Commit 63551ae0 authored by David Gibson's avatar David Gibson Committed by Linus Torvalds
Browse files

[PATCH] Hugepage consolidation



A lot of the code in arch/*/mm/hugetlbpage.c is quite similar.  This patch
attempts to consolidate a lot of the code across the arch's, putting the
combined version in mm/hugetlb.c.  There are a couple of uglyish hacks in
order to covert all the hugepage archs, but the result is a very large
reduction in the total amount of code.  It also means things like hugepage
lazy allocation could be implemented in one place, instead of six.

Tested, at least a little, on ppc64, i386 and x86_64.

Notes:
	- this patch changes the meaning of set_huge_pte() to be more
	  analagous to set_pte()
	- does SH4 need s special huge_ptep_get_and_clear()??
Acked-by: default avatarWilliam Lee Irwin <wli@holomorphy.com>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
parent 1e7e5a90
......@@ -18,7 +18,7 @@
#include <asm/tlb.h>
#include <asm/tlbflush.h>
static pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
pud_t *pud;
......@@ -30,7 +30,7 @@ static pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
return (pte_t *) pmd;
}
static pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
pud_t *pud;
......@@ -42,21 +42,6 @@ static pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
return (pte_t *) pmd;
}
static void set_huge_pte(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page, pte_t * page_table, int write_access)
{
pte_t entry;
add_mm_counter(mm, rss, HPAGE_SIZE / PAGE_SIZE);
if (write_access) {
entry =
pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
} else
entry = pte_wrprotect(mk_pte(page, vma->vm_page_prot));
entry = pte_mkyoung(entry);
mk_pte_huge(entry);
set_pte(page_table, entry);
}
/*
* This function checks for proper alignment of input addr and len parameters.
*/
......@@ -69,77 +54,6 @@ int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
return 0;
}
int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
struct vm_area_struct *vma)
{
pte_t *src_pte, *dst_pte, entry;
struct page *ptepage;
unsigned long addr = vma->vm_start;
unsigned long end = vma->vm_end;
while (addr < end) {
dst_pte = huge_pte_alloc(dst, addr);
if (!dst_pte)
goto nomem;
src_pte = huge_pte_offset(src, addr);
entry = *src_pte;
ptepage = pte_page(entry);
get_page(ptepage);
set_pte(dst_pte, entry);
add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE);
addr += HPAGE_SIZE;
}
return 0;
nomem:
return -ENOMEM;
}
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) {
if (pages) {
pte_t *pte;
struct page *page;
pte = huge_pte_offset(mm, vaddr);
/* hugetlb should be locked, and hence, prefaulted */
WARN_ON(!pte || pte_none(*pte));
page = &pte_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;
}
#if 0 /* This is just for testing */
struct page *
follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
......@@ -204,83 +118,15 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
}
#endif
void unmap_hugepage_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
void hugetlb_clean_stale_pgtable(pte_t *pte)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
pte_t pte, *ptep;
pmd_t *pmd = (pmd_t *) pte;
struct page *page;
BUG_ON(start & (HPAGE_SIZE - 1));
BUG_ON(end & (HPAGE_SIZE - 1));
for (address = start; address < end; address += HPAGE_SIZE) {
ptep = huge_pte_offset(mm, address);
if (!ptep)
continue;
pte = ptep_get_and_clear(mm, address, ptep);
if (pte_none(pte))
continue;
page = pte_page(pte);
put_page(page);
}
add_mm_counter(mm ,rss, -((end - start) >> PAGE_SHIFT));
flush_tlb_range(vma, start, end);
}
int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
{
struct mm_struct *mm = current->mm;
unsigned long addr;
int ret = 0;
BUG_ON(vma->vm_start & ~HPAGE_MASK);
BUG_ON(vma->vm_end & ~HPAGE_MASK);
spin_lock(&mm->page_table_lock);
for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
unsigned long idx;
pte_t *pte = huge_pte_alloc(mm, addr);
struct page *page;
if (!pte) {
ret = -ENOMEM;
goto out;
}
if (!pte_none(*pte))
continue;
idx = ((addr - vma->vm_start) >> HPAGE_SHIFT)
+ (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
page = find_get_page(mapping, idx);
if (!page) {
/* charge the fs quota first */
if (hugetlb_get_quota(mapping)) {
ret = -ENOMEM;
goto out;
}
page = alloc_huge_page();
if (!page) {
hugetlb_put_quota(mapping);
ret = -ENOMEM;
goto out;
}
ret = add_to_page_cache(page, mapping, idx, GFP_ATOMIC);
if (! ret) {
unlock_page(page);
} else {
hugetlb_put_quota(mapping);
free_huge_page(page);
goto out;
}
}
set_huge_pte(mm, vma, page, pte, vma->vm_flags & VM_WRITE);
}
out:
spin_unlock(&mm->page_table_lock);
return ret;
page = pmd_page(*pmd);
pmd_clear(pmd);
dec_page_state(nr_page_table_pages);
page_cache_release(page);
}
/* x86_64 also uses this file */
......
