Combined with earlier nstart/nend removal it allows to remove several locks
from request path of GEOM and few other places. It would be cool if we had
more SMP-friendly statistics, but this helps too.
Sponsored by: iXsystems, Inc.
With the previous reviews, the page lock is no longer required in order
to perform queue operations on a page. It is also no longer needed in
the page queue scans. This change effectively eliminates remaining uses
of the page lock and also the false sharing caused by multiple pages
sharing a page lock.
Reviewed by: jeff
Tested by: pho
Sponsored by: Netflix, Intel
Differential Revision: https://reviews.freebsd.org/D22885
an exclusive object lock.
Previously swap space was freed on a best effort basis when a page that
had valid swap was dirtied, thus invalidating the swap copy. This may be
done inconsistently and requires the object lock which is not always
convenient.
Instead, track when swap space is present. The first dirty is responsible
for deleting space or setting PGA_SWAP_FREE which will trigger background
scans to free the swap space.
Simplify the locking in vm_fault_dirty() now that we can reliably identify
the first dirty.
Discussed with: alc, kib, markj
Differential Revision: https://reviews.freebsd.org/D22654
The current vnode layout is not smp-friendly by having frequently read data
avoidably sharing cachelines with very frequently modified fields. In
particular v_iflag inspected for VI_DOOMED can be found in the same line with
v_usecount. Instead make it available in the same cacheline as the v_op, v_data
and v_type which all get read all the time.
v_type is avoidably 4 bytes while the necessary data will easily fit in 1.
Shrinking it frees up 3 bytes, 2 of which get used here to introduce a new
flag field with a new value: VIRF_DOOMED.
Reviewed by: kib, jeff
Differential Revision: https://reviews.freebsd.org/D22715
tightening constraints on busy as a precursor to lockless page lookup and
should largely be a NOP for these cases.
Reviewed by: alc, kib, markj
Differential Revision: https://reviews.freebsd.org/D22611
Atomics are used for page busy and valid state when the shared busy is
held. The details of the locking protocol and valid and dirty
synchronization are in the updated vm_page.h comments.
Reviewed by: kib, markj
Tested by: pho
Sponsored by: Netflix, Intel
Differential Revision: https://reviews.freebsd.org/D21594
There are several mechanisms by which a vm_page reference is held,
preventing the page from being freed back to the page allocator. In
particular, holding the page's object lock is sufficient to prevent the
page from being freed; holding the busy lock or a wiring is sufficent as
well. These references are protected by the page lock, which must
therefore be acquired for many per-page operations. This results in
false sharing since the page locks are external to the vm_page
structures themselves and each lock protects multiple structures.
Transition to using an atomically updated per-page reference counter.
The object's reference is counted using a flag bit in the counter. A
second flag bit is used to atomically block new references via
pmap_extract_and_hold() while removing managed mappings of a page.
Thus, the reference count of a page is guaranteed not to increase if the
page is unbusied, unmapped, and the object's write lock is held. As
a consequence of this, the page lock no longer protects a page's
identity; operations which move pages between objects are now
synchronized solely by the objects' locks.
The vm_page_wire() and vm_page_unwire() KPIs are changed. The former
requires that either the object lock or the busy lock is held. The
latter no longer has a return value and may free the page if it releases
the last reference to that page. vm_page_unwire_noq() behaves the same
as before; the caller is responsible for checking its return value and
freeing or enqueuing the page as appropriate. vm_page_wire_mapped() is
introduced for use in pmap_extract_and_hold(). It fails if the page is
concurrently being unmapped, typically triggering a fallback to the
fault handler. vm_page_wire() no longer requires the page lock and
vm_page_unwire() now internally acquires the page lock when releasing
the last wiring of a page (since the page lock still protects a page's
queue state). In particular, synchronization details are no longer
leaked into the caller.
