truncation, immediately queue the page for asynchronous laundering rather
than making the page pass through inactive queue first.
Reviewed by: kib, markj
Changes include modifications in kernel crash dump routines, dumpon(8) and
savecore(8). A new tool called decryptcore(8) was added.
A new DIOCSKERNELDUMP I/O control was added to send a kernel crash dump
configuration in the diocskerneldump_arg structure to the kernel.
The old DIOCSKERNELDUMP I/O control was renamed to DIOCSKERNELDUMP_FREEBSD11 for
backward ABI compatibility.
dumpon(8) generates an one-time random symmetric key and encrypts it using
an RSA public key in capability mode. Currently only AES-256-CBC is supported
but EKCD was designed to implement support for other algorithms in the future.
The public key is chosen using the -k flag. The dumpon rc(8) script can do this
automatically during startup using the dumppubkey rc.conf(5) variable. Once the
keys are calculated dumpon sends them to the kernel via DIOCSKERNELDUMP I/O
control.
When the kernel receives the DIOCSKERNELDUMP I/O control it generates a random
IV and sets up the key schedule for the specified algorithm. Each time the
kernel tries to write a crash dump to the dump device, the IV is replaced by
a SHA-256 hash of the previous value. This is intended to make a possible
differential cryptanalysis harder since it is possible to write multiple crash
dumps without reboot by repeating the following commands:
# sysctl debug.kdb.enter=1
db> call doadump(0)
db> continue
# savecore
A kernel dump key consists of an algorithm identifier, an IV and an encrypted
symmetric key. The kernel dump key size is included in a kernel dump header.
The size is an unsigned 32-bit integer and it is aligned to a block size.
The header structure has 512 bytes to match the block size so it was required to
make a panic string 4 bytes shorter to add a new field to the header structure.
If the kernel dump key size in the header is nonzero it is assumed that the
kernel dump key is placed after the first header on the dump device and the core
dump is encrypted.
Separate functions were implemented to write the kernel dump header and the
kernel dump key as they need to be unencrypted. The dump_write function encrypts
data if the kernel was compiled with the EKCD option. Encrypted kernel textdumps
are not supported due to the way they are constructed which makes it impossible
to use the CBC mode for encryption. It should be also noted that textdumps don't
contain sensitive data by design as a user decides what information should be
dumped.
savecore(8) writes the kernel dump key to a key.# file if its size in the header
is nonzero. # is the number of the current core dump.
decryptcore(8) decrypts the core dump using a private RSA key and the kernel
dump key. This is performed by a child process in capability mode.
If the decryption was not successful the parent process removes a partially
decrypted core dump.
Description on how to encrypt crash dumps was added to the decryptcore(8),
dumpon(8), rc.conf(5) and savecore(8) manual pages.
EKCD was tested on amd64 using bhyve and i386, mipsel and sparc64 using QEMU.
The feature still has to be tested on arm and arm64 as it wasn't possible to run
FreeBSD due to the problems with QEMU emulation and lack of hardware.
Designed by: def, pjd
Reviewed by: cem, oshogbo, pjd
Partial review: delphij, emaste, jhb, kib
Approved by: pjd (mentor)
Differential Revision: https://reviews.freebsd.org/D4712
kinfo_proc::ki_tdname is three characters shorter than
thread::td_name. Add a ki_moretdname field for these three
extra characters. Add the new field to kinfo_proc32, as well.
Update all in-tree consumers to read the new field and assemble
the full name, except for lldb's HostThreadFreeBSD.cpp, which
I will handle separately. Bump __FreeBSD_version.
Reviewed by: kib
MFC after: 1 week
Relnotes: yes
Sponsored by: Dell EMC
Differential Revision: https://reviews.freebsd.org/D8722
wait(2).
- Do not acquire the process spinlock if neither WTRAPPED nor WUNTRACED
options were passed [1].
- Extract the code to report alive process into a new helper
report_alive_proc() and use it for trapped, stopped and continued
childrens.
Note that the process spinlock is required around the WTRAPPED and
WUNTRACED tests, because P_STOPPED_TRACE and P_STOPPED_SIG flags are
set before other threads are stopped at the suspension point, and that
threads increment p_suspcount while owning only the process spinlock,
the process lock is dropped by them. If the spinlock is not taken for
tests, the syscall thread might miss both p_suspcount increment and
wakeup in wakeup in thread_suspend_switch().
Based on the submission by: mjg [1]
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Instead of failing with ENAMETOOLONG, which is swallowed by
pthread_set_name_np() anyway, truncate the given name to MAXCOMLEN+1
bytes. This is more likely what the user wants, and saves the
caller from truncating it before the call (which was the only
recourse).
Polish pthread_set_name_np(3) and add a .Xr to thr_set_name(2)
so the user might find the documentation for this behavior.
Reviewed by: jilles
MFC after: 3 days
Sponsored by: Dell EMC
Since the vnode is only expected to be shared locked, we can save a
little overhead by only pretending we are locking in the first place.
Reviewed by: kib
Tested by: pho
As of r234483, vnode deactivation causes non-VPO_NOSYNC pages to be
laundered. This behaviour has two problems:
1. Dirty VPO_NOSYNC pages must be laundered before the vnode can be
reclaimed, and this work may be unfairly deferred to the vnlru process
or an unrelated application when the system is under vnode pressure.
2. Deactivation of a vnode with dirty VPO_NOSYNC pages requires a scan of
the corresponding VM object's memq for non-VPO_NOSYNC dirty pages; if
the laundry thread needs to launder pages from an unreferenced such
vnode, it will reactivate and deactivate the vnode with each laundering,
potentially resulting in a large number of expensive scans.
Therefore, ensure that all dirty pages are laundered upon deactivation,
i.e., when all maps of the vnode are removed and all references are
released.
Reviewed by: alc, kib
MFC after: 1 month
Differential Revision: https://reviews.freebsd.org/D8641
The callout subsystem already handles early callouts and schedules
the first clock interrupt appropriately based on the currently pending
callouts. The one nit to fix was that callouts scheduled via C_HARDCLOCK
during early boot could fire too early once timers were enabled as the
per-CPU base time is always zero until timers are initialized. The change
in callout_when() handles this case by using the current uptime as the
base time of the callout during bootup if the per-CPU base time is zero.
Reviewed by: kib
MFC after: 2 weeks
Sponsored by: Netflix
The size can be changed by side effect of modifying kern.maxvnodes.
Since numbucketlocks was not modified, setting a sufficiently low value
would give more locks than actual buckets, which would then lead to
corruption.
Force the number of buckets to be not smaller.
Note this should not matter for real world cases.
Reported and tested by: pho
The swap pager enqueues laundered pages near the head of the inactive queue
to avoid another trip through LRU before reclamation. This change adds
support for this behaviour to the vnode pager and makes use of it in UFS and
ext2fs. Some ioflag handling is consolidated into a common subroutine so
that this support can be easily extended to other filesystems which make use
of the buffer cache. No changes are needed for ZFS since its putpages
routine always undirties the pages before returning, and the laundry
thread requeues the pages appropriately in this case.
Reviewed by: alc, kib
Differential Revision: https://reviews.freebsd.org/D8589
This avoids the time-warp after kthreads have started running and the
required fixup to td_slptick and td_blktick in the EARLY_AP_STARTUP
case. Now, 'ticks' is initialized before any kthreads are created or
any context switches are performed.
Tested by: gavin
MFC after: 2 weeks
Sponsored by: Netflix
always audit the file-descriptor number and vnode information for all
fnctl(2) commands, not just locking-related ones. This was likely an
oversight in the original adaptation of this code from XNU.
MFC after: 3 days
Sponsored by: DARPA, AFRL
do any speculations about readahead, and use exactly the amount of readahead
specified by user. E.g. setting SF_FLAGS(0, SF_USER_READAHEAD) will guarantee
that no readahead at all will be performed.
sendfile_swapin() loop works this way:
- Find first invalid page in the request.
- Do vm_pager_has_page() and get count of pages, that can be taken in
single I/O.
- Trim valid pages from the end of the request.
- Cycle through the request and substitute to bogus_page all valid
pages that are in the middle of the request.
- After I/O launched (pager copies array of pages into buf(9), it
is important to restore proper page pointers with help vm_page_lookup().
Count bogus pages used and report them in sendfile stats.
not remove user-space visible fields from vm_cnt or all of the references to
cached pages from comments. Those changes will come later.)
Reviewed by: kib, markj
Tested by: pho
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D8497
The negative list shrinker can demote an entry with only hotlist + neglist
locks held. On the other hand entry removal possibly sets the NCF_DVDROP
without aformentioned locks held prior to detaching it from the respective
netlist., which can lose the update made by the shrinker.
Reported and tested by: truckman
Although the higher end MIPS hardware handles cache aliasing issues in
hardware, the older cores (r4k, etc) and some compile versions of the
newer cores (mips24k, mips34k, mips74k) don't have this feature.
This means we end up with some very unfortunate behaviour that was
made very obvious by some recent changes to the FFS pager by kib.
So, flip this off until we get our MIPS pmap/cache code upgraded to
handle aliased pages in software.
Discussed with: kib, bsdimp, juli
The default (512) wastes quite a bit of space which doesn't really buy
us much on highly embedded systems which don't take a lot of locks in
parallel.
This makes it at least build time configurable so people can experiment.
Currently mount update keeps vfs_busy(9) reference on the mount point
during MNT_UPDATE VFS_MOUNT() vfsops call. This already provides the
exclusion, but is problematic for filesystems which need to perform
namei(9) during VFS_MOUNT(MNT_UPDATE) operations, e.g. to refresh
mnt_from path, because namei(9) must not be called while the
vfs_busy(9) reference is owned.
Check for MNT_UPDATE flag before setting MNTK_UNMOUNT, and for
MNTK_UNMOUNT before entering innards of vfs_domount_update(), failing
syscalls with EBUSY if conflict is detected. Keep vfs_busy(9)
reference around VFS_MOUNT(MNT_UPDATE) calls still to not change VFS
KPI.
In the update path in ffs_mount(), drop vfs_busy() reference around
namei(), which is now safe due to unmount never executing in parallel
with VFS_MOUNT(MNT_UPDATE), and which avoids the deadlock.
Reported and tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
- Send IPI wakeups once SMP is started even if cold is true.
- Permit preemptions when cold is true.
These changes are needed for EARLY_AP_STARTUP.
MFC after: 2 weeks
Sponsored by: Netflix
The other CPU might resume and see a still-empty runq and go back to
sleep before sched_add() adds the thread to the runq. This results
in a lost wakeup and a potential hang if the system is otherwise
completely idle.
The race originated due to a micro-optimization (my fault) in 4BSD in
that it avoided putting a thread on the run queue if the scheduler was
going to preempt to the new thread. To avoid complexity while fixing
this race, just drop this optimization. 4BSD now always sets the
"owepreempt" flag when a preemption is warranted and defers the actual
preemption to the thread_unlock of the caller the same as ULE.
MFC after: 2 weeks
Sponsored by: Netflix
Pass current thread credentials instead of NOCRED.
Only allow unmapped buffers for filesystem which proclaimed the support.
For all filesystems which currently use buffer pager (UFS, msdosfs and
cd9660), the changes are effectively nop.
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
vp->v_mount->mnt_vnodecovered unlocked. This allowed unmount to race.
Lock vnode after we noticed the VV_ROOT flag. See comments for
explanation why unlocked check for the flag is considered safe.
Reported and tested by: avg
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
we never try to sleep while the thread is on a sleepqueue.
Reviewed by: jhb
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D8422
If dotdot lookup does not escape from the file descriptor passed as
the lookup root, we can allow the component traversal. Track the
directories traversed, and check the result of dotdot lookup against
the recorded list of the directory vnodes.
Dotdot lookups are enabled by sysctl vfs.lookup_cap_dotdot, currently
disabled by default until more verification of the approach is done.
Disallow non-local filesystems for dotdot, since remote server might
conspire with the local process to allow it to escape the namespace.
This might be too cautious, provide the knob
vfs.lookup_cap_dotdot_nonlocal to override as well.
Idea by: rwatson
Discussed with: emaste, jonathan, rwatson
Reviewed by: mjg (previous version)
Tested by: pho (previous version)
Sponsored by: The FreeBSD Foundation
MFC after: 2 week
Differential revision: https://reviews.freebsd.org/D8110
process of being unmounted. Previously it would skip them, even if the
unmount eventually failed eg due to the filesystem being busy.