......@@ -24,7 +24,7 @@
unsigned int hpage_shift=HPAGE_SHIFT_DEFAULT;
static pte_t *
pte_t *
huge_pte_alloc (struct mm_struct *mm, unsigned long addr)
{
unsigned long taddr = htlbpage_to_page(addr);
......@@ -43,7 +43,7 @@ huge_pte_alloc (struct mm_struct *mm, unsigned long addr)
return pte;
}
static pte_t *
pte_t *
huge_pte_offset (struct mm_struct *mm, unsigned long addr)
{
unsigned long taddr = htlbpage_to_page(addr);
......@@ -67,23 +67,6 @@ huge_pte_offset (struct mm_struct *mm, unsigned long addr)
#define mk_pte_huge(entry) { pte_val(entry) |= _PAGE_P; }
static void
set_huge_pte (struct mm_struct *mm, struct vm_area_struct *vma,
struct page *page, pte_t * page_table, int write_access)
{
pte_t entry;
add_mm_counter(mm, rss, HPAGE_SIZE / PAGE_SIZE);
if (write_access) {
entry =
pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
} else
entry = pte_wrprotect(mk_pte(page, vma->vm_page_prot));
entry = pte_mkyoung(entry);
mk_pte_huge(entry);
set_pte(page_table, entry);
return;
}
/*
* This function checks for proper alignment of input addr and len parameters.
*/
......@@ -99,68 +82,6 @@ int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
return 0;
}
int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
struct vm_area_struct *vma)
{
pte_t *src_pte, *dst_pte, entry;
struct page *ptepage;
unsigned long addr = vma->vm_start;
unsigned long end = vma->vm_end;
while (addr < end) {
dst_pte = huge_pte_alloc(dst, addr);
if (!dst_pte)
goto nomem;
src_pte = huge_pte_offset(src, addr);
entry = *src_pte;
ptepage = pte_page(entry);
get_page(ptepage);
set_pte(dst_pte, entry);
add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE);
addr += HPAGE_SIZE;
}
return 0;
nomem:
return -ENOMEM;
}
int
follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
struct page **pages, struct vm_area_struct **vmas,
unsigned long *st, int *length, int i)
{
pte_t *ptep, pte;
unsigned long start = *st;
unsigned long pstart;
int len = *length;
struct page *page;
do {
pstart = start & HPAGE_MASK;
ptep = huge_pte_offset(mm, start);
pte = *ptep;
back1:
page = pte_page(pte);
if (pages) {
page += ((start & ~HPAGE_MASK) >> PAGE_SHIFT);
get_page(page);
pages[i] = page;
}
if (vmas)
vmas[i] = vma;
i++;
len--;
start += PAGE_SIZE;
if (((start & HPAGE_MASK) == pstart) && len &&
(start < vma->vm_end))
goto back1;
} while (len && start < vma->vm_end);
*length = len;
*st = start;
return i;
}
struct page *follow_huge_addr(struct mm_struct *mm, unsigned long addr, int write)
{
struct page *page;
......@@ -212,81 +133,6 @@ void hugetlb_free_pgd_range(struct mmu_gather **tlb,
free_pgd_range(tlb, addr, end, floor, ceiling);
}
void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
pte_t *pte;
struct page *page;
BUG_ON(start & (HPAGE_SIZE - 1));
BUG_ON(end & (HPAGE_SIZE - 1));
for (address = start; address < end; address += HPAGE_SIZE) {
pte = huge_pte_offset(mm, address);
if (pte_none(*pte))
continue;
page = pte_page(*pte);
put_page(page);
pte_clear(mm, address, pte);
}
add_mm_counter(mm, rss, - ((end - start) >> PAGE_SHIFT));
flush_tlb_range(vma, start, end);
}
int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
{
struct mm_struct *mm = current->mm;
unsigned long addr;
int ret = 0;
BUG_ON(vma->vm_start & ~HPAGE_MASK);
BUG_ON(vma->vm_end & ~HPAGE_MASK);
spin_lock(&mm->page_table_lock);
for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
unsigned long idx;
pte_t *pte = huge_pte_alloc(mm, addr);
struct page *page;
if (!pte) {
ret = -ENOMEM;
goto out;
}
if (!pte_none(*pte))
continue;
idx = ((addr - vma->vm_start) >> HPAGE_SHIFT)
+ (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
page = find_get_page(mapping, idx);
if (!page) {
/* charge the fs quota first */
if (hugetlb_get_quota(mapping)) {
ret = -ENOMEM;
goto out;
}
page = alloc_huge_page();
if (!page) {
hugetlb_put_quota(mapping);
ret = -ENOMEM;
goto out;
}
ret = add_to_page_cache(page, mapping, idx, GFP_ATOMIC);
if (! ret) {
unlock_page(page);
} else {
hugetlb_put_quota(mapping);
page_cache_release(page);
goto out;
}
}
set_huge_pte(mm, vma, page, pte, vma->vm_flags & VM_WRITE);
}
out:
spin_unlock(&mm->page_table_lock);
return ret;
}
unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags)
{
......