The change excises the page lock from several frequently executed code
paths. In particular, vm_object_terminate() no longer bounces between
page locks as it releases an object's pages, and direct I/O and
sendfile(SF_NOCACHE) completions no longer require the page lock. In
these latter cases we now get linear scalability in the common scenario
where different threads are operating on different files.
__FreeBSD_version is bumped. The DRM ports have been updated to
accomodate the KPI changes.
Reviewed by: jeff (earlier version)
Tested by: gallatin (earlier version), pho
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D20486
It is unused, the ABI was broken in r322969, and it is broken by design
(more than MDNPAD md devices can exist and there is no way to retreive
them with this interface).
mdconfig(8) was converted to use libgeom to obtain this information
in r157160 and any other consumers of MDIOCLIST should likewise be
converted.
Reviewed by: emaste
Relnotes: yes
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D18936
I/O operations already in its queue were not being properly drained.
The GEOM framework does the queue draining, but the device driver
needs to wait for the draining to happen. The waiting is done by
adding a g_md_providergone() function to wait for the I/O operations
to finish up.
It is likely that every GEOM provider that implements orphaning
attached GEOM consumers needs to use the "providergone" mechanism
for this same reason, but some of them do not do so. Apparently
Kenneth Merry (ken@) added the drain for just such races, but he
missed adding it to some of the device drivers that needed it.
Submitted by: Chuck Silvers
Reviewed by: imp
Tested by: Chuck Silvers
MFC after: 1 week
Sponsored by: Netflix
o In vm_pager_bufferinit() create pbuf_zone and start accounting on how many
pbufs are we going to have set.
In various subsystems that are going to utilize pbufs create private zones
via call to pbuf_zsecond_create(). The latter calls uma_zsecond_create(),
and sets a limit on created zone. After startup preallocate pbufs according
to requirements of all pbuf zones.
Subsystems that used to have a private limit with old allocator now have
private pbuf zones: md(4), fusefs, NFS client, smbfs, VFS cluster, FFS,
swap, vnode pager.
The following subsystems use shared pbuf zone: cam(4), nvme(4), physio(9),
aio(4). They should have their private limits, but changing that is out of
scope of this commit.
o Fetch tunable value of kern.nswbuf from init_param2() and while here move
NSWBUF_MIN to opt_param.h and eliminate opt_swap.h, that was holding only
this option.
Default values aren't touched by this commit, but they probably should be
reviewed wrt to modern hardware.
This change removes a tight bottleneck from sendfile(2) operation, that
uses pbufs in vnode pager. Other pagers also would benefit from faster
allocation.
Together with: gallatin
Tested by: pho
g_io_deliver() finishing initialization of the bio, but g_io_deliver()
actually destroys the bio. INVARIANTS makes the bug obvious by
overwriting the bio with garbage.
Restore the old order for calling devstat (except don't restore not calling
it for the error case), and translate to the devstat KPI so that this order
works.
Reviewed by: kib
implement not double-caching for reads from vnode-backed md devices.
Use VOP_ADVISE() similarly instead of !IO_DIRECT unsimilarly for writes.
Add a "cache" option to mdconfig to allow changing the default of not
caching.
This depends on a recent commit to fix VOP_ADVISE(). A previous version
had optimizations for sequential i/o's (merge the i/o's and only uncache
for discontiguous i/o's and for full blocks), but optimizations and
knowledge of block boundaries belong in VOP_ADVISE(). Read-ahead should
also be handled better, by supporting it in md and discarding it in
VOP_ADVISE().
POSIX_FADV_DONTNEED is ignored by zfs, but so is IO_DIRECT.
POSIX_FADV_DONTNEED works better than IO_DIRECT if it is not ignored,
since it only discards from the buffer cache immediately, while
IO_DIRECT also discards from the page cache immediately.
IO_DIRECT was not used for writes since it was claimed to be too slow,
but most of the slowness for writes is from doing them synchronously by
default. Non-synchronous writes still deadlock in many cases.
