pNFS/flexfiles: Fix up the ff_layout_write_pagelist failure path
If the attempt to write through pNFS fails, we need to use the same
failure semantics as for the read path: If the FF_FLAGS_NO_IO_THRU_MDS
flag is set or we have sufficient valid DSes, then we must retry through
pNFS
NFS4.1 handle interrupted slot reuse from ERR_DELAY
If the RPC slot was interrupted and server replied to the next
operation on the "reused" slot with ERR_DELAY, don't clear out
the "interrupted" flag until we properly recover.
Signed-off-by: Olga Kornievskaia <kolga@netapp.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Pan Bian [Sun, 23 Apr 2017 06:49:41 +0000 (14:49 +0800)]
NFSv4: check return value of xdr_inline_decode
Function xdr_inline_decode() will return a NULL pointer if the input
buffer does not have long enough buffer to decode nbytes of data.
However, in function decode_op_map(), the return value of
xdr_inline_decode() is not validated before it is used. This patch adds
a check to the return value of xdr_inline_decode().
Signed-off-by: Pan Bian <bianpan2016@163.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
nfs/filelayout: fix NULL pointer dereference in fl_pnfs_update_layout()
Calling pnfs_put_lset on an IS_ERR pointer results in a NULL pointer
dereference like the one below. At the same time the check of retvalue
of filelayout_check_deviceid() sets lseg to error, but does not free it
before that.
Merge tag 'nfs-rdma-4.12-1' of git://git.linux-nfs.org/projects/anna/nfs-rdma
NFS: NFS over RDMA Client Side Changes
New Features:
- Break RDMA connections after a connection timeout
- Support for unloading the underlying device driver
Bugfixes and cleanups:
- Mark the receive workqueue as "read-mostly"
- Silence warnings caused by ENOBUFS
- Update a comment in xdr_init_decode_pages()
- Remove rpcrdma_buffer->rb_pool.
Device removal is now adequately supported. Pinning the underlying
device driver to prevent removal while an NFS mount is active is no
longer necessary.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Tue, 11 Apr 2017 17:23:18 +0000 (13:23 -0400)]
xprtrdma: Refactor rpcrdma_ep_connect
I'm about to add another arm to
if (ep->rep_connected != 0)
It will be cleaner to use a switch statement here. We'll be looking
for a couple of specific errnos, or "anything else," basically to
sort out the difference between a normal reconnect and recovery from
device removal.
This is a refactoring change only.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Tue, 11 Apr 2017 17:23:10 +0000 (13:23 -0400)]
xprtrdma: Support unplugging an HCA from under an NFS mount
The device driver for the underlying physical device associated
with an RPC-over-RDMA transport can be removed while RPC-over-RDMA
transports are still in use (ie, while NFS filesystems are still
mounted and active). The IB core performs a connection event upcall
to request that consumers free all RDMA resources associated with
a transport.
There may be pending RPCs when this occurs. Care must be taken to
release associated resources without leaving references that can
trigger a subsequent crash if a signal or soft timeout occurs. We
rely on the caller of the transport's ->close method to ensure that
the previous RPC task has invoked xprt_release but the transport
remains write-locked.
A DEVICE_REMOVE upcall forces a disconnect then sleeps. When ->close
is invoked, it destroys the transport's H/W resources, then wakes
the upcall, which completes and allows the core driver unload to
continue.
Chuck Lever [Tue, 11 Apr 2017 17:23:02 +0000 (13:23 -0400)]
xprtrdma: Use same device when mapping or syncing DMA buffers
When the underlying device driver is reloaded, ia->ri_device will be
replaced. All cached copies of that device pointer have to be
updated as well.
Commit 54cbd6b0c6b9 ("xprtrdma: Delay DMA mapping Send and Receive
buffers") added the rg_device field to each regbuf. As part of
handling a device removal, rpcrdma_dma_unmap_regbuf is invoked on
all regbufs for a transport.
Simply calling rpcrdma_dma_map_regbuf for each Receive buffer after
the driver has been reloaded should reinitialize rg_device correctly
for every case except rpcrdma_wc_receive, which still uses
rpcrdma_rep::rr_device.
Ensure the same device that was used to map a Receive buffer is also
used to sync it in rpcrdma_wc_receive by using rg_device there
instead of rr_device.
