Commit Graph

1839 Commits

Author SHA1 Message Date
Kenneth D. Merry
ce625ec719 Change the way that unmapped I/O capability is advertised.
The previous method was to set the D_UNMAPPED_IO flag in the cdevsw
for the driver.  The problem with this is that in many cases (e.g.
sa(4)) there may be some instances of the driver that can handle
unmapped I/O and some that can't.  The isp(4) driver can handle
unmapped I/O, but the esp(4) driver currently cannot.  The cdevsw
is shared among all driver instances.

So instead of setting a flag on the cdevsw, set a flag on the cdev.
This allows drivers to indicate support for unmapped I/O on a
per-instance basis.

sys/conf.h:	Remove the D_UNMAPPED_IO cdevsw flag and replace it
		with an SI_UNMAPPED cdev flag.

kern_physio.c:	Look at the cdev SI_UNMAPPED flag to determine
		whether or not a particular driver can handle
		unmapped I/O.

geom_dev.c:	Set the SI_UNMAPPED flag for all GEOM cdevs.
		Since GEOM will create a temporary mapping when
		needed, setting SI_UNMAPPED unconditionally will
		work.

		Remove the D_UNMAPPED_IO flag.

nvme_ns.c:	Set the SI_UNMAPPED flag on cdevs created here
		if NVME_UNMAPPED_BIO_SUPPORT is enabled.

vfs_aio.c:	In aio_qphysio(), check the SI_UNMAPPED flag on a
		cdev instead of the D_UNMAPPED_IO flag on the cdevsw.

sys/param.h:	Bump __FreeBSD_version to 1000045 for the switch from
		setting the D_UNMAPPED_IO flag in the cdevsw to setting
		SI_UNMAPPED in the cdev.

Reviewed by:	kib, jimharris
MFC after:	1 week
Sponsored by:	Spectra Logic
2013-08-15 22:52:39 +00:00
Alexander Motin
0f0b2fd889 Return error when opening read-only volumes (like RAID4/5/...) for writing.
Previously opens succeeded, but actual write operations returned errors.

Requested by:	peter
MFC after:	2 weeks
2013-08-13 07:56:40 +00:00
Alexander Motin
db8645f05e Oops, wrong constant at r254269. 2013-08-13 06:25:34 +00:00
Alexander Motin
e70b565ba4 Fix reasonable but safe Clang warnings. 2013-08-13 06:21:36 +00:00
Ed Schouten
647a92d62b Fix the formatting of the error message.
The G_MIRROR_DEBUG() macro already appends a newline. Also, most of the
log messages emitted by gmirror start with an uppercase letter.
2013-08-12 18:17:45 +00:00
Andrey V. Elsukov
b74dd6c77b gpt_entries is used as limit for the number of partition entries in
the GEOM_PART. Instead of just using number of entries from the GPT
header, calculate this limit based on the reserved space between
GPT header and first available LBA.

MFC after:	2 weeks
2013-08-08 16:09:20 +00:00
Marcel Moolenaar
e01c6f329a Change <sys/diskpc98.h> to not redefine the same symbols that are
being defined in <sys/diskmbr.h>. Instead give the symbols here a
"PC98_" prefix. This way, both <sys/diskmbr.h> and <sys/diskpc98.h>
can be included in the same C source file.

The renaming is trivial. The only gotcha is that DOSBBSECTOR is
also redefined from 0 to 1. This because DOSBBSECTOR was always
used in conjunction with an addition of 1. The PC98_BBSECTOR symbol
is defined as 1 and the expression is simplified.

Note: it is not believed that ports are seriously impacted; or at
all for that matter.

Approved by: nyan@
2013-08-07 00:00:48 +00:00
Marcel Moolenaar
b9fdaa9b19 Remove inclusion of <sys/diskmbr.h>. We have no business knowing
anything related to MBR in this file.
2013-08-04 21:00:22 +00:00
Alexander Motin
8531bb3f0c Introduce 3 seconds timeout on graid stop command (mostly with -f flag).
Since completion waiting goes in g_event thread, it may cause GEOM deadlock
if consumer on top (for example, ZFS) uses g_event thread for closing.
2013-07-27 15:02:19 +00:00
Konstantin Belousov
a4a65e69c6 When panicing due to the gjournal overflow, print the geom metadata
journal id.

