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>
		
			
				
	
	
		
			226 lines
		
	
	
	
		
			4.9 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			226 lines
		
	
	
	
		
			4.9 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
/*
 | 
						|
 * SPARC64 Huge TLB page support.
 | 
						|
 *
 | 
						|
 * Copyright (C) 2002, 2003, 2006 David S. Miller (davem@davemloft.net)
 | 
						|
 */
 | 
						|
 | 
						|
#include <linux/fs.h>
 | 
						|
#include <linux/mm.h>
 | 
						|
#include <linux/hugetlb.h>
 | 
						|
#include <linux/pagemap.h>
 | 
						|
#include <linux/sysctl.h>
 | 
						|
 | 
						|
#include <asm/mman.h>
 | 
						|
#include <asm/pgalloc.h>
 | 
						|
#include <asm/tlb.h>
 | 
						|
#include <asm/tlbflush.h>
 | 
						|
#include <asm/cacheflush.h>
 | 
						|
#include <asm/mmu_context.h>
 | 
						|
 | 
						|
/* Slightly simplified from the non-hugepage variant because by
 | 
						|
 * definition we don't have to worry about any page coloring stuff
 | 
						|
 */
 | 
						|
 | 
						|
static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp,
 | 
						|
							unsigned long addr,
 | 
						|
							unsigned long len,
 | 
						|
							unsigned long pgoff,
 | 
						|
							unsigned long flags)
 | 
						|
{
 | 
						|
	unsigned long task_size = TASK_SIZE;
 | 
						|
	struct vm_unmapped_area_info info;
 | 
						|
 | 
						|
	if (test_thread_flag(TIF_32BIT))
 | 
						|
		task_size = STACK_TOP32;
 | 
						|
 | 
						|
	info.flags = 0;
 | 
						|
	info.length = len;
 | 
						|
	info.low_limit = TASK_UNMAPPED_BASE;
 | 
						|
	info.high_limit = min(task_size, VA_EXCLUDE_START);
 | 
						|
	info.align_mask = PAGE_MASK & ~HPAGE_MASK;
 | 
						|
	info.align_offset = 0;
 | 
						|
	addr = vm_unmapped_area(&info);
 | 
						|
 | 
						|
	if ((addr & ~PAGE_MASK) && task_size > VA_EXCLUDE_END) {
 | 
						|
		VM_BUG_ON(addr != -ENOMEM);
 | 
						|
		info.low_limit = VA_EXCLUDE_END;
 | 
						|
		info.high_limit = task_size;
 | 
						|
		addr = vm_unmapped_area(&info);
 | 
						|
	}
 | 
						|
 | 
						|
	return addr;
 | 
						|
}
 | 
						|
 | 
						|
static unsigned long
 | 
						|
hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 | 
						|
				  const unsigned long len,
 | 
						|
				  const unsigned long pgoff,
 | 
						|
				  const unsigned long flags)
 | 
						|
{
 | 
						|
	struct mm_struct *mm = current->mm;
 | 
						|
	unsigned long addr = addr0;
 | 
						|
	struct vm_unmapped_area_info info;
 | 
						|
 | 
						|
	/* This should only ever run for 32-bit processes.  */
 | 
						|
	BUG_ON(!test_thread_flag(TIF_32BIT));
 | 
						|
 | 
						|
	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 | 
						|
	info.length = len;
 | 
						|
	info.low_limit = PAGE_SIZE;
 | 
						|
	info.high_limit = mm->mmap_base;
 | 
						|
	info.align_mask = PAGE_MASK & ~HPAGE_MASK;
 | 
						|
	info.align_offset = 0;
 | 
						|
	addr = vm_unmapped_area(&info);
 | 
						|
 | 
						|
	/*
 | 
						|
	 * A failed mmap() very likely causes application failure,
 | 
						|
	 * so fall back to the bottom-up function here. This scenario
 | 
						|
	 * can happen with large stack limits and large mmap()
 | 
						|
	 * allocations.
 | 
						|
	 */
 | 
						|
	if (addr & ~PAGE_MASK) {
 | 
						|
		VM_BUG_ON(addr != -ENOMEM);
 | 
						|
		info.flags = 0;
 | 
						|
		info.low_limit = TASK_UNMAPPED_BASE;
 | 
						|
		info.high_limit = STACK_TOP32;
 | 
						|
		addr = vm_unmapped_area(&info);
 | 
						|
	}
 | 
						|
 | 
						|
	return addr;
 | 
						|
}
 | 
						|
 | 
						|
unsigned long
 | 
						|
hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 | 
						|
		unsigned long len, unsigned long pgoff, unsigned long flags)
 | 
						|
{
 | 
						|
	struct mm_struct *mm = current->mm;
 | 
						|
	struct vm_area_struct *vma;
 | 
						|
	unsigned long task_size = TASK_SIZE;
 | 
						|
