For creation, as soon as the umem_odp is created the notifier can be
called, however the underlying MR may not have been setup yet. This would
cause problems if mlx5_ib_invalidate_range() runs. There is some
confusing/ulocked/racy code that might by trying to solve this, but
without locks it isn't going to work right.

Instead trivially solve the problem by short-circuiting the invalidation
if there are not yet any DMA mapped pages. By definition there is nothing
to invalidate in this case.

The create code will have the umem fully setup before anything is DMA
mapped, and npages is fully locked by the umem_mutex.

For destroy, invalidate the entire MR at the HW to stop DMA then DMA unmap
the pages before destroying the MR. This drives npages to zero and
prevents similar racing with invalidate while the MR is undergoing
destruction.

Arguably it would be better if the umem was created after the MR and
destroyed before, but that would require a big rework of the MR code.

Fixes: 6aec21f6 ("IB/mlx5: Page faults handling infrastructure")
Link: https://lore.kernel.org/r/20191009160934.3143-15-jgg@ziepe.caReviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

These mkeys are entirely internal and are never used by the HW for
page fault. They should also never be used by userspace for prefetch.
Simplify & optimize things by not including them in the xarray.

Since the prefetch path can now never see a child mkey there is no need
for the second synchronize_srcu() during imr destroy.

Link: https://lore.kernel.org/r/20191009160934.3143-14-jgg@ziepe.caReviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

Use SRCU in a sensible way by removing all MRs in the implicit tree from
the two xarrays (the update operation), then a synchronize, followed by a
normal single threaded teardown.

This is only a little unusual from the normal pattern as there can still
be some work pending in the unbound wq that may also require a workqueue
flush. This is tracked with a single atomic, consolidating the redundant
existing atomics and wait queue.

For understand-ability the entire ODP implicit create/destroy flow now
largely exists in a single pair of functions within odp.c, with a few
support functions for tearing down an unused child.

Link: https://lore.kernel.org/r/20191009160934.3143-13-jgg@ziepe.caReviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

Now that the locking is simplified combine pagefault_implicit_mr() with
implicit_mr_get_data() so that we sweep over the idx range only once,
and do the single xlt update at the end, after the child umems are
setup.

This avoids double iteration/xa_loads plus the sketchy failure path if the
xa_load() fails.

Link: https://lore.kernel.org/r/20191009160934.3143-12-jgg@ziepe.caReviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

Now that the child MRs are stored in an xarray we can rely on the SRCU
lock to protect the xa_load and use xa_cmpxchg on the slow allocation path
to resolve races with concurrent page fault.

This reduces the scope of the critical section of umem_mutex for implicit
MRs to only cover mlx5_ib_update_xlt, and avoids taking a lock at all if
the child MR is already in the xarray. This makes it consistent with the
normal ODP MR critical section for umem_lock, and the locking approach
used for destroying an unusued implicit child MR.

The MLX5_IB_UPD_XLT_ATOMIC is no longer needed in implicit_get_child_mr()
since it is no longer called with any locks.

Link: https://lore.kernel.org/r/20191009160934.3143-11-jgg@ziepe.caReviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

Currently the child leaves are stored in the shared interval tree and
every lookup for a child must be done under the interval tree rwsem.

This is further complicated by dropping the rwsem during iteration (ie the
odp_lookup(), odp_next() pattern), which requires a very tricky an
difficult to understand locking scheme with SRCU.

Instead reserve the interval tree for the exclusive use of the mmu
notifier related code in umem_odp.c and give each implicit MR a xarray
containing all the child MRs.

Since the size of each child is 1GB of VA, a 1 level xarray will index 64G
of VA, and a 2 level will index 2TB, making xarray a much better
data structure choice than an interval tree.

The locking properties of xarray will be used in the next patches to
rework the implicit ODP locking scheme into something simpler.

At this point, the xarray is locked by the implicit MR's umem_mutex, and
read can also be locked by the odp_srcu.

