A known weakness in ptr_ring design is that it does not handle well the
situation when ring is almost full: as entries are consumed they are
immediately used again by the producer, so consumer and producer are
writing to a shared cache line.

To fix this, add batching to consume calls: as entries are
consumed do not write NULL into the ring until we get
a multiple (in current implementation 2x) of cache lines
away from the producer. At that point, write them all out.

We do the write out in the reverse order to keep
producer from sharing cache with consumer for as long
as possible.

Writeout also triggers when ring wraps around - there's
no special reason to do this but it helps keep the code
a bit simpler.

What should we do if getting away from producer by 2 cache lines
would mean we are keeping the ring moe than half empty?
Maybe we should reduce the batching in this case,
current patch simply reduces the batching.

Notes:
- it is no longer true that a call to consume guarantees
  that the following call to produce will succeed.
  No users seem to assume that.
- batching can also in theory reduce the signalling rate:
  users that would previously send interrups to the producer
  to wake it up after consuming each entry would now only
  need to do this once in a batch.
  Doing this would be easy by returning a flag to the caller.
  No users seem to do signalling on consume yet so this was not
  implemented yet.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>

Add comments for the virtio_driver members that were not documented.
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

We already do a reset once in remove_vq_common -
there appears to be no point in doing another one
when we add/remove XDP.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

When ring size is small (<32 entries) making buffers smaller means a
full ring might not be able to hold enough buffers to fit a single large
packet.

Make sure a ring full of buffers is large enough to allow at least one
packet of max size.

Fixes: 2613af0e ("virtio_net: migrate mergeable rx buffers to page frag allocators")
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

We don't need to align length to any particular
value anymore. Aligning to L1 cache size probably
sill makes sense to reduce false sharing.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Use the new _ctx virtio API to maintain true length for each buffer.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

With mergeable buffers we never use s/g for rx,
so allow specifying context in that case.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Allow extra context per descriptor. To avoid slow down for data path,
this disables use of indirect descriptors for this vq.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Previous commit ("virtio: add context flag to find vqs")
added a new 'context' flag to vring_new_virtqueue(), but the
corresponding API in tools/virtio/ is not updated causing
build errors due to conflicting declarations.

Bring code in tools/virtio in sync with that in kernel.

I have used 'false' for the value of the new boolean 'context'
flag as that seems to be the best way to preserve existing
behavior.

Tested with:

$ make -C tools/virtio clean all ARCH=x86
Signed-off-by: Sekhar Nori <nsekhar@ti.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Allows maintaining extra context per vq.  For ease of use, passing in
NULL is legal and disables the feature for all vqs.

Includes fixes by Christian for s390, acked by Cornelia.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

We are going to add more parameters to find_vqs, let's wrap the call so
we don't need to tweak all drivers every time.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

There is an || vs && typo so the assert can never be triggered.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>

Pull x86 fixes from Thomas Gleixner:
 "The final fixes for 4.11:

   - prevent a triple fault with function graph tracing triggered via
     suspend to ram

   - prevent optimizing for size when function graph tracing is enabled
     and the compiler does not support -mfentry

   - prevent mwaitx() being called with a zero timeout as mwaitx() might
     never return. Observed on the new Ryzen CPUs"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  Prevent timer value 0 for MWAITX
  x86/build: convert function graph '-Os' error to warning
  ftrace/x86: Fix triple fault with graph tracing and suspend-to-ram

Pull scheduler fix from Thomas Gleixner:
 "A single fix for a cputime accounting regression which got introduced
  in the 4.11 cycle"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/cputime: Fix ksoftirqd cputime accounting regression

Newer hardware has uncovered a bug in the software implementation of
using MWAITX for the delay function. A value of 0 for the timer is meant
to indicate that a timeout will not be used to exit MWAITX. On newer
hardware this can result in MWAITX never returning, resulting in NMI
soft lockup messages being printed. On older hardware, some of the other
conditions under which MWAITX can exit masked this issue. The AMD APM
does not currently document this and will be updated.

Please refer to http://marc.info/?l=kvm&m=148950623231140 for
information regarding NMI soft lockup messages on an AMD Ryzen 1800X.
This has been root-caused as a 0 passed to MWAITX causing it to wait
indefinitely.

