Merge tag 'mm-hotfixes-stable-2023-12-27-15-00' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

torvalds · torvalds · commit f5837722ffec · 2023-12-27T16:14:41.000-08:00
Pull misc fixes from Andrew Morton:
 "11 hotfixes. 7 are cc:stable and the other 4 address post-6.6 issues
  or are not considered backporting material"

* tag 'mm-hotfixes-stable-2023-12-27-15-00' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  mailmap: add an old address for Naoya Horiguchi
  mm/memory-failure: cast index to loff_t before shifting it
  mm/memory-failure: check the mapcount of the precise page
  mm/memory-failure: pass the folio and the page to collect_procs()
  selftests: secretmem: floor the memory size to the multiple of page_size
  mm: migrate high-order folios in swap cache correctly
  maple_tree: do not preallocate nodes for slot stores
  mm/filemap: avoid buffered read/write race to read inconsistent data
  kunit: kasan_test: disable fortify string checker on kmalloc_oob_memset
  kexec: select CRYPTO from KEXEC_FILE instead of depending on it
  kexec: fix KEXEC_FILE dependencies
diff --git a/.mailmap b/.mailmap
@@ -436,6 +436,7 @@ Muna Sinada <quic_msinada@quicinc.com> <msinada@codeaurora.org>
 Murali Nalajala <quic_mnalajal@quicinc.com> <mnalajal@codeaurora.org>
 Mythri P K <mythripk@ti.com>
 Nadia Yvette Chambers <nyc@holomorphy.com> William Lee Irwin III <wli@holomorphy.com>
+Naoya Horiguchi <naoya.horiguchi@nec.com> <n-horiguchi@ah.jp.nec.com>
 Nathan Chancellor <nathan@kernel.org> <natechancellor@gmail.com>
 Neeraj Upadhyay <quic_neeraju@quicinc.com> <neeraju@codeaurora.org>
 Neil Armstrong <neil.armstrong@linaro.org> <narmstrong@baylibre.com>
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
@@ -608,10 +608,10 @@ config ARCH_SUPPORTS_KEXEC
 	def_bool PPC_BOOK3S || PPC_E500 || (44x && !SMP)
 
 config ARCH_SUPPORTS_KEXEC_FILE
-	def_bool PPC64 && CRYPTO=y && CRYPTO_SHA256=y
+	def_bool PPC64
 
 config ARCH_SUPPORTS_KEXEC_PURGATORY
-	def_bool KEXEC_FILE
+	def_bool y
 
 config ARCH_SELECTS_KEXEC_FILE
 	def_bool y
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
@@ -702,9 +702,7 @@ config ARCH_SELECTS_KEXEC_FILE
 	select KEXEC_ELF
 
 config ARCH_SUPPORTS_KEXEC_PURGATORY
-	def_bool KEXEC_FILE
-	depends on CRYPTO=y
-	depends on CRYPTO_SHA256=y
+	def_bool ARCH_SUPPORTS_KEXEC_FILE
 
 config ARCH_SUPPORTS_CRASH_DUMP
 	def_bool y
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
@@ -254,13 +254,13 @@ config ARCH_SUPPORTS_KEXEC
 	def_bool y
 
 config ARCH_SUPPORTS_KEXEC_FILE
-	def_bool CRYPTO && CRYPTO_SHA256 && CRYPTO_SHA256_S390
+	def_bool y
 
 config ARCH_SUPPORTS_KEXEC_SIG
 	def_bool MODULE_SIG_FORMAT
 
 config ARCH_SUPPORTS_KEXEC_PURGATORY
-	def_bool KEXEC_FILE
+	def_bool y
 
 config ARCH_SUPPORTS_CRASH_DUMP
 	def_bool y
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
@@ -2072,15 +2072,15 @@ config ARCH_SUPPORTS_KEXEC
 	def_bool y
 
 config ARCH_SUPPORTS_KEXEC_FILE
-	def_bool X86_64 && CRYPTO && CRYPTO_SHA256
+	def_bool X86_64
 
 config ARCH_SELECTS_KEXEC_FILE
 	def_bool y
 	depends on KEXEC_FILE
 	select HAVE_IMA_KEXEC if IMA
 
 config ARCH_SUPPORTS_KEXEC_PURGATORY
-	def_bool KEXEC_FILE
+	def_bool y
 
 config ARCH_SUPPORTS_KEXEC_SIG
 	def_bool y
diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
@@ -36,6 +36,8 @@ config KEXEC
 config KEXEC_FILE
 	bool "Enable kexec file based system call"
 	depends on ARCH_SUPPORTS_KEXEC_FILE
+	select CRYPTO
+	select CRYPTO_SHA256
 	select KEXEC_CORE
 	help
 	  This is new version of kexec system call. This system call is
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
@@ -5501,6 +5501,17 @@ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp)
 
 	mas_wr_end_piv(&wr_mas);
 	node_size = mas_wr_new_end(&wr_mas);
+
+	/* Slot store, does not require additional nodes */
+	if (node_size == wr_mas.node_end) {
+		/* reuse node */
+		if (!mt_in_rcu(mas->tree))
+			return 0;
+		/* shifting boundary */
+		if (wr_mas.offset_end - mas->offset == 1)
+			return 0;
+	}
+
 	if (node_size >= mt_slots[wr_mas.type]) {
 		/* Split, worst case for now. */
 		request = 1 + mas_mt_height(mas) * 2;
diff --git a/mm/filemap.c b/mm/filemap.c
@@ -2607,6 +2607,15 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
 			goto put_folios;
 		end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count);
 
+		/*
+		 * Pairs with a barrier in
+		 * block_write_end()->mark_buffer_dirty() or other page
+		 * dirtying routines like iomap_write_end() to ensure
+		 * changes to page contents are visible before we see
+		 * increased inode size.
+		 */
+		smp_rmb();
+
 		/*
 		 * Once we start copying data, we don't want to be touching any
 		 * cachelines that might be contended:
diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c
@@ -493,59 +493,71 @@ static void kmalloc_oob_memset_2(struct kunit *test)
 {
 	char *ptr;
 	size_t size = 128 - KASAN_GRANULE_SIZE;
+	size_t memset_size = 2;
 
 	KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test);
 
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	OPTIMIZER_HIDE_VAR(ptr);
 	OPTIMIZER_HIDE_VAR(size);
-	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 1, 0, 2));
+	OPTIMIZER_HIDE_VAR(memset_size);
+	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 1, 0, memset_size));
 	kfree(ptr);
 }
 
 static void kmalloc_oob_memset_4(struct kunit *test)
 {
 	char *ptr;
 	size_t size = 128 - KASAN_GRANULE_SIZE;
+	size_t memset_size = 4;
 
 	KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test);
 
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	OPTIMIZER_HIDE_VAR(ptr);
 	OPTIMIZER_HIDE_VAR(size);
-	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 3, 0, 4));
+	OPTIMIZER_HIDE_VAR(memset_size);
+	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 3, 0, memset_size));
 	kfree(ptr);
 }
 
 static void kmalloc_oob_memset_8(struct kunit *test)
 {
 	char *ptr;
 	size_t size = 128 - KASAN_GRANULE_SIZE;
+	size_t memset_size = 8;
 
 	KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test);
 
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	OPTIMIZER_HIDE_VAR(ptr);
 	OPTIMIZER_HIDE_VAR(size);
-	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 7, 0, 8));
+	OPTIMIZER_HIDE_VAR(memset_size);
+	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 7, 0, memset_size));
 	kfree(ptr);
 }
 
 static void kmalloc_oob_memset_16(struct kunit *test)
 {
 	char *ptr;
 	size_t size = 128 - KASAN_GRANULE_SIZE;
+	size_t memset_size = 16;
 
 	KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test);
 
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	OPTIMIZER_HIDE_VAR(ptr);
 	OPTIMIZER_HIDE_VAR(size);
-	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 15, 0, 16));
+	OPTIMIZER_HIDE_VAR(memset_size);
+	KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 15, 0, memset_size));
 	kfree(ptr);
 }
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
@@ -595,10 +595,9 @@ struct task_struct *task_early_kill(struct task_struct *tsk, int force_early)
 /*
  * Collect processes when the error hit an anonymous page.
  */
-static void collect_procs_anon(struct page *page, struct list_head *to_kill,
-				int force_early)
+static void collect_procs_anon(struct folio *folio, struct page *page,
+		struct list_head *to_kill, int force_early)
 {
-	struct folio *folio = page_folio(page);
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
 	struct anon_vma *av;
@@ -633,12 +632,12 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 /*
  * Collect processes when the error hit a file mapped page.
  */
-static void collect_procs_file(struct page *page, struct list_head *to_kill,
-				int force_early)
+static void collect_procs_file(struct folio *folio, struct page *page,
+		struct list_head *to_kill, int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
-	struct address_space *mapping = page->mapping;
+	struct address_space *mapping = folio->mapping;
 	pgoff_t pgoff;
 
 	i_mmap_lock_read(mapping);
@@ -704,17 +703,17 @@ static void collect_procs_fsdax(struct page *page,
 /*
  * Collect the processes who have the corrupted page mapped to kill.
  */
-static void collect_procs(struct page *page, struct list_head *tokill,
-				int force_early)
+static void collect_procs(struct folio *folio, struct page *page,
+		struct list_head *tokill, int force_early)
 {
-	if (!page->mapping)
+	if (!folio->mapping)
 		return;
 	if (unlikely(PageKsm(page)))
 		collect_procs_ksm(page, tokill, force_early);
 	else if (PageAnon(page))
-		collect_procs_anon(page, tokill, force_early);
+		collect_procs_anon(folio, page, tokill, force_early);
 	else
-		collect_procs_file(page, tokill, force_early);
+		collect_procs_file(folio, page, tokill, force_early);
 }
 
 struct hwpoison_walk {
@@ -1571,7 +1570,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * This check implies we don't kill processes if their pages
 	 * are in the swap cache early. Those are always late kills.
 	 */
-	if (!page_mapped(hpage))
+	if (!page_mapped(p))
 		return true;
 
 	if (PageSwapCache(p)) {
@@ -1602,7 +1601,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * mapped in dirty form.  This has to be done before try_to_unmap,
 	 * because ttu takes the rmap data structures down.
 	 */
-	collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED);
+	collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED);
 
 	if (PageHuge(hpage) && !PageAnon(hpage)) {
 		/*
@@ -1622,10 +1621,10 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 		try_to_unmap(folio, ttu);
 	}
 
-	unmap_success = !page_mapped(hpage);
+	unmap_success = !page_mapped(p);
 	if (!unmap_success)
 		pr_err("%#lx: failed to unmap page (mapcount=%d)\n",
-		       pfn, page_mapcount(hpage));
+		       pfn, page_mapcount(p));
 
 	/*
 	 * try_to_unmap() might put mlocked page in lru cache, so call
@@ -1705,7 +1704,7 @@ static void unmap_and_kill(struct list_head *to_kill, unsigned long pfn,
 		 * mapping being torn down is communicated in siginfo, see
 		 * kill_proc()
 		 */
-		loff_t start = (index << PAGE_SHIFT) & ~(size - 1);
+		loff_t start = ((loff_t)index << PAGE_SHIFT) & ~(size - 1);
 
 		unmap_mapping_range(mapping, start, size, 0);
 	}
@@ -1772,7 +1771,7 @@ static int mf_generic_kill_procs(unsigned long long pfn, int flags,
 	 * SIGBUS (i.e. MF_MUST_KILL)
 	 */
 	flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
-	collect_procs(&folio->page, &to_kill, true);
+	collect_procs(folio, &folio->page, &to_kill, true);
 
 	unmap_and_kill(&to_kill, pfn, folio->mapping, folio->index, flags);
 unlock:
diff --git a/mm/migrate.c b/mm/migrate.c
@@ -405,6 +405,7 @@ int folio_migrate_mapping(struct address_space *mapping,
 	int dirty;
 	int expected_count = folio_expected_refs(mapping, folio) + extra_count;
 	long nr = folio_nr_pages(folio);
+	long entries, i;
 
 	if (!mapping) {
 		/* Anonymous page without mapping */
@@ -442,8 +443,10 @@ int folio_migrate_mapping(struct address_space *mapping,
 			folio_set_swapcache(newfolio);
 			newfolio->private = folio_get_private(folio);
 		}
+		entries = nr;
 	} else {
 		VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio);
+		entries = 1;
 	}
 
 	/* Move dirty while page refs frozen and newpage not yet exposed */
@@ -453,7 +456,11 @@ int folio_migrate_mapping(struct address_space *mapping,
 		folio_set_dirty(newfolio);
 	}
 
-	xas_store(&xas, newfolio);
+	/* Swap cache still stores N entries instead of a high-order entry */
+	for (i = 0; i < entries; i++) {
+		xas_store(&xas, newfolio);
+		xas_next(&xas);
+	}
 
 	/*
 	 * Drop cache reference from old page by unfreezing
diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c
@@ -35538,7 +35538,7 @@ static noinline void __init check_prealloc(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
 	allocated = mas_allocated(&mas);
 	height = mas_mt_height(&mas);
-	MT_BUG_ON(mt, allocated != 1);
+	MT_BUG_ON(mt, allocated != 0);
 	mas_store_prealloc(&mas, ptr);
 	MT_BUG_ON(mt, mas_allocated(&mas) != 0);
 
diff --git a/tools/testing/selftests/mm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c
@@ -62,6 +62,9 @@ static void test_mlock_limit(int fd)
 	char *mem;
 
 	len = mlock_limit_cur;
+	if (len % page_size != 0)
+		len = (len/page_size) * page_size;
+
 	mem = mmap(NULL, len, prot, mode, fd, 0);
 	if (mem == MAP_FAILED) {
 		fail("unable to mmap secret memory\n");
