Merge tag 'vfs-6.19-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull misc vfs updates from Christian Brauner:
"Features:

- Cheaper MAY_EXEC handling for path lookup. This elides MAY_WRITE
permission checks during path lookup and adds the
IOP_FASTPERM_MAY_EXEC flag so filesystems like btrfs can avoid
expensive permission work.

- Hide dentry_cache behind runtime const machinery.

- Add German Maglione as virtiofs co-maintainer.

Cleanups:

- Tidy up and inline step_into() and walk_component() for improved
code generation.

- Re-enable IOCB_NOWAIT writes to files. This refactors file
timestamp update logic, fixing a layering bypass in btrfs when
updating timestamps on device files and improving FMODE_NOCMTIME
handling in VFS now that nfsd started using it.

- Path lookup optimizations extracting slowpaths into dedicated
routines and adding branch prediction hints for mntput_no_expire(),
fd_install(), lookup_slow(), and various other hot paths.

- Enable clang's -fms-extensions flag, requiring a JFS rename to
avoid conflicts.

- Remove spurious exports in fs/file_attr.c.

- Stop duplicating union pipe_index declaration. This depends on the
shared kbuild branch that brings in -fms-extensions support which
is merged into this branch.

- Use MD5 library instead of crypto_shash in ecryptfs.

- Use largest_zero_folio() in iomap_dio_zero().

- Replace simple_strtol/strtoul with kstrtoint/kstrtouint in init and
initrd code.

- Various typo fixes.

Fixes:

- Fix emergency sync for btrfs. Btrfs requires an explicit sync_fs()
call with wait == 1 to commit super blocks. The emergency sync path
never passed this, leaving btrfs data uncommitted during emergency
sync.

- Use local kmap in watch_queue's post_one_notification().

- Add hint prints in sb_set_blocksize() for LBS dependency on THP"

* tag 'vfs-6.19-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (35 commits)
MAINTAINERS: add German Maglione as virtiofs co-maintainer
fs: inline step_into() and walk_component()
fs: tidy up step_into() & friends before inlining
orangefs: use inode_update_timestamps directly
btrfs: fix the comment on btrfs_update_time
btrfs: use vfs_utimes to update file timestamps
fs: export vfs_utimes
fs: lift the FMODE_NOCMTIME check into file_update_time_flags
fs: refactor file timestamp update logic
include/linux/fs.h: trivial fix: regualr -> regular
fs/splice.c: trivial fix: pipes -> pipe's
fs: mark lookup_slow() as noinline
fs: add predicts based on nd->depth
fs: move mntput_no_expire() slowpath into a dedicated routine
fs: remove spurious exports in fs/file_attr.c
watch_queue: Use local kmap in post_one_notification()
fs: touch up predicts in path lookup
fs: move fd_install() slowpath into a dedicated routine and provide commentary
fs: hide dentry_cache behind runtime const machinery
fs: touch predicts in do_dentry_open()
...

MAINTAINERS

···
 F:	drivers/s390/virtio/
 
 VIRTIO FILE SYSTEM
+M:	German Maglione <[e-mail]>
 M:	Vivek Goyal <[e-mail]>
 M:	Stefan Hajnoczi <[e-mail]>
 M:	Miklos Szeredi <[e-mail]>

Makefile

···
 # perform bounds checking.
 KBUILD_CFLAGS += $(call cc-option, -fstrict-flex-arrays=3)
 
+# Allow including a tagged struct or union anonymously in another struct/union.
+KBUILD_CFLAGS += -fms-extensions
+
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= -fno-strict-overflow
 

arch/arm64/kernel/vdso32/Makefile

···
                $(filter -Werror,$(KBUILD_CPPFLAGS)) \
                -Werror-implicit-function-declaration \
                -Wno-format-security \
-               -std=gnu11
+               -std=gnu11 -fms-extensions
 VDSO_CFLAGS  += -O2
 # Some useful compiler-dependent flags from top-level Makefile
 VDSO_CFLAGS += $(call cc32-option,-Wno-pointer-sign)
···
 VDSO_CFLAGS += $(call cc32-option,-Werror=strict-prototypes)
 VDSO_CFLAGS += -Werror=date-time
 VDSO_CFLAGS += $(call cc32-option,-Werror=incompatible-pointer-types)
+VDSO_CFLAGS += $(if $(CONFIG_CC_IS_CLANG),-Wno-microsoft-anon-tag)
 
 # Compile as THUMB2 or ARM. Unwinding via frame-pointers in THUMB2 is
 # unreliable.

arch/loongarch/vdso/Makefile

···
 cflags-vdso := $(ccflags-vdso) \
 	-isystem $(shell $(CC) -print-file-name=include) \
 	$(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \
-	-std=gnu11 -O2 -g -fno-strict-aliasing -fno-common -fno-builtin \
+	-std=gnu11 -fms-extensions -O2 -g -fno-strict-aliasing -fno-common -fno-builtin \
 	-fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
 	$(call cc-option, -fno-asynchronous-unwind-tables) \
 	$(call cc-option, -fno-stack-protector)

arch/parisc/boot/compressed/Makefile

···
 ifndef CONFIG_64BIT
 KBUILD_CFLAGS += -mfast-indirect-calls
 endif
-KBUILD_CFLAGS += -std=gnu11
+KBUILD_CFLAGS += -std=gnu11 -fms-extensions
 
