hugetlbpage.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 865 行 · 第 1/2 页

/*
 * PPC64 (POWER4) Huge TLB Page Support for Kernel.
 *
 * Copyright (C) 2003 David Gibson, IBM Corporation.
 *
 * Based on the IA-32 version:
 * Copyright (C) 2002, Rohit Seth <[e-mail]>
 */

#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/smp_lock.h>
#include <linux/slab.h>
#include <linux/err.h>
#include <linux/sysctl.h>
#include <asm/mman.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/machdep.h>
#include <asm/cputable.h>
#include <asm/tlb.h>

#include <linux/sysctl.h>

/* HugePTE layout:
 *
 * 31 30 ... 15 14 13 12 10 9  8  7   6    5    4    3    2    1    0
 * PFN>>12..... -  -  -  -  -  -  HASH_IX....   2ND  HASH RW   -    HG=1
 */

#define HUGEPTE_SHIFT	15
#define _HUGEPAGE_PFN		0xffff8000
#define _HUGEPAGE_BAD		0x00007f00
#define _HUGEPAGE_HASHPTE	0x00000008
#define _HUGEPAGE_SECONDARY	0x00000010
#define _HUGEPAGE_GROUP_IX	0x000000e0
#define _HUGEPAGE_HPTEFLAGS	(_HUGEPAGE_HASHPTE | _HUGEPAGE_SECONDARY | \
				 _HUGEPAGE_GROUP_IX)
#define _HUGEPAGE_RW		0x00000004

typedef struct {unsigned int val;} hugepte_t;
#define hugepte_val(hugepte)	((hugepte).val)
#define __hugepte(x)		((hugepte_t) { (x) } )
#define hugepte_pfn(x)		\
	((unsigned long)(hugepte_val(x)>>HUGEPTE_SHIFT) << HUGETLB_PAGE_ORDER)
#define mk_hugepte(page,wr)	__hugepte( \
	((page_to_pfn(page)>>HUGETLB_PAGE_ORDER) << HUGEPTE_SHIFT ) \
	| (!!(wr) * _HUGEPAGE_RW) | _PMD_HUGEPAGE )

#define hugepte_bad(x)	( !(hugepte_val(x) & _PMD_HUGEPAGE) || \
			  (hugepte_val(x) & _HUGEPAGE_BAD) )
#define hugepte_page(x)	pfn_to_page(hugepte_pfn(x))
#define hugepte_none(x)	(!(hugepte_val(x) & _HUGEPAGE_PFN))


static void flush_hash_hugepage(mm_context_t context, unsigned long ea,
				hugepte_t pte, int local);

static inline unsigned int hugepte_update(hugepte_t *p, unsigned int clr,
					  unsigned int set)
{
	unsigned int old, tmp;

	__asm__ __volatile__(
	"1:	lwarx	%0,0,%3		# pte_update\n\
	andc	%1,%0,%4 \n\
	or	%1,%1,%5 \n\
	stwcx.	%1,0,%3 \n\
	bne-	1b"
	: "=&r" (old), "=&r" (tmp), "=m" (*p)
	: "r" (p), "r" (clr), "r" (set), "m" (*p)
	: "cc" );
	return old;
}

static inline void set_hugepte(hugepte_t *ptep, hugepte_t pte)
{
	hugepte_update(ptep, ~_HUGEPAGE_HPTEFLAGS,
		       hugepte_val(pte) & ~_HUGEPAGE_HPTEFLAGS);
}

static hugepte_t *hugepte_alloc(struct mm_struct *mm, unsigned long addr)
{
	pgd_t *pgd;
	pmd_t *pmd = NULL;

	BUG_ON(!in_hugepage_area(mm->context, addr));

	pgd = pgd_offset(mm, addr);
	pmd = pmd_alloc(mm, pgd, addr);

	/* We shouldn't find a (normal) PTE page pointer here */
	BUG_ON(!pmd_none(*pmd) && !pmd_hugepage(*pmd));
	
	return (hugepte_t *)pmd;
}

static hugepte_t *hugepte_offset(struct mm_struct *mm, unsigned long addr)
{
	pgd_t *pgd;
	pmd_t *pmd = NULL;

	BUG_ON(!in_hugepage_area(mm->context, addr));

	pgd = pgd_offset(mm, addr);
	if (pgd_none(*pgd))
		return NULL;

	pmd = pmd_offset(pgd, addr);

