summaryrefslogtreecommitdiff
path: root/mm/swap_state.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/swap_state.c')
-rw-r--r--mm/swap_state.c396
1 files changed, 330 insertions, 66 deletions
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 539b8885e3d1..05b6803f0cce 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -19,6 +19,7 @@
#include <linux/migrate.h>
#include <linux/vmalloc.h>
#include <linux/swap_slots.h>
+#include <linux/huge_mm.h>
#include <asm/pgtable.h>
@@ -36,8 +37,28 @@ static const struct address_space_operations swap_aops = {
struct address_space *swapper_spaces[MAX_SWAPFILES];
static unsigned int nr_swapper_spaces[MAX_SWAPFILES];
+bool swap_vma_readahead = 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))
+
+/* Initial readahead hits is 4 to start up with a small window */
+#define GET_SWAP_RA_VAL(vma) \
+ (atomic_long_read(&(vma)->swap_readahead_info) ? : 4)
#define INC_CACHE_INFO(x) do { swap_cache_info.x++; } while (0)
+#define ADD_CACHE_INFO(x, nr) do { swap_cache_info.x += (nr); } while (0)
static struct {
unsigned long add_total;
@@ -90,39 +111,46 @@ void show_swap_cache_info(void)
*/
int __add_to_swap_cache(struct page *page, swp_entry_t entry)
{
- int error;
+ int error, i, nr = hpage_nr_pages(page);
struct address_space *address_space;
+ pgoff_t idx = swp_offset(entry);
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageSwapCache(page), page);
VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
- get_page(page);
+ page_ref_add(page, nr);
SetPageSwapCache(page);
- set_page_private(page, entry.val);
address_space = swap_address_space(entry);
spin_lock_irq(&address_space->tree_lock);
- error = radix_tree_insert(&address_space->page_tree,
- swp_offset(entry), page);
- if (likely(!error)) {
- address_space->nrpages++;
- __inc_node_page_state(page, NR_FILE_PAGES);
- INC_CACHE_INFO(add_total);
+ for (i = 0; i < nr; i++) {
+ set_page_private(page + i, entry.val + i);
+ error = radix_tree_insert(&address_space->page_tree,
+ idx + i, page + i);
+ if (unlikely(error))
+ break;
}
- spin_unlock_irq(&address_space->tree_lock);
-
- if (unlikely(error)) {
+ if (likely(!error)) {
+ address_space->nrpages += nr;
+ __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
+ ADD_CACHE_INFO(add_total, nr);
+ } else {
/*
* Only the context which have set SWAP_HAS_CACHE flag
* would call add_to_swap_cache().
* So add_to_swap_cache() doesn't returns -EEXIST.
*/
VM_BUG_ON(error == -EEXIST);
- set_page_private(page, 0UL);
+ set_page_private(page + i, 0UL);
+ while (i--) {
+ radix_tree_delete(&address_space->page_tree, idx + i);
+ set_page_private(page + i, 0UL);
+ }
ClearPageSwapCache(page);
- put_page(page);
+ page_ref_sub(page, nr);
}
+ spin_unlock_irq(&address_space->tree_lock);
return error;
}
@@ -132,7 +160,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
{
int error;
- error = radix_tree_maybe_preload(gfp_mask);
+ error = radix_tree_maybe_preload_order(gfp_mask, compound_order(page));
if (!error) {
error = __add_to_swap_cache(page, entry);
radix_tree_preload_end();
@@ -146,8 +174,10 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
*/
void __delete_from_swap_cache(struct page *page)
{
- swp_entry_t entry;
struct address_space *address_space;
+ int i, nr = hpage_nr_pages(page);
+ swp_entry_t entry;
+ pgoff_t idx;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageSwapCache(page), page);
@@ -155,12 +185,15 @@ void __delete_from_swap_cache(struct page *page)
entry.val = page_private(page);
address_space = swap_address_space(entry);
- radix_tree_delete(&address_space->page_tree, swp_offset(entry));
- set_page_private(page, 0);
+ idx = swp_offset(entry);
+ for (i = 0; i < nr; i++) {
+ radix_tree_delete(&address_space->page_tree, idx + i);
+ set_page_private(page + i, 0);
+ }
ClearPageSwapCache(page);
- address_space->nrpages--;
- __dec_node_page_state(page, NR_FILE_PAGES);
- INC_CACHE_INFO(del_total);
+ address_space->nrpages -= nr;
+ __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
+ ADD_CACHE_INFO(del_total, nr);
}
/**
@@ -170,7 +203,7 @@ void __delete_from_swap_cache(struct page *page)
* Allocate swap space for the page and add the page to the
* swap cache. Caller needs to hold the page lock.
