freebsd-dev/sys/i386/include/pmap.h

347 lines
9.2 KiB
C
Raw Normal View History

1995-05-30 08:16:23 +00:00
/*
1993-06-12 14:58:17 +00:00
* Copyright (c) 1991 Regents of the University of California.
* All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* the Systems Programming Group of the University of Utah Computer
* Science Department and William Jolitz of UUNET Technologies Inc.
*
* 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.
*
* Derived from hp300 version by Mike Hibler, this version by William
* Jolitz uses a recursive map [a pde points to the page directory] to
* map the page tables using the pagetables themselves. This is done to
* reduce the impact on kernel virtual memory for lots of sparse address
* space, and to reduce the cost of memory to each process.
*
* from: hp300: @(#)pmap.h 7.2 (Berkeley) 12/16/90
* from: @(#)pmap.h 7.4 (Berkeley) 5/12/91
1999-08-28 01:08:13 +00:00
* $FreeBSD$
1993-06-12 14:58:17 +00:00
*/
#ifndef _MACHINE_PMAP_H_
#define _MACHINE_PMAP_H_
1993-06-12 14:58:17 +00:00
/*
* Page-directory and page-table entires follow this format, with a few
* of the fields not present here and there, depending on a lot of things.
*/
/* ---- Intel Nomenclature ---- */
#define PG_V 0x001 /* P Valid */
#define PG_RW 0x002 /* R/W Read/Write */
#define PG_U 0x004 /* U/S User/Supervisor */
#define PG_NC_PWT 0x008 /* PWT Write through */
#define PG_NC_PCD 0x010 /* PCD Cache disable */
#define PG_A 0x020 /* A Accessed */
#define PG_M 0x040 /* D Dirty */
#define PG_PS 0x080 /* PS Page size (0=4k,1=4M) */
#define PG_G 0x100 /* G Global */
#define PG_AVAIL1 0x200 /* / Available for system */
#define PG_AVAIL2 0x400 /* < programmers use */
#define PG_AVAIL3 0x800 /* \ */
/* Our various interpretations of the above */
#define PG_W PG_AVAIL1 /* "Wired" pseudoflag */
This set of commits to the VM system does the following, and contain contributions or ideas from Stephen McKay <syssgm@devetir.qld.gov.au>, Alan Cox <alc@cs.rice.edu>, David Greenman <davidg@freebsd.org> and me: More usage of the TAILQ macros. Additional minor fix to queue.h. Performance enhancements to the pageout daemon. Addition of a wait in the case that the pageout daemon has to run immediately. Slightly modify the pageout algorithm. Significant revamp of the pmap/fork code: 1) PTE's and UPAGES's are NO LONGER in the process's map. 2) PTE's and UPAGES's reside in their own objects. 3) TOTAL elimination of recursive page table pagefaults. 4) The page directory now resides in the PTE object. 5) Implemented pmap_copy, thereby speeding up fork time. 6) Changed the pv entries so that the head is a pointer and not an entire entry. 7) Significant cleanup of pmap_protect, and pmap_remove. 8) Removed significant amounts of machine dependent fork code from vm_glue. Pushed much of that code into the machine dependent pmap module. 9) Support more completely the reuse of already zeroed pages (Page table pages and page directories) as being already zeroed. Performance and code cleanups in vm_map: 1) Improved and simplified allocation of map entries. 2) Improved vm_map_copy code. 3) Corrected some minor problems in the simplify code. Implemented splvm (combo of splbio and splimp.) The VM code now seldom uses splhigh. Improved the speed of and simplified kmem_malloc. Minor mod to vm_fault to avoid using pre-zeroed pages in the case of objects with backing objects along with the already existant condition of having a vnode. (If there is a backing object, there will likely be a COW... With a COW, it isn't necessary to start with a pre-zeroed page.) Minor reorg of source to perhaps improve locality of ref.
1996-05-18 03:38:05 +00:00
#define PG_MANAGED PG_AVAIL2
#define PG_FRAME (~((vm_paddr_t)PAGE_MASK))
#define PG_PROT (PG_RW|PG_U) /* all protection bits . */
#define PG_N (PG_NC_PWT|PG_NC_PCD) /* Non-cacheable */
1993-06-12 14:58:17 +00:00
/*
* Page Protection Exception bits
*/
#define PGEX_P 0x01 /* Protection violation vs. not present */
#define PGEX_W 0x02 /* during a Write cycle */
#define PGEX_U 0x04 /* access from User mode (UPL) */
/*
* Size of Kernel address space. This is the number of page table pages
* (4MB each) to use for the kernel. 256 pages == 1 Gigabyte.
