From: Feng Sun loyou85@gmail.com

[ Upstream commit 2c1644cf6d46a8267d79ed95cb9b563839346562 ]

After commit baeababb5b85d5c4e6c917efe2a1504179438d3b ("tun: return NET_XMIT_DROP for dropped packets"), when tun_net_xmit drop packets, it will free skb and return NET_XMIT_DROP, netpoll_send_skb_on_dev will run into following use after free cases: 1. retry netpoll_start_xmit with freed skb; 2. queue freed skb in npinfo->txq. queue_process will also run into use after free case.

hit netpoll_send_skb_on_dev first case with following kernel log:

[ 117.864773] kernel BUG at mm/slub.c:306! [ 117.864773] invalid opcode: 0000 [#1] SMP PTI [ 117.864774] CPU: 3 PID: 2627 Comm: loop_printmsg Kdump: loaded Tainted: P OE 5.3.0-050300rc5-generic #201908182231 [ 117.864775] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 117.864775] RIP: 0010:kmem_cache_free+0x28d/0x2b0 [ 117.864781] Call Trace: [ 117.864781] ? tun_net_xmit+0x21c/0x460 [ 117.864781] kfree_skbmem+0x4e/0x60 [ 117.864782] kfree_skb+0x3a/0xa0 [ 117.864782] tun_net_xmit+0x21c/0x460 [ 117.864782] netpoll_start_xmit+0x11d/0x1b0 [ 117.864788] netpoll_send_skb_on_dev+0x1b8/0x200 [ 117.864789] __br_forward+0x1b9/0x1e0 [bridge] [ 117.864789] ? skb_clone+0x53/0xd0 [ 117.864790] ? __skb_clone+0x2e/0x120 [ 117.864790] deliver_clone+0x37/0x50 [bridge] [ 117.864790] maybe_deliver+0x89/0xc0 [bridge] [ 117.864791] br_flood+0x6c/0x130 [bridge] [ 117.864791] br_dev_xmit+0x315/0x3c0 [bridge] [ 117.864792] netpoll_start_xmit+0x11d/0x1b0 [ 117.864792] netpoll_send_skb_on_dev+0x1b8/0x200 [ 117.864792] netpoll_send_udp+0x2c6/0x3e8 [ 117.864793] write_msg+0xd9/0xf0 [netconsole] [ 117.864793] console_unlock+0x386/0x4e0 [ 117.864793] vprintk_emit+0x17e/0x280 [ 117.864794] vprintk_default+0x29/0x50 [ 117.864794] vprintk_func+0x4c/0xbc [ 117.864794] printk+0x58/0x6f [ 117.864795] loop_fun+0x24/0x41 [printmsg_loop] [ 117.864795] kthread+0x104/0x140 [ 117.864795] ? 0xffffffffc05b1000 [ 117.864796] ? kthread_park+0x80/0x80 [ 117.864796] ret_from_fork+0x35/0x40

Signed-off-by: Feng Sun loyou85@gmail.com Signed-off-by: Xiaojun Zhao xiaojunzhao141@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/netpoll.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -122,7 +122,7 @@ static void queue_process(struct work_st txq = netdev_get_tx_queue(dev, q_index); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (netif_xmit_frozen_or_stopped(txq) || - netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) { + !dev_xmit_complete(netpoll_start_xmit(skb, dev, txq))) { skb_queue_head(&npinfo->txq, skb); HARD_TX_UNLOCK(dev, txq); local_irq_restore(flags); @@ -335,7 +335,7 @@ void netpoll_send_skb_on_dev(struct netp

HARD_TX_UNLOCK(dev, txq);

- if (status == NETDEV_TX_OK) + if (dev_xmit_complete(status)) break;

} @@ -352,7 +352,7 @@ void netpoll_send_skb_on_dev(struct netp

}

- if (status != NETDEV_TX_OK) { + if (!dev_xmit_complete(status)) { skb_queue_tail(&npinfo->txq, skb); schedule_delayed_work(&npinfo->tx_work,0); }

From: Cong Wang xiyou.wangcong@gmail.com

[ Upstream commit 981471bd3abf4d572097645d765391533aac327d ]

The net pointer in struct xt_tgdtor_param is not explicitly initialized therefore is still NULL when dereferencing it. So we have to find a way to pass the correct net pointer to ipt_destroy_target().

The best way I find is just saving the net pointer inside the per netns struct tcf_idrinfo, which could make this patch smaller.

Fixes: 0c66dc1ea3f0 ("netfilter: conntrack: register hooks in netns when needed by ruleset") Reported-and-tested-by: itugrok@yahoo.com Cc: Jamal Hadi Salim jhs@mojatatu.com Cc: Jiri Pirko jiri@resnulli.us Signed-off-by: Cong Wang xiyou.wangcong@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/act_api.h | 4 +++- net/sched/act_bpf.c | 2 +- net/sched/act_connmark.c | 2 +- net/sched/act_csum.c | 2 +- net/sched/act_gact.c | 2 +- net/sched/act_ife.c | 2 +- net/sched/act_ipt.c | 11 ++++++----- net/sched/act_mirred.c | 2 +- net/sched/act_nat.c | 2 +- net/sched/act_pedit.c | 2 +- net/sched/act_police.c | 2 +- net/sched/act_sample.c | 2 +- net/sched/act_simple.c | 2 +- net/sched/act_skbedit.c | 2 +- net/sched/act_skbmod.c | 2 +- net/sched/act_tunnel_key.c | 2 +- net/sched/act_vlan.c | 2 +- 17 files changed, 24 insertions(+), 21 deletions(-)

--- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -15,6 +15,7 @@ struct tcf_idrinfo { spinlock_t lock; struct idr action_idr; + struct net *net; };

struct tc_action_ops; @@ -107,7 +108,7 @@ struct tc_action_net { };

static inline -int tc_action_net_init(struct tc_action_net *tn, +int tc_action_net_init(struct net *net, struct tc_action_net *tn, const struct tc_action_ops *ops) { int err = 0; @@ -116,6 +117,7 @@ int tc_action_net_init(struct tc_action_ if (!tn->idrinfo) return -ENOMEM; tn->ops = ops; + tn->idrinfo->net = net; spin_lock_init(&tn->idrinfo->lock); idr_init(&tn->idrinfo->action_idr); return err; --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -413,7 +413,7 @@ static __net_init int bpf_init_net(struc { struct tc_action_net *tn = net_generic(net, bpf_net_id);

- return tc_action_net_init(tn, &act_bpf_ops); + return tc_action_net_init(net, tn, &act_bpf_ops); }

static void __net_exit bpf_exit_net(struct list_head *net_list) --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -215,7 +215,7 @@ static __net_init int connmark_init_net( { struct tc_action_net *tn = net_generic(net, connmark_net_id);

- return tc_action_net_init(tn, &act_connmark_ops); + return tc_action_net_init(net, tn, &act_connmark_ops); }

static void __net_exit connmark_exit_net(struct list_head *net_list) --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -678,7 +678,7 @@ static __net_init int csum_init_net(stru { struct tc_action_net *tn = net_generic(net, csum_net_id);

- return tc_action_net_init(tn, &act_csum_ops); + return tc_action_net_init(net, tn, &act_csum_ops); }

static void __net_exit csum_exit_net(struct list_head *net_list) --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -263,7 +263,7 @@ static __net_init int gact_init_net(stru { struct tc_action_net *tn = net_generic(net, gact_net_id);

- return tc_action_net_init(tn, &act_gact_ops); + return tc_action_net_init(net, tn, &act_gact_ops); }

static void __net_exit gact_exit_net(struct list_head *net_list) --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -887,7 +887,7 @@ static __net_init int ife_init_net(struc { struct tc_action_net *tn = net_generic(net, ife_net_id);

- return tc_action_net_init(tn, &act_ife_ops); + return tc_action_net_init(net, tn, &act_ife_ops); }

static void __net_exit ife_exit_net(struct list_head *net_list) --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -65,12 +65,13 @@ static int ipt_init_target(struct net *n return 0; }

