kernel-ark/mm/memory.c

2260 lines
60 KiB
C
Raw Normal View History

/*
* linux/mm/memory.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*/
/*
* demand-loading started 01.12.91 - seems it is high on the list of
* things wanted, and it should be easy to implement. - Linus
*/
/*
* Ok, demand-loading was easy, shared pages a little bit tricker. Shared
* pages started 02.12.91, seems to work. - Linus.
*
* Tested sharing by executing about 30 /bin/sh: under the old kernel it
* would have taken more than the 6M I have free, but it worked well as
* far as I could see.
*
* Also corrected some "invalidate()"s - I wasn't doing enough of them.
*/
/*
* Real VM (paging to/from disk) started 18.12.91. Much more work and
* thought has to go into this. Oh, well..
* 19.12.91 - works, somewhat. Sometimes I get faults, don't know why.
* Found it. Everything seems to work now.
* 20.12.91 - Ok, making the swap-device changeable like the root.
*/
/*
* 05.04.94 - Multi-page memory management added for v1.1.
* Idea by Alex Bligh (alex@cconcepts.co.uk)
*
* 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG
* (Gerhard.Wichert@pdb.siemens.de)
*
* Aug/Sep 2004 Changed to four level page tables (Andi Kleen)
*/
#include <linux/kernel_stat.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/module.h>
#include <linux/init.h>
#include <asm/pgalloc.h>
#include <asm/uaccess.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgtable.h>
#include <linux/swapops.h>
#include <linux/elf.h>
[PATCH] sparsemem memory model Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of mem_map[] is needed by discontiguous memory machines (like in the old CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually become a complete replacement. A significant advantage over DISCONTIGMEM is that it's completely separated from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA and DISCONTIG are often confused. Another advantage is that sparse doesn't require each NUMA node's ranges to be contiguous. It can handle overlapping ranges between nodes with no problems, where DISCONTIGMEM currently throws away that memory. Sparsemem uses an array to provide different pfn_to_page() translations for each SECTION_SIZE area of physical memory. This is what allows the mem_map[] to be chopped up. In order to do quick pfn_to_page() operations, the section number of the page is encoded in page->flags. Part of the sparsemem infrastructure enables sharing of these bits more dynamically (at compile-time) between the page_zone() and sparsemem operations. However, on 32-bit architectures, the number of bits is quite limited, and may require growing the size of the page->flags type in certain conditions. Several things might force this to occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of memory), an increase in the physical address space, or an increase in the number of used page->flags. One thing to note is that, once sparsemem is present, the NUMA node information no longer needs to be stored in the page->flags. It might provide speed increases on certain platforms and will be stored there if there is room. But, if out of room, an alternate (theoretically slower) mechanism is used. This patch introduces CONFIG_FLATMEM. It is used in almost all cases where there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM often have to compile out the same areas of code. Signed-off-by: Andy Whitcroft <apw@shadowen.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Martin Bligh <mbligh@aracnet.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 07:07:54 +00:00
#ifndef CONFIG_NEED_MULTIPLE_NODES
/* use the per-pgdat data instead for discontigmem - mbligh */
unsigned long max_mapnr;
struct page *mem_map;
EXPORT_SYMBOL(max_mapnr);
EXPORT_SYMBOL(mem_map);
#endif
unsigned long num_physpages;
/*
* A number of key systems in x86 including ioremap() rely on the assumption
* that high_memory defines the upper bound on direct map memory, then end
* of ZONE_NORMAL. Under CONFIG_DISCONTIG this means that max_low_pfn and
* highstart_pfn must be the same; there must be no gap between ZONE_NORMAL
* and ZONE_HIGHMEM.
*/
void * high_memory;
unsigned long vmalloc_earlyreserve;
EXPORT_SYMBOL(num_physpages);
EXPORT_SYMBOL(high_memory);
EXPORT_SYMBOL(vmalloc_earlyreserve);
/*
* If a p?d_bad entry is found while walking page tables, report
* the error, before resetting entry to p?d_none. Usually (but
* very seldom) called out from the p?d_none_or_clear_bad macros.
*/
void pgd_clear_bad(pgd_t *pgd)
{
pgd_ERROR(*pgd);
pgd_clear(pgd);
}
void pud_clear_bad(pud_t *pud)
{
pud_ERROR(*pud);
pud_clear(pud);
}
void pmd_clear_bad(pmd_t *pmd)
{
pmd_ERROR(*pmd);
pmd_clear(pmd);
}
/*
* Note: this doesn't free the actual pages themselves. That
* has been handled earlier when unmapping all the memory regions.
*/
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd)
{
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
struct page *page = pmd_page(*pmd);
pmd_clear(pmd);
pte_free_tlb(tlb, page);
dec_page_state(nr_page_table_pages);
tlb->mm->nr_ptes--;
}
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pmd_t *pmd;
unsigned long next;
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
unsigned long start;
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
start = addr;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(pmd))
continue;
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
free_pte_range(tlb, pmd);
} while (pmd++, addr = next, addr != end);
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
start &= PUD_MASK;
if (start < floor)
return;
if (ceiling) {
ceiling &= PUD_MASK;
if (!ceiling)
return;
}
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
if (end - 1 > ceiling - 1)
return;
pmd = pmd_offset(pud, start);
pud_clear(pud);
pmd_free_tlb(tlb, pmd);
}
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pud_t *pud;
unsigned long next;
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
unsigned long start;
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
start = addr;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
free_pmd_range(tlb, pud, addr, next, floor, ceiling);
} while (pud++, addr = next, addr != end);
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
start &= PGDIR_MASK;
if (start < floor)
return;
if (ceiling) {
ceiling &= PGDIR_MASK;
if (!ceiling)
return;
}
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
if (end - 1 > ceiling - 1)
return;
pud = pud_offset(pgd, start);
pgd_clear(pgd);
pud_free_tlb(tlb, pud);
}
/*
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
* This function frees user-level page tables of a process.
*
* Must be called with pagetable lock held.
*/
void free_pgd_range(struct mmu_gather **tlb,
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pgd_t *pgd;
unsigned long next;
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
unsigned long start;
/*
* The next few lines have given us lots of grief...
*
* Why are we testing PMD* at this top level? Because often
* there will be no work to do at all, and we'd prefer not to
* go all the way down to the bottom just to discover that.
*
* Why all these "- 1"s? Because 0 represents both the bottom
* of the address space and the top of it (using -1 for the
* top wouldn't help much: the masks would do the wrong thing).
* The rule is that addr 0 and floor 0 refer to the bottom of
* the address space, but end 0 and ceiling 0 refer to the top
* Comparisons need to use "end - 1" and "ceiling - 1" (though
* that end 0 case should be mythical).
*
* Wherever addr is brought up or ceiling brought down, we must
* be careful to reject "the opposite 0" before it confuses the
* subsequent tests. But what about where end is brought down
* by PMD_SIZE below? no, end can't go down to 0 there.
*
* Whereas we round start (addr) and ceiling down, by different
* masks at different levels, in order to test whether a table
* now has no other vmas using it, so can be freed, we don't
* bother to round floor or end up - the tests don't need that.
