Commit Graph

354 Commits

Author SHA1 Message Date
Kip Macy
469ef3e563 rename xdr support files to avoid conflicts when linking in to the kernel 2009-05-11 04:18:58 +00:00
Kip Macy
8569258bf8 - rename atomic.S and crc32.c to avoid collisions when linking zfs in to the kernel
- update Makefile
- ifdef out acl_{alloc, free}, they aren't used by zfs and conflict with existing in-kernel routines
2009-05-09 01:45:55 +00:00
Marko Zec
29b02909eb Introduce a new virtualization container, provisionally named vprocg, to hold
virtualized instances of hostname and domainname, as well as a new top-level
virtualization struct vimage, which holds pointers to struct vnet and struct
vprocg.  Struct vprocg is likely to become replaced in the near future with
a new jail management API import.

As a consequence of this change, change struct ucred to point to a struct
vimage, instead of directly pointing to a vnet.

Merge vnet / vimage / ucred refcounting infrastructure from p4 / vimage
branch.

Permit kldload / kldunload operations to be executed only from the default
vimage context.

This change should have no functional impact on nooptions VIMAGE kernel
builds.

Reviewed by:	bz
Approved by:	julian (mentor)
2009-05-08 14:11:06 +00:00
Kip Macy
a6827463ad don't call vn_rele_async_fini in the !_KERNEL case 2009-05-07 23:34:41 +00:00
Kip Macy
c20fd07777 move VN_RELE_ASYNC to the compatibility layer with the rest of the VN_* defines 2009-05-07 23:02:15 +00:00
Kip Macy
6ef1a81d6e avoid LOR and gratuitous extra lock acquisitions by moving user_evict list buffers to
a temporary list
2009-05-07 21:51:13 +00:00
Kip Macy
77d0162c70 Allow the VM to provide backpressure on the ARC cache as it does
on Solaris.
2009-05-07 20:57:06 +00:00
Kip Macy
62fa227ccd Asynchronously release vnodes to avoid blocking on range locks when calling back in to zfs.
This is based on a fix that went in to opensolaris on March 9th. However, it uses a dedicated
thread instead of a Solaris' taskq to avoid doing a blocking memory allocation with the vnode
interlock held.

This fixes a long-time deadlock in ZFS. This is not, strictly speaking, an LOR. The spa_zio
thread releases a vnode, this calls in to vn_reclaim which in turn needs to acquire range locks
to sync dirty data out to disk. The range locks are already held by a user-level process waiting
on a condition variable that it the process is waiting on a spa_zio thread to signal it on. The
process could not be signalled because the spa_zio thread could not proceed.

The nature of this problem was not apparent due to ZFS locks opting out of witness which meant
that DDB did not know about the locks that were held by ZFS.

Reviewed by:	pjd
MFC after:	7 days
2009-05-07 20:28:06 +00:00
Jamie Gritton
b38ff370e4 Introduce the extensible jail framework, using the same "name=value"
interface as nmount(2).  Three new system calls are added:
* jail_set, to create jails and change the parameters of existing jails.
  This replaces jail(2).
* jail_get, to read the parameters of existing jails.  This replaces the
  security.jail.list sysctl.
* jail_remove to kill off a jail's processes and remove the jail.
Most jail parameters may now be changed after creation, and jails may be
set to exist without any attached processes.  The current jail(2) system
call still exists, though it is now a stub to jail_set(2).

Approved by:	bz (mentor)
2009-04-29 21:14:15 +00:00
Robert Watson
885868cd8f Remove VOP_LEASE and supporting functions. This hasn't been used since
the removal of NQNFS, but was left in in case it was required for NFSv4.
Since our new NFSv4 client and server can't use it for their
requirements, GC the old mechanism, as well as other unused lease-
related code and interfaces.

Due to its impact on kernel programming and binary interfaces, this
change should not be MFC'd.

Proposed by:    jeff
Reviewed by:    jeff
Discussed with: rmacklem, zach loafman @ isilon
2009-04-10 10:52:19 +00:00
Andrew Thompson
853a10a581 Revert r190676,190677
The geom and CAM changes for root_hold are the wrong solution for USB design
quirks.

Requested by:	scottl
2009-04-10 04:08:34 +00:00
Andrew Thompson
626fc9fe3d Add a how argument to root_mount_hold() so it can be passed NOWAIT and be called
in situations where sleeping isnt allowed.
2009-04-03 19:46:12 +00:00
Robert Watson
455f3aa24f Move dtnfsclient.c in the cddl tree to nfs_kdtrace.c in the nfsclient
directory, since it's under a BSD license, and this keeps NFS internals-
aware tracing parts close to NFS.

MFC after:	1 month
Suggested by:	jhb
2009-03-25 17:47:22 +00:00
Robert Watson
10263f0832 Add DTrace probes to the NFS access and attribute caches. Access cache
events are:

  nfsclient:accesscache:flush:done
  nfsclient:accesscache:get:hit
  nfsclient:accesscache:get:miss
  nfsclient:accesscache:load:done

They pass the vnode, uid, and requested or loaded access mode (if any);
the load event may also report a load error if the RPC fails.

The attribute cache events are:

  nfsclient:attrcache:flush:done
  nfsclient:attrcache:get:hit
  nfsclient:attrcache:get:miss
  nfsclient:attrcache:load:done

They pass the vnode, optionally the vattr if one is present (hit or load),
and in the case of a load event, also a possible RPC error.

MFC after:	1 month
Sponsored by:	Google, Inc.
2009-03-24 17:14:34 +00:00
Robert Watson
47294818f9 Add dtnfsclient, a first cut at an NFSv2/v3 client reuest DTrace
provider.  The NFS client exposes 'start' and 'done' probes for NFSv2
and NFSv3 RPCs when using the new RPC implementation, passing in the
vnode, mbuf chain, credential, and NFSv2 or NFSv3 procedure number.
For 'done' probes, the error number is also available.

Probes are named in the following way:

  ...
  nfsclient:nfs2:write:start
  nfsclient:nfs2:write:done
  ...
  nfsclient:nfs3:access:start
  nfsclient:nfs3:access:done
  ...

Access to the unmarshalled arguments is not easily available at this
point in the stack, but the passed probe arguments are sufficient to
to a lot of interesting things in practice.  Technically, these probes
may cover multiple RPC retransmits, and even transactions if the
transaction ID change as a result of authentication failure or a
jukebox error from the server, but usefully capture the intent of a
single NFS request, such as access, getattr, write, etc.

Typical use might involve profiling RPC latency by system call, number
of RPCs, how often a getattr leads to a call to access, when failed
access control checks occur, etc.  More detailed RPC information might
best be provided by adding a krpc provider.  It would also be useful
to add NFS client probes for events such as the access cache or
attribute cache satisfying requests without an RPC.

Sponsored by:	Google, Inc.
MFC after:	1 month
2009-03-22 22:07:52 +00:00
John Baldwin
9fca7a854c The zfs_get_xattrdir() function is used to find the extended attribute
directory for a znode.  When the directory already exists, it returns a
referenced but unlocked vnode.  When a directory does not yet exist, it
calls zfs_make_xattrdir() to create a new one.  zfs_make_xattrdir() returns
the vnode both referenced and and locked and zfs_get_xattrdir() was leaking
this vnode lock to its callers.  Fix this by dropping the vnode lock if
zfs_make_xattrdir() successfully creates a new extended attribute
directory.

Reviewed by:	pjd
2009-03-18 16:19:44 +00:00
John Baldwin
33fc362512 Add a new internal mount flag (MNTK_EXTENDED_SHARED) to indicate that a
filesystem supports additional operations using shared vnode locks.
Currently this is used to enable shared locks for open() and close() of
read-only file descriptors.
- When an ISOPEN namei() request is performed with LOCKSHARED, use a
  shared vnode lock for the leaf vnode only if the mount point has the
  extended shared flag set.
- Set LOCKSHARED in vn_open_cred() for requests that specify O_RDONLY but
  not O_CREAT.
- Use a shared vnode lock around VOP_CLOSE() if the file was opened with
  O_RDONLY and the mountpoint has the extended shared flag set.
- Adjust md(4) to upgrade the vnode lock on the vnode it gets back from
  vn_open() since it now may only have a shared vnode lock.
- Don't enable shared vnode locks on FIFO vnodes in ZFS and UFS since
  FIFO's require exclusive vnode locks for their open() and close()
  routines.  (My recent MPSAFE patches for UDF and cd9660 already included
  this change.)
- Enable extended shared operations on UFS, cd9660, and UDF.

