From ea08eeccae9297f7aabd2ef7f0c2517ac4549acc Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:18:26 +0000
Subject: [PATCH] write in 30M

---
 kernel/mm/swap_state.c |  392 +++++++++++++++++++++++++++++++++++--------------------
 1 files changed, 247 insertions(+), 145 deletions(-)

diff --git a/kernel/mm/swap_state.c b/kernel/mm/swap_state.c
index b99e8fd..a8a98bf 100644
--- a/kernel/mm/swap_state.c
+++ b/kernel/mm/swap_state.c
@@ -21,8 +21,7 @@
 #include <linux/vmalloc.h>
 #include <linux/swap_slots.h>
 #include <linux/huge_mm.h>
-
-#include <asm/pgtable.h>
+#include <linux/shmem_fs.h>
 #include "internal.h"
 
 /*
@@ -59,8 +58,8 @@
 #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)
+#define INC_CACHE_INFO(x)	data_race(swap_cache_info.x++)
+#define ADD_CACHE_INFO(x, nr)	data_race(swap_cache_info.x += (nr))
 
 static struct {
 	unsigned long add_total;
@@ -74,25 +73,27 @@
 	unsigned int i, j, nr;
 	unsigned long ret = 0;
 	struct address_space *spaces;
+	struct swap_info_struct *si;
 
-	rcu_read_lock();
 	for (i = 0; i < MAX_SWAPFILES; i++) {
-		/*
-		 * The corresponding entries in nr_swapper_spaces and
-		 * swapper_spaces will be reused only after at least
-		 * one grace period.  So it is impossible for them
-		 * belongs to different usage.
-		 */
-		nr = nr_swapper_spaces[i];
-		spaces = rcu_dereference(swapper_spaces[i]);
-		if (!nr || !spaces)
+		swp_entry_t entry = swp_entry(i, 1);
+
+		/* Avoid get_swap_device() to warn for bad swap entry */
+		if (!swp_swap_info(entry))
 			continue;
+		/* Prevent swapoff to free swapper_spaces */
+		si = get_swap_device(entry);
+		if (!si)
+			continue;
+		nr = nr_swapper_spaces[i];
+		spaces = swapper_spaces[i];
 		for (j = 0; j < nr; j++)
 			ret += spaces[j].nrpages;
+		put_swap_device(si);
 	}
-	rcu_read_unlock();
 	return ret;
 }
+EXPORT_SYMBOL_GPL(total_swapcache_pages);
 
 static atomic_t swapin_readahead_hits = ATOMIC_INIT(4);
 
@@ -107,15 +108,32 @@
 	printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10));
 }
 
+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 = find_get_entry(address_space, idx);
+	if (xa_is_value(page))
+		return page;
+	if (page)
+		put_page(page);
+	return NULL;
+}
+
 /*
- * __add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
+ * add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
  * but sets SwapCache flag and private instead of mapping and index.
  */
-int __add_to_swap_cache(struct page *page, swp_entry_t entry)
+int add_to_swap_cache(struct page *page, swp_entry_t entry,
+			gfp_t gfp, void **shadowp)
 {
-	int error, i, nr = hpage_nr_pages(page);
-	struct address_space *address_space;
+	struct address_space *address_space = swap_address_space(entry);
 	pgoff_t idx = swp_offset(entry);
+	XA_STATE_ORDER(xas, &address_space->i_pages, idx, compound_order(page));
+	unsigned long i, nr = thp_nr_pages(page);
+	void *old;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageSwapCache(page), page);
@@ -124,75 +142,66 @@
 	page_ref_add(page, nr);
 	SetPageSwapCache(page);
 
-	address_space = swap_address_space(entry);
-	xa_lock_irq(&address_space->i_pages);
-	for (i = 0; i < nr; i++) {
-		set_page_private(page + i, entry.val + i);
-		error = radix_tree_insert(&address_space->i_pages,
-					  idx + i, page + i);
-		if (unlikely(error))
-			break;
-	}
-	if (likely(!error)) {
+	do {
+		unsigned long nr_shadows = 0;
+
+		xas_lock_irq(&xas);
+		xas_create_range(&xas);
+		if (xas_error(&xas))
+			goto unlock;
+		for (i = 0; i < nr; i++) {
+			VM_BUG_ON_PAGE(xas.xa_index != idx + i, page);
+			old = xas_load(&xas);
+			if (xa_is_value(old)) {
+				nr_shadows++;
+				if (shadowp)
+					*shadowp = old;
+			}
+			set_page_private(page + i, entry.val + i);
+			xas_store(&xas, page);
+			xas_next(&xas);
+		}
+		address_space->nrexceptional -= nr_shadows;
 		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 + i, 0UL);
-		while (i--) {
-			radix_tree_delete(&address_space->i_pages, idx + i);
-			set_page_private(page + i, 0UL);
-		}
-		ClearPageSwapCache(page);
-		page_ref_sub(page, nr);
-	}
-	xa_unlock_irq(&address_space->i_pages);
+unlock:
+		xas_unlock_irq(&xas);
+	} while (xas_nomem(&xas, gfp));
 
