Currently we have many duplicates in definitions around follow_huge_addr(), follow_huge_pmd(), and follow_huge_pud(), so this patch tries to remove the m. The basic idea is to put the default implementation for these functions in mm/hugetlb.c as weak symbols (regardless of CONFIG_ARCH_WANT_GENERAL_HUGETL B), and to implement arch-specific code only when the arch needs it. For follow_huge_addr(), only powerpc and ia64 have their own implementation, and in all other architectures this function just returns ERR_PTR(-EINVAL). So this patch sets returning ERR_PTR(-EINVAL) as default. As for follow_huge_(pmd|pud)(), if (pmd|pud)_huge() is implemented to always return 0 in your architecture (like in ia64 or sparc,) it's never called (the callsite is optimized away) no matter how implemented it is. So in such architectures, we don't need arch-specific implementation. In some architecture (like mips, s390 and tile,) their current arch-specific follow_huge_(pmd|pud)() are effectively identical with the common code, so this patch lets these architecture use the common code. One exception is metag, where pmd_huge() could return non-zero but it expects follow_huge_pmd() to always return NULL. This means that we need arch-specific implementation which returns NULL. This behavior looks strange to me (because non-zero pmd_huge() implies that the architecture supports PMD-based hugepage, so follow_huge_pmd() can/should return some relevant value,) but that's beyond this cleanup patch, so let's keep it. Justification of non-trivial changes: - in s390, follow_huge_pmd() checks !MACHINE_HAS_HPAGE at first, and this patch removes the check. This is OK because we can assume MACHINE_HAS_HPAGE is true when follow_huge_pmd() can be called (note that pmd_huge() has the same check and always returns 0 for !MACHINE_HAS_HPAGE.) - in s390 and mips, we use HPAGE_MASK instead of PMD_MASK as done in common code. This patch forces these archs use PMD_MASK, but it's OK because they are identical in both archs. In s390, both of HPAGE_SHIFT and PMD_SHIFT are 20. In mips, HPAGE_SHIFT is defined as (PAGE_SHIFT + PAGE_SHIFT - 3) and PMD_SHIFT is define as (PAGE_SHIFT + PAGE_SHIFT + PTE_ORDER - 3), but PTE_ORDER is always 0, so these are identical. Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: James Hogan <james.hogan@imgtec.com> Cc: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Nishanth Aravamudan <nacc@linux.vnet.ibm.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Steve Capper <steve.capper@linaro.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
		
			
				
	
	
		
			199 lines
		
	
	
	
		
			4.6 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			199 lines
		
	
	
	
		