Submitted by:	ups
Reviewed by:	pjd (ZFS bits)
MFC after:	1 month
2009-03-11 14:13:47 +00:00
Jamie Gritton
f86bce5ed0 Extend the "vfsopt" mount options for more general use. Make struct
vfsopt and the vfs_buildopts function public, and add some new fields
to struct vfsopt (pos and seen), and new functions vfs_getopt_pos and
vfs_opterror.

Further extend the interface to allow reading options from the kernel
in addition to sending them to the kernel, with vfs_setopt and related
functions.

While this allows the "name=value" option interface to be used for more
than just FS mounts (planned use is for jails), it retains the current
"vfsopt" name and <sys/mount.h> requirement.

Approved by:	bz (mentor)
2009-03-02 23:26:30 +00:00
Ed Schouten
802cb57e34 Add memmove() to the kernel, making the kernel compile with Clang.
When copying big structures, LLVM generates calls to memmove(), because
it may not be able to figure out whether structures overlap. This caused
linker errors to occur. memmove() is now implemented using bcopy().
Ideally it would be the other way around, but that can be solved in the
future. On ARM we don't do add anything, because it already has
memmove().

Discussed on:	arch@
Reviewed by:	rdivacky
2009-02-28 16:21:25 +00:00
John Baldwin
ea77ff0a15 Use shared vnode locks when invoking VOP_READDIR().
MFC after:	1 month
2009-02-13 18:18:14 +00:00
Ed Schouten
a4611ab612 Last step of splitting up minor and unit numbers: remove minor().
Inside the kernel, the minor() function was responsible for obtaining
the device minor number of a character device. Because we made device
numbers dynamically allocated and independent of the unit number passed
to make_dev() a long time ago, it was actually a misnomer. If you really
want to obtain the device number, you should use dev2udev().

We already converted all the drivers to use dev2unit() to obtain the
device unit number, which is still used by a lot of drivers. I've
noticed not a single driver passes NULL to dev2unit(). Even if they
would, its behaviour would make little sense. This is why I've removed
the NULL check.

Ths commit removes minor(), minor2unit() and unit2minor() from the
kernel. Because there was a naming collision with uminor(), we can
rename umajor() and uminor() back to major() and minor(). This means
that the makedev(3) manual page also applies to kernel space code now.

I suspect umajor() and uminor() isn't used that often in external code,
but to make it easier for other parties to port their code, I've
increased __FreeBSD_version to 800062.
2009-01-28 17:57:16 +00:00
Warner Losh
78bc7eec0d Put the MIPS support back in after it was removed in r185029. 2008-12-04 16:31:08 +00:00
Pawel Jakub Dawidek
35a15332f3 MFp4: Remove assertion that is no longer valid - we now use VOP_CLOSE() in
more places (ie vdev_file.c).
2008-11-29 12:32:42 +00:00
Edward Tomasz Napierala
38cc5da78e MFp4: We don't support TX_CREATE_ACL_ATTR nor TX_MKDIR_ACL_ATTR; code found
in zfs_replay.c will panic if it encounters transactions of this type.
Make sure we don't put these into the ZIL.

Approved by:	rwatson (mentor), pjd
2008-11-25 23:05:46 +00:00
Pawel Jakub Dawidek
ad35ee04f4 Fix locking (file descriptor table and Giant around VFS).
Most submitted by:	kib
Reviewed by:		kib
2008-11-25 21:14:00 +00:00
Ganbold Tsagaankhuu
79dae0aa0b Remove unused variable.
Found with:     Coverity Prevent(tm)
CID: 3669,3671

Approved by: jb
2008-11-25 19:25:54 +00:00
Pawel Jakub Dawidek
83080c1ece Don't use PRIV_ROOT. Here we check if user can share ZFS file system, so
PRIV_NFS_DAEMON seems best choice.

Discussed with:	rwatson
2008-11-23 20:14:19 +00:00
Pawel Jakub Dawidek
bcfbcdca9c IFp4: Don't rely on disk IDs and always use vdev guids, which means always look
up for components by reading metadata. This might be slower when there are big
number of disks in the system, but is definiately more reliable.
2008-11-22 13:33:06 +00:00
Pawel Jakub Dawidek
74303ba55c IFp4: Finish implemnetation of chflags(2) for ZFS. While doing this I found
that zfs_access() can only handle VREAD, VWRITE and VEXEC, for the rest we need
to use vaccess(9).
2008-11-22 13:24:44 +00:00
Pawel Jakub Dawidek
5189bf22c0 IFp4: Don't free pathname too soon, debugging code is still using it. 2008-11-22 13:22:24 +00:00
Doug Rabson
786895f6ba Add definitions for ZFS pool version 13. 2008-11-21 09:10:35 +00:00
Doug Rabson
0d16312b46 Some zfsboot fixes from Norikatsu Shigemura:
1. zfsboot2 (boot2) doesn't %d (printf), so change %d to %u.
2. chase new zpool versioning as SPA_VERSION.
   Obtained from: sys/cddl/contrib/opensolaris/uts/common/sys/fs/zfs.h

Submitted by:	nork
2008-11-19 16:59:19 +00:00
Pawel Jakub Dawidek
1ba4a712dd Update ZFS from version 6 to 13 and bring some FreeBSD-specific changes.
This bring huge amount of changes, I'll enumerate only user-visible changes:

- Delegated Administration

	Allows regular users to perform ZFS operations, like file system
	creation, snapshot creation, etc.

- L2ARC

	Level 2 cache for ZFS - allows to use additional disks for cache.
	Huge performance improvements mostly for random read of mostly
	static content.

- slog

	Allow to use additional disks for ZFS Intent Log to speed up
	operations like fsync(2).

- vfs.zfs.super_owner

	Allows regular users to perform privileged operations on files stored
	on ZFS file systems owned by him. Very careful with this one.

- chflags(2)

	Not all the flags are supported. This still needs work.

- ZFSBoot

	Support to boot off of ZFS pool. Not finished, AFAIK.

	Submitted by:	dfr

- Snapshot properties

- New failure modes

	Before if write requested failed, system paniced. Now one
	can select from one of three failure modes:
	- panic - panic on write error
	- wait - wait for disk to reappear
	- continue - serve read requests if possible, block write requests

- Refquota, refreservation properties

	Just quota and reservation properties, but don't count space consumed
	by children file systems, clones and snapshots.

- Sparse volumes

	ZVOLs that don't reserve space in the pool.

- External attributes

	Compatible with extattr(2).

- NFSv4-ACLs

	Not sure about the status, might not be complete yet.

	Submitted by:	trasz

- Creation-time properties

- Regression tests for zpool(8) command.

Obtained from:	OpenSolaris
2008-11-17 20:49:29 +00:00
Edward Tomasz Napierala
4bdaada206 Require write access on a directory being moved from one parent
directory to another in ZFS.

Approved by:	rwatson (mentor), pjd
2008-11-08 19:56:32 +00:00
Edward Tomasz Napierala
36d227d9ed Backoff the last patch. It was overly restrictive - we want to check
for write permission on target only when moving the target between two
directories.

Approved by:	rwatson (mentor)
2008-11-06 22:28:04 +00:00
Edward Tomasz Napierala
b92eda309d Change ZFS behaviour to match UFS: when moving (rename(2)) a subdirectory
from one parent directory to another, in addition to the usual access checks
one also needs write access to the subdirectory being moved.

