freebsd-skq/sys/vm/uma_dbg.c
bmilekic f7574a2276 Bring in mbuma to replace mballoc.
mbuma is an Mbuf & Cluster allocator built on top of a number of
extensions to the UMA framework, all included herein.

Extensions to UMA worth noting:
  - Better layering between slab <-> zone caches; introduce
    Keg structure which splits off slab cache away from the
    zone structure and allows multiple zones to be stacked
    on top of a single Keg (single type of slab cache);
    perhaps we should look into defining a subset API on
    top of the Keg for special use by malloc(9),
    for example.
  - UMA_ZONE_REFCNT zones can now be added, and reference
    counters automagically allocated for them within the end
    of the associated slab structures.  uma_find_refcnt()
    does a kextract to fetch the slab struct reference from
    the underlying page, and lookup the corresponding refcnt.

mbuma things worth noting:
  - integrates mbuf & cluster allocations with extended UMA
    and provides caches for commonly-allocated items; defines
    several zones (two primary, one secondary) and two kegs.
  - change up certain code paths that always used to do:
    m_get() + m_clget() to instead just use m_getcl() and
    try to take advantage of the newly defined secondary
    Packet zone.
  - netstat(1) and systat(1) quickly hacked up to do basic
    stat reporting but additional stats work needs to be
    done once some other details within UMA have been taken
    care of and it becomes clearer to how stats will work
    within the modified framework.

From the user perspective, one implication is that the
NMBCLUSTERS compile-time option is no longer used.  The
maximum number of clusters is still capped off according
to maxusers, but it can be made unlimited by setting
the kern.ipc.nmbclusters boot-time tunable to zero.
Work should be done to write an appropriate sysctl
handler allowing dynamic tuning of kern.ipc.nmbclusters
at runtime.

Additional things worth noting/known issues (READ):
   - One report of 'ips' (ServeRAID) driver acting really
     slow in conjunction with mbuma.  Need more data.
     Latest report is that ips is equally sucking with
     and without mbuma.
   - Giant leak in NFS code sometimes occurs, can't
     reproduce but currently analyzing; brueffer is
     able to reproduce but THIS IS NOT an mbuma-specific
     problem and currently occurs even WITHOUT mbuma.
   - Issues in network locking: there is at least one
     code path in the rip code where one or more locks
     are acquired and we end up in m_prepend() with
     M_WAITOK, which causes WITNESS to whine from within
     UMA.  Current temporary solution: force all UMA
     allocations to be M_NOWAIT from within UMA for now
     to avoid deadlocks unless WITNESS is defined and we
     can determine with certainty that we're not holding
     any locks when we're M_WAITOK.
   - I've seen at least one weird socketbuffer empty-but-
     mbuf-still-attached panic.  I don't believe this
     to be related to mbuma but please keep your eyes
     open, turn on debugging, and capture crash dumps.

This change removes more code than it adds.

A paper is available detailing the change and considering
various performance issues, it was presented at BSDCan2004:
http://www.unixdaemons.com/~bmilekic/netbuf_bmilekic.pdf
Please read the paper for Future Work and implementation
details, as well as credits.

Testing and Debugging:
    rwatson,
    brueffer,
    Ketrien I. Saihr-Kesenchedra,
    ...
Reviewed by: Lots of people (for different parts)
2004-05-31 21:46:06 +00:00