	/* We shouldn't find a (normal) PTE page pointer here */
	BUG_ON(!pmd_none(*pmd) && !pmd_hugepage(*pmd));

	return (hugepte_t *)pmd;
}

static void setup_huge_pte(struct mm_struct *mm, struct page *page,
			   hugepte_t *ptep, int write_access)
{
	hugepte_t entry;
	int i;

	mm->rss += (HPAGE_SIZE / PAGE_SIZE);
	entry = mk_hugepte(page, write_access);
	for (i = 0; i < HUGEPTE_BATCH_SIZE; i++)
		set_hugepte(ptep+i, entry);
}

static void teardown_huge_pte(hugepte_t *ptep)
{
	int i;

	for (i = 0; i < HUGEPTE_BATCH_SIZE; i++)
		pmd_clear((pmd_t *)(ptep+i));
}

/*
 * This function checks for proper alignment of input addr and len parameters.
 */
int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
{
	if (len & ~HPAGE_MASK)
		return -EINVAL;
	if (addr & ~HPAGE_MASK)
		return -EINVAL;
	if (! (within_hugepage_low_range(addr, len)
	       || within_hugepage_high_range(addr, len)) )
		return -EINVAL;
	return 0;
}

static void flush_segments(void *parm)
{
	u16 segs = (unsigned long) parm;
	unsigned long i;

	asm volatile("isync" : : : "memory");

	for (i = 0; i < 16; i++) {
		if (! (segs & (1U << i)))
			continue;
		asm volatile("slbie %0" : : "r" (i << SID_SHIFT));
	}

	asm volatile("isync" : : : "memory");
}

static int prepare_low_seg_for_htlb(struct mm_struct *mm, unsigned long seg)
{
	unsigned long start = seg << SID_SHIFT;
	unsigned long end = (seg+1) << SID_SHIFT;
	struct vm_area_struct *vma;
	unsigned long addr;
	struct mmu_gather *tlb;

	BUG_ON(seg >= 16);

	/* Check no VMAs are in the region */
	vma = find_vma(mm, start);
	if (vma && (vma->vm_start < end))
		return -EBUSY;

	/* Clean up any leftover PTE pages in the region */
	spin_lock(&mm->page_table_lock);
	tlb = tlb_gather_mmu(mm, 0);
	for (addr = start; addr < end; addr += PMD_SIZE) {
		pgd_t *pgd = pgd_offset(mm, addr);
		pmd_t *pmd;
		struct page *page;
		pte_t *pte;
		int i;

		if (pgd_none(*pgd))
			continue;
		pmd = pmd_offset(pgd, addr);
		if (!pmd || pmd_none(*pmd))
			continue;
		if (pmd_bad(*pmd)) {
			pmd_ERROR(*pmd);
			pmd_clear(pmd);
			continue;
		}
		pte = (pte_t *)pmd_page_kernel(*pmd);
		/* No VMAs, so there should be no PTEs, check just in case. */
		for (i = 0; i < PTRS_PER_PTE; i++) {
			BUG_ON(!pte_none(*pte));
			pte++;
		}
		page = pmd_page(*pmd);
		pmd_clear(pmd);
		dec_page_state(nr_page_table_pages);
		pte_free_tlb(tlb, page);
	}
	tlb_finish_mmu(tlb, start, end);
	spin_unlock(&mm->page_table_lock);

	return 0;
}

static int open_low_hpage_segs(struct mm_struct *mm, u16 newsegs)
{
	unsigned long i;

	newsegs &= ~(mm->context.htlb_segs);
	if (! newsegs)
		return 0; /* The segments we want are already open */

	for (i = 0; i < 16; i++)
		if ((1 << i) & newsegs)
			if (prepare_low_seg_for_htlb(mm, i) != 0)
				return -EBUSY;

	mm->context.htlb_segs |= newsegs;
	/* the context change must make it to memory before the flush,
	 * so that further SLB misses do the right thing. */
	mb();
	on_each_cpu(flush_segments, (void *)(unsigned long)newsegs, 0, 1);

	return 0;
}

int prepare_hugepage_range(unsigned long addr, unsigned long len)
{
	if (within_hugepage_high_range(addr, len))
		return 0;
	else if ((addr < 0x100000000) && ((addr+len) < 0x100000000)) {
		int err;
		/* Yes, we need both tests, in case addr+len overflows
		 * 64-bit arithmetic */
		err = open_low_hpage_segs(current->mm,
					  LOW_ESID_MASK(addr, len));
		if (err)
			printk(KERN_DEBUG "prepare_hugepage_range(%lx, %lx)"
			       " failed (segs: 0x%04hx)\n", addr, len,
			       LOW_ESID_MASK(addr, len));
		return err;
	}