Approved by:    rwatson (mentor), pjd
2008-11-06 19:17:58 +00:00
Craig Rodrigues
6a73ed4f46 Remove definition of KMEM_DEBUG accidentally brought in by latest DTrace
import.

Noticed by:	thompsa
2008-11-05 20:32:13 +00:00
Craig Rodrigues
f5a97d1bcb Merge latest DTrace changes from Perforce. 2008-11-05 19:39:11 +00:00
Edward Tomasz Napierala
15bc6b2bd8 Introduce accmode_t. This is required for NFSv4 ACLs - it will be neccessary
to add more V* constants, and the variables changed by this patch were often
being assigned to mode_t variables, which is 16 bit.

Approved by:	rwatson (mentor)
2008-10-28 13:44:11 +00:00
Attilio Rao
0d7935fd01 Remove the struct thread unuseful argument from bufobj interface.
In particular following functions KPI results modified:
- bufobj_invalbuf()
- bufsync()

and BO_SYNC() "virtual method" of the buffer objects set.
Main consumers of bufobj functions are affected by this change too and,
in particular, functions which changed their KPI are:
- vinvalbuf()
- g_vfs_close()

Due to the KPI breakage, __FreeBSD_version will be bumped in a later
commit.

As a side note, please consider just temporary the 'curthread' argument
passing to VOP_SYNC() (in bufsync()) as it will be axed out ASAP

Reviewed by:	kib
Tested by:	Giovanni Trematerra <giovanni dot trematerra at gmail dot com>
2008-10-10 21:23:50 +00:00
John Birrell
fd4cdfbf46 Disable use of the user credentials until there is code to set the levels
that DTrace uses.

This fixes a bug that would have affected kernels built with MAC and all
kernels built after the mpsafetty integration.

The bug will be apparent in RELENG7 on MAC kernels.

Reported by: kan
2008-09-27 17:52:48 +00:00
Ed Schouten
6bfa9a2d66 Replace all calls to minor() with dev2unit().
After I removed all the unit2minor()/minor2unit() calls from the kernel
yesterday, I realised calling minor() everywhere is quite confusing.
Character devices now only have the ability to store a unit number, not
a minor number. Remove the confusion by using dev2unit() everywhere.

This commit could also be considered as a bug fix. A lot of drivers call
minor(), while they should actually be calling dev2unit(). In -CURRENT
this isn't a problem, but it turns out we never had any problem reports
related to that issue in the past. I suspect not many people connect
more than 256 pieces of the same hardware.

Reviewed by:	kib
2008-09-27 08:51:18 +00:00
Ed Schouten
d3ce832719 Remove unit2minor() use from kernel code.
When I changed kern_conf.c three months ago I made device unit numbers
equal to (unneeded) device minor numbers. We used to require
bitshifting, because there were eight bits in the middle that were
reserved for a device major number. Not very long after I turned
dev2unit(), minor(), unit2minor() and minor2unit() into macro's.
The unit2minor() and minor2unit() macro's were no-ops.

We'd better not remove these four macro's from the kernel, because there
is a lot of (external) code that may still depend on them. For now it's
harmless to remove all invocations of unit2minor() and minor2unit().

Reviewed by:	kib
2008-09-26 14:19:52 +00:00
Warner Losh
6e1a9d1739 Mips needs the same treatment for atomic_or_8 as the other RISCy
architectures.
2008-09-18 19:57:06 +00:00
Pawel Jakub Dawidek
062ea27ee4 Add missing ZFS_EXIT().
PR:		kern/124899
Submitted by:	Masakazu Asama <m-asama@ginzado.ne.jp>
2008-09-15 11:27:25 +00:00
Edward Tomasz Napierala
dfa7fd1d70 Remove VSVTX, VSGID and VSUID. This should be a no-op,
as VSVTX == S_ISVTX, VSGID == S_ISGID and VSUID == S_ISUID.

Approved by:	rwatson (mentor)
2008-09-10 13:16:41 +00:00
Pawel Jakub Dawidek
1b856fa491 Initialize vp, so we don't call VOP_UNLOCK() with NULL vnode pointer.
Confirmed by:	marcus
2008-09-07 07:55:12 +00:00
Pawel Jakub Dawidek
433751bb50 Lock vnode exclusively around insmntque(). 2008-09-06 17:24:07 +00:00
Pawel Jakub Dawidek
7fa1f32a7e Catch up after last insmntque() changes:
- The vnode has to be locked exclusively before calling insmntque().
- Until I find a way to handle insmntque() failures use VV_FORCEINSMQ flag
  to force insmntque() to always succeed.

Reported by:	kris, trasz, des, others
Suggested by:	kib
Tested by:	trasz
2008-09-05 07:00:40 +00:00
Attilio Rao
59d4932531 Decontextualize vfs_busy(), vfs_unbusy() and vfs_mount_alloc() functions.
Manpages are updated accordingly.

Tested by:	Diego Sardina <siarodx at gmail dot com>
2008-08-31 14:26:08 +00:00
Scott Long
a25cb00747 Ensure that the padding calcualtion doesn't return a negative value.
Submitted by:	kib
Approved by:	jb
2008-08-29 15:55:49 +00:00
Attilio Rao
0359a12ead Decontextualize the couplet VOP_GETATTR / VOP_SETATTR as the passed thread
was always curthread and totally unuseful.

Tested by: Giovanni Trematerra <giovanni dot trematerra at gmail dot com>
2008-08-28 15:23:18 +00:00
Warner Losh
e6b3a7a9c1 Add MIPS support.
Reviewed by:	jb@
2008-08-23 04:58:11 +00:00
John Birrell
ac80559536 Add calls to callout_drain() to ensure the callouts are flushed before
we free memory from underneath them.

This fixes an occasional panic I've been seeing in softclock() where a bad
pointer would be encountered when pushing DTrace hard.
2008-08-19 21:28:58 +00:00
Pawel Jakub Dawidek
37876323b1 We want to use LBOLT instead of lbolt on FreeBSD.
I've this already fixed in p4, but the fix was never integrated into HEAD.

Reported by:	ed
2008-07-21 14:35:48 +00:00
Pawel Jakub Dawidek
28814ddbe8 We want to check new options given, not the current ones.
This fixes 'zpool import -o <mntopt> <name>' not working properly.
2008-07-21 09:45:44 +00:00
Ed Schouten
3f7eea97fd Remove the $FreeBSD$ tag again, now I know fbsd:nokeywords exists.
Requested by:	pjd
Approved by:	philip (mentor)
2008-06-12 08:53:54 +00:00
Ed Schouten
0f03ce1bb8 Turn dev2unit(), minor(), unit2minor() and minor2unit() into macro's.
Now that we got rid of the minor-to-unit conversion and the constraints
on device minor numbers, we can convert the functions that operate on
minor and unit numbers to simple macro's. The unit2minor() and
minor2unit() macro's are now no-ops.

The ZFS code als defined a macro named `minor'. Change the ZFS code to
use umajor() and uminor() here, as it is the correct approach to do
this. Also add $FreeBSD$ to keep SVN happy.

Approved by:	philip (mentor), pjd
2008-06-12 08:30:54 +00:00
Ed Schouten
29d4cb241b Don't enforce unique device minor number policy anymore.
Except for the case where we use the cloner library (clone_create() and
friends), there is no reason to enforce a unique device minor number
policy. There are various drivers in the source tree that allocate unr
pools and such to provide minor numbers, without using them themselves.

Because we still need to support unique device minor numbers for the
cloner library, introduce a new flag called D_NEEDMINOR. All cdevsw's
that are used in combination with the cloner library should be marked
with this flag to make the cloning work.

This means drivers can now freely use si_drv0 to store their own flags
and state, making it effectively the same as si_drv1 and si_drv2. We
still keep the minor() and dev2unit() routines around to make drivers
happy.

The NTFS code also used the minor number in its hash table. We should
not do this anymore. If the si_drv0 field would be changed, it would no
longer end up in the same list.

Approved by:	philip (mentor)
2008-06-11 18:55:19 +00:00
John Birrell
4ca07625aa Merge a recent change from the OpenSolaris source tree.
(Don't ask for a vendor import of this yet, we're in the early days of svn)

Instead of using cyclic timers to call the state clean and deadman callbacks,
use a callout on FreeBSD to avoid the deadlock on FreeBSD due to trying to
send interprocessor interrupts with interrupts disabled.

Reported by: ps, jhb, peter, thompsa
2008-06-01 01:46:37 +00:00
Pawel Jakub Dawidek
ed5a2ac45c Fix namespace collision after src/sys/sys/file.h:1.78. 2008-05-25 22:34:17 +00:00
John Birrell
727acbb41b Comment out the code that breaks with invariants. This is stuff that is
still WIP along with the lockstat provider, so there is no harm leaving
it out for now.
2008-05-25 20:24:07 +00:00
Bjoern A. Zeeb
079d3bfcfb Remove redundant redeclaration of 'zone_drain'. 2008-05-24 19:30:38 +00:00
John Birrell
8fc6245976 Make the zfs module depend on the opensolaris module in preparation for it
to shared stuff with the DTrace modules.
2008-05-24 06:43:55 +00:00
John Birrell
25f292128c Messing with the endian defines breaks the use of other FreeBSD headers. 2008-05-23 23:03:17 +00:00
John Birrell
fd930d81d8 Delete a couple of OpenSolaris headers which get in the way of our
implementation.
2008-05-23 22:40:58 +00:00
John Birrell
8599306711 OpenSolaris kernel module compatibility sources. 2008-05-23 22:39:28 +00:00
John Birrell
5a3c3bfaa3 The cyclic timer device. This is a cut down version of the one in
OpenSolaris. We don't have the lock levels that they do, so this is just
hooked into clock interrupts.
2008-05-23 22:21:58 +00:00
John Birrell
91eaf3e183 Custom DTrace kernel module files plus FreeBSD-specific DTrace providers. 2008-05-23 05:59:42 +00:00
John Birrell
32a109c1d8 A 'special' compatibility header to plug OpenSolaris code. 2008-05-22 09:08:41 +00:00
John Birrell
4706efa4f6 Additional compatibility headers. 2008-05-22 08:35:03 +00:00
John Birrell
1583a68737 Compatibility stuff for DTrace. 2008-05-22 08:33:24 +00:00
John Birrell
5a1b490d50 FreeBSD changes to vendor source. 2008-05-22 07:33:39 +00:00
John Birrell
cd844e7a7d This commit was generated by cvs2svn to compensate for changes in r179193,
which included commits to RCS files with non-trunk default branches.
2008-05-22 07:04:10 +00:00
Attilio Rao
295624f56a LO_ENROLLPEND is no more existing so just axe it (it was left out by the
original commit axing it).
2008-05-16 02:09:13 +00:00
John Birrell
db612abe8d Add FreeBSD IDs to files that originate in FreeBSD. 2008-04-22 07:43:00 +00:00
Konstantin Belousov
eab626f110 Move the head of byte-level advisory lock list from the
filesystem-specific vnode data to the struct vnode. Provide the
default implementation for the vop_advlock and vop_advlockasync.
Purge the locks on the vnode reclaim by using the lf_purgelocks().
The default implementation is augmented for the nfs and smbfs.
In the nfs_advlock, push the Giant inside the nfs_dolock.

Before the change, the vop_advlock and vop_advlockasync have taken the
unlocked vnode and dereferenced the fs-private inode data, racing with
with the vnode reclamation due to forced unmount. Now, the vop_getattr
under the shared vnode lock is used to obtain the inode size, and
later, in the lf_advlockasync, after locking the vnode interlock, the
VI_DOOMED flag is checked to prevent an operation on the doomed vnode.

The implementation of the lf_purgelocks() is submitted by dfr.

Reported by:	kris
Tested by:	kris, pho
Discussed with:	jeff, dfr
MFC after:	2 weeks
2008-04-16 11:33:32 +00:00
Marius Strobl
5b20de10b9 Add atomic operations for ZFS/sparc64.
Approved by:	core, pjd
Obtained from:	OpenSolaris (w/ adaptations)
MFC after:	2 weeks
2008-04-11 22:59:33 +00:00
Marius Strobl
20a8e8d594 - Fix the path encoded in the multiple inclusion protection.
- GCC uses 32-byte function alignment for UltraSPARC CPUs.
- Remove code duplication.

Approved by:	core, pjd
MFC after:	2 weeks
2008-04-11 22:53:06 +00:00
Doug Rabson
dfdcada31e Add the new kernel-mode NFS Lock Manager. To use it instead of the
user-mode lock manager, build a kernel with the NFSLOCKD option and
add '-k' to 'rpc_lockd_flags' in rc.conf.

Highlights include:

* Thread-safe kernel RPC client - many threads can use the same RPC
  client handle safely with replies being de-multiplexed at the socket
  upcall (typically driven directly by the NIC interrupt) and handed
  off to whichever thread matches the reply. For UDP sockets, many RPC
  clients can share the same socket. This allows the use of a single
  privileged UDP port number to talk to an arbitrary number of remote
  hosts.

* Single-threaded kernel RPC server. Adding support for multi-threaded
  server would be relatively straightforward and would follow
  approximately the Solaris KPI. A single thread should be sufficient
  for the NLM since it should rarely block in normal operation.

* Kernel mode NLM server supporting cancel requests and granted
  callbacks. I've tested the NLM server reasonably extensively - it
  passes both my own tests and the NFS Connectathon locking tests
  running on Solaris, Mac OS X and Ubuntu Linux.

* Userland NLM client supported. While the NLM server doesn't have
  support for the local NFS client's locking needs, it does have to
  field async replies and granted callbacks from remote NLMs that the
  local client has contacted. We relay these replies to the userland
  rpc.lockd over a local domain RPC socket.

* Robust deadlock detection for the local lock manager. In particular
  it will detect deadlocks caused by a lock request that covers more
  than one blocking request. As required by the NLM protocol, all
  deadlock detection happens synchronously - a user is guaranteed that
  if a lock request isn't rejected immediately, the lock will
  eventually be granted. The old system allowed for a 'deferred
  deadlock' condition where a blocked lock request could wake up and
  find that some other deadlock-causing lock owner had beaten them to
  the lock.

* Since both local and remote locks are managed by the same kernel
  locking code, local and remote processes can safely use file locks
  for mutual exclusion. Local processes have no fairness advantage
  compared to remote processes when contending to lock a region that
  has just been unlocked - the local lock manager enforces a strict
  first-come first-served model for both local and remote lockers.

Sponsored by:	Isilon Systems
PR:		95247 107555 115524 116679
MFC after:	2 weeks
2008-03-26 15:23:12 +00:00
Robert Watson
237fdd787b In keeping with style(9)'s recommendations on macros, use a ';'
after each SYSINIT() macro invocation.  This makes a number of
lightweight C parsers much happier with the FreeBSD kernel
source, including cflow's prcc and lxr.

MFC after:	1 month
Discussed with:	imp, rink
2008-03-16 10:58:09 +00:00
Pawel Jakub Dawidek
2b1c6615bc Fix mmap(2) on ZFS after some changes in VM subsystem.
Submitted by:	alc
Reported by:	kris (originally) and many others
Tested with:	fsx
MFC after:	1 week
2008-03-15 23:23:04 +00:00
Attilio Rao
81c794f998 Axe the 'thread' argument from VOP_ISLOCKED() and lockstatus() as it is
always curthread.

As KPI gets broken by this patch, manpages and __FreeBSD_version will be
updated by further commits.