 LDFLAGS_vmlinux := -X -e startup --as-needed -T
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(addprefix $(obj)/, $(OBJECTS)) $(LIBGCC) FORCE

arch/powerpc/boot/Makefile

···
 BOOTCPPFLAGS	+= -isystem $(shell $(BOOTCC) -print-file-name=include)
 
 BOOTCFLAGS	:= $(BOOTTARGETFLAGS) \
-		   -std=gnu11 \
+		   -std=gnu11 -fms-extensions \
 		   -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		   -fno-strict-aliasing -O2 \
 		   -msoft-float -mno-altivec -mno-vsx \
···
 
 ifdef CONFIG_CC_IS_CLANG
 BOOTCFLAGS += $(CLANG_FLAGS)
+BOOTCFLAGS += -Wno-microsoft-anon-tag
 BOOTAFLAGS += $(CLANG_FLAGS)
 endif
 

arch/s390/Makefile

···
 ifndef CONFIG_AS_IS_LLVM
 KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf))
 endif
-KBUILD_CFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -O2 -mpacked-stack -std=gnu11
+KBUILD_CFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -O2 -mpacked-stack -std=gnu11 -fms-extensions
 KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
 KBUILD_CFLAGS_DECOMPRESSOR += -D__DECOMPRESSOR
 KBUILD_CFLAGS_DECOMPRESSOR += -Wno-pointer-sign
···
 KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g)
 KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,))
 KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_CC_NO_ARRAY_BOUNDS),-Wno-array-bounds)
+KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_CC_IS_CLANG),-Wno-microsoft-anon-tag)
 
 UTS_MACHINE	:= s390x
 STACK_SIZE	:= $(if $(CONFIG_KASAN),65536,$(if $(CONFIG_KMSAN),65536,16384))

arch/s390/purgatory/Makefile

···
 $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
 	$(call if_changed_rule,as_o_S)
 
-KBUILD_CFLAGS := -std=gnu11 -fno-strict-aliasing -Wall -Wstrict-prototypes
+KBUILD_CFLAGS := -std=gnu11 -fms-extensions -fno-strict-aliasing -Wall -Wstrict-prototypes
 KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
 KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
 KBUILD_CFLAGS += -Os -m64 -msoft-float -fno-common
···
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 KBUILD_CFLAGS += -D__DISABLE_EXPORTS
 KBUILD_CFLAGS += $(CLANG_FLAGS)
+KBUILD_CFLAGS += $(if $(CONFIG_CC_IS_CLANG),-Wno-microsoft-anon-tag)
 KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))
 KBUILD_AFLAGS += -D__DISABLE_EXPORTS

arch/x86/Makefile

···
 
 # How to compile the 16-bit code.  Note we always compile for -march=i386;
 # that way we can complain to the user if the CPU is insufficient.
-REALMODE_CFLAGS	:= -std=gnu11 -m16 -g -Os -DDISABLE_BRANCH_PROFILING -D__DISABLE_EXPORTS \
+REALMODE_CFLAGS	:= -std=gnu11 -fms-extensions -m16 -g -Os \
+		   -DDISABLE_BRANCH_PROFILING -D__DISABLE_EXPORTS \
 		   -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \
 		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
 		   -mno-mmx -mno-sse $(call cc-option,-fcf-protection=none)
···
 REALMODE_CFLAGS += $(CLANG_FLAGS)
 ifdef CONFIG_CC_IS_CLANG
 REALMODE_CFLAGS += -Wno-gnu
+REALMODE_CFLAGS += -Wno-microsoft-anon-tag
 endif
 export REALMODE_CFLAGS
 

arch/x86/boot/compressed/Makefile

···
 # avoid errors with '-march=i386', and future flags may depend on the target to
 # be valid.
 KBUILD_CFLAGS := -m$(BITS) -O2 $(CLANG_FLAGS)
-KBUILD_CFLAGS += -std=gnu11
+KBUILD_CFLAGS += -std=gnu11 -fms-extensions
 KBUILD_CFLAGS += -fno-strict-aliasing -fPIE
 KBUILD_CFLAGS += -Wundef
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
···
 KBUILD_CFLAGS += -ffreestanding -fshort-wchar
 KBUILD_CFLAGS += -fno-stack-protector
 KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
-KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
+ifdef CONFIG_CC_IS_CLANG
+KBUILD_CFLAGS += -Wno-gnu
+KBUILD_CFLAGS += -Wno-microsoft-anon-tag
+endif
 KBUILD_CFLAGS += -Wno-pointer-sign
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS += -D__DISABLE_EXPORTS

block/bdev.c

···
 
 EXPORT_SYMBOL(set_blocksize);
 
