d/freebsd-dev
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
a9934668aa
freebsd-dev/sys/geom/geom_disk.c
Kenneth D. Merry a9934668aa Add asynchronous command support to the pass(4) driver, and the new 
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
2015-12-03 20:54:55 +00:00

894 lines
22 KiB
C
Raw Blame History

/*-
* Copyright (c) 2002 Poul-Henning Kamp
* Copyright (c) 2002 Networks Associates Technology, Inc.
* All rights reserved.
*
* This software was developed for the FreeBSD Project by Poul-Henning Kamp
* and NAI Labs, the Security Research Division of Network Associates, Inc.
* under DARPA/SPAWAR contract N66001-01-C-8035 ("CBOSS"), as part of the
* DARPA CHATS research program.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. The names of the authors may not be used to endorse or promote
* products derived from this software without specific prior written
* permission.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_geom.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/sysctl.h>
#include <sys/bio.h>
#include <sys/ctype.h>
#include <sys/fcntl.h>
#include <sys/malloc.h>
#include <sys/sbuf.h>
#include <sys/devicestat.h>
#include <machine/md_var.h>
#include <sys/lock.h>
#include <sys/mutex.h>
#include <geom/geom.h>
#include <geom/geom_disk.h>
#include <geom/geom_int.h>
#include <dev/led/led.h>
#include <machine/bus.h>
struct g_disk_softc {
struct mtx done_mtx;
struct disk *dp;
struct sysctl_ctx_list sysctl_ctx;
struct sysctl_oid *sysctl_tree;
char led[64];
uint32_t state;
struct mtx start_mtx;
};
static g_access_t g_disk_access;
static g_start_t g_disk_start;
static g_ioctl_t g_disk_ioctl;
static g_dumpconf_t g_disk_dumpconf;
static g_provgone_t g_disk_providergone;
static struct g_class g_disk_class = {
.name = G_DISK_CLASS_NAME,
.version = G_VERSION,
.start = g_disk_start,
.access = g_disk_access,
.ioctl = g_disk_ioctl,
.providergone = g_disk_providergone,
.dumpconf = g_disk_dumpconf,
};
SYSCTL_DECL(_kern_geom);
static SYSCTL_NODE(_kern_geom, OID_AUTO, disk, CTLFLAG_RW, 0,
"GEOM_DISK stuff");
DECLARE_GEOM_CLASS(g_disk_class, g_disk);
static int
g_disk_access(struct g_provider *pp, int r, int w, int e)
{
struct disk *dp;
struct g_disk_softc *sc;
int error;
g_trace(G_T_ACCESS, "g_disk_access(%s, %d, %d, %d)",
pp->name, r, w, e);
g_topology_assert();
sc = pp->private;
if (sc == NULL || (dp = sc->dp) == NULL || dp->d_destroyed) {
/*
* Allow decreasing access count even if disk is not
* avaliable anymore.
