pNFS: Clear the layout metadata if the server changed the layout stateid
If the server changed the layout stateid's "other" field, then
we should treat the old layout as being completely gone. In that
case, we want to clear the metadata such as scheduled layoutreturns.
Do this by calling pnfs_mark_layout_stateid_invalid().
NFS: pnfs_mark_matching_lsegs_return() should match the layout sequence id
When determining which layout segments to return, we do want
pnfs_mark_matching_lsegs_return to check that they match the layout
sequence id. This ensures that we don't waste time if the server
is replaying a layout recall that has already been satisfied.
pNFS: Ensure layoutreturn acts as a completion for layout callbacks
When we return NFS_OK to the CB_LAYOUTRECALL, we are required to
send a layoutreturn that "completes" that layout recall request, using
the correct stateid.
If the client holds no layout for this inode, then return
NFS4ERR_NOMATCHING_LAYOUT; it probably forgot the layout.
If the client finds the inode among the list of layouts, but the corresponding
stateid has not yet been initialised, then return NFS4ERR_DELAY to ask the
server to retry once the outstanding LAYOUTGET is complete.
If the current layout stateid's "other" field does not match the recalled
stateid, return NFS4ERR_BAD_STATEID.
If already processing a layout recall with a newer stateid, return
NFS4ERR_OLD_STATEID. This can only happens for servers that are
non-compliant with the NFSv4.1 protocol.
If already processing a layout recall with an older stateid, return
NFS4ERR_DELAY to ask the server to retry once the outstanding
LAYOUTRETURN is complete. Again, this is technically incompliant with
the NFSv4.1 protocol.
If the current layout sequence id is newer than the recalled stateid's
sequence id, return NFS4ERR_OLD_STATEID. This too implies protocol
non-compliance.
If the current layout sequence id is older than the recalled stateid's
sequence id+1, return NFS4ERR_DELAY.
pNFS: Always update the layout barrier seqid on LAYOUTGET
Currently, pnfs_set_layout_stateid() will update the layout sequence
id barrier only if the stateid itself is newer than the current
layout stateid. However in a situation where multiple LAYOUTGET calls
and a LAYOUTRETURN raced, it is entirely possible for one of the
LAYOUTGET to set the current stateid to something newer than the
LAYOUTRETURN that needs to set the barrier.
The fix is to allow the "update_barrier" flag to force a check as to
whether or not the barrier needs to be updated.
NFS doesn't expect requests with wb_bytes set to zero and may make
unexpected decisions about how to handle that request at the page IO layer.
Skip request creation if we won't have any wb_bytes in the request.
When bl_parse_deviceid() fails in bl_alloc_deviceid_node() on
blkdev_get_by_*() step we get an pnfs_block_dev struct that is
uninitialized except for bdev field which is set to whatever error
blkdev_get_by_*() returns. bl_free_device() then tries to call
blkdev_put() if bdev is not 0 resulting in a wrong pointer dereference.
Fixing this by setting bdev in struct pnfs_block_dev only if we didn't
get an error from blkdev_get_by_*().
pNFS/files: filelayout_write_done_cb must call nfs_writeback_update_inode()
All write callbacks are required to call nfs_writeback_update_inode() upon
success to ensure that file size changes are recorded, and the attribute
cache is invalidated.
Frank Sorenson [Fri, 8 Jul 2016 21:35:25 +0000 (16:35 -0500)]
sunrpc: Prevent resvport min/max inversion via sysfs and module parameter
The current min/max resvport settings are independently limited
by the entire range of allowed ports, so max_resvport can be
set to a port lower than min_resvport.
Prevent inversion of min/max values when set through sysfs and
module parameter by setting the limits dependent on each other.
Signed-off-by: Frank Sorenson <sorenson@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Frank Sorenson [Fri, 8 Jul 2016 21:35:24 +0000 (16:35 -0500)]
sunrpc: Prevent resvport min/max inversion via sysctl
The current min/max resvport settings are independently limited
by the entire range of allowed ports, so max_resvport can be
set to a port lower than min_resvport.
Prevent inversion of min/max values when set through sysctl by
setting the limits dependent on each other.
Signed-off-by: Frank Sorenson <sorenson@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Frank Sorenson [Fri, 8 Jul 2016 21:35:23 +0000 (16:35 -0500)]
sunrpc: Fix reserved port range calculation
The range calculation for choosing the random reserved port will panic
with divide-by-zero when min_resvport == max_resvport, a range of one
port, not zero.
Fix the reserved port range calculation by adding one to the difference.
Signed-off-by: Frank Sorenson <sorenson@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Frank Sorenson [Mon, 27 Jun 2016 19:17:19 +0000 (15:17 -0400)]
sunrpc: Fix bit count when setting hashtable size to power-of-two
Author: Frank Sorenson <sorenson@redhat.com>
Date: 2016-06-27 13:55:48 -0500
sunrpc: Fix bit count when setting hashtable size to power-of-two
The hashtable size is incorrectly calculated as the next higher
power-of-two when being set to a power-of-two. fls() returns the
bit number of the most significant set bit, with the least
significant bit being numbered '1'. For a power-of-two, fls()
will return a bit number which is one higher than the number of bits
required, leading to a hashtable which is twice the requested size.