* This **MUST** be a multiple of 4 (eg: 252, 256, 260, etc).
*/
#ifndef KVA_PAGES
#ifdef PAE
#define KVA_PAGES 512
#else
#define KVA_PAGES 256
#endif
#endif
/*
* Pte related macros
*/
#define VADDR(pdi, pti) ((vm_offset_t)(((pdi)<<PDRSHIFT)|((pti)<<PAGE_SHIFT)))
1993-06-12 14:58:17 +00:00
#ifndef NKPT
#ifdef PAE
#define NKPT 120 /* actual number of kernel page tables */
#else
#define NKPT 30 /* actual number of kernel page tables */
These changes embody the support of the fully coherent merged VM buffer cache, much higher filesystem I/O performance, and much better paging performance. It represents the culmination of over 6 months of R&D. The majority of the merged VM/cache work is by John Dyson. The following highlights the most significant changes. Additionally, there are (mostly minor) changes to the various filesystem modules (nfs, msdosfs, etc) to support the new VM/buffer scheme. vfs_bio.c: Significant rewrite of most of vfs_bio to support the merged VM buffer cache scheme. The scheme is almost fully compatible with the old filesystem interface. Significant improvement in the number of opportunities for write clustering. vfs_cluster.c, vfs_subr.c Upgrade and performance enhancements in vfs layer code to support merged VM/buffer cache. Fixup of vfs_cluster to eliminate the bogus pagemove stuff. vm_object.c: Yet more improvements in the collapse code. Elimination of some windows that can cause list corruption. vm_pageout.c: Fixed it, it really works better now. Somehow in 2.0, some "enhancements" broke the code. This code has been reworked from the ground-up. vm_fault.c, vm_page.c, pmap.c, vm_object.c Support for small-block filesystems with merged VM/buffer cache scheme. pmap.c vm_map.c Dynamic kernel VM size, now we dont have to pre-allocate excessive numbers of kernel PTs. vm_glue.c Much simpler and more effective swapping code. No more gratuitous swapping. proc.h Fixed the problem that the p_lock flag was not being cleared on a fork. swap_pager.c, vnode_pager.c Removal of old vfs_bio cruft to support the past pseudo-coherency. Now the code doesn't need it anymore. machdep.c Changes to better support the parameter values for the merged VM/buffer cache scheme. machdep.c, kern_exec.c, vm_glue.c Implemented a seperate submap for temporary exec string space and another one to contain process upages. This eliminates all map fragmentation problems that previously existed. ffs_inode.c, ufs_inode.c, ufs_readwrite.c Changes for merged VM/buffer cache. Add "bypass" support for sneaking in on busy buffers. Submitted by: John Dyson and David Greenman
1995-01-09 16:06:02 +00:00
#endif
#endif
#ifndef NKPDE
#ifdef SMP
#define NKPDE (KVA_PAGES - 1) /* number of page tables/pde's */
#else
#define NKPDE (KVA_PAGES) /* number of page tables/pde's */
#endif
#endif
/*
* The *PTDI values control the layout of virtual memory
*
* XXX This works for now, but I am not real happy with it, I'll fix it
* right after I fix locore.s and the magic 28K hole
*
* SMP_PRIVPAGES: The per-cpu address space is 0xff80000 -> 0xffbfffff
*/
#ifdef SMP
#define MPPTDI (NPDEPTD-1) /* per cpu ptd entry */
#define KPTDI (MPPTDI-NKPDE) /* start of kernel virtual pde's */
#else
#define KPTDI (NPDEPTD-NKPDE)/* start of kernel virtual pde's */
#endif /* SMP */
#define PTDPTDI (KPTDI-NPGPTD) /* ptd entry that points to ptd! */
First steps in rewriting locore.s, and making info useful when the machine panics. i386/i386/locore.s: 1) got rid of most .set directives that were being used like #define's, and replaced them with appropriate #define's in the appropriate header files (accessed via genassym). 2) added comments to header inclusions and global definitions, and global variables 3) replaced some hardcoded constants with cpp defines (such as PDESIZE and others) 4) aligned all comments to the same column to make them easier to read 5) moved macro definitions for ENTRY, ALIGN, NOP, etc. to /sys/i386/include/asmacros.h 6) added #ifdef BDE_DEBUGGER around all of Bruce's debugger code 7) added new global '_KERNend' to store last location+1 of kernel 8) cleaned up zeroing of bss so that only bss is zeroed 9) fix zeroing of page tables so that it really does zero them all - not just if they follow the bss. 10) rewrote page table initialization code so that 1) works correctly and 2) write protects the kernel text by default 11) properly initialize the kernel page directory, upages, p0stack PT, and page tables. The previous scheme was more than a bit screwy. 