-static void ipt_destroy_target(struct xt_entry_target *t) +static void ipt_destroy_target(struct xt_entry_target *t, struct net *net) { struct xt_tgdtor_param par = { .target = t->u.kernel.target, .targinfo = t->data, .family = NFPROTO_IPV4, + .net = net, }; if (par.target->destroy != NULL) par.target->destroy(&par); @@ -82,7 +83,7 @@ static void tcf_ipt_release(struct tc_ac struct tcf_ipt *ipt = to_ipt(a);

if (ipt->tcfi_t) { - ipt_destroy_target(ipt->tcfi_t); + ipt_destroy_target(ipt->tcfi_t, a->idrinfo->net); kfree(ipt->tcfi_t); } kfree(ipt->tcfi_tname); @@ -182,7 +183,7 @@ static int __tcf_ipt_init(struct net *ne

spin_lock_bh(&ipt->tcf_lock); if (ret != ACT_P_CREATED) { - ipt_destroy_target(ipt->tcfi_t); + ipt_destroy_target(ipt->tcfi_t, net); kfree(ipt->tcfi_tname); kfree(ipt->tcfi_t); } @@ -353,7 +354,7 @@ static __net_init int ipt_init_net(struc { struct tc_action_net *tn = net_generic(net, ipt_net_id);

- return tc_action_net_init(tn, &act_ipt_ops); + return tc_action_net_init(net, tn, &act_ipt_ops); }

static void __net_exit ipt_exit_net(struct list_head *net_list) @@ -403,7 +404,7 @@ static __net_init int xt_init_net(struct { struct tc_action_net *tn = net_generic(net, xt_net_id);

- return tc_action_net_init(tn, &act_xt_ops); + return tc_action_net_init(net, tn, &act_xt_ops); }

static void __net_exit xt_exit_net(struct list_head *net_list) --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -419,7 +419,7 @@ static __net_init int mirred_init_net(st { struct tc_action_net *tn = net_generic(net, mirred_net_id);

- return tc_action_net_init(tn, &act_mirred_ops); + return tc_action_net_init(net, tn, &act_mirred_ops); }

static void __net_exit mirred_exit_net(struct list_head *net_list) --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -317,7 +317,7 @@ static __net_init int nat_init_net(struc { struct tc_action_net *tn = net_generic(net, nat_net_id);

- return tc_action_net_init(tn, &act_nat_ops); + return tc_action_net_init(net, tn, &act_nat_ops); }

static void __net_exit nat_exit_net(struct list_head *net_list) --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -488,7 +488,7 @@ static __net_init int pedit_init_net(str { struct tc_action_net *tn = net_generic(net, pedit_net_id);

- return tc_action_net_init(tn, &act_pedit_ops); + return tc_action_net_init(net, tn, &act_pedit_ops); }

static void __net_exit pedit_exit_net(struct list_head *net_list) --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -342,7 +342,7 @@ static __net_init int police_init_net(st { struct tc_action_net *tn = net_generic(net, police_net_id);

- return tc_action_net_init(tn, &act_police_ops); + return tc_action_net_init(net, tn, &act_police_ops); }

static void __net_exit police_exit_net(struct list_head *net_list) --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -258,7 +258,7 @@ static __net_init int sample_init_net(st { struct tc_action_net *tn = net_generic(net, sample_net_id);

- return tc_action_net_init(tn, &act_sample_ops); + return tc_action_net_init(net, tn, &act_sample_ops); }

static void __net_exit sample_exit_net(struct list_head *net_list) --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -215,7 +215,7 @@ static __net_init int simp_init_net(stru { struct tc_action_net *tn = net_generic(net, simp_net_id);

- return tc_action_net_init(tn, &act_simp_ops); + return tc_action_net_init(net, tn, &act_simp_ops); }

static void __net_exit simp_exit_net(struct list_head *net_list) --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -316,7 +316,7 @@ static __net_init int skbedit_init_net(s { struct tc_action_net *tn = net_generic(net, skbedit_net_id);

- return tc_action_net_init(tn, &act_skbedit_ops); + return tc_action_net_init(net, tn, &act_skbedit_ops); }

static void __net_exit skbedit_exit_net(struct list_head *net_list) --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -277,7 +277,7 @@ static __net_init int skbmod_init_net(st { struct tc_action_net *tn = net_generic(net, skbmod_net_id);

- return tc_action_net_init(tn, &act_skbmod_ops); + return tc_action_net_init(net, tn, &act_skbmod_ops); }

static void __net_exit skbmod_exit_net(struct list_head *net_list) --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -579,7 +579,7 @@ static __net_init int tunnel_key_init_ne { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);

- return tc_action_net_init(tn, &act_tunnel_key_ops); + return tc_action_net_init(net, tn, &act_tunnel_key_ops); }

static void __net_exit tunnel_key_exit_net(struct list_head *net_list) --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -324,7 +324,7 @@ static __net_init int vlan_init_net(stru { struct tc_action_net *tn = net_generic(net, vlan_net_id);

- return tc_action_net_init(tn, &act_vlan_ops); + return tc_action_net_init(net, tn, &act_vlan_ops); }

static void __net_exit vlan_exit_net(struct list_head *net_list)

From: Willem de Bruijn willemb@google.com

[ Upstream commit 888a5c53c0d8be6e98bc85b677f179f77a647873 ]

TCP associates tx timestamp requests with a byte in the bytestream. If merging skbs in tcp_mtu_probe, migrate the tstamp request.

Similar to MSG_EOR, do not allow moving a timestamp from any segment in the probe but the last. This to avoid merging multiple timestamps.

Tested with the packetdrill script at https://github.com/wdebruij/packetdrill/commits/mtu_probe-1

Link: http://patchwork.ozlabs.org/patch/1143278/#2232897 Fixes: 4ed2d765dfac ("net-timestamp: TCP timestamping") Signed-off-by: Willem de Bruijn willemb@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_output.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2046,7 +2046,7 @@ static bool tcp_can_coalesce_send_queue_ if (len <= skb->len) break;

- if (unlikely(TCP_SKB_CB(skb)->eor)) + if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb)) return false;

len -= skb->len; @@ -2162,6 +2162,7 @@ static int tcp_mtu_probe(struct sock *sk * we need to propagate it to the new skb. */ TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor; + tcp_skb_collapse_tstamp(nskb, skb); tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); } else {

From: Ka-Cheong Poon ka-cheong.poon@oracle.com

[ Upstream commit 7d0a06586b2686ba80c4a2da5f91cb10ffbea736 ]

The rds6_inc_info_copy() function has a couple struct members which are leaking stack information. The ->tos field should hold actual information and the ->flags field needs to be zeroed out.

Fixes: 3eb450367d08 ("rds: add type of service(tos) infrastructure") Fixes: b7ff8b1036f0 ("rds: Extend RDS API for IPv6 support") Reported-by: 黄ID蝴蝶 butterflyhuangxx@gmail.com Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: Ka-Cheong Poon ka-cheong.poon@oracle.com Acked-by: Santosh Shilimkar santosh.shilimkar@oracle.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/rds/recv.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved. + * Copyright (c) 2006, 2019 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -803,6 +803,7 @@ void rds6_inc_info_copy(struct rds_incom

minfo6.seq = be64_to_cpu(inc->i_hdr.h_sequence); minfo6.len = be32_to_cpu(inc->i_hdr.h_len); + minfo6.tos = 0;

if (flip) { minfo6.laddr = *daddr; @@ -816,6 +817,8 @@ void rds6_inc_info_copy(struct rds_incom minfo6.fport = inc->i_hdr.h_dport; }

+ minfo6.flags = 0; + rds_info_copy(iter, &minfo6, sizeof(minfo6)); } #endif

[ Upstream commit 7188a6f0eee3f1fae5d826cfc6d569657ff950ec ]

Sharing more code between polling and interrupt-driven mode.

