From: yu kuai yukuai3@huawei.com

commit a75ca9303175d36af93c0937dd9b1a6422908b8d upstream.

commit e7bf90e5afe3 ("block/bio-integrity: fix a memory leak bug") added a kfree() for 'buf' if bio_integrity_add_page() returns '0'. However, the object will be freed in bio_integrity_free() since 'bio->bi_opf' and 'bio->bi_integrity' were set previousy in bio_integrity_alloc().

Fixes: commit e7bf90e5afe3 ("block/bio-integrity: fix a memory leak bug") Signed-off-by: yu kuai yukuai3@huawei.com Reviewed-by: Ming Lei ming.lei@redhat.com Reviewed-by: Bob Liu bob.liu@oracle.com Acked-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Jens Axboe axboe@kernel.dk Cc: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- block/bio-integrity.c | 1 - 1 file changed, 1 deletion(-)

diff --git a/block/bio-integrity.c b/block/bio-integrity.c index bf62c25cde8f4..ae07dd78e9518 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -278,7 +278,6 @@ bool bio_integrity_prep(struct bio *bio)

if (ret == 0) { printk(KERN_ERR "could not attach integrity payload\n"); - kfree(buf); status = BLK_STS_RESOURCE; goto err_end_io; }

From: Gaurav Singh gaurav1086@gmail.com

[ Upstream commit 21a739c64d3e9871186483a0cc3e7b52638c3d59 ]

Fix check in ethtool_rx_flow_rule_create

Fixes: eca4205f9ec3 ("ethtool: add ethtool_rx_flow_spec to flow_rule structure translator") Signed-off-by: Gaurav Singh gaurav1086@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ethtool/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 89d0b1827aaff..d3eeeb26396cd 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -2957,7 +2957,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) sizeof(match->mask.ipv6.dst)); } if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr)) || - memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) { + memcmp(v6_m_spec->ip6dst, &zero_addr, sizeof(zero_addr))) { match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); match->dissector.offset[FLOW_DISSECTOR_KEY_IPV6_ADDRS] =

From: Thomas Falcon tlfalcon@linux.ibm.com

[ Upstream commit 5948378b26d89f8aa5eac37629dbd0616ce8d7a7 ]

The max MTU limit defined for ibmveth is not accounting for virtual ethernet buffer overhead, which is twenty-two additional bytes set aside for the ethernet header and eight additional bytes of an opaque handle reserved for use by the hypervisor. Update the max MTU to reflect this overhead.

Fixes: d894be57ca92 ("ethernet: use net core MTU range checking in more drivers") Fixes: 110447f8269a ("ethernet: fix min/max MTU typos") Signed-off-by: Thomas Falcon tlfalcon@linux.ibm.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/ibm/ibmveth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 96d36ae5049e1..c5c732601e35e 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1715,7 +1715,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) }

netdev->min_mtu = IBMVETH_MIN_MTU; - netdev->max_mtu = ETH_MAX_MTU; + netdev->max_mtu = ETH_MAX_MTU - IBMVETH_BUFF_OH;

memcpy(netdev->dev_addr, mac_addr_p, ETH_ALEN);

From: Ido Schimmel idosch@mellanox.com

[ Upstream commit f3fe412b0a634286a6a3753c3f9ff201e6bec716 ]

The second commit cited below performed a cast of 'u32 buffsize' to '(u16 *)' when calling mlxsw_sp_port_headroom_8x_adjust():

mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, (u16 *) &buffsize);

Colin noted that this will behave differently on big endian architectures compared to little endian architectures.

Fix this by following Colin's suggestion and have the function accept and return 'u32' instead of passing the current size by reference.

Fixes: da382875c616 ("mlxsw: spectrum: Extend to support Spectrum-3 ASIC") Fixes: 60833d54d56c ("mlxsw: spectrum: Adjust headroom buffers for 8x ports") Signed-off-by: Ido Schimmel idosch@mellanox.com Reported-by: Colin Ian King colin.king@canonical.com Suggested-by: Colin Ian King colin.king@canonical.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 ++-- drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 8 +++----- drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 2 +- drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c | 2 +- 4 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 3e4199246a18d..d9a2267aeaea2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -990,10 +990,10 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,

lossy = !(pfc || pause_en); thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu); - mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &thres_cells); + thres_cells = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, thres_cells); delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, pfc, pause_en); - mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &delay_cells); + delay_cells = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, delay_cells); total_cells = thres_cells + delay_cells;

taken_headroom_cells += total_cells; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index e28ecb84b8164..6b2e4e730b189 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -395,17 +395,15 @@ mlxsw_sp_port_vlan_find_by_vid(const struct mlxsw_sp_port *mlxsw_sp_port, return NULL; }

-static inline void +static inline u32 mlxsw_sp_port_headroom_8x_adjust(const struct mlxsw_sp_port *mlxsw_sp_port, - u16 *p_size) + u32 size_cells) { /* Ports with eight lanes use two headroom buffers between which the * configured headroom size is split. Therefore, multiply the calculated * headroom size by two. */ - if (mlxsw_sp_port->mapping.width != 8) - return; - *p_size *= 2; + return mlxsw_sp_port->mapping.width == 8 ? 2 * size_cells : size_cells; }

enum mlxsw_sp_flood_type { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 19bf0768ed788..2fb2cbd4f229e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -312,7 +312,7 @@ static int mlxsw_sp_port_pb_init(struct mlxsw_sp_port *mlxsw_sp_port)

if (i == MLXSW_SP_PB_UNUSED) continue; - mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &size); + size = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, size); mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, i, size); } mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 7c5032f9c8fff..76242c70d41ad 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -776,7 +776,7 @@ mlxsw_sp_span_port_buffsize_update(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu) speed = 0;

buffsize = mlxsw_sp_span_buffsize_get(mlxsw_sp, speed, mtu); - mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, (u16 *) &buffsize); + buffsize = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, buffsize); mlxsw_reg_sbib_pack(sbib_pl, mlxsw_sp_port->local_port, buffsize); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); }

From: Thomas Martitz t.martitz@avm.de

[ Upstream commit db7202dec92e6caa2706c21d6fc359af318bde2e ]

The eth_addr member is passed to ether_addr functions that require 2-byte alignment, therefore the member must be properly aligned to avoid unaligned accesses.

The problem is in place since the initial merge of multicast to unicast: commit 6db6f0eae6052b70885562e1733896647ec1d807 bridge: multicast to unicast

Fixes: 6db6f0eae605 ("bridge: multicast to unicast") Cc: Roopa Prabhu roopa@cumulusnetworks.com Cc: Nikolay Aleksandrov nikolay@cumulusnetworks.com Cc: David S. Miller davem@davemloft.net Cc: Jakub Kicinski kuba@kernel.org Cc: Felix Fietkau nbd@nbd.name Cc: stable@vger.kernel.org Signed-off-by: Thomas Martitz t.martitz@avm.de Acked-by: Nikolay Aleksandrov nikolay@cumulusnetworks.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bridge/br_private.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 1f97703a52ffb..18430f79ac37e 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -217,8 +217,8 @@ struct net_bridge_port_group { struct rcu_head rcu; struct timer_list timer; struct br_ip addr; + unsigned char eth_addr[ETH_ALEN] __aligned(2); unsigned char flags; - unsigned char eth_addr[ETH_ALEN]; };

struct net_bridge_mdb_entry {

From: Tariq Toukan tariqt@mellanox.com

[ Upstream commit 41b14fb8724d5a4b382a63cb4a1a61880347ccb8 ]

Clearing the sock TX queue in sk_set_socket() might cause unexpected out-of-order transmit when called from sock_orphan(), as outstanding packets can pick a different TX queue and bypass the ones already queued.

This is undesired in general. More specifically, it breaks the in-order scheduling property guarantee for device-offloaded TLS sockets.

Remove the call to sk_tx_queue_clear() in sk_set_socket(), and add it explicitly only where needed.

Fixes: e022f0b4a03f ("net: Introduce sk_tx_queue_mapping") Signed-off-by: Tariq Toukan tariqt@mellanox.com Reviewed-by: Boris Pismenny borisp@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/sock.h | 1 - net/core/sock.c | 2 ++ 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/net/sock.h b/include/net/sock.h index 3e8c6d4b4b59f..46423e86dba50 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1846,7 +1846,6 @@ static inline int sk_rx_queue_get(const struct sock *sk)

static inline void sk_set_socket(struct sock *sk, struct socket *sock) { - sk_tx_queue_clear(sk); sk->sk_socket = sock; }

diff --git a/net/core/sock.c b/net/core/sock.c index b714162213aea..da244f4d00363 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1678,6 +1678,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, cgroup_sk_alloc(&sk->sk_cgrp_data); sock_update_classid(&sk->sk_cgrp_data); sock_update_netprioidx(&sk->sk_cgrp_data); + sk_tx_queue_clear(sk); }

return sk; @@ -1901,6 +1902,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) */ sk_refcnt_debug_inc(newsk); sk_set_socket(newsk, NULL); + sk_tx_queue_clear(newsk); RCU_INIT_POINTER(newsk->sk_wq, NULL);

if (newsk->sk_prot->sockets_allocated)

From: Yang Yingliang yangyingliang@huawei.com

[ Upstream commit 814152a89ed52c722ab92e9fbabcac3cb8a39245 ]

I got a memleak report when doing some fuzz test:

unreferenced object 0xffff888112584000 (size 13599): comm "ip", pid 3048, jiffies 4294911734 (age 343.491s) hex dump (first 32 bytes): 74 61 70 30 00 00 00 00 00 00 00 00 00 00 00 00 tap0............ 00 ee d9 19 81 88 ff ff 00 00 00 00 00 00 00 00 ................ backtrace: [<000000002f60ba65>] __kmalloc_node+0x309/0x3a0 [<0000000075b211ec>] kvmalloc_node+0x7f/0xc0 [<00000000d3a97396>] alloc_netdev_mqs+0x76/0xfc0 [<00000000609c3655>] __tun_chr_ioctl+0x1456/0x3d70 [<000000001127ca24>] ksys_ioctl+0xe5/0x130 [<00000000b7d5e66a>] __x64_sys_ioctl+0x6f/0xb0 [<00000000e1023498>] do_syscall_64+0x56/0xa0 [<000000009ec0eb12>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 unreferenced object 0xffff888111845cc0 (size 8): comm "ip", pid 3048, jiffies 4294911734 (age 343.491s) hex dump (first 8 bytes): 74 61 70 30 00 88 ff ff tap0.... backtrace: [<000000004c159777>] kstrdup+0x35/0x70 [<00000000d8b496ad>] kstrdup_const+0x3d/0x50 [<00000000494e884a>] kvasprintf_const+0xf1/0x180 [<0000000097880a2b>] kobject_set_name_vargs+0x56/0x140 [<000000008fbdfc7b>] dev_set_name+0xab/0xe0 [<000000005b99e3b4>] netdev_register_kobject+0xc0/0x390 [<00000000602704fe>] register_netdevice+0xb61/0x1250 [<000000002b7ca244>] __tun_chr_ioctl+0x1cd1/0x3d70 [<000000001127ca24>] ksys_ioctl+0xe5/0x130 [<00000000b7d5e66a>] __x64_sys_ioctl+0x6f/0xb0 [<00000000e1023498>] do_syscall_64+0x56/0xa0 [<000000009ec0eb12>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 unreferenced object 0xffff88811886d800 (size 512): comm "ip", pid 3048, jiffies 4294911734 (age 343.491s) hex dump (first 32 bytes): 00 00 00 00 ad 4e ad de ff ff ff ff 00 00 00 00 .....N.......... ff ff ff ff ff ff ff ff c0 66 3d a3 ff ff ff ff .........f=..... backtrace: [<0000000050315800>] device_add+0x61e/0x1950 [<0000000021008dfb>] netdev_register_kobject+0x17e/0x390 [<00000000602704fe>] register_netdevice+0xb61/0x1250 [<000000002b7ca244>] __tun_chr_ioctl+0x1cd1/0x3d70 [<000000001127ca24>] ksys_ioctl+0xe5/0x130 [<00000000b7d5e66a>] __x64_sys_ioctl+0x6f/0xb0 [<00000000e1023498>] do_syscall_64+0x56/0xa0 [<000000009ec0eb12>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

If call_netdevice_notifiers() failed, then rollback_registered() calls netdev_unregister_kobject() which holds the kobject. The reference cannot be put because the netdev won't be add to todo list, so it will leads a memleak, we need put the reference to avoid memleak.

Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/dev.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c index 93a279ab4e97c..096b0dfa95890 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9435,6 +9435,13 @@ int register_netdevice(struct net_device *dev) rcu_barrier();

dev->reg_state = NETREG_UNREGISTERED; + /* We should put the kobject that hold in + * netdev_unregister_kobject(), otherwise + * the net device cannot be freed when + * driver calls free_netdev(), because the + * kobject is being hold. + */ + kobject_put(&dev->dev.kobj); } /* * Prevent userspace races by waiting until the network

From: Eric Dumazet edumazet@google.com

[ Upstream commit 0ad6f6e767ec2f613418cbc7ebe5ec4c35af540c ]

Back in commit f60e5990d9c1 ("ipv6: protect skb->sk accesses from recursive dereference inside the stack") Hannes added code so that IPv6 stack would not trust skb->sk for typical cases where packet goes through 'standard' xmit path (__dev_queue_xmit())

Alas af_packet had a dev_direct_xmit() path that was not dealing yet with xmit_recursion level.

Also change sk_mc_loop() to dump a stack once only.

Without this patch, syzbot was able to trigger :

[1] [ 153.567378] WARNING: CPU: 7 PID: 11273 at net/core/sock.c:721 sk_mc_loop+0x51/0x70 [ 153.567378] Modules linked in: nfnetlink ip6table_raw ip6table_filter iptable_raw iptable_nat nf_nat nf_conntrack nf_defrag_ipv4 nf_defrag_ipv6 iptable_filter macsec macvtap tap macvlan 8021q hsr wireguard libblake2s blake2s_x86_64 libblake2s_generic udp_tunnel ip6_udp_tunnel libchacha20poly1305 poly1305_x86_64 chacha_x86_64 libchacha curve25519_x86_64 libcurve25519_generic netdevsim batman_adv dummy team bridge stp llc w1_therm wire i2c_mux_pca954x i2c_mux cdc_acm ehci_pci ehci_hcd mlx4_en mlx4_ib ib_uverbs ib_core mlx4_core [ 153.567386] CPU: 7 PID: 11273 Comm: b159172088 Not tainted 5.8.0-smp-DEV #273 [ 153.567387] RIP: 0010:sk_mc_loop+0x51/0x70 [ 153.567388] Code: 66 83 f8 0a 75 24 0f b6 4f 12 b8 01 00 00 00 31 d2 d3 e0 a9 bf ef ff ff 74 07 48 8b 97 f0 02 00 00 0f b6 42 3a 83 e0 01 5d c3 <0f> 0b b8 01 00 00 00 5d c3 0f b6 87 18 03 00 00 5d c0 e8 04 83 e0 [ 153.567388] RSP: 0018:ffff95c69bb93990 EFLAGS: 00010212 [ 153.567388] RAX: 0000000000000011 RBX: ffff95c6e0ee3e00 RCX: 0000000000000007 [ 153.567389] RDX: ffff95c69ae50000 RSI: ffff95c6c30c3000 RDI: ffff95c6c30c3000 [ 153.567389] RBP: ffff95c69bb93990 R08: ffff95c69a77f000 R09: 0000000000000008 [ 153.567389] R10: 0000000000000040 R11: 00003e0e00026128 R12: ffff95c6c30c3000 [ 153.567390] R13: ffff95c6cc4fd500 R14: ffff95c6f84500c0 R15: ffff95c69aa13c00 [ 153.567390] FS: 00007fdc3a283700(0000) GS:ffff95c6ff9c0000(0000) knlGS:0000000000000000 [ 153.567390] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 153.567391] CR2: 00007ffee758e890 CR3: 0000001f9ba20003 CR4: 00000000001606e0 [ 153.567391] Call Trace: [ 153.567391] ip6_finish_output2+0x34e/0x550 [ 153.567391] __ip6_finish_output+0xe7/0x110 [ 153.567391] ip6_finish_output+0x2d/0xb0 [ 153.567392] ip6_output+0x77/0x120 [ 153.567392] ? __ip6_finish_output+0x110/0x110 [ 153.567392] ip6_local_out+0x3d/0x50 [ 153.567392] ipvlan_queue_xmit+0x56c/0x5e0 [ 153.567393] ? ksize+0x19/0x30 [ 153.567393] ipvlan_start_xmit+0x18/0x50 [ 153.567393] dev_direct_xmit+0xf3/0x1c0 [ 153.567393] packet_direct_xmit+0x69/0xa0 [ 153.567394] packet_sendmsg+0xbf0/0x19b0 [ 153.567394] ? plist_del+0x62/0xb0 [ 153.567394] sock_sendmsg+0x65/0x70 [ 153.567394] sock_write_iter+0x93/0xf0 [ 153.567394] new_sync_write+0x18e/0x1a0 [ 153.567395] __vfs_write+0x29/0x40 [ 153.567395] vfs_write+0xb9/0x1b0 [ 153.567395] ksys_write+0xb1/0xe0 [ 153.567395] __x64_sys_write+0x1a/0x20 [ 153.567395] do_syscall_64+0x43/0x70 [ 153.567396] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 153.567396] RIP: 0033:0x453549 [ 153.567396] Code: Bad RIP value. [ 153.567396] RSP: 002b:00007fdc3a282cc8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 153.567397] RAX: ffffffffffffffda RBX: 00000000004d32d0 RCX: 0000000000453549 [ 153.567397] RDX: 0000000000000020 RSI: 0000000020000300 RDI: 0000000000000003 [ 153.567398] RBP: 00000000004d32d8 R08: 0000000000000000 R09: 0000000000000000 [ 153.567398] R10: 0000000000000000 R11: 0000000000000246 R12: 00000000004d32dc [ 153.567398] R13: 00007ffee742260f R14: 00007fdc3a282dc0 R15: 00007fdc3a283700 [ 153.567399] ---[ end trace c1d5ae2b1059ec62 ]---

f60e5990d9c1 ("ipv6: protect skb->sk accesses from recursive dereference inside the stack") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/dev.c | 2 ++ net/core/sock.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c index 096b0dfa95890..c9ee5d80d5ea1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4109,10 +4109,12 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)

local_bh_disable();

+ dev_xmit_recursion_inc(); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_drv_stopped(txq)) ret = netdev_start_xmit(skb, dev, txq, false); HARD_TX_UNLOCK(dev, txq); + dev_xmit_recursion_dec();

local_bh_enable();

diff --git a/net/core/sock.c b/net/core/sock.c index da244f4d00363..afe4a62adf8ff 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -707,7 +707,7 @@ bool sk_mc_loop(struct sock *sk) return inet6_sk(sk)->mc_loop; #endif } - WARN_ON(1); + WARN_ON_ONCE(1); return true; } EXPORT_SYMBOL(sk_mc_loop);

From: Lorenzo Bianconi lorenzo@kernel.org

[ Upstream commit 17843655708e1941c0653af3cd61be6948e36f43 ]

ovs connection tracking module performs de-fragmentation on incoming fragmented traffic. Take info account if traffic has been de-fragmented in execute_check_pkt_len action otherwise we will perform the wrong nested action considering the original packet size. This issue typically occurs if ovs-vswitchd adds a rule in the pipeline that requires connection tracking (e.g. OVN stateful ACLs) before execute_check_pkt_len action. Moreover take into account GSO fragment size for GSO packet in execute_check_pkt_len routine

Fixes: 4d5ec89fc8d14 ("net: openvswitch: Add a new action check_pkt_len") Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/openvswitch/actions.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index fc0efd8833c84..2611657f40cac 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1169,9 +1169,10 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *attr, bool last) { + struct ovs_skb_cb *ovs_cb = OVS_CB(skb); const struct nlattr *actions, *cpl_arg; + int len, max_len, rem = nla_len(attr); const struct check_pkt_len_arg *arg; - int rem = nla_len(attr); bool clone_flow_key;

/* The first netlink attribute in 'attr' is always @@ -1180,7 +1181,11 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb, cpl_arg = nla_data(attr); arg = nla_data(cpl_arg);

- if (skb->len <= arg->pkt_len) { + len = ovs_cb->mru ? ovs_cb->mru + skb->mac_len : skb->len; + max_len = arg->pkt_len; + + if ((skb_is_gso(skb) && skb_gso_validate_mac_len(skb, max_len)) || + len <= max_len) { /* Second netlink attribute in 'attr' is always * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'. */

From: David Howells dhowells@redhat.com

[ Upstream commit 0041cd5a50442db6e456b145892a0eaf2dff061f ]

When preallocated service calls are being discarded, they're passed to ->discard_new_call() to have the caller clean up any attached higher-layer preallocated pieces before being marked completed. However, the act of marking them completed now invokes the call's notification function - which causes a problem because that function might assume that the previously freed pieces of memory are still there.

Fix this by setting a dummy notification function on the socket after calling ->discard_new_call().

This results in the following kasan message when the kafs module is removed.

================================================================== BUG: KASAN: use-after-free in afs_wake_up_async_call+0x6aa/0x770 fs/afs/rxrpc.c:707 Write of size 1 at addr ffff8880946c39e4 by task kworker/u4:1/21

CPU: 0 PID: 21 Comm: kworker/u4:1 Not tainted 5.8.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: netns cleanup_net Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x18f/0x20d lib/dump_stack.c:118 print_address_description.constprop.0.cold+0xd3/0x413 mm/kasan/report.c:383 __kasan_report mm/kasan/report.c:513 [inline] kasan_report.cold+0x1f/0x37 mm/kasan/report.c:530 afs_wake_up_async_call+0x6aa/0x770 fs/afs/rxrpc.c:707 rxrpc_notify_socket+0x1db/0x5d0 net/rxrpc/recvmsg.c:40 __rxrpc_set_call_completion.part.0+0x172/0x410 net/rxrpc/recvmsg.c:76 __rxrpc_call_completed net/rxrpc/recvmsg.c:112 [inline] rxrpc_call_completed+0xca/0xf0 net/rxrpc/recvmsg.c:111 rxrpc_discard_prealloc+0x781/0xab0 net/rxrpc/call_accept.c:233 rxrpc_listen+0x147/0x360 net/rxrpc/af_rxrpc.c:245 afs_close_socket+0x95/0x320 fs/afs/rxrpc.c:110 afs_net_exit+0x1bc/0x310 fs/afs/main.c:155 ops_exit_list.isra.0+0xa8/0x150 net/core/net_namespace.c:186 cleanup_net+0x511/0xa50 net/core/net_namespace.c:603 process_one_work+0x965/0x1690 kernel/workqueue.c:2269 worker_thread+0x96/0xe10 kernel/workqueue.c:2415 kthread+0x3b5/0x4a0 kernel/kthread.c:291 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:293

Allocated by task 6820: save_stack+0x1b/0x40 mm/kasan/common.c:48 set_track mm/kasan/common.c:56 [inline] __kasan_kmalloc mm/kasan/common.c:494 [inline] __kasan_kmalloc.constprop.0+0xbf/0xd0 mm/kasan/common.c:467 kmem_cache_alloc_trace+0x153/0x7d0 mm/slab.c:3551 kmalloc include/linux/slab.h:555 [inline] kzalloc include/linux/slab.h:669 [inline] afs_alloc_call+0x55/0x630 fs/afs/rxrpc.c:141 afs_charge_preallocation+0xe9/0x2d0 fs/afs/rxrpc.c:757 afs_open_socket+0x292/0x360 fs/afs/rxrpc.c:92 afs_net_init+0xa6c/0xe30 fs/afs/main.c:125 ops_init+0xaf/0x420 net/core/net_namespace.c:151 setup_net+0x2de/0x860 net/core/net_namespace.c:341 copy_net_ns+0x293/0x590 net/core/net_namespace.c:482 create_new_namespaces+0x3fb/0xb30 kernel/nsproxy.c:110 unshare_nsproxy_namespaces+0xbd/0x1f0 kernel/nsproxy.c:231 ksys_unshare+0x43d/0x8e0 kernel/fork.c:2983 __do_sys_unshare kernel/fork.c:3051 [inline] __se_sys_unshare kernel/fork.c:3049 [inline] __x64_sys_unshare+0x2d/0x40 kernel/fork.c:3049 do_syscall_64+0x60/0xe0 arch/x86/entry/common.c:359 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Freed by task 21: save_stack+0x1b/0x40 mm/kasan/common.c:48 set_track mm/kasan/common.c:56 [inline] kasan_set_free_info mm/kasan/common.c:316 [inline] __kasan_slab_free+0xf7/0x140 mm/kasan/common.c:455 __cache_free mm/slab.c:3426 [inline] kfree+0x109/0x2b0 mm/slab.c:3757 afs_put_call+0x585/0xa40 fs/afs/rxrpc.c:190 rxrpc_discard_prealloc+0x764/0xab0 net/rxrpc/call_accept.c:230 rxrpc_listen+0x147/0x360 net/rxrpc/af_rxrpc.c:245 afs_close_socket+0x95/0x320 fs/afs/rxrpc.c:110 afs_net_exit+0x1bc/0x310 fs/afs/main.c:155 ops_exit_list.isra.0+0xa8/0x150 net/core/net_namespace.c:186 cleanup_net+0x511/0xa50 net/core/net_namespace.c:603 process_one_work+0x965/0x1690 kernel/workqueue.c:2269 worker_thread+0x96/0xe10 kernel/workqueue.c:2415 kthread+0x3b5/0x4a0 kernel/kthread.c:291 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:293

