2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-24 21:24:00 +08:00
Commit Graph

542 Commits

Author SHA1 Message Date
wangyan
a691ffb46e vhost: correct the related warning message
Fixes: 'commit d588cf8f61 ("target: Fix se_tpg_tfo->tf_subsys regression + remove tf_subsystem")'
       'commit cbbd26b8b1 ("[iov_iter] new primitives - copy_from_iter_full() and friends")'

Signed-off-by: Yan Wang <wangyan122@huawei.com>
Reviewed-by: Jun Piao <piaojun@huawei.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2018-12-19 18:23:50 -05:00
Stefan Hajnoczi
6db3d8dc5d vhost/vsock: switch to a mutex for vhost_vsock_hash
Now that there are no more data path users of vhost_vsock_lock, it can
be turned into a mutex.  It's only used by .release() and in the
.ioctl() path.

Depends-on: <20181105103547.22018-1-stefanha@redhat.com>
Suggested-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
2018-12-19 18:23:49 -05:00
Linus Torvalds
d48f782e4f Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller:
 "A decent batch of fixes here. I'd say about half are for problems that
  have existed for a while, and half are for new regressions added in
  the 4.20 merge window.

   1) Fix 10G SFP phy module detection in mvpp2, from Baruch Siach.

   2) Revert bogus emac driver change, from Benjamin Herrenschmidt.

   3) Handle BPF exported data structure with pointers when building
      32-bit userland, from Daniel Borkmann.

   4) Memory leak fix in act_police, from Davide Caratti.

   5) Check RX checksum offload in RX descriptors properly in aquantia
      driver, from Dmitry Bogdanov.

   6) SKB unlink fix in various spots, from Edward Cree.

   7) ndo_dflt_fdb_dump() only works with ethernet, enforce this, from
      Eric Dumazet.

   8) Fix FID leak in mlxsw driver, from Ido Schimmel.

   9) IOTLB locking fix in vhost, from Jean-Philippe Brucker.

  10) Fix SKB truesize accounting in ipv4/ipv6/netfilter frag memory
      limits otherwise namespace exit can hang. From Jiri Wiesner.

  11) Address block parsing length fixes in x25 from Martin Schiller.

  12) IRQ and ring accounting fixes in bnxt_en, from Michael Chan.

  13) For tun interfaces, only iface delete works with rtnl ops, enforce
      this by disallowing add. From Nicolas Dichtel.

  14) Use after free in liquidio, from Pan Bian.

  15) Fix SKB use after passing to netif_receive_skb(), from Prashant
      Bhole.

  16) Static key accounting and other fixes in XPS from Sabrina Dubroca.

  17) Partially initialized flow key passed to ip6_route_output(), from
      Shmulik Ladkani.

  18) Fix RTNL deadlock during reset in ibmvnic driver, from Thomas
      Falcon.

  19) Several small TCP fixes (off-by-one on window probe abort, NULL
      deref in tail loss probe, SNMP mis-estimations) from Yuchung
      Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (93 commits)
  net/sched: cls_flower: Reject duplicated rules also under skip_sw
  bnxt_en: Fix _bnxt_get_max_rings() for 57500 chips.
  bnxt_en: Fix NQ/CP rings accounting on the new 57500 chips.
  bnxt_en: Keep track of reserved IRQs.
  bnxt_en: Fix CNP CoS queue regression.
  net/mlx4_core: Correctly set PFC param if global pause is turned off.
  Revert "net/ibm/emac: wrong bit is used for STA control"
  neighbour: Avoid writing before skb->head in neigh_hh_output()
  ipv6: Check available headroom in ip6_xmit() even without options
  tcp: lack of available data can also cause TSO defer
  ipv6: sr: properly initialize flowi6 prior passing to ip6_route_output
  mlxsw: spectrum_switchdev: Fix VLAN device deletion via ioctl
  mlxsw: spectrum_router: Relax GRE decap matching check
  mlxsw: spectrum_switchdev: Avoid leaking FID's reference count
  mlxsw: spectrum_nve: Remove easily triggerable warnings
  ipv4: ipv6: netfilter: Adjust the frag mem limit when truesize changes
  sctp: frag_point sanity check
  tcp: fix NULL ref in tail loss probe
  tcp: Do not underestimate rwnd_limited
  net: use skb_list_del_init() to remove from RX sublists
  ...
2018-12-09 15:12:33 -08:00
Stefan Hajnoczi
834e772c8d vhost/vsock: fix use-after-free in network stack callers
If the network stack calls .send_pkt()/.cancel_pkt() during .release(),
a struct vhost_vsock use-after-free is possible.  This occurs because
.release() does not wait for other CPUs to stop using struct
vhost_vsock.

Switch to an RCU-enabled hashtable (indexed by guest CID) so that
.release() can wait for other CPUs by calling synchronize_rcu().  This
also eliminates vhost_vsock_lock acquisition in the data path so it
could have a positive effect on performance.

This is CVE-2018-14625 "kernel: use-after-free Read in vhost_transport_send_pkt".