IO_DIRECT only has a special implementation for ffs reads with DIRECTIO
configured. Otherwise, if it is not ignored than it uses the buffer and
page caches normally except for discarding everything after each i/o,
and then it has much the same overheads as POSIX_FADV_DONTNEED. The
overheads for reading with ffs and DIRECTIO were similar in tests of md.
Reviewed by: kib
devstat_end_transaction() was called before the i/o was actually ended
(by delivering it to GEOM), so at least the i/o length was messed up.
It was always recorded as 0, so the average transaction size and the
average transfer rate was always displayed as 0.
devstat_end_transaction() was not called at all for the error case, so
there were sometimes multiple starts per end. I didn't observe this in
practice and don't know if it did much damage. I think it extended the
length of the i/o to the next transaction.
Reviewed by: kib
On PowerNV systems, the rootfs is passed through kexec, which loads the rootfs
into memory and set two fdt entries to describe where the file is located in
the memory;
I need to pass this memory region to the md device as a mfs_root, but, current
md driver does not support two things:
* Just getting a pointer from an external (bootloader) memory. If I need to
workaround it, I would need to declare a static array and memcopy from this
external memory to this static variable.
* The size of the image. The usage of mfs_root_end, which is not a pointer,
seems to be not possible for this prestaged scenario.
This patch simply adds a new way to load mfs_root from memory.
Differential Revision: https://reviews.freebsd.org/D15625
Approved by: kib, jhibbits (mentor)
opt_compat.h is mentioned in nearly 180 files. In-progress network
driver compabibility improvements may add over 100 more so this is
closer to "just about everywhere" than "only some files" per the
guidance in sys/conf/options.
Keep COMPAT_LINUX32 in opt_compat.h as it is confined to a subset of
sys/compat/linux/*.c. A fake _COMPAT_LINUX option ensure opt_compat.h
is created on all architectures.
Move COMPAT_LINUXKPI to opt_dontuse.h as it is only used to control the
set of compiled files.
Reviewed by: kib, cem, jhb, jtl
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D14941
This is more correct in that ioctl commands have no meaning until they
hit the handler associated with the file descriptor.
Add support for MDIOCRESIZE_32 which was missed when it was added.
Reviewed by: cem, kib, markj (various versions)
Obtained from: CheriBSD
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D14714
Include _uio.h instead of uio.h in several headers to reduce header
polution.
Fix a few places that relied on header polution to get the uio.h header.
I have not moved struct uio as many more things that use it rely on
header polution to get other definitions from uio.h.
Reviewed by: cem, kib, markj
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D14811
This allows compatibility translation to take place on the stack
(md_ioctl is too big) and is more suitable as a public interface within
the kernel than the kern_ioctl interface.
Except for the initialization of the md_req from the md_ioctl
(including detection of kernel md_file pointers) and the updating
of the md_ioctl prior to return, this is a mechanical replacment
of md_ioctl and mdio with md_req and mdr.
Reviewed by: markj, cem, kib (assorted versions)
Obtained from: CheriBSD
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D14704
Move locks from outside ioctl to the individual implementations.
This is the first step of changing the implementations to act on a
kernel-internal request struct rather than on struct md_ioctl and to
removing the use of kern_ioctl in mountroot.
Reviewed by: cem, kib, markj (prior version)
Obtained from: CheriBSD
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D14700
unconditionally incrementing i in the loop;
Reported by: cem
MFC with: r330880
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D14685
Always terminate the list with -1 and document the ioctl behavior.
This preserves existing behavior as seen from userspace with the
addition of the unconditional termination which will not be seen by
working consumers of MDIOCLIST.
Because this ioctl can only be performed by root (in default
configurations) and is not used in the base system this bug is not
deemed to warrant either a security advisory or an eratta notice.