This is the only use of rr_device, so it can be removed.
The use of regbufs in the send path is also updated, for
completeness.
Fixes: 54cbd6b0c6b9 ("xprtrdma: Delay DMA mapping Send and ... ") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Tue, 11 Apr 2017 17:22:54 +0000 (13:22 -0400)]
xprtrdma: Refactor rpcrdma_ia_open()
In order to unload a device driver and reload it, xprtrdma will need
to close a transport's interface adapter, and then call
rpcrdma_ia_open again, possibly finding a different interface
adapter.
Make rpcrdma_ia_open safe to call on the same transport multiple
times.
This is a refactoring change only.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Tue, 11 Apr 2017 17:22:46 +0000 (13:22 -0400)]
xprtrdma: Detect unreachable NFS/RDMA servers more reliably
Current NFS clients rely on connection loss to determine when to
retransmit. In particular, for protocols like NFSv4, clients no
longer rely on RPC timeouts to drive retransmission: NFSv4 servers
are required to terminate a connection when they need a client to
retransmit pending RPCs.
When a server is no longer reachable, either because it has crashed
or because the network path has broken, the server cannot actively
terminate a connection. Thus NFS clients depend on transport-level
keepalive to determine when a connection must be replaced and
pending RPCs retransmitted.
However, RDMA RC connections do not have a native keepalive
mechanism. If an NFS/RDMA server crashes after a client has sent
RPCs successfully (an RC ACK has been received for all OTW RDMA
requests), there is no way for the client to know the connection is
moribund.
In addition, new RDMA requests are subject to the RPC-over-RDMA
credit limit. If the client has consumed all granted credits with
NFS traffic, it is not allowed to send another RDMA request until
the server replies. Thus it has no way to send a true keepalive when
the workload has already consumed all credits with pending RPCs.
To address this, forcibly disconnect a transport when an RPC times
out. This prevents moribund connections from stopping the
detection of failover or other configuration changes on the server.
Note that even if the connection is still good, retransmitting
any RPC will trigger a disconnect thanks to this logic in
xprt_rdma_send_request:
/* Must suppress retransmit to maintain credits */
if (req->rl_connect_cookie == xprt->connect_cookie)
goto drop_connection;
req->rl_connect_cookie = xprt->connect_cookie;
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Tue, 11 Apr 2017 17:22:38 +0000 (13:22 -0400)]
sunrpc: Export xprt_force_disconnect()
xprt_force_disconnect() is already invoked from the socket
transport. I want to invoke xprt_force_disconnect() from the
RPC-over-RDMA transport, which is a separate module from sunrpc.ko.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Tue, 11 Apr 2017 17:22:29 +0000 (13:22 -0400)]
xprtrdma: Cancel refresh worker during buffer shutdown
Trying to create MRs while the transport is being torn down can
cause a crash.
Fixes: e2ac236c0b65 ("xprtrdma: Allocate MRs on demand") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
NFS: Don't write back further requests if there is a pending write error
If the server has already returned a fatal write error that the user
has not yet received on this file, then don't write back the other pages.
Instead, act as if they have been sent, and have returned with the same
error.
The assumption should be that if the caller returns PNFS_ATTEMPTED, then hdr
has been consumed, and so we should not be testing hdr->task.tk_status.
If the caller returns PNFS_TRY_AGAIN, then we need to recoalesce and
free hdr.
pNFS: Ensure we check layout segment validity in the pg_init() callback
If we have a layout segment cached in pgio->pg_lseg, we should check it
for validity before reusing it in a new RPC request. Otherwise, if we
recoalesce, we can end up looping forever.
NFS attempts to wait for read and write completion before unlocking in
order to ensure that the data returned was protected by the lock. When
this waiting is interrupted by a signal, the unlock may be skipped, and
messages similar to the following are seen in the kernel ring buffer:
For NFSv3, the missing unlock will cause the server to refuse conflicting
locks indefinitely. For NFSv4, the leftover lock will be removed by the
server after the lease timeout.
This patch fixes this issue by skipping the usual wait in
nfs_iocounter_wait if the FL_CLOSE flag is set when signaled. Instead, the
wait happens in the unlock RPC task on the NFS UOC rpc_waitqueue.
