forked from Minki/linux
79c1c594f4
Patch series "Subject: [PATCH v2 0/5] Implement huge VMAP and VMALLOC on powerpc 8xx", v2. This series implements huge VMAP and VMALLOC on powerpc 8xx. Powerpc 8xx has 4 page sizes: - 4k - 16k - 512k - 8M At the time being, vmalloc and vmap only support huge pages which are leaf at PMD level. Here the PMD level is 4M, it doesn't correspond to any supported page size. For now, implement use of 16k and 512k pages which is done at PTE level. Support of 8M pages will be implemented later, it requires use of hugepd tables. To allow this, the architecture provides two functions: - arch_vmap_pte_range_map_size() which tells vmap_pte_range() what page size to use. A stub returning PAGE_SIZE is provided when the architecture doesn't provide this function. - arch_vmap_pte_supported_shift() which tells __vmalloc_node_range() what page shift to use for a given area size. A stub returning PAGE_SHIFT is provided when the architecture doesn't provide this function. This patch (of 5): At the time being, arch_make_huge_pte() has the following prototype: pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, struct page *page, int writable); vma is used to get the pages shift or size. vma is also used on Sparc to get vm_flags. page is not used. writable is not used. In order to use this function without a vma, replace vma by shift and flags. Also remove the used parameters. Link: https://lkml.kernel.org/r/cover.1620795204.git.christophe.leroy@csgroup.eu Link: https://lkml.kernel.org/r/f4633ac6a7da2f22f31a04a89e0a7026bb78b15b.1620795204.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Acked-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Uladzislau Rezki <uladzislau.rezki@sony.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
517 lines
12 KiB
C
517 lines
12 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* arch/arm64/mm/hugetlbpage.c
|
|
*
|
|
* Copyright (C) 2013 Linaro Ltd.
|
|
*
|
|
* Based on arch/x86/mm/hugetlbpage.c.
|
|
*/
|
|
|
|
#include <linux/init.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/hugetlb.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/err.h>
|
|
#include <linux/sysctl.h>
|
|
#include <asm/mman.h>
|
|
#include <asm/tlb.h>
|
|
#include <asm/tlbflush.h>
|
|
|
|
/*
|
|
* HugeTLB Support Matrix
|
|
*
|
|
* ---------------------------------------------------
|
|
* | Page Size | CONT PTE | PMD | CONT PMD | PUD |
|
|
* ---------------------------------------------------
|
|
* | 4K | 64K | 2M | 32M | 1G |
|
|
* | 16K | 2M | 32M | 1G | |
|
|
* | 64K | 2M | 512M | 16G | |
|
|
* ---------------------------------------------------
|
|
*/
|
|
|
|
/*
|
|
* Reserve CMA areas for the largest supported gigantic
|
|
* huge page when requested. Any other smaller gigantic
|
|
* huge pages could still be served from those areas.
|
|
*/
|
|
#ifdef CONFIG_CMA
|
|
void __init arm64_hugetlb_cma_reserve(void)
|
|
{
|
|
int order;
|
|
|
|
#ifdef CONFIG_ARM64_4K_PAGES
|
|
order = PUD_SHIFT - PAGE_SHIFT;
|
|
#else
|
|
order = CONT_PMD_SHIFT + PMD_SHIFT - PAGE_SHIFT;
|
|
#endif
|
|
/*
|
|
* HugeTLB CMA reservation is required for gigantic
|
|
* huge pages which could not be allocated via the
|
|
* page allocator. Just warn if there is any change
|
|
* breaking this assumption.