*/
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
addr &= PMD_MASK;
if (addr < floor) {
addr += PMD_SIZE;
if (!addr)
return;
}
if (ceiling) {
ceiling &= PMD_MASK;
if (!ceiling)
return;
}
if (end - 1 > ceiling - 1)
end -= PMD_SIZE;
if (addr > end - 1)
return;
start = addr;
pgd = pgd_offset((*tlb)->mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
free_pud_range(*tlb, pgd, addr, next, floor, ceiling);
} while (pgd++, addr = next, addr != end);
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
if (!tlb_is_full_mm(*tlb))
flush_tlb_pgtables((*tlb)->mm, start, end);
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
}
void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma,
unsigned long floor, unsigned long ceiling)
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
{
while (vma) {
struct vm_area_struct *next = vma->vm_next;
unsigned long addr = vma->vm_start;
if (is_hugepage_only_range(vma->vm_mm, addr, HPAGE_SIZE)) {
hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
floor, next? next->vm_start: ceiling);
} else {
/*
* Optimization: gather nearby vmas into one call down
*/
while (next && next->vm_start <= vma->vm_end + PMD_SIZE
&& !is_hugepage_only_range(vma->vm_mm, next->vm_start,
HPAGE_SIZE)) {
vma = next;
next = vma->vm_next;
}
free_pgd_range(tlb, addr, vma->vm_end,
floor, next? next->vm_start: ceiling);
}
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-19 20:29:15 +00:00
vma = next;
}
}
pte_t fastcall *pte_alloc_map(struct mm_struct *mm, pmd_t *pmd,
unsigned long address)
{
if (!pmd_present(*pmd)) {
struct page *new;
spin_unlock(&mm->page_table_lock);
new = pte_alloc_one(mm, address);
spin_lock(&mm->page_table_lock);
if (!new)
return NULL;
/*
* Because we dropped the lock, we should re-check the
* entry, as somebody else could have populated it..
*/
if (pmd_present(*pmd)) {
pte_free(new);
goto out;
}
mm->nr_ptes++;
inc_page_state(nr_page_table_pages);
pmd_populate(mm, pmd, new);
}
out:
return pte_offset_map(pmd, address);
}
pte_t fastcall * pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
{
if (!pmd_present(*pmd)) {
pte_t *new;
spin_unlock(&mm->page_table_lock);
new = pte_alloc_one_kernel(mm, address);
spin_lock(&mm->page_table_lock);
if (!new)
return NULL;
/*
* Because we dropped the lock, we should re-check the
* entry, as somebody else could have populated it..
*/
if (pmd_present(*pmd)) {
pte_free_kernel(new);
goto out;
}
pmd_populate_kernel(mm, pmd, new);
}
out:
return pte_offset_kernel(pmd, address);
}
/*
* copy one vm_area from one task to the other. Assumes the page tables
* already present in the new task to be cleared in the whole range
* covered by this vma.
*
* dst->page_table_lock is held on entry and exit,
* but may be dropped within p[mg]d_alloc() and pte_alloc_map().
*/
static inline void
copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pte_t *dst_pte, pte_t *src_pte, unsigned long vm_flags,
unsigned long addr)
{
pte_t pte = *src_pte;
struct page *page;
unsigned long pfn;
/* pte contains position in swap or file, so copy. */
if (unlikely(!pte_present(pte))) {
if (!pte_file(pte)) {
swap_duplicate(pte_to_swp_entry(pte));
/* make sure dst_mm is on swapoff's mmlist. */
if (unlikely(list_empty(&dst_mm->mmlist))) {
spin_lock(&mmlist_lock);
list_add(&dst_mm->mmlist, &src_mm->mmlist);
spin_unlock(&mmlist_lock);
}
}
set_pte_at(dst_mm, addr, dst_pte, pte);
return;
}
pfn = pte_pfn(pte);
/* the pte points outside of valid memory, the
* mapping is assumed to be good, meaningful
* and not mapped via rmap - duplicate the
* mapping as is.
*/
page = NULL;
if (pfn_valid(pfn))
page = pfn_to_page(pfn);
if (!page || PageReserved(page)) {
set_pte_at(dst_mm, addr, dst_pte, pte);
return;
}
/*
* If it's a COW mapping, write protect it both
* in the parent and the child
*/
if ((vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE) {
ptep_set_wrprotect(src_mm, addr, src_pte);
pte = *src_pte;
}
/*
* If it's a shared mapping, mark it clean in
* the child
*/
if (vm_flags & VM_SHARED)
pte = pte_mkclean(pte);
pte = pte_mkold(pte);
get_page(page);
inc_mm_counter(dst_mm, rss);
if (PageAnon(page))
inc_mm_counter(dst_mm, anon_rss);
set_pte_at(dst_mm, addr, dst_pte, pte);
page_dup_rmap(page);
}
static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
pte_t *src_pte, *dst_pte;
unsigned long vm_flags = vma->vm_flags;
int progress;
again:
dst_pte = pte_alloc_map(dst_mm, dst_pmd, addr);
if (!dst_pte)
return -ENOMEM;
src_pte = pte_offset_map_nested(src_pmd, addr);
progress = 0;
spin_lock(&src_mm->page_table_lock);
do {
/*
* We are holding two locks at this point - either of them
* could generate latencies in another task on another CPU.
*/
if (progress >= 32 && (need_resched() ||
need_lockbreak(&src_mm->page_table_lock) ||
need_lockbreak(&dst_mm->page_table_lock)))
break;
if (pte_none(*src_pte)) {
progress++;
continue;
}
copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vm_flags, addr);
progress += 8;
} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
spin_unlock(&src_mm->page_table_lock);
pte_unmap_nested(src_pte - 1);
pte_unmap(dst_pte - 1);
cond_resched_lock(&dst_mm->page_table_lock);
if (addr != end)
goto again;
return 0;
}
static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
pmd_t *src_pmd, *dst_pmd;
unsigned long next;
dst_pmd = pmd_alloc(dst_mm, dst_pud, addr);
if (!dst_pmd)
return -ENOMEM;
src_pmd = pmd_offset(src_pud, addr);
do {
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(src_pmd))
continue;
if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
vma, addr, next))
return -ENOMEM;
} while (dst_pmd++, src_pmd++, addr = next, addr != end);
return 0;
}
static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
pud_t *src_pud, *dst_pud;
unsigned long next;
dst_pud = pud_alloc(dst_mm, dst_pgd, addr);
if (!dst_pud)
return -ENOMEM;
src_pud = pud_offset(src_pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(src_pud))
continue;
if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
vma, addr, next))
return -ENOMEM;
} while (dst_pud++, src_pud++, addr = next, addr != end);
return 0;
}
int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
struct vm_area_struct *vma)
{
pgd_t *src_pgd, *dst_pgd;
unsigned long next;
unsigned long addr = vma->vm_start;
unsigned long end = vma->vm_end;
/*
* Don't copy ptes where a page fault will fill them correctly.
* Fork becomes much lighter when there are big shared or private
* readonly mappings. The tradeoff is that copy_page_range is more
* efficient than faulting.
*/
if (!(vma->vm_flags & (VM_HUGETLB|VM_NONLINEAR|VM_RESERVED))) {
if (!vma->anon_vma)
return 0;
}
if (is_vm_hugetlb_page(vma))
return copy_hugetlb_page_range(dst_mm, src_mm, vma);
dst_pgd = pgd_offset(dst_mm, addr);
src_pgd = pgd_offset(src_mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(src_pgd))
continue;
if (copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
vma, addr, next))
return -ENOMEM;
} while (dst_pgd++, src_pgd++, addr = next, addr != end);
return 0;
}
static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
pte_t *pte;
pte = pte_offset_map(pmd, addr);
do {
pte_t ptent = *pte;
if (pte_none(ptent))
continue;
if (pte_present(ptent)) {
struct page *page = NULL;
unsigned long pfn = pte_pfn(ptent);
if (pfn_valid(pfn)) {
page = pfn_to_page(pfn);
if (PageReserved(page))
page = NULL;
}
if (unlikely(details) && page) {
/*
* unmap_shared_mapping_pages() wants to
* invalidate cache without truncating:
* unmap shared but keep private pages.
*/
if (details->check_mapping &&
details->check_mapping != page->mapping)
continue;
/*
* Each page->index must be checked when
* invalidating or truncating nonlinear.