Reviewed by: kib
Obtained from: CheriBSD
Discussed with: security-officer (gordon)
MFC after: 3 days
Security: kernel heap buffer overflow
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D14685
If the MD_VERIFY flag is set, we should use O_VERIFY. If the MD_VERIFY flag
is not set, we should not.
Reviewed by: stevek
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D13814
MD_READONLY flag for the md device automatically instantiated during
kernel init for an mdroot filesystem.
Note that there is specifically and by design no tunable or sysctl
control over this feature. Without this option, you already have control
over whether the mdroot fs is writeable using vfs.root.mountfrom.options
from loader(8), the root_rw_mount rcvar, and by using "mount -u[rw] /"
or equivelent on the fly. This option is being added to provide a way
to make the mdroot fs truly immutable before userland code begins running.
Differential Revision: https://reviews.freebsd.org/D13411
Mainly focus on files that use BSD 3-Clause license.
The Software Package Data Exchange (SPDX) group provides a specification
to make it easier for automated tools to detect and summarize well known
opensource licenses. We are gradually adopting the specification, noting
that the tags are considered only advisory and do not, in any way,
superceed or replace the license texts.
Special thanks to Wind River for providing access to "The Duke of
Highlander" tool: an older (2014) run over FreeBSD tree was useful as a
starting point.
on backing file device and inode numbers.
This is useful for gmountver(8) regression tests.
MFC after: 2 weeks
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D12230
mark the page as referenced rather than calling vm_page_activate(). This
allows the page's act_count to grow beyond ACT_INIT and better reflect
its usage. (See also r324146, which modified a function used by tmpfs,
uiomove_object_page(), to behave in the same way.)
Reviewed by: kib, markj
MFC after: 2 weeks
This feature comes from the fact that we rely memory-backed md(4)
in our build process heavily. However, if the build goes haywire
the allocated resources (i.e. swap and memory-backed md(4)'s) need
to be purged. It is extremely useful to have ability to attach
arbitrary labels to each of the virtual disks so that they can
be identified and GC'ed if neecessary.
MFC after: 4 weeks
Differential Revision: https://reviews.freebsd.org/D10457
The swap space backing a clean page is released when it is first dirtied,
so there's no need to attempt to release swap space when the page is
already dirty.
Reviewed by: alc
MFC after: 1 week
After such a failure, the page is invalid, so there's point in keeping it
around. Moreover, such pages were not being inserted into the active queue,
making them unreclaimable until a subsequent write or delete made them
valid.
Reported by: alc
Reviewed by: alc (previous revision)
MFC after: 1 week
Such requests would previously mark the entire page as valid, which was
incorrect since nothing guaranteed that the page's contents had been
initialized. This change also modifies subpage BIO_DELETEs so that the
entire page is marked dirty, rather than only a subrange. There is no
benefit to creating partially dirty swap pages.
Reviewed by: alc, kib (previous version)
MFC after: 3 days
Add -o [no]verify option to mdconfig (and document in man page.)
Implement GEOM attribute MNT::verified to ask md if the backing vnode is
verified.
Check for MNT::verified in cd9660 mount to flag the mount as MNT_VERIFIED if
the underlying device has been verified.
Reviewed by: rwatson
Approved by: sjg (mentor)
Obtained from: Juniper Networks, Inc.
Differential Revision: https://reviews.freebsd.org/D2902
Renumber cluase 4 to 3, per what everybody else did when BSD granted
them permission to remove clause 3. My insistance on keeping the same
numbering for legal reasons is too pedantic, so give up on that point.
Submitted by: Jan Schaumann <jschauma@stevens.edu>
Pull Request: https://github.com/freebsd/freebsd/pull/96
meta-data, copy it into the softc structure.
When returning md(4) device details to the caller, include the file name in
any MD_PRELOAD type devices if it is set (first character is not NUL.)
In mdconfig, for "preload" type md(4) devices, if there is file config
available, print it in the file column of the output.