In addition, the value of (1 << nbits) will always be at least num,
so the test will never be true.
Fix the hash table size calculation to correctly set hashtable
size, and eliminate the unnecessary check.
Signed-off-by: Frank Sorenson <sorenson@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Scott Mayhew [Tue, 7 Jun 2016 19:14:48 +0000 (15:14 -0400)]
sunrpc: move NO_CRKEY_TIMEOUT to the auth->au_flags
A generic_cred can be used to look up a unx_cred or a gss_cred, so it's
not really safe to use the the generic_cred->acred->ac_flags to store
the NO_CRKEY_TIMEOUT flag. A lookup for a unx_cred triggered while the
KEY_EXPIRE_SOON flag is already set will cause both NO_CRKEY_TIMEOUT and
KEY_EXPIRE_SOON to be set in the ac_flags, leaving the user associated
with the auth_cred to be in a state where they're perpetually doing 4K
NFS_FILE_SYNC writes.
This can be reproduced as follows:
1. Mount two NFS filesystems, one with sec=krb5 and one with sec=sys.
They do not need to be the same export, nor do they even need to be from
the same NFS server. Also, v3 is fine.
$ sudo mount -o v3,sec=krb5 server1:/export /mnt/krb5
$ sudo mount -o v3,sec=sys server2:/export /mnt/sys
2. As the normal user, before accessing the kerberized mount, kinit with
a short lifetime (but not so short that renewing the ticket would leave
you within the 4-minute window again by the time the original ticket
expires), e.g.
$ kinit -l 10m -r 60m
3. Do some I/O to the kerberized mount and verify that the writes are
wsize, UNSTABLE:
$ dd if=/dev/zero of=/mnt/krb5/file bs=1M count=1
4. Wait until you're within 4 minutes of key expiry, then do some more
I/O to the kerberized mount to ensure that RPC_CRED_KEY_EXPIRE_SOON gets
set. Verify that the writes are 4K, FILE_SYNC:
$ dd if=/dev/zero of=/mnt/krb5/file bs=1M count=1
5. Now do some I/O to the sec=sys mount. This will cause
RPC_CRED_NO_CRKEY_TIMEOUT to be set:
$ dd if=/dev/zero of=/mnt/sys/file bs=1M count=1
6. Writes for that user will now be permanently 4K, FILE_SYNC for that
user, regardless of which mount is being written to, until you reboot
the client. Renewing the kerberos ticket (assuming it hasn't already
expired) will have no effect. Grabbing a new kerberos ticket at this
point will have no effect either.
Move the flag to the auth->au_flags field (which is currently unused)
and rename it slightly to reflect that it's no longer associated with
the auth_cred->ac_flags. Add the rpc_auth to the arg list of
rpcauth_cred_key_to_expire and check the au_flags there too. Finally,
add the inode to the arg list of nfs_ctx_key_to_expire so we can
determine the rpc_auth to pass to rpcauth_cred_key_to_expire.
Signed-off-by: Scott Mayhew <smayhew@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Steve Dickson [Wed, 25 May 2016 14:36:50 +0000 (10:36 -0400)]
mount: use sec= that was specified on the command line
When older servers return RPC_AUTH_NULL, it means the
rpc creds will be ignored. In that case use the sec=
that was specified instead of setting sec=null
pNFS: Fix LAYOUTGET handling of NFS4ERR_BAD_STATEID and NFS4ERR_EXPIRED
We want to recover the open stateid if there is no layout stateid
and/or the stateid argument matches an open stateid.
Otherwise throw out the existing layout and recover from scratch, as
the layout stateid is bad.
pNFS: Handle NFS4ERR_RECALLCONFLICT correctly in LAYOUTGET
Instead of giving up altogether and falling back to doing I/O
through the MDS, which may make the situation worse, wait for
2 lease periods for the callback to resolve itself, and then
try destroying the existing layout.
Only if this was an attempt at getting a first layout, do we
give up altogether, as the server is clearly crazy.
pNFS: Fix post-layoutget error handling in pnfs_update_layout()
The non-retry error path is currently broken and ends up releasing the
reference to the layout twice. It also can end up clearing the
NFS_LAYOUT_FIRST_LAYOUTGET flag twice, causing a race.
In addition, the retry path will fail to decrement the plh_outstanding
counter.
SUNRPC: Fix infinite looping in rpc_clnt_iterate_for_each_xprt
If there were less than 2 entries in the multipath list, then
xprt_iter_next_entry_multiple() would never advance beyond the
first entry, which is correct for round robin behaviour, but not
for the list iteration.
The end result would be infinite looping in rpc_clnt_iterate_for_each_xprt()
as we would never see the xprt == NULL condition fulfilled.