*/
if (details->nonlinear_vma &&
(page->index < details->first_index ||
page->index > details->last_index))
continue;
}
ptent = ptep_get_and_clear(tlb->mm, addr, pte);
tlb_remove_tlb_entry(tlb, pte, addr);
if (unlikely(!page))
continue;
if (unlikely(details) && details->nonlinear_vma
&& linear_page_index(details->nonlinear_vma,
addr) != page->index)
set_pte_at(tlb->mm, addr, pte,
pgoff_to_pte(page->index));
if (pte_dirty(ptent))
set_page_dirty(page);
if (PageAnon(page))
dec_mm_counter(tlb->mm, anon_rss);
else if (pte_young(ptent))
mark_page_accessed(page);
tlb->freed++;
page_remove_rmap(page);
tlb_remove_page(tlb, page);
continue;
}
/*
* If details->check_mapping, we leave swap entries;
* if details->nonlinear_vma, we leave file entries.
*/
if (unlikely(details))
continue;
if (!pte_file(ptent))
free_swap_and_cache(pte_to_swp_entry(ptent));
pte_clear(tlb->mm, addr, pte);
} while (pte++, addr += PAGE_SIZE, addr != end);
pte_unmap(pte - 1);
}
static inline void zap_pmd_range(struct mmu_gather *tlb, pud_t *pud,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
pmd_t *pmd;
unsigned long next;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(pmd))
continue;
zap_pte_range(tlb, pmd, addr, next, details);
} while (pmd++, addr = next, addr != end);
}
static inline void zap_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
pud_t *pud;
unsigned long next;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
zap_pmd_range(tlb, pud, addr, next, details);
} while (pud++, addr = next, addr != end);
}
static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
pgd_t *pgd;
unsigned long next;
if (details && !details->check_mapping && !details->nonlinear_vma)
details = NULL;
BUG_ON(addr >= end);
tlb_start_vma(tlb, vma);
pgd = pgd_offset(vma->vm_mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
zap_pud_range(tlb, pgd, addr, next, details);
} while (pgd++, addr = next, addr != end);
tlb_end_vma(tlb, vma);
}
#ifdef CONFIG_PREEMPT
# define ZAP_BLOCK_SIZE (8 * PAGE_SIZE)
#else
/* No preempt: go for improved straight-line efficiency */
# define ZAP_BLOCK_SIZE (1024 * PAGE_SIZE)
#endif
/**
* unmap_vmas - unmap a range of memory covered by a list of vma's
* @tlbp: address of the caller's struct mmu_gather
* @mm: the controlling mm_struct
* @vma: the starting vma
* @start_addr: virtual address at which to start unmapping
* @end_addr: virtual address at which to end unmapping
* @nr_accounted: Place number of unmapped pages in vm-accountable vma's here
* @details: details of nonlinear truncation or shared cache invalidation
*
* Returns the end address of the unmapping (restart addr if interrupted).
*
* Unmap all pages in the vma list. Called under page_table_lock.
*
* We aim to not hold page_table_lock for too long (for scheduling latency
* reasons). So zap pages in ZAP_BLOCK_SIZE bytecounts. This means we need to
* return the ending mmu_gather to the caller.
*
* Only addresses between `start' and `end' will be unmapped.
*
* The VMA list must be sorted in ascending virtual address order.
*
* unmap_vmas() assumes that the caller will flush the whole unmapped address
* range after unmap_vmas() returns. So the only responsibility here is to
* ensure that any thus-far unmapped pages are flushed before unmap_vmas()
* drops the lock and schedules.
*/
unsigned long unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long start_addr,
unsigned long end_addr, unsigned long *nr_accounted,
struct zap_details *details)
{
unsigned long zap_bytes = ZAP_BLOCK_SIZE;
unsigned long tlb_start = 0; /* For tlb_finish_mmu */
int tlb_start_valid = 0;
unsigned long start = start_addr;
spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
int fullmm = tlb_is_full_mm(*tlbp);
for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) {
unsigned long end;
start = max(vma->vm_start, start_addr);
if (start >= vma->vm_end)
continue;
end = min(vma->vm_end, end_addr);
if (end <= vma->vm_start)
continue;
if (vma->vm_flags & VM_ACCOUNT)
*nr_accounted += (end - start) >> PAGE_SHIFT;
while (start != end) {
unsigned long block;
if (!tlb_start_valid) {
tlb_start = start;
tlb_start_valid = 1;
}
if (is_vm_hugetlb_page(vma)) {
block = end - start;
unmap_hugepage_range(vma, start, end);
} else {
block = min(zap_bytes, end - start);
unmap_page_range(*tlbp, vma, start,
start + block, details);
}
start += block;
zap_bytes -= block;
if ((long)zap_bytes > 0)
continue;
tlb_finish_mmu(*tlbp, tlb_start, start);
if (need_resched() ||
need_lockbreak(&mm->page_table_lock) ||
(i_mmap_lock && need_lockbreak(i_mmap_lock))) {
if (i_mmap_lock) {
/* must reset count of rss freed */
*tlbp = tlb_gather_mmu(mm, fullmm);
goto out;
}
spin_unlock(&mm->page_table_lock);
cond_resched();
spin_lock(&mm->page_table_lock);
}
*tlbp = tlb_gather_mmu(mm, fullmm);
tlb_start_valid = 0;
zap_bytes = ZAP_BLOCK_SIZE;
}
}
out:
return start; /* which is now the end (or restart) address */
}
/**
* zap_page_range - remove user pages in a given range
* @vma: vm_area_struct holding the applicable pages
* @address: starting address of pages to zap
* @size: number of bytes to zap
* @details: details of nonlinear truncation or shared cache invalidation
*/
unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
unsigned long size, struct zap_details *details)
{
struct mm_struct *mm = vma->vm_mm;
struct mmu_gather *tlb;
unsigned long end = address + size;
unsigned long nr_accounted = 0;
if (is_vm_hugetlb_page(vma)) {
zap_hugepage_range(vma, address, size);
return end;
}
lru_add_drain();
spin_lock(&mm->page_table_lock);
tlb = tlb_gather_mmu(mm, 0);
end = unmap_vmas(&tlb, mm, vma, address, end, &nr_accounted, details);
tlb_finish_mmu(tlb, address, end);
spin_unlock(&mm->page_table_lock);
return end;
}
/*
* Do a quick page-table lookup for a single page.
* mm->page_table_lock must be held.
*/
static struct page *__follow_page(struct mm_struct *mm, unsigned long address,
int read, int write, int accessed)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *ptep, pte;
unsigned long pfn;
struct page *page;
page = follow_huge_addr(mm, address, write);
if (! IS_ERR(page))
return page;
pgd = pgd_offset(mm, address);
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
goto out;
pud = pud_offset(pgd, address);
if (pud_none(*pud) || unlikely(pud_bad(*pud)))
goto out;
pmd = pmd_offset(pud, address);
if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
goto out;
if (pmd_huge(*pmd))
return follow_huge_pmd(mm, address, pmd, write);
ptep = pte_offset_map(pmd, address);
if (!ptep)
goto out;
pte = *ptep;
pte_unmap(ptep);
if (pte_present(pte)) {
if (write && !pte_write(pte))
goto out;
if (read && !pte_read(pte))
goto out;
pfn = pte_pfn(pte);
if (pfn_valid(pfn)) {
page = pfn_to_page(pfn);
if (accessed) {
if (write && !pte_dirty(pte) &&!PageDirty(page))
set_page_dirty(page);
mark_page_accessed(page);
}
return page;
}
}
out:
return NULL;
}
inline struct page *
follow_page(struct mm_struct *mm, unsigned long address, int write)
{
return __follow_page(mm, address, 0, write, 1);
}
/*
* check_user_page_readable() can be called frm niterrupt context by oprofile,
* so we need to avoid taking any non-irq-safe locks
*/
int check_user_page_readable(struct mm_struct *mm, unsigned long address)
{
return __follow_page(mm, address, 1, 0, 0) != NULL;
}
EXPORT_SYMBOL(check_user_page_readable);
static inline int
untouched_anonymous_page(struct mm_struct* mm, struct vm_area_struct *vma,
unsigned long address)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
/* Check if the vma is for an anonymous mapping. */
if (vma->vm_ops && vma->vm_ops->nopage)
return 0;
/* Check if page directory entry exists. */
pgd = pgd_offset(mm, address);
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
return 1;
pud = pud_offset(pgd, address);
if (pud_none(*pud) || unlikely(pud_bad(*pud)))
return 1;
/* Check if page middle directory entry exists. */
pmd = pmd_offset(pud, address);
if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
return 1;
/* There is a pte slot for 'address' in 'mm'. */
return 0;
}
int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, int len, int write, int force,
struct page **pages, struct vm_area_struct **vmas)
{
int i;
unsigned int flags;
/*
* Require read or write permissions.