287 lines
6.4 KiB
C

/*
* Copyright (c) 2002, Jeffrey Roberson <jeff@freebsd.org>
* All rights reserved.
*
* 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 unmodified, 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.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``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 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.
*/
/*
* uma_dbg.c Debugging features for UMA users
*
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/types.h>
#include <sys/queue.h>
#include <sys/lock.h>
#include <sys/mutex.h>
#include <sys/malloc.h>
#include <vm/vm.h>
#include <vm/vm_object.h>
#include <vm/vm_page.h>
#include <vm/uma.h>
#include <vm/uma_int.h>
#include <vm/uma_dbg.h>
static const u_int32_t uma_junk = 0xdeadc0de;
/*
* Checks an item to make sure it hasn't been overwritten since freed.
*
* Complies with standard ctor arg/return
*
*/
void
trash_ctor(void *mem, int size, void *arg)
{
int cnt;
u_int32_t *p;
cnt = size / sizeof(uma_junk);
for (p = mem; cnt > 0; cnt--, p++)
if (*p != uma_junk)
panic("Memory modified after free %p(%d) val=%x @ %p\n",
mem, size, *p, p);
}
/*
* Fills an item with predictable garbage
*
* Complies with standard dtor arg/return
*
*/
void
trash_dtor(void *mem, int size, void *arg)
{
int cnt;
u_int32_t *p;
cnt = size / sizeof(uma_junk);
for (p = mem; cnt > 0; cnt--, p++)
*p = uma_junk;
}
/*
* Fills an item with predictable garbage
*
* Complies with standard init arg/return
*
*/
void
trash_init(void *mem, int size)
{
trash_dtor(mem, size, NULL);
}
/*
* Checks an item to make sure it hasn't been overwritten since it was freed.
*
* Complies with standard fini arg/return
*
*/
void
trash_fini(void *mem, int size)
{
trash_ctor(mem, size, NULL);
}
/*
* Checks an item to make sure it hasn't been overwritten since freed.
*
* Complies with standard ctor arg/return
*
*/
void
mtrash_ctor(void *mem, int size, void *arg)
{
struct malloc_type **ksp;
u_int32_t *p = mem;
int cnt;
size -= sizeof(struct malloc_type *);
ksp = (struct malloc_type **)mem;
ksp += size / sizeof(struct malloc_type *);
cnt = size / sizeof(uma_junk);
for (p = mem; cnt > 0; cnt--, p++)
if (*p != uma_junk) {
printf("Memory modified after free %p(%d) val=%x @ %p\n",
mem, size, *p, p);
panic("Most recently used by %s\n", (*ksp == NULL)?
"none" : (*ksp)->ks_shortdesc);
}
}
/*
* Fills an item with predictable garbage
*
* Complies with standard dtor arg/return
*
*/
void
mtrash_dtor(void *mem, int size, void *arg)
{
int cnt;
u_int32_t *p;
size -= sizeof(struct malloc_type *);
cnt = size / sizeof(uma_junk);
for (p = mem; cnt > 0; cnt--, p++)
*p = uma_junk;
}
/*
* Fills an item with predictable garbage
*
* Complies with standard init arg/return
*
*/
void
mtrash_init(void *mem, int size)
{
struct malloc_type **ksp;
mtrash_dtor(mem, size, NULL);
ksp = (struct malloc_type **)mem;
ksp += (size / sizeof(struct malloc_type *)) - 1;
*ksp = NULL;
}
/*
* Checks an item to make sure it hasn't been overwritten since it was freed.
*
* Complies with standard fini arg/return
*
*/
void
mtrash_fini(void *mem, int size)
{
mtrash_ctor(mem, size, NULL);
}
static uma_slab_t
uma_dbg_getslab(uma_zone_t zone, void *item)
{
uma_slab_t slab;
uma_keg_t keg;
u_int8_t *mem;
keg = zone->uz_keg;
mem = (u_int8_t *)((unsigned long)item & (~UMA_SLAB_MASK));
if (keg->uk_flags & UMA_ZONE_MALLOC) {
slab = vtoslab((vm_offset_t)mem);
} else if (keg->uk_flags & UMA_ZONE_HASH) {
slab = hash_sfind(&keg->uk_hash, mem);
} else {
mem += keg->uk_pgoff;
slab = (uma_slab_t)mem;
}
return (slab);
}
/*
* Set up the slab's freei data such that uma_dbg_free can function.
*
*/
void
uma_dbg_alloc(uma_zone_t zone, uma_slab_t slab, void *item)
{
uma_keg_t keg;
int freei;
keg = zone->uz_keg;
if (slab == NULL) {
slab = uma_dbg_getslab(zone, item);
if (slab == NULL)
panic("uma: item %p did not belong to zone %s\n",
item, zone->uz_name);
}
freei = ((unsigned long)item - (unsigned long)slab->us_data)
/ keg->uk_rsize;
slab->us_freelist[freei].us_item = 255;
return;
}
/*
* Verifies freed addresses. Checks for alignment, valid slab membership
* and duplicate frees.
*
*/
void
uma_dbg_free(uma_zone_t zone, uma_slab_t slab, void *item)
{
uma_keg_t keg;
int freei;
keg = zone->uz_keg;
if (slab == NULL) {
slab = uma_dbg_getslab(zone, item);
if (slab == NULL)
panic("uma: Freed item %p did not belong to zone %s\n",
item, zone->uz_name);
}
freei = ((unsigned long)item - (unsigned long)slab->us_data)
/ keg->uk_rsize;
if (freei >= keg->uk_ipers)
panic("zone: %s(%p) slab %p freelist %d out of range 0-%d\n",
zone->uz_name, zone, slab, freei, keg->uk_ipers-1);
if (((freei * keg->uk_rsize) + slab->us_data) != item) {
printf("zone: %s(%p) slab %p freed address %p unaligned.\n",
zone->uz_name, zone, slab, item);
panic("should be %p\n",
(freei * keg->uk_rsize) + slab->us_data);
}
if (slab->us_freelist[freei].us_item != 255) {
printf("Slab at %p, freei %d = %d.\n",
slab, freei, slab->us_freelist[freei].us_item);
panic("Duplicate free of item %p from zone %p(%s)\n",
item, zone, zone->uz_name);
}
/*
* When this is actually linked into the slab this will change.
* Until then the count of valid slabs will make sure we don't
* accidentally follow this and assume it's a valid index.
*/
slab->us_freelist[freei].us_item = 0;
}