*/
if (r <= 0 && w <= 0 && e <= 0)
return (0);
return (ENXIO);
}
r += pp->acr;
w += pp->acw;
e += pp->ace;
error = 0;
if ((pp->acr + pp->acw + pp->ace) == 0 && (r + w + e) > 0) {
if (dp->d_open != NULL) {
error = dp->d_open(dp);
if (bootverbose && error != 0)
printf("Opened disk %s -> %d\n",
pp->name, error);
if (error != 0)
return (error);
}
pp->mediasize = dp->d_mediasize;
pp->sectorsize = dp->d_sectorsize;
if (dp->d_maxsize == 0) {
printf("WARNING: Disk drive %s%d has no d_maxsize\n",
dp->d_name, dp->d_unit);
dp->d_maxsize = DFLTPHYS;
}
if (dp->d_delmaxsize == 0) {
if (bootverbose && dp->d_flags & DISKFLAG_CANDELETE) {
printf("WARNING: Disk drive %s%d has no "
"d_delmaxsize\n", dp->d_name, dp->d_unit);
}
dp->d_delmaxsize = dp->d_maxsize;
}
pp->stripeoffset = dp->d_stripeoffset;
pp->stripesize = dp->d_stripesize;
dp->d_flags |= DISKFLAG_OPEN;
} else if ((pp->acr + pp->acw + pp->ace) > 0 && (r + w + e) == 0) {
if (dp->d_close != NULL) {
error = dp->d_close(dp);
if (error != 0)
printf("Closed disk %s -> %d\n",
pp->name, error);
}
sc->state = G_STATE_ACTIVE;
if (sc->led[0] != 0)
led_set(sc->led, "0");
dp->d_flags &= ~DISKFLAG_OPEN;
}
return (error);
}
static void
g_disk_kerneldump(struct bio *bp, struct disk *dp)
{
struct g_kerneldump *gkd;
struct g_geom *gp;
gkd = (struct g_kerneldump*)bp->bio_data;
gp = bp->bio_to->geom;
g_trace(G_T_TOPOLOGY, "g_disk_kerneldump(%s, %jd, %jd)",
gp->name, (intmax_t)gkd->offset, (intmax_t)gkd->length);
if (dp->d_dump == NULL) {
g_io_deliver(bp, ENODEV);
return;
}
gkd->di.dumper = dp->d_dump;
gkd->di.priv = dp;
gkd->di.blocksize = dp->d_sectorsize;
gkd->di.maxiosize = dp->d_maxsize;
gkd->di.mediaoffset = gkd->offset;
if ((gkd->offset + gkd->length) > dp->d_mediasize)
gkd->length = dp->d_mediasize - gkd->offset;
gkd->di.mediasize = gkd->length;
g_io_deliver(bp, 0);
}
static void
g_disk_setstate(struct bio *bp, struct g_disk_softc *sc)
{
const char *cmd;
memcpy(&sc->state, bp->bio_data, sizeof(sc->state));
if (sc->led[0] != 0) {
switch (sc->state) {
case G_STATE_FAILED:
cmd = "1";
break;
case G_STATE_REBUILD:
cmd = "f5";
break;
case G_STATE_RESYNC:
cmd = "f1";
break;
default:
cmd = "0";
break;
}
led_set(sc->led, cmd);
}
g_io_deliver(bp, 0);
}
static void
g_disk_done(struct bio *bp)
{
struct bintime now;
struct bio *bp2;
struct g_disk_softc *sc;
/* See "notes" for why we need a mutex here */
/* XXX: will witness accept a mix of Giant/unGiant drivers here ? */
bp2 = bp->bio_parent;
sc = bp2->bio_to->private;
bp->bio_completed = bp->bio_length - bp->bio_resid;
binuptime(&now);
mtx_lock(&sc->done_mtx);
if (bp2->bio_error == 0)
bp2->bio_error = bp->bio_error;
bp2->bio_completed += bp->bio_completed;
if ((bp->bio_cmd & (BIO_READ|BIO_WRITE|BIO_DELETE|BIO_FLUSH)) != 0)
devstat_end_transaction_bio_bt(sc->dp->d_devstat, bp, &now);
bp2->bio_inbed++;
if (bp2->bio_children == bp2->bio_inbed) {
mtx_unlock(&sc->done_mtx);
bp2->bio_resid = bp2->bio_bcount - bp2->bio_completed;
g_io_deliver(bp2, bp2->bio_error);
} else
mtx_unlock(&sc->done_mtx);
g_destroy_bio(bp);
}
static int
g_disk_ioctl(struct g_provider *pp, u_long cmd, void * data, int fflag, struct thread *td)
{
struct disk *dp;
struct g_disk_softc *sc;
int error;
sc = pp->private;
dp = sc->dp;
if (dp->d_ioctl == NULL)
return (ENOIOCTL);
error = dp->d_ioctl(dp, cmd, data, fflag, td);
return (error);
}
static int
g_disk_maxsegs(struct disk *dp)
{
return ((dp->d_maxsize / PAGE_SIZE) + 1);
}
static void
g_disk_advance(struct disk *dp, struct bio *bp, off_t off)
{
bp->bio_offset += off;
bp->bio_length -= off;
