This combination doesn't make sense, unit numbers should be hardwired
only in context of a known driver. The wildcard devices should have
wildcard unit numbers.
Reviewed by: jhb
MFC after: 2 weeks
this is a VNET-kernel or not. gcc used to put the static symbol into
the symbol table, clang does not. This fixes the 'netstat: no namelist'
error seen on clang+VNET systems.
'flags' field is added to the end of bpf_if structure. Currently the only
flag is BPFIF_FLAG_DYING which is set on bpf detach and checked by bpf_attachd()
Problem can be easily triggered on SMP stable/[89] by the following command (sort of):
'while true; do ifconfig vlan222 create vlan 222 vlandev em0 up ; tcpdump -pi vlan222 & ; ifconfig vlan222 destroy ; done'
Fix possible use-after-free when BPF detaches itself from interface, freeing bpf_bif memory,
while interface is still UP and there can be routes via this interface.
Freeing is now delayed till ifnet_departure_event is received via eventhandler(9) api.
Convert bpfd rwlock back to mutex due lack of performance gain (currently checking if packet
matches filter is done without holding bpfd lock and we have to acquire write lock if packet matches)
Approved by: kib(mentor)
MFC in: 4 weeks
Most part is merged from amd64.
- i386/acpica/acpi_wakecode.S
Replaced with amd64 code (from realmode to paging enabling code).
- i386/acpica/acpi_wakeup.c
Replaced with amd64 code (except for wakeup_pagetables stuff).
- i386/include/pcb.h
- i386/i386/genassym.c
Added PCB new members (CR0, CR2, CR4, DS, ED, FS, SS, GDT, IDT, LDT
and TR) needed for suspend/resume, not for context switch.
- i386/i386/swtch.s
Added suspendctx() and resumectx().
Note that savectx() was not changed and used for suspending (while
amd64 code uses it).
BSP and AP execute the same sequence, suspendctx(), acpi_wakecode()
and resumectx() for suspend/resume (in case of UP system also).
- i386/i386/apic_vector.s
Added cpususpend().
- i386/i386/mp_machdep.c
- i386/include/smp.h
Added cpususpend_handler().
- i386/include/apicvar.h
- kern/subr_smp.c
- sys/smp.h
Added IPI_SUSPEND and suspend_cpus().
- i386/i386/initcpu.c
- i386/i386/machdep.c
- i386/include/md_var.h
- pc98/pc98/machdep.c
Moved initializecpu() declarations to md_var.h.
MFC after: 3 days
Entries with zero inode number are considered placeholders by libc and
UFS. Fix remaining uses of VOP_READDIR in kernel: vop_stdvptocnp,
unionfs.
Sponsored by: Google Summer of Code 2011
compatible with the sched provider implemented by Solaris and its open-
source derivatives. Full documentation of the sched provider can be found
on Oracle's DTrace wiki pages.
Note that for compatibility with scripts originally written for Solaris,
serveral probes are defined that will never fire. These probes are defined
to fire when Solaris-specific features perform certain actions. As these
features are not present in FreeBSD, the probes can never fire.
Also, I have added a two probes that are not defined in Solaris, lend-pri
and load-change. These probes have been added to make it possible to
collect schedgraph data with DTrace.
Finally, a few probes are defined in Solaris to take a cpuinfo_t *
argument. As it was not immediately clear to me how to translate that to
FreeBSD, currently those probes are passed NULL in place of a cpuinfo_t *.
Sponsored by: Sandvine Incorporated
MFC after: 2 weeks
is running on other cpu, the CALLOUT_PENDING flag is temporarily
cleared. Then, callout_stop() on this, in fact active, callout fails
because CALLOUT_PENDING is not set, and callout_stop() returns 0.
Now, in sleepq_check_timeout(), the failed callout_stop() causes the
sleepq code to execute mi_switch() without even setting the wmesg,
since the switch-out is supposed to be transient. In fact, the thread
is put off the CPU for full timeout interval, instead of being put on
runq immediately. Until timeout fires, the process is unkillable for
obvious reasons.
Fix this by marking the migrating callouts with CALLOUT_DFRMIGRATION
flag. The flag is cleared by callout_stop_safe() when the function
detects a migration, besides returning the success. The softclock()
rechecks the flag for migrating callout and cancels its execution if
the flag was cleared meantime.
PR: misc/166340
Reported, debugging traces provided and tested by:
Christian Esken <christian.esken trivago com>
Reviewed by: avg, jhb
MFC after: 1 week
if the accounting log file is atomically replaced with a new file
(such as during log rotation).
- Simplify accounting log rotation a bit. There is no need to re-run
accton(8) after renaming the new log file to it's real name.
PR: kern/167321
Tested by: Jeremy Chadwick
to the process id. It follows the ptrace(2) interface and allows debugging
libraries to use thread ids directly, without slow and verbose conversion
of thread id into pid.
The PGET_NOTID flag is provided to allow a specific sysctl to disallow
this behaviour. All current callers of pget(9) have useful semantic to
operate on tid and do not need this flag.
Reviewed by: jhb, trocini
MFC after: 1 week
over just the active vnodes associated with a mount point to replace
MNT_VNODE_FOREACH_ALL in the vfs_msync, ffs_sync_lazy, and qsync
routines.
