It looks like EVFILT_READ and EVFILT_WRITE trigger under the same
conditions as poll()'s POLLRDNORM and POLLWRNORM as described by POSIX.
The only difference is that POLLRDNORM has to be triggered on regular
files unconditionally, whereas EVFILT_READ only triggers when not EOF.
Introduce a new flag, NOTE_FILE_POLL, that can be used to make
EVFILT_READ and EVFILT_WRITE behave identically to poll(). This flag
will be used by cloudlibc's poll() function.
Reviewed by: jmg
Differential Revision: https://reviews.freebsd.org/D3303
Transitions 0->1 and 1->0 (which decide e.g. on putting the vnode on the free
list) of either counter are still guarded with vnode interlock.
Reviewed by: kib (earlier version)
Tested by: pho
Previously vputx would detect the condition and clear the flag.
With this change it is invalid to have both v_usecount > 0 and the flag
set. Assert the condition is met in all revlevant places.
Reviewed by: kib
objects, i.e. for buffer objects which vnode was reclaimed. Buffer
cache cannot write such buffers. Return the error and discard the
buffer immediately on write attempt.
BO_DIRTY now always set during vnode reclamation, since it is used not
only for the INVARIANTS checks. Do allow placement of the clean
buffers on dead bufobj list, otherwise filesystems cannot use bufcache
at all after the devvp reclaim.
Reported and tested by: trasz
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
the active vnode list for the given mount point, with the assumption
that vnodes with dirty pages are active. This is enforced by
vinactive() doing vm_object_page_clean() pass over the vnode pages.
The issue is, if vinactive() cannot be called during vput() due to the
vnode being only shared-locked, we might end up with the dirty pages
for the vnode on the free list. Such vnode is invisible to syncer,
and pages are only cleaned on the vnode reactivation. In other words,
the race results in the broken guarantee that user data, written
through the mmap(2), is written to the disk not later than in 30
seconds after the write.
Fix this by keeping the vnode which is freed but still owing
inactivation, on the active list. When syncer loops find such vnode,
it is deactivated and cleaned by the final vput() call.
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Nothing stops a parallel unmount to suceed before the given call to
dounmount() checks and locks the covered vnode. Prevent dounmount()
from acting on the freed (although type-stable) memory by changing the
interface to require the mount point to be referenced. dounmount()
consumes the reference on return, regardless of the sucessfull or
erronous result.
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
use VOP_FSYNC() to perform the NFS server's Commit operation.
This patch adds a mnt_kern_flag called MNTK_USES_BCACHE which
is set by file systems that use the buffer cache. If this flag
is not set, the NFS server always does a VOP_FSYNC().
This should be ok for old file system modules that do not set
MNTK_USES_BCACHE, since calling VOP_FSYNC() is correct, although
it might not be optimal for file systems that use the buffer cache.
Reviewed by: kib
MFC after: 2 weeks
prevent errors from yanking devices out from under filesystems. Only
care about special vnodes on devfs, special nodes on other kinds of
filesystems do not have special properties.
Sponsored by: EMC / Isilon Storage Division
Submitted by: Conrad Meyer
MFC after: 1 week
- vfs.recycles counts the number of vnodes forcefully recycled to avoid
exceeding kern.maxvnodes.
- vfs.vnodes_created counts the number of vnodes created by successful
calls to getnewvnode().
Differential Revision: https://reviews.freebsd.org/D1671
Reviewed by: kib
MFC after: 1 week
creating delayed write buffers belonging to the reclaimed vnode. Put
the buffer cleanup code after inactivation.
Add asserts that ensure that buffer queues are empty and add BO_DEAD
flag for bufobj to check that no buffers are added after the cleanup.
BO_DEAD is only used by INVARIANTS-enabled kernels.
Reported and tested by: pho (previous version)
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
to be called before suspension and after resume, correspondingly. The
syncer_suspend() ensures that all filesystems dirty data and metadata
are saved to the permanent storage, and stops kernel threads which
might modify filesystems. The syncer_resume() restores stopped
threads.
For now, only syncer is stopped. This is needed, because each sync
loop causes superblock updates for UFS.
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Some watchdog drivers (like ipmi) need to sleep while patting the watchdog.
See sys/dev/ipmi/ipmi.c:ipmi_wd_event(), which calls malloc(M_WAITOK).
Submitted by: asomers
MFC after: 1 month
Sponsored by: Spectra Logic
MFSpectraBSD: 637548 on 2012/10/04
It could be claimed that two things were reasonable protected by
Giant. One is vfsconf list links, which is converted to the new
dedicated sx vfsconf_sx. Another is vfsconf.vfc_refcount, which is
now updated with atomics.
Note that vfc_refcount still has the same races now as it has under
the Giant, the unload of filesystem modules can happen while the
module is still in use.
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
some parts of the checks are in fact redundand in the surrounding
code, and it is more clear what the conditions are by direct testing
of the flags. Two of the three macros were only used in assertions.
