#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/backing-dev.h>
#include <linux/blkdev.h>
#include <linux/migrate.h>
#include <linux/vmalloc.h>
#include <linux/swap_slots.h>
#include <linux/huge_mm.h>
#include <linux/shmem_fs.h>
#include "internal.h"
#include "swap.h"
static const struct address_space_operations swap_aops = {
.writepage = swap_writepage,
.dirty_folio = noop_dirty_folio,
#ifdef CONFIG_MIGRATION
.migrate_folio = migrate_folio,
#endif
};
struct address_space *swapper_spaces[MAX_SWAPFILES] __read_mostly;
static unsigned int nr_swapper_spaces[MAX_SWAPFILES] __read_mostly;
static bool enable_vma_readahead __read_mostly = true;
#define SWAP_RA_WIN_SHIFT (PAGE_SHIFT / 2)
#define SWAP_RA_HITS_MASK ((1UL << SWAP_RA_WIN_SHIFT) - 1)
#define SWAP_RA_HITS_MAX SWAP_RA_HITS_MASK
#define SWAP_RA_WIN_MASK (~PAGE_MASK & ~SWAP_RA_HITS_MASK)
#define SWAP_RA_HITS(v) ((v) & SWAP_RA_HITS_MASK)
#define SWAP_RA_WIN(v) (((v) & SWAP_RA_WIN_MASK) >> SWAP_RA_WIN_SHIFT)
#define SWAP_RA_ADDR(v) ((v) & PAGE_MASK)
#define SWAP_RA_VAL(addr, win, hits) \
(((addr) & PAGE_MASK) | \
(((win) << SWAP_RA_WIN_SHIFT) & SWAP_RA_WIN_MASK) | \
((hits) & SWAP_RA_HITS_MASK))
#define GET_SWAP_RA_VAL(vma) \
(atomic_long_read(&(vma)->swap_readahead_info) ? : 4)
static atomic_t swapin_readahead_hits = ATOMIC_INIT(4);
void show_swap_cache_info(void)
{
printk("%lu pages in swap cache\n", total_swapcache_pages());
printk("Free swap = %ldkB\n", K(get_nr_swap_pages()));
printk("Total swap = %lukB\n", K(total_swap_pages));
}
void *get_shadow_from_swap_cache(swp_entry_t entry)
{
struct address_space *address_space = swap_address_space(entry);
pgoff_t idx = swp_offset(entry);
struct page *page;
page = xa_load(&address_space->i_pages, idx);
if (xa_is_value(page))
return page;
return NULL;
}
int add_to_swap_cache(struct folio *folio, swp_entry_t entry,
gfp_t gfp, void **shadowp)
{
struct address_space *address_space = swap_address_space(entry);
pgoff_t idx = swp_offset(entry);
XA_STATE_ORDER(xas, &address_space->i_pages, idx, folio_order(folio));
unsigned long i, nr = folio_nr_pages(folio);
void *old;
xas_set_update(&xas, workingset_update_node);
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_swapbacked(folio), folio);
folio_ref_add(folio, nr);
folio_set_swapcache(folio);
folio->swap = entry;
do {
xas_lock_irq(&xas);
xas_create_range(&xas);
if (xas_error(&xas))
goto unlock;
for (i = 0; i < nr; i++) {
VM_BUG_ON_FOLIO(xas.xa_index != idx + i, folio);
old = xas_load(&xas);
if (xa_is_value(old)) {
if (shadowp)
*shadowp = old;
}
xas_store(&xas, folio);
xas_next(&xas);
}
address_space->nrpages += nr;
__node_stat_mod_folio(folio, NR_FILE_PAGES, nr);
__lruvec_stat_mod_folio(folio, NR_SWAPCACHE, nr);
unlock:
xas_unlock_irq(&xas);
} while (xas_nomem(&xas, gfp));
if (!xas_error(&xas))
return 0;
folio_clear_swapcache(folio);
folio_ref_sub(folio, nr);
return xas_error(&xas);
}
void __delete_from_swap_cache(struct folio *folio,
swp_entry_t entry, void *shadow)
{
struct address_space *address_space = swap_address_space(entry);
int i;
long nr = folio_nr_pages(folio);