+static int sb_validate_large_blocksize(struct super_block *sb, int size)
+{
+	const char *err_str = NULL;
+
+	if (!(sb->s_type->fs_flags & FS_LBS))
+		err_str = "not supported by filesystem";
+	else if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		err_str = "is only supported with CONFIG_TRANSPARENT_HUGEPAGE";
+
+	if (!err_str)
+		return 0;
+
+	pr_warn_ratelimited("%s: block size(%d) > page size(%lu) %s\n",
+				sb->s_type->name, size, PAGE_SIZE, err_str);
+	return -EINVAL;
+}
+
 int sb_set_blocksize(struct super_block *sb, int size)
 {
-	if (!(sb->s_type->fs_flags & FS_LBS) && size > PAGE_SIZE)
+	if (size > PAGE_SIZE && sb_validate_large_blocksize(sb, size))
 		return 0;
 	if (set_blocksize(sb->s_bdev_file, size))
 		return 0;

drivers/firmware/efi/libstub/Makefile

···
 
 cflags-$(CONFIG_X86_32)		:= -march=i386
 cflags-$(CONFIG_X86_64)		:= -mcmodel=small
-cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ -std=gnu11 \
+cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ -std=gnu11 -fms-extensions \
 				   -fPIC -fno-strict-aliasing -mno-red-zone \
 				   -mno-mmx -mno-sse -fshort-wchar \
 				   -Wno-pointer-sign \
 				   $(call cc-disable-warning, address-of-packed-member) \
-				   $(call cc-disable-warning, gnu) \
+				   $(if $(CONFIG_CC_IS_CLANG),-Wno-gnu -Wno-microsoft-anon-tag) \
 				   -fno-asynchronous-unwind-tables \
 				   $(CLANG_FLAGS)
 

fs/btrfs/inode.c

···
 	if (ret)
 		return ERR_PTR(ret);
 
+	if (S_ISDIR(inode->vfs_inode.i_mode))
+		inode->vfs_inode.i_opflags |= IOP_FASTPERM_MAY_EXEC;
 	unlock_new_inode(&inode->vfs_inode);
 	return inode;
 }
···
 }
 
 /*
- * This is a copy of file_update_time.  We need this so we can return error on
- * ENOSPC for updating the inode in the case of file write and mmap writes.
+ * We need our own ->update_time so that we can return error on ENOSPC for
+ * updating the inode in the case of file write and mmap writes.
  */
 static int btrfs_update_time(struct inode *inode, int flags)
 {
···
 	}
 
 	ret = btrfs_create_new_inode(trans, &new_inode_args);
-	if (!ret)
+	if (!ret) {
+		if (S_ISDIR(inode->i_mode))
+			inode->i_opflags |= IOP_FASTPERM_MAY_EXEC;
 		d_instantiate_new(dentry, inode);
+	}
 
 	btrfs_end_transaction(trans);
 	btrfs_btree_balance_dirty(fs_info);
···
 					   min_size, actual_len, alloc_hint, trans);
 }
 
+/*
+ * NOTE: in case you are adding MAY_EXEC check for directories:
+ * we are marking them with IOP_FASTPERM_MAY_EXEC, allowing path lookup to
+ * elide calls here.
+ */
 static int btrfs_permission(struct mnt_idmap *idmap,
 			    struct inode *inode, int mask)
 {

fs/btrfs/volumes.c

···
 static void update_dev_time(const char *device_path)
 {
 	struct path path;
-	int ret;
 
-	ret = kern_path(device_path, LOOKUP_FOLLOW, &path);
-	if (ret)
-		return;
-
-	inode_update_time(d_inode(path.dentry), S_MTIME | S_CTIME | S_VERSION);
-	path_put(&path);
+	if (!kern_path(device_path, LOOKUP_FOLLOW, &path)) {
+		vfs_utimes(&path, NULL);
+		path_put(&path);
+	}
 }
 
 static int btrfs_rm_dev_item(struct btrfs_trans_handle *trans,

fs/dcache.c

···
 
 EXPORT_SYMBOL(rename_lock);
 
-static struct kmem_cache *dentry_cache __ro_after_init;
+static struct kmem_cache *__dentry_cache __ro_after_init;
+#define dentry_cache runtime_const_ptr(__dentry_cache)
 
 const struct qstr empty_name = QSTR_INIT("", 0);
 EXPORT_SYMBOL(empty_name);
···
 	 * but it is probably not worth it because of the cache nature
 	 * of the dcache.
 	 */
-	dentry_cache = KMEM_CACHE_USERCOPY(dentry,
+	__dentry_cache = KMEM_CACHE_USERCOPY(dentry,
 		SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT,
 		d_shortname.string);
+	runtime_const_init(ptr, __dentry_cache);
 