The vfs_msync routine is run every 30 seconds for every writably
mounted filesystem. It ensures that any files mmap'ed from the
filesystem with modified pages have those pages queued to be
written back to the file from which they are mapped.
The ffs_lazy_sync and qsync routines are run every 30 seconds for
every writably mounted UFS/FFS filesystem. The ffs_lazy_sync routine
ensures that any files that have been accessed in the previous
30 seconds have had their access times queued for updating in the
filesystem. The qsync routine ensures that any files with modified
quotas have those quotas queued to be written back to their
associated quota file.
In a system configured with 250,000 vnodes, less than 1000 are
typically active at any point in time. Prior to this change all
250,000 vnodes would be locked and inspected twice every minute
by the syncer. For UFS/FFS filesystems they would be locked and
inspected six times every minute (twice by each of these three
routines since each of these routines does its own pass over the
vnodes associated with a mount point). With this change the syncer
now locks and inspects only the tiny set of vnodes that are active.
Reviewed by: kib
Tested by: Peter Holm
MFC after: 2 weeks
a mount point. Active vnodes are those with a non-zero use or hold
count, e.g., those vnodes that are not on the free list. Note that
this list is in addition to the list of all the vnodes associated
with a mount point.
To avoid adding another set of linkage pointers to the vnode
structure, the active list uses the existing linkage pointers
used by the free list (previously named v_freelist, now renamed
v_actfreelist).
This update adds the MNT_VNODE_FOREACH_ACTIVE interface that loops
over just the active vnodes associated with a mount point (typically
less than 1% of the vnodes associated with the mount point).
Reviewed by: kib
Tested by: Peter Holm
MFC after: 2 weeks
used only as a helper function in that file. Replace sole call to
vbusy() with inline code in vholdl(). Replace sole calls to vfree()
and vdestroy() with inline code in vdropl().
The Clang compiler already inlines these functions, so they do not
show up in a kernel backtrace which is confusing. Also you cannot
set their frame in kgdb which means that it is impossible to view
their local variables. So, while the produced code is unchanged,
the debugging should be easier.
Discussed with: kib
MFC after: 2 weeks
The primary changes are that the user of the interface no longer
needs to manage the mount-mutex locking and that the vnode that
is returned has its mutex locked (thus avoiding the need to check
to see if its is DOOMED or other possible end of life senarios).
To minimize compatibility issues for third-party developers, the
old MNT_VNODE_FOREACH interface will remain available so that this
change can be MFC'ed to 9. Following the MFC to 9, MNT_VNODE_FOREACH
will be removed in head.
The reason for this update is to prepare for the addition of the
MNT_VNODE_FOREACH_ACTIVE interface that will loop over just the
active vnodes associated with a mount point (typically less than
1% of the vnodes associated with the mount point).
Reviewed by: kib
Tested by: Peter Holm
MFC after: 2 weeks
allow the owner to read and write ACL and file attributes when there
was no entry with subject matching the owner. In other words,
'getfacl meh' shouldn't fail for the owner if the ACL looks like this:
# file: meh
# owner: trasz
# group: wheel
user:root:------a-------:------:allow
Reported by: kientzle
like the one triggered by this:
# kldload geom_vinum
# pwait `pgrep -S gv_worker` &
# kldunload geom_vinum
or this:
GEOM_JOURNAL: Shutting down geom gjournal 3464572051.
panic: destroying non-empty racct: 1 allocated for resource 6
which were tracked by jh@ to be caused by checking p->p_flag,
while it wasn't initialised yet. Basically, during fork, the code
checked p_flag, concluded the process isn't marked as P_SYSTEM,
incremented the counter, and later on, when exiting, checked that
the process was marked as P_SYSTEM, and thus didn't decrement it.
Also, I believe there wasn't any good reason for checking P_SYSTEM
in the first place.
Tested by: jh
but GNU libc used it without checking its kernel version, e. g., Fedora 10.
- Move pipe(2) implementation for Linuxulator from MD files to MI file,
sys/compat/linux/linux_file.c. There is no MD code for this syscall at all.
- Correct an argument type for pipe() from l_ulong * to l_int *. Probably
this was the source of MI/MD confusion.
Reviewed by: emulation
backtrace for an arbitrary thread (rather than the calling thread).
A kdb_backtrace_thread() wrapper function uses the configured debugger
if possible, otherwise it falls back to using stack(9) if that is
available.
- Replace a direct call to db_trace_thread() in propagate_priority()
with a call to kdb_backtrace_thread() instead.
MFC after: 1 week
fail to load (the MOD_LOAD event fails) during a kldload(2), unload the
linker file and fail the kldload(2) with ENOEXEC.
Reported by: gcooper
MFC after: 1 week
in td_errno. Flag is supposed to be used by syscalls returning
EJUSTRETURN because errno was already placed into the usermode frame
by a call to set_syscall_retval(9). Both ktrace and dtrace get errno
value from td_errno if the flag is set.
Use the flag to fix sigsuspend(2) error return ktrace records.