pgoff_t idx = swp_offset(entry);
XA_STATE(xas, &address_space->i_pages, idx);
xas_set_update(&xas, workingset_update_node);
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio);
for (i = 0; i < nr; i++) {
void *entry = xas_store(&xas, shadow);
VM_BUG_ON_PAGE(entry != folio, entry);
xas_next(&xas);
}
folio->swap.val = 0;
folio_clear_swapcache(folio);
address_space->nrpages -= nr;
__node_stat_mod_folio(folio, NR_FILE_PAGES, -nr);
__lruvec_stat_mod_folio(folio, NR_SWAPCACHE, -nr);
}
bool add_to_swap(struct folio *folio)
{
swp_entry_t entry;
int err;
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio);
entry = folio_alloc_swap(folio);
if (!entry.val)
return false;
err = add_to_swap_cache(folio, entry,
__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN, NULL);
if (err)
goto fail;
folio_mark_dirty(folio);
return true;
fail:
put_swap_folio(folio, entry);
return false;
}
void delete_from_swap_cache(struct folio *folio)
{
swp_entry_t entry = folio->swap;
struct address_space *address_space = swap_address_space(entry);
xa_lock_irq(&address_space->i_pages);
__delete_from_swap_cache(folio, entry, NULL);
xa_unlock_irq(&address_space->i_pages);
put_swap_folio(folio, entry);
folio_ref_sub(folio, folio_nr_pages(folio));
}
void clear_shadow_from_swap_cache(int type, unsigned long begin,
unsigned long end)
{
unsigned long curr = begin;
void *old;
for (;;) {
swp_entry_t entry = swp_entry(type, curr);
struct address_space *address_space = swap_address_space(entry);
XA_STATE(xas, &address_space->i_pages, curr);
xas_set_update(&xas, workingset_update_node);
xa_lock_irq(&address_space->i_pages);
xas_for_each(&xas, old, end) {
if (!xa_is_value(old))
continue;
xas_store(&xas, NULL);
}
xa_unlock_irq(&address_space->i_pages);
curr >>= SWAP_ADDRESS_SPACE_SHIFT;
curr++;
curr <<= SWAP_ADDRESS_SPACE_SHIFT;
if (curr > end)
break;
}
}
void free_swap_cache(struct page *page)
{
struct folio *folio = page_folio(page);
if (folio_test_swapcache(folio) && !folio_mapped(folio) &&
folio_trylock(folio)) {
folio_free_swap(folio);
folio_unlock(folio);
}
}
void free_page_and_swap_cache(struct page *page)
{
free_swap_cache(page);
if (!is_huge_zero_page(page))
put_page(page);
}
void free_pages_and_swap_cache(struct encoded_page **pages, int nr)
{
lru_add_drain();
for (int i = 0; i < nr; i++)
free_swap_cache(encoded_page_ptr(pages[i]));
release_pages(pages, nr);
}
static inline bool swap_use_vma_readahead(void)
{
return READ_ONCE(enable_vma_readahead) && !atomic_read(&nr_rotate_swap);
}
struct folio *swap_cache_get_folio(swp_entry_t entry,
struct vm_area_struct *vma, unsigned long addr)
{
struct folio *folio;
folio = filemap_get_folio(swap_address_space(entry), swp_offset(entry));
if (!IS_ERR(folio)) {
bool vma_ra = swap_use_vma_readahead();
bool readahead;
if (unlikely(folio_test_large(folio)))
return folio;
readahead = folio_test_clear_readahead(folio);
if (vma && vma_ra) {
unsigned long ra_val;
int win, hits;
ra_val = GET_SWAP_RA_VAL(vma);
win = SWAP_RA_WIN(ra_val);
hits = SWAP_RA_HITS(ra_val);
if (readahead)
hits = min_t(int, hits + 1, SWAP_RA_HITS_MAX);