This behaviour broke autounmountd(8) - if you tried to manually unmount
a mounted filesystem, using 'automount -u', and the autounmountd attempted
to refresh the filesystem list in that very moment, it would conclude that
the filesystem got unmounted and not try to unmount it afterwards.
Reviewed by: kib@
Tested by: pho@
MFC after: 1 month
Differential Revision: https://reviews.freebsd.org/D8030
Upstream the BUF_TRACKING and FULL_BUF_TRACKING buffer debugging code.
This can be handy in tracking down what code touched hung bios and bufs
last. The full history is especially useful, but adds enough bloat that
it shouldn't be enabled in release builds.
Function names (or arbitrary string constants) are tracked in a
fixed-size ring in bufs. Bios gain a pointer to the upper buf for
tracking. SCSI CCBs gain a pointer to the upper bio for tracking.
Reviewed by: markj
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D8366
not a bitfield. For the intended usage - being passed either MNT_WAIT,
or MNT_NOWAIT - this shouldn't introduce any changes in behaviour.
Reviewed by: jhb@
MFC after: 1 month
Differential Revision: https://reviews.freebsd.org/D8373
which also use buffer cache.
Most important addition to the code is the handling of filesystems
where the block size is less than the machine page size, which might
require reading several buffers to validate single page.
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
On several Intel chipsets, diagnostic NMIs sent from BMC or NMIs
reporting hardware errors are broadcasted to all CPUs.
When kernel is configured to enter kdb on NMI, the outcome is
problematic, because each CPU tries to enter kdb. All CPUs are
executing NMI handlers, which set the latches disabling the nested NMI
delivery; this means that stop_cpus_hard(), used by kdb_enter() to
stop other cpus by broadcasting IPI_STOP_HARD NMI, cannot work. One
indication of this is the harmless but annoying diagnostic "timeout
stopping cpus".
Much more harming behaviour is that because all CPUs try to enter kdb,
and if ddb is used as debugger, all CPUs issue prompt on console and
race for the input, not to mention the simultaneous use of the ddb
shared state.
Try to fix this by introducing a pseudo-lock for simultaneous attempts
to handle NMIs. If one core happens to enter NMI trap handler, other
cores see it and simulate reception of the IPI_STOP_HARD. More,
generic_stop_cpus() avoids sending IPI_STOP_HARD and avoids waiting
for the acknowledgement, relying on the nmi handler on other cores
suspending and then restarting the CPU.
Since it is impossible to detect at runtime whether some stray NMI is
broadcast or unicast, add a knob for administrator (really developer)
to configure debugging NMI handling mode.
The updated patch was debugged with the help from Andrey Gapon (avg)
and discussed with him.
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Differential revision: https://reviews.freebsd.org/D8249
native fueword64(9) still, use proper type for local where fuword64()
result is stored.
Note that fueword64() is unused in the tree.
Submitted by: Chunhui He <hchunhui@mail.ustc.edu.cn>
PR: 212520
MFC after: 1 week
In sendit(), if mp->msg_control is present, then in sockargs() we are
allocating mbuf to store mp->msg_control. Later in kern_sendit(), call
to getsock_cap(), will check validity of file pointer passed, if this
fails EBADF is returned but mbuf allocated in sockargs() is not freed.
Made code changes to free the same.
Since freeing control mbuf in sendit() after checking (control != NULL)
may lead to double freeing of control mbuf in sendit(), we can free
control mbuf in kern_sendit() if there are any errors in the routine.
Submitted by: Lohith Bellad <lohith.bellad@me.com>
Reviewed by: glebius
MFC after: 3 weeks
Differential Revision: https://reviews.freebsd.org/D8152
If no negative entry is found on the last list, the ncp pointer will be
left uninitialized and a non-null value will make the function assume an
entry was found.
Fix the problem by initializing to NULL on entry.
Reported by: glebius
This splits the ncneg_mtx lock while preserving the hit ratio at least
during buildworld.
Create N dedicated lists for new negative entries.
Entries with at least one hit get promoted to the hot list, where they
get requeued every M hits.
Shrinking demotes one hot entry and performs a round-robin shrinking of
regular lists.
Reviewed by: kib
ref: 535865d02c
Fix cpu assignment by assuring stride is non-zero, assert that all tasks
have a valid taskqueue.
ref: db39817623
Start cpu assignment from zero.
ref: d99d39b6b6
Submitted by: mmacy@nextbsd.org
In r10905 and r10906 makesyscalls was modified to avoid emitting a
literal $Id$ string in the generated file, with:
gsub("[$]Id: ", "", $0)
gsub(" [$]", "", $0)
Then r11294 added some functionality and also tried to address the $Id$
problem in a different way, by removing every $:
sed -e 's/\$//g ...
This rendered the gsub infeffective. The gsub was later updated to
track the $Id$ -> $FreeBSD$ switch, even though it did not do anything.
Revert the addition of the s/\$//g, and update the gsub to keep the
resulting format the same.
Discussed with: bde
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
When detaching device trees parent devices must be detached prior to
detaching its children. This is because parent devices can have
pointers to the child devices in their softcs which are not
invalidated by device_delete_child(). This can cause use after free
issues and panic().
Device drivers implementing trees, must ensure its detach function
detaches or deletes all its children before returning.
While at it remove now redundant device_detach() calls before
device_delete_child() and device_delete_children(), mostly in
the USB controller drivers.
Tested by: Jan Henrik Sylvester <me@janh.de>
Reviewed by: jhb
Differential Revision: https://reviews.freebsd.org/D8070
MFC after: 2 weeks
Suppose that we have an exclusively busy page, and a thread which can
accept shared-busy page. In this case, typical code waiting for the
page xbusy state to pass is
again:
VM_OBJECT_WLOCK(object);
...
if (vm_page_xbusied(m)) {
vm_page_lock(m);
VM_OBJECT_WUNLOCK(object); <---1
vm_page_busy_sleep(p, "vmopax");
goto again;
}
Suppose that the xbusy state owner locked the object, unbusied the
page and unlocked the object after we are at the line [1], but before we
executed the load of the busy_lock word in vm_page_busy_sleep(). If it
happens that there is still no waiters recorded for the busy state,
the xbusy owner did not acquired the page lock, so it proceeded.
More, suppose that some other thread happen to share-busy the page
after xbusy state was relinquished but before the m->busy_lock is read
in vm_page_busy_sleep(). Again, that thread only needs vm_object lock
to proceed. Then, vm_page_busy_sleep() reads busy_lock value equal to
the VPB_SHARERS_WORD(1).
In this case, all tests in vm_page_busy_sleep(9) pass and we are going
to sleep, despite the page being share-busied.
Update check for m->busy_lock == VPB_UNBUSIED in vm_page_busy_sleep(9)
to also accept shared-busy state if we only wait for the xbusy state to
pass.
Merge sequential if()s with the same 'then' clause in
vm_page_busy_sleep().
Note that the current code does not share-busy pages from parallel
threads, the only way to have more that one sbusy owner is right now
is to recurse.
Reported and tested by: pho (previous version)
Reviewed by: alc, markj
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D8196
The runtime kernel loader, linker_load_file, unloads kernel files that
failed to load all of their modules. For consistency, treat preloaded
(loader.conf loaded) kernel files in the same way.
Reviewed by: kib
Sponsored by: Dell EMC Isilon
Differential Revision: https://reviews.freebsd.org/D8200
Use isrc in attached MSI data structure instead of using map's
isrc directly. map's isrc is set to NULL on IRQ deactivation
which happens prior to pci_release_msi so MSI_RELEASE_MSI
receives array of NULLs
Reviewed by: mmel
Differential Revision: https://reviews.freebsd.org/D8206
Other uses of cache_purgevfs() do rely on the cache purge for correct
operations, when paths are invalidated without unmount.
Reported and tested by: jkim
Discussed with: mjg
Sponsored by: The FreeBSD Foundation
purgevfs is purely optional and induces lock contention in workloads
which frequently mount and unmount filesystems.
In particular, poudriere will do this for filesystems with 4 vnodes or
less. Full cache scan is clearly wasteful.
Since there is no explicit counter for namecache entries, the number of
vnodes used by the target fs is checked.
The default limit is the number of bucket locks.
Reviewed by: kib
Previously free vnodes would always by directly returned to the global
LRU list. With this change up to mnt_free_list_batch vnodes are collected
first.
syncer runs always return the batch regardless of its size.
While vnodes on per-mnt lists are not counted as free, they can be
returned in case of vnode shortage.
Reviewed by: kib
Tested by: pho
function from restarting the timer.
Commonly taskqueue_enqueue_timeout() is called from within the task
function itself without any checks for teardown. Then it can happen
the timer stays active after the return of taskqueue_drain_timeout(),
because the timeout and task is drained separately.
This patch factors out the teardown flag into the timeout task itself,
allowing existing code to stay as-is instead of applying a teardown
flag to each and every of the timeout task consumers.
Add assert to taskqueue_drain_timeout() which prevents parallel
execution on the same timeout task.
Update manual page documenting the return value of
taskqueue_enqueue_timeout().
Differential Revision: https://reviews.freebsd.org/D8012
Reviewed by: kib, trasz
MFC after: 1 week
mbuf to store mp->msg_control. Later in kern_sendit(), call to getsock_cap(),
will check validity of file pointer passed, if this fails EBADF is returned but
mbuf allocated in sockargs() is not freed. Fix this possible leak.
Submitted by: Lohith Bellad <lohith.bellad@me.com>
Reviewed by: adrian
MFC after: 3 weeks
Differential Revision: https://reviews.freebsd.org/D7910
If the kernel is not compiled with the CAPABILITIES kernel options
fget_unlocked doesn't return the sequence number so fd_modify will
always report modification, in that case we got infinity loop.
Reported by: br
Reviewed by: mjg
Tested by: br, def
fget_cap_locked returns a referenced file, but the fgetvp_rights does
not need it. Instead, due to the filedesc lock being held, it can
ref the vnode after the file was looked up.
Fix up fget_cap_locked to be consistent with other _locked helpers and not
ref the file.
This plugs a leak introduced in r306184.
Pointy hat to: mjg, oshogbo
Add a table of vnode locks and use them along with bucketlocks to provide
concurrent modification support. The approach taken is to preserve the
current behaviour of the namecache and just lock all relevant parts before
any changes are made.
Lookups still require the relevant bucket to be locked.
Discussed with: kib
Tested by: pho
buffer and put a small optimization for low socket buffer case:
- Do not hack uio_resid, and let m_uiotombuf() properly take care of it. This
fixes truncation of headers at low buffer.
- If headers ate all the space, jump right to the end of the cycle, to
avoid doing single page I/O and allocating zero length mbuf.
- Clear hdr_uio only if space is positive, which indicates that all uio
was copied in.
Reviewed by: pluknet, jtl, emax, rrs, lstewart, emax, gallatin, scottl
sooptcopyin() checks if size of data provided by user is <= than we can
accept, else it strips down the size. On bigendian platforms we have to
move pointer as well so we copy the actual data.
Reviewed by: gnn
Sponsored by: DARPA, AFRL
Sponsored by: HEIF5
Differential Revision: https://reviews.freebsd.org/D7980
Descriptor returned by accept(2) should inherits capabilities rights from
the listening socket.
PR: 201052
Reviewed by: emaste, jonathan
Discussed with: many
Differential Revision: https://reviews.freebsd.org/D7724
This causes dtrace to automatically copyin arguments from userland, so
one no longer has to explicitly use the copyin() action to do so. Moreover,
copyin() on userland addresses is a no-op, so existing scripts should be
unaffected by this change.
Discussed with: rstone
MFC after: 2 weeks
CLOCK_GETTIME() with the lock.
Now all time-related accesses to the CMOS for RTC should be under the
lock. This is needed to allow upcoming EFI Runtime Services support
to provide required execution environment for the firmware calls.
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Both can be used to cause processes in capability mode to receive
SIGTRAP when ENOTCAPABLE or ECAPMODE errors are returned from
syscalls.
Idea by: emaste
Reviewed by: oshogbo (previous version), emaste
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D7965
In particular, reset the DF_QUIET flag when detaching from a device so
that a driver that marks a device quiet doesn't dictate policy for a
different driver that may claim the device in the future.
Reviewed by: rpokala, wblock
MFC after: 2 weeks
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D7803
An array of bucket locks is added.
All modifications still require the global cache_lock to be held for
writing. However, most readers only need the relevant bucket lock and in
effect can run concurrently to the writer as long as they use a
different lock. See the added comment for more details.
