Commit Graph

95 Commits

Author SHA1 Message Date
pjd
e225ca8138 - Assert that we don't send new provider event for a provider which has
G_PF_WITHER flag set.
- Fix typo in assertion condition (sorry, but I forgot who report that).
2008-05-18 22:50:50 +00:00
pjd
21a0be64c7 Play nice with DDB pager.
Educated by:	jhb's BSDCan presentation
2008-05-18 21:13:10 +00:00
marcel
dd866faa70 When retasting, wither any existing GEOMs of the same class. This
allows the class to create a different GEOM for the same provider
as well as avoid that we end up with multiple GEOMs of the same
class with the same name.

For example, when a disk contains a PC98 partition table but
only MBR is supported, then the partition table can be treated
as a MBR. If support for PC98 is later loaded as a module, the
MBR scheme is pre-empted for the PC98 scheme as expected.
2008-03-28 06:31:12 +00:00
marcel
31a163ef06 Add g_retaste(), which given a class will present all non-open providers
to it for tasting. This is useful when the class, through means outside
the scope of GEOM, can claim providers previously unclaimed.

The g_retaste() function posts an event which is handled by the
g_retaste_event().

Event suggested by: phk
2008-03-23 01:23:35 +00:00
pjd
ddfa2416f5 - Implement helper g_handleattr_str() function for string attributes
handling.
- Extend g_handleattr() to treat attribute as string when len=0.

OK'ed by:	phk
2007-05-05 16:33:44 +00:00
pjd
556424a17a Add 'show geom [addr]' ddb(4) command, which prints entire GEOM topology if
no additional argument is given or details about the given GEOM object
(class, geom, provider or consumer).

Approved by:	phk
2006-09-15 16:36:45 +00:00
marcel
c168f9530e Add g_wither_provider() to abstract the details of destroying a
particular provider. Use this function where g_orphan_provider()
is being called so that the flags are updated correctly and
g_orphan_provider() is called only when allowed.
2006-04-10 03:55:13 +00:00
jdp
536960dbba Fix a bug that caused some /dev entries to continue to exist after
the underlying drive had been hot-unplugged from the system.  Here
is a specific example.  Filesystem code had opened /dev/da1s1e.
Subsequently, the drive was hot-unplugged.  This (correctly) caused
all of the associated /dev/da1* entries to be deleted.  When the
filesystem later realized that the drive was gone it closed the
device, reducing the write-access counts to 0 on the geom providers
for da1s1e, da1s1, and da1.  This caused geom to re-taste the
providers, resulting in the devices being created again.  When the
drive was hot-plugged back in, it resulted in duplicate /dev entries
for da1s1e, da1s1, and da1.

This fix adds a new disk_gone() function which is called by CAM when a
drive goes away.  It orphans all of the providers associated with the
drive, setting an error condition of ENXIO in each one.  In addition,
we prevent a re-taste on last close for writing if an error condition
has been set in the provider.

Sponsored by:   Isilon Systems
Reviewed by:    phk
MFC after:      1 week
2005-11-18 02:43:49 +00:00
phk
55543da1eb fix a "modify after free" bug which is practically impossible to
experience.

Found by:	Coverity (id #540 #541)
2005-03-26 21:07:35 +00:00
phk
269b7a298a Add g_wither_geom_close() function. 2004-10-29 09:19:03 +00:00
phk
80dc3e1bc2 Don't call g_waitidle(), it happens automagically now. 2004-10-23 20:52:15 +00:00
arr
b510c7b809 - Turn KASSERT()s into warning printf()'s in the g_class_load() routine.
This removes a panic that will occur if you build with GENERIC and
  attempt to kldload a GEOM module that is already in the kernel.

Reviewed by: phk
2004-10-22 22:16:24 +00:00
green
c125751bac When loading GEOM modules, we expect the actual load process to be done
by the time that kldload(8) returns.  Satisfy that by making the GEOM
module load event -- only when the kernel is !cold -- wait until the
GEOM module init function has finished instead of returning immediately.