|
|
*/
|
|
WARN_ON(order <= MAX_ORDER);
|
|
hugetlb_cma_reserve(order);
|
|
}
|
|
#endif /* CONFIG_CMA */
|
|
|
|
#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
|
|
bool arch_hugetlb_migration_supported(struct hstate *h)
|
|
{
|
|
size_t pagesize = huge_page_size(h);
|
|
|
|
switch (pagesize) {
|
|
#ifdef CONFIG_ARM64_4K_PAGES
|
|
case PUD_SIZE:
|
|
#endif
|
|
case PMD_SIZE:
|
|
case CONT_PMD_SIZE:
|
|
case CONT_PTE_SIZE:
|
|
return true;
|
|
}
|
|
pr_warn("%s: unrecognized huge page size 0x%lx\n",
|
|
__func__, pagesize);
|
|
return false;
|
|
}
|
|
#endif
|
|
|
|
int pmd_huge(pmd_t pmd)
|
|
{
|
|
return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
|
|
}
|
|
|
|
int pud_huge(pud_t pud)
|
|
{
|
|
#ifndef __PAGETABLE_PMD_FOLDED
|
|
return pud_val(pud) && !(pud_val(pud) & PUD_TABLE_BIT);
|
|
#else
|
|
return 0;
|
|
#endif
|
|
}
|
|
|
|
/*
|
|
* Select all bits except the pfn
|
|
*/
|
|
static inline pgprot_t pte_pgprot(pte_t pte)
|
|
{
|
|
unsigned long pfn = pte_pfn(pte);
|
|
|
|
return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
|
|
}
|
|
|
|
static int find_num_contig(struct mm_struct *mm, unsigned long addr,
|
|
pte_t *ptep, size_t *pgsize)
|
|
{
|
|
pgd_t *pgdp = pgd_offset(mm, addr);
|
|
p4d_t *p4dp;
|
|
pud_t *pudp;
|
|
pmd_t *pmdp;
|
|
|
|
*pgsize = PAGE_SIZE;
|
|
p4dp = p4d_offset(pgdp, addr);
|
|
pudp = pud_offset(p4dp, addr);
|
|
pmdp = pmd_offset(pudp, addr);
|
|
if ((pte_t *)pmdp == ptep) {
|
|
*pgsize = PMD_SIZE;
|
|
return CONT_PMDS;
|
|
}
|
|
return CONT_PTES;
|
|
}
|
|
|
|
static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
|
|
{
|
|
int contig_ptes = 0;
|
|
|
|
*pgsize = size;
|
|
|
|
switch (size) {
|
|
#ifdef CONFIG_ARM64_4K_PAGES
|
|
case PUD_SIZE:
|
|
#endif
|
|
case PMD_SIZE:
|
|
contig_ptes = 1;
|
|
break;
|
|
case CONT_PMD_SIZE:
|
|
*pgsize = PMD_SIZE;
|
|
contig_ptes = CONT_PMDS;
|
|
break;
|
|
case CONT_PTE_SIZE:
|
|
*pgsize = PAGE_SIZE;
|
|
contig_ptes = CONT_PTES;
|
|
break;
|
|
}
|
|
|
|
return contig_ptes;
|
|
}
|
|
|
|
/*
|
|
* Changing some bits of contiguous entries requires us to follow a
|
|
* Break-Before-Make approach, breaking the whole contiguous set
|
|
* before we can change any entries. See ARM DDI 0487A.k_iss10775,
|
|
* "Misprogramming of the Contiguous bit", page D4-1762.
|
|
*
|
|
* This helper performs the break step.
|
|
*/
|
|
static pte_t get_clear_flush(struct mm_struct *mm,
|
|
unsigned long addr,
|
|
pte_t *ptep,
|
|
unsigned long pgsize,
|
|
unsigned long ncontig)
|
|
{
|
|
pte_t orig_pte = huge_ptep_get(ptep);
|
|
bool valid = pte_valid(orig_pte);
|
|
unsigned long i, saddr = addr;
|
|
|
|
for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
|
|
pte_t pte = ptep_get_and_clear(mm, addr, ptep);
|
|
|
|
/*
|
|
* If HW_AFDBM is enabled, then the HW could turn on
|
|
* the dirty or accessed bit for any page in the set,
|
|
* so check them all.