atomic_long_set(&vma->swap_readahead_info,
SWAP_RA_VAL(addr, win, hits));
}
if (readahead) {
count_vm_event(SWAP_RA_HIT);
if (!vma || !vma_ra)
atomic_inc(&swapin_readahead_hits);
}
} else {
folio = NULL;
}
return folio;
}
struct folio *filemap_get_incore_folio(struct address_space *mapping,
pgoff_t index)
{
swp_entry_t swp;
struct swap_info_struct *si;
struct folio *folio = filemap_get_entry(mapping, index);
if (!folio)
return ERR_PTR(-ENOENT);
if (!xa_is_value(folio))
return folio;
if (!shmem_mapping(mapping))
return ERR_PTR(-ENOENT);
swp = radix_to_swp_entry(folio);
if (non_swap_entry(swp))
return ERR_PTR(-ENOENT);
si = get_swap_device(swp);
if (!si)
return ERR_PTR(-ENOENT);
index = swp_offset(swp);
folio = filemap_get_folio(swap_address_space(swp), index);
put_swap_device(si);
return folio;
}
struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr,
bool *new_page_allocated)
{
struct swap_info_struct *si;
struct folio *folio;
struct page *page;
void *shadow = NULL;
*new_page_allocated = false;
si = get_swap_device(entry);
if (!si)
return NULL;
for (;;) {
int err;
folio = filemap_get_folio(swap_address_space(entry),
swp_offset(entry));
if (!IS_ERR(folio)) {
page = folio_file_page(folio, swp_offset(entry));
goto got_page;
}
if (!swap_swapcount(si, entry) && swap_slot_cache_enabled)
goto fail_put_swap;
folio = vma_alloc_folio(gfp_mask, 0, vma, addr, false);
if (!folio)
goto fail_put_swap;
err = swapcache_prepare(entry);
if (!err)
break;
folio_put(folio);
if (err != -EEXIST)
goto fail_put_swap;
schedule_timeout_uninterruptible(1);
}
__folio_set_locked(folio);
__folio_set_swapbacked(folio);
if (mem_cgroup_swapin_charge_folio(folio, NULL, gfp_mask, entry))
goto fail_unlock;
if (add_to_swap_cache(folio, entry, gfp_mask & GFP_RECLAIM_MASK, &shadow))
goto fail_unlock;
mem_cgroup_swapin_uncharge_swap(entry);
if (shadow)
workingset_refault(folio, shadow);
folio_add_lru(folio);
*new_page_allocated = true;
page = &folio->page;
got_page:
put_swap_device(si);
return page;
fail_unlock:
put_swap_folio(folio, entry);
folio_unlock(folio);
folio_put(folio);
fail_put_swap:
put_swap_device(si);
return NULL;
}
struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma,
unsigned long addr, struct swap_iocb **plug)
{
bool page_was_allocated;
struct page *retpage = __read_swap_cache_async(entry, gfp_mask,
vma, addr, &page_was_allocated);
if (page_was_allocated)
swap_readpage(retpage, false, plug);
return retpage;
}
static unsigned int __swapin_nr_pages(unsigned long prev_offset,
unsigned long offset,
int hits,
int max_pages,
int prev_win)
{
unsigned int pages, last_ra;
pages = hits + 2;
if (pages == 2) {
if (offset != prev_offset + 1 && offset != prev_offset - 1)
pages = 1;
} else {
unsigned int roundup = 4;
while (roundup < pages)
roundup <<= 1;
pages = roundup;
}
if (pages > max_pages)
pages = max_pages;
last_ra = prev_win / 2;
if (pages < last_ra)
pages = last_ra;
return pages;
}
static unsigned long swapin_nr_pages(unsigned long offset)
{
static unsigned long prev_offset;
unsigned int hits, pages, max_pages;