*/
-int add_to_swap(struct page *page, struct list_head *list)
+int add_to_swap(struct page *page)
{
swp_entry_t entry;
int err;
@@ -178,20 +211,12 @@ int add_to_swap(struct page *page, struct list_head *list)
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageUptodate(page), page);
- entry = get_swap_page();
+ entry = get_swap_page(page);
if (!entry.val)
return 0;
- if (mem_cgroup_try_charge_swap(page, entry)) {
- swapcache_free(entry);
- return 0;
- }
-
- if (unlikely(PageTransHuge(page)))
- if (unlikely(split_huge_page_to_list(page, list))) {
- swapcache_free(entry);
- return 0;
- }
+ if (mem_cgroup_try_charge_swap(page, entry))
+ goto fail;
/*
* Radix-tree node allocations from PF_MEMALLOC contexts could
@@ -206,17 +231,30 @@ int add_to_swap(struct page *page, struct list_head *list)
*/
err = add_to_swap_cache(page, entry,
__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
-
- if (!err) {
- return 1;
- } else { /* -ENOMEM radix-tree allocation failure */
+ /* -ENOMEM radix-tree allocation failure */
+ if (err)
/*
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
- swapcache_free(entry);
- return 0;
- }
+ goto fail;
+ /*
+ * Normally the page will be dirtied in unmap because its pte should be
+ * dirty. A special case is MADV_FREE page. The page'e pte could have
+ * dirty bit cleared but the page's SwapBacked bit is still set because
+ * clearing the dirty bit and SwapBacked bit has no lock protected. For
+ * such page, unmap will not set dirty bit for it, so page reclaim will
+ * not write the page out. This can cause data corruption when the page
+ * is swap in later. Always setting the dirty bit for the page solves
+ * the problem.
+ */
+ set_page_dirty(page);
+
+ return 1;
+
+fail:
+ put_swap_page(page, entry);
+ return 0;
}
/*
@@ -237,8 +275,8 @@ void delete_from_swap_cache(struct page *page)
__delete_from_swap_cache(page);
spin_unlock_irq(&address_space->tree_lock);
- swapcache_free(entry);
- put_page(page);
+ put_swap_page(page, entry);
+ page_ref_sub(page, hpage_nr_pages(page));
}
/*
@@ -289,19 +327,36 @@ void free_pages_and_swap_cache(struct page **pages, int nr)
* lock getting page table operations atomic even if we drop the page
* lock before returning.
*/
-struct page * lookup_swap_cache(swp_entry_t entry)
+struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma,
+ unsigned long addr)
{
struct page *page;
+ unsigned long ra_info;
+ int win, hits, readahead;
page = find_get_page(swap_address_space(entry), swp_offset(entry));
+ INC_CACHE_INFO(find_total);
if (page) {
INC_CACHE_INFO(find_success);
- if (TestClearPageReadahead(page))
- atomic_inc(&swapin_readahead_hits);
+ if (unlikely(PageTransCompound(page)))
+ return page;
+ readahead = TestClearPageReadahead(page);
+ if (vma) {
+ ra_info = GET_SWAP_RA_VAL(vma);
+ win = SWAP_RA_WIN(ra_info);
+ hits = SWAP_RA_HITS(ra_info);
+ 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)
+ atomic_inc(&swapin_readahead_hits);
+ }
}
-
- INC_CACHE_INFO(find_total);
return page;
}
@@ -389,7 +444,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
- swapcache_free(entry);
+ put_swap_page(new_page, entry);
} while (err != -ENOMEM);
if (new_page)
@@ -404,34 +459,32 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
* the swap entry is no longer in use.
