlib.h> #include <stdio.h> #include <sys/stat.h> #include <sys/sysinfo.h> #include <sys/types.h> #include <unistd.h>

static char *buf; static int bufSize;

static void set_affinity(int cpu) { cpu_set_t affinity;

CPU_ZERO(&affinity); CPU_SET(cpu, &affinity); if (sched_setaffinity(0, sizeof(affinity), &affinity)) err(1, "sched_setaffinity"); }

static void dirty_on(int output_fd, int cpu) { int i, wrote;

set_affinity(cpu); for (i = 0; i < 32; i++) { for (wrote = 0; wrote < bufSize; ) { int ret = write(output_fd, buf+wrote, bufSize-wrote); if (ret == -1) err(1, "write"); wrote += ret; } } }

int main(int argc, char **argv) { int cpu, flush_cpu = 1, output_fd; const char *output;

if (argc != 2) errx(1, "usage: output_file");

output = argv[1]; bufSize = getpagesize(); buf = malloc(getpagesize()); if (buf == NULL) errx(1, "malloc failed");

output_fd = open(output, O_CREAT|O_RDWR); if (output_fd == -1) err(1, "open(%s)", output);

for (cpu = 0; cpu < get_nprocs(); cpu++) { if (cpu != flush_cpu) dirty_on(output_fd, cpu); }

set_affinity(flush_cpu); if (fsync(output_fd)) err(1, "fsync(%s)", output); if (close(output_fd)) err(1, "close(%s)", output); free(buf); }

Make balance_dirty_pages() and wb_over_bg_thresh() work harder to collect exact per memcg counters. This avoids the aforementioned oom kills.

This does not affect the overhead of memory.stat, which still reads the single atomic counter.

Why not use percpu_counter? memcg already handles cpus going offline, so no need for that overhead from percpu_counter. And the percpu_counter spinlocks are more heavyweight than is required.

It probably also makes sense to use exact dirty and writeback counters in memcg oom reports. But that is saved for later.

Link: http://lkml.kernel.org/r/20190329174609.164344-1-gthelen@google.com Signed-off-by: Greg Thelen gthelen@google.com Reviewed-by: Roman Gushchin guro@fb.com Acked-by: Johannes Weiner hannes@cmpxchg.org Cc: Michal Hocko mhocko@kernel.org Cc: Vladimir Davydov vdavydov.dev@gmail.com Cc: Tejun Heo tj@kernel.org Cc: stable@vger.kernel.org [4.16+] Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/linux/memcontrol.h | 5 ++++- mm/memcontrol.c | 20 ++++++++++++++++++-- 2 files changed, 22 insertions(+), 3 deletions(-)

--- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -559,7 +559,10 @@ struct mem_cgroup *lock_page_memcg(struc void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page);

-/* idx can be of type enum memcg_stat_item or node_stat_item */ +/* + * idx can be of type enum memcg_stat_item or node_stat_item. + * Keep in sync with memcg_exact_page_state(). + */ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3897,6 +3897,22 @@ struct wb_domain *mem_cgroup_wb_domain(s return &memcg->cgwb_domain; }

+/* + * idx can be of type enum memcg_stat_item or node_stat_item. + * Keep in sync with memcg_exact_page(). + */ +static unsigned long memcg_exact_page_state(struct mem_cgroup *memcg, int idx) +{ + long x = atomic_long_read(&memcg->stat[idx]); + int cpu; + + for_each_online_cpu(cpu) + x += per_cpu_ptr(memcg->stat_cpu, cpu)->count[idx]; + if (x < 0) + x = 0; + return x; +} + /** * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg * @wb: bdi_writeback in question @@ -3922,10 +3938,10 @@ void mem_cgroup_wb_stats(struct bdi_writ struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); struct mem_cgroup *parent;

- *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY); + *pdirty = memcg_exact_page_state(memcg, NR_FILE_DIRTY);

/* this should eventually include NR_UNSTABLE_NFS */ - *pwriteback = memcg_page_state(memcg, NR_WRITEBACK); + *pwriteback = memcg_exact_page_state(memcg, NR_WRITEBACK); *pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) | (1 << LRU_ACTIVE_FILE)); *pheadroom = PAGE_COUNTER_MAX;

From: S.j. Wang shengjiu.wang@nxp.com

commit 0ff4e8c61b794a4bf6c854ab071a1abaaa80f358 upstream.

There is very low possibility ( < 0.1% ) that channel swap happened in beginning when multi output/input pin is enabled. The issue is that hardware can't send data to correct pin in the beginning with the normal enable flow.

This is hardware issue, but there is no errata, the workaround flow is that: Each time playback/recording, firstly clear the xSMA/xSMB, then enable TE/RE, then enable xSMB and xSMA (xSMB must be enabled before xSMA). Which is to use the xSMA as the trigger start register, previously the xCR_TE or xCR_RE is the bit for starting.

Fixes commit 43d24e76b698 ("ASoC: fsl_esai: Add ESAI CPU DAI driver") Cc: stable@vger.kernel.org Reviewed-by: Fabio Estevam festevam@gmail.com Acked-by: Nicolin Chen nicoleotsuka@gmail.com Signed-off-by: Shengjiu Wang shengjiu.wang@nxp.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/soc/fsl/fsl_esai.c | 47 +++++++++++++++++++++++++++++++++++++---------- 1 file changed, 37 insertions(+), 10 deletions(-)

--- a/sound/soc/fsl/fsl_esai.c +++ b/sound/soc/fsl/fsl_esai.c @@ -54,6 +54,8 @@ struct fsl_esai { u32 fifo_depth; u32 slot_width; u32 slots; + u32 tx_mask; + u32 rx_mask; u32 hck_rate[2]; u32 sck_rate[2]; bool hck_dir[2]; @@ -361,21 +363,13 @@ static int fsl_esai_set_dai_tdm_slot(str regmap_update_bits(esai_priv->regmap, REG_ESAI_TCCR, ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots));

- regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMA, - ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(tx_mask)); - regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMB, - ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(tx_mask)); - regmap_update_bits(esai_priv->regmap, REG_ESAI_RCCR, ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots));

- regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMA, - ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(rx_mask)); - regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMB, - ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(rx_mask)); - esai_priv->slot_width = slot_width; esai_priv->slots = slots; + esai_priv->tx_mask = tx_mask; + esai_priv->rx_mask = rx_mask;

return 0; } @@ -596,6 +590,7 @@ static int fsl_esai_trigger(struct snd_p bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; u8 i, channels = substream->runtime->channels; u32 pins = DIV_ROUND_UP(channels, esai_priv->slots); + u32 mask;

switch (cmd) { case SNDRV_PCM_TRIGGER_START: @@ -608,15 +603,38 @@ static int fsl_esai_trigger(struct snd_p for (i = 0; tx && i < channels; i++) regmap_write(esai_priv->regmap, REG_ESAI_ETDR, 0x0);

+ /* + * When set the TE/RE in the end of enablement flow, there + * will be channel swap issue for multi data line case. + * In order to workaround this issue, we switch the bit + * enablement sequence to below sequence + * 1) clear the xSMB & xSMA: which is done in probe and + * stop state. + * 2) set TE/RE + * 3) set xSMB + * 4) set xSMA: xSMA is the last one in this flow, which + * will trigger esai to start. + */ regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx), tx ? ESAI_xCR_TE_MASK : ESAI_xCR_RE_MASK, tx ? ESAI_xCR_TE(pins) : ESAI_xCR_RE(pins)); + mask = tx ? esai_priv->tx_mask : esai_priv->rx_mask; + + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMB(tx), + ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(mask)); + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMA(tx), + ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(mask)); + break; case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx), tx ? ESAI_xCR_TE_MASK : ESAI_xCR_RE_MASK, 0); + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMA(tx), + ESAI_xSMA_xS_MASK, 0); + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMB(tx), + ESAI_xSMB_xS_MASK, 0);

/* Disable and reset FIFO */ regmap_update_bits(esai_priv->regmap, REG_ESAI_xFCR(tx), @@ -906,6 +924,15 @@ static int fsl_esai_probe(struct platfor return ret; }

+ esai_priv->tx_mask = 0xFFFFFFFF; + esai_priv->rx_mask = 0xFFFFFFFF; + + /* Clear the TSMA, TSMB, RSMA, RSMB */ + regmap_write(esai_priv->regmap, REG_ESAI_TSMA, 0); + regmap_write(esai_priv->regmap, REG_ESAI_TSMB, 0); + regmap_write(esai_priv->regmap, REG_ESAI_RSMA, 0); + regmap_write(esai_priv->regmap, REG_ESAI_RSMB, 0); + ret = devm_snd_soc_register_component(&pdev->dev, &fsl_esai_component, &fsl_esai_dai, 1); if (ret) {

From: Anand Jain anand.jain@oracle.com

commit 50398fde997f6be8faebdb5f38e9c9c467370f51 upstream.

We let pass zstd compression parameter even if it is not fully valid. For example:

$ btrfs prop set /btrfs compression zst $ btrfs prop get /btrfs compression compression=zst

zlib and lzo are fine.

Fix it by checking the correct prefix length.

Fixes: 5c1aab1dd544 ("btrfs: Add zstd support") CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Nikolay Borisov nborisov@suse.com Signed-off-by: Anand Jain anand.jain@oracle.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/btrfs/props.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -396,7 +396,7 @@ static int prop_compression_apply(struct btrfs_set_fs_incompat(fs_info, COMPRESS_LZO); } else if (!strncmp("zlib", value, 4)) { type = BTRFS_COMPRESS_ZLIB; - } else if (!strncmp("zstd", value, len)) { + } else if (!strncmp("zstd", value, 4)) { type = BTRFS_COMPRESS_ZSTD; btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD); } else {

From: Dmitry V. Levin ldv@altlinux.org

commit 10a16997db3d99fc02c026cf2c6e6c670acafab0 upstream.

RISC-V syscall arguments are located in orig_a0,a1..a5 fields of struct pt_regs.

Due to an off-by-one bug and a bug in pointer arithmetic syscall_get_arguments() was reading s3..s7 fields instead of a1..a5. Likewise, syscall_set_arguments() was writing s3..s7 fields instead of a1..a5.

Link: http://lkml.kernel.org/r/20190329171221.GA32456@altlinux.org

Fixes: e2c0cdfba7f69 ("RISC-V: User-facing API") Cc: Ingo Molnar mingo@redhat.com Cc: Kees Cook keescook@chromium.org Cc: Andy Lutomirski luto@amacapital.net Cc: Will Drewry wad@chromium.org Cc: Albert Ou aou@eecs.berkeley.edu Cc: linux-riscv@lists.infradead.org Cc: stable@vger.kernel.org # v4.15+ Acked-by: Palmer Dabbelt palmer@sifive.com Signed-off-by: Dmitry V. Levin ldv@altlinux.org Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/riscv/include/asm/syscall.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-)

--- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -78,10 +78,11 @@ static inline void syscall_get_arguments if (i == 0) { args[0] = regs->orig_a0; args++; - i++; n--; + } else { + i--; } - memcpy(args, &regs->a1 + i * sizeof(regs->a1), n * sizeof(args[0])); + memcpy(args, &regs->a1 + i, n * sizeof(args[0])); }

static inline void syscall_set_arguments(struct task_struct *task, @@ -93,10 +94,11 @@ static inline void syscall_set_arguments if (i == 0) { regs->orig_a0 = args[0]; args++; - i++; n--; - } - memcpy(&regs->a1 + i * sizeof(regs->a1), args, n * sizeof(regs->a0)); + } else { + i--; + } + memcpy(&regs->a1 + i, args, n * sizeof(regs->a1)); }

#endif /* _ASM_RISCV_SYSCALL_H */

From: Jason Yan yanaijie@huawei.com

commit a89afe58f1a74aac768a5eb77af95ef4ee15beaa upstream.