This is the other half of fixing md(8) (actually, "mfs" in fstab(5))
that is similar to r1.128 of src/sys/dev/md/md.c.  This bug would be
why RAM disks would often fail on boot and the first call to mdconfig(8)
would probably fail.

pjd has ideas for not requiring kldload(8) to work synchronously for
control devices that could make this obsolete.

Silence on:	-arch
2004-10-12 04:44:54 +00:00
phk
38ae102f61 For removable devices without media we set a zero mediasize but a non-zero
sectorsize in order to avoid a lot of checks around various divisions etc.

Enforce the sectorsize being > 0 with a KASSERT on successful open.

Fix scsi_cd.c to return 2k sectors when no media inserted.
2004-09-05 21:15:58 +00:00
phk
685cf0583f OK, now check geom class version numbers. 2004-08-08 08:34:46 +00:00
phk
2568a59fae OOps, that check was a bit premature. Allow zero versions as well. 2004-08-08 07:30:47 +00:00
phk
e7ff003728 Give classes a version number and refuse to touch classes which are not
understood.  This makes room for additional binary compatibility in the
future.

Put fields in the class for the geom's methods and initialize the methods
of a new geom from these fields.  This saves some code in all classes.
2004-08-08 06:46:27 +00:00
phk
5be6baa85c Only detach consumers which are attached when we wither stuff away.
Pointed out by:	pjd
2004-07-09 14:06:17 +00:00
phk
042d10f8ef Make withering water tight.
When we orphan/wither a provider, an attached geom+consumer could
end up being withered as a result and it may be in front of us in
the normal object scanning order so we need to do multi-pass.  On
the other hand, there may be withering stuff we can't get rid off
(yet), so we need to keep track of both the existence of withering
stuff and if there is more we can do at this time.
2004-07-08 16:17:14 +00:00
phk
a0a0195602 Fail normally rather than KASSERT if attempt to open a spoiled consumer. 2004-07-08 10:34:09 +00:00
pjd
5fae899223 Move "is consumer attached?" check before G_VALID_PROVIDER() check,
because if consumer is not attached, its provider never will be valid,
so we never reach this check.

Approved by:	phk
2004-03-18 07:17:10 +00:00
phk
8940a1c435 Be more insistent on destroying geoms at unload time. Still not perfect,
but it will do (better) for now.

KASSERT that to have providers a class must have an access method.

Tag the new_provider event with the geom as well.
2004-03-11 08:16:23 +00:00
phk
9a7074f4cb Rearrange some of the GEOM debugging tools to be more structured.
Retire g_sanity() and corresponding debugflag (0x8)

  Retire g_{stall,release}_events().

  Under #ifdef DIAGNOSTIC:

    Make g_valid_obj() an official function and have it return an an
    non-zero integer which indicates the kind of object when found.

    Implement G_VALID_{CLASS,GEOM,CONSUMER,PROVIDER}() macros based
    on g_valid_obj().

    Sprinkle calls to these macros liberally over the infrastructure.

    Always check that we do not free a live object.
2004-03-10 08:49:08 +00:00
phk
4b105bbf3a Don't panic on providers already withered when we wither a geom. 2004-03-07 17:33:15 +00:00
phk
14df0ab802 Add a KASSERT which checks that a class never fails a closing ->access()
call.
2004-02-14 17:58:57 +00:00
phk
124977fbb6 Remove the absolute count g_access_abs() function since experience has
shown that it is not useful.

Rename the relative count g_access_rel() function to g_access(), only
the name has changed.

Change all g_access_rel() calls in our CVS tree to call g_access() instead.

Add an #ifndef BURN_BRIDGES #define of g_access_rel() for source
code compatibility.
2004-02-12 22:42:11 +00:00
phk
f0fded48fd Allow a GEOM class to unload if it has no geoms or a method function to
get rid of them.