Signed-off-by: Martin Sperl kernel@martin.sperl.org Acked-by: Stefan Wahren stefan.wahren@i2se.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-bcm2835aux.c | 51 +++++++++++++----------------------- 1 file changed, 18 insertions(+), 33 deletions(-)

diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c index 3094d818cf06d..79306e654f735 100644 --- a/drivers/spi/spi-bcm2835aux.c +++ b/drivers/spi/spi-bcm2835aux.c @@ -178,23 +178,13 @@ static void bcm2835aux_spi_reset_hw(struct bcm2835aux_spi *bs) BCM2835_AUX_SPI_CNTL0_CLEARFIFO); }

-static irqreturn_t bcm2835aux_spi_interrupt(int irq, void *dev_id) +static void bcm2835aux_spi_transfer_helper(struct bcm2835aux_spi *bs) { - struct spi_master *master = dev_id; - struct bcm2835aux_spi *bs = spi_master_get_devdata(master); - irqreturn_t ret = IRQ_NONE; - - /* IRQ may be shared, so return if our interrupts are disabled */ - if (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_CNTL1) & - (BCM2835_AUX_SPI_CNTL1_TXEMPTY | BCM2835_AUX_SPI_CNTL1_IDLE))) - return ret; - /* check if we have data to read */ while (bs->rx_len && (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT) & BCM2835_AUX_SPI_STAT_RX_EMPTY))) { bcm2835aux_rd_fifo(bs); - ret = IRQ_HANDLED; }

/* check if we have data to write */ @@ -203,7 +193,6 @@ static irqreturn_t bcm2835aux_spi_interrupt(int irq, void *dev_id) (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT) & BCM2835_AUX_SPI_STAT_TX_FULL))) { bcm2835aux_wr_fifo(bs); - ret = IRQ_HANDLED; }

/* and check if we have reached "done" */ @@ -211,8 +200,21 @@ static irqreturn_t bcm2835aux_spi_interrupt(int irq, void *dev_id) (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT) & BCM2835_AUX_SPI_STAT_BUSY))) { bcm2835aux_rd_fifo(bs); - ret = IRQ_HANDLED; } +} + +static irqreturn_t bcm2835aux_spi_interrupt(int irq, void *dev_id) +{ + struct spi_master *master = dev_id; + struct bcm2835aux_spi *bs = spi_master_get_devdata(master); + + /* IRQ may be shared, so return if our interrupts are disabled */ + if (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_CNTL1) & + (BCM2835_AUX_SPI_CNTL1_TXEMPTY | BCM2835_AUX_SPI_CNTL1_IDLE))) + return IRQ_NONE; + + /* do common fifo handling */ + bcm2835aux_spi_transfer_helper(bs);

if (!bs->tx_len) { /* disable tx fifo empty interrupt */ @@ -226,8 +228,7 @@ static irqreturn_t bcm2835aux_spi_interrupt(int irq, void *dev_id) complete(&master->xfer_completion); }

- /* and return */ - return ret; + return IRQ_HANDLED; }

static int __bcm2835aux_spi_transfer_one_irq(struct spi_master *master, @@ -273,7 +274,6 @@ static int bcm2835aux_spi_transfer_one_poll(struct spi_master *master, { struct bcm2835aux_spi *bs = spi_master_get_devdata(master); unsigned long timeout; - u32 stat;

/* configure spi */ bcm2835aux_wr(bs, BCM2835_AUX_SPI_CNTL1, bs->cntl[1]); @@ -284,24 +284,9 @@ static int bcm2835aux_spi_transfer_one_poll(struct spi_master *master,

/* loop until finished the transfer */ while (bs->rx_len) { - /* read status */ - stat = bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT); - - /* fill in tx fifo with remaining data */ - if ((bs->tx_len) && (!(stat & BCM2835_AUX_SPI_STAT_TX_FULL))) { - bcm2835aux_wr_fifo(bs); - continue; - }

- /* read data from fifo for both cases */ - if (!(stat & BCM2835_AUX_SPI_STAT_RX_EMPTY)) { - bcm2835aux_rd_fifo(bs); - continue; - } - if (!(stat & BCM2835_AUX_SPI_STAT_BUSY)) { - bcm2835aux_rd_fifo(bs); - continue; - } + /* do common fifo handling */ + bcm2835aux_spi_transfer_helper(bs);

/* there is still data pending to read check the timeout */ if (bs->rx_len && time_after(jiffies, timeout)) {

[ Upstream commit 73b114ee7db1750c0b535199fae383b109bd61d0 ]

On long running tests with a mcp2517fd can controller it showed that on rare occations the data read shows corruptions for longer spi transfers.

Example of a 22 byte transfer:

expected (as captured on logic analyzer): FF FF 78 00 00 00 08 06 00 00 91 20 77 56 84 85 86 87 88 89 8a 8b

read by the driver: FF FF 78 00 00 00 08 06 00 00 91 20 77 56 84 88 89 8a 00 00 8b 9b

To fix this use BCM2835_AUX_SPI_STAT_RX_LVL to determine when we may read data from the fifo reliably without any corruption.

Surprisingly the only values ever empirically read in BCM2835_AUX_SPI_STAT_RX_LVL are 0x00, 0x10, 0x20 and 0x30. So whenever the mask is not 0 we can read from the fifo in a safe manner.

The patch has now been tested intensively and we are no longer able to reproduce the "RX" issue any longer.

Fixes: 1ea29b39f4c812ec ("spi: bcm2835aux: add bcm2835 auxiliary spi device...") Reported-by: Hubert Denkmair h.denkmair@intence.de Signed-off-by: Martin Sperl kernel@martin.sperl.org Acked-by: Stefan Wahren stefan.wahren@i2se.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-bcm2835aux.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c index b4217f9480014..12c1fa5b06c5b 100644 --- a/drivers/spi/spi-bcm2835aux.c +++ b/drivers/spi/spi-bcm2835aux.c @@ -180,12 +180,12 @@ static void bcm2835aux_spi_reset_hw(struct bcm2835aux_spi *bs)

static void bcm2835aux_spi_transfer_helper(struct bcm2835aux_spi *bs) { + u32 stat = bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT); + /* check if we have data to read */ - while (bs->rx_len && - (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT) & - BCM2835_AUX_SPI_STAT_RX_EMPTY))) { + for (; bs->rx_len && (stat & BCM2835_AUX_SPI_STAT_RX_LVL); + stat = bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT)) bcm2835aux_rd_fifo(bs); - }

/* check if we have data to write */ while (bs->tx_len &&

[ Upstream commit 6a0a8d10a3661a036b55af695542a714c429ab7c ]

If a rule that has already a bound anonymous set fails to be added, the preparation phase releases the rule and the bound set. However, the transaction object from the abort path still has a reference to the set object that is stale, leading to a use-after-free when checking for the set->bound field. Add a new field to the transaction that specifies if the set is bound, so the abort path can skip releasing it since the rule command owns it and it takes care of releasing it. After this update, the set->bound field is removed.

[ 24.649883] Unable to handle kernel paging request at virtual address 0000000000040434 [ 24.657858] Mem abort info: [ 24.660686] ESR = 0x96000004 [ 24.663769] Exception class = DABT (current EL), IL = 32 bits [ 24.669725] SET = 0, FnV = 0 [ 24.672804] EA = 0, S1PTW = 0 [ 24.675975] Data abort info: [ 24.678880] ISV = 0, ISS = 0x00000004 [ 24.682743] CM = 0, WnR = 0 [ 24.685723] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000428952000 [ 24.692207] [0000000000040434] pgd=0000000000000000 [ 24.697119] Internal error: Oops: 96000004 [#1] SMP [...] [ 24.889414] Call trace: [ 24.891870] __nf_tables_abort+0x3f0/0x7a0 [ 24.895984] nf_tables_abort+0x20/0x40 [ 24.899750] nfnetlink_rcv_batch+0x17c/0x588 [ 24.904037] nfnetlink_rcv+0x13c/0x190 [ 24.907803] netlink_unicast+0x18c/0x208 [ 24.911742] netlink_sendmsg+0x1b0/0x350 [ 24.915682] sock_sendmsg+0x4c/0x68 [ 24.919185] ___sys_sendmsg+0x288/0x2c8 [ 24.923037] __sys_sendmsg+0x7c/0xd0 [ 24.926628] __arm64_sys_sendmsg+0x2c/0x38 [ 24.930744] el0_svc_common.constprop.0+0x94/0x158 [ 24.935556] el0_svc_handler+0x34/0x90 [ 24.939322] el0_svc+0x8/0xc [ 24.942216] Code: 37280300 f9404023 91014262 aa1703e0 (f9401863) [ 24.948336] ---[ end trace cebbb9dcbed3b56f ]---