Link: https://lore.kernel.org/r/20191009160934.3143-10-jgg@ziepe.caReviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

The single routine has a very confusing scheme to advance to the next
child MR when working on an implicit parent. This scheme can only be used
when working with an implicit parent and must not be triggered when
working on a normal MR.

Re-arrange things by directly putting all the single-MR stuff into one
function and calling it in a loop for the implicit case. Simplify some of
the error handling in the new pagefault_real_mr() to remove unneeded gotos.

Link: https://lore.kernel.org/r/20191009160934.3143-9-jgg@ziepe.caReviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

Instead of rewriting all the IOVA's to 0 as things progress down the tree
make the IOVA of the children equal to placement in the tree. This makes
things easier to understand by keeping mmkey.iova == HW configuration.

Link: https://lore.kernel.org/r/20191009160934.3143-8-jgg@ziepe.caReviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

This makes the routines easier to understand, particularly with respect
the locking requirements of the entire sequence. The implicit_mr_alloc()
had a lot of ifs specializing it to each of the callers, and only a very
small amount of code was actually shared.

Following patches will cause the flow in the two functions to diverge
further.

Link: https://lore.kernel.org/r/20191009160934.3143-7-jgg@ziepe.caReviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

This function is intended to loop across each MTT chunk in the implicit
parent that intersects the range [io_virt, io_virt+bnct).  But it is has a
confusing construction, so:

- Consistently use imr and odp_imr to refer to the implicit parent
  to avoid confusion with the normal mr and odp of the child
- Directly compute the inclusive start/end indexes by shifting. This is
  clearer to understand the intent and avoids any errors from unaligned
  values of addr
- Iterate directly over the range of MTT indexes, do not make a loop
  out of goto
- Follow 'success oriented flow', with goto error unwind
- Directly calculate the range of idx's that need update_xlt
- Ensure that any leaf MR added to the interval tree always results in an
  update to the XLT

Link: https://lore.kernel.org/r/20191009160934.3143-6-jgg@ziepe.caReviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

No users are left, delete it.

Link: https://lore.kernel.org/r/20191009160934.3143-5-jgg@ziepe.caReviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

There is a per device xarray storing mkeys that is used to store every
mkey in the system. However, this xarray is now only read by ODP for
certain ODP designated MRs (ODP, implicit ODP, MW, DEVX_INDIRECT).

Create an xarray only for use by ODP, that only contains ODP related
MKeys. This xarray is protected by SRCU and all erases are protected by a
synchronize.

This improves performance:

 - All MRs in the odp_mkeys xarray are ODP MRs, so some tests for is_odp()
   can be deleted. The xarray will also consume fewer nodes.

 - normal MR's are never mixed with ODP MRs in a SRCU data structure so
   performance sucking synchronize_srcu() on every MR destruction is not
   needed.

 - No smp_load_acquire(live) and xa_load() double barrier on read

Due to the SRCU locking scheme care must be taken with the placement of
the xa_store(). Once it completes the MR is immediately visible to other
threads and only through a xa_erase() & synchronize_srcu() cycle could it
be destroyed.

Link: https://lore.kernel.org/r/20191009160934.3143-4-jgg@ziepe.caReviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

The locking model for signature is completely different than ODP, do not
share the same xarray that relies on SRCU locking to support ODP.

Simply store the active mlx5_core_sig_ctx's in an xarray when signature
MRs are created and rely on trivial xarray locking to serialize
everything.

The overhead of storing only a handful of SIG related MRs is going to be
much less than an xarray full of every mkey.

Link: https://lore.kernel.org/r/20191009160934.3143-3-jgg@ziepe.caReviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

When working with SRCU protected xarrays the xarray itself should be the
SRCU 'update' point. Instead prefetch is using live as the SRCU update
point and this prevents switching the locking design to use the xarray
instead.