......@@ -121,7 +121,7 @@ static pte_t *hugepte_alloc(struct mm_struct *mm, pud_t *dir, unsigned long addr
return hugepte_offset(dir, addr);
}
static pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
pud_t *pud;
......@@ -134,7 +134,7 @@ static pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
return hugepte_offset(pud, addr);
}
static pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
{
pud_t *pud;
......@@ -147,25 +147,6 @@ static pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
return hugepte_alloc(mm, pud, addr);
}
static void set_huge_pte(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, struct page *page,
pte_t *ptep, int write_access)
{
pte_t entry;
add_mm_counter(mm, rss, HPAGE_SIZE / PAGE_SIZE);
if (write_access) {
entry =
pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
} else {
entry = pte_wrprotect(mk_pte(page, vma->vm_page_prot));
}
entry = pte_mkyoung(entry);
entry = pte_mkhuge(entry);
set_pte_at(mm, addr, ptep, entry);
}
/*
* This function checks for proper alignment of input addr and len parameters.
*/
......@@ -259,80 +240,6 @@ int prepare_hugepage_range(unsigned long addr, unsigned long len)
return -EINVAL;
}
int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
struct vm_area_struct *vma)
{
pte_t *src_pte, *dst_pte, entry;
struct page *ptepage;
unsigned long addr = vma->vm_start;
unsigned long end = vma->vm_end;
int err = -ENOMEM;
while (addr < end) {
dst_pte = huge_pte_alloc(dst, addr);
if (!dst_pte)
goto out;
src_pte = huge_pte_offset(src, addr);
entry = *src_pte;
ptepage = pte_page(entry);
get_page(ptepage);
add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE);
set_pte_at(dst, addr, dst_pte, entry);
addr += HPAGE_SIZE;
}
err = 0;
out:
return err;
}
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) {
if (pages) {
pte_t *pte;
struct page *page;
pte = huge_pte_offset(mm, vaddr);
/* hugetlb should be locked, and hence, prefaulted */
WARN_ON(!pte || pte_none(*pte));
page = &pte_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)
{
......@@ -363,89 +270,6 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
return NULL;
}
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;
pte_t *ptep;
struct page *page;
WARN_ON(!is_vm_hugetlb_page(vma));
BUG_ON((start % HPAGE_SIZE) != 0);
BUG_ON((end % HPAGE_SIZE) != 0);
for (addr = start; addr < end; addr += HPAGE_SIZE) {
pte_t pte;
ptep = huge_pte_offset(mm, addr);
if (!ptep || pte_none(*ptep))
continue;
pte = *ptep;
page = pte_page(pte);
pte_clear(mm, addr, ptep);
put_page(page);
}
add_mm_counter(mm, rss, -((end - start) >> PAGE_SHIFT));
flush_tlb_pending();
}
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;
pte_t *pte = huge_pte_alloc(mm, addr);
struct page *page;
if (!pte) {
ret = -ENOMEM;
goto out;
}
if (! pte_none(*pte))
continue;
idx = ((addr - vma->vm_start) >> HPAGE_SHIFT)
+ (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
page = find_get_page(mapping, idx);
if (!page) {
/* charge the fs quota first */
if (hugetlb_get_quota(mapping)) {
ret = -ENOMEM;
goto out;
}
page = alloc_huge_page();
if (!page) {
hugetlb_put_quota(mapping);
ret = -ENOMEM;
goto out;
}
ret = add_to_page_cache(page, mapping, idx, GFP_ATOMIC);
if (! ret) {
unlock_page(page);
} else {
hugetlb_put_quota(mapping);
free_huge_page(page);
goto out;
}
}
set_huge_pte(mm, vma, addr, page, pte, vma->vm_flags & VM_WRITE);
}
out:
spin_unlock(&mm->page_table_lock);
return ret;
}
/* Because we have an exclusive hugepage region which lies within the
* normal user address space, we have to take special measures to make
* non-huge mmap()s evade the hugepage reserved regions. */
......
......@@ -24,7 +24,7 @@
#include <asm/tlbflush.h>