Requested by:	Andreas Longwitz <longwitz@incore.de>
MFC after:	1 week
2013-07-10 10:11:43 +00:00
Konstantin Belousov
cc3d8c35f5 There are several code sequences like
vfs_busy(mp);
      vfs_write_suspend(mp);
which are problematic if other thread starts unmount between two
calls.  The unmount starts a write, while vfs_write_suspend() drain
writers.  On the other hand, unmount drains busy references, causing
the deadlock.

Add a flag argument to vfs_write_suspend and require the callers of it
to specify VS_SKIP_UNMOUNT flag, when the call is performed not in the
mount path, i.e. the covered vnode is not locked.  The suspension is
not attempted if VS_SKIP_UNMOUNT is specified and unmount is in
progress.

Reported and tested by:	Andreas Longwitz <longwitz@incore.de>
Sponsored by:	The FreeBSD Foundation
MFC after:	3 weeks
2013-07-09 20:49:32 +00:00
Steven Hartland
8383a92e5b Bump disk(9) ABI version to signify the addition of d_delmaxsize by r249940.
Ensure that d_delmaxsize is always set, removing init to 0 which could cause
future issues if use cases change.

Allow kern.cam.da.X.delete_max (which maps to d_delmaxsize) to be increased
up to the calculated max after being reduced.

MFC after:	1 day
X-MFC-With: r249940
2013-07-03 23:46:30 +00:00
Jeff Roberson
5f51836645 - Add a general purpose resource allocator, vmem, from NetBSD. It was
originally inspired by the Solaris vmem detailed in the proceedings
   of usenix 2001.  The NetBSD version was heavily refactored for bugs
   and simplicity.
 - Use this resource allocator to allocate the buffer and transient maps.
   Buffer cache defrags are reduced by 25% when used by filesystems with
   mixed block sizes.  Ultimately this may permit dynamic buffer cache
   sizing on low KVA machines.

Discussed with:	alc, kib, attilio
Tested by:	pho
Sponsored by:	EMC / Isilon Storage Division
2013-06-28 03:51:20 +00:00
Scott Long
f07b69478e Fix a mystery cut-n-paste corruption from the previous commit.
Submitted by:	Brenden Fabeny
2013-06-19 23:09:10 +00:00
Scott Long
2084cbe975 Mark geom_mirror as capable of unmapped i/o
Obtained from:	Netflix
MFC after:	3 days
2013-06-19 21:52:32 +00:00
Alexander Motin
ccba710262 Make CAM return and GEOM DISK pass through new GEOM::lunid attribute.
SPC-4 specification states that serial number may be property of device,
but not a specific logical unit.  People reported about FC storages using
serial number in that way, making it unusable for purposes of LUN multipath
detection.  SPC-4 states that designators associated with logical unit from
the VPD page 83h "Device Identification" should be used for that purpose.
Report first of them in the new attribute in such preference order: NAA,
EUI-64, T10 and SCSI name string.

While there, make GEOM DISK properly report GEOM::ident in XML output also
using d_getattr() method, if available.  This fixes serial numbers reporting
for SCSI disks in `geom disk list` output and confxml.

Discussed with:	gibbs, ken
Sponsored by:	iXsystems, Inc.
MFC after:	2 weeks
2013-06-12 13:36:20 +00:00
Alexander Motin
c145d6005f Don't update provider properties and don't set DISKFLAG_OPEN if d_open()
disk method call returned error.  GEOM considers devices in such case as
still closed, and won't call symmetric d_close() for them.
2013-06-11 10:06:07 +00:00
Marcel Moolenaar
3bd22a9cc8 Change the set and unset ctlreqs by making the index argument optional.
This allows setting attributes on tables. One simply does not provide
an index in that case. Otherwise the entry corresponding the index has
the attribute set or unset.

Use this change to fix a relatively longstanding bug in our GPT scheme
that's the result of rev 198097 (relatively harmless) followed by rev
237057 (damaging). The damaging part being that our GPT scheme always
has the active flag set on the PMBR slice. This is in violation with
EFI. Existing EFI implementions for both x86 and ia64 reject the GPT.
As such, GPT disks created by us aren't usable under EFI because of
that.

After this change, GPT disks never have the active flag set on the PMBR
slice. In order to make the GPT disk bootable under some x86 BIOSes,
the reason of rev 198097, one must now set the active attribute on the
gpt table. The kernel will apply this to the PMBR slice For (S)ATA:
	gpart set -a active ada0

To fix an existing GPT disk that has the active flag set in the PMBR,
and that does not need the flag, use (again for (S)ATA):
	gpart unset -a active ada0

The EBR, MBR & PC98 schemes, which also impement at least 1 attribute,
now check to make sure the entry passed is valid. They do not have
attributes that apply to the table.
2013-06-09 23:34:26 +00:00
Marcel Moolenaar
0f4389991c Remove stub implementation. 2013-06-09 23:12:43 +00:00
Brooks Davis
444e780150 MFP4 @222836
Add support for partitioning CFI disks from FDT using geom_flashmap.