Reported-by: Oleg Drokin <green@linuxhacker.ru> Fixes: 80b14d5e61ca ("SUNRPC: Add a structure to track multiple transports") Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
nfs/blocklayout: support RH/Fedora dm-mpath device nodes
Instead of reusing the wwn-* names for multipath devices nodes RHEL and
Fedora introduce new dm-mpath-uuid-* nodes with a slightly different
naming scheme. Try these names first to ensure we always get a
multipath-capable device if it exists.
Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
The current code works with the standard udev/systemd names, but we'll have
to add another method in the next patch. Refactor it into a separate helper
to make room for the new variant.
Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
NFSv4: Revert "Truncating file opens should also sync O_DIRECT writes"
We're not holding any locks, so both nfs_wb_all() and inode_dio_wait()
are unenforcible and have livelock potential. Just limit ourselves to
flushing out the data.
Chuck Lever [Wed, 29 Jun 2016 17:55:22 +0000 (13:55 -0400)]
NFS: Don't drop CB requests with invalid principals
Before commit 778be232a207 ("NFS do not find client in NFSv4
pg_authenticate"), the Linux callback server replied with
RPC_AUTH_ERROR / RPC_AUTH_BADCRED, instead of dropping the CB
request. Let's restore that behavior so the server has a chance to
do something useful about it, and provide a warning that helps
admins correct the problem.
Fixes: 778be232a207 ("NFS do not find client in NFSv4 ...") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:55:14 +0000 (13:55 -0400)]
svc: Avoid garbage replies when pc_func() returns rpc_drop_reply
If an RPC program does not set vs_dispatch and pc_func() returns
rpc_drop_reply, the server sends a reply anyway containing a single
word containing the value RPC_DROP_REPLY (in network byte-order, of
course). This is a nonsense RPC message.
Fixes: 9e701c610923 ("svcrpc: simpler request dropping") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:55:06 +0000 (13:55 -0400)]
xprtrdma: No direct data placement with krb5i and krb5p
Direct data placement is not allowed when using flavors that
guarantee integrity or privacy. When such security flavors are in
effect, don't allow the use of Read and Write chunks for moving
individual data items. All messages larger than the inline threshold
are sent via Long Call or Long Reply.
On my systems (CX-3 Pro on FDR), for small I/O operations, the use
of Long messages adds only around 5 usecs of latency in each
direction.
Note that when integrity or encryption is used, the host CPU touches
every byte in these messages. Even if it could be used, data
movement offload doesn't buy much in this case.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:54:58 +0000 (13:54 -0400)]
xprtrdma: Clean up fixup_copy_count accounting
fixup_copy_count should count only the number of bytes copied to the
page list. The head and tail are now always handled without a data
copy.
And the debugging at the end of rpcrdma_inline_fixup() is also no
longer necessary, since copy_len will be non-zero when there is reply
data in the tail (a normal and valid case).
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:54:49 +0000 (13:54 -0400)]
xprtrdma: Update only specific fields in private receive buffer
Now that rpcrdma_inline_fixup() updates only two fields in
rq_rcv_buf, a full memcpy of that structure to rq_private_buf is
unwarranted. Updating rq_private_buf fields only where needed also
better documents what is going on.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:54:41 +0000 (13:54 -0400)]
xprtrdma: Do not update {head, tail}.iov_len in rpcrdma_inline_fixup()
While trying NFSv4.0/RDMA with sec=krb5p, I noticed small NFS READ
operations failed. After the client unwrapped the NFS READ reply
message, the NFS READ XDR decoder was not able to decode the reply.
The message was "Server cheating in reply", with the reported
number of received payload bytes being zero. Applications reported
a read(2) that returned -1/EIO.
The problem is rpcrdma_inline_fixup() sets the tail.iov_len to zero
when the incoming reply fits entirely in the head iovec. The zero
tail.iov_len confused xdr_buf_trim(), which then mangled the actual
reply data instead of simply removing the trailing GSS checksum.
As near as I can tell, RPC transports are not supposed to update the
head.iov_len, page_len, or tail.iov_len fields in the receive XDR
buffer when handling an incoming RPC reply message. These fields
contain the length of each component of the XDR buffer, and hence
the maximum number of bytes of reply data that can be stored in each
XDR buffer component. I've concluded this because:
- This is how xdr_partial_copy_from_skb() appears to behave
- rpcrdma_inline_fixup() already does not alter page_len
- call_decode() compares rq_private_buf and rq_rcv_buf and WARNs
if they are not exactly the same
Unfortunately, as soon as I tried the simple fix to just remove the
line that sets tail.iov_len to zero, I saw that the logic that
appends the implicit Write chunk pad inline depends on inline_fixup
setting tail.iov_len to zero.
To address this, re-organize the tail iovec handling logic to use
the same approach as with the head iovec: simply point tail.iov_base
to the correct bytes in the receive buffer.
While I remember all this, write down the conclusion in documenting
comments.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:54:33 +0000 (13:54 -0400)]
xprtrdma: rpcrdma_inline_fixup() overruns the receive page list
When the remaining length of an incoming reply is longer than the
XDR buf's page_len, switch over to the tail iovec instead of
copying more than page_len bytes into the page list.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:54:25 +0000 (13:54 -0400)]
xprtrdma: Chunk list encoders no longer share one rl_segments array
Currently, all three chunk list encoders each use a portion of the
one rl_segments array in rpcrdma_req. This is because the MWs for
each chunk list were preserved in rl_segments so that ro_unmap could
find and invalidate them after the RPC was complete.
However, now that MWs are placed on a per-req linked list as they
are registered, there is no longer any information in rpcrdma_mr_seg
that is shared between ro_map and ro_unmap_{sync,safe}, and thus
nothing in rl_segments needs to be preserved after
rpcrdma_marshal_req is complete.
Thus the rl_segments array can be used now just for the needs of
each rpcrdma_convert_iovs call. Once each chunk list is encoded, the
next chunk list encoder is free to re-use all of rl_segments.
This means all three chunk lists in one RPC request can now each
encode a full size data payload with no increase in the size of
rl_segments.
This is a key requirement for Kerberos support, since both the Call
and Reply for a single RPC transaction are conveyed via Long
messages (RDMA Read/Write). Both can be large.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:54:16 +0000 (13:54 -0400)]
xprtrdma: Place registered MWs on a per-req list
Instead of placing registered MWs sparsely into the rl_segments
array, place these MWs on a per-req list.
ro_unmap_{sync,safe} can then simply pull those MWs off the list
instead of walking through the array.
This change significantly reduces the size of struct rpcrdma_req
by removing nsegs and rl_mw from every array element.
As an additional clean-up, chunk co-ordinates are returned in the
"*mw" output argument so they are no longer needed in every
array element.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:54:08 +0000 (13:54 -0400)]
xprtrdma: Release orphaned MRs immediately
Instead of leaving orphaned MRs to be released when the transport
is destroyed, release them immediately. The MR free list can now be
replenished if it becomes exhausted.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:54:00 +0000 (13:54 -0400)]
xprtrdma: Allocate MRs on demand
Frequent MR list exhaustion can impact I/O throughput, so enough MRs
are always created during transport set-up to prevent running out.
This means more MRs are created than most workloads need.
Commit 94f58c58c0b4 ("xprtrdma: Allow Read list and Reply chunk
simultaneously") introduced support for sending two chunk lists per
RPC, which consumes more MRs per RPC.
Instead of trying to provision more MRs, introduce a mechanism for
allocating MRs on demand. A few MRs are allocated during transport
set-up to kick things off.
This significantly reduces the average number of MRs per transport
while allowing the MR count to grow for workloads or devices that
need more MRs.
FRWR with mlx4 allocated almost 400 MRs per transport before this
patch. Now it starts with 32.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:53:52 +0000 (13:53 -0400)]
xprtrdma: Chunk list encoders must not return zero
Clean up, based on code audit: Remove the possibility that the
chunk list XDR encoders can return zero, which would be interpreted
as a NULL.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:53:43 +0000 (13:53 -0400)]
xprtrdma: Honor ->send_request API contract
Commit c93c62231cf5 ("xprtrdma: Disconnect on registration failure")
added a disconnect for some RPC marshaling failures. This is needed
only in a handful of cases, but it was triggering for simple stuff
like temporary resource shortages. Try to straighten this out.
Fix up the lower layers so they don't return -ENOMEM or other error
codes that the RPC client's FSM doesn't explicitly recognize.
Also fix up the places in the send_request path that do want a
disconnect. For example, when ib_post_send or ib_post_recv fail,
this is a sign that there is a send or receive queue resource
miscalculation. That should be rare, and is a sign of a software
bug. But xprtrdma can recover: disconnect to reset the transport and
start over.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:53:35 +0000 (13:53 -0400)]
xprtrdma: Reply buffer exhaustion can be catastrophic
Not having an rpcrdma_rep at call_allocate time can be a problem.
It means that send_request can't post a receive buffer to catch
the RPC's reply. Possible consequences are RPC timeouts or even
transport deadlock.
Instead of allowing an RPC to proceed if an rpcrdma_rep is
not available, return NULL to force call_allocate to wait and
try again.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:53:27 +0000 (13:53 -0400)]
xprtrdma: Clean up device capability detection
Clean up: Move device capability detection into memreg-specific
source files.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:53:19 +0000 (13:53 -0400)]
xprtrdma: Remove rpcrdma_map_one() and friends
Clean up: ALLPHYSICAL is gone and FMR has been converted to use
scatterlists. There are no more users of these functions.
This patch shrinks the size of struct rpcrdma_req by about 3500
bytes on x86_64. There is one of these structs for each RPC credit
(128 credits per transport connection).
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
No HCA or RNIC in the kernel tree requires the use of ALLPHYSICAL.
ALLPHYSICAL advertises in the clear on the network fabric an R_key
that is good for all of the client's memory. No known exploit
exists, but theoretically any user on the server can use that R_key
on the client's QP to read or update any part of the client's memory.
ALLPHYSICAL exposes the client to server bugs, including:
o base/bounds errors causing data outside the i/o buffer to be
accessed
o RDMA access after reply causing data corruption and/or integrity
fail
ALLPHYSICAL can't protect application memory regions from server
update after a local signal or soft timeout has terminated an RPC.
ALLPHYSICAL chunks are no larger than a page. Special cases to
handle small chunks and long chunk lists have been a source of
implementation complexity and bugs.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:53:02 +0000 (13:53 -0400)]
xprtrdma: Do not leak an MW during a DMA map failure
Based on code audit.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:52:54 +0000 (13:52 -0400)]
xprtrdma: Refactor MR recovery work queues
I found that commit ead3f26e359e ("xprtrdma: Add ro_unmap_safe
memreg method"), which introduces ro_unmap_safe, never wired up the
FMR recovery worker.
The FMR and FRWR recovery work queues both do the same thing.
Instead of setting up separate individual work queues for this,
schedule a delayed worker to deal with them, since recovering MRs is
not performance-critical.
Fixes: ead3f26e359e ("xprtrdma: Add ro_unmap_safe memreg method") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:52:45 +0000 (13:52 -0400)]
xprtrdma: Use scatterlist for DMA mapping and unmapping under FMR
The use of a scatterlist for handling DMA mapping and unmapping
was recently introduced in frwr_ops.c in commit 4143f34e01e9
("xprtrdma: Port to new memory registration API"). That commit did
not make a similar update to xprtrdma's FMR support because the
core ib_map_phys_fmr() and ib_unmap_fmr() APIs have not been changed
to take a scatterlist argument.
However, FMR still needs to do DMA mapping and unmapping. It appears
that RDS, for example, uses a scatterlist for this, then builds the
DMA addr array for the ib_map_phys_fmr call separately. I see that
SRP also utilizes a scatterlist for DMA mapping. xprtrdma can do
something similar.
This modernization is used immediately to properly defer DMA
unmapping during fmr_unmap_safe (a FIXME). It separates the DMA
unmapping coordinates from the rl_segments array. This array, being
part of an rpcrdma_req, is always re-used immediately when an RPC
exits. A scatterlist is allocated in memory independent of the
rl_segments array, so it can be preserved indefinitely (ie, until
the MR invalidation and DMA unmapping can actually be done by a
worker thread).
The FRWR and FMR DMA mapping code are slightly different from each
other now, and will diverge further when the "Check for holes" logic
can be removed from FRWR (support for SG_GAP MRs). So I chose not to
create helpers for the common-looking code.
Fixes: ead3f26e359e ("xprtrdma: Add ro_unmap_safe memreg method") Suggested-by: Sagi Grimberg <sagi@lightbits.io> Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:52:37 +0000 (13:52 -0400)]
xprtrdma: Rename fields in rpcrdma_fmr
Clean up: Use the same naming convention used in other
RPC/RDMA-related data structures.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:52:29 +0000 (13:52 -0400)]
xprtrdma: Move init and release helpers
Clean up: Moving these helpers in a separate patch makes later
patches more readable.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:52:21 +0000 (13:52 -0400)]
xprtrdma: Create common scatterlist fields in rpcrdma_mw
Clean up: FMR is about to replace the rpcrdma_map_one code with
scatterlists. Move the scatterlist fields out of the FRWR-specific
union and into the generic part of rpcrdma_mw.
One minor change: -EIO is now returned if FRWR registration fails.
The RPC is terminated immediately, since the problem is likely due
to a software bug, thus retrying likely won't help.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Chuck Lever [Wed, 29 Jun 2016 17:52:12 +0000 (13:52 -0400)]
xprtrdma: Remove FMRs from the unmap list after unmapping
ib_unmap_fmr() takes a list of FMRs to unmap. However, it does not
remove the FMRs from this list as it processes them. Other
ib_unmap_fmr() call sites are careful to remove FMRs from the list
after ib_unmap_fmr() returns.
Since commit 7c7a5390dc6c8 ("xprtrdma: Add ro_unmap_sync method for FMR")
fmr_op_unmap_sync passes more than one FMR to ib_unmap_fmr(), but
it didn't bother to remove the FMRs from that list once the call was
complete.
I've noticed some instability that could be related to list
tangling by the new fmr_op_unmap_sync() logic. In an abundance
of caution, add some defensive logic to clean up properly after
ib_unmap_fmr().
Fixes: 7c7a5390dc6c8 ("xprtrdma: Add ro_unmap_sync method for FMR") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
The well-spotted fallocate undo fix is good in most cases, but not when
fallocate failed on the very first page. index 0 then passes lend -1
to shmem_undo_range(), and that has two bad effects: (a) that it will
undo every fallocation throughout the file, unrestricted by the current
range; but more importantly (b) it can cause the undo to hang, because
lend -1 is treated as truncation, which makes it keep on retrying until
every page has gone, but those already fully instantiated will never go
away. Big thank you to xfstests generic/269 which demonstrates this.