if ((bp->bio_flags & BIO_VLIST) != 0) {
bus_dma_segment_t *seg, *end;
seg = (bus_dma_segment_t *)bp->bio_data;
end = (bus_dma_segment_t *)bp->bio_data + bp->bio_ma_n;
off += bp->bio_ma_offset;
while (off >= seg->ds_len) {
KASSERT((seg != end),
("vlist request runs off the end"));
off -= seg->ds_len;
seg++;
}
bp->bio_ma_offset = off;
bp->bio_ma_n = end - seg;
bp->bio_data = (void *)seg;
} else if ((bp->bio_flags & BIO_UNMAPPED) != 0) {
bp->bio_ma += off / PAGE_SIZE;
bp->bio_ma_offset += off;
bp->bio_ma_offset %= PAGE_SIZE;
bp->bio_ma_n -= off / PAGE_SIZE;
} else {
bp->bio_data += off;
}
}
static void
g_disk_seg_limit(bus_dma_segment_t *seg, off_t *poffset,
off_t *plength, int *ppages)
{
uintptr_t seg_page_base;
uintptr_t seg_page_end;
off_t offset;
off_t length;
int seg_pages;
offset = *poffset;
length = *plength;
if (length > seg->ds_len - offset)
length = seg->ds_len - offset;
seg_page_base = trunc_page(seg->ds_addr + offset);
seg_page_end = round_page(seg->ds_addr + offset + length);
seg_pages = (seg_page_end - seg_page_base) >> PAGE_SHIFT;
if (seg_pages > *ppages) {
seg_pages = *ppages;
length = (seg_page_base + (seg_pages << PAGE_SHIFT)) -
(seg->ds_addr + offset);
}
*poffset = 0;
*plength -= length;
*ppages -= seg_pages;
}
static off_t
g_disk_vlist_limit(struct disk *dp, struct bio *bp, bus_dma_segment_t **pendseg)
{
bus_dma_segment_t *seg, *end;
off_t residual;
off_t offset;
int pages;
seg = (bus_dma_segment_t *)bp->bio_data;
end = (bus_dma_segment_t *)bp->bio_data + bp->bio_ma_n;
residual = bp->bio_length;
offset = bp->bio_ma_offset;
pages = g_disk_maxsegs(dp);
while (residual != 0 && pages != 0) {
KASSERT((seg != end),
("vlist limit runs off the end"));
g_disk_seg_limit(seg, &offset, &residual, &pages);
seg++;
}
if (pendseg != NULL)
*pendseg = seg;
return (residual);
}
static bool
g_disk_limit(struct disk *dp, struct bio *bp)
{
bool limited = false;
off_t d_maxsize;
d_maxsize = (bp->bio_cmd == BIO_DELETE) ?
dp->d_delmaxsize : dp->d_maxsize;
/*
* XXX: If we have a stripesize we should really use it here.
* Care should be taken in the delete case if this is done
* as deletes can be very sensitive to size given how they
* are processed.
*/
if (bp->bio_length > d_maxsize) {
bp->bio_length = d_maxsize;
limited = true;
}
if ((bp->bio_flags & BIO_VLIST) != 0) {
bus_dma_segment_t *firstseg, *endseg;
off_t residual;
firstseg = (bus_dma_segment_t*)bp->bio_data;
residual = g_disk_vlist_limit(dp, bp, &endseg);
if (residual != 0) {
bp->bio_ma_n = endseg - firstseg;
bp->bio_length -= residual;
limited = true;
}
} else if ((bp->bio_flags & BIO_UNMAPPED) != 0) {
bp->bio_ma_n =
howmany(bp->bio_ma_offset + bp->bio_length, PAGE_SIZE);
}
return (limited);
}
static void
g_disk_start(struct bio *bp)
{
struct bio *bp2, *bp3;
struct disk *dp;
struct g_disk_softc *sc;
int error;
off_t off;
sc = bp->bio_to->private;
if (sc == NULL || (dp = sc->dp) == NULL || dp->d_destroyed) {
g_io_deliver(bp, ENXIO);
return;
}
error = EJUSTRETURN;
switch(bp->bio_cmd) {
case BIO_DELETE:
if (!(dp->d_flags & DISKFLAG_CANDELETE)) {
error = EOPNOTSUPP;
break;
}
/* fall-through */
case BIO_READ:
case BIO_WRITE:
KASSERT((dp->d_flags & DISKFLAG_UNMAPPED_BIO) != 0 ||
(bp->bio_flags & BIO_UNMAPPED) == 0,
("unmapped bio not supported by disk %s", dp->d_name));
off = 0;
bp3 = NULL;
bp2 = g_clone_bio(bp);
if (bp2 == NULL) {
error = ENOMEM;
break;
}
for (;;) {
if (g_disk_limit(dp, bp2)) {
off += bp2->bio_length;
/*
* To avoid a race, we need to grab the next bio
* before we schedule this one. See "notes".