This is an intermediate step towards removal of the global lock.
Reviewed by: kib
Tested by: pho
If wait4() or wait6() return 0 because of WNOHANG, the status, rusage and
wrusage information should not be returned.
PR: 212048
Reported by: Casey Lucas
MFC after: 2 weeks
Use C99 designators to set the value of each slot and the nitems macro to
check for valid entries. In the process, switch to indexing by signal
number rather than signal-1 for improved clarity.
Obtained from: CheriBSD (a6053c5abf)
Sponsored by: DARPA, AFRL
Reviewed by: kib
Since negative entries are managed with a LRU list, a hit requires a
modificaton.
Currently the code tries to upgrade the global lock if needed and is
forced to retry the lookup if it fails.
Provide a dedicated lock for use when the cache is only shared-locked.
Reviewed by: kib
MFC after: 1 week
getdtablesize is "trivial global state" and is similar to
getrlimit(RLIMIT_NOFILE), so should be permitted in capability mode.
Reviewed by: oshogbo
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D7719
Calling cap_rights_contains() several times with the same inputs is not
going to produce a different output. The variable being iterated, i, is
never used inside the for loop.
The loop is actually done in cap_rights_contains()
Submitted by: Ryan Moeller <ryan@freqlabs.com>
Reviewed by: oshogbo, ed
MFC after: 1 month
Differential Revision: https://reviews.freebsd.org/D7369
Add a new 'clear driver' command for devctl along with the accompanying
ioctl and devctl_clear_driver() library routine to reset a device to
use a wildcard devclass instead of a fixed devclass. This can be used
to undo a previous 'set driver' command. After the device's name has
been reset to permit wildcard names, it is reprobed so that it can
attach to newly-available (to it) device drivers.
MFC after: 1 month
Sponsored by: Chelsio Communications
obliterate possible error from sleep with errors from
umtxq_check_susp(), when looping to clear URWLOCK_{READ,WRITE}_WAITERS.
Noted and reviewed by: vangyzen
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
If there was some error, e.g. the sleep was interrupted, as in the
referenced PR, do_rw_rdlock() did not cleared URWLOCK_READ_WAITERS.
Since unlock only wakes up write waiters when there is no read
waiters, for URWLOCK_PREFER_READER kind of locks, the result was
missed wakeups for writers.
In particular, the most visible victims are ld-elf.so locks in
processes which loaded libthr, because rtld locks are urwlocks in
prefer-reader mode. Normal rwlocks fall into prefer-reader mode only
if thread already owns rw lock in read mode, which is not typical and
correspondingly less visible. In the PR, unowned rtld bind lock was
waited for in the process where only one thread was left alive.
Note that do_rw_wrlock() correctly clears URWLOCK_WRITE_WAITERS in
case of errors.
Reported and tested by: longwitz@incore.de
PR: 211947
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
syscons spinlock for the output routine alone. It is better to extend
the coverage of the first syscons spinlock added in r162285. 2 locks
might work with complicated juggling, but no juggling was done. What
the 2 locks actually did was to cover some of the missing locking in
each other and deadlock less often against each other than a single
lock with larger coverage would against itself. Races are preferable
to deadlocks here, but 2 locks are still worse since they are harder
to understand and fix.
Prefer deadlocks to races and merge the second lock into the first one.
Extend the scope of the spinlocking to all of sc_cnputc() instead of
just the sc_puts() part. This further prefers deadlocks to races.
Extend the kdb_active hack from sc_puts() internals for the second lock
to all spinlocking. This reduces deadlocks much more than the other
changes increases them. The s/p,10* test in ddb gets much further now.
Hide this detail in the SC_VIDEO_LOCK() macro. Add namespace pollution
in 1 nested #include and reduce namespace pollution in other nested
#includes to pay for this.
Move the first lock higher in the witness order. The second lock was
unnaturally low and the first lock was unnaturally high. The second
lock had to be above "sleepq chain" and/or "callout" to avoid spurious
LORs for visual bells in sc_puts(). Other console driver locks are
already even higher (but not adjacent like they should be) except when
they are missing from the table. Audio bells also benefit from the
syscons lock being high so that audio mutexes have chance of being
lower. Otherwise, console drviver locks should be as low as possible.
Non-spurious LORs now occur if the bell code calls printf() or is
interrupted (perhaps by an NMI) and the interrupt handler calls
printf(). Previous commits turned off many bells in console i/o but
missed ones done by the teken layer.
(NB: This was likely a mismerge from XNU in audit support, where the
text argument to setlogin(2) is captured -- but as a text token,
whereas this change uses the dedicated login-name field in struct
audit_record.)
MFC after: 2 weeks
Sponsored by: DARPA, AFRL
ftruncate(2) system call. This was not required by the Common
Criteria, which needed only open-time audit.
MFC after: 2 weeks
Sponsored by: DARPA, AFRL
Such processes are stopped synchronously by a direct call to
ptracestop(SIGTRAP) upon exec. P2_PTRACE_FSTP causes the exec()ing thread
to suspend itself while waiting for a SIGSTOP that never arrives.
Reviewed by: kib
MFC after: 3 days
Differential Revision: https://reviews.freebsd.org/D7576
- Read interrupt properties at bus enumeration time and store
it into global mapping table.
- At bus_activate_resource() time, given mapping entry is resolved and
connected to real interrupt source. A copy of mapping entry is attached
to given resource.
- At bus_setup_intr() time, mapping entry stored in resource is used
for delivery of requested interrupt configuration.
- For MSI/MSIX interrupts, mapping entry is created within
pci_alloc_msi()/pci_alloc_msix() call.
- For legacy PCI interrupts, mapping entry must be created within
pcib_route_interrupt() by pcib driver itself.
Reviewed by: nwhitehorn, andrew
Differential Revision: https://reviews.freebsd.org/D7493
aio_aqueue() calls aio_init_aioinfo() as the first action. There is no
need to duplicate the code in kern_aio_fsync().
Also fix indent for aio_aqueue() definition.
Reviewed by: jhb
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D7523
Right now, userspace (fast) gettimeofday(2) on x86 only works for
RDTSC. For older machines, like Core2, where RDTSC is not C2/C3
invariant, and which fall to HPET hardware, this means that the call
has both the penalty of the syscall and of the uncached hw behind the
QPI or PCIe connection to the sought bridge. Nothing can me done
against the access latency, but the syscall overhead can be removed.
System already provides mappable /dev/hpetX devices, which gives
straight access to the HPET registers page.
Add yet another algorithm to the x86 'vdso' timehands. Libc is updated
to handle both RDTSC and HPET. For HPET, the index of the hpet device
to mmap is passed from kernel to userspace, index might be changed and
libc invalidates its mapping as needed.
Remove cpu_fill_vdso_timehands() KPI, instead require that
timecounters which can be used from userspace, to provide
tc_fill_vdso_timehands{,32}() methods. Merge i386 and amd64
libc/<arch>/sys/__vdso_gettc.c into one source file in the new
libc/x86/sys location. __vdso_gettc() internal interface is changed
to move timecounter algorithm detection into the MD code.
Measurements show that RDTSC even with the syscall overhead is faster
than userspace HPET access. But still, userspace HPET is three-four
times faster than syscall HPET on several Core2 and SandyBridge
machines.
Tested by: Howard Su <howard0su@gmail.com>
Sponsored by: The FreeBSD Foundation
MFC after: 1 month
Differential revision: https://reviews.freebsd.org/D7473
it (either async or sync drain).
At this moment the only user of drain is TCP, but TCP wouldn't reschedule a
callout after it has drained it, since it drains only when a tcpcb is closed.
This for now the problem isn't observed.
Submitted by: rrs
Make the kern_fsync() function public, so that it can be used by other
parts of the kernel. Fix up existing consumers to make use of it.
Requested by: kib
If the caller of sem_post() wakes up a thread sleeping via sem_wait()
before it clears the has_waiters flag, the caller of sem_wait() has no way of
knowing when it is safe to destroy the semaphore and reuse the memory. This is
because the caller of sem_post() may be interrupted between the wake step and
the clearing of has_waiters. It will then write into the has_waiters flag in
userspace after being preempted for some unknown amount of time.
Reviewed by: jhb, kib, vangyzen
Approved by: kib (mentor), vangyzen (mentor)
MFC after: 2 weeks
Sponsored by: Dell Inc.
Differential Revision: https://reviews.freebsd.org/D7505
Standard VOP_FSYNC() implementation just syncs data buffers, and due
to this, is the correct and efficient implementation for msdosfs or
any other filesystem which uses bufer cache trivially. Provide
globally visible wrapper vop_stdfdatasync_buf() for future consumption
by other filesystems.
Reviewed by: mckusick
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Differential revision: https://reviews.freebsd.org/D7471
The syscall is a trivial wrapper around new VOP_FDATASYNC(), sharing
code with fsync(2). For all filesystems, this commit provides the
implementation which delegates the work of VOP_FDATASYNC() to
VOP_FSYNC(). This is functionally correct but not efficient.
This is not yet POSIX-compliant implementation, because it does not
ensure that queued AIO requests are completed before returning.
Reviewed by: mckusick
Discussed with: avg (ZFS), jhb (AIO part)
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Differential revision: https://reviews.freebsd.org/D7471
It was remarkably hard to trace all current threads. "show pcpu" only
showed the pid, and there was nothing (?) better than searching ps output
to find the tids on CPUs. This change simplifies the search, but you
still have to trace the tid for each CPU manually.
incorrect from the error cases in exec_map_first_page(). They are
unnecessary because we automatically unbusy the page in vm_page_free()
when we remove it from the object. The calls are incorrect because they
happen after the page is freed, so we might actually unbusy the page
after it has been reallocated to a different object. (This error was
introduced in r292373.)
Reviewed by: kib
MFC after: 1 week
- Move group task queue into kern/subr_gtaskqueue.c
- Change intr_enable to return an int so it can be detected if it's not
implemented
- Allow different TX/RX queues per set to be different sizes
- Don't split up TX mbufs before transmit
- Allow a completion queue for TX as well as RX
- Pass the RX budget to isc_rxd_available() to allow an earlier return
and avoid multiple calls
Submitted by: shurd
Reviewed by: gallatin
Approved by: scottl
Differential Revision: https://reviews.freebsd.org/D7393
It was added in r153192 for XFS and doesn't appear to have been used for
anything else. XFS was disconnected in r241607 and removed entirely in
r247631.
Reported by: mlaier
Reviewed by: imp, kib
Differential Revision: https://reviews.freebsd.org/D7468
processes which combine kernel and non-kernel threads, e.g. nfsd. For
such processes, termination of a kthread must recheck signal delivery
among other threads according to masks.
Reported and tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Several files use the internal name of `struct device` instead of
`device_t` which is part of the public API. This patch changes all
`struct device *` to `device_t`.
The remaining occurrences of `struct device` are those referring to the
Linux or OpenBSD version of the structure, or the code is not built on
FreeBSD and it's unclear what to do.
Submitted by: Matthew Macy <mmacy@nextbsd.org> (previous version)
Approved by: emaste, jhibbits, sbruno
MFC after: 3 days
Differential Revision: https://reviews.freebsd.org/D7447
_prison_check_ip4 renamed to prison_check_ip4_locked
Move IPv6-specific jail functions to new file netinet6/in6_jail.c
_prison_check_ip6 renamed to prison_check_ip6_locked
Add appropriate prototypes to sys/sys/jail.h
Adjust kern_jail.c to call prison_check_ip4_locked and
prison_check_ip6_locked accordingly.
Add netinet/in_jail.c and netinet6/in6_jail.c to the list of files that
need to be built when INET and INET6, respectively, are configured in the
kernel configuration file.
Reviewed by: jtl
Approved by: sjg (mentor)
Sponsored by: Juniper Networks, Inc.
Differential Revision: https://reviews.freebsd.org/D6799
If the listening socket is closed while sonewconn() is executing, the
nascent child socket is aborted, which results in recursion on the
unp_link lock when the child's pru_detach method is invoked. Fix this
by using a flag to mark such sockets, and skip a part of the socket's
teardown during detach.
Reported by: Raviprakash Darbha <rdarbha@juniper.net>
Tested by: pho
MFC after: 2 weeks
Differential Revision: https://reviews.freebsd.org/D7398
r296773 was done to only remove libc symbols for <7. We want to provide
the syscall symbols going forward for 7+.
