server-side RPC retranmission cache for non-idempotent operations: these
hacks substituted 0 (success) for the expected EEXIST in the event that
a target name already existed for LINK, SYMLINK, and MKDIR operations,
under the assumption that EEXIST represented a second application of the
original RPC rather than a true failure.
Background: certain NFS operations (in this case, LINK, SYMLINK, and
MKDIR) are not idempotent, as they leave behind persisting state on the
server that prevents them from being replayed without an error;if an UDP
RPC reply is lost leading to a retransmission by theclient, the second
reply will return EEXIST rather than success, asthe new object has
already been created. The NFS client previouslysilently mapped the
EEXIST return into success to paper over thisproblem.
However, in all modern NFS server implementations, a reply cache is kept
in order to retransmit the original reply to a retransmitted request,
rather than performing the operation a second time, allowing this hack
to be avoided. This allows link()-based filelocking over NFS to operate
correctly, as an application requestingthe creation of a new link for a
file to tell if it succeededatomically or not.
Other NFS clients, including Solaris and Linux, generally follow this
behavior for the same reasons. Most clients also now default to TCP,
which also helps avoid the issue of retransmitted but non-idempotent
requests in most cases.
Reported by: Adam McDougall <mcdouga9 at egr dot msu dot edu>,
Timo Sirainen <tss at iki dot fi>
Reviewed by: mohans
MFC after: 1 week
noatime, noexec, suiddir, nosuid, nosymfollow, union,
noclusterr, noclusterw, multilabel, acls, force, update,
async. These options correspond to MOPT_STDOPTS, MOPT_FORCE, MOPT_UPDATE,
and MOPT_ASYNC.
Currently, mount_nfs converts these "-o" options from strings
to MNT_ flags via getmntopts(),
and passes the flags from userspace to the kernel.
This change will allow us in future to pass these mount options
as strings directly to the kernel via nmount() when doing NFS mounts.
to kproc_xxx as they actually make whole processes.
Thos makes way for us to add REAL kthread_create() and friends
that actually make theads. it turns out that most of these
calls actually end up being moved back to the thread version
when it's added. but we need to make this cosmetic change first.
I'd LOVE to do this rename in 7.0 so that we can eventually MFC the
new kthread_xxx() calls.
- Eliminate the hideous nfs_sndlock that serialized NFS/TCP request senders
thru the sndlock.
- Institute a new nfs_connectlock that serializes NFS/TCP reconnects. Add
logic to wait for pending request senders to finish sending before
reconnecting. Dial down the sb_timeo for NFS/TCP sockets to 1 sec.
- Break out the nfs xid manipulation under a new nfs xid lock, rather than
over loading the nfs request lock for this purpose.
- Fix some of the locking in nfs_request.
Many thanks to Kris Kennaway for his help with this and for initiating the
MP scaling analysis and work. Kris also tested this patch thorougly.
Approved by: re@ (Ken Smith)
timeout occurring at exactly the same time. If this happens, the nfsiod
exits although there may be a queued async IO request for it.
Found by : Kris Kennaway
Approved by: re
previously conditionally acquired Giant based on debug.mpsafenet. As that
has now been removed, they are no longer required. Removing them
significantly simplifies error-handling in the socket layer, eliminated
quite a bit of unwinding of locking in error cases.
While here clean up the now unneeded opt_net.h, which previously was used
for the NET_WITH_GIANT kernel option. Clean up some related gotos for
consistency.
Reviewed by: bz, csjp
Tested by: kris
Approved by: re (kensmith)
nfsnode could lead to attrs being stale. One example (that we
ran into) was a READDIR+, WRITE. The responses came back in
order, but the attrs from the WRITE were loaded before the
attrs from the READDIR+, leading to the wrong size from being
read on the next stat() call.
MFC after: 1 week
Submitted by: mohans
Approved by: re (kensmith)
recoverable and unrecoverable. For the former, we redirty the
buffer and hang onto it for future retries. For the latter (eg.
ESTALE), we discard the buffer and return the error back to the
user on the next syscall. This fixes a number of vfs panics and
fixes having a large number of dirty buffers (that cannot be
written out and reclaimed) from hanging around. Thanks to ups@
for discussions on this issue.
Reported by: kris, Kai, others
Approved by: re (kensmith)
Now, we assume no more sched_lock protection for some of them and use the
distribuited loads method for vmmeter (distribuited through CPUs).
Reviewed by: alc, bde
Approved by: jeff (mentor)
td_ru. This removes the requirement for per-process synchronization in
statclock() and mi_switch(). This was previously supported by
sched_lock which is going away. All modifications to rusage are now
done in the context of the owning thread. reads proceed without locks.