Fixes: f6ac85858976 ("netfilter: nf_tables: unbind set in rule from commit path") Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/netfilter/nf_tables.h | 9 +++++++-- net/netfilter/nf_tables_api.c | 15 ++++++++++----- 2 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index f2be5d041ba3a..7685cbda9f28b 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -418,8 +418,7 @@ struct nft_set { unsigned char *udata; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; - u16 flags:13, - bound:1, + u16 flags:14, genmask:2; u8 klen; u8 dlen; @@ -1337,12 +1336,15 @@ struct nft_trans_rule { struct nft_trans_set { struct nft_set *set; u32 set_id; + bool bound; };

#define nft_trans_set(trans) \ (((struct nft_trans_set *)trans->data)->set) #define nft_trans_set_id(trans) \ (((struct nft_trans_set *)trans->data)->set_id) +#define nft_trans_set_bound(trans) \ + (((struct nft_trans_set *)trans->data)->bound)

struct nft_trans_chain { bool update; @@ -1373,12 +1375,15 @@ struct nft_trans_table { struct nft_trans_elem { struct nft_set *set; struct nft_set_elem elem; + bool bound; };

#define nft_trans_elem_set(trans) \ (((struct nft_trans_elem *)trans->data)->set) #define nft_trans_elem(trans) \ (((struct nft_trans_elem *)trans->data)->elem) +#define nft_trans_elem_set_bound(trans) \ + (((struct nft_trans_elem *)trans->data)->bound)

struct nft_trans_obj { struct nft_object *obj; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 29ff59dd99ace..2145581d7b3dc 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -121,9 +121,14 @@ static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) return;

list_for_each_entry_reverse(trans, &net->nft.commit_list, list) { - if (trans->msg_type == NFT_MSG_NEWSET && - nft_trans_set(trans) == set) { - set->bound = true; + switch (trans->msg_type) { + case NFT_MSG_NEWSET: + if (nft_trans_set(trans) == set) + nft_trans_set_bound(trans) = true; + break; + case NFT_MSG_NEWSETELEM: + if (nft_trans_elem_set(trans) == set) + nft_trans_elem_set_bound(trans) = true; break; } } @@ -6656,7 +6661,7 @@ static int __nf_tables_abort(struct net *net) break; case NFT_MSG_NEWSET: trans->ctx.table->use--; - if (nft_trans_set(trans)->bound) { + if (nft_trans_set_bound(trans)) { nft_trans_destroy(trans); break; } @@ -6668,7 +6673,7 @@ static int __nf_tables_abort(struct net *net) nft_trans_destroy(trans); break; case NFT_MSG_NEWSETELEM: - if (nft_trans_elem_set(trans)->bound) { + if (nft_trans_elem_set_bound(trans)) { nft_trans_destroy(trans); break; }

[ Upstream commit 6d0d779dca73cd5acb649c54f81401f93098b298 ]

This fixes a warning of "suspicious rcu_dereference_check() usage" when nload runs.

Fixes: 776e726bfb34 ("netvsc: fix RCU warning in get_stats") Signed-off-by: Dexuan Cui decui@microsoft.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/hyperv/netvsc_drv.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index cc60ef9634db2..6f6c0dbd91fc8 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1248,12 +1248,15 @@ static void netvsc_get_stats64(struct net_device *net, struct rtnl_link_stats64 *t) { struct net_device_context *ndev_ctx = netdev_priv(net); - struct netvsc_device *nvdev = rcu_dereference_rtnl(ndev_ctx->nvdev); + struct netvsc_device *nvdev; struct netvsc_vf_pcpu_stats vf_tot; int i;

+ rcu_read_lock(); + + nvdev = rcu_dereference(ndev_ctx->nvdev); if (!nvdev) - return; + goto out;

netdev_stats_to_stats64(t, &net->stats);

@@ -1292,6 +1295,8 @@ static void netvsc_get_stats64(struct net_device *net, t->rx_packets += packets; t->multicast += multicast; } +out: + rcu_read_unlock(); }

static int netvsc_set_mac_addr(struct net_device *ndev, void *p)

[ Upstream commit 8059ba0bd0e4694e51c2ee6438a77b325f06c0d5 ]

On WCN3990 downloading the NVM sometimes fails with a "TLV response size mismatch" error:

[ 174.949955] Bluetooth: btqca.c:qca_download_firmware() hci0: QCA Downloading qca/crnv21.bin [ 174.958718] Bluetooth: btqca.c:qca_tlv_send_segment() hci0: QCA TLV response size mismatch

It seems the controller needs a short time after downloading the firmware before it is ready for the NVM. A delay as short as 1 ms seems sufficient, make it 10 ms just in case. No event is received during the delay, hence we don't just silently drop an extra event.

Signed-off-by: Matthias Kaehlcke mka@chromium.org Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/bluetooth/btqca.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index ec9e03a6b7786..9e70f7c7e5659 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -363,6 +363,9 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, return err; }

+ /* Give the controller some time to get ready to receive the NVM */ + msleep(10); + /* Download NVM configuration */ config.type = TLV_TYPE_NVM; if (soc_type == QCA_WCN3990)

[ Upstream commit 68e03b85474a51ec1921b4d13204782594ef7223 ]

when do randbuilding, I got this error:

In file included from drivers/hwmon/pmbus/ucd9000.c:19:0: ./include/linux/gpio/driver.h:576:1: error: redefinition of gpiochip_add_pin_range gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name, ^~~~~~~~~~~~~~~~~~~~~~ In file included from drivers/hwmon/pmbus/ucd9000.c:18:0: ./include/linux/gpio.h:245:1: note: previous definition of gpiochip_add_pin_range was here gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name, ^~~~~~~~~~~~~~~~~~~~~~

Reported-by: Hulk Robot hulkci@huawei.com Fixes: 964cb341882f ("gpio: move pincontrol calls to <linux/gpio/driver.h>") Signed-off-by: YueHaibing yuehaibing@huawei.com Link: https://lore.kernel.org/r/20190731123814.46624-1-yuehaibing@huawei.com Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/gpio.h | 24 ------------------------ 1 file changed, 24 deletions(-)

diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 39745b8bdd65d..b3115d1a7d494 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -240,30 +240,6 @@ static inline int irq_to_gpio(unsigned irq) return -EINVAL; }

-static inline int -gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name, - unsigned int gpio_offset, unsigned int pin_offset, - unsigned int npins) -{ - WARN_ON(1); - return -EINVAL; -} - -static inline int -gpiochip_add_pingroup_range(struct gpio_chip *chip, - struct pinctrl_dev *pctldev, - unsigned int gpio_offset, const char *pin_group) -{ - WARN_ON(1); - return -EINVAL; -} - -static inline void -gpiochip_remove_pin_ranges(struct gpio_chip *chip) -{ - WARN_ON(1); -} - static inline int devm_gpio_request(struct device *dev, unsigned gpio, const char *label) {

[ Upstream commit dfe42be15fde16232340b8b2a57c359f51cc10d9 ]

TCP rst and fin packets do not qualify to place a flow into the flowtable. Most likely there will be no more packets after connection closure. Without this patch, this flow entry expires and connection tracking picks up the entry in ESTABLISHED state using the fixup timeout, which makes this look inconsistent to the user for a connection that is actually already closed.

Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nft_flow_offload.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 6e0c26025ab13..69decbe2c9884 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -71,11 +71,11 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, { struct nft_flow_offload *priv = nft_expr_priv(expr); struct nf_flowtable *flowtable = &priv->flowtable->data; + struct tcphdr _tcph, *tcph = NULL; enum ip_conntrack_info ctinfo; struct nf_flow_route route; struct flow_offload *flow; enum ip_conntrack_dir dir; - bool is_tcp = false; struct nf_conn *ct; int ret;

@@ -88,7 +88,10 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,

switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) { case IPPROTO_TCP: - is_tcp = true; + tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff, + sizeof(_tcph), &_tcph); + if (unlikely(!tcph || tcph->fin || tcph->rst)) + goto out; break; case IPPROTO_UDP: break; @@ -115,7 +118,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, if (!flow) goto err_flow_alloc;

- if (is_tcp) { + if (tcph) { ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; }

[ Upstream commit 070955558e820b9a89c570b91b1f21762f62b288 ]

This driver requires imported PRIME buffers to appear contiguously in its IO address space. Make sure this is the case by setting the maximum DMA segment size to a more suitable value than the default 64KB.