If the last bio returned is not dio->bio, the status of the bio will not assigned to dio->bio if it is error. This will cause the whole IO status wrong.

ksoftirqd/21-117 [021] ..s. 4017.966090: 8,0 C N 4883648 [0] <idle>-0 [018] ..s. 4017.970888: 8,0 C WS 4924800 + 1024 [0] <idle>-0 [018] ..s. 4017.970909: 8,0 D WS 4935424 + 1024 [<idle>] <idle>-0 [018] ..s. 4017.970924: 8,0 D WS 4936448 + 321 [<idle>] ksoftirqd/21-117 [021] ..s. 4017.995033: 8,0 C R 4883648 + 336 [65475] ksoftirqd/21-117 [021] d.s. 4018.001988: myprobe1: (blkdev_bio_end_io+0x0/0x168) bi_status=7 ksoftirqd/21-117 [021] d.s. 4018.001992: myprobe: (aio_complete_rw+0x0/0x148) x0=0xffff802f2595ad80 res=0x12a000 res2=0x0

We always have to assign bio->bi_status to dio->bio.bi_status because we will only check dio->bio.bi_status when we return the whole IO to the upper layer.

Fixes: 542ff7bf18c6 ("block: new direct I/O implementation") Cc: stable@vger.kernel.org Cc: Christoph Hellwig hch@lst.de Cc: Jens Axboe axboe@kernel.dk Reviewed-by: Ming Lei ming.lei@redhat.com Signed-off-by: Jason Yan yanaijie@huawei.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/block_dev.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -296,10 +296,10 @@ static void blkdev_bio_end_io(struct bio struct blkdev_dio *dio = bio->bi_private; bool should_dirty = dio->should_dirty;

- if (dio->multi_bio && !atomic_dec_and_test(&dio->ref)) { - if (bio->bi_status && !dio->bio.bi_status) - dio->bio.bi_status = bio->bi_status; - } else { + if (bio->bi_status && !dio->bio.bi_status) + dio->bio.bi_status = bio->bi_status; + + if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) { if (!dio->is_sync) { struct kiocb *iocb = dio->iocb; ssize_t ret;

From: Kefeng Wang wangkefeng.wang@huawei.com

commit e8458e7afa855317b14915d7b86ab3caceea7eb6 upstream.

When CONFIG_SPARSE_IRQ is disable, the request_mutex in struct irq_desc is not initialized which causes malfunction.

Fixes: 9114014cf4e6 ("genirq: Add mutex to irq desc to serialize request/free_irq()") Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Mukesh Ojha mojha@codeaurora.org Cc: Marc Zyngier marc.zyngier@arm.com Cc: linux-arm-kernel@lists.infradead.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190404074512.145533-1-wangkefeng.wang@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/irq/irqdesc.c | 1 + 1 file changed, 1 insertion(+)

--- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -554,6 +554,7 @@ int __init early_irq_init(void) alloc_masks(&desc[i], node); raw_spin_lock_init(&desc[i].lock); lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); + mutex_init(&desc[i].request_mutex); desc_set_defaults(i, &desc[i], node, NULL, NULL); } return arch_early_irq_init();

From: Jonas Karlman jonas@kwiboo.se

commit 6b2fde3dbfab6ebc45b0cd605e17ca5057ff9a3b upstream.

The following error can be seen during boot:

of: /cpus/cpu@501: Couldn't find opp node

Change cpu nodes to use operating-points-v2 in order to fix this.

Fixes: ce76de984649 ("ARM: dts: rockchip: convert rk3288 to operating-points-v2") Cc: stable@vger.kernel.org Signed-off-by: Jonas Karlman jonas@kwiboo.se Signed-off-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/boot/dts/rk3288.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -70,7 +70,7 @@ compatible = "arm,cortex-a12"; reg = <0x501>; resets = <&cru SRST_CORE1>; - operating-points = <&cpu_opp_table>; + operating-points-v2 = <&cpu_opp_table>; #cooling-cells = <2>; /* min followed by max */ clock-latency = <40000>; clocks = <&cru ARMCLK>; @@ -80,7 +80,7 @@ compatible = "arm,cortex-a12"; reg = <0x502>; resets = <&cru SRST_CORE2>; - operating-points = <&cpu_opp_table>; + operating-points-v2 = <&cpu_opp_table>; #cooling-cells = <2>; /* min followed by max */ clock-latency = <40000>; clocks = <&cru ARMCLK>; @@ -90,7 +90,7 @@ compatible = "arm,cortex-a12"; reg = <0x503>; resets = <&cru SRST_CORE3>; - operating-points = <&cpu_opp_table>; + operating-points-v2 = <&cpu_opp_table>; #cooling-cells = <2>; /* min followed by max */ clock-latency = <40000>; clocks = <&cru ARMCLK>;

From: Peter Ujfalusi peter.ujfalusi@ti.com

commit 4f96dc0a3e79ec257a2b082dab3ee694ff88c317 upstream.

Correctly map the regulators used by tlv320aic3106. Both 1.8V and 3.3V for the codec is derived from VBAT via fixed regulators.

Cc: Stable@vger.kernel.org # v4.14+ Signed-off-by: Peter Ujfalusi peter.ujfalusi@ti.com Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/boot/dts/am335x-evm.dts | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-)

--- a/arch/arm/boot/dts/am335x-evm.dts +++ b/arch/arm/boot/dts/am335x-evm.dts @@ -57,6 +57,24 @@ enable-active-high; };

+ /* TPS79501 */ + v1_8d_reg: fixedregulator-v1_8d { + compatible = "regulator-fixed"; + regulator-name = "v1_8d"; + vin-supply = <&vbat>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + /* TPS79501 */ + v3_3d_reg: fixedregulator-v3_3d { + compatible = "regulator-fixed"; + regulator-name = "v3_3d"; + vin-supply = <&vbat>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + matrix_keypad: matrix_keypad0 { compatible = "gpio-matrix-keypad"; debounce-delay-ms = <5>; @@ -499,10 +517,10 @@ status = "okay";

/* Regulators */ - AVDD-supply = <&vaux2_reg>; - IOVDD-supply = <&vaux2_reg>; - DRVDD-supply = <&vaux2_reg>; - DVDD-supply = <&vbat>; + AVDD-supply = <&v3_3d_reg>; + IOVDD-supply = <&v3_3d_reg>; + DRVDD-supply = <&v3_3d_reg>; + DVDD-supply = <&v1_8d_reg>; }; };

From: Will Deacon will.deacon@arm.com

commit 045afc24124d80c6998d9c770844c67912083506 upstream.