Requested by: bde
MFC after: 1 week
static and declare its prototype in sys/vnode.h) so that it can be
called from process_deferred_inactive() (in ufs/ffs/ffs_snapshot.c)
instead of the body of vinactive() being cut and pasted into
process_deferred_inactive().
Reviewed by: kib
MFC after: 2 weeks
being attached. This is implemented by adding a new DS_ATTACHING state
while a device's DEVICE_ATTACH() method is being invoked. A driver is
required to not fail an attach of a busy device. The device's state will
be promoted to DS_BUSY rather than DS_ACTIVE() if the device was marked
busy during DEVICE_ATTACH().
Reviewed by: kib
MFC after: 1 week
outside the range of valid file descriptors
PR: kern/164970
Submitted by: Peter Jeremy <peterjeremy@acm.org>
Reviewed by: jilles
Approved by: cperciva
MFC after: 1 week
The SA_PROC signal property indicated whether each signal number is directed
at a specific thread or at the process in general. However, that depends on
how the signal was generated and not on the signal number. SA_PROC was not
used.
Interface locks and descriptor locks are converted from mutex(9) to rwlock(9).
This greately improves performance: in most common case we need to acquire 1
reader lock instead of 2 mutexes.
- Remove filter(descriptor) (reader) lock in bpf_mtap[2]
This was suggested by glebius@. We protect filter by requesting interface
writer lock on filter change.
- Cover struct bpf_if under BPF_INTERNAL define. This permits including bpf.h
without including rwlock stuff. However, this is is temporary solution,
struct bpf_if should be made opaque for any external caller.
Found by: Dmitrij Tejblum <tejblum@yandex-team.ru>
Sponsored by: Yandex LLC
Reviewed by: glebius (previous version)
Reviewed by: silence on -net@
Approved by: (mentor)
MFC after: 3 weeks
a pair of records similar to syscall entry and return that a user can
use to determine how long page faults take. The new ktrace records are
enabled via the 'p' trace type, and are enabled in the default set of
trace points.
Reviewed by: kib
MFC after: 2 weeks
application destroys semaphore after sem_wait returns. Just enter
kernel to wake up sleeping threads, only update _has_waiters if
it is safe. While here, check if the value exceed SEM_VALUE_MAX and
return EOVERFLOW if this is true.
a mutex after a thread has unlocked it, it event writes data to the mutex
memory to clear contention bit, there is a race that other threads
can lock it and unlock it, then destroy it, so it should not write
data to the mutex memory if there isn't any waiter.
The new operation UMTX_OP_MUTEX_WAKE2 try to fix the problem. It
requires thread library to clear the lock word entirely, then
call the WAKE2 operation to check if there is any waiter in kernel,
and try to wake up a thread, if necessary, the contention bit is set again
by the operation. This also mitgates the chance that other threads find
the contention bit and try to enter kernel to compete with each other
to wake up sleeping thread, this is unnecessary. With this change, the
mutex owner is no longer holding the mutex until it reaches a point
where kernel umtx queue is locked, it releases the mutex as soon as
possible.
Performance is improved when the mutex is contensted heavily. On Intel
i3-2310M, the runtime of a benchmark program is reduced from 26.87 seconds
to 2.39 seconds, it even is better than UMTX_OP_MUTEX_WAKE which is
deprecated now. http://people.freebsd.org/~davidxu/bench/mutex_perf.c
via procstat(1) and fstat(1):
- Change shm file descriptors to track the pathname they are associated
with and add a shm_path() method to copy the path out to a caller-supplied
buffer.
- Use the fo_stat() method of shared memory objects and shm_path() to
export the path, mode, and size of a shared memory object via
struct kinfo_file.
- Add a struct shmstat to the libprocstat(3) interface along with a
procstat_get_shm_info() to export the mode and size of a shared memory
object.
- Change procstat to always print out the path for a given object if it
is valid.
- Teach fstat about shared memory objects and to display their path,
mode, and size.
MFC after: 2 weeks
New kernel events can be added at various location for sampling or counting.
This will for example allow easy system profiling whatever the processor is
with known tools like pmcstat(8).
Simultaneous usage of software PMC and hardware PMC is possible, for example
looking at the lock acquire failure, page fault while sampling on
instructions.
Sponsored by: NETASQ
MFC after: 1 month
loaded and unloaded, also have sdt.ko register callbacks with kern_sdt.c
that will be called when a newly loaded KLD module adds more probes or
a module with probes is unloaded.
This fixes two issues: first, if a module with SDT probes was loaded after
sdt.ko was loaded, those new probes would not be available in DTrace.
Second, if a module with SDT probes was unloaded while sdt.ko was loaded,
the kernel would panic the next time DTrace had cause to try and do
anything with the no-longer-existent probes.
This makes it possible to create SDT probes in KLD modules, although there
are still two caveats: first, any SDT probes in a KLD module must be part
of a DTrace provider that is defined in that module. At present DTrace
only destroys probes when the provider is destroyed, so you can still
panic the system if a KLD module creates new probes in a provider from a
different module(including the kernel) and then unload the the first module.
Second, the system will panic if you unload a module containing SDT probes
while there is an active D script that has enabled those probes.
MFC after: 1 month
Function acquired reader lock if needed.