Signed-off-by: Alexandre Courbot acourbot@chromium.org Reviewed-by: Tomasz Figa tfiga@chromium.org Signed-off-by: CK Hu ck.hu@mediatek.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/mediatek/mtk_drm_drv.c | 35 ++++++++++++++++++++++++-- drivers/gpu/drm/mediatek/mtk_drm_drv.h | 2 ++ 2 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index ffb997440851d..f6389479fccb5 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -220,6 +220,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) struct mtk_drm_private *private = drm->dev_private; struct platform_device *pdev; struct device_node *np; + struct device *dma_dev; int ret;

if (!iommu_present(&platform_bus_type)) @@ -282,7 +283,29 @@ static int mtk_drm_kms_init(struct drm_device *drm) goto err_component_unbind; }

- private->dma_dev = &pdev->dev; + dma_dev = &pdev->dev; + private->dma_dev = dma_dev; + + /* + * Configure the DMA segment size to make sure we get contiguous IOVA + * when importing PRIME buffers. + */ + if (!dma_dev->dma_parms) { + private->dma_parms_allocated = true; + dma_dev->dma_parms = + devm_kzalloc(drm->dev, sizeof(*dma_dev->dma_parms), + GFP_KERNEL); + } + if (!dma_dev->dma_parms) { + ret = -ENOMEM; + goto err_component_unbind; + } + + ret = dma_set_max_seg_size(dma_dev, (unsigned int)DMA_BIT_MASK(32)); + if (ret) { + dev_err(dma_dev, "Failed to set DMA segment size\n"); + goto err_unset_dma_parms; + }

/* * We don't use the drm_irq_install() helpers provided by the DRM @@ -292,13 +315,16 @@ static int mtk_drm_kms_init(struct drm_device *drm) drm->irq_enabled = true; ret = drm_vblank_init(drm, MAX_CRTC); if (ret < 0) - goto err_component_unbind; + goto err_unset_dma_parms;

drm_kms_helper_poll_init(drm); drm_mode_config_reset(drm);

return 0;

+err_unset_dma_parms: + if (private->dma_parms_allocated) + dma_dev->dma_parms = NULL; err_component_unbind: component_unbind_all(drm->dev, drm); err_config_cleanup: @@ -309,9 +335,14 @@ err_config_cleanup:

static void mtk_drm_kms_deinit(struct drm_device *drm) { + struct mtk_drm_private *private = drm->dev_private; + drm_kms_helper_poll_fini(drm); drm_atomic_helper_shutdown(drm);

+ if (private->dma_parms_allocated) + private->dma_dev->dma_parms = NULL; + component_unbind_all(drm->dev, drm); drm_mode_config_cleanup(drm); } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.h b/drivers/gpu/drm/mediatek/mtk_drm_drv.h index ecc00ca3221da..8fa60d46f8605 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.h +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.h @@ -59,6 +59,8 @@ struct mtk_drm_private { } commit;

struct drm_atomic_state *suspend_state; + + bool dma_parms_allocated; };

extern struct platform_driver mtk_ddp_driver;

[ Upstream commit a86a75865ff4d8c05f355d1750a5250aec89ab15 ]

In tcmu_handle_completion() function, the variable called read_len is always initialized with a value taken from se_cmd structure. If this function is called to complete an expired (timed out) out command, the session command pointed by se_cmd is likely to be already deallocated by the target core at that moment. As the result, this access triggers a use-after-free warning from KASAN.

This patch fixes the code not to touch se_cmd when completing timed out TCMU commands. It also resets the pointer to se_cmd at the time when the TCMU_CMD_BIT_EXPIRED flag is set because it is going to become invalid after calling target_complete_cmd() later in the same function, tcmu_check_expired_cmd().

Signed-off-by: Dmitry Fomichev dmitry.fomichev@wdc.com Acked-by: Mike Christie mchristi@redhat.com Reviewed-by: Damien Le Moal damien.lemoal@wdc.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/target/target_core_user.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index c46efa47d68a5..7159e8363b83b 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1143,14 +1143,16 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry * struct se_cmd *se_cmd = cmd->se_cmd; struct tcmu_dev *udev = cmd->tcmu_dev; bool read_len_valid = false; - uint32_t read_len = se_cmd->data_length; + uint32_t read_len;

/* * cmd has been completed already from timeout, just reclaim * data area space and free cmd */ - if (test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags)) + if (test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags)) { + WARN_ON_ONCE(se_cmd); goto out; + }

list_del_init(&cmd->queue_entry);

@@ -1163,6 +1165,7 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry * goto done; }

+ read_len = se_cmd->data_length; if (se_cmd->data_direction == DMA_FROM_DEVICE && (entry->hdr.uflags & TCMU_UFLAG_READ_LEN) && entry->rsp.read_len) { read_len_valid = true; @@ -1318,6 +1321,7 @@ static int tcmu_check_expired_cmd(int id, void *p, void *data) */ scsi_status = SAM_STAT_CHECK_CONDITION; list_del_init(&cmd->queue_entry); + cmd->se_cmd = NULL; } else { list_del_init(&cmd->queue_entry); idr_remove(&udev->commands, id); @@ -2036,6 +2040,7 @@ static void tcmu_reset_ring(struct tcmu_dev *udev, u8 err_level)

idr_remove(&udev->commands, i); if (!test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags)) { + WARN_ON(!cmd->se_cmd); list_del_init(&cmd->queue_entry); if (err_level == 1) { /*

[ Upstream commit 20fb7c7a39b5c719e2e619673b5f5729ee7d2306 ]

In myri10ge_probe(), myri10ge_alloc_slices() is invoked to allocate slices related structures. Later on, myri10ge_request_irq() is used to get an irq. However, if this process fails, the allocated slices related structures are not deallocated, leading to memory leaks. To fix this issue, revise the target label of the goto statement to 'abort_with_slices'.

Signed-off-by: Wenwen Wang wenwen@cs.uga.edu Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/myricom/myri10ge/myri10ge.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index b2d2ec8c11e2d..6789eed78ff70 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -3922,7 +3922,7 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * setup (if available). */ status = myri10ge_request_irq(mgp); if (status != 0) - goto abort_with_firmware; + goto abort_with_slices; myri10ge_free_irq(mgp);

/* Save configuration space to be restored if the

[ Upstream commit edc58dd0123b552453a74369bd0c8d890b497b4b ]

When dedupe wants to use the page cache to compare parts of two files for dedupe, we must be very careful to handle locking correctly. The current code doesn't do this. It must lock and unlock the page only once if the two pages are the same, since the overlapping range check doesn't catch this when blocksize < pagesize. If the pages are distinct but from the same file, we must observe page locking order and lock them in order of increasing offset to avoid clashing with writeback locking.

Fixes: 876bec6f9bbfcb3 ("vfs: refactor clone/dedupe_file_range common functions") Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Reviewed-by: Bill O'Donnell billodo@redhat.com Reviewed-by: Matthew Wilcox (Oracle) willy@infradead.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/read_write.c | 49 +++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 41 insertions(+), 8 deletions(-)

diff --git a/fs/read_write.c b/fs/read_write.c index 85fd7a8ee29eb..5fb5ee5b8cd70 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1888,10 +1888,7 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in, } EXPORT_SYMBOL(vfs_clone_file_range);

-/* - * Read a page's worth of file data into the page cache. Return the page - * locked. - */ +/* Read a page's worth of file data into the page cache. */ static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset) { struct address_space *mapping; @@ -1907,10 +1904,32 @@ static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset) put_page(page); return ERR_PTR(-EIO); } - lock_page(page); return page; }

+/* + * Lock two pages, ensuring that we lock in offset order if the pages are from + * the same file. + */ +static void vfs_lock_two_pages(struct page *page1, struct page *page2) +{ + /* Always lock in order of increasing index. */ + if (page1->index > page2->index) + swap(page1, page2); + + lock_page(page1); + if (page1 != page2) + lock_page(page2); +} + +/* Unlock two pages, being careful not to unlock the same page twice. */ +static void vfs_unlock_two_pages(struct page *page1, struct page *page2) +{ + unlock_page(page1); + if (page1 != page2) + unlock_page(page2); +} + /* * Compare extents of two files to see if they are the same. * Caller must have locked both inodes to prevent write races. @@ -1948,10 +1967,24 @@ int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, dest_page = vfs_dedupe_get_page(dest, destoff); if (IS_ERR(dest_page)) { error = PTR_ERR(dest_page); - unlock_page(src_page); put_page(src_page); goto out_error; } + + vfs_lock_two_pages(src_page, dest_page); + + /* + * Now that we've locked both pages, make sure they're still + * mapped to the file data we're interested in. If not, + * someone is invalidating pages on us and we lose. + */ + if (!PageUptodate(src_page) || !PageUptodate(dest_page) || + src_page->mapping != src->i_mapping || + dest_page->mapping != dest->i_mapping) { + same = false; + goto unlock; + } + src_addr = kmap_atomic(src_page); dest_addr = kmap_atomic(dest_page);