Rather embarrassingly, our futex() FUTEX_WAKE_OP implementation doesn't explicitly set the return value on the non-faulting path and instead leaves it holding the result of the underlying atomic operation. This means that any FUTEX_WAKE_OP atomic operation which computes a non-zero value will be reported as having failed. Regrettably, I wrote the buggy code back in 2011 and it was upstreamed as part of the initial arm64 support in 2012.

The reasons we appear to get away with this are:

1. FUTEX_WAKE_OP is rarely used and therefore doesn't appear to get exercised by futex() test applications

2. If the result of the atomic operation is zero, the system call behaves correctly

3. Prior to version 2.25, the only operation used by GLIBC set the futex to zero, and therefore worked as expected. From 2.25 onwards, FUTEX_WAKE_OP is not used by GLIBC at all.

Fix the implementation by ensuring that the return value is either 0 to indicate that the atomic operation completed successfully, or -EFAULT if we encountered a fault when accessing the user mapping.

Cc: stable@kernel.org Fixes: 6170a97460db ("arm64: Atomic operations") Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/include/asm/futex.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)

--- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -30,8 +30,8 @@ do { \ " prfm pstl1strm, %2\n" \ "1: ldxr %w1, %2\n" \ insn "\n" \ -"2: stlxr %w3, %w0, %2\n" \ -" cbnz %w3, 1b\n" \ +"2: stlxr %w0, %w3, %2\n" \ +" cbnz %w0, 1b\n" \ " dmb ish\n" \ "3:\n" \ " .pushsection .fixup,"ax"\n" \ @@ -50,30 +50,30 @@ do { \ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr) { - int oldval = 0, ret, tmp; + int oldval, ret, tmp; u32 __user *uaddr = __uaccess_mask_ptr(_uaddr);

pagefault_disable();

switch (op) { case FUTEX_OP_SET: - __futex_atomic_op("mov %w0, %w4", + __futex_atomic_op("mov %w3, %w4", ret, oldval, uaddr, tmp, oparg); break; case FUTEX_OP_ADD: - __futex_atomic_op("add %w0, %w1, %w4", + __futex_atomic_op("add %w3, %w1, %w4", ret, oldval, uaddr, tmp, oparg); break; case FUTEX_OP_OR: - __futex_atomic_op("orr %w0, %w1, %w4", + __futex_atomic_op("orr %w3, %w1, %w4", ret, oldval, uaddr, tmp, oparg); break; case FUTEX_OP_ANDN: - __futex_atomic_op("and %w0, %w1, %w4", + __futex_atomic_op("and %w3, %w1, %w4", ret, oldval, uaddr, tmp, ~oparg); break; case FUTEX_OP_XOR: - __futex_atomic_op("eor %w0, %w1, %w4", + __futex_atomic_op("eor %w3, %w1, %w4", ret, oldval, uaddr, tmp, oparg); break; default:

From: Will Deacon will.deacon@arm.com

commit 1e6f5440a6814d28c32d347f338bfef68bc3e69d upstream.

Calling dump_backtrace() with a pt_regs argument corresponding to userspace doesn't make any sense and our unwinder will simply print "Call trace:" before unwinding the stack looking for user frames.

Rather than go through this song and dance, just return early if we're passed a user register state.

Cc: stable@vger.kernel.org Fixes: 1149aad10b1e ("arm64: Add dump_backtrace() in show_regs") Reported-by: Kefeng Wang wangkefeng.wang@huawei.com Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/kernel/traps.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)

--- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -101,10 +101,16 @@ static void dump_instr(const char *lvl, void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) { struct stackframe frame; - int skip; + int skip = 0;

pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);

+ if (regs) { + if (user_mode(regs)) + return; + skip = 1; + } + if (!tsk) tsk = current;

@@ -125,7 +131,6 @@ void dump_backtrace(struct pt_regs *regs frame.graph = tsk->curr_ret_stack; #endif

- skip = !!regs; printk("Call trace:\n"); do { /* skip until specified stack frame */ @@ -175,15 +180,13 @@ static int __die(const char *str, int er return ret;

print_modules(); - __show_regs(regs); pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n", TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), end_of_stack(tsk)); + show_regs(regs);

- if (!user_mode(regs)) { - dump_backtrace(regs, tsk); + if (!user_mode(regs)) dump_instr(KERN_EMERG, regs); - }

return ret; }

From: Mel Gorman mgorman@techsingularity.net

commit 0e9f02450da07fc7b1346c8c32c771555173e397 upstream.

A NULL pointer dereference bug was reported on a distribution kernel but the same issue should be present on mainline kernel. It occured on s390 but should not be arch-specific. A partial oops looks like:

Unable to handle kernel pointer dereference in virtual kernel address space ... Call Trace: ... try_to_wake_up+0xfc/0x450 vhost_poll_wakeup+0x3a/0x50 [vhost] __wake_up_common+0xbc/0x178 __wake_up_common_lock+0x9e/0x160 __wake_up_sync_key+0x4e/0x60 sock_def_readable+0x5e/0x98

The bug hits any time between 1 hour to 3 days. The dereference occurs in update_cfs_rq_h_load when accumulating h_load. The problem is that cfq_rq->h_load_next is not protected by any locking and can be updated by parallel calls to task_h_load. Depending on the compiler, code may be generated that re-reads cfq_rq->h_load_next after the check for NULL and then oops when reading se->avg.load_avg. The dissassembly showed that it was possible to reread h_load_next after the check for NULL.