Tested by:	Andrea Barberio <insomniac at slackware dot it>
2008-02-25 18:45:57 +00:00
Attilio Rao
628f51d275 Introduce some functions in the vnode locks namespace and in the ffs
namespace in order to handle lockmgr fields in a controlled way instead
than spreading all around bogus stubs:
- VN_LOCK_AREC() allows lock recursion for a specified vnode
- VN_LOCK_ASHARE() allows lock sharing for a specified vnode

In FFS land:
- BUF_AREC() allows lock recursion for a specified buffer lock
- BUF_NOREC() disallows recursion for a specified buffer lock

Side note: union_subr.c::unionfs_node_update() is the only other function
directly handling lockmgr fields. As this is not simple to fix, it has
been left behind as "sole" exception.
2008-02-24 16:38:58 +00:00
Pawel Jakub Dawidek
79bc018dd7 - Reduce how much ZFS caches by default. This is another change to mitigate
'kmem_map too small panics'.
- Print two warnings if there is not enough memory and not enough address
  space.
- Improve comment.
2008-01-24 11:24:16 +00:00
Pawel Jakub Dawidek
44ce1efd91 Change type of kmem_used() and kmem_size() functions to uint64_t, so it
doesn't overflow in arc.c in this check:

	if (kmem_used() > (kmem_size() * 4) / 5)
		return (1);

With this bug ZFS almost doesn't cache.

Only 32bit machines are affected that have vm.kmem_size set to values >=1GB.

Reported by:	David Taylor <davidt@yadt.co.uk>
2008-01-24 11:21:54 +00:00
Attilio Rao
22db15c06f VOP_LOCK1() (and so VOP_LOCK()) and VOP_UNLOCK() are only used in
conjuction with 'thread' argument passing which is always curthread.
Remove the unuseful extra-argument and pass explicitly curthread to lower
layer functions, when necessary.

KPI results broken by this change, which should affect several ports, so
version bumping and manpage update will be further committed.

Tested by: kris, pho, Diego Sardina <siarodx at gmail dot com>
2008-01-13 14:44:15 +00:00
Attilio Rao
cb05b60a89 vn_lock() is currently only used with the 'curthread' passed as argument.
Remove this argument and pass curthread directly to underlying
VOP_LOCK1() VFS method. This modify makes the code cleaner and in
particular remove an annoying dependence helping next lockmgr() cleanup.
KPI results, obviously, changed.

Manpage and FreeBSD_version will be updated through further commits.

As a side note, would be valuable to say that next commits will address
a similar cleanup about VFS methods, in particular vop_lock1 and
vop_unlock.

Tested by:	Diego Sardina <siarodx at gmail dot com>,
		Andrea Di Pasquale <whyx dot it at gmail dot com>
2008-01-10 01:10:58 +00:00
John Birrell
35a04710d7 Remove some compatibility stuff that we now get from the Solaris header. 2007-11-29 00:15:08 +00:00
John Birrell
b468fe2bce * Check endianness the FreeBSD way.
* Use LBOLT rather than lbolt to avoid a clash with a FreeBSD global
  variable.
2007-11-28 22:16:00 +00:00
John Birrell
9587fed572 Fix a prototype definition. 2007-11-28 22:13:28 +00:00
John Birrell
da9085a1c0 Check endianness the FreeBSD way. 2007-11-28 22:12:21 +00:00
John Birrell
47b288c152 Include an extra header to get this to compile cleanly. 2007-11-28 22:11:39 +00:00
John Birrell
57438287ab Add more OpenSolaris compatibility headers. 2007-11-28 21:50:40 +00:00
John Birrell
eca148b637 Remove an extern that is defined elsewhere. 2007-11-28 21:50:05 +00:00
John Birrell
edadde229a Add compatibility cruft moved from under _SOLARIS_C_SOURCE in sys/types.h 2007-11-28 21:49:16 +00:00
John Birrell
35ba7f225f Remove a typedef which was just a hack to avoid including vmem.h.
That typedef breaks other Solaris code.
2007-11-28 21:48:25 +00:00
John Birrell
773f4e3849 Add a missing volatile so that the code compiles cleanly. 2007-11-28 21:47:09 +00:00
John Birrell
4fc8feafc7 Rename the definition of lbolt to LBOLT to avoid a clash with a global
variable in FreeBSD. Until now lbolt in sys/proc.h has been #ifdef'ed
out based on _SOLARIS_C_SOURCE, but that is going away now.
2007-11-28 21:44:17 +00:00
Pawel Jakub Dawidek
4d4daf5901 Warn if kmem_map size is set to less than 512MB. Previous warning was a bit
pointless, because default is set to something around 300MB and also
insufficient.

MFC after:	3 days
2007-11-07 14:44:31 +00:00
Pawel Jakub Dawidek
232a80f675 Remove unused header.
MFC after:	3 days
2007-11-05 22:18:34 +00:00
Pawel Jakub Dawidek
a33b7a8f5f If setting a state to anything but open state, close access to vdev.
This fixes replacing drive in place, eg. zpool replace tank da1 da1.
Before it complained that device is already open.

MFC after:	1 week
2007-11-05 21:30:48 +00:00
Pawel Jakub Dawidek
171eb887e9 Remove "zfs:" prefix from lock and condvar names and also skip non-letter
characters (mostly "&"). Because top(1) shows only first six characters of
wait channel, without this change we saw only one meaningful character.

Requested by:	kris & others
MFC after:	1 week
2007-11-05 18:40:55 +00:00
Ulf Lilleengen
6509baf851 - Add sysctl for sizeof(znode_t), which will be used by fstat(1).
Approved by:	pjd (mentor)
2007-11-02 00:35:05 +00:00
Pawel Jakub Dawidek
ef2d58b58f Call zil_commit() (if ZIL is not disabled) after every non-read request
(BIO_WRITE and BIO_FLUSH) as it is done is Solaris. The difference is
that Solaris calls it only for sync requests, but we can't say in GEOM
is the request is sync or async, so we do it for every request.

MFC after:	1 week
2007-11-01 11:04:21 +00:00
Pawel Jakub Dawidek
4f2398ea17 - Move crfree() outside MNT_ILOCK()/MNT_IUNLOCK() to eliminate a LOR:
1st 0xc4cea568 struct mount mtx (struct mount mtx) @ /usr/src/sys/modules/zfs/../../compat/opensolaris/kern/opensolaris_vfs.c:209
  2nd 0xc3ee9010 sleep mtxpool (sleep mtxpool) @ /usr/src/sys/kern/kern_resource.c:1266
- Move crdup() outside MNT_ILOCK()/MNT_IUNLOCK(), as it can sleep.

Reported by:	Olli Hauer <ohauer@gmx.de>
MFC after:	3 days
2007-11-01 08:58:29 +00:00
Julian Elischer
3745c395ec Rename the kthread_xxx (e.g. kthread_create()) calls
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.
2007-10-20 23:23:23 +00:00
Andrew Thompson
1fe1be1535 ZFS_LOG adds a newline by itself.
Pointed out by:	pjd
2007-10-14 16:14:32 +00:00
Andrew Thompson
9528621759 Print the ZFS ereport to the console if vfs.zfs.debug is set to help diagnose
problems with zfs-on-root since devd isnt running yet.

Reviewed by:	pjd
2007-10-14 07:58:50 +00:00
Pawel Jakub Dawidek
e8bd23b460 Fix lock leak leading to the 'System call <name> returning with 1 locks held'
panic.

Reported by:	kris
Approved by:	re (kensmith)
2007-10-04 17:51:59 +00:00
Pawel Jakub Dawidek
a95a61fc19 Now that we have CDDLed code in the tree, add CDDL license.
Discussed with:	core
Approved by:	re (kensmith)
2007-09-23 07:04:50 +00:00
Pawel Jakub Dawidek
a3c8c2e60f Reduce the limit of vnodes on i386 when ZFS is loaded to 3/4 of the original
value, so we don't run out of KVA. The default vnodes limit fits better for
UFS, but ZFS allocated more file system specific memory for a vnode than UFS.

Don't touch vnodes limit if we detect it was tuned by system administrator
and restore original value when ZFS is unloaded.

This isn't final fix, but before we implement something better, this will
help to stabilize ZFS under heavy load on i386.