Prodded by:	pjd
2004-02-02 19:49:41 +00:00
pjd
35dc7138a2 - Use proper names in KASSERTs.
- Typos.

Approved by:	phk, scottl (mentor)
2004-02-02 17:50:09 +00:00
phk
67d8392228 Add KASSERTS.
Submitted by:	Pawel Jakub Dawidek <nick@garage.freebsd.pl>
2004-01-23 21:02:49 +00:00
phk
cd37a85408 Plug an insignificant memoryleak.
Submitted by:	Pawel Jakub Dawidek <nick@garage.freebsd.pl>
2004-01-23 20:40:25 +00:00
phk
437b669def Print the correct pointer in a KASSERT.
Submitted by:	Pawel Jakub Dawidek <nick@garage.freebsd.pl>
2004-01-11 10:02:42 +00:00
phk
cce4827569 KASSERT against no-op access requests.
Submitted by:	Pawel Jakub Dawidek <nick@garage.freebsd.pl>
2004-01-09 16:10:32 +00:00
phk
d7fc6b258d Call class->init() an class->fini() while the class is hooked up,
rather than right before and right after.  This allows these routines
to manipulate the mesh.

KASSERT that nobody creates a geom on an alien class.

Assert topology in g_valid_obj().

Approved by:	re@
2003-11-18 18:17:39 +00:00
phk
06ab707e79 This is a crude bandaid for 5.2 to protect against providers which disappear
while being tasted.  I can moderately easy trigger this with atapi-cd, but
I do not fully understand the circumstances.
2003-11-15 18:44:43 +00:00
phk
dc1586f843 Introduce a per provider wither flag 2003-10-06 09:05:44 +00:00
phk
ec0641f616 Don't panic over the fact that unloading failed if we already knew that. 2003-08-22 11:00:54 +00:00
obrien
40ee2bd5c8 Use __FBSDID().
Approved by:	phk
2003-06-11 06:49:16 +00:00
phk
dd1aaed417 Drop a memory-corruption debugging test-tool. 2003-06-07 10:55:48 +00:00
phk
69b4e9ce01 Add missing va_end() calls.
Noticed by:	tmm
2003-06-07 10:16:53 +00:00
phk
e23e34a198 Introduce g_provider_by_name() function, and use it. 2003-06-04 18:17:52 +00:00
phk
1ee949187c Add a KASSERT to prevent the same GEOM class from being processed loaded
twice.

Enforce that classes should have different names while we are here.
2003-06-04 17:51:10 +00:00
phk
5a2388f470 constify g_sanity() 2003-06-01 13:30:39 +00:00
phk
3325608f8f Introduce a init and fini member functions on a class.
Use ->init() and ->fini() to handle the mutex in geom_disk.c

Remove the g_add_class() function and replace it with a standardized
g_modevent() function.

This adds the basic infrastructure for loading/unloading GEOM classes
2003-05-31 18:13:07 +00:00
phk
055cf65eb1 Back out all the stuff that didn't belong in the last commit. 2003-05-02 06:42:59 +00:00
phk
4c52a206d2 Use g_slice_spoiled() rather than g_std_spoiled().
Remember to free the buffer we got from g_read_data().
2003-05-02 06:36:14 +00:00
phk
098143e63b Rework the "withering" mechanism:
Introduce g_wither_geom() to do the work in one single place.
2003-05-02 06:15:27 +00:00
phk
c51ae09b82 Remove the now obsolete geomidorname hack. 2003-05-01 20:32:24 +00:00
phk
def0071c3d Remove now unneeded special case for "geom.ctl". 2003-05-01 18:18:14 +00:00
phk
3bbfe9f43b Rename g_call_me() to g_post_event(), and give it a flag
argument to determine if we can M_WAITOK in malloc.
2003-04-23 20:46:12 +00:00
phk
7c462ceb2b Turn EV_NEW_PROVIDER into a g_call_me() event. 2003-04-23 20:16:13 +00:00