While this does not appear to be an issue for later compilers, it's still an accident if the correct code is generated. Full locking in this path would have high overhead so this patch uses READ_ONCE to read h_load_next only once and check for NULL before dereferencing. It was confirmed that there were no further oops after 10 days of testing.

As Peter pointed out, it is also necessary to use WRITE_ONCE() to avoid any potential problems with store tearing.

Signed-off-by: Mel Gorman mgorman@techsingularity.net Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Valentin Schneider valentin.schneider@arm.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Mike Galbraith efault@gmx.de Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: stable@vger.kernel.org Fixes: 685207963be9 ("sched: Move h_load calculation to task_h_load()") Link: https://lkml.kernel.org/r/20190319123610.nsivgf3mjbjjesxb@techsingularity.ne... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/sched/fair.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7437,10 +7437,10 @@ static void update_cfs_rq_h_load(struct if (cfs_rq->last_h_load_update == now) return;

- cfs_rq->h_load_next = NULL; + WRITE_ONCE(cfs_rq->h_load_next, NULL); for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); - cfs_rq->h_load_next = se; + WRITE_ONCE(cfs_rq->h_load_next, se); if (cfs_rq->last_h_load_update == now) break; } @@ -7450,7 +7450,7 @@ static void update_cfs_rq_h_load(struct cfs_rq->last_h_load_update = now; }

- while ((se = cfs_rq->h_load_next) != NULL) { + while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) { load = cfs_rq->h_load; load = div64_ul(load * se->avg.load_avg, cfs_rq_load_avg(cfs_rq) + 1);

From: Rasmus Villemoes linux@rasmusvillemoes.dk

commit 88ca66d8540ca26119b1428cddb96b37925bdf01 upstream.

The minimum supported gcc version is >= 4.6, so these can be removed.

Signed-off-by: Rasmus Villemoes linux@rasmusvillemoes.dk Signed-off-by: Borislav Petkov bp@suse.de Cc: "H. Peter Anvin" hpa@zytor.com Cc: Dan Williams dan.j.williams@intel.com Cc: Geert Uytterhoeven geert@linux-m68k.org Cc: Ingo Molnar mingo@redhat.com Cc: Matthew Wilcox willy@infradead.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: x86-ml x86@kernel.org Link: https://lkml.kernel.org/r/20190111084931.24601-1-linux@rasmusvillemoes.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/include/asm/bitops.h | 6 ------ arch/x86/include/asm/string_32.h | 20 -------------------- arch/x86/include/asm/string_64.h | 15 --------------- 3 files changed, 41 deletions(-)

--- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -36,13 +36,7 @@ * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1). */

-#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 1) -/* Technically wrong, but this avoids compilation errors on some gcc - versions. */ -#define BITOP_ADDR(x) "=m" (*(volatile long *) (x)) -#else #define BITOP_ADDR(x) "+m" (*(volatile long *) (x)) -#endif

#define ADDR BITOP_ADDR(addr)

--- a/arch/x86/include/asm/string_32.h +++ b/arch/x86/include/asm/string_32.h @@ -179,14 +179,7 @@ static inline void *__memcpy3d(void *to, * No 3D Now! */

-#if (__GNUC__ >= 4) #define memcpy(t, f, n) __builtin_memcpy(t, f, n) -#else -#define memcpy(t, f, n) \ - (__builtin_constant_p((n)) \ - ? __constant_memcpy((t), (f), (n)) \ - : __memcpy((t), (f), (n))) -#endif

#endif #endif /* !CONFIG_FORTIFY_SOURCE */ @@ -282,12 +275,7 @@ void *__constant_c_and_count_memset(void

{ int d0, d1; -#if __GNUC__ == 4 && __GNUC_MINOR__ == 0 - /* Workaround for broken gcc 4.0 */ - register unsigned long eax asm("%eax") = pattern; -#else unsigned long eax = pattern; -#endif

switch (count % 4) { case 0: @@ -321,15 +309,7 @@ void *__constant_c_and_count_memset(void #define __HAVE_ARCH_MEMSET extern void *memset(void *, int, size_t); #ifndef CONFIG_FORTIFY_SOURCE -#if (__GNUC__ >= 4) #define memset(s, c, count) __builtin_memset(s, c, count) -#else -#define memset(s, c, count) \ - (__builtin_constant_p(c) \ - ? __constant_c_x_memset((s), (0x01010101UL * (unsigned char)(c)), \ - (count)) \ - : __memset((s), (c), (count))) -#endif #endif /* !CONFIG_FORTIFY_SOURCE */

#define __HAVE_ARCH_MEMSET16 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -32,21 +32,6 @@ static __always_inline void *__inline_me extern void *memcpy(void *to, const void *from, size_t len); extern void *__memcpy(void *to, const void *from, size_t len);

-#ifndef CONFIG_FORTIFY_SOURCE -#if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4 -#define memcpy(dst, src, len) \ -({ \ - size_t __len = (len); \ - void *__ret; \ - if (__builtin_constant_p(len) && __len >= 64) \ - __ret = __memcpy((dst), (src), __len); \ - else \ - __ret = __builtin_memcpy((dst), (src), __len); \ - __ret; \ -}) -#endif -#endif /* !CONFIG_FORTIFY_SOURCE */ - #define __HAVE_ARCH_MEMSET void *memset(void *s, int c, size_t n); void *__memset(void *s, int c, size_t n);

From: Lendacky, Thomas Thomas.Lendacky@amd.com

commit 914123fa39042e651d79eaf86bbf63a1b938dddf upstream.

On AMD processors, the detection of an overflowed counter in the NMI handler relies on the current value of the counter. So, for example, to check for overflow on a 48 bit counter, bit 47 is checked to see if it is 1 (not overflowed) or 0 (overflowed).