 	/* Hash may have been set up in dcache_init_early */
 	if (!hashdist)

fs/ecryptfs/Kconfig

···
 	depends on KEYS && CRYPTO && (ENCRYPTED_KEYS || ENCRYPTED_KEYS=n)
 	select CRYPTO_ECB
 	select CRYPTO_CBC
-	select CRYPTO_MD5
+	select CRYPTO_LIB_MD5
 	help
 	  Encrypted filesystem that operates on the VFS layer.  See
 	  <file:Documentation/filesystems/ecryptfs.rst> to learn more about

fs/ecryptfs/crypto.c

···
  *   		Michael C. Thompson <[e-mail]>
  */
 
-#include <crypto/hash.h>
 #include <crypto/skcipher.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
···
 	}
 }
 
-/**
- * ecryptfs_calculate_md5 - calculates the md5 of @src
- * @dst: Pointer to 16 bytes of allocated memory
- * @crypt_stat: Pointer to crypt_stat struct for the current inode
- * @src: Data to be md5'd
- * @len: Length of @src
- *
- * Uses the allocated crypto context that crypt_stat references to
- * generate the MD5 sum of the contents of src.
- */
-static int ecryptfs_calculate_md5(char *dst,
-				  struct ecryptfs_crypt_stat *crypt_stat,
-				  char *src, int len)
-{
-	int rc = crypto_shash_tfm_digest(crypt_stat->hash_tfm, src, len, dst);
-
-	if (rc) {
-		printk(KERN_ERR
-		       "%s: Error computing crypto hash; rc = [%d]\n",
-		       __func__, rc);
-		goto out;
-	}
-out:
-	return rc;
-}
-
 static int ecryptfs_crypto_api_algify_cipher_name(char **algified_name,
 						  char *cipher_name,
 						  char *chaining_modifier)
···
  *
  * Generate the initialization vector from the given root IV and page
  * offset.
- *
- * Returns zero on success; non-zero on error.
  */
-int ecryptfs_derive_iv(char *iv, struct ecryptfs_crypt_stat *crypt_stat,
-		       loff_t offset)
+void ecryptfs_derive_iv(char *iv, struct ecryptfs_crypt_stat *crypt_stat,
+			loff_t offset)
 {
-	int rc = 0;
 	char dst[MD5_DIGEST_SIZE];
 	char src[ECRYPTFS_MAX_IV_BYTES + 16];
 
···
 		ecryptfs_printk(KERN_DEBUG, "source:\n");
 		ecryptfs_dump_hex(src, (crypt_stat->iv_bytes + 16));
 	}
-	rc = ecryptfs_calculate_md5(dst, crypt_stat, src,
-				    (crypt_stat->iv_bytes + 16));
-	if (rc) {
-		ecryptfs_printk(KERN_WARNING, "Error attempting to compute "
-				"MD5 while generating IV for a page\n");
-		goto out;
-	}
+	md5(src, crypt_stat->iv_bytes + 16, dst);
 	memcpy(iv, dst, crypt_stat->iv_bytes);
 	if (unlikely(ecryptfs_verbosity > 0)) {
 		ecryptfs_printk(KERN_DEBUG, "derived iv:\n");
 		ecryptfs_dump_hex(iv, crypt_stat->iv_bytes);
 	}
-out:
-	return rc;
 }
 
 /**
···
  *
  * Initialize the crypt_stat structure.
  */
-int ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat)
+void ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat)
 {
-	struct crypto_shash *tfm;
-	int rc;
-
-	tfm = crypto_alloc_shash(ECRYPTFS_DEFAULT_HASH, 0, 0);
-	if (IS_ERR(tfm)) {
-		rc = PTR_ERR(tfm);
-		ecryptfs_printk(KERN_ERR, "Error attempting to "
-				"allocate crypto context; rc = [%d]\n",
-				rc);
-		return rc;
-	}
-
 	memset((void *)crypt_stat, 0, sizeof(struct ecryptfs_crypt_stat));
 	INIT_LIST_HEAD(&crypt_stat->keysig_list);
 	mutex_init(&crypt_stat->keysig_list_mutex);
 	mutex_init(&crypt_stat->cs_mutex);
 	mutex_init(&crypt_stat->cs_tfm_mutex);
-	crypt_stat->hash_tfm = tfm;
 	crypt_stat->flags |= ECRYPTFS_STRUCT_INITIALIZED;
-
-	return 0;
 }
 
 /**
···
 	struct ecryptfs_key_sig *key_sig, *key_sig_tmp;
 
 	crypto_free_skcipher(crypt_stat->tfm);
-	crypto_free_shash(crypt_stat->hash_tfm);
 	list_for_each_entry_safe(key_sig, key_sig_tmp,
 				 &crypt_stat->keysig_list, crypt_stat_list) {
 		list_del(&key_sig->crypt_stat_list);
···
 	int rc;
 
 	extent_base = (((loff_t)page_index) * (PAGE_SIZE / extent_size));
-	rc = ecryptfs_derive_iv(extent_iv, crypt_stat,
-				(extent_base + extent_offset));
-	if (rc) {
-		ecryptfs_printk(KERN_ERR, "Error attempting to derive IV for "
-			"extent [0x%.16llx]; rc = [%d]\n",
-			(unsigned long long)(extent_base + extent_offset), rc);
-		goto out;
-	}
+	ecryptfs_derive_iv(extent_iv, crypt_stat, extent_base + extent_offset);
 
 	sg_init_table(&src_sg, 1);
 	sg_init_table(&dst_sg, 1);
···
  */
 int ecryptfs_compute_root_iv(struct ecryptfs_crypt_stat *crypt_stat)
 {
-	int rc = 0;
 	char dst[MD5_DIGEST_SIZE];
 