Cc: stable@vger.kernel.org
Reported-and-tested-by: syzbot+bd391451452fb0b93039@syzkaller.appspotmail.com
Reported-by: syzbot+e3e074963495f92a89ed@syzkaller.appspotmail.com
Reported-by: syzbot+d5a0a170c5069658b141@syzkaller.appspotmail.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
2018-12-06 14:28:38 -05:00
Stefan Hajnoczi
c38f57da42 vhost/vsock: fix reset orphans race with close timeout
If a local process has closed a connected socket and hasn't received a
RST packet yet, then the socket remains in the table until a timeout
expires.

When a vhost_vsock instance is released with the timeout still pending,
the socket is never freed because vhost_vsock has already set the
SOCK_DONE flag.

Check if the close timer is pending and let it close the socket.  This
prevents the race which can leak sockets.

Reported-by: Maximilian Riemensberger <riemensberger@cadami.net>
Cc: Graham Whaley <graham.whaley@gmail.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2018-12-06 14:22:34 -05:00
Jean-Philippe Brucker
e3f787189e vhost: fix IOTLB locking
Commit 78139c94dc ("net: vhost: lock the vqs one by one") moved the vq
lock to improve scalability, but introduced a possible deadlock in
vhost-iotlb. vhost_iotlb_notify_vq() now takes vq->mutex while holding
the device's IOTLB spinlock. And on the vhost_iotlb_miss() path, the
spinlock is taken while holding vq->mutex.

Since calling vhost_poll_queue() doesn't require any lock, avoid the
deadlock by not taking vq->mutex.

Fixes: 78139c94dc ("net: vhost: lock the vqs one by one")
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-12-03 15:52:30 -08:00
Linus Torvalds
b5b1de3537 virtio, vhost: fixes, tweaks
virtio balloon page hinting support
 vhost scsi control queue
 
 misc fixes.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJb222AAAoJECgfDbjSjVRpfHMH/1uh87pIj6Qbh9LRZm0dRVHs
 iEuIa0TECb+9AmqHRBliEcqWjihWnlQnSwE6d/ZTk9cH9zEEXsIu0B7nDzjGwJ5b
 m7wq679JqrtGpCdQhRH85sk8P3fs5ldatdbc4/0fsPwwkoXHcqTOpSZWyhtQHGc4
 EkzzxHXVhVXgRBjzLXVCMoOAQ+8QfMZFrKIgKuOB0I4OVughFrAGf0Hemm18f4CL
 5+YwsJQjleDkm+Udf+FTQS2oZ57DJsOLm2bwoKgqCkBaDfPlR92uWjgTa50WXggo
 RaokpFQkJKpz11yenezslzrVWUJApnWnUhfRd71t1ttvujrrcD9zUvWEVMURbuU=
 =2i/5
 -----END PGP SIGNATURE-----

Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio/vhost updates from Michael Tsirkin:
 "Fixes and tweaks:

   - virtio balloon page hinting support

   - vhost scsi control queue

   - misc fixes"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  MAINTAINERS: remove reference to bogus vsock file
  vhost/scsi: Use common handling code in request queue handler
  vhost/scsi: Extract common handling code from control queue handler
  vhost/scsi: Respond to control queue operations
  vhost/scsi: truncate T10 PI iov_iter to prot_bytes
  virtio-balloon: VIRTIO_BALLOON_F_PAGE_POISON
  mm/page_poison: expose page_poisoning_enabled to kernel modules
  virtio-balloon: VIRTIO_BALLOON_F_FREE_PAGE_HINT
  kvm_config: add CONFIG_VIRTIO_MENU
2018-11-01 14:42:49 -07:00
Jason Wang
ff002269a4 vhost: Fix Spectre V1 vulnerability
The idx in vhost_vring_ioctl() was controlled by userspace, hence a
potential exploitation of the Spectre variant 1 vulnerability.

Fixing this by sanitizing idx before using it to index d->vqs.

Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-31 12:39:15 -07:00
Bijan Mottahedeh
09d7583294 vhost/scsi: Use common handling code in request queue handler
Change the request queue handler to use common handling routines same
as the control queue handler.

Signed-off-by: Bijan Mottahedeh <bijan.mottahedeh@oracle.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2018-10-24 21:16:13 -04:00
Bijan Mottahedeh
3f8ca2e115 vhost/scsi: Extract common handling code from control queue handler
Prepare to change the request queue handler to use common handling
routines.

Signed-off-by: Bijan Mottahedeh <bijan.mottahedeh@oracle.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2018-10-24 21:16:13 -04:00
Bijan Mottahedeh
0d02dbd68c vhost/scsi: Respond to control queue operations
The vhost-scsi driver currently does not handle any control queue
operations. In particular, vhost_scsi_ctl_handle_kick, merely prints out
a debug message but does nothing else. This can cause guest VMs to hang.

As part of SCSI recovery from an error, e.g., an I/O timeout, the SCSI
midlayer attempts to abort the failed operation. The SCSI virtio driver
translates the abort to a SCSI TMF request that gets put on the control
queue (virtscsi_abort -> virtscsi_tmf). The SCSI virtio driver then
waits indefinitely for this request to be completed, but it never will
because vhost-scsi never responds to that request.

To avoid a hang, always respond to control queue operations; explicitly
reject TMF requests, and return a no-op response to event requests.