There is currently a race condition present when disabling and then updating the PMC. Increased NMI latency in newer AMD processors makes this race condition more pronounced. If the counter value has overflowed, it is possible to update the PMC value before the NMI handler can run. The updated PMC value is not an overflowed value, so when the perf NMI handler does run, it will not find an overflowed counter. This may appear as an unknown NMI resulting in either a panic or a series of messages, depending on how the kernel is configured.

To eliminate this race condition, the PMC value must be checked after disabling the counter. Add an AMD function, amd_pmu_disable_all(), that will wait for the NMI handler to reset any active and overflowed counter after calling x86_pmu_disable_all().

Signed-off-by: Tom Lendacky thomas.lendacky@amd.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org # 4.14.x- Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Arnaldo Carvalho de Melo acme@kernel.org Cc: Arnaldo Carvalho de Melo acme@redhat.com Cc: Borislav Petkov bp@alien8.de Cc: Jiri Olsa jolsa@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Link: https://lkml.kernel.org/r/Message-ID: Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/events/amd/core.c | 65 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 62 insertions(+), 3 deletions(-)

--- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -3,6 +3,7 @@ #include <linux/types.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/delay.h> #include <asm/apicdef.h>

#include "../perf_event.h" @@ -429,6 +430,64 @@ static void amd_pmu_cpu_dead(int cpu) } }

+/* + * When a PMC counter overflows, an NMI is used to process the event and + * reset the counter. NMI latency can result in the counter being updated + * before the NMI can run, which can result in what appear to be spurious + * NMIs. This function is intended to wait for the NMI to run and reset + * the counter to avoid possible unhandled NMI messages. + */ +#define OVERFLOW_WAIT_COUNT 50 + +static void amd_pmu_wait_on_overflow(int idx) +{ + unsigned int i; + u64 counter; + + /* + * Wait for the counter to be reset if it has overflowed. This loop + * should exit very, very quickly, but just in case, don't wait + * forever... + */ + for (i = 0; i < OVERFLOW_WAIT_COUNT; i++) { + rdmsrl(x86_pmu_event_addr(idx), counter); + if (counter & (1ULL << (x86_pmu.cntval_bits - 1))) + break; + + /* Might be in IRQ context, so can't sleep */ + udelay(1); + } +} + +static void amd_pmu_disable_all(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int idx; + + x86_pmu_disable_all(); + + /* + * This shouldn't be called from NMI context, but add a safeguard here + * to return, since if we're in NMI context we can't wait for an NMI + * to reset an overflowed counter value. + */ + if (in_nmi()) + return; + + /* + * Check each counter for overflow and wait for it to be reset by the + * NMI if it has overflowed. This relies on the fact that all active + * counters are always enabled when this function is caled and + * ARCH_PERFMON_EVENTSEL_INT is always set. + */ + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + if (!test_bit(idx, cpuc->active_mask)) + continue; + + amd_pmu_wait_on_overflow(idx); + } +} + static struct event_constraint * amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) @@ -622,7 +681,7 @@ static ssize_t amd_event_sysfs_show(char static __initconst const struct x86_pmu amd_pmu = { .name = "AMD", .handle_irq = x86_pmu_handle_irq, - .disable_all = x86_pmu_disable_all, + .disable_all = amd_pmu_disable_all, .enable_all = x86_pmu_enable_all, .enable = x86_pmu_enable_event, .disable = x86_pmu_disable_event, @@ -728,7 +787,7 @@ void amd_pmu_enable_virt(void) cpuc->perf_ctr_virt_mask = 0;

/* Reload all events */ - x86_pmu_disable_all(); + amd_pmu_disable_all(); x86_pmu_enable_all(0); } EXPORT_SYMBOL_GPL(amd_pmu_enable_virt); @@ -746,7 +805,7 @@ void amd_pmu_disable_virt(void) cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;

/* Reload all events */ - x86_pmu_disable_all(); + amd_pmu_disable_all(); x86_pmu_enable_all(0); } EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);

From: Lendacky, Thomas Thomas.Lendacky@amd.com

commit 3966c3feca3fd10b2935caa0b4a08c7dd59469e5 upstream.

Spurious interrupt support was added to perf in the following commit, almost a decade ago:

63e6be6d98e1 ("perf, x86: Catch spurious interrupts after disabling counters")

The two previous patches (resolving the race condition when disabling a PMC and NMI latency mitigation) allow for the removal of this older spurious interrupt support.

Currently in x86_pmu_stop(), the bit for the PMC in the active_mask bitmap is cleared before disabling the PMC, which sets up a race condition. This race condition was mitigated by introducing the running bitmap. That race condition can be eliminated by first disabling the PMC, waiting for PMC reset on overflow and then clearing the bit for the PMC in the active_mask bitmap. The NMI handler will not re-enable a disabled counter.

If x86_pmu_stop() is called from the perf NMI handler, the NMI latency mitigation support will guard against any unhandled NMI messages.

Signed-off-by: Tom Lendacky thomas.lendacky@amd.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org # 4.14.x- Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Arnaldo Carvalho de Melo acme@kernel.org Cc: Arnaldo Carvalho de Melo acme@redhat.com Cc: Borislav Petkov bp@alien8.de Cc: Jiri Olsa jolsa@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Link: https://lkml.kernel.org/r/Message-ID: Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/events/amd/core.c | 21 +++++++++++++++++++-- arch/x86/events/core.c | 13 +++---------- 2 files changed, 22 insertions(+), 12 deletions(-)

--- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -4,8 +4,8 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/delay.h> -#include <linux/nmi.h> #include <asm/apicdef.h> +#include <asm/nmi.h>

#include "../perf_event.h"

@@ -491,6 +491,23 @@ static void amd_pmu_disable_all(void) } }

+static void amd_pmu_disable_event(struct perf_event *event) +{ + x86_pmu_disable_event(event); + + /* + * This can be called from NMI context (via x86_pmu_stop). The counter + * may have overflowed, but either way, we'll never see it get reset + * by the NMI if we're already in the NMI. And the NMI latency support + * below will take care of any pending NMI that might have been + * generated by the overflow. + */ + if (in_nmi()) + return; + + amd_pmu_wait_on_overflow(event->hw.idx); +} + /* * Because of NMI latency, if multiple PMC counters are active or other sources * of NMIs are received, the perf NMI handler can handle one or more overflowed @@ -738,7 +755,7 @@ static __initconst const struct x86_pmu .disable_all = amd_pmu_disable_all, .enable_all = x86_pmu_enable_all, .enable = x86_pmu_enable_event, - .disable = x86_pmu_disable_event, + .disable = amd_pmu_disable_event, .hw_config = amd_pmu_hw_config, .schedule_events = x86_schedule_events, .eventsel = MSR_K7_EVNTSEL0, --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1328,8 +1328,9 @@ void x86_pmu_stop(struct perf_event *eve struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw;

- if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) { + if (test_bit(hwc->idx, cpuc->active_mask)) { x86_pmu.disable(event); + __clear_bit(hwc->idx, cpuc->active_mask); cpuc->events[hwc->idx] = NULL; WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; @@ -1426,16 +1427,8 @@ int x86_pmu_handle_irq(struct pt_regs *r apic_write(APIC_LVTPC, APIC_DM_NMI);

for (idx = 0; idx < x86_pmu.num_counters; idx++) { - if (!test_bit(idx, cpuc->active_mask)) { - /* - * Though we deactivated the counter some cpus - * might still deliver spurious interrupts still - * in flight. Catch them: - */ - if (__test_and_clear_bit(idx, cpuc->running)) - handled++; + if (!test_bit(idx, cpuc->active_mask)) continue; - }

event = cpuc->events[idx];

From: Sergey Miroshnichenko s.miroshnichenko@yadro.com

commit 3943af9d01e94330d0cfac6fccdbc829aad50c92 upstream.

During a safe hot remove, the OS powers off the slot, which may cause a Data Link Layer State Changed event. The slot has already been set to OFF_STATE, so that event results in re-enabling the device, making it impossible to safely remove it.

Clear out the Presence Detect Changed and Data Link Layer State Changed events when the disabled slot has settled down.

It is still possible to re-enable the device if it remains in the slot after pressing the Attention Button by pressing it again.

Fixes the problem that Micah reported below: an NVMe drive power button may not actually turn off the drive.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=203237 Reported-by: Micah Parrish micah.parrish@hpe.com Tested-by: Micah Parrish micah.parrish@hpe.com Signed-off-by: Sergey Miroshnichenko s.miroshnichenko@yadro.com [bhelgaas: changelog, add bugzilla URL] Signed-off-by: Bjorn Helgaas bhelgaas@google.com Reviewed-by: Lukas Wunner lukas@wunner.de Cc: stable@vger.kernel.org # v4.19+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/pci/hotplug/pciehp_ctrl.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -117,6 +117,10 @@ static void remove_board(struct slot *p_ * removed from the slot/adapter. */ msleep(1000); + + /* Ignore link or presence changes caused by power off */ + atomic_and(~(PCI_EXP_SLTSTA_DLLSC | PCI_EXP_SLTSTA_PDC), + &ctrl->pending_events); }

/* turn off Green LED */

From: Mikulas Patocka mpatocka@redhat.com

commit 75ae193626de3238ca5fb895868ec91c94e63b1b upstream.

The limit was already incorporated to dm-crypt with commit 4e870e948fba ("dm crypt: fix error with too large bios"), so we don't need to apply it globally to all targets. The quantity BIO_MAX_PAGES * PAGE_SIZE is wrong anyway because the variable ti->max_io_len it is supposed to be in the units of 512-byte sectors not in bytes.

Reduction of the limit to 1048576 sectors could even cause data corruption in rare cases - suppose that we have a dm-striped device with stripe size 768MiB. The target will call dm_set_target_max_io_len with the value 1572864. The buggy code would reduce it to 1048576. Now, the dm-core will errorneously split the bios on 1048576-sector boundary insetad of 1572864-sector boundary and pass these stripe-crossing bios to the striped target.

Cc: stable@vger.kernel.org # v4.16+ Fixes: 8f50e358153d ("dm: limit the max bio size as BIO_MAX_PAGES * PAGE_SIZE") Signed-off-by: Mikulas Patocka mpatocka@redhat.com Acked-by: Ming Lei ming.lei@redhat.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/md/dm.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-)

--- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1007,15 +1007,7 @@ int dm_set_target_max_io_len(struct dm_t return -EINVAL; }

- /* - * BIO based queue uses its own splitting. When multipage bvecs - * is switched on, size of the incoming bio may be too big to - * be handled in some targets, such as crypt. - * - * When these targets are ready for the big bio, we can remove - * the limit. - */ - ti->max_io_len = min_t(uint32_t, len, BIO_MAX_PAGES * PAGE_SIZE); + ti->max_io_len = (uint32_t) len;

return 0; }

From: Mikulas Patocka mpatocka@redhat.com

commit 4ed319c6ac08e9a28fca7ac188181ac122f4de84 upstream.

dm-integrity will deadlock if overlapping I/O is issued to it, the bug was introduced by commit 724376a04d1a ("dm integrity: implement fair range locks"). Users rarely use overlapping I/O so this bug went undetected until now.

Fix this bug by correcting, likely cut-n-paste, typos in ranges_overlap() and also remove a flawed ranges_overlap() check in remove_range_unlocked(). This condition could leave unprocessed bios hanging on wait_list forever.