The buggy address belongs to the object at ffff8880946c3800 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 484 bytes inside of 1024-byte region [ffff8880946c3800, ffff8880946c3c00) The buggy address belongs to the page: page:ffffea000251b0c0 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 flags: 0xfffe0000000200(slab) raw: 00fffe0000000200 ffffea0002546508 ffffea00024fa248 ffff8880aa000c40 raw: 0000000000000000 ffff8880946c3000 0000000100000002 0000000000000000 page dumped because: kasan: bad access detected

Memory state around the buggy address: ffff8880946c3880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880946c3900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

ffff8880946c3980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

^ ffff8880946c3a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880946c3a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ==================================================================

Reported-by: syzbot+d3eccef36ddbd02713e9@syzkaller.appspotmail.com Fixes: 5ac0d62226a0 ("rxrpc: Fix missing notification") Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/rxrpc/call_accept.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index b7611cc159e51..032ed76c0166d 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -22,6 +22,11 @@ #include <net/ip.h> #include "ar-internal.h"

+static void rxrpc_dummy_notify(struct sock *sk, struct rxrpc_call *call, + unsigned long user_call_ID) +{ +} + /* * Preallocate a single service call, connection and peer and, if possible, * give them a user ID and attach the user's side of the ID to them. @@ -228,6 +233,8 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) if (rx->discard_new_call) { _debug("discard %lx", call->user_call_ID); rx->discard_new_call(call, call->user_call_ID); + if (call->notify_rx) + call->notify_rx = rxrpc_dummy_notify; rxrpc_put_call(call, rxrpc_call_put_kernel); } rxrpc_call_completed(call);

From: Denis Kirjanov kda@linux-powerpc.org

[ Upstream commit 2570284060b48f3f79d8f1a2698792f36c385e9a ]

there is a problem with the CWR flag set in an incoming ACK segment and it leads to the situation when the ECE flag is latched forever

the following packetdrill script shows what happens:

// Stack receives incoming segments with CE set +0.1 <[ect0] . 11001:12001(1000) ack 1001 win 65535 +0.0 <[ce] . 12001:13001(1000) ack 1001 win 65535 +0.0 <[ect0] P. 13001:14001(1000) ack 1001 win 65535

// Stack repsonds with ECN ECHO +0.0 >[noecn] . 1001:1001(0) ack 12001 +0.0 >[noecn] E. 1001:1001(0) ack 13001 +0.0 >[noecn] E. 1001:1001(0) ack 14001

// Write a packet +0.1 write(3, ..., 1000) = 1000 +0.0 >[ect0] PE. 1001:2001(1000) ack 14001

// Pure ACK received +0.01 <[noecn] W. 14001:14001(0) ack 2001 win 65535

// Since CWR was sent, this packet should NOT have ECE set

+0.1 write(3, ..., 1000) = 1000 +0.0 >[ect0] P. 2001:3001(1000) ack 14001 // but Linux will still keep ECE latched here, with packetdrill // flagging a missing ECE flag, expecting // >[ect0] PE. 2001:3001(1000) ack 14001 // in the script

In the situation above we will continue to send ECN ECHO packets and trigger the peer to reduce the congestion window. To avoid that we can check CWR on pure ACKs received.

v3: - Add a sequence check to avoid sending an ACK to an ACK

v2: - Adjusted the comment - move CWR check before checking for unacknowledged packets

Signed-off-by: Denis Kirjanov denis.kirjanov@suse.com Acked-by: Neal Cardwell ncardwell@google.com Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/tcp_input.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 29c6fc8c77168..ccab8bc29e2b1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -261,7 +261,8 @@ static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb) * cwnd may be very low (even just 1 packet), so we should ACK * immediately. */ - inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; + if (TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; } }

@@ -3683,6 +3684,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_in_ack_event(sk, ack_ev_flags); }

+ /* This is a deviation from RFC3168 since it states that: + * "When the TCP data sender is ready to set the CWR bit after reducing + * the congestion window, it SHOULD set the CWR bit only on the first + * new data packet that it transmits." + * We accept CWR on pure ACKs to be more robust + * with widely-deployed TCP implementations that do this. + */ + tcp_ecn_accept_cwr(sk, skb); + /* We passed data and got it acked, remove any soft error * log. Something worked... */ @@ -4780,8 +4790,6 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) skb_dst_drop(skb); __skb_pull(skb, tcp_hdr(skb)->doff * 4);

- tcp_ecn_accept_cwr(sk, skb); - tp->rx_opt.dsack = 0;

/* Queue data for delivery to the user.

From: David Christensen drc@linux.vnet.ibm.com

[ Upstream commit 3a2656a211caf35e56afc9425e6e518fa52f7fbc ]

The driver function tg3_io_error_detected() calls napi_disable twice, without an intervening napi_enable, when the number of EEH errors exceeds eeh_max_freezes, resulting in an indefinite sleep while holding rtnl_lock.

Add check for pcierr_recovery which skips code already executed for the "Frozen" state.

Signed-off-by: David Christensen drc@linux.vnet.ibm.com Reviewed-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/tg3.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index ff98a82b7bc47..d71ce7634ac19 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -18170,8 +18170,8 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,

rtnl_lock();

- /* We probably don't have netdev yet */ - if (!netdev || !netif_running(netdev)) + /* Could be second call or maybe we don't have netdev yet */ + if (!netdev || tp->pcierr_recovery || !netif_running(netdev)) goto done;

/* We needn't recover from permanent error */

From: Florian Fainelli f.fainelli@gmail.com

[ Upstream commit b2ffc75e2e990b09903f9d15ccd53bc5f3a4217c ]

Commit 02a6efcab675 ("net: phy: allow scanning busses with missing phys") added a special condition to return -ENODEV in case -ENODEV or -EIO was returned from the first read of the MII_PHYSID1 register.

In case the MDIO bus data line pull-up is not strong enough, the MDIO bus controller will not flag this as a read error. This can happen when a pluggable daughter card is not connected and weak internal pull-ups are used (since that is the only option, otherwise the pins are floating).

The second read of MII_PHYSID2 will be correctly flagged an error though, but now we will return -EIO which will be treated as a hard error, thus preventing MDIO bus scanning loops to continue succesfully.

Apply the same logic to both register reads, thus allowing the scanning logic to proceed.

Fixes: 02a6efcab675 ("net: phy: allow scanning busses with missing phys") Reviewed-by: Andrew Lunn andrew@lunn.ch Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/phy/phy_device.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 697c74deb222b..0881b4b923632 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -798,8 +798,10 @@ static int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id,

/* Grab the bits from PHYIR2, and put them in the lower half */ phy_reg = mdiobus_read(bus, addr, MII_PHYSID2); - if (phy_reg < 0) - return -EIO; + if (phy_reg < 0) { + /* returning -ENODEV doesn't stop bus scanning */ + return (phy_reg == -EIO || phy_reg == -ENODEV) ? -ENODEV : -EIO; + }

*phy_id |= phy_reg;

From: Michael Chan michael.chan@broadcom.com

[ Upstream commit d0ad2ea2bc185835f8a749302ad07b70528d2a09 ]

We currently only store the firmware version as a string for ethtool and devlink info. Store it also as a version code. The next 2 patches will need to check the firmware major version to determine some workarounds.

We also use the 16-bit firmware version fields if the firmware is newer and provides the 16-bit fields.

Reviewed-by: Edwin Peer edwin.peer@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 22 ++++++++++++++++++---- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 4 ++++ 2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 19c4a0a5727a4..83ed6f31a1fae 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7217,8 +7217,9 @@ static int __bnxt_hwrm_ver_get(struct bnxt *bp, bool silent) static int bnxt_hwrm_ver_get(struct bnxt *bp) { struct hwrm_ver_get_output *resp = bp->hwrm_cmd_resp_addr; + u16 fw_maj, fw_min, fw_bld, fw_rsv; u32 dev_caps_cfg, hwrm_ver; - int rc; + int rc, len;

bp->hwrm_max_req_len = HWRM_MAX_REQ_LEN; mutex_lock(&bp->hwrm_cmd_lock); @@ -7250,9 +7251,22 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp) resp->hwrm_intf_maj_8b, resp->hwrm_intf_min_8b, resp->hwrm_intf_upd_8b);

- snprintf(bp->fw_ver_str, BC_HWRM_STR_LEN, "%d.%d.%d.%d", - resp->hwrm_fw_maj_8b, resp->hwrm_fw_min_8b, - resp->hwrm_fw_bld_8b, resp->hwrm_fw_rsvd_8b); + fw_maj = le16_to_cpu(resp->hwrm_fw_major); + if (bp->hwrm_spec_code > 0x10803 && fw_maj) { + fw_min = le16_to_cpu(resp->hwrm_fw_minor); + fw_bld = le16_to_cpu(resp->hwrm_fw_build); + fw_rsv = le16_to_cpu(resp->hwrm_fw_patch); + len = FW_VER_STR_LEN; + } else { + fw_maj = resp->hwrm_fw_maj_8b; + fw_min = resp->hwrm_fw_min_8b; + fw_bld = resp->hwrm_fw_bld_8b; + fw_rsv = resp->hwrm_fw_rsvd_8b; + len = BC_HWRM_STR_LEN; + } + bp->fw_ver_code = BNXT_FW_VER_CODE(fw_maj, fw_min, fw_bld, fw_rsv); + snprintf(bp->fw_ver_str, len, "%d.%d.%d.%d", fw_maj, fw_min, fw_bld, + fw_rsv);

if (strlen(resp->active_pkg_name)) { int fw_ver_len = strlen(bp->fw_ver_str); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 3d39638521d6c..a880aea0c20b5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1729,6 +1729,10 @@ struct bnxt { #define PHY_VER_STR_LEN (FW_VER_STR_LEN - BC_HWRM_STR_LEN) char fw_ver_str[FW_VER_STR_LEN]; char hwrm_ver_supp[FW_VER_STR_LEN]; + u64 fw_ver_code; +#define BNXT_FW_VER_CODE(maj, min, bld, rsv) \ + ((u64)(maj) << 48 | (u64)(min) << 32 | (u64)(bld) << 16 | (rsv)) + __be16 vxlan_port; u8 vxlan_port_cnt; __le16 vxlan_fw_dst_port_id;

From: Michael Chan michael.chan@broadcom.com

[ Upstream commit c2dec363feb41544a76c8083aca2378990e17166 ]

On older firmware, the hardware statistics are not cleared when the driver frees the hardware stats contexts during ifdown. The driver expects these stats to be cleared and saves a copy before freeing the stats contexts. During the next ifup, the driver will likely allocate the same hardware stats contexts and this will cause a big increase in the counters as the old counters are added back to the saved counters.

We fix it by making an additional firmware call to clear the counters before freeing the hw stats contexts when the firmware is the older 20.x firmware.

Fixes: b8875ca356f1 ("bnxt_en: Save ring statistics before reset.") Reported-by: Jakub Kicinski kicinski@fb.com Reviewed-by: Vasundhara Volam vasundhara-v.volam@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Tested-by: Jakub Kicinski kicinski@fb.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6bf97b3acdadc..c202c2a3d140d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6293,6 +6293,7 @@ int bnxt_hwrm_set_coal(struct bnxt *bp)

static void bnxt_hwrm_stat_ctx_free(struct bnxt *bp) { + struct hwrm_stat_ctx_clr_stats_input req0 = {0}; struct hwrm_stat_ctx_free_input req = {0}; int i;

@@ -6302,6 +6303,7 @@ static void bnxt_hwrm_stat_ctx_free(struct bnxt *bp) if (BNXT_CHIP_TYPE_NITRO_A0(bp)) return;

+ bnxt_hwrm_cmd_hdr_init(bp, &req0, HWRM_STAT_CTX_CLR_STATS, -1, -1); bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_STAT_CTX_FREE, -1, -1);

mutex_lock(&bp->hwrm_cmd_lock); @@ -6311,7 +6313,11 @@ static void bnxt_hwrm_stat_ctx_free(struct bnxt *bp)

if (cpr->hw_stats_ctx_id != INVALID_STATS_CTX_ID) { req.stat_ctx_id = cpu_to_le32(cpr->hw_stats_ctx_id); - + if (BNXT_FW_MAJ(bp) <= 20) { + req0.stat_ctx_id = req.stat_ctx_id; + _hwrm_send_message(bp, &req0, sizeof(req0), + HWRM_CMD_TIMEOUT); + } _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);

From: Russell King rmk+kernel@armlinux.org.uk

[ Upstream commit c718af2d00a37587b09e5958d142da7569f3d55b ]

Fix a phylink's ethtool set_pauseparam support deadlock caused by phylib interacting with phylink: we must not hold the state lock while calling phylib functions that may call into phylink_phy_change().

Fixes: f904f15ea9b5 ("net: phylink: allow ethtool -A to change flow control advertisement") Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/phy/phylink.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 34ca12aec61b3..b0ddeab2a8d2f 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1519,18 +1519,20 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl, linkmode_set_pause(config->advertising, pause->tx_pause, pause->rx_pause);

- /* If we have a PHY, phylib will call our link state function if the - * mode has changed, which will trigger a resolve and update the MAC - * configuration. + if (!pl->phydev && !test_bit(PHYLINK_DISABLE_STOPPED, + &pl->phylink_disable_state)) + phylink_pcs_config(pl, true, &pl->link_config); + + mutex_unlock(&pl->state_mutex); + + /* If we have a PHY, a change of the pause frame advertisement will + * cause phylib to renegotiate (if AN is enabled) which will in turn + * call our phylink_phy_change() and trigger a resolve. Note that + * we can't hold our state mutex while calling phy_set_asym_pause(). */ - if (pl->phydev) { + if (pl->phydev) phy_set_asym_pause(pl->phydev, pause->rx_pause, pause->tx_pause); - } else if (!test_bit(PHYLINK_DISABLE_STOPPED, - &pl->phylink_disable_state)) { - phylink_pcs_config(pl, true, &pl->link_config); - } - mutex_unlock(&pl->state_mutex);

return 0; }

From: Ilya Ponetayev i.ponetaev@ndmsystems.com

[ Upstream commit 9208d2863ac689a563b92f2161d8d1e7127d0add ]

cake_handle_diffserv() tries to linearize mac and network header parts of skb and to make it writable unconditionally. In some cases it leads to full skb reallocation, which reduces throughput and increases CPU load. Some measurements of IPv4 forward + NAPT on MIPS router with 580 MHz single-core CPU was conducted. It appears that on kernel 4.9 skb_try_make_writable() reallocates skb, if skb was allocated in ethernet driver via so-called 'build skb' method from page cache (it was discovered by strange increase of kmalloc-2048 slab at first).

Obtain DSCP value via read-only skb_header_pointer() call, and leave linearization only for DSCP bleaching or ECN CE setting. And, as an additional optimisation, skip diffserv parsing entirely if it is not needed by the current configuration.

Fixes: c87b4ecdbe8d ("sch_cake: Make sure we can write the IP header before changing DSCP bits") Signed-off-by: Ilya Ponetayev i.ponetaev@ndmsystems.com [ fix a few style issues, reflow commit message ] Signed-off-by: Toke Høiland-Jørgensen toke@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/sch_cake.c | 41 ++++++++++++++++++++++++++++++----------- 1 file changed, 30 insertions(+), 11 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 1496e87cd07bb..a92d6c57aa9a5 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1516,30 +1516,49 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)

static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash) { - int wlen = skb_network_offset(skb); + const int offset = skb_network_offset(skb); + u16 *buf, buf_; u8 dscp;

switch (tc_skb_protocol(skb)) { case htons(ETH_P_IP): - wlen += sizeof(struct iphdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) + buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); + if (unlikely(!buf)) return 0;

- dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2; - if (wash && dscp) + /* ToS is in the second byte of iphdr */ + dscp = ipv4_get_dsfield((struct iphdr *)buf) >> 2; + + if (wash && dscp) { + const int wlen = offset + sizeof(struct iphdr); + + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0); + } + return dscp;

case htons(ETH_P_IPV6): - wlen += sizeof(struct ipv6hdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) + buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); + if (unlikely(!buf)) return 0;

- dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; - if (wash && dscp) + /* Traffic class is in the first and second bytes of ipv6hdr */ + dscp = ipv6_get_dsfield((struct ipv6hdr *)buf) >> 2; + + if (wash && dscp) { + const int wlen = offset + sizeof(struct ipv6hdr); + + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0); + } + return dscp;

case htons(ETH_P_ARP):

From: Toke Høiland-Jørgensen toke@redhat.com

[ Upstream commit 3f608f0c41360b11b04c763f348b712f651c8bac ]

I spotted a few nits when comparing the in-tree version of sch_cake with the out-of-tree one: A redundant error variable declaration shadowing an outer declaration, and an indentation alignment issue. Fix both of these.

Fixes: 046f6fd5daef ("sched: Add Common Applications Kept Enhanced (cake) qdisc") Signed-off-by: Toke Høiland-Jørgensen toke@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/sch_cake.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 3482f9569dce5..9475fa81ea7f6 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -2678,7 +2678,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, qdisc_watchdog_init(&q->watchdog, sch);

if (opt) { - int err = cake_change(sch, opt, extack); + err = cake_change(sch, opt, extack);

if (err) return err; @@ -2995,7 +2995,7 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl, PUT_STAT_S32(BLUE_TIMER_US, ktime_to_us( ktime_sub(now, - flow->cvars.blue_timer))); + flow->cvars.blue_timer))); } if (flow->cvars.dropping) { PUT_STAT_S32(DROP_NEXT_US,

From: Neal Cardwell ncardwell@google.com

[ Upstream commit 7d21d54d624777358ab6c7be7ff778808fef70ba ]

Apply the fix from: "tcp_cubic: fix spurious HYSTART_DELAY exit upon drop in min RTT" to the BPF implementation of TCP CUBIC congestion control.

Repeating the commit description here for completeness:

Mirja Kuehlewind reported a bug in Linux TCP CUBIC Hystart, where Hystart HYSTART_DELAY mechanism can exit Slow Start spuriously on an ACK when the minimum rtt of a connection goes down. From inspection it is clear from the existing code that this could happen in an example like the following:

o The first 8 RTT samples in a round trip are 150ms, resulting in a curr_rtt of 150ms and a delay_min of 150ms.

o The 9th RTT sample is 100ms. The curr_rtt does not change after the first 8 samples, so curr_rtt remains 150ms. But delay_min can be lowered at any time, so delay_min falls to 100ms. The code executes the HYSTART_DELAY comparison between curr_rtt of 150ms and delay_min of 100ms, and the curr_rtt is declared far enough above delay_min to force a (spurious) exit of Slow start.

The fix here is simple: allow every RTT sample in a round trip to lower the curr_rtt.

Fixes: 6de4a9c430b5 ("bpf: tcp: Add bpf_cubic example") Reported-by: Mirja Kuehlewind mirja.kuehlewind@ericsson.com Signed-off-by: Neal Cardwell ncardwell@google.com Signed-off-by: Eric Dumazet edumazet@google.com Acked-by: Soheil Hassas Yeganeh soheil@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/bpf/progs/bpf_cubic.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c index 7897c8f4d363b..ef574087f1e1f 100644 --- a/tools/testing/selftests/bpf/progs/bpf_cubic.c +++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c @@ -480,10 +480,9 @@ static __always_inline void hystart_update(struct sock *sk, __u32 delay)

if (hystart_detect & HYSTART_DELAY) { /* obtain the minimum delay of more than sampling packets */ + if (ca->curr_rtt > delay) + ca->curr_rtt = delay; if (ca->sample_cnt < HYSTART_MIN_SAMPLES) { - if (ca->curr_rtt > delay) - ca->curr_rtt = delay; - ca->sample_cnt++; } else { if (ca->curr_rtt > ca->delay_min +

From: Heiner Kallweit hkallweit1@gmail.com

[ Upstream commit 89fbd26cca7ec9e82ec4787a4b6e95939b57d073 ]

Typically the firmware takes care that tp->ocp_base is reset to its default value. That's not the case (at least) for RTL8117. As a result subsequent PHY access reads/writes the wrong page and the link is broken. Fix this be resetting tp->ocp_base explicitly.

Fixes: 229c1e0dfd3d ("r8169: load firmware for RTL8168fp/RTL8117") Reported-by: Aaron Ma mapengyu@gmail.com Tested-by: Aaron Ma mapengyu@gmail.com Signed-off-by: Heiner Kallweit hkallweit1@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/realtek/r8169_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index c51b48dc36397..7bda2671bd5b6 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2192,8 +2192,11 @@ static void rtl_release_firmware(struct rtl8169_private *tp) void r8169_apply_firmware(struct rtl8169_private *tp) { /* TODO: release firmware if rtl_fw_write_firmware signals failure. */ - if (tp->rtl_fw) + if (tp->rtl_fw) { rtl_fw_write_firmware(tp, tp->rtl_fw); + /* At least one firmware doesn't reset tp->ocp_base. */ + tp->ocp_base = OCP_STD_PHY_BASE; + } }

static void rtl8168_config_eee_mac(struct rtl8169_private *tp)

From: Wei Yongjun weiyongjun1@huawei.com

[ Upstream commit b8ad540dd4e40566c520dff491fc06c71ae6b989 ]

socket malloced by sock_create_kern() should be release before return in the error handling, otherwise it cause memory leak.

unreferenced object 0xffff88810910c000 (size 1216): comm "00000003_test_m", pid 12238, jiffies 4295050289 (age 54.237s) hex dump (first 32 bytes): 01 00 00 00 01 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 2f 30 0a 81 88 ff ff ........./0..... backtrace: [<00000000e877f89f>] sock_alloc_inode+0x18/0x1c0 [<0000000093d1dd51>] alloc_inode+0x63/0x1d0 [<000000005673fec6>] new_inode_pseudo+0x14/0xe0 [<00000000b5db6be8>] sock_alloc+0x3c/0x260 [<00000000e7e3cbb2>] __sock_create+0x89/0x620 [<0000000023e48593>] mptcp_subflow_create_socket+0xc0/0x5e0 [<00000000419795e4>] __mptcp_socket_create+0x1ad/0x3f0 [<00000000b2f942e8>] mptcp_stream_connect+0x281/0x4f0 [<00000000c80cd5cc>] __sys_connect_file+0x14d/0x190 [<00000000dc761f11>] __sys_connect+0x128/0x160 [<000000008b14e764>] __x64_sys_connect+0x6f/0xb0 [<000000007b4f93bd>] do_syscall_64+0xa1/0x530 [<00000000d3e770b6>] entry_SYSCALL_64_after_hwframe+0x49/0xb3

Fixes: 2303f994b3e1 ("mptcp: Associate MPTCP context with TCP socket") Signed-off-by: Wei Yongjun weiyongjun1@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/mptcp/subflow.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index e6feb05a93dc3..db3e4e74e7857 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1015,8 +1015,10 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) err = tcp_set_ulp(sf->sk, "mptcp"); release_sock(sf->sk);

- if (err) + if (err) { + sock_release(sf); return err; + }

/* the newly created socket really belongs to the owning MPTCP master * socket, even if for additional subflows the allocation is performed

From: Claudiu Beznea claudiu.beznea@microchip.com

[ Upstream commit 0eaf228d574bd82a9aed73e3953bfb81721f4227 ]

Call pm_runtime_put_sync() on failure path of at91ether_open.

Fixes: e6a41c23df0d ("net: macb: ensure interface is not suspended on at91rm9200") Signed-off-by: Claudiu Beznea claudiu.beznea@microchip.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/cadence/macb_main.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 257c4920cb886..5705359a36124 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -3837,7 +3837,7 @@ static int at91ether_open(struct net_device *dev)

ret = at91ether_start(dev); if (ret) - return ret; + goto pm_exit;

/* Enable MAC interrupts */ macb_writel(lp, IER, MACB_BIT(RCOMP) | @@ -3850,11 +3850,15 @@ static int at91ether_open(struct net_device *dev)

ret = macb_phylink_connect(lp); if (ret) - return ret; + goto pm_exit;

netif_start_queue(dev);

return 0; + +pm_exit: + pm_runtime_put_sync(&lp->pdev->dev); + return ret; }

/* Close the interface */

From: Florian Fainelli f.fainelli@gmail.com

[ Upstream commit 5a8d7f126c97d04d893f5e5be2b286437a0d01b0 ]

Commit 209c65b61d94 ("drivers/of/of_mdio.c:fix of_mdiobus_register()") introduced a break of the loop on the premise that a successful registration should exit the loop. The premise is correct but not to code, because rc && rc != -ENODEV is just a special error condition, that means we would exit the loop even with rc == -ENODEV which is absolutely not correct since this is the error code to indicate to the MDIO bus layer that scanning should continue.

Fix this by explicitly checking for rc = 0 as the only valid condition to break out of the loop.

Fixes: 209c65b61d94 ("drivers/of/of_mdio.c:fix of_mdiobus_register()") Reviewed-by: Andrew Lunn andrew@lunn.ch Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/of/of_mdio.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 9f982c0627a0d..95a3bb2e5eabf 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -303,10 +303,15 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) child, addr);

if (of_mdiobus_child_is_phy(child)) { + /* -ENODEV is the return code that PHYLIB has + * standardized on to indicate that bus + * scanning should continue. + */ rc = of_mdiobus_register_phy(mdio, child, addr); - if (rc && rc != -ENODEV) + if (!rc) + break; + if (rc != -ENODEV) goto unregister; - break; } } }

From: Martin martin.varghese@nokia.com

[ Upstream commit 4c98045c9b74feab837be58986c0517d3cc661f1 ]

Code to handle multiproto configuration is missing.