 	BUG_ON(crypt_stat->iv_bytes > MD5_DIGEST_SIZE);
 	BUG_ON(crypt_stat->iv_bytes <= 0);
 	if (!(crypt_stat->flags & ECRYPTFS_KEY_VALID)) {
-		rc = -EINVAL;
 		ecryptfs_printk(KERN_WARNING, "Session key not valid; "
 				"cannot generate root IV\n");
-		goto out;
-	}
-	rc = ecryptfs_calculate_md5(dst, crypt_stat, crypt_stat->key,
-				    crypt_stat->key_size);
-	if (rc) {
-		ecryptfs_printk(KERN_WARNING, "Error attempting to compute "
-				"MD5 while generating root IV\n");
-		goto out;
-	}
-	memcpy(crypt_stat->root_iv, dst, crypt_stat->iv_bytes);
-out:
-	if (rc) {
 		memset(crypt_stat->root_iv, 0, crypt_stat->iv_bytes);
 		crypt_stat->flags |= ECRYPTFS_SECURITY_WARNING;
+		return -EINVAL;
 	}
-	return rc;
+	md5(crypt_stat->key, crypt_stat->key_size, dst);
+	memcpy(crypt_stat->root_iv, dst, crypt_stat->iv_bytes);
+	return 0;
 }
 
 static void ecryptfs_generate_new_key(struct ecryptfs_crypt_stat *crypt_stat)

fs/ecryptfs/ecryptfs_kernel.h

···
 #ifndef ECRYPTFS_KERNEL_H
 #define ECRYPTFS_KERNEL_H
 
+#include <crypto/md5.h>
 #include <crypto/skcipher.h>
 #include <keys/user-type.h>
 #include <keys/encrypted-type.h>
···
 					+ MAGIC_ECRYPTFS_MARKER_SIZE_BYTES)
 #define ECRYPTFS_DEFAULT_CIPHER "aes"
 #define ECRYPTFS_DEFAULT_KEY_BYTES 16
-#define ECRYPTFS_DEFAULT_HASH "md5"
-#define ECRYPTFS_TAG_70_DIGEST ECRYPTFS_DEFAULT_HASH
 #define ECRYPTFS_TAG_1_PACKET_TYPE 0x01
 #define ECRYPTFS_TAG_3_PACKET_TYPE 0x8C
 #define ECRYPTFS_TAG_11_PACKET_TYPE 0xED
···
  * ECRYPTFS_MAX_IV_BYTES */
 #define ECRYPTFS_FILENAME_MIN_RANDOM_PREPEND_BYTES 16
 #define ECRYPTFS_NON_NULL 0x42 /* A reasonable substitute for NULL */
-#define MD5_DIGEST_SIZE 16
-#define ECRYPTFS_TAG_70_DIGEST_SIZE MD5_DIGEST_SIZE
 #define ECRYPTFS_TAG_70_MIN_METADATA_SIZE (1 + ECRYPTFS_MIN_PKT_LEN_SIZE \
 					   + ECRYPTFS_SIG_SIZE + 1 + 1)
 #define ECRYPTFS_TAG_70_MAX_METADATA_SIZE (1 + ECRYPTFS_MAX_PKT_LEN_SIZE \
···
 	unsigned int extent_mask;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
 	struct crypto_skcipher *tfm;
-	struct crypto_shash *hash_tfm; /* Crypto context for generating
-					* the initialization vectors */
 	unsigned char cipher[ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1];
 	unsigned char key[ECRYPTFS_MAX_KEY_BYTES];
 	unsigned char root_iv[ECRYPTFS_MAX_IV_BYTES];
···
 			int sg_size);
 int ecryptfs_compute_root_iv(struct ecryptfs_crypt_stat *crypt_stat);
 void ecryptfs_rotate_iv(unsigned char *iv);
-int ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat);
+void ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat);
 void ecryptfs_destroy_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat);
 void ecryptfs_destroy_mount_crypt_stat(
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat);
···
 			     char *data, size_t max_packet_size);
 int ecryptfs_set_f_namelen(long *namelen, long lower_namelen,
 			   struct ecryptfs_mount_crypt_stat *mount_crypt_stat);
-int ecryptfs_derive_iv(char *iv, struct ecryptfs_crypt_stat *crypt_stat,
-		       loff_t offset);
+void ecryptfs_derive_iv(char *iv, struct ecryptfs_crypt_stat *crypt_stat,
+			loff_t offset);
 
 extern const struct xattr_handler * const ecryptfs_xattr_handlers[];
 