Assert check for reader or writer lock (RA_LOCKED / RA_UNLOCKED)
- While here, add knlist_init_mtx.9 to MLINKS and fix some style(9) issues
Reviewed by: glebius
Approved by: ae(mentor)
MFC after: 2 weeks
kernel.
When access restrictions are added to a page table entry, we flush the
corresponding virtual address mapping from the TLB. In contrast, when
access restrictions are removed from a page table entry, we do not
flush the virtual address mapping from the TLB. This is exactly as
recommended in AMD's documentation. In effect, when access
restrictions are removed from a page table entry, AMD's MMUs will
transparently refresh a stale TLB entry. In short, this saves us from
having to perform potentially costly TLB flushes. In contrast,
Intel's MMUs are allowed to generate a spurious page fault based upon
the stale TLB entry. Usually, such spurious page faults are handled
by vm_fault() without incident. However, when we are executing
no-fault sections of the kernel, we are not allowed to execute
vm_fault(). This change introduces special-case handling for spurious
page faults that occur in no-fault sections of the kernel.
In collaboration with: kib
Tested by: gibbs (an earlier version)
I would also like to acknowledge Hiroki Sato's assistance in
diagnosing this problem.
MFC after: 1 week
inserted after the priority token thus cleaning up the output.
- Remove the needless double internal do_add_char function.
- Resolve a possible deadlock if interrupts are
disabled and getnanotime is called
Reviewed by: bde kmacy, avg, sbruno (various versions)
Approved by: cperciva
MFC after: 2 weeks
hardclock() tick should be run on every active CPU, or on only one.
On my tests, avoiding extra interrupts because of this on 8-CPU Core i7
system with HZ=10000 saves about 2% of performance. At this moment option
implemented only for global timers, as reprogramming per-CPU timers is
too expensive now to be compensated by this benefit, especially since we
still have to regularly run hardclock() on at least one active CPU to
update system uptime. For global timer it is quite trivial: timer runs
always, but we just skip IPIs to other CPUs when possible.
Option is enabled by default now, keeping previous behavior, as periodic
hardclock() calls are still used at least to implement setitimer(2) with
ITIMER_VIRTUAL and ITIMER_PROF arguments. But since default schedulers don't
depend on it since r232917, we are much more free to experiment with it.
MFC after: 1 month
with HZ rate through the sched_tick() calls from hardclock().
Potentially it can be used to improve precision, but now it is just minus
one more reason to call hardclock() for every HZ tick on every active CPU.
SCHED_4BSD never used sched_tick(), but keep it in place for now, as at
least SCHED_FBFS existing in patches out of the tree depends on it.
MFC after: 1 month
Instead of using 25MHz equality threshold, look for the nearest value when
handling dev.cpu.0.freq sysctl and for exact match when it is expected.
ACPI may report extra level with frequency 1MHz above the nominal to
control Intel Turbo Boost operation. It is not a bug, but feature:
dev.cpu.0.freq_levels: 2934/106000 2933/95000 2800/82000 ...
In this case value 2933 means 2.93GHz, but 2934 means 3.2-3.6GHz.
I've found that my Core i7-870 based system has Intel Turbo Boost disabled
by default and without this change it was absolutely invisible and hard
to control.
MFC after: 2 weeks
- Pass number of events to the statclock() and profclock() functions
same as to hardclock() before to not call them many times in a loop.
- Rename them into statclock_cnt() and profclock_cnt().
- Turn statclock() and profclock() into compatibility wrappers,
still needed for arm.
- Rename hardclock_anycpu() into hardclock_cnt() for unification.
MFC after: 1 week
the cached name used for KTR_SCHED traces when a thread's name changes.
This way KTR_SCHED traces (and thus schedgraph) will notice when a thread's
name changes, most commonly via execve().
MFC after: 2 weeks
fifo_iseof() condition, allowing the v_fifoinfo to be reset and freed
by fifo_cleanup().
Precalculate EOF at the places were fo_wgen is changed, and cache the
state in a new pipe state flag PIPE_SAMEWGEN.
Reported and tested by: bf
Submitted by: gianni
MFC after: 1 week (a backport)
does not fit into registers, declare that we do not support this case
using CTASSERT(), and remove endianess-unsafe code to split return value
into td_retval.
While there, change the style of the sysctl debug.iosize_max_clamp
definition.
Requested by: bde
MFC after: 3 weeks
using the o32 ABI. This mostly follows nwhitehorn's lead in implementing
COMPAT_FREEBSD32 on powerpc64.
o) Add a new type to the freebsd32 compat layer, time32_t, which is time_t in the
32-bit ABI being used. Since the MIPS port is relatively-new, even the 32-bit
ABIs use a 64-bit time_t.
o) Because time{spec,val}32 has the same size and layout as time{spec,val} on MIPS
with 32-bit compatibility, then, disable some code which assumes otherwise
wrongly when built for MIPS. A more general macro to check in this case would
seem like a good idea eventually. If someone adds support for using n32
userland with n64 kernels on MIPS, then they will have to add a variety of
flags related to each piece of the ABI that can vary. That's probably the
right time to generalize further.
o) Add MIPS to the list of architectures which use PAD64_REQUIRED in the
freebsd32 compat code. Probably this should be generalized at some point.