In vnlru_free(), all relevant parts of vholdl() were already inlined,
except the increment of v_holdcnt itself. Do not call vholdl() to do
the increment as well, this allows to make assertions in
vholdl()/vhold() more strict.
In v_incr_usecount(), call vholdl() before incrementing other ref
counters. The change is no-op, but it makes less surprising to see
the vnode state in debugger if interrupted inside v_incr_usecount().
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
avoid congestion on global mountlist_mtx mutex in vfs_busyfs(), while
traversing through the list of mount points.
This change significantly improves NFS server scalability, since it had
to do this translation for every request, and the global lock becomes quite
congested.
This code is more optimized for relatively small number of mount points.
On systems with hundreds of active mount points this simple cache may have
many collisions. But the original traversal code in that case should also
behave much worse, so we are not loosing much.
Reviewed by: attilio
MFC after: 2 weeks
Sponsored by: iXsystems, Inc.
This allows to mostly avoid lock usage in getnewvnode_[drop_]reserve(),
that reduces number of global vnode_free_list_mtx mutex acquisitions
from 4 to 2 per NFS request on ZFS, improving SMP scalability.
Reviewed by: kib
MFC after: 2 weeks
Sponsored by: iXsystems, Inc.
Assert that the hold count has not fallen below the use count, a situation
that would only happen when a vref() (or similar) is erroneously paired
with a vdrop(). This situation has not been observed in the wild, but
could be helpful for someone implementing a new filesystem.
Reviewed by: kib
Approved by: hrs (mentor)
To reduce the diff struct pcu.cnt field was not renamed, so
PCPU_OP(cnt.field) is still used. pc_cnt and pcpu are also used in
kvm(3) and vmstat(8). The goal was to not affect externally used KPI.
Bump __FreeBSD_version_ in case some out-of-tree module/code relies on the
the global cnt variable.
Exp-run revealed no ports using it directly.
No objection from: arch@
Sponsored by: EMC / Isilon Storage Division
really belong to it. Such vnodes, with the pointers to other vnodes
v_objects, are typically instantiated by the bypass filesystems.
Invalidating mappings of other vnode pages and the pages is wrong,
since reclamation of the upper vnode does not imply that lower vnode
is reclaimed too.
One of the consequences of the improper reclamation was destruction of
the wired mappings of the lower vnode pages, triggering miscellaneous
assertions in the VM system.
Reported by: John Marshall <john.marshall@riverwillow.com.au>
Tested by: John Marshall <john.marshall@riverwillow.com.au>, pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Approved by: re (gjb)
with the vnode shared-locked. If upgrade succeeded, the inactivation
can be done immediately, instead of being postponed.
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Approved by: re (glebius)
Otherwise, knote keeps a pointer to a vnode which could become invalid
any time.
Reported by: many
Tested by: Patrick Lamaiziere <patfbsd@davenulle.org>
Discussed with: jmg
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Approved by: re (marius)
must be destroyed, knlist_clear() and seldrain() calls could be
avoided, since vpollinfo was not used. More, the knlist_clear()
calling protocol requires the knlist locked, which is not true at the
call site.
Split the destruction into the helper destroy_vpollinfo_free(), and
call it when raced, instead of destroy_vpollinfo().
Reported and tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 3 days
the vnode lock while iterating over the free vnode list. Instead of
yielding, pause for 1 tick. The change is reported to help in some
virtualized environments.
Submitted by: Roger Pau Monn? <roger.pau@citrix.com>
Discussed with: jilles
Tested by: pho
MFC after: 2 weeks
- Use a shared bufobj lock in getblk() and inmem().
- Convert softdep's lk to rwlock to match the bufobj lock.
- Move INFREECNT to b_flags and protect it with the buf lock.
- Remove unnecessary locking around bremfree() and BKGRDINPROG.
Sponsored by: EMC / Isilon Storage Division
Discussed with: mckusick, kib, mdf
with any structure containing a uint64_t index. The tree code
auto-generates type safe wrappers.
- Eliminate the buf splay and replace it with pctrie. This is not only
significantly faster with large files but also allows for the possibility
of shared locking.
Reviewed by: alc, attilio
Sponsored by: EMC / Isilon Storage Division
null_hashget() obtains the reference on the nullfs vnode, which must
be dropped.
- Fix a wart which existed from the introduction of the nullfs
caching, do not unlock lower vnode in the nullfs_reclaim_lowervp().
It should be innocent, but now it is also formally safe. Inform the
nullfs_reclaim() about this using the NULLV_NOUNLOCK flag set on
nullfs inode.
- Add a callback to the upper filesystems for the lower vnode
unlinking. When inactivating a nullfs vnode, check if the lower
vnode was unlinked, indicated by nullfs flag NULLV_DROP or VV_NOSYNC
on the lower vnode, and reclaim upper vnode if so. This allows
nullfs to purge cached vnodes for the unlinked lower vnode, avoiding
excessive caching.
Reported by: G??ran L??wkrantz <goran.lowkrantz@ismobile.com>
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
locks. To support this, VNODE locks are created with the LK_IS_VNODE
flag. This flag is propagated down using the LO_IS_VNODE flag.