For NFSv3, use lockd's new nlmclnt_operations along with
nfs_async_iocounter_wait to defer NLM's unlock task until the lock
context's iocounter reaches zero.
For NFSv4, call nfs_async_iocounter_wait() directly from unlock's
current rpc_call_prepare.
Signed-off-by: Benjamin Coddington <bcodding@redhat.com> Reviewed-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
NFS would enjoy the ability to modify the behavior of the NLM client's
unlock RPC task in order to delay the transmission of the unlock until IO
that was submitted under that lock has completed. This ability can ensure
that the NLM client will always complete the transmission of an unlock even
if the waiting caller has been interrupted with fatal signal.
For this purpose, a pointer to a struct nlmclnt_operations can be assigned
in a nfs_module's nfs_rpc_ops that will install those nlmclnt_operations on
the nlm_host. The struct nlmclnt_operations defines three callback
operations that will be used in a following patch:
nlmclnt_alloc_call - used to call back after a successful allocation of
a struct nlm_rqst in nlmclnt_proc().
nlmclnt_unlock_prepare - used to call back during NLM unlock's
rpc_call_prepare. The NLM client defers calling rpc_call_start()
until this callback returns false.
nlmclnt_release_call - used to call back when the NLM client's struct
nlm_rqst is freed.
Signed-off-by: Benjamin Coddington <bcodding@redhat.com> Reviewed-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
NFS: Add an iocounter wait function for async RPC tasks
By sleeping on a new NFS Unlock-On-Close waitqueue, rpc tasks may wait for
a lock context's iocounter to reach zero. The rpc waitqueue is only woken
when the open_context has the NFS_CONTEXT_UNLOCK flag set in order to
mitigate spurious wake-ups for any iocounter reaching zero.
Signed-off-by: Benjamin Coddington <bcodding@redhat.com> Reviewed-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
locks: Set FL_CLOSE when removing flock locks on close()
Set FL_CLOSE in fl_flags as in locks_remove_posix() when clearing locks.
NFS will check for this flag to ensure an unlock is sent in a following
patch.
Fuse handles flock and posix locks differently for FL_CLOSE, and so
requires a fixup to retain the existing behavior for flock.
Signed-off-by: Benjamin Coddington <bcodding@redhat.com> Reviewed-by: Jeff Layton <jlayton@redhat.com> Acked-by: Miklos Szeredi <miklos@szeredi.hu> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
NFS: Move the flock open mode check into nfs_flock()
We only need to check lock exclusive/shared types against open mode when
flock() is used on NFS, so move it into the flock-specific path instead of
checking it for all locks.
Signed-off-by: Benjamin Coddington <bcodding@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
NFSv4: Fix a hang in OPEN related to server reboot
If the server fails to return the attributes as part of an OPEN
reply, and then reboots, we can end up hanging. The reason is that
the client attempts to send a GETATTR in order to pick up the
missing OPEN call, but fails to release the slot first, causing
reboot recovery to deadlock.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com> Fixes: 2e80dbe7ac51a ("NFSv4.1: Close callback races for OPEN, LAYOUTGET...") Cc: stable@vger.kernel.org # v4.8+
Since commit 00bfa30abe86 ("NFS: Create a common pgio_alloc and
pgio_release function"), nfs_pgarray_set() has only a single caller. Let's
open code it.
Signed-off-by: Benjamin Coddington <bcodding@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
NFS: Fix missing pg_cleanup after nfs_pageio_cond_complete()
Commit a7d42ddb3099727f58366fa006f850a219cce6c8 ("nfs: add mirroring
support to pgio layer") moved pg_cleanup out of the path when there was
non-sequental I/O that needed to be flushed. The result is that for
layouts that have more than one layout segment per file, the pg_lseg is not
cleared, so we can end up hitting the WARN_ON_ONCE(req_start >= seg_end) in
pnfs_generic_pg_test since the pg_lseg will be pointing to that
previously-flushed layout segment.
Signed-off-by: Benjamin Coddington <bcodding@redhat.com> Fixes: a7d42ddb3099 ("nfs: add mirroring support to pgio layer") Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
sunrpc: don't check for failure from mempool_alloc()
When mempool_alloc() is allowed to sleep (GFP_NOIO allows
sleeping) it cannot fail.