Reviewed by: gonzo
significantly. Upon investigation this was caused by name cache
misses for lookups of "..". For name cache entries for non-".."
directories, the cache entry serves double duty. It maps both the
named directory plus ".." for the parent of the directory. As such,
two ctime values (one for each of the directory and its parent) need
to be saved in the name cache entry.
This patch adds an entry for ctime of the parent directory to the
name cache. It also adds an additional uma zone for large entries
with this time value, in order to minimize memory wastage.
As well, it fixes a couple of cases where the mtime of the parent
directory was being saved instead of ctime for positive name cache
entries. With this patch, Lookup RPC counts return to values similar
to pre-r230394 kernels.
Reported by: bde
Discussed with: kib
Reviewed by: jhb
MFC after: 2 weeks
long for specifying a boundary constraint.
- Change bus_dma tags to use bus_addr_t instead of bus_size_t for boundary
constraints.
These allow boundary constraints to be fully expressed for cases where
sizeof(bus_addr_t) != sizeof(bus_size_t). Specifically, it allows a
driver to properly specify a 4GB boundary in a PAE kernel.
Note that this cannot be safely MFC'd without a lot of compat shims due
to KBI changes, so I do not intend to merge it.
Reviewed by: scottl
snapshots on UFS filesystems running with journaled soft updates.
This is the first of several bugs that need to be fixed before
removing the restriction added in -r230250 to prevent the use
of snapshots on filesystems running with journaled soft updates.
The deadlock occurs when holding the snapshot lock (snaplk)
and then trying to flush an inode via ffs_update(). We become
blocked by another process trying to flush a different inode
contained in the same inode block that we need. It holds the
inode block for which we are waiting locked. When it tries to
write the inode block, it gets blocked waiting for the our
snaplk when it calls ffs_copyonwrite() to see if the inode
block needs to be copied in our snapshot.
The most obvious place that this deadlock arises is in the
ffs_copyonwrite() routine when it updates critical metadata
in a snapshot and tries to write it out before proceeding.
The fix here is to write the data and indirect block pointer
for the snapshot, but to skip the call to ffs_update() to
write the snapshot inode. To ensure that we will never have
to update a pointer in the inode itself, the ffs_snapshot()
routine that creates the snapshot has to ensure that all the
direct blocks are allocated as part of the creation of the
snapshot.
A less obvious place that this deadlock occurs is when we hold
the snaplk because we are deleting a snapshot. In the course of
doing the deletion, we need to allocate various soft update
dependency structures and allocate some journal space. If we
hit a resource limit while doing this we decrease the resources
in use by flushing out an existing dirty file to get it to give
up the soft dependency resources that it holds. The flush can
cause an ffs_update() to be done on the inode for the file that
we have selected to flush resulting in the same deadlock as
described above when the inode that we have chosen to flush
resides in the same inode block as the snapshot inode that we hold.
The fix is to defer cleaning up any time that the inode on which
we are operating is a snapshot.
Help and review by: Jeff Roberson
Tested by: Peter Holm
MFC (to 9 only) after: 2 weeks
operations for setting and accessing vnode's v_socket field.
The operations are necessary to implement proper unix socket handling
on layered file systems like nullfs(5).
This change fixes the long standing issue with nullfs(5) being in that
unix sockets did not work between lower and upper layers: if we bound
to a socket on the lower layer we could connect only to the lower
path; if we bound to the upper layer we could connect only to the
upper path. The new behavior is one can connect to both the lower and
the upper paths regardless what layer path one binds to.
PR: kern/51583, kern/159663
Suggested by: kib
Reviewed by: arch
MFC after: 2 weeks
following clang warning:
sys/kern/sys_pipe.c:1556:10: error: promoted type 'int' of K&R function parameter is not compatible with the parameter type 'mode_t'
(aka 'unsigned short') declared in a previous prototype [-Werror]
mode_t mode;
^
sys/kern/sys_pipe.c:155:19: note: previous declaration is here
static fo_chmod_t pipe_chmod;
^
not get syscall exit notification until the child performed exec of
exit. Swap the order of doing ptracestop() and waiting for P_PPWAIT
clearing, by postponing the wait into syscallret after ptracestop()
notification is done.
Reported, tested and reviewed by: Dmitry Mikulin <dmitrym juniper net>
MFC after: 2 weeks
Descriptions are specific to drivers and we don't change drivers on attached
devices. This fixes a few places where we were not clearing the description
when detaching a driver (e.g. with device_attach() failed). While here, fix
a few other nits:
- Remove spurious call to remove a device's driver from
devclass_driver_deleted(). device_detach() removes it already.
- Fix a typo.
- In sched_pickcpu() be more careful taking previous CPU on SMT systems.
Do it only if all other logical CPUs of that physical one are idle to avoid
extra resource sharing.
- In sched_pickcpu() change general logic of CPU selection. First
look for idle CPU, sharing last level cache with previously used one,
skipping SMT CPU groups. If none found, search all CPUs for the least loaded
one, where the thread with its priority can run now. If none found, search
just for the least loaded CPU.
- Make cpu_search() compare lowest/highest CPU load when comparing CPU
groups with equal load. That allows to differentiate 1+1 and 2+0 loads.