fs/ecryptfs/inode.c

···
 	struct ecryptfs_crypt_stat *crypt_stat;
 
 	crypt_stat = &ecryptfs_inode_to_private(d_inode(dentry))->crypt_stat;
-	if (!(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)) {
-		rc = ecryptfs_init_crypt_stat(crypt_stat);
-		if (rc)
-			return rc;
-	}
+	if (!(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED))
+		ecryptfs_init_crypt_stat(crypt_stat);
 	inode = d_inode(dentry);
 	lower_inode = ecryptfs_inode_to_lower(inode);
 	lower_dentry = ecryptfs_dentry_to_lower(dentry);

fs/ecryptfs/keystore.c

···
  *              Trevor S. Highland <[e-mail]>
  */
 
-#include <crypto/hash.h>
 #include <crypto/skcipher.h>
 #include <linux/string.h>
 #include <linux/pagemap.h>
···
 	struct crypto_skcipher *skcipher_tfm;
 	struct skcipher_request *skcipher_req;
 	char iv[ECRYPTFS_MAX_IV_BYTES];
-	char hash[ECRYPTFS_TAG_70_DIGEST_SIZE];
-	char tmp_hash[ECRYPTFS_TAG_70_DIGEST_SIZE];
-	struct crypto_shash *hash_tfm;
-	struct shash_desc *hash_desc;
+	char hash[MD5_DIGEST_SIZE];
 };
 
 /*
···
 		       "password tokens\n", __func__);
 		goto out_free_unlock;
 	}
-	s->hash_tfm = crypto_alloc_shash(ECRYPTFS_TAG_70_DIGEST, 0, 0);
-	if (IS_ERR(s->hash_tfm)) {
-			rc = PTR_ERR(s->hash_tfm);
-			printk(KERN_ERR "%s: Error attempting to "
-			       "allocate hash crypto context; rc = [%d]\n",
-			       __func__, rc);
-			goto out_free_unlock;
-	}
 
-	s->hash_desc = kmalloc(sizeof(*s->hash_desc) +
-			       crypto_shash_descsize(s->hash_tfm), GFP_KERNEL);
-	if (!s->hash_desc) {
-		rc = -ENOMEM;
-		goto out_release_free_unlock;
-	}
-
-	s->hash_desc->tfm = s->hash_tfm;
-
-	rc = crypto_shash_digest(s->hash_desc,
-				 (u8 *)s->auth_tok->token.password.session_key_encryption_key,
-				 s->auth_tok->token.password.session_key_encryption_key_bytes,
-				 s->hash);
-	if (rc) {
-		printk(KERN_ERR
-		       "%s: Error computing crypto hash; rc = [%d]\n",
-		       __func__, rc);
-		goto out_release_free_unlock;
-	}
+	md5(s->auth_tok->token.password.session_key_encryption_key,
+	    s->auth_tok->token.password.session_key_encryption_key_bytes,
+	    s->hash);
 	for (s->j = 0; s->j < (s->num_rand_bytes - 1); s->j++) {
 		s->block_aligned_filename[s->j] =
-			s->hash[(s->j % ECRYPTFS_TAG_70_DIGEST_SIZE)];
-		if ((s->j % ECRYPTFS_TAG_70_DIGEST_SIZE)
-		    == (ECRYPTFS_TAG_70_DIGEST_SIZE - 1)) {
-			rc = crypto_shash_digest(s->hash_desc, (u8 *)s->hash,
-						ECRYPTFS_TAG_70_DIGEST_SIZE,
-						s->tmp_hash);
-			if (rc) {
-				printk(KERN_ERR
-				       "%s: Error computing crypto hash; "
-				       "rc = [%d]\n", __func__, rc);
-				goto out_release_free_unlock;
-			}
-			memcpy(s->hash, s->tmp_hash,
-			       ECRYPTFS_TAG_70_DIGEST_SIZE);
-		}
+			s->hash[s->j % MD5_DIGEST_SIZE];
+		if ((s->j % MD5_DIGEST_SIZE) == (MD5_DIGEST_SIZE - 1))
+			md5(s->hash, MD5_DIGEST_SIZE, s->hash);
 		if (s->block_aligned_filename[s->j] == '\0')
 			s->block_aligned_filename[s->j] = ECRYPTFS_NON_NULL;
 	}
···
 		       "convert filename memory to scatterlist; rc = [%d]. "
 		       "block_aligned_filename_size = [%zd]\n", __func__, rc,
 		       s->block_aligned_filename_size);
-		goto out_release_free_unlock;
+		goto out_free_unlock;
 	}
 	rc = virt_to_scatterlist(&dest[s->i], s->block_aligned_filename_size,
 				 s->dst_sg, 2);
···
 		       "convert encrypted filename memory to scatterlist; "
 		       "rc = [%d]. block_aligned_filename_size = [%zd]\n",
 		       __func__, rc, s->block_aligned_filename_size);
-		goto out_release_free_unlock;
+		goto out_free_unlock;
 	}
 	/* The characters in the first block effectively do the job
 	 * of the IV here, so we just use 0's for the IV. Note the
···
 		       rc,
 		       s->auth_tok->token.password.session_key_encryption_key,
 		       mount_crypt_stat->global_default_fn_cipher_key_bytes);
-		goto out_release_free_unlock;
+		goto out_free_unlock;
 	}
 	skcipher_request_set_crypt(s->skcipher_req, s->src_sg, s->dst_sg,
 				   s->block_aligned_filename_size, s->iv);
···
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to encrypt filename; "
 		       "rc = [%d]\n", __func__, rc);
-		goto out_release_free_unlock;
+		goto out_free_unlock;
 	}
 	s->i += s->block_aligned_filename_size;
 	(*packet_size) = s->i;
 	(*remaining_bytes) -= (*packet_size);
-out_release_free_unlock:
-	crypto_free_shash(s->hash_tfm);
 out_free_unlock:
 	kfree_sensitive(s->block_aligned_filename);
 out_unlock:
···
 		key_put(auth_tok_key);
 	}
 	skcipher_request_free(s->skcipher_req);
-	kfree_sensitive(s->hash_desc);
 	kfree(s);
 	return rc;
 }