Discussed with: jhb
MFC after: 3 days
Sponsored by: EMC / Isilon Storage Division
Our mprotect() function seems to take a "const void *" address to the
pages whose permissions need to be adjusted. POSIX uses "void *". Simply
stick to the POSIX one to prevent us from writing unportable code.
PR: 211423 (exp-run)
Tested by: antoine@ (Thanks!)
All current spinning loops retry an atomic op the first chance they get,
which leads to performance degradation under load.
One classic solution to the problem consists of delaying the test to an
extent. This implementation has a trivial linear increment and a random
factor for each attempt.
For simplicity, this first thouch implementation only modifies spinning
loops where the lock owner is running. spin mutexes and thread lock were
not modified.
Current parameters are autotuned on boot based on mp_cpus.
Autotune factors are very conservative and are subject to change later.
Reviewed by: kib, jhb
Tested by: pho
MFC after: 1 week
Both variables are uint64_t, but they only count spins or sleeps.
All reasonable values which we can get here comfortably hit in 32-bit range.
Suggested by: kib
MFC after: 1 week
If a thread is created bound to a cpuset it might already be bound before
it's very first timeslice, and td_lastcpu will be NOCPU in that case.
MFC after: 1 week
- Use correct lock in aio_cancel_sync when dequeueing job.
- Add _locked variants of aio_set/clear_cancel_function and use those
to avoid lock recursion when adding and removing fsync jobs to the
per-process sync queue.
- While here, add a basic test for aio_fsync().
PR: 211390
Reported by: Randy Westlund <rwestlun@gmail.com>
MFC after: 1 week
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D7339
Any sensible workflow will include a revision control system from which
to restore the old files if required. In normal usage, developers just
have to clean up the mess.
Reviewed by: jhb
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D7353
It looks like the msgrcv() system call is already written in such a way
that the size is internally computed as a size_t and written into all of
td_retval[0]. This means that it is effectively already returning
ssize_t. It's just that the userspace prototype doesn't match up.
specifics of callout KPI. Esp., do not depend on the exact interface
of callout_stop(9) return values.
The main change is that instead of requiring precise callouts, code
maintains absolute time to wake up. Callouts now should ensure that a
wake occurs at the requested moment, but we can tolerate both run-away
callout, and callout_stop(9) lying about running callout either way.
As consequence, it removes the constant source of the bugs where
sleepq_check_timeout() causes uninterruptible thread state where the
thread is detached from CPU, see e.g. r234952 and r296320.
Patch also removes dual meaning of the TDF_TIMEOUT flag, making code
(IMO much) simpler to reason about.
Tested by: pho
Reviewed by: jhb
Sponsored by: The FreeBSD Foundation
MFC after: 1 month
Differential revision: https://reviews.freebsd.org/D7137
callout_when(9). See the man page update for the description of the
intended use.
Tested by: pho
Reviewed by: jhb, bjk (man page updates)
Sponsored by: The FreeBSD Foundation
MFC after: 1 month
X-Differential revision: https://reviews.freebsd.org/D7137
target. Due to a way issignal() selects the next signal to deliver
and report, if the simultaneous or already pending another signal
exists, that signal might be reported by the next waitpid(2) call.
This causes minor annoyance for debuggers, which must be prepared to
take any signal as the first event, then filter SIGSTOP later.
More importantly, for tools like gcore(1), which attach and then
detach without processing events, SIGSTOP might leak to be delivered
after PT_DETACH. This results in the process being unintentionally
stopped after detach, which is fatal for automatic tools.
The solution is to force SIGSTOP to be the first signal reported after
the attach. Attach code is modified to set P2_PTRACE_FSTP to indicate
that the attaching ritual was not yet finished, and issignal() prefers
SIGSTOP in that condition. Also, the thread which handles
P2_PTRACE_FSTP is made to guarantee to own p_xthread during the first
waitpid(2). All that ensures that SIGSTOP is consumed first.
Additionally, if P2_PTRACE_FSTP is still set on detach, which means
that waitpid(2) was not called at all, SIGSTOP is removed from the
queue, ensuring that the process is resumed on detach.
In issignal(), when acting on STOPing signals, remove the signal from
queue before suspending. Otherwise parallel attach could result in
ptracestop() acting on that STOP as if it was the STOP signal from the
attach. Then SIGSTOP from attach leaks again.
As a minor refactoring, some bits of the common attach code is moved
to new helper proc_set_traced().
Reported by: markj
Reviewed by: jhb, markj
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Differential revision: https://reviews.freebsd.org/D7256
- Move cr_canseeinpcb to sys/netinet/in_prot.c in order to separate the
INET and INET6-specific code from the rest of the prot code (It is only
used by the network stack, so it makes sense for it to live with the
other network stack code.)
- Move cr_canseeinpcb prototype from sys/systm.h to netinet/in_systm.h
- Rename cr_seeotheruids to cr_canseeotheruids and cr_seeothergids to
cr_canseeothergids, make them non-static, and add prototypes (so they
can be seen/called by in_prot.c functions.)
- Remove sw_csum variable from ip6_forward in ip6_forward.c, as it is an
unused variable.
Reviewed by: gnn, jtl
Approved by: sjg (mentor)
Sponsored by: Juniper Networks, Inc.
Differential Revision: https://reviews.freebsd.org/D2901
and there is no other issues with parallel settime(). Remove spl()
vestiges there as well.
Tested by: pho (as part of the whole patch)
Reviewed by: jhb (same)
Discussed wit: bde
Sponsored by: The FreeBSD Foundation
MFC after: 1 month
Differential revision: https://reviews.freebsd.org/D7302
setclock() and from simultaneous top-level and interrupt. For this,
tc_windup() is protected with a tc_setclock_mtx spinlock, in the try
mode when called from hardclock interrupt. If spinlock cannot be
obtained without spinning from the interrupt context, this means that
top-level executes tc_windup() on other core and our try may be
avoided.
The boottimebin and boottime variables should be adjusted from
tc_windup(). To be correct, they must be part of the timehands and
read using lockless protocol. Remove the globals and reimplement the
getboottime(9)/getboottimebin(9) KPI using the timehands read
protocol.
Tested by: pho (as part of the whole patch)
Reviewed by: jhb (same)
Discussed wit: bde
Sponsored by: The FreeBSD Foundation
MFC after: 1 month
X-Differential revision: https://reviews.freebsd.org/D7302
Change ntpadj_lock to spinlock always, and rename stuff removing
ADJ/adj from the names. ntp_update_second() requires ntp_lock and is
called from the tc_windup(), so ntp_lock must be a spinlock. Add
missed lock to ntp_update_second().
Tested by: pho (as part of the whole patch)
Reviewed by: jhb (same)
Noted by: bde
Sponsored by: The FreeBSD Foundation
MFC after: 1 month
X-Differential revision: https://reviews.freebsd.org/D7302
consumers can now be only one tc_windup() call late.
Use C99 initialization.
Tested by: pho (as part of the whole patch)
Reviewed by: jhb (same)
Discussed with: bde
Sponsored by: The FreeBSD Foundation
MFC after: 1 month
X-Differential revision: https://reviews.freebsd.org/D7302
and getboottimebin(9) KPI. Change consumers of boottime to use the
KPI. The variables were renamed to avoid shadowing issues with local
variables of the same name.
Issue is that boottime* should be adjusted from tc_windup(), which
requires them to be members of the timehands structure. As a
preparation, this commit only introduces the interface.
Some uses of boottime were found doubtful, e.g. NLM uses boottime to
identify the system boot instance. Arguably the identity should not
change on the leap second adjustment, but the commit is about the
timekeeping code and the consumers were kept bug-to-bug compatible.
Tested by: pho (as part of the bigger patch)
Reviewed by: jhb (same)
Discussed with: bde
Sponsored by: The FreeBSD Foundation
MFC after: 1 month
X-Differential revision: https://reviews.freebsd.org/D7302
number of core files allowed by a particular process when using the %I core
file name pattern.
Sanity check at compile time to ensure the value is within the valid range of
0-10.
Reviewed by: jtl, sjg
Approved by: sjg (mentor)
Sponsored by: Juniper Networks, Inc.
Differential Revision: https://reviews.freebsd.org/D6812
It looks like our "struct shmid_ds::shm_nattch" deviates from the
standard in the sense that it is a signed integer, whereas POSIX
requires that it is unsigned, having a special type shmatt_t.
Patch up our native and 32-bit copies to use a new shmatt_t that is an
unsigned integer. As it's unsigned, we can relax the comparisons that
are performed on it. Leave the Linux, iBCS2, etc. copies of the
structure alone.
Reviewed by: ngie
Differential Revision: https://reviews.freebsd.org/D6655
Devfs' file layer ioctl is now just a thin shim around the vnode layer.
Reviewed by: kib
Sponsored by: EMC / Isilon Storage Division
Differential Revision: https://reviews.freebsd.org/D7286
The asynchronous I/O changes made previously result in different
behavior out of the box. Previously all AIO requests failed with
ENOSYS / SIGSYS unless aio.ko was explicitly loaded. Now, some AIO
requests complete and others ("unsafe" requests) fail with EOPNOTSUPP.
Reword the introductory paragraph in aio(4) to add a general
description of AIO before describing the vfs.aio.enable_unsafe sysctl.
Remove the ENOSYS error description from aio_fsync(2), aio_read(2),
and aio_write(2) and replace it with a description of EOPNOTSUPP.
Remove the ENOSYS error description from aio_mlock(2).
Log a message to the system log the first time a process requests an
"unsafe" AIO request that fails with EOPNOTSUPP. This is modeled on
the log message used for processes using the legacy pty devices.
Reviewed by: kib (earlier version)
MFC after: 1 week
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D7151
Two notes:
- I allow AIO on reclaimed vnodes, since it is deterministically terminated
fast.
- devfs mounts are marked as MNT_LOCAL, but device vnodes have type
VCHR, so the slow device io is not allowed.
Reviewed by: jhb
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D7273
warnings for some kernel events, mostly intended for the use of
obsoleted or otherwise undersired interfaces.
This is an abstracted and race-expelled code from compat pty driver.
Requested and reviewed by: jhb
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D7270
The each_writable_segment routine evaluates segments on a slightly little more
nuanced metric than simply "writable" or not. Rename the function to more
closely match its behavior (each_dumpable_segment).
Suggested by: jhb
Sponsored by: EMC / Isilon Storage Division
The ELF e_phnum field is only 16 bits wide. To support more than 65535 segments
(program headers), Sun's "Linker and Libraries Guide" table 7-7 (or 12-7,
depending on document version) prescribes a special first section header where
sh_info represents the real number of program headers.
Test code to follow, when it is ready.
Reference: http://docs.oracle.com/cd/E18752_01/pdf/817-1984.pdf
Reviewed by: emaste, markj
Sponsored by: EMC / Isilon Storage Division
Differential Revision: https://reviews.freebsd.org/D7255
fixes that I think closes up the races Gleb was
looking for. This is running quite nicely in Netflix and
now no longer causes TCP-tcb leaks.
Differential Revision: 7135
When threads were added to the kernel, the pr_pid member of the
NT_PRSTATUS note was repurposed to store LWP IDs instead of process
IDs. However, the process ID was no longer recorded in core dumps.
This change adds a pr_pid field to prpsinfo (NT_PRSINFO). Rather than
bumping the prpsinfo version number, note parsers can use the note's
payload size to determine if pr_pid is present.
Reviewed by: kib, emaste (older version)
MFC after: 2 months
Differential Revision: https://reviews.freebsd.org/D7117
First, PL_FLAG_FORKED events now also set a PL_FLAG_VFORKED flag when
the new child was created via vfork() rather than fork(). Second, a
new PL_FLAG_VFORK_DONE event can now be enabled via the PTRACE_VFORK
event mask. This new stop is reported after the vfork parent resumes
due to the child calling exit or exec. Debuggers can use this stop to
reinsert breakpoints in the vfork parent process before it resumes.
Reviewed by: kib
MFC after: 1 month
Differential Revision: https://reviews.freebsd.org/D7045
is delivered to vforked child. Issue is that we avoid stopping such
children in issignal() to not block parents. But executed AST, which
ignored stops, leaves the child with the signal pending but no AST
pending.
On first exec after vfork(), call signotify() to handle pending
reenabled signals. Adjust the assert to not check vfork children
until exec.
Reported and tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
that struct kevent member ident has uintptr_t type, which is silently
truncated to int in the call to fget(). Explicitely check for the
valid range.
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
object lock.