This change has the added benefit of avoiding the unnecessary setup of
MONITORX/MWAITX when the delay value is zero.
Signed-off-by: Janakarajan Natarajan <Janakarajan.Natarajan@amd.com>
Link: http://lkml.kernel.org/r/1493156643-29366-1-git-send-email-Janakarajan.Natarajan@amd.comSigned-off-by: Thomas Gleixner <tglx@linutronix.de>

Pull iov iter fix from Al Viro.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  fix a braino in ITER_PIPE iov_iter_revert()

Fixes: 27c0e374Tested-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

Pull clk fix from Stephen Boyd:
 "One odd config build fix for a recent Allwinner clock driver change
  that got merged. The common code called code in another file that
  wasn't always built. This just forces it on so people don't run into
  this bad configuration"

* tag 'clk-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux:
  clk: sunxi-ng: always select CCU_GATE

Pull networking fixes from David Miller:
 "Just a couple more stragglers, I really hope this is it.

  1) Don't let frags slip down into the GRO segmentation handlers, from
     Steffen Klassert.

  2) Truesize under-estimation triggers warnings in TCP over loopback
     with socket filters, 2 part fix from Eric Dumazet.

  3) Fix undesirable reset of bonding MTU to ETH_HLEN on slave removal,
     from Paolo Abeni.

  4) If we flush the XFRM policy after garbage collection, it doesn't
     work because stray entries can be created afterwards. Fix from Xin
     Long.

  5) Hung socket connection fixes in TIPC from Parthasarathy Bhuvaragan.

  6) Fix GRO regression with IPSEC when netfilter is disabled, from
     Sabrina Dubroca.

  7) Fix cpsw driver Kconfig dependency regression, from Arnd Bergmann"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  net: hso: register netdev later to avoid a race condition
  net: adjust skb->truesize in ___pskb_trim()
  tcp: do not underestimate skb->truesize in tcp_trim_head()
  bonding: avoid defaulting hard_header_len to ETH_HLEN on slave removal
  ipv4: Don't pass IP fragments to upper layer GRO handlers.
  cpsw/netcp: refine cpts dependency
  tipc: close the connection if protocol messages contain errors
  tipc: improve error validations for sockets in CONNECTING state
  tipc: Fix missing connection request handling
  xfrm: fix GRO for !CONFIG_NETFILTER
  xfrm: do the garbage collection after flushing policy

If the netdev is accessed before the urbs are initialized,
there will be NULL pointer dereferences. That is avoided by
registering it when it is fully initialized.

This case occurs e.g. if dhcpcd is running in the background
and the device is probed, either after insmod hso or
when the device appears on the usb bus.

A backtrace is the following:

[ 1357.356048] usb 1-2: new high-speed USB device number 12 using ehci-omap
[ 1357.551177] usb 1-2: New USB device found, idVendor=0af0, idProduct=8800
[ 1357.558654] usb 1-2: New USB device strings: Mfr=3, Product=2, SerialNumber=0
[ 1357.568572] usb 1-2: Product: Globetrotter HSUPA Modem
[ 1357.574096] usb 1-2: Manufacturer: Option N.V.
[ 1357.685882] hso 1-2:1.5: Not our interface
[ 1460.886352] hso: unloaded
[ 1460.889984] usbcore: deregistering interface driver hso
[ 1513.769134] hso: ../drivers/net/usb/hso.c: Option Wireless
[ 1513.846771] Unable to handle kernel NULL pointer dereference at virtual address 00000030
[ 1513.887664] hso 1-2:1.5: Not our interface
[ 1513.906890] usbcore: registered new interface driver hso
[ 1513.937988] pgd = ecdec000
[ 1513.949890] [00000030] *pgd=acd15831, *pte=00000000, *ppte=00000000
[ 1513.956573] Internal error: Oops: 817 [#1] PREEMPT SMP ARM
[ 1513.962371] Modules linked in: hso usb_f_ecm omap2430 bnep bluetooth g_ether usb_f_rndis u_ether libcomposite configfs ipv6 arc4 wl18xx wlcore mac80211 cfg80211 bq27xxx_battery panel_tpo_td028ttec1 omapdrm drm_kms_helper cfbfillrect snd_soc_simple_card syscopyarea cfbimgblt snd_soc_simple_card_utils sysfillrect sysimgblt fb_sys_fops snd_soc_omap_twl4030 cfbcopyarea encoder_opa362 drm twl4030_madc_hwmon wwan_on_off snd_soc_gtm601 pwm_omap_dmtimer generic_adc_battery connector_analog_tv pwm_bl extcon_gpio omap3_isp wlcore_sdio videobuf2_dma_contig videobuf2_memops w1_bq27000 videobuf2_v4l2 videobuf2_core omap_hdq snd_soc_omap_mcbsp ov9650 snd_soc_omap bmp280_i2c bmg160_i2c v4l2_common snd_pcm_dmaengine bmp280 bmg160_core at24 bmc150_magn_i2c nvmem_core videodev phy_twl4030_usb bmc150_accel_i2c tsc2007
[ 1514.037384]  bmc150_magn bmc150_accel_core media leds_tca6507 bno055 industrialio_triggered_buffer kfifo_buf gpio_twl4030 musb_hdrc snd_soc_twl4030 twl4030_vibra twl4030_madc twl4030_pwrbutton twl4030_charger industrialio w2sg0004 ehci_omap omapdss [last unloaded: hso]
[ 1514.062622] CPU: 0 PID: 3433 Comm: dhcpcd Tainted: G        W       4.11.0-rc8-letux+ #1
[ 1514.071136] Hardware name: Generic OMAP36xx (Flattened Device Tree)
[ 1514.077758] task: ee748240 task.stack: ecdd6000
[ 1514.082580] PC is at hso_start_net_device+0x50/0xc0 [hso]
[ 1514.088287] LR is at hso_net_open+0x68/0x84 [hso]
[ 1514.093231] pc : [<bf79c304>]    lr : [<bf79ced8>]    psr: a00f0013
sp : ecdd7e20  ip : 00000000  fp : ffffffff
[ 1514.105316] r10: 00000000  r9 : ed0e080c  r8 : ecd8fe2c
[ 1514.110839] r7 : bf79cef4  r6 : ecd8fe00  r5 : 00000000  r4 : ed0dbd80
[ 1514.117706] r3 : 00000000  r2 : c0020c80  r1 : 00000000  r0 : ecdb7800
[ 1514.124572] Flags: NzCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none
[ 1514.132110] Control: 10c5387d  Table: acdec019  DAC: 00000051
[ 1514.138153] Process dhcpcd (pid: 3433, stack limit = 0xecdd6218)
[ 1514.144470] Stack: (0xecdd7e20 to 0xecdd8000)
[ 1514.149078] 7e20: ed0dbd80 ecd8fe98 00000001 00000000 ecd8f800 ecd8fe00 ecd8fe60 00000000
[ 1514.157714] 7e40: ed0e080c bf79ced8 bf79ce70 ecd8f800 00000001 bf7a0258 ecd8f830 c068d958
[ 1514.166320] 7e60: c068d8b8 ecd8f800 00000001 00001091 00001090 c068dba4 ecd8f800 00001090
[ 1514.174926] 7e80: ecd8f940 ecd8f800 00000000 c068dc60 00000000 00000001 ed0e0800 ecd8f800
[ 1514.183563] 7ea0: 00000000 c06feaa8 c0ca39c2 beea57dc 00000020 00000000 306f7368 00000000
[ 1514.192169] 7ec0: 00000000 00000000 00001091 00000000 00000000 00000000 00000000 00008914
[ 1514.200805] 7ee0: eaa9ab60 beea57dc c0c9bfc0 eaa9ab40 00000006 00000000 00046858 c066a948
[ 1514.209411] 7f00: beea57dc eaa9ab60 ecc6b0c0 c02837b0 00000006 c0282c90 0000c000 c0283654
[ 1514.218017] 7f20: c09b0c00 c098bc31 00000001 c0c5e513 c0c5e513 00000000 c0151354 c01a20c0
[ 1514.226654] 7f40: c0c5e513 c01a3134 ecdd6000 c01a3160 ee7487f0 600f0013 00000000 ee748240
[ 1514.235260] 7f60: ee748734 00000000 ecc6b0c0 ecc6b0c0 beea57dc 00008914 00000006 00000000
[ 1514.243896] 7f80: 00046858 c02837b0 00001091 0003a1f0 00046608 0003a248 00000036 c01071e4
[ 1514.252502] 7fa0: ecdd6000 c0107040 0003a1f0 00046608 00000006 00008914 beea57dc 00001091
[ 1514.261108] 7fc0: 0003a1f0 00046608 0003a248 00000036 0003ac0c 00046608 00046610 00046858
[ 1514.269744] 7fe0: 0003a0ac beea57d4 000167eb b6f23106 400f0030 00000006 00000000 00000000
[ 1514.278411] [<bf79c304>] (hso_start_net_device [hso]) from [<bf79ced8>] (hso_net_open+0x68/0x84 [hso])
[ 1514.288238] [<bf79ced8>] (hso_net_open [hso]) from [<c068d958>] (__dev_open+0xa0/0xf4)
[ 1514.296600] [<c068d958>] (__dev_open) from [<c068dba4>] (__dev_change_flags+0x8c/0x130)
[ 1514.305023] [<c068dba4>] (__dev_change_flags) from [<c068dc60>] (dev_change_flags+0x18/0x48)
[ 1514.313934] [<c068dc60>] (dev_change_flags) from [<c06feaa8>] (devinet_ioctl+0x348/0x714)
[ 1514.322540] [<c06feaa8>] (devinet_ioctl) from [<c066a948>] (sock_ioctl+0x2b0/0x308)
[ 1514.330627] [<c066a948>] (sock_ioctl) from [<c0282c90>] (vfs_ioctl+0x20/0x34)
[ 1514.338165] [<c0282c90>] (vfs_ioctl) from [<c0283654>] (do_vfs_ioctl+0x82c/0x93c)
[ 1514.346038] [<c0283654>] (do_vfs_ioctl) from [<c02837b0>] (SyS_ioctl+0x4c/0x74)
[ 1514.353759] [<c02837b0>] (SyS_ioctl) from [<c0107040>] (ret_fast_syscall+0x0/0x1c)
[ 1514.361755] Code: e3822103 e3822080 e1822781 e5981014 (e5832030)
[ 1514.510833] ---[ end trace dfb3e53c657f34a0 ]---
Reported-by: H. Nikolaus Schaller <hns@goldelico.com>
Signed-off-by: Andreas Kemnade <andreas@kemnade.info>
Reviewed-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Andrey found a way to trigger the WARN_ON_ONCE(delta < len) in
skb_try_coalesce() using syzkaller and a filter attached to a TCP
socket.