Note that WITNESS still records the LOR. Only the printing and the
optional entering into the kernel debugger is bypassed with the
WITNESS_NO_VNODE option.
LK_EXCLOTHER. LK_EXCLOTHER is only used to acquire a
usecount on a vnode during NFSv4 recovery from an
expired lease.
Reported and tested by: pho
MFC after: 2 weeks
- Don't insert BKGRDMARKER bufs into the splay or dirty/clean buf lists.
No consumers need to find them there and it complicates the tree.
These flags are all FFS specific and could be moved out of the buf
cache.
- Use pbgetvp() and pbrelvp() to associate the background and journal
bufs with the vp. Not only is this much cheaper it makes more sense
for these transient bufs.
- Fix the assertions in pbget* and pbrel*. It's not safe to check list
pointers which were never initialized. Use the BX flags instead. We
also check B_PAGING in reassignbuf() so this should cover all cases.
Discussed with: kib, mckusick, attilio
Sponsored by: EMC / Isilon Storage Division
future further optimizations where the vm_object lock will be held
in read mode most of the time the page cache resident pool of pages
are accessed for reading purposes.
The change is mostly mechanical but few notes are reported:
* The KPI changes as follow:
- VM_OBJECT_LOCK() -> VM_OBJECT_WLOCK()
- VM_OBJECT_TRYLOCK() -> VM_OBJECT_TRYWLOCK()
- VM_OBJECT_UNLOCK() -> VM_OBJECT_WUNLOCK()
- VM_OBJECT_LOCK_ASSERT(MA_OWNED) -> VM_OBJECT_ASSERT_WLOCKED()
(in order to avoid visibility of implementation details)
- The read-mode operations are added:
VM_OBJECT_RLOCK(), VM_OBJECT_TRYRLOCK(), VM_OBJECT_RUNLOCK(),
VM_OBJECT_ASSERT_RLOCKED(), VM_OBJECT_ASSERT_LOCKED()
* The vm/vm_pager.h namespace pollution avoidance (forcing requiring
sys/mutex.h in consumers directly to cater its inlining functions
using VM_OBJECT_LOCK()) imposes that all the vm/vm_pager.h
consumers now must include also sys/rwlock.h.
* zfs requires a quite convoluted fix to include FreeBSD rwlocks into
the compat layer because the name clash between FreeBSD and solaris
versions must be avoided.
At this purpose zfs redefines the vm_object locking functions
directly, isolating the FreeBSD components in specific compat stubs.
The KPI results heavilly broken by this commit. Thirdy part ports must
be updated accordingly (I can think off-hand of VirtualBox, for example).
Sponsored by: EMC / Isilon storage division
Reviewed by: jeff
Reviewed by: pjd (ZFS specific review)
Discussed with: alc
Tested by: pho
Set the v_hash for a new vnode in the getnewvnode() to the value
calculated based on the vnode structure address. Filesystems using
vfs_hash_insert() override the v_hash using the standard formula of
(inode_number + mnt_hashseed). For other filesystems, the
initialization allows the vfs_hash_index() to provide useful hash too.
Suggested, reviewed and tested by: peter
Sponsored by: The FreeBSD Foundation
MFC after: 5 days
case. There is no point in optimizing further the code and use a TRUE
litteral for a path that does heavyweight stuff anyway (like lock acq),
at the price of obfuscated code.
Use the appropriate check where necessary and remove a macro.
Sponsored by: EMC / Isilon storage division
MFC after: 3 days
When kern_yield() was introduced with the possibility to specify
a new priority, the behaviour changed by not lowering priority at all
in the consumers, making the yielding mechanism highly ineffective for
high priority kthreads like bufdaemon, syncer, vlrudaemon, etc.
There are no evidences that consumers could bear with such change in
semantic and this situation could finally lead to bugs similar to the
ones fixed in r244240.
Re-specify userland pri for kthreads involved.
Tested by: pho
Reviewed by: kib, mdf
MFC after: 1 week
yields, specify the user priority for the yield. Otherwise, a
higher-priority (kernel) thread could fall into the priority-inversion
with the thread owning the mutex lock.
On single-processor machines or UP kernels, do not loop adaptively
when the next vnode cannot be locked, instead yield unconditionally.
Restructure the iteration initializer and the iterator to remove code
duplication. Put the code to fetch and lock a vnode next to the
current marker, into the mnt_vnode_next_active() function, and use it
instead of repeating the loop.
Reported by: hrs, rmacklem
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 3 days
kern_yield() is problematic than.
The owned mutex is the mount interlock, and it is in fact not needed
to guarantee the stability of the mount list of active vnodes, so fix
the the issue by only taking the mount interlock for MNT_REF and
MNT_REL operations.
While there, augment the unconditional yield by some amount of
spinning [1].
Reported and tested by: pho
Reviewed by: attilio
Submitted by: attilio [1]
MFC after: 3 days