static atomic_t last_readahead_pages;
max_pages = 1 << READ_ONCE(page_cluster);
if (max_pages <= 1)
return 1;
hits = atomic_xchg(&swapin_readahead_hits, 0);
pages = __swapin_nr_pages(READ_ONCE(prev_offset), offset, hits,
max_pages,
atomic_read(&last_readahead_pages));
if (!hits)
WRITE_ONCE(prev_offset, offset);
atomic_set(&last_readahead_pages, pages);
return pages;
}
struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
struct vm_fault *vmf)
{
struct page *page;
unsigned long entry_offset = swp_offset(entry);
unsigned long offset = entry_offset;
unsigned long start_offset, end_offset;
unsigned long mask;
struct swap_info_struct *si = swp_swap_info(entry);
struct blk_plug plug;
struct swap_iocb *splug = NULL;
bool page_allocated;
struct vm_area_struct *vma = vmf->vma;
unsigned long addr = vmf->address;
mask = swapin_nr_pages(offset) - 1;
if (!mask)
goto skip;
start_offset = offset & ~mask;
end_offset = offset | mask;
if (!start_offset)
start_offset++;
if (end_offset >= si->max)
end_offset = si->max - 1;
blk_start_plug(&plug);
for (offset = start_offset; offset <= end_offset ; offset++) {
page = __read_swap_cache_async(
swp_entry(swp_type(entry), offset),
gfp_mask, vma, addr, &page_allocated);
if (!page)
continue;
if (page_allocated) {
swap_readpage(page, false, &splug);
if (offset != entry_offset) {
SetPageReadahead(page);
count_vm_event(SWAP_RA);
}
}
put_page(page);
}
blk_finish_plug(&plug);
swap_read_unplug(splug);
lru_add_drain();
skip:
return read_swap_cache_async(entry, gfp_mask, vma, addr, NULL);
}
int init_swap_address_space(unsigned int type, unsigned long nr_pages)
{
struct address_space *spaces, *space;
unsigned int i, nr;
nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES);
spaces = kvcalloc(nr, sizeof(struct address_space), GFP_KERNEL);
if (!spaces)
return -ENOMEM;
for (i = 0; i < nr; i++) {
space = spaces + i;
xa_init_flags(&space->i_pages, XA_FLAGS_LOCK_IRQ);
atomic_set(&space->i_mmap_writable, 0);
space->a_ops = &swap_aops;
mapping_set_no_writeback_tags(space);
}
nr_swapper_spaces[type] = nr;
swapper_spaces[type] = spaces;
return 0;
}
void exit_swap_address_space(unsigned int type)
{
int i;
struct address_space *spaces = swapper_spaces[type];
for (i = 0; i < nr_swapper_spaces[type]; i++)
VM_WARN_ON_ONCE(!mapping_empty(&spaces[i]));
kvfree(spaces);
nr_swapper_spaces[type] = 0;
swapper_spaces[type] = NULL;
}
#define SWAP_RA_ORDER_CEILING 5
struct vma_swap_readahead {
unsigned short win;
unsigned short offset;
unsigned short nr_pte;
};
static void swap_ra_info(struct vm_fault *vmf,
struct vma_swap_readahead *ra_info)
{
struct vm_area_struct *vma = vmf->vma;
unsigned long ra_val;
unsigned long faddr, pfn, fpfn, lpfn, rpfn;
unsigned long start, end;
unsigned int max_win, hits, prev_win, win;
max_win = 1 << min_t(unsigned int, READ_ONCE(page_cluster),
SWAP_RA_ORDER_CEILING);
if (max_win == 1) {
ra_info->win = 1;
return;
}
faddr = vmf->address;
fpfn = PFN_DOWN(faddr);
ra_val = GET_SWAP_RA_VAL(vma);
pfn = PFN_DOWN(SWAP_RA_ADDR(ra_val));
prev_win = SWAP_RA_WIN(ra_val);
hits = SWAP_RA_HITS(ra_val);
