pgtable.c 6.6 KB
Newer Older
1 2
/*
 * This file contains common routines for dealing with free of page tables
3
 * Along with common page table handling code
4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118
 *
 *  Derived from arch/powerpc/mm/tlb_64.c:
 *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
 *
 *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
 *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
 *    Copyright (C) 1996 Paul Mackerras
 *
 *  Derived from "arch/i386/mm/init.c"
 *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  Dave Engebretsen <engebret@us.ibm.com>
 *      Rework for PPC64 port.
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License
 *  as published by the Free Software Foundation; either version
 *  2 of the License, or (at your option) any later version.
 */

#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/tlb.h>

static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
static unsigned long pte_freelist_forced_free;

struct pte_freelist_batch
{
	struct rcu_head	rcu;
	unsigned int	index;
	pgtable_free_t	tables[0];
};

#define PTE_FREELIST_SIZE \
	((PAGE_SIZE - sizeof(struct pte_freelist_batch)) \
	  / sizeof(pgtable_free_t))

static void pte_free_smp_sync(void *arg)
{
	/* Do nothing, just ensure we sync with all CPUs */
}

/* This is only called when we are critically out of memory
 * (and fail to get a page in pte_free_tlb).
 */
static void pgtable_free_now(pgtable_free_t pgf)
{
	pte_freelist_forced_free++;

	smp_call_function(pte_free_smp_sync, NULL, 1);

	pgtable_free(pgf);
}

static void pte_free_rcu_callback(struct rcu_head *head)
{
	struct pte_freelist_batch *batch =
		container_of(head, struct pte_freelist_batch, rcu);
	unsigned int i;

	for (i = 0; i < batch->index; i++)
		pgtable_free(batch->tables[i]);

	free_page((unsigned long)batch);
}

static void pte_free_submit(struct pte_freelist_batch *batch)
{
	INIT_RCU_HEAD(&batch->rcu);
	call_rcu(&batch->rcu, pte_free_rcu_callback);
}

void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf)
{
	/* This is safe since tlb_gather_mmu has disabled preemption */
        cpumask_t local_cpumask = cpumask_of_cpu(smp_processor_id());
	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);

	if (atomic_read(&tlb->mm->mm_users) < 2 ||
	    cpus_equal(tlb->mm->cpu_vm_mask, local_cpumask)) {
		pgtable_free(pgf);
		return;
	}

	if (*batchp == NULL) {
		*batchp = (struct pte_freelist_batch *)__get_free_page(GFP_ATOMIC);
		if (*batchp == NULL) {
			pgtable_free_now(pgf);
			return;
		}
		(*batchp)->index = 0;
	}
	(*batchp)->tables[(*batchp)->index++] = pgf;
	if ((*batchp)->index == PTE_FREELIST_SIZE) {
		pte_free_submit(*batchp);
		*batchp = NULL;
	}
}

void pte_free_finish(void)
{
	/* This is safe since tlb_gather_mmu has disabled preemption */
	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);

	if (*batchp == NULL)
		return;
	pte_free_submit(*batchp);
	*batchp = NULL;
}
119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248

/*
 * Handle i/d cache flushing, called from set_pte_at() or ptep_set_access_flags()
 */
static pte_t do_dcache_icache_coherency(pte_t pte)
{
	unsigned long pfn = pte_pfn(pte);
	struct page *page;

	if (unlikely(!pfn_valid(pfn)))
		return pte;
	page = pfn_to_page(pfn);

	if (!PageReserved(page) && !test_bit(PG_arch_1, &page->flags)) {
		pr_debug("do_dcache_icache_coherency... flushing\n");
		flush_dcache_icache_page(page);
		set_bit(PG_arch_1, &page->flags);
	}
	else
		pr_debug("do_dcache_icache_coherency... already clean\n");
	return __pte(pte_val(pte) | _PAGE_HWEXEC);
}

static inline int is_exec_fault(void)
{
	return current->thread.regs && TRAP(current->thread.regs) == 0x400;
}

/* We only try to do i/d cache coherency on stuff that looks like
 * reasonably "normal" PTEs. We currently require a PTE to be present
 * and we avoid _PAGE_SPECIAL and _PAGE_NO_CACHE
 */
static inline int pte_looks_normal(pte_t pte)
{
	return (pte_val(pte) &
		(_PAGE_PRESENT | _PAGE_SPECIAL | _PAGE_NO_CACHE)) ==
		(_PAGE_PRESENT);
}

#if defined(CONFIG_PPC_STD_MMU)
/* Server-style MMU handles coherency when hashing if HW exec permission
 * is supposed per page (currently 64-bit only). Else, we always flush
 * valid PTEs in set_pte.
 */
static inline int pte_need_exec_flush(pte_t pte, int set_pte)
{
	return set_pte && pte_looks_normal(pte) &&
		!(cpu_has_feature(CPU_FTR_COHERENT_ICACHE) ||
		  cpu_has_feature(CPU_FTR_NOEXECUTE));
}
#elif _PAGE_HWEXEC == 0
/* Embedded type MMU without HW exec support (8xx only so far), we flush
 * the cache for any present PTE
 */
static inline int pte_need_exec_flush(pte_t pte, int set_pte)
{
	return set_pte && pte_looks_normal(pte);
}
#else
/* Other embedded CPUs with HW exec support per-page, we flush on exec
 * fault if HWEXEC is not set
 */
static inline int pte_need_exec_flush(pte_t pte, int set_pte)
{
	return pte_looks_normal(pte) && is_exec_fault() &&
		!(pte_val(pte) & _PAGE_HWEXEC);
}
#endif

/*
 * set_pte stores a linux PTE into the linux page table.
 */
void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
{
#ifdef CONFIG_DEBUG_VM
	WARN_ON(pte_present(*ptep));
#endif
	/* Note: mm->context.id might not yet have been assigned as
	 * this context might not have been activated yet when this
	 * is called.
	 */
	pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
	if (pte_need_exec_flush(pte, 1))
		pte = do_dcache_icache_coherency(pte);

	/* Perform the setting of the PTE */
	__set_pte_at(mm, addr, ptep, pte, 0);
}

/*
 * This is called when relaxing access to a PTE. It's also called in the page
 * fault path when we don't hit any of the major fault cases, ie, a minor
 * update of _PAGE_ACCESSED, _PAGE_DIRTY, etc... The generic code will have
 * handled those two for us, we additionally deal with missing execute
 * permission here on some processors
 */
int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
			  pte_t *ptep, pte_t entry, int dirty)
{
	int changed;
	if (!dirty && pte_need_exec_flush(entry, 0))
		entry = do_dcache_icache_coherency(entry);
	changed = !pte_same(*(ptep), entry);
	if (changed) {
		assert_pte_locked(vma->vm_mm, address);
		__ptep_set_access_flags(ptep, entry);
		flush_tlb_page_nohash(vma, address);
	}
	return changed;
}

#ifdef CONFIG_DEBUG_VM
void assert_pte_locked(struct mm_struct *mm, unsigned long addr)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;

	if (mm == &init_mm)
		return;
	pgd = mm->pgd + pgd_index(addr);
	BUG_ON(pgd_none(*pgd));
	pud = pud_offset(pgd, addr);
	BUG_ON(pud_none(*pud));
	pmd = pmd_offset(pud, addr);
	BUG_ON(!pmd_present(*pmd));
	BUG_ON(!spin_is_locked(pte_lockptr(mm, pmd)));
}
#endif /* CONFIG_DEBUG_VM */