fs/ecryptfs/main.c

···
 
 #include <linux/dcache.h>
 #include <linux/file.h>
+#include <linux/fips.h>
 #include <linux/module.h>
 #include <linux/namei.h>
 #include <linux/skbuff.h>
···
 	rc = ecryptfs_validate_options(fc);
 	if (rc) {
 		err = "Error validating options";
+		goto out;
+	}
+
+	if (fips_enabled) {
+		rc = -EINVAL;
+		err = "eCryptfs support is disabled due to FIPS";
 		goto out;
 	}
 

fs/ecryptfs/super.c

···
 	inode_info = alloc_inode_sb(sb, ecryptfs_inode_info_cache, GFP_KERNEL);
 	if (unlikely(!inode_info))
 		goto out;
-	if (ecryptfs_init_crypt_stat(&inode_info->crypt_stat)) {
-		kmem_cache_free(ecryptfs_inode_info_cache, inode_info);
-		goto out;
-	}
+	ecryptfs_init_crypt_stat(&inode_info->crypt_stat);
 	mutex_init(&inode_info->lower_file_mutex);
 	atomic_set(&inode_info->lower_file_count, 0);
 	inode_info->lower_file = NULL;

fs/file.c

···
 
 EXPORT_SYMBOL(put_unused_fd);
 
+/*
+ * Install a file pointer in the fd array while it is being resized.
+ *
+ * We need to make sure our update to the array does not get lost as the resizing
+ * thread can be copying the content as we modify it.
+ *
+ * We have two ways to do it:
+ * - go off CPU waiting for resize_in_progress to clear
+ * - take the spin lock
+ *
+ * The latter is trivial to implement and saves us from having to might_sleep()
+ * for debugging purposes.
+ *
+ * This is moved out of line from fd_install() to convince gcc to optimize that
+ * routine better.
+ */
+static void noinline fd_install_slowpath(unsigned int fd, struct file *file)
+{
+	struct files_struct *files = current->files;
+	struct fdtable *fdt;
+
+	spin_lock(&files->file_lock);
+	fdt = files_fdtable(files);
+	VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL);
+	rcu_assign_pointer(fdt->fd[fd], file);
+	spin_unlock(&files->file_lock);
+}
+
 /**
  * fd_install - install a file pointer in the fd array
  * @fd: file descriptor to install the file in
···
 		return;
 
 	rcu_read_lock_sched();
-
 	if (unlikely(files->resize_in_progress)) {
 		rcu_read_unlock_sched();
-		spin_lock(&files->file_lock);
-		fdt = files_fdtable(files);
-		VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL);
-		rcu_assign_pointer(fdt->fd[fd], file);
-		spin_unlock(&files->file_lock);
+		fd_install_slowpath(fd, file);
 		return;
 	}
 	/* coupled with smp_wmb() in expand_fdtable() */

fs/file_attr.c

···
 		err = put_user(fa.flags, argp);
 	return err;
 }
-EXPORT_SYMBOL(ioctl_getflags);
 
 int ioctl_setflags(struct file *file, unsigned int __user *argp)
 {
···
 	}
 	return err;
 }
-EXPORT_SYMBOL(ioctl_setflags);
 
 int ioctl_fsgetxattr(struct file *file, void __user *argp)
 {
···
 
 	return err;
 }
-EXPORT_SYMBOL(ioctl_fsgetxattr);
 
 int ioctl_fssetxattr(struct file *file, void __user *argp)
 {
···
 	}
 	return err;
 }
-EXPORT_SYMBOL(ioctl_fssetxattr);
 
 SYSCALL_DEFINE5(file_getattr, int, dfd, const char __user *, filename,
 		struct file_attr __user *, ufattr, size_t, usize,

fs/inode.c

···
 }
 EXPORT_SYMBOL(current_time);
 