To solve this the prefetch must only read from the xarray once, and hold
on to the actual MR pointer for the duration of the async
operation. Incrementing num_pending_prefetch delays destruction of the MR,
so it is suitable.

Prefetch calls directly to the pagefault_mr using the MR pointer and only
does a single xarray lookup.

All the testing if a MR is prefetchable or not is now done only in the
prefetch code and removed from the pagefault critical path.

Link: https://lore.kernel.org/r/20191009160934.3143-2-jgg@ziepe.caReviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

Pull x86 fixes from Thomas Gleixner:
 "Two fixes for the VMWare guest support:

   - Unbreak VMWare platform detection which got wreckaged by converting
     an integer constant to a string constant.

   - Fix the clang build of the VMWAre hypercall by explicitely
     specifying the ouput register for INL instead of using the short
     form"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpu/vmware: Fix platform detection VMWARE_PORT macro
  x86/cpu/vmware: Use the full form of INL in VMWARE_HYPERCALL, for clang/llvm

Pull timer fixes from Thomas Gleixner:
 "A small set of fixes for time(keeping):

   - Add a missing include to prevent compiler warnings.

   - Make the VDSO implementation of clock_getres() POSIX compliant
     again. A recent change dropped the NULL pointer guard which is
     required as NULL is a valid pointer value for this function.

   - Fix two function documentation typos"

* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  posix-cpu-timers: Fix two trivial comments
  timers/sched_clock: Include local timekeeping.h for missing declarations
  lib/vdso: Make clock_getres() POSIX compliant again

Pull perf fixes from Thomas Gleixner:
 "A set of perf fixes:

  kernel:

   - Unbreak the tracking of auxiliary buffer allocations which got
     imbalanced causing recource limit failures.

   - Fix the fallout of splitting of ToPA entries which missed to shift
     the base entry PA correctly.

   - Use the correct context to lookup the AUX event when unmapping the
     associated AUX buffer so the event can be stopped and the buffer
     reference dropped.

  tools:

   - Fix buildiid-cache mode setting in copyfile_mode_ns() when copying
     /proc/kcore

   - Fix freeing id arrays in the event list so the correct event is
     closed.

   - Sync sched.h anc kvm.h headers with the kernel sources.

   - Link jvmti against tools/lib/ctype.o to have weak strlcpy().

   - Fix multiple memory and file descriptor leaks, found by coverity in
     perf annotate.

   - Fix leaks in error handling paths in 'perf c2c', 'perf kmem', found
     by a static analysis tool"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/aux: Fix AUX output stopping
  perf/aux: Fix tracking of auxiliary trace buffer allocation
  perf/x86/intel/pt: Fix base for single entry topa
  perf kmem: Fix memory leak in compact_gfp_flags()
  tools headers UAPI: Sync sched.h with the kernel
  tools headers kvm: Sync kvm.h headers with the kernel sources
  tools headers kvm: Sync kvm headers with the kernel sources
  tools headers kvm: Sync kvm headers with the kernel sources
  perf c2c: Fix memory leak in build_cl_output()
  perf tools: Fix mode setting in copyfile_mode_ns()
  perf annotate: Fix multiple memory and file descriptor leaks
  perf tools: Fix resource leak of closedir() on the error paths
  perf evlist: Fix fix for freed id arrays
  perf jvmti: Link against tools/lib/ctype.h to have weak strlcpy()

Pull irq fixes from Thomas Gleixner:
 "Two fixes for interrupt controller drivers:

   - Skip IRQ_M_EXT entries in the device tree when initializing the
     RISCV PLIC controller to avoid a double init attempt.