Approved by:	re (bmah)
2007-09-10 19:58:14 +00:00
Pawel Jakub Dawidek
ef0ffc1c6f After dfr@ vnode leak fix, we can allow ARC to consume more memory.
Tested by:	kris
Approved by:	re (bmah)
2007-09-10 18:12:27 +00:00
Pawel Jakub Dawidek
6bc581fcf0 Use CTLFLAG_RDTUN for tunable sysctls.
Approved by:	re (bmah)
2007-09-01 06:23:42 +00:00
Pawel Jakub Dawidek
70eaa4219c Some ZFS threads needs stack larger than the default 8kB, so use 16kB of
alternate stack if the default is smaller than 16kB.

Approved by:	re (rwatson)
2007-08-16 20:33:20 +00:00
Pawel Jakub Dawidek
aa222db26f Update assertion after revision 1.23.
Reviewed by:	dfr
Approved by:	re (rwatson)
2007-07-24 15:00:43 +00:00
Doug Rabson
2dc26b36c8 Correct a reference-counting mistake in the ZFS code which led to abnormal
memory usage and pessimal cache performance.

Reviewed by: pjd
Approved by: re (rwatson)
2007-07-09 09:03:49 +00:00
Doug Rabson
7761242694 In zfs_vget, if we fail to translate an inode number to the corresponding
vnode, make sure we return an error code to the caller.

Reviewed by: pjd
Approved by: re
2007-06-27 12:00:24 +00:00
Robert Watson
32f9753cfb Eliminate now-unused SUSER_ALLOWJAIL arguments to priv_check_cred(); in
some cases, move to priv_check() if it was an operation on a thread and
no other flags were present.

Eliminate caller-side jail exception checking (also now-unused); jail
privilege exception code now goes solely in kern_jail.c.

We can't yet eliminate suser() due to some cases in the KAME code where
a privilege check is performed and then used in many different deferred
paths.  Do, however, move those prototypes to priv.h.

Reviewed by:	csjp
Obtained from:	TrustedBSD Project
2007-06-12 00:12:01 +00:00
Marcel Moolenaar
6d63683c41 Add my copyright.
Requested by: pjd@
2007-06-08 16:20:03 +00:00
Pawel Jakub Dawidek
3b7917d766 - Reduce number of atomic operations needed to be implemented in asm by
implementing some of them using existing ones.
- Allow to compile ZFS on all archs and use atomic operations surrounded
  by global mutex on archs we don't have or can't have all atomic
  operations needed by ZFS.
2007-06-08 12:35:47 +00:00
Pawel Jakub Dawidek
083c4dd695 Missing atomic operations for ZFS/ia64.
Submitted by:	marcel
2007-06-08 12:26:30 +00:00
David Malone
041b706b2f Despite several examples in the kernel, the third argument of
sysctl_handle_int is not sizeof the int type you want to export.
The type must always be an int or an unsigned int.

Remove the instances where a sizeof(variable) is passed to stop
people accidently cut and pasting these examples.

In a few places this was sysctl_handle_int was being used on 64 bit
types, which would truncate the value to be exported.  In these
cases use sysctl_handle_quad to export them and change the format
to Q so that sysctl(1) can still print them.
2007-06-04 18:25:08 +00:00
Pawel Jakub Dawidek
b166b92692 Reimplement traverse() helper function:
1. Pass locking flags to VFS_ROOT().
2. Check v_mountedhere while the vnode is locked.
3. Always return locked vnode on success.

Change 1 fixes problem reported by Stephen M. Rumble - after
zfs_vfsops.c,1.9 change, zfs_root() no longer locks the vnode
unconditionally and traverse() didn't pass right lock type to
VFS_ROOT(). The result was that kernel paniced when .zfs/ directory
was accessed via NFS.
2007-06-04 11:31:46 +00:00
Konstantin Belousov
9e223287c0 Revert UF_OPENING workaround for CURRENT.
Change the VOP_OPEN(), vn_open() vnode operation and d_fdopen() cdev operation
argument from being file descriptor index into the pointer to struct file.

Proposed and reviewed by:	jhb
Reviewed by:	daichi (unionfs)
Approved by:	re (kensmith)
2007-05-31 11:51:53 +00:00
Pawel Jakub Dawidek
5750956634 Adjust va_mask for setattr. FreeBSD doesn't have va_mask, so we initialize it
based on individual fields beeing set. This doesn't work for setattr replay,
because va_type is set there, so we add AT_TYPE flag to va_mask, which won't
be accepted by zfs_setattr().

Reported by:	kris
2007-05-28 02:37:43 +00:00
Pawel Jakub Dawidek
a906fff9c5 Because we allocate componentname structures on stack, bzero() them before
use just in case.
2007-05-28 00:26:20 +00:00
Pawel Jakub Dawidek
0d99488ded There are too many false positive LORs reported by WITNESS, so when ZFS
debug is turned off, initialize locks with NOWITNESS flag.
At some point I'll get back to them, we would probably need BLESSING
functionality, which is currently turned off by default.
2007-05-26 21:37:14 +00:00
Pawel Jakub Dawidek
fbd08bbe6a DNLC_NO_VNODE can't be NULL.
Reported by:	ru
2007-05-24 13:44:45 +00:00
Pawel Jakub Dawidek
f92dd5c2d9 Initialize ZFS a bit earlier and block root mounting until
initialization is complete. This fixes some root-on-ZFS
configurations.

Reported by:	Bruno Damour <freebsd.ruomad@free.fr>
Tested by:	Bruno Damour <freebsd.ruomad@free.fr>
2007-05-24 07:43:00 +00:00
Pawel Jakub Dawidek
d4c4dfe96f FreeBSD's namecache works quite well with ZFS, so remove DNLC. 2007-05-23 21:33:02 +00:00
Pawel Jakub Dawidek
4282c449dc All objects we create using GFS are directories, so initialize d_type
properly, but add XXX comment saying that it can eventually change in
the future.
2007-05-23 21:27:47 +00:00
Pawel Jakub Dawidek
124427f96d Lock vnode on lookup. This fixes ZIL replay for rmdir/unlink/rename.
Reported by:	des
2007-05-22 21:22:25 +00:00
Pawel Jakub Dawidek
68e752c31c Increase debug level - this message is not that important. 2007-05-09 22:32:49 +00:00
Pawel Jakub Dawidek
6a7309390f - Add missing lock destruction and remove duplicate initializations.
With this change it is possible to unload zfs.ko module from
  WITNESS-enabled kernel.
- Remove bogus comment.
2007-05-06 19:05:37 +00:00
Pawel Jakub Dawidek
7baf73a6c2 Use provider's ident to handle situations when disks are moved around
and show up with different names: first try to open provider using
remembered name and compare its ident, if equal, this is our provider,
if not equal or there is no provider with such name, find provider with
remembered ident and don't care about the name.
2007-05-06 01:39:39 +00:00
Pawel Jakub Dawidek
fab3f4465e MFp4: We don't need to cover vnode_pager_setsize() with the z_map_lock. 2007-05-06 01:27:54 +00:00
Pawel Jakub Dawidek
57504dcfaf Share-lock a vnode where possible. 2007-05-02 01:03:10 +00:00
Pawel Jakub Dawidek
5bec66402b When parent directory has to be unlocked, lock it back with the same lock
type. Before this change, if directory was shared-locked, it was relocked
exclusively.
2007-05-02 00:41:44 +00:00
Pawel Jakub Dawidek
9167141244 Lock vnode using cn_lkflags in case the caller wants the vnode to be
shared-locked.
2007-05-02 00:39:52 +00:00
Pawel Jakub Dawidek
04748b1b2e The getnewvnode() function sets LK_NOSHARE by default, so if we want to
support shared vnodes locking, we need to remove that flag.
Also add LK_CANRECURSE flag as found in nfsclient.
2007-05-02 00:22:12 +00:00
Pawel Jakub Dawidek
0775674bbc ZFS should update timestamps upon the creat() of an existing file.
Obtained from:	OpenSolaris
Bug:		http://bugs.opensolaris.org/view_bug.do?bug_id=6465105
2007-05-02 00:18:22 +00:00
Pawel Jakub Dawidek
6de6bff649 - Lock vnode with flags passed in as argument in zfs_vget() and zfs_root().
Pointed out by:	ups
  Also reported by:	kris

- Add comments where I'm not sure if LK_RETRY should be used.
2007-05-02 00:09:34 +00:00
Pawel Jakub Dawidek
d1d7399da5 MFp4: Remove LK_RETRY flag when locking vnode in zfs_lookup, we don't want
dead vnodes here.