12) change allocation of virtual area of IO hole so that it is fixed at KERNBASE + 0xa0000. The previous scheme put it right after the kernel page tables and then later expected it to be at KERNBASE +0xa0000 13) change multiple bogus settings of user read/write of various areas of kernel VM - including the IO hole; we should never be accessing the IO hole in user mode through the kernel page tables 14) split kernel support routines such as bcopy, bzero, copyin, copyout, etc. into a seperate file 'support.s' 15) split swtch and related routines into a seperate 'swtch.s' 16) split routines related to traps, syscalls, and interrupts into a seperate file 'exception.s' 17) remove some unused global variables from locore that got inserted by Garrett when he pulled them out of some .h files. i386/isa/icu.s: 1) clean up global variable declarations 2) move in declaration of astpending and netisr i386/i386/pmap.c: 1) fix calculation of virtual_avail. It previously was calculated to be right in the middle of the kernel page tables - not a good place to start allocating kernel VM. 2) properly allocate kernel page dir/tables etc out of kernel map - previously only took out 2 pages. i386/i386/machdep.c: 1) modify boot() to print a warning that the system will reboot in PANIC_REBOOT_WAIT_TIME amount of seconds, and let the user abort with a key on the console. The machine will wait for ever if a key is typed before the reboot. The default is 15 seconds, but can be set to 0 to mean don't wait at all, -1 to mean wait forever, or any positive value to wait for that many seconds. 2) print "Rebooting..." just before doing it. kern/subr_prf.c: 1) remove PANICWAIT as it is deprecated by the change to machdep.c i386/i386/trap.c: 1) add table of trap type strings and use it to print a real trap/ panic message rather than just a number. Lot's of work to be done here, but this is the first step. Symbolic traceback is in the TODO. i386/i386/Makefile.i386: 1) add support in to build support.s, exception.s and swtch.s ...and various changes to various header files to make all of the above happen.
1993-11-13 02:25:21 +00:00
/*
* XXX doesn't really belong here I guess...
*/
#define ISA_HOLE_START 0xa0000
#define ISA_HOLE_LENGTH (0x100000-ISA_HOLE_START)
#ifndef LOCORE
#include <sys/queue.h>
#ifdef PAE
typedef uint64_t pdpt_entry_t;
typedef uint64_t pd_entry_t;
typedef uint64_t pt_entry_t;
#define PTESHIFT (3)
#define PDESHIFT (3)
#else
typedef uint32_t pd_entry_t;
typedef uint32_t pt_entry_t;
#define PTESHIFT (2)
#define PDESHIFT (2)
1993-06-12 14:58:17 +00:00
#endif
1993-06-12 14:58:17 +00:00
/*
* Address of current and alternate address space page table maps
* and directories.
*/
#ifdef _KERNEL
extern pt_entry_t PTmap[];
extern pd_entry_t PTD[];
extern pd_entry_t PTDpde[];
1993-06-12 14:58:17 +00:00
#ifdef PAE
extern pdpt_entry_t *IdlePDPT;
#endif
Revive backed out pmap related changes from Feb 2002. The highlights are: - It actually works this time, honest! - Fine grained TLB shootdowns for SMP on i386. IPI's are very expensive, so try and optimize things where possible. - Introduce ranged shootdowns that can be done as a single IPI. - PG_G support for i386 - Specific-cpu targeted shootdowns. For example, there is no sense in globally purging the TLB cache for where we are stealing a page from the local unshared process on the local cpu. Use pm_active to track this. - Add some instrumentation for the tlb shootdown code. - Rip out SMP code from <machine/cpufunc.h> - Try and fix some very bogus PG_G and PG_PS interactions that were bad enough to cause vm86 bios calls to break. vm86 depended on our existing bugs and this was the cause of the VESA panics last time. - Fix the silly one-line error that caused the 'panic: bad pte' last time. - Fix a couple of other silly one-line errors that should have caused more pain than they did. Some more work is needed: - pmap_{zero,copy}_page[_idle]. These can be done without IPI's if we have a hook in cpu_switch. - The IPI handlers need some cleanup. I have a bogus %ds load that can be avoided. - APTD handling is rather bogus and appears to be a large source of global TLB IPI shootdowns for no really good reason. I see speedups of between 1.5% and ~4% on buildworlds in a while 1 loop. I expect to see a bigger difference when there is significant pageout activity or the system otherwise has memory shortages. I have backed out a few optimizations that I had been using over the last few days in order to be a little more conservative. I'll revisit these again over the next few days as the dust settles. New option: DISABLE_PG_G - In case I missed something.