* If 'force' is set, we only require the "MAY" flags.
*/
flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
i = 0;
do {
struct vm_area_struct * vma;
vma = find_extend_vma(mm, start);
if (!vma && in_gate_area(tsk, start)) {
unsigned long pg = start & PAGE_MASK;
struct vm_area_struct *gate_vma = get_gate_vma(tsk);
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
if (write) /* user gate pages are read-only */
return i ? : -EFAULT;
if (pg > TASK_SIZE)
pgd = pgd_offset_k(pg);
else
pgd = pgd_offset_gate(mm, pg);
BUG_ON(pgd_none(*pgd));
pud = pud_offset(pgd, pg);
BUG_ON(pud_none(*pud));
pmd = pmd_offset(pud, pg);
if (pmd_none(*pmd))
return i ? : -EFAULT;
pte = pte_offset_map(pmd, pg);
if (pte_none(*pte)) {
pte_unmap(pte);
return i ? : -EFAULT;
}
if (pages) {
pages[i] = pte_page(*pte);
get_page(pages[i]);
}
pte_unmap(pte);
if (vmas)
vmas[i] = gate_vma;
i++;
start += PAGE_SIZE;
len--;
continue;
}
if (!vma || (vma->vm_flags & VM_IO)
|| !(flags & vma->vm_flags))
return i ? : -EFAULT;
if (is_vm_hugetlb_page(vma)) {
i = follow_hugetlb_page(mm, vma, pages, vmas,
&start, &len, i);
continue;
}
spin_lock(&mm->page_table_lock);
do {
int write_access = write;
struct page *page;
cond_resched_lock(&mm->page_table_lock);
while (!(page = follow_page(mm, start, write_access))) {
int ret;
/*
* Shortcut for anonymous pages. We don't want
* to force the creation of pages tables for
* insanely big anonymously mapped areas that
* nobody touched so far. This is important
* for doing a core dump for these mappings.
*/
if (!write && untouched_anonymous_page(mm,vma,start)) {
page = ZERO_PAGE(start);
break;
}
spin_unlock(&mm->page_table_lock);
ret = __handle_mm_fault(mm, vma, start, write_access);
/*
* The VM_FAULT_WRITE bit tells us that do_wp_page has
* broken COW when necessary, even if maybe_mkwrite
* decided not to set pte_write. We can thus safely do
* subsequent page lookups as if they were reads.
*/
if (ret & VM_FAULT_WRITE)
write_access = 0;
switch (ret & ~VM_FAULT_WRITE) {
case VM_FAULT_MINOR:
tsk->min_flt++;
break;
case VM_FAULT_MAJOR:
tsk->maj_flt++;
break;
case VM_FAULT_SIGBUS:
return i ? i : -EFAULT;
case VM_FAULT_OOM:
return i ? i : -ENOMEM;
default:
BUG();
}
spin_lock(&mm->page_table_lock);
}
if (pages) {
pages[i] = page;
flush_dcache_page(page);
if (!PageReserved(page))
page_cache_get(page);
}
if (vmas)
vmas[i] = vma;
i++;
start += PAGE_SIZE;
len--;
} while (len && start < vma->vm_end);
spin_unlock(&mm->page_table_lock);
} while (len);
return i;
}
EXPORT_SYMBOL(get_user_pages);
static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, unsigned long end, pgprot_t prot)
{
pte_t *pte;
pte = pte_alloc_map(mm, pmd, addr);
if (!pte)
return -ENOMEM;
do {
pte_t zero_pte = pte_wrprotect(mk_pte(ZERO_PAGE(addr), prot));
BUG_ON(!pte_none(*pte));
set_pte_at(mm, addr, pte, zero_pte);
} while (pte++, addr += PAGE_SIZE, addr != end);
pte_unmap(pte - 1);
return 0;
}
static inline int zeromap_pmd_range(struct mm_struct *mm, pud_t *pud,
unsigned long addr, unsigned long end, pgprot_t prot)
{
pmd_t *pmd;
unsigned long next;
pmd = pmd_alloc(mm, pud, addr);
if (!pmd)
return -ENOMEM;
do {
next = pmd_addr_end(addr, end);
if (zeromap_pte_range(mm, pmd, addr, next, prot))
return -ENOMEM;
} while (pmd++, addr = next, addr != end);
return 0;
}
static inline int zeromap_pud_range(struct mm_struct *mm, pgd_t *pgd,
unsigned long addr, unsigned long end, pgprot_t prot)
{
pud_t *pud;
unsigned long next;
pud = pud_alloc(mm, pgd, addr);
if (!pud)
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
if (zeromap_pmd_range(mm, pud, addr, next, prot))
return -ENOMEM;
} while (pud++, addr = next, addr != end);
return 0;
}
int zeromap_page_range(struct vm_area_struct *vma,
unsigned long addr, unsigned long size, pgprot_t prot)
{
pgd_t *pgd;
unsigned long next;
unsigned long end = addr + size;
struct mm_struct *mm = vma->vm_mm;
int err;
BUG_ON(addr >= end);
pgd = pgd_offset(mm, addr);
flush_cache_range(vma, addr, end);
spin_lock(&mm->page_table_lock);
do {
next = pgd_addr_end(addr, end);
err = zeromap_pud_range(mm, pgd, addr, next, prot);
if (err)
break;
} while (pgd++, addr = next, addr != end);
spin_unlock(&mm->page_table_lock);
return err;
}
/*
* maps a range of physical memory into the requested pages. the old
* mappings are removed. any references to nonexistent pages results
* in null mappings (currently treated as "copy-on-access")
*/
static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
pte_t *pte;
pte = pte_alloc_map(mm, pmd, addr);
if (!pte)
return -ENOMEM;
do {
BUG_ON(!pte_none(*pte));
if (!pfn_valid(pfn) || PageReserved(pfn_to_page(pfn)))
set_pte_at(mm, addr, pte, pfn_pte(pfn, prot));
pfn++;
} while (pte++, addr += PAGE_SIZE, addr != end);
pte_unmap(pte - 1);
return 0;
}
static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
pmd_t *pmd;
unsigned long next;
pfn -= addr >> PAGE_SHIFT;
pmd = pmd_alloc(mm, pud, addr);
if (!pmd)
return -ENOMEM;
do {
next = pmd_addr_end(addr, end);
if (remap_pte_range(mm, pmd, addr, next,
pfn + (addr >> PAGE_SHIFT), prot))
return -ENOMEM;
} while (pmd++, addr = next, addr != end);
return 0;
}
static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
pud_t *pud;
unsigned long next;
pfn -= addr >> PAGE_SHIFT;
pud = pud_alloc(mm, pgd, addr);
if (!pud)
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
if (remap_pmd_range(mm, pud, addr, next,
pfn + (addr >> PAGE_SHIFT), prot))
return -ENOMEM;
} while (pud++, addr = next, addr != end);
return 0;
}
/* Note: this is only safe if the mm semaphore is held when called. */
int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn, unsigned long size, pgprot_t prot)
{
pgd_t *pgd;
unsigned long next;
unsigned long end = addr + PAGE_ALIGN(size);
struct mm_struct *mm = vma->vm_mm;
int err;
/*
* Physically remapped pages are special. Tell the
* rest of the world about it:
* VM_IO tells people not to look at these pages
* (accesses can have side effects).
* VM_RESERVED tells swapout not to try to touch
* this region.