Fixes: 4b5f67232d95 ("net: Special handling for IP & MPLS") Signed-off-by: Martin martin.varghese@nokia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/bareudp.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index 5d3c691a1c668..3dd46cd551145 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -572,6 +572,9 @@ static int bareudp2info(struct nlattr *data[], struct bareudp_conf *conf, if (data[IFLA_BAREUDP_SRCPORT_MIN]) conf->sport_min = nla_get_u16(data[IFLA_BAREUDP_SRCPORT_MIN]);

+ if (data[IFLA_BAREUDP_MULTIPROTO_MODE]) + conf->multi_proto_mode = true; + return 0; }

From: Florian Fainelli f.fainelli@gmail.com

[ Upstream commit 8dbe4c5d5e40fe140221024f7b16bec9f310bf70 ]

of_find_node_by_name() will do an of_node_put() on the "from" argument. With CONFIG_OF_DYNAMIC enabled which checks for device_node reference counts, we would be getting a warning like this:

[ 6.347230] refcount_t: increment on 0; use-after-free. [ 6.352498] WARNING: CPU: 3 PID: 77 at lib/refcount.c:156 refcount_inc_checked+0x38/0x44 [ 6.360601] Modules linked in: [ 6.363661] CPU: 3 PID: 77 Comm: kworker/3:1 Tainted: G W 5.4.46-gb78b3e9956e6 #13 [ 6.372546] Hardware name: BCM97278SV (DT) [ 6.376649] Workqueue: events deferred_probe_work_func [ 6.381796] pstate: 60000005 (nZCv daif -PAN -UAO) [ 6.386595] pc : refcount_inc_checked+0x38/0x44 [ 6.391133] lr : refcount_inc_checked+0x38/0x44 ... [ 6.478791] Call trace: [ 6.481243] refcount_inc_checked+0x38/0x44 [ 6.485433] kobject_get+0x3c/0x4c [ 6.488840] of_node_get+0x24/0x34 [ 6.492247] of_irq_find_parent+0x3c/0xe0 [ 6.496263] of_irq_parse_one+0xe4/0x1d0 [ 6.500191] irq_of_parse_and_map+0x44/0x84 [ 6.504381] bcm_sf2_sw_probe+0x22c/0x844 [ 6.508397] platform_drv_probe+0x58/0xa8 [ 6.512413] really_probe+0x238/0x3fc [ 6.516081] driver_probe_device+0x11c/0x12c [ 6.520358] __device_attach_driver+0xa8/0x100 [ 6.524808] bus_for_each_drv+0xb4/0xd0 [ 6.528650] __device_attach+0xd0/0x164 [ 6.532493] device_initial_probe+0x24/0x30 [ 6.536682] bus_probe_device+0x38/0x98 [ 6.540524] deferred_probe_work_func+0xa8/0xd4 [ 6.545061] process_one_work+0x178/0x288 [ 6.549078] process_scheduled_works+0x44/0x48 [ 6.553529] worker_thread+0x218/0x270 [ 6.557285] kthread+0xdc/0xe4 [ 6.560344] ret_from_fork+0x10/0x18 [ 6.563925] ---[ end trace 68f65caf69bb152a ]---

Fix this by adding a of_node_get() to increment the reference count prior to the call.

Fixes: afa3b592953b ("net: dsa: bcm_sf2: Ensure correct sub-node is parsed") Signed-off-by: Florian Fainelli f.fainelli@gmail.com Reviewed-by: Andrew Lunn andrew@lunn.ch Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/dsa/bcm_sf2.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index c7ac63f419184..946e41f020a56 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1147,6 +1147,8 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) set_bit(0, priv->cfp.used); set_bit(0, priv->cfp.unique);

+ /* Balance of_node_put() done by of_find_node_by_name() */ + of_node_get(dn); ports = of_find_node_by_name(dn, "ports"); if (ports) { bcm_sf2_identify_ports(priv, ports);

From: Cong Wang xiyou.wangcong@gmail.com

[ Upstream commit b65ce380b754e77fbfdcfc83fd6e29c8ceedf431 ]

genl_family_rcv_msg_attrs_parse() and genl_family_rcv_msg_attrs_free() take a boolean parameter to determine whether allocate/free the family attrs. This is unnecessary as we can just check family->parallel_ops. More importantly, callers would not need to worry about pairing these parameters correctly after this patch.

And this fixes a memory leak, as after commit c36f05559104 ("genetlink: fix memory leaks in genl_family_rcv_msg_dumpit()") we call genl_family_rcv_msg_attrs_parse() for both parallel and non-parallel cases.

Fixes: c36f05559104 ("genetlink: fix memory leaks in genl_family_rcv_msg_dumpit()") Reported-by: Ido Schimmel idosch@idosch.org Signed-off-by: Cong Wang xiyou.wangcong@gmail.com Reviewed-by: Ido Schimmel idosch@mellanox.com Tested-by: Ido Schimmel idosch@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/netlink/genetlink.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-)

diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index bcbba0bef1c2a..9c1c27f3a0894 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -474,8 +474,7 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, struct netlink_ext_ack *extack, const struct genl_ops *ops, int hdrlen, - enum genl_validate_flags no_strict_flag, - bool parallel) + enum genl_validate_flags no_strict_flag) { enum netlink_validation validate = ops->validate & no_strict_flag ? NL_VALIDATE_LIBERAL : @@ -486,7 +485,7 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, if (!family->maxattr) return NULL;

- if (parallel) { + if (family->parallel_ops) { attrbuf = kmalloc_array(family->maxattr + 1, sizeof(struct nlattr *), GFP_KERNEL); if (!attrbuf) @@ -498,7 +497,7 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr, family->policy, validate, extack); if (err) { - if (parallel) + if (family->parallel_ops) kfree(attrbuf); return ERR_PTR(err); } @@ -506,10 +505,9 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, }

static void genl_family_rcv_msg_attrs_free(const struct genl_family *family, - struct nlattr **attrbuf, - bool parallel) + struct nlattr **attrbuf) { - if (parallel) + if (family->parallel_ops) kfree(attrbuf); }

@@ -537,15 +535,14 @@ static int genl_start(struct netlink_callback *cb)

attrs = genl_family_rcv_msg_attrs_parse(ctx->family, ctx->nlh, ctx->extack, ops, ctx->hdrlen, - GENL_DONT_VALIDATE_DUMP_STRICT, - true); + GENL_DONT_VALIDATE_DUMP_STRICT); if (IS_ERR(attrs)) return PTR_ERR(attrs);

no_attrs: info = genl_dumpit_info_alloc(); if (!info) { - kfree(attrs); + genl_family_rcv_msg_attrs_free(ctx->family, attrs); return -ENOMEM; } info->family = ctx->family; @@ -562,7 +559,7 @@ no_attrs: }

if (rc) { - kfree(attrs); + genl_family_rcv_msg_attrs_free(info->family, info->attrs); genl_dumpit_info_free(info); cb->data = NULL; } @@ -591,7 +588,7 @@ static int genl_lock_done(struct netlink_callback *cb) rc = ops->done(cb); genl_unlock(); } - genl_family_rcv_msg_attrs_free(info->family, info->attrs, false); + genl_family_rcv_msg_attrs_free(info->family, info->attrs); genl_dumpit_info_free(info); return rc; } @@ -604,7 +601,7 @@ static int genl_parallel_done(struct netlink_callback *cb)

if (ops->done) rc = ops->done(cb); - genl_family_rcv_msg_attrs_free(info->family, info->attrs, true); + genl_family_rcv_msg_attrs_free(info->family, info->attrs); genl_dumpit_info_free(info); return rc; } @@ -671,8 +668,7 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family,

attrbuf = genl_family_rcv_msg_attrs_parse(family, nlh, extack, ops, hdrlen, - GENL_DONT_VALIDATE_STRICT, - family->parallel_ops); + GENL_DONT_VALIDATE_STRICT); if (IS_ERR(attrbuf)) return PTR_ERR(attrbuf);

@@ -698,7 +694,7 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family, family->post_doit(ops, skb, &info);

out: - genl_family_rcv_msg_attrs_free(family, attrbuf, family->parallel_ops); + genl_family_rcv_msg_attrs_free(family, attrbuf);

return err; }

From: Chaitanya Kulkarni chaitanya.kulkarni@wdc.com

[ Upstream commit 819f7b88b48fd2bce932cfe3a38bf8fcefbcabe7 ]

In function nvmet_async_event_process() we only process AENs iff there is an open slot on the ctrl->async_event_cmds[] && aen event list posted by the target is not empty. This keeps host posted AEN outstanding if target generated AEN list is empty. We do cleanup the target generated entries from the aen list in nvmet_ctrl_free()-> nvmet_async_events_free() but we don't process AEN posted by the host. This leads to following problem :-

When processing admin sq at the time of nvmet_sq_destroy() holds an extra percpu reference(atomic value = 1), so in the following code path after switching to atomic rcu, release function (nvmet_sq_free()) is not getting called which blocks the sq->free_done in nvmet_sq_destroy() :-

nvmet_sq_destroy() percpu_ref_kill_and_confirm() - __percpu_ref_switch_mode() -- __percpu_ref_switch_to_atomic() --- call_rcu() -> percpu_ref_switch_to_atomic_rcu() ---- /* calls switch callback */ - percpu_ref_put() -- percpu_ref_put_many(ref, 1) --- else if (unlikely(atomic_long_sub_and_test(nr, &ref->count))) ---- ref->release(ref); <---- Not called.

This results in indefinite hang:-

void nvmet_sq_destroy(struct nvmet_sq *sq) ... if (ctrl && ctrl->sqs && ctrl->sqs[0] == sq) { nvmet_async_events_process(ctrl, status); percpu_ref_put(&sq->ref); } percpu_ref_kill_and_confirm(&sq->ref, nvmet_confirm_sq); wait_for_completion(&sq->confirm_done); wait_for_completion(&sq->free_done); <-- Hang here

Which breaks the further disconnect sequence. This problem seems to be introduced after commit 64f5e9cdd711b ("nvmet: fix memory leak when removing namespaces and controllers concurrently").

This patch processes ctrl->async_event_cmds[] in the admin sq destroy() context irrespetive of aen_list. Also we get rid of the controller's aen_list processing in the nvmet_sq_destroy() context and just ignore ctrl->aen_list.

This results in nvmet_async_events_process() being called from workqueue context so we adjust the code accordingly.

Fixes: 64f5e9cdd711 ("nvmet: fix memory leak when removing namespaces and controllers concurrently ") Signed-off-by: Chaitanya Kulkarni chaitanya.kulkarni@wdc.com Reviewed-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/target/core.c | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index ac7ae031ce78d..96deaf3484662 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -129,7 +129,22 @@ static u32 nvmet_async_event_result(struct nvmet_async_event *aen) return aen->event_type | (aen->event_info << 8) | (aen->log_page << 16); }

-static void nvmet_async_events_process(struct nvmet_ctrl *ctrl, u16 status) +static void nvmet_async_events_failall(struct nvmet_ctrl *ctrl) +{ + u16 status = NVME_SC_INTERNAL | NVME_SC_DNR; + struct nvmet_req *req; + + mutex_lock(&ctrl->lock); + while (ctrl->nr_async_event_cmds) { + req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds]; + mutex_unlock(&ctrl->lock); + nvmet_req_complete(req, status); + mutex_lock(&ctrl->lock); + } + mutex_unlock(&ctrl->lock); +} + +static void nvmet_async_events_process(struct nvmet_ctrl *ctrl) { struct nvmet_async_event *aen; struct nvmet_req *req; @@ -139,14 +154,13 @@ static void nvmet_async_events_process(struct nvmet_ctrl *ctrl, u16 status) aen = list_first_entry(&ctrl->async_events, struct nvmet_async_event, entry); req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds]; - if (status == 0) - nvmet_set_result(req, nvmet_async_event_result(aen)); + nvmet_set_result(req, nvmet_async_event_result(aen));

list_del(&aen->entry); kfree(aen);

mutex_unlock(&ctrl->lock); - nvmet_req_complete(req, status); + nvmet_req_complete(req, 0); mutex_lock(&ctrl->lock); } mutex_unlock(&ctrl->lock); @@ -169,7 +183,7 @@ static void nvmet_async_event_work(struct work_struct *work) struct nvmet_ctrl *ctrl = container_of(work, struct nvmet_ctrl, async_event_work);

- nvmet_async_events_process(ctrl, 0); + nvmet_async_events_process(ctrl); }

void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type, @@ -752,7 +766,6 @@ static void nvmet_confirm_sq(struct percpu_ref *ref)

void nvmet_sq_destroy(struct nvmet_sq *sq) { - u16 status = NVME_SC_INTERNAL | NVME_SC_DNR; struct nvmet_ctrl *ctrl = sq->ctrl;

/* @@ -760,7 +773,7 @@ void nvmet_sq_destroy(struct nvmet_sq *sq) * queue doesn't have outstanding requests on it. */ if (ctrl && ctrl->sqs && ctrl->sqs[0] == sq) - nvmet_async_events_process(ctrl, status); + nvmet_async_events_failall(ctrl); percpu_ref_kill_and_confirm(&sq->ref, nvmet_confirm_sq); wait_for_completion(&sq->confirm_done); wait_for_completion(&sq->free_done);

From: Takashi Iwai tiwai@suse.de

[ Upstream commit ff58bbc7b9704a5869204176f804eff57307fef0 ]

With the recent full-duplex support of implicit feedback streams, an endpoint can be still running after closing the capture stream as long as the playback stream with the sync-endpoint is running. In such a state, the URBs are still be handled and they may call retire_data_urb callback, which tries to transfer the data from the PCM buffer. Since the PCM stream gets closed, this may lead to use-after-free.

This patch adds the proper clearance of the callback at stopping the capture stream for addressing the possible UAF above.

Fixes: 10ce77e4817f ("ALSA: usb-audio: Add duplex sound support for USB devices using implicit feedback") Link: https://lore.kernel.org/r/20200616120921.12249-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/usb/pcm.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index d61c2f1095b5c..3411e27eb64bb 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -1782,6 +1782,7 @@ static int snd_usb_substream_capture_trigger(struct snd_pcm_substream *substream return 0; case SNDRV_PCM_TRIGGER_STOP: stop_endpoints(subs); + subs->data_endpoint->retire_data_urb = NULL; subs->running = 0; return 0; case SNDRV_PCM_TRIGGER_PAUSE_PUSH:

From: Filipe Manana fdmanana@suse.com

[ Upstream commit 9fecd13202f520f3f25d5b1c313adb740fe19773 ]

When removing a block group, if we fail to delete the block group's item from the extent tree, we jump to the 'out' label and end up decrementing the block group's reference count once only (by 1), resulting in a counter leak because the block group at that point was already removed from the block group cache rbtree - so we have to decrement the reference count twice, once for the rbtree and once for our lookup at the start of the function.

There is a second bug where if removing the free space tree entries (the call to remove_block_group_free_space()) fails we end up jumping to the 'out_put_group' label but end up decrementing the reference count only once, when we should have done it twice, since we have already removed the block group from the block group cache rbtree. This happens because the reference count decrement for the rbtree reference happens after attempting to remove the free space tree entries, which is far away from the place where we remove the block group from the rbtree.

To make things less error prone, decrement the reference count for the rbtree immediately after removing the block group from it. This also eleminates the need for two different exit labels on error, renaming 'out_put_label' to just 'out' and removing the old 'out'.

Fixes: f6033c5e333238 ("btrfs: fix block group leak when removing fails") CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Nikolay Borisov nborisov@suse.com Reviewed-by: Anand Jain anand.jain@oracle.com Signed-off-by: Filipe Manana fdmanana@suse.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/block-group.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 233c5663f2332..0c17f18b47940 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -916,7 +916,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; - goto out_put_group; + goto out; }

/* @@ -954,7 +954,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, ret = btrfs_orphan_add(trans, BTRFS_I(inode)); if (ret) { btrfs_add_delayed_iput(inode); - goto out_put_group; + goto out; } clear_nlink(inode); /* One for the block groups ref */ @@ -977,13 +977,13 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,

ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); if (ret < 0) - goto out_put_group; + goto out; if (ret > 0) btrfs_release_path(path); if (ret == 0) { ret = btrfs_del_item(trans, tree_root, path); if (ret) - goto out_put_group; + goto out; btrfs_release_path(path); }

@@ -992,6 +992,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, &fs_info->block_group_cache_tree); RB_CLEAR_NODE(&block_group->cache_node);

+ /* Once for the block groups rbtree */ + btrfs_put_block_group(block_group); + if (fs_info->first_logical_byte == block_group->start) fs_info->first_logical_byte = (u64)-1; spin_unlock(&fs_info->block_group_cache_lock); @@ -1102,10 +1105,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,

ret = remove_block_group_free_space(trans, block_group); if (ret) - goto out_put_group; - - /* Once for the block groups rbtree */ - btrfs_put_block_group(block_group); + goto out;

ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret > 0) @@ -1128,10 +1128,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, free_extent_map(em); }

-out_put_group: +out: /* Once for the lookup reference */ btrfs_put_block_group(block_group); -out: if (remove_rsv) btrfs_delayed_refs_rsv_release(fs_info, 1); btrfs_free_path(path);

From: Tomas Winkler tomas.winkler@intel.com

commit f76d77f50b343bc7f7d01e4c2771d43fb074f617 upstream.

For SPS firmware versions 5.0 and newer the way detection has changed. The detection is done now via PCI_CFG_HFS_3 register. To prevent conflict the previous method will get sps_4 suffix Disable both CNP_H and CNP_H_3 interfaces. CNP_H_3 requires a separate configuration as it doesn't support DMA.

Cc: stable@vger.kernel.org Signed-off-by: Tomas Winkler tomas.winkler@intel.com Link: https://lore.kernel.org/r/20200619165121.2145330-1-tomas.winkler@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/misc/mei/hw-me-regs.h | 2 ++ drivers/misc/mei/hw-me.c | 60 +++++++++++++++++++++++++++++++---- drivers/misc/mei/hw-me.h | 13 +++++--- drivers/misc/mei/pci-me.c | 16 +++++----- 4 files changed, 73 insertions(+), 18 deletions(-)

diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index 9392934e3a060..01b1bf74f2626 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -107,6 +107,8 @@ # define PCI_CFG_HFS_1_D0I3_MSK 0x80000000 #define PCI_CFG_HFS_2 0x48 #define PCI_CFG_HFS_3 0x60 +# define PCI_CFG_HFS_3_FW_SKU_MSK 0x00000070 +# define PCI_CFG_HFS_3_FW_SKU_SPS 0x00000060 #define PCI_CFG_HFS_4 0x64 #define PCI_CFG_HFS_5 0x68 #define PCI_CFG_HFS_6 0x6C diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index f620442addf52..f8155c1e811d7 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -1366,7 +1366,7 @@ static bool mei_me_fw_type_nm(struct pci_dev *pdev) #define MEI_CFG_FW_NM \ .quirk_probe = mei_me_fw_type_nm

-static bool mei_me_fw_type_sps(struct pci_dev *pdev) +static bool mei_me_fw_type_sps_4(struct pci_dev *pdev) { u32 reg; unsigned int devfn; @@ -1382,7 +1382,36 @@ static bool mei_me_fw_type_sps(struct pci_dev *pdev) return (reg & 0xf0000) == 0xf0000; }

-#define MEI_CFG_FW_SPS \ +#define MEI_CFG_FW_SPS_4 \ + .quirk_probe = mei_me_fw_type_sps_4 + +/** + * mei_me_fw_sku_sps() - check for sps sku + * + * Read ME FW Status register to check for SPS Firmware. + * The SPS FW is only signaled in pci function 0 + * + * @pdev: pci device + * + * Return: true in case of SPS firmware + */ +static bool mei_me_fw_type_sps(struct pci_dev *pdev) +{ + u32 reg; + u32 fw_type; + unsigned int devfn; + + devfn = PCI_DEVFN(PCI_SLOT(pdev->devfn), 0); + pci_bus_read_config_dword(pdev->bus, devfn, PCI_CFG_HFS_3, &reg); + trace_mei_pci_cfg_read(&pdev->dev, "PCI_CFG_HFS_3", PCI_CFG_HFS_3, reg); + fw_type = (reg & PCI_CFG_HFS_3_FW_SKU_MSK); + + dev_dbg(&pdev->dev, "fw type is %d\n", fw_type); + + return fw_type == PCI_CFG_HFS_3_FW_SKU_SPS; +} + +#define MEI_CFG_FW_SPS \ .quirk_probe = mei_me_fw_type_sps

#define MEI_CFG_FW_VER_SUPP \ @@ -1452,10 +1481,17 @@ static const struct mei_cfg mei_me_pch8_cfg = { };

/* PCH8 Lynx Point with quirk for SPS Firmware exclusion */ -static const struct mei_cfg mei_me_pch8_sps_cfg = { +static const struct mei_cfg mei_me_pch8_sps_4_cfg = { MEI_CFG_PCH8_HFS, MEI_CFG_FW_VER_SUPP, - MEI_CFG_FW_SPS, + MEI_CFG_FW_SPS_4, +}; + +/* LBG with quirk for SPS (4.0) Firmware exclusion */ +static const struct mei_cfg mei_me_pch12_sps_4_cfg = { + MEI_CFG_PCH8_HFS, + MEI_CFG_FW_VER_SUPP, + MEI_CFG_FW_SPS_4, };

/* Cannon Lake and newer devices */ @@ -1465,8 +1501,18 @@ static const struct mei_cfg mei_me_pch12_cfg = { MEI_CFG_DMA_128, };

-/* LBG with quirk for SPS Firmware exclusion */ +/* Cannon Lake with quirk for SPS 5.0 and newer Firmware exclusion */ static const struct mei_cfg mei_me_pch12_sps_cfg = { + MEI_CFG_PCH8_HFS, + MEI_CFG_FW_VER_SUPP, + MEI_CFG_DMA_128, + MEI_CFG_FW_SPS, +}; + +/* Cannon Lake with quirk for SPS 5.0 and newer Firmware exclusion + * w/o DMA support + */ +static const struct mei_cfg mei_me_pch12_nodma_sps_cfg = { MEI_CFG_PCH8_HFS, MEI_CFG_FW_VER_SUPP, MEI_CFG_FW_SPS, @@ -1492,9 +1538,11 @@ static const struct mei_cfg *const mei_cfg_list[] = { [MEI_ME_PCH7_CFG] = &mei_me_pch7_cfg, [MEI_ME_PCH_CPT_PBG_CFG] = &mei_me_pch_cpt_pbg_cfg, [MEI_ME_PCH8_CFG] = &mei_me_pch8_cfg, - [MEI_ME_PCH8_SPS_CFG] = &mei_me_pch8_sps_cfg, + [MEI_ME_PCH8_SPS_4_CFG] = &mei_me_pch8_sps_4_cfg, [MEI_ME_PCH12_CFG] = &mei_me_pch12_cfg, + [MEI_ME_PCH12_SPS_4_CFG] = &mei_me_pch12_sps_4_cfg, [MEI_ME_PCH12_SPS_CFG] = &mei_me_pch12_sps_cfg, + [MEI_ME_PCH12_SPS_NODMA_CFG] = &mei_me_pch12_nodma_sps_cfg, [MEI_ME_PCH15_CFG] = &mei_me_pch15_cfg, };

diff --git a/drivers/misc/mei/hw-me.h b/drivers/misc/mei/hw-me.h index b6b94e2114645..52e0c6d578f27 100644 --- a/drivers/misc/mei/hw-me.h +++ b/drivers/misc/mei/hw-me.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Copyright (c) 2012-2019, Intel Corporation. All rights reserved. + * Copyright (c) 2012-2020, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver */

@@ -76,11 +76,14 @@ struct mei_me_hw { * with quirk for Node Manager exclusion. * @MEI_ME_PCH8_CFG: Platform Controller Hub Gen8 and newer * client platforms. - * @MEI_ME_PCH8_SPS_CFG: Platform Controller Hub Gen8 and newer + * @MEI_ME_PCH8_SPS_4_CFG: Platform Controller Hub Gen8 and newer * servers platforms with quirk for * SPS firmware exclusion. * @MEI_ME_PCH12_CFG: Platform Controller Hub Gen12 and newer - * @MEI_ME_PCH12_SPS_CFG: Platform Controller Hub Gen12 and newer + * @MEI_ME_PCH12_SPS_4_CFG:Platform Controller Hub Gen12 up to 4.0 + * servers platforms with quirk for + * SPS firmware exclusion. + * @MEI_ME_PCH12_SPS_CFG: Platform Controller Hub Gen12 5.0 and newer * servers platforms with quirk for * SPS firmware exclusion. * @MEI_ME_PCH15_CFG: Platform Controller Hub Gen15 and newer @@ -94,9 +97,11 @@ enum mei_cfg_idx { MEI_ME_PCH7_CFG, MEI_ME_PCH_CPT_PBG_CFG, MEI_ME_PCH8_CFG, - MEI_ME_PCH8_SPS_CFG, + MEI_ME_PCH8_SPS_4_CFG, MEI_ME_PCH12_CFG, + MEI_ME_PCH12_SPS_4_CFG, MEI_ME_PCH12_SPS_CFG, + MEI_ME_PCH12_SPS_NODMA_CFG, MEI_ME_PCH15_CFG, MEI_ME_NUM_CFG, }; diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index a1ed375fed374..f74c6113812d6 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -59,18 +59,18 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_PPT_1, MEI_ME_PCH7_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_PPT_2, MEI_ME_PCH7_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_PPT_3, MEI_ME_PCH7_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_H, MEI_ME_PCH8_SPS_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_W, MEI_ME_PCH8_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_H, MEI_ME_PCH8_SPS_4_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_W, MEI_ME_PCH8_SPS_4_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_LP, MEI_ME_PCH8_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_HR, MEI_ME_PCH8_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_HR, MEI_ME_PCH8_SPS_4_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_WPT_LP, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_WPT_LP_2, MEI_ME_PCH8_CFG)},

{MEI_PCI_DEVICE(MEI_DEV_ID_SPT, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_2, MEI_ME_PCH8_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, MEI_ME_PCH8_SPS_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, MEI_ME_PCH8_SPS_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, MEI_ME_PCH8_SPS_4_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, MEI_ME_PCH8_SPS_4_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_SPS_4_CFG)},

{MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, MEI_ME_PCH8_CFG)}, @@ -84,8 +84,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = {

{MEI_PCI_DEVICE(MEI_DEV_ID_CNP_LP, MEI_ME_PCH12_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_LP_3, MEI_ME_PCH8_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H, MEI_ME_PCH12_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H_3, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H, MEI_ME_PCH12_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H_3, MEI_ME_PCH12_SPS_NODMA_CFG)},

{MEI_PCI_DEVICE(MEI_DEV_ID_CMP_LP, MEI_ME_PCH12_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_CMP_LP_3, MEI_ME_PCH8_CFG)},

From: Anand Moon linux.amoon@gmail.com

commit ad38beb373a14e082f4e64b68c0b6e6b09764680 upstream.