Signed-off-by: Bijan Mottahedeh <bijan.mottahedeh@oracle.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2018-10-24 21:16:13 -04:00
Greg Edwards
4542d623c7 vhost/scsi: truncate T10 PI iov_iter to prot_bytes
Commands with protection information included were not truncating the
protection iov_iter to the number of protection bytes in the command.
This resulted in vhost_scsi mis-calculating the size of the protection
SGL in vhost_scsi_calc_sgls(), and including both the protection and
data SG entries in the protection SGL.

Fixes: 09b13fa8c1 ("vhost/scsi: Add ANY_LAYOUT support in vhost_scsi_handle_vq")
Signed-off-by: Greg Edwards <gedwards@ddn.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Fixes: 09b13fa8c1
Cc: stable@vger.kernel.org
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
2018-10-24 21:16:13 -04:00
Tonghao Zhang
abf1a08ff3 net: vhost: remove bad code line
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-07 21:31:32 -07:00
Tonghao Zhang
441abde4cd net: vhost: add rx busy polling in tx path
This patch improves the guest receive performance.
On the handle_tx side, we poll the sock receive queue at the
same time. handle_rx do that in the same way.

We set the poll-us=100us and use the netperf to test throughput
and mean latency. When running the tests, the vhost-net kthread
of that VM, is alway 100% CPU. The commands are shown as below.

Rx performance is greatly improved by this patch. There is not
notable performance change on tx with this series though. This
patch is useful for bi-directional traffic.

netperf -H IP -t TCP_STREAM -l 20 -- -O "THROUGHPUT, THROUGHPUT_UNITS, MEAN_LATENCY"

Topology:
[Host] ->linux bridge -> tap vhost-net ->[Guest]

TCP_STREAM:
* Without the patch:  19842.95 Mbps, 6.50 us mean latency
* With the patch:     37598.20 Mbps, 3.43 us mean latency

Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-26 20:25:55 -07:00
Tonghao Zhang
dc151282bb net: vhost: factor out busy polling logic to vhost_net_busy_poll()
Factor out generic busy polling logic and will be
used for in tx path in the next patch. And with the patch,
qemu can set differently the busyloop_timeout for rx queue.

To avoid duplicate codes, introduce the helper functions:
* sock_has_rx_data(changed from sk_has_rx_data)
* vhost_net_busy_poll_try_queue

Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-26 20:25:55 -07:00
Tonghao Zhang
a6a67a2f34 net: vhost: replace magic number of lock annotation
Use the VHOST_NET_VQ_XXX as a subclass for mutex_lock_nested.

Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-26 20:25:55 -07:00
Tonghao Zhang
78139c94dc net: vhost: lock the vqs one by one
This patch changes the way that lock all vqs
at the same, to lock them one by one. It will
be used for next patch to avoid the deadlock.

Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-26 20:25:54 -07:00
Dan Carpenter
8a1aff144d vhost_net: add a missing error return
We accidentally left out this error return so it leads to some use after
free bugs later on.

Fixes: 0a0be13b8f ("vhost_net: batch submitting XDP buffers to underlayer sockets")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-21 09:05:57 -07:00
Jason Wang
0a0be13b8f vhost_net: batch submitting XDP buffers to underlayer sockets
This patch implements XDP batching for vhost_net. The idea is first to
try to do userspace copy and build XDP buff directly in vhost. Instead
of submitting the packet immediately, vhost_net will batch them in an
array and submit every 64 (VHOST_NET_BATCH) packets to the under layer
sockets through msg_control of sendmsg().

When XDP is enabled on the TUN/TAP, TUN/TAP can process XDP inside a
loop without caring GUP thus it can do batch map flushing. When XDP is
not enabled or not supported, the underlayer socket need to build skb
and pass it to network core. The batched packet submission allows us
to do batching like netif_receive_skb_list() in the future.

This saves lots of indirect calls for better cache utilization. For
the case that we can't so batching e.g when sndbuf is limited or
packet size is too large, we will go for usual one packet per
sendmsg() way.

Doing testpmd on various setups gives us:

Test                /+pps%
XDP_DROP on TAP     /+44.8%
XDP_REDIRECT on TAP /+29%
macvtap (skb)       /+26%

Netperf tests shows obvious improvements for small packet transmission:

size/session/+thu%/+normalize%
   64/     1/   +2%/    0%
   64/     2/   +3%/   +1%
   64/     4/   +7%/   +5%
   64/     8/   +8%/   +6%
  256/     1/   +3%/    0%
  256/     2/  +10%/   +7%
  256/     4/  +26%/  +22%
  256/     8/  +27%/  +23%
  512/     1/   +3%/   +2%
  512/     2/  +19%/  +14%
  512/     4/  +43%/  +40%
  512/     8/  +45%/  +41%
 1024/     1/   +4%/    0%
 1024/     2/  +27%/  +21%
 1024/     4/  +38%/  +73%
 1024/     8/  +15%/  +24%
 2048/     1/  +10%/   +7%
 2048/     2/  +16%/  +12%
 2048/     4/    0%/   +2%
 2048/     8/    0%/   +2%
 4096/     1/  +36%/  +60%
 4096/     2/  -11%/  -26%
 4096/     4/    0%/  +14%
 4096/     8/    0%/   +4%
16384/     1/   -1%/   +5%
16384/     2/    0%/   +2%
16384/     4/    0%/   -3%
16384/     8/    0%/   +4%
65535/     1/    0%/  +10%
65535/     2/    0%/   +8%
65535/     4/    0%/   +1%
65535/     8/    0%/   +3%