 | 
						|
	if (test_thread_flag(TIF_32BIT))
 | 
						|
		task_size = STACK_TOP32;
 | 
						|
 | 
						|
	if (len & ~HPAGE_MASK)
 | 
						|
		return -EINVAL;
 | 
						|
	if (len > task_size)
 | 
						|
		return -ENOMEM;
 | 
						|
 | 
						|
	if (flags & MAP_FIXED) {
 | 
						|
		if (prepare_hugepage_range(file, addr, len))
 | 
						|
			return -EINVAL;
 | 
						|
		return addr;
 | 
						|
	}
 | 
						|
 | 
						|
	if (addr) {
 | 
						|
		addr = ALIGN(addr, HPAGE_SIZE);
 | 
						|
		vma = find_vma(mm, addr);
 | 
						|
		if (task_size - len >= addr &&
 | 
						|
		    (!vma || addr + len <= vma->vm_start))
 | 
						|
			return addr;
 | 
						|
	}
 | 
						|
	if (mm->get_unmapped_area == arch_get_unmapped_area)
 | 
						|
		return hugetlb_get_unmapped_area_bottomup(file, addr, len,
 | 
						|
				pgoff, flags);
 | 
						|
	else
 | 
						|
		return hugetlb_get_unmapped_area_topdown(file, addr, len,
 | 
						|
				pgoff, flags);
 | 
						|
}
 | 
						|
 | 
						|
pte_t *huge_pte_alloc(struct mm_struct *mm,
 | 
						|
			unsigned long addr, unsigned long sz)
 | 
						|
{
 | 
						|
	pgd_t *pgd;
 | 
						|
	pud_t *pud;
 | 
						|
	pmd_t *pmd;
 | 
						|
	pte_t *pte = NULL;
 | 
						|
 | 
						|
	/* We must align the address, because our caller will run
 | 
						|
	 * set_huge_pte_at() on whatever we return, which writes out
 | 
						|
	 * all of the sub-ptes for the hugepage range.  So we have
 | 
						|
	 * to give it the first such sub-pte.
 | 
						|
	 */
 | 
						|
	addr &= HPAGE_MASK;
 | 
						|
 | 
						|
	pgd = pgd_offset(mm, addr);
 | 
						|
	pud = pud_alloc(mm, pgd, addr);
 | 
						|
	if (pud) {
 | 
						|
		pmd = pmd_alloc(mm, pud, addr);
 | 
						|
		if (pmd)
 | 
						|
			pte = pte_alloc_map(mm, NULL, pmd, addr);
 | 
						|
	}
 | 
						|
	return pte;
 | 
						|
}
 | 
						|
 | 
						|
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 | 
						|
{
 | 
						|
	pgd_t *pgd;
 | 
						|
	pud_t *pud;
 | 
						|
	pmd_t *pmd;
 | 
						|
	pte_t *pte = NULL;
 | 
						|
 | 
						|
	addr &= HPAGE_MASK;
 | 
						|
 | 
						|
	pgd = pgd_offset(mm, addr);
 | 
						|
	if (!pgd_none(*pgd)) {
 | 
						|
		pud = pud_offset(pgd, addr);
 | 
						|
		if (!pud_none(*pud)) {
 | 
						|
			pmd = pmd_offset(pud, addr);
 | 
						|
			if (!pmd_none(*pmd))
 | 
						|
				pte = pte_offset_map(pmd, addr);
 | 
						|
		}
 | 
						|
	}
 | 
						|
	return pte;
 | 
						|
}
 | 
						|
 | 
						|
int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 | 
						|
{
 | 
						|
	return 0;
 | 
						|
}
 | 
						|
 | 
						|
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 | 
						|
		     pte_t *ptep, pte_t entry)
 | 
						|
{
 | 
						|
	int i;
 | 
						|
 | 
						|
	if (!pte_present(*ptep) && pte_present(entry))
 | 
						|
		mm->context.huge_pte_count++;
 | 
						|
 | 
						|
	addr &= HPAGE_MASK;
 | 
						|
	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
 | 
						|
		set_pte_at(mm, addr, ptep, entry);
 | 
						|
		ptep++;
 | 
						|
		addr += PAGE_SIZE;
 | 
						|
		pte_val(entry) += PAGE_SIZE;
 | 
						|
	}
 | 
						|
}
 | 
						|
 | 
						|
pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 | 
						|
			      pte_t *ptep)
 | 
						|
{
 | 
						|
	pte_t entry;
 | 
						|
	int i;
 | 
						|
 | 
						|
	entry = *ptep;
 | 
						|
	if (pte_present(entry))
 | 
						|
		mm->context.huge_pte_count--;
 | 
						|
 | 
						|
	addr &= HPAGE_MASK;
 | 
						|
 | 
						|
	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
 | 
						|
		pte_clear(mm, addr, ptep);
 | 
						|
		addr += PAGE_SIZE;
 | 
						|
		ptep++;
 | 
						|
	}
 | 
						|
 | 
						|
	return entry;
 | 
						|
}
 | 
						|
 | 
						|
int pmd_huge(pmd_t pmd)
 | 
						|
{
 | 
						|
	return 0;
 | 
						|
}
 | 
						|
 | 
						|
int pud_huge(pud_t pud)
 | 
						|
{
 | 
						|
	return 0;
 | 
						|
}
 |