This reverts commit 07f6842341abe978e6375078f84506ec3280ece5.

Since SCLK_SCLK_USBD300 suspend clock need to be configured for phy module, I wrongly mapped this clock to DWC3 code.

Cc: Felipe Balbi balbi@kernel.org Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Anand Moon linux.amoon@gmail.com Cc: stable stable@vger.kernel.org Fixes: 07f6842341ab ("usb: dwc3: exynos: Add support for Exynos5422 suspend clk") Link: https://lore.kernel.org/r/20200623074637.756-1-linux.amoon@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/dwc3/dwc3-exynos.c | 9 --------- 1 file changed, 9 deletions(-)

diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c index 48b68b6f0dc82..90bb022737da8 100644 --- a/drivers/usb/dwc3/dwc3-exynos.c +++ b/drivers/usb/dwc3/dwc3-exynos.c @@ -162,12 +162,6 @@ static const struct dwc3_exynos_driverdata exynos5250_drvdata = { .suspend_clk_idx = -1, };

-static const struct dwc3_exynos_driverdata exynos5420_drvdata = { - .clk_names = { "usbdrd30", "usbdrd30_susp_clk"}, - .num_clks = 2, - .suspend_clk_idx = 1, -}; - static const struct dwc3_exynos_driverdata exynos5433_drvdata = { .clk_names = { "aclk", "susp_clk", "pipe_pclk", "phyclk" }, .num_clks = 4, @@ -184,9 +178,6 @@ static const struct of_device_id exynos_dwc3_match[] = { { .compatible = "samsung,exynos5250-dwusb3", .data = &exynos5250_drvdata, - }, { - .compatible = "samsung,exynos5420-dwusb3", - .data = &exynos5420_drvdata, }, { .compatible = "samsung,exynos5433-dwusb3", .data = &exynos5433_drvdata,

From: Minas Harutyunyan Minas.Harutyunyan@synopsys.com

commit 207324a321a866401b098cadf19e4a2dd6584622 upstream.

During dwc2 driver probe, after gadget registration to the udc class driver, if exist any builtin function driver it immediately bound to dwc2 and after init host side (dwc2_hcd_init()) stucked in host mode. Patch postpone gadget registration after host side initialization done.

Fixes: 117777b2c3bb9 ("usb: dwc2: Move gadget probe function into platform code") Reported-by: kbuild test robot lkp@intel.com Tested-by: Marek Vasut marex@denx.de Cc: stable stable@vger.kernel.org Signed-off-by: Minas Harutyunyan hminas@synopsys.com Link: https://lore.kernel.org/r/f21cb38fecc72a230b86155d94c7e60c9cb66f58.159169093... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/dwc2/gadget.c | 6 ------ drivers/usb/dwc2/platform.c | 11 +++++++++++ 2 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index 12b98b4662872..7faf5f8c056d4 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -4920,12 +4920,6 @@ int dwc2_gadget_init(struct dwc2_hsotg *hsotg) epnum, 0); }

- ret = usb_add_gadget_udc(dev, &hsotg->gadget); - if (ret) { - dwc2_hsotg_ep_free_request(&hsotg->eps_out[0]->ep, - hsotg->ctrl_req); - return ret; - } dwc2_hsotg_dump(hsotg);

return 0; diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index 69972750e1612..5684c4781af9e 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -536,6 +536,17 @@ static int dwc2_driver_probe(struct platform_device *dev) if (hsotg->dr_mode == USB_DR_MODE_PERIPHERAL) dwc2_lowlevel_hw_disable(hsotg);

+#if IS_ENABLED(CONFIG_USB_DWC2_PERIPHERAL) || \ + IS_ENABLED(CONFIG_USB_DWC2_DUAL_ROLE) + /* Postponed adding a new gadget to the udc class driver list */ + if (hsotg->gadget_enabled) { + retval = usb_add_gadget_udc(hsotg->dev, &hsotg->gadget); + if (retval) { + dwc2_hsotg_remove(hsotg); + goto error_init; + } + } +#endif /* CONFIG_USB_DWC2_PERIPHERAL || CONFIG_USB_DWC2_DUAL_ROLE */ return 0;

error_init:

From: Longfang Liu liulongfang@huawei.com

commit 1ddcb71a3edf0e1682b6e056158e4c4b00325f66 upstream.

A Synopsys USB2.0 core used in Huawei Kunpeng920 SoC has a bug which might cause the host controller not issuing ping.

Bug description: After indicating an Interrupt on Async Advance, the software uses the doorbell mechanism to delete the Next Link queue head of the last executed queue head. At this time, the host controller still references the removed queue head(the queue head is NULL). NULL reference causes the host controller to lose the USB device.

Solution: After deleting the Next Link queue head, when has_synopsys_hc_bug set to 1，the software can write one of the valid queue head addresses to the ASYNCLISTADDR register to allow the host controller to get the valid queue head. in order to solve that problem, this patch set the flag for Huawei Kunpeng920

There are detailed instructions and solutions in this patch: commit 2f7ac6c19997 ("USB: ehci: add workaround for Synopsys HC bug")

Signed-off-by: Longfang Liu liulongfang@huawei.com Cc: stable stable@vger.kernel.org Acked-by: Alan Stern stern@rowland.harvard.edu Link: https://lore.kernel.org/r/1591588019-44284-1-git-send-email-liulongfang@huaw... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/host/ehci-pci.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c index 1a48ab1bd3b2a..7ff2cbdcd0b22 100644 --- a/drivers/usb/host/ehci-pci.c +++ b/drivers/usb/host/ehci-pci.c @@ -216,6 +216,13 @@ static int ehci_pci_setup(struct usb_hcd *hcd) ehci_info(ehci, "applying MosChip frame-index workaround\n"); ehci->frame_index_bug = 1; break; + case PCI_VENDOR_ID_HUAWEI: + /* Synopsys HC bug */ + if (pdev->device == 0xa239) { + ehci_info(ehci, "applying Synopsys HC workaround\n"); + ehci->has_synopsys_hc_bug = 1; + } + break; }

/* optional debug port, normally in the first BAR */

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

commit b3d71abd135e6919ca0b6cab463738472653ddfb upstream.

USB2 devices with LPM enabled may interrupt the system suspend: [ 932.510475] usb 1-7: usb suspend, wakeup 0 [ 932.510549] hub 1-0:1.0: hub_suspend [ 932.510581] usb usb1: bus suspend, wakeup 0 [ 932.510590] xhci_hcd 0000:00:14.0: port 9 not suspended [ 932.510593] xhci_hcd 0000:00:14.0: port 8 not suspended .. [ 932.520323] xhci_hcd 0000:00:14.0: Port change event, 1-7, id 7, portsc: 0x400e03 .. [ 932.591405] PM: pci_pm_suspend(): hcd_pci_suspend+0x0/0x30 returns -16 [ 932.591414] PM: dpm_run_callback(): pci_pm_suspend+0x0/0x160 returns -16 [ 932.591418] PM: Device 0000:00:14.0 failed to suspend async: error -16

During system suspend, USB core will let HC suspends the device if it doesn't have remote wakeup enabled and doesn't have any children. However, from the log above we can see that the usb 1-7 doesn't get bus suspended due to not in U0. After a while the port finished U2 -> U0 transition, interrupts the suspend process.

The observation is that after disabling LPM, port doesn't transit to U0 immediately and can linger in U2. xHCI spec 4.23.5.2 states that the maximum exit latency for USB2 LPM should be BESL + 10us. The BESL for the affected device is advertised as 400us, which is still not enough based on my testing result.

So let's use the maximum permitted latency, 10000, to poll for U0 status to solve the issue.

Cc: stable@vger.kernel.org Signed-off-by: Kai-Heng Feng kai.heng.feng@canonical.com Signed-off-by: Mathias Nyman mathias.nyman@linux.intel.com Link: https://lore.kernel.org/r/20200624135949.22611-6-mathias.nyman@linux.intel.c... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/host/xhci.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index bee5deccc83d8..10d76205a79ca 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -4471,6 +4471,9 @@ static int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd, mutex_lock(hcd->bandwidth_mutex); xhci_change_max_exit_latency(xhci, udev, 0); mutex_unlock(hcd->bandwidth_mutex); + readl_poll_timeout(ports[port_num]->addr, pm_val, + (pm_val & PORT_PLS_MASK) == XDEV_U0, + 100, 10000); return 0; } }

From: Li Jun jun.li@nxp.com

commit 302c570bf36e997d55ad0d60628a2feec76954a4 upstream.

John reported screaming irq caused by rt1711h when system boot[1], this is because irq request is done before tcpci_register_port(), so the chip->tcpci has not been setup, irq handler is entered but can't do anything, this patch is to address this by moving the irq request after tcpci_register_port().

[1] https://lore.kernel.org/linux-usb/20200530040157.31038-1-john.stultz@linaro....

Fixes: ce08eaeb6388 ("staging: typec: rt1711h typec chip driver") Cc: stable stable@vger.kernel.org # v4.18+ Cc: John Stultz john.stultz@linaro.org Reported-and-tested-by: John Stultz john.stultz@linaro.org Reviewed-by: Guenter Roeck linux@roeck-us.net Reviewed-by: Heikki Krogerus heikki.krogerus@linux.intel.com Signed-off-by: Li Jun jun.li@nxp.com Link: https://lore.kernel.org/r/20200604112118.38062-1-jun.li@nxp.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/typec/tcpm/tcpci_rt1711h.c | 31 +++++++++----------------- 1 file changed, 10 insertions(+), 21 deletions(-)

diff --git a/drivers/usb/typec/tcpm/tcpci_rt1711h.c b/drivers/usb/typec/tcpm/tcpci_rt1711h.c index 017389021b96a..b56a0880a0441 100644 --- a/drivers/usb/typec/tcpm/tcpci_rt1711h.c +++ b/drivers/usb/typec/tcpm/tcpci_rt1711h.c @@ -179,26 +179,6 @@ out: return tcpci_irq(chip->tcpci); }

-static int rt1711h_init_alert(struct rt1711h_chip *chip, - struct i2c_client *client) -{ - int ret; - - /* Disable chip interrupts before requesting irq */ - ret = rt1711h_write16(chip, TCPC_ALERT_MASK, 0); - if (ret < 0) - return ret; - - ret = devm_request_threaded_irq(chip->dev, client->irq, NULL, - rt1711h_irq, - IRQF_ONESHOT | IRQF_TRIGGER_LOW, - dev_name(chip->dev), chip); - if (ret < 0) - return ret; - enable_irq_wake(client->irq); - return 0; -} - static int rt1711h_sw_reset(struct rt1711h_chip *chip) { int ret; @@ -260,7 +240,8 @@ static int rt1711h_probe(struct i2c_client *client, if (ret < 0) return ret;

- ret = rt1711h_init_alert(chip, client); + /* Disable chip interrupts before requesting irq */ + ret = rt1711h_write16(chip, TCPC_ALERT_MASK, 0); if (ret < 0) return ret;

@@ -271,6 +252,14 @@ static int rt1711h_probe(struct i2c_client *client, if (IS_ERR_OR_NULL(chip->tcpci)) return PTR_ERR(chip->tcpci);

+ ret = devm_request_threaded_irq(chip->dev, client->irq, NULL, + rt1711h_irq, + IRQF_ONESHOT | IRQF_TRIGGER_LOW, + dev_name(chip->dev), chip); + if (ret < 0) + return ret; + enable_irq_wake(client->irq); + return 0; }

From: Laurence Tratt laurie@tratt.net

commit e7585db1b0b5b4e4eb1967bb1472df308f7ffcbf upstream.

This uses the same quirk as the Motu M2 and M4 to ensure the driver uses the audio interface's clock. Tested on an SSL2+.

Signed-off-by: Laurence Tratt laurie@tratt.net Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200612111807.dgnig6rwhmsl2bod@overdrive.tratt.ne... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/usb/pcm.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 3411e27eb64bb..39aec83f8aca4 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -367,6 +367,7 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, ifnum = 0; goto add_sync_ep_from_ifnum; case USB_ID(0x07fd, 0x0008): /* MOTU M Series */ + case USB_ID(0x31e9, 0x0002): /* Solid State Logic SSL2+ */ ep = 0x81; ifnum = 2; goto add_sync_ep_from_ifnum;

From: Christopher Swenson swenson@swenson.io

commit 8abf41dcd1bcdda0d09905fb59d18f45c035c752 upstream.

Like the Line6 devices, the Rode Rodecaster Pro does not support UAC2_CS_RANGE and only supports a sample rate of 48 kHz.

Tested against a Rode Rodecaster Pro.

Tested-by: Christopher Swenson swenson@swenson.io Signed-off-by: Christopher Swenson swenson@swenson.io Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/ebdb9e72-9649-0b5e-b9b9-d757dbf26927@swenson.io Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/usb/format.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/sound/usb/format.c b/sound/usb/format.c index 5ffb457cc88cf..1b28d01d1f4cd 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -394,8 +394,9 @@ skip_rate: return nr_rates; }

-/* Line6 Helix series don't support the UAC2_CS_RANGE usb function - * call. Return a static table of known clock rates. +/* Line6 Helix series and the Rode Rodecaster Pro don't support the + * UAC2_CS_RANGE usb function call. Return a static table of known + * clock rates. */ static int line6_parse_audio_format_rates_quirk(struct snd_usb_audio *chip, struct audioformat *fp) @@ -408,6 +409,7 @@ static int line6_parse_audio_format_rates_quirk(struct snd_usb_audio *chip, case USB_ID(0x0e41, 0x4248): /* Line6 Helix >= fw 2.82 */ case USB_ID(0x0e41, 0x4249): /* Line6 Helix Rack >= fw 2.82 */ case USB_ID(0x0e41, 0x424a): /* Line6 Helix LT >= fw 2.82 */ + case USB_ID(0x19f7, 0x0011): /* Rode Rodecaster Pro */ return set_fixed_rate(fp, 48000, SNDRV_PCM_RATE_48000); }

From: Macpaul Lin macpaul.lin@mediatek.com

commit a32a1fc99807244d920d274adc46ba04b538cc8a upstream.

We've found Samsung USBC Headset (AKG) (VID: 0x04e8, PID: 0xa051) need a tiny delay after each class compliant request. Otherwise the device might not be able to be recognized each times.

Signed-off-by: Chihhao Chen chihhao.chen@mediatek.com Signed-off-by: Macpaul Lin macpaul.lin@mediatek.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/1592910203-24035-1-git-send-email-macpaul.lin@medi... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/usb/quirks.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index b5e9fe0486189..d7d900ebcf37f 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1647,6 +1647,14 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, chip->usb_id == USB_ID(0x0951, 0x16ad)) && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) usleep_range(1000, 2000); + + /* + * Samsung USBC Headset (AKG) need a tiny delay after each + * class compliant request. (Model number: AAM625R or AAM627R) + */ + if (chip->usb_id == USB_ID(0x04e8, 0xa051) && + (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) + usleep_range(5000, 6000); }

/*

From: Peter Chen peter.chen@nxp.com

commit ba3a80fe0fb67d8790f62b7bc60df97406d89871 upstream.

It should use the correct direction value from register, not depends on previous software setting. It fixed the EP number wrong issue at trace when the TRBERR interrupt occurs for EP0IN.

When the EP0IN IOC has finished, software prepares the setup packet request, the expected direction is OUT, but at that time, the TRBERR for EP0IN may occur since it is DMULT mode, the DMA does not stop until TRBERR has met.

Cc: stable@vger.kernel.org Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver") Reviewed-by: Pawel Laszczak pawell@cadence.com Signed-off-by: Peter Chen peter.chen@nxp.com Signed-off-by: Felipe Balbi balbi@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/cdns3/trace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/cdns3/trace.h b/drivers/usb/cdns3/trace.h index 8d121e207fd8f..755c565822575 100644 --- a/drivers/usb/cdns3/trace.h +++ b/drivers/usb/cdns3/trace.h @@ -156,7 +156,7 @@ DECLARE_EVENT_CLASS(cdns3_log_ep0_irq, __dynamic_array(char, str, CDNS3_MSG_MAX) ), TP_fast_assign( - __entry->ep_dir = priv_dev->ep0_data_dir; + __entry->ep_dir = priv_dev->selected_ep; __entry->ep_sts = ep_sts; ), TP_printk("%s", cdns3_decode_ep0_irq(__get_str(str),

From: Peter Chen peter.chen@nxp.com

commit 2587a029fa2a877d0a8dda955ef1b24c94b4bd0e upstream.

The other thread may access other endpoints when the cdns3_check_new_setup is handling, add spinlock to protect it.

Cc: stable@vger.kernel.org Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver") Reviewed-by: Pawel Laszczak pawell@cadence.com Signed-off-by: Peter Chen peter.chen@nxp.com Signed-off-by: Felipe Balbi balbi@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/cdns3/ep0.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/cdns3/ep0.c b/drivers/usb/cdns3/ep0.c index f785ce84aba62..da4c5eb03d7ee 100644 --- a/drivers/usb/cdns3/ep0.c +++ b/drivers/usb/cdns3/ep0.c @@ -712,15 +712,17 @@ static int cdns3_gadget_ep0_queue(struct usb_ep *ep, int ret = 0; u8 zlp = 0;

+ spin_lock_irqsave(&priv_dev->lock, flags); trace_cdns3_ep0_queue(priv_dev, request);

/* cancel the request if controller receive new SETUP packet. */ - if (cdns3_check_new_setup(priv_dev)) + if (cdns3_check_new_setup(priv_dev)) { + spin_unlock_irqrestore(&priv_dev->lock, flags); return -ECONNRESET; + }

/* send STATUS stage. Should be called only for SET_CONFIGURATION */ if (priv_dev->ep0_stage == CDNS3_STATUS_STAGE) { - spin_lock_irqsave(&priv_dev->lock, flags); cdns3_select_ep(priv_dev, 0x00);

erdy_sent = !priv_dev->hw_configured_flag; @@ -745,7 +747,6 @@ static int cdns3_gadget_ep0_queue(struct usb_ep *ep, return 0; }

- spin_lock_irqsave(&priv_dev->lock, flags); if (!list_empty(&priv_ep->pending_req_list)) { dev_err(priv_dev->dev, "can't handle multiple requests for ep0\n");

From: Steffen Maier maier@linux.ibm.com

commit 936e6b85da0476dd2edac7c51c68072da9fb4ba2 upstream.

Suppose that, for unrelated reasons, FSF requests on behalf of recovery are very slow and can run into the ERP timeout.

In the case at hand, we did adapter recovery to a large degree. However due to the slowness a LUN open is pending so the corresponding fc_rport remains blocked. After fast_io_fail_tmo we trigger close physical port recovery for the port under which the LUN should have been opened. The new higher order port recovery dismisses the pending LUN open ERP action and dismisses the pending LUN open FSF request. Such dismissal decouples the ERP action from the pending corresponding FSF request by setting zfcp_fsf_req->erp_action to NULL (among other things) [zfcp_erp_strategy_check_fsfreq()].

If now the ERP timeout for the pending open LUN request runs out, we must not use zfcp_fsf_req->erp_action in the ERP timeout handler. This is a problem since v4.15 commit 75492a51568b ("s390/scsi: Convert timers to use timer_setup()"). Before that we intentionally only passed zfcp_erp_action as context argument to zfcp_erp_timeout_handler().

Note: The lifetime of the corresponding zfcp_fsf_req object continues until a (late) response or an (unrelated) adapter recovery.

Just like the regular response path ignores dismissed requests [zfcp_fsf_req_complete() => zfcp_fsf_protstatus_eval() => return early] the ERP timeout handler now needs to ignore dismissed requests. So simply return early in the ERP timeout handler if the FSF request is marked as dismissed in its status flags. To protect against the race where zfcp_erp_strategy_check_fsfreq() dismisses and sets zfcp_fsf_req->erp_action to NULL after our previous status flag check, return early if zfcp_fsf_req->erp_action is NULL. After all, the former ERP action does not need to be woken up as that was already done as part of the dismissal above [zfcp_erp_action_dismiss()].

This fixes the following panic due to kernel page fault in IRQ context:

Unable to handle kernel pointer dereference in virtual kernel address space Failing address: 0000000000000000 TEID: 0000000000000483 Fault in home space mode while using kernel ASCE. AS:000009859238c00b R2:00000e3e7ffd000b R3:00000e3e7ffcc007 S:00000e3e7ffd7000 P:000000000000013d Oops: 0004 ilc:2 [#1] SMP Modules linked in: ... CPU: 82 PID: 311273 Comm: stress Kdump: loaded Tainted: G E X ... Hardware name: IBM 8561 T01 701 (LPAR) Krnl PSW : 0404c00180000000 001fffff80549be0 (zfcp_erp_notify+0x40/0xc0 [zfcp]) R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:3 CC:0 PM:0 RI:0 EA:3 Krnl GPRS: 0000000000000080 00000e3d00000000 00000000000000f0 0000000000030000 000000010028e700 000000000400a39c 000000010028e700 00000e3e7cf87e02 0000000010000000 0700098591cb67f0 0000000000000000 0000000000000000 0000033840e9a000 0000000000000000 001fffe008d6bc18 001fffe008d6bbc8 Krnl Code: 001fffff80549bd4: a7180000 lhi %r1,0 001fffff80549bd8: 4120a0f0 la %r2,240(%r10) #001fffff80549bdc: a53e0003 llilh %r3,3 >001fffff80549be0: ba132000 cs %r1,%r3,0(%r2) 001fffff80549be4: a7740037 brc 7,1fffff80549c52 001fffff80549be8: e320b0180004 lg %r2,24(%r11) 001fffff80549bee: e31020e00004 lg %r1,224(%r2) 001fffff80549bf4: 412020e0 la %r2,224(%r2) Call Trace: [<001fffff80549be0>] zfcp_erp_notify+0x40/0xc0 [zfcp] [<00000985915e26f0>] call_timer_fn+0x38/0x190 [<00000985915e2944>] expire_timers+0xfc/0x190 [<00000985915e2ac4>] run_timer_softirq+0xec/0x218 [<0000098591ca7c4c>] __do_softirq+0x144/0x398 [<00000985915110aa>] do_softirq_own_stack+0x72/0x88 [<0000098591551b58>] irq_exit+0xb0/0xb8 [<0000098591510c6a>] do_IRQ+0x82/0xb0 [<0000098591ca7140>] ext_int_handler+0x128/0x12c [<0000098591722d98>] clear_subpage.constprop.13+0x38/0x60 ([<000009859172ae4c>] clear_huge_page+0xec/0x250) [<000009859177e7a2>] do_huge_pmd_anonymous_page+0x32a/0x768 [<000009859172a712>] __handle_mm_fault+0x88a/0x900 [<000009859172a860>] handle_mm_fault+0xd8/0x1b0 [<0000098591529ef6>] do_dat_exception+0x136/0x3e8 [<0000098591ca6d34>] pgm_check_handler+0x1c8/0x220 Last Breaking-Event-Address: [<001fffff80549c88>] zfcp_erp_timeout_handler+0x10/0x18 [zfcp] Kernel panic - not syncing: Fatal exception in interrupt

Link: https://lore.kernel.org/r/20200623140242.98864-1-maier@linux.ibm.com Fixes: 75492a51568b ("s390/scsi: Convert timers to use timer_setup()") Cc: stable@vger.kernel.org #4.15+ Reviewed-by: Julian Wiedmann jwi@linux.ibm.com Signed-off-by: Steffen Maier maier@linux.ibm.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/s390/scsi/zfcp_erp.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c index 3d0bc000f5005..c621e8f0897f2 100644 --- a/drivers/s390/scsi/zfcp_erp.c +++ b/drivers/s390/scsi/zfcp_erp.c @@ -576,7 +576,10 @@ static void zfcp_erp_strategy_check_fsfreq(struct zfcp_erp_action *act) ZFCP_STATUS_ERP_TIMEDOUT)) { req->status |= ZFCP_STATUS_FSFREQ_DISMISSED; zfcp_dbf_rec_run("erscf_1", act); - req->erp_action = NULL; + /* lock-free concurrent access with + * zfcp_erp_timeout_handler() + */ + WRITE_ONCE(req->erp_action, NULL); } if (act->status & ZFCP_STATUS_ERP_TIMEDOUT) zfcp_dbf_rec_run("erscf_2", act); @@ -612,8 +615,14 @@ void zfcp_erp_notify(struct zfcp_erp_action *erp_action, unsigned long set_mask) void zfcp_erp_timeout_handler(struct timer_list *t) { struct zfcp_fsf_req *fsf_req = from_timer(fsf_req, t, timer); - struct zfcp_erp_action *act = fsf_req->erp_action; + struct zfcp_erp_action *act;

+ if (fsf_req->status & ZFCP_STATUS_FSFREQ_DISMISSED) + return; + /* lock-free concurrent access with zfcp_erp_strategy_check_fsfreq() */ + act = READ_ONCE(fsf_req->erp_action); + if (!act) + return; zfcp_erp_notify(act, ZFCP_STATUS_ERP_TIMEDOUT); }

From: Zhang Xiaoxu zhangxiaoxu5@huawei.com

commit acc91c2d8de4ef46ed751c5f9df99ed9a109b100 upstream.