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-13 09:25:41 -07:00
Jason Wang
fe8dd45bb7 tun: switch to new type of msg_control
This patch introduces to a new tun/tap specific msg_control:

#define TUN_MSG_UBUF 1
#define TUN_MSG_PTR  2
struct tun_msg_ctl {
       int type;
       void *ptr;
};

This allows us to pass different kinds of msg_control through
sendmsg(). The first supported type is ubuf (TUN_MSG_UBUF) which will
be used by the existed vhost_net zerocopy code. The second is XDP
buff, which allows vhost_net to pass XDP buff to TUN. This could be
used to implement accepting an array of XDP buffs from vhost_net in
the following patches.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-13 09:25:40 -07:00
Linus Torvalds
050cdc6c95 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller:

 1) ICE, E1000, IGB, IXGBE, and I40E bug fixes from the Intel folks.

 2) Better fix for AB-BA deadlock in packet scheduler code, from Cong
    Wang.

 3) bpf sockmap fixes (zero sized key handling, etc.) from Daniel
    Borkmann.

 4) Send zero IPID in TCP resets and SYN-RECV state ACKs, to prevent
    attackers using it as a side-channel. From Eric Dumazet.

 5) Memory leak in mediatek bluetooth driver, from Gustavo A. R. Silva.

 6) Hook up rt->dst.input of ipv6 anycast routes properly, from Hangbin
    Liu.

 7) hns and hns3 bug fixes from Huazhong Tan.

 8) Fix RIF leak in mlxsw driver, from Ido Schimmel.

 9) iova range check fix in vhost, from Jason Wang.

10) Fix hang in do_tcp_sendpages() with tls, from John Fastabend.

11) More r8152 chips need to disable RX aggregation, from Kai-Heng Feng.

12) Memory exposure in TCA_U32_SEL handling, from Kees Cook.

13) TCP BBR congestion control fixes from Kevin Yang.

14) hv_netvsc, ignore non-PCI devices, from Stephen Hemminger.

15) qed driver fixes from Tomer Tayar.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (77 commits)
  net: sched: Fix memory exposure from short TCA_U32_SEL
  qed: fix spelling mistake "comparsion" -> "comparison"
  vhost: correctly check the iova range when waking virtqueue
  qlge: Fix netdev features configuration.
  net: macb: do not disable MDIO bus at open/close time
  Revert "net: stmmac: fix build failure due to missing COMMON_CLK dependency"
  net: macb: Fix regression breaking non-MDIO fixed-link PHYs
  mlxsw: spectrum_switchdev: Do not leak RIFs when removing bridge
  i40e: fix condition of WARN_ONCE for stat strings
  i40e: Fix for Tx timeouts when interface is brought up if DCB is enabled
  ixgbe: fix driver behaviour after issuing VFLR
  ixgbe: Prevent unsupported configurations with XDP
  ixgbe: Replace GFP_ATOMIC with GFP_KERNEL
  igb: Replace mdelay() with msleep() in igb_integrated_phy_loopback()
  igb: Replace GFP_ATOMIC with GFP_KERNEL in igb_sw_init()
  igb: Use an advanced ctx descriptor for launchtime
  e1000: ensure to free old tx/rx rings in set_ringparam()
  e1000: check on netif_running() before calling e1000_up()
  ixgb: use dma_zalloc_coherent instead of allocator/memset
  ice: Trivial formatting fixes
  ...
2018-08-27 11:59:39 -07:00
Jason Wang
2d66f997f0 vhost: correctly check the iova range when waking virtqueue
We don't wakeup the virtqueue if the first byte of pending iova range
is the last byte of the range we just got updated. This will lead a
virtqueue to wait for IOTLB updating forever. Fixing by correct the
check and wake up the virtqueue in this case.

Fixes: 6b1e6cc785 ("vhost: new device IOTLB API")
Reported-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Tested-by: Peter Xu <peterx@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-25 17:39:41 -07:00
Linus Torvalds
d002924f93 virtio, vhost: fixes, tweaks
No new features but a bunch of tweaks such as
 switching balloon from oom notifier to shrinker.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJbfIxQAAoJECgfDbjSjVRp/3AH/1z+pJMvkDQN412qVOFEo+BI
 gRnTBw+0XdnR76eug11PFhMqBupQXwJ26NHfmSkoxqXy2NwRxX5Za2dHE1KJ+Sws
 NeBfwVIqwFBufGHMG7Uq/JNsLgSEB/ketNPWnJIzNVQbQOfdGbhmYMyS0nSy4S8m
 JcZX/iwA7XTxApSL5IWCM0ScddgFTdTkB6K/me8XNnIFWsX0mnRWly+L/7CDNx18
 QdKWsAimZxIjtF6DIYieph1oirzeWmAf42raEghNe1dSeT3k4CnU+hYw/ofMo9Wm
 5gtFRLP8vTyR1zlaSTDxElgFcTwwgiTpkX+xd1htegrm8M7Yd3RO/WUTFCFPhf4=
 =JrpR
 -----END PGP SIGNATURE-----

Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:
 "virtio, vhost: fixes, tweaks

  No new features but a bunch of tweaks such as switching balloon from
  oom notifier to shrinker"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  vhost/scsi: increase VHOST_SCSI_PREALLOC_PROT_SGLS to 2048
  vhost: allow vhost-scsi driver to be built-in
  virtio: pci-legacy: Validate queue pfn
  virtio: mmio-v1: Validate queue PFN
  virtio_balloon: replace oom notifier with shrinker
  virtio-balloon: kzalloc the vb struct
  virtio-balloon: remove BUG() in init_vqs
2018-08-24 08:45:19 -07:00
Greg Edwards
864d39df09 vhost/scsi: increase VHOST_SCSI_PREALLOC_PROT_SGLS to 2048
The current value of VHOST_SCSI_PREALLOC_PROT_SGLS is too small to
accommodate larger I/Os, e.g. 16-32 MiB, when the VIRTIO_SCSI_F_T10_PI
feature bit is negotiated and the backing store supports T10 PI.

vhost-scsi rejects the command with errors like:

[   59.581317] vhost_scsi_calc_sgls: requested sgl_count: 1820 exceeds pre-allocated max_sgls: 512

Signed-off-by: Greg Edwards <gedwards@ddn.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2018-08-22 01:01:47 +03:00
Greg Edwards
84f3396b71 vhost: allow vhost-scsi driver to be built-in
It's useful to allow vhost-scsi to be built-in when testing vhost in L1
+ L2 VMs and booting L1 VM with QEMU '-kernel' option.

Signed-off-by: Greg Edwards <gedwards@ddn.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2018-08-22 01:01:32 +03:00
Linus Torvalds
72f02ba66b SCSI misc on 20180815
This is mostly updates to the usual drivers: mpt3sas, lpfc, qla2xxx,
 hisi_sas, smartpqi, megaraid_sas, arcmsr.  In addition, with the
 continuing absence of Nic we have target updates for tcmu and target
 core (all with reviews and acks).  The biggest observable change is
 going to be that we're (again) trying to switch to mulitqueue as the
 default (a user can still override the setting on the kernel command
 line).  Other major core stuff is the removal of the remaining
 Microchannel drivers, an update of the internal timers and some
 reworks of completion and result handling.
 
 Signed-off-by: James E.J. Bottomley <jejb@linux.vnet.ibm.com>
 -----BEGIN PGP SIGNATURE-----
 
 iJwEABMIAEQWIQTnYEDbdso9F2cI+arnQslM7pishQUCW3R3niYcamFtZXMuYm90
 dG9tbGV5QGhhbnNlbnBhcnRuZXJzaGlwLmNvbQAKCRDnQslM7pishauRAP4yfBKK
 dbxF81c/Bxi/Stk16FWkOOrjs4CizwmnMcpM5wD/UmM9o6ebDzaYpZgA8wIl7X/N
 o/JckEZZpIp+5NySZNc=
 =ggLB
 -----END PGP SIGNATURE-----

Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi

Pull SCSI updates from James Bottomley:
 "This is mostly updates to the usual drivers: mpt3sas, lpfc, qla2xxx,
  hisi_sas, smartpqi, megaraid_sas, arcmsr.

  In addition, with the continuing absence of Nic we have target updates
  for tcmu and target core (all with reviews and acks).

  The biggest observable change is going to be that we're (again) trying
  to switch to mulitqueue as the default (a user can still override the
  setting on the kernel command line).

  Other major core stuff is the removal of the remaining Microchannel
  drivers, an update of the internal timers and some reworks of
  completion and result handling"

* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (203 commits)
  scsi: core: use blk_mq_run_hw_queues in scsi_kick_queue
  scsi: ufs: remove unnecessary query(DM) UPIU trace
  scsi: qla2xxx: Fix issue reported by static checker for qla2x00_els_dcmd2_sp_done()
  scsi: aacraid: Spelling fix in comment
  scsi: mpt3sas: Fix calltrace observed while running IO & reset
  scsi: aic94xx: fix an error code in aic94xx_init()
  scsi: st: remove redundant pointer STbuffer
  scsi: qla2xxx: Update driver version to 10.00.00.08-k
  scsi: qla2xxx: Migrate NVME N2N handling into state machine
  scsi: qla2xxx: Save frame payload size from ICB
  scsi: qla2xxx: Fix stalled relogin
  scsi: qla2xxx: Fix race between switch cmd completion and timeout
  scsi: qla2xxx: Fix Management Server NPort handle reservation logic
  scsi: qla2xxx: Flush mailbox commands on chip reset
  scsi: qla2xxx: Fix unintended Logout
  scsi: qla2xxx: Fix session state stuck in Get Port DB
  scsi: qla2xxx: Fix redundant fc_rport registration
  scsi: qla2xxx: Silent erroneous message
  scsi: qla2xxx: Prevent sysfs access when chip is down
  scsi: qla2xxx: Add longer window for chip reset
  ...
2018-08-15 22:06:26 -07:00
David S. Miller
a736e07468 Merge ra.kernel.org:/pub/scm/linux/kernel/git/davem/net
Overlapping changes in RXRPC, changing to ktime_get_seconds() whilst
adding some tracepoints.

Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-09 11:52:36 -07:00
Jason Wang
b13f9c6364 vhost: reset metadata cache when initializing new IOTLB
We need to reset metadata cache during new IOTLB initialization,
otherwise the stale pointers to previous IOTLB may be still accessed
which will lead a use after free.

Reported-by: syzbot+c51e6736a1bf614b3272@syzkaller.appspotmail.com
Fixes: f889491380 ("vhost: introduce O(1) vq metadata cache")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 09:44:39 -07:00
Jason Wang
429711aec2 vhost: switch to use new message format
We use to have message like:

struct vhost_msg {
	int type;
	union {
		struct vhost_iotlb_msg iotlb;
		__u8 padding[64];
	};
};

Unfortunately, there will be a hole of 32bit in 64bit machine because
of the alignment. This leads a different formats between 32bit API and
64bit API. What's more it will break 32bit program running on 64bit
machine.

So fixing this by introducing a new message type with an explicit
32bit reserved field after type like:

struct vhost_msg_v2 {
	__u32 type;
	__u32 reserved;
	union {
		struct vhost_iotlb_msg iotlb;
		__u8 padding[64];
	};
};

We will have a consistent ABI after switching to use this. To enable
this capability, introduce a new ioctl (VHOST_SET_BAKCEND_FEATURE) for
userspace to enable this feature (VHOST_BACKEND_F_IOTLB_V2).

Fixes: 6b1e6cc785 ("vhost: new device IOTLB API")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-06 10:41:04 -07:00
Mike Christie
25b88550b7 scsi: target: loop, usb, vhost, xen: use target_remove_session
This converts drivers that were only calling transport_deregister_session
to use target_remove_session. The calling of
transport_deregister_session_configfs via target_remove_session for these
types of drivers is ok, because they were not exporting info from fields
like sess_acl_list, sess->se_tpg and sess->fabric_sess_ptr from configfs
accessible functions, so they will see no difference.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Felipe Balbi <balbi@kernel.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2018-08-02 15:29:31 -04:00
Mike Christie
fa83428730 scsi: target: rename target_alloc_session
Rename target_alloc_session to target_setup_session to avoid confusion with
the other transport session allocation function that only allocates the
session and because the target_alloc_session does so much more. It
allocates the session, sets up the nacl and registers the session.

The next patch will then add a remove function to match the setup in this
one, so it should make sense for all drivers, except iscsi, to just call
those 2 functions to setup and remove a session.

iscsi will continue to be the odd driver.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Chris Boot <bootc@bootc.net>
Cc: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Cc: Michael Cyr <mikecyr@linux.vnet.ibm.com>
Cc: <qla2xxx-upstream@qlogic.com>
Cc: Johannes Thumshirn <jth@kernel.org>
Cc: Felipe Balbi <balbi@kernel.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2018-08-02 15:29:31 -04:00
Jason Wang
4afb52c2af vhost_net: batch update used ring for datacopy TX
Like commit e2b3b35eb9 ("vhost_net: batch used ring update in rx"),
this patches implements batch used ring update for datacopy TX
(zerocopy has already done some kind of batching).

Testpmd transmission from guest to host (XDP_DROP on tap) shows 25.8%
improvement (from ~3.1Mpps to ~3.9Mpps) on Broadwell i7-5600U CPU @
2.60GHz machine. Netperf TCP tests does not show obvious differences.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-22 09:43:31 -07:00
Jason Wang
d0d8697187 vhost_net: rename VHOST_RX_BATCH to VHOST_NET_BATCH
A more generic name which could be used for TX as well.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-22 09:43:31 -07:00
Jason Wang
09c3248938 vhost_net: rename vhost_rx_signal_used() to vhost_net_signal_used()
Rename for reusing this for TX.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-22 09:43:31 -07:00
Jason Wang
0d20bdf34d vhost_net: split out datacopy logic
Instead of mixing zerocopy and datacopy logics, this patch tries to
split datacopy logic out. This results for a more compact code and
ad-hoc optimization could be done on top more easily.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-22 09:43:31 -07:00
Jason Wang
c92a8a8cb7 vhost_net: introduce tx_can_batch()
Introduce tx_can_batch() to determine whether TX could be
batched. This will help to reduce the code duplication in the future.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-22 09:43:31 -07:00
Jason Wang
a2a91a137a vhost_net: introduce get_tx_bufs()
Factor out logic of getting tx buffer and iov iter
initialization. This will be used for reducing codes duplication in
the future.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-22 09:43:31 -07:00
Jason Wang
272f35cba5 vhost_net: introduce vhost_exceeds_weight()
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-22 09:43:30 -07:00
Jason Wang
b0d0ea50e7 vhost_net: introduce helper to initialize tx iov iter
Introduce init_iov_iter() in order to be reused by future patch.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-22 09:43:30 -07:00
Jason Wang
652e4f3e82 vhost_net: drop unnecessary parameter
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-22 09:43:30 -07:00
Toshiaki Makita
6369fec5be vhost_net: Avoid rx vring kicks during busyloop
We may run out of avail rx ring descriptor under heavy load but busypoll
did not detect it so busypoll may have exited prematurely. Avoid this by
checking rx ring full during busypoll.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-04 21:30:47 +09:00
Toshiaki Makita
be294a51ad vhost_net: Avoid rx queue wake-ups during busypoll
We may run handle_rx() while rx work is queued. For example a packet can
push the rx work during the window before handle_rx calls
vhost_net_disable_vq().
In that case busypoll immediately exits due to vhost_has_work()
condition and enables vq again. This can lead to another unnecessary rx
wake-ups, so poll rx work instead of enabling the vq.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-04 21:30:46 +09:00
Toshiaki Makita
027b17603b vhost_net: Avoid tx vring kicks during busyloop
Under heavy load vhost busypoll may run without suppressing
notification. For example tx zerocopy callback can push tx work while
handle_tx() is running, then busyloop exits due to vhost_has_work()
condition and enables notification but immediately reenters handle_tx()
because the pushed work was tx. In this case handle_tx() tries to
disable notification again, but when using event_idx it by design
cannot. Then busyloop will run without suppressing notification.
Another example is the case where handle_tx() tries to enable
notification but avail idx is advanced so disables it again. This case
also leads to the same situation with event_idx.