   - Use the correct ITS list when issuing the VMOVP synchronization
     command so the operation works only on the ITS instances which are
     associated to a VM"

* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  irqchip/sifive-plic: Skip contexts except supervisor in plic_init()
  irqchip/gic-v3-its: Use the exact ITSList for VMOVP

Pull cifs fixes from Steve French:
 "Seven cifs/smb3 fixes, including three for stable"

* tag '5.4-rc5-smb3-fixes' of git://git.samba.org/sfrench/cifs-2.6:
  cifs: Fix cifsInodeInfo lock_sem deadlock when reconnect occurs
  CIFS: Fix use after free of file info structures
  CIFS: Fix retry mid list corruption on reconnects
  cifs: Fix missed free operations
  CIFS: avoid using MID 0xFFFF
  cifs: clarify comment about timestamp granularity for old servers
  cifs: Handle -EINPROGRESS only when noblockcnt is set

Pull RISC-V fixes from Paul Walmsley:
 "Several minor fixes and cleanups for v5.4-rc5:

   - Three build fixes for various SPARSEMEM-related kernel
     configurations

   - Two cleanup patches for the kernel bug and breakpoint trap handler
     code"

* tag 'riscv/for-v5.4-rc5-b' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
  riscv: cleanup do_trap_break
  riscv: cleanup <asm/bug.h>
  riscv: Fix undefined reference to vmemmap_populate_basepages
  riscv: Fix implicit declaration of 'page_to_section'
  riscv: fix fs/proc/kcore.c compilation with sparsemem enabled

Pull MIPS fixes from Paul Burton:
 "A few MIPS fixes:

   - Fix VDSO time-related function behavior for systems where we need
     to fall back to syscalls, but were instead returning bogus results.

   - A fix to TLB exception handlers for Cavium Octeon systems where
     they would inadvertently clobber the $1/$at register.

   - A build fix for bcm63xx configurations.

   - Switch to using my @kernel.org email address"

* tag 'mips_fixes_5.4_3' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux:
  MIPS: tlbex: Fix build_restore_pagemask KScratch restore
  MIPS: bmips: mark exception vectors as char arrays
  mips: vdso: Fix __arch_get_hw_counter()
  MAINTAINERS: Use @kernel.org address for Paul Burton

Pull tty/serial driver fix from Greg KH:
 "Here is a single tty/serial driver fix for 5.4-rc5 that resolves a
  reported issue.

  It has been in linux-next for a while with no problems"

* tag 'tty-5.4-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty:
  8250-men-mcb: fix error checking when get_num_ports returns -ENODEV

Pull staging driver fix from Greg KH:
 "Here is a single staging driver fix, for the wlan-ng driver, that
  resolves a reported issue.

  It is been in linux-next for a while with no reported issues"

* tag 'staging-5.4-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging:
  staging: wlan-ng: fix exit return when sme->key_idx >= NUM_WEPKEYS

Pull driver core fix from Greg KH:
 "Here is a single sysfs fix for 5.4-rc5.

  It resolves an error if you actually try to use the __BIN_ATTR_WO()
  macro, seems I never tested it properly before :(

  This has been in linux-next for a while with no reported issues"

* tag 'driver-core-5.4-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core:
  sysfs: Fixes __BIN_ATTR_WO() macro

Pull binder fix from Greg KH:
 "This is a single binder fix to resolve a reported issue by Jann. It's
  been in linux-next for a while with no reported issues"

* tag 'char-misc-5.4-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc:
  binder: Don't modify VMA bounds in ->mmap handler

Pull USB fixes from Greg KH:
 "Here are a number of small USB driver fixes for 5.4-rc5.

  More "fun" with some of the misc USB drivers as found by syzbot, and
  there are a number of other small bugfixes in here for reported
  issues.