When punch hole success, we also can read old data from file: # strace -e trace=pread64,fallocate xfs_io -f -c "pread 20 40" \ -c "fpunch 20 40" -c"pread 20 40" file pread64(3, " version 5.8.0-rc1+"..., 40, 20) = 40 fallocate(3, FALLOC_FL_KEEP_SIZE|FALLOC_FL_PUNCH_HOLE, 20, 40) = 0 pread64(3, " version 5.8.0-rc1+"..., 40, 20) = 40

CIFS implements the fallocate(FALLOCATE_FL_PUNCH_HOLE) with send SMB ioctl(FSCTL_SET_ZERO_DATA) to server. It just set the range of the remote file to zero, but local page caches not updated, then the local page caches inconsistent with server.

Also can be found by xfstests generic/316.

So, we need to remove the page caches before send the SMB ioctl(FSCTL_SET_ZERO_DATA) to server.

Fixes: 31742c5a33176 ("enable fallocate punch hole ("fallocate -p") for SMB3") Suggested-by: Pavel Shilovsky pshilov@microsoft.com Reviewed-by: Pavel Shilovsky pshilov@microsoft.com Signed-off-by: Zhang Xiaoxu zhangxiaoxu5@huawei.com Cc: stable@vger.kernel.org # v3.17 Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/cifs/smb2ops.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index c6a4caa7053e9..3de9113eb8e35 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3211,6 +3211,12 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, return rc; }

+ /* + * We implement the punch hole through ioctl, so we need remove the page + * caches first, otherwise the data may be inconsistent with the server. + */ + truncate_pagecache_range(inode, offset, offset + len - 1); + cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len);

fsctl_buf.FileOffset = cpu_to_le64(offset);

From: Mathias Nyman mathias.nyman@linux.intel.com

commit dceea67058fe22075db3aed62d5cb62092be5053 upstream.

EP_STATE_MASK should be 0x7 instead of 0xf

xhci spec 6.2.3 shows that the EP state field in the endpoint context data structure consist of bits [2:0]. The old value included a bit from the next field which fortunately is a RsvdZ region. So hopefully this hasn't caused too much harm

Cc: stable@vger.kernel.org Signed-off-by: Mathias Nyman mathias.nyman@linux.intel.com Link: https://lore.kernel.org/r/20200624135949.22611-2-mathias.nyman@linux.intel.c... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/host/xhci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 86cfefdd6632b..c80710e474769 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -716,7 +716,7 @@ struct xhci_ep_ctx { * 4 - TRB error * 5-7 - reserved */ -#define EP_STATE_MASK (0xf) +#define EP_STATE_MASK (0x7) #define EP_STATE_DISABLED 0 #define EP_STATE_RUNNING 1 #define EP_STATE_HALTED 2

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

commit f0c472a6da51f9fac15e80fe2fd9c83b68754cff upstream.

Just return if xHCI is quirked to disable LPM. We can save some time from reading registers and doing spinlocks.

Add stable tag as we want this patch together with the next one, "Poll for U0 after disabling USB2 LPM" which fixes a suspend issue for some USB2 LPM devices

Cc: stable@vger.kernel.org Signed-off-by: Kai-Heng Feng kai.heng.feng@canonical.com Signed-off-by: Mathias Nyman mathias.nyman@linux.intel.com Link: https://lore.kernel.org/r/20200624135949.22611-5-mathias.nyman@linux.intel.c... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/host/xhci.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index dcc987e1d57b0..ed468eed299c5 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -4391,6 +4391,9 @@ static int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd, int hird, exit_latency; int ret;

+ if (xhci->quirks & XHCI_HW_LPM_DISABLE) + return -EPERM; + if (hcd->speed >= HCD_USB3 || !xhci->hw_lpm_support || !udev->lpm_capable) return -EPERM; @@ -4413,7 +4416,7 @@ static int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd, xhci_dbg(xhci, "%s port %d USB2 hardware LPM\n", enable ? "enable" : "disable", port_num + 1);

- if (enable && !(xhci->quirks & XHCI_HW_LPM_DISABLE)) { + if (enable) { /* Host supports BESL timeout instead of HIRD */ if (udev->usb2_hw_lpm_besl_capable) { /* if device doesn't have a preferred BESL value use a

From: Zheng Bin zhengbin13@huawei.com

[ Upstream commit f4bd34b139a3fa2808c4205f12714c65e1548c6c ]

When a filesystem is mounted on a loop device and on a loop ioctl LOOP_SET_STATUS64, because of kill_bdev, buffer_head mappings are getting destroyed. kill_bdev truncate_inode_pages truncate_inode_pages_range do_invalidatepage block_invalidatepage discard_buffer -->clear BH_Mapped flag

sb_bread __bread_gfp bh = __getblk_gfp -->discard_buffer clear BH_Mapped flag __bread_slow submit_bh submit_bh_wbc BUG_ON(!buffer_mapped(bh)) --> hit this BUG_ON

Fixes: 5db470e229e2 ("loop: drop caches if offset or block_size are changed") Signed-off-by: Zheng Bin zhengbin13@huawei.com Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Bart Van Assche bvanassche@acm.org Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/block/loop.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c index da693e6a834e5..418bb4621255a 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1289,7 +1289,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) if (lo->lo_offset != info->lo_offset || lo->lo_sizelimit != info->lo_sizelimit) { sync_blockdev(lo->lo_device); - kill_bdev(lo->lo_device); + invalidate_bdev(lo->lo_device); }

/* I/O need to be drained during transfer transition */ @@ -1320,7 +1320,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)

if (lo->lo_offset != info->lo_offset || lo->lo_sizelimit != info->lo_sizelimit) { - /* kill_bdev should have truncated all the pages */ + /* invalidate_bdev should have truncated all the pages */ if (lo->lo_device->bd_inode->i_mapping->nrpages) { err = -EAGAIN; pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", @@ -1565,11 +1565,11 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg) return 0;

sync_blockdev(lo->lo_device); - kill_bdev(lo->lo_device); + invalidate_bdev(lo->lo_device);

blk_mq_freeze_queue(lo->lo_queue);

- /* kill_bdev should have truncated all the pages */ + /* invalidate_bdev should have truncated all the pages */ if (lo->lo_device->bd_inode->i_mapping->nrpages) { err = -EAGAIN; pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n",

From: Dennis Dalessandro dennis.dalessandro@intel.com

commit 822fbd37410639acdae368ea55477ddd3498651d upstream.

When the try_module_get calls were removed from opening and closing of the i2c debugfs file, the corresponding module_put calls were missed. This results in an inaccurate module use count that requires a power cycle to fix.

Fixes: 09fbca8e6240 ("IB/hfi1: No need to use try_module_get for debugfs") Link: https://lore.kernel.org/r/20200623203230.106975.76240.stgit@awfm-01.aw.intel... Cc: stable@vger.kernel.org Reviewed-by: Kaike Wan kaike.wan@intel.com Reviewed-by: Mike Marciniszyn mike.marciniszyn@intel.com Signed-off-by: Dennis Dalessandro dennis.dalessandro@intel.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/infiniband/hw/hfi1/debugfs.c | 19 ++----------------- 1 file changed, 2 insertions(+), 17 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c index 4633a0ce1a8c0..2ced236e1553c 100644 --- a/drivers/infiniband/hw/hfi1/debugfs.c +++ b/drivers/infiniband/hw/hfi1/debugfs.c @@ -985,15 +985,10 @@ static ssize_t qsfp2_debugfs_read(struct file *file, char __user *buf, static int __i2c_debugfs_open(struct inode *in, struct file *fp, u32 target) { struct hfi1_pportdata *ppd; - int ret;

ppd = private2ppd(fp);

- ret = acquire_chip_resource(ppd->dd, i2c_target(target), 0); - if (ret) /* failed - release the module */ - module_put(THIS_MODULE); - - return ret; + return acquire_chip_resource(ppd->dd, i2c_target(target), 0); }

static int i2c1_debugfs_open(struct inode *in, struct file *fp) @@ -1013,7 +1008,6 @@ static int __i2c_debugfs_release(struct inode *in, struct file *fp, u32 target) ppd = private2ppd(fp);

release_chip_resource(ppd->dd, i2c_target(target)); - module_put(THIS_MODULE);

return 0; } @@ -1031,18 +1025,10 @@ static int i2c2_debugfs_release(struct inode *in, struct file *fp) static int __qsfp_debugfs_open(struct inode *in, struct file *fp, u32 target) { struct hfi1_pportdata *ppd; - int ret; - - if (!try_module_get(THIS_MODULE)) - return -ENODEV;

ppd = private2ppd(fp);

- ret = acquire_chip_resource(ppd->dd, i2c_target(target), 0); - if (ret) /* failed - release the module */ - module_put(THIS_MODULE); - - return ret; + return acquire_chip_resource(ppd->dd, i2c_target(target), 0); }

static int qsfp1_debugfs_open(struct inode *in, struct file *fp) @@ -1062,7 +1048,6 @@ static int __qsfp_debugfs_release(struct inode *in, struct file *fp, u32 target) ppd = private2ppd(fp);

release_chip_resource(ppd->dd, i2c_target(target)); - module_put(THIS_MODULE);

return 0; }

From: Tony Lindgren tony@atomide.com

[ Upstream commit d46f9fbec71997420e4fb83c04d9affdf423f879 ]

Some modules reset automatically when idled, and when re-enabled, we must wait for the automatic OCP softreset to complete. And if optional clocks are configured, we need to keep the clocks on while waiting for the reset to complete.

Let's fix the issue by moving the OCP softreset code to a separate function sysc_wait_softreset(), and call it also from sysc_enable_module() with the optional clocks enabled.

This is based on what we're already doing for legacy platform data booting in _enable_sysc().

Fixes: 7324a7a0d5e2 ("bus: ti-sysc: Implement display subsystem reset quirk") Reported-by: Faiz Abbas faiz_abbas@ti.com Cc: Laurent Pinchart laurent.pinchart@ideasonboard.com Cc: Tomi Valkeinen tomi.valkeinen@ti.com Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/bus/ti-sysc.c | 80 ++++++++++++++++++++++++++++++++----------- 1 file changed, 60 insertions(+), 20 deletions(-)

diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 369c97c3e0c0b..a3a2c269e9ad7 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -221,6 +221,35 @@ static u32 sysc_read_sysstatus(struct sysc *ddata) return sysc_read(ddata, offset); }

+/* Poll on reset status */ +static int sysc_wait_softreset(struct sysc *ddata) +{ + u32 sysc_mask, syss_done, rstval; + int syss_offset, error = 0; + + syss_offset = ddata->offsets[SYSC_SYSSTATUS]; + sysc_mask = BIT(ddata->cap->regbits->srst_shift); + + if (ddata->cfg.quirks & SYSS_QUIRK_RESETDONE_INVERTED) + syss_done = 0; + else + syss_done = ddata->cfg.syss_mask; + + if (syss_offset >= 0) { + error = readx_poll_timeout(sysc_read_sysstatus, ddata, rstval, + (rstval & ddata->cfg.syss_mask) == + syss_done, + 100, MAX_MODULE_SOFTRESET_WAIT); + + } else if (ddata->cfg.quirks & SYSC_QUIRK_RESET_STATUS) { + error = readx_poll_timeout(sysc_read_sysconfig, ddata, rstval, + !(rstval & sysc_mask), + 100, MAX_MODULE_SOFTRESET_WAIT); + } + + return error; +} + static int sysc_add_named_clock_from_child(struct sysc *ddata, const char *name, const char *optfck_name) @@ -925,8 +954,34 @@ static int sysc_enable_module(struct device *dev) struct sysc *ddata; const struct sysc_regbits *regbits; u32 reg, idlemodes, best_mode; + int error;

ddata = dev_get_drvdata(dev); + + /* + * Some modules like DSS reset automatically on idle. Enable optional + * reset clocks and wait for OCP softreset to complete. + */ + if (ddata->cfg.quirks & SYSC_QUIRK_OPT_CLKS_IN_RESET) { + error = sysc_enable_opt_clocks(ddata); + if (error) { + dev_err(ddata->dev, + "Optional clocks failed for enable: %i\n", + error); + return error; + } + } + error = sysc_wait_softreset(ddata); + if (error) + dev_warn(ddata->dev, "OCP softreset timed out\n"); + if (ddata->cfg.quirks & SYSC_QUIRK_OPT_CLKS_IN_RESET) + sysc_disable_opt_clocks(ddata); + + /* + * Some subsystem private interconnects, like DSS top level module, + * need only the automatic OCP softreset handling with no sysconfig + * register bits to configure. + */ if (ddata->offsets[SYSC_SYSCONFIG] == -ENODEV) return 0;

@@ -1828,11 +1883,10 @@ static int sysc_legacy_init(struct sysc *ddata) */ static int sysc_reset(struct sysc *ddata) { - int sysc_offset, syss_offset, sysc_val, rstval, error = 0; - u32 sysc_mask, syss_done; + int sysc_offset, sysc_val, error; + u32 sysc_mask;

sysc_offset = ddata->offsets[SYSC_SYSCONFIG]; - syss_offset = ddata->offsets[SYSC_SYSSTATUS];

if (ddata->legacy_mode || ddata->cap->regbits->srst_shift < 0 || @@ -1841,11 +1895,6 @@ static int sysc_reset(struct sysc *ddata)

sysc_mask = BIT(ddata->cap->regbits->srst_shift);

- if (ddata->cfg.quirks & SYSS_QUIRK_RESETDONE_INVERTED) - syss_done = 0; - else - syss_done = ddata->cfg.syss_mask; - if (ddata->pre_reset_quirk) ddata->pre_reset_quirk(ddata);

@@ -1862,18 +1911,9 @@ static int sysc_reset(struct sysc *ddata) if (ddata->post_reset_quirk) ddata->post_reset_quirk(ddata);

- /* Poll on reset status */ - if (syss_offset >= 0) { - error = readx_poll_timeout(sysc_read_sysstatus, ddata, rstval, - (rstval & ddata->cfg.syss_mask) == - syss_done, - 100, MAX_MODULE_SOFTRESET_WAIT); - - } else if (ddata->cfg.quirks & SYSC_QUIRK_RESET_STATUS) { - error = readx_poll_timeout(sysc_read_sysconfig, ddata, rstval, - !(rstval & sysc_mask), - 100, MAX_MODULE_SOFTRESET_WAIT); - } + error = sysc_wait_softreset(ddata); + if (error) + dev_warn(ddata->dev, "OCP softreset timed out\n");

if (ddata->reset_done_quirk) ddata->reset_done_quirk(ddata);

From: Tony Lindgren tony@atomide.com

[ Upstream commit 085bc0e576a4bf53b67a917c54908f299a2fb949 ]

We are currently only setting the framedonetv_irq disabled for the SoCs that don't have it. But we are never setting it enabled for the SoCs that have it. Let's initialized it to true by default.

Fixes: 7324a7a0d5e2 ("bus: ti-sysc: Implement display subsystem reset quirk") Cc: Laurent Pinchart laurent.pinchart@ideasonboard.com Cc: Tomi Valkeinen tomi.valkeinen@ti.com Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/bus/ti-sysc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 4f640a635ded1..db9541f385055 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -1552,7 +1552,7 @@ static u32 sysc_quirk_dispc(struct sysc *ddata, int dispc_offset, bool lcd_en, digit_en, lcd2_en = false, lcd3_en = false; const int lcd_en_mask = BIT(0), digit_en_mask = BIT(1); int manager_count; - bool framedonetv_irq; + bool framedonetv_irq = true; u32 val, irq_mask = 0;

switch (sysc_soc->soc) { @@ -1569,6 +1569,7 @@ static u32 sysc_quirk_dispc(struct sysc *ddata, int dispc_offset, break; case SOC_AM4: manager_count = 1; + framedonetv_irq = false; break; case SOC_UNKNOWN: default:

From: Huy Nguyen huyn@mellanox.com

[ Upstream commit 94579ac3f6d0820adc83b5dc5358ead0158101e9 ]

During IPsec performance testing, we see bad ICMP checksum. The error packet has duplicated ESP trailer due to double validate_xmit_xfrm calls. The first call is from ip_output, but the packet cannot be sent because netif_xmit_frozen_or_stopped is true and the packet gets dev_requeue_skb. The second call is from NET_TX softirq. However after the first call, the packet already has the ESP trailer.

Fix by marking the skb with XFRM_XMIT bit after the packet is handled by validate_xmit_xfrm to avoid duplicate ESP trailer insertion.

Fixes: f6e27114a60a ("net: Add a xfrm validate function to validate_xmit_skb") Signed-off-by: Huy Nguyen huyn@mellanox.com Reviewed-by: Boris Pismenny borisp@mellanox.com Reviewed-by: Raed Salem raeds@mellanox.com Reviewed-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/xfrm.h | 1 + net/xfrm/xfrm_device.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 8f71c111e65af..03024701c79f7 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1013,6 +1013,7 @@ struct xfrm_offload { #define XFRM_GRO 32 #define XFRM_ESP_NO_TRAILER 64 #define XFRM_DEV_RESUME 128 +#define XFRM_XMIT 256

__u32 status; #define CRYPTO_SUCCESS 1 diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index f50d1f97cf8ec..626096bd0d294 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -108,7 +108,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur struct xfrm_offload *xo = xfrm_offload(skb); struct sec_path *sp;

- if (!xo) + if (!xo || (xo->flags & XFRM_XMIT)) return skb;

if (!(features & NETIF_F_HW_ESP)) @@ -129,6 +129,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; }

+ xo->flags |= XFRM_XMIT; + if (skb_is_gso(skb)) { struct net_device *dev = skb->dev;

From: Oskar Holmlund oskar@ohdata.se

[ Upstream commit 9f872f924545324a06fa216ad38132804c20f2db ]

AM335x TRM: Figure 16-23 define sysconfig register and soft_reset are in first position corresponding to SYSC_OMAP4_SOFTRESET defined in ti-sysc.h.

Fixes: 0782e8572ce4 ("ARM: dts: Probe am335x musb with ti-sysc") Signed-off-by: Oskar Holmlund oskar@ohdata.se Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/am33xx.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index be76ded7e4c0c..ed6634d34c3c7 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -335,7 +335,7 @@ <0x47400010 0x4>; reg-names = "rev", "sysc"; ti,sysc-mask = <(SYSC_OMAP4_FREEEMU | - SYSC_OMAP2_SOFTRESET)>; + SYSC_OMAP4_SOFTRESET)>; ti,sysc-midle = <SYSC_IDLE_FORCE>, <SYSC_IDLE_NO>, <SYSC_IDLE_SMART>;

From: Martin Fuzzey martin.fuzzey@flowbird.group

[ Upstream commit d7442ba13d62de9afc4e57344a676f9f4623dcaa ]

Commit 99f75ce66619 ("regulator: da9063: fix suspend") converted the regulators to use a common (corrected) suspend bit setting but one of regulators (LDO9) slipped through the crack.

This means that the original problem was not fixed for LDO9 and also leads to a warning found by the test robot. da9063-regulator.c:515:3: warning: initialized field overwritten

Fix this by converting that regulator too like the others.

Fixes: 99f75ce66619 ("regulator: da9063: fix suspend") Reported-by: kernel test robot lkp@intel.com

Signed-off-by: Martin Fuzzey martin.fuzzey@flowbird.group Link: https://lore.kernel.org/r/1591959073-16792-1-git-send-email-martin.fuzzey@fl... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/regulator/da9063-regulator.c | 1 - 1 file changed, 1 deletion(-)

diff --git a/drivers/regulator/da9063-regulator.c b/drivers/regulator/da9063-regulator.c index e1d6c8f6d40bb..fe65b5acaf280 100644 --- a/drivers/regulator/da9063-regulator.c +++ b/drivers/regulator/da9063-regulator.c @@ -512,7 +512,6 @@ static const struct da9063_regulator_info da9063_regulator_info[] = { }, { DA9063_LDO(DA9063, LDO9, 950, 50, 3600), - .suspend = BFIELD(DA9063_REG_LDO9_CONT, DA9063_VLDO9_SEL), }, { DA9063_LDO(DA9063, LDO11, 900, 50, 3600),

From: Matthew Hagan mnhagan88@gmail.com

[ Upstream commit 0386e9ce5877ee73e07675529d5ae594d00f0900 ]

The NSP SoC includes an SP804 timer so should be enabled here.

Fixes: a0efb0d28b77 ("ARM: dts: NSP: Add SP804 Support to DT") Signed-off-by: Matthew Hagan mnhagan88@gmail.com Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/mach-bcm/Kconfig | 1 + 1 file changed, 1 insertion(+)

diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig index 6aa938b949db2..1df0ee01ee02b 100644 --- a/arch/arm/mach-bcm/Kconfig +++ b/arch/arm/mach-bcm/Kconfig @@ -53,6 +53,7 @@ config ARCH_BCM_NSP select ARM_ERRATA_754322 select ARM_ERRATA_775420 select ARM_ERRATA_764369 if SMP + select ARM_TIMER_SP804 select THERMAL select THERMAL_OF help

From: Reinette Chatre reinette.chatre@intel.com

[ Upstream commit f3d44f18b0662327c42128b9d3604489bdb6e36f ]

The original Memory Bandwidth Monitoring (MBM) architectural definition defines counters of up to 62 bits in the IA32_QM_CTR MSR while the first-generation MBM implementation uses statically defined 24 bit counters.

Expand the MBM CPUID enumeration properties to include the MBM counter width. The previously undefined EAX output register contains, in bits [7:0], the MBM counter width encoded as an offset from 24 bits. Enumerating this property is only specified for Intel CPUs.

Suggested-by: Borislav Petkov bp@suse.de Signed-off-by: Reinette Chatre reinette.chatre@intel.com Signed-off-by: Borislav Petkov bp@suse.de Link: https://lkml.kernel.org/r/afa3af2f753f6bc301fb743bc8944e749cb24afa.158871569... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/include/asm/processor.h | 3 ++- arch/x86/kernel/cpu/resctrl/core.c | 5 +++++ 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 3bcf27caf6c9f..c4e8fd709cf67 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -113,9 +113,10 @@ struct cpuinfo_x86 { /* in KB - valid for CPUS which support this call: */ unsigned int x86_cache_size; int x86_cache_alignment; /* In bytes */ - /* Cache QoS architectural values: */ + /* Cache QoS architectural values, valid only on the BSP: */ int x86_cache_max_rmid; /* max index */ int x86_cache_occ_scale; /* scale to bytes */ + int x86_cache_mbm_width_offset; int x86_power; unsigned long loops_per_jiffy; /* cpuid returned max cores value: */ diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 49599733fa94d..d242e864726c0 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -963,6 +963,7 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c) if (!cpu_has(c, X86_FEATURE_CQM_LLC)) { c->x86_cache_max_rmid = -1; c->x86_cache_occ_scale = -1; + c->x86_cache_mbm_width_offset = -1; return; }

@@ -979,6 +980,10 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c)

c->x86_cache_max_rmid = ecx; c->x86_cache_occ_scale = ebx; + if (c->x86_vendor == X86_VENDOR_INTEL) + c->x86_cache_mbm_width_offset = eax & 0xff; + else + c->x86_cache_mbm_width_offset = -1; } }

From: Fabian Vogt fvogt@suse.de

[ Upstream commit 7dfc06a0f25b593a9f51992f540c0f80a57f3629 ]

It is possible that the first event in the event log is not actually a log header at all, but rather a normal event. This leads to the cast in __calc_tpm2_event_size being an invalid conversion, which means that the values read are effectively garbage. Depending on the first event's contents, this leads either to apparently normal behaviour, a crash or a freeze.

While this behaviour of the firmware is not in accordance with the TCG Client EFI Specification, this happens on a Dell Precision 5510 with the TPM enabled but hidden from the OS ("TPM On" disabled, state otherwise untouched). The EFI firmware claims that the TPM is present and active and that it supports the TCG 2.0 event log format.

Fortunately, this can be worked around by simply checking the header of the first event and the event log header signature itself.

Commit b4f1874c6216 ("tpm: check event log version before reading final events") addressed a similar issue also found on Dell models.

