Skip to content

L
linux
Switch branch/tag
  1. 24 Jan, 2017 23 commits
  3. 10 Jan, 2017 3 commits
    • Steve Wise's avatar
      iw_cxgb4: do not send RX_DATA_ACK CPLs after close/abort · 3bcf96e0
      Steve Wise authored 
      Function rx_data(), which handles ingress CPL_RX_DATA messages, was
always sending an RX_DATA_ACK with the goal of updating the credits.
However, if the RDMA connection is moved out of FPDU mode abruptly,
then it is possible for iw_cxgb4 to process queued RX_DATA CPLs after HW
has aborted the connection.  These CPLs should not trigger RX_DATA_ACKS.
If they do, HW can see a READ after DELETE of the DB_LE hash entry for
the tid and post a LE_DB HashTblMemCrcError.
Signed-off-by: default avatarSteve Wise <swise@opengridcomputing.com>
Signed-off-by: default avatarDoug Ledford <dledford@redhat.com>
      3bcf96e0
    • Steve Wise's avatar
      iw_cxgb4: free EQ queue memory on last deref · c12a67fe
      Steve Wise authored 
      Commit ad61a4c7 ("iw_cxgb4: don't block in destroy_qp awaiting
the last deref") introduced a bug where the RDMA QP EQ queue memory
(and QIDs) are possibly freed before the underlying connection has been
fully shutdown.  The result being a possible DMA read issued by HW after
the queue memory has been unmapped and freed.  This results in possible
WR corruption in the worst case, system bus errors if an IOMMU is in use,
and SGE "bad WR" errors reported in the very least.  The fix is to defer
unmap/free of queue memory and QID resources until the QP struct has
been fully dereferenced.  To do this, the c4iw_ucontext must also be kept
around until the last QP that references it is fully freed.  In addition,
since the last QP deref can happen in an IRQ disabled context, we need
a new workqueue thread to do the final unmap/free of the EQ queue memory.

Fixes: ad61a4c7 ("iw_cxgb4: don't block in destroy_qp awaiting the last deref")
Cc: stable@vger.kernel.org
Signed-off-by: default avatarSteve Wise <swise@opengridcomputing.com>
Signed-off-by: default avatarDoug Ledford <dledford@redhat.com>
      c12a67fe
    • Steve Wise's avatar
      iw_cxgb4: refactor sq/rq drain logic · 4fe7c296
      Steve Wise authored 
      With the addition of the IB/Core drain API, iw_cxgb4 supported drain
by watching the CQs when the QP was out of RTS and signalling "drain
complete" when the last CQE is polled.  This, however, doesn't fully
support the drain semantics. Namely, the drain logic is supposed to signal
"drain complete" only when the application has _processed_ the last CQE,
not just removed them from the CQ.  Thus a small timing hole exists that
can cause touch after free type bugs in applications using the drain API
(nvmf, iSER, for example).  So iw_cxgb4 needs a better solution.

The iWARP Verbs spec mandates that "_at some point_ after the QP is
moved to ERROR", the iWARP driver MUST synchronously fail post_send and
post_recv calls.  iw_cxgb4 was currently not allowing any posts once the
QP is in ERROR.  This was in part due to the fact that the HW queues for
the QP in ERROR state are disabled at this point, so there wasn't much
else to do but fail the post operation synchronously.  This restriction
is what drove the first drain implementation in iw_cxgb4 that has the
above mentioned flaw.

This patch changes iw_cxgb4 to allow post_send and post_recv WRs after
the QP is moved to ERROR state for kernel mode users, thus still adhering
to the Verbs spec for user mode users, but allowing flush WRs for kernel
users.  Since the HW queues are disabled, we just synthesize a CQE for
this post, queue it to the SW CQ, and then call the CQ event handler.
This enables proper drain operations for the various storage applications.
Signed-off-by: default avatarSteve Wise <swise@opengridcomputing.com>
Signed-off-by: default avatarDoug Ledford <dledford@redhat.com>
      4fe7c296
  5. 08 Jan, 2017 6 commits
    • Linus Torvalds's avatar
      Linux 4.10-rc3 · a121103c
      Linus Torvalds authored
      a121103c
    • Linus Torvalds's avatar
      Merge tag 'usb-4.10-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb · 83280e90
      Linus Torvalds authored 
      Pull USB fixes from Greg KH:
 "Here are a bunch of USB fixes for 4.10-rc3. Yeah, it's a lot, an
  artifact of the holiday break I think.