2002-07-12 07:56:11 +00:00
extern pd_entry_t *IdlePTD; /* physical address of "Idle" state directory */
1993-06-12 14:58:17 +00:00
#endif
#ifdef _KERNEL
1993-06-12 14:58:17 +00:00
/*
* virtual address to page table entry and
* to physical address. Likewise for alternate address space.
* Note: these work recursively, thus vtopte of a pte will give
* the corresponding pde that in turn maps it.
*/
#define vtopte(va) (PTmap + i386_btop(va))
/*
* Routine: pmap_kextract
* Function:
* Extract the physical page address associated
* kernel virtual address.
*/
static __inline vm_paddr_t
pmap_kextract(vm_offset_t va)
{
vm_paddr_t pa;
if ((pa = PTD[va >> PDRSHIFT]) & PG_PS) {
pa = (pa & ~(NBPDR - 1)) | (va & (NBPDR - 1));
} else {
pa = *vtopte(va);
pa = (pa & PG_FRAME) | (va & PAGE_MASK);
}
return pa;
}
#define vtophys(va) pmap_kextract(((vm_offset_t) (va)))
#ifdef PAE
static __inline pt_entry_t
pte_load(pt_entry_t *ptep)
{
pt_entry_t r;
__asm __volatile(
"lock; cmpxchg8b %1"
: "=A" (r)
: "m" (*ptep), "a" (0), "d" (0), "b" (0), "c" (0));
return (r);
}
static __inline pt_entry_t
pte_load_store(pt_entry_t *ptep, pt_entry_t v)
{
pt_entry_t r;
r = *ptep;
__asm __volatile(
"1:\n"
"\tlock; cmpxchg8b %1\n"
"\tjnz 1b"
: "+A" (r)
: "m" (*ptep), "b" ((uint32_t)v), "c" ((uint32_t)(v >> 32)));
return (r);
}
#define pte_load_clear(ptep) pte_load_store((ptep), (pt_entry_t)0ULL)
#else /* PAE */
static __inline pt_entry_t
pte_load(pt_entry_t *ptep)
{
pt_entry_t r;
r = *ptep;
return (r);
}
static __inline pt_entry_t
pte_load_store(pt_entry_t *ptep, pt_entry_t pte)
{
pt_entry_t r;
r = *ptep;
*ptep = pte;
return (r);
}
#define pte_load_clear(pte) atomic_readandclear_int(pte)
#endif /* PAE */
#define pte_clear(ptep) pte_load_store((ptep), (pt_entry_t)0ULL)
#define pte_store(ptep, pte) pte_load_store((ptep), (pt_entry_t)pte)
#define pde_store(pdep, pde) pte_store((pdep), (pde))
#endif /* _KERNEL */
1993-06-12 14:58:17 +00:00
/*
* Pmap stuff
*/
struct pv_entry;
struct md_page {
int pv_list_count;
TAILQ_HEAD(,pv_entry) pv_list;
};
1993-06-12 14:58:17 +00:00
struct pmap {
pd_entry_t *pm_pdir; /* KVA of page directory */
TAILQ_HEAD(,pv_entry) pm_pvlist; /* list of mappings in pmap */
Commit a partial lazy thread switch mechanism for i386. it isn't as lazy as it could be and can do with some more cleanup. Currently its under options LAZY_SWITCH. What this does is avoid %cr3 reloads for short context switches that do not involve another user process. ie: we can take an interrupt, switch to a kthread and return to the user without explicitly flushing the tlb. However, this isn't as exciting as it could be, the interrupt overhead is still high and too much blocks on Giant still. There are some debug sysctls, for stats and for an on/off switch. The main problem with doing this has been "what if the process that you're running on exits while we're borrowing its address space?" - in this case we use an IPI to give it a kick when we're about to reclaim the pmap. Its not compiled in unless you add the LAZY_SWITCH option. I want to fix a few more things and get some more feedback before turning it on by default. This is NOT a replacement for Bosko's lazy interrupt stuff. This was more meant for the kthread case, while his was for interrupts. Mine helps a little for interrupts, but his helps a lot more. The stats are enabled with options SWTCH_OPTIM_STATS - this has been a pseudo-option for years, I just added a bunch of stuff to it. One non-trivial change was to select a new thread before calling cpu_switch() in the first place. This allows us to catch the silly case of doing a cpu_switch() to the current process. This happens uncomfortably often. This simplifies a bit of the asm code in cpu_switch (no longer have to call choosethread() in the middle). This has been implemented on i386 and (thanks to jake) sparc64. The others will come soon. This is actually seperate to the lazy switch stuff. Glanced at by: jake, jhb
2003-04-02 23:53:30 +00:00
u_int pm_active; /* active on cpus */
1993-06-12 14:58:17 +00:00
struct pmap_statistics pm_stats; /* pmap statistics */
LIST_ENTRY(pmap) pm_list; /* List of all pmaps */
#ifdef PAE
pdpt_entry_t *pm_pdpt; /* KVA of page director pointer
table */
#endif
1993-06-12 14:58:17 +00:00
};
#define pmap_page_is_mapped(m) (!TAILQ_EMPTY(&(m)->md.pv_list))
1993-06-12 14:58:17 +00:00
typedef struct pmap *pmap_t;
#ifdef _KERNEL
extern struct pmap kernel_pmap_store;
#define kernel_pmap (&kernel_pmap_store)
1993-06-12 14:58:17 +00:00
#endif
/*
* For each vm_page_t, there is a list of all currently valid virtual
* mappings of that page. An entry is a pv_entry_t, the list is pv_table.
*/
typedef struct pv_entry {
pmap_t pv_pmap; /* pmap where mapping lies */
vm_offset_t pv_va; /* virtual address for mapping */
TAILQ_ENTRY(pv_entry) pv_list;
TAILQ_ENTRY(pv_entry) pv_plist;
vm_page_t pv_ptem; /* VM page for pte */
1993-06-12 14:58:17 +00:00
} *pv_entry_t;
#ifdef _KERNEL
1993-06-12 14:58:17 +00:00
#define NPPROVMTRR 8
#define PPRO_VMTRRphysBase0 0x200
#define PPRO_VMTRRphysMask0 0x201
struct ppro_vmtrr {
u_int64_t base, mask;
};
extern struct ppro_vmtrr PPro_vmtrr[NPPROVMTRR];
extern caddr_t CADDR1;
extern pt_entry_t *CMAP1;
extern vm_paddr_t avail_end;
extern vm_paddr_t phys_avail[];
extern int pseflag;
extern int pgeflag;
extern char *ptvmmap; /* poor name! */
extern vm_offset_t virtual_avail;
extern vm_offset_t virtual_end;
1993-06-12 14:58:17 +00:00
void pmap_bootstrap(vm_paddr_t, vm_paddr_t);
void pmap_kenter(vm_offset_t va, vm_paddr_t pa);
void pmap_kremove(vm_offset_t);
void *pmap_mapdev(vm_paddr_t, vm_size_t);
2002-03-20 05:48:58 +00:00
void pmap_unmapdev(vm_offset_t, vm_size_t);
pt_entry_t *pmap_pte(pmap_t, vm_offset_t) __pure2;
void pmap_set_pg(void);
Revive backed out pmap related changes from Feb 2002. The highlights are: - It actually works this time, honest! - Fine grained TLB shootdowns for SMP on i386. IPI's are very expensive, so try and optimize things where possible. - Introduce ranged shootdowns that can be done as a single IPI. - PG_G support for i386 - Specific-cpu targeted shootdowns. For example, there is no sense in globally purging the TLB cache for where we are stealing a page from the local unshared process on the local cpu. Use pm_active to track this. - Add some instrumentation for the tlb shootdown code. - Rip out SMP code from <machine/cpufunc.h> - Try and fix some very bogus PG_G and PG_PS interactions that were bad enough to cause vm86 bios calls to break. vm86 depended on our existing bugs and this was the cause of the VESA panics last time. - Fix the silly one-line error that caused the 'panic: bad pte' last time. - Fix a couple of other silly one-line errors that should have caused more pain than they did. Some more work is needed: - pmap_{zero,copy}_page[_idle]. These can be done without IPI's if we have a hook in cpu_switch. - The IPI handlers need some cleanup. I have a bogus %ds load that can be avoided. - APTD handling is rather bogus and appears to be a large source of global TLB IPI shootdowns for no really good reason. I see speedups of between 1.5% and ~4% on buildworlds in a while 1 loop. I expect to see a bigger difference when there is significant pageout activity or the system otherwise has memory shortages. I have backed out a few optimizations that I had been using over the last few days in order to be a little more conservative. I'll revisit these again over the next few days as the dust settles. New option: DISABLE_PG_G - In case I missed something.
2002-07-12 07:56:11 +00:00
void pmap_invalidate_page(pmap_t, vm_offset_t);
void pmap_invalidate_range(pmap_t, vm_offset_t, vm_offset_t);
void pmap_invalidate_all(pmap_t);
#endif /* _KERNEL */
#endif /* !LOCORE */
1993-06-12 14:58:17 +00:00
#endif /* !_MACHINE_PMAP_H_ */