Sponsored by:	DARPA, AFRL
2013-05-30 01:19:02 +00:00
Jaakko Heinonen
9641a51279 Remove an extra semicolon from the DOT language output.
PR:		kern/178540
Submitted by:	Trond Endrestol
MFC after:	1 week
2013-05-21 18:40:54 +00:00
Alexander Motin
57eed4a86f Fix vdc->Secondary_Element_Count metadata field access from 16 to 8 bit.
In some cases it could cause kernel panic during failed drive replacement.

Reported by:	trasz
MFC after:	1 week
2013-05-20 00:33:54 +00:00
Stanislav Sedov
77f8606428 - Use int8_t type for the mftrecsz field in g_label_ntfs. char type
used previously caused probe failure on platforms where char is unsigned
  (e.g. ARM), as mftrecsz can be negative.

Submitted by:	Ilya Bakulin <ilya@bakulin.de>
MFC after:	2 weeks
2013-05-05 08:00:16 +00:00
Alexander Motin
bcb6ad36f2 Return "descr" field alike to "Intel RAID1 volume" for GEOM RAID to make
it look better in bsdinstall.
2013-04-27 06:57:39 +00:00
Steven Hartland
9fe9ba5bef Teach GEOM and CAM about the difference between the max "size" of r/w and delete
requests.

sys/geom/geom_disk.h:
        - Added d_delmaxsize which represents the maximum size of individual
          device delete requests in bytes. This can be used by devices to
          inform geom of their size limitations regarding delete operations
          which are generally different from the read / write limits as data
          is not usually transferred from the host to physical device.

sys/geom/geom_disk.c:
        - Use new d_delmaxsize to calculate the size of chunks passed through to
          the underlying strategy during deletes instead of using read / write
          optimised values. This defaults to d_maxsize if unset (0).

        - Moved d_maxsize default up so it can be used to default d_delmaxsize

sys/cam/ata/ata_da.c:
        - Added d_delmaxsize calculations for TRIM and CFA

sys/cam/scsi/scsi_da.c:
        - Added re-calculation of d_delmaxsize whenever delete_method is set.

        - Added kern.cam.da.X.delete_max sysctl which allows the max size for
          delete requests to be limited. This is useful in preventing timeouts
          on devices who's delete methods are slow. It should be noted that
          this limit is reset then the device delete method is changed and
          that it can only be lowered not increased from the device max.

Reviewed by:	mav
Approved by:	pjd (mentor)
2013-04-26 16:22:54 +00:00
Steven Hartland
6f926c0b82 Added a sysctl (kern.geom.dev.delete_max_sectors) to control the maximum
size of a delete request sent to the providing device performed by g_dev_ioctl.

This allows the kernel and apps via ioctl e.g. newfs -E to request large LBA
deletes which siginificantly improves performance.

Previously this was hard coded to 65536 sectors, the new default is 262144
which doubles the throughput of deletes on commonly available SSD's.

In tests on a Intel 520 120GB FW: 400i disk it improved the delete throughput
from 1.6GB/s to over 2.6GB/s on a full disk delete such as that done via
newfs -E

For some SSD's where delete time is pretty much constant, no matter what
the request, setting this to 0 will provide significantly better throughput
e.g. Samsung 840 240GB FW DXT07B0Q @ 262144 = 79G/s, @ 0 = 2259G/s

Reviewed by:	mav
Approved by:	pjd (mentor)
MFC after:	2 weeks
2013-04-26 15:43:24 +00:00
Ivan Voras
8e9405e8a7 Comment typo fix.
Is aware of the importance of comments: dim
2013-04-16 22:42:40 +00:00
Ivan Voras
9a796b22f6 Fix the buffer-overflow-fixing fixes.
Pointy-hat to: me, for not realizing snprintf() is available in kernel.
Thanks to: jh, for bringing me the good news of snprintf(), Pawel Worach, for
           noting that the panic can be provoked in i386 and not in amd64
2013-04-16 19:58:24 +00:00
Brooks Davis
b7b63db789 Partial MFP4 of 222836:
Only look for FDT partitions if our potential parent is a DISK device.

Excluding direct recursion on the flashmap geoms was insufficient
because it did not prevent the underlying device from being retrieved if
flashmap geoms were further partitioned.

Reviewed by:	imp
Sponsored by:	DARPA, AFRL
2013-04-16 17:47:13 +00:00
Ivan Voras
c072011223 Introduce glabel labels based on GEOM ident attributes. In this initial
implementation, error on the side of conservatism and only create labels
for GEOMs of classes DISK and MULTIPATH.

Discussed with:	trasz
Approved by:	silence from freebsd-geom@
2013-04-15 16:09:24 +00:00
Ivan Voras
252c094e53 Introduce a symbol for the GEOM class name instead of using the ad-hoc string
constant.
2013-04-15 15:55:40 +00:00
John-Mark Gurney
d7078f3ba0 move the error report to a lower log level... Now you can see when it
returns an error without getting every single io that went through it..

MFC after:	1 week
2013-04-13 19:02:58 +00:00
Edward Tomasz Napierala
16fac6c92a Make it possible to submit FLUSH bios through geom_dev strategy. This
is required for CTL to work with device-backed LUNs.

Reviewed by:	mav
2013-04-06 10:32:06 +00:00
Alexander Motin
0fb832fdf0 Following r241022, replace iteration over the provider list on media events
by taking first one and asserting that there is no others.

MFC after:	1 week
2013-04-05 13:11:28 +00:00
Alexander Motin
7868ec506b geom_slice.c and its consumers like GEOM_LABEL are not touching the data
unless hotspots are used.  Pass G_PF_ACCEPT_UNMAPPED flag through except
such rare cases (obsolete GEOM_SUNLABEL and GEOM_BSD).
2013-03-26 07:55:24 +00:00
Alexander Motin
6c6e13b6e1 GEOM NOP does not touch the data, so pass G_PF_ACCEPT_UNMAPPED flag through. 2013-03-26 05:58:49 +00:00
Alexander Motin
a93c0ed463 Remove extra bio_data and bio_length copying to child request after calling
g_clone_bio(), that already copied them.
2013-03-26 05:42:12 +00:00
Alexander Kabaev
31932fae1e Do not pass unmapped buffers to drivers that cannot handle them
In physio, check if device can handle unmapped IO and pass an
appropriately mapped buffer to the driver strategy routine. The
only driver in the tree that can handle unmapped buffers is one
exposed by GEOM, so mark it as such with the new flag in the
driver cdevsw structure.

This fixes insta-panics on hosts, running dconschat, as /dev/fwmem
is an example of the driver that makes use of physio routine, but
bypasses the g_down thread, where the buffer gets mapped normally.

Discussed with: kib (earlier version)
2013-03-26 01:17:06 +00:00
Alexander Motin
f4673017b3 Make GEOM MULTIPATH to report unmapped bio support if underling path report
it.  GEOM MULTIPATH itself never touches the data and so transparent.
2013-03-25 07:24:58 +00:00
Alexander Motin
30ba747160 In GEOM DISK:
- Replace single done mutex with per-disk ones.  On system with several
disks on several HBAs that removes small, but measurable lock congestion.
 - Modify disk destruction process to not destroy the mutex prematurely.
 - Remove some extra pointer derefences.
2013-03-25 05:45:24 +00:00
Alexander Motin
3c330aff3f Fix long known deadlock between geom dev destruction and d_close() call.
Use destroy_dev_sched_cb() to not wait for device destruction while holding
GEOM topology lock (that actually caused deadlock).  Use request counting
protected by mutex to properly wait for outstanding requests completion in
cases of device closing and geom destruction.  Unlike r227009, this code
does not block taskqueue thread for indefinite time, waiting for completion.
2013-03-24 10:14:25 +00:00
Alexander Motin
50199fa0d0 Make g_wither_washer() to not loop by itself, but only when there was some
more topology change done that may require its attention.  Add few missing
g_do_wither() calls in respective places to signal it.

This fixes potential infinite loop here when some provider is withered, but
still opened or connected for some reason and so can not be destroyed.  For
example, see r227009 and r227510.
2013-03-24 03:15:20 +00:00
Konstantin Belousov
e808788c05 Correct the page count when excess length is trimmed from the bio.
Reported and tested by:	Ivan Klymenko <fidaj@ukr.net
2013-03-21 22:36:43 +00:00
Konstantin Belousov
6c83fce371 Assert that transient mapping of the bio is only done when unmapped
buffers are allowed.