  Lots of gadget and the usual XHCI fixups for reported issues (one day
  that driver will calm down...) Also included are a bunch of usb-serial
  driver fixes, and for good measure, a number of much-reported MUSB
  driver issues have finally been resolved.

  All of these have been in linux-next with no reported issues"

* tag 'usb-4.10-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb: (72 commits)
  USB: fix problems with duplicate endpoint addresses
  usb: ohci-at91: use descriptor-based gpio APIs correctly
  usb: storage: unusual_uas: Add JMicron JMS56x to unusual device
  usb: hub: Move hub_port_disable() to fix warning if PM is disabled
  usb: musb: blackfin: add bfin_fifo_offset in bfin_ops
  usb: musb: fix compilation warning on unused function
  usb: musb: Fix trying to free already-free IRQ 4
  usb: musb: dsps: implement clear_ep_rxintr() callback
  usb: musb: core: add clear_ep_rxintr() to musb_platform_ops
  USB: serial: ti_usb_3410_5052: fix NULL-deref at open
  USB: serial: spcp8x5: fix NULL-deref at open
  USB: serial: quatech2: fix sleep-while-atomic in close
  USB: serial: pl2303: fix NULL-deref at open
  USB: serial: oti6858: fix NULL-deref at open
  USB: serial: omninet: fix NULL-derefs at open and disconnect
  USB: serial: mos7840: fix misleading interrupt-URB comment
  USB: serial: mos7840: remove unused write URB
  USB: serial: mos7840: fix NULL-deref at open
  USB: serial: mos7720: remove obsolete port initialisation
  USB: serial: mos7720: fix parallel probe
  ...
      83280e90
    • Linus Torvalds's avatar
      Merge tag 'char-misc-4.10-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc · cc250e26
      Linus Torvalds authored 
      Pull char/misc fixes from Greg KH:
 "Here are a few small char/misc driver fixes for 4.10-rc3.

  Two MEI driver fixes, and three NVMEM patches for reported issues, and
  a new Hyper-V driver MAINTAINER update. Nothing major at all, all have
  been in linux-next with no reported issues"

* tag 'char-misc-4.10-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc:
  hyper-v: Add myself as additional MAINTAINER
  nvmem: fix nvmem_cell_read() return type doc
  nvmem: imx-ocotp: Fix wrong register size
  nvmem: qfprom: Allow single byte accesses for read/write
  mei: move write cb to completion on credentials failures
  mei: bus: fix mei_cldev_enable KDoc
      cc250e26
    • Linus Torvalds's avatar
      Merge tag 'staging-4.10-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging · 6ea17ed1
      Linus Torvalds authored 
      Pull staging/IIO fixes from Greg KH:
 "Here are some staging and IIO driver fixes for 4.10-rc3.

  Most of these are minor IIO fixes of reported issues, along with one
  network driver fix to resolve an issue. And a MAINTAINERS update with
  a new mailing list. All of these, except the MAINTAINERS file update,
  have been in linux-next with no reported issues (the MAINTAINERS patch
  happened on Friday...)"

* tag 'staging-4.10-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging:
  MAINTAINERS: add greybus subsystem mailing list
  staging: octeon: Call SET_NETDEV_DEV()
  iio: accel: st_accel: fix LIS3LV02 reading and scaling
  iio: common: st_sensors: fix channel data parsing
  iio: max44000: correct value in illuminance_integration_time_available
  iio: adc: TI_AM335X_ADC should depend on HAS_DMA
  iio: bmi160: Fix time needed to sleep after command execution
  iio: 104-quad-8: Fix active level mismatch for the preset enable option
  iio: 104-quad-8: Fix off-by-one errors when addressing IOR
  iio: 104-quad-8: Fix index control configuration
      6ea17ed1
    • Johannes Weiner's avatar
      mm: workingset: fix use-after-free in shadow node shrinker · ea07b862
      Johannes Weiner authored 
      Several people report seeing warnings about inconsistent radix tree
nodes followed by crashes in the workingset code, which all looked like
use-after-free access from the shadow node shrinker.