|
|
*/
|
|
if (pte_dirty(pte))
|
|
orig_pte = pte_mkdirty(orig_pte);
|
|
|
|
if (pte_young(pte))
|
|
orig_pte = pte_mkyoung(orig_pte);
|
|
}
|
|
|
|
if (valid) {
|
|
struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
|
|
flush_tlb_range(&vma, saddr, addr);
|
|
}
|
|
return orig_pte;
|
|
}
|
|
|
|
/*
|
|
* Changing some bits of contiguous entries requires us to follow a
|
|
* Break-Before-Make approach, breaking the whole contiguous set
|
|
* before we can change any entries. See ARM DDI 0487A.k_iss10775,
|
|
* "Misprogramming of the Contiguous bit", page D4-1762.
|
|
*
|
|
* This helper performs the break step for use cases where the
|
|
* original pte is not needed.
|
|
*/
|
|
static void clear_flush(struct mm_struct *mm,
|
|
unsigned long addr,
|
|
pte_t *ptep,
|
|
unsigned long pgsize,
|
|
unsigned long ncontig)
|
|
{
|
|
struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
|
|
unsigned long i, saddr = addr;
|
|
|
|
for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
|
|
pte_clear(mm, addr, ptep);
|
|
|
|
flush_tlb_range(&vma, saddr, addr);
|
|
}
|
|
|
|
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
|
|
pte_t *ptep, pte_t pte)
|
|
{
|
|
size_t pgsize;
|
|
int i;
|
|
int ncontig;
|
|
unsigned long pfn, dpfn;
|
|
pgprot_t hugeprot;
|
|
|
|
/*
|
|
* Code needs to be expanded to handle huge swap and migration
|
|
* entries. Needed for HUGETLB and MEMORY_FAILURE.
|
|
*/
|
|
WARN_ON(!pte_present(pte));
|
|
|
|
if (!pte_cont(pte)) {
|
|
set_pte_at(mm, addr, ptep, pte);
|
|
return;
|
|
}
|
|
|
|
ncontig = find_num_contig(mm, addr, ptep, &pgsize);
|
|
pfn = pte_pfn(pte);
|
|
dpfn = pgsize >> PAGE_SHIFT;
|
|
hugeprot = pte_pgprot(pte);
|
|
|
|
clear_flush(mm, addr, ptep, pgsize, ncontig);
|
|
|
|
for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
|
|
set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
|
|
}
|
|
|
|
void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
|
|
pte_t *ptep, pte_t pte, unsigned long sz)
|
|
{
|
|
int i, ncontig;
|
|
size_t pgsize;
|
|
|
|
ncontig = num_contig_ptes(sz, &pgsize);
|
|
|
|
for (i = 0; i < ncontig; i++, ptep++)
|
|
set_pte(ptep, pte);
|
|
}
|
|
|
|
pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
|
|
unsigned long addr, unsigned long sz)
|
|
{
|
|
pgd_t *pgdp;
|
|
p4d_t *p4dp;
|
|
pud_t *pudp;
|
|
pmd_t *pmdp;
|
|
pte_t *ptep = NULL;
|
|
|
|
pgdp = pgd_offset(mm, addr);
|
|
p4dp = p4d_offset(pgdp, addr);
|
|
pudp = pud_alloc(mm, p4dp, addr);
|
|
if (!pudp)
|
|
return NULL;
|
|
|
|
if (sz == PUD_SIZE) {
|
|
ptep = (pte_t *)pudp;
|
|
} else if (sz == (CONT_PTE_SIZE)) {
|
|
pmdp = pmd_alloc(mm, pudp, addr);
|
|
if (!pmdp)
|
|
return NULL;
|
|
|
|
WARN_ON(addr & (sz - 1));
|
|
/*
|
|
* Note that if this code were ever ported to the
|
|
* 32-bit arm platform then it will cause trouble in
|
|
* the case where CONFIG_HIGHPTE is set, since there
|
|
* will be no pte_unmap() to correspond with this
|
|
* pte_alloc_map().