Reviewed by: brooks
Approved by: sjg (mentor)
MFC after: 1 month
Sponsored by: Juniper Networks, Inc.
Differential Revision: https://reviews.freebsd.org/D9529
is defined explicitly. It's kinda pointless and results in extra step in
boot sequence which is not really needed, i.e.:
md0: Embedded image 1331200 bytes at 0x8038b7b4
Trying to mount root from ufs:/dev/md0 []...
Mounting from ufs:/dev/md0 failed with error 22.
Trying to mount root from ufs:md0.uzip []...
warning: no time-of-day clock registered, system time will not be set accurately
start_init: trying /sbin/init
MD_ROOT_SIZE and embed_mfs.sh were basically retired as part of
https://reviews.freebsd.org/D2903 .
However, when building a kernel with 'options MD_ROOT_SIZE' specified, this
results in a non-working MFS, as within sys/dev/md/md.c we fall within the
wrong # ifdef.
This patch implements the following:
* Allow kernels to be built without the MD_ROOT_SIZE option, which results
in a kernel built as per D2903.
* Allow kernels to be built with the MD_ROOT_SIZE option, which results
in a kernel built similarly to the pre-D2903 way, with the following
differences:
* The MFS is now put in a separate section within the kernel (oldmfs,
so it differs from the mfs section introduced by D2903).
* embed_mfs.sh is changed, so it looks up the oldmfs section within the
kernel, gets its size and offset, sees if the MFS will fit within the
allocated oldmfs section and only if all is well does a dd of the MFS
image into the kernel.
Submitted by: Stanislav Galabov <sgalabov@gmail.com>
Reviewed by: brooks, imp
Differential Revision: https://reviews.freebsd.org/D5093
o With new KPI consumers can request contiguous ranges of pages, and
unlike before, all pages will be kept busied on return, like it was
done before with the 'reqpage' only. Now the reqpage goes away. With
new interface it is easier to implement code protected from race
conditions.
Such arrayed requests for now should be preceeded by a call to
vm_pager_haspage() to make sure that request is possible. This
could be improved later, making vm_pager_haspage() obsolete.
Strenghtening the promises on the business of the array of pages
allows us to remove such hacks as swp_pager_free_nrpage() and
vm_pager_free_nonreq().
o New KPI accepts two integer pointers that may optionally point at
values for read ahead and read behind, that a pager may do, if it
can. These pages are completely owned by pager, and not controlled
by the caller.
This shifts the UFS-specific readahead logic from vm_fault.c, which
should be file system agnostic, into vnode_pager.c. It also removes
one VOP_BMAP() request per hard fault.
Discussed with: kib, alc, jeff, scottl
Sponsored by: Nginx, Inc.
Sponsored by: Netflix
requests which page alignment + size is greater than MAXPHYS. Right
now md(4) over vnode would use the physical buffer of the size MAXPHYS
to map a data of size MAXPHYS + page offset of the user buffer. This
typically corrupts next pbuf, or, if the pbuf used was the last pbuf
in the map, the next page after the pbuf's map.
Split request up to the size of io which fits into pbuf KVA with
alignment, and retry if a part of the bio is left unprocessed.
Reported by: Fabian Keil <fk@fabiankeil.de>
Tested by: Fabian Keil, pho
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
camdd(8) utility.
CCBs may be queued to the driver via the new CAMIOQUEUE ioctl, and
completed CCBs may be retrieved via the CAMIOGET ioctl. User
processes can use poll(2) or kevent(2) to get notification when
I/O has completed.
While the existing CAMIOCOMMAND blocking ioctl interface only
supports user virtual data pointers in a CCB (generally only
one per CCB), the new CAMIOQUEUE ioctl supports user virtual and
physical address pointers, as well as user virtual and physical
scatter/gather lists. This allows user applications to have more
flexibility in their data handling operations.
Kernel memory for data transferred via the queued interface is
allocated from the zone allocator in MAXPHYS sized chunks, and user
data is copied in and out. This is likely faster than the
vmapbuf()/vunmapbuf() method used by the CAMIOCOMMAND ioctl in
configurations with many processors (there are more TLB shootdowns
caused by the mapping/unmapping operation) but may not be as fast
as running with unmapped I/O.
The new memory handling model for user requests also allows
applications to send CCBs with request sizes that are larger than
MAXPHYS. The pass(4) driver now limits queued requests to the I/O
size listed by the SIM driver in the maxio field in the Path
Inquiry (XPT_PATH_INQ) CCB.
There are some things things would be good to add:
1. Come up with a way to do unmapped I/O on multiple buffers.
Currently the unmapped I/O interface operates on a struct bio,
which includes only one address and length. It would be nice
to be able to send an unmapped scatter/gather list down to
busdma. This would allow eliminating the copy we currently do
for data.
2. Add an ioctl to list currently outstanding CCBs in the various
queues.
3. Add an ioctl to cancel a request, or use the XPT_ABORT CCB to do
that.
4. Test physical address support. Virtual pointers and scatter
gather lists have been tested, but I have not yet tested
physical addresses or scatter/gather lists.
5. Investigate multiple queue support. At the moment there is one
queue of commands per pass(4) device. If multiple processes
open the device, they will submit I/O into the same queue and
get events for the same completions. This is probably the right
model for most applications, but it is something that could be
changed later on.
Also, add a new utility, camdd(8) that uses the asynchronous pass(4)
driver interface.
This utility is intended to be a basic data transfer/copy utility,
a simple benchmark utility, and an example of how to use the
asynchronous pass(4) interface.
It can copy data to and from pass(4) devices using any target queue
depth, starting offset and blocksize for the input and ouptut devices.
It currently only supports SCSI devices, but could be easily extended
to support ATA devices.
It can also copy data to and from regular files, block devices, tape
devices, pipes, stdin, and stdout. It does not support queueing
multiple commands to any of those targets, since it uses the standard
read(2)/write(2)/writev(2)/readv(2) system calls.
The I/O is done by two threads, one for the reader and one for the
writer. The reader thread sends completed read requests to the
writer thread in strictly sequential order, even if they complete
out of order. That could be modified later on for random I/O patterns
or slightly out of order I/O.
camdd(8) uses kqueue(2)/kevent(2) to get I/O completion events from
the pass(4) driver and also to send request notifications internally.
For pass(4) devcies, camdd(8) uses a single buffer (CAM_DATA_VADDR)
per CAM CCB on the reading side, and a scatter/gather list
(CAM_DATA_SG) on the writing side. In addition to testing both
interfaces, this makes any potential reblocking of I/O easier. No
data is copied between the reader and the writer, but rather the
reader's buffers are split into multiple I/O requests or combined
into a single I/O request depending on the input and output blocksize.
For the file I/O path, camdd(8) also uses a single buffer (read(2),
write(2), pread(2) or pwrite(2)) on reads, and a scatter/gather list
(readv(2), writev(2), preadv(2), pwritev(2)) on writes.
Things that would be nice to do for camdd(8) eventually:
1. Add support for I/O pattern generation. Patterns like all
zeros, all ones, LBA-based patterns, random patterns, etc. Right
Now you can always use /dev/zero, /dev/random, etc.
2. Add support for a "sink" mode, so we do only reads with no
writes. Right now, you can use /dev/null.
3. Add support for automatic queue depth probing, so that we can
figure out the right queue depth on the input and output side
for maximum throughput. At the moment it defaults to 6.
4. Add support for SATA device passthrough I/O.
5. Add support for random LBAs and/or lengths on the input and
output sides.
6. Track average per-I/O latency and busy time. The busy time
and latency could also feed in to the automatic queue depth
determination.
sys/cam/scsi/scsi_pass.h:
Define two new ioctls, CAMIOQUEUE and CAMIOGET, that queue
and fetch asynchronous CAM CCBs respectively.