-	return error;
-}
+	if (!xas_error(&xas))
+		return 0;
 
-
-int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
-{
-	int error;
-
-	error = radix_tree_maybe_preload_order(gfp_mask, compound_order(page));
-	if (!error) {
-		error = __add_to_swap_cache(page, entry);
-		radix_tree_preload_end();
-	}
-	return error;
+	ClearPageSwapCache(page);
+	page_ref_sub(page, nr);
+	return xas_error(&xas);
 }
 
 /*
  * This must be called only on pages that have
  * been verified to be in the swap cache.
  */
-void __delete_from_swap_cache(struct page *page)
+void __delete_from_swap_cache(struct page *page,
+			swp_entry_t entry, void *shadow)
 {
-	struct address_space *address_space;
-	int i, nr = hpage_nr_pages(page);
-	swp_entry_t entry;
-	pgoff_t idx;
+	struct address_space *address_space = swap_address_space(entry);
+	int i, nr = thp_nr_pages(page);
+	pgoff_t idx = swp_offset(entry);
+	XA_STATE(xas, &address_space->i_pages, idx);
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(!PageSwapCache(page), page);
 	VM_BUG_ON_PAGE(PageWriteback(page), page);
 
-	entry.val = page_private(page);
-	address_space = swap_address_space(entry);
-	idx = swp_offset(entry);
 	for (i = 0; i < nr; i++) {
-		radix_tree_delete(&address_space->i_pages, idx + i);
+		void *entry = xas_store(&xas, shadow);
+		VM_BUG_ON_PAGE(entry != page, entry);
 		set_page_private(page + i, 0);
+		xas_next(&xas);
 	}
 	ClearPageSwapCache(page);
+	if (shadow)
+		address_space->nrexceptional += nr;
 	address_space->nrpages -= nr;
 	__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
 	ADD_CACHE_INFO(del_total, nr);
@@ -218,7 +227,7 @@
 		return 0;
 
 	/*
-	 * Radix-tree node allocations from PF_MEMALLOC contexts could
+	 * XArray node allocations from PF_MEMALLOC contexts could
 	 * completely exhaust the page allocator. __GFP_NOMEMALLOC
 	 * stops emergency reserves from being allocated.
 	 *
@@ -229,8 +238,7 @@
 	 * Add it to the swap cache.
 	 */
 	err = add_to_swap_cache(page, entry,
-			__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
-	/* -ENOMEM radix-tree allocation failure */
+			__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN, NULL);
 	if (err)
 		/*
 		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
@@ -239,7 +247,7 @@
 		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. A special case is MADV_FREE page. The page's 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
@@ -264,18 +272,46 @@
  */
 void delete_from_swap_cache(struct page *page)
 {
-	swp_entry_t entry;
-	struct address_space *address_space;
+	swp_entry_t entry = { .val = page_private(page) };
+	struct address_space *address_space = swap_address_space(entry);
 
-	entry.val = page_private(page);
-
-	address_space = swap_address_space(entry);
 	xa_lock_irq(&address_space->i_pages);
-	__delete_from_swap_cache(page);
+	__delete_from_swap_cache(page, entry, NULL);
 	xa_unlock_irq(&address_space->i_pages);
 
 	put_swap_page(page, entry);
-	page_ref_sub(page, hpage_nr_pages(page));
+	page_ref_sub(page, thp_nr_pages(page));
+}
+
+void clear_shadow_from_swap_cache(int type, unsigned long begin,
+				unsigned long end)
+{
+	unsigned long curr = begin;
+	void *old;
+
+	for (;;) {
+		unsigned long nr_shadows = 0;
+		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);
+
+		xa_lock_irq(&address_space->i_pages);
+		xas_for_each(&xas, old, end) {
+			if (!xa_is_value(old))
+				continue;
+			xas_store(&xas, NULL);
+			nr_shadows++;
+		}
+		address_space->nrexceptional -= nr_shadows;
+		xa_unlock_irq(&address_space->i_pages);
+
+		/* search the next swapcache until we meet end */
+		curr >>= SWAP_ADDRESS_SPACE_SHIFT;
+		curr++;
+		curr <<= SWAP_ADDRESS_SPACE_SHIFT;
+		if (curr > end)
+			break;
+	}
 }
 
 /* 
@@ -335,8 +371,13 @@
 			       unsigned long addr)
 {
 	struct page *page;
+	struct swap_info_struct *si;
 