Fixes: b9b4bb26af01 ("tmpfs: don't undo fallocate past its last page") Cc: stable@vger.kernel.org Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Merge tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi
Pull SCSI fixes from James Bottomley:
"Three fixes. One is the qla24xx MSI regression, one is a theoretical
problem over blacklist matching, which would bite USB badly if it ever
triggered and one is a system hang with a particular type of IPR
device"
* tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi:
qla2xxx: Fix NULL pointer deref in QLA interrupt
SCSI: fix new bug in scsi_dev_info_list string matching
ipr: Clear interrupt on croc/crocodile when running with LSI
Merge tag 'ecryptfs-4.7-rc7-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tyhicks/ecryptfs
Pull eCryptfs fixes from Tyler Hicks:
"Provide a more concise fix for CVE-2016-1583:
- Additionally fixes linux-stable regressions caused by the
cherry-picking of the original fix
Some very minor changes that have queued up:
- Fix typos in code comments
- Remove unnecessary check for NULL before destroying kmem_cache"
* tag 'ecryptfs-4.7-rc7-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tyhicks/ecryptfs:
ecryptfs: don't allow mmap when the lower fs doesn't support it
Revert "ecryptfs: forbid opening files without mmap handler"
ecryptfs: fix spelling mistakes
eCryptfs: fix typos in comment
ecryptfs: drop null test before destroy functions
Merge tag 'iommu-fixes-v4.7-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull IOMMU fixes from Joerg Roedel:
"Two Fixes:
- Intel VT-d fix for a suspend/resume issue, introduced with the
scalability improvements in this cycle.
- AMD IOMMU fix for systems that have unity mappings defined. There
was a race where translation got enabled before the unity mappings
were in place. This issue was seen on some HP servers"
* tag 'iommu-fixes-v4.7-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
iommu/amd: Fix unity mapping initialization race
iommu/vt-d: Fix infinite loop in free_all_cpu_cached_iovas
Merge tag 'for-linus-4.7b-rc6-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip
Pull xen bug fixes from David Vrabel:
- Fix two bugs in the handling of xenbus transactions.
- Make the xen acpi driver compatible with Xen 4.7.
* tag 'for-linus-4.7b-rc6-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
xen/acpi: allow xen-acpi-processor driver to load on Xen 4.7
xenbus: simplify xenbus_dev_request_and_reply()
xenbus: don't bail early from xenbus_dev_request_and_reply()
xenbus: don't BUG() on user mode induced condition
Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull arm64 fixes from Will Deacon:
"A couple of late fixes here, but one that we've been sitting on for a
few weeks while the details were worked out. Specifically, we now
enforce USER_DS on taking exceptions whilst in the kernel, which
avoids leaking kernel data to userspace through things like perf. The
other patch is an update to a workaround for a hardware erratum on
some Cavium SoCs.
Summary:
- Enforce USER_DS on exception entry from EL1
- Apply workaround for Cavium errata #27456 on Thunderx-81xx parts"
* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
arm64: Enable workaround for Cavium erratum 27456 on thunderx-81xx
arm64: kernel: Save and restore UAO and addr_limit on exception entry
Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fixes from Ingo Molnar:
"Three fixes:
- A boot crash fix with certain configs
- a MAINTAINERS entry update
- Documentation typo fixes"
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/Documentation: Fix various typos in Documentation/x86/ files
x86/amd_nb: Fix boot crash on non-AMD systems
MAINTAINERS: Update the Calgary IOMMU entry
Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler fixes from Ingo Molnar:
"Two load-balancing fixes for cgroups-intense workloads"
* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/fair: Fix calc_cfs_shares() fixed point arithmetics width confusion
sched/fair: Fix effective_load() to consistently use smoothed load
Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf fixes from Ingo Molnar:
"Various fixes:
- 32-bit callgraph bug fix
- suboptimal event group scheduling bug fix
- event constraint fixes for Broadwell/Skylake
- RAPL module name collision fix"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/core: Fix pmu::filter_match for SW-led groups
x86/perf/intel/rapl: Fix module name collision with powercap intel-rapl
perf/x86: Fix 32-bit perf user callgraph collection
perf/x86/intel: Update event constraints when HT is off
Merge branch 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull irq fixes from Ingo Molnar:
"Two MIPS-GIC irqchip driver fixes to unbreak certain MIPS boards"
* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
irqchip/mips-gic: Match IPI IRQ domain by bus token only
irqchip/mips-gic: Map to VPs using HW VPNum
Merge tag 'gpio-v4.7-5' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio
Pull GPIO fixes from Linus Walleij:
"I don't like to toss in last minute patches, but these are all for
things that are broken, and have bitten people for real. Two of them
go into stable. Maybe all of them if the compile test problem is a
pain in the ass also for stable folks.
