litmus-rt.git - The LITMUS^RT kernel.

/*
 *  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/ksm.h>
#include <linux/rmap.h>
#include <linux/module.h>
#include <linux/delayacct.h>
#include <linux/init.h>
#include <linux/writeback.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
#include <linux/kallsyms.h>
#include <linux/swapops.h>
#include <linux/elf.h>
#include <linux/gfp.h>

#include <asm/io.h>
#include <asm/pgalloc.h>
#include <asm/uaccess.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgtable.h>

#include "internal.h"

#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;

EXPORT_SYMBOL(num_physpages);
EXPORT_SYMBOL(high_memory);

/*
 * Randomize the address space (stacks, mmaps, brk, etc.).
 *
 * ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization,
 *   as ancient (libc5 based) binaries can segfault. )
 */
int randomize_va_space __read_mostly =
#ifdef CONFIG_COMPAT_BRK
					1;
#else
					2;
#endif

static int __init disable_randmaps(char *s)
{
	randomize_va_space = 0;
	return 1;
}
__setup("norandmaps", disable_randmaps);

unsigned long zero_pfn __read_mostly;
unsigned long highest_memmap_pfn __read_mostly;

/*
 * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init()
 */
static int __init init_zero_pfn(void)
{
	zero_pfn = page_to_pfn(ZERO_PAGE(0));
	return 0;
}
core_initcall(init_zero_pfn);


#if defined(SPLIT_RSS_COUNTING)

static void __sync_task_rss_stat(struct task_struct *task, struct mm_struct *mm)
{
	int i;

	for (i = 0; i < NR_MM_COUNTERS; i++) {
		if (task->rss_stat.count[i]) {
			add_mm_counter(mm, i, task->rss_stat.count[i]);
			task->rss_stat.count[i] = 0;
		}
	}
	task->rss_stat.events = 0;
}

static void add_mm_counter_fast(struct mm_struct *mm, int member, int val)
{
	struct task_struct *task = current;

	if (likely(task->mm == mm))
		task->rss_stat.count[member] += val;
	else
		add_mm_counter(mm, member, val);
}
#define inc_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, 1)
#define dec_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, -1)

/* sync counter once per 64 page faults */
#define TASK_RSS_EVENTS_THRESH	(64)
static void check_sync_rss_stat(struct task_struct *task)
{
	if (unlikely(task != current))
		return;
	if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH))
		__sync_task_rss_stat(task, task->mm);
}

unsigned long get_mm_counter(struct mm_struct *mm, int member)
{
	long val = 0;

	/*
	 * Don't use task->mm here...for avoiding to use task_get_mm()..
	 * The caller must guarantee task->mm is not invalid.
	 */
	val = atomic_long_read(&mm->rss_stat.count[member]);
	/*
	 * counter is updated in asynchronous manner and may go to minus.
	 * But it's never be expected number for users.
	 */
	if (val < 0)
		return 0;
	return (unsigned long)val;
}

void sync_mm_rss(struct task_struct *task, struct mm_struct *mm)
{
	__sync_task_rss_stat(task, mm);
}
#else /* SPLIT_RSS_COUNTING */

#define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member)
#define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member)

static void check_sync_rss_stat(struct task_struct *task)
{
}

#endif /* SPLIT_RSS_COUNTING */

#ifdef HAVE_GENERIC_MMU_GATHER

static int tlb_next_batch(struct mmu_gather *tlb)
{
	struct mmu_gather_batch *batch;

	batch = tlb->active;
	if (batch->next) {
		tlb->active = batch->next;
		return 1;
	}

	batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
	if (!batch)
		return 0;

	batch->next = NULL;
	batch->nr   = 0;
	batch->max  = MAX_GATHER_BATCH;

	tlb->active->next = batch;
	tlb->active = batch;

	return 1;
}

/* tlb_gather_mmu
 *	Called to initialize an (on-stack) mmu_gather structure for page-table
 *	tear-down from @mm. The @fullmm argument is used when @mm is without
 *	users and we're going to destroy the full address space (exit/execve).
 */
void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
{
	tlb->mm = mm;

	tlb->fullmm     = fullmm;
	tlb->need_flush = 0;
	tlb->fast_mode  = (num_possible_cpus() == 1);
	tlb->local.next = NULL;
	tlb->local.nr   = 0;
	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
	tlb->active     = &tlb->local;

#ifdef CONFIG_HAVE_RCU_TABLE_FREE
	tlb->batch = NULL;
#endif
}

void tlb_flush_mmu(struct mmu_gather *tlb)
{
	struct mmu_gather_batch *batch;

	if (!tlb->need_flush)
		return;
	tlb->need_flush = 0;
	tlb_flush(tlb);
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
	tlb_table_flush(tlb);
#endif

	if (tlb_fast_mode(tlb))
		return;

	for (batch = &tlb->local; batch; batch = batch->next) {
		free_pages_and_swap_cache(batch->pages, batch->nr);
		batch->nr = 0;
	}
	tlb->active = &tlb->local;
}

/* tlb_finish_mmu
 *	Called at the end of the shootdown operation to free up any resources
 *	that were required.
 */
void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
{
	struct mmu_gather_batch *batch, *next;

	tlb_flush_mmu(tlb);

	/* keep the page table cache within bounds */
	check_pgt_cache();

	for (batch = tlb->local.next; batch; batch = next) {
		next = batch->next;
		free_pages((unsigned long)batch, 0);
	}
	tlb->local.next = NULL;
}