The problem is that once we enter this situation busyloop does not work
under heavy load for considerable amount of time, because notification
is likely to happen during busyloop and handle_tx() immediately enables
notification after notification happens. Specifically busyloop detects
notification by vhost_has_work() and then handle_tx() calls
vhost_enable_notify(). Because the detected work was the tx work, it
enters handle_tx(), and enters busyloop without suppression again.
This is likely to be repeated, so with event_idx we are almost not able
to suppress notification in this case.

To fix this, poll the work instead of enabling notification when
busypoll is interrupted by something. IMHO vhost_has_work() is kind of
interruption rather than a signal to completely cancel the busypoll, so
let's run busypoll after the necessary work is done.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-04 21:30:46 +09:00
Toshiaki Makita
28b9b33b98 vhost_net: Rename local variables in vhost_net_rx_peek_head_len
So we can easily see which variable is for which, tx or rx.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-04 21:30:46 +09:00
Bart Van Assche
aa090eabcb scsi: target: Remove second argument from fabric_make_tpg()
Since most target drivers do not use the second fabric_make_tpg() argument
("group") and since it is trivial to derive the group pointer from the wwn
pointer, do not pass the group pointer to fabric_make_tpg().

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Felipe Balbi <felipe.balbi@linux.intel.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2018-07-02 16:44:32 -04:00
Jason Wang
b8f1f65882 vhost_net: validate sock before trying to put its fd
Sock will be NULL if we pass -1 to vhost_net_set_backend(), but when
we meet errors during ubuf allocation, the code does not check for
NULL before calling sockfd_put(), this will lead NULL
dereferencing. Fixing by checking sock pointer before.

Fixes: bab632d69e ("vhost: vhost TX zero-copy support")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-06-23 10:23:49 +09:00
Matthew Wilcox
10e9cbb6b5 scsi: target: Convert target drivers to use sbitmap
The sbitmap and the percpu_ida perform essentially the same task,
allocating tags for commands.  The sbitmap outperforms the percpu_ida as
documented here: https://lkml.org/lkml/2014/4/22/553

The sbitmap interface is a little harder to use, but being able to remove
the percpu_ida code and getting better performance justifies the additional
complexity.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Acked-by: Felipe Balbi <felipe.balbi@linux.intel.com>	# f_tcm
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2018-06-19 22:02:25 -04:00
Matthew Wilcox
83c2b54b92 scsi: target: Abstract tag freeing
Introduce target_free_tag() and convert all drivers to use it.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2018-06-19 22:02:25 -04:00
Linus Torvalds
2f3f056685 virtio, vhost: features, fixes
VF support for virtio.
 DMA barriers for virtio strong barriers.
 Bugfixes.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJbHykhAAoJECgfDbjSjVRpTAgH/iS2bIo0DOvlC5wPljVMopKV
 fD3n5dPUDOc2yWv2H9wwc3xDO6f3kByMjLnHvn+PM2ZX/ms731QaPd5sTlzUm+jj
 LzvI0gc9cyym8INZcU+xuTLQhiC13wZmZIHuP7X4TRsKBPTSaT+goSRk63qmuJF7
 0V8BJcj2QXaygaWD1P5SczrL4nFK7nn5PWZqZTPk3ohuLcUtgcv6Qb+idj+tCnov
 6osK122JkN6GO/LuVgEPxKamDgi9SB+sXeqNCYSzgKzXEUyC/cMtxyExXKxwqDEI
 MCcfPcoS1IklvII0ZYCTFKJYDTkPCjZ3HQwxF9aVjy4FirJGpRI3NRp5Eqr9rG4=
 =+EYn
 -----END PGP SIGNATURE-----

Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:
 "virtio, vhost: features, fixes

   - PCI virtual function support for virtio

   - DMA barriers for virtio strong barriers

   - bugfixes"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio: update the comments for transport features
  virtio_pci: support enabling VFs
  vhost: fix info leak due to uninitialized memory
  virtio_ring: switch to dma_XX barriers for rpmsg
2018-06-16 06:35:02 +09:00
Kees Cook
6396bb2215 treewide: kzalloc() -> kcalloc()
The kzalloc() function has a 2-factor argument form, kcalloc(). This
patch replaces cases of:

        kzalloc(a * b, gfp)

with:
        kcalloc(a * b, gfp)

as well as handling cases of:

        kzalloc(a * b * c, gfp)

with:

        kzalloc(array3_size(a, b, c), gfp)

as it's slightly less ugly than:

        kzalloc_array(array_size(a, b), c, gfp)

This does, however, attempt to ignore constant size factors like:

        kzalloc(4 * 1024, gfp)

though any constants defined via macros get caught up in the conversion.

Any factors with a sizeof() of "unsigned char", "char", and "u8" were
dropped, since they're redundant.

The Coccinelle script used for this was:

// Fix redundant parens around sizeof().
@@
type TYPE;
expression THING, E;
@@

(
  kzalloc(
-	(sizeof(TYPE)) * E
+	sizeof(TYPE) * E
  , ...)
|
  kzalloc(
-	(sizeof(THING)) * E
+	sizeof(THING) * E
  , ...)
)

// Drop single-byte sizes and redundant parens.
@@
expression COUNT;
typedef u8;
typedef __u8;
@@

(
  kzalloc(
-	sizeof(u8) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(__u8) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(char) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(unsigned char) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(u8) * COUNT
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(__u8) * COUNT
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(char) * COUNT
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(unsigned char) * COUNT
+	COUNT
  , ...)
)

// 2-factor product with sizeof(type/expression) and identifier or constant.
@@
type TYPE;
expression THING;
identifier COUNT_ID;
constant COUNT_CONST;
@@

(
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * (COUNT_ID)
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * COUNT_ID
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * (COUNT_CONST)
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * COUNT_CONST
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * (COUNT_ID)
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * COUNT_ID
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * (COUNT_CONST)
+	COUNT_CONST, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * COUNT_CONST
+	COUNT_CONST, sizeof(THING)
  , ...)
)

// 2-factor product, only identifiers.
@@
identifier SIZE, COUNT;
@@

- kzalloc
+ kcalloc
  (
-	SIZE * COUNT
+	COUNT, SIZE
  , ...)

// 3-factor product with 1 sizeof(type) or sizeof(expression), with
// redundant parens removed.
@@
expression THING;
identifier STRIDE, COUNT;
type TYPE;
@@

(
  kzalloc(
-	sizeof(TYPE) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(TYPE) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(TYPE) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(TYPE) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(THING) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kzalloc(
-	sizeof(THING) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kzalloc(
-	sizeof(THING) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kzalloc(
-	sizeof(THING) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
)

// 3-factor product with 2 sizeof(variable), with redundant parens removed.
@@
expression THING1, THING2;
identifier COUNT;
type TYPE1, TYPE2;
@@

(
  kzalloc(
-	sizeof(TYPE1) * sizeof(TYPE2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kzalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kzalloc(
-	sizeof(THING1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kzalloc(
-	sizeof(THING1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kzalloc(
-	sizeof(TYPE1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
|
  kzalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
)

// 3-factor product, only identifiers, with redundant parens removed.
@@
identifier STRIDE, SIZE, COUNT;
@@

(
  kzalloc(
-	(COUNT) * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	(COUNT) * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	(COUNT) * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	(COUNT) * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
)

// Any remaining multi-factor products, first at least 3-factor products,
// when they're not all constants...
@@
expression E1, E2, E3;
constant C1, C2, C3;
@@

(
  kzalloc(C1 * C2 * C3, ...)
|
  kzalloc(
-	(E1) * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kzalloc(
-	(E1) * (E2) * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kzalloc(
-	(E1) * (E2) * (E3)
+	array3_size(E1, E2, E3)
  , ...)
|
  kzalloc(
-	E1 * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
)

// And then all remaining 2 factors products when they're not all constants,
// keeping sizeof() as the second factor argument.
@@
expression THING, E1, E2;
type TYPE;
constant C1, C2, C3;
@@

(
  kzalloc(sizeof(THING) * C2, ...)
|
  kzalloc(sizeof(TYPE) * C2, ...)
|
  kzalloc(C1 * C2 * C3, ...)
|
  kzalloc(C1 * C2, ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * (E2)
+	E2, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * E2
+	E2, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * (E2)
+	E2, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * E2
+	E2, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	(E1) * E2
+	E1, E2
  , ...)
|
- kzalloc
+ kcalloc
  (
-	(E1) * (E2)
+	E1, E2
  , ...)
|
- kzalloc
+ kcalloc
  (
-	E1 * E2
+	E1, E2
  , ...)
)

Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-12 16:19:22 -07:00