Dave Jones managed to reproduce the issue with a debug patch applied,
which confirmed that the radix tree shrinking indeed frees shadow nodes
while they are still linked to the shadow LRU:

  WARNING: CPU: 2 PID: 53 at lib/radix-tree.c:643 delete_node+0x1e4/0x200
  CPU: 2 PID: 53 Comm: kswapd0 Not tainted 4.10.0-rc2-think+ #3
  Call Trace:
     delete_node+0x1e4/0x200
     __radix_tree_delete_node+0xd/0x10
     shadow_lru_isolate+0xe6/0x220
     __list_lru_walk_one.isra.4+0x9b/0x190
     list_lru_walk_one+0x23/0x30
     scan_shadow_nodes+0x2e/0x40
     shrink_slab.part.44+0x23d/0x5d0
     shrink_node+0x22c/0x330
     kswapd+0x392/0x8f0

This is the WARN_ON_ONCE(!list_empty(&node->private_list)) placed in the
inlined radix_tree_shrink().

The problem is with 14b46879 ("mm: workingset: move shadow entry
tracking to radix tree exceptional tracking"), which passes an update
callback into the radix tree to link and unlink shadow leaf nodes when
tree entries change, but forgot to pass the callback when reclaiming a
shadow node.

While the reclaimed shadow node itself is unlinked by the shrinker, its
deletion from the tree can cause the left-most leaf node in the tree to
be shrunk.  If that happens to be a shadow node as well, we don't unlink
it from the LRU as we should.

Consider this tree, where the s are shadow entries:

       root->rnode
            |
       [0       n]
        |       |
     [s    ] [sssss]

Now the shadow node shrinker reclaims the rightmost leaf node through
the shadow node LRU:

       root->rnode
            |
       [0        ]
        |
    [s     ]

Because the parent of the deleted node is the first level below the
root and has only one child in the left-most slot, the intermediate
level is shrunk and the node containing the single shadow is put in
its place:

       root->rnode
            |
       [s        ]

The shrinker again sees a single left-most slot in a first level node
and thus decides to store the shadow in root->rnode directly and free
the node - which is a leaf node on the shadow node LRU.

  root->rnode
       |
       s

Without the update callback, the freed node remains on the shadow LRU,
where it causes later shrinker runs to crash.

Pass the node updater callback into __radix_tree_delete_node() in case
the deletion causes the left-most branch in the tree to collapse too.

Also add warnings when linked nodes are freed right away, rather than
wait for the use-after-free when the list is scanned much later.

Fixes: 14b46879 ("mm: workingset: move shadow entry tracking to radix tree exceptional tracking")
Reported-by: default avatarDave Chinner <david@fromorbit.com>
Reported-by: default avatarHugh Dickins <hughd@google.com>
Reported-by: default avatarAndrea Arcangeli <aarcange@redhat.com>
Reported-and-tested-by: default avatarDave Jones <davej@codemonkey.org.uk>
Signed-off-by: default avatarJohannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Chris Leech <cleech@redhat.com>
Cc: Lee Duncan <lduncan@suse.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <mawilcox@linuxonhyperv.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      ea07b862
    • Hugh Dickins's avatar
      mm: stop leaking PageTables · b0b9b3df
      Hugh Dickins authored 
      4.10-rc loadtest (even on x86, and even without THPCache) fails with
"fork: Cannot allocate memory" or some such; and /proc/meminfo shows
PageTables growing.

Commit 953c66c2 ("mm: THP page cache support for ppc64") that got
merged in rc1 removed the freeing of an unused preallocated pagetable
after do_fault_around() has called map_pages().

This is usually a good optimization, so that the followup doesn't have
to reallocate one; but it's not sufficient to shift the freeing into
alloc_set_pte(), since there are failure cases (most commonly
VM_FAULT_RETRY) which never reach finish_fault().

Check and free it at the outer level in do_fault(), then we don't need
to worry in alloc_set_pte(), and can restore that to how it was (I
cannot find any reason to pte_free() under lock as it was doing).

And fix a separate pagetable leak, or crash, introduced by the same
change, that could only show up on some ppc64: why does do_set_pmd()'s
failure case attempt to withdraw a pagetable when it never deposited
one, at the same time overwriting (so leaking) the vmf->prealloc_pte?
Residue of an earlier implementation, perhaps? Delete it.

Fixes: 953c66c2 ("mm: THP page cache support for ppc64")
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarHugh Dickins <hughd@google.com>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      b0b9b3df
  7. 07 Jan, 2017 2 commits
  9. 06 Jan, 2017 6 commits
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7