ra_info->win = win = __swapin_nr_pages(pfn, fpfn, hits,
max_win, prev_win);
atomic_long_set(&vma->swap_readahead_info,
SWAP_RA_VAL(faddr, win, 0));
if (win == 1)
return;
if (fpfn == pfn + 1) {
lpfn = fpfn;
rpfn = fpfn + win;
} else if (pfn == fpfn + 1) {
lpfn = fpfn - win + 1;
rpfn = fpfn + 1;
} else {
unsigned int left = (win - 1) / 2;
lpfn = fpfn - left;
rpfn = fpfn + win - left;
}
start = max3(lpfn, PFN_DOWN(vma->vm_start),
PFN_DOWN(faddr & PMD_MASK));
end = min3(rpfn, PFN_DOWN(vma->vm_end),
PFN_DOWN((faddr & PMD_MASK) + PMD_SIZE));
ra_info->nr_pte = end - start;
ra_info->offset = fpfn - start;
}
static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
struct vm_fault *vmf)
{
struct blk_plug plug;
struct swap_iocb *splug = NULL;
struct vm_area_struct *vma = vmf->vma;
struct page *page;
pte_t *pte = NULL, pentry;
unsigned long addr;
swp_entry_t entry;
unsigned int i;
bool page_allocated;
struct vma_swap_readahead ra_info = {
.win = 1,
};
swap_ra_info(vmf, &ra_info);
if (ra_info.win == 1)
goto skip;
addr = vmf->address - (ra_info.offset * PAGE_SIZE);
blk_start_plug(&plug);
for (i = 0; i < ra_info.nr_pte; i++, addr += PAGE_SIZE) {
if (!pte++) {
pte = pte_offset_map(vmf->pmd, addr);
if (!pte)
break;
}
pentry = ptep_get_lockless(pte);
if (!is_swap_pte(pentry))
continue;
entry = pte_to_swp_entry(pentry);
if (unlikely(non_swap_entry(entry)))
continue;
pte_unmap(pte);
pte = NULL;
page = __read_swap_cache_async(entry, gfp_mask, vma,
addr, &page_allocated);
if (!page)
continue;
if (page_allocated) {
swap_readpage(page, false, &splug);
if (i != ra_info.offset) {
SetPageReadahead(page);
count_vm_event(SWAP_RA);
}
}
put_page(page);
}
if (pte)
pte_unmap(pte);
blk_finish_plug(&plug);
swap_read_unplug(splug);
lru_add_drain();
skip:
return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address,
NULL);
}
struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
struct vm_fault *vmf)
{
return swap_use_vma_readahead() ?
swap_vma_readahead(entry, gfp_mask, vmf) :
swap_cluster_readahead(entry, gfp_mask, vmf);
}
#ifdef CONFIG_SYSFS
static ssize_t vma_ra_enabled_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sysfs_emit(buf, "%s\n",
enable_vma_readahead ? "true" : "false");
}
static ssize_t vma_ra_enabled_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
ssize_t ret;
ret = kstrtobool(buf, &enable_vma_readahead);
if (ret)
return ret;
return count;
}
static struct kobj_attribute vma_ra_enabled_attr = __ATTR_RW(vma_ra_enabled);
static struct attribute *swap_attrs[] = {
&vma_ra_enabled_attr.attr,
NULL,
};
static const struct attribute_group swap_attr_group = {
.attrs = swap_attrs,
};
static int __init swap_init_sysfs(void)
{
int err;
struct kobject *swap_kobj;
swap_kobj = kobject_create_and_add("swap", mm_kobj);
if (!swap_kobj) {
pr_err("failed to create swap kobject\n");
return -ENOMEM;
}
err = sysfs_create_group(swap_kobj, &swap_attr_group);
if (err) {
pr_err("failed to register swap group\n");
goto delete_obj;
}
return 0;
delete_obj:
kobject_put(swap_kobj);
return err;
}
subsys_initcall(swap_init_sysfs);
#endif