@@ -1963,8 +1996,8 @@ int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,

kunmap_atomic(dest_addr); kunmap_atomic(src_addr); - unlock_page(dest_page); - unlock_page(src_page); +unlock: + vfs_unlock_two_pages(src_page, dest_page); put_page(dest_page); put_page(src_page);

[ Upstream commit f1472cb09f11ddb41d4be84f0650835cb65a9073 ]

In kalmia_init_and_get_ethernet_addr(), 'usb_buf' is allocated through kmalloc(). In the following execution, if the 'status' returned by kalmia_send_init_packet() is not 0, 'usb_buf' is not deallocated, leading to memory leaks. To fix this issue, add the 'out' label to free 'usb_buf'.

Signed-off-by: Wenwen Wang wenwen@cs.uga.edu Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/kalmia.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/usb/kalmia.c b/drivers/net/usb/kalmia.c index bd2ba36590288..0cc6993c279a2 100644 --- a/drivers/net/usb/kalmia.c +++ b/drivers/net/usb/kalmia.c @@ -117,16 +117,16 @@ kalmia_init_and_get_ethernet_addr(struct usbnet *dev, u8 *ethernet_addr) status = kalmia_send_init_packet(dev, usb_buf, ARRAY_SIZE(init_msg_1), usb_buf, 24); if (status != 0) - return status; + goto out;

memcpy(usb_buf, init_msg_2, 12); status = kalmia_send_init_packet(dev, usb_buf, ARRAY_SIZE(init_msg_2), usb_buf, 28); if (status != 0) - return status; + goto out;

memcpy(ethernet_addr, usb_buf + 10, ETH_ALEN); - +out: kfree(usb_buf); return status; }

[ Upstream commit 3434341004a380f4e47c3a03d4320d43982162a0 ]

The driver name gets exposed in sysfs under /sys/bus/pci/drivers so it should look like other devices. Change it to be common format (instead of "Cavium PTP").

This is a trivial fix that was observed by accident because Debian kernels were building this driver into kernel (bug).

Signed-off-by: Stephen Hemminger stephen@networkplumber.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/cavium/common/cavium_ptp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cavium/common/cavium_ptp.c b/drivers/net/ethernet/cavium/common/cavium_ptp.c index 6aeb1045c302a..1ab40c97403ba 100644 --- a/drivers/net/ethernet/cavium/common/cavium_ptp.c +++ b/drivers/net/ethernet/cavium/common/cavium_ptp.c @@ -10,7 +10,7 @@

#include "cavium_ptp.h"

-#define DRV_NAME "Cavium PTP Driver" +#define DRV_NAME "cavium_ptp"

#define PCI_DEVICE_ID_CAVIUM_PTP 0xA00C #define PCI_DEVICE_ID_CAVIUM_RST 0xA00E

[ Upstream commit cfef46d692efd852a0da6803f920cc756eea2855 ]

When a Tx timestamp is requested, a pointer to the skb is stored in the ravb_tstamp_skb struct. This was done without an skb_get. There exists the possibility that the skb could be freed by ravb_tx_free (when ravb_tx_free is called from ravb_start_xmit) before the timestamp was processed, leading to a use-after-free bug.

Use skb_get when filling a ravb_tstamp_skb struct, and add appropriate frees/consumes when a ravb_tstamp_skb struct is freed.

Fixes: c156633f1353 ("Renesas Ethernet AVB driver proper") Signed-off-by: Tho Vu tho.vu.wh@rvc.renesas.com Signed-off-by: Kazuya Mizuguchi kazuya.mizuguchi.ks@renesas.com Signed-off-by: Simon Horman horms+renesas@verge.net.au Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/renesas/ravb_main.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 5f092bbd05148..5462d2e8a1b71 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Renesas Ethernet AVB device driver * - * Copyright (C) 2014-2015 Renesas Electronics Corporation + * Copyright (C) 2014-2019 Renesas Electronics Corporation * Copyright (C) 2015 Renesas Solutions Corp. * Copyright (C) 2015-2016 Cogent Embedded, Inc. source@cogentembedded.com * @@ -514,7 +514,10 @@ static void ravb_get_tx_tstamp(struct net_device *ndev) kfree(ts_skb); if (tag == tfa_tag) { skb_tstamp_tx(skb, &shhwtstamps); + dev_consume_skb_any(skb); break; + } else { + dev_kfree_skb_any(skb); } } ravb_modify(ndev, TCCR, TCCR_TFR, TCCR_TFR); @@ -1556,7 +1559,7 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) DMA_TO_DEVICE); goto unmap; } - ts_skb->skb = skb; + ts_skb->skb = skb_get(skb); ts_skb->tag = priv->ts_skb_tag++; priv->ts_skb_tag &= 0x3ff; list_add_tail(&ts_skb->list, &priv->ts_skb_list); @@ -1685,6 +1688,7 @@ static int ravb_close(struct net_device *ndev) /* Clear the timestamp list */ list_for_each_entry_safe(ts_skb, ts_skb2, &priv->ts_skb_list, list) { list_del(&ts_skb->list); + kfree_skb(ts_skb->skb); kfree(ts_skb); }

[ Upstream commit 2d05dba2b25ecb0f8fc3a0b4eb2232da6454a47b ]

When calling request_threaded_irq() with a CP2112, the function cp2112_gpio_irq_startup() is called in a IRQ context.

Therefore we can not sleep, and we can not call cp2112_gpio_direction_input() there.

Move the call to cp2112_gpio_direction_input() earlier to have a working driver.

Signed-off-by: Benjamin Tissoires benjamin.tissoires@redhat.com Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/hid-cp2112.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c index 271f31461da42..6f65f52572368 100644 --- a/drivers/hid/hid-cp2112.c +++ b/drivers/hid/hid-cp2112.c @@ -1160,8 +1160,6 @@ static unsigned int cp2112_gpio_irq_startup(struct irq_data *d)

INIT_DELAYED_WORK(&dev->gpio_poll_worker, cp2112_gpio_poll_callback);

- cp2112_gpio_direction_input(gc, d->hwirq); - if (!dev->gpio_poll) { dev->gpio_poll = true; schedule_delayed_work(&dev->gpio_poll_worker, 0); @@ -1209,6 +1207,12 @@ static int __maybe_unused cp2112_allocate_irq(struct cp2112_device *dev, return PTR_ERR(dev->desc[pin]); }

+ ret = cp2112_gpio_direction_input(&dev->gc, pin); + if (ret < 0) { + dev_err(dev->gc.parent, "Failed to set GPIO to input dir\n"); + goto err_desc; + } + ret = gpiochip_lock_as_irq(&dev->gc, pin); if (ret) { dev_err(dev->gc.parent, "Failed to lock GPIO as interrupt\n");

[ Upstream commit d09bc83640d524b8467a660db7b1d15e6562a1de ]

Simplify the ring buffer handling with the in-place API.

Also avoid the dynamic allocation and the memory leak in the channel callback function.