			4.6 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
/*
 | 
						|
 * IA-64 Huge TLB Page Support for Kernel.
 | 
						|
 *
 | 
						|
 * Copyright (C) 2002-2004 Rohit Seth <rohit.seth@intel.com>
 | 
						|
 * Copyright (C) 2003-2004 Ken Chen <kenneth.w.chen@intel.com>
 | 
						|
 *
 | 
						|
 * Sep, 2003: add numa support
 | 
						|
 * Feb, 2004: dynamic hugetlb page size via boot parameter
 | 
						|
 */
 | 
						|
 | 
						|
#include <linux/init.h>
 | 
						|
#include <linux/fs.h>
 | 
						|
#include <linux/mm.h>
 | 
						|
#include <linux/hugetlb.h>
 | 
						|
#include <linux/pagemap.h>
 | 
						|
#include <linux/module.h>
 | 
						|
#include <linux/sysctl.h>
 | 
						|
#include <linux/log2.h>
 | 
						|
#include <asm/mman.h>
 | 
						|
#include <asm/pgalloc.h>
 | 
						|
#include <asm/tlb.h>
 | 
						|
#include <asm/tlbflush.h>
 | 
						|
 | 
						|
unsigned int hpage_shift = HPAGE_SHIFT_DEFAULT;
 | 
						|
EXPORT_SYMBOL(hpage_shift);
 | 
						|
 | 
						|
pte_t *
 | 
						|
huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
 | 
						|
{
 | 
						|
	unsigned long taddr = htlbpage_to_page(addr);
 | 
						|
	pgd_t *pgd;
 | 
						|
	pud_t *pud;
 | 
						|
	pmd_t *pmd;
 | 
						|
	pte_t *pte = NULL;
 | 
						|
 | 
						|
	pgd = pgd_offset(mm, taddr);
 | 
						|
	pud = pud_alloc(mm, pgd, taddr);
 | 
						|
	if (pud) {
 | 
						|
		pmd = pmd_alloc(mm, pud, taddr);
 | 
						|
		if (pmd)
 | 
						|
			pte = pte_alloc_map(mm, NULL, pmd, taddr);
 | 
						|
	}
 | 
						|
	return pte;
 | 
						|
}
 | 
						|
 | 
						|
pte_t *
 | 
						|
huge_pte_offset (struct mm_struct *mm, unsigned long addr)
 | 
						|
{
 | 
						|
	unsigned long taddr = htlbpage_to_page(addr);
 | 
						|
	pgd_t *pgd;
 | 
						|
	pud_t *pud;
 | 
						|
	pmd_t *pmd;
 | 
						|
	pte_t *pte = NULL;
 | 
						|
 | 
						|
	pgd = pgd_offset(mm, taddr);
 | 
						|
	if (pgd_present(*pgd)) {
 | 
						|
		pud = pud_offset(pgd, taddr);
 | 
						|
		if (pud_present(*pud)) {
 | 
						|
			pmd = pmd_offset(pud, taddr);
 | 
						|
			if (pmd_present(*pmd))
 | 
						|
				pte = pte_offset_map(pmd, taddr);
 | 
						|
		}
 | 
						|
	}
 | 
						|
 | 
						|
	return pte;
 | 
						|
}
 | 
						|
 | 
						|
int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 | 
						|
{
 | 
						|
	return 0;
 | 
						|
}
 | 
						|
 | 
						|
#define mk_pte_huge(entry) { pte_val(entry) |= _PAGE_P; }
 | 
						|
 | 
						|
/*
 | 
						|
 * Don't actually need to do any preparation, but need to make sure
 | 
						|
 * the address is in the right region.
 | 
						|
 */
 | 
						|
int prepare_hugepage_range(struct file *file,
 | 
						|
			unsigned long addr, unsigned long len)
 | 
						|
{
 | 
						|
	if (len & ~HPAGE_MASK)
 | 
						|
		return -EINVAL;
 | 
						|
	if (addr & ~HPAGE_MASK)
 | 
						|
		return -EINVAL;
 | 
						|
	if (REGION_NUMBER(addr) != RGN_HPAGE)
 | 
						|
		return -EINVAL;
 | 
						|
 | 
						|
	return 0;
 | 
						|
}
 | 
						|
 | 
						|
struct page *follow_huge_addr(struct mm_struct *mm, unsigned long addr, int write)
 | 
						|
{
 | 
						|
	struct page *page;
 | 
						|
	pte_t *ptep;
 | 
						|
 | 
						|
	if (REGION_NUMBER(addr) != RGN_HPAGE)
 | 
						|
		return ERR_PTR(-EINVAL);
 | 
						|
 | 
						|
	ptep = huge_pte_offset(mm, addr);
 | 
						|
	if (!ptep || pte_none(*ptep))
 | 
						|
		return NULL;
 | 
						|
	page = pte_page(*ptep);
 | 
						|
