a9934668aa
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
|
||
|---|---|---|
| .. | ||
| ata | ||
| ctl | ||
| scsi | ||
| cam_ccb.h | ||
| cam_compat.c | ||
| cam_compat.h | ||
| cam_debug.h | ||
| cam_periph.c | ||
| cam_periph.h | ||
| cam_queue.c | ||
| cam_queue.h | ||
| cam_sim.c | ||
| cam_sim.h | ||
| cam_xpt_internal.h | ||
| cam_xpt_periph.h | ||
| cam_xpt_sim.h | ||
| cam_xpt.c | ||
| cam_xpt.h | ||
| cam.c | ||
| cam.h | ||
| README.quirks | ||
/* $FreeBSD$ */
FreeBSD Quirk Guidelines
Nate Lawson - njl at freebsd org
0. Introduction
FreeBSD drivers make every attempt possible to support the standards
behind hardware. Where possible and not in conflict with the standard,
they also attempt to work around hardware which doesn't strictly
conform. However, some devices have flaws which can't be worked
around while keeping the driver compatible with the standard. For
these devices, we have created a quirks mechanism to indicate to
the driver that it must avoid certain commands or use them differently
with a specific model and/or version of hardware. This document
focuses on identifying and committing quirks for storage hardware
involving CAM and UMASS but is applicable to other areas.
CAM provides a generic transport for SCSI-like devices. Many different
transports use SCSI command sets including parallel SCSI, firewire
(1394), USB UMASS, fibre channel, and ATAPI. For block devices (i.e.
hard drives, flash adapters, cameras) there are two standards, SBC
and RBC. SCSI hard drives are usually SBC-compliant and smaller
devices like flash drives are usually RBC-compliant. Multimedia
devices including CDROMs and DVD-RW are usually MMC-compliant.
Please follow these guidelines to get your device working as soon
as possible. If you are a committer, please do NOT commit quirks
directly but follow this process also.
1. Determing the problem
The first step is to determine what's wrong. If the device should
be supported but hangs while attaching, it's possible a quirk can
help. The types of things a quirk can fix are:
`
* cam/cam_xpt.c quirks
o CAM_QUIRK_NOLUNS - do not probe luns other than 0 since device
responds to all inquiries with "lun present".
o CAM_QUIRK_NOSERIAL - do not send an inquiry for serial number.
o CAM_QUIRK_HILUNS - probe all luns even if some respond "not present"
since device has a sparse lun space.
* cam/scsi/scsi_da.c quirks
o DA_Q_NO_SYNC_CACHE - The sync cache command is used to force a
drive to write out all changes to disk before shutting down. Some
drives hang when receiving this command even though it is required
by all SBC and RBC standards. Note that a warning message on
console is NOT sufficient to add this quirk. The warning messages
are harmless and only a device or system hang is cause for adding
this quirk.
o DA_Q_NO_6_BYTE - The RBC spec (see Links below) does not allow
for 6-byte READ/WRITE commands. Some manufacturers took that too
literally and crash when receiving 6-byte commands. This quirk
causes FreeBSD to only send 10-byte commands. Since the CAM subsystem
has been modified to not send 6-byte commands to USB, 1394, and
other transports that don't support SBC, this quirk should be very
rare.
o DA_Q_NO_PREVENT - Don't use the prevent/allow commands to keep a
removable medium from being ejected. Some systems can't handle these
commands (rare).
* cam/scsi/scsi_cd.c quirks
o CD_Q_NO_TOUCH - not implemented
o CD_Q_BCD_TRACKS - convert start/end track to BCD
o CD_Q_NO_CHANGER - never treat as a changer
o CD_Q_CHANGER - always treat as a changer
* cam/scsi/scsi_ch.c quirks
o CH_Q_NO_DBD - disable block descriptors in mode sense
* cam/scsi/scsi_sa.c quirks
o SA_QUIRK_NOCOMP - Can't deal with compression at all
o SA_QUIRK_FIXED - Force fixed mode
o SA_QUIRK_VARIABLE - Force variable mode
o SA_QUIRK_2FM - Needs Two File Marks at EOD
o SA_QUIRK_1FM - No more than 1 File Mark at EOD
o SA_QUIRK_NODREAD - Don't try and dummy read density
o SA_QUIRK_NO_MODESEL - Don't do mode select at all
o SA_QUIRK_NO_CPAGE - Don't use DEVICE COMPRESSION page
* dev/usb/umass.c quirks
o NO_TEST_UNIT_READY - The drive does not support Test Unit Ready.