Although these ioctls do not have a declared argument, they
both take a union ccb pointer. If we declare a size here,
the ioctl code in sys/kern/sys_generic.c will malloc and free
a buffer for either the CCB or the CCB pointer (depending on
how it is declared). Since we have to keep a copy of the
CCB (which is fairly large) anyway, having the ioctl malloc
and free a CCB for each call is wasteful.
sys/cam/scsi/scsi_pass.c:
Add asynchronous CCB support.
Add two new ioctls, CAMIOQUEUE and CAMIOGET.
CAMIOQUEUE adds a CCB to the incoming queue. The CCB is
executed immediately (and moved to the active queue) if it
is an immediate CCB, but otherwise it will be executed
in passstart() when a CCB is available from the transport layer.
When CCBs are completed (because they are immediate or
passdone() if they are queued), they are put on the done
queue.
If we get the final close on the device before all pending
I/O is complete, all active I/O is moved to the abandoned
queue and we increment the peripheral reference count so
that the peripheral driver instance doesn't go away before
all pending I/O is done.
The new passcreatezone() function is called on the first
call to the CAMIOQUEUE ioctl on a given device to allocate
the UMA zones for I/O requests and S/G list buffers. This
may be good to move off to a taskqueue at some point.
The new passmemsetup() function allocates memory and
scatter/gather lists to hold the user's data, and copies
in any data that needs to be written. For virtual pointers
(CAM_DATA_VADDR), the kernel buffer is malloced from the
new pass(4) driver malloc bucket. For virtual
scatter/gather lists (CAM_DATA_SG), buffers are allocated
from a new per-pass(9) UMA zone in MAXPHYS-sized chunks.
Physical pointers are passed in unchanged. We have support
for up to 16 scatter/gather segments (for the user and
kernel S/G lists) in the default struct pass_io_req, so
requests with longer S/G lists require an extra kernel malloc.
The new passcopysglist() function copies a user scatter/gather
list to a kernel scatter/gather list. The number of elements
in each list may be different, but (obviously) the amount of data
stored has to be identical.
The new passmemdone() function copies data out for the
CAM_DATA_VADDR and CAM_DATA_SG cases.
The new passiocleanup() function restores data pointers in
user CCBs and frees memory.
Add new functions to support kqueue(2)/kevent(2):
passreadfilt() tells kevent whether or not the done
queue is empty.
passkqfilter() adds a knote to our list.
passreadfiltdetach() removes a knote from our list.
Add a new function, passpoll(), for poll(2)/select(2)
to use.
Add devstat(9) support for the queued CCB path.
sys/cam/ata/ata_da.c:
Add support for the BIO_VLIST bio type.
sys/cam/cam_ccb.h:
Add a new enumeration for the xflags field in the CCB header.
(This doesn't change the CCB header, just adds an enumeration to
use.)
sys/cam/cam_xpt.c:
Add a new function, xpt_setup_ccb_flags(), that allows specifying
CCB flags.
sys/cam/cam_xpt.h:
Add a prototype for xpt_setup_ccb_flags().
sys/cam/scsi/scsi_da.c:
Add support for BIO_VLIST.
sys/dev/md/md.c:
Add BIO_VLIST support to md(4).
sys/geom/geom_disk.c:
Add BIO_VLIST support to the GEOM disk class. Re-factor the I/O size
limiting code in g_disk_start() a bit.
sys/kern/subr_bus_dma.c:
Change _bus_dmamap_load_vlist() to take a starting offset and
length.
Add a new function, _bus_dmamap_load_pages(), that will load a list
of physical pages starting at an offset.
Update _bus_dmamap_load_bio() to allow loading BIO_VLIST bios.