|
|
*/
|
|
ptep = pte_alloc_map(mm, pmdp, addr);
|
|
} else if (sz == PMD_SIZE) {
|
|
if (want_pmd_share(vma, addr) && pud_none(READ_ONCE(*pudp)))
|
|
ptep = huge_pmd_share(mm, vma, addr, pudp);
|
|
else
|
|
ptep = (pte_t *)pmd_alloc(mm, pudp, addr);
|
|
} else if (sz == (CONT_PMD_SIZE)) {
|
|
pmdp = pmd_alloc(mm, pudp, addr);
|
|
WARN_ON(addr & (sz - 1));
|
|
return (pte_t *)pmdp;
|
|
}
|
|
|
|
return ptep;
|
|
}
|
|
|
|
pte_t *huge_pte_offset(struct mm_struct *mm,
|
|
unsigned long addr, unsigned long sz)
|
|
{
|
|
pgd_t *pgdp;
|
|
p4d_t *p4dp;
|
|
pud_t *pudp, pud;
|
|
pmd_t *pmdp, pmd;
|
|
|
|
pgdp = pgd_offset(mm, addr);
|
|
if (!pgd_present(READ_ONCE(*pgdp)))
|
|
return NULL;
|
|
|
|
p4dp = p4d_offset(pgdp, addr);
|
|
if (!p4d_present(READ_ONCE(*p4dp)))
|
|
return NULL;
|
|
|
|
pudp = pud_offset(p4dp, addr);
|
|
pud = READ_ONCE(*pudp);
|
|
if (sz != PUD_SIZE && pud_none(pud))
|
|
return NULL;
|
|
/* hugepage or swap? */
|
|
if (pud_huge(pud) || !pud_present(pud))
|
|
return (pte_t *)pudp;
|
|
/* table; check the next level */
|
|
|
|
if (sz == CONT_PMD_SIZE)
|
|
addr &= CONT_PMD_MASK;
|
|
|
|
pmdp = pmd_offset(pudp, addr);
|
|
pmd = READ_ONCE(*pmdp);
|
|
if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) &&
|
|
pmd_none(pmd))
|
|
return NULL;
|
|
if (pmd_huge(pmd) || !pmd_present(pmd))
|
|
return (pte_t *)pmdp;
|
|
|
|
if (sz == CONT_PTE_SIZE)
|
|
return pte_offset_kernel(pmdp, (addr & CONT_PTE_MASK));
|
|
|
|
return NULL;
|
|
}
|
|
|
|
pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
|
|
{
|
|
size_t pagesize = 1UL << shift;
|
|
|
|
if (pagesize == CONT_PTE_SIZE) {
|
|
entry = pte_mkcont(entry);
|
|
} else if (pagesize == CONT_PMD_SIZE) {
|
|
entry = pmd_pte(pmd_mkcont(pte_pmd(entry)));
|
|
} else if (pagesize != PUD_SIZE && pagesize != PMD_SIZE) {
|
|
pr_warn("%s: unrecognized huge page size 0x%lx\n",
|
|
__func__, pagesize);
|
|
}
|
|
return entry;
|
|
}
|
|
|
|
void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
|
|
pte_t *ptep, unsigned long sz)
|
|
{
|
|
int i, ncontig;
|
|
size_t pgsize;
|
|
|
|
ncontig = num_contig_ptes(sz, &pgsize);
|
|
|
|
for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
|
|
pte_clear(mm, addr, ptep);
|
|
}
|
|
|
|
pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
|
|
unsigned long addr, pte_t *ptep)
|
|
{
|
|
int ncontig;
|
|
size_t pgsize;
|
|
pte_t orig_pte = huge_ptep_get(ptep);
|
|
|
|
if (!pte_cont(orig_pte))
|
|
return ptep_get_and_clear(mm, addr, ptep);
|
|
|
|
ncontig = find_num_contig(mm, addr, ptep, &pgsize);
|
|
|
|
return get_clear_flush(mm, addr, ptep, pgsize, ncontig);
|
|
}
|
|
|
|
/*
|
|
* huge_ptep_set_access_flags will update access flags (dirty, accesssed)
|
|
* and write permission.
|
|
*
|
|
* For a contiguous huge pte range we need to check whether or not write
|
|
* permission has to change only on the first pte in the set. Then for
|
|
* all the contiguous ptes we need to check whether or not there is a
|
|
* discrepancy between dirty or young.