+	si = get_swap_device(entry);
+	if (!si)
+		return NULL;
 	page = find_get_page(swap_address_space(entry), swp_offset(entry));
+	put_swap_device(si);
 
 	INC_CACHE_INFO(find_total);
 	if (page) {
@@ -375,24 +416,64 @@
 	return page;
 }
 
+/**
+ * find_get_incore_page - Find and get a page from the page or swap caches.
+ * @mapping: The address_space to search.
+ * @index: The page cache index.
+ *
+ * This differs from find_get_page() in that it will also look for the
+ * page in the swap cache.
+ *
+ * Return: The found page or %NULL.
+ */
+struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index)
+{
+	swp_entry_t swp;
+	struct swap_info_struct *si;
+	struct page *page = find_get_entry(mapping, index);
+
+	if (!page)
+		return page;
+	if (!xa_is_value(page))
+		return find_subpage(page, index);
+	if (!shmem_mapping(mapping))
+		return NULL;
+
+	swp = radix_to_swp_entry(page);
+	/* Prevent swapoff from happening to us */
+	si = get_swap_device(swp);
+	if (!si)
+		return NULL;
+	page = find_get_page(swap_address_space(swp), swp_offset(swp));
+	put_swap_device(si);
+	return page;
+}
+
 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 page *found_page, *new_page = NULL;
-	struct address_space *swapper_space = swap_address_space(entry);
-	int err;
+	struct swap_info_struct *si;
+	struct page *page;
+	void *shadow = NULL;
+
 	*new_page_allocated = false;
 
-	do {
+	for (;;) {
+		int err;
 		/*
 		 * First check the swap cache.  Since this is normally
 		 * called after lookup_swap_cache() failed, re-calling
 		 * that would confuse statistics.
 		 */
-		found_page = find_get_page(swapper_space, swp_offset(entry));
-		if (found_page)
-			break;
+		si = get_swap_device(entry);
+		if (!si)
+			return NULL;
+		page = find_get_page(swap_address_space(entry),
+				     swp_offset(entry));
+		put_swap_device(si);
+		if (page)
+			return page;
 
 		/*
 		 * Just skip read ahead for unused swap slot.
@@ -403,69 +484,69 @@
 		 * else swap_off will be aborted if we return NULL.
 		 */
 		if (!__swp_swapcount(entry) && swap_slot_cache_enabled)
-			break;
+			return NULL;
 
 		/*
-		 * Get a new page to read into from swap.
+		 * Get a new page to read into from swap.  Allocate it now,
+		 * before marking swap_map SWAP_HAS_CACHE, when -EEXIST will
+		 * cause any racers to loop around until we add it to cache.
 		 */
-		if (!new_page) {
-			new_page = alloc_page_vma(gfp_mask, vma, addr);
-			if (!new_page)
-				break;		/* Out of memory */
-		}
-
-		/*
-		 * call radix_tree_preload() while we can wait.
-		 */
-		err = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK);
-		if (err)
-			break;
+		page = alloc_page_vma(gfp_mask, vma, addr);
+		if (!page)
+			return NULL;
 
 		/*
 		 * Swap entry may have been freed since our caller observed it.
 		 */
 		err = swapcache_prepare(entry);
-		if (err == -EEXIST) {
-			radix_tree_preload_end();
-			/*
-			 * We might race against get_swap_page() and stumble
-			 * across a SWAP_HAS_CACHE swap_map entry whose page
-			 * has not been brought into the swapcache yet.
-			 */
-			cond_resched();
-			continue;
-		}
-		if (err) {		/* swp entry is obsolete ? */
-			radix_tree_preload_end();
+		if (!err)
 			break;
-		}
 
-		/* May fail (-ENOMEM) if radix-tree node allocation failed. */
-		__SetPageLocked(new_page);
-		__SetPageSwapBacked(new_page);
-		err = __add_to_swap_cache(new_page, entry);
-		if (likely(!err)) {
-			radix_tree_preload_end();
-			/*
-			 * Initiate read into locked page and return.
-			 */
-			SetPageWorkingset(new_page);
-			lru_cache_add_anon(new_page);
-			*new_page_allocated = true;
-			return new_page;
-		}
-		radix_tree_preload_end();
-		__ClearPageLocked(new_page);
+		put_page(page);
+		if (err != -EEXIST)
+			return NULL;
+
 		/*
-		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
-		 * clear SWAP_HAS_CACHE flag.
+		 * We might race against __delete_from_swap_cache(), and
+		 * stumble across a swap_map entry whose SWAP_HAS_CACHE
+		 * has not yet been cleared.  Or race against another
+		 * __read_swap_cache_async(), which has set SWAP_HAS_CACHE
+		 * in swap_map, but not yet added its page to swap cache.
 		 */
-		put_swap_page(new_page, entry);
-	} while (err != -ENOMEM);
+		schedule_timeout_uninterruptible(1);
+	}
 
