[ Upstream commit a07e3324538a989b7cdbf2c679be6a7f9df2544f ]

i8253 clocksource needs a free running timer. This could only be used, if i8253 clockevent is set up as periodic.

Signed-off-by: Thomas Bogendoerfer tbogendoerfer@suse.de Signed-off-by: Paul Burton paul.burton@mips.com Cc: Ralf Baechle ralf@linux-mips.org Cc: James Hogan jhogan@kernel.org Cc: linux-mips@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/mips/kernel/i8253.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c index 5f209f111e59e..df7ddd246eaac 100644 --- a/arch/mips/kernel/i8253.c +++ b/arch/mips/kernel/i8253.c @@ -32,7 +32,8 @@ void __init setup_pit_timer(void)

static int __init init_pit_clocksource(void) { - if (num_possible_cpus() > 1) /* PIT does not scale! */ + if (num_possible_cpus() > 1 || /* PIT does not scale! */ + !clockevent_state_periodic(&i8253_clockevent)) return 0;

return clocksource_i8253_init();

[ Upstream commit 15a78ba1844a8e052c1226f930133de4cef4e7ad ]

In compat_do_replace(), a temporary buffer is allocated through vmalloc() to hold entries copied from the user space. The buffer address is firstly saved to 'newinfo->entries', and later on assigned to 'entries_tmp'. Then the entries in this temporary buffer is copied to the internal kernel structure through compat_copy_entries(). If this copy process fails, compat_do_replace() should be terminated. However, the allocated temporary buffer is not freed on this path, leading to a memory leak.

To fix the bug, free the buffer before returning from compat_do_replace().

Signed-off-by: Wenwen Wang wenwen@cs.uga.edu Reviewed-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/bridge/netfilter/ebtables.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 995b3842ba7c0..62ffc989a44a2 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2274,8 +2274,10 @@ static int compat_do_replace(struct net *net, void __user *user, state.buf_kern_len = size64;

ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); - if (WARN_ON(ret < 0)) + if (WARN_ON(ret < 0)) { + vfree(entries_tmp); goto out_unlock; + }

vfree(entries_tmp); tmp.entries_size = size64;

[ Upstream commit c8eee4135a456bc031d67cadc454e76880d1afd8 ]

"sendmsg6: rewrite IP & port (C)" fails on s390, because the code in sendmsg_v6_prog() assumes that (ctx->user_ip6[0] & 0xFFFF) refers to leading IPv6 address digits, which is not the case on big-endian machines.

Since checking bitwise operations doesn't seem to be the point of the test, replace two short comparisons with a single int comparison.

Signed-off-by: Ilya Leoshkevich iii@linux.ibm.com Acked-by: Andrey Ignatov rdna@fb.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/bpf/sendmsg6_prog.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/sendmsg6_prog.c b/tools/testing/selftests/bpf/sendmsg6_prog.c index 5aeaa284fc474..a680628204108 100644 --- a/tools/testing/selftests/bpf/sendmsg6_prog.c +++ b/tools/testing/selftests/bpf/sendmsg6_prog.c @@ -41,8 +41,7 @@ int sendmsg_v6_prog(struct bpf_sock_addr *ctx) }

/* Rewrite destination. */ - if ((ctx->user_ip6[0] & 0xFFFF) == bpf_htons(0xFACE) && - ctx->user_ip6[0] >> 16 == bpf_htons(0xB00C)) { + if (ctx->user_ip6[0] == bpf_htonl(0xFACEB00C)) { ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0); ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_1); ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2);

[ Upstream commit bba18318e7d1d5c8b0bbafd65010a0cee3c65608 ]

PPv2's XLGMAC can wait for 3 idle frames before triggering a link up event. This can cause the link to be stuck low when there's traffic on the interface, so disable this feature.

Fixes: 4bb043262878 ("net: mvpp2: phylink support") Signed-off-by: Maxime Chevallier maxime.chevallier@bootlin.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 6455511457ca3..9b608d23ff7ee 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4412,9 +4412,9 @@ static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode, if (state->pause & MLO_PAUSE_RX) ctrl0 |= MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN;

- ctrl4 &= ~MVPP22_XLG_CTRL4_MACMODSELECT_GMAC; - ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC | - MVPP22_XLG_CTRL4_EN_IDLE_CHECK; + ctrl4 &= ~(MVPP22_XLG_CTRL4_MACMODSELECT_GMAC | + MVPP22_XLG_CTRL4_EN_IDLE_CHECK); + ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC;

writel(ctrl0, port->base + MVPP22_XLG_CTRL0_REG); writel(ctrl4, port->base + MVPP22_XLG_CTRL4_REG);

[ Upstream commit 1be79d89b7ae96e004911bd228ce8c2b5cc6415f ]

The TC filters used in the test do not work with veth devices because the outer Ethertype is 802.1Q and not IPv4. The test passes with mlxsw netdevs since the hardware always looks at "The first Ethertype that does not point to either: VLAN, CNTAG or configurable Ethertype".

Fix this by matching on the VLAN ID instead, but on the ingress side. The reason why this is not performed at egress is explained in the commit cited below.

Fixes: 541ad323db3a ("selftests: forwarding: gre_multipath: Update next-hop statistics match criteria") Signed-off-by: Ido Schimmel idosch@mellanox.com Reported-by: Stephen Suryaputra ssuryaextr@gmail.com Tested-by: Stephen Suryaputra ssuryaextr@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- .../selftests/net/forwarding/gre_multipath.sh | 24 +++++++++---------- 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/gre_multipath.sh b/tools/testing/selftests/net/forwarding/gre_multipath.sh index 37d7297e1cf8a..a8d8e8b3dc819 100755 --- a/tools/testing/selftests/net/forwarding/gre_multipath.sh +++ b/tools/testing/selftests/net/forwarding/gre_multipath.sh @@ -93,18 +93,10 @@ sw1_create() ip route add vrf v$ol1 192.0.2.16/28 \ nexthop dev g1a \ nexthop dev g1b - - tc qdisc add dev $ul1 clsact - tc filter add dev $ul1 egress pref 111 prot ipv4 \ - flower dst_ip 192.0.2.66 action pass - tc filter add dev $ul1 egress pref 222 prot ipv4 \ - flower dst_ip 192.0.2.82 action pass }

sw1_destroy() { - tc qdisc del dev $ul1 clsact - ip route del vrf v$ol1 192.0.2.16/28

ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146 @@ -139,10 +131,18 @@ sw2_create() ip route add vrf v$ol2 192.0.2.0/28 \ nexthop dev g2a \ nexthop dev g2b + + tc qdisc add dev $ul2 clsact + tc filter add dev $ul2 ingress pref 111 prot 802.1Q \ + flower vlan_id 111 action pass + tc filter add dev $ul2 ingress pref 222 prot 802.1Q \ + flower vlan_id 222 action pass }

sw2_destroy() { + tc qdisc del dev $ul2 clsact + ip route del vrf v$ol2 192.0.2.0/28

ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145 @@ -215,15 +215,15 @@ multipath4_test() nexthop dev g1a weight $weight1 \ nexthop dev g1b weight $weight2

- local t0_111=$(tc_rule_stats_get $ul1 111 egress) - local t0_222=$(tc_rule_stats_get $ul1 222 egress) + local t0_111=$(tc_rule_stats_get $ul2 111 ingress) + local t0_222=$(tc_rule_stats_get $ul2 222 ingress)

ip vrf exec v$h1 \ $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \ -d 1msec -t udp "sp=1024,dp=0-32768"

- local t1_111=$(tc_rule_stats_get $ul1 111 egress) - local t1_222=$(tc_rule_stats_get $ul1 222 egress) + local t1_111=$(tc_rule_stats_get $ul2 111 ingress) + local t1_222=$(tc_rule_stats_get $ul2 222 ingress)

local d111=$((t1_111 - t0_111)) local d222=$((t1_222 - t0_222))

[ Upstream commit 375f755899b8fc21196197e02aab26257df26e85 ]

add error check when workqueue alloc failed, and remove redundant code to make it clear.

Fixes: e0000163e30e ("can: Driver for the Microchip MCP251x SPI CAN controllers") Signed-off-by: Weitao Hou houweitaoo@gmail.com Acked-by: Willem de Bruijn willemb@google.com Tested-by: Sean Nyekjaer sean@geanix.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/can/spi/mcp251x.c | 49 ++++++++++++++++------------------- 1 file changed, 22 insertions(+), 27 deletions(-)

diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index da64e71a62ee2..fccb6bf21fada 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -678,17 +678,6 @@ static int mcp251x_power_enable(struct regulator *reg, int enable) return regulator_disable(reg); }

-static void mcp251x_open_clean(struct net_device *net) -{ - struct mcp251x_priv *priv = netdev_priv(net); - struct spi_device *spi = priv->spi; - - free_irq(spi->irq, priv); - mcp251x_hw_sleep(spi); - mcp251x_power_enable(priv->transceiver, 0); - close_candev(net); -} - static int mcp251x_stop(struct net_device *net) { struct mcp251x_priv *priv = netdev_priv(net); @@ -954,37 +943,43 @@ static int mcp251x_open(struct net_device *net) flags | IRQF_ONESHOT, DEVICE_NAME, priv); if (ret) { dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq); - mcp251x_power_enable(priv->transceiver, 0); - close_candev(net); - goto open_unlock; + goto out_close; }

priv->wq = alloc_workqueue("mcp251x_wq", WQ_FREEZABLE | WQ_MEM_RECLAIM, 0); + if (!priv->wq) { + ret = -ENOMEM; + goto out_clean; + } INIT_WORK(&priv->tx_work, mcp251x_tx_work_handler); INIT_WORK(&priv->restart_work, mcp251x_restart_work_handler);

ret = mcp251x_hw_reset(spi); - if (ret) { - mcp251x_open_clean(net); - goto open_unlock; - } + if (ret) + goto out_free_wq; ret = mcp251x_setup(net, spi); - if (ret) { - mcp251x_open_clean(net); - goto open_unlock; - } + if (ret) + goto out_free_wq; ret = mcp251x_set_normal_mode(spi); - if (ret) { - mcp251x_open_clean(net); - goto open_unlock; - } + if (ret) + goto out_free_wq;

can_led_event(net, CAN_LED_EVENT_OPEN);

netif_wake_queue(net); + mutex_unlock(&priv->mcp_lock);

-open_unlock: + return 0; + +out_free_wq: + destroy_workqueue(priv->wq); +out_clean: + free_irq(spi->irq, priv); + mcp251x_hw_sleep(spi); +out_close: + mcp251x_power_enable(priv->transceiver, 0); + close_candev(net); mutex_unlock(&priv->mcp_lock); return ret; }

[ Upstream commit 40aa5383e393d72f6aa3943a4e7b1aae25a1e43b ]

If the DAI format setup fails, there is no valid communication format between CPU and CODEC, so fail card instantiation, rather than continue with a card that will most likely not function properly.

Signed-off-by: Ricard Wanderlof ricardw@axis.com Link: https://lore.kernel.org/r/alpine.DEB.2.20.1907241132350.6338@lnxricardw1.se.... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/soc-core.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 62aa320c20708..dafc3b7f8d723 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1513,8 +1513,11 @@ static int soc_probe_link_dais(struct snd_soc_card *card, } }

- if (dai_link->dai_fmt) - snd_soc_runtime_set_dai_fmt(rtd, dai_link->dai_fmt); + if (dai_link->dai_fmt) { + ret = snd_soc_runtime_set_dai_fmt(rtd, dai_link->dai_fmt); + if (ret) + return ret; + }

ret = soc_post_component_init(rtd, dai_link->name); if (ret)

[ Upstream commit 3008e06fdf0973770370f97d5f1fba3701d8281d ]

devm_kzalloc may fail and return NULL. So the null check is needed.

Signed-off-by: Navid Emamdoost navid.emamdoost@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nfc/st-nci/se.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index f55d082ace715..5d6e7e931bc6c 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -344,6 +344,8 @@ static int st_nci_hci_connectivity_event_received(struct nci_dev *ndev,

transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev, skb->len - 2, GFP_KERNEL); + if (!transaction) + return -ENOMEM;

transaction->aid_len = skb->data[1]; memcpy(transaction->aid, &skb->data[2], transaction->aid_len);

[ Upstream commit 1e112c35e3c96db7c8ca6ddaa96574f00c06e7db ]

The slot_width is a property for the bus while the constraint for SNDRV_PCM_HW_PARAM_SAMPLE_BITS is for the in memory format.

Applying slot_width constraint to sample_bits works most of the time, but it will blacklist valid formats in some cases.

With slot_width 24 we can support S24_3LE and S24_LE formats as they both look the same on the bus, but a a 24 constraint on sample_bits would not allow S24_LE as it is stored in 32bits in memory.

Implement a simple hw_rule function to allow all formats which require less or equal number of bits on the bus as slot_width (if configured).

Signed-off-by: Peter Ujfalusi peter.ujfalusi@ti.com Link: https://lore.kernel.org/r/20190726064244.3762-2-peter.ujfalusi@ti.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/davinci/davinci-mcasp.c | 43 ++++++++++++++++++++++++------- 1 file changed, 34 insertions(+), 9 deletions(-)

diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c index 160b2764b2ad8..6a8c279a4b20b 100644 --- a/sound/soc/davinci/davinci-mcasp.c +++ b/sound/soc/davinci/davinci-mcasp.c @@ -1150,6 +1150,28 @@ static int davinci_mcasp_trigger(struct snd_pcm_substream *substream, return ret; }

+static int davinci_mcasp_hw_rule_slot_width(struct snd_pcm_hw_params *params, + struct snd_pcm_hw_rule *rule) +{ + struct davinci_mcasp_ruledata *rd = rule->private; + struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT); + struct snd_mask nfmt; + int i, slot_width; + + snd_mask_none(&nfmt); + slot_width = rd->mcasp->slot_width; + + for (i = 0; i <= SNDRV_PCM_FORMAT_LAST; i++) { + if (snd_mask_test(fmt, i)) { + if (snd_pcm_format_width(i) <= slot_width) { + snd_mask_set(&nfmt, i); + } + } + } + + return snd_mask_refine(fmt, &nfmt); +} + static const unsigned int davinci_mcasp_dai_rates[] = { 8000, 11025, 16000, 22050, 32000, 44100, 48000, 64000, 88200, 96000, 176400, 192000, @@ -1257,7 +1279,7 @@ static int davinci_mcasp_startup(struct snd_pcm_substream *substream, struct davinci_mcasp_ruledata *ruledata = &mcasp->ruledata[substream->stream]; u32 max_channels = 0; - int i, dir; + int i, dir, ret; int tdm_slots = mcasp->tdm_slots;

/* Do not allow more then one stream per direction */ @@ -1286,6 +1308,7 @@ static int davinci_mcasp_startup(struct snd_pcm_substream *substream, max_channels++; } ruledata->serializers = max_channels; + ruledata->mcasp = mcasp; max_channels *= tdm_slots; /* * If the already active stream has less channels than the calculated @@ -1311,20 +1334,22 @@ static int davinci_mcasp_startup(struct snd_pcm_substream *substream, 0, SNDRV_PCM_HW_PARAM_CHANNELS, &mcasp->chconstr[substream->stream]);

- if (mcasp->slot_width) - snd_pcm_hw_constraint_minmax(substream->runtime, - SNDRV_PCM_HW_PARAM_SAMPLE_BITS, - 8, mcasp->slot_width); + if (mcasp->slot_width) { + /* Only allow formats require <= slot_width bits on the bus */ + ret = snd_pcm_hw_rule_add(substream->runtime, 0, + SNDRV_PCM_HW_PARAM_FORMAT, + davinci_mcasp_hw_rule_slot_width, + ruledata, + SNDRV_PCM_HW_PARAM_FORMAT, -1); + if (ret) + return ret; + }

/* * If we rely on implicit BCLK divider setting we should * set constraints based on what we can provide. */ if (mcasp->bclk_master && mcasp->bclk_div == 0 && mcasp->sysclk_freq) { - int ret; - - ruledata->mcasp = mcasp; - ret = snd_pcm_hw_rule_add(substream->runtime, 0, SNDRV_PCM_HW_PARAM_RATE, davinci_mcasp_hw_rule_rate,

[ Upstream commit 81af04b432fdfabcdbd2c06be2ee647e3ca41a22 ]

The hw_ver field was initialized to zero. Return the chip revision. This is relevant for rdma driver.