Allow unmapped I/O to start at an offset.
sys/kern/subr_uio.c:
Add two new functions, physcopyin_vlist() and physcopyout_vlist().
sys/pc98/include/bus.h:
Guard kernel-only parts of the pc98 machine/bus.h header with
#ifdef _KERNEL.
This allows userland programs to include <machine/bus.h> to get the
definition of bus_addr_t and bus_size_t.
sys/sys/bio.h:
Add a new bio flag, BIO_VLIST.
sys/sys/uio.h:
Add prototypes for physcopyin_vlist() and physcopyout_vlist().
share/man/man4/pass.4:
Document the CAMIOQUEUE and CAMIOGET ioctls.
usr.sbin/Makefile:
Add camdd.
usr.sbin/camdd/Makefile:
Add a makefile for camdd(8).
usr.sbin/camdd/camdd.8:
Man page for camdd(8).
usr.sbin/camdd/camdd.c:
The new camdd(8) utility.
Sponsored by: Spectra Logic
MFC after: 1 week
root disk. The embedded image is linked into the kernel in the .mfs
section.
Add rules and variables to kern.pre.mk and kern.post.mk that handle the
linking of the image. First objcopy is used to generate an object file.
Then, the object file is linked into the kernel.
Submitted by: Steve Kiernan <stevek@juniper.net>
Reviewed by: brooks@
Obtained from: Juniper Networks, Inc.
Differential Revision: https://reviews.freebsd.org/D2903
then threads can sleep on the pip condition.
Avoid to deadlock such threads by correctly awakening the sleeping ones
after the pip is finished.
swapoff side of the bug can likely result in shutdown deadlocks.
Sponsored by: EMC / Isilon Storage Division
Reported by: pho, pluknet
Tested by: pho
the bio is unmapped, so we must map the bio pages into pbuf. This
works around the geom classes which do not follow the MAXPHYS limit on
the i/o size, since such classes do not know about unmapped bios
either.
Reported by: Paolo Pinto <paolo.pinto@netasq.com>
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
When safety requirements are met, it allows to avoid passing I/O requests
to GEOM g_up/g_down thread, executing them directly in the caller context.
That allows to avoid CPU bottlenecks in g_up/g_down threads, plus avoid
several context switches per I/O.
The defined now safety requirements are:
- caller should not hold any locks and should be reenterable;
- callee should not depend on GEOM dual-threaded concurency semantics;
- on the way down, if request is unmapped while callee doesn't support it,
the context should be sleepable;
- kernel thread stack usage should be below 50%.
To keep compatibility with GEOM classes not meeting above requirements
new provider and consumer flags added:
- G_CF_DIRECT_SEND -- consumer code meets caller requirements (request);
- G_CF_DIRECT_RECEIVE -- consumer code meets callee requirements (done);
- G_PF_DIRECT_SEND -- provider code meets caller requirements (done);
- G_PF_DIRECT_RECEIVE -- provider code meets callee requirements (request).
Capable GEOM class can set them, allowing direct dispatch in cases where
it is safe. If any of requirements are not met, request is queued to
g_up or g_down thread same as before.
Such GEOM classes were reviewed and updated to support direct dispatch:
CONCAT, DEV, DISK, GATE, MD, MIRROR, MULTIPATH, NOP, PART, RAID, STRIPE,
VFS, ZERO, ZFS::VDEV, ZFS::ZVOL, all classes based on g_slice KPI (LABEL,
MAP, FLASHMAP, etc).
To declare direct completion capability disk(9) KPI got new flag equivalent
to G_PF_DIRECT_SEND -- DISKFLAG_DIRECT_COMPLETION. da(4) and ada(4) disk
drivers got it set now thanks to earlier CAM locking work.
This change more then twice increases peak block storage performance on
systems with manu CPUs, together with earlier CAM locking changes reaching
more then 1 million IOPS (512 byte raw reads from 16 SATA SSDs on 4 HBAs to
256 user-level threads).
Sponsored by: iXsystems, Inc.
MFC after: 2 months