So rpc_alloc_task() cannot fail, so rpc_new_task doesn't need
to test for failure.
Consequently rpc_new_task() cannot fail, so the callers
don't need to test.
When passed GFP flags that allow sleeping (such as
GFP_NOIO), mempool_alloc() will never return NULL, it will
wait until memory is available.
This means that we don't need to handle failure, but that we
do need to ensure one thread doesn't call mempool_alloc()
twice on the one pool without queuing or freeing the first
allocation. If multiple threads did this during times of
high memory pressure, the pool could be exhausted and a
deadlock could result.
pnfs_generic_alloc_ds_commits() attempts to allocate from
the nfs_commit_mempool while already holding an allocation
from that pool. This is not safe. So change
nfs_commitdata_alloc() to take a flag that indicates whether
failure is acceptable.
In pnfs_generic_alloc_ds_commits(), accept failure and
handle it as we currently do. Else where, do not accept
failure, and do not handle it.
Even when failure is acceptable, we want to succeed if
possible. That means both
- using an entry from the pool if there is one
- waiting for direct reclaim is there isn't.
We call mempool_alloc(GFP_NOWAIT) to achieve the first, then
kmem_cache_alloc(GFP_NOIO|__GFP_NORETRY) to achieve the
second. Each of these can fail, but together they do the
best they can without blocking indefinitely.
The objects returned by kmem_cache_alloc() will still be freed
by mempool_free(). This is safe as mempool_alloc() uses
exactly the same function to allocate objects (since the mempool
was created with mempool_create_slab_pool()). The object returned
by mempool_alloc() and kmem_cache_alloc() are indistinguishable
so mempool_free() will handle both identically, either adding to the
pool or calling kmem_cache_free().
Also, don't test for failure when allocating from
nfs_wdata_mempool.
Anna Schumaker [Fri, 7 Apr 2017 18:15:05 +0000 (14:15 -0400)]
NFS: Clean up nfs_init_client()
We always call nfs_mark_client_ready() even if nfs_create_rpc_client()
returns an error, so we can rearrange nfs_init_client() to mark the
client ready from a single place.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Anna Schumaker [Fri, 7 Apr 2017 18:14:55 +0000 (14:14 -0400)]
NFS: Clean up do_callback_layoutrecall()
Removing the dprintk()s lets us simplify the function by removing the
else condition entirely and returning the status of
initiate_{file,bulk}_draining() directly.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
nfs: flexfilelayout: remove v3-only data server limitation
Flexfilelayout supports data servers which talk NFS v3 and v4.{0,1,2}.
However, this code path is disabled and v3 only servers are accepted.
This change removes this limitation. Signed-off-by: Tigran Mkrtchyan <tigran.mkrtchyan@desy.de> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
NFS has some optimizations for readdir to choose between using READDIR or
READDIRPLUS based on workload, and which NFS operation to use is determined
by subsequent interactions with lookup, d_revalidate, and getattr.
Concurrent use of nfs_readdir() via ->iterate_shared() can cause those
optimizations to repeatedly invalidate the pagecache used to store
directory entries during readdir(), which causes some very bad performance
for directories with many entries (more than about 10000).
There's a couple ways to fix this in NFS, but no fix would be as simple as
going back to ->iterate() to serialize nfs_readdir(), and neither fix I
tested performed as well as going back to ->iterate().
The first required taking the directory's i_lock for each entry, with the
result of terrible contention.
The second way adds another flag to the nfs_inode, and so keeps the
optimizations working for large directories. The difference from using
->iterate() here is that much more memory is consumed for a given workload
without any performance gain.
The workings of nfs_readdir() are such that concurrent users are serialized
within read_cache_page() waiting to retrieve pages of entries from the
server. By serializing this work in iterate_dir() instead, contention for
cache pages is reduced. Waiting processes can have an uncontended pass at
the entirety of the directory's pagecache once previous processes have
completed filling it.
v2 - Keep the bits needed for parallel lookup
Signed-off-by: Benjamin Coddington <bcodding@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Merge tag 'armsoc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc
Pull ARM SoC fixes from Olof Johansson:
"Again, a batch that's been sitting a couple of weeks, mostly because
I anticipated a bit more material but it didn't show up -- which is
good.
These are all your garden variety fixes for ARM platforms.
