bianbu-linux-6.6/arch/riscv/mm/hugetlbpage.c
Linus Torvalds 6e17c6de3d - Yosry Ahmed brought back some cgroup v1 stats in OOM logs.
- Yosry has also eliminated cgroup's atomic rstat flushing.
 
 - Nhat Pham adds the new cachestat() syscall.  It provides userspace
   with the ability to query pagecache status - a similar concept to
   mincore() but more powerful and with improved usability.
 
 - Mel Gorman provides more optimizations for compaction, reducing the
   prevalence of page rescanning.
 
 - Lorenzo Stoakes has done some maintanance work on the get_user_pages()
   interface.
 
 - Liam Howlett continues with cleanups and maintenance work to the maple
   tree code.  Peng Zhang also does some work on maple tree.
 
 - Johannes Weiner has done some cleanup work on the compaction code.
 
 - David Hildenbrand has contributed additional selftests for
   get_user_pages().
 
 - Thomas Gleixner has contributed some maintenance and optimization work
   for the vmalloc code.
 
 - Baolin Wang has provided some compaction cleanups,
 
 - SeongJae Park continues maintenance work on the DAMON code.
 
 - Huang Ying has done some maintenance on the swap code's usage of
   device refcounting.
 
 - Christoph Hellwig has some cleanups for the filemap/directio code.
 
 - Ryan Roberts provides two patch series which yield some
   rationalization of the kernel's access to pte entries - use the provided
   APIs rather than open-coding accesses.
 
 - Lorenzo Stoakes has some fixes to the interaction between pagecache
   and directio access to file mappings.
 
 - John Hubbard has a series of fixes to the MM selftesting code.
 
 - ZhangPeng continues the folio conversion campaign.
 
 - Hugh Dickins has been working on the pagetable handling code, mainly
   with a view to reducing the load on the mmap_lock.
 
 - Catalin Marinas has reduced the arm64 kmalloc() minimum alignment from
   128 to 8.
 
 - Domenico Cerasuolo has improved the zswap reclaim mechanism by
   reorganizing the LRU management.
 
 - Matthew Wilcox provides some fixups to make gfs2 work better with the
   buffer_head code.
 
 - Vishal Moola also has done some folio conversion work.
 
 - Matthew Wilcox has removed the remnants of the pagevec code - their
   functionality is migrated over to struct folio_batch.
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZJejewAKCRDdBJ7gKXxA
 joggAPwKMfT9lvDBEUnJagY7dbDPky1cSYZdJKxxM2cApGa42gEA6Cl8HRAWqSOh
 J0qXCzqaaN8+BuEyLGDVPaXur9KirwY=
 =B7yQ
 -----END PGP SIGNATURE-----

Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull mm updates from Andrew Morton:

 - Yosry Ahmed brought back some cgroup v1 stats in OOM logs

 - Yosry has also eliminated cgroup's atomic rstat flushing

 - Nhat Pham adds the new cachestat() syscall. It provides userspace
   with the ability to query pagecache status - a similar concept to
   mincore() but more powerful and with improved usability

 - Mel Gorman provides more optimizations for compaction, reducing the
   prevalence of page rescanning

 - Lorenzo Stoakes has done some maintanance work on the
   get_user_pages() interface

 - Liam Howlett continues with cleanups and maintenance work to the
   maple tree code. Peng Zhang also does some work on maple tree

 - Johannes Weiner has done some cleanup work on the compaction code

 - David Hildenbrand has contributed additional selftests for
   get_user_pages()

 - Thomas Gleixner has contributed some maintenance and optimization
   work for the vmalloc code

 - Baolin Wang has provided some compaction cleanups,

 - SeongJae Park continues maintenance work on the DAMON code

 - Huang Ying has done some maintenance on the swap code's usage of
   device refcounting

 - Christoph Hellwig has some cleanups for the filemap/directio code

 - Ryan Roberts provides two patch series which yield some
   rationalization of the kernel's access to pte entries - use the
   provided APIs rather than open-coding accesses

 - Lorenzo Stoakes has some fixes to the interaction between pagecache
   and directio access to file mappings

 - John Hubbard has a series of fixes to the MM selftesting code

 - ZhangPeng continues the folio conversion campaign

 - Hugh Dickins has been working on the pagetable handling code, mainly
   with a view to reducing the load on the mmap_lock

 - Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
   from 128 to 8

 - Domenico Cerasuolo has improved the zswap reclaim mechanism by
   reorganizing the LRU management

 - Matthew Wilcox provides some fixups to make gfs2 work better with the
   buffer_head code