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_rdma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index 13802b825d65a..909422d939033 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -442,7 +442,7 @@ static void qed_rdma_init_devinfo(struct qed_hwfn *p_hwfn, /* Vendor specific information */ dev->vendor_id = cdev->vendor_id; dev->vendor_part_id = cdev->device_id; - dev->hw_ver = 0; + dev->hw_ver = cdev->chip_rev; dev->fw_ver = (FW_MAJOR_VERSION << 24) | (FW_MINOR_VERSION << 16) | (FW_REVISION_VERSION << 8) | (FW_ENGINEERING_VERSION);

[ Upstream commit b55f3b841099e641bdb2701d361a4c304e2dbd6f ]

In hwsim_dump_radio_nl(), when genlmsg_put() on line 3617 fails, hdr is assigned to NULL. Then hdr is used on lines 3622 and 3623: genl_dump_check_consistent(cb, hdr); genlmsg_end(skb, hdr);

Thus, possible null-pointer dereferences may occur.

To fix these bugs, hdr is used here when it is not NULL.

This bug is found by a static analysis tool STCheck written by us.

Signed-off-by: Jia-Ju Bai baijiaju1990@gmail.com Link: https://lore.kernel.org/r/20190729082332.28895-1-baijiaju1990@gmail.com [put braces on all branches] Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/mac80211_hwsim.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 7cd428c0af433..ce2dd06af62e8 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3502,10 +3502,12 @@ static int hwsim_dump_radio_nl(struct sk_buff *skb, hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &hwsim_genl_family, NLM_F_MULTI, HWSIM_CMD_GET_RADIO); - if (!hdr) + if (hdr) { + genl_dump_check_consistent(cb, hdr); + genlmsg_end(skb, hdr); + } else { res = -EMSGSIZE; - genl_dump_check_consistent(cb, hdr); - genlmsg_end(skb, hdr); + } }

done:

[ Upstream commit 1b4a75108d5bc153daf965d334e77e8e94534f96 ]

In commit 8cc4ccf58379 ("ipset: Allow matching on destination MAC address for mac and ipmac sets"), ipset.git commit 1543514c46a7, I added to the KADT functions for sets matching on MAC addreses the copy of source or destination MAC address depending on the configured match.

This was done correctly for hash:mac, but for hash:ip,mac and bitmap:ip,mac, copying and pasting the same code block presents an obvious problem: in these two set types, the MAC address is the second dimension, not the first one, and we are actually selecting the MAC address depending on whether the first dimension (IP address) specifies source or destination.

Fix this by checking for the IPSET_DIM_TWO_SRC flag in option flags.

This way, mixing source and destination matches for the two dimensions of ip,mac set types works as expected. With this setup:

ip netns add A ip link add veth1 type veth peer name veth2 netns A ip addr add 192.0.2.1/24 dev veth1 ip -net A addr add 192.0.2.2/24 dev veth2 ip link set veth1 up ip -net A link set veth2 up

dst=$(ip netns exec A cat /sys/class/net/veth2/address)

ip netns exec A ipset create test_bitmap bitmap:ip,mac range 192.0.0.0/16 ip netns exec A ipset add test_bitmap 192.0.2.1,${dst} ip netns exec A iptables -A INPUT -m set ! --match-set test_bitmap src,dst -j DROP

ip netns exec A ipset create test_hash hash:ip,mac ip netns exec A ipset add test_hash 192.0.2.1,${dst} ip netns exec A iptables -A INPUT -m set ! --match-set test_hash src,dst -j DROP

ipset correctly matches a test packet:

# ping -c1 192.0.2.2 >/dev/null # echo $? 0

Reported-by: Chen Yi yiche@redhat.com Fixes: 8cc4ccf58379 ("ipset: Allow matching on destination MAC address for mac and ipmac sets") Signed-off-by: Stefano Brivio sbrivio@redhat.com Signed-off-by: Jozsef Kadlecsik kadlec@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/ipset/ip_set_bitmap_ipmac.c | 2 +- net/netfilter/ipset/ip_set_hash_ipmac.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 13ade5782847b..4f01321e793ce 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -230,7 +230,7 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb,

e.id = ip_to_id(map, ip);

- if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c index 75c21c8b76514..16ec822e40447 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmac.c +++ b/net/netfilter/ipset/ip_set_hash_ipmac.c @@ -99,7 +99,7 @@ hash_ipmac4_kadt(struct ip_set *set, const struct sk_buff *skb, (skb_mac_header(skb) + ETH_HLEN) > skb->data) return -EINVAL;

- if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest);

[ Upstream commit 60034d3d146b11922ab1db613bce062dddc0327a ]

There is a potential deadlock in rxrpc_peer_keepalive_dispatch() whereby rxrpc_put_peer() is called with the peer_hash_lock held, but if it reduces the peer's refcount to 0, rxrpc_put_peer() calls __rxrpc_put_peer() - which the tries to take the already held lock.

Fix this by providing a version of rxrpc_put_peer() that can be called in situations where the lock is already held.

The bug may produce the following lockdep report:

============================================ WARNING: possible recursive locking detected 5.2.0-next-20190718 #41 Not tainted -------------------------------------------- kworker/0:3/21678 is trying to acquire lock: 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: spin_lock_bh /./include/linux/spinlock.h:343 [inline] 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: __rxrpc_put_peer /net/rxrpc/peer_object.c:415 [inline] 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: rxrpc_put_peer+0x2d3/0x6a0 /net/rxrpc/peer_object.c:435

but task is already holding lock: 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: spin_lock_bh /./include/linux/spinlock.h:343 [inline] 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: rxrpc_peer_keepalive_dispatch /net/rxrpc/peer_event.c:378 [inline] 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: rxrpc_peer_keepalive_worker+0x6b3/0xd02 /net/rxrpc/peer_event.c:430

Fixes: 330bdcfadcee ("rxrpc: Fix the keepalive generator [ver #2]") Reported-by: syzbot+72af434e4b3417318f84@syzkaller.appspotmail.com Signed-off-by: David Howells dhowells@redhat.com Reviewed-by: Marc Dionne marc.dionne@auristor.com Reviewed-by: Jeffrey Altman jaltman@auristor.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/rxrpc/ar-internal.h | 1 + net/rxrpc/peer_event.c | 2 +- net/rxrpc/peer_object.c | 18 ++++++++++++++++++ 3 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 03e0fc8c183f0..a4c341828b72f 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1057,6 +1057,7 @@ void rxrpc_destroy_all_peers(struct rxrpc_net *); struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *); struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *); void rxrpc_put_peer(struct rxrpc_peer *); +void rxrpc_put_peer_locked(struct rxrpc_peer *);

/* * proc.c diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index bd2fa3b7caa7e..dc7fdaf20445b 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -375,7 +375,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, spin_lock_bh(&rxnet->peer_hash_lock); list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive[slot & mask]); - rxrpc_put_peer(peer); + rxrpc_put_peer_locked(peer); }

spin_unlock_bh(&rxnet->peer_hash_lock); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 5691b7d266ca0..71547e8673b99 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -440,6 +440,24 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) } }

+/* + * Drop a ref on a peer record where the caller already holds the + * peer_hash_lock. + */ +void rxrpc_put_peer_locked(struct rxrpc_peer *peer) +{ + const void *here = __builtin_return_address(0); + int n; + + n = atomic_dec_return(&peer->usage); + trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + if (n == 0) { + hash_del_rcu(&peer->hash_link); + list_del_init(&peer->keepalive_link); + kfree_rcu(peer, rcu); + } +} + /* * Make sure all peer records have been discarded. */

[ Upstream commit d8a1de3d5bb881507602bc02e004904828f88711 ]

Since linux 4.9 it is not possible to use buffers on the stack for DMA transfers.

During usb probe the driver crashes with "transfer buffer is on stack" message.

This fix k-allocates a buffer to be used on "read_reg_atomic", which is a macro that calls "usb_control_msg" under the hood.

Kernel 4.19 backtrace:

usb_hcd_submit_urb+0x3e5/0x900 ? sched_clock+0x9/0x10 ? log_store+0x203/0x270 ? get_random_u32+0x6f/0x90 ? cache_alloc_refill+0x784/0x8a0 usb_submit_urb+0x3b4/0x550 usb_start_wait_urb+0x4e/0xd0 usb_control_msg+0xb8/0x120 hfcsusb_probe+0x6bc/0xb40 [hfcsusb] usb_probe_interface+0xc2/0x260 really_probe+0x176/0x280 driver_probe_device+0x49/0x130 __driver_attach+0xa9/0xb0 ? driver_probe_device+0x130/0x130 bus_for_each_dev+0x5a/0x90 driver_attach+0x14/0x20 ? driver_probe_device+0x130/0x130 bus_add_driver+0x157/0x1e0 driver_register+0x51/0xe0 usb_register_driver+0x5d/0x120 ? 0xf81ed000 hfcsusb_drv_init+0x17/0x1000 [hfcsusb] do_one_initcall+0x44/0x190 ? free_unref_page_commit+0x6a/0xd0 do_init_module+0x46/0x1c0 load_module+0x1dc1/0x2400 sys_init_module+0xed/0x120 do_fast_syscall_32+0x7a/0x200 entry_SYSENTER_32+0x6b/0xbe

Signed-off-by: Juliana Rodrigueiro juliana.rodrigueiro@intra2net.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/isdn/hardware/mISDN/hfcsusb.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c index cfdb130cb1008..c952002c6301d 100644 --- a/drivers/isdn/hardware/mISDN/hfcsusb.c +++ b/drivers/isdn/hardware/mISDN/hfcsusb.c @@ -1705,13 +1705,23 @@ hfcsusb_stop_endpoint(struct hfcsusb *hw, int channel) static int setup_hfcsusb(struct hfcsusb *hw) { + void *dmabuf = kmalloc(sizeof(u_char), GFP_KERNEL); u_char b; + int ret;

if (debug & DBG_HFC_CALL_TRACE) printk(KERN_DEBUG "%s: %s\n", hw->name, __func__);

+ if (!dmabuf) + return -ENOMEM; + + ret = read_reg_atomic(hw, HFCUSB_CHIP_ID, dmabuf); + + memcpy(&b, dmabuf, sizeof(u_char)); + kfree(dmabuf); + /* check the chip id */ - if (read_reg_atomic(hw, HFCUSB_CHIP_ID, &b) != 1) { + if (ret != 1) { printk(KERN_DEBUG "%s: %s: cannot read chip id\n", hw->name, __func__); return 1;

[ Upstream commit 6bbfe4e602691b90ac866712bd4c43c51e546a60 ]

Michael reported an issue with perf bench numa failing with binding to cpu0 with '-0' option.

# perf bench numa mem -p 3 -t 1 -P 512 -s 100 -zZcm0 --thp 1 -M 1 -ddd # Running 'numa/mem' benchmark:

# Running main, "perf bench numa numa-mem -p 3 -t 1 -P 512 -s 100 -zZcm0 --thp 1 -M 1 -ddd" binding to node 0, mask: 0000000000000001 => -1 perf: bench/numa.c:356: bind_to_memnode: Assertion `!(ret)' failed. Aborted (core dumped)

This happens when the cpu0 is not part of node0, which is the benchmark assumption and we can see that's not the case for some powerpc servers.

Using correct node for cpu0 binding.

Reported-by: Michael Petlan mpetlan@redhat.com Signed-off-by: Jiri Olsa jolsa@kernel.org Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Andi Kleen ak@linux.intel.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Satheesh Rajendran sathnaga@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/20190801142642.28004-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/bench/numa.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index fa56fde6e8d80..91c0a4434da27 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -378,8 +378,10 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags,

/* Allocate and initialize all memory on CPU#0: */ if (init_cpu0) { - orig_mask = bind_to_node(0); - bind_to_memnode(0); + int node = numa_node_of_cpu(0); + + orig_mask = bind_to_node(node); + bind_to_memnode(node); }

bytes = bytes0 + HPSIZE;

[ Upstream commit e787f19373b8a5fa24087800ed78314fd17b984a ]

strncpy() does not ensure NULL-termination when the input string size equals to the destination buffer size IFNAMSIZ. The output string is passed to dev_info() which relies on the NULL-termination.

Use strlcpy() instead.

This issue is identified by a Coccinelle script.

Signed-off-by: Wang Xiayang xywang.sjtu@sjtu.edu.cn Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/can/usb/peak_usb/pcan_usb_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 740ef47eab017..43b0fa2b99322 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -863,7 +863,7 @@ static void peak_usb_disconnect(struct usb_interface *intf)

dev_prev_siblings = dev->prev_siblings; dev->state &= ~PCAN_USB_STATE_CONNECTED; - strncpy(name, netdev->name, IFNAMSIZ); + strlcpy(name, netdev->name, IFNAMSIZ);

unregister_netdev(netdev);

[ Upstream commit c77e22834ae9a11891cb613bd9a551be1b94f2bc ]

John Hubbard reports seeing the following stack trace:

nfs4_do_reclaim rcu_read_lock /* we are now in_atomic() and must not sleep */ nfs4_purge_state_owners nfs4_free_state_owner nfs4_destroy_seqid_counter rpc_destroy_wait_queue cancel_delayed_work_sync __cancel_work_timer __flush_work start_flush_work might_sleep: (kernel/workqueue.c:2975: BUG)

The solution is to separate out the freeing of the state owners from nfs4_purge_state_owners(), and perform that outside the atomic context.