The most visible issue fixed here is probably the SMP reset issue on
OMAP, the rest are minor stuff"
* tag 'armsoc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc:
arm64: allwinner: a64: add pmu0 regs for USB PHY
ARM: OMAP2+: omap_device: Sync omap_device and pm_runtime after probe defer
reset: add exported __reset_control_get, return NULL if optional
ARM: orion5x: only call into phylib when available
ARM: omap2+: Revert omap-smp.c changes resetting CPU1 during boot
ARM: dts: am335x-evmsk: adjust mmc2 param to allow suspend
ARM: dts: ti: fix PCI bus dtc warnings
ARM: dts: am335x-baltos: disable EEE for Atheros 8035 PHY
ARM: dts: OMAP3: Fix MFG ID EEPROM
ARM: sun8i: a33: add operating-points-v2 property to all nodes
ARM: sun8i: a33: remove highest OPP to fix CPU crashes
Merge branch 'for-linus' of git://git.kernel.dk/linux-block
Pull block fixes from Jens Axboe:
"Four small fixes.
Three of them fix the same error in NVMe, in loop, fc, and rdma
respectively. The last fix from Ming fixes a regression in this
series, where our bvec gap logic was wrong and causes an oops on
NVMe for certain conditions"
* 'for-linus' of git://git.kernel.dk/linux-block:
block: fix bio_will_gap() for first bvec with offset
nvme-fc: Fix sqsize wrong assignment based on ctrl MQES capability
nvme-rdma: Fix sqsize wrong assignment based on ctrl MQES capability
nvme-loop: Fix sqsize wrong assignment based on ctrl MQES capability
Olof Johansson [Sun, 16 Apr 2017 18:52:26 +0000 (11:52 -0700)]
Merge tag 'omap-for-v4.11/fixes-rc6-signed' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap into fixes
Regression fix for omap interconnect code for deferred probe.
Without this fix we can get PM related warnings for devices that
use deferred probe. If necessary, this fix can wait for the
v4.12 merge window no problem.
* tag 'omap-for-v4.11/fixes-rc6-signed' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap:
ARM: OMAP2+: omap_device: Sync omap_device and pm_runtime after probe defer
ARM: omap2+: Revert omap-smp.c changes resetting CPU1 during boot
ARM: dts: am335x-evmsk: adjust mmc2 param to allow suspend
ARM: dts: ti: fix PCI bus dtc warnings
ARM: dts: am335x-baltos: disable EEE for Atheros 8035 PHY
ARM: dts: OMAP3: Fix MFG ID EEPROM
Merge branch 'for-4.11-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
Pull cgroup fix from Tejun Heo:
"Unfortunately, the commit to fix the cgroup mount race in the previous
pull request can lead to hangs.
The original bug has been around for a while and isn't too likely to
be triggered in usual use cases. Revert the commit for now"
* 'for-4.11-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
Revert "cgroup: avoid attaching a cgroup root to two different superblocks"
Merge tag 'tty-4.11-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty
Pull tty fix from Greg KH:
"Here is a single tty core revert for a patch that was reported to
cause problems.
The original issue is one that we have lived with for decades, so
trying to scramble to fix the fix in time for 4.11-final does not make
sense due to the fragility of the tty ldisc layer. Just reverting it
makes sense for now"
* tag 'tty-4.11-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty:
Revert "tty: don't panic on OOM in tty_set_ldisc()"
Merge tag 'trace-v4.11-rc5-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull ftrace fix from Steven Rostedt:
"While rewriting the function probe code, I stumbled over a long
standing bug. This bug has been there sinc function tracing was added
way back when. But my new development depends on this bug being fixed,
and it should be fixed regardless as it causes ftrace to disable
itself when triggered, and a reboot is required to enable it again.
The bug is that the function probe does not disable itself properly if
there's another probe of its type still enabled. For example:
The above registers two traceoff probes (one for schedule and one for
do_IRQ, and then removes do_IRQ.
But since there still exists one for schedule, it is not done
properly. When adding do_IRQ back, the breakage in the accounting is
noticed by the ftrace self tests, and it causes a warning and disables
ftrace"
* tag 'trace-v4.11-rc5-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
ftrace: Fix removing of second function probe
Andrei reports CRIU test hangs with the patch applied. The bug fixed
by the patch isn't too likely to trigger in actual uses. Revert the
patch for now.