	return -EINVAL;
}

int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
			struct vm_area_struct *vma)
{
	hugepte_t *src_pte, *dst_pte, entry;
	struct page *ptepage;
	unsigned long addr = vma->vm_start;
	unsigned long end = vma->vm_end;

	while (addr < end) {
		BUG_ON(! in_hugepage_area(src->context, addr));
		BUG_ON(! in_hugepage_area(dst->context, addr));

		dst_pte = hugepte_alloc(dst, addr);
		if (!dst_pte)
			return -ENOMEM;

		src_pte = hugepte_offset(src, addr);
		entry = *src_pte;
		
		if ((addr % HPAGE_SIZE) == 0) {
			/* This is the first hugepte in a batch */
			ptepage = hugepte_page(entry);
			get_page(ptepage);
			dst->rss += (HPAGE_SIZE / PAGE_SIZE);
		}
		set_hugepte(dst_pte, entry);


		addr += PMD_SIZE;
	}
	return 0;
}

int
follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
		    struct page **pages, struct vm_area_struct **vmas,
		    unsigned long *position, int *length, int i)
{
	unsigned long vpfn, vaddr = *position;
	int remainder = *length;

	WARN_ON(!is_vm_hugetlb_page(vma));

	vpfn = vaddr/PAGE_SIZE;
	while (vaddr < vma->vm_end && remainder) {
		BUG_ON(!in_hugepage_area(mm->context, vaddr));

		if (pages) {
			hugepte_t *pte;
			struct page *page;

			pte = hugepte_offset(mm, vaddr);

			/* hugetlb should be locked, and hence, prefaulted */
			WARN_ON(!pte || hugepte_none(*pte));

			page = &hugepte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];

			WARN_ON(!PageCompound(page));

			get_page(page);
			pages[i] = page;
		}

		if (vmas)
			vmas[i] = vma;

		vaddr += PAGE_SIZE;
		++vpfn;
		--remainder;
		++i;
	}

	*length = remainder;
	*position = vaddr;

	return i;
}

struct page *
follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
{
	return ERR_PTR(-EINVAL);
}

int pmd_huge(pmd_t pmd)
{
	return pmd_hugepage(pmd);
}

struct page *
follow_huge_pmd(struct mm_struct *mm, unsigned long address,
		pmd_t *pmd, int write)
{
	struct page *page;

	BUG_ON(! pmd_hugepage(*pmd));

	page = hugepte_page(*(hugepte_t *)pmd);
	if (page)
		page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT);
	return page;
}

void unmap_hugepage_range(struct vm_area_struct *vma,
			  unsigned long start, unsigned long end)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long addr;
	hugepte_t *ptep;
	struct page *page;
	int cpu;
	int local = 0;
	cpumask_t tmp;

	WARN_ON(!is_vm_hugetlb_page(vma));
	BUG_ON((start % HPAGE_SIZE) != 0);
	BUG_ON((end % HPAGE_SIZE) != 0);

	/* XXX are there races with checking cpu_vm_mask? - Anton */
	cpu = get_cpu();
	tmp = cpumask_of_cpu(cpu);
	if (cpus_equal(vma->vm_mm->cpu_vm_mask, tmp))
		local = 1;

	for (addr = start; addr < end; addr += HPAGE_SIZE) {
		hugepte_t pte;

		BUG_ON(!in_hugepage_area(mm->context, addr));

		ptep = hugepte_offset(mm, addr);
		if (!ptep || hugepte_none(*ptep))
			continue;

		pte = *ptep;
		page = hugepte_page(pte);
		teardown_huge_pte(ptep);
		
		if (hugepte_val(pte) & _HUGEPAGE_HASHPTE)
			flush_hash_hugepage(mm->context, addr,
					    pte, local);

		put_page(page);
	}
	put_cpu();

	mm->rss -= (end - start) >> PAGE_SHIFT;
}

int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
{
	struct mm_struct *mm = current->mm;
	unsigned long addr;
	int ret = 0;

	WARN_ON(!is_vm_hugetlb_page(vma));
	BUG_ON((vma->vm_start % HPAGE_SIZE) != 0);
	BUG_ON((vma->vm_end % HPAGE_SIZE) != 0);

	spin_lock(&mm->page_table_lock);
	for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
		unsigned long idx;
		hugepte_t *pte = hugepte_alloc(mm, addr);
		struct page *page;

		BUG_ON(!in_hugepage_area(mm->context, addr));