Signed-off-by: Dexuan Cui decui@microsoft.com Acked-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/input/serio/hyperv-keyboard.c | 35 +++++---------------------- 1 file changed, 6 insertions(+), 29 deletions(-)

diff --git a/drivers/input/serio/hyperv-keyboard.c b/drivers/input/serio/hyperv-keyboard.c index a8b9be3e28db7..7d0a5ccf57751 100644 --- a/drivers/input/serio/hyperv-keyboard.c +++ b/drivers/input/serio/hyperv-keyboard.c @@ -245,40 +245,17 @@ static void hv_kbd_handle_received_packet(struct hv_device *hv_dev,

static void hv_kbd_on_channel_callback(void *context) { + struct vmpacket_descriptor *desc; struct hv_device *hv_dev = context; - void *buffer; - int bufferlen = 0x100; /* Start with sensible size */ u32 bytes_recvd; u64 req_id; - int error;

- buffer = kmalloc(bufferlen, GFP_ATOMIC); - if (!buffer) - return; - - while (1) { - error = vmbus_recvpacket_raw(hv_dev->channel, buffer, bufferlen, - &bytes_recvd, &req_id); - switch (error) { - case 0: - if (bytes_recvd == 0) { - kfree(buffer); - return; - } - - hv_kbd_handle_received_packet(hv_dev, buffer, - bytes_recvd, req_id); - break; + foreach_vmbus_pkt(desc, hv_dev->channel) { + bytes_recvd = desc->len8 * 8; + req_id = desc->trans_id;

- case -ENOBUFS: - kfree(buffer); - /* Handle large packet */ - bufferlen = bytes_recvd; - buffer = kmalloc(bytes_recvd, GFP_ATOMIC); - if (!buffer) - return; - break; - } + hv_kbd_handle_received_packet(hv_dev, desc, bytes_recvd, + req_id); } }

[ Upstream commit 504db087aaccdb32af61539916409f7dca31ceb5 ]

nvme_state_set_live() making a path available triggers requeue_work in order to resubmit requests that ended up on requeue_list when no paths were available.

This requeue_work may race with concurrent nvme_ns_head_make_request() that do not observe the live path yet. Such concurrent requests may by made by either: - New IO submission. - Requeue_work triggered by nvme_failover_req() or another ana_work.

A race may cause requeue_work capture the state of requeue_list before more requests get onto the list. These requests will stay on the list forever unless requeue_work is triggered again.

In order to prevent such race, nvme_state_set_live() should synchronize_srcu(&head->srcu) before triggering the requeue_work and prevent nvme_ns_head_make_request referencing an old snapshot of the path list.

Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Anton Eidelman anton@lightbitslabs.com Signed-off-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/multipath.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 05d6371c7f385..f57feb8fdea45 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -323,6 +323,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns) "failed to create id group.\n"); }

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

[ Upstream commit b08afa064c320e5d85cdc27228426b696c4c8dae ]

In fault_opcodes_read(), 'data' is not deallocated if debugfs_file_get() fails, leading to a memory leak. To fix this bug, introduce the 'free_data' label to free 'data' before returning the error.

Signed-off-by: Wenwen Wang wenwen@cs.uga.edu Reviewed-by: Leon Romanovsky leonro@mellanox.com Acked-by: Dennis Dalessandro dennis.dalessandro@intel.com Link: https://lore.kernel.org/r/1566156571-4335-1-git-send-email-wenwen@cs.uga.edu Signed-off-by: Doug Ledford dledford@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/hfi1/fault.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/hfi1/fault.c b/drivers/infiniband/hw/hfi1/fault.c index 7eaff4dcbfd77..72ca0dc5f3b59 100644 --- a/drivers/infiniband/hw/hfi1/fault.c +++ b/drivers/infiniband/hw/hfi1/fault.c @@ -214,7 +214,7 @@ static ssize_t fault_opcodes_read(struct file *file, char __user *buf, return -ENOMEM; ret = debugfs_file_get(file->f_path.dentry); if (unlikely(ret)) - return ret; + goto free_data; bit = find_first_bit(fault->opcodes, bitsize); while (bit < bitsize) { zero = find_next_zero_bit(fault->opcodes, bitsize, bit); @@ -232,6 +232,7 @@ static ssize_t fault_opcodes_read(struct file *file, char __user *buf, data[size - 1] = '\n'; data[size] = '\0'; ret = simple_read_from_buffer(buf, len, pos, data, size); +free_data: kfree(data); return ret; }

[ Upstream commit 54577e5018a8c0cb79c9a0fa118a55c68715d398 ]

state_test and smm_test are failing on older processors that do not have xcr0. This is because on those processor KVM does provide support for KVM_GET/SET_XSAVE (to avoid having to rely on the older KVM_GET/SET_FPU) but not for KVM_GET/SET_XCRS.

Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/kvm/lib/x86.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/kvm/lib/x86.c b/tools/testing/selftests/kvm/lib/x86.c index a3122f1949a8e..4d35eba73dc97 100644 --- a/tools/testing/selftests/kvm/lib/x86.c +++ b/tools/testing/selftests/kvm/lib/x86.c @@ -809,9 +809,11 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i", r);

- r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XCRS, r: %i", - r); + if (kvm_check_cap(KVM_CAP_XCRS)) { + r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XCRS, r: %i", + r); + }

r = ioctl(vcpu->fd, KVM_GET_SREGS, &state->sregs); TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i", @@ -858,9 +860,11 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i", r);

- r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XCRS, r: %i", - r); + if (kvm_check_cap(KVM_CAP_XCRS)) { + r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XCRS, r: %i", + r); + }

r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs); TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i",

[ Upstream commit 86968ef21596515958d5f0a40233d02be78ecec0 ]

Calling ceph_buffer_put() in __ceph_setxattr() may end up freeing the i_xattrs.prealloc_blob buffer while holding the i_ceph_lock. This can be fixed by postponing the call until later, when the lock is released.

The following backtrace was triggered by fstests generic/117.

BUG: sleeping function called from invalid context at mm/vmalloc.c:2283 in_atomic(): 1, irqs_disabled(): 0, pid: 650, name: fsstress 3 locks held by fsstress/650: #0: 00000000870a0fe8 (sb_writers#8){.+.+}, at: mnt_want_write+0x20/0x50 #1: 00000000ba0c4c74 (&type->i_mutex_dir_key#6){++++}, at: vfs_setxattr+0x55/0xa0 #2: 000000008dfbb3f2 (&(&ci->i_ceph_lock)->rlock){+.+.}, at: __ceph_setxattr+0x297/0x810 CPU: 1 PID: 650 Comm: fsstress Not tainted 5.2.0+ #437 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack+0x67/0x90 ___might_sleep.cold+0x9f/0xb1 vfree+0x4b/0x60 ceph_buffer_release+0x1b/0x60 __ceph_setxattr+0x2b4/0x810 __vfs_setxattr+0x66/0x80 __vfs_setxattr_noperm+0x59/0xf0 vfs_setxattr+0x81/0xa0 setxattr+0x115/0x230 ? filename_lookup+0xc9/0x140 ? rcu_read_lock_sched_held+0x74/0x80 ? rcu_sync_lockdep_assert+0x2e/0x60 ? __sb_start_write+0x142/0x1a0 ? mnt_want_write+0x20/0x50 path_setxattr+0xba/0xd0 __x64_sys_lsetxattr+0x24/0x30 do_syscall_64+0x50/0x1c0 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7ff23514359a

Signed-off-by: Luis Henriques lhenriques@suse.com Reviewed-by: Jeff Layton jlayton@kernel.org Signed-off-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ceph/xattr.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 0a2d4898ee163..71ea45b0231f9 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1011,6 +1011,7 @@ int __ceph_setxattr(struct inode *inode, const char *name, struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; struct ceph_cap_flush *prealloc_cf = NULL; + struct ceph_buffer *old_blob = NULL; int issued; int err; int dirty = 0; @@ -1084,13 +1085,15 @@ retry: struct ceph_buffer *blob;

spin_unlock(&ci->i_ceph_lock); - dout(" preaallocating new blob size=%d\n", required_blob_size); + ceph_buffer_put(old_blob); /* Shouldn't be required */ + dout(" pre-allocating new blob size=%d\n", required_blob_size); blob = ceph_buffer_new(required_blob_size, GFP_NOFS); if (!blob) goto do_sync_unlocked; spin_lock(&ci->i_ceph_lock); + /* prealloc_blob can't be released while holding i_ceph_lock */ if (ci->i_xattrs.prealloc_blob) - ceph_buffer_put(ci->i_xattrs.prealloc_blob); + old_blob = ci->i_xattrs.prealloc_blob; ci->i_xattrs.prealloc_blob = blob; goto retry; } @@ -1106,6 +1109,7 @@ retry: }

spin_unlock(&ci->i_ceph_lock); + ceph_buffer_put(old_blob); if (lock_snap_rwsem) up_read(&mdsc->snap_rwsem); if (dirty)

[ Upstream commit af8a85a41734f37b67ba8ce69d56b685bee4ac48 ]

Calling ceph_buffer_put() in fill_inode() may result in freeing the i_xattrs.blob buffer while holding the i_ceph_lock. This can be fixed by postponing the call until later, when the lock is released.