Merge branch 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull nvdimm fixes from Dan Williams:
"A small crop of lockdep, sleeping while atomic, and other fixes /
band-aids in advance of the full-blown reworks targeting the next
merge window. The largest change here is "libnvdimm: fix blk free
space accounting" which deletes a pile of buggy code that better
testing would have caught before merging. The next change that is
borderline too big for a late rc is switching the device-dax locking
from rcu to srcu, I couldn't think of a smaller way to make that fix.
The __copy_user_nocache fix will have a full replacement in 4.12 to
move those pmem special case considerations into the pmem driver. The
"libnvdimm: band aid btt vs clear poison locking" commit admits that
our error clearing support for btt went in broken, so we just disable
it in 4.11 and -stable. A replacement / full fix is in the pipeline
for 4.12
Some of these would have been caught earlier had DEBUG_ATOMIC_SLEEP
been enabled on my development station. I wonder if we should have:
config DEBUG_ATOMIC_SLEEP
default PROVE_LOCKING
...since I mistakenly thought I got both with PROVE_LOCKING=y.
These have received a build success notification from the 0day robot,
and some have appeared in a -next release with no reported issues"
* 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
x86, pmem: fix broken __copy_user_nocache cache-bypass assumptions
device-dax: switch to srcu, fix rcu_read_lock() vs pte allocation
libnvdimm: band aid btt vs clear poison locking
libnvdimm: fix reconfig_mutex, mmap_sem, and jbd2_handle lockdep splat
libnvdimm: fix blk free space accounting
acpi, nfit, libnvdimm: fix interleave set cookie calculation (64-bit comparison)
Merge tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi
Pull SCSI fixes from James Bottomley:
"This is seven small fixes which are all for user visible issues that
fortunately only occur in rare circumstances.
The most serious is the sr one in which QEMU can cause us to read
beyond the end of a buffer (I don't think it's exploitable, but just
in case).
The next is the sd capacity fix which means all non 512 byte sector
drives greater than 2TB fail to be correctly sized.
The rest are either in new drivers (qedf) or on error legs"
* tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi:
scsi: ipr: do not set DID_PASSTHROUGH on CHECK CONDITION
scsi: aacraid: fix PCI error recovery path
scsi: sd: Fix capacity calculation with 32-bit sector_t
scsi: qla2xxx: Add fix to read correct register value for ISP82xx.
scsi: qedf: Fix crash due to unsolicited FIP VLAN response.
scsi: sr: Sanity check returned mode data
scsi: sd: Consider max_xfer_blocks if opt_xfer_blocks is unusable
Merge branch 'parisc-4.11-4' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux
Pull parisc fix from Helge Deller:
"Mikulas Patocka fixed a few bugs in our new pa_memcpy() assembler
function, e.g. one bug made the kernel unbootable if source and
destination address are the same"
* 'parisc-4.11-4' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux:
parisc: fix bugs in pa_memcpy
[ 1337.483798] ================================================
[ 1337.483999] [ BUG: lock held when returning to user space! ]
[ 1337.484252] 4.11.0-rc6 #19 Not tainted
[ 1337.484423] ------------------------------------------------
[ 1337.484626] mount/14766 is leaving the kernel with locks still held!
[ 1337.484841] 1 lock held by mount/14766:
[ 1337.485017] #0: (&type->s_umount_key#33/1){+.+.+.}, at: [<ffffffff8124171f>] sget_userns+0x2af/0x520
Caught by xfstests generic/413 which tried to mount with the unsupported
mount option dax. Then xfstests generic/422 ran sync which deadlocks.
Signed-off-by: Martin Brandenburg <martin@omnibond.com> Acked-by: Mike Marshall <hubcap@omnibond.com> Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Normal pathname lookup doesn't allow empty pathnames, but using
AT_EMPTY_PATH (with name_to_handle_at() or fstatat(), for example) you
can trigger an empty pathname lookup.
And not only is the RCU lookup in that case entirely unnecessary
(because we'll obviously immediately finalize the end result), it is
actively wrong.
Why? An empth path is a special case that will return the original
'dirfd' dentry - and that dentry may not actually be RCU-free'd,
resulting in a potential use-after-free if we were to initialize the
path lazily under the RCU read lock and depend on complete_walk()
finalizing the dentry.