*/
vma->vm_flags |= VM_IO | VM_RESERVED;
BUG_ON(addr >= end);
pfn -= addr >> PAGE_SHIFT;
pgd = pgd_offset(mm, addr);
flush_cache_range(vma, addr, end);
spin_lock(&mm->page_table_lock);
do {
next = pgd_addr_end(addr, end);
err = remap_pud_range(mm, pgd, addr, next,
pfn + (addr >> PAGE_SHIFT), prot);
if (err)
break;
} while (pgd++, addr = next, addr != end);
spin_unlock(&mm->page_table_lock);
return err;
}
EXPORT_SYMBOL(remap_pfn_range);
/*
* Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when
* servicing faults for write access. In the normal case, do always want
* pte_mkwrite. But get_user_pages can cause write faults for mappings
* that do not have writing enabled, when used by access_process_vm.
*/
static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
{
if (likely(vma->vm_flags & VM_WRITE))
pte = pte_mkwrite(pte);
return pte;
}
/*
* We hold the mm semaphore for reading and vma->vm_mm->page_table_lock
*/
static inline void break_cow(struct vm_area_struct * vma, struct page * new_page, unsigned long address,
pte_t *page_table)
{
pte_t entry;
entry = maybe_mkwrite(pte_mkdirty(mk_pte(new_page, vma->vm_page_prot)),
vma);
ptep_establish(vma, address, page_table, entry);
update_mmu_cache(vma, address, entry);
lazy_mmu_prot_update(entry);
}
/*
* This routine handles present pages, when users try to write
* to a shared page. It is done by copying the page to a new address
* and decrementing the shared-page counter for the old page.
*
* Goto-purists beware: the only reason for goto's here is that it results
* in better assembly code.. The "default" path will see no jumps at all.
*
* Note that this routine assumes that the protection checks have been
* done by the caller (the low-level page fault routine in most cases).
* Thus we can safely just mark it writable once we've done any necessary
* COW.
*
* We also mark the page dirty at this point even though the page will
* change only once the write actually happens. This avoids a few races,
* and potentially makes it more efficient.
*
* We hold the mm semaphore and the page_table_lock on entry and exit
* with the page_table_lock released.
*/
static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
unsigned long address, pte_t *page_table, pmd_t *pmd, pte_t pte)
{
struct page *old_page, *new_page;
unsigned long pfn = pte_pfn(pte);
pte_t entry;
int ret;
if (unlikely(!pfn_valid(pfn))) {
/*
* This should really halt the system so it can be debugged or
* at least the kernel stops what it's doing before it corrupts
* data, but for the moment just pretend this is OOM.
*/
pte_unmap(page_table);
printk(KERN_ERR "do_wp_page: bogus page at address %08lx\n",
address);
spin_unlock(&mm->page_table_lock);
return VM_FAULT_OOM;
}
old_page = pfn_to_page(pfn);
if (PageAnon(old_page) && !TestSetPageLocked(old_page)) {
int reuse = can_share_swap_page(old_page);
unlock_page(old_page);
if (reuse) {
flush_cache_page(vma, address, pfn);
entry = maybe_mkwrite(pte_mkyoung(pte_mkdirty(pte)),
vma);
ptep_set_access_flags(vma, address, page_table, entry, 1);
update_mmu_cache(vma, address, entry);
lazy_mmu_prot_update(entry);
pte_unmap(page_table);
spin_unlock(&mm->page_table_lock);
return VM_FAULT_MINOR|VM_FAULT_WRITE;
}
}
pte_unmap(page_table);
/*
* Ok, we need to copy. Oh, well..
*/
if (!PageReserved(old_page))
page_cache_get(old_page);
spin_unlock(&mm->page_table_lock);
if (unlikely(anon_vma_prepare(vma)))
goto no_new_page;
if (old_page == ZERO_PAGE(address)) {
new_page = alloc_zeroed_user_highpage(vma, address);
if (!new_page)
goto no_new_page;
} else {
new_page = alloc_page_vma(GFP_HIGHUSER, vma, address);
if (!new_page)
goto no_new_page;
copy_user_highpage(new_page, old_page, address);
}
/*
* Re-check the pte - we dropped the lock
*/
ret = VM_FAULT_MINOR;
spin_lock(&mm->page_table_lock);
page_table = pte_offset_map(pmd, address);
if (likely(pte_same(*page_table, pte))) {
if (PageAnon(old_page))
dec_mm_counter(mm, anon_rss);
if (PageReserved(old_page))
inc_mm_counter(mm, rss);
else
page_remove_rmap(old_page);
flush_cache_page(vma, address, pfn);
break_cow(vma, new_page, address, page_table);
lru_cache_add_active(new_page);
page_add_anon_rmap(new_page, vma, address);
/* Free the old page.. */
new_page = old_page;
ret |= VM_FAULT_WRITE;
}
pte_unmap(page_table);
page_cache_release(new_page);
page_cache_release(old_page);
spin_unlock(&mm->page_table_lock);
return ret;
no_new_page:
page_cache_release(old_page);
return VM_FAULT_OOM;
}
/*
* Helper functions for unmap_mapping_range().
*
* __ Notes on dropping i_mmap_lock to reduce latency while unmapping __
*
* We have to restart searching the prio_tree whenever we drop the lock,
* since the iterator is only valid while the lock is held, and anyway
* a later vma might be split and reinserted earlier while lock dropped.
*
* The list of nonlinear vmas could be handled more efficiently, using
* a placeholder, but handle it in the same way until a need is shown.
* It is important to search the prio_tree before nonlinear list: a vma
* may become nonlinear and be shifted from prio_tree to nonlinear list
* while the lock is dropped; but never shifted from list to prio_tree.
*
* In order to make forward progress despite restarting the search,
* vm_truncate_count is used to mark a vma as now dealt with, so we can
* quickly skip it next time around. Since the prio_tree search only
* shows us those vmas affected by unmapping the range in question, we
* can't efficiently keep all vmas in step with mapping->truncate_count:
* so instead reset them all whenever it wraps back to 0 (then go to 1).
* mapping->truncate_count and vma->vm_truncate_count are protected by
* i_mmap_lock.
*
* In order to make forward progress despite repeatedly restarting some
* large vma, note the restart_addr from unmap_vmas when it breaks out:
* and restart from that address when we reach that vma again. It might
* have been split or merged, shrunk or extended, but never shifted: so
* restart_addr remains valid so long as it remains in the vma's range.
* unmap_mapping_range forces truncate_count to leap over page-aligned
* values so we can save vma's restart_addr in its truncate_count field.
*/
#define is_restart_addr(truncate_count) (!((truncate_count) & ~PAGE_MASK))
static void reset_vma_truncate_counts(struct address_space *mapping)
{
struct vm_area_struct *vma;
struct prio_tree_iter iter;
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)
vma->vm_truncate_count = 0;
list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
vma->vm_truncate_count = 0;
}
static int unmap_mapping_range_vma(struct vm_area_struct *vma,
unsigned long start_addr, unsigned long end_addr,
struct zap_details *details)
{
unsigned long restart_addr;
int need_break;
again:
restart_addr = vma->vm_truncate_count;
if (is_restart_addr(restart_addr) && start_addr < restart_addr) {
start_addr = restart_addr;
if (start_addr >= end_addr) {
/* Top of vma has been split off since last time */
vma->vm_truncate_count = details->truncate_count;
return 0;
}
}
restart_addr = zap_page_range(vma, start_addr,
end_addr - start_addr, details);
/*
* We cannot rely on the break test in unmap_vmas:
* on the one hand, we don't want to restart our loop
* just because that broke out for the page_table_lock;
* on the other hand, it does no test when vma is small.