Reported-by: John Hubbard jhubbard@nvidia.com Fixes: 0aaaf5c424c7f ("NFS: Cache state owners after files are closed") Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/nfs4_fs.h | 3 ++- fs/nfs/nfs4client.c | 5 ++++- fs/nfs/nfs4state.c | 27 ++++++++++++++++++++++----- 3 files changed, 28 insertions(+), 7 deletions(-)

diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 63287d911c088..5b61520dce888 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -469,7 +469,8 @@ static inline void nfs4_schedule_session_recovery(struct nfs4_session *session,

extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *, gfp_t); extern void nfs4_put_state_owner(struct nfs4_state_owner *); -extern void nfs4_purge_state_owners(struct nfs_server *); +extern void nfs4_purge_state_owners(struct nfs_server *, struct list_head *); +extern void nfs4_free_state_owners(struct list_head *head); extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *); extern void nfs4_put_open_state(struct nfs4_state *); extern void nfs4_close_state(struct nfs4_state *, fmode_t); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 8f53455c47653..86991bcfbeb12 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -754,9 +754,12 @@ out:

static void nfs4_destroy_server(struct nfs_server *server) { + LIST_HEAD(freeme); + nfs_server_return_all_delegations(server); unset_pnfs_layoutdriver(server); - nfs4_purge_state_owners(server); + nfs4_purge_state_owners(server, &freeme); + nfs4_free_state_owners(&freeme); }

/* diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 3ba2087469ac8..c36ef75f2054b 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -628,24 +628,39 @@ void nfs4_put_state_owner(struct nfs4_state_owner *sp) /** * nfs4_purge_state_owners - Release all cached state owners * @server: nfs_server with cached state owners to release + * @head: resulting list of state owners * * Called at umount time. Remaining state owners will be on * the LRU with ref count of zero. + * Note that the state owners are not freed, but are added + * to the list @head, which can later be used as an argument + * to nfs4_free_state_owners. */ -void nfs4_purge_state_owners(struct nfs_server *server) +void nfs4_purge_state_owners(struct nfs_server *server, struct list_head *head) { struct nfs_client *clp = server->nfs_client; struct nfs4_state_owner *sp, *tmp; - LIST_HEAD(doomed);

spin_lock(&clp->cl_lock); list_for_each_entry_safe(sp, tmp, &server->state_owners_lru, so_lru) { - list_move(&sp->so_lru, &doomed); + list_move(&sp->so_lru, head); nfs4_remove_state_owner_locked(sp); } spin_unlock(&clp->cl_lock); +}

- list_for_each_entry_safe(sp, tmp, &doomed, so_lru) { +/** + * nfs4_purge_state_owners - Release all cached state owners + * @head: resulting list of state owners + * + * Frees a list of state owners that was generated by + * nfs4_purge_state_owners + */ +void nfs4_free_state_owners(struct list_head *head) +{ + struct nfs4_state_owner *sp, *tmp; + + list_for_each_entry_safe(sp, tmp, head, so_lru) { list_del(&sp->so_lru); nfs4_free_state_owner(sp); } @@ -1843,12 +1858,13 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov struct nfs4_state_owner *sp; struct nfs_server *server; struct rb_node *pos; + LIST_HEAD(freeme); int status = 0;

restart: rcu_read_lock(); list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { - nfs4_purge_state_owners(server); + nfs4_purge_state_owners(server, &freeme); spin_lock(&clp->cl_lock); for (pos = rb_first(&server->state_owners); pos != NULL; @@ -1877,6 +1893,7 @@ restart: spin_unlock(&clp->cl_lock); } rcu_read_unlock(); + nfs4_free_state_owners(&freeme); return 0; }

[ Upstream commit 7bc74853fd61432ec59f812a40425bf6d8c986a4 ]

The Saitek X52 joystick has a pair of axes that are originally (by the Windows driver) used as mouse pointer controls. The corresponding usage->hid values are 0x50024 and 0x50026. Thus they are handled as unknown axes and both get mapped to ABS_MISC. The quirk makes the second axis to be mapped to ABS_MISC1 and thus made available separately.

[jkosina@suse.cz: squashed two patches into one] Signed-off-by: István Váradi ivaradi@varadiistvan.hu Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/hid-ids.h | 1 + drivers/hid/hid-quirks.c | 1 + 2 files changed, 2 insertions(+)

diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 2898bb0619454..4a2fa57ddcb84 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -971,6 +971,7 @@ #define USB_DEVICE_ID_SAITEK_RAT7 0x0cd7 #define USB_DEVICE_ID_SAITEK_RAT9 0x0cfa #define USB_DEVICE_ID_SAITEK_MMO7 0x0cd0 +#define USB_DEVICE_ID_SAITEK_X52 0x075c

#define USB_VENDOR_ID_SAMSUNG 0x0419 #define USB_DEVICE_ID_SAMSUNG_IR_REMOTE 0x0001 diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index d29c7c9cd185d..e553f6fae7a4c 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -143,6 +143,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPAD), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPORT), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RUMBLEPAD), HID_QUIRK_BADPAD }, + { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SENNHEISER, USB_DEVICE_ID_SENNHEISER_BTD500USB), HID_QUIRK_NOGET },

[ Upstream commit f7ccbed656f78212593ca965d9a8f34bf24e0aab ]

In commit fe64ba5c6323 ("drm/rockchip: Resume DP early") we moved resume to be early but left suspend at its normal time. This seems like it could be OK, but casues problems if a suspend gets interrupted partway through. The OS only balances matching suspend/resume levels. ...so if suspend was called then resume will be called. If suspend late was called then resume early will be called. ...but if suspend was called resume early might not get called. This leads to an unbalance in the clock enables / disables.

Lets take the simple fix and just move suspend to be late to match. This makes the PM core take proper care in keeping things balanced.

Fixes: fe64ba5c6323 ("drm/rockchip: Resume DP early") Signed-off-by: Douglas Anderson dianders@chromium.org Signed-off-by: Sean Paul seanpaul@chromium.org Link: https://patchwork.freedesktop.org/patch/msgid/20190802184616.44822-1-diander... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/rockchip/analogix_dp-rockchip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c index 080f053521950..6a4da3a0ff1c3 100644 --- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c +++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c @@ -436,7 +436,7 @@ static int rockchip_dp_resume(struct device *dev)

static const struct dev_pm_ops rockchip_dp_pm_ops = { #ifdef CONFIG_PM_SLEEP - .suspend = rockchip_dp_suspend, + .suspend_late = rockchip_dp_suspend, .resume_early = rockchip_dp_resume, #endif };

[ Upstream commit ee9d66182392695535cc9fccfcb40c16f72de2a9 ]

Fix kernel oops when mounting a encryptData CIFS share with CONFIG_DEBUG_VIRTUAL

Signed-off-by: Sebastien Tisserant stisserant@wallix.com Reviewed-by: Pavel Shilovsky pshilov@microsoft.com Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cifs/smb2ops.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 97fdbec54db97..cc9e846a38658 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2545,7 +2545,15 @@ fill_transform_hdr(struct smb2_transform_hdr *tr_hdr, unsigned int orig_len, static inline void smb2_sg_set_buf(struct scatterlist *sg, const void *buf, unsigned int buflen) { - sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf)); + void *addr; + /* + * VMAP_STACK (at least) puts stack into the vmalloc address space + */ + if (is_vmalloc_addr(buf)) + addr = vmalloc_to_page(buf); + else + addr = virt_to_page(buf); + sg_set_page(sg, addr, buflen, offset_in_page(buf)); }

/* Assumes the first rqst has a transform header as the first iov.

[ Upstream commit debea2cd3193ac868289e8893c3a719c265b0612 ]

A call to 'kfree_skb()' is missing in the error handling path of 'init_one()'. This is already present in 'remove_one()' but is missing here.

Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index c34ea385fe4a5..6be6de0774b61 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -3270,7 +3270,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (!adapter->regs) { dev_err(&pdev->dev, "cannot map device registers\n"); err = -ENOMEM; - goto out_free_adapter; + goto out_free_adapter_nofail; }

adapter->pdev = pdev; @@ -3398,6 +3398,9 @@ out_free_dev: if (adapter->port[i]) free_netdev(adapter->port[i]);

+out_free_adapter_nofail: + kfree_skb(adapter->nofail_skb); + out_free_adapter: kfree(adapter);

[ Upstream commit 4a6a1385a4db5f42258a40fcd497cbfd22075968 ]

Do not try to return a fragment entry from TC list. Otherwise we may not clean properly allocated entries.

Signed-off-by: Jose Abreu joabreu@synopsys.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 58ea18af9813a..37c0bc699cd9c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -37,7 +37,7 @@ static struct stmmac_tc_entry *tc_find_entry(struct stmmac_priv *priv, entry = &priv->tc_entries[i]; if (!entry->in_use && !first && free) first = entry; - if (entry->handle == loc && !free) + if ((entry->handle == loc) && !free && !entry->is_frag) dup = entry; }

[ Upstream commit f2243b82785942be519016067ee6c55a063bbfe2 ]

TX_DESC_NUM is 256, in tx_count, the maximum value of mod(TX_DESC_NUM - 1) is 254, the variable "count" in the hip04_mac_start_xmit function is never equal to (TX_DESC_NUM - 1), so hip04_mac_start_xmit never return NETDEV_TX_BUSY.

tx_count is modified to mod(TX_DESC_NUM) so that the maximum value of tx_count can reach (TX_DESC_NUM - 1), then hip04_mac_start_xmit can reurn NETDEV_TX_BUSY.

Signed-off-by: Jiangfeng Xiao xiaojiangfeng@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/hisilicon/hip04_eth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 57c0afa25f9fb..fe3b1637fd5f4 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -185,7 +185,7 @@ struct hip04_priv {

static inline unsigned int tx_count(unsigned int head, unsigned int tail) { - return (head - tail) % (TX_DESC_NUM - 1); + return (head - tail) % TX_DESC_NUM; }

static void hip04_config_port(struct net_device *ndev, u32 speed, u32 duplex)

[ Upstream commit 2d7271501720038381d45fb3dcbe4831228fc8cc ]

For passthrough requests, libata-scsi takes what the user passes in as gospel. This can be problematic if the user fills in the CDB incorrectly. One example of that is in request sizes. For read/write commands, the CDB contains fields describing the transfer length of the request. These should match with the SG_IO header fields, but libata-scsi currently does no validation of that.

Check that the number of blocks in the CDB for passthrough requests matches what was mapped into the request. If the CDB asks for more data then the validated SG_IO header fields, error it.

Reported-by: Krishna Ram Prakash R krp@gtux.in Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/ata/libata-scsi.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+)

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 1984fc78c750b..3a64fa4aaf7e3 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1803,6 +1803,21 @@ nothing_to_do: return 1; }

+static bool ata_check_nblocks(struct scsi_cmnd *scmd, u32 n_blocks) +{ + struct request *rq = scmd->request; + u32 req_blocks; + + if (!blk_rq_is_passthrough(rq)) + return true; + + req_blocks = blk_rq_bytes(rq) / scmd->device->sector_size; + if (n_blocks > req_blocks) + return false; + + return true; +} + /** * ata_scsi_rw_xlat - Translate SCSI r/w command into an ATA one * @qc: Storage for translated ATA taskfile @@ -1847,6 +1862,8 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc) scsi_10_lba_len(cdb, &block, &n_block); if (cdb[1] & (1 << 3)) tf_flags |= ATA_TFLAG_FUA; + if (!ata_check_nblocks(scmd, n_block)) + goto invalid_fld; break; case READ_6: case WRITE_6: @@ -1861,6 +1878,8 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc) */ if (!n_block) n_block = 256; + if (!ata_check_nblocks(scmd, n_block)) + goto invalid_fld; break; case READ_16: case WRITE_16: @@ -1871,6 +1890,8 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc) scsi_16_lba_len(cdb, &block, &n_block); if (cdb[1] & (1 << 3)) tf_flags |= ATA_TFLAG_FUA; + if (!ata_check_nblocks(scmd, n_block)) + goto invalid_fld; break; default: DPRINTK("no-byte command\n");

[ Upstream commit 04f5bda84b0712d6f172556a7e8dca9ded5e73b9 ]

When building with W=1, warnings about missing prototypes are emitted:

CC arch/x86/lib/cpu.o arch/x86/lib/cpu.c:5:14: warning: no previous prototype for 'x86_family' [-Wmissing-prototypes] 5 | unsigned int x86_family(unsigned int sig) | ^~~~~~~~~~ arch/x86/lib/cpu.c:18:14: warning: no previous prototype for 'x86_model' [-Wmissing-prototypes] 18 | unsigned int x86_model(unsigned int sig) | ^~~~~~~~~ arch/x86/lib/cpu.c:33:14: warning: no previous prototype for 'x86_stepping' [-Wmissing-prototypes] 33 | unsigned int x86_stepping(unsigned int sig) | ^~~~~~~~~~~~

Add the proper include file so the prototypes are there.

Signed-off-by: Valdis Kletnieks valdis.kletnieks@vt.edu Signed-off-by: Thomas Gleixner tglx@linutronix.de Link: https://lkml.kernel.org/r/42513.1565234837@turing-police Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/lib/cpu.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c index 2dd1fe13a37b3..19f707992db22 100644 --- a/arch/x86/lib/cpu.c +++ b/arch/x86/lib/cpu.c @@ -1,5 +1,6 @@ #include <linux/types.h> #include <linux/export.h> +#include <asm/cpu.h>

unsigned int x86_family(unsigned int sig) {

[ Upstream commit fd03177c33b287c6541f4048f1d67b7b45a1abc9 ]

As reported in [1], the call bfq_init_rq(rq) may return NULL in case of OOM (in particular, if rq->elv.icq is NULL because memory allocation failed in failed in ioc_create_icq()).

This commit handles this circumstance.

[1] https://lkml.org/lkml/2019/7/22/824

Cc: Hsin-Yi Wang hsinyi@google.com Cc: Nicolas Boichat drinkcat@chromium.org Cc: Doug Anderson dianders@chromium.org Reported-by: Guenter Roeck linux@roeck-us.net Reported-by: Hsin-Yi Wang hsinyi@google.com Reviewed-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Paolo Valente paolo.valente@linaro.org Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/bfq-iosched.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index becd793a258c8..d8d2ac294b0c0 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -1886,9 +1886,14 @@ static void bfq_request_merged(struct request_queue *q, struct request *req, blk_rq_pos(container_of(rb_prev(&req->rb_node), struct request, rb_node))) { struct bfq_queue *bfqq = bfq_init_rq(req); - struct bfq_data *bfqd = bfqq->bfqd; + struct bfq_data *bfqd; struct request *prev, *next_rq;

+ if (!bfqq) + return; + + bfqd = bfqq->bfqd; + /* Reposition request in its sort_list */ elv_rb_del(&bfqq->sort_list, req); elv_rb_add(&bfqq->sort_list, req); @@ -1930,6 +1935,9 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq, struct bfq_queue *bfqq = bfq_init_rq(rq), *next_bfqq = bfq_init_rq(next);

+ if (!bfqq) + return; + /* * If next and rq belong to the same bfq_queue and next is older * than rq, then reposition rq in the fifo (by substituting next @@ -4590,12 +4598,12 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,

spin_lock_irq(&bfqd->lock); bfqq = bfq_init_rq(rq); - if (at_head || blk_rq_is_passthrough(rq)) { + if (!bfqq || at_head || blk_rq_is_passthrough(rq)) { if (at_head) list_add(&rq->queuelist, &bfqd->dispatch); else list_add_tail(&rq->queuelist, &bfqd->dispatch); - } else { /* bfqq is assumed to be non null here */ + } else { idle_timer_disabled = __bfq_insert_request(bfqd, rq); /* * Update bfqq, because, if a queue merge has occurred

[ Upstream commit 5f5e25f1c7933a6e1673515c0b1d5acd82fea1ed ]

cpu_map__snprint_mask() would write to illegal memory pointed by zalloc(0) when there is only one cpu.