The vmspace_free() operations might need to lock map, object etc on
last dereference. Postpone the free until object's inspection is
done.
Reported and tested by: will
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
ptrace() now stores a mask of optional events in p_ptevents. Currently
this mask is a single integer, but it can be expanded into an array of
integers in the future.
Two new ptrace requests can be used to manipulate the event mask:
PT_GET_EVENT_MASK fetches the current event mask and PT_SET_EVENT_MASK
sets the current event mask.
The current set of events include:
- PTRACE_EXEC: trace calls to execve().
- PTRACE_SCE: trace system call entries.
- PTRACE_SCX: trace syscam call exits.
- PTRACE_FORK: trace forks and auto-attach to new child processes.
- PTRACE_LWP: trace LWP events.
The S_PT_SCX and S_PT_SCE events in the procfs p_stops flags have
been replaced by PTRACE_SCE and PTRACE_SCX. PTRACE_FORK replaces
P_FOLLOW_FORK and PTRACE_LWP replaces P2_LWP_EVENTS.
The PT_FOLLOW_FORK and PT_LWP_EVENTS ptrace requests remain for
compatibility but now simply toggle corresponding flags in the
event mask.
While here, document that PT_SYSCALL, PT_TO_SCE, and PT_TO_SCX both
modify the event mask and continue the traced process.
Reviewed by: kib
MFC after: 1 month
Differential Revision: https://reviews.freebsd.org/D7044
As was reported on http://seclists.org/oss-sec/2016/q3/68, tmpfs code
contains assertion that rdev != VNOVAL. On FreeBSD, there is no other
consequences except triggering the assert. To be compatible with
systems where device nodes have some significance, reject mknod(2)
call with dev == VNOVAL at the syscall level.
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Fill in pr_psargs in the NT_PRSINFO ELF core dump note with command
line arguments.
Reviewed by: kib
Differential Revision: https://reviews.freebsd.org/D7116
A buf's b_pages and b_npages fields may be inconsistent after a panic.
For instance, vfs_vmio_invalidate() sets b_npages to zero only after all
pages are unwired and their page array entries are cleared.
MFC after: 1 week
Sponsored by: EMC / Isilon Storage Division
Set vm_guest to a new enum value (VM_GUEST_KVM) when kvm is detected and use
vm_guest in conditionals testing for KVM.
Also, fix a conditional checking if we're running in a VM which caught only
the generic VM case, but not more specific VMs (KVM, VMWare, etc.). (Spotted
by: vangyzen).
Differential revision: https://reviews.freebsd.org/D7172
Sponsored by: Dell Inc.
Approved by: kib (mentor), vangyzen (mentor)
Reviewed by: alc
MFC after: 4 weeks
Despite the implication (process has pending signals -> the current
thread marked for AST and has TDF_NEEDSIGCHK set) is not true due to
other thread might manipulate its signal blocking mask, it should still
hold for the single-threaded processes. Enable check for the condition
for single-threaded case, and replicate it from userret() to ast() as
well, where we check that ast indeed has no signal to deliver.
Note that the check is under DIAGNOSTIC, it is not enabled for INVARIANTS
but !DIAGNOSTIC since it imposes too heavy-weight locking for day-to-day
used debugging kernel.
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
AST must not execute with TDF_SBDRY or TDF_SEINTR/TDF_SERESTART thread
flags set, which is asserted in userret(). As the consequence, -1 return
from cursig() must not be possible.
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
if vnode is VMIO. For VMIO vnodes, set BO_DEAD in vm_object_terminate().
The vnode_destroy_object(), when calling into vm_object_terminate(),
must be able to flush buffers. BO_DEAD purpose is to quickly destroy
buffers on write when the underlying vnode is not operable any more
(one example is the devfs node after geom is gone). Setting BO_DEAD
for reclaiming vnode before object is terminated is premature, and
results in unability to flush buffers with live SU dependencies from
vinvalbuf() in vm_object_terminate().
Reported by: David Cross <dcrosstech@gmail.com>
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
those system calls audit event identifiers AUE_READ and AUE_WRITE.
While auditing file-descriptor I/O is not required by the Common
Criteria, in practice this proves useful for both live and forensic
analysis.
NB: freebsd32 already assigns AUE_READ and AUE_WRITE to read(2) and
write(2).
MFC after: 3 days
Sponsored by: DARPA, AFRL
about the desirability of auditing the number, as it was in fact in the
wrong place (in the common path for open(2) and openat(2), and only the
latter accepts a file-descriptor argument). Where other ABIs support
openat(2), it may be necessary to do additional argument auditing as it is
not performed in kern_openat(9).
MFC after: 3 days
Sponsored by: DARPA, AFRL
read(2), write(2), dup(2), and mmap(2). This auditing is not
required by the Common Criteria (and hence was not being
performed), but is valuable in both contemporary live analysis
and forensic use cases.
MFC after: 3 days
Sponsored by: DARPA, AFRL
any open vnodes before proceeding. Make autounmound(8) use this flag.
Without it, even an unsuccessfull unmount causes filesystem flush,
which interferes with normal operation.
Reviewed by: kib@
Approved by: re (gjb@)
MFC after: 1 month
Differential Revision: https://reviews.freebsd.org/D7047
mp_maxid or CPU_FOREACH() as appropriate. This fixes a number of places in
the kernel that assumed CPU IDs are dense in [0, mp_ncpus) and would try,
for example, to run tasks on CPUs that did not exist or to allocate too
few buffers on systems with sparse CPU IDs in which there are holes in the
range and mp_maxid > mp_ncpus. Such circumstances generally occur on
systems with SMT, but on which SMT is disabled. This patch restores system
operation at least on POWER8 systems configured in this way.
There are a number of other places in the kernel with potential problems
in these situations, but where sparse CPU IDs are not currently known
to occur, mostly in the ARM machine-dependent code. These will be fixed
in a follow-up commit after the stable/11 branch.
PR: kern/210106
Reviewed by: jhb
Approved by: re (glebius)
not scheduled -> scheduled -> running -> not scheduled. The API and the
manual page assume that, some comments in the code assume that, and looks
like some contributors to the code also did. The problem is that this
paradigm isn't true. A callout can be scheduled and running at the same
time, which makes API description ambigouous. In such case callout_stop()
family of functions/macros should return 1 and 0 at the same time, since it
successfully unscheduled future callout but the current one is running.
Before this change we returned 1 in such a case, with an exception that
if running callout was migrating we returned 0, unless CS_MIGRBLOCK was
specified.
With this change, we now return 0 in case if future callout was unscheduled,
but another one is still in action, indicating to API users that resources
are not yet safe to be freed.
However, the sleepqueue code relies on getting 1 return code in that case,
and there already was CS_MIGRBLOCK flag, that covered one of the edge cases.
In the new return path we will also use this flag, to keep sleepqueue safe.
Since the flag CS_MIGRBLOCK doesn't block migration and now isn't limited to
migration edge case, rename it to CS_EXECUTING.
This change fixes panics on a high loaded TCP server.
Reviewed by: jch, hselasky, rrs, kib
Approved by: re (gjb)
Differential Revision: https://reviews.freebsd.org/D7042
option, not INVARIANTS. The function is required if we want
to load in a module that is compiled with INVARIANTS.
Reviewed by: jhb
Approved by: re (gjb)
vpanic() uses spinlock_enter() to disable interrupts before dumping core.
However, when the scheduler is stopped and INVARIANTS is not configured,
thread_lock() does not acquire a spinlock section, while thread_unlock()
releases one. This can result in interrupts staying enabled while the
kernel dumps core, complicating post-mortem analysis of the crash.
Approved by: re (gjb)
MFC after: 1 week
Sponsored by: EMC / Isilon Storage Division
method implementations: fstat(2), close(2), and poll(2). This change
synchronises auditing here with similar auditing for VFS-specific system
calls such as stat(2) that audit more complete vnode information.
Sponsored by: DARPA, AFRL
Approved by: re (kib)
MFC after: 1 week
calculate appropriate return value for stops. Simplify the code by
using them.
Fix typo in sig_suspend_threads(). The thread which sleep must be
aborted is td2. (*)
In issignal(), when handling stopping signal for thread in
TD_SBDRY_INTR state, do not stop, this is wrong and fires assert.
This is yet another place where execution should be forced out of
SBDRY-protected region. For such case, return -1 from issignal() and
translate it to corresponding error code in sleepq_catch_signals().
Assert that other consumers of cursig() are not affected by the new
return value. (*)
Micro-optimize, mostly VFS and VOP methods, by avoiding calling the
functions when SIGDEFERSTOP_NOP non-change is requested. (**)
Reported and tested by: pho (*)
Requested by: bde (**)
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Approved by: re (gjb)
does it under the vnode interlock, but the interlock is not owned by the
asserting thread. As result, we might read increased use counter but also
still see VI_OWEINACT.
In collaboration with: nwhitehorn
Hardware donated by: IBM LTC
Sponsored by: The FreeBSD Foundation (kib)
Approved by: re (gjb)
the knote is activated immediately. If the exit1() later activates
knotes, such knote is attempted to be activated second time. Detect
the condition by zeroed kn_ptr.p_proc pointer, and avoid excessive
activation.
Before r302235, such knotes were removed from the knlist immediately
upon activation.
Reported by: truckman
Sponsored by: The FreeBSD Foundation
Approved by: re (gjb)
particular, the Giant is supposed to protect against parallel
ntp_adjtime(2) invocations. But, for instance, sys_ntp_adjtime() does
copyout(9) under Giant and then examines time_status to return syscall
result. Since copyout(9) could sleep, the syscall result might be
inconsistent.
Another and more important issue is that if PPS is configured,
hardpps(9) is executed without any protection against the parallel
top-level code invocation. Potentially, this may result in the
inconsistent state of the ntptime state variables, but I cannot say
how serious such distortion is. The non-functional splclock() call in
sys_ntp_adjtime() protected against clock interrupts calling hardpps()
in the pre-SMP era.
Modernize the locking. A mutex protects ntptime data. Due to the
hardpps() KPI legitimately serving from the interrupt filters (and
e.g. uart(4) does call it from filter), the lock cannot be sleepable
mutex if PPS_SYNC is defined. Otherwise, use normal sleepable mutex
to reduce interrupt latency.
Reviewed by: imp, jhb
Sponsored by: The FreeBSD Foundation
Approved by: re (gjb)
Differential revision: https://reviews.freebsd.org/D6825
private mtx in resettodr(), no implementation of CLOCK_SETTIME() is
allowed to sleep.
Reviewed by: imp, jhb
Sponsored by: The FreeBSD Foundation
Approved by: re (gjb)
X-Differential revision: https://reviews.freebsd.org/D6825
TDF_SEINTR flags values, unlike TDF_SBDRY, must be treated almost as
if TDF_SBDRY is not set for STOP signal delivery. The only difference
is that sig_suspend_threads() should abort the sleep instead of doing
immediate suspension.
Reported by: ngie
Sponsored by: The FreeBSD Foundation
MFC after: 12 days
Approved by: re (gjb)
structure, change it to int.
The real fix is to sanitize user-visible definitions in sys/event.h,
e.g. the affected struct knlist is of no use for userspace programs.
Reported and tested by: jkim
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Approved by: re (gjb)
exiting (NOTE_EXIT->knlist_remove_inevent()), two things happen:
- knote kn_knlist pointer is reset
- INFLUX knote is removed from the process knlist.
And, there are two consequences:
- KN_LIST_UNLOCK() on such knote is nop
- there is nothing which would block exit1() from processing past the
knlist_destroy() (and knlist_destroy() resets knlist lock pointers).
Both consequences result either in leaked process lock, or
dereferencing NULL function pointers for locking.
Handle this by stopping embedding the process knlist into struct proc.
Instead, the knlist is allocated together with struct proc, but marked
as autodestroy on the zombie reap, by knlist_detach() function. The
knlist is freed when last kevent is removed from the list, in
particular, at the zombie reap time if the list is empty. As result,
the knlist_remove_inevent() is no longer needed and removed.
Other changes:
In filt_procattach(), clear NOTE_EXEC and NOTE_FORK desired events
from kn_sfflags for knote registered by kernel to only get NOTE_CHILD
notifications. The flags leak resulted in excessive
NOTE_EXEC/NOTE_FORK reports.
Fix immediate note activation in filt_procattach(). Condition should
be either the immediate CHILD_NOTE activation, or immediate NOTE_EXIT
report for the exiting process.