  All have been in linux-next for a while with no reported issues"

* tag 'usb-5.4-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb:
  usb: cdns3: Error out if USB_DR_MODE_UNKNOWN in cdns3_core_init_role()
  USB: ldusb: fix read info leaks
  USB: serial: ti_usb_3410_5052: clean up serial data access
  USB: serial: ti_usb_3410_5052: fix port-close races
  USB: usblp: fix use-after-free on disconnect
  usb: udc: lpc32xx: fix bad bit shift operation
  usb: cdns3: Fix dequeue implementation.
  USB: legousbtower: fix a signedness bug in tower_probe()
  USB: legousbtower: fix memleak on disconnect
  USB: ldusb: fix memleak on disconnect

Pull i2c fixes from Wolfram Sang:
 "A few driver fixes for the I2C subsystem"

* 'i2c/for-current-fixed' of git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux:
  i2c: stm32f7: remove warning when compiling with W=1
  i2c: stm32f7: fix a race in slave mode with arbitration loss irq
  i2c: stm32f7: fix first byte to send in slave mode
  i2c: mt65xx: fix NULL ptr dereference
  i2c: aspeed: fix master pending state handling

Pull block and io_uring fixes from Jens Axboe:
 "A bit bigger than usual at this point in time, mostly due to some good
  bug hunting work by Pavel that resulted in three io_uring fixes from
  him and two from me. Anyway, this pull request contains:

   - Revert of the submit-and-wait optimization for io_uring, it can't
     always be done safely. It depends on commands always making
     progress on their own, which isn't necessarily the case outside of
     strict file IO. (me)

   - Series of two patches from me and three from Pavel, fixing issues
     with shared data and sequencing for io_uring.

   - Lastly, two timeout sequence fixes for io_uring (zhangyi)

   - Two nbd patches fixing races (Josef)

   - libahci regulator_get_optional() fix (Mark)"

* tag 'for-linus-2019-10-26' of git://git.kernel.dk/linux-block:
  nbd: verify socket is supported during setup
  ata: libahci_platform: Fix regulator_get_optional() misuse
  nbd: handle racing with error'ed out commands
  nbd: protect cmd->status with cmd->lock
  io_uring: fix bad inflight accounting for SETUP_IOPOLL|SETUP_SQTHREAD
  io_uring: used cached copies of sq->dropped and cq->overflow
  io_uring: Fix race for sqes with userspace
  io_uring: Fix broken links with offloading
  io_uring: Fix corrupted user_data
  io_uring: correct timeout req sequence when inserting a new entry
  io_uring : correct timeout req sequence when waiting timeout
  io_uring: revert "io_uring: optimize submit_and_wait API"

Pull s390 fixes from Vasily Gorbik:

 - Add R_390_GLOB_DAT relocation type support. This fixes boot problem
   on linux-next.

 - Fix memory leak in zcrypt

* tag 's390-5.4-5' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
  s390/kaslr: add support for R_390_GLOB_DAT relocation type
  s390/zcrypt: fix memleak at release

Pull xen fixlet from Juergen Gross:
 "Just one patch for issuing a deprecation warning for 32-bit Xen pv
  guests"

* tag 'for-linus-5.4-rc5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen: issue deprecation warning for 32-bit pv guest

Pull dma-mapping fix from Christoph Hellwig:
 "Fix a regression in the intel-iommu get_required_mask conversion
  (Arvind Sankar)"

* tag 'dma-mapping-5.4-2' of git://git.infradead.org/users/hch/dma-mapping:
  iommu/vt-d: Return the correct dma mask when we are bypassing the IOMMU

Pull dax fix from Dan Williams:
 "Fix a performance regression that followed from a fix to the
  conversion of the fsdax implementation to the xarray. v5.3 users
  report that they stop seeing huge page mappings on an application +
  filesystem layout that was seeing huge pages previously on v5.2"

* tag 'dax-fix-5.4-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  fs/dax: Fix pmd vs pte conflict detection

Pull SCSI fixes from James Bottomley:
 "Nine changes, eight to drivers (qla2xxx, hpsa, lpfc, alua, ch,
  53c710[x2], target) and one core change that tries to close a race
  between sysfs delete and module removal"

* tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi:
  scsi: lpfc: remove left-over BUILD_NVME defines
  scsi: core: try to get module before removing device
  scsi: hpsa: add missing hunks in reset-patch
  scsi: target: core: Do not overwrite CDB byte 1
  scsi: ch: Make it possible to open a ch device multiple times again
  scsi: fix kconfig dependency warning related to 53C700_LE_ON_BE
  scsi: sni_53c710: fix compilation error
  scsi: scsi_dh_alua: handle RTPG sense code correctly during state transitions
  scsi: qla2xxx: fix a potential NULL pointer dereference

If we always compile the get_break_insn_length inline function we can
remove the ifdefs and let dead code elimination take care of the warn
branch that is now unreadable because the report_bug stub always
returns BUG_TRAP_TYPE_BUG.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>

Pull input fix from Dmitry Torokhov:
 "A fix for st1232 driver to properly report coordinates for 2nd and
  subsequent fingers when more than one is on the surface"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input:
  Input: st1232 - fix reporting multitouch coordinates

nbd requires socket families to support the shutdown method so the nbd
recv workqueue can be woken up from its sock_recvmsg call. If the socket
does not support the callout we will leave recv works running or get hangs
later when the device or module is removed.

This adds a check during socket connection/reconnection to make sure the
socket being passed in supports the needed callout.

Reported-by: syzbot+24c12fa8d218ed26011a@syzkaller.appspotmail.com
Fixes: e9e006f5 ("nbd: fix max number of supported devs")
Tested-by: Richard W.M. Jones <rjones@redhat.com>
Signed-off-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

This driver is using regulator_get_optional() to handle all the supplies
that it handles, and only ever enables and disables all supplies en masse
without ever doing any other configuration of the device to handle missing
power. These are clear signs that the API is being misused - it should only
be used for supplies that may be physically absent from the system and in
these cases the hardware usually needs different configuration if the
supply is missing. Instead use normal regualtor_get(), if the supply is
not described in DT then the framework will substitute a dummy regulator in
so no special handling is needed by the consumer driver.

In the case of the PHY regulator the handling in the driver is a hack to
deal with integrated PHYs; the supplies are only optional in the sense
that that there's some confusion in the code about where they're bound to.
From a code point of view they function exactly as normal supplies so can
be treated as such. It'd probably be better to model this by instantiating
a PHY object for integrated PHYs.
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

We hit the following warning in production

print_req_error: I/O error, dev nbd0, sector 7213934408 flags 80700
------------[ cut here ]------------
refcount_t: underflow; use-after-free.
WARNING: CPU: 25 PID: 32407 at lib/refcount.c:190 refcount_sub_and_test_checked+0x53/0x60
Workqueue: knbd-recv recv_work [nbd]
RIP: 0010:refcount_sub_and_test_checked+0x53/0x60
Call Trace:
 blk_mq_free_request+0xb7/0xf0
 blk_mq_complete_request+0x62/0xf0
 recv_work+0x29/0xa1 [nbd]
 process_one_work+0x1f5/0x3f0
 worker_thread+0x2d/0x3d0
 ? rescuer_thread+0x340/0x340
 kthread+0x111/0x130
 ? kthread_create_on_node+0x60/0x60
 ret_from_fork+0x1f/0x30
---[ end trace b079c3c67f98bb7c ]---

This was preceded by us timing out everything and shutting down the
sockets for the device.  The problem is we had a request in the queue at
the same time, so we completed the request twice.  This can actually
happen in a lot of cases, we fail to get a ref on our config, we only
have one connection and just error out the command, etc.

Fix this by checking cmd->status in nbd_read_stat.  We only change this
under the cmd->lock, so we are safe to check this here and see if we've
already error'ed this command out, which would indicate that we've
completed it as well.
Reviewed-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

We already do this for the most part, except in timeout and clear_req.
For the timeout case we take the lock after we grab a ref on the config,
but that isn't really necessary because we're safe to touch the cmd at
this point, so just move the order around.

For the clear_req cause this is initiated by the user, so again is safe.
Reviewed-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>