As we did recently in commit 158f323b ("net: adjust skb->truesize in
pskb_expand_head()") we can adjust skb->truesize from ___pskb_trim(),
via a call to skb_condense().

If all frags were freed, then skb->truesize can be recomputed.

This call can be done if skb is not yet owned, or destructor is
sock_edemux().
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Andrey found a way to trigger the WARN_ON_ONCE(delta < len) in
skb_try_coalesce() using syzkaller and a filter attached to a TCP
socket over loopback interface.

I believe one issue with looped skbs is that tcp_trim_head() can end up
producing skb with under estimated truesize.

It hardly matters for normal conditions, since packets sent over
loopback are never truncated.

Bytes trimmed from skb->head should not change skb truesize, since
skb->head is not reallocated.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

On slave list updates, the bonding driver computes its hard_header_len
as the maximum of all enslaved devices's hard_header_len.
If the slave list is empty, e.g. on last enslaved device removal,
ETH_HLEN is used.

Since the bonding header_ops are set only when the first enslaved
device is attached, the above can lead to header_ops->create()
being called with the wrong skb headroom in place.

If bond0 is configured on top of ipoib devices, with the
following commands:

ifup bond0
for slave in $BOND_SLAVES_LIST; do
	ip link set dev $slave nomaster
done
ping -c 1 <ip on bond0 subnet>

we will obtain a skb_under_panic() with a similar call trace:
	skb_push+0x3d/0x40
	push_pseudo_header+0x17/0x30 [ib_ipoib]
	ipoib_hard_header+0x4e/0x80 [ib_ipoib]
	arp_create+0x12f/0x220
	arp_send_dst.part.19+0x28/0x50
	arp_solicit+0x115/0x290
	neigh_probe+0x4d/0x70
	__neigh_event_send+0xa7/0x230
	neigh_resolve_output+0x12e/0x1c0
	ip_finish_output2+0x14b/0x390
	ip_finish_output+0x136/0x1e0
	ip_output+0x76/0xe0
	ip_local_out+0x35/0x40
	ip_send_skb+0x19/0x40
	ip_push_pending_frames+0x33/0x40
	raw_sendmsg+0x7d3/0xb50
	inet_sendmsg+0x31/0xb0
	sock_sendmsg+0x38/0x50
	SYSC_sendto+0x102/0x190
	SyS_sendto+0xe/0x10
	do_syscall_64+0x67/0x180
	entry_SYSCALL64_slow_path+0x25/0x25

This change addresses the issue avoiding updating the bonding device
hard_header_len when the slaves list become empty, forbidding to
shrink it below the value used by header_ops->create().

