Merge branch 'mm-hotfixes-stable' into mm-stable

To pick up depended-upon changes

18 files changed, 102 insertions, 45 deletions

diff --git a/.mailmap b/.mailmap
index 79e0d680c748..a17b3c8f69d5 100644
--- a/.mailmap
+++ b/.mailmap
@@ -25,6 +25,8 @@ Aleksey Gorelov <aleksey_gorelov@phoenix.com>
 Alexander Lobakin <alobakin@pm.me> <alobakin@dlink.ru>
 Alexander Lobakin <alobakin@pm.me> <alobakin@marvell.com>
 Alexander Lobakin <alobakin@pm.me> <bloodyreaper@yandex.ru>
+Alexander Mikhalitsyn <alexander@mihalicyn.com> <alexander.mikhalitsyn@virtuozzo.com>
+Alexander Mikhalitsyn <alexander@mihalicyn.com> <aleksandr.mikhalitsyn@canonical.com>
 Alexandre Belloni <alexandre.belloni@bootlin.com> <alexandre.belloni@free-electrons.com>
 Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com>
 Alexei Starovoitov <ast@kernel.org> <ast@fb.com>
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 65f3b02a0e4e..f90975e00446 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -48,9 +48,10 @@ static int __init early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
 		err = memblock_mark_nomap(base, size);
 		if (err)
 			memblock_phys_free(base, size);
-		kmemleak_ignore_phys(base);
 	}
 
+	kmemleak_ignore_phys(base);
+
 	return err;
 }
 
diff --git a/fs/aio.c b/fs/aio.c
index 5a88caf52be4..b0b17bd098bb 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -361,6 +361,9 @@ static int aio_ring_mremap(struct vm_area_struct *vma)
 	spin_lock(&mm->ioctx_lock);
 	rcu_read_lock();
 	table = rcu_dereference(mm->ioctx_table);
+	if (!table)
+		goto out_unlock;
+
 	for (i = 0; i < table->nr; i++) {
 		struct kioctx *ctx;
 
@@ -374,6 +377,7 @@ static int aio_ring_mremap(struct vm_area_struct *vma)
 		}
 	}
 
+out_unlock:
 	rcu_read_unlock();
 	spin_unlock(&mm->ioctx_lock);
 	return res;
diff --git a/fs/dax.c b/fs/dax.c
index c48a3a93ab29..3e457a16c7d1 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1271,8 +1271,9 @@ static s64 dax_unshare_iter(struct iomap_iter *iter)
 	if (ret < 0)
 		goto out_unlock;
 
-	ret = copy_mc_to_kernel(daddr, saddr, length);
-	if (ret)
+	if (copy_mc_to_kernel(daddr, saddr, length) == 0)
+		ret = length;
+	else
 		ret = -EIO;
 
 out_unlock:
diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c
index b88d19e9581e..c8469c656e0d 100644
--- a/fs/squashfs/xattr_id.c
+++ b/fs/squashfs/xattr_id.c
@@ -76,7 +76,7 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start,
 	/* Sanity check values */
 
 	/* there is always at least one xattr id */
-	if (*xattr_ids <= 0)
+	if (*xattr_ids == 0)
 		return ERR_PTR(-EINVAL);
 
 	len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4a0695ef969a..9454b7eb055b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -137,7 +137,7 @@ extern int mmap_rnd_compat_bits __read_mostly;
  * define their own version of this macro in <asm/pgtable.h>
  */
 #if BITS_PER_LONG == 64
-/* This function must be updated when the size of struct page grows above 80
+/* This function must be updated when the size of struct page grows above 96
  * or reduces below 56. The idea that compiler optimizes out switch()
  * statement, and only leaves move/store instructions. Also the compiler can
  * combine write statements if they are both assignments and can be reordered,
@@ -148,12 +148,18 @@ static inline void __mm_zero_struct_page(struct page *page)
 {
 	unsigned long *_pp = (void *)page;
 
-	 /* Check that struct page is either 56, 64, 72, or 80 bytes */
+	 /* Check that struct page is either 56, 64, 72, 80, 88 or 96 bytes */
 	BUILD_BUG_ON(sizeof(struct page) & 7);
 	BUILD_BUG_ON(sizeof(struct page) < 56);
-	BUILD_BUG_ON(sizeof(struct page) > 80);
+	BUILD_BUG_ON(sizeof(struct page) > 96);
 
 	switch (sizeof(struct page)) {
+	case 96:
+		_pp[11] = 0;
+		fallthrough;
+	case 88:
+		_pp[10] = 0;
+		fallthrough;
 	case 80:
 		_pp[9] = 0;
 		fallthrough;
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 71310efe2fab..7bde8e1c228a 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -107,7 +107,7 @@ extern void synchronize_shrinkers(void);
 
 #ifdef CONFIG_SHRINKER_DEBUG
 extern int shrinker_debugfs_add(struct shrinker *shrinker);
-extern void shrinker_debugfs_remove(struct shrinker *shrinker);
+extern struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker);
 extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker,
 						  const char *fmt, ...);
 #else /* CONFIG_SHRINKER_DEBUG */
@@ -115,8 +115,9 @@ static inline int shrinker_debugfs_add(struct shrinker *shrinker)
 {
 	return 0;
 }
-static inline void shrinker_debugfs_remove(struct shrinker *shrinker)
+static inline struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker)
 {
+	return NULL;
 }
 static inline __printf(2, 3)
 int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...)
diff --git a/lib/parser.c b/lib/parser.c
index bcb23484100e..2b5e2b480253 100644
--- a/lib/parser.c
+++ b/lib/parser.c
@@ -11,6 +11,15 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 
+/*
+ * max size needed by different bases to express U64
+ * HEX: "0xFFFFFFFFFFFFFFFF" --> 18
+ * DEC: "18446744073709551615" --> 20
+ * OCT: "01777777777777777777777" --> 23
+ * pick the max one to define NUMBER_BUF_LEN
+ */
+#define NUMBER_BUF_LEN 24
+
 /**
  * match_one - Determines if a string matches a simple pattern
  * @s: the string to examine for presence of the pattern
@@ -129,14 +138,12 @@ EXPORT_SYMBOL(match_token);
 static int match_number(substring_t *s, int *result, int base)
 {
 	char *endp;
-	char *buf;
+	char buf[NUMBER_BUF_LEN];
 	int ret;
 	long val;
 
-	buf = match_strdup(s);
-	if (!buf)
-		return -ENOMEM;
-
+	if (match_strlcpy(buf, s, NUMBER_BUF_LEN) >= NUMBER_BUF_LEN)
+		return -ERANGE;
 	ret = 0;
 	val = simple_strtol(buf, &endp, base);
 	if (endp == buf)
@@ -145,7 +152,6 @@ static int match_number(substring_t *s, int *result, int base)
 		ret = -ERANGE;
 	else
 		*result = (int) val;
-	kfree(buf);
 	return ret;
 }
 
@@ -163,18 +169,15 @@ static int match_number(substring_t *s, int *result, int base)
  */
 static int match_u64int(substring_t *s, u64 *result, int base)
 {
-	char *buf;
+	char buf[NUMBER_BUF_LEN];
 	int ret;
 	u64 val;
 
-	buf = match_strdup(s);
-	if (!buf)
-		return -ENOMEM;
-
+	if (match_strlcpy(buf, s, NUMBER_BUF_LEN) >= NUMBER_BUF_LEN)
+		return -ERANGE;
 	ret = kstrtoull(buf, base, &val);
 	if (!ret)
 		*result = val;
-	kfree(buf);
 	return ret;
 }
 
@@ -206,14 +209,12 @@ EXPORT_SYMBOL(match_int);
  */
 int match_uint(substring_t *s, unsigned int *result)
 {
-	int err = -ENOMEM;
-	char *buf = match_strdup(s);
+	char buf[NUMBER_BUF_LEN];
 
-	if (buf) {
-		err = kstrtouint(buf, 10, result);
-		kfree(buf);
-	}
-	return err;
+	if (match_strlcpy(buf, s, NUMBER_BUF_LEN) >= NUMBER_BUF_LEN)
+		return -ERANGE;
+
+	return kstrtouint(buf, 10, result);
 }
 EXPORT_SYMBOL(match_uint);
 
diff --git a/mm/gup.c b/mm/gup.c
index 91d047096c09..25e4a3d923d6 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1939,7 +1939,7 @@ static unsigned long collect_longterm_unpinnable_pages(
 			drain_allow = false;
 		}
 
-		if (!folio_isolate_lru(folio))
+		if (folio_isolate_lru(folio))
 			continue;
 
 		list_add_tail(&folio->lru, movable_page_list);
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 6b8e9c848573..1e7336ae3786 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -246,6 +246,9 @@ bool __kasan_slab_free(struct kmem_cache *cache, void *object,
 
 static inline bool ____kasan_kfree_large(void *ptr, unsigned long ip)
 {
+	if (!kasan_arch_is_ready())
+		return false;
+
 	if (ptr != page_address(virt_to_head_page(ptr))) {
 		kasan_report_invalid_free(ptr, ip, KASAN_REPORT_INVALID_FREE);
 		return true;
diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
index a37b5b57bf5c..e5eef670735e 100644
--- a/mm/kasan/generic.c
+++ b/mm/kasan/generic.c
@@ -189,7 +189,12 @@ bool kasan_check_range(unsigned long addr, size_t size, bool write,
 
 bool kasan_byte_accessible(const void *addr)
 {
-	s8 shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(addr));
+	s8 shadow_byte;
+
+	if (!kasan_arch_is_ready())
+		return true;
+
+	shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(addr));
 
 	return shadow_byte >= 0 && shadow_byte < KASAN_GRANULE_SIZE;
 }
diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
index 2fba1f51f042..15cfb34d16a1 100644
--- a/mm/kasan/shadow.c
+++ b/mm/kasan/shadow.c
@@ -291,6 +291,9 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
 	unsigned long shadow_start, shadow_end;
 	int ret;
 
+	if (!kasan_arch_is_ready())
+		return 0;
+
 	if (!is_vmalloc_or_module_addr((void *)addr))
 		return 0;
 
@@ -459,6 +462,9 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end,
 	unsigned long region_start, region_end;
 	unsigned long size;
 
+	if (!kasan_arch_is_ready())
+		return;
+
 	region_start = ALIGN(start, KASAN_MEMORY_PER_SHADOW_PAGE);
 	region_end = ALIGN_DOWN(end, KASAN_MEMORY_PER_SHADOW_PAGE);
 
@@ -502,6 +508,9 @@ void *__kasan_unpoison_vmalloc(const void *start, unsigned long size,
 	 * with setting memory tags, so the KASAN_VMALLOC_INIT flag is ignored.
 	 */
 
+	if (!kasan_arch_is_ready())
+		return (void *)start;
+
 	if (!is_vmalloc_or_module_addr(start))
 		return (void *)start;
 
@@ -524,6 +533,9 @@ void *__kasan_unpoison_vmalloc(const void *start, unsigned long size,
  */
 void __kasan_poison_vmalloc(const void *start, unsigned long size)
 {
+	if (!kasan_arch_is_ready())
+		return;
+
 	if (!is_vmalloc_or_module_addr(start))
 		return;
 
diff --git a/mm/ksm.c b/mm/ksm.c
index cea0c4478220..ad591b779d53 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2628,8 +2628,11 @@ struct page *ksm_might_need_to_copy(struct page *page,
 		new_page = NULL;
 	}
 	if (new_page) {
-		copy_user_highpage(new_page, page, address, vma);
-
+		if (copy_mc_user_highpage(new_page, page, address, vma)) {
+			put_page(new_page);
+			memory_failure_queue(page_to_pfn(page), 0);
+			return ERR_PTR(-EHWPOISON);
+		}
 		SetPageDirty(new_page);
 		__SetPageUptodate(new_page);
 		__SetPageLocked(new_page);
diff --git a/mm/memory.c b/mm/memory.c
index ce1d84d022d3..7a04a1130ec1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3823,6 +3823,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		if (unlikely(!page)) {
 			ret = VM_FAULT_OOM;
 			goto out_page;
+		} else if (unlikely(PTR_ERR(page) == -EHWPOISON)) {
+			ret = VM_FAULT_HWPOISON;
+			goto out_page;
 		}
 		folio = page_folio(page);
 
diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c
index b05295bab322..39c3491e28a3 100644
--- a/mm/shrinker_debug.c
+++ b/mm/shrinker_debug.c
@@ -246,18 +246,21 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...)
 }
 EXPORT_SYMBOL(shrinker_debugfs_rename);
 
-void shrinker_debugfs_remove(struct shrinker *shrinker)
+struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker)
 {
+	struct dentry *entry = shrinker->debugfs_entry;
+
 	lockdep_assert_held(&shrinker_rwsem);
 
 	kfree_const(shrinker->name);
 	shrinker->name = NULL;
 
-	if (!shrinker->debugfs_entry)
-		return;
+	if (entry) {
+		ida_free(&shrinker_debugfs_ida, shrinker->debugfs_id);
+		shrinker->debugfs_entry = NULL;
+	}
 
-	debugfs_remove_recursive(shrinker->debugfs_entry);
-	ida_free(&shrinker_debugfs_ida, shrinker->debugfs_id);
+	return entry;
 }
 
 static int __init shrinker_debugfs_init(void)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index cf0d72020f97..da8b8e1f97f1 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1762,12 +1762,15 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	struct page *swapcache;
 	spinlock_t *ptl;
 	pte_t *pte, new_pte;
+	bool hwposioned = false;
 	int ret = 1;
 
 	swapcache = page;
 	page = ksm_might_need_to_copy(page, vma, addr);
 	if (unlikely(!page))
 		return -ENOMEM;
+	else if (unlikely(PTR_ERR(page) == -EHWPOISON))
+		hwposioned = true;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) {
@@ -1775,15 +1778,19 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		goto out;
 	}
 
-	if (unlikely(!PageUptodate(page))) {
-		pte_t pteval;
+	if (unlikely(hwposioned || !PageUptodate(page))) {
+		swp_entry_t swp_entry;
 
 		dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
-		pteval = swp_entry_to_pte(make_swapin_error_entry());
-		set_pte_at(vma->vm_mm, addr, pte, pteval);
-		swap_free(entry);
+		if (hwposioned) {
+			swp_entry = make_hwpoison_entry(swapcache);
+			page = swapcache;
+		} else {
+			swp_entry = make_swapin_error_entry();
+		}
+		new_pte = swp_entry_to_pte(swp_entry);
 		ret = 0;
-		goto out;
+		goto setpte;
 	}
 
 	/* See do_swap_page() */
@@ -1815,6 +1822,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		new_pte = pte_mksoft_dirty(new_pte);
 	if (pte_swp_uffd_wp(*pte))
 		new_pte = pte_mkuffd_wp(new_pte);
+setpte:
 	set_pte_at(vma->vm_mm, addr, pte, new_pte);
 	swap_free(entry);
 out:
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ac51150d2d36..d4b9fd1ae0ed 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -747,6 +747,8 @@ EXPORT_SYMBOL(register_shrinker);
  */
 void unregister_shrinker(struct shrinker *shrinker)
 {
+	struct dentry *debugfs_entry;
+
 	if (!(shrinker->flags & SHRINKER_REGISTERED))
 		return;
 
@@ -755,9 +757,11 @@ void unregister_shrinker(struct shrinker *shrinker)
 	shrinker->flags &= ~SHRINKER_REGISTERED;
 	if (shrinker->flags & SHRINKER_MEMCG_AWARE)
 		unregister_memcg_shrinker(shrinker);
-	shrinker_debugfs_remove(shrinker);
+	debugfs_entry = shrinker_debugfs_remove(shrinker);
 	up_write(&shrinker_rwsem);
 
+	debugfs_remove_recursive(debugfs_entry);
+
 	kfree(shrinker->nr_deferred);
 	shrinker->nr_deferred = NULL;
 }
diff --git a/scripts/gdb/linux/cpus.py b/scripts/gdb/linux/cpus.py
index 15fc4626d236..9ee99f9fae8d 100644
--- a/scripts/gdb/linux/cpus.py
+++ b/scripts/gdb/linux/cpus.py
@@ -163,7 +163,7 @@ def get_current_task(cpu):
     task_ptr_type = task_type.get_type().pointer()
 
     if utils.is_target_arch("x86"):
-         var_ptr = gdb.parse_and_eval("&current_task")
+         var_ptr = gdb.parse_and_eval("&pcpu_hot.current_task")
          return per_cpu(var_ptr, cpu).dereference()
     elif utils.is_target_arch("aarch64"):
          current_task_addr = gdb.parse_and_eval("$SP_EL0")