- Aggregate exiting threads rusage in thread_exit() such that the exiting
thread's rusage is not lost.
- Provide a new routine, rufetch() to fetch an aggregate of all rusage
structures from all threads in a process. This routine must be used
in any place requiring a rusage from a process prior to it's exit. The
exited process's rusage is still available via p_ru.
- Aggregate tick statistics only on demand via rufetch() or when a thread
exits. Tick statistics are kept in the thread and protected by sched_lock
until it exits.
Initial patch by: attilio
Reviewed by: attilio, bde (some objections), arch (mostly silent)
Probabilly, a general approach is not the better solution here, so we should
solve the sched_lock protection problems separately.
Requested by: alc
Approved by: jeff (mentor)
lock and unlock conditionally, not just set the flag on it conditionally.
In practice, this bug couldn't manifest, as in the current revision of
the code, no callers pass a NULL rep.
CID: 1416
Found with: Coverity Prevent(tm)
vmcnts. This can be used to abstract away pcpu details but also changes
to use atomics for all counters now. This means sched lock is no longer
responsible for protecting counts in the switch routines.
Contributed by: Attilio Rao <attilio@FreeBSD.org>
- Fix for a bug where a close would not wait for all (directio)
dirty buffers to drain. The nfsnode was not marked NMODIFIED
when there were directio dirtied buffers pending, causing this.
- No reason to vhold/vrele the vp when enqueueing DirectIO requests
for the nfsiods. The vnode can't really go way since the close
has to wait for these requests to drain.
MFC after: 1 week
Submitted by: mohans
- Replace PRIV_NFSD with PRIV_NFS_DAEMON, add PRIV_NFS_LOCKD.
- Use PRIV_NFS_DAEMON in the NFS server.
- In the NFS client, move the privilege check from nfslockdans(), which
occurs every time a write is performed on /dev/nfslock, and instead do it
in nfslock_open() just once. This allows us to avoid checking the saved
uid for root, and just use the effective on open. Use PRIV_NFS_LOCKD.
late stages of unmount). On failure, the vnode is recycled.
Add insmntque1(), to allow for file system specific cleanup when
recycling vnode on failure.
Change getnewvnode() to no longer call insmntque(). Previously,
embryonic vnodes were put onto the list of vnode belonging to a file
system, which is unsafe for a file system marked MPSAFE.
Change vfs_hash_insert() to no longer lock the vnode. The caller now
has that responsibility.
Change most file systems to lock the vnode and call insmntque() or
insmntque1() after a new vnode has been sufficiently setup. Handle
failed insmntque*() calls by propagating errors to callers, possibly
after some file system specific cleanup.
Approved by: re (kensmith)
Reviewed by: kib
In collaboration with: kib
GETATTRs being generated - one from lookup()/namei() and the other
from nfs_open() (for cto consistency). This change eliminates the
GETATTR in nfs_open() if an otw GETATTR was done from the namei()
path. Instead of extending the vop interface, we timestamp each attr
load, and use this to detect whether a GETATTR was done from namei()
for this syscall. Introduces a thread-local variable that counts the
syscalls made by the thread and uses <pid, tid, thread syscalls> as
the attrload timestamp. Thanks to jhb@ and peter@ for a discussion on
thread state that could be used as the timestamp with minimal overhead.
SOCK_DGRAM (i.e. UDP), respect the value configured earlier. This allows
TCP NFS root mounts using e.g. the boot.nfsroot.options="tcp" tunable.
In this case some of the connection parameters like the retry timer were
previously set appropriately for TCP but inappropriately for the UDP
socket that was actually used, leading to e.g. extremely long recovery
times (O(hours)) after a nfs server reboot.
Reviewed by: mohans
MFC After: 2 weeks
of duplicating it except for larger style bugs in the copy.
Fix some nearby style bugs (including a harmless type mismatch)
in and near the remaining copy.
This is part of fixing collisions of the 2 nfs*client's names. Even
static names should have a unique prefixes so that they can be debugged
easily.
file are after snaplock, while other ffs device buffers are before
snaplock in global lock order. By itself, this could cause deadlock
when bdwrite() tries to flush dirty buffers on snapshotted ffs. If,
during the flush, COW activity for snapshot needs to allocate block
and ffs_alloccg() selects the cylinder group that is being written
by bdwrite(), then kernel would panic due to recursive buffer lock
acquision.
Avoid dealing with buffers in bdwrite() that are from other side of
snaplock divisor in the lock order then the buffer being written. Add
new BOP, bop_bdwrite(), to do dirty buffer flushing for same vnode in
the bdwrite(). Default implementation, bufbdflush(), refactors the code
from bdwrite(). For ffs device buffers, specialized implementation is
used.