The following backtrace was triggered by fstests generic/070.

BUG: sleeping function called from invalid context at mm/vmalloc.c:2283 in_atomic(): 1, irqs_disabled(): 0, pid: 3852, name: kworker/0:4 6 locks held by kworker/0:4/3852: #0: 000000004270f6bb ((wq_completion)ceph-msgr){+.+.}, at: process_one_work+0x1b8/0x5f0 #1: 00000000eb420803 ((work_completion)(&(&con->work)->work)){+.+.}, at: process_one_work+0x1b8/0x5f0 #2: 00000000be1c53a4 (&s->s_mutex){+.+.}, at: dispatch+0x288/0x1476 #3: 00000000559cb958 (&mdsc->snap_rwsem){++++}, at: dispatch+0x2eb/0x1476 #4: 000000000d5ebbae (&req->r_fill_mutex){+.+.}, at: dispatch+0x2fc/0x1476 #5: 00000000a83d0514 (&(&ci->i_ceph_lock)->rlock){+.+.}, at: fill_inode.isra.0+0xf8/0xf70 CPU: 0 PID: 3852 Comm: kworker/0:4 Not tainted 5.2.0+ #441 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-prebuilt.qemu.org 04/01/2014 Workqueue: ceph-msgr ceph_con_workfn Call Trace: dump_stack+0x67/0x90 ___might_sleep.cold+0x9f/0xb1 vfree+0x4b/0x60 ceph_buffer_release+0x1b/0x60 fill_inode.isra.0+0xa9b/0xf70 ceph_fill_trace+0x13b/0xc70 ? dispatch+0x2eb/0x1476 dispatch+0x320/0x1476 ? __mutex_unlock_slowpath+0x4d/0x2a0 ceph_con_workfn+0xc97/0x2ec0 ? process_one_work+0x1b8/0x5f0 process_one_work+0x244/0x5f0 worker_thread+0x4d/0x3e0 kthread+0x105/0x140 ? process_one_work+0x5f0/0x5f0 ? kthread_park+0x90/0x90 ret_from_fork+0x3a/0x50

Signed-off-by: Luis Henriques lhenriques@suse.com Reviewed-by: Jeff Layton jlayton@kernel.org Signed-off-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ceph/inode.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 3e518c2ae2bf9..11f19432a74c4 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -742,6 +742,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page, int issued, new_issued, info_caps; struct timespec64 mtime, atime, ctime; struct ceph_buffer *xattr_blob = NULL; + struct ceph_buffer *old_blob = NULL; struct ceph_string *pool_ns = NULL; struct ceph_cap *new_cap = NULL; int err = 0; @@ -878,7 +879,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page, if ((ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL)) && le64_to_cpu(info->xattr_version) > ci->i_xattrs.version) { if (ci->i_xattrs.blob) - ceph_buffer_put(ci->i_xattrs.blob); + old_blob = ci->i_xattrs.blob; ci->i_xattrs.blob = xattr_blob; if (xattr_blob) memcpy(ci->i_xattrs.blob->vec.iov_base, @@ -1017,8 +1018,8 @@ static int fill_inode(struct inode *inode, struct page *locked_page, out: if (new_cap) ceph_put_cap(mdsc, new_cap); - if (xattr_blob) - ceph_buffer_put(xattr_blob); + ceph_buffer_put(old_blob); + ceph_buffer_put(xattr_blob); ceph_put_string(pool_ns); return err; }

[ Upstream commit a5fb8e6c02d6a518fb2b1a2b8c2471fa77b69436 ]

Fix a leak on the cell refcount in afs_lookup_cell_rcu() due to non-clearance of the default error in the case a NULL cell name is passed and the workstation default cell is used.

Also put a bit at the end to make sure we don't leak a cell ref if we're going to be returning an error.

This leak results in an assertion like the following when the kafs module is unloaded:

AFS: Assertion failed 2 == 1 is false 0x2 == 0x1 is false ------------[ cut here ]------------ kernel BUG at fs/afs/cell.c:770! ... RIP: 0010:afs_manage_cells+0x220/0x42f [kafs] ... process_one_work+0x4c2/0x82c ? pool_mayday_timeout+0x1e1/0x1e1 ? do_raw_spin_lock+0x134/0x175 worker_thread+0x336/0x4a6 ? rescuer_thread+0x4af/0x4af kthread+0x1de/0x1ee ? kthread_park+0xd4/0xd4 ret_from_fork+0x24/0x30

Fixes: 989782dcdc91 ("afs: Overhaul cell database management") Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/afs/cell.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 6127f0fcd62c4..ee07162d35c7a 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -76,6 +76,7 @@ struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net, cell = rcu_dereference_raw(net->ws_cell); if (cell) { afs_get_cell(cell); + ret = 0; break; } ret = -EDESTADDRREQ; @@ -110,6 +111,9 @@ struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net,

done_seqretry(&net->cells_lock, seq);

+ if (ret != 0 && cell) + afs_put_cell(net, cell); + return ret == 0 ? cell : ERR_PTR(ret); }

[ Upstream commit c96e8483cb2da6695c8b8d0896fe7ae272a07b54 ]

Gustavo noticed that 'new' can be left uninitialized if 'bios_start' happens to be less or equal to 'entry->addr + entry->size'.

Initialize the variable at the begin of the iteration to the current value of 'bios_start'.

Fixes: 0a46fff2f910 ("x86/boot/compressed/64: Fix boot on machines with broken E820 table") Reported-by: "Gustavo A. R. Silva" gustavo@embeddedor.com Signed-off-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Link: https://lkml.kernel.org/r/20190826133326.7cxb4vbmiawffv2r@box Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/boot/compressed/pgtable_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index f0537a1f7fc25..76e1edf5bf12a 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -73,7 +73,7 @@ static unsigned long find_trampoline_placement(void)

/* Find the first usable memory region under bios_start. */ for (i = boot_params->e820_entries - 1; i >= 0; i--) { - unsigned long new; + unsigned long new = bios_start;

entry = &boot_params->e820_table[i];

[ Upstream commit 950b07c14e8c59444e2359f15fd70ed5112e11a0 ]

This reverts commit 558682b5291937a70748d36fd9ba757fb25b99ae.

Chris Wilson reports that it breaks his CPU hotplug test scripts. In particular, it breaks offlining and then re-onlining the boot CPU, which we treat specially (and the BIOS does too).

The symptoms are that we can offline the CPU, but it then does not come back online again:

smpboot: CPU 0 is now offline smpboot: Booting Node 0 Processor 0 APIC 0x0 smpboot: do_boot_cpu failed(-1) to wakeup CPU#0

Thomas says he knows why it's broken (my personal suspicion: our magic handling of the "cpu0_logical_apicid" thing), but for 5.3 the right fix is to just revert it, since we've never touched the LDR bits before, and it's not worth the risk to do anything else at this stage.

[ Hotpluging of the boot CPU is special anyway, and should be off by default. See the "BOOTPARAM_HOTPLUG_CPU0" config option and the cpu0_hotplug kernel parameter.

In general you should not do it, and it has various known limitations (hibernate and suspend require the boot CPU, for example).

But it should work, even if the boot CPU is special and needs careful treatment - Linus ]

Link: https://lore.kernel.org/lkml/156785100521.13300.14461504732265570003@skylake... Reported-by: Chris Wilson chris@chris-wilson.co.uk Acked-by: Thomas Gleixner tglx@linutronix.de Cc: Bandan Das bsd@redhat.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/apic/apic.c | 4 ---- 1 file changed, 4 deletions(-)

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 90be3a1506d3f..b316bd61a6ace 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1140,10 +1140,6 @@ void clear_local_APIC(void) apic_write(APIC_LVT0, v | APIC_LVT_MASKED); v = apic_read(APIC_LVT1); apic_write(APIC_LVT1, v | APIC_LVT_MASKED); - if (!x2apic_enabled()) { - v = apic_read(APIC_LDR) & ~APIC_LDR_MASK; - apic_write(APIC_LDR, v); - } if (maxlvt >= 4) { v = apic_read(APIC_LVTPC); apic_write(APIC_LVTPC, v | APIC_LVT_MASKED);