Suggested by:	kib
2007-05-01 13:58:56 +00:00
Pawel Jakub Dawidek
80ae748326 White space fixes. 2007-05-01 13:32:22 +00:00
Pawel Jakub Dawidek
7555fddd83 Add a comment explaining why we call dmu_write() unconditionally, even if
uiomove() fails, especially that it is different from what OpenSolaris
does (I'm not entirely sure they are right).

Suggested by:	darrenr
2007-05-01 12:09:45 +00:00
Pawel Jakub Dawidek
2f51d93626 - Define d_type for ".", ".." and ".zfs" directories.
- Add a TODO comment where d_type is still noe defined.
2007-04-29 23:28:07 +00:00
Pawel Jakub Dawidek
b9f28e4a35 Oops, correct important typo in last commit. 2007-04-29 23:12:00 +00:00
Pawel Jakub Dawidek
2c965e1956 Avoid freeing NULL pointer in case of an error. 2007-04-29 23:08:24 +00:00
Pawel Jakub Dawidek
f2c9356328 Fix two use-after-free cases. 2007-04-29 00:41:29 +00:00
Pawel Jakub Dawidek
c28672efcc MFp4: Optimize mappedwrite() and mappedread() functions to write/read as much
non-mapped data as possible at once and not page-by-page. Which this change we
combain I/Os, but also saves many VM_OBJECT_UNLOCK()/VM_OBJECT_LOCK()
operations.

Simple 'fsx -l 33554432 -o 524288 -N 10000 /tank/fsx' test shows ~23%
performance increase.
2007-04-26 17:07:50 +00:00
Pawel Jakub Dawidek
171c4b21e2 - Always try to write one whole page at a time.
- vm_page_undirty() is enough (instead of vm_page_set_validclean()), but it has
  to be called before we write the data in case someone makes page dirty after
  our write, but before our vm_page_undirty() call.
- Always dmu_write, not matter if uiomove() succeeded, because it could
  partially be ok and we would lose some changes.

All good ideas from:	ups
2007-04-26 12:58:17 +00:00
Pawel Jakub Dawidek
caa93cc3a0 MFV: Free znodes immediatelly, allowing the ARC to hold onto less memory.
Full description at:	http://bugs.opensolaris.org/view_bug.do?bug_id=6543706
2007-04-26 10:08:54 +00:00
Pawel Jakub Dawidek
5da1b1ed71 MFV: Functions name change. 2007-04-26 09:38:20 +00:00
Pawel Jakub Dawidek
1e788bd7e5 ZIL (ZFS Intent Log) can be safely turned on and off at run time, because
it is only used when dataset is beeing mounted to decide if log should also
be opened.
2007-04-24 19:02:51 +00:00
Pawel Jakub Dawidek
8b384c52c0 MFp4: Now that ZFS can use FreeBSD's namecache, turn it off by default and
turn off DNLC, but don't remove DNLC yet just in case.
2007-04-24 16:59:20 +00:00
Pawel Jakub Dawidek
f13f738876 MFp4: Rearange the code so vobject is destroyed from reclaim() method like
in all other file system on FreeBSD (instead from inactive() method).

A nice side-effect of this change, except that it speedups file system
when mmaped file are often open/closed, is that it makes FreeBSD's
namecache work:)
2007-04-24 16:57:53 +00:00
Pawel Jakub Dawidek
0cdad5e228 MFp4: Once page is written successfully, we should clear the dirty bits.
This fixes slow operations on mmaped files, because without this fix,
pages were written to disk multiple times.

If one is looking for even greater speed up for such operation, he should
disable ZIL (by setting vfs.zfs.zil_disable to 1 in /boot/loader.conf).
Disabling ZIL makes fsx run ~9 times faster.
2007-04-24 16:53:01 +00:00
Pawel Jakub Dawidek
71ce4c9c10 MFp4: Reduce diff against vendor. 2007-04-24 16:49:01 +00:00
Pawel Jakub Dawidek
692fd5a7b9 MFp4: We have stronger 'lock already initialized' check now, so we can
reduce diff against the vendor by removing bzero of this mutex.
2007-04-24 16:45:42 +00:00
Bruce A. Mah
9100d31299 Mostly-cosmetic fixes in low-memory warning messages:
o Fix linewrap issues.

o Fix two typos (s/Recomended/Recommended/ and s/tunning/tuning/)

o Remove a couple of extra instances of the word "of".

o Update names of kmem_size variables.

Approved by:	pjd
2007-04-23 21:52:14 +00:00
Pawel Jakub Dawidek
cfda925270 Too much diff reduction. 'cmd' has to be u_long.
Reported by:	delphij
2007-04-23 13:47:49 +00:00
Pawel Jakub Dawidek
cc7cd831b2 MFp4: Reduce diff against vendor code:
- Move FreeBSD-specific code to zfs_freebsd_*() functions in zfs_vnops.c
  and keep original functions as similar to vendor's code as possible.
- Add various includes back, now that we have them.
2007-04-23 00:52:07 +00:00
Pawel Jakub Dawidek
3698384259 Fix 'zpool status -v'. To get object number we should use ZFS_DIRENT_OBJ()
macro, as za_first_integer field also contains type. This should be fixed in
ZFS itself, but this bug is not visible on Solaris, because there, type is
not stored in za_first_integer. On the other hand it will be visible on
MacOS X.

Reported by:	Barry Pederson <bp@barryp.org>
2007-04-22 21:18:40 +00:00
Pawel Jakub Dawidek
77128a226d Fix st_rdev handling (implement it, actually).
Reported by:	gj
2007-04-22 21:16:15 +00:00
Pawel Jakub Dawidek
9de81c7273 MFp4:
@118370	Correct typo.

@118371	Integrate changes from vendor.

@118491	Show backtrace on unexpected code paths.

@118494	Integrate changes from vendor.

@118504	Fix sendfile(2). I had two ways of fixing it:
	1. Fixing sendfile(2) itself to use VOP_GETPAGES() instead of
	   hacking around with vn_rdwr(UIO_NOCOPY), which was suggested
	   by ups.
	2. Modify ZFS behaviour to handle this special case.

	Although 1 is more correct, I've choosen 2, because hack from 1
	have a side-effect of beeing faster - it reads ahead MAXBSIZE
	bytes instead of reading page by page. This is not easy to implement
	with VOP_GETPAGES(), at least not for me in this very moment.

	Reported by:	Andrey V. Elsukov <bu7cher@yandex.ru>

@118525	Reorganize the code to reduce diff.

@118526	This code path is expected. It is simply when file is opened with
	O_FSYNC flag.

	Reported by:	kris
	Reported by:	Michal Suszko <dry@dry.pl>
2007-04-21 12:02:57 +00:00
Pawel Jakub Dawidek
32371d2025 MFp4: Fix automatic snapshot mount when unprivileged user does lookup
on a snapshot directory:
- Remove PRIV_VFS_MOUNT check - regular users can mount snapshots
  via lookups on snapshot directory.
- Reset mount credential to kcred, so user won't be able to unmount
  the snapshot.
- Reset owner uid.
- Unlock vnode in case of a failure.