Reviewed by: tegge, jeff, Russell Cattelan (cattelan xfs org, xfs changes)
Tested by: Peter Holm
X-MFC after: 3 weeks (if ever: it changes ABI)
This is easy to reproduce for EROFS. I am not sure if the attrs can be corrupt
for other NFS error responses. For now, disabling wcc pre-op attr checks and
post-op attr loads on NFS errors (sysctl'ed).
Reported by: Kris Kennaway
vnode into the vfs hash. Otherwise, another thread walking the hash can trip
on an nfsnode with an uninitialized or partially initialized fh.
Thanks to ups@ for spotting this race.
have to explicitly acquire Giant (although they need to be aware of this and
not hold any locks at that point). Remove the acquisitions of Giant in the
NFS client wrapping tprintf().
file. Leave the loser's lock(s) initialized, so the reclaim logic can
unconditionally destroy them when that race occurs (or if the vfs hash
insert happened to fail for some other reason). Thanks to ups@ for a
careful review of the code.
Reported by : Kris Kennaway
2) Reduce the acquisitions of the Giant lock in the nfs_socket.c paths significantly.
- We don't need to acquire Giant before tsleeping on lbolt anymore,
since jhb specialcased lbolt handling in msleep.
- nfs_up() needs to acquire Giant only if printing the "server up"
message.
- nfs_timer() held Giant for the duration of the NFS timer processing,
just because the printing of the message in nfs_down() needed it
(and we acquire other locks in nfs_timer()). The acquisition of
Giant is moved down into nfs_down() now, reducing the time Giant is
held in that path.
Reported by: Kris Kennaway
This bug results in data corruption with NFS/TCP. Writes are silently dropped
on EWOULDBLOCK (because socket send buffer is full and sockbuf timer fires).
Reviewed by: ups@
VA_MARK_ATIME feature to fix POSIX conformance fore execve() and mmap(),
we thought that it was optimized well enough for the one file system
that supports it (ffs) and harmless for other file systems (except
layered ones which already get the layering for VOP_SETATTR() wrong).
However, nfs_setattr() doesn't do much parameter checking, so when
it gets a combination of parameters that it doesn't understand, it
always does a Setattr RPC. This RPC can't do anything good, and for
VA_MARK_ATIME it is null except for wasting a lot of time.
This is the smallest and easiest to fix of several bugs that have
increased the number of RPCs for kernel builds on nfs by more than
100% since 2004-11-05. The real-time increase depends on network
latency and parallelization and can also be very large (approaching
the same percentage for unparallelized operations like "make depend"
on systems with fast CPUs and high-latency networks).
sync() and sync_fsync() without losing MNT_ASYNC. Add MNTK_ASYNC flag
which is set only when MNT_ASYNC is set and mnt_noasync is zero, and
check that flag instead of MNT_ASYNC before initiating async io.
adds a FS type specific flag indicating that the FS supports shared
vnode lock lookups, adds some logic in vfs_lookup.c to test this flag
and set lock flags appropriately.
- amd on 6.x is a non-starter (without this change). Using amd under
heavy load results in a deadlock (with cascading vnode locks all the
way to the root) very quickly.
- This change should also fix the more general problem of cascading
vnode deadlocks when an NFS server goes down.
Ideally, we wouldn't need these changes, as enabling shared vnode lock
lookups globally would work. Unfortunately, UFS, for example isn't
ready for shared vnode lock lookups, crashing pretty quickly.
This change is the result of discussions with Stephan Uphoff (ups@).
Reviewed by: ups@
synchronized by the lock on the object containing the page.
Transition PG_WANTED and PG_SWAPINPROG to use the new field,
eliminating the need for holding the page queues lock when setting
or clearing these flags. Rename PG_WANTED and PG_SWAPINPROG to
VPO_WANTED and VPO_SWAPINPROG, respectively.
Eliminate the assertion that the page queues lock is held in
vm_page_io_finish().
Eliminate the acquisition and release of the page queues lock
around calls to vm_page_io_finish() in kern_sendfile() and
vfs_unbusy_pages().
set the MTU prior to mounting root via NFS. This is required if the
server supports a higher than default MTU because the client will not
see the responses otherwise.
MFC after: 3 weeks
soreceive(), and sopoll(), which are wrappers for pru_sosend,
pru_soreceive, and pru_sopoll, and are now used univerally by socket
consumers rather than either directly invoking the old so*() functions
or directly invoking the protocol switch method (about an even split
prior to this commit).
This completes an architectural change that was begun in 1996 to permit
protocols to provide substitute implementations, as now used by UDP.
Consumers now uniformly invoke sosend(), soreceive(), and sopoll() to
perform these operations on sockets -- in particular, distributed file
systems and socket system calls.
Architectural head nod: sam, gnn, wollman