*/
bp3 = g_clone_bio(bp);
if (bp3 == NULL)
bp->bio_error = ENOMEM;
}
bp2->bio_done = g_disk_done;
bp2->bio_pblkno = bp2->bio_offset / dp->d_sectorsize;
bp2->bio_bcount = bp2->bio_length;
bp2->bio_disk = dp;
mtx_lock(&sc->start_mtx);
devstat_start_transaction_bio(dp->d_devstat, bp2);
mtx_unlock(&sc->start_mtx);
dp->d_strategy(bp2);
if (bp3 == NULL)
break;
bp2 = bp3;
bp3 = NULL;
g_disk_advance(dp, bp2, off);
}
break;
case BIO_GETATTR:
/* Give the driver a chance to override */
if (dp->d_getattr != NULL) {
if (bp->bio_disk == NULL)
bp->bio_disk = dp;
error = dp->d_getattr(bp);
if (error != -1)
break;
error = EJUSTRETURN;
}
if (g_handleattr_int(bp, "GEOM::candelete",
(dp->d_flags & DISKFLAG_CANDELETE) != 0))
break;
else if (g_handleattr_int(bp, "GEOM::fwsectors",
dp->d_fwsectors))
break;
else if (g_handleattr_int(bp, "GEOM::fwheads", dp->d_fwheads))
break;
else if (g_handleattr_off_t(bp, "GEOM::frontstuff", 0))
break;
else if (g_handleattr_str(bp, "GEOM::ident", dp->d_ident))
break;
else if (g_handleattr_uint16_t(bp, "GEOM::hba_vendor",
dp->d_hba_vendor))
break;
else if (g_handleattr_uint16_t(bp, "GEOM::hba_device",
dp->d_hba_device))
break;
else if (g_handleattr_uint16_t(bp, "GEOM::hba_subvendor",
dp->d_hba_subvendor))
break;
else if (g_handleattr_uint16_t(bp, "GEOM::hba_subdevice",
dp->d_hba_subdevice))
break;
else if (!strcmp(bp->bio_attribute, "GEOM::kerneldump"))
g_disk_kerneldump(bp, dp);
else if (!strcmp(bp->bio_attribute, "GEOM::setstate"))
g_disk_setstate(bp, sc);
else if (g_handleattr_uint16_t(bp, "GEOM::rotation_rate",
dp->d_rotation_rate))
break;
else
error = ENOIOCTL;
break;
case BIO_FLUSH:
g_trace(G_T_BIO, "g_disk_flushcache(%s)",
bp->bio_to->name);
if (!(dp->d_flags & DISKFLAG_CANFLUSHCACHE)) {
error = EOPNOTSUPP;
break;
}
bp2 = g_clone_bio(bp);
if (bp2 == NULL) {
g_io_deliver(bp, ENOMEM);
return;
}
bp2->bio_done = g_disk_done;
bp2->bio_disk = dp;
mtx_lock(&sc->start_mtx);
devstat_start_transaction_bio(dp->d_devstat, bp2);
mtx_unlock(&sc->start_mtx);
dp->d_strategy(bp2);
break;
default:
error = EOPNOTSUPP;
break;
}
if (error != EJUSTRETURN)
g_io_deliver(bp, error);
return;
}
static void
g_disk_dumpconf(struct sbuf *sb, const char *indent, struct g_geom *gp, struct g_consumer *cp, struct g_provider *pp)
{
struct bio *bp;
struct disk *dp;
struct g_disk_softc *sc;
char *buf;
int res = 0;
sc = gp->softc;
if (sc == NULL || (dp = sc->dp) == NULL)
return;
if (indent == NULL) {
sbuf_printf(sb, " hd %u", dp->d_fwheads);
sbuf_printf(sb, " sc %u", dp->d_fwsectors);
return;
}
if (pp != NULL) {
sbuf_printf(sb, "%s<fwheads>%u</fwheads>\n",
indent, dp->d_fwheads);