The patch 554bfeceb8a22d448cd986fc9efce25e833278a1 ("parisc: Fix access
fault handling in pa_memcpy()") reimplements the pa_memcpy function.
Unfortunatelly, it makes the kernel unbootable. The crash happens in the
function ide_complete_cmd where memcpy is called with the same source
and destination address.
This patch fixes a few bugs in pa_memcpy:
* When jumping to .Lcopy_loop_16 for the first time, don't skip the
instruction "ldi 31,t0" (this bug made the kernel unbootable)
* Use the COND macro when comparing length, so that the comparison is
64-bit (a theoretical issue, in case the length is greater than
0xffffffff)
* Don't use the COND macro after the "extru" instruction (the PA-RISC
specification says that the upper 32-bits of extru result are undefined,
although they are set to zero in practice)
* Fix exception addresses in .Lcopy16_fault and .Lcopy8_fault
* Rename .Lcopy_loop_4 to .Lcopy_loop_8 (so that it is consistent with
.Lcopy8_fault)
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input
Pull input fixes from Dmitry Torokhov:
"Just a small update to xpad driver to recognize yet another gamepad,
and another change making sure userio.h is exported"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input:
Input: xpad - add support for Razer Wildcat gamepad
uapi: add missing install of userio.h
Pull networking fixes from David Miller:
"Things seem to be settling down as far as networking is concerned,
let's hope this trend continues...
1) Add iov_iter_revert() and use it to fix the behavior of
skb_copy_datagram_msg() et al., from Al Viro.
2) Fix the protocol used in the synthetic SKB we cons up for the
purposes of doing a simulated route lookup for RTM_GETROUTE
requests. From Florian Larysch.
3) Don't add noop_qdisc to the per-device qdisc hashes, from Cong
Wang.
4) Don't call netdev_change_features with the team lock held, from
Xin Long.
5) Revert TCP F-RTO extension to catch more spurious timeouts because
it interacts very badly with some middle-boxes. From Yuchung
Cheng.
6) Fix the loss of error values in l2tp {s,g}etsockopt calls, from
Guillaume Nault.
7) ctnetlink uses bit positions where it should be using bit masks,
fix from Liping Zhang.
8) Missing RCU locking in netfilter helper code, from Gao Feng.
9) Avoid double frees and use-after-frees in tcp_disconnect(), from
Eric Dumazet.
10) Don't do a changelink before we register the netdevice in
bridging, from Ido Schimmel.
11) Lock the ipv6 device address list properly, from Rabin Vincent"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (29 commits)
netfilter: ipt_CLUSTERIP: Fix wrong conntrack netns refcnt usage
netfilter: nft_hash: do not dump the auto generated seed
drivers: net: usb: qmi_wwan: add QMI_QUIRK_SET_DTR for Telit PID 0x1201
ipv6: Fix idev->addr_list corruption
net: xdp: don't export dev_change_xdp_fd()
bridge: netlink: register netdevice before executing changelink
bridge: implement missing ndo_uninit()
bpf: reference may_access_skb() from __bpf_prog_run()
tcp: clear saved_syn in tcp_disconnect()
netfilter: nf_ct_expect: use proper RCU list traversal/update APIs
netfilter: ctnetlink: skip dumping expect when nfct_help(ct) is NULL
netfilter: make it safer during the inet6_dev->addr_list traversal
netfilter: ctnetlink: make it safer when checking the ct helper name
netfilter: helper: Add the rcu lock when call __nf_conntrack_helper_find
netfilter: ctnetlink: using bit to represent the ct event
netfilter: xt_TCPMSS: add more sanity tests on tcph->doff
net: tcp: Increase TCP_MIB_OUTRSTS even though fail to alloc skb
l2tp: don't mask errors in pppol2tp_getsockopt()
l2tp: don't mask errors in pppol2tp_setsockopt()
tcp: restrict F-RTO to work-around broken middle-boxes
...
Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fixes from Thomas Gleixner:
"A set of small fixes for x86:
- fix locking in RDT to prevent memory leaks and freeing in use
memory
- prevent setting invalid values for vdso32_enabled which cause
inconsistencies for user space resulting in application crashes.