	page += ((addr & ~HPAGE_MASK) >> PAGE_SHIFT);
 | 
						|
	return page;
 | 
						|
}
 | 
						|
int pmd_huge(pmd_t pmd)
 | 
						|
{
 | 
						|
	return 0;
 | 
						|
}
 | 
						|
 | 
						|
int pud_huge(pud_t pud)
 | 
						|
{
 | 
						|
	return 0;
 | 
						|
}
 | 
						|
 | 
						|
void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 | 
						|
			unsigned long addr, unsigned long end,
 | 
						|
			unsigned long floor, unsigned long ceiling)
 | 
						|
{
 | 
						|
	/*
 | 
						|
	 * This is called to free hugetlb page tables.
 | 
						|
	 *
 | 
						|
	 * The offset of these addresses from the base of the hugetlb
 | 
						|
	 * region must be scaled down by HPAGE_SIZE/PAGE_SIZE so that
 | 
						|
	 * the standard free_pgd_range will free the right page tables.
 | 
						|
	 *
 | 
						|
	 * If floor and ceiling are also in the hugetlb region, they
 | 
						|
	 * must likewise be scaled down; but if outside, left unchanged.
 | 
						|
	 */
 | 
						|
 | 
						|
	addr = htlbpage_to_page(addr);
 | 
						|
	end  = htlbpage_to_page(end);
 | 
						|
	if (REGION_NUMBER(floor) == RGN_HPAGE)
 | 
						|
		floor = htlbpage_to_page(floor);
 | 
						|
	if (REGION_NUMBER(ceiling) == RGN_HPAGE)
 | 
						|
		ceiling = htlbpage_to_page(ceiling);
 | 
						|
 | 
						|
	free_pgd_range(tlb, addr, end, floor, ceiling);
 | 
						|
}
 | 
						|
 | 
						|
unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 | 
						|
		unsigned long pgoff, unsigned long flags)
 | 
						|
{
 | 
						|
	struct vm_unmapped_area_info info;
 | 
						|
 | 
						|
	if (len > RGN_MAP_LIMIT)
 | 
						|
		return -ENOMEM;
 | 
						|
	if (len & ~HPAGE_MASK)
 | 
						|
		return -EINVAL;
 | 
						|
 | 
						|
	/* Handle MAP_FIXED */
 | 
						|
	if (flags & MAP_FIXED) {
 | 
						|
		if (prepare_hugepage_range(file, addr, len))
 | 
						|
			return -EINVAL;
 | 
						|
		return addr;
 | 
						|
	}
 | 
						|
 | 
						|
	/* This code assumes that RGN_HPAGE != 0. */
 | 
						|
	if ((REGION_NUMBER(addr) != RGN_HPAGE) || (addr & (HPAGE_SIZE - 1)))
 | 
						|
		addr = HPAGE_REGION_BASE;
 | 
						|
 | 
						|
	info.flags = 0;
 | 
						|
	info.length = len;
 | 
						|
	info.low_limit = addr;
 | 
						|
	info.high_limit = HPAGE_REGION_BASE + RGN_MAP_LIMIT;
 | 
						|
	info.align_mask = PAGE_MASK & (HPAGE_SIZE - 1);
 | 
						|
	info.align_offset = 0;
 | 
						|
	return vm_unmapped_area(&info);
 | 
						|
}
 | 
						|
 | 
						|
static int __init hugetlb_setup_sz(char *str)
 | 
						|
{
 | 
						|
	u64 tr_pages;
 | 
						|
	unsigned long long size;
 | 
						|
 | 
						|
	if (ia64_pal_vm_page_size(&tr_pages, NULL) != 0)
 | 
						|
		/*
 | 
						|
		 * shouldn't happen, but just in case.
 | 
						|
		 */
 | 
						|
		tr_pages = 0x15557000UL;
 | 
						|
 | 
						|
	size = memparse(str, &str);
 | 
						|
	if (*str || !is_power_of_2(size) || !(tr_pages & size) ||
 | 
						|
		size <= PAGE_SIZE ||
 | 
						|
		size >= (1UL << PAGE_SHIFT << MAX_ORDER)) {
 | 
						|
		printk(KERN_WARNING "Invalid huge page size specified\n");
 | 
						|
		return 1;
 | 
						|
	}
 | 
						|
 | 
						|
	hpage_shift = __ffs(size);
 | 
						|
	/*
 | 
						|
	 * boot cpu already executed ia64_mmu_init, and has HPAGE_SHIFT_DEFAULT
 | 
						|
	 * override here with new page shift.
 | 
						|
	 */
 | 
						|
	ia64_set_rr(HPAGE_REGION_BASE, hpage_shift << 2);
 | 
						|
	return 0;
 | 
						|
}
 | 
						|
early_param("hugepagesz", hugetlb_setup_sz);
 |