sbuf_printf(sb, "%s<fwsectors>%u</fwsectors>\n",
indent, dp->d_fwsectors);
if (dp->d_getattr != NULL) {
buf = g_malloc(DISK_IDENT_SIZE, M_WAITOK);
bp = g_alloc_bio();
bp->bio_disk = dp;
bp->bio_attribute = "GEOM::ident";
bp->bio_length = DISK_IDENT_SIZE;
bp->bio_data = buf;
res = dp->d_getattr(bp);
sbuf_printf(sb, "%s<ident>", indent);
g_conf_printf_escaped(sb, "%s",
res == 0 ? buf: dp->d_ident);
sbuf_printf(sb, "</ident>\n");
bp->bio_attribute = "GEOM::lunid";
bp->bio_length = DISK_IDENT_SIZE;
bp->bio_data = buf;
if (dp->d_getattr(bp) == 0) {
sbuf_printf(sb, "%s<lunid>", indent);
g_conf_printf_escaped(sb, "%s", buf);
sbuf_printf(sb, "</lunid>\n");
}
bp->bio_attribute = "GEOM::lunname";
bp->bio_length = DISK_IDENT_SIZE;
bp->bio_data = buf;
if (dp->d_getattr(bp) == 0) {
sbuf_printf(sb, "%s<lunname>", indent);
g_conf_printf_escaped(sb, "%s", buf);
sbuf_printf(sb, "</lunname>\n");
}
g_destroy_bio(bp);
g_free(buf);
} else {
sbuf_printf(sb, "%s<ident>", indent);
g_conf_printf_escaped(sb, "%s", dp->d_ident);
sbuf_printf(sb, "</ident>\n");
}
sbuf_printf(sb, "%s<descr>", indent);
g_conf_printf_escaped(sb, "%s", dp->d_descr);
sbuf_printf(sb, "</descr>\n");
}
}
static void
g_disk_resize(void *ptr, int flag)
{
struct disk *dp;
struct g_geom *gp;
struct g_provider *pp;
if (flag == EV_CANCEL)
return;
g_topology_assert();
dp = ptr;
gp = dp->d_geom;
if (dp->d_destroyed || gp == NULL)
return;
LIST_FOREACH(pp, &gp->provider, provider) {
if (pp->sectorsize != 0 &&
pp->sectorsize != dp->d_sectorsize)
g_wither_provider(pp, ENXIO);
else
g_resize_provider(pp, dp->d_mediasize);
}
}
static void
g_disk_create(void *arg, int flag)
{
struct g_geom *gp;
struct g_provider *pp;
struct disk *dp;
struct g_disk_softc *sc;
char tmpstr[80];
if (flag == EV_CANCEL)
return;
g_topology_assert();
dp = arg;
sc = g_malloc(sizeof(*sc), M_WAITOK | M_ZERO);
mtx_init(&sc->start_mtx, "g_disk_start", NULL, MTX_DEF);
mtx_init(&sc->done_mtx, "g_disk_done", NULL, MTX_DEF);
sc->dp = dp;
gp = g_new_geomf(&g_disk_class, "%s%d", dp->d_name, dp->d_unit);
gp->softc = sc;
pp = g_new_providerf(gp, "%s", gp->name);
devstat_remove_entry(pp->stat);
pp->stat = NULL;
dp->d_devstat->id = pp;
pp->mediasize = dp->d_mediasize;
pp->sectorsize = dp->d_sectorsize;
pp->stripeoffset = dp->d_stripeoffset;
pp->stripesize = dp->d_stripesize;
if ((dp->d_flags & DISKFLAG_UNMAPPED_BIO) != 0)
pp->flags |= G_PF_ACCEPT_UNMAPPED;
if ((dp->d_flags & DISKFLAG_DIRECT_COMPLETION) != 0)
pp->flags |= G_PF_DIRECT_SEND;
pp->flags |= G_PF_DIRECT_RECEIVE;
if (bootverbose)
printf("GEOM: new disk %s\n", gp->name);
sysctl_ctx_init(&sc->sysctl_ctx);