- plug a race in the vdso32 code between fork and sysctl which causes
inconsistencies for user space resulting in application crashes.
- make MPX signal delivery work in compat mode
- make the dmesg output of traps and faults readable again"
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/intel_rdt: Fix locking in rdtgroup_schemata_write()
x86/debug: Fix the printk() debug output of signal_fault(), do_trap() and do_general_protection()
x86/vdso: Plug race between mapping and ELF header setup
x86/vdso: Ensure vdso32_enabled gets set to valid values only
x86/signals: Fix lower/upper bound reporting in compat siginfo
Merge branch 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull irq fixes from Thomas Gleixner:
"The irq department provides:
- two fixes for the CPU affinity spread infrastructure to prevent
unbalanced spreading in corner cases which leads to horrible
performance, because interrupts are rather aggregated than spread
- add a missing spinlock initializer in the imx-gpcv2 init code"
* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
irqchip/irq-imx-gpcv2: Fix spinlock initialization
irq/affinity: Fix extra vecs calculation
irq/affinity: Fix CPU spread for unbalanced nodes
Merge branch 'efi-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull EFI fixes from Thomas Gleixner:
"Three fixes from EFI land:
- prevent accessing a Graphic Output Device (GOP) which the kernel
does not know to handle
- prevent PCI reconfiguration to modify a BAR which covers the
framebuffer because that's already in use through the EFI GOP
interface
- avoid reserving EFI runtime regions as this results in bogus memory
mappings"
* 'efi-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/efi: Don't try to reserve runtime regions
efi/fb: Avoid reconfiguration of BAR that covers the framebuffer
efi/libstub: Skip GOP with PIXEL_BLT_ONLY format
Merge branch 'for-linus-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs
Pull btrfs fixes from Chris Mason:
"Dave Sterba collected a few more fixes for the last rc.
These aren't marked for stable, but I'm putting them in with a batch
were testing/sending by hand for this release"
* 'for-linus-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
Btrfs: fix potential use-after-free for cloned bio
Btrfs: fix segmentation fault when doing dio read
Btrfs: fix invalid dereference in btrfs_retry_endio
btrfs: drop the nossd flag when remounting with -o ssd
Merge branch 'for-next' of git://git.samba.org/sfrench/cifs-2.6
Pull more CIFS fixes from Steve French:
"As promised, here is the remaining set of cifs/smb3 fixes for stable
(and a fix for one regression) now that they have had additional
review and testing"
* 'for-next' of git://git.samba.org/sfrench/cifs-2.6:
CIFS: Fix SMB3 mount without specifying a security mechanism
CIFS: store results of cifs_reopen_file to avoid infinite wait
CIFS: remove bad_network_name flag
CIFS: reconnect thread reschedule itself
CIFS: handle guest access errors to Windows shares
CIFS: Fix null pointer deref during read resp processing
When two function probes are added to set_ftrace_filter, and then one of
them is removed, the update to the function locations is not performed, and
the record keeping of the function states are corrupted, and causes an
ftrace_bug() to occur.
This is easily reproducable by adding two probes, removing one, and then
adding it back again.
Cc: stable@vger.kernel.org Fixes: 59df055f1991 ("ftrace: trace different functions with a different tracer") Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Ming Lei [Fri, 14 Apr 2017 19:58:29 +0000 (13:58 -0600)]
block: fix bio_will_gap() for first bvec with offset
Commit 729204ef49ec("block: relax check on sg gap") allows us to merge
bios, if both are physically contiguous. This change can merge a huge
number of small bios, through mkfs for example, mkfs.ntfs running time
can be decreased to ~1/10.
But if one rq starts with a non-aligned buffer (the 1st bvec's bv_offset
is non-zero) and if we allow the merge, it is quite difficult to respect
sg gap limit, especially the max segment size, or we risk having an
unaligned virtual boundary. This patch tries to avoid the issue by
disallowing a merge, if the req starts with an unaligned buffer.
Also add comments to explain why the merged segment can't end in
unaligned virt boundary.
Fixes: 729204ef49ec ("block: relax check on sg gap") Tested-by: Johannes Thumshirn <jthumshirn@suse.de> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: Ming Lei <ming.lei@redhat.com>
Rewrote parts of the commit message and comments.
projects / karo-tx-linux.git / log