In knote_fork(), do not perform racy check for KN_INFLUX before kq
lock is taken. Besides being racy, it did not accounted for notes
just added by scan (KN_SCAN).
Some minor and incomplete style fixes.
Analyzed and tested by: Eric Badger <eric@badgerio.us>
Reviewed by: jhb
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Approved by: re (gjb)
Differential revision: https://reviews.freebsd.org/D6859
interrupt sleeps with the ERESTART on the suspension attempts.
Otherwise, single-threading requests are deferred until the locks are
granted for NFS files, which causes hangs.
When retrying local registration of the remotely-granted adv lock,
allow full suspension and check for suspension, for usual reasons.
Reported by: markj, pho
Reviewed by: jilles
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Approved by: re (gjb)
framework allowing to set the suspension policy for the dynamic block.
Extend the currently possible policies of stopping on interruptible
sleeps and ignoring such sleeps by two more: do not suspend at
interruptible sleeps, but interrupt them with either EINTR or ERESTART.
Reviewed by: jilles
Tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Approved by: re (gjb)
lists must be functional.
Reported by: Daniel Engberg <daniel.engberg.lists@pyret.net>,
Guy Yur <guyyur@gmail.com>
Tested by: Guy Yur <guyyur@gmail.com>
Sponsored by: The FreeBSD Foundation
Approved by: re (gjb), including the KBI change
While reading the code, I noticed that shm_read() returns without unlocking
foffset and rangelock if mac_posixshm_check_read() rejects the read.
Reviewed by: kib, jhb, rwatson
Approved by: re (gjb)
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D6927
Mark the pipe() system call as COMPAT10.
As of r302092 libc uses pipe2() with a zero flags value instead of pipe().
Approved by: re (gjb)
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D6816
As of r302092 libc uses pipe2() with a zero flags value instead of pipe().
Commit with regenerated files and implementation to follow.
Approved by: re (gjb)
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D6816
File and disk-backed I/O requests store counts of read/written disk
blocks in each AIO job so that they can be charged to the thread that
completes an AIO request via aio_return() or aio_waitcomplete(). This
change extends AIO jobs to store counts of received/sent messages and
updates socket backends to set these counts accordingly. Note that
the socket backends are careful to only charge a single messages for
each AIO request even though a single request on a blocking socket might
invoke sosend or soreceive multiple times. This is to mimic the
resource accounting of synchronous read/write.
Adjust the UNIX socketpair AIO test to verify that the message resource
usage counts update accordingly for aio_read and aio_write.
Approved by: re (hrs)
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D6911
than removing the network interfaces first. This change is rather larger
and convoluted as the ordering requirements cannot be separated.
Move the pfil(9) framework to SI_SUB_PROTO_PFIL, move Firewalls and
related modules to their own SI_SUB_PROTO_FIREWALL.
Move initialization of "physical" interfaces to SI_SUB_DRIVERS,
move virtual (cloned) interfaces to SI_SUB_PSEUDO.
Move Multicast to SI_SUB_PROTO_MC.
Re-work parts of multicast initialisation and teardown, not taking the
huge amount of memory into account if used as a module yet.
For interface teardown we try to do as many of them as we can on
SI_SUB_INIT_IF, but for some this makes no sense, e.g., when tunnelling
over a higher layer protocol such as IP. In that case the interface
has to go along (or before) the higher layer protocol is shutdown.
Kernel hhooks need to go last on teardown as they may be used at various
higher layers and we cannot remove them before we cleaned up the higher
layers.
For interface teardown there are multiple paths:
(a) a cloned interface is destroyed (inside a VIMAGE or in the base system),
(b) any interface is moved from a virtual network stack to a different
network stack ("vmove"), or (c) a virtual network stack is being shut down.
All code paths go through if_detach_internal() where we, depending on the
vmove flag or the vnet state, make a decision on how much to shut down;
in case we are destroying a VNET the individual protocol layers will
cleanup their own parts thus we cannot do so again for each interface as
we end up with, e.g., double-frees, destroying locks twice or acquiring
already destroyed locks.
When calling into protocol cleanups we equally have to tell them
whether they need to detach upper layer protocols ("ulp") or not
(e.g., in6_ifdetach()).
Provide or enahnce helper functions to do proper cleanup at a protocol
rather than at an interface level.
Approved by: re (hrs)
Obtained from: projects/vnet
Reviewed by: gnn, jhb
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
Differential Revision: https://reviews.freebsd.org/D6747
to mount points with the given filesystem type, specified by mount
vfs_ops pointer.
Based on patch by: mckusick
Reviewed by: avg, mckusick
Tested by: allanjude, madpilot
Sponsored by: The FreeBSD Foundation
Approved by: re (gjb)
threads, to make it less confusing and using modern kernel terms.
Rename the functions to reflect current use of the functions, instead
of the historic KSE conventions:
cpu_set_fork_handler -> cpu_fork_kthread_handler (for kthreads)
cpu_set_upcall -> cpu_copy_thread (for forks)
cpu_set_upcall_kse -> cpu_set_upcall (for new threads creation)
Reviewed by: jhb (previous version)
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Approved by: re (hrs)
Differential revision: https://reviews.freebsd.org/D6731
reason for it in modern times. In the other case, expand the comment
stating instead of doubting.
Reviewed by: jhb
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Approved by: re (hrs)
X-Differential revision: https://reviews.freebsd.org/D6731
This reduces the size of kaiocb slightly. I've also added some generic
fields that other backends can use in place of the BIO-specific fields.
Change the socket and Chelsio DDP backends to use 'backend3' instead of
abusing _aiocb_private.status directly. This confines the use of
_aiocb_private to the AIO internals in vfs_aio.c.
Reviewed by: kib (earlier version)
Approved by: re (gjb)
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D6547
we set MNTK_UNMOUNT flag on the mp. Otherwise parallel unmount which
wins race with us could dereference the covered vnode, and we are
left with the locked freed memory.
Reported and tested by: pho
Sponsored by: The FreeBSD Foundation
Approved by: re (gjb)
MFC after: 1 week
The allproc_lock lock used in the sysctl_kern_corefile function is initialized
in the procinit function which is called after setting sysctl values at boot.
That means if we set kern.corefile at boot we will be trying to use
lock with is uninitialized and machine will crash.
If we define kern.corefile as tunable instead of using CTFLAG_RWTUN we will
not call the sysctl_kern_corefile function and we will not use an uninitialized
lock. When machine will boot then we will start using function depending on
the lock.
Reviewed by: pjd
by holding allprison_lock exclusively (even if only for a moment before
downgrading) on all paths that call PR_METHOD_REMOVE. Since they may run
on a downgraded lock, it's still possible for them to run concurrently
with PR_METHOD_GET, which will need to use the prison lock.
when the process credentials were not changed. This can happen if an
error occured trying to activate the setuid binary. And on error, if
new credentials were not yet assigned, they must be freed to not
create the leak.
Use oldcred == NULL as the predicate to detect credential
reassignment.
Reported and tested by: pho
Sponsored by: The FreeBSD Foundation
panic string again if set, in case it scrolled out of the active
window. This avoids having to remember the symbol name.
Also add a show callout <addr> command to DDB in order to inspect
some struct callout fields in case of panics in the callout code.
This may help to see if there was memory corruption or to further
ease debugging problems.
Obtained from: projects/vnet
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Reviewed by: jhb (comment only on the show panic initally)
Differential Revision: https://reviews.freebsd.org/D4527
p_sched is unused.
The struct td_sched is always co-allocated with the struct thread,
except for the thread0. Avoid useless indirection, instead calculate
td_sched location using simple pointer arithmetic in td_get_sched(9).
For thread0, which is statically allocated, create a structure to
emulate layout of the dynamic allocation.
Reviewed by: jhb (previous version)
Sponsored by: The FreeBSD Foundation
Differential revision: https://reviews.freebsd.org/D6711
BUS_MAP_INTR() is used to get an interrupt mapping data according
to provided hints. The hints could be modified afterwards, but only
if mapping data was allocated. This method is intended to be called
before BUS_ALLOC_RESOURCE().
An interrupt mapping data describes an interrupt - hardware number,
type, configuration, cpu binding, and whatever is needed to setup it.
(2) Introduce a method which allows storing of an additional data
in struct resource to be available for bus drivers. This method is
convenient in two ways:
- there is no need to rework existing bus drivers as they can simply
be extended to provide an additional data,
- there is no need to modify any existing bus methods as struct
resource is already passed to them as argument and thus stored data
is simply accessible by other bus drivers.
For now, implement this method only for INTRNG.
This is motivated by needs of modern SOCs where hardware initialization
is not straightforward and resources descriptions are complex, opaque
for everyone but provider, and may vary from SOC to SOC. Typical
situation is that one bus driver can fetch a resource description for
its child device, but it's opaque for this driver. Another bus driver
knows a provider for this kind of resource and can pass this resource
description to it. In fact, something like device IVARS would be
perfect for that if implemented generally enough. Unfortunatelly, IVARS
are usable only by their owners now. Only owner knows its IVARS layout,
thus other bus drivers are not able to use them.
Differential Revision: https://reviews.freebsd.org/D6632
range of interrupts they pass to a second controller driver to handle.
The parent driver is expected to detect when one of these interrupts has
been triggered and call intr_child_irq_handler to pass the interrupt to
a child. The children controllers are then expected to manage the range
by allocating interrupts as needed.
This will initially be used by the ARM GICv3 driver, but is is expected to
be useful for other driver where this type of allocation applies.
Obtained from: ABT Systems Ltd
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D6436
Inline version of primitives do an atomic op and if it fails they fallback to
actual primitives, which immediately retry the atomic op.
The obvious optimisation is to check if the lock is free and only then proceed
to do an atomic op.
Reviewed by: jhb, vangyzen
specific order. VNET_SYSUNINITs however are doing exactly that.
Thus remove the VIMAGE conditional field from the domain(9) protosw
structure and replace it with VNET_SYSUNINITs.
This also allows us to change some order and to make the teardown functions
file local static.
Also convert divert(4) as it uses the same mechanism ip(4) and ip6(4) use
internally.
Slightly reshuffle the SI_SUB_* fields in kernel.h and add a new ones, e.g.,
for pfil consumers (firewalls), partially for this commit and for others
to come.
Reviewed by: gnn, tuexen (sctp), jhb (kernel.h)
Obtained from: projects/vnet
MFC after: 2 weeks
X-MFC: do not remove pr_destroy
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D6652
The lock was temporarily dropped for vrele calls, but they can be
postponed to a point where the lock is not held in the first place.
While here shuffle other code not needing the lock.
This was previously set after the hook and only if auxargs were present.
Now always provide it if possible.
MFC after: 2 weeks
Reviewed by: kib
Sponsored by: EMC / Isilon Storage Division
Differential Revision: https://reviews.freebsd.org/D6546
This allows an EVENTHANDLER(process_exec) hook to see if the new image
will cause credentials to change whether due to setgid/setuid or because
of POSIX saved-id semantics.
This adds 3 new fields into image_params:
struct ucred *newcred Non-null if the credentials will change.
bool credential_setid True if the new image is setuid or setgid.
This will pre-determine the new credentials before invoking the image
activators, where the process_exec hook is called. The new credentials
will be installed into the process in the same place as before, after
image activators are done handling the image.
MFC after: 2 weeks
Reviewed by: kib
Sponsored by: EMC / Isilon Storage Division
Differential Revision: https://reviews.freebsd.org/D6544
Use the C99 'static' keyword to hint to the compiler IVs and output digest
sizes. The keyword informs the compiler of the minimum valid size for a given
array. Obviously not every pointer can be validated (i.e., the compiler can
produce false negative but not false positive reports).
No functional change. No ABI change.
Sponsored by: EMC / Isilon Storage Division
Because the size of bool can be implementation defined, make a bool
sysctl handler which handle bools. Userspace sees the bools like
unsigned 8-bit integers. Values are filtered to either 1 or 0 upon
read and write, similar to what a compiler would do.
Requested by: kmacy @
Sponsored by: Mellanox Technologies
have ACLE support built in. The ACLE (ARM C Language Extensions) defines
a set of standardized symbols which indicate the architecture version and
features available. ACLE support is built in to modern compilers (both
clang and gcc), but absent from gcc prior to 4.4.
ARM (the company) provides the acle-compat.h header file to define the
right symbols for older versions of gcc. Basically, acle-compat.h does
for arm about the same thing cdefs.h does for freebsd: defines
standardized macros that work no matter which compiler you use. If ARM
hadn't provided this file we would have ended up with a big #ifdef __arm__
section in cdefs.h with our own compatibility shims.