snprintf(tmpstr, sizeof(tmpstr), "GEOM disk %s", gp->name);
sc->sysctl_tree = SYSCTL_ADD_NODE(&sc->sysctl_ctx,
SYSCTL_STATIC_CHILDREN(_kern_geom_disk), OID_AUTO, gp->name,
CTLFLAG_RD, 0, tmpstr);
if (sc->sysctl_tree != NULL) {
SYSCTL_ADD_STRING(&sc->sysctl_ctx,
SYSCTL_CHILDREN(sc->sysctl_tree), OID_AUTO, "led",
CTLFLAG_RWTUN, sc->led, sizeof(sc->led),
"LED name");
}
pp->private = sc;
dp->d_geom = gp;
g_error_provider(pp, 0);
}
/*
* We get this callback after all of the consumers have gone away, and just
* before the provider is freed. If the disk driver provided a d_gone
* callback, let them know that it is okay to free resources -- they won't
* be getting any more accesses from GEOM.
*/
static void
g_disk_providergone(struct g_provider *pp)
{
struct disk *dp;
struct g_disk_softc *sc;
sc = (struct g_disk_softc *)pp->private;
dp = sc->dp;
if (dp != NULL && dp->d_gone != NULL)
dp->d_gone(dp);
if (sc->sysctl_tree != NULL) {
sysctl_ctx_free(&sc->sysctl_ctx);
sc->sysctl_tree = NULL;
}
if (sc->led[0] != 0) {
led_set(sc->led, "0");
sc->led[0] = 0;
}
pp->private = NULL;
pp->geom->softc = NULL;
mtx_destroy(&sc->done_mtx);
mtx_destroy(&sc->start_mtx);
g_free(sc);
}
static void
g_disk_destroy(void *ptr, int flag)
{
struct disk *dp;
struct g_geom *gp;
struct g_disk_softc *sc;
g_topology_assert();
dp = ptr;
gp = dp->d_geom;
if (gp != NULL) {
sc = gp->softc;
if (sc != NULL)
sc->dp = NULL;
dp->d_geom = NULL;
g_wither_geom(gp, ENXIO);
}
g_free(dp);
}
/*
* We only allow printable characters in disk ident,
* the rest is converted to 'x<HH>'.
*/
static void
g_disk_ident_adjust(char *ident, size_t size)
{
char *p, tmp[4], newid[DISK_IDENT_SIZE];
newid[0] = '\0';
for (p = ident; *p != '\0'; p++) {
if (isprint(*p)) {
tmp[0] = *p;
tmp[1] = '\0';
} else {
snprintf(tmp, sizeof(tmp), "x%02hhx",
*(unsigned char *)p);
}
if (strlcat(newid, tmp, sizeof(newid)) >= sizeof(newid))
break;
}
bzero(ident, size);
strlcpy(ident, newid, size);
}
struct disk *
disk_alloc(void)
{
return (g_malloc(sizeof(struct disk), M_WAITOK | M_ZERO));
}
void
disk_create(struct disk *dp, int version)
{
if (version != DISK_VERSION) {
printf("WARNING: Attempt to add disk %s%d %s",
dp->d_name, dp->d_unit,
" using incompatible ABI version of disk(9)\n");
printf("WARNING: Ignoring disk %s%d\n",
dp->d_name, dp->d_unit);
return;
}
if (dp->d_flags & DISKFLAG_RESERVED) {
printf("WARNING: Attempt to add non-MPSAFE disk %s%d\n",
dp->d_name, dp->d_unit);
printf("WARNING: Ignoring disk %s%d\n",
dp->d_name, dp->d_unit);
return;
}
KASSERT(dp->d_strategy != NULL, ("disk_create need d_strategy"));