-static int inode_needs_update_time(struct inode *inode)
+static int file_update_time_flags(struct file *file, unsigned int flags)
 {
+	struct inode *inode = file_inode(file);
 	struct timespec64 now, ts;
-	int sync_it = 0;
+	int sync_mode = 0;
+	int ret = 0;
 
 	/* First try to exhaust all avenues to not sync */
 	if (IS_NOCMTIME(inode))
+		return 0;
+	if (unlikely(file->f_mode & FMODE_NOCMTIME))
 		return 0;
 
 	now = current_time(inode);
 
 	ts = inode_get_mtime(inode);
 	if (!timespec64_equal(&ts, &now))
-		sync_it |= S_MTIME;
-
+		sync_mode |= S_MTIME;
 	ts = inode_get_ctime(inode);
 	if (!timespec64_equal(&ts, &now))
-		sync_it |= S_CTIME;
-
+		sync_mode |= S_CTIME;
 	if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode))
-		sync_it |= S_VERSION;
+		sync_mode |= S_VERSION;
 
-	return sync_it;
-}
+	if (!sync_mode)
+		return 0;
 
-static int __file_update_time(struct file *file, int sync_mode)
-{
-	int ret = 0;
-	struct inode *inode = file_inode(file);
+	if (flags & IOCB_NOWAIT)
+		return -EAGAIN;
 
-	/* try to update time settings */
-	if (!mnt_get_write_access_file(file)) {
-		ret = inode_update_time(inode, sync_mode);
-		mnt_put_write_access_file(file);
-	}
-
+	if (mnt_get_write_access_file(file))
+		return 0;
+	ret = inode_update_time(inode, sync_mode);
+	mnt_put_write_access_file(file);
 	return ret;
 }
 
···
  */
 int file_update_time(struct file *file)
 {
-	int ret;
-	struct inode *inode = file_inode(file);
-
-	ret = inode_needs_update_time(inode);
-	if (ret <= 0)
-		return ret;
-
-	return __file_update_time(file, ret);
+	return file_update_time_flags(file, 0);
 }
 EXPORT_SYMBOL(file_update_time);
 
···
 static int file_modified_flags(struct file *file, int flags)
 {
 	int ret;
-	struct inode *inode = file_inode(file);
 
 	/*
 	 * Clear the security bits if the process is not being run by root.
···
 	ret = file_remove_privs_flags(file, flags);
 	if (ret)
 		return ret;
-
-	if (unlikely(file->f_mode & FMODE_NOCMTIME))
-		return 0;
-
-	ret = inode_needs_update_time(inode);
-	if (ret <= 0)
-		return ret;
-	if (flags & IOCB_NOWAIT)
-		return -EAGAIN;
-
-	return __file_update_time(file, ret);
+	return file_update_time_flags(file, flags);
 }
 
 /**

fs/iomap/direct-io.c

···
 #define IOMAP_DIO_WRITE		(1U << 30)
 #define IOMAP_DIO_DIRTY		(1U << 31)
 
-/*
- * Used for sub block zeroing in iomap_dio_zero()
- */
-#define IOMAP_ZERO_PAGE_SIZE (SZ_64K)
-#define IOMAP_ZERO_PAGE_ORDER (get_order(IOMAP_ZERO_PAGE_SIZE))
-static struct page *zero_page;
-
 struct iomap_dio {
 	struct kiocb		*iocb;
 	const struct iomap_dio_ops *dops;
···
 {
 	struct inode *inode = file_inode(dio->iocb->ki_filp);
 	struct bio *bio;
+	struct folio *zero_folio = largest_zero_folio();
+	int nr_vecs = max(1, i_blocksize(inode) / folio_size(zero_folio));
 
 	if (!len)
 		return 0;
+
 	/*
-	 * Max block size supported is 64k
+	 * This limit shall never be reached as most filesystems have a
+	 * maximum blocksize of 64k.
 	 */
-	if (WARN_ON_ONCE(len > IOMAP_ZERO_PAGE_SIZE))
+	if (WARN_ON_ONCE(nr_vecs > BIO_MAX_VECS))
 		return -EINVAL;
 
-	bio = iomap_dio_alloc_bio(iter, dio, 1, REQ_OP_WRITE | REQ_SYNC | REQ_IDLE);
+	bio = iomap_dio_alloc_bio(iter, dio, nr_vecs,
+				  REQ_OP_WRITE | REQ_SYNC | REQ_IDLE);
 	fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits,
 				  GFP_KERNEL);
 	bio->bi_iter.bi_sector = iomap_sector(&iter->iomap, pos);
 	bio->bi_private = dio;
 	bio->bi_end_io = iomap_dio_bio_end_io;
 
-	__bio_add_page(bio, zero_page, len, 0);
+	while (len > 0) {
+		unsigned int io_len = min(len, folio_size(zero_folio));
+
+		bio_add_folio_nofail(bio, zero_folio, io_len, 0);
+		len -= io_len;
+	}
 	iomap_dio_submit_bio(iter, dio, bio, pos);
+
 	return