 - Vishal Moola also has done some folio conversion work

 - Matthew Wilcox has removed the remnants of the pagevec code - their
   functionality is migrated over to struct folio_batch

* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
  mm/hugetlb: remove hugetlb_set_page_subpool()
  mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
  hugetlb: revert use of page_cache_next_miss()
  Revert "page cache: fix page_cache_next/prev_miss off by one"
  mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
  mm: memcg: rename and document global_reclaim()
  mm: kill [add|del]_page_to_lru_list()
  mm: compaction: convert to use a folio in isolate_migratepages_block()
  mm: zswap: fix double invalidate with exclusive loads
  mm: remove unnecessary pagevec includes
  mm: remove references to pagevec
  mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
  mm: remove struct pagevec
  net: convert sunrpc from pagevec to folio_batch
  i915: convert i915_gpu_error to use a folio_batch
  pagevec: rename fbatch_count()
  mm: remove check_move_unevictable_pages()
  drm: convert drm_gem_put_pages() to use a folio_batch
  i915: convert shmem_sg_free_table() to use a folio_batch
  scatterlist: add sg_set_folio()
  ...
2023-06-28 10:28:11 -07:00

363 lines
7.2 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <linux/hugetlb.h>
#include <linux/err.h>
#ifdef CONFIG_RISCV_ISA_SVNAPOT
pte_t huge_ptep_get(pte_t *ptep)
{
unsigned long pte_num;
int i;
pte_t orig_pte = ptep_get(ptep);
if (!pte_present(orig_pte) || !pte_napot(orig_pte))
return orig_pte;
pte_num = napot_pte_num(napot_cont_order(orig_pte));
for (i = 0; i < pte_num; i++, ptep++) {
pte_t pte = ptep_get(ptep);
if (pte_dirty(pte))
orig_pte = pte_mkdirty(orig_pte);
if (pte_young(pte))
orig_pte = pte_mkyoung(orig_pte);
}
return orig_pte;
}
pte_t *huge_pte_alloc(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long addr,
unsigned long sz)
{
unsigned long order;
pte_t *pte = NULL;
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pgd = pgd_offset(mm, addr);
p4d = p4d_alloc(mm, pgd, addr);
if (!p4d)
return NULL;
pud = pud_alloc(mm, p4d, addr);
if (!pud)
return NULL;
if (sz == PUD_SIZE) {
pte = (pte_t *)pud;
goto out;
}
if (sz == PMD_SIZE) {
if (want_pmd_share(vma, addr) && pud_none(*pud))
pte = huge_pmd_share(mm, vma, addr, pud);
else
pte = (pte_t *)pmd_alloc(mm, pud, addr);
goto out;
}
pmd = pmd_alloc(mm, pud, addr);
if (!pmd)
return NULL;
for_each_napot_order(order) {
if (napot_cont_size(order) == sz) {
pte = pte_alloc_huge(mm, pmd, addr & napot_cont_mask(order));
break;
}
}
out:
WARN_ON_ONCE(pte && pte_present(*pte) && !pte_huge(*pte));
return pte;
}
pte_t *huge_pte_offset(struct mm_struct *mm,
unsigned long addr,
unsigned long sz)
{
unsigned long order;
pte_t *pte = NULL;
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pgd = pgd_offset(mm, addr);
if (!pgd_present(*pgd))
return NULL;
p4d = p4d_offset(pgd, addr);
if (!p4d_present(*p4d))
return NULL;
pud = pud_offset(p4d, addr);
if (sz == PUD_SIZE)
/* must be pud huge, non-present or none */
return (pte_t *)pud;
if (!pud_present(*pud))
return NULL;
pmd = pmd_offset(pud, addr);
if (sz == PMD_SIZE)
/* must be pmd huge, non-present or none */
return (pte_t *)pmd;
if (!pmd_present(*pmd))
return NULL;
for_each_napot_order(order) {
if (napot_cont_size(order) == sz) {
pte = pte_offset_huge(pmd, addr & napot_cont_mask(order));
break;
}
}
return pte;
}
static pte_t get_clear_contig(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep,
unsigned long pte_num)
{
pte_t orig_pte = ptep_get(ptep);
unsigned long i;
for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) {
pte_t pte = ptep_get_and_clear(mm, addr, ptep);
if (pte_dirty(pte))
orig_pte = pte_mkdirty(orig_pte);
if (pte_young(pte))
orig_pte = pte_mkyoung(orig_pte);
}
return orig_pte;
}
static pte_t get_clear_contig_flush(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep,
unsigned long pte_num)
{
pte_t orig_pte = get_clear_contig(mm, addr, ptep, pte_num);
struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
bool valid = !pte_none(orig_pte);
if (valid)
flush_tlb_range(&vma, addr, addr + (PAGE_SIZE * pte_num));
return orig_pte;
}
pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
{
unsigned long order;
for_each_napot_order(order) {
if (shift == napot_cont_shift(order)) {
entry = pte_mknapot(entry, order);
break;
}
}
if (order == NAPOT_ORDER_MAX)
entry = pte_mkhuge(entry);
return entry;
}
void set_huge_pte_at(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep,
pte_t pte)
{
int i, pte_num;
if (!pte_napot(pte)) {
set_pte_at(mm, addr, ptep, pte);
return;
}
pte_num = napot_pte_num(napot_cont_order(pte));
for (i = 0; i < pte_num; i++, ptep++, addr += PAGE_SIZE)
set_pte_at(mm, addr, ptep, pte);
}
int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep,
pte_t pte,
int dirty)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long order;
pte_t orig_pte;
int i, pte_num;
if (!pte_napot(pte))
return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
order = napot_cont_order(pte);
pte_num = napot_pte_num(order);
ptep = huge_pte_offset(mm, addr, napot_cont_size(order));
orig_pte = get_clear_contig_flush(mm, addr, ptep, pte_num);
if (pte_dirty(orig_pte))
pte = pte_mkdirty(pte);
if (pte_young(orig_pte))
pte = pte_mkyoung(pte);
for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++)
set_pte_at(mm, addr, ptep, pte);
return true;
}
pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep)
{
pte_t orig_pte = ptep_get(ptep);
int pte_num;
if (!pte_napot(orig_pte))
return ptep_get_and_clear(mm, addr, ptep);
pte_num = napot_pte_num(napot_cont_order(orig_pte));
return get_clear_contig(mm, addr, ptep, pte_num);
}
void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep)
{
pte_t pte = ptep_get(ptep);
unsigned long order;
pte_t orig_pte;
int i, pte_num;
if (!pte_napot(pte)) {
ptep_set_wrprotect(mm, addr, ptep);
return;
}
order = napot_cont_order(pte);
pte_num = napot_pte_num(order);
ptep = huge_pte_offset(mm, addr, napot_cont_size(order));
orig_pte = get_clear_contig_flush(mm, addr, ptep, pte_num);
orig_pte = pte_wrprotect(orig_pte);
for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++)
set_pte_at(mm, addr, ptep, orig_pte);
}
pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep)
{
pte_t pte = ptep_get(ptep);
int pte_num;
if (!pte_napot(pte))
return ptep_clear_flush(vma, addr, ptep);
pte_num = napot_pte_num(napot_cont_order(pte));
return get_clear_contig_flush(vma->vm_mm, addr, ptep, pte_num);
}
void huge_pte_clear(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep,
unsigned long sz)
{
pte_t pte = READ_ONCE(*ptep);
int i, pte_num;
if (!pte_napot(pte)) {
pte_clear(mm, addr, ptep);
return;
}
pte_num = napot_pte_num(napot_cont_order(pte));
for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++)
pte_clear(mm, addr, ptep);
}
static __init bool is_napot_size(unsigned long size)
{
unsigned long order;
if (!has_svnapot())
return false;
for_each_napot_order(order) {
if (size == napot_cont_size(order))
return true;
}
return false;
}
static __init int napot_hugetlbpages_init(void)
{
if (has_svnapot()) {
unsigned long order;
for_each_napot_order(order)
hugetlb_add_hstate(order);
}
return 0;
}
arch_initcall(napot_hugetlbpages_init);
#else
static __init bool is_napot_size(unsigned long size)
{
return false;
}
#endif /*CONFIG_RISCV_ISA_SVNAPOT*/
int pud_huge(pud_t pud)
{
return pud_leaf(pud);
}
int pmd_huge(pmd_t pmd)
{
return pmd_leaf(pmd);
}
bool __init arch_hugetlb_valid_size(unsigned long size)
{
if (size == HPAGE_SIZE)
return true;
else if (IS_ENABLED(CONFIG_64BIT) && size == PUD_SIZE)
return true;
else if (is_napot_size(size))
return true;
else
return false;
}
#ifdef CONFIG_CONTIG_ALLOC
static __init int gigantic_pages_init(void)
{
/* With CONTIG_ALLOC, we can allocate gigantic pages at runtime */
if (IS_ENABLED(CONFIG_64BIT))
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
return 0;
}
arch_initcall(gigantic_pages_init);
#endif