Cc: stable@vger.kernel.org # v4.19+ Fixes: 724376a04d1a ("dm integrity: implement fair range locks") Signed-off-by: Mikulas Patocka mpatocka@redhat.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/md/dm-integrity.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

--- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -908,7 +908,7 @@ static void copy_from_journal(struct dm_ static bool ranges_overlap(struct dm_integrity_range *range1, struct dm_integrity_range *range2) { return range1->logical_sector < range2->logical_sector + range2->n_sectors && - range2->logical_sector + range2->n_sectors > range2->logical_sector; + range1->logical_sector + range1->n_sectors > range2->logical_sector; }

static bool add_new_range(struct dm_integrity_c *ic, struct dm_integrity_range *new_range, bool check_waiting) @@ -954,8 +954,6 @@ static void remove_range_unlocked(struct struct dm_integrity_range *last_range = list_first_entry(&ic->wait_list, struct dm_integrity_range, wait_entry); struct task_struct *last_range_task; - if (!ranges_overlap(range, last_range)) - break; last_range_task = last_range->task; list_del(&last_range->wait_entry); if (!add_new_range(ic, last_range, false)) {

From: Tomohiro Mayama parly-gh@iris.mystia.org

commit a8772e5d826d0f61f8aa9c284b3ab49035d5273d upstream.

This patch makes USB ports functioning again.

Fixes: 955bebde057e ("arm64: dts: rockchip: add rk3328-rock64 board") Cc: stable@vger.kernel.org Suggested-by: Robin Murphy robin.murphy@arm.com Signed-off-by: Tomohiro Mayama parly-gh@iris.mystia.org Tested-by: Katsuhiro Suzuki katsuhiro@katsuster.net Signed-off-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/boot/dts/rockchip/rk3328-rock64.dts | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts @@ -45,8 +45,7 @@

vcc_host1_5v: vcc_otg_5v: vcc-host1-5v-regulator { compatible = "regulator-fixed"; - enable-active-high; - gpio = <&gpio0 RK_PA2 GPIO_ACTIVE_HIGH>; + gpio = <&gpio0 RK_PA2 GPIO_ACTIVE_LOW>; pinctrl-names = "default"; pinctrl-0 = <&usb20_host_drv>; regulator-name = "vcc_host1_5v";

From: Marc Orr marcorr@google.com

commit acff78477b9b4f26ecdf65733a4ed77fe837e9dc upstream.

The nested_vmx_prepare_msr_bitmap() function doesn't directly guard the x2APIC MSR intercepts with the "virtualize x2APIC mode" MSR. As a result, we discovered the potential for a buggy or malicious L1 to get access to L0's x2APIC MSRs, via an L2, as follows.

1. L1 executes WRMSR(IA32_SPEC_CTRL, 1). This causes the spec_ctrl variable, in nested_vmx_prepare_msr_bitmap() to become true. 2. L1 disables "virtualize x2APIC mode" in VMCS12. 3. L1 enables "APIC-register virtualization" in VMCS12.

Now, KVM will set VMCS02's x2APIC MSR intercepts from VMCS12, and then set "virtualize x2APIC mode" to 0 in VMCS02. Oops.

This patch closes the leak by explicitly guarding VMCS02's x2APIC MSR intercepts with VMCS12's "virtualize x2APIC mode" control.

The scenario outlined above and fix prescribed here, were verified with a related patch in kvm-unit-tests titled "Add leak scenario to virt_x2apic_mode_test".

Note, it looks like this issue may have been introduced inadvertently during a merge---see 15303ba5d1cd.

Signed-off-by: Marc Orr marcorr@google.com Reviewed-by: Jim Mattson jmattson@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kvm/vmx.c | 72 ++++++++++++++++++++++++++++++++--------------------- 1 file changed, 44 insertions(+), 28 deletions(-)

--- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -11582,6 +11582,17 @@ static int nested_vmx_check_tpr_shadow_c return 0; }

+static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) { + int msr; + + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + + msr_bitmap[word] = ~0; + msr_bitmap[word + (0x800 / sizeof(long))] = ~0; + } +} + /* * Merge L0's and L1's MSR bitmap, return false to indicate that * we do not use the hardware. @@ -11623,39 +11634,44 @@ static inline bool nested_vmx_prepare_ms return false;

msr_bitmap_l1 = (unsigned long *)kmap(page); - if (nested_cpu_has_apic_reg_virt(vmcs12)) { - /* - * L0 need not intercept reads for MSRs between 0x800 and 0x8ff, it - * just lets the processor take the value from the virtual-APIC page; - * take those 256 bits directly from the L1 bitmap. - */ - for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { - unsigned word = msr / BITS_PER_LONG; - msr_bitmap_l0[word] = msr_bitmap_l1[word]; - msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0; - } - } else { - for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { - unsigned word = msr / BITS_PER_LONG; - msr_bitmap_l0[word] = ~0; - msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0; - } - }

- nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - X2APIC_MSR(APIC_TASKPRI), - MSR_TYPE_W); + /* + * To keep the control flow simple, pay eight 8-byte writes (sixteen + * 4-byte writes on 32-bit systems) up front to enable intercepts for + * the x2APIC MSR range and selectively disable them below. + */ + enable_x2apic_msr_intercepts(msr_bitmap_l0); + + if (nested_cpu_has_virt_x2apic_mode(vmcs12)) { + if (nested_cpu_has_apic_reg_virt(vmcs12)) { + /* + * L0 need not intercept reads for MSRs between 0x800 + * and 0x8ff, it just lets the processor take the value + * from the virtual-APIC page; take those 256 bits + * directly from the L1 bitmap. + */ + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + + msr_bitmap_l0[word] = msr_bitmap_l1[word]; + } + }

- if (nested_cpu_has_vid(vmcs12)) { - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - X2APIC_MSR(APIC_EOI), - MSR_TYPE_W); nested_vmx_disable_intercept_for_msr( msr_bitmap_l1, msr_bitmap_l0, - X2APIC_MSR(APIC_SELF_IPI), + X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_W); + + if (nested_cpu_has_vid(vmcs12)) { + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + X2APIC_MSR(APIC_EOI), + MSR_TYPE_W); + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + X2APIC_MSR(APIC_SELF_IPI), + MSR_TYPE_W); + } }

if (spec_ctrl)