This patch fixes the calculation and adds sanity check against the input parameters.

Signed-off-by: He Zhe zhe.he@windriver.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Alexey Budankov alexey.budankov@linux.intel.com Cc: Jiri Olsa jolsa@redhat.com Cc: Kan Liang kan.liang@linux.intel.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Fixes: 4400ac8a9a90 ("perf cpumap: Introduce cpu_map__snprint_mask()") Link: http://lkml.kernel.org/r/1564734592-15624-2-git-send-email-zhe.he@windriver.... Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/util/cpumap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 383674f448fcd..f93846edc1e0d 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -701,7 +701,10 @@ size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size) unsigned char *bitmap; int last_cpu = cpu_map__cpu(map, map->nr - 1);

- bitmap = zalloc((last_cpu + 7) / 8); + if (buf == NULL) + return 0; + + bitmap = zalloc(last_cpu / 8 + 1); if (bitmap == NULL) { buf[0] = '\0'; return 0;

[ Upstream commit 03fdfb2690099c19160a3f2c5b77db60b3afeded ]

At the moment, the way we reset system registers is mildly insane: We write junk to them, call the reset functions, and then check that we have something else in them.

The "fun" thing is that this can happen while the guest is running (PSCI, for example). If anything in KVM has to evaluate the state of a system register while junk is in there, bad thing may happen.

Let's stop doing that. Instead, we track that we have called a reset function for that register, and assume that the reset function has done something. This requires fixing a couple of sysreg refinition in the trap table.

In the end, the very need of this reset check is pretty dubious, as it doesn't check everything (a lot of the sysregs leave outside of the sys_regs[] array). It may well be axed in the near future.

Tested-by: Zenghui Yu yuzenghui@huawei.com Signed-off-by: Marc Zyngier maz@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/kvm/sys_regs.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index d112af75680bb..6da2bbdb9648f 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -626,7 +626,7 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) */ val = ((pmcr & ~ARMV8_PMU_PMCR_MASK) | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E); - __vcpu_sys_reg(vcpu, PMCR_EL0) = val; + __vcpu_sys_reg(vcpu, r->reg) = val; }

static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags) @@ -968,13 +968,13 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */ #define DBG_BCR_BVR_WCR_WVR_EL1(n) \ { SYS_DESC(SYS_DBGBVRn_EL1(n)), \ - trap_bvr, reset_bvr, n, 0, get_bvr, set_bvr }, \ + trap_bvr, reset_bvr, 0, 0, get_bvr, set_bvr }, \ { SYS_DESC(SYS_DBGBCRn_EL1(n)), \ - trap_bcr, reset_bcr, n, 0, get_bcr, set_bcr }, \ + trap_bcr, reset_bcr, 0, 0, get_bcr, set_bcr }, \ { SYS_DESC(SYS_DBGWVRn_EL1(n)), \ - trap_wvr, reset_wvr, n, 0, get_wvr, set_wvr }, \ + trap_wvr, reset_wvr, 0, 0, get_wvr, set_wvr }, \ { SYS_DESC(SYS_DBGWCRn_EL1(n)), \ - trap_wcr, reset_wcr, n, 0, get_wcr, set_wcr } + trap_wcr, reset_wcr, 0, 0, get_wcr, set_wcr }

/* Macro to expand the PMEVCNTRn_EL0 register */ #define PMU_PMEVCNTR_EL0(n) \ @@ -1359,7 +1359,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {

{ SYS_DESC(SYS_CSSELR_EL1), NULL, reset_unknown, CSSELR_EL1 },

- { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, }, + { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, PMCR_EL0 }, { SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 }, { SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, NULL, PMCNTENSET_EL0 }, { SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, NULL, PMOVSSET_EL0 }, @@ -2072,13 +2072,19 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu, }

static void reset_sys_reg_descs(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *table, size_t num) + const struct sys_reg_desc *table, size_t num, + unsigned long *bmap) { unsigned long i;

for (i = 0; i < num; i++) - if (table[i].reset) + if (table[i].reset) { + int reg = table[i].reg; + table[i].reset(vcpu, &table[i]); + if (reg > 0 && reg < NR_SYS_REGS) + set_bit(reg, bmap); + } }

/** @@ -2576,18 +2582,16 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu) { size_t num; const struct sys_reg_desc *table; - - /* Catch someone adding a register without putting in reset entry. */ - memset(&vcpu->arch.ctxt.sys_regs, 0x42, sizeof(vcpu->arch.ctxt.sys_regs)); + DECLARE_BITMAP(bmap, NR_SYS_REGS) = { 0, };

/* Generic chip reset first (so target could override). */ - reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); + reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs), bmap);

table = get_target_table(vcpu->arch.target, true, &num); - reset_sys_reg_descs(vcpu, table, num); + reset_sys_reg_descs(vcpu, table, num, bmap);

for (num = 1; num < NR_SYS_REGS; num++) { - if (WARN(__vcpu_sys_reg(vcpu, num) == 0x4242424242424242, + if (WARN(!test_bit(num, bmap), "Didn't reset __vcpu_sys_reg(%zi)\n", num)) break; }

[ Upstream commit c096397c78f766db972f923433031f2dec01cae0 ]

selftests kvm test cases need pre-required kernel configs for the test to get pass.

Signed-off-by: Naresh Kamboju naresh.kamboju@linaro.org Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/kvm/config | 3 +++ 1 file changed, 3 insertions(+) create mode 100644 tools/testing/selftests/kvm/config

diff --git a/tools/testing/selftests/kvm/config b/tools/testing/selftests/kvm/config new file mode 100644 index 0000000000000..63ed533f73d6e --- /dev/null +++ b/tools/testing/selftests/kvm/config @@ -0,0 +1,3 @@ +CONFIG_KVM=y +CONFIG_KVM_INTEL=y +CONFIG_KVM_AMD=y

From: Jason Gerecke jason.gerecke@wacom.com

commit b72fb1dcd2ea9d29417711cb302cef3006fa8d5a upstream.

Distance values reported by 2nd-gen Intuos tablets are on an inverted scale (0 == far, 63 == near). We need to change them over to a normal scale before reporting to userspace or else userspace drivers and applications can get confused.

Ref: https://github.com/linuxwacom/input-wacom/issues/98 Fixes: eda01dab53 ("HID: wacom: Add four new Intuos devices") Signed-off-by: Jason Gerecke jason.gerecke@wacom.com Cc: stable@vger.kernel.org # v4.4+ Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/hid/wacom_wac.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -848,6 +848,8 @@ static int wacom_intuos_general(struct w y >>= 1; distance >>= 1; } + if (features->type == INTUOSHT2) + distance = features->distance_max - distance; input_report_abs(input, ABS_X, x); input_report_abs(input, ABS_Y, y); input_report_abs(input, ABS_DISTANCE, distance);

From: Dinh Nguyen dinguyen@kernel.org

commit c7ec75ea4d5316518adc87224e3cff47192579e7 upstream.

Checking bypass_reg is incorrect for calculating the cnt_clk rates. Instead we should be checking that there is a proper hardware register that holds the clock divider.

Cc: stable@vger.kernel.org Signed-off-by: Dinh Nguyen dinguyen@kernel.org Link: https://lkml.kernel.org/r/20190814153014.12962-1-dinguyen@kernel.org Signed-off-by: Stephen Boyd sboyd@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/clk/socfpga/clk-periph-s10.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/clk/socfpga/clk-periph-s10.c +++ b/drivers/clk/socfpga/clk-periph-s10.c @@ -37,7 +37,7 @@ static unsigned long clk_peri_cnt_clk_re if (socfpgaclk->fixed_div) { div = socfpgaclk->fixed_div; } else { - if (!socfpgaclk->bypass_reg) + if (socfpgaclk->hw.reg) div = ((readl(socfpgaclk->hw.reg) & 0x7ff) + 1); }

From: Jeff Layton jlayton@kernel.org

commit 28a282616f56990547b9dcd5c6fbd2001344664c upstream.

When ceph_mdsc_do_request returns an error, we can't assume that the filelock_reply pointer will be set. Only try to fetch fields out of the r_reply_info when it returns success.

Cc: stable@vger.kernel.org Reported-by: Hector Martin hector@marcansoft.com Signed-off-by: Jeff Layton jlayton@kernel.org Reviewed-by: "Yan, Zheng" zyan@redhat.com Signed-off-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/ceph/locks.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -111,8 +111,7 @@ static int ceph_lock_message(u8 lock_typ req->r_wait_for_completion = ceph_lock_wait_for_completion;

err = ceph_mdsc_do_request(mdsc, inode, req); - - if (operation == CEPH_MDS_OP_GETFILELOCK) { + if (!err && operation == CEPH_MDS_OP_GETFILELOCK) { fl->fl_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid); if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type) fl->fl_type = F_RDLCK;

From: Lyude Paul lyude@redhat.com

commit c358ebf59634f06d8ed176da651ec150df3c8686 upstream.

While I had thought I had fixed this issue in:

commit 342406e4fbba ("drm/nouveau/i2c: Disable i2c bus access after ->fini()")

It turns out that while I did fix the error messages I was seeing on my P50 when trying to access i2c busses with the GPU in runtime suspend, I accidentally had missed one important detail that was mentioned on the bug report this commit was supposed to fix: that the CPU would only lock up when trying to access i2c busses _on connected devices_ _while the GPU is not in runtime suspend_. Whoops. That definitely explains why I was not able to get my machine to hang with i2c bus interactions until now, as plugging my P50 into it's dock with an HDMI monitor connected allowed me to finally reproduce this locally.

Now that I have managed to reproduce this issue properly, it looks like the problem is much simpler then it looks. It turns out that some connected devices, such as MST laptop docks, will actually ACK i2c reads even if no data was actually read:

[ 275.063043] nouveau 0000:01:00.0: i2c: aux 000a: 1: 0000004c 1 [ 275.063447] nouveau 0000:01:00.0: i2c: aux 000a: 00 01101000 10040000 [ 275.063759] nouveau 0000:01:00.0: i2c: aux 000a: rd 00000001 [ 275.064024] nouveau 0000:01:00.0: i2c: aux 000a: rd 00000000 [ 275.064285] nouveau 0000:01:00.0: i2c: aux 000a: rd 00000000 [ 275.064594] nouveau 0000:01:00.0: i2c: aux 000a: rd 00000000

Because we don't handle the situation of i2c ack without any data, we end up entering an infinite loop in nvkm_i2c_aux_i2c_xfer() since the value of cnt always remains at 0. This finally properly explains how this could result in a CPU hang like the ones observed in the aforementioned commit.

So, fix this by retrying transactions if no data is written or received, and give up and fail the transaction if we continue to not write or receive any data after 32 retries.

Signed-off-by: Lyude Paul lyude@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Ben Skeggs bskeggs@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-)

--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c @@ -40,8 +40,7 @@ nvkm_i2c_aux_i2c_xfer(struct i2c_adapter u8 *ptr = msg->buf;

while (remaining) { - u8 cnt = (remaining > 16) ? 16 : remaining; - u8 cmd; + u8 cnt, retries, cmd;

if (msg->flags & I2C_M_RD) cmd = 1; @@ -51,10 +50,19 @@ nvkm_i2c_aux_i2c_xfer(struct i2c_adapter if (mcnt || remaining > 16) cmd |= 4; /* MOT */

- ret = aux->func->xfer(aux, true, cmd, msg->addr, ptr, &cnt); - if (ret < 0) { - nvkm_i2c_aux_release(aux); - return ret; + for (retries = 0, cnt = 0; + retries < 32 && !cnt; + retries++) { + cnt = min_t(u8, remaining, 16); + ret = aux->func->xfer(aux, true, cmd, + msg->addr, ptr, &cnt); + if (ret < 0) + goto out; + } + if (!cnt) { + AUX_TRACE(aux, "no data after 32 retries"); + ret = -EIO; + goto out; }

ptr += cnt; @@ -64,8 +72,10 @@ nvkm_i2c_aux_i2c_xfer(struct i2c_adapter msg++; }

+ ret = num; +out: nvkm_i2c_aux_release(aux); - return num; + return ret; }

static u32

From: Dexuan Cui decui@microsoft.com

commit a9fc4340aee041dd186d1fb8f1b5d1e9caf28212 upstream.

In the case of X86_PAE, unsigned long is u32, but the physical address type should be u64. Due to the bug here, the netvsc driver can not load successfully, and sometimes the VM can panic due to memory corruption (the hypervisor writes data to the wrong location).

Fixes: 6ba34171bcbd ("Drivers: hv: vmbus: Remove use of slow_virt_to_phys()") Cc: stable@vger.kernel.org Cc: Michael Kelley mikelley@microsoft.com Reported-and-tested-by: Juliana Rodrigueiro juliana.rodrigueiro@intra2net.com Signed-off-by: Dexuan Cui decui@microsoft.com Reviewed-by: Michael Kelley mikelley@microsoft.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/hv/channel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -38,7 +38,7 @@

static unsigned long virt_to_hvpfn(void *addr) { - unsigned long paddr; + phys_addr_t paddr;

if (is_vmalloc_addr(addr)) paddr = page_to_phys(vmalloc_to_page(addr)) +

From: Sean Christopherson sean.j.christopherson@intel.com

commit b63f20a778c88b6a04458ed6ffc69da953d3a109 upstream.

Use 'lea' instead of 'add' when adjusting %rsp in CALL_NOSPEC so as to avoid clobbering flags.