/* __tlb_remove_page
 *	Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
 *	handling the additional races in SMP caused by other CPUs caching valid
 *	mappings in their TLBs. Returns the number of free page slots left.
 *	When out of page slots we must call tlb_flush_mmu().
 */
int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
	struct mmu_gather_batch *batch;

	tlb->need_flush = 1;

	if (tlb_fast_mode(tlb)) {
		free_page_and_swap_cache(page);
		return 1; /* avoid calling tlb_flush_mmu() */
	}

	batch = tlb->active;
	batch->pages[batch->nr++] = page;
	if (batch->nr == batch->max) {
		if (!tlb_next_batch(tlb))
			return 0;
	}
	VM_BUG_ON(batch->nr > batch->max);

	return batch->max - batch->nr;
}

#endif /* HAVE_GENERIC_MMU_GATHER */

#ifdef CONFIG_HAVE_RCU_TABLE_FREE

/*
 * See the comment near struct mmu_table_batch.
 */

static void tlb_remove_table_smp_sync(void *arg)
{
	/* Simply deliver the interrupt */
}

static void tlb_remove_table_one(void *table)
{
	/*
	 * This isn't an RCU grace period and hence the page-tables cannot be
	 * assumed to be actually RCU-freed.
	 *
	 * It is however sufficient for software page-table walkers that rely on
	 * IRQ disabling. See the comment near struct mmu_table_batch.
	 */
	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
	__tlb_remove_table(table);
}

static void tlb_remove_table_rcu(struct rcu_head *head)
{
	struct mmu_table_batch *batch;
	int i;

	batch = container_of(head, struct mmu_table_batch, rcu);

	for (i = 0; i < batch->nr; i++)
		__tlb_remove_table(batch->tables[i]);

	free_page((unsigned long)batch);
}

void tlb_table_flush(struct mmu_gather *tlb)
{
	struct mmu_table_batch **batch = &tlb->batch;

	if (*batch) {
		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
		*batch = NULL;
	}
}

void tlb_remove_table(struct mmu_gather *tlb, void *table)
{
	struct mmu_table_batch **batch = &tlb->batch;

	tlb->need_flush = 1;

	/*
	 * When there's less then two users of this mm there cannot be a
	 * concurrent page-table walk.
	 */
	if (atomic_read(&tlb->mm->mm_users) < 2) {
		__tlb_remove_table(table);
		return;
	}

	if (*batch == NULL) {
		*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
		if (*batch == NULL) {
			tlb_remove_table_one(table);
			return;
		}
		(*batch)->nr = 0;
	}
	(*batch)->tables[(*batch)->nr++] = table;
	if ((*batch)->nr == MAX_TABLE_BATCH)
		tlb_table_flush(tlb);
}

#endif /* CONFIG_HAVE_RCU_TABLE_FREE */

/*
 * 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.
 */
static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
			   unsigned long addr)
{
	pgtable_t token = pmd_pgtable(*pmd);
	pmd_clear(pmd);
	pte_free_tlb(tlb, token, addr);
	tlb->mm->nr_ptes--;
}

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;
	unsigned long start;

	start = addr;
	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_none_or_clear_bad(pmd))
			continue;
		free_pte_range(tlb, pmd, addr);
	} while (pmd++, addr = next, addr != end);

	start &= PUD_MASK;
	if (start < floor)
		return;
	if (ceiling) {
		ceiling &= PUD_MASK;
		if (!ceiling)
			return;
	}
	if (end - 1 > ceiling - 1)
		return;

	pmd = pmd_offset(pud, start);
	pud_clear(pud);
	pmd_free_tlb(tlb, pmd, start);
}

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;
	unsigned long start;

	start = addr;
	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud))
			continue;
		free_pmd_range(tlb, pud, addr, next, floor, ceiling);
	} while (pud++, addr = next, addr != end);

	start &= PGDIR_MASK;
	if (start < floor)
		return;
	if (ceiling) {
		ceiling &= PGDIR_MASK;
		if (!ceiling)
			return;
	}
	if (end - 1 > ceiling - 1)
		return;

	pud = pud_offset(pgd, start);
	pgd_clear(pgd);
	pud_free_tlb(tlb, pud, start);
}

/*
 * 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,
			unsigned long addr, unsigned long end,
			unsigned long floor, unsigned long ceiling)
{
	pgd_t *pgd;
	unsigned long next;

	/*
	 * 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.
	 */

	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;

	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);
}

void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
		unsigned long floor, unsigned long ceiling)
{
	while (vma) {
		struct vm_area_struct *next = vma->vm_next;
		unsigned long addr = vma->vm_start;

		/*
		 * Hide vma from rmap and truncate_pagecache before freeing
		 * pgtables
		 */
		unlink_anon_vmas(vma);
		unlink_file_vma(vma);

		if (is_vm_hugetlb_page(vma)) {
			hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
				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_vm_hugetlb_page(next)) {
				vma = next;
				next = vma->vm_next;
				unlink_anon_vmas(vma);
				unlink_file_vma(vma);
			}
			free_pgd_range(tlb, addr, vma->vm_end,
				floor, next? next->vm_start: ceiling);
		}
		vma = next;
	}
}

int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
		pmd_t *pmd, unsigned long address)
{
	pgtable_t new = pte_alloc_one(mm, address);
	int wait_split_huge_page;
	if (!new)
		return -ENOMEM;

	/*
	 * Ensure all pte setup (eg. pte page lock and page clearing) are
	 * visible before the pte is made visible to other CPUs by being
	 * put into page tables.
	 *
	 * The other side of the story is the pointer chasing in the page
	 * table walking code (when walking the page table without locking;
	 * ie. most of the time). Fortunately, these data accesses consist
	 * of a chain of data-dependent loads, meaning most CPUs (alpha


context:
space:
mode: