Merging upstream version 6.1.82.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

12 files changed, 123 insertions, 18 deletions

diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c
index 63bdad20d..98a678129 100644
--- a/mm/damon/lru_sort.c
+++ b/mm/damon/lru_sort.c
@@ -185,9 +185,21 @@ static struct damos *damon_lru_sort_new_cold_scheme(unsigned int cold_thres)
 	return damon_lru_sort_new_scheme(&pattern, DAMOS_LRU_DEPRIO);
 }
 
+static void damon_lru_sort_copy_quota_status(struct damos_quota *dst,
+		struct damos_quota *src)
+{
+	dst->total_charged_sz = src->total_charged_sz;
+	dst->total_charged_ns = src->total_charged_ns;
+	dst->charged_sz = src->charged_sz;
+	dst->charged_from = src->charged_from;
+	dst->charge_target_from = src->charge_target_from;
+	dst->charge_addr_from = src->charge_addr_from;
+}
+
 static int damon_lru_sort_apply_parameters(void)
 {
-	struct damos *scheme;
+	struct damos *scheme, *hot_scheme, *cold_scheme;
+	struct damos *old_hot_scheme = NULL, *old_cold_scheme = NULL;
 	unsigned int hot_thres, cold_thres;
 	int err = 0;
 
@@ -195,18 +207,35 @@ static int damon_lru_sort_apply_parameters(void)
 	if (err)
 		return err;
 
+	damon_for_each_scheme(scheme, ctx) {
+		if (!old_hot_scheme) {
+			old_hot_scheme = scheme;
+			continue;
+		}
+		old_cold_scheme = scheme;
+	}
+
 	hot_thres = damon_max_nr_accesses(&damon_lru_sort_mon_attrs) *
 		hot_thres_access_freq / 1000;
-	scheme = damon_lru_sort_new_hot_scheme(hot_thres);
-	if (!scheme)
+	hot_scheme = damon_lru_sort_new_hot_scheme(hot_thres);
+	if (!hot_scheme)
 		return -ENOMEM;
-	damon_set_schemes(ctx, &scheme, 1);
+	if (old_hot_scheme)
+		damon_lru_sort_copy_quota_status(&hot_scheme->quota,
+				&old_hot_scheme->quota);
 
 	cold_thres = cold_min_age / damon_lru_sort_mon_attrs.aggr_interval;
-	scheme = damon_lru_sort_new_cold_scheme(cold_thres);
-	if (!scheme)
+	cold_scheme = damon_lru_sort_new_cold_scheme(cold_thres);
+	if (!cold_scheme) {
+		damon_destroy_scheme(hot_scheme);
 		return -ENOMEM;
-	damon_add_scheme(ctx, scheme);
+	}
+	if (old_cold_scheme)
+		damon_lru_sort_copy_quota_status(&cold_scheme->quota,
+				&old_cold_scheme->quota);
+
+	damon_set_schemes(ctx, &hot_scheme, 1);
+	damon_add_scheme(ctx, cold_scheme);
 
 	return damon_set_region_biggest_system_ram_default(target,
 					&monitor_region_start,
diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c
index 162c9b1ca..cc337e94a 100644
--- a/mm/damon/reclaim.c
+++ b/mm/damon/reclaim.c
@@ -141,9 +141,20 @@ static struct damos *damon_reclaim_new_scheme(void)
 			&damon_reclaim_wmarks);
 }
 
+static void damon_reclaim_copy_quota_status(struct damos_quota *dst,
+		struct damos_quota *src)
+{
+	dst->total_charged_sz = src->total_charged_sz;
+	dst->total_charged_ns = src->total_charged_ns;
+	dst->charged_sz = src->charged_sz;
+	dst->charged_from = src->charged_from;
+	dst->charge_target_from = src->charge_target_from;
+	dst->charge_addr_from = src->charge_addr_from;
+}
+
 static int damon_reclaim_apply_parameters(void)
 {
-	struct damos *scheme;
+	struct damos *scheme, *old_scheme;
 	int err = 0;
 
 	err = damon_set_attrs(ctx, &damon_reclaim_mon_attrs);
@@ -154,6 +165,11 @@ static int damon_reclaim_apply_parameters(void)
 	scheme = damon_reclaim_new_scheme();
 	if (!scheme)
 		return -ENOMEM;
+	if (!list_empty(&ctx->schemes)) {
+		damon_for_each_scheme(old_scheme, ctx)
+			damon_reclaim_copy_quota_status(&scheme->quota,
+					&old_scheme->quota);
+	}
 	damon_set_schemes(ctx, &scheme, 1);
 
 	return damon_set_region_biggest_system_ram_default(target,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 595779467..9736e7621 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -37,6 +37,7 @@
 #include <linux/page_owner.h>
 #include <linux/sched/sysctl.h>
 #include <linux/memory-tiers.h>
+#include <linux/compat.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -607,6 +608,9 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
 	loff_t off_align = round_up(off, size);
 	unsigned long len_pad, ret;
 
+	if (IS_ENABLED(CONFIG_32BIT) || in_compat_syscall())
+		return 0;
+
 	if (off_end <= off_align || (off_end - off_align) < size)
 		return 0;
 
diff --git a/mm/memblock.c b/mm/memblock.c
index 511d4783d..516efec80 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -175,8 +175,9 @@ static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size)
 /*
  * Address comparison utilities
  */
-static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
-				       phys_addr_t base2, phys_addr_t size2)
+unsigned long __init_memblock
+memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, phys_addr_t base2,
+		       phys_addr_t size2)
 {
 	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9da98e3e7..4570d3e31 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -7517,9 +7517,13 @@ bool mem_cgroup_swap_full(struct folio *folio)
 
 static int __init setup_swap_account(char *s)
 {
-	pr_warn_once("The swapaccount= commandline option is deprecated. "
-		     "Please report your usecase to linux-mm@kvack.org if you "
-		     "depend on this functionality.\n");
+	bool res;
+
+	if (!kstrtobool(s, &res) && !res)
+		pr_warn_once("The swapaccount=0 commandline option is deprecated "
+			     "in favor of configuring swap control via cgroupfs. "
+			     "Please report your usecase to linux-mm@kvack.org if you "
+			     "depend on this functionality.\n");
 	return 1;
 }
 __setup("swapaccount=", setup_swap_account);
diff --git a/mm/memory.c b/mm/memory.c
index fc8b264ec..fb83cf563 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3761,6 +3761,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	struct page *page;
 	struct swap_info_struct *si = NULL;
 	rmap_t rmap_flags = RMAP_NONE;
+	bool need_clear_cache = false;
 	bool exclusive = false;
 	swp_entry_t entry;
 	pte_t pte;
@@ -3822,6 +3823,20 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	if (!folio) {
 		if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
 		    __swap_count(entry) == 1) {
+			/*
+			 * Prevent parallel swapin from proceeding with
+			 * the cache flag. Otherwise, another thread may
+			 * finish swapin first, free the entry, and swapout
+			 * reusing the same entry. It's undetectable as
+			 * pte_same() returns true due to entry reuse.
+			 */
+			if (swapcache_prepare(entry)) {
+				/* Relax a bit to prevent rapid repeated page faults */
+				schedule_timeout_uninterruptible(1);
+				goto out;
+			}
+			need_clear_cache = true;
+
 			/* skip swapcache */
 			folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0,
 						vma, vmf->address, false);
@@ -4073,6 +4088,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 unlock:
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 out:
+	/* Clear the swap cache pin for direct swapin after PTL unlock */
+	if (need_clear_cache)
+		swapcache_clear(si, entry);
 	if (si)
 		put_swap_device(si);
 	return ret;
@@ -4086,6 +4104,8 @@ out_release:
 		folio_unlock(swapcache);
 		folio_put(swapcache);
 	}
+	if (need_clear_cache)
+		swapcache_clear(si, entry);
 	if (si)
 		put_swap_device(si);
 	return ret;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index de5f69921..d3e9d1286 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1526,7 +1526,7 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc)
 	 */
 	dtc->wb_thresh = __wb_calc_thresh(dtc);
 	dtc->wb_bg_thresh = dtc->thresh ?
-		div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
+		div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
 
 	/*
 	 * In order to avoid the stacked BDI deadlock we need
diff --git a/mm/readahead.c b/mm/readahead.c
index ba4342804..e4b772bb7 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -483,7 +483,7 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index,
 
 	if (!folio)
 		return -ENOMEM;
-	mark = round_up(mark, 1UL << order);
+	mark = round_down(mark, 1UL << order);
 	if (index == mark)
 		folio_set_readahead(folio);
 	err = filemap_add_folio(ractl->mapping, folio, index, gfp);
@@ -591,7 +591,7 @@ static void ondemand_readahead(struct readahead_control *ractl,
 	 * It's the expected callback index, assume sequential access.
 	 * Ramp up sizes, and push forward the readahead window.
 	 */
-	expected = round_up(ra->start + ra->size - ra->async_size,
+	expected = round_down(ra->start + ra->size - ra->async_size,
 			1UL << order);
 	if (index == expected || index == (ra->start + ra->size)) {
 		ra->start += ra->size;
diff --git a/mm/swap.h b/mm/swap.h
index cc08c459c..5eff40ef7 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -39,6 +39,7 @@ void __delete_from_swap_cache(struct folio *folio,
 void delete_from_swap_cache(struct folio *folio);
 void clear_shadow_from_swap_cache(int type, unsigned long begin,
 				  unsigned long end);
+void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry);
 struct folio *swap_cache_get_folio(swp_entry_t entry,
 		struct vm_area_struct *vma, unsigned long addr);
 struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index);
@@ -98,6 +99,10 @@ static inline int swap_writepage(struct page *p, struct writeback_control *wbc)
 	return 0;
 }
 
+static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry)
+{
+}
+
 static inline struct folio *swap_cache_get_folio(swp_entry_t entry,
 		struct vm_area_struct *vma, unsigned long addr)
 {
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 71db6d8a1..cca9fda9d 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3373,6 +3373,19 @@ int swapcache_prepare(swp_entry_t entry)
 	return __swap_duplicate(entry, SWAP_HAS_CACHE);
 }
 
+void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry)
+{
+	struct swap_cluster_info *ci;
+	unsigned long offset = swp_offset(entry);
+	unsigned char usage;
+
+	ci = lock_cluster_or_swap_info(si, offset);
+	usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE);
+	unlock_cluster_or_swap_info(si, ci);
+	if (!usage)
+		free_swap_slot(entry);
+}
+
 struct swap_info_struct *swp_swap_info(swp_entry_t entry)
 {
 	return swap_type_to_swap_info(swp_type(entry));
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 650ab6cfd..992a0a168 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -327,6 +327,7 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
 					      unsigned long dst_start,
 					      unsigned long src_start,
 					      unsigned long len,
+					      atomic_t *mmap_changing,
 					      enum mcopy_atomic_mode mode,
 					      bool wp_copy)
 {
@@ -445,6 +446,15 @@ retry:
 				goto out;
 			}
 			mmap_read_lock(dst_mm);
+			/*
+			 * If memory mappings are changing because of non-cooperative
+			 * operation (e.g. mremap) running in parallel, bail out and
+			 * request the user to retry later
+			 */
+			if (mmap_changing && atomic_read(mmap_changing)) {
+				err = -EAGAIN;
+				break;
+			}
 
 			dst_vma = NULL;
 			goto retry;
@@ -480,6 +490,7 @@ extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
 				      unsigned long dst_start,
 				      unsigned long src_start,
 				      unsigned long len,
+				      atomic_t *mmap_changing,
 				      enum mcopy_atomic_mode mode,
 				      bool wp_copy);
 #endif /* CONFIG_HUGETLB_PAGE */
@@ -601,8 +612,8 @@ retry:
 	 */
 	if (is_vm_hugetlb_page(dst_vma))
 		return  __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start,
-					       src_start, len, mcopy_mode,
-					       wp_copy);
+					       src_start, len, mmap_changing,
+					       mcopy_mode, wp_copy);
 
 	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
 		goto out_unlock;
diff --git a/mm/zswap.c b/mm/zswap.c
index b3829ada4..b7cb12679 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1013,6 +1013,8 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 		if (zswap_rb_search(&tree->rbroot, entry->offset) != entry) {
 			spin_unlock(&tree->lock);
 			delete_from_swap_cache(page_folio(page));
+			unlock_page(page);
+			put_page(page);
 			ret = -ENOMEM;
 			goto fail;
 		}