Fixes: 6b0326190205 ("efi: Attempt to get the TCG2 event log in the boot stub") Signed-off-by: Fabian Vogt fvogt@suse.de Link: https://lore.kernel.org/r/1927248.evlx2EsYKh@linux-e202.suse.de Bugzilla: https://bugzilla.suse.com/show_bug.cgi?id=1165773 Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/tpm_eventlog.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index c253461b1c4e6..96d36b7a13440 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -81,6 +81,8 @@ struct tcg_efi_specid_event_algs { u16 digest_size; } __packed;

+#define TCG_SPECID_SIG "Spec ID Event03" + struct tcg_efi_specid_event_head { u8 signature[16]; u32 platform_class; @@ -171,6 +173,7 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, int i; int j; u32 count, event_type; + const u8 zero_digest[sizeof(event_header->digest)] = {0};

marker = event; marker_start = marker; @@ -198,10 +201,19 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, count = READ_ONCE(event->count); event_type = READ_ONCE(event->event_type);

+ /* Verify that it's the log header */ + if (event_header->pcr_idx != 0 || + event_header->event_type != NO_ACTION || + memcmp(event_header->digest, zero_digest, sizeof(zero_digest))) { + size = 0; + goto out; + } + efispecid = (struct tcg_efi_specid_event_head *)event_header->event;

/* Check if event is malformed. */ - if (count > efispecid->num_algs) { + if (memcmp(efispecid->signature, TCG_SPECID_SIG, + sizeof(TCG_SPECID_SIG)) || count > efispecid->num_algs) { size = 0; goto out; }

From: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com

[ Upstream commit 96bf62f018f40cb5d4e4bed95e50fd990a2354af ]

soc_dpcm_fe_runtime_update() is called for all dailinks, and we want to first discard all back-ends, then deal with front-ends.

The existing code first reports an error with multi-cpu front-ends, and that check needs to be moved after we know that we are dealing with a front-end.

Fixes: 6e1276a5e613d ('ASoC: Return error if the function does not support multi-cpu') Signed-off-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Reviewed-by: Ranjani Sridharan ranjani.sridharan@linux.intel.com Reviewed-by: Bard Liao yung-chuan.liao@linux.intel.com BugLink: https://github.com/thesofproject/linux/issues/1970 Link: https://lore.kernel.org/r/20200612203507.25621-1-pierre-louis.bossart@linux.... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/soc-pcm.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 39ce61c5b8744..fde097a7aad32 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -2749,15 +2749,15 @@ static int soc_dpcm_fe_runtime_update(struct snd_soc_pcm_runtime *fe, int new) int count, paths; int ret;

+ if (!fe->dai_link->dynamic) + return 0; + if (fe->num_cpus > 1) { dev_err(fe->dev, "%s doesn't support Multi CPU yet\n", __func__); return -EINVAL; }

- if (!fe->dai_link->dynamic) - return 0; - /* only check active links */ if (!fe->cpu_dai->active) return 0;

From: Srinivas Kandagatla srinivas.kandagatla@linaro.org

[ Upstream commit a2120089251f1fe221305e88df99af16f940e236 ]

Currently both FE and BE dai-links are configured bi-directional, However the DSP BE dais are only single directional, so set the directions as supported by the BE dais.

Fixes: c25e295cd77b (ASoC: qcom: Add support to parse common audio device nodes) Reported-by: John Stultz john.stultz@linaro.org Signed-off-by: Srinivas Kandagatla srinivas.kandagatla@linaro.org Tested-by: John Stultz john.stultz@linaro.org Reviewed-by: Vinod Koul vkoul@kernel.org Link: https://lore.kernel.org/r/20200612123711.29130-2-srinivas.kandagatla@linaro.... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/qcom/common.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/sound/soc/qcom/common.c b/sound/soc/qcom/common.c index 6c20bdd850f33..8ada4ecba8472 100644 --- a/sound/soc/qcom/common.c +++ b/sound/soc/qcom/common.c @@ -4,6 +4,7 @@

#include <linux/module.h> #include "common.h" +#include "qdsp6/q6afe.h"

int qcom_snd_parse_of(struct snd_soc_card *card) { @@ -101,6 +102,15 @@ int qcom_snd_parse_of(struct snd_soc_card *card) } link->no_pcm = 1; link->ignore_pmdown_time = 1; + + if (q6afe_is_rx_port(link->id)) { + link->dpcm_playback = 1; + link->dpcm_capture = 0; + } else { + link->dpcm_playback = 0; + link->dpcm_capture = 1; + } + } else { dlc = devm_kzalloc(dev, sizeof(*dlc), GFP_KERNEL); if (!dlc) @@ -113,12 +123,12 @@ int qcom_snd_parse_of(struct snd_soc_card *card) link->codecs->dai_name = "snd-soc-dummy-dai"; link->codecs->name = "snd-soc-dummy"; link->dynamic = 1; + link->dpcm_playback = 1; + link->dpcm_capture = 1; }

link->ignore_suspend = 1; link->nonatomic = 1; - link->dpcm_playback = 1; - link->dpcm_capture = 1; link->stream_name = link->name; link++;

From: Philipp Fent fent@in.tum.de

[ Upstream commit 7a88a6227dc7f2e723bba11ece05e57bd8dce8e4 ]

Commit 9302c1bb8e47 ("efi/libstub: Rewrite file I/O routine") introduced a regression that made a couple of (badly configured) systems fail to boot [1]: Until 5.6, we silently accepted Unix-style file separators in EFI paths, which might violate the EFI standard, but are an easy to make mistake. This fix restores the pre-5.7 behaviour.

[1] https://bbs.archlinux.org/viewtopic.php?id=256273

Fixes: 9302c1bb8e47 ("efi/libstub: Rewrite file I/O routine") Signed-off-by: Philipp Fent fent@in.tum.de Link: https://lore.kernel.org/r/20200615115109.7823-1-fent@in.tum.de [ardb: rewrite as chained if/else statements] Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/firmware/efi/libstub/file.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/firmware/efi/libstub/file.c b/drivers/firmware/efi/libstub/file.c index ea66b1f16a79d..f1c4faf58c764 100644 --- a/drivers/firmware/efi/libstub/file.c +++ b/drivers/firmware/efi/libstub/file.c @@ -104,12 +104,20 @@ static int find_file_option(const efi_char16_t *cmdline, int cmdline_len, if (!found) return 0;

+ /* Skip any leading slashes */ + while (cmdline[i] == L'/' || cmdline[i] == L'\') + i++; + while (--result_len > 0 && i < cmdline_len) { - if (cmdline[i] == L'\0' || - cmdline[i] == L'\n' || - cmdline[i] == L' ') + efi_char16_t c = cmdline[i++]; + + if (c == L'\0' || c == L'\n' || c == L' ') break; - *result++ = cmdline[i++]; + else if (c == L'/') + /* Replace UNIX dir separators with EFI standard ones */ + *result++ = L'\'; + else + *result++ = c; } *result = L'\0'; return i;

From: Matthew Hagan mnhagan88@gmail.com

[ Upstream commit b9dbe0101e344e8339406a11b7a91d4a0c50ad13 ]

Currently the PL330 is enabled by default. However if left in IDM reset, as is the case with the Meraki and Synology NSP devices, the system will hang when probing for the PL330's AMBA peripheral ID. We therefore should be able to disable it in these cases.

The PL330 is also included among of the list of peripherals put into coherent mode, so "dma-coherent" has been added here as well.

Fixes: 5fa1026a3e4d ("ARM: dts: NSP: Add PL330 support") Signed-off-by: Matthew Hagan mnhagan88@gmail.com Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/bcm-nsp.dtsi | 4 +++- arch/arm/boot/dts/bcm958522er.dts | 4 ++++ arch/arm/boot/dts/bcm958525er.dts | 4 ++++ arch/arm/boot/dts/bcm958525xmc.dts | 4 ++++ arch/arm/boot/dts/bcm958622hr.dts | 4 ++++ arch/arm/boot/dts/bcm958623hr.dts | 4 ++++ arch/arm/boot/dts/bcm958625hr.dts | 4 ++++ arch/arm/boot/dts/bcm958625k.dts | 4 ++++ 8 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi index da6d70f09ef19..920c0f561e5ce 100644 --- a/arch/arm/boot/dts/bcm-nsp.dtsi +++ b/arch/arm/boot/dts/bcm-nsp.dtsi @@ -200,7 +200,7 @@ status = "disabled"; };

- dma@20000 { + dma: dma@20000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x20000 0x1000>; interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>, @@ -215,6 +215,8 @@ clocks = <&iprocslow>; clock-names = "apb_pclk"; #dma-cells = <1>; + dma-coherent; + status = "disabled"; };

sdio: sdhci@21000 { diff --git a/arch/arm/boot/dts/bcm958522er.dts b/arch/arm/boot/dts/bcm958522er.dts index 8c388eb8a08f8..7be4c4e628e02 100644 --- a/arch/arm/boot/dts/bcm958522er.dts +++ b/arch/arm/boot/dts/bcm958522er.dts @@ -58,6 +58,10 @@

/* USB 3 support needed to be complete */

+&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958525er.dts b/arch/arm/boot/dts/bcm958525er.dts index c339771bb22e0..e58ed7e953460 100644 --- a/arch/arm/boot/dts/bcm958525er.dts +++ b/arch/arm/boot/dts/bcm958525er.dts @@ -58,6 +58,10 @@

/* USB 3 support needed to be complete */

+&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958525xmc.dts b/arch/arm/boot/dts/bcm958525xmc.dts index 1c72ec8288de4..716da62f57885 100644 --- a/arch/arm/boot/dts/bcm958525xmc.dts +++ b/arch/arm/boot/dts/bcm958525xmc.dts @@ -58,6 +58,10 @@

/* XHCI support needed to be complete */

+&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958622hr.dts b/arch/arm/boot/dts/bcm958622hr.dts index 96a021cebd97b..a49c2fd21f4a8 100644 --- a/arch/arm/boot/dts/bcm958622hr.dts +++ b/arch/arm/boot/dts/bcm958622hr.dts @@ -58,6 +58,10 @@

/* USB 3 and SLIC support needed to be complete */

+&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958623hr.dts b/arch/arm/boot/dts/bcm958623hr.dts index b2c7f21d471e6..dd6dff6452b87 100644 --- a/arch/arm/boot/dts/bcm958623hr.dts +++ b/arch/arm/boot/dts/bcm958623hr.dts @@ -58,6 +58,10 @@

/* USB 3 and SLIC support needed to be complete */

+&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts index 536fb24f38bb7..a71371b4065ed 100644 --- a/arch/arm/boot/dts/bcm958625hr.dts +++ b/arch/arm/boot/dts/bcm958625hr.dts @@ -69,6 +69,10 @@ status = "okay"; };

+&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958625k.dts b/arch/arm/boot/dts/bcm958625k.dts index 3fcca12d83c2d..7b84b54436edd 100644 --- a/arch/arm/boot/dts/bcm958625k.dts +++ b/arch/arm/boot/dts/bcm958625k.dts @@ -48,6 +48,10 @@ }; };

+&dma { + status = "okay"; +}; + &amac0 { status = "okay"; };

From: Lorenzo Bianconi lorenzo@kernel.org

[ Upstream commit 6a09815428547657f3ffd2f5c31ac2a191e7fdf3 ]

xdp_redirect_cpu is currently failing in bpf_prog_load_xattr() allocating cpu_map map if CONFIG_NR_CPUS is less than 64 since cpu_map_alloc() requires max_entries to be less than NR_CPUS. Set cpu_map max_entries according to NR_CPUS in xdp_redirect_cpu_kern.c and get currently running cpus in xdp_redirect_cpu_user.c

Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org Signed-off-by: Alexei Starovoitov ast@kernel.org Acked-by: Yonghong Song yhs@fb.com Link: https://lore.kernel.org/bpf/374472755001c260158c4e4b22f193bdd3c56fb7.1589300... Signed-off-by: Sasha Levin sashal@kernel.org --- samples/bpf/xdp_redirect_cpu_kern.c | 2 +- samples/bpf/xdp_redirect_cpu_user.c | 29 ++++++++++++++++------------- 2 files changed, 17 insertions(+), 14 deletions(-)

diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c index 313a8fe6d125c..2baf8db1f7e70 100644 --- a/samples/bpf/xdp_redirect_cpu_kern.c +++ b/samples/bpf/xdp_redirect_cpu_kern.c @@ -15,7 +15,7 @@ #include <bpf/bpf_helpers.h> #include "hash_func01.h"

-#define MAX_CPUS 64 /* WARNING - sync with _user.c */ +#define MAX_CPUS NR_CPUS

/* Special map type that can XDP_REDIRECT frames to another CPU */ struct { diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index 15bdf047a2221..9b8f21abeac47 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -13,6 +13,7 @@ static const char *__doc__ = #include <unistd.h> #include <locale.h> #include <sys/resource.h> +#include <sys/sysinfo.h> #include <getopt.h> #include <net/if.h> #include <time.h> @@ -24,8 +25,6 @@ static const char *__doc__ = #include <arpa/inet.h> #include <linux/if_link.h>

-#define MAX_CPUS 64 /* WARNING - sync with _kern.c */ - /* How many xdp_progs are defined in _kern.c */ #define MAX_PROG 6

@@ -40,6 +39,7 @@ static char *ifname; static __u32 prog_id;

static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static int n_cpus; static int cpu_map_fd; static int rx_cnt_map_fd; static int redirect_err_cnt_map_fd; @@ -170,7 +170,7 @@ struct stats_record { struct record redir_err; struct record kthread; struct record exception; - struct record enq[MAX_CPUS]; + struct record enq[]; };

static bool map_collect_percpu(int fd, __u32 key, struct record *rec) @@ -225,10 +225,11 @@ static struct datarec *alloc_record_per_cpu(void) static struct stats_record *alloc_stats_record(void) { struct stats_record *rec; - int i; + int i, size;

- rec = malloc(sizeof(*rec)); - memset(rec, 0, sizeof(*rec)); + size = sizeof(*rec) + n_cpus * sizeof(struct record); + rec = malloc(size); + memset(rec, 0, size); if (!rec) { fprintf(stderr, "Mem alloc error\n"); exit(EXIT_FAIL_MEM); @@ -237,7 +238,7 @@ static struct stats_record *alloc_stats_record(void) rec->redir_err.cpu = alloc_record_per_cpu(); rec->kthread.cpu = alloc_record_per_cpu(); rec->exception.cpu = alloc_record_per_cpu(); - for (i = 0; i < MAX_CPUS; i++) + for (i = 0; i < n_cpus; i++) rec->enq[i].cpu = alloc_record_per_cpu();

return rec; @@ -247,7 +248,7 @@ static void free_stats_record(struct stats_record *r) { int i;

- for (i = 0; i < MAX_CPUS; i++) + for (i = 0; i < n_cpus; i++) free(r->enq[i].cpu); free(r->exception.cpu); free(r->kthread.cpu); @@ -350,7 +351,7 @@ static void stats_print(struct stats_record *stats_rec, }

/* cpumap enqueue stats */ - for (to_cpu = 0; to_cpu < MAX_CPUS; to_cpu++) { + for (to_cpu = 0; to_cpu < n_cpus; to_cpu++) { char *fmt = "%-15s %3d:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n"; char *fm2 = "%-15s %3s:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n"; char *errstr = ""; @@ -475,7 +476,7 @@ static void stats_collect(struct stats_record *rec) map_collect_percpu(fd, 1, &rec->redir_err);

fd = cpumap_enqueue_cnt_map_fd; - for (i = 0; i < MAX_CPUS; i++) + for (i = 0; i < n_cpus; i++) map_collect_percpu(fd, i, &rec->enq[i]);

fd = cpumap_kthread_cnt_map_fd; @@ -549,10 +550,10 @@ static int create_cpu_entry(__u32 cpu, __u32 queue_size, */ static void mark_cpus_unavailable(void) { - __u32 invalid_cpu = MAX_CPUS; + __u32 invalid_cpu = n_cpus; int ret, i;

- for (i = 0; i < MAX_CPUS; i++) { + for (i = 0; i < n_cpus; i++) { ret = bpf_map_update_elem(cpus_available_map_fd, &i, &invalid_cpu, 0); if (ret) { @@ -688,6 +689,8 @@ int main(int argc, char **argv) int prog_fd; __u32 qsize;

+ n_cpus = get_nprocs_conf(); + /* Notice: choosing he queue size is very important with the * ixgbe driver, because it's driver page recycling trick is * dependend on pages being returned quickly. The number of @@ -757,7 +760,7 @@ int main(int argc, char **argv) case 'c': /* Add multiple CPUs */ add_cpu = strtoul(optarg, NULL, 0); - if (add_cpu >= MAX_CPUS) { + if (add_cpu >= n_cpus) { fprintf(stderr, "--cpu nr too large for cpumap err(%d):%s\n", errno, strerror(errno));

From: Drew Fustini drew@beagleboard.org

[ Upstream commit d7af722344e6dc52d87649100516515263e15c75 ]

AM3358 pin mcasp0_aclkr (ZCZ ball B13) [0] is routed to P1.31 header [1] Mode 4 of this pin is mmc0_sdwp (SD Write Protect). A signal connected to P1.31 may accidentally trigger mmc0 write protection. To avoid this situation, do not put mcasp0_aclkr in mode 4 (mmc0_sdwp) by default.

[0] http://www.ti.com/lit/ds/symlink/am3358.pdf [1] https://github.com/beagleboard/pocketbeagle/wiki/System-Reference-Manual#531...

Fixes: 047905376a16 (ARM: dts: Add am335x-pocketbeagle) Signed-off-by: Robert Nelson robertcnelson@gmail.com Signed-off-by: Drew Fustini drew@beagleboard.org Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/am335x-pocketbeagle.dts | 1 - 1 file changed, 1 deletion(-)

diff --git a/arch/arm/boot/dts/am335x-pocketbeagle.dts b/arch/arm/boot/dts/am335x-pocketbeagle.dts index 4da719098028f..f0b222201b867 100644 --- a/arch/arm/boot/dts/am335x-pocketbeagle.dts +++ b/arch/arm/boot/dts/am335x-pocketbeagle.dts @@ -88,7 +88,6 @@ AM33XX_PADCONF(AM335X_PIN_MMC0_DAT3, PIN_INPUT_PULLUP, MUX_MODE0) AM33XX_PADCONF(AM335X_PIN_MMC0_CMD, PIN_INPUT_PULLUP, MUX_MODE0) AM33XX_PADCONF(AM335X_PIN_MMC0_CLK, PIN_INPUT_PULLUP, MUX_MODE0) - AM33XX_PADCONF(AM335X_PIN_MCASP0_ACLKR, PIN_INPUT, MUX_MODE4) /* (B12) mcasp0_aclkr.mmc0_sdwp */ >; };

From: David Rientjes rientjes@google.com

[ Upstream commit 96a539fa3bb71f443ae08e57b9f63d6e5bb2207c ]

If arch_dma_set_uncached() fails after memory has been decrypted, it needs to be re-encrypted before freeing.

Fixes: fa7e2247c572 ("dma-direct: make uncached_kernel_address more general") Signed-off-by: David Rientjes rientjes@google.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/dma/direct.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 8f4bbdaf965eb..4e789c46ff0bf 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -186,7 +186,7 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, arch_dma_prep_coherent(page, size); ret = arch_dma_set_uncached(ret, size); if (IS_ERR(ret)) - goto out_free_pages; + goto out_encrypt_pages; } done: if (force_dma_unencrypted(dev)) @@ -194,6 +194,11 @@ done: else *dma_handle = phys_to_dma(dev, page_to_phys(page)); return ret; + +out_encrypt_pages: + if (force_dma_unencrypted(dev)) + set_memory_encrypted((unsigned long)page_address(page), + 1 << get_order(size)); out_free_pages: dma_free_contiguous(dev, page, size); return NULL;

From: Dan Carpenter dan.carpenter@oracle.com

[ Upstream commit cc5277fe66cf3ad68f41f1c539b2ef0d5e432974 ]

The callers don't expect *d_cdp to be set to an error pointer, they only check for NULL. This leads to a static checker warning:

arch/x86/kernel/cpu/resctrl/rdtgroup.c:2648 __init_one_rdt_domain() warn: 'd_cdp' could be an error pointer

This would not trigger a bug in this specific case because __init_one_rdt_domain() calls it with a valid domain that would not have a negative id and thus not trigger the return of the ERR_PTR(). If this was a negative domain id then the call to rdt_find_domain() in domain_add_cpu() would have returned the ERR_PTR() much earlier and the creation of the domain with an invalid id would have been prevented.

Even though a bug is not triggered currently the right and safe thing to do is to set the pointer to NULL because that is what can be checked for when the caller is handling the CDP and non-CDP cases.

Fixes: 52eb74339a62 ("x86/resctrl: Fix rdt_find_domain() return value and checks") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Reinette Chatre reinette.chatre@intel.com Acked-by: Fenghua Yu fenghua.yu@intel.com Link: https://lkml.kernel.org/r/20200602193611.GA190851@mwanda Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 5a359d9fcc055..29a3878ab3c01 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1117,6 +1117,7 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, _d_cdp = rdt_find_domain(_r_cdp, d->id, NULL); if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) { _r_cdp = NULL; + _d_cdp = NULL; ret = -EINVAL; }

From: Charles Keepax ckeepax@opensource.cirrus.com

[ Upstream commit 95b2c3ec4cb1689db2389c251d39f64490ba641c ]

When a register patch is registered the reg_sequence is copied but the memory allocated is never freed. Add a kfree in regmap_exit to clean it up.

Fixes: 22f0d90a3482 ("regmap: Support register patch sets") Signed-off-by: Charles Keepax ckeepax@opensource.cirrus.com Link: https://lore.kernel.org/r/20200617152129.19655-1-ckeepax@opensource.cirrus.c... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/base/regmap/regmap.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 59f911e577192..508bbd6ea4396 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1356,6 +1356,7 @@ void regmap_exit(struct regmap *map) if (map->hwlock) hwspin_lock_free(map->hwlock); kfree_const(map->name); + kfree(map->patch); kfree(map); } EXPORT_SYMBOL_GPL(regmap_exit);

From: Stanislav Fomichev sdf@google.com

[ Upstream commit d8fe449a9c51a37d844ab607e14e2f5c657d3cf2 ]

Attaching to these hooks can break iptables because its optval is usually quite big, or at least bigger than the current PAGE_SIZE limit. David also mentioned some SCTP options can be big (around 256k).

For such optvals we expose only the first PAGE_SIZE bytes to the BPF program. BPF program has two options: 1. Set ctx->optlen to 0 to indicate that the BPF's optval should be ignored and the kernel should use original userspace value. 2. Set ctx->optlen to something that's smaller than the PAGE_SIZE.

v5: * use ctx->optlen == 0 with trimmed buffer (Alexei Starovoitov) * update the docs accordingly

v4: * use temporary buffer to avoid optval == optval_end == NULL; this removes the corner case in the verifier that might assume non-zero PTR_TO_PACKET/PTR_TO_PACKET_END.

v3: * don't increase the limit, bypass the argument

v2: * proper comments formatting (Jakub Kicinski)

Fixes: 0d01da6afc54 ("bpf: implement getsockopt and setsockopt hooks") Signed-off-by: Stanislav Fomichev sdf@google.com Signed-off-by: Alexei Starovoitov ast@kernel.org Cc: David Laight David.Laight@ACULAB.COM Link: https://lore.kernel.org/bpf/20200617010416.93086-1-sdf@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/bpf/cgroup.c | 53 ++++++++++++++++++++++++++++----------------- 1 file changed, 33 insertions(+), 20 deletions(-)

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index cb305e71e7deb..25aebd21c15b1 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1240,16 +1240,23 @@ static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,

static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen) { - if (unlikely(max_optlen > PAGE_SIZE) || max_optlen < 0) + if (unlikely(max_optlen < 0)) return -EINVAL;

+ if (unlikely(max_optlen > PAGE_SIZE)) { + /* We don't expose optvals that are greater than PAGE_SIZE + * to the BPF program. + */ + max_optlen = PAGE_SIZE; + } + ctx->optval = kzalloc(max_optlen, GFP_USER); if (!ctx->optval) return -ENOMEM;

ctx->optval_end = ctx->optval + max_optlen;

- return 0; + return max_optlen; }

static void sockopt_free_buf(struct bpf_sockopt_kern *ctx) @@ -1283,13 +1290,13 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, */ max_optlen = max_t(int, 16, *optlen);

- ret = sockopt_alloc_buf(&ctx, max_optlen); - if (ret) - return ret; + max_optlen = sockopt_alloc_buf(&ctx, max_optlen); + if (max_optlen < 0) + return max_optlen;

ctx.optlen = *optlen;

- if (copy_from_user(ctx.optval, optval, *optlen) != 0) { + if (copy_from_user(ctx.optval, optval, min(*optlen, max_optlen)) != 0) { ret = -EFAULT; goto out; } @@ -1317,8 +1324,14 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, /* export any potential modifications */ *level = ctx.level; *optname = ctx.optname; - *optlen = ctx.optlen; - *kernel_optval = ctx.optval; + + /* optlen == 0 from BPF indicates that we should + * use original userspace data. + */ + if (ctx.optlen != 0) { + *optlen = ctx.optlen; + *kernel_optval = ctx.optval; + } }

out: @@ -1350,12 +1363,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT)) return retval;

- ret = sockopt_alloc_buf(&ctx, max_optlen); - if (ret) - return ret; - ctx.optlen = max_optlen;

+ max_optlen = sockopt_alloc_buf(&ctx, max_optlen); + if (max_optlen < 0) + return max_optlen; + if (!retval) { /* If kernel getsockopt finished successfully, * copy whatever was returned to the user back @@ -1369,10 +1382,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; }

- if (ctx.optlen > max_optlen) - ctx.optlen = max_optlen; - - if (copy_from_user(ctx.optval, optval, ctx.optlen) != 0) { + if (copy_from_user(ctx.optval, optval, + min(ctx.optlen, max_optlen)) != 0) { ret = -EFAULT; goto out; } @@ -1401,10 +1412,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; }

- if (copy_to_user(optval, ctx.optval, ctx.optlen) || - put_user(ctx.optlen, optlen)) { - ret = -EFAULT; - goto out; + if (ctx.optlen != 0) { + if (copy_to_user(optval, ctx.optval, ctx.optlen) || + put_user(ctx.optlen, optlen)) { + ret = -EFAULT; + goto out; + } }

ret = ctx.retval;

From: David Howells dhowells@redhat.com

[ Upstream commit a2ad7c21ad8cf1ce4ad65e13df1c2a1c29b38ac5 ]

The handling of the receive window size (rwind) from a received ACK packet is not correct. The rxrpc_input_ackinfo() function currently checks the current Tx window size against the rwind from the ACK to see if it has changed, but then limits the rwind size before storing it in the tx_winsize member and, if it increased, wake up the transmitting process. This means that if rwind > RXRPC_RXTX_BUFF_SIZE - 1, this path will always be followed.