*/
struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
- struct vm_area_struct *vma, unsigned long addr)
+ struct vm_area_struct *vma, unsigned long addr, bool do_poll)
{
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);
+ swap_readpage(retpage, do_poll);
return retpage;
}
-static unsigned long swapin_nr_pages(unsigned long offset)
+static unsigned int __swapin_nr_pages(unsigned long prev_offset,
+ unsigned long offset,
+ int hits,
+ int max_pages,
+ int prev_win)
{
- static unsigned long prev_offset;
- unsigned int pages, max_pages, last_ra;
- static atomic_t last_readahead_pages;
-
- max_pages = 1 << READ_ONCE(page_cluster);
- if (max_pages <= 1)
- return 1;
+ unsigned int pages, last_ra;
/*
* This heuristic has been found to work well on both sequential and
* random loads, swapping to hard disk or to SSD: please don't ask
* what the "+ 2" means, it just happens to work well, that's all.
*/
- pages = atomic_xchg(&swapin_readahead_hits, 0) + 2;
+ pages = hits + 2;
if (pages == 2) {
/*
* We can have no readahead hits to judge by: but must not get
@@ -440,7 +493,6 @@ static unsigned long swapin_nr_pages(unsigned long offset)
*/
if (offset != prev_offset + 1 && offset != prev_offset - 1)
pages = 1;
- prev_offset = offset;
} else {
unsigned int roundup = 4;
while (roundup < pages)
@@ -452,9 +504,28 @@ static unsigned long swapin_nr_pages(unsigned long offset)
pages = max_pages;
/* Don't shrink readahead too fast */
- last_ra = atomic_read(&last_readahead_pages) / 2;
+ 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(prev_offset, offset, hits, max_pages,
+ atomic_read(&last_readahead_pages));
+ if (!hits)
+ prev_offset = offset;
atomic_set(&last_readahead_pages, pages);
return pages;
@@ -488,11 +559,13 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
unsigned long start_offset, end_offset;
unsigned long mask;
struct blk_plug plug;
+ bool do_poll = true, page_allocated;
mask = swapin_nr_pages(offset) - 1;
if (!mask)
goto skip;
+ do_poll = false;
/* Read a page_cluster sized and aligned cluster around offset. */
start_offset = offset & ~mask;
end_offset = offset | mask;
@@ -502,19 +575,26 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
blk_start_plug(&plug);
for (offset = start_offset; offset <= end_offset ; offset++) {
/* Ok, do the async read-ahead now */
- page = read_swap_cache_async(swp_entry(swp_type(entry), offset),
- gfp_mask, vma, addr);
+ page = __read_swap_cache_async(
+ swp_entry(swp_type(entry), offset),
+ gfp_mask, vma, addr, &page_allocated);
if (!page)
continue;
- if (offset != entry_offset)
- SetPageReadahead(page);
+ if (page_allocated) {
+ swap_readpage(page, false);
+ if (offset != entry_offset &&
+ likely(!PageTransCompound(page))) {
+ SetPageReadahead(page);
+ count_vm_event(SWAP_RA);
+ }
+ }
put_page(page);
}
blk_finish_plug(&plug);
lru_add_drain(); /* Push any new pages onto the LRU now */
skip:
- return read_swap_cache_async(entry, gfp_mask, vma, addr);
+ return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll);
}
int init_swap_address_space(unsigned int type, unsigned long nr_pages)
@@ -551,3 +631,187 @@ void exit_swap_address_space(unsigned int type)
synchronize_rcu();
kvfree(spaces);
}
+
+static inline void swap_ra_clamp_pfn(struct vm_area_struct *vma,
+ unsigned long faddr,
+ unsigned long lpfn,
+ unsigned long rpfn,
+ unsigned long *start,
+ unsigned long *end)
+{
+ *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));
+}
+