The bug is there since commit 54ef3137 ("[PATCH] bonding: Handle large
hard_header_len") but the panic can be triggered only since
commit fc791b63 ("IB/ipoib: move back IB LL address into the hard
header").
Reported-by: Norbert P <noe@physik.uzh.ch>
Fixes: 54ef3137 ("[PATCH] bonding: Handle large hard_header_len")
Fixes: fc791b63 ("IB/ipoib: move back IB LL address into the hard header")
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Upper layer GRO handlers can not handle IP fragments, so
exit GRO processing in this case.

This fixes ESP GRO because the packet must be reassembled
before we can decapsulate, otherwise we get authentication
failures.

It also aligns IPv4 to IPv6 where packets with fragmentation
headers are not passed to upper layer GRO handlers.

Fixes: 7785bba2 ("esp: Add a software GRO codepath")
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Tony Lindgren reports a kernel oops that resulted from my compile-time
fix on the default config. This shows two problems:

a) configurations that did not already enable PTP_1588_CLOCK will
   now miss the cpts driver

b) when cpts support is disabled, the driver crashes. This is a
   preexisting problem that we did not notice before my patch.

While the second problem is still being investigated, this modifies
the dependencies again, getting us back to the original state, with
another 'select NET_PTP_CLASSIFY' added in to avoid the original
link error we got, and the 'depends on POSIX_TIMERS' to hide
the CPTS support when turning it on would be useless.

Cc: stable@vger.kernel.org # 4.11 needs this
Fixes: 07fef362 ("cpsw/netcp: cpts depends on posix_timers")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Steffen Klassert says:

====================
pull request (net): ipsec 2017-04-28

1) Do garbage collecting after a policy flush to remove old
   bundles immediately. From Xin Long.

2) Fix GRO if netfilter is not defined.
   From Sabrina Dubroca.

Please pull or let me know if there are problems.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Pull input fix from Dmitry Torokhov:
 "Yet another quirk to i8042 to get touchpad recognized on some laptops"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input:
  Input: i8042 - add Clevo P650RS to the i8042 reset list

When the base driver is enabled but all SoC specific drivers are turned
off, we now get a build error after code was added to always refer to the
clk gates:

drivers/clk/built-in.o: In function `ccu_pll_notifier_cb':
:(.text+0x154f8): undefined reference to `ccu_gate_helper_disable'
:(.text+0x15504): undefined reference to `ccu_gate_helper_enable'

This changes the Kconfig to always require the gate code to be built-in
when CONFIG_SUNXI_CCU is set.

Fixes: 02ae2bc6 ("clk: sunxi-ng: Add clk notifier to gate then ungate PLL clocks")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>

Pull btrfs fix from Chris Mason:
 "We have one more fix for btrfs.

  This gets rid of a new WARN_ON from rc1 that ended up making more
  noise than we really want. The larger fix for the underflow got
  delayed a bit and it's better for now to put it under
  CONFIG_BTRFS_DEBUG"

* 'for-linus-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
  btrfs: qgroup: move noisy underflow warning to debugging build

Parthasarathy Bhuvaragan says:

====================
tipc: fix hanging socket connections

This patch series contains fixes for the socket layer to
prevent hanging / stale connections.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

When a socket is shutting down, we notify the peer node about the
connection termination by reusing an incoming message if possible.
If the last received message was a connection acknowledgment
message, we reverse this message and set the error code to
TIPC_ERR_NO_PORT and send it to peer.

In tipc_sk_proto_rcv(), we never check for message errors while
processing the connection acknowledgment or probe messages. Thus
this message performs the usual flow control accounting and leaves
the session hanging.

In this commit, we terminate the connection when we receive such
error messages.
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Until now, the checks for sockets in CONNECTING state was based on
the assumption that the incoming message was always from the
peer's accepted data socket.