KVM's emulator makes indirect calls into a jump table of sorts, where the destination of the CALL_NOSPEC is a small blob of code that performs fast emulation by executing the target instruction with fixed operands.

adcb_al_dl: 0x000339f8 <+0>: adc %dl,%al 0x000339fa <+2>: ret

A major motiviation for doing fast emulation is to leverage the CPU to handle consumption and manipulation of arithmetic flags, i.e. RFLAGS is both an input and output to the target of CALL_NOSPEC. Clobbering flags results in all sorts of incorrect emulation, e.g. Jcc instructions often take the wrong path. Sans the nops...

asm("push %[flags]; popf; " CALL_NOSPEC " ; pushf; pop %[flags]\n" 0x0003595a <+58>: mov 0xc0(%ebx),%eax 0x00035960 <+64>: mov 0x60(%ebx),%edx 0x00035963 <+67>: mov 0x90(%ebx),%ecx 0x00035969 <+73>: push %edi 0x0003596a <+74>: popf 0x0003596b <+75>: call *%esi 0x000359a0 <+128>: pushf 0x000359a1 <+129>: pop %edi 0x000359a2 <+130>: mov %eax,0xc0(%ebx) 0x000359b1 <+145>: mov %edx,0x60(%ebx)

ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); 0x000359a8 <+136>: mov -0x10(%ebp),%eax 0x000359ab <+139>: and $0x8d5,%edi 0x000359b4 <+148>: and $0xfffff72a,%eax 0x000359b9 <+153>: or %eax,%edi 0x000359bd <+157>: mov %edi,0x4(%ebx)

For the most part this has gone unnoticed as emulation of guest code that can trigger fast emulation is effectively limited to MMIO when running on modern hardware, and MMIO is rarely, if ever, accessed by instructions that affect or consume flags.

Breakage is almost instantaneous when running with unrestricted guest disabled, in which case KVM must emulate all instructions when the guest has invalid state, e.g. when the guest is in Big Real Mode during early BIOS.

Fixes: 776b043848fd2 ("x86/retpoline: Add initial retpoline support") Fixes: 1a29b5b7f347a ("KVM: x86: Make indirect calls in emulator speculation safe") Signed-off-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190822211122.27579-1-sean.j.christopherson@intel... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/include/asm/nospec-branch.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -202,7 +202,7 @@ " lfence;\n" \ " jmp 902b;\n" \ " .align 16\n" \ - "903: addl $4, %%esp;\n" \ + "903: lea 4(%%esp), %%esp;\n" \ " pushl %[thunk_target];\n" \ " ret;\n" \ " .align 16\n" \

From: Tom Lendacky thomas.lendacky@amd.com

commit c49a0a80137c7ca7d6ced4c812c9e07a949f6f24 upstream.

There have been reports of RDRAND issues after resuming from suspend on some AMD family 15h and family 16h systems. This issue stems from a BIOS not performing the proper steps during resume to ensure RDRAND continues to function properly.

RDRAND support is indicated by CPUID Fn00000001_ECX[30]. This bit can be reset by clearing MSR C001_1004[62]. Any software that checks for RDRAND support using CPUID, including the kernel, will believe that RDRAND is not supported.

Update the CPU initialization to clear the RDRAND CPUID bit for any family 15h and 16h processor that supports RDRAND. If it is known that the family 15h or family 16h system does not have an RDRAND resume issue or that the system will not be placed in suspend, the "rdrand=force" kernel parameter can be used to stop the clearing of the RDRAND CPUID bit.

Additionally, update the suspend and resume path to save and restore the MSR C001_1004 value to ensure that the RDRAND CPUID setting remains in place after resuming from suspend.

Note, that clearing the RDRAND CPUID bit does not prevent a processor that normally supports the RDRAND instruction from executing it. So any code that determined the support based on family and model won't #UD.

Signed-off-by: Tom Lendacky thomas.lendacky@amd.com Signed-off-by: Borislav Petkov bp@suse.de Cc: Andrew Cooper andrew.cooper3@citrix.com Cc: Andrew Morton akpm@linux-foundation.org Cc: Chen Yu yu.c.chen@intel.com Cc: "H. Peter Anvin" hpa@zytor.com Cc: Ingo Molnar mingo@redhat.com Cc: Jonathan Corbet corbet@lwn.net Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: Juergen Gross jgross@suse.com Cc: Kees Cook keescook@chromium.org Cc: "linux-doc@vger.kernel.org" linux-doc@vger.kernel.org Cc: "linux-pm@vger.kernel.org" linux-pm@vger.kernel.org Cc: Nathan Chancellor natechancellor@gmail.com Cc: Paolo Bonzini pbonzini@redhat.com Cc: Pavel Machek pavel@ucw.cz Cc: "Rafael J. Wysocki" rjw@rjwysocki.net Cc: stable@vger.kernel.org Cc: Thomas Gleixner tglx@linutronix.de Cc: "x86@kernel.org" x86@kernel.org Link: https://lkml.kernel.org/r/7543af91666f491547bd86cebb1e17c66824ab9f.156622994... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- Documentation/admin-guide/kernel-parameters.txt | 7 + arch/x86/include/asm/msr-index.h | 1 arch/x86/kernel/cpu/amd.c | 66 ++++++++++++++++++ arch/x86/power/cpu.c | 86 ++++++++++++++++++++---- 4 files changed, 147 insertions(+), 13 deletions(-)

--- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3948,6 +3948,13 @@ Run specified binary instead of /init from the ramdisk, used for early userspace startup. See initrd.

+ rdrand= [X86] + force - Override the decision by the kernel to hide the + advertisement of RDRAND support (this affects + certain AMD processors because of buggy BIOS + support, specifically around the suspend/resume + path). + rdt= [HW,X86,RDT] Turn on/off individual RDT features. List is: cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp, --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -334,6 +334,7 @@ #define MSR_AMD64_PATCH_LEVEL 0x0000008b #define MSR_AMD64_TSC_RATIO 0xc0000104 #define MSR_AMD64_NB_CFG 0xc001001f +#define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_PATCH_LOADER 0xc0010020 #define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 #define MSR_AMD64_OSVW_STATUS 0xc0010141 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -799,6 +799,64 @@ static void init_amd_ln(struct cpuinfo_x msr_set_bit(MSR_AMD64_DE_CFG, 31); }

+static bool rdrand_force; + +static int __init rdrand_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "force")) + rdrand_force = true; + else + return -EINVAL; + + return 0; +} +early_param("rdrand", rdrand_cmdline); + +static void clear_rdrand_cpuid_bit(struct cpuinfo_x86 *c) +{ + /* + * Saving of the MSR used to hide the RDRAND support during + * suspend/resume is done by arch/x86/power/cpu.c, which is + * dependent on CONFIG_PM_SLEEP. + */ + if (!IS_ENABLED(CONFIG_PM_SLEEP)) + return; + + /* + * The nordrand option can clear X86_FEATURE_RDRAND, so check for + * RDRAND support using the CPUID function directly. + */ + if (!(cpuid_ecx(1) & BIT(30)) || rdrand_force) + return; + + msr_clear_bit(MSR_AMD64_CPUID_FN_1, 62); + + /* + * Verify that the CPUID change has occurred in case the kernel is + * running virtualized and the hypervisor doesn't support the MSR. + */ + if (cpuid_ecx(1) & BIT(30)) { + pr_info_once("BIOS may not properly restore RDRAND after suspend, but hypervisor does not support hiding RDRAND via CPUID.\n"); + return; + } + + clear_cpu_cap(c, X86_FEATURE_RDRAND); + pr_info_once("BIOS may not properly restore RDRAND after suspend, hiding RDRAND via CPUID. Use rdrand=force to reenable.\n"); +} + +static void init_amd_jg(struct cpuinfo_x86 *c) +{ + /* + * Some BIOS implementations do not restore proper RDRAND support + * across suspend and resume. Check on whether to hide the RDRAND + * instruction support via CPUID. + */ + clear_rdrand_cpuid_bit(c); +} + static void init_amd_bd(struct cpuinfo_x86 *c) { u64 value; @@ -813,6 +871,13 @@ static void init_amd_bd(struct cpuinfo_x wrmsrl_safe(MSR_F15H_IC_CFG, value); } } + + /* + * Some BIOS implementations do not restore proper RDRAND support + * across suspend and resume. Check on whether to hide the RDRAND + * instruction support via CPUID. + */ + clear_rdrand_cpuid_bit(c); }

static void init_amd_zn(struct cpuinfo_x86 *c) @@ -855,6 +920,7 @@ static void init_amd(struct cpuinfo_x86 case 0x10: init_amd_gh(c); break; case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; + case 0x16: init_amd_jg(c); break; case 0x17: init_amd_zn(c); break; }

--- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -13,6 +13,7 @@ #include <linux/smp.h> #include <linux/perf_event.h> #include <linux/tboot.h> +#include <linux/dmi.h>

#include <asm/pgtable.h> #include <asm/proto.h> @@ -24,7 +25,7 @@ #include <asm/debugreg.h> #include <asm/cpu.h> #include <asm/mmu_context.h> -#include <linux/dmi.h> +#include <asm/cpu_device_id.h>

#ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -398,15 +399,14 @@ static int __init bsp_pm_check_init(void

core_initcall(bsp_pm_check_init);

-static int msr_init_context(const u32 *msr_id, const int total_num) +static int msr_build_context(const u32 *msr_id, const int num) { - int i = 0; + struct saved_msrs *saved_msrs = &saved_context.saved_msrs; struct saved_msr *msr_array; + int total_num; + int i, j;

- if (saved_context.saved_msrs.array || saved_context.saved_msrs.num > 0) { - pr_err("x86/pm: MSR quirk already applied, please check your DMI match table.\n"); - return -EINVAL; - } + total_num = saved_msrs->num + num;

msr_array = kmalloc_array(total_num, sizeof(struct saved_msr), GFP_KERNEL); if (!msr_array) { @@ -414,19 +414,30 @@ static int msr_init_context(const u32 *m return -ENOMEM; }

- for (i = 0; i < total_num; i++) { - msr_array[i].info.msr_no = msr_id[i]; + if (saved_msrs->array) { + /* + * Multiple callbacks can invoke this function, so copy any + * MSR save requests from previous invocations. + */ + memcpy(msr_array, saved_msrs->array, + sizeof(struct saved_msr) * saved_msrs->num); + + kfree(saved_msrs->array); + } + + for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) { + msr_array[i].info.msr_no = msr_id[j]; msr_array[i].valid = false; msr_array[i].info.reg.q = 0; } - saved_context.saved_msrs.num = total_num; - saved_context.saved_msrs.array = msr_array; + saved_msrs->num = total_num; + saved_msrs->array = msr_array;

return 0; }

/* - * The following section is a quirk framework for problematic BIOSen: + * The following sections are a quirk framework for problematic BIOSen: * Sometimes MSRs are modified by the BIOSen after suspended to * RAM, this might cause unexpected behavior after wakeup. * Thus we save/restore these specified MSRs across suspend/resume @@ -441,7 +452,7 @@ static int msr_initialize_bdw(const stru u32 bdw_msr_id[] = { MSR_IA32_THERM_CONTROL };

pr_info("x86/pm: %s detected, MSR saving is needed during suspending.\n", d->ident); - return msr_init_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id)); + return msr_build_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id)); }

static const struct dmi_system_id msr_save_dmi_table[] = { @@ -456,9 +467,58 @@ static const struct dmi_system_id msr_sa {} };

+static int msr_save_cpuid_features(const struct x86_cpu_id *c) +{ + u32 cpuid_msr_id[] = { + MSR_AMD64_CPUID_FN_1, + }; + + pr_info("x86/pm: family %#hx cpu detected, MSR saving is needed during suspending.\n", + c->family); + + return msr_build_context(cpuid_msr_id, ARRAY_SIZE(cpuid_msr_id)); +} + +static const struct x86_cpu_id msr_save_cpu_table[] = { + { + .vendor = X86_VENDOR_AMD, + .family = 0x15, + .model = X86_MODEL_ANY, + .feature = X86_FEATURE_ANY, + .driver_data = (kernel_ulong_t)msr_save_cpuid_features, + }, + { + .vendor = X86_VENDOR_AMD, + .family = 0x16, + .model = X86_MODEL_ANY, + .feature = X86_FEATURE_ANY, + .driver_data = (kernel_ulong_t)msr_save_cpuid_features, + }, + {} +}; + +typedef int (*pm_cpu_match_t)(const struct x86_cpu_id *); +static int pm_cpu_check(const struct x86_cpu_id *c) +{ + const struct x86_cpu_id *m; + int ret = 0; + + m = x86_match_cpu(msr_save_cpu_table); + if (m) { + pm_cpu_match_t fn; + + fn = (pm_cpu_match_t)m->driver_data; + ret = fn(m); + } + + return ret; +} + static int pm_check_save_msr(void) { dmi_check_system(msr_save_dmi_table); + pm_cpu_check(msr_save_cpu_table); + return 0; }

From: John Hubbard jhubbard@nvidia.com

commit a90118c445cc7f07781de26a9684d4ec58bfcfd1 upstream.

Recent gcc compilers (gcc 9.1) generate warnings about an out of bounds memset, if the memset goes accross several fields of a struct. This generated a couple of warnings on x86_64 builds in sanitize_boot_params().

Fix this by explicitly saving the fields in struct boot_params that are intended to be preserved, and zeroing all the rest.

[ tglx: Tagged for stable as it breaks the warning free build there as well ]

Suggested-by: Thomas Gleixner tglx@linutronix.de Suggested-by: H. Peter Anvin hpa@zytor.com Signed-off-by: John Hubbard jhubbard@nvidia.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190731054627.5627-2-jhubbard@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/include/asm/bootparam_utils.h | 60 +++++++++++++++++++++++++-------- 1 file changed, 47 insertions(+), 13 deletions(-)

--- a/arch/x86/include/asm/bootparam_utils.h +++ b/arch/x86/include/asm/bootparam_utils.h @@ -18,6 +18,20 @@ * Note: efi_info is commonly left uninitialized, but that field has a * private magic, so it is better to leave it unchanged. */ + +#define sizeof_mbr(type, member) ({ sizeof(((type *)0)->member); }) + +#define BOOT_PARAM_PRESERVE(struct_member) \ + { \ + .start = offsetof(struct boot_params, struct_member), \ + .len = sizeof_mbr(struct boot_params, struct_member), \ + } + +struct boot_params_to_save { + unsigned int start; + unsigned int len; +}; + static void sanitize_boot_params(struct boot_params *boot_params) { /* @@ -36,19 +50,39 @@ static void sanitize_boot_params(struct */ if (boot_params->sentinel) { /* fields in boot_params are left uninitialized, clear them */ - memset(&boot_params->ext_ramdisk_image, 0, - (char *)&boot_params->efi_info - - (char *)&boot_params->ext_ramdisk_image); - memset(&boot_params->kbd_status, 0, - (char *)&boot_params->hdr - - (char *)&boot_params->kbd_status); - memset(&boot_params->_pad7[0], 0, - (char *)&boot_params->edd_mbr_sig_buffer[0] - - (char *)&boot_params->_pad7[0]); - memset(&boot_params->_pad8[0], 0, - (char *)&boot_params->eddbuf[0] - - (char *)&boot_params->_pad8[0]); - memset(&boot_params->_pad9[0], 0, sizeof(boot_params->_pad9)); + static struct boot_params scratch; + char *bp_base = (char *)boot_params; + char *save_base = (char *)&scratch; + int i; + + const struct boot_params_to_save to_save[] = { + BOOT_PARAM_PRESERVE(screen_info), + BOOT_PARAM_PRESERVE(apm_bios_info), + BOOT_PARAM_PRESERVE(tboot_addr), + BOOT_PARAM_PRESERVE(ist_info), + BOOT_PARAM_PRESERVE(hd0_info), + BOOT_PARAM_PRESERVE(hd1_info), + BOOT_PARAM_PRESERVE(sys_desc_table), + BOOT_PARAM_PRESERVE(olpc_ofw_header), + BOOT_PARAM_PRESERVE(efi_info), + BOOT_PARAM_PRESERVE(alt_mem_k), + BOOT_PARAM_PRESERVE(scratch), + BOOT_PARAM_PRESERVE(e820_entries), + BOOT_PARAM_PRESERVE(eddbuf_entries), + BOOT_PARAM_PRESERVE(edd_mbr_sig_buf_entries), + BOOT_PARAM_PRESERVE(edd_mbr_sig_buffer), + BOOT_PARAM_PRESERVE(e820_table), + BOOT_PARAM_PRESERVE(eddbuf), + }; + + memset(&scratch, 0, sizeof(scratch)); + + for (i = 0; i < ARRAY_SIZE(to_save); i++) { + memcpy(save_base + to_save[i].start, + bp_base + to_save[i].start, to_save[i].len); + } + + memcpy(boot_params, save_base, sizeof(*boot_params)); } }

From: Dmitry Fomichev dmitry.fomichev@wdc.com

commit d1fef41465f0e8cae0693fb184caa6bfafb6cd16 upstream.