Reported by:	simokawa
2007-04-18 15:24:48 +00:00
Pawel Jakub Dawidek
f2c9a576db MFp4: We check for PRIV_VFS_MOUNT already in mount(2) syscall and we don't
want to do the check when snapshot is automatically mounted by an
      unprivileged user doing lookup on a snapshot directory.
2007-04-18 15:22:07 +00:00
Pawel Jakub Dawidek
35e8a7fad7 Simplify. 2007-04-17 21:58:34 +00:00
Pawel Jakub Dawidek
a1bcf4dc7b - Fix a leftover - vfs_mount_alloc() is now exported properly.
This fixes stange panics when listing .zfs/snapshot/ directory for me.
  Reported by:	simokawa
  Reported by:	Johan Hendriks <Johan@double-l.nl>
- Hide cache_purge() under FREEBSD_NAMECACHE like in other files.
- Protect mnt_flag with mount interlock.
2007-04-17 21:16:34 +00:00
Pawel Jakub Dawidek
39db4c6e0f Ignore hostid check for root-on-ZFS configurations. Making hostid available
before the root is mounted is tricky and having it in /boot/ is not really
desire.

Reported by:	Zephiris <zephiris@gmail.com>
2007-04-17 17:57:34 +00:00
Pawel Jakub Dawidek
8cb195f758 Uncomment forgotten check. Without this check in-place, ZFS will panic on
unload instead of returning EBUSY. This check tells if there are mounted
ZFS file systems or not. We can't unload if there are mounted file systems.

Reported by:	Andrey V. Elsukov <bu7cher@yandex.ru>
2007-04-16 10:23:24 +00:00
Pawel Jakub Dawidek
7ae6548e62 MFp4: Start DNLC after desiredvnodes variable is initialized.
Before this change if zfs.ko was loaded by the loader, DNLC was
      automatically disabled.

Reported by:	Zephiris <zephiris@gmail.com>
2007-04-15 09:10:17 +00:00
Pawel Jakub Dawidek
87e89536f1 Fix RAID-Z resilvering.
Obtained from:	OpenSolaris
2007-04-14 20:50:14 +00:00
Pawel Jakub Dawidek
d48078479c MFp4: Hmm, it seems to work now. 2007-04-14 15:01:50 +00:00
Pawel Jakub Dawidek
8aff52ca4e MFp4: Use max_ncpus, which is used in other places in the code. 2007-04-14 12:33:47 +00:00
Pawel Jakub Dawidek
8870baf005 MFp4: Add more debug, so we can see if zpool.cache was loaded or why it
wasn't loaded.
2007-04-14 12:23:03 +00:00
Pawel Jakub Dawidek
dbd490e0e2 MFp4: Allow to tune vfs.zfs.debug from loader.conf. 2007-04-14 12:21:06 +00:00
Pawel Jakub Dawidek
c98fbf0418 MFp4: - Allow to tune number of spa_zio_* threads.
- Reduce default number of spa_zio_* threads to N*spa_zio_issue
	  plus N*spa_zio_intr threads per ZIO type, where N is the number
	  of CPUs.
	- Put ZIO type number in thread's name.
2007-04-14 12:20:06 +00:00
Pawel Jakub Dawidek
bd59d85850 Fix overflow, which was causing endless loops when 32bit machine had more
than 2GB of RAM. This was because our physmem is long and 'physmem*PAGESIZE'
can be negative for more than 2GB of memory.

Reported by:	Andrey V. Elsukov <bu7cher@yandex.ru>

It is not yet tested by Andrey, so there can be other problems, but this
was definiately a bug, so I'm committing a fix now.
2007-04-13 18:50:03 +00:00
Pawel Jakub Dawidek
f0bc5ac3e1 Fix vnodes starvation caused by DNLC (ZFS name cache):
- Tune number of namecache entires better (based on desiredvnodes).
- Handle vfs_lowvnodes event by releasing requested number of name cache
  entries, but no less than 5%.

Reported by:	simokawa
2007-04-13 08:42:01 +00:00
Pawel Jakub Dawidek
6704017a15 MFp4: Synchronize with vendor (mostly 'zfs rename -r'). 2007-04-12 23:16:02 +00:00
Pawel Jakub Dawidek
1da61b3665 MFp4: Bring back comments.
Requested by:	jhb
2007-04-12 23:14:25 +00:00
Wojciech A. Koszek
f7caeade24 strchr() and strrchr() are already present in the kernel, but with less
popular names. Hence:

- comment current index() and rindex() functions, as these serve the same
  functionality as, respectively, strchr() and strrchr() from userland;
- add inlined version of strchr() and strrchr(), as we tend to use them more
  often;
- remove str[r]chr() definitions from ZFS code;

Reviewed by:	pjd
Approved by:	cognet (mentor)
2007-04-10 21:42:12 +00:00
Pawel Jakub Dawidek
1b6e2c02fe MFp4: Allow to set zfs_recover via vfs.zfs.recover from /boot/loader.conf. 2007-04-10 12:54:19 +00:00
Pawel Jakub Dawidek
5b9528e2d4 MFp4: Hide under '#ifdef _KERNEL' only what's really needed. 2007-04-10 12:52:14 +00:00
Pawel Jakub Dawidek
2d03e33170 Try to stabilize ZFS with regard to memory consumption:
- Allow to shrink ARC down to 16MB (instead of 64MB).
- Set arc_max to 1/2 of kmem_map by default.
- Start freeing things earlier when low memory situation is detected.
- Serialize execution of arc_lowmem().

I decided to setup minimum ZFS memory requirements to 512MB of RAM and 256MB of
kmem_map size. If there is less RAM or kmem_map, a warning will be printed.
World is cruel, be no better. In other words: modern file system requires
modern hardware:)

From ZFS administration guide:

"Currently the minimum amount of memory recommended to install a Solaris
 system is 512 Mbytes. However, for good ZFS performance, at least one
 Gbyte or more of memory is recommended."
2007-04-10 02:35:57 +00:00
Pawel Jakub Dawidek
52124c7f1c Reduce diff against vendor - we have now stronger check for "mutex already
initialized", so we can go back to kmem_alloc().
2007-04-10 02:19:12 +00:00
Pawel Jakub Dawidek
0404b7791b Remove unused #define. 2007-04-09 23:30:28 +00:00
Pawel Jakub Dawidek
24bda1641f Instead of detecting if lock is already initialized based on standard 1 bit
check, use more accurate 13 bits check. We had too many false-positives with
the standard check.

Reported by:	mlaier
2007-04-09 01:05:31 +00:00
Pawel Jakub Dawidek
33fc425c85 We don't have to wait for the root file system to be mounted anymore, now that
kobj KPI supports operating on files loaded by the loader.
2007-04-09 00:03:45 +00:00
Pawel Jakub Dawidek
5fc5d6ed61 Drop the Giant lock before calling zfs_domount(), which is held when
mounting root file system.
2007-04-09 00:02:11 +00:00
Pawel Jakub Dawidek
f92cb15e7b Move zpool.cache from /etc/zfs/ to /boot/zfs/, so we can keep it on
dedicated /boot/ file system and use ZFS for the root file system.
2007-04-08 23:59:39 +00:00
Pawel Jakub Dawidek
bdebccf9b9 Extend kobj compatibility KPI to support operating on files before and
after the root file system is mounted.
This is one of the changes that will allow to put root file system on ZFS.
2007-04-08 23:57:08 +00:00
Pawel Jakub Dawidek
ffe54ff0ec MFp4: Synchronize with recent OpenSolaris changes. 2007-04-08 16:29:25 +00:00
Pawel Jakub Dawidek
425d75486e - Use 'name=value' so it can be properly recognized by devd(8).
- Use only subclass as devd's type.
2007-04-08 15:55:48 +00:00
Pawel Jakub Dawidek
61cfeccd58 Take vnode pointer and hold it under znode lock, so we won't race with
zfs_reclaim(). This may or may not fix problem reported by kris, but it's
definiatelly better that way.
2007-04-08 10:29:14 +00:00
Pawel Jakub Dawidek
3dc4488c91 Move atomic.S files to directories that better fit OpenSolaris directory
layout.
2007-04-07 23:54:54 +00:00
Pawel Jakub Dawidek
e321494eca Fix libzpool compilation.
Reported by:	des
2007-04-07 23:47:14 +00:00
Pawel Jakub Dawidek
9a691cb33a Limit the number of system taskq threads to the number of CPUs.
They are only used when there is a need for reducing namecache.

Observed by:	kris, csjp
2007-04-07 21:41:11 +00:00