- Make cpu_search() to prefer specified (previous) CPU or group if load
is equal. This improves cache affinity for more complicated topologies.
- Randomize CPU selection if above factors are equal. Previous code tend
to prefer CPUs with lower IDs, causing unneeded collisions.
- Rework periodic balancer in sched_balance_group(). With cpu_search()
more intelligent now, make balansing process flat, removing recursion
over the topology tree. That fixes double swap problem and makes load
distribution more even and predictable.
All together this gives 10-15% performance improvement in many tests on
CPUs with SMT, such as Core i7, for number of threads is less then number
of logical CPUs. In some tests it also gives positive effect to systems
without SMT.
Reviewed by: jeff
Tested by: flo, hackers@
MFC after: 1 month
Sponsored by: iXsystems, Inc.
Uftdi(4) examines (c_iflag & (IXON|IXOFF)) to control hw XON-XOFF support.
This is obviously no good, if changes to those bits are not communicated
down the stack.
allow.mount.zfs:
allow mounting the zfs filesystem inside a jail
This way the permssions for mounting all current VFCF_JAIL filesystems
inside a jail are controlled wia allow.mount.* jail parameters.
Update sysctl descriptions.
Update jail(8) and zfs(8) manpages.
TODO: document the connection of allow.mount.* and VFCF_JAIL for kernel
developers
MFC after: 10 days
socket protocol number. This is useful since the socket type can
be implemented by different protocols in the same protocol family,
e.g. SOCK_STREAM may be provided by both TCP and SCTP.
Submitted by: Jukka A. Ukkonen <jau iki fi>
PR: kern/162352
Discussed with: bz
Reviewed by: glebius
MFC after: 2 weeks
unp->unp_vnode pointer to detect if there is a vnode associated with
(binded to) this socket and does necessary cleanup if there is.
The issue is that after forced unmount this check may be too late as
the unp_vnode is reclaimed and the reference is stale.
To fix this provide a helper function that is called on a socket vnode
reclamation to do necessary cleanup.
Pointed by: kib
Reviewed by: kib
MFC after: 2 weeks
according to POSIX document, the clock ID may be dynamically allocated,
it unlikely will be in 64K forever. To make it future compatible, we
pack all timeout information into a new structure called _umtx_time, and
use fourth argument as a size indication, a zero means it is old code
using timespec as timeout value, but the new structure also includes flags
and a clock ID, so the size argument is different than before, and it is
non-zero. With this change, it is possible that a thread can sleep
on any supported clock, though current kernel code does not have such a
POSIX clock driver system.
a new jail parameter node with the following parameters:
allow.mount.devfs:
allow mounting the devfs filesystem inside a jail
allow.mount.nullfs:
allow mounting the nullfs filesystem inside a jail
Both parameters are disabled by default (equals the behavior before
devfs and nullfs in jails). Administrators have to explicitly allow
mounting devfs and nullfs for each jail. The value "-1" of the
devfs_ruleset parameter is removed in favor of the new allow setting.
Reviewed by: jamie
Suggested by: pjd
MFC after: 2 weeks
to the debugger. When reparenting for debugging, keep the child in
the new orphan list of old parent. When looping over the children in
kern_wait(), iterate over both children list and orphan list to search
for the process by pid.
Submitted by: Dmitry Mikulin <dmitrym juniper.net>
MFC after: 2 weeks
UMTX_OP_WAIT. Upper 16bits is enough to hold a clock id, and lower
16bits is used to pass flags. The change saves a clock_gettime() syscall
from libthr.
Add the sysctl debug.iosize_max_clamp, enabled by default. Setting the
sysctl to zero allows to perform the SSIZE_MAX-sized i/o requests from
the usermode.
Discussed with: bde, das (previous versions)
MFC after: 1 month
Vnode-backed mappings cannot be put into the kernel map, since it is a
system map.
Use exec_map for transient mappings, and remove the mappings with
kmem_free_wakeup() to notify the waiters on available map space.
Do not map the whole executable into KVA at all to copy it out into
usermode. Directly use vn_rdwr() for the case of not page aligned
binary.
There is one place left where the potentially unbounded amount of data
is mapped into exec_map, namely, in the COFF image activator
enumeration of the needed shared libraries.
Reviewed by: alc
MFC after: 2 weeks
messages were printed.
This can be enabled with the kern.msgbuf_show_timestamp sysctl
PR: kern/161553
Reviewed by: avg
Submitted by: Arnaud Lacombe <lacombar@gmail.com>
Approved by: cperciva
MFC after: 1 month
A new jail(8) option "devfs_ruleset" defines the ruleset enforcement for
mounting devfs inside jails. A value of -1 disables mounting devfs in
jails, a value of zero means no restrictions. Nested jails can only
have mounting devfs disabled or inherit parent's enforcement as jails are
not allowed to view or manipulate devfs(8) rules.
Utilizes new functions introduced in r231265.
Reviewed by: jamie
MFC after: 1 month
mnt_noasync counter to temporary remove MNTK_ASYNC mount option, which
is needed to guarantee a synchronous completion of the initiated i/o
before syscall or VOP return. Global removal of MNTK_ASYNC option is
harmful because not only i/o started from corresponding thread becomes
synchronous, but all i/o is synchronous on the filesystem which is
initiated during sync(2) or syncer activity.