Final (hopefully) GPIO fixes for v4.7:
- Fix an oops on the Asus Eee PC 1201
- Revert a patch trying to split GPIO parsing and GPIO configuration
- Revert a too liberal compile testing thing"
* tag 'gpio-v4.7-5' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio:
Revert "gpio: gpiolib-of: Allow compile testing"
Revert "gpiolib: Split GPIO flags parsing and GPIO configuration"
gpio: sch: Fix Oops on module load on Asus Eee PC 1201
Merge tag 'drm-fixes-for-v4.7-rc7' of git://people.freedesktop.org/~airlied/linux
Pull drm fixes from Dave Airlie:
"One nouveau fix, and a few AMD Polaris fixes and some Allwinner fixes.
I've got some vmware fixes that I might send separate over the
weekend, they fix some black screens, but I'm still debating them"
* tag 'drm-fixes-for-v4.7-rc7' of git://people.freedesktop.org/~airlied/linux:
drm/amd/powerplay: Update CKS on/ CKS off voltage offset calculation.
drm/amd/powerplay: fix bug that get wrong polaris evv voltage.
drm/amd/powerplay: incorrectly use of the function return value
drm/amd/powerplay: fix incorrect voltage table value for tonga
drm/amd/powerplay: fix incorrect voltage table value for polaris10
drm/nouveau/disp/sor/gf119: select correct sor when poking training pattern
gpu: drm: sun4i_drv: add missing of_node_put after calling of_parse_phandle
drm/sun4i: Send vblank event when the CRTC is disabled
drm/sun4i: Report proper vblank
Jeff Mahoney [Tue, 5 Jul 2016 21:32:30 +0000 (17:32 -0400)]
ecryptfs: don't allow mmap when the lower fs doesn't support it
There are legitimate reasons to disallow mmap on certain files, notably
in sysfs or procfs. We shouldn't emulate mmap support on file systems
that don't offer support natively.
CVE-2016-1583
Signed-off-by: Jeff Mahoney <jeffm@suse.com> Cc: stable@vger.kernel.org
[tyhicks: clean up f_op check by using ecryptfs_file_to_lower()] Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
Jan Beulich [Fri, 8 Jul 2016 12:15:07 +0000 (06:15 -0600)]
xen/acpi: allow xen-acpi-processor driver to load on Xen 4.7
As of Xen 4.7 PV CPUID doesn't expose either of CPUID[1].ECX[7] and
CPUID[0x80000007].EDX[7] anymore, causing the driver to fail to load on
both Intel and AMD systems. Doing any kind of hardware capability
checks in the driver as a prerequisite was wrong anyway: With the
hypervisor being in charge, all such checking should be done by it. If
ACPI data gets uploaded despite some missing capability, the hypervisor
is free to ignore part or all of that data.
Ditch the entire check_prereq() function, and do the only valid check
(xen_initial_domain()) in the caller in its place.
Signed-off-by: Jan Beulich <jbeulich@suse.com> Cc: <stable@vger.kernel.org> Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Jan Beulich [Thu, 7 Jul 2016 07:32:04 +0000 (01:32 -0600)]
xenbus: don't bail early from xenbus_dev_request_and_reply()
xenbus_dev_request_and_reply() needs to track whether a transaction is
open. For XS_TRANSACTION_START messages it calls transaction_start()
and for XS_TRANSACTION_END messages it calls transaction_end().
If sending an XS_TRANSACTION_START message fails or responds with an
an error, the transaction is not open and transaction_end() must be
called.
If sending an XS_TRANSACTION_END message fails, the transaction is
still open, but if an error response is returned the transaction is
closed.
Commit 027bd7e89906 ("xen/xenbus: Avoid synchronous wait on XenBus
stalling shutdown/restart") introduced a regression where failed
XS_TRANSACTION_START messages were leaving the transaction open. This
can cause problems with suspend (and migration) as all transactions
must be closed before suspending.
It appears that the problematic change was added accidentally, so just
remove it.
Signed-off-by: Jan Beulich <jbeulich@suse.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Merge tag 'acpi-4.7-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull ACPI fixes from Rafael Wysocki:
"All of these fix recent regressions in ACPICA, in the ACPI PCI IRQ
management code and in the ACPI AML debugger.
Specifics:
- Fix a lock ordering issue in ACPICA introduced by a recent commit
that attempted to fix a deadlock in the dynamic table loading code
which in turn appeared after changes related to the handling of
module-level AML also made in this cycle (Lv Zheng).
- Fix a recent regression in the ACPI IRQ management code that may
cause PCI drivers to be unable to register an IRQ if that IRQ
happens to be shared with a device on the ISA bus, like the
parallel port, by reverting one commit entirely and restoring the
previous behavior in two other places (Sinan Kaya).