*/
need_break = need_resched() ||
need_lockbreak(details->i_mmap_lock);
if (restart_addr >= end_addr) {
/* We have now completed this vma: mark it so */
vma->vm_truncate_count = details->truncate_count;
if (!need_break)
return 0;
} else {
/* Note restart_addr in vma's truncate_count field */
vma->vm_truncate_count = restart_addr;
if (!need_break)
goto again;
}
spin_unlock(details->i_mmap_lock);
cond_resched();
spin_lock(details->i_mmap_lock);
return -EINTR;
}
static inline void unmap_mapping_range_tree(struct prio_tree_root *root,
struct zap_details *details)
{
struct vm_area_struct *vma;
struct prio_tree_iter iter;
pgoff_t vba, vea, zba, zea;
restart:
vma_prio_tree_foreach(vma, &iter, root,
details->first_index, details->last_index) {
/* Skip quickly over those we have already dealt with */
if (vma->vm_truncate_count == details->truncate_count)
continue;
vba = vma->vm_pgoff;
vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1;
/* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */
zba = details->first_index;
if (zba < vba)
zba = vba;
zea = details->last_index;
if (zea > vea)
zea = vea;
if (unmap_mapping_range_vma(vma,
((zba - vba) << PAGE_SHIFT) + vma->vm_start,
((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
details) < 0)
goto restart;
}
}
static inline void unmap_mapping_range_list(struct list_head *head,
struct zap_details *details)
{
struct vm_area_struct *vma;
/*
* In nonlinear VMAs there is no correspondence between virtual address
* offset and file offset. So we must perform an exhaustive search
* across *all* the pages in each nonlinear VMA, not just the pages
* whose virtual address lies outside the file truncation point.
*/
restart:
list_for_each_entry(vma, head, shared.vm_set.list) {
/* Skip quickly over those we have already dealt with */
if (vma->vm_truncate_count == details->truncate_count)
continue;
details->nonlinear_vma = vma;
if (unmap_mapping_range_vma(vma, vma->vm_start,
vma->vm_end, details) < 0)
goto restart;
}
}
/**
* unmap_mapping_range - unmap the portion of all mmaps
* in the specified address_space corresponding to the specified
* page range in the underlying file.
* @mapping: the address space containing mmaps to be unmapped.
* @holebegin: byte in first page to unmap, relative to the start of
* the underlying file. This will be rounded down to a PAGE_SIZE
* boundary. Note that this is different from vmtruncate(), which
* must keep the partial page. In contrast, we must get rid of
* partial pages.
* @holelen: size of prospective hole in bytes. This will be rounded
* up to a PAGE_SIZE boundary. A holelen of zero truncates to the
* end of the file.
* @even_cows: 1 when truncating a file, unmap even private COWed pages;
* but 0 when invalidating pagecache, don't throw away private data.
*/
void unmap_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen, int even_cows)
{
struct zap_details details;
pgoff_t hba = holebegin >> PAGE_SHIFT;
pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
/* Check for overflow. */
if (sizeof(holelen) > sizeof(hlen)) {
long long holeend =
(holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (holeend & ~(long long)ULONG_MAX)
hlen = ULONG_MAX - hba + 1;
}
details.check_mapping = even_cows? NULL: mapping;
details.nonlinear_vma = NULL;
details.first_index = hba;
details.last_index = hba + hlen - 1;
if (details.last_index < details.first_index)
details.last_index = ULONG_MAX;
details.i_mmap_lock = &mapping->i_mmap_lock;
spin_lock(&mapping->i_mmap_lock);
/* serialize i_size write against truncate_count write */
smp_wmb();
/* Protect against page faults, and endless unmapping loops */
mapping->truncate_count++;
/*
* For archs where spin_lock has inclusive semantics like ia64
* this smp_mb() will prevent to read pagetable contents
* before the truncate_count increment is visible to
* other cpus.
*/
smp_mb();
if (unlikely(is_restart_addr(mapping->truncate_count))) {
if (mapping->truncate_count == 0)
reset_vma_truncate_counts(mapping);
mapping->truncate_count++;
}
details.truncate_count = mapping->truncate_count;
if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
unmap_mapping_range_tree(&mapping->i_mmap, &details);
if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
spin_unlock(&mapping->i_mmap_lock);
}
EXPORT_SYMBOL(unmap_mapping_range);
/*
* Handle all mappings that got truncated by a "truncate()"
* system call.
*
* NOTE! We have to be ready to update the memory sharing
* between the file and the memory map for a potential last
* incomplete page. Ugly, but necessary.
*/
int vmtruncate(struct inode * inode, loff_t offset)
{
struct address_space *mapping = inode->i_mapping;
unsigned long limit;
if (inode->i_size < offset)
goto do_expand;
/*
* truncation of in-use swapfiles is disallowed - it would cause
* subsequent swapout to scribble on the now-freed blocks.
*/
if (IS_SWAPFILE(inode))
goto out_busy;
i_size_write(inode, offset);
unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
truncate_inode_pages(mapping, offset);
goto out_truncate;
do_expand:
limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
if (limit != RLIM_INFINITY && offset > limit)
goto out_sig;
if (offset > inode->i_sb->s_maxbytes)
goto out_big;
i_size_write(inode, offset);
out_truncate:
if (inode->i_op && inode->i_op->truncate)
inode->i_op->truncate(inode);
return 0;
out_sig:
send_sig(SIGXFSZ, current, 0);
out_big:
return -EFBIG;
out_busy:
return -ETXTBSY;
}
EXPORT_SYMBOL(vmtruncate);
/*
* Primitive swap readahead code. We simply read an aligned block of
* (1 << page_cluster) entries in the swap area. This method is chosen
* because it doesn't cost us any seek time. We also make sure to queue
* the 'original' request together with the readahead ones...
*
* This has been extended to use the NUMA policies from the mm triggering
* the readahead.
*
* Caller must hold down_read on the vma->vm_mm if vma is not NULL.
*/
void swapin_readahead(swp_entry_t entry, unsigned long addr,struct vm_area_struct *vma)
{
#ifdef CONFIG_NUMA
struct vm_area_struct *next_vma = vma ? vma->vm_next : NULL;
#endif
int i, num;
struct page *new_page;
unsigned long offset;
/*
* Get the number of handles we should do readahead io to.
*/
num = valid_swaphandles(entry, &offset);
for (i = 0; i < num; offset++, i++) {
/* Ok, do the async read-ahead now */
new_page = read_swap_cache_async(swp_entry(swp_type(entry),
offset), vma, addr);
if (!new_page)
break;
page_cache_release(new_page);
#ifdef CONFIG_NUMA
/*
* Find the next applicable VMA for the NUMA policy.
*/
addr += PAGE_SIZE;
if (addr == 0)
vma = NULL;
if (vma) {
if (addr >= vma->vm_end) {
vma = next_vma;
next_vma = vma ? vma->vm_next : NULL;
}
if (vma && addr < vma->vm_start)
vma = NULL;
} else {
if (next_vma && addr >= next_vma->vm_start) {
vma = next_vma;
next_vma = vma->vm_next;
}
}
#endif
}
lru_add_drain(); /* Push any new pages onto the LRU now */
}
/*
* We hold the mm semaphore and the page_table_lock on entry and
* should release the pagetable lock on exit..
*/
static int do_swap_page(struct mm_struct * mm,
struct vm_area_struct * vma, unsigned long address,
pte_t *page_table, pmd_t *pmd, pte_t orig_pte, int write_access)
{
struct page *page;
swp_entry_t entry = pte_to_swp_entry(orig_pte);
pte_t pte;
int ret = VM_FAULT_MINOR;
pte_unmap(page_table);
spin_unlock(&mm->page_table_lock);
page = lookup_swap_cache(entry);
if (!page) {
swapin_readahead(entry, address, vma);
page = read_swap_cache_async(entry, vma, address);
if (!page) {
/*
* Back out if somebody else faulted in this pte while
* we released the page table lock.
*/
spin_lock(&mm->page_table_lock);
page_table = pte_offset_map(pmd, address);
if (likely(pte_same(*page_table, orig_pte)))
ret = VM_FAULT_OOM;
else
ret = VM_FAULT_MINOR;
pte_unmap(page_table);
spin_unlock(&mm->page_table_lock);
goto out;
}
/* Had to read the page from swap area: Major fault */
ret = VM_FAULT_MAJOR;
inc_page_state(pgmajfault);
grab_swap_token();
}
mark_page_accessed(page);
lock_page(page);
/*
* Back out if somebody else faulted in this pte while we
* released the page table lock.