Instead of removing MNTK_ASYNC from mnt_kern_flag, provide a local
thread flag to disable async i/o for current thread only. Use the
opportunity to move DOINGASYNC() macro into sys/vnode.h and
consistently use it through places which tested for MNTK_ASYNC.
Some testing demonstrated 60-70% improvements in run time for the
metadata-intensive operations on async-mounted UFS volumes, but still
with great deviation due to other reasons.
Reviewed by: mckusick
Tested by: scottl
MFC after: 2 weeks
set on the new thread. This prevents the thread from inadvertently
inheriting affinity from a random sibling.
Submitted by: attilio
Tested by: pho
MFC after: 1 week
it is possible that a single AIO event will be reported to multiple
threads, it is not threading friendly, and the existing API can not
control this behavior.
Allocate a kevent flags field sigev_notify_kevent_flags for AIO event
notification in sigevent, and allow user to pass EV_CLEAR, EV_DISPATCH
or EV_ONESHOT to AIO kernel code, user can control whether the event
should be cleared once it is retrieved by a thread. This change should
be comptaible with existing application, because the field should have
already been zero-filled, and no additional action will be taken by
kernel.
PR: kern/156567
about new child not only when doing PT_TO_SCX, but also for PT_CONTINUE.
If TDB_FORK flag is set, always issue a stop, the same as is done for
TDB_EXEC.
Reported by: Dmitry Mikulin <dmitrym juniper net>
MFC after: 1 week
that instead of using direct I/O it allows read-ahead similar to
POSIX_FADV_NORMAL, but invokes VOP_ADVISE(POSIX_FADV_DONTNEED) after the
read(2) has completed to purge just-read data. The write(2) path continues
to use direct I/O for POSIX_FADV_NOREUSE for now. Note that NOREUSE works
optimally if an application reads and writes full fs blocks.
that we have the lock now. This cleans up a locking panic ASSERT when
knlist_empty is called without a lock when INVARIANTS etc. are turned.
Reviewed by: kib jhb
MFC after: 1 week
primitives by breaking stop_scheduler into a per-thread variable.
Also, store the new td_stopsched very close to td_*locks members as
they will be accessed mostly in the same codepaths as td_stopsched and
this results in avoiding a further cache-line pollution, possibly.
STOP_SCHEDULER() was pondered to use a new 'thread' argument, in order to
take advantage of already cached curthread, but in the end there should
not really be a performance benefit, while introducing a KPI breakage.
In collabouration with: flo
Reviewed by: avg
MFC after: 3 months (or never)
X-MFC: r228424
share/man/man4/Makefile,
share/man/man4/xnb.4,
sys/dev/xen/netback/netback.c,
sys/dev/xen/netback/netback_unit_tests.c:
Rewrote the netback driver for xen to attach properly via newbus
and work properly in both HVM and PVM mode (only HVM is tested).
Works with the in-tree FreeBSD netfront driver or the Windows
netfront driver from SuSE. Has not been extensively tested with
a Linux netfront driver. Does not implement LRO, TSO, or
polling. Includes unit tests that may be run through sysctl
after compiling with XNB_DEBUG defined.
sys/dev/xen/blkback/blkback.c,
sys/xen/interface/io/netif.h:
Comment elaboration.
sys/kern/uipc_mbuf.c:
Fix page fault in kernel mode when calling m_print() on a
null mbuf. Since m_print() is only used for debugging, there
are no performance concerns for extra error checking code.
sys/kern/subr_scanf.c:
Add the "hh" and "ll" width specifiers from C99 to scanf().
A few callers were already using "ll" even though scanf()
was handling it as "l".
Submitted by: Alan Somers <alans@spectralogic.com>
Submitted by: John Suykerbuyk <johns@spectralogic.com>
Sponsored by: Spectra Logic
MFC after: 1 week
Reviewed by: ken
casted types: to ssize_t in filesystem code and to
int in buf code, thus supplying a negative argument
leads to kernel panic later. To fix that check user
supplied argument in the beginning of syscall.
Submitted by: Maxim Dounin <mdounin mdounin.ru>, maxim@
Unmounts do vfs_msync() before calling VFS_UNMOUNT(), but there is
still a race allowing a process to dirty pages after msync
finished. Remounts rw->ro just left dirty pages in system.
Reviewed by: alc, tegge (long time ago)
Tested by: pho
MFC after: 2 weeks
appropriate timestamps. Restore the assertions which verify that
NCF_TS is set when timestamp is asked for.
Reviewed by: jhb (previous version)
MFC after: 2 weeks
consistently, creating some namecache entries without NCF_TS flag.
This causes panic due to failed assertion.
As a temporal relief, remove the assert. Return epoch timestamp for
the entries without timestamp if asked.
While there, consolidate the code which returns timestamps, into a
helper cache_out_ts().
Discussed with: jhb
MFC after: 2 weeks
- retrive only one, specified limit for a process, not the whole
array, as it was previously (the sysctl has been added recently and
has not been backported to stable yet, so this change is ok);
- allow to set a resource limit for another process.