Fix this by limiting rwind before we compare it to tx_winsize.

The effect of this can be seen by enabling the rxrpc_rx_rwind_change tracepoint.

Fixes: 702f2ac87a9a ("rxrpc: Wake up the transmitter if Rx window size increases on the peer") Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/rxrpc/input.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 3be4177baf707..22dec6049e1bb 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -723,13 +723,12 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU), rwind, ntohl(ackinfo->jumbo_max));

+ if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) + rwind = RXRPC_RXTX_BUFF_SIZE - 1; if (call->tx_winsize != rwind) { - if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) - rwind = RXRPC_RXTX_BUFF_SIZE - 1; if (rwind > call->tx_winsize) wake = true; - trace_rxrpc_rx_rwind_change(call, sp->hdr.serial, - ntohl(ackinfo->rwind), wake); + trace_rxrpc_rx_rwind_change(call, sp->hdr.serial, rwind, wake); call->tx_winsize = rwind; }

From: Gal Pressman galpress@amazon.com

[ Upstream commit 0133654d8eb8607eacc96badfe49bf992155f4cb ]

The max_pkeys device attribute was not set in query device verb, set it to one in order to account for the default pkey (0xffff). This information is exposed to userspace and can cause malfunction

Fixes: 40909f664d27 ("RDMA/efa: Add EFA verbs implementation") Link: https://lore.kernel.org/r/20200614103534.88060-1-galpress@amazon.com Reviewed-by: Firas JahJah firasj@amazon.com Reviewed-by: Yossi Leybovich sleybo@amazon.com Signed-off-by: Gal Pressman galpress@amazon.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/efa/efa_verbs.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 5c57098a4aee5..3420c77424861 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -209,6 +209,7 @@ int efa_query_device(struct ib_device *ibdev, props->max_send_sge = dev_attr->max_sq_sge; props->max_recv_sge = dev_attr->max_rq_sge; props->max_sge_rd = dev_attr->max_wr_rdma_sge; + props->max_pkeys = 1;

if (udata && udata->outlen) { resp.max_sq_sge = dev_attr->max_sq_sge;

From: Mark Zhang markz@mellanox.com

[ Upstream commit 730c8912484186d4623d0c76509066d285c3a755 ]

The bind_list and listen_list must be accessed under a lock, add the missing locking around the access in cm_ib_id_from_event()

In addition add lockdep asserts to make it clearer what the locking semantic is here.

general protection fault: 0000 [#1] SMP NOPTI CPU: 226 PID: 126135 Comm: kworker/226:1 Tainted: G OE 4.12.14-150.47-default #1 SLE15 Hardware name: Cray Inc. Windom/Windom, BIOS 0.8.7 01-10-2020 Workqueue: ib_cm cm_work_handler [ib_cm] task: ffff9c5a60a1d2c0 task.stack: ffffc1d91f554000 RIP: 0010:cma_ib_req_handler+0x3f1/0x11b0 [rdma_cm] RSP: 0018:ffffc1d91f557b40 EFLAGS: 00010286 RAX: deacffffffffff30 RBX: 0000000000000001 RCX: ffff9c2af5bb6000 RDX: 00000000000000a9 RSI: ffff9c5aa4ed2f10 RDI: ffffc1d91f557b08 RBP: ffffc1d91f557d90 R08: ffff9c340cc80000 R09: ffff9c2c0f901900 R10: 0000000000000000 R11: 0000000000000001 R12: deacffffffffff30 R13: ffff9c5a48aeec00 R14: ffffc1d91f557c30 R15: ffff9c5c2eea3688 FS: 0000000000000000(0000) GS:ffff9c5c2fa80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00002b5cc03fa320 CR3: 0000003f8500a000 CR4: 00000000003406e0 Call Trace: ? rdma_addr_cancel+0xa0/0xa0 [ib_core] ? cm_process_work+0x28/0x140 [ib_cm] cm_process_work+0x28/0x140 [ib_cm] ? cm_get_bth_pkey.isra.44+0x34/0xa0 [ib_cm] cm_work_handler+0xa06/0x1a6f [ib_cm] ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 ? __switch_to+0x7c/0x4b0 ? __switch_to_asm+0x40/0x70 ? __switch_to_asm+0x34/0x70 process_one_work+0x1da/0x400 worker_thread+0x2b/0x3f0 ? process_one_work+0x400/0x400 kthread+0x118/0x140 ? kthread_create_on_node+0x40/0x40 ret_from_fork+0x22/0x40 Code: 00 66 83 f8 02 0f 84 ca 05 00 00 49 8b 84 24 d0 01 00 00 48 85 c0 0f 84 68 07 00 00 48 2d d0 01 00 00 49 89 c4 0f 84 59 07 00 00 <41> 0f b7 44 24 20 49 8b 77 50 66 83 f8 0a 75 9e 49 8b 7c 24 28

Fixes: 4c21b5bcef73 ("IB/cma: Add net_dev and private data checks to RDMA CM") Link: https://lore.kernel.org/r/20200616104304.2426081-1-leon@kernel.org Signed-off-by: Mark Zhang markz@mellanox.com Reviewed-by: Maor Gottlieb maorg@mellanox.com Signed-off-by: Leon Romanovsky leonro@mellanox.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/core/cma.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 26e6f7df247b6..12ada58c96a90 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1619,6 +1619,8 @@ static struct rdma_id_private *cma_find_listener( { struct rdma_id_private *id_priv, *id_priv_dev;

+ lockdep_assert_held(&lock); + if (!bind_list) return ERR_PTR(-EINVAL);

@@ -1665,6 +1667,7 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id, } }

+ mutex_lock(&lock); /* * Net namespace might be getting deleted while route lookup, * cm_id lookup is in progress. Therefore, perform netdevice @@ -1706,6 +1709,7 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id, id_priv = cma_find_listener(bind_list, cm_id, ib_event, req, *net_dev); err: rcu_read_unlock(); + mutex_unlock(&lock); if (IS_ERR(id_priv) && *net_dev) { dev_put(*net_dev); *net_dev = NULL; @@ -2481,6 +2485,8 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv, struct net *net = id_priv->id.route.addr.dev_addr.net; int ret;

+ lockdep_assert_held(&lock); + if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1)) return;

@@ -3308,6 +3314,8 @@ static void cma_bind_port(struct rdma_bind_list *bind_list, u64 sid, mask; __be16 port;

+ lockdep_assert_held(&lock); + addr = cma_src_addr(id_priv); port = htons(bind_list->port);

@@ -3336,6 +3344,8 @@ static int cma_alloc_port(enum rdma_ucm_port_space ps, struct rdma_bind_list *bind_list; int ret;

+ lockdep_assert_held(&lock); + bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL); if (!bind_list) return -ENOMEM; @@ -3362,6 +3372,8 @@ static int cma_port_is_unique(struct rdma_bind_list *bind_list, struct sockaddr *saddr = cma_src_addr(id_priv); __be16 dport = cma_port(daddr);

+ lockdep_assert_held(&lock); + hlist_for_each_entry(cur_id, &bind_list->owners, node) { struct sockaddr *cur_daddr = cma_dst_addr(cur_id); struct sockaddr *cur_saddr = cma_src_addr(cur_id); @@ -3401,6 +3413,8 @@ static int cma_alloc_any_port(enum rdma_ucm_port_space ps, unsigned int rover; struct net *net = id_priv->id.route.addr.dev_addr.net;

+ lockdep_assert_held(&lock); + inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; rover = prandom_u32() % remaining + low; @@ -3448,6 +3462,8 @@ static int cma_check_port(struct rdma_bind_list *bind_list, struct rdma_id_private *cur_id; struct sockaddr *addr, *cur_addr;

+ lockdep_assert_held(&lock); + addr = cma_src_addr(id_priv); hlist_for_each_entry(cur_id, &bind_list->owners, node) { if (id_priv == cur_id) @@ -3478,6 +3494,8 @@ static int cma_use_port(enum rdma_ucm_port_space ps, unsigned short snum; int ret;

+ lockdep_assert_held(&lock); + snum = ntohs(cma_port(cma_src_addr(id_priv))); if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) return -EACCES;

From: Qiushi Wu wu000273@umn.edu

[ Upstream commit f141a422159a199f4c8dedb7e0df55b3b2cf16cd ]

Calling pm_runtime_get_sync increments the counter even in case of failure, causing incorrect ref count if pm_runtime_put is not called in error handling paths. Call pm_runtime_put if pm_runtime_get_sync fails.

Fixes: fc05a5b22253 ("ASoC: rockchip: add support for pdm controller") Signed-off-by: Qiushi Wu wu000273@umn.edu Reviewed-by: Heiko Stuebner heiko@sntech.de Link: https://lore.kernel.org/r/20200613205158.27296-1-wu000273@umn.edu Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/rockchip/rockchip_pdm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/sound/soc/rockchip/rockchip_pdm.c b/sound/soc/rockchip/rockchip_pdm.c index 7cd42fcfcf38a..1707414cfa921 100644 --- a/sound/soc/rockchip/rockchip_pdm.c +++ b/sound/soc/rockchip/rockchip_pdm.c @@ -590,8 +590,10 @@ static int rockchip_pdm_resume(struct device *dev) int ret;

ret = pm_runtime_get_sync(dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put(dev); return ret; + }

ret = regcache_sync(pdm->regmap);

From: Fan Guo guofan5@huawei.com

[ Upstream commit a17f4bed811c60712d8131883cdba11a105d0161 ]

If ib_dma_mapping_error() returns non-zero value, ib_mad_post_receive_mads() will jump out of loops and return -ENOMEM without freeing mad_priv. Fix this memory-leak problem by freeing mad_priv in this case.

Fixes: 2c34e68f4261 ("IB/mad: Check and handle potential DMA mapping errors") Link: https://lore.kernel.org/r/20200612063824.180611-1-guofan5@huawei.com Signed-off-by: Fan Guo guofan5@huawei.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/core/mad.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index f7626ebcf31cf..049c9cdc10dec 100644 --- a/drivers/infiniband/core/mad.c +++ b/drivers/infiniband/core/mad.c @@ -2941,6 +2941,7 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info, DMA_FROM_DEVICE); if (unlikely(ib_dma_mapping_error(qp_info->port_priv->device, sg_list.addr))) { + kfree(mad_priv); ret = -ENOMEM; break; }

From: Shannon Nelson snelson@pensando.io

[ Upstream commit b59eabd23ee53e8c3492602722e1697f9a2f63ad ]

Even with moving netif_tx_disable() to an earlier point when taking down the queues for a reconfiguration, we still end up with the occasional netdev watchdog Tx Timeout complaint. The old method of using netif_trans_update() works fine for queue 0, but has no effect on the remaining queues. Using netif_device_detach() allows us to signal to the watchdog to ignore us for the moment.

Fixes: beead698b173 ("ionic: Add the basic NDO callbacks for netdev support") Signed-off-by: Shannon Nelson snelson@pensando.io Acked-by: Jonathan Toppins jtoppins@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/pensando/ionic/ionic_lif.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 2729b0bb12739..790d4854b8ef5 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1682,8 +1682,8 @@ static void ionic_stop_queues(struct ionic_lif *lif) if (!test_and_clear_bit(IONIC_LIF_F_UP, lif->state)) return;

- ionic_txrx_disable(lif); netif_tx_disable(lif->netdev); + ionic_txrx_disable(lif); }

int ionic_stop(struct net_device *netdev) @@ -1949,18 +1949,19 @@ int ionic_reset_queues(struct ionic_lif *lif) bool running; int err = 0;

- /* Put off the next watchdog timeout */ - netif_trans_update(lif->netdev); - err = ionic_wait_for_bit(lif, IONIC_LIF_F_QUEUE_RESET); if (err) return err;

running = netif_running(lif->netdev); - if (running) + if (running) { + netif_device_detach(lif->netdev); err = ionic_stop(lif->netdev); - if (!err && running) + } + if (!err && running) { ionic_open(lif->netdev); + netif_device_attach(lif->netdev); + }

clear_bit(IONIC_LIF_F_QUEUE_RESET, lif->state);

From: Lu Baolu baolu.lu@linux.intel.com

[ Upstream commit 16ecf10e815d70d11d2300243f4a3b4c7c5acac7 ]

When using first-level translation for IOVA, currently the U/S bit in the page table is cleared which implies DMA requests with user privilege are blocked. As the result, following error messages might be observed when passing through a device to user level:

DMAR: DRHD: handling fault status reg 3 DMAR: [DMA Read] Request device [41:00.0] PASID 1 fault addr 7ecdcd000 [fault reason 129] SM: U/S set 0 for first-level translation with user privilege

This fixes it by setting U/S bit in the first level page table and makes IOVA over first level compatible with previous second-level translation.

Fixes: b802d070a52a1 ("iommu/vt-d: Use iova over first level") Reported-by: Xin Zeng xin.zeng@intel.com Signed-off-by: Lu Baolu baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20200622231345.29722-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iommu/intel-iommu.c | 5 ++--- include/linux/intel-iommu.h | 1 + 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index fde7aba49b746..a0b9ea0805210 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -943,7 +943,7 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE); pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE; if (domain_use_first_level(domain)) - pteval |= DMA_FL_PTE_XD; + pteval |= DMA_FL_PTE_XD | DMA_FL_PTE_US; if (cmpxchg64(&pte->val, 0ULL, pteval)) /* Someone else set it while we were thinking; use theirs. */ free_pgtable_page(tmp_page); @@ -2034,7 +2034,6 @@ static inline void context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid) { context->hi |= pasid & ((1 << 20) - 1); - context->hi |= (1 << 20); }

/* @@ -2326,7 +2325,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,

attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP); if (domain_use_first_level(domain)) - attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD; + attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD | DMA_FL_PTE_US;

if (!sg) { sg_res = nr_pages; diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index de23fb95fe918..64a5335046b00 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -40,6 +40,7 @@ #define DMA_PTE_SNP BIT_ULL(11)

#define DMA_FL_PTE_PRESENT BIT_ULL(0) +#define DMA_FL_PTE_US BIT_ULL(2) #define DMA_FL_PTE_XD BIT_ULL(63)

#define CONTEXT_TT_MULTI_LEVEL 0

From: Lu Baolu baolu.lu@linux.intel.com

[ Upstream commit 04c00956ee3cd138fd38560a91452a804a8c5550 ]

The Scalable-mode Page-walk Coherency (SMPWC) field in the VT-d extended capability register indicates the hardware coherency behavior on paging structures accessed through the pasid table entry. This is ignored in current code and using ECAP.C instead which is only valid in legacy mode. Fix this so that paging structure updates could be manually flushed from the cache line if hardware page walking is not snooped.

Fixes: 765b6a98c1de3 ("iommu/vt-d: Enumerate the scalable mode capability") Signed-off-by: Lu Baolu baolu.lu@linux.intel.com Cc: Ashok Raj ashok.raj@intel.com Cc: Kevin Tian kevin.tian@intel.com Cc: Jacob Pan jacob.jun.pan@linux.intel.com Link: https://lore.kernel.org/r/20200622231345.29722-6-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iommu/intel-iommu.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index a0b9ea0805210..34b2ed91cf4d9 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -634,6 +634,12 @@ struct intel_iommu *domain_get_iommu(struct dmar_domain *domain) return g_iommus[iommu_id]; }

+static inline bool iommu_paging_structure_coherency(struct intel_iommu *iommu) +{ + return sm_supported(iommu) ? + ecap_smpwc(iommu->ecap) : ecap_coherent(iommu->ecap); +} + static void domain_update_iommu_coherency(struct dmar_domain *domain) { struct dmar_drhd_unit *drhd; @@ -645,7 +651,7 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain)

for_each_domain_iommu(i, domain) { found = true; - if (!ecap_coherent(g_iommus[i]->ecap)) { + if (!iommu_paging_structure_coherency(g_iommus[i])) { domain->iommu_coherency = 0; break; } @@ -656,7 +662,7 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain) /* No hardware attached; use lowest common denominator */ rcu_read_lock(); for_each_active_iommu(iommu, drhd) { - if (!ecap_coherent(iommu->ecap)) { + if (!iommu_paging_structure_coherency(iommu)) { domain->iommu_coherency = 0; break; } @@ -2177,7 +2183,8 @@ static int domain_context_mapping_one(struct dmar_domain *domain,

context_set_fault_enable(context); context_set_present(context); - domain_flush_cache(domain, context, sizeof(*context)); + if (!ecap_coherent(iommu->ecap)) + clflush_cache_range(context, sizeof(*context));

/* * It's a non-present to present mapping. If hardware doesn't cache

From: David Rientjes rientjes@google.com

[ Upstream commit 1a2b3357e860d890f8045367b179c7e7e802cd71 ]

When a coherent mapping is created in dma_direct_alloc_pages(), it needs to be decrypted if the device requires unencrypted DMA before returning.

Fixes: 3acac065508f ("dma-mapping: merge the generic remapping helpers into dma-direct") Signed-off-by: David Rientjes rientjes@google.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/dma/direct.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 98c445dcb308b..2270930f36f83 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -161,6 +161,12 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, __builtin_return_address(0)); if (!ret) goto out_free_pages; + if (force_dma_unencrypted(dev)) { + err = set_memory_decrypted((unsigned long)ret, + 1 << get_order(size)); + if (err) + goto out_free_pages; + } memset(ret, 0, size); goto done; }

From: Alexander Lobakin alobakin@marvell.com

[ Upstream commit 31333c1a2521ff4b4ceb0c29de492549cd4a8de3 ]

qed_spq_unregister_async_cb() should be called before qed_rdma_info_free() to avoid crash-spawning uses-after-free. Instead of calling it from each subsystem exit code, do it in one place on PF down.

Fixes: 291d57f67d24 ("qed: Fix rdma_info structure allocation") Signed-off-by: Alexander Lobakin alobakin@marvell.com Signed-off-by: Igor Russkikh irusskikh@marvell.com Signed-off-by: Michal Kalderon michal.kalderon@marvell.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qed/qed_dev.c | 9 +++++++-- drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 2 -- drivers/net/ethernet/qlogic/qed/qed_roce.c | 1 - 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 38a65b984e476..9b00988fb77e1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -1368,6 +1368,8 @@ static void qed_dbg_user_data_free(struct qed_hwfn *p_hwfn)

void qed_resc_free(struct qed_dev *cdev) { + struct qed_rdma_info *rdma_info; + struct qed_hwfn *p_hwfn; int i;

if (IS_VF(cdev)) { @@ -1385,7 +1387,8 @@ void qed_resc_free(struct qed_dev *cdev) qed_llh_free(cdev);

for_each_hwfn(cdev, i) { - struct qed_hwfn *p_hwfn = &cdev->hwfns[i]; + p_hwfn = cdev->hwfns + i; + rdma_info = p_hwfn->p_rdma_info;

qed_cxt_mngr_free(p_hwfn); qed_qm_info_free(p_hwfn); @@ -1404,8 +1407,10 @@ void qed_resc_free(struct qed_dev *cdev) qed_ooo_free(p_hwfn); }

- if (QED_IS_RDMA_PERSONALITY(p_hwfn)) + if (QED_IS_RDMA_PERSONALITY(p_hwfn) && rdma_info) { + qed_spq_unregister_async_cb(p_hwfn, rdma_info->proto); qed_rdma_info_free(p_hwfn); + }

qed_iov_free(p_hwfn); qed_l2_free(p_hwfn); diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index d2fe61a5cf567..5409a2da6106d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -2836,8 +2836,6 @@ int qed_iwarp_stop(struct qed_hwfn *p_hwfn) if (rc) return rc;

- qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_IWARP); - return qed_iwarp_ll2_stop(p_hwfn); }

diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c index 37e70562a9645..f15c26ef88709 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.c +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c @@ -113,7 +113,6 @@ void qed_roce_stop(struct qed_hwfn *p_hwfn) break; } } - qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_ROCE); }

static void qed_rdma_copy_gids(struct qed_rdma_qp *qp, __le32 *src_gid,

From: Alexander Lobakin alobakin@marvell.com

[ Upstream commit ccd7c7ce167a21dbf2b698ffcf00f11d96d44f9b ]

25ms sleep cycles in waiting for PF response are excessive and may lead to different timeout failures.

Start to wait with short udelays, and in most cases polling will end here. If the time was not sufficient, switch to msleeps. usleep_range() may go far beyond 100us depending on platform and tick configuration, hence atomic udelays for consistency.

Also add explicit DMA barriers since 'done' always comes from a shared request-response DMA pool, and note that in the comment nearby.

Fixes: 1408cc1fa48c ("qed: Introduce VFs") Signed-off-by: Alexander Lobakin alobakin@marvell.com Signed-off-by: Igor Russkikh irusskikh@marvell.com Signed-off-by: Michal Kalderon michal.kalderon@marvell.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qed/qed_vf.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 856051f50eb75..adc2c8f3d48ef 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -81,12 +81,17 @@ static void qed_vf_pf_req_end(struct qed_hwfn *p_hwfn, int req_status) mutex_unlock(&(p_hwfn->vf_iov_info->mutex)); }

+#define QED_VF_CHANNEL_USLEEP_ITERATIONS 90 +#define QED_VF_CHANNEL_USLEEP_DELAY 100 +#define QED_VF_CHANNEL_MSLEEP_ITERATIONS 10 +#define QED_VF_CHANNEL_MSLEEP_DELAY 25 + static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size) { union vfpf_tlvs *p_req = p_hwfn->vf_iov_info->vf2pf_request; struct ustorm_trigger_vf_zone trigger; struct ustorm_vf_zone *zone_data; - int rc = 0, time = 100; + int iter, rc = 0;

zone_data = (struct ustorm_vf_zone *)PXP_VF_BAR0_START_USDM_ZONE_B;

@@ -126,11 +131,19 @@ static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size) REG_WR(p_hwfn, (uintptr_t)&zone_data->trigger, *((u32 *)&trigger));

/* When PF would be done with the response, it would write back to the - * `done' address. Poll until then. + * `done' address from a coherent DMA zone. Poll until then. */ - while ((!*done) && time) { - msleep(25); - time--; + + iter = QED_VF_CHANNEL_USLEEP_ITERATIONS; + while (!*done && iter--) { + udelay(QED_VF_CHANNEL_USLEEP_DELAY); + dma_rmb(); + } + + iter = QED_VF_CHANNEL_MSLEEP_ITERATIONS; + while (!*done && iter--) { + msleep(QED_VF_CHANNEL_MSLEEP_DELAY); + dma_rmb(); }

if (!*done) {

From: Alexander Lobakin alobakin@marvell.com

[ Upstream commit 1c85f394c2206ea3835f43534d5675f0574e1b70 ]

Currently PTP cyclecounter and timecounter are initialized only on the first probing and are cleaned up during removal. This means that PTP becomes non-functional after device recovery. Fix this by unconditional PTP initialization on probing and clearing Tx pending bit on exiting.