+struct page *swap_readahead_detect(struct vm_fault *vmf,
+ struct vma_swap_readahead *swap_ra)
+{
+ struct vm_area_struct *vma = vmf->vma;
+ unsigned long swap_ra_info;
+ struct page *page;
+ swp_entry_t entry;
+ unsigned long faddr, pfn, fpfn;
+ unsigned long start, end;
+ pte_t *pte;
+ unsigned int max_win, hits, prev_win, win, left;
+#ifndef CONFIG_64BIT
+ pte_t *tpte;
+#endif
+
+ max_win = 1 << min_t(unsigned int, READ_ONCE(page_cluster),
+ SWAP_RA_ORDER_CEILING);
+ if (max_win == 1) {
+ swap_ra->win = 1;
+ return NULL;
+ }
+
+ faddr = vmf->address;
+ entry = pte_to_swp_entry(vmf->orig_pte);
+ if ((unlikely(non_swap_entry(entry))))
+ return NULL;
+ page = lookup_swap_cache(entry, vma, faddr);
+ if (page)
+ return page;
+
+ fpfn = PFN_DOWN(faddr);
+ swap_ra_info = GET_SWAP_RA_VAL(vma);
+ pfn = PFN_DOWN(SWAP_RA_ADDR(swap_ra_info));
+ prev_win = SWAP_RA_WIN(swap_ra_info);
+ hits = SWAP_RA_HITS(swap_ra_info);
+ swap_ra->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 NULL;
+
+ /* Copy the PTEs because the page table may be unmapped */
+ if (fpfn == pfn + 1)
+ swap_ra_clamp_pfn(vma, faddr, fpfn, fpfn + win, &start, &end);
+ else if (pfn == fpfn + 1)
+ swap_ra_clamp_pfn(vma, faddr, fpfn - win + 1, fpfn + 1,
+ &start, &end);
+ else {
+ left = (win - 1) / 2;
+ swap_ra_clamp_pfn(vma, faddr, fpfn - left, fpfn + win - left,
+ &start, &end);
+ }
+ swap_ra->nr_pte = end - start;
+ swap_ra->offset = fpfn - start;
+ pte = vmf->pte - swap_ra->offset;
+#ifdef CONFIG_64BIT
+ swap_ra->ptes = pte;
+#else
+ tpte = swap_ra->ptes;
+ for (pfn = start; pfn != end; pfn++)
+ *tpte++ = *pte++;
+#endif
+
+ return NULL;
+}
+
+struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask,
+ struct vm_fault *vmf,
+ struct vma_swap_readahead *swap_ra)
+{
+ struct blk_plug plug;
+ struct vm_area_struct *vma = vmf->vma;
+ struct page *page;
+ pte_t *pte, pentry;
+ swp_entry_t entry;
+ unsigned int i;
+ bool page_allocated;
+
+ if (swap_ra->win == 1)
+ goto skip;
+
+ blk_start_plug(&plug);
+ for (i = 0, pte = swap_ra->ptes; i < swap_ra->nr_pte;
+ i++, pte++) {
+ pentry = *pte;
+ if (pte_none(pentry))
+ continue;
+ if (pte_present(pentry))
+ continue;
+ entry = pte_to_swp_entry(pentry);
+ if (unlikely(non_swap_entry(entry)))
+ continue;
+ page = __read_swap_cache_async(entry, gfp_mask, vma,
+ vmf->address, &page_allocated);
+ if (!page)
+ continue;
+ if (page_allocated) {
+ swap_readpage(page, false);
+ if (i != swap_ra->offset &&
+ likely(!PageTransCompound(page))) {
+ SetPageReadahead(page);
+ count_vm_event(SWAP_RA);
+ }
+ }
+ put_page(page);
+ }
+ blk_finish_plug(&plug);
+ lru_add_drain();
+skip:
+ return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address,
+ swap_ra->win == 1);
+}
+
+#ifdef CONFIG_SYSFS
+static ssize_t vma_ra_enabled_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%s\n", swap_vma_readahead ? "true" : "false");
+}
+static ssize_t vma_ra_enabled_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1))
+ swap_vma_readahead = true;
+ else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1))
+ swap_vma_readahead = false;
+ else
+ return -EINVAL;
+
+ return count;
+}
+static struct kobj_attribute vma_ra_enabled_attr =
+ __ATTR(vma_ra_enabled, 0644, vma_ra_enabled_show,
+ vma_ra_enabled_store);
+
+static struct attribute *swap_attrs[] = {
+ &vma_ra_enabled_attr.attr,
+ NULL,
+};
+
+static 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
generated by cgit v1.2.3 (git 2.46.0) at 2025-09-06 07:39:07 +0000