Remove #include <machine/acle-compat.h> from the zillion other places (an
ever-growing list) that it appears. Since style(9) requires sys/types.h
or sys/param.h early in the include list, and both of those lead to
including cdefs.h, only a couple special cases still need to include
acle-compat.h directly.
Loves it: imp
After the previous changes to fix requests on blocking sockets to complete
across multiple operations, an edge case exists where a request can be
cancelled after it has partially completed. POSIX doesn't appear to
dictate exactly how to handle this case, but in general I feel that
aio_cancel() should arrange to cancel any request it can, but that any
partially completed requests should return a partial completion rather
than ECANCELED. To that end, fix the socket AIO cancellation routine to
return a short read/write if a partially completed request is cancelled
rather than ECANCELED.
Sponsored by: Chelsio Communications
We may enable interrupts from within the callback, e.g. in a data abort
during copyin. If we receive an interrupt at that time pmc_hook will be
called again and, as it is handling userspace stack tracing, will hit a
KASSERT as it checks if the trapframe is from userland.
With this I can run hwpmc with intrng on a ThunderX and have it trace all
CPUs.
Obtained from: ABT Systems Ltd
Sponsored by: The FreeBSD Foundation
Always requeue an AIO job at the head of the socket buffer's queue if
sosend() or soreceive() returns EWOULDBLOCK on a blocking socket.
Previously, requests were only requeued if they returned EWOULDBLOCK
and completed no data. Now after a partial completion on a blocking
socket the request is queued and the remaining request is retried when
the socket is ready. This allows writes larger than the currently
available space on a blocking socket to fully complete. Reads on a
blocking socket that satifsy the low watermark can still return a short
read (same as read()).
In order to track previously completed data, the internal 'status'
field of the AIO job is used to store the amount of previously
computed data.
Non-blocking sockets continue to return short completions for both
reads and writes.
Add a test for a "large" AIO write on a blocking socket that writes
twice the socket buffer size to a UNIX domain socket.
Sponsored by: Chelsio Communications
Add a bit_count function, which efficiently counts the number of bits set in
a bitstring.
sys/sys/bitstring.h
tests/sys/sys/bitstring_test.c
share/man/man3/bitstring.3
Add bit_alloc
sys/kern/subr_unit.c
Use bit_count instead of a naive counting loop in check_unrhdr, used
when INVARIANTS are enabled. The userland test runs about 6x faster
in a generic build, or 8.5x faster when built for Nehalem, which has
the POPCNT instruction.
sys/sys/param.h
Bump __FreeBSD_version due to the addition of bit_alloc
UPDATING
Add a note about the ABI incompatibility of the bitstring(3)
changes, as suggested by lidl.
Suggested by: gibbs
Reviewed by: gibbs, ngie
MFC after: 9 days
X-MFC-With: 299090, 300538
Relnotes: yes
Sponsored by: Spectra Logic Corp
Differential Revision: https://reviews.freebsd.org/D6255
pause_sbt(). This allows pause() to continue working during a panic()
which is not invoking KDB. This is useful when debugging graphics
drivers using the LinuxKPI.
Obtained from: kmacy @
MFC after: 1 week
sglist_count_vmpages() determines the number of segments required for
a buffer described by an array of VM pages. sglist_append_vmpages()
adds the segments described by such a buffer to an sglist. The latter
function is largely pulled from sglist_append_bio(), and
sglist_append_bio() now uses sglist_append_vmpages().
Reviewed by: kib
Sponsored by: Chelsio Communications
Add a pair of bus methods that can be used to "map" resources for direct
CPU access using bus_space(9). bus_map_resource() creates a mapping and
bus_unmap_resource() releases a previously created mapping. Mappings are
described by 'struct resource_map' object. Pointers to these objects can
be passed as the first argument to the bus_space wrapper API used for bus
resources.
Drivers that wish to map all of a resource using default settings
(for example, using uncacheable memory attributes) do not need to change.
However, drivers that wish to use non-default settings can now do so
without jumping through hoops.
First, an RF_UNMAPPED flag is added to request that a resource is not
implicitly mapped with the default settings when it is activated. This
permits other activation steps (such as enabling I/O or memory decoding
in a device's PCI command register) to be taken without creating a
mapping. Right now the AGP drivers don't set RF_ACTIVE to avoid using
up a large amount of KVA to map the AGP aperture on 32-bit platforms.
Once RF_UNMAPPED is supported on all platforms that support AGP this
can be changed to using RF_UNMAPPED with RF_ACTIVE instead.
Second, bus_map_resource accepts an optional structure that defines
additional settings for a given mapping.
For example, a driver can now request to map only a subset of a resource
instead of the entire range. The AGP driver could also use this to only
map the first page of the aperture (IIRC, it calls pmap_mapdev() directly
to map the first page currently). I will also eventually change the
PCI-PCI bridge driver to request mappings of the subset of the I/O window
resource on its parent side to create mappings for child devices rather
than passing child resources directly up to nexus to be mapped. This
also permits bridges that do address translation to request suitable
mappings from a resource on the "upper" side of the bus when mapping
resources on the "lower" side of the bus.
Another attribute that can be specified is an alternate memory attribute
for memory-mapped resources. This can be used to request a
Write-Combining mapping of a PCI BAR in an MI fashion. (Currently the
drivers that do this call pmap_change_attr() directly for x86 only.)
Note that this commit only adds the MI framework. Each platform needs
to add support for handling RF_UNMAPPED and thew new
bus_map/unmap_resource methods. Generally speaking, any drivers that
are calling rman_set_bustag() and rman_set_bushandle() need to be
updated.
Discussed on: arch
Reviewed by: cem
Differential Revision: https://reviews.freebsd.org/D5237
This change includes support for SCSI SMR drives (which conform to the
Zoned Block Commands or ZBC spec) and ATA SMR drives (which conform to
the Zoned ATA Command Set or ZAC spec) behind SAS expanders.
This includes full management support through the GEOM BIO interface, and
through a new userland utility, zonectl(8), and through camcontrol(8).
This is now ready for filesystems to use to detect and manage zoned drives.
(There is no work in progress that I know of to use this for ZFS or UFS, if
anyone is interested, let me know and I may have some suggestions.)
Also, improve ATA command passthrough and dispatch support, both via ATA
and ATA passthrough over SCSI.
Also, add support to camcontrol(8) for the ATA Extended Power Conditions
feature set. You can now manage ATA device power states, and set various
idle time thresholds for a drive to enter lower power states.
Note that this change cannot be MFCed in full, because it depends on
changes to the struct bio API that break compatilibity. In order to
avoid breaking the stable API, only changes that don't touch or depend on
the struct bio changes can be merged. For example, the camcontrol(8)
changes don't depend on the new bio API, but zonectl(8) and the probe
changes to the da(4) and ada(4) drivers do depend on it.
Also note that the SMR changes have not yet been tested with an actual
SCSI ZBC device, or a SCSI to ATA translation layer (SAT) that supports
ZBC to ZAC translation. I have not yet gotten a suitable drive or SAT
layer, so any testing help would be appreciated. These changes have been
tested with Seagate Host Aware SATA drives attached to both SAS and SATA
controllers. Also, I do not have any SATA Host Managed devices, and I
suspect that it may take additional (hopefully minor) changes to support
them.
Thanks to Seagate for supplying the test hardware and answering questions.
sbin/camcontrol/Makefile:
Add epc.c and zone.c.
sbin/camcontrol/camcontrol.8:
Document the zone and epc subcommands.
sbin/camcontrol/camcontrol.c:
Add the zone and epc subcommands.
Add auxiliary register support to build_ata_cmd(). Make sure to
set the CAM_ATAIO_NEEDRESULT, CAM_ATAIO_DMA, and CAM_ATAIO_FPDMA
flags as appropriate for ATA commands.
Add a new get_ata_status() function to parse ATA result from SCSI
sense descriptors (for ATA passthrough over SCSI) and ATA I/O
requests.
sbin/camcontrol/camcontrol.h:
Update the build_ata_cmd() prototype
Add get_ata_status(), zone(), and epc().
sbin/camcontrol/epc.c:
Support for ATA Extended Power Conditions features. This includes
support for all features documented in the ACS-4 Revision 12
specification from t13.org (dated February 18, 2016).
The EPC feature set allows putting a drive into a power power mode
immediately, or setting timeouts so that the drive will
automatically enter progressively lower power states after various
idle times.
sbin/camcontrol/fwdownload.c:
Update the firmware download code for the new build_ata_cmd()
arguments.
sbin/camcontrol/zone.c:
Implement support for Shingled Magnetic Recording (SMR) drives
via SCSI Zoned Block Commands (ZBC) and ATA Zoned Device ATA
Command Set (ZAC).
These specs were developed in concert, and are functionally
identical. The primary differences are due to SCSI and ATA
differences. (SCSI is big endian, ATA is little endian, for
example.)
This includes support for all commands defined in the ZBC and
ZAC specs.
sys/cam/ata/ata_all.c:
Decode a number of additional ATA command names in ata_op_string().
Add a new CCB building function, ata_read_log().
Add ata_zac_mgmt_in() and ata_zac_mgmt_out() CCB building
functions. These support both DMA and NCQ encapsulation.
sys/cam/ata/ata_all.h:
Add prototypes for ata_read_log(), ata_zac_mgmt_out(), and
ata_zac_mgmt_in().
sys/cam/ata/ata_da.c:
Revamp the ada(4) driver to support zoned devices.
Add four new probe states to gather information needed for zone
support.
Add a new adasetflags() function to avoid duplication of large
blocks of flag setting between the async handler and register
functions.
Add new sysctl variables that describe zone support and paramters.
Add support for the new BIO_ZONE bio, and all of its subcommands:
DISK_ZONE_OPEN, DISK_ZONE_CLOSE, DISK_ZONE_FINISH, DISK_ZONE_RWP,
DISK_ZONE_REPORT_ZONES, and DISK_ZONE_GET_PARAMS.
sys/cam/scsi/scsi_all.c:
Add command descriptions for the ZBC IN/OUT commands.
Add descriptions for ZBC Host Managed devices.
Add a new function, scsi_ata_pass() to do ATA passthrough over
SCSI. This will eventually replace scsi_ata_pass_16() -- it
can create the 12, 16, and 32-byte variants of the ATA
PASS-THROUGH command, and supports setting all of the
registers defined as of SAT-4, Revision 5 (March 11, 2016).
Change scsi_ata_identify() to use scsi_ata_pass() instead of
scsi_ata_pass_16().
Add a new scsi_ata_read_log() function to facilitate reading
ATA logs via SCSI.
sys/cam/scsi/scsi_all.h:
Add the new ATA PASS-THROUGH(32) command CDB. Add extended and
variable CDB opcodes.
Add Zoned Block Device Characteristics VPD page.
Add ATA Return SCSI sense descriptor.
Add prototypes for scsi_ata_read_log() and scsi_ata_pass().
sys/cam/scsi/scsi_da.c:
Revamp the da(4) driver to support zoned devices.
Add five new probe states, four of which are needed for ATA
devices.
Add five new sysctl variables that describe zone support and
parameters.
The da(4) driver supports SCSI ZBC devices, as well as ATA ZAC
devices when they are attached via a SCSI to ATA Translation (SAT)
layer. Since ZBC -> ZAC translation is a new feature in the T10
SAT-4 spec, most SATA drives will be supported via ATA commands
sent via the SCSI ATA PASS-THROUGH command. The da(4) driver will
prefer the ZBC interface, if it is available, for performance
reasons, but will use the ATA PASS-THROUGH interface to the ZAC
command set if the SAT layer doesn't support translation yet.
As I mentioned above, ZBC command support is untested.
Add support for the new BIO_ZONE bio, and all of its subcommands:
DISK_ZONE_OPEN, DISK_ZONE_CLOSE, DISK_ZONE_FINISH, DISK_ZONE_RWP,
DISK_ZONE_REPORT_ZONES, and DISK_ZONE_GET_PARAMS.
Add scsi_zbc_in() and scsi_zbc_out() CCB building functions.
Add scsi_ata_zac_mgmt_out() and scsi_ata_zac_mgmt_in() CCB/CDB
building functions. Note that these have return values, unlike
almost all other CCB building functions in CAM. The reason is
that they can fail, depending upon the particular combination
of input parameters. The primary failure case is if the user
wants NCQ, but fails to specify additional CDB storage. NCQ
requires using the 32-byte version of the SCSI ATA PASS-THROUGH
command, and the current CAM CDB size is 16 bytes.
sys/cam/scsi/scsi_da.h:
Add ZBC IN and ZBC OUT CDBs and opcodes.
Add SCSI Report Zones data structures.
Add scsi_zbc_in(), scsi_zbc_out(), scsi_ata_zac_mgmt_out(), and
scsi_ata_zac_mgmt_in() prototypes.
sys/dev/ahci/ahci.c:
Fix SEND / RECEIVE FPDMA QUEUED in the ahci(4) driver.
ahci_setup_fis() previously set the top bits of the sector count
register in the FIS to 0 for FPDMA commands. This is okay for
read and write, because the PRIO field is in the only thing in
those bits, and we don't implement that further up the stack.
But, for SEND and RECEIVE FPDMA QUEUED, the subcommand is in that
byte, so it needs to be transmitted to the drive.
In ahci_setup_fis(), always set the the top 8 bits of the
sector count register. We need it in both the standard
and NCQ / FPDMA cases.
sys/geom/eli/g_eli.c:
Pass BIO_ZONE commands through the GELI class.
sys/geom/geom.h:
Add g_io_zonecmd() prototype.
sys/geom/geom_dev.c:
Add new DIOCZONECMD ioctl, which allows sending zone commands to
disks.
sys/geom/geom_disk.c:
Add support for BIO_ZONE commands.
sys/geom/geom_disk.h:
Add a new flag, DISKFLAG_CANZONE, that indicates that a given
GEOM disk client can handle BIO_ZONE commands.
sys/geom/geom_io.c:
Add a new function, g_io_zonecmd(), that handles execution of
BIO_ZONE commands.
Add permissions check for BIO_ZONE commands.
Add command decoding for BIO_ZONE commands.
sys/geom/geom_subr.c:
Add DDB command decoding for BIO_ZONE commands.
sys/kern/subr_devstat.c:
Record statistics for REPORT ZONES commands. Note that the
number of bytes transferred for REPORT ZONES won't quite match
what is received from the harware. This is because we're
necessarily counting bytes coming from the da(4) / ada(4) drivers,
which are using the disk_zone.h interface to communicate up
the stack. The structure sizes it uses are slightly different
than the SCSI and ATA structure sizes.
sys/sys/ata.h:
Add many bit and structure definitions for ZAC, NCQ, and EPC
command support.
sys/sys/bio.h:
Convert the bio_cmd field to a straight enumeration. This will
yield more space for additional commands in the future. After
change r297955 and other related changes, this is now possible.
Converting to an enumeration will also prevent use as a bitmask
in the future.
sys/sys/disk.h:
Define the DIOCZONECMD ioctl.
sys/sys/disk_zone.h:
Add a new API for managing zoned disks. This is very close to
the SCSI ZBC and ATA ZAC standards, but uses integers in native
byte order instead of big endian (SCSI) or little endian (ATA)
byte arrays.
This is intended to offer to the complete feature set of the ZBC
and ZAC disk management without requiring the application developer
to include SCSI or ATA headers. We also use one set of headers
for ioctl consumers and kernel bio-level consumers.
sys/sys/param.h:
Bump __FreeBSD_version for sys/bio.h command changes, and inclusion
of SMR support.
usr.sbin/Makefile:
Add the zonectl utility.
usr.sbin/diskinfo/diskinfo.c
Add disk zoning capability to the 'diskinfo -v' output.
usr.sbin/zonectl/Makefile:
Add zonectl makefile.
usr.sbin/zonectl/zonectl.8
zonectl(8) man page.
usr.sbin/zonectl/zonectl.c
The zonectl(8) utility. This allows managing SCSI or ATA zoned
disks via the disk_zone.h API. You can report zones, reset write
pointers, get parameters, etc.
Sponsored by: Spectra Logic
Differential Revision: https://reviews.freebsd.org/D6147
Reviewed by: wblock (documentation)
While looking at r300073, I noticed these incorrect comments in the context
of the diff.
Reviewed by: imp, jhb
Differential Revision: https://reviews.freebsd.org/D6431
needed in later changes where we may not be able to lock the pic list lock
to perform a lookup, e.g. from within interrupt context.
Obtained from: ABT Systems Ltd
Sponsored by: The FreeBSD Foundation
opened in O_SYNC mode, at least for UFS. This also handles
truncation, done due to the O_SYNC | O_TRUNC flags combination to
open(2), in synchronous way.
Noted by: bde
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
"iflib is a library to eliminate the need for frequently duplicated device
independent logic propagated (poorly) across many network drivers."
Participation is purely optional. The IFLIB kernel config option is
provided for drivers that want to transition between legacy and iflib
modes of operation. ixl and ixgbe driver conversions will be committed
shortly. We hope to see participation from the Broadcom and maybe
Chelsio drivers in the near future.
Submitted by: mmacy@nextbsd.org
Reviewed by: gallatin
Differential Revision: D5211
- Avoid a conditional branch on the return value of sleepq_resume_thread()
by ORing its return value into the boolean wakeup_swapper. This is
consistent with other sleepqueue functions which just pass this return
value to their caller.
- sleepq_resume_thread() unconditionally removes the thread from its queue,
so there's no need to maintain a pointer to the next element in the queue.
MFC after: 2 weeks
It has no counterpart among the other lock primitives and has been a
no-op for years. Mutex consistency checks are generally done whenver
INVARIANTS is enabled.
devd requires location and pnpinfo strings generated by bus drivers
to be formatted as a list of name=value keypairs. Non-conforming
bus drivers cause devd to mis-parse device events for these buses.
Note that this documents the desired requirements. devctl_safe_quote()
doesn't yet escape backslash characters, and devd doesn't handle escaped
characters in quoted values.
Differential Revision: https://reviews.freebsd.org/D6252
intention of the POSIX IEEE Std 1003.1TM-2008/Cor 1-2013.
A robust mutex is guaranteed to be cleared by the system upon either
thread or process owner termination while the mutex is held. The next
mutex locker is then notified about inconsistent mutex state and can
execute (or abandon) corrective actions.
The patch mostly consists of small changes here and there, adding
neccessary checks for the inconsistent and abandoned conditions into
existing paths. Additionally, the thread exit handler was extended to
iterate over the userspace-maintained list of owned robust mutexes,
unlocking and marking as terminated each of them.
The list of owned robust mutexes cannot be maintained atomically
synchronous with the mutex lock state (it is possible in kernel, but
is too expensive). Instead, for the duration of lock or unlock
operation, the current mutex is remembered in a special slot that is
also checked by the kernel at thread termination.
Kernel must be aware about the per-thread location of the heads of
robust mutex lists and the current active mutex slot. When a thread
touches a robust mutex for the first time, a new umtx op syscall is
issued which informs about location of lists heads.
The umtx sleep queues for PP and PI mutexes are split between
non-robust and robust.
Somewhat unrelated changes in the patch:
1. Style.
2. The fix for proper tdfind() call use in umtxq_sleep_pi() for shared
pi mutexes.
3. Removal of the userspace struct pthread_mutex m_owner field.
4. The sysctl kern.ipc.umtx_vnode_persistent is added, which controls
the lifetime of the shared mutex associated with a vnode' page.
Reviewed by: jilles (previous version, supposedly the objection was fixed)
Discussed with: brooks, Martin Simmons <martin@lispworks.com> (some aspects)
Tested by: pho
Sponsored by: The FreeBSD Foundation
interface with 5 methods to mirror the 5 MSI/MSI-X methods in the pcib
interface. The pcib driver will need to perform a device specific lookup
to find the MSI controller and pass this to intrng as the xref. Intrng
will finally find the controller and have it handle the requested operation.
Obtained from: ABT Systems Ltd
MFH: yes
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D5985
It seems that at present vfs_read_dirent() is used only with filesystems
that do not support cookies, so the bug never manifested itself.
MFC after: 1 week
This is a bit hackish, but the flag is currently set only for ZFS
snapshots mounted under .zfs. mountcheckdirs() can change cdir/rdir
references to a covered vnode. But for the said snapshots the covered
vnode is really ephemeral and it must never be accessed (except
for a few specific cases).
To do: consider removing mountcheckdirs() entirely
MFC after: 5 days
Currently, Application Processors (non-boot CPUs) are started by
MD code at SI_SUB_CPU, but they are kept waiting in a "pen" until
SI_SUB_SMP at which point they are released to run kernel threads.
SI_SUB_SMP is one of the last SYSINIT levels, so APs don't enter
the scheduler and start running threads until fairly late in the
boot.
This change moves SI_SUB_SMP up to just before software interrupt
threads are created allowing the APs to start executing kernel
threads much sooner (before any devices are probed). This allows
several initialization routines that need to perform initialization
on all CPUs to now perform that initialization in one step rather
than having to defer the AP initialization to a second SYSINIT run
at SI_SUB_SMP. It also permits all CPUs to be available for
handling interrupts before any devices are probed.
This last feature fixes a problem on with interrupt vector exhaustion.
Specifically, in the old model all device interrupts were routed
onto the boot CPU during boot. Later after the APs were released at
SI_SUB_SMP, interrupts were redistributed across all CPUs.
However, several drivers for multiqueue hardware allocate N interrupts
per CPU in the system. In a system with many CPUs, just a few drivers
doing this could exhaust the available pool of interrupt vectors on
the boot CPU as each driver was allocating N * mp_ncpu vectors on the
boot CPU. Now, drivers will allocate interrupts on their desired CPUs
during boot meaning that only N interrupts are allocated from the boot
CPU instead of N * mp_ncpu.
Some other bits of code can also be simplified as smp_started is
now true much earlier and will now always be true for these bits of
code. This removes the need to treat the single-CPU boot environment
as a special case.
As a transition aid, the new behavior is available under a new kernel
option (EARLY_AP_STARTUP). This will allow the option to be turned off
if need be during initial testing. I plan to enable this on x86 by
default in a followup commit in the next few days and to have all
platforms moved over before 11.0. Once the transition is complete,
the option will be removed along with the !EARLY_AP_STARTUP code.
These changes have only been tested on x86. Other platform maintainers
are encouraged to port their architectures over as well. The main
things to check for are any uses of smp_started in MD code that can be
simplified and SI_SUB_SMP SYSINITs in MD code that can be removed in
the EARLY_AP_STARTUP case (e.g. the interrupt shuffling).
PR: kern/199321
Reviewed by: markj, gnn, kib
Sponsored by: Netflix
missing /dev directory makes one end up with a completely deaf (init
without stdout/stderr) system with no hints on the console, unless
you've booted up with bootverbose.
MFC after: 1 month
Sponsored by: The FreeBSD Foundation
and returns it referenced.
The function is similar to vfs_hash_get(9), but unlike the later,
returned vnode is not locked. This operation cannot be requested with
the vget(9) flags.
Reviewed and tested by: rmacklem
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
bus_get_cpus() returns a specified set of CPUs for a device. It accepts
an enum for the second parameter that indicates the type of cpuset to
request. Currently two valus are supported:
- LOCAL_CPUS (on x86 this returns all the CPUs in the package closest to
the device when DEVICE_NUMA is enabled)
- INTR_CPUS (like LOCAL_CPUS but only returns 1 SMT thread for each core)
For systems that do not support NUMA (or if it is not enabled in the kernel
config), LOCAL_CPUS fails with EINVAL. INTR_CPUS is mapped to 'all_cpus'
by default. The idea is that INTR_CPUS should always return a valid set.
Device drivers which want to use per-CPU interrupts should start using
INTR_CPUS instead of simply assigning interrupts to all available CPUs.
In the future we may wish to add tunables to control the policy of
INTR_CPUS (e.g. should it be local-only or global, should it ignore
SMT threads or not).
The x86 nexus driver exposes the internal set of interrupt CPUs from the
the x86 interrupt code via INTR_CPUS.
The ACPI bus driver and PCI bridge drivers use _PXM to return a suitable
LOCAL_CPUS set when _PXM exists and DEVICE_NUMA is enabled. They also and
the global INTR_CPUS set from the nexus driver with the per-domain set from
_PXM to generate a local INTR_CPUS set for child devices.
Compared to the r298933, this version uses 'struct _cpuset' in
<sys/bus.h> instead of 'cpuset_t' to avoid requiring <sys/param.h>
(<sys/_cpuset.h> still requires <sys/param.h> for MAXCPU even though
<sys/_bitset.h> does not after recent changes).