Fixes: ccc67ef50b90 ("qede: Error recovery process") Signed-off-by: Alexander Lobakin alobakin@marvell.com Signed-off-by: Igor Russkikh irusskikh@marvell.com Signed-off-by: Michal Kalderon michal.kalderon@marvell.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qede/qede_main.c | 2 +- drivers/net/ethernet/qlogic/qede/qede_ptp.c | 31 ++++++++------------ drivers/net/ethernet/qlogic/qede/qede_ptp.h | 2 +- 3 files changed, 15 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 1a83d1fd8ccd6..51bb5866a212c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -1158,7 +1158,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,

/* PTP not supported on VFs */ if (!is_vf) - qede_ptp_enable(edev, (mode == QEDE_PROBE_NORMAL)); + qede_ptp_enable(edev);

edev->ops->register_ops(cdev, &qede_ll_ops, edev);

diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c index 4c7f7a7fc1515..cd5841a9415ef 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c @@ -412,6 +412,7 @@ void qede_ptp_disable(struct qede_dev *edev) if (ptp->tx_skb) { dev_kfree_skb_any(ptp->tx_skb); ptp->tx_skb = NULL; + clear_bit_unlock(QEDE_FLAGS_PTP_TX_IN_PRORGESS, &edev->flags); }

/* Disable PTP in HW */ @@ -423,7 +424,7 @@ void qede_ptp_disable(struct qede_dev *edev) edev->ptp = NULL; }

-static int qede_ptp_init(struct qede_dev *edev, bool init_tc) +static int qede_ptp_init(struct qede_dev *edev) { struct qede_ptp *ptp; int rc; @@ -444,25 +445,19 @@ static int qede_ptp_init(struct qede_dev *edev, bool init_tc) /* Init work queue for Tx timestamping */ INIT_WORK(&ptp->work, qede_ptp_task);

- /* Init cyclecounter and timecounter. This is done only in the first - * load. If done in every load, PTP application will fail when doing - * unload / load (e.g. MTU change) while it is running. - */ - if (init_tc) { - memset(&ptp->cc, 0, sizeof(ptp->cc)); - ptp->cc.read = qede_ptp_read_cc; - ptp->cc.mask = CYCLECOUNTER_MASK(64); - ptp->cc.shift = 0; - ptp->cc.mult = 1; - - timecounter_init(&ptp->tc, &ptp->cc, - ktime_to_ns(ktime_get_real())); - } + /* Init cyclecounter and timecounter */ + memset(&ptp->cc, 0, sizeof(ptp->cc)); + ptp->cc.read = qede_ptp_read_cc; + ptp->cc.mask = CYCLECOUNTER_MASK(64); + ptp->cc.shift = 0; + ptp->cc.mult = 1;

- return rc; + timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real())); + + return 0; }

-int qede_ptp_enable(struct qede_dev *edev, bool init_tc) +int qede_ptp_enable(struct qede_dev *edev) { struct qede_ptp *ptp; int rc; @@ -483,7 +478,7 @@ int qede_ptp_enable(struct qede_dev *edev, bool init_tc)

edev->ptp = ptp;

- rc = qede_ptp_init(edev, init_tc); + rc = qede_ptp_init(edev); if (rc) goto err1;

diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.h b/drivers/net/ethernet/qlogic/qede/qede_ptp.h index 691a14c4b2c5a..89c7f3cf3ee28 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.h +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.h @@ -41,7 +41,7 @@ void qede_ptp_rx_ts(struct qede_dev *edev, struct sk_buff *skb); void qede_ptp_tx_ts(struct qede_dev *edev, struct sk_buff *skb); int qede_ptp_hw_ts(struct qede_dev *edev, struct ifreq *req); void qede_ptp_disable(struct qede_dev *edev); -int qede_ptp_enable(struct qede_dev *edev, bool init_tc); +int qede_ptp_enable(struct qede_dev *edev); int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *ts);

static inline void qede_ptp_record_rx_ts(struct qede_dev *edev,

From: Alexander Lobakin alobakin@marvell.com

[ Upstream commit c221dd1831732449f844e03631a34fd21c2b9429 ]

Sizes of all ILT blocks must be reset before ILT recomputing when disabling clients, or memory allocation may exceed ILT shadow array and provoke system crashes.

Fixes: 1408cc1fa48c ("qed: Introduce VFs") Signed-off-by: Alexander Lobakin alobakin@marvell.com Signed-off-by: Igor Russkikh irusskikh@marvell.com Signed-off-by: Michal Kalderon michal.kalderon@marvell.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qed/qed_cxt.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 1880aa1d3bb59..aeed8939f410a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -442,6 +442,20 @@ static struct qed_ilt_cli_blk *qed_cxt_set_blk(struct qed_ilt_cli_blk *p_blk) return p_blk; }

+static void qed_cxt_ilt_blk_reset(struct qed_hwfn *p_hwfn) +{ + struct qed_ilt_client_cfg *clients = p_hwfn->p_cxt_mngr->clients; + u32 cli_idx, blk_idx; + + for (cli_idx = 0; cli_idx < MAX_ILT_CLIENTS; cli_idx++) { + for (blk_idx = 0; blk_idx < ILT_CLI_PF_BLOCKS; blk_idx++) + clients[cli_idx].pf_blks[blk_idx].total_size = 0; + + for (blk_idx = 0; blk_idx < ILT_CLI_VF_BLOCKS; blk_idx++) + clients[cli_idx].vf_blks[blk_idx].total_size = 0; + } +} + int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *line_count) { struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr; @@ -461,6 +475,11 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *line_count)

p_mngr->pf_start_line = RESC_START(p_hwfn, QED_ILT);

+ /* Reset all ILT blocks at the beginning of ILT computing in order + * to prevent memory allocation for irrelevant blocks afterwards. + */ + qed_cxt_ilt_blk_reset(p_hwfn); + DP_VERBOSE(p_hwfn, QED_MSG_ILT, "hwfn [%d] - Set context manager starting line to be 0x%08x\n", p_hwfn->my_id, p_hwfn->p_cxt_mngr->pf_start_line);

From: Rahul Lakkireddy rahul.lakkireddy@chelsio.com

[ Upstream commit 030c98824deaba205787af501a074b3d7f46e32e ]

Check for whether PTP is enabled or not at the caller and perform locking/unlocking at the caller.

Fixes following sparse warning: sge.c:1641:26: warning: context imbalance in 'cxgb4_eth_xmit' - different lock contexts for basic block

Fixes: a456950445a0 ("cxgb4: time stamping interface for PTP") Signed-off-by: Rahul Lakkireddy rahul.lakkireddy@chelsio.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/chelsio/cxgb4/sge.c | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 6516c45864b35..db8106d9d6edf 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -1425,12 +1425,10 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)

qidx = skb_get_queue_mapping(skb); if (ptp_enabled) { - spin_lock(&adap->ptp_lock); if (!(adap->ptp_tx_skb)) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; adap->ptp_tx_skb = skb_get(skb); } else { - spin_unlock(&adap->ptp_lock); goto out_free; } q = &adap->sge.ptptxq; @@ -1444,11 +1442,8 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)

#ifdef CONFIG_CHELSIO_T4_FCOE ret = cxgb_fcoe_offload(skb, adap, pi, &cntrl); - if (unlikely(ret == -ENOTSUPP)) { - if (ptp_enabled) - spin_unlock(&adap->ptp_lock); + if (unlikely(ret == -EOPNOTSUPP)) goto out_free; - } #endif /* CONFIG_CHELSIO_T4_FCOE */

chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip); @@ -1461,8 +1456,6 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) dev_err(adap->pdev_dev, "%s: Tx ring %u full while queue awake!\n", dev->name, qidx); - if (ptp_enabled) - spin_unlock(&adap->ptp_lock); return NETDEV_TX_BUSY; }

@@ -1481,8 +1474,6 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) unlikely(cxgb4_map_skb(adap->pdev_dev, skb, sgl_sdesc->addr) < 0)) { memset(sgl_sdesc->addr, 0, sizeof(sgl_sdesc->addr)); q->mapping_err++; - if (ptp_enabled) - spin_unlock(&adap->ptp_lock); goto out_free; }

@@ -1630,8 +1621,6 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) txq_advance(&q->q, ndesc);

cxgb4_ring_tx_db(adap, &q->q, ndesc); - if (ptp_enabled) - spin_unlock(&adap->ptp_lock); return NETDEV_TX_OK;

out_free: @@ -2365,6 +2354,16 @@ netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(qid >= pi->nqsets)) return cxgb4_ethofld_xmit(skb, dev);

+ if (is_ptp_enabled(skb, dev)) { + struct adapter *adap = netdev2adap(dev); + netdev_tx_t ret; + + spin_lock(&adap->ptp_lock); + ret = cxgb4_eth_xmit(skb, dev); + spin_unlock(&adap->ptp_lock); + return ret; + } + return cxgb4_eth_xmit(skb, dev); }

From: SeongJae Park sjpark@amazon.de

[ Upstream commit 46da547e21d6cefceec3fb3dba5ebbca056627fc ]

Commit cdb42becdd40 ("scsi: lpfc: Replace io_channels for nvme and fcp with general hdw_queues per cpu") has introduced static checker warnings for potential null dereferences in 'lpfc_sli4_hba_unset()' and commit 1ffdd2c0440d ("scsi: lpfc: resolve static checker warning in lpfc_sli4_hba_unset") has tried to fix it. However, yet another potential null dereference is remaining. This commit fixes it.

This bug was discovered and resolved using Coverity Static Analysis Security Testing (SAST) by Synopsys, Inc.

Link: https://lore.kernel.org/r/20200623084122.30633-1-sjpark@amazon.com Fixes: 1ffdd2c0440d ("scsi: lpfc: resolve static checker warning inlpfc_sli4_hba_unset") Fixes: cdb42becdd40 ("scsi: lpfc: Replace io_channels for nvme and fcp with general hdw_queues per cpu") Reviewed-by: James Smart james.smart@broadcom.com Signed-off-by: SeongJae Park sjpark@amazon.de Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/lpfc/lpfc_init.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 4104bdcdbb6fd..70be1f5de8730 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -11895,7 +11895,8 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba) lpfc_sli4_xri_exchange_busy_wait(phba);

/* per-phba callback de-registration for hotplug event */ - lpfc_cpuhp_remove(phba); + if (phba->pport) + lpfc_cpuhp_remove(phba);

/* Disable PCI subsystem interrupt */ lpfc_sli4_disable_intr(phba);

From: Yoshihiro Shimoda yoshihiro.shimoda.uh@renesas.com

[ Upstream commit ea0efd687b01355cd799c8643d0c636ba4859ffc ]

This driver assumed that dmaengine_tx_status() could return the residue even if the transfer was completed. However, this was not correct usage [1] and this caused to break getting the residue after the commit 24461d9792c2 ("dmaengine: virt-dma: Fix access after free in vchan_complete()") actually. So, this is possible to get wrong received size if the usb controller gets a short packet. For example, g_zero driver causes "bad OUT byte" errors.

The usb-dmac driver will support the callback_result, so this driver can use it to get residue correctly. Note that even if the usb-dmac driver has not supported the callback_result yet, this patch doesn't cause any side-effects.

[1] https://lore.kernel.org/dmaengine/20200616165550.GP2324254@vkoul-mobl/

Reported-by: Hien Dang hien.dang.eb@renesas.com Fixes: 24461d9792c2 ("dmaengine: virt-dma: Fix access after free in vchan_complete()") Signed-off-by: Yoshihiro Shimoda yoshihiro.shimoda.uh@renesas.com Link: https://lore.kernel.org/r/1592482277-19563-1-git-send-email-yoshihiro.shimod... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/renesas_usbhs/fifo.c | 23 +++++++++++++---------- drivers/usb/renesas_usbhs/fifo.h | 2 +- 2 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c index 01c6a48c41bc9..ac9a81ae82164 100644 --- a/drivers/usb/renesas_usbhs/fifo.c +++ b/drivers/usb/renesas_usbhs/fifo.c @@ -803,7 +803,8 @@ static int __usbhsf_dma_map_ctrl(struct usbhs_pkt *pkt, int map) return info->dma_map_ctrl(chan->device->dev, pkt, map); }

-static void usbhsf_dma_complete(void *arg); +static void usbhsf_dma_complete(void *arg, + const struct dmaengine_result *result); static void usbhsf_dma_xfer_preparing(struct usbhs_pkt *pkt) { struct usbhs_pipe *pipe = pkt->pipe; @@ -813,6 +814,7 @@ static void usbhsf_dma_xfer_preparing(struct usbhs_pkt *pkt) struct dma_chan *chan; struct device *dev = usbhs_priv_to_dev(priv); enum dma_transfer_direction dir; + dma_cookie_t cookie;

fifo = usbhs_pipe_to_fifo(pipe); if (!fifo) @@ -827,11 +829,11 @@ static void usbhsf_dma_xfer_preparing(struct usbhs_pkt *pkt) if (!desc) return;

- desc->callback = usbhsf_dma_complete; - desc->callback_param = pipe; + desc->callback_result = usbhsf_dma_complete; + desc->callback_param = pkt;

- pkt->cookie = dmaengine_submit(desc); - if (pkt->cookie < 0) { + cookie = dmaengine_submit(desc); + if (cookie < 0) { dev_err(dev, "Failed to submit dma descriptor\n"); return; } @@ -1152,12 +1154,10 @@ static size_t usbhs_dma_calc_received_size(struct usbhs_pkt *pkt, struct dma_chan *chan, int dtln) { struct usbhs_pipe *pipe = pkt->pipe; - struct dma_tx_state state; size_t received_size; int maxp = usbhs_pipe_get_maxpacket(pipe);

- dmaengine_tx_status(chan, pkt->cookie, &state); - received_size = pkt->length - state.residue; + received_size = pkt->length - pkt->dma_result->residue;

if (dtln) { received_size -= USBHS_USB_DMAC_XFER_SIZE; @@ -1363,13 +1363,16 @@ static int usbhsf_irq_ready(struct usbhs_priv *priv, return 0; }

-static void usbhsf_dma_complete(void *arg) +static void usbhsf_dma_complete(void *arg, + const struct dmaengine_result *result) { - struct usbhs_pipe *pipe = arg; + struct usbhs_pkt *pkt = arg; + struct usbhs_pipe *pipe = pkt->pipe; struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe); struct device *dev = usbhs_priv_to_dev(priv); int ret;

+ pkt->dma_result = result; ret = usbhsf_pkt_handler(pipe, USBHSF_PKT_DMA_DONE); if (ret < 0) dev_err(dev, "dma_complete run_error %d : %d\n", diff --git a/drivers/usb/renesas_usbhs/fifo.h b/drivers/usb/renesas_usbhs/fifo.h index c3d3cc35cee0f..4a7dc23ce3d35 100644 --- a/drivers/usb/renesas_usbhs/fifo.h +++ b/drivers/usb/renesas_usbhs/fifo.h @@ -50,7 +50,7 @@ struct usbhs_pkt { struct usbhs_pkt *pkt); struct work_struct work; dma_addr_t dma; - dma_cookie_t cookie; + const struct dmaengine_result *dma_result; void *buf; int length; int trans;

From: Sagi Grimberg sagi@grimberg.me

[ Upstream commit 3b4b19721ec652ad2c4fe51dfbe5124212b5f581 ]

Revert fab7772bfbcf ("nvme-multipath: revalidate nvme_ns_head gendisk in nvme_validate_ns")

When adding a new namespace to the head disk (via nvme_mpath_set_live) we will see partition scan which triggers I/O on the mpath device node. This process will usually be triggered from the scan_work which holds the scan_lock. If I/O blocks (if we got ana change currently have only available paths but none are accessible) this can deadlock on the head disk bd_mutex as both partition scan I/O takes it, and head disk revalidation takes it to check for resize (also triggered from scan_work on a different path). See trace [1].

The mpath disk revalidation was originally added to detect online disk size change, but this is no longer needed since commit cb224c3af4df ("nvme: Convert to use set_capacity_revalidate_and_notify") which already updates resize info without unnecessarily revalidating the disk (the mpath disk doesn't even implement .revalidate_disk fop).

[1]: -- kernel: INFO: task kworker/u65:9:494 blocked for more than 241 seconds. kernel: Tainted: G OE 5.3.5-050305-generic #201910071830 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kernel: kworker/u65:9 D 0 494 2 0x80004000 kernel: Workqueue: nvme-wq nvme_scan_work [nvme_core] kernel: Call Trace: kernel: __schedule+0x2b9/0x6c0 kernel: schedule+0x42/0xb0 kernel: schedule_preempt_disabled+0xe/0x10 kernel: __mutex_lock.isra.0+0x182/0x4f0 kernel: __mutex_lock_slowpath+0x13/0x20 kernel: mutex_lock+0x2e/0x40 kernel: revalidate_disk+0x63/0xa0 kernel: __nvme_revalidate_disk+0xfe/0x110 [nvme_core] kernel: nvme_revalidate_disk+0xa4/0x160 [nvme_core] kernel: ? evict+0x14c/0x1b0 kernel: revalidate_disk+0x2b/0xa0 kernel: nvme_validate_ns+0x49/0x940 [nvme_core] kernel: ? blk_mq_free_request+0xd2/0x100 kernel: ? __nvme_submit_sync_cmd+0xbe/0x1e0 [nvme_core] kernel: nvme_scan_work+0x24f/0x380 [nvme_core] kernel: process_one_work+0x1db/0x380 kernel: worker_thread+0x249/0x400 kernel: kthread+0x104/0x140 kernel: ? process_one_work+0x380/0x380 kernel: ? kthread_park+0x80/0x80 kernel: ret_from_fork+0x1f/0x40 ... kernel: INFO: task kworker/u65:1:2630 blocked for more than 241 seconds. kernel: Tainted: G OE 5.3.5-050305-generic #201910071830 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kernel: kworker/u65:1 D 0 2630 2 0x80004000 kernel: Workqueue: nvme-wq nvme_scan_work [nvme_core] kernel: Call Trace: kernel: __schedule+0x2b9/0x6c0 kernel: schedule+0x42/0xb0 kernel: io_schedule+0x16/0x40 kernel: do_read_cache_page+0x438/0x830 kernel: ? __switch_to_asm+0x34/0x70 kernel: ? file_fdatawait_range+0x30/0x30 kernel: read_cache_page+0x12/0x20 kernel: read_dev_sector+0x27/0xc0 kernel: read_lba+0xc1/0x220 kernel: ? kmem_cache_alloc_trace+0x19c/0x230 kernel: efi_partition+0x1e6/0x708 kernel: ? vsnprintf+0x39e/0x4e0 kernel: ? snprintf+0x49/0x60 kernel: check_partition+0x154/0x244 kernel: rescan_partitions+0xae/0x280 kernel: __blkdev_get+0x40f/0x560 kernel: blkdev_get+0x3d/0x140 kernel: __device_add_disk+0x388/0x480 kernel: device_add_disk+0x13/0x20 kernel: nvme_mpath_set_live+0x119/0x140 [nvme_core] kernel: nvme_update_ns_ana_state+0x5c/0x60 [nvme_core] kernel: nvme_set_ns_ana_state+0x1e/0x30 [nvme_core] kernel: nvme_parse_ana_log+0xa1/0x180 [nvme_core] kernel: ? nvme_update_ns_ana_state+0x60/0x60 [nvme_core] kernel: nvme_mpath_add_disk+0x47/0x90 [nvme_core] kernel: nvme_validate_ns+0x396/0x940 [nvme_core] kernel: ? blk_mq_free_request+0xd2/0x100 kernel: nvme_scan_work+0x24f/0x380 [nvme_core] kernel: process_one_work+0x1db/0x380 kernel: worker_thread+0x249/0x400 kernel: kthread+0x104/0x140 kernel: ? process_one_work+0x380/0x380 kernel: ? kthread_park+0x80/0x80 kernel: ret_from_fork+0x1f/0x40 --

Fixes: fab7772bfbcf ("nvme-multipath: revalidate nvme_ns_head gendisk in nvme_validate_ns") Signed-off-by: Anton Eidelman anton@lightbitslabs.com Signed-off-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/core.c | 1 - 1 file changed, 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 887139f8fa53b..85ce6c682849e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1910,7 +1910,6 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) if (ns->head->disk) { nvme_update_disk_info(ns->head->disk, ns, id); blk_queue_stack_limits(ns->head->disk->queue, ns->queue); - revalidate_disk(ns->head->disk); } #endif }

From: Sagi Grimberg sagi@grimberg.me

[ Upstream commit e164471dcf19308d154adb69e7760d8ba426a77f ]

Right now ns->head->lock is protecting namespace mutation which is wrong and unneeded. Move it to only protect against head mutations. While we're at it, remove unnecessary ns->head reference as we already have head pointer.

The problem with this is that the head->lock spans mpath disk node I/O that may block under some conditions (if for example the controller is disconnecting or the path became inaccessible), The locking scheme does not allow any other path to enable itself, preventing blocked I/O to complete and forward-progress from there.

This is a preparation patch for the fix in a subsequent patch where the disk I/O will also be done outside the head->lock.

Fixes: 0d0b660f214d ("nvme: add ANA support") Signed-off-by: Anton Eidelman anton@lightbitslabs.com Signed-off-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/multipath.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index fece4654fa3e7..f4287d8550a9f 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -410,11 +410,10 @@ static void nvme_mpath_set_live(struct nvme_ns *ns) { struct nvme_ns_head *head = ns->head;

- lockdep_assert_held(&ns->head->lock); - if (!head->disk) return;

+ mutex_lock(&head->lock); if (!(head->disk->flags & GENHD_FL_UP)) device_add_disk(&head->subsys->dev, head->disk, nvme_ns_id_attr_groups); @@ -427,9 +426,10 @@ static void nvme_mpath_set_live(struct nvme_ns *ns) __nvme_find_path(head, node); srcu_read_unlock(&head->srcu, srcu_idx); } + mutex_unlock(&head->lock);

- synchronize_srcu(&ns->head->srcu); - kblockd_schedule_work(&ns->head->requeue_work); + synchronize_srcu(&head->srcu); + kblockd_schedule_work(&head->requeue_work); }

static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data, @@ -484,14 +484,12 @@ static inline bool nvme_state_is_live(enum nvme_ana_state state) static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc, struct nvme_ns *ns) { - mutex_lock(&ns->head->lock); ns->ana_grpid = le32_to_cpu(desc->grpid); ns->ana_state = desc->state; clear_bit(NVME_NS_ANA_PENDING, &ns->flags);

if (nvme_state_is_live(ns->ana_state)) nvme_mpath_set_live(ns); - mutex_unlock(&ns->head->lock); }

static int nvme_update_ana_state(struct nvme_ctrl *ctrl, @@ -670,10 +668,8 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id) nvme_update_ns_ana_state(&desc, ns); } } else { - mutex_lock(&ns->head->lock); ns->ana_state = NVME_ANA_OPTIMIZED; nvme_mpath_set_live(ns); - mutex_unlock(&ns->head->lock); }

if (bdi_cap_stable_pages_required(ns->queue->backing_dev_info)) {

From: Colin Ian King colin.king@canonical.com

[ Upstream commit a51243860893615b457b149da1ef5df0a4f1ffc2 ]

The error DBG_STATUS_NO_MATCHING_FRAMING_MODE was added to the enum enum dbg_status however there is a missing corresponding entry for this in the array s_status_str. This causes an out-of-bounds read when indexing into the last entry of s_status_str. Fix this by adding in the missing entry.

Addresses-Coverity: ("Out-of-bounds read"). Fixes: 2d22bc8354b1 ("qed: FW 8.42.2.0 debug features") Signed-off-by: Colin Ian King colin.king@canonical.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qed/qed_debug.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index f4eebaabb6d0d..3e56b6056b477 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -5568,7 +5568,8 @@ static const char * const s_status_str[] = {

/* DBG_STATUS_INVALID_FILTER_TRIGGER_DWORDS */ "The filter/trigger constraint dword offsets are not enabled for recording", - + /* DBG_STATUS_NO_MATCHING_FRAMING_MODE */ + "No matching framing mode",

/* DBG_STATUS_VFC_READ_ERROR */ "Error reading from VFC",

From: Doug Berger opendmb@gmail.com

[ Upstream commit 20d1f2d1b024f6be199a3bedf1578a1d21592bc5 ]

When commit 474ea9cafc45 ("net: bcmgenet: correctly pad short packets") added the call to skb_padto() it should have been located before the nr_frags parameter was read since that value could be changed when padding packets with lengths between 55 and 59 bytes (inclusive).

The use of a stale nr_frags value can cause corruption of the pad data when tx-scatter-gather is enabled. This corruption of the pad can cause invalid checksum computation when hardware offload of tx-checksum is also enabled.

Since the original reason for the padding was corrected by commit 7dd399130efb ("net: bcmgenet: fix skb_len in bcmgenet_xmit_single()") we can remove the software padding all together and make use of hardware padding of short frames as long as the hardware also always appends the FCS value to the frame.

Fixes: 474ea9cafc45 ("net: bcmgenet: correctly pad short packets") Signed-off-by: Doug Berger opendmb@gmail.com Acked-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 38bdfd4b46f0f..dde1c23c8e399 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1520,11 +1520,6 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) goto out; }

- if (skb_padto(skb, ETH_ZLEN)) { - ret = NETDEV_TX_OK; - goto out; - } - /* Retain how many bytes will be sent on the wire, without TSB inserted * by transmit checksum offload */ @@ -1571,6 +1566,9 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) len_stat = (size << DMA_BUFLENGTH_SHIFT) | (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT);

+ /* Note: if we ever change from DMA_TX_APPEND_CRC below we + * will need to restore software padding of "runt" packets + */ if (!i) { len_stat |= DMA_TX_APPEND_CRC | DMA_SOP; if (skb->ip_summed == CHECKSUM_PARTIAL)

From: Vincent Chen vincent.chen@sifive.com

[ Upstream commit d0a5fdf4cc83dabcdea668f971b8a2e916437711 ]

The (struct __prci_data).hw_clks.hws is an array with dynamic elements. Using struct_size(pd, hw_clks.hws, ARRAY_SIZE(__prci_init_clocks)) instead of sizeof(*pd) to get the correct memory size of struct __prci_data for sifive/fu540-prci. After applying this modifications, the kernel runs smoothly with CONFIG_SLAB_FREELIST_RANDOM enabled on the HiFive unleashed board.

Fixes: 30b8e27e3b58 ("clk: sifive: add a driver for the SiFive FU540 PRCI IP block") Signed-off-by: Vincent Chen vincent.chen@sifive.com Signed-off-by: Palmer Dabbelt palmerdabbelt@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/clk/sifive/fu540-prci.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/sifive/fu540-prci.c b/drivers/clk/sifive/fu540-prci.c index 6282ee2f361cd..a8901f90a61ac 100644 --- a/drivers/clk/sifive/fu540-prci.c +++ b/drivers/clk/sifive/fu540-prci.c @@ -586,7 +586,10 @@ static int sifive_fu540_prci_probe(struct platform_device *pdev) struct __prci_data *pd; int r;

- pd = devm_kzalloc(dev, sizeof(*pd), GFP_KERNEL); + pd = devm_kzalloc(dev, + struct_size(pd, hw_clks.hws, + ARRAY_SIZE(__prci_init_clocks)), + GFP_KERNEL); if (!pd) return -ENOMEM;