Convert to Start Unit. This command is a simple no-op for most
firmware but some of them hang when this command is sent.
o RS_NO_CLEAR_UA - The drive does not reset the Unit Attention state
after REQUEST SENSE has been sent. The INQUIRY command does not
reset the UA either, and so CAM runs in circles trying to retrieve
the initial INQUIRY data. This quirk signifies that after a unit
attention condition, don't try to clear the condition with a request
sense command.
o NO_START_STOP - Like test unit ready, don't send this command if it hangs the device.
o FORCE_SHORT_INQUIRY - Don't ask for full inquiry data (256
bytes). Some drives can only handle the shorter inquiry length
(36 bytes).
o SHUTTLE_INIT - Needs to be initialised the Shuttle way. Haven't
looked into what this does but apparently it's mostly Shuttle
devices.
o ALT_IFACE_1 - Drive needs to be switched to alternate interface 1. Rare.
o FLOPPY_SPEED - Drive does not do 1Mb/s, but just floppy speeds (20kb/s).
o IGNORE_RESIDUE - The device can't count and gets the residue
of transfers wrong. This is sometimes needed for devices where
large transfers cause stalls.
o NO_GETMAXLUN - Get maximum LUN is a command to identify multiple
devices sharing the same ID. For instance, a multislot compact
flash reader might be on two LUNS. Some non-standard devices hang
when receiving this command so this quirk disables it.
o WRONG_CSWSIG - The device uses a weird CSWSIGNATURE. Rare.
o NO_INQUIRY - Device cannot handle INQUIRY so fake a generic
response. INQUIRY is one of the most basic commands but some
drives can't even handle it. (No idea how such devices even work
at all on other OS's.) This quirk fakes up a valid but generic
response for devices that can't handle INQUIRY.
o NO_INQUIRY_EVPD - Device cannot handle an extended INQUIRY
asking for vital product data (EVPD) so just return a "no data"
response (check condition) without sending the command to the
device.
2. Testing a Quirk
After you have an idea what you want to try, edit the proper file
above, using wildcarding to be sure your device is matched. Here
is a list of the common things to try. Note that some devices require
multiple quirks or quirks in different drivers. For example, some
USB pen drives or flash readers require quirks in both da(4) and
umass(4).
* umass(4) device (sys/dev/usb/umass.c) -- this quirk matches an Asahi Optical device with any product ID or revision ID.
*
* { USB_VENDOR_ASAHIOPTICAL, PID_WILDCARD, RID_WILDCARD,
* UMASS_PROTO_ATAPI | UMASS_PROTO_CBI_I,
* RS_NO_CLEAR_UA
* },
* da(4) device (sys/cam/scsi/scsi_da.c) -- this quirk matches a Creative device with a name of "NOMAD_MUVO" and any revision.
*
* {
* /*
* * Creative Nomad MUVO mp3 player (USB)
* * PR: kern/53094
* */
* {T_DIRECT, SIP_MEDIA_REMOVABLE, "CREATIVE", "NOMAD_MUVO", "*"},
* /*quirks*/ DA_Q_NO_SYNC_CACHE|DA_Q_NO_PREVENT
* },
3. Filing a PR
All quirk submissions MUST go through GNATS. For information on how
to submit a PR, see this page.
Please include the following in your PR:
* Subject: QUIRK: FooCo USB DVD-RAM drive
* Output of "camcontrol inquiry yourdevice"
* Manufacturer name, model number, etc.
* Transport type (FC, SCSI, USB, Firewire)
* Output from dmesg for failed attach attempts
* Output from dmesg for successful attach attempts (after quirk added)
* Output of "usbdevs -v" with device attached
* Valid email address
Here are some examples of well-formed PRs:
* kern/43580
* kern/49054
4. What happens next
I will review your submission, respond with comments, and once the
quirk is deemed necessary and ready for committing, I'll commit it,
referencing the PR. (Again, all quirks must be submitted as PRs).
Questions? Email njl AT freebsd.org.
5. Note to Committers
Please insert quirks in the right section in scsi_da.c, sorted by
PR number. Always include the name and PR number for scsi_da.c (see
above for an example.) Please sort quirks alphabetically in umass.c.
Follow the surrounding style in all drivers. Be sure to correspond
with the submitter to be sure the quirk you are adding is the minimum
necessary, not quirking other useful features and not overly broad
(i.e., too many wildcards).