freebsd-nq/sys/vm/vm_init.c
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

210 lines
6.6 KiB
C

/*-
* Copyright (c) 1991, 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* The Mach Operating System project at Carnegie-Mellon University.
*
* 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.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS 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 REGENTS 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.
*
* from: @(#)vm_init.c 8.1 (Berkeley) 6/11/93
*
*
* Copyright (c) 1987, 1990 Carnegie-Mellon University.
* All rights reserved.
*
* Authors: Avadis Tevanian, Jr., Michael Wayne Young
*
* Permission to use, copy, modify and distribute this software and
* its documentation is hereby granted, provided that both the copyright
* notice and this permission notice appear in all copies of the
* software, derivative works or modified versions, and any portions
* thereof, and that both notices appear in supporting documentation.
*
* CARNEGIE MELLON ALLOWS FREE USE OF THIS SOFTWARE IN ITS "AS IS"
* CONDITION. CARNEGIE MELLON DISCLAIMS ANY LIABILITY OF ANY KIND
* FOR ANY DAMAGES WHATSOEVER RESULTING FROM THE USE OF THIS SOFTWARE.
*
* Carnegie Mellon requests users of this software to return to
*
* Software Distribution Coordinator or Software.Distribution@CS.CMU.EDU
* School of Computer Science
* Carnegie Mellon University
* Pittsburgh PA 15213-3890
*
* any improvements or extensions that they make and grant Carnegie the
* rights to redistribute these changes.
*/
/*
* Initialize the Virtual Memory subsystem.
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <sys/param.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/proc.h>
#include <sys/rwlock.h>
#include <sys/sysctl.h>
#include <sys/systm.h>
#include <sys/selinfo.h>
#include <sys/pipe.h>
#include <sys/bio.h>
#include <sys/buf.h>
#include <vm/vm.h>
#include <vm/vm_param.h>
#include <vm/vm_kern.h>
#include <vm/vm_object.h>
#include <vm/vm_page.h>
#include <vm/vm_map.h>
#include <vm/vm_pager.h>
#include <vm/vm_extern.h>
long physmem;
static int exec_map_entries = 16;
TUNABLE_INT("vm.exec_map_entries", &exec_map_entries);
SYSCTL_INT(_vm, OID_AUTO, exec_map_entries, CTLFLAG_RD, &exec_map_entries, 0,
"Maximum number of simultaneous execs");
/*
* System initialization
*/
static void vm_mem_init(void *);
SYSINIT(vm_mem, SI_SUB_VM, SI_ORDER_FIRST, vm_mem_init, NULL);
/*
* vm_init initializes the virtual memory system.
* This is done only by the first cpu up.
*
* The start and end address of physical memory is passed in.
*/
/* ARGSUSED*/
static void
vm_mem_init(dummy)
void *dummy;
{
/*
* Initializes resident memory structures. From here on, all physical
* memory is accounted for, and we use only virtual addresses.
*/
vm_set_page_size();
virtual_avail = vm_page_startup(virtual_avail);
/*
* Initialize other VM packages
*/
vm_object_init();
vm_map_startup();
kmem_init(virtual_avail, virtual_end);
pmap_init();
vm_pager_init();
}
void
vm_ksubmap_init(struct kva_md_info *kmi)
{
vm_offset_t firstaddr;
caddr_t v;
vm_size_t size = 0;
long physmem_est;
vm_offset_t minaddr;
vm_offset_t maxaddr;
vm_map_t clean_map;
/*
* Allocate space for system data structures.
* The first available kernel virtual address is in "v".
* As pages of kernel virtual memory are allocated, "v" is incremented.
* As pages of memory are allocated and cleared,
* "firstaddr" is incremented.
* An index into the kernel page table corresponding to the
* virtual memory address maintained in "v" is kept in "mapaddr".
*/
/*
* Make two passes. The first pass calculates how much memory is
* needed and allocates it. The second pass assigns virtual
* addresses to the various data structures.
*/
firstaddr = 0;
again:
v = (caddr_t)firstaddr;
/*
* Discount the physical memory larger than the size of kernel_map
* to avoid eating up all of KVA space.
*/
physmem_est = lmin(physmem, btoc(kernel_map->max_offset -
kernel_map->min_offset));
v = kern_vfs_bio_buffer_alloc(v, physmem_est);
/*
* End of first pass, size has been calculated so allocate memory
*/
if (firstaddr == 0) {
size = (vm_size_t)v;
firstaddr = kmem_alloc(kernel_map, round_page(size));
if (firstaddr == 0)
panic("startup: no room for tables");
goto again;
}
/*
* End of second pass, addresses have been assigned
*/
if ((vm_size_t)((char *)v - firstaddr) != size)
panic("startup: table size inconsistency");
clean_map = kmem_suballoc(kernel_map, &kmi->clean_sva, &kmi->clean_eva,
(long)nbuf * BKVASIZE + (long)nswbuf * MAXPHYS +
(long)bio_transient_maxcnt * MAXPHYS, TRUE);
buffer_map = kmem_suballoc(clean_map, &kmi->buffer_sva,
&kmi->buffer_eva, (long)nbuf * BKVASIZE, FALSE);
buffer_map->system_map = 1;
bio_transient_map = kmem_suballoc(clean_map, &kmi->bio_transient_sva,
&kmi->bio_transient_eva, (long)bio_transient_maxcnt * MAXPHYS,
FALSE);
bio_transient_map->system_map = 1;
pager_map = kmem_suballoc(clean_map, &kmi->pager_sva, &kmi->pager_eva,
(long)nswbuf * MAXPHYS, FALSE);
pager_map->system_map = 1;
exec_map = kmem_suballoc(kernel_map, &minaddr, &maxaddr,
exec_map_entries * round_page(PATH_MAX + ARG_MAX), FALSE);
pipe_map = kmem_suballoc(kernel_map, &minaddr, &maxaddr, maxpipekva,
FALSE);
/*
* XXX: Mbuf system machine-specific initializations should
* go here, if anywhere.
*/
}