Submitted by: Andrey Zonov <andrey at zonov.org>
Discussed with: kib
Reviewed by: kib
MFC after: 2 weeks
provide struct namecache_ts which is the old struct namecache. Only
allocate struct namecache_ts if non-null struct timespec *tsp was
passed to cache_enter_time, otherwise use struct namecache.
Change struct namecache allocation and deallocation macros into static
functions, since logic becomes somewhat twisty. Provide accessor for
the nc_name member of struct namecache to hide difference between
struct namecache and namecache_ts.
The aim of the change is to not waste 20 bytes per small namecache
entry.
Reviewed by: jhb
MFC after: 2 weeks
X-MFC-note: after r230394
entries on one client when a directory was renamed on another client. The
root cause for the stale entry being trusted is that each per-vnode nfsnode
structure has a single 'n_ctime' timestamp used to validate positive name
cache entries. However, if there are multiple entries for a single vnode,
they all share a single timestamp. To fix this, extend the name cache
to allow filesystems to optionally store a timestamp value in each name
cache entry. The NFS clients now fetch the timestamp associated with
each name cache entry and use that to validate cache hits instead of the
timestamps previously stored in the nfsnode. Another part of the fix is
that the NFS clients now use timestamps from the post-op attributes of
RPCs when adding name cache entries rather than pulling the timestamps out
of the file's attribute cache. The latter is subject to races with other
lookups updating the attribute cache concurrently. Some more details:
- Add a variant of nfsm_postop_attr() to the old NFS client that can return
a vattr structure with a copy of the post-op attributes.
- Handle lookups of "." as a special case in the NFS clients since the name
cache does not store name cache entries for ".", so we cannot get a
useful timestamp. It didn't really make much sense to recheck the
attributes on the the directory to validate the namecache hit for "."
anyway.
- ABI compat shims for the name cache routines are present in this commit
so that it is safe to MFC.
MFC after: 2 weeks
to an OBJT_VNODE-specific field of the vm object. The same
information can be just as easily obtained from the struct vattr that
is in struct image_params if the latter is passed to
elf*_load_section(). Moreover, by replacing the vmspace and vm
object parameters to elf*_load_section() with a struct image_params
parameter, we actually reduce the size of the object code.
In collaboration with: kib
to read strings completely to know the actual size.
As a side effect it fixes the issue with kern.proc.args and kern.proc.env
sysctls, which didn't return the size of available data when calling
sysctl(3) with the NULL argument for oldp.
Note, in get_ps_strings(), which does actual work for proc_getargv() and
proc_getenvv(), we still have a safety limit on the size of data read in
case of a corrupted procces stack.
Suggested by: kib
MFC after: 3 days
This function updates path string to vnode's full global path and checks
the size of the new path string against the pathlen argument.
In vfs_domount(), sys_unmount() and kern_jail_set() this new function
is used to update the supplied path argument to the respective global path.
Unbreaks jailed zfs(8) with enforce_statfs set to 1.
Reviewed by: kib
MFC after: 1 month
On amd64, link_elf_obj.c must specify KERNBASE rather than
VM_MIN_KERNEL_ADDRESS to vm_map_find() because kernel loadable
modules must be mapped for execution in the same upper region
of the kernel map as the kernel code and data segments.
For MIPS32 KERNBASE lies below KVA area (it's less than
VM_MIN_KERNEL_ADDRESS) so basically vm_map_find got whole
KVA to look through. On MIPS64 it's not the case because
KERNBASE is set to the very end of XKSEG, well out of KVA
bounds, so vm_map_find always fails. We should use
VM_MIN_KERNEL_ADDRESS as a base for vm_map_find.
Details obtained from: alc@
The vfs_busy() is after covered vnode lock in the global lock order, but
since quotaon() does recursive VFS call to open quota file, we usually
end up locking covered vnode after mp is busied in sys_quotactl().
Change the interface of VFS_QUOTACTL(), requiring that mp was unbusied
by fs code, and do not try to pick up vfs_busy() reference in ufs quotaon,
esp. if vfs_busy cannot succeed due to unmount being performed.
Reported and tested by: pho
MFC after: 1 week
operation on POSIX shared memory objects and tmpfs. Previously, neither of
these modules correctly handled the case in which the new size of the object
or file was not a multiple of the page size. Specifically, they did not
handle partial page truncation of data stored on swap. As a result, stale
data might later be returned to an application.
Interestingly, a data inconsistency was less likely to occur under tmpfs
than POSIX shared memory objects. The reason being that a different mistake
by the tmpfs truncation operation helped avoid a data inconsistency. If the
data was still resident in memory in a PG_CACHED page, then the tmpfs
truncation operation would reactivate that page, zero the truncated portion,
and leave the page pinned in memory. More precisely, the benevolent error
was that the truncation operation didn't add the reactivated page to any of
the paging queues, effectively pinning the page. This page would remain
pinned until the file was destroyed or the page was read or written. With
this change, the page is now added to the inactive queue.
Discussed with: jhb
Reviewed by: kib (an earlier version)
MFC after: 3 weeks
The wrong structure happened to work since the only argument used was
the vnode which is in the same place in both VOP_SETATTR() and the two
extattr VOPs.
MFC after: 3 days