KASSERT(dp->d_name != NULL, ("disk_create need d_name"));
KASSERT(*dp->d_name != 0, ("disk_create need d_name"));
KASSERT(strlen(dp->d_name) < SPECNAMELEN - 4, ("disk name too long"));
if (dp->d_devstat == NULL)
dp->d_devstat = devstat_new_entry(dp->d_name, dp->d_unit,
dp->d_sectorsize, DEVSTAT_ALL_SUPPORTED,
DEVSTAT_TYPE_DIRECT, DEVSTAT_PRIORITY_MAX);
dp->d_geom = NULL;
g_disk_ident_adjust(dp->d_ident, sizeof(dp->d_ident));
g_post_event(g_disk_create, dp, M_WAITOK, dp, NULL);
}
void
disk_destroy(struct disk *dp)
{
g_cancel_event(dp);
dp->d_destroyed = 1;
if (dp->d_devstat != NULL)
devstat_remove_entry(dp->d_devstat);
g_post_event(g_disk_destroy, dp, M_WAITOK, NULL);
}
void
disk_gone(struct disk *dp)
{
struct g_geom *gp;
struct g_provider *pp;
gp = dp->d_geom;
if (gp != NULL) {
pp = LIST_FIRST(&gp->provider);
if (pp != NULL) {
KASSERT(LIST_NEXT(pp, provider) == NULL,
("geom %p has more than one provider", gp));
g_wither_provider(pp, ENXIO);
}
}
}
void
disk_attr_changed(struct disk *dp, const char *attr, int flag)
{
struct g_geom *gp;
struct g_provider *pp;
gp = dp->d_geom;
if (gp != NULL)
LIST_FOREACH(pp, &gp->provider, provider)
(void)g_attr_changed(pp, attr, flag);
}
void
disk_media_changed(struct disk *dp, int flag)
{
struct g_geom *gp;
struct g_provider *pp;
gp = dp->d_geom;
if (gp != NULL) {
pp = LIST_FIRST(&gp->provider);
if (pp != NULL) {
KASSERT(LIST_NEXT(pp, provider) == NULL,
("geom %p has more than one provider", gp));
g_media_changed(pp, flag);
}
}
}
void
disk_media_gone(struct disk *dp, int flag)
{
struct g_geom *gp;
struct g_provider *pp;
gp = dp->d_geom;
if (gp != NULL) {
pp = LIST_FIRST(&gp->provider);
if (pp != NULL) {
KASSERT(LIST_NEXT(pp, provider) == NULL,
("geom %p has more than one provider", gp));
g_media_gone(pp, flag);
}
}
}
int
disk_resize(struct disk *dp, int flag)
{
if (dp->d_destroyed || dp->d_geom == NULL)
return (0);
return (g_post_event(g_disk_resize, dp, flag, NULL));
}
static void
g_kern_disks(void *p, int flag __unused)
{
struct sbuf *sb;
struct g_geom *gp;
char *sp;
sb = p;
sp = "";
g_topology_assert();
LIST_FOREACH(gp, &g_disk_class.geom, geom) {
sbuf_printf(sb, "%s%s", sp, gp->name);
sp = " ";
}
sbuf_finish(sb);
}
static int
sysctl_disks(SYSCTL_HANDLER_ARGS)
{
int error;
struct sbuf *sb;
sb = sbuf_new_auto();
g_waitfor_event(g_kern_disks, sb, M_WAITOK, NULL);
error = SYSCTL_OUT(req, sbuf_data(sb), sbuf_len(sb) + 1);
sbuf_delete(sb);
return error;
}
SYSCTL_PROC(_kern, OID_AUTO, disks,
CTLTYPE_STRING | CTLFLAG_RD | CTLFLAG_MPSAFE, NULL, 0,
sysctl_disks, "A", "names of available disks");
Reference in New Issue View Git Blame Copy Permalink