|
|
*/
|
|
static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig)
|
|
{
|
|
int i;
|
|
|
|
if (pte_write(pte) != pte_write(huge_ptep_get(ptep)))
|
|
return 1;
|
|
|
|
for (i = 0; i < ncontig; i++) {
|
|
pte_t orig_pte = huge_ptep_get(ptep + i);
|
|
|
|
if (pte_dirty(pte) != pte_dirty(orig_pte))
|
|
return 1;
|
|
|
|
if (pte_young(pte) != pte_young(orig_pte))
|
|
return 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
int huge_ptep_set_access_flags(struct vm_area_struct *vma,
|
|
unsigned long addr, pte_t *ptep,
|
|
pte_t pte, int dirty)
|
|
{
|
|
int ncontig, i;
|
|
size_t pgsize = 0;
|
|
unsigned long pfn = pte_pfn(pte), dpfn;
|
|
pgprot_t hugeprot;
|
|
pte_t orig_pte;
|
|
|
|
if (!pte_cont(pte))
|
|
return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
|
|
|
|
ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
|
|
dpfn = pgsize >> PAGE_SHIFT;
|
|
|
|
if (!__cont_access_flags_changed(ptep, pte, ncontig))
|
|
return 0;
|
|
|
|
orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
|
|
|
|
/* Make sure we don't lose the dirty or young state */
|
|
if (pte_dirty(orig_pte))
|
|
pte = pte_mkdirty(pte);
|
|
|
|
if (pte_young(orig_pte))
|
|
pte = pte_mkyoung(pte);
|
|
|
|
hugeprot = pte_pgprot(pte);
|
|
for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
|
|
set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
|
|
|
|
return 1;
|
|
}
|
|
|
|
void huge_ptep_set_wrprotect(struct mm_struct *mm,
|
|
unsigned long addr, pte_t *ptep)
|
|
{
|
|
unsigned long pfn, dpfn;
|
|
pgprot_t hugeprot;
|
|
int ncontig, i;
|
|
size_t pgsize;
|
|
pte_t pte;
|
|
|
|
if (!pte_cont(READ_ONCE(*ptep))) {
|
|
ptep_set_wrprotect(mm, addr, ptep);
|
|
return;
|
|
}
|
|
|
|
ncontig = find_num_contig(mm, addr, ptep, &pgsize);
|
|
dpfn = pgsize >> PAGE_SHIFT;
|
|
|
|
pte = get_clear_flush(mm, addr, ptep, pgsize, ncontig);
|
|
pte = pte_wrprotect(pte);
|
|
|
|
hugeprot = pte_pgprot(pte);
|
|
pfn = pte_pfn(pte);
|
|
|
|
for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
|
|
set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
|
|
}
|
|
|
|
void huge_ptep_clear_flush(struct vm_area_struct *vma,
|
|
unsigned long addr, pte_t *ptep)
|
|
{
|
|
size_t pgsize;
|
|
int ncontig;
|
|
|
|
if (!pte_cont(READ_ONCE(*ptep))) {
|
|
ptep_clear_flush(vma, addr, ptep);
|
|
return;
|
|
}
|
|
|
|
ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
|
|
clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
|
|
}
|
|
|
|
static int __init hugetlbpage_init(void)
|
|
{
|
|
#ifdef CONFIG_ARM64_4K_PAGES
|
|
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
|
|
#endif
|
|
hugetlb_add_hstate(CONT_PMD_SHIFT - PAGE_SHIFT);
|
|
hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
|
|
hugetlb_add_hstate(CONT_PTE_SHIFT - PAGE_SHIFT);
|
|
|
|
return 0;
|
|
}
|
|
arch_initcall(hugetlbpage_init);
|
|
|
|
bool __init arch_hugetlb_valid_size(unsigned long size)
|
|
{
|
|
switch (size) {
|
|
#ifdef CONFIG_ARM64_4K_PAGES
|
|
case PUD_SIZE:
|
|
#endif
|
|
case CONT_PMD_SIZE:
|
|
case PMD_SIZE:
|
|
case CONT_PTE_SIZE:
|
|
return true;
|
|
}
|
|
|
|
return false;
|
|
}
|