Sponsored by:	The FreeBSD Foundation
2013-03-21 07:26:33 +00:00
Konstantin Belousov
db7bfaa8ce The geom_part provider supports unmapped bio iff the underlying
provider does so, since geom_part never inspects the bio_data.

Sponsored by:	The FreeBSD Foundation
Tested by:	pho
2013-03-19 14:50:24 +00:00
Konstantin Belousov
f8c19ba466 A flag for the geom disk driver to indicate that it accepts the
unmapped i/o requests.

Sponsored by:	The FreeBSD Foundation
Tested by:	pho
2013-03-19 14:49:15 +00:00
Konstantin Belousov
ee75e7de7b Implement the concept of the unmapped VMIO buffers, i.e. buffers which
do not map the b_pages pages into buffer_map KVA.  The use of the
unmapped buffers eliminate the need to perform TLB shootdown for
mapping on the buffer creation and reuse, greatly reducing the amount
of IPIs for shootdown on big-SMP machines and eliminating up to 25-30%
of the system time on i/o intensive workloads.

The unmapped buffer should be explicitely requested by the GB_UNMAPPED
flag by the consumer.  For unmapped buffer, no KVA reservation is
performed at all. The consumer might request unmapped buffer which
does have a KVA reserve, to manually map it without recursing into
buffer cache and blocking, with the GB_KVAALLOC flag.

When the mapped buffer is requested and unmapped buffer already
exists, the cache performs an upgrade, possibly reusing the KVA
reservation.

Unmapped buffer is translated into unmapped bio in g_vfs_strategy().
Unmapped bio carry a pointer to the vm_page_t array, offset and length
instead of the data pointer.  The provider which processes the bio
should explicitely specify a readiness to accept unmapped bio,
otherwise g_down geom thread performs the transient upgrade of the bio
request by mapping the pages into the new bio_transient_map KVA
submap.

The bio_transient_map submap claims up to 10% of the buffer map, and
the total buffer_map + bio_transient_map KVA usage stays the
same. Still, it could be manually tuned by kern.bio_transient_maxcnt
tunable, in the units of the transient mappings.  Eventually, the
bio_transient_map could be removed after all geom classes and drivers
can accept unmapped i/o requests.

Unmapped support can be turned off by the vfs.unmapped_buf_allowed
tunable, disabling which makes the buffer (or cluster) creation
requests to ignore GB_UNMAPPED and GB_KVAALLOC flags.  Unmapped
buffers are only enabled by default on the architectures where
pmap_copy_page() was implemented and tested.

In the rework, filesystem metadata is not the subject to maxbufspace
limit anymore. Since the metadata buffers are always mapped, the
buffers still have to fit into the buffer map, which provides a
reasonable (but practically unreachable) upper bound on it. The
non-metadata buffer allocations, both mapped and unmapped, is
accounted against maxbufspace, as before. Effectively, this means that
the maxbufspace is forced on mapped and unmapped buffers separately.
The pre-patch bufspace limiting code did not worked, because
buffer_map fragmentation does not allow the limit to be reached.

By Jeff Roberson request, the getnewbuf() function was split into
smaller single-purpose functions.

Sponsored by:	The FreeBSD Foundation
Discussed with:	jeff (previous version)
Tested by:	pho, scottl (previous version), jhb, bf
MFC after:	2 weeks
2013-03-19 14:13:12 +00:00
Pawel Jakub Dawidek
c4d2d401f8 We don't need buffer to handle BIO_DELETE, so don't check buffer size for it.
This fixes handling BIO_DELETE larger than MAXPHYS.
2013-03-14 23:07:01 +00:00
Sean Bruno
bd9fba0cfe Add legacy support to geom raid to create a /dev/arX device for support
of upgrading older machines using ataraid(4) to newer releases.

This optional parameter is controlled via kern.geom.raid.legacy_aliases
and will create a /dev/ar0 device that will point at /dev/raid/r0 for
example.

Tested on Dell SC 1425 DDF-1 format software raid controllers installing from
stable/7 and upgrading to stable/9 without having to adjust /etc/fstab

Reviewed by:	mav
Obtained from:	Yahoo!
MFC after:	2 Weeks
2013-03-08 20:07:32 +00:00
Jean-Sébastien Pédron
f5c1ef84f9 g_label_ntfs_taste: Abort taste is recsize == 0
This will avoid a 0-byte read (in g_read_data()) leading to a panic, if
previously read data are erroneous.

Suggested by:	John-Mark Gurney <jmg@funkthat.com>
2013-03-08 18:07:43 +00:00