However an application using a non-blocking socket sends an implicit
connect, this socket which is in CONNECTING state can receive error
messages from the peer's listening socket. As we discard these
messages, the application socket hangs as there due to inactivity.
In addition to this, there are other places where we process errors
but do not notify the user.

In this commit, we process such incoming error messages and notify
our users about them using sk_state_change().
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

In filter_connect, we use waitqueue_active() to check for any
connections to wakeup. But waitqueue_active() is missing memory
barriers while accessing the critical sections, leading to
inconsistent results.

In this commit, we replace this with an SMP safe wq_has_sleeper()
using the generic socket callback sk_data_ready().
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Pull nfsd fixes from Bruce Fields:
 "Thanks to Ari Kauppi and Tuomas Haanpää at Synopsis for spotting bugs
  in our NFSv2/v3 xdr code that could crash the server or leak memory"

* tag 'nfsd-4.11-3' of git://linux-nfs.org/~bfields/linux:
  nfsd: stricter decoding of write-like NFSv2/v3 ops
  nfsd4: minor NFSv2/v3 write decoding cleanup
  nfsd: check for oversized NFSv2/v3 arguments

Pull ceph fix from Ilya Dryomov:
 "A fix for a kernel stack overflow bug in ceph setattr code, marked for
  stable"

* tag 'ceph-for-4.11-rc9' of git://github.com/ceph/ceph-client:
  ceph: fix recursion between ceph_set_acl() and __ceph_setattr()

Pull vfs fixes from Al Viro:

 - fix orangefs handling of faults on write() - I'd missed that one back
   when orangefs was going through review.

 - readdir counterpart of "9p: cope with bogus responses from server in
   p9_client_{read,write}" - server might be lying or broken, and we'd
   better not overrun the kmalloc'ed buffer we are copying the results
   into.

 - NFS O_DIRECT read/write can leave iov_iter advanced by too much;
   that's what had been causing iov_iter_pipe() warnings davej had been
   seeing.

 - statx_timestamp.tv_nsec type fix (s32 -> u32). That one really should
   go in before 4.11.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  uapi: change the type of struct statx_timestamp.tv_nsec to unsigned
  fix nfs O_DIRECT advancing iov_iter too much
  p9_client_readdir() fix
  orangefs_bufmap_copy_from_iovec(): fix EFAULT handling

The change in commit 1e2f82d1 ("statx: Kill fd-with-NULL-path
support in favour of AT_EMPTY_PATH") to error on a NULL pathname to
statx() is inconsistent.

It results in the error EINVAL for a NULL pathname.  Other system calls
with similar APIs (fchownat(), fstatat(), linkat()), return EFAULT.

The solution is simply to remove the EINVAL check.  As I already pointed
out in [1], user_path_at*() and filename_lookup() will handle the NULL
pathname as per the other APIs, to correctly produce the error EFAULT.

[1] https://lkml.org/lkml/2017/4/26/561Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Eric Sandeen <sandeen@sandeen.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

In xfrm_input() when called from GRO, async == 0, and we end up
skipping the processing in xfrm4_transport_finish(). GRO path will
always skip the NF_HOOK, so we don't need the special-case for
!NETFILTER during GRO processing.

Fixes: 7785bba2 ("esp: Add a software GRO codepath")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>

irq_time_read() returns the irqtime minus the ksoftirqd time. This
is necessary because irq_time_read() is used to substract the IRQ time
from the sum_exec_runtime of a task. If we were to include the softirq
time of ksoftirqd, this task would substract its own CPU time everytime
it updates ksoftirqd->sum_exec_runtime which would therefore never
progress.

But this behaviour got broken by:

  a499a5a1 ("sched/cputime: Increment kcpustat directly on irqtime account")

... which now includes ksoftirqd softirq time in the time returned by
irq_time_read().

This has resulted in wrong ksoftirqd cputime reported to userspace
through /proc/stat and thus "top" not showing ksoftirqd when it should
after intense networking load.

ksoftirqd->stime happens to be correct but it gets scaled down by
sum_exec_runtime through task_cputime_adjusted().

To fix this, just account the strict IRQ time in a separate counter and
use it to report the IRQ time.
Reported-and-tested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Link: http://lkml.kernel.org/r/1493129448-5356-1-git-send-email-fweisbec@gmail.comSigned-off-by: Ingo Molnar <mingo@kernel.org>