gup.c 5.52 KB
Newer Older
1 2 3 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
/*
 * Lockless get_user_pages_fast for sparc, cribbed from powerpc
 *
 * Copyright (C) 2008 Nick Piggin
 * Copyright (C) 2008 Novell Inc.
 */

#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/vmstat.h>
#include <linux/pagemap.h>
#include <linux/rwsem.h>
#include <asm/pgtable.h>

/*
 * The performance critical leaf functions are made noinline otherwise gcc
 * inlines everything into a single function which results in too much
 * register pressure.
 */
static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
		unsigned long end, int write, struct page **pages, int *nr)
{
	unsigned long mask, result;
	pte_t *ptep;

	if (tlb_type == hypervisor) {
		result = _PAGE_PRESENT_4V|_PAGE_P_4V;
		if (write)
			result |= _PAGE_WRITE_4V;
	} else {
		result = _PAGE_PRESENT_4U|_PAGE_P_4U;
		if (write)
			result |= _PAGE_WRITE_4U;
	}
	mask = result | _PAGE_SPECIAL;

	ptep = pte_offset_kernel(&pmd, addr);
	do {
		struct page *page, *head;
		pte_t pte = *ptep;

		if ((pte_val(pte) & mask) != result)
			return 0;
		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));

		/* The hugepage case is simplified on sparc64 because
		 * we encode the sub-page pfn offsets into the
		 * hugepage PTEs.  We could optimize this in the future
		 * use page_cache_add_speculative() for the hugepage case.
		 */
		page = pte_page(pte);
		head = compound_head(page);
		if (!page_cache_get_speculative(head))
			return 0;
		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
			put_page(head);
			return 0;
		}

		pages[*nr] = page;
		(*nr)++;
	} while (ptep++, addr += PAGE_SIZE, addr != end);

	return 1;
}

67 68 69 70
static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
			unsigned long end, int write, struct page **pages,
			int *nr)
{
71
	struct page *head, *page;
72 73
	int refs;

74
	if (!(pmd_val(pmd) & _PAGE_VALID))
75 76 77
		return 0;

	if (write && !pmd_write(pmd))
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
		return 0;

	refs = 0;
	head = pmd_page(pmd);
	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
	do {
		VM_BUG_ON(compound_head(page) != head);
		pages[*nr] = page;
		(*nr)++;
		page++;
		refs++;
	} while (addr += PAGE_SIZE, addr != end);

	if (!page_cache_add_speculative(head, refs)) {
		*nr -= refs;
		return 0;
	}

	if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) {
		*nr -= refs;
		while (refs--)
			put_page(head);
		return 0;
	}

	return 1;
}

106 107 108 109 110 111 112 113 114 115 116
static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
		int write, struct page **pages, int *nr)
{
	unsigned long next;
	pmd_t *pmdp;

	pmdp = pmd_offset(&pud, addr);
	do {
		pmd_t pmd = *pmdp;

		next = pmd_addr_end(addr, end);
117
		if (pmd_none(pmd))
118
			return 0;
119 120 121 122 123 124
		if (unlikely(pmd_large(pmd))) {
			if (!gup_huge_pmd(pmdp, pmd, addr, next,
					  write, pages, nr))
				return 0;
		} else if (!gup_pte_range(pmd, addr, next, write,
					  pages, nr))
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
			return 0;
	} while (pmdp++, addr = next, addr != end);

	return 1;
}

static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
		int write, struct page **pages, int *nr)
{
	unsigned long next;
	pud_t *pudp;

	pudp = pud_offset(&pgd, addr);
	do {
		pud_t pud = *pudp;

		next = pud_addr_end(addr, end);
		if (pud_none(pud))
			return 0;
		if (!gup_pmd_range(pud, addr, next, write, pages, nr))
			return 0;
	} while (pudp++, addr = next, addr != end);

	return 1;
}

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
int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
			  struct page **pages)
{
	struct mm_struct *mm = current->mm;
	unsigned long addr, len, end;
	unsigned long next, flags;
	pgd_t *pgdp;
	int nr = 0;

	start &= PAGE_MASK;
	addr = start;
	len = (unsigned long) nr_pages << PAGE_SHIFT;
	end = start + len;

	local_irq_save(flags);
	pgdp = pgd_offset(mm, addr);
	do {
		pgd_t pgd = *pgdp;

		next = pgd_addr_end(addr, end);
		if (pgd_none(pgd))
			break;
		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
			break;
	} while (pgdp++, addr = next, addr != end);
	local_irq_restore(flags);

	return nr;
}

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
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
			struct page **pages)
{
	struct mm_struct *mm = current->mm;
	unsigned long addr, len, end;
	unsigned long next;
	pgd_t *pgdp;
	int nr = 0;

	start &= PAGE_MASK;
	addr = start;
	len = (unsigned long) nr_pages << PAGE_SHIFT;
	end = start + len;

	/*
	 * XXX: batch / limit 'nr', to avoid large irq off latency
	 * needs some instrumenting to determine the common sizes used by
	 * important workloads (eg. DB2), and whether limiting the batch size
	 * will decrease performance.
	 *
	 * It seems like we're in the clear for the moment. Direct-IO is
	 * the main guy that batches up lots of get_user_pages, and even
	 * they are limited to 64-at-a-time which is not so many.
	 */
	/*
	 * This doesn't prevent pagetable teardown, but does prevent
	 * the pagetables from being freed on sparc.
	 *
	 * So long as we atomically load page table pointers versus teardown,
	 * we can follow the address down to the the page and take a ref on it.
	 */
	local_irq_disable();

	pgdp = pgd_offset(mm, addr);
	do {
		pgd_t pgd = *pgdp;

		next = pgd_addr_end(addr, end);
		if (pgd_none(pgd))
			goto slow;
		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
			goto slow;
	} while (pgdp++, addr = next, addr != end);

	local_irq_enable();

	VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT);
	return nr;

	{
		int ret;

slow:
		local_irq_enable();

		/* Try to get the remaining pages with get_user_pages */
		start += nr << PAGE_SHIFT;
		pages += nr;

240
		ret = get_user_pages_unlocked(start,
241 242
			(end - start) >> PAGE_SHIFT, pages,
			write ? FOLL_WRITE : 0);
243 244 245 246 247 248 249 250 251 252 253 254

		/* Have to be a bit careful with return values */
		if (nr > 0) {
			if (ret < 0)
				ret = nr;
			else
				ret += nr;
		}

		return ret;
	}
}