This patch fixes a problem in dm-kcopyd that may leave jobs in complete queue indefinitely in the event of backing storage failure.

This behavior has been observed while running 100% write file fio workload against an XFS volume created on top of a dm-zoned target device. If the underlying storage of dm-zoned goes to offline state under I/O, kcopyd sometimes never issues the end copy callback and dm-zoned reclaim work hangs indefinitely waiting for that completion.

This behavior was traced down to the error handling code in process_jobs() function that places the failed job to complete_jobs queue, but doesn't wake up the job handler. In case of backing device failure, all outstanding jobs may end up going to complete_jobs queue via this code path and then stay there forever because there are no more successful I/O jobs to wake up the job handler.

This patch adds a wake() call to always wake up kcopyd job wait queue for all I/O jobs that fail before dm_io() gets called for that job.

The patch also sets the write error status in all sub jobs that are failed because their master job has failed.

Fixes: b73c67c2cbb00 ("dm kcopyd: add sequential write feature") Cc: stable@vger.kernel.org Signed-off-by: Dmitry Fomichev dmitry.fomichev@wdc.com Reviewed-by: Damien Le Moal damien.lemoal@wdc.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/md/dm-kcopyd.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -548,8 +548,10 @@ static int run_io_job(struct kcopyd_job * no point in continuing. */ if (test_bit(DM_KCOPYD_WRITE_SEQ, &job->flags) && - job->master_job->write_err) + job->master_job->write_err) { + job->write_err = job->master_job->write_err; return -EIO; + }

io_job_start(job->kc->throttle);

@@ -601,6 +603,7 @@ static int process_jobs(struct list_head else job->read_err = 1; push(&kc->complete_jobs, job); + wake(kc); break; }

From: Mikulas Patocka mpatocka@redhat.com

commit 5729b6e5a1bcb0bbc28abe82d749c7392f66d2c7 upstream.

Fix a crash that was introduced by the commit 724376a04d1a. The crash is reported here: https://gitlab.com/cryptsetup/cryptsetup/issues/468

When reading from the integrity device, the function dm_integrity_map_continue calls find_journal_node to find out if the location to read is present in the journal. Then, it calculates how many sectors are consecutively stored in the journal. Then, it locks the range with add_new_range and wait_and_add_new_range.

The problem is that during wait_and_add_new_range, we hold no locks (we don't hold ic->endio_wait.lock and we don't hold a range lock), so the journal may change arbitrarily while wait_and_add_new_range sleeps.

The code then goes to __journal_read_write and hits BUG_ON(journal_entry_get_sector(je) != logical_sector); because the journal has changed.

In order to fix this bug, we need to re-check the journal location after wait_and_add_new_range. We restrict the length to one block in order to not complicate the code too much.

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

--- drivers/md/dm-integrity.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+)

--- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -1749,7 +1749,22 @@ offload_to_thread: queue_work(ic->wait_wq, &dio->work); return; } + if (journal_read_pos != NOT_FOUND) + dio->range.n_sectors = ic->sectors_per_block; wait_and_add_new_range(ic, &dio->range); + /* + * wait_and_add_new_range drops the spinlock, so the journal + * may have been changed arbitrarily. We need to recheck. + * To simplify the code, we restrict I/O size to just one block. + */ + if (journal_read_pos != NOT_FOUND) { + sector_t next_sector; + unsigned new_pos = find_journal_node(ic, dio->range.logical_sector, &next_sector); + if (unlikely(new_pos != journal_read_pos)) { + remove_range_unlocked(ic, &dio->range); + goto retry; + } + } } spin_unlock_irq(&ic->endio_wait.lock);

From: ZhangXiaoxu zhangxiaoxu5@huawei.com

commit ae148243d3f0816b37477106c05a2ec7d5f32614 upstream.

In commit 6096d91af0b6 ("dm space map metadata: fix occasional leak of a metadata block on resize"), we refactor the commit logic to a new function 'apply_bops'. But when that logic was replaced in out() the return value was not stored. This may lead out() returning a wrong value to the caller.

Fixes: 6096d91af0b6 ("dm space map metadata: fix occasional leak of a metadata block on resize") Cc: stable@vger.kernel.org Signed-off-by: ZhangXiaoxu zhangxiaoxu5@huawei.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/md/persistent-data/dm-space-map-metadata.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -249,7 +249,7 @@ static int out(struct sm_metadata *smm) }

if (smm->recursion_count == 1) - apply_bops(smm); + r = apply_bops(smm);

smm->recursion_count--;

From: Dmitry Fomichev dmitry.fomichev@wdc.com

commit b234c6d7a703661b5045c5bf569b7c99d2edbf88 upstream.

There are several places in reclaim code where errors are not propagated to the main function, dmz_reclaim(). This function is responsible for unlocking zones that might be still locked at the end of any failed reclaim iterations. As the result, some device zones may be left permanently locked for reclaim, degrading target's capability to reclaim zones.

This patch fixes these issues as follows -

Make sure that dmz_reclaim_buf(), dmz_reclaim_seq_data() and dmz_reclaim_rnd_data() return error codes to the caller.

dmz_reclaim() function is renamed to dmz_do_reclaim() to avoid clashing with "struct dmz_reclaim" and is modified to return the error to the caller.

dmz_get_zone_for_reclaim() now returns an error instead of NULL pointer and reclaim code checks for that error.

Error logging/debug messages are added where necessary.

Fixes: 3b1a94c88b79 ("dm zoned: drive-managed zoned block device target") Cc: stable@vger.kernel.org Signed-off-by: Dmitry Fomichev dmitry.fomichev@wdc.com Reviewed-by: Damien Le Moal damien.lemoal@wdc.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/md/dm-zoned-metadata.c | 4 ++-- drivers/md/dm-zoned-reclaim.c | 28 +++++++++++++++++++--------- 2 files changed, 21 insertions(+), 11 deletions(-)

--- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -1534,7 +1534,7 @@ static struct dm_zone *dmz_get_rnd_zone_ struct dm_zone *zone;

if (list_empty(&zmd->map_rnd_list)) - return NULL; + return ERR_PTR(-EBUSY);

list_for_each_entry(zone, &zmd->map_rnd_list, link) { if (dmz_is_buf(zone)) @@ -1545,7 +1545,7 @@ static struct dm_zone *dmz_get_rnd_zone_ return dzone; }

- return NULL; + return ERR_PTR(-EBUSY); }

/* --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -215,7 +215,7 @@ static int dmz_reclaim_buf(struct dmz_re

dmz_unlock_flush(zmd);

- return 0; + return ret; }

/* @@ -259,7 +259,7 @@ static int dmz_reclaim_seq_data(struct d

dmz_unlock_flush(zmd);

- return 0; + return ret; }

/* @@ -312,7 +312,7 @@ static int dmz_reclaim_rnd_data(struct d

dmz_unlock_flush(zmd);

- return 0; + return ret; }

/* @@ -334,7 +334,7 @@ static void dmz_reclaim_empty(struct dmz /* * Find a candidate zone for reclaim and process it. */ -static void dmz_reclaim(struct dmz_reclaim *zrc) +static int dmz_do_reclaim(struct dmz_reclaim *zrc) { struct dmz_metadata *zmd = zrc->metadata; struct dm_zone *dzone; @@ -344,8 +344,8 @@ static void dmz_reclaim(struct dmz_recla

/* Get a data zone */ dzone = dmz_get_zone_for_reclaim(zmd); - if (!dzone) - return; + if (IS_ERR(dzone)) + return PTR_ERR(dzone);

start = jiffies;

@@ -391,13 +391,20 @@ static void dmz_reclaim(struct dmz_recla out: if (ret) { dmz_unlock_zone_reclaim(dzone); - return; + return ret; }

- (void) dmz_flush_metadata(zrc->metadata); + ret = dmz_flush_metadata(zrc->metadata); + if (ret) { + dmz_dev_debug(zrc->dev, + "Metadata flush for zone %u failed, err %d\n", + dmz_id(zmd, rzone), ret); + return ret; + }

dmz_dev_debug(zrc->dev, "Reclaimed zone %u in %u ms", dmz_id(zmd, rzone), jiffies_to_msecs(jiffies - start)); + return 0; }

/* @@ -442,6 +449,7 @@ static void dmz_reclaim_work(struct work struct dmz_metadata *zmd = zrc->metadata; unsigned int nr_rnd, nr_unmap_rnd; unsigned int p_unmap_rnd; + int ret;

if (!dmz_should_reclaim(zrc)) { mod_delayed_work(zrc->wq, &zrc->work, DMZ_IDLE_PERIOD); @@ -471,7 +479,9 @@ static void dmz_reclaim_work(struct work (dmz_target_idle(zrc) ? "Idle" : "Busy"), p_unmap_rnd, nr_unmap_rnd, nr_rnd);

- dmz_reclaim(zrc); + ret = dmz_do_reclaim(zrc); + if (ret) + dmz_dev_debug(zrc->dev, "Reclaim error %d\n", ret);

dmz_schedule_reclaim(zrc); }

From: Dmitry Fomichev dmitry.fomichev@wdc.com

commit 75d66ffb48efb30f2dd42f041ba8b39c5b2bd115 upstream.

dm-zoned is observed to lock up or livelock in case of hardware failure or some misconfiguration of the backing zoned device.

This patch adds a new dm-zoned target function that checks the status of the backing device. If the request queue of the backing device is found to be in dying state or the SCSI backing device enters offline state, the health check code sets a dm-zoned target flag prompting all further incoming I/O to be rejected. In order to detect backing device failures timely, this new function is called in the request mapping path, at the beginning of every reclaim run and before performing any metadata I/O.

The proper way out of this situation is to do

dmsetup remove <dm-zoned target>

and recreate the target when the problem with the backing device is resolved.

Fixes: 3b1a94c88b79 ("dm zoned: drive-managed zoned block device target") Cc: stable@vger.kernel.org Signed-off-by: Dmitry Fomichev dmitry.fomichev@wdc.com Reviewed-by: Damien Le Moal damien.lemoal@wdc.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/md/dm-zoned-metadata.c | 51 ++++++++++++++++++++++++++++++++--------- drivers/md/dm-zoned-reclaim.c | 18 ++++++++++++-- drivers/md/dm-zoned-target.c | 45 ++++++++++++++++++++++++++++++++++-- drivers/md/dm-zoned.h | 10 ++++++++ 4 files changed, 110 insertions(+), 14 deletions(-)

--- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -401,15 +401,18 @@ static struct dmz_mblock *dmz_get_mblock sector_t block = zmd->sb[zmd->mblk_primary].block + mblk_no; struct bio *bio;

+ if (dmz_bdev_is_dying(zmd->dev)) + return ERR_PTR(-EIO); + /* Get a new block and a BIO to read it */ mblk = dmz_alloc_mblock(zmd, mblk_no); if (!mblk) - return NULL; + return ERR_PTR(-ENOMEM);

bio = bio_alloc(GFP_NOIO, 1); if (!bio) { dmz_free_mblock(zmd, mblk); - return NULL; + return ERR_PTR(-ENOMEM); }

spin_lock(&zmd->mblk_lock); @@ -540,8 +543,8 @@ static struct dmz_mblock *dmz_get_mblock if (!mblk) { /* Cache miss: read the block from disk */ mblk = dmz_get_mblock_slow(zmd, mblk_no); - if (!mblk) - return ERR_PTR(-ENOMEM); + if (IS_ERR(mblk)) + return mblk; }

/* Wait for on-going read I/O and check for error */ @@ -569,16 +572,19 @@ static void dmz_dirty_mblock(struct dmz_ /* * Issue a metadata block write BIO. */ -static void dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk, - unsigned int set) +static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk, + unsigned int set) { sector_t block = zmd->sb[set].block + mblk->no; struct bio *bio;

+ if (dmz_bdev_is_dying(zmd->dev)) + return -EIO; + bio = bio_alloc(GFP_NOIO, 1); if (!bio) { set_bit(DMZ_META_ERROR, &mblk->state); - return; + return -ENOMEM; }

set_bit(DMZ_META_WRITING, &mblk->state); @@ -590,6 +596,8 @@ static void dmz_write_mblock(struct dmz_ bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_META | REQ_PRIO); bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0); submit_bio(bio); + + return 0; }

/* @@ -601,6 +609,9 @@ static int dmz_rdwr_block(struct dmz_met struct bio *bio; int ret;

+ if (dmz_bdev_is_dying(zmd->dev)) + return -EIO; + bio = bio_alloc(GFP_NOIO, 1); if (!bio) return -ENOMEM; @@ -658,22 +669,29 @@ static int dmz_write_dirty_mblocks(struc { struct dmz_mblock *mblk; struct blk_plug plug; - int ret = 0; + int ret = 0, nr_mblks_submitted = 0;

/* Issue writes */ blk_start_plug(&plug); - list_for_each_entry(mblk, write_list, link) - dmz_write_mblock(zmd, mblk, set); + list_for_each_entry(mblk, write_list, link) { + ret = dmz_write_mblock(zmd, mblk, set); + if (ret) + break; + nr_mblks_submitted++; + } blk_finish_plug(&plug);

/* Wait for completion */ list_for_each_entry(mblk, write_list, link) { + if (!nr_mblks_submitted) + break; wait_on_bit_io(&mblk->state, DMZ_META_WRITING, TASK_UNINTERRUPTIBLE); if (test_bit(DMZ_META_ERROR, &mblk->state)) { clear_bit(DMZ_META_ERROR, &mblk->state); ret = -EIO; } + nr_mblks_submitted--; }

/* Flush drive cache (this will also sync data) */ @@ -735,6 +753,11 @@ int dmz_flush_metadata(struct dmz_metada */ dmz_lock_flush(zmd);

+ if (dmz_bdev_is_dying(zmd->dev)) { + ret = -EIO; + goto out; + } + /* Get dirty blocks */ spin_lock(&zmd->mblk_lock); list_splice_init(&zmd->mblk_dirty_list, &write_list); @@ -1623,6 +1646,10 @@ again: /* Alloate a random zone */ dzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND); if (!dzone) { + if (dmz_bdev_is_dying(zmd->dev)) { + dzone = ERR_PTR(-EIO); + goto out; + } dmz_wait_for_free_zones(zmd); goto again; } @@ -1720,6 +1747,10 @@ again: /* Alloate a random zone */ bzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND); if (!bzone) { + if (dmz_bdev_is_dying(zmd->dev)) { + bzone = ERR_PTR(-EIO); + goto out; + } dmz_wait_for_free_zones(zmd); goto again; } --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -37,7 +37,7 @@ enum { /* * Number of seconds of target BIO inactivity to consider the target idle. */ -#define DMZ_IDLE_PERIOD (10UL * HZ) +#define DMZ_IDLE_PERIOD (10UL * HZ)

/* * Percentage of unmapped (free) random zones below which reclaim starts @@ -134,6 +134,9 @@ static int dmz_reclaim_copy(struct dmz_r set_bit(DM_KCOPYD_WRITE_SEQ, &flags);

while (block < end_block) { + if (dev->flags & DMZ_BDEV_DYING) + return -EIO; + /* Get a valid region from the source zone */ ret = dmz_first_valid_block(zmd, src_zone, &block); if (ret <= 0) @@ -451,6 +454,9 @@ static void dmz_reclaim_work(struct work unsigned int p_unmap_rnd; int ret;

+ if (dmz_bdev_is_dying(zrc->dev)) + return; + if (!dmz_should_reclaim(zrc)) { mod_delayed_work(zrc->wq, &zrc->work, DMZ_IDLE_PERIOD); return; @@ -480,8 +486,16 @@ static void dmz_reclaim_work(struct work p_unmap_rnd, nr_unmap_rnd, nr_rnd);

ret = dmz_do_reclaim(zrc); - if (ret) + if (ret) { dmz_dev_debug(zrc->dev, "Reclaim error %d\n", ret); + if (ret == -EIO) + /* + * LLD might be performing some error handling sequence + * at the underlying device. To not interfere, do not + * attempt to schedule the next reclaim run immediately. + */ + return; + }

dmz_schedule_reclaim(zrc); } --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -133,6 +133,8 @@ static int dmz_submit_bio(struct dmz_tar

atomic_inc(&bioctx->ref); generic_make_request(clone); + if (clone->bi_status == BLK_STS_IOERR) + return -EIO;

if (bio_op(bio) == REQ_OP_WRITE && dmz_is_seq(zone)) zone->wp_block += nr_blocks; @@ -277,8 +279,8 @@ static int dmz_handle_buffered_write(str

/* Get the buffer zone. One will be allocated if needed */ bzone = dmz_get_chunk_buffer(zmd, zone); - if (!bzone) - return -ENOSPC; + if (IS_ERR(bzone)) + return PTR_ERR(bzone);

if (dmz_is_readonly(bzone)) return -EROFS; @@ -389,6 +391,11 @@ static void dmz_handle_bio(struct dmz_ta

dmz_lock_metadata(zmd);

+ if (dmz->dev->flags & DMZ_BDEV_DYING) { + ret = -EIO; + goto out; + } + /* * Get the data zone mapping the chunk. There may be no * mapping for read and discard. If a mapping is obtained, @@ -493,6 +500,8 @@ static void dmz_flush_work(struct work_s

/* Flush dirty metadata blocks */ ret = dmz_flush_metadata(dmz->metadata); + if (ret) + dmz_dev_debug(dmz->dev, "Metadata flush failed, rc=%d\n", ret);

/* Process queued flush requests */ while (1) { @@ -557,6 +566,32 @@ out: }

/* + * Check the backing device availability. If it's on the way out, + * start failing I/O. Reclaim and metadata components also call this + * function to cleanly abort operation in the event of such failure. + */ +bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev) +{ + struct gendisk *disk; + + if (!(dmz_dev->flags & DMZ_BDEV_DYING)) { + disk = dmz_dev->bdev->bd_disk; + if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) { + dmz_dev_warn(dmz_dev, "Backing device queue dying"); + dmz_dev->flags |= DMZ_BDEV_DYING; + } else if (disk->fops->check_events) { + if (disk->fops->check_events(disk, 0) & + DISK_EVENT_MEDIA_CHANGE) { + dmz_dev_warn(dmz_dev, "Backing device offline"); + dmz_dev->flags |= DMZ_BDEV_DYING; + } + } + } + + return dmz_dev->flags & DMZ_BDEV_DYING; +} + +/* * Process a new BIO. */ static int dmz_map(struct dm_target *ti, struct bio *bio) @@ -569,6 +604,9 @@ static int dmz_map(struct dm_target *ti, sector_t chunk_sector; int ret;

+ if (dmz_bdev_is_dying(dmz->dev)) + return DM_MAPIO_KILL; + dmz_dev_debug(dev, "BIO op %d sector %llu + %u => chunk %llu, block %llu, %u blocks", bio_op(bio), (unsigned long long)sector, nr_sectors, (unsigned long long)dmz_bio_chunk(dmz->dev, bio), @@ -866,6 +904,9 @@ static int dmz_prepare_ioctl(struct dm_t { struct dmz_target *dmz = ti->private;

+ if (dmz_bdev_is_dying(dmz->dev)) + return -ENODEV; + *bdev = dmz->dev->bdev;

return 0; --- a/drivers/md/dm-zoned.h +++ b/drivers/md/dm-zoned.h @@ -56,6 +56,8 @@ struct dmz_dev {

unsigned int nr_zones;

+ unsigned int flags; + sector_t zone_nr_sectors; unsigned int zone_nr_sectors_shift;

@@ -67,6 +69,9 @@ struct dmz_dev { (dev)->zone_nr_sectors_shift) #define dmz_chunk_block(dev, b) ((b) & ((dev)->zone_nr_blocks - 1))

+/* Device flags. */ +#define DMZ_BDEV_DYING (1 << 0) + /* * Zone descriptor. */ @@ -245,4 +250,9 @@ void dmz_resume_reclaim(struct dmz_recla void dmz_reclaim_bio_acc(struct dmz_reclaim *zrc); void dmz_schedule_reclaim(struct dmz_reclaim *zrc);

+/* + * Functions defined in dm-zoned-target.c + */ +bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev); + #endif /* DM_ZONED_H */

From: Vlastimil Babka vbabka@suse.cz

commit f7da677bc6e72033f0981b9d58b5c5d409fa641e upstream.

THP splitting path is missing the split_page_owner() call that split_page() has.

As a result, split THP pages are wrongly reported in the page_owner file as order-9 pages. Furthermore when the former head page is freed, the remaining former tail pages are not listed in the page_owner file at all. This patch fixes that by adding the split_page_owner() call into __split_huge_page().

Link: http://lkml.kernel.org/r/20190820131828.22684-2-vbabka@suse.cz Fixes: a9627bc5e34e ("mm/page_owner: introduce split_page_owner and replace manual handling") Reported-by: Kirill A. Shutemov kirill@shutemov.name Signed-off-by: Vlastimil Babka vbabka@suse.cz Cc: Michal Hocko mhocko@kernel.org Cc: Mel Gorman mgorman@techsingularity.net Cc: Matthew Wilcox willy@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- mm/huge_memory.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -33,6 +33,7 @@ #include <linux/page_idle.h> #include <linux/shmem_fs.h> #include <linux/oom.h> +#include <linux/page_owner.h>

#include <asm/tlb.h> #include <asm/pgalloc.h> @@ -2477,6 +2478,9 @@ static void __split_huge_page(struct pag }

ClearPageCompound(head); + + split_page_owner(head, HPAGE_PMD_ORDER); + /* See comment in __split_huge_page_tail() */ if (PageAnon(head)) { /* Additional pin to radix tree of swap cache */

From: Henry Burns henryburns@google.com

commit 701d678599d0c1623aaf4139c03eea260a75b027 upstream.

In zs_destroy_pool() we call flush_work(&pool->free_work). However, we have no guarantee that migration isn't happening in the background at that time.

Since migration can't directly free pages, it relies on free_work being scheduled to free the pages. But there's nothing preventing an in-progress migrate from queuing the work *after* zs_unregister_migration() has called flush_work(). Which would mean pages still pointing at the inode when we free it.

Since we know at destroy time all objects should be free, no new migrations can come in (since zs_page_isolate() fails for fully-free zspages). This means it is sufficient to track a "# isolated zspages" count by class, and have the destroy logic ensure all such pages have drained before proceeding. Keeping that state under the class spinlock keeps the logic straightforward.

In this case a memory leak could lead to an eventual crash if compaction hits the leaked page. This crash would only occur if people are changing their zswap backend at runtime (which eventually starts destruction).

Link: http://lkml.kernel.org/r/20190809181751.219326-2-henryburns@google.com Fixes: 48b4800a1c6a ("zsmalloc: page migration support") Signed-off-by: Henry Burns henryburns@google.com Reviewed-by: Sergey Senozhatsky sergey.senozhatsky@gmail.com Cc: Henry Burns henrywolfeburns@gmail.com Cc: Minchan Kim minchan@kernel.org Cc: Shakeel Butt shakeelb@google.com Cc: Jonathan Adams jwadams@google.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- mm/zsmalloc.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 59 insertions(+), 2 deletions(-)

--- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -53,6 +53,7 @@ #include <linux/zpool.h> #include <linux/mount.h> #include <linux/migrate.h> +#include <linux/wait.h> #include <linux/pagemap.h> #include <linux/fs.h>

@@ -267,6 +268,10 @@ struct zs_pool { #ifdef CONFIG_COMPACTION struct inode *inode; struct work_struct free_work; + /* A wait queue for when migration races with async_free_zspage() */ + struct wait_queue_head migration_wait; + atomic_long_t isolated_pages; + bool destroying; #endif };

@@ -1894,6 +1899,19 @@ static void putback_zspage_deferred(stru

}

+static inline void zs_pool_dec_isolated(struct zs_pool *pool) +{ + VM_BUG_ON(atomic_long_read(&pool->isolated_pages) <= 0); + atomic_long_dec(&pool->isolated_pages); + /* + * There's no possibility of racing, since wait_for_isolated_drain() + * checks the isolated count under &class->lock after enqueuing + * on migration_wait. + */ + if (atomic_long_read(&pool->isolated_pages) == 0 && pool->destroying) + wake_up_all(&pool->migration_wait); +} + static void replace_sub_page(struct size_class *class, struct zspage *zspage, struct page *newpage, struct page *oldpage) { @@ -1963,6 +1981,7 @@ static bool zs_page_isolate(struct page */ if (!list_empty(&zspage->list) && !is_zspage_isolated(zspage)) { get_zspage_mapping(zspage, &class_idx, &fullness); + atomic_long_inc(&pool->isolated_pages); remove_zspage(class, zspage, fullness); }

@@ -2062,8 +2081,16 @@ static int zs_page_migrate(struct addres * Page migration is done so let's putback isolated zspage to * the list if @page is final isolated subpage in the zspage. */ - if (!is_zspage_isolated(zspage)) + if (!is_zspage_isolated(zspage)) { + /* + * We cannot race with zs_destroy_pool() here because we wait + * for isolation to hit zero before we start destroying. + * Also, we ensure that everyone can see pool->destroying before + * we start waiting. + */ putback_zspage_deferred(pool, class, zspage); + zs_pool_dec_isolated(pool); + }

reset_page(page); put_page(page); @@ -2114,8 +2141,8 @@ static void zs_page_putback(struct page * so let's defer. */ putback_zspage_deferred(pool, class, zspage); + zs_pool_dec_isolated(pool); } - spin_unlock(&class->lock); }

@@ -2138,8 +2165,36 @@ static int zs_register_migration(struct return 0; }

+static bool pool_isolated_are_drained(struct zs_pool *pool) +{ + return atomic_long_read(&pool->isolated_pages) == 0; +} + +/* Function for resolving migration */ +static void wait_for_isolated_drain(struct zs_pool *pool) +{ + + /* + * We're in the process of destroying the pool, so there are no + * active allocations. zs_page_isolate() fails for completely free + * zspages, so we need only wait for the zs_pool's isolated + * count to hit zero. + */ + wait_event(pool->migration_wait, + pool_isolated_are_drained(pool)); +} + static void zs_unregister_migration(struct zs_pool *pool) { + pool->destroying = true; + /* + * We need a memory barrier here to ensure global visibility of + * pool->destroying. Thus pool->isolated pages will either be 0 in which + * case we don't care, or it will be > 0 and pool->destroying will + * ensure that we wake up once isolation hits 0. + */ + smp_mb(); + wait_for_isolated_drain(pool); /* This can block */ flush_work(&pool->free_work); iput(pool->inode); } @@ -2377,6 +2432,8 @@ struct zs_pool *zs_create_pool(const cha if (!pool->name) goto err;

+ init_waitqueue_head(&pool->migration_wait); + if (create_cache(pool)) goto err;

commit 6958d11f77d45db80f7e22a21a74d4d5f44dc667 upstream.

We've had rather rare reports of bmap btree block corruption where the bmap root block has a level count of zero. The root cause of the corruption is so far unknown. We do have verifier checks to detect this form of on-disk corruption, but this doesn't cover a memory corruption variant of the problem. The latter is a reasonable possibility because the root block is part of the inode fork and can reside in-core for some time before inode extents are read.

If this occurs, it leads to a system crash such as the following:

BUG: unable to handle kernel paging request at ffffffff00000221 PF error: [normal kernel read fault] ... RIP: 0010:xfs_trans_brelse+0xf/0x200 [xfs] ... Call Trace: xfs_iread_extents+0x379/0x540 [xfs] xfs_file_iomap_begin_delay+0x11a/0xb40 [xfs] ? xfs_attr_get+0xd1/0x120 [xfs] ? iomap_write_begin.constprop.40+0x2d0/0x2d0 xfs_file_iomap_begin+0x4c4/0x6d0 [xfs] ? __vfs_getxattr+0x53/0x70 ? iomap_write_begin.constprop.40+0x2d0/0x2d0 iomap_apply+0x63/0x130 ? iomap_write_begin.constprop.40+0x2d0/0x2d0 iomap_file_buffered_write+0x62/0x90 ? iomap_write_begin.constprop.40+0x2d0/0x2d0 xfs_file_buffered_aio_write+0xe4/0x3b0 [xfs] __vfs_write+0x150/0x1b0 vfs_write+0xba/0x1c0 ksys_pwrite64+0x64/0xa0 do_syscall_64+0x5a/0x1d0 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The crash occurs because xfs_iread_extents() attempts to release an uninitialized buffer pointer as the level == 0 value prevented the buffer from ever being allocated or read. Change the level > 0 assert to an explicit error check in xfs_iread_extents() to avoid crashing the kernel in the event of localized, in-core inode corruption.

Signed-off-by: Brian Foster bfoster@redhat.com Reviewed-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Luis Chamberlain mcgrof@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/xfs/libxfs/xfs_bmap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 3a496ffe6551c..ab2465bc413af 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1178,7 +1178,10 @@ xfs_iread_extents( * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out. */ level = be16_to_cpu(block->bb_level); - ASSERT(level > 0); + if (unlikely(level == 0)) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); + return -EFSCORRUPTED; + } pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes); bno = be64_to_cpu(*pp);

commit 4c74a56b9de76bb6b581274b76b52535ad77c2a7 upstream.

This patch adds a subroutine xfs_attr_try_sf_addname used by xfs_attr_set. This subrotine will attempt to add the attribute name specified in args in shortform, as well and perform error handling previously done in xfs_attr_set.

This patch helps to pre-simplify xfs_attr_set for reviewing purposes and reduce indentation. New function will be added in the next patch.

[dgc: moved commit to helper function, too.]

Signed-off-by: Allison Henderson allison.henderson@oracle.com Reviewed-by: Dave Chinner dchinner@redhat.com Signed-off-by: Dave Chinner david@fromorbit.com Signed-off-by: Luis Chamberlain mcgrof@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/xfs/libxfs/xfs_attr.c | 53 +++++++++++++++++++++++----------------- 1 file changed, 30 insertions(+), 23 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index c6299f82a6e49..c15a1debec907 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -191,6 +191,33 @@ xfs_attr_calc_size( return nblks; }

+STATIC int +xfs_attr_try_sf_addname( + struct xfs_inode *dp, + struct xfs_da_args *args) +{ + + struct xfs_mount *mp = dp->i_mount; + int error, error2; + + error = xfs_attr_shortform_addname(args); + if (error == -ENOSPC) + return error; + + /* + * Commit the shortform mods, and we're done. + * NOTE: this is also the error path (EEXIST, etc). + */ + if (!error && (args->flags & ATTR_KERNOTIME) == 0) + xfs_trans_ichgtime(args->trans, dp, XFS_ICHGTIME_CHG); + + if (mp->m_flags & XFS_MOUNT_WSYNC) + xfs_trans_set_sync(args->trans); + + error2 = xfs_trans_commit(args->trans); + return error ? error : error2; +} + int xfs_attr_set( struct xfs_inode *dp, @@ -204,7 +231,7 @@ xfs_attr_set( struct xfs_da_args args; struct xfs_trans_res tres; int rsvd = (flags & ATTR_ROOT) != 0; - int error, err2, local; + int error, local;

XFS_STATS_INC(mp, xs_attr_set);

@@ -281,30 +308,10 @@ xfs_attr_set( * Try to add the attr to the attribute list in * the inode. */ - error = xfs_attr_shortform_addname(&args); + error = xfs_attr_try_sf_addname(dp, &args); if (error != -ENOSPC) { - /* - * Commit the shortform mods, and we're done. - * NOTE: this is also the error path (EEXIST, etc). - */ - ASSERT(args.trans != NULL); - - /* - * If this is a synchronous mount, make sure that - * the transaction goes to disk before returning - * to the user. - */ - if (mp->m_flags & XFS_MOUNT_WSYNC) - xfs_trans_set_sync(args.trans); - - if (!error && (flags & ATTR_KERNOTIME) == 0) { - xfs_trans_ichgtime(args.trans, dp, - XFS_ICHGTIME_CHG); - } - err2 = xfs_trans_commit(args.trans); xfs_iunlock(dp, XFS_ILOCK_EXCL); - - return error ? error : err2; + return error; }

/*

commit 068f985a9e5ec70fde58d8f679994fdbbd093a36 upstream.

This patch adds xfs_attr_remove_args. These sub-routines remove the attributes specified in @args. We will use this later for setting parent pointers as a deferred attribute operation.

Signed-off-by: Allison Henderson allison.henderson@oracle.com Reviewed-by: Dave Chinner dchinner@redhat.com Signed-off-by: Dave Chinner david@fromorbit.com Signed-off-by: Luis Chamberlain mcgrof@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/xfs/libxfs/xfs_attr.c | 36 +++++++++++++++++++++++++----------- fs/xfs/libxfs/xfs_attr.h | 1 + 2 files changed, 26 insertions(+), 11 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index 25431ddba1fab..844ed87b19007 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -289,6 +289,30 @@ xfs_attr_set_args( return error; }

+/* + * Remove the attribute specified in @args. + */ +int +xfs_attr_remove_args( + struct xfs_da_args *args) +{ + struct xfs_inode *dp = args->dp; + int error; + + if (!xfs_inode_hasattr(dp)) { + error = -ENOATTR; + } else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) { + ASSERT(dp->i_afp->if_flags & XFS_IFINLINE); + error = xfs_attr_shortform_remove(args); + } else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) { + error = xfs_attr_leaf_removename(args); + } else { + error = xfs_attr_node_removename(args); + } + + return error; +} + int xfs_attr_set( struct xfs_inode *dp, @@ -445,17 +469,7 @@ xfs_attr_remove( */ xfs_trans_ijoin(args.trans, dp, 0);

- if (!xfs_inode_hasattr(dp)) { - error = -ENOATTR; - } else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) { - ASSERT(dp->i_afp->if_flags & XFS_IFINLINE); - error = xfs_attr_shortform_remove(&args); - } else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) { - error = xfs_attr_leaf_removename(&args); - } else { - error = xfs_attr_node_removename(&args); - } - + error = xfs_attr_remove_args(&args); if (error) goto out;

diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h index f608ac8f306f9..bdf52a333f3f9 100644 --- a/fs/xfs/libxfs/xfs_attr.h +++ b/fs/xfs/libxfs/xfs_attr.h @@ -142,6 +142,7 @@ int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name, unsigned char *value, int valuelen, int flags); int xfs_attr_set_args(struct xfs_da_args *args, struct xfs_buf **leaf_bp); int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags); +int xfs_attr_remove_args(struct xfs_da_args *args); int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize, int flags, struct attrlist_cursor_kern *cursor);

[ Upstream commit e0702d90b79d430b0ccc276ead4f88440bb51352 ]

This function is supposed to return error pointers so it matches the dmz_get_rnd_zone_for_reclaim() function. The current code could lead to a NULL dereference in dmz_do_reclaim()

Fixes: b234c6d7a703 ("dm zoned: improve error handling in reclaim") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Reviewed-by: Dmitry Fomichev dmitry.fomichev@wdc.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/md/dm-zoned-metadata.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 00e7a343eacf1..7e8d7fc99410d 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -1579,7 +1579,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd) struct dm_zone *zone;

if (list_empty(&zmd->map_seq_list)) - return NULL; + return ERR_PTR(-EBUSY);

list_for_each_entry(zone, &zmd->map_seq_list, link) { if (!zone->bzone) @@ -1588,7 +1588,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd) return zone; }

- return NULL; + return ERR_PTR(-EBUSY); }

/*

From: David Howells dhowells@redhat.com

commit 730c5fd42c1e3652a065448fd235cb9fafb2bd10 upstream.

The object lifetime management on the rxrpc_local struct is broken in that the rxrpc_local_processor() function is expected to clean up and remove an object - but it may get requeued by packets coming in on the backing UDP socket once it starts running.

This may result in the assertion in rxrpc_local_rcu() firing because the memory has been scheduled for RCU destruction whilst still queued:

rxrpc: Assertion failed ------------[ cut here ]------------ kernel BUG at net/rxrpc/local_object.c:468!

Note that if the processor comes around before the RCU free function, it will just do nothing because ->dead is true.

Fix this by adding a separate refcount to count active users of the endpoint that causes the endpoint to be destroyed when it reaches 0.

The original refcount can then be used to refcount objects through the work processor and cause the memory to be rcu freed when that reaches 0.

Fixes: 4f95dd78a77e ("rxrpc: Rework local endpoint management") Reported-by: syzbot+1e0edc4b8b7494c28450@syzkaller.appspotmail.com Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/rxrpc/af_rxrpc.c | 4 +- net/rxrpc/ar-internal.h | 5 ++ net/rxrpc/input.c | 16 ++++++-- net/rxrpc/local_object.c | 86 +++++++++++++++++++++++++++++------------------ 4 files changed, 72 insertions(+), 39 deletions(-)

--- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -195,7 +195,7 @@ static int rxrpc_bind(struct socket *soc

service_in_use: write_unlock(&local->services_lock); - rxrpc_put_local(local); + rxrpc_unuse_local(local); ret = -EADDRINUSE; error_unlock: release_sock(&rx->sk); @@ -908,7 +908,7 @@ static int rxrpc_release_sock(struct soc rxrpc_queue_work(&rxnet->service_conn_reaper); rxrpc_queue_work(&rxnet->client_conn_reaper);

- rxrpc_put_local(rx->local); + rxrpc_unuse_local(rx->local); rx->local = NULL; key_put(rx->key); rx->key = NULL; --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -258,7 +258,8 @@ struct rxrpc_security { */ struct rxrpc_local { struct rcu_head rcu; - atomic_t usage; + atomic_t active_users; /* Number of users of the local endpoint */ + atomic_t usage; /* Number of references to the structure */ struct rxrpc_net *rxnet; /* The network ns in which this resides */ struct list_head link; struct socket *socket; /* my UDP socket */ @@ -998,6 +999,8 @@ struct rxrpc_local *rxrpc_lookup_local(s struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *); struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *); void rxrpc_put_local(struct rxrpc_local *); +struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *); +void rxrpc_unuse_local(struct rxrpc_local *); void rxrpc_queue_local(struct rxrpc_local *); void rxrpc_destroy_all_locals(struct rxrpc_net *);

--- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1106,8 +1106,12 @@ static void rxrpc_post_packet_to_local(s { _enter("%p,%p", local, skb);

- skb_queue_tail(&local->event_queue, skb); - rxrpc_queue_local(local); + if (rxrpc_get_local_maybe(local)) { + skb_queue_tail(&local->event_queue, skb); + rxrpc_queue_local(local); + } else { + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + } }

/* @@ -1117,8 +1121,12 @@ static void rxrpc_reject_packet(struct r { CHECK_SLAB_OKAY(&local->usage);

- skb_queue_tail(&local->reject_queue, skb); - rxrpc_queue_local(local); + if (rxrpc_get_local_maybe(local)) { + skb_queue_tail(&local->reject_queue, skb); + rxrpc_queue_local(local); + } else { + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + } }

/* --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -83,6 +83,7 @@ static struct rxrpc_local *rxrpc_alloc_l local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL); if (local) { atomic_set(&local->usage, 1); + atomic_set(&local->active_users, 1); local->rxnet = rxnet; INIT_LIST_HEAD(&local->link); INIT_WORK(&local->processor, rxrpc_local_processor); @@ -270,11 +271,8 @@ struct rxrpc_local *rxrpc_lookup_local(s * bind the transport socket may still fail if we're attempting * to use a local address that the dying object is still using. */ - if (!rxrpc_get_local_maybe(local)) { - cursor = cursor->next; - list_del_init(&local->link); + if (!rxrpc_use_local(local)) break; - }

age = "old"; goto found; @@ -288,7 +286,10 @@ struct rxrpc_local *rxrpc_lookup_local(s if (ret < 0) goto sock_error;

- list_add_tail(&local->link, cursor); + if (cursor != &rxnet->local_endpoints) + list_replace(cursor, &local->link); + else + list_add_tail(&local->link, cursor); age = "new";

found: @@ -346,7 +347,8 @@ struct rxrpc_local *rxrpc_get_local_mayb }

/* - * Queue a local endpoint. + * Queue a local endpoint unless it has become unreferenced and pass the + * caller's reference to the work item. */ void rxrpc_queue_local(struct rxrpc_local *local) { @@ -355,15 +357,8 @@ void rxrpc_queue_local(struct rxrpc_loca if (rxrpc_queue_work(&local->processor)) trace_rxrpc_local(local, rxrpc_local_queued, atomic_read(&local->usage), here); -} - -/* - * A local endpoint reached its end of life. - */ -static void __rxrpc_put_local(struct rxrpc_local *local) -{ - _enter("%d", local->debug_id); - rxrpc_queue_work(&local->processor); + else + rxrpc_put_local(local); }

/* @@ -379,11 +374,46 @@ void rxrpc_put_local(struct rxrpc_local trace_rxrpc_local(local, rxrpc_local_put, n, here);

if (n == 0) - __rxrpc_put_local(local); + call_rcu(&local->rcu, rxrpc_local_rcu); } }

/* + * Start using a local endpoint. + */ +struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local) +{ + unsigned int au; + + local = rxrpc_get_local_maybe(local); + if (!local) + return NULL; + + au = atomic_fetch_add_unless(&local->active_users, 1, 0); + if (au == 0) { + rxrpc_put_local(local); + return NULL; + } + + return local; +} + +/* + * Cease using a local endpoint. Once the number of active users reaches 0, we + * start the closure of the transport in the work processor. + */ +void rxrpc_unuse_local(struct rxrpc_local *local) +{ + unsigned int au; + + au = atomic_dec_return(&local->active_users); + if (au == 0) + rxrpc_queue_local(local); + else + rxrpc_put_local(local); +} + +/* * Destroy a local endpoint's socket and then hand the record to RCU to dispose * of. * @@ -397,16 +427,6 @@ static void rxrpc_local_destroyer(struct

_enter("%d", local->debug_id);

- /* We can get a race between an incoming call packet queueing the - * processor again and the work processor starting the destruction - * process which will shut down the UDP socket. - */ - if (local->dead) { - _leave(" [already dead]"); - return; - } - local->dead = true; - mutex_lock(&rxnet->local_mutex); list_del_init(&local->link); mutex_unlock(&rxnet->local_mutex); @@ -426,13 +446,11 @@ static void rxrpc_local_destroyer(struct */ rxrpc_purge_queue(&local->reject_queue); rxrpc_purge_queue(&local->event_queue); - - _debug("rcu local %d", local->debug_id); - call_rcu(&local->rcu, rxrpc_local_rcu); }

/* - * Process events on an endpoint + * Process events on an endpoint. The work item carries a ref which + * we must release. */ static void rxrpc_local_processor(struct work_struct *work) { @@ -445,8 +463,10 @@ static void rxrpc_local_processor(struct

do { again = false; - if (atomic_read(&local->usage) == 0) - return rxrpc_local_destroyer(local); + if (atomic_read(&local->active_users) == 0) { + rxrpc_local_destroyer(local); + break; + }

if (!skb_queue_empty(&local->reject_queue)) { rxrpc_reject_packets(local); @@ -458,6 +478,8 @@ static void rxrpc_local_processor(struct again = true; } } while (again); + + rxrpc_put_local(local); }

/*