-	if (new_page)
-		put_page(new_page);
-	return found_page;
+	/*
+	 * The swap entry is ours to swap in. Prepare the new page.
+	 */
+
+	__SetPageLocked(page);
+	__SetPageSwapBacked(page);
+
+	/* May fail (-ENOMEM) if XArray node allocation failed. */
+	if (add_to_swap_cache(page, entry, gfp_mask & GFP_RECLAIM_MASK, &shadow)) {
+		put_swap_page(page, entry);
+		goto fail_unlock;
+	}
+
+	if (mem_cgroup_charge(page, NULL, gfp_mask)) {
+		delete_from_swap_cache(page);
+		goto fail_unlock;
+	}
+
+	if (shadow)
+		workingset_refault(page, shadow);
+
+	/* Caller will initiate read into locked page */
+	SetPageWorkingset(page);
+	lru_cache_add(page);
+	*new_page_allocated = true;
+	return page;
+
+fail_unlock:
+	unlock_page(page);
+	put_page(page);
+	return NULL;
 }
 
 /*
@@ -565,6 +646,10 @@
  * the readahead.
  *
  * Caller must hold down_read on the vma->vm_mm if vmf->vma is not NULL.
+ * This is needed to ensure the VMA will not be freed in our back. In the case
+ * of the speculative page fault handler, this cannot happen, even if we don't
+ * hold the mmap_sem. Callees are assumed to take care of reading VMA's fields
+ * using READ_ONCE() to read consistent values.
  */
 struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 				struct vm_fault *vmf)
@@ -583,6 +668,13 @@
 	mask = swapin_nr_pages(offset) - 1;
 	if (!mask)
 		goto skip;
+
+	/* Test swap type to make sure the dereference is safe */
+	if (likely(si->flags & (SWP_BLKDEV | SWP_FS_OPS))) {
+		struct inode *inode = si->swap_file->f_mapping->host;
+		if (inode_read_congested(inode))
+			goto skip;
+	}
 
 	do_poll = false;
 	/* Read a page_cluster sized and aligned cluster around offset. */
@@ -628,27 +720,23 @@
 		return -ENOMEM;
 	for (i = 0; i < nr; i++) {
 		space = spaces + i;
-		INIT_RADIX_TREE(&space->i_pages, GFP_ATOMIC|__GFP_NOWARN);
+		xa_init_flags(&space->i_pages, XA_FLAGS_LOCK_IRQ);
 		atomic_set(&space->i_mmap_writable, 0);
 		space->a_ops = &swap_aops;
 		/* swap cache doesn't use writeback related tags */
 		mapping_set_no_writeback_tags(space);
 	}
 	nr_swapper_spaces[type] = nr;
-	rcu_assign_pointer(swapper_spaces[type], spaces);
+	swapper_spaces[type] = spaces;
 
 	return 0;
 }
 
 void exit_swap_address_space(unsigned int type)
 {
-	struct address_space *spaces;
-
-	spaces = swapper_spaces[type];
+	kvfree(swapper_spaces[type]);
 	nr_swapper_spaces[type] = 0;
-	rcu_assign_pointer(swapper_spaces[type], NULL);
-	synchronize_rcu();
-	kvfree(spaces);
+	swapper_spaces[type] = NULL;
 }
 
 static inline void swap_ra_clamp_pfn(struct vm_area_struct *vma,
@@ -658,9 +746,9 @@
 				     unsigned long *start,
 				     unsigned long *end)
 {
-	*start = max3(lpfn, PFN_DOWN(vma->vm_start),
+	*start = max3(lpfn, PFN_DOWN(READ_ONCE(vma->vm_start)),
 		      PFN_DOWN(faddr & PMD_MASK));
-	*end = min3(rpfn, PFN_DOWN(vma->vm_end),
+	*end = min3(rpfn, PFN_DOWN(READ_ONCE(vma->vm_end)),
 		    PFN_DOWN((faddr & PMD_MASK) + PMD_SIZE));
 }
 
@@ -732,6 +820,20 @@
 	pte_unmap(orig_pte);
 }
 
+/**
+ * swap_vma_readahead - swap in pages in hope we need them soon
+ * @fentry: swap entry of this memory
+ * @gfp_mask: memory allocation flags
+ * @vmf: fault information
+ *
+ * Returns the struct page for entry and addr, after queueing swapin.
+ *
+ * Primitive swap readahead code. We simply read in a few pages whoes
+ * virtual addresses are around the fault address in the same vma.
+ *
+ * Caller must hold read mmap_lock if vmf->vma is not NULL.
+ *
+ */
 static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
 				       struct vm_fault *vmf)
 {

--
Gitblit v1.6.2