- Fix a recent regression in the ACPI AML debugger introduced by the
commit that removed incorrect usage of IS_ERR_VALUE() from multiple
places (Lv Zheng)"
* tag 'acpi-4.7-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
ACPI / debugger: Fix regression introduced by IS_ERR_VALUE() removal
ACPICA: Namespace: Fix namespace/interpreter lock ordering
ACPI,PCI,IRQ: separate ISA penalty calculation
Revert "ACPI, PCI, IRQ: remove redundant code in acpi_irq_penalty_init()"
ACPI,PCI,IRQ: factor in PCI possible
Merge tag 'pm-4.7-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull power management fixes from Rafael Wysocki:
"One fix for a recent cpuidle core change that, against all odds,
introduced a functional regression on Power systems and the fix for
the crash during resume from hibernation on x86-64 that has been in
the works for the last few weeks (it actually was ready last week, but
I wanted to allow the reporters to test if for some more time).
Specifics:
- Fix a recent performance regression on Power systems (powernv and
pseries) introduced by a core cpuidle commit that decreased the
precision of the last_residency conversion from nano- to
microseconds, which should not matter in theory, but turned out to
play not-so-well with the special "snooze" idle state on Power
(Shreyas B Prabhu).
- Fix a crash during resume from hibernation on x86-64 caused by
possible corruption of the kernel text part of page tables in the
last phase of image restoration exposed by a security-related
change during the 4.3 development cycle (Rafael Wysocki)"
* tag 'pm-4.7-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
cpuidle: Fix last_residency division
x86/power/64: Fix kernel text mapping corruption during image restoration
Dave Airlie [Fri, 8 Jul 2016 03:29:11 +0000 (13:29 +1000)]
Merge tag 'sunxi-drm-fixes-for-4.7-2' of https://git.kernel.org/pub/scm/linux/kernel/git/mripard/linux into drm-fixes
Allwinner DRM driver fixes for 4.7, take 2
A new set of fixes for the sun4i driver, mostly related to vblank handling,
and a minor fix to release a reference on the device tree nodes we're
parsing in the probe logic.
* tag 'sunxi-drm-fixes-for-4.7-2' of https://git.kernel.org/pub/scm/linux/kernel/git/mripard/linux:
gpu: drm: sun4i_drv: add missing of_node_put after calling of_parse_phandle
drm/sun4i: Send vblank event when the CRTC is disabled
drm/sun4i: Report proper vblank
apparmor: fix oops, validate buffer size in apparmor_setprocattr()
When proc_pid_attr_write() was changed to use memdup_user apparmor's
(interface violating) assumption that the setprocattr buffer was always
a single page was violated.
The size test is not strictly speaking needed as proc_pid_attr_write()
will reject anything larger, but for the sake of robustness we can keep
it in.
SMACK and SELinux look safe to me, but somebody else should probably
have a look just in case.
Based on original patch from Vegard Nossum <vegard.nossum@oracle.com>
modified for the case that apparmor provides null termination.
Fixes: bb646cdb12e75d82258c2f2e7746d5952d3e321a Reported-by: Vegard Nossum <vegard.nossum@oracle.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: John Johansen <john.johansen@canonical.com> Cc: Paul Moore <paul@paul-moore.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: Eric Paris <eparis@parisplace.org> Cc: Casey Schaufler <casey@schaufler-ca.com> Cc: stable@kernel.org Signed-off-by: John Johansen <john.johansen@canonical.com> Reviewed-by: Tyler Hicks <tyhicks@canonical.com> Signed-off-by: James Morris <james.l.morris@oracle.com>
It fixed a local root exploit but also introduced a dependency on
the lower file system implementing an mmap operation just to open a file,
which is a bit of a heavy hammer. The right fix is to have mmap depend
on the existence of the mmap handler instead.
Signed-off-by: Jeff Mahoney <jeffm@suse.com> Cc: stable@vger.kernel.org Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
Merge branch 'for-linus' of git://git.kernel.dk/linux-block
Pull block IO fixes from Jens Axboe:
"Three small fixes that have been queued up and tested for this series:
- A bug fix for xen-blkfront from Bob Liu, fixing an issue with
incomplete requests during migration.
- A fix for an ancient issue in retrieving the IO priority of a
different PID than self, preventing that task from going away while
we access it. From Omar.
- A writeback fix from Tahsin, fixing a case where we'd call ihold()
with a zero ref count inode"
* 'for-linus' of git://git.kernel.dk/linux-block:
block: fix use-after-free in sys_ioprio_get()
writeback: inode cgroup wb switch should not call ihold()
xen-blkfront: save uncompleted reqs in blkfront_resume()
Merge tag 'configfs-for-4.7' of git://git.infradead.org/users/hch/configfs
Pull configfs fix from Christoph Hellwig:
"A fix from Marek for ppos handling in configfs_write_bin_file, which
was introduced in Linux 4.5, but didn't have any users until recently"
* tag 'configfs-for-4.7' of git://git.infradead.org/users/hch/configfs:
configfs: Remove ppos increment in configfs_write_bin_file
* acpi-pci-fixes:
ACPI,PCI,IRQ: separate ISA penalty calculation
Revert "ACPI, PCI, IRQ: remove redundant code in acpi_irq_penalty_init()"
ACPI,PCI,IRQ: factor in PCI possible
projects / linux-beck.git / log