*/
spin_lock(&mm->page_table_lock);
page_table = pte_offset_map(pmd, address);
if (unlikely(!pte_same(*page_table, orig_pte))) {
ret = VM_FAULT_MINOR;
goto out_nomap;
}
if (unlikely(!PageUptodate(page))) {
ret = VM_FAULT_SIGBUS;
goto out_nomap;
}
/* The page isn't present yet, go ahead with the fault. */
inc_mm_counter(mm, rss);
pte = mk_pte(page, vma->vm_page_prot);
if (write_access && can_share_swap_page(page)) {
pte = maybe_mkwrite(pte_mkdirty(pte), vma);
write_access = 0;
}
flush_icache_page(vma, page);
set_pte_at(mm, address, page_table, pte);
page_add_anon_rmap(page, vma, address);
swap_free(entry);
if (vm_swap_full())
remove_exclusive_swap_page(page);
unlock_page(page);
if (write_access) {
if (do_wp_page(mm, vma, address,
page_table, pmd, pte) == VM_FAULT_OOM)
ret = VM_FAULT_OOM;
goto out;
}
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, address, pte);
lazy_mmu_prot_update(pte);
pte_unmap(page_table);
spin_unlock(&mm->page_table_lock);
out:
return ret;
out_nomap:
pte_unmap(page_table);
spin_unlock(&mm->page_table_lock);
unlock_page(page);
page_cache_release(page);
goto out;
}
/*
* We are called with the MM semaphore and page_table_lock
* spinlock held to protect against concurrent faults in
* multithreaded programs.
*/
static int
do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
pte_t *page_table, pmd_t *pmd, int write_access,
unsigned long addr)
{
pte_t entry;
struct page * page = ZERO_PAGE(addr);
/* Read-only mapping of ZERO_PAGE. */
entry = pte_wrprotect(mk_pte(ZERO_PAGE(addr), vma->vm_page_prot));
/* ..except if it's a write access */
if (write_access) {
/* Allocate our own private page. */
pte_unmap(page_table);
spin_unlock(&mm->page_table_lock);
if (unlikely(anon_vma_prepare(vma)))
goto no_mem;
page = alloc_zeroed_user_highpage(vma, addr);
if (!page)
goto no_mem;
spin_lock(&mm->page_table_lock);
page_table = pte_offset_map(pmd, addr);
if (!pte_none(*page_table)) {
pte_unmap(page_table);
page_cache_release(page);
spin_unlock(&mm->page_table_lock);
goto out;
}
inc_mm_counter(mm, rss);
entry = maybe_mkwrite(pte_mkdirty(mk_pte(page,
vma->vm_page_prot)),
vma);
lru_cache_add_active(page);
SetPageReferenced(page);
page_add_anon_rmap(page, vma, addr);
}
set_pte_at(mm, addr, page_table, entry);
pte_unmap(page_table);
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, addr, entry);
lazy_mmu_prot_update(entry);
spin_unlock(&mm->page_table_lock);
out:
return VM_FAULT_MINOR;
no_mem:
return VM_FAULT_OOM;
}
/*
* do_no_page() tries to create a new page mapping. It aggressively
* tries to share with existing pages, but makes a separate copy if
* the "write_access" parameter is true in order to avoid the next
* page fault.
*
* As this is called only for pages that do not currently exist, we
* do not need to flush old virtual caches or the TLB.
*
* This is called with the MM semaphore held and the page table
* spinlock held. Exit with the spinlock released.
*/
static int
do_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, int write_access, pte_t *page_table, pmd_t *pmd)
{
struct page * new_page;
struct address_space *mapping = NULL;
pte_t entry;
unsigned int sequence = 0;
int ret = VM_FAULT_MINOR;
int anon = 0;
if (!vma->vm_ops || !vma->vm_ops->nopage)
return do_anonymous_page(mm, vma, page_table,
pmd, write_access, address);
pte_unmap(page_table);
spin_unlock(&mm->page_table_lock);
if (vma->vm_file) {
mapping = vma->vm_file->f_mapping;
sequence = mapping->truncate_count;
smp_rmb(); /* serializes i_size against truncate_count */
}
retry:
cond_resched();
new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret);
/*
* No smp_rmb is needed here as long as there's a full
* spin_lock/unlock sequence inside the ->nopage callback
* (for the pagecache lookup) that acts as an implicit
* smp_mb() and prevents the i_size read to happen
* after the next truncate_count read.
*/
/* no page was available -- either SIGBUS or OOM */
if (new_page == NOPAGE_SIGBUS)
return VM_FAULT_SIGBUS;
if (new_page == NOPAGE_OOM)
return VM_FAULT_OOM;
/*
* Should we do an early C-O-W break?
*/
if (write_access && !(vma->vm_flags & VM_SHARED)) {
struct page *page;
if (unlikely(anon_vma_prepare(vma)))
goto oom;
page = alloc_page_vma(GFP_HIGHUSER, vma, address);
if (!page)
goto oom;
copy_user_highpage(page, new_page, address);
page_cache_release(new_page);
new_page = page;
anon = 1;
}
spin_lock(&mm->page_table_lock);
/*
* For a file-backed vma, someone could have truncated or otherwise
* invalidated this page. If unmap_mapping_range got called,
* retry getting the page.
*/
if (mapping && unlikely(sequence != mapping->truncate_count)) {
sequence = mapping->truncate_count;
spin_unlock(&mm->page_table_lock);
page_cache_release(new_page);
goto retry;
}
page_table = pte_offset_map(pmd, address);
/*
* This silly early PAGE_DIRTY setting removes a race
* due to the bad i386 page protection. But it's valid
* for other architectures too.
*
* Note that if write_access is true, we either now have
* an exclusive copy of the page, or this is a shared mapping,
* so we can make it writable and dirty to avoid having to
* handle that later.
*/
/* Only go through if we didn't race with anybody else... */
if (pte_none(*page_table)) {
if (!PageReserved(new_page))
inc_mm_counter(mm, rss);
flush_icache_page(vma, new_page);
entry = mk_pte(new_page, vma->vm_page_prot);
if (write_access)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
set_pte_at(mm, address, page_table, entry);
if (anon) {
lru_cache_add_active(new_page);
page_add_anon_rmap(new_page, vma, address);
} else
page_add_file_rmap(new_page);
pte_unmap(page_table);
} else {
/* One of our sibling threads was faster, back out. */
pte_unmap(page_table);
page_cache_release(new_page);
spin_unlock(&mm->page_table_lock);
goto out;
}
/* no need to invalidate: a not-present page shouldn't be cached */
update_mmu_cache(vma, address, entry);
lazy_mmu_prot_update(entry);
spin_unlock(&mm->page_table_lock);
out:
return ret;
oom:
page_cache_release(new_page);
ret = VM_FAULT_OOM;
goto out;
}
/*
* Fault of a previously existing named mapping. Repopulate the pte
* from the encoded file_pte if possible. This enables swappable
* nonlinear vmas.
*/
static int do_file_page(struct mm_struct * mm, struct vm_area_struct * vma,
unsigned long address, int write_access, pte_t *pte, pmd_t *pmd)
{
unsigned long pgoff;
int err;
BUG_ON(!vma->vm_ops || !vma->vm_ops->nopage);
/*
* Fall back to the linear mapping if the fs does not support
* ->populate:
*/
if (!vma->vm_ops || !vma->vm_ops->populate ||
(write_access && !(vma->vm_flags & VM_SHARED))) {
pte_clear(mm, address, pte);
return do_no_page(mm, vma, address, write_access, pte, pmd);
}
pgoff = pte_to_pgoff(*pte);
pte_unmap(pte);
spin_unlock(&mm->page_table_lock);
err = vma->vm_ops->populate(vma, address & PAGE_MASK, PAGE_SIZE, vma->vm_page_prot, pgoff, 0);
if (err == -ENOMEM)
return VM_FAULT_OOM;
if (err)
return VM_FAULT_SIGBUS;
return VM_FAULT_MAJOR;
}
/*
* These routines also need to handle stuff like marking pages dirty
* and/or accessed for architectures that don't do it in hardware (most
* RISC architectures). The early dirtying is also good on the i386.
*
* There is also a hook called "update_mmu_cache()" that architectures
* with external mmu caches can use to update those (ie the Sparc or
* PowerPC hashed page tables that act as extended TLBs).
*
* Note the "page_table_lock". It is to protect against kswapd removing
* pages from under us. Note that kswapd only ever _removes_ pages, never
* adds them. As such, once we have noticed that the page is not present,
* we can drop the lock early.
*
* The adding of pages is protected by the MM semaphore (which we hold),
* so we don't need to worry about a page being suddenly been added into
* our VM.
*
* We enter with the pagetable spinlock held, we are supposed to
* release it when done.
*/
static inline int handle_pte_fault(struct mm_struct *mm,
struct vm_area_struct * vma, unsigned long address,
int write_access, pte_t *pte, pmd_t *pmd)
{
pte_t entry;
entry = *pte;
if (!pte_present(entry)) {
/*
* If it truly wasn't present, we know that kswapd
* and the PTE updates will not touch it later. So
* drop the lock.
*/
if (pte_none(entry))
return do_no_page(mm, vma, address, write_access, pte, pmd);
if (pte_file(entry))
return do_file_page(mm, vma, address, write_access, pte, pmd);
return do_swap_page(mm, vma, address, pte, pmd, entry, write_access);
}
if (write_access) {
if (!pte_write(entry))
return do_wp_page(mm, vma, address, pte, pmd, entry);
entry = pte_mkdirty(entry);
}
entry = pte_mkyoung(entry);
ptep_set_access_flags(vma, address, pte, entry, write_access);
update_mmu_cache(vma, address, entry);
lazy_mmu_prot_update(entry);
pte_unmap(pte);
spin_unlock(&mm->page_table_lock);
return VM_FAULT_MINOR;
}
/*
* By the time we get here, we already hold the mm semaphore
*/
int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
unsigned long address, int write_access)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
__set_current_state(TASK_RUNNING);
inc_page_state(pgfault);
if (is_vm_hugetlb_page(vma))
return VM_FAULT_SIGBUS; /* mapping truncation does this. */
/*
* We need the page table lock to synchronize with kswapd
* and the SMP-safe atomic PTE updates.
*/
pgd = pgd_offset(mm, address);
spin_lock(&mm->page_table_lock);
pud = pud_alloc(mm, pgd, address);
if (!pud)
goto oom;
pmd = pmd_alloc(mm, pud, address);
if (!pmd)
goto oom;
pte = pte_alloc_map(mm, pmd, address);
if (!pte)
goto oom;
return handle_pte_fault(mm, vma, address, write_access, pte, pmd);
oom:
spin_unlock(&mm->page_table_lock);
return VM_FAULT_OOM;
}
#ifndef __PAGETABLE_PUD_FOLDED
/*
* Allocate page upper directory.
*
* We've already handled the fast-path in-line, and we own the
* page table lock.
*/
pud_t fastcall *__pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
{
pud_t *new;
spin_unlock(&mm->page_table_lock);
new = pud_alloc_one(mm, address);
spin_lock(&mm->page_table_lock);
if (!new)
return NULL;
/*
* Because we dropped the lock, we should re-check the
* entry, as somebody else could have populated it..
*/
if (pgd_present(*pgd)) {
pud_free(new);
goto out;
}
pgd_populate(mm, pgd, new);
out:
return pud_offset(pgd, address);
}
#endif /* __PAGETABLE_PUD_FOLDED */
#ifndef __PAGETABLE_PMD_FOLDED
/*
* Allocate page middle directory.
*
* We've already handled the fast-path in-line, and we own the
* page table lock.
*/
pmd_t fastcall *__pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
pmd_t *new;
spin_unlock(&mm->page_table_lock);
new = pmd_alloc_one(mm, address);
spin_lock(&mm->page_table_lock);
if (!new)
return NULL;
/*
* Because we dropped the lock, we should re-check the
* entry, as somebody else could have populated it..
*/
#ifndef __ARCH_HAS_4LEVEL_HACK
if (pud_present(*pud)) {
pmd_free(new);
goto out;
}
pud_populate(mm, pud, new);
#else
if (pgd_present(*pud)) {
pmd_free(new);
goto out;
}
pgd_populate(mm, pud, new);
#endif /* __ARCH_HAS_4LEVEL_HACK */
out:
return pmd_offset(pud, address);
}
#endif /* __PAGETABLE_PMD_FOLDED */
int make_pages_present(unsigned long addr, unsigned long end)
{
int ret, len, write;
struct vm_area_struct * vma;
vma = find_vma(current->mm, addr);
if (!vma)
return -1;
write = (vma->vm_flags & VM_WRITE) != 0;
if (addr >= end)
BUG();
if (end > vma->vm_end)
BUG();
len = (end+PAGE_SIZE-1)/PAGE_SIZE-addr/PAGE_SIZE;
ret = get_user_pages(current, current->mm, addr,
len, write, 0, NULL, NULL);
if (ret < 0)
return ret;
return ret == len ? 0 : -1;
}
/*
* Map a vmalloc()-space virtual address to the physical page.
*/
struct page * vmalloc_to_page(void * vmalloc_addr)
{
unsigned long addr = (unsigned long) vmalloc_addr;
struct page *page = NULL;
pgd_t *pgd = pgd_offset_k(addr);
pud_t *pud;
pmd_t *pmd;
pte_t *ptep, pte;
if (!pgd_none(*pgd)) {
pud = pud_offset(pgd, addr);
if (!pud_none(*pud)) {
pmd = pmd_offset(pud, addr);
if (!pmd_none(*pmd)) {
ptep = pte_offset_map(pmd, addr);
pte = *ptep;
if (pte_present(pte))
page = pte_page(pte);
pte_unmap(ptep);
}
}
}
return page;
}
EXPORT_SYMBOL(vmalloc_to_page);
/*
* Map a vmalloc()-space virtual address to the physical page frame number.
*/
unsigned long vmalloc_to_pfn(void * vmalloc_addr)
{
return page_to_pfn(vmalloc_to_page(vmalloc_addr));
}
EXPORT_SYMBOL(vmalloc_to_pfn);
/*
* update_mem_hiwater
* - update per process rss and vm high water data
*/
void update_mem_hiwater(struct task_struct *tsk)
{
if (tsk->mm) {
unsigned long rss = get_mm_counter(tsk->mm, rss);
if (tsk->mm->hiwater_rss < rss)
tsk->mm->hiwater_rss = rss;
if (tsk->mm->hiwater_vm < tsk->mm->total_vm)
tsk->mm->hiwater_vm = tsk->mm->total_vm;
}
}
#if !defined(__HAVE_ARCH_GATE_AREA)
#if defined(AT_SYSINFO_EHDR)
struct vm_area_struct gate_vma;
static int __init gate_vma_init(void)
{
gate_vma.vm_mm = NULL;
gate_vma.vm_start = FIXADDR_USER_START;
gate_vma.vm_end = FIXADDR_USER_END;
gate_vma.vm_page_prot = PAGE_READONLY;
gate_vma.vm_flags = 0;
return 0;
}
__initcall(gate_vma_init);
#endif
struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
{
#ifdef AT_SYSINFO_EHDR
return &gate_vma;
#else
return NULL;
#endif
}
int in_gate_area_no_task(unsigned long addr)
{
#ifdef AT_SYSINFO_EHDR
if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END))
return 1;
#endif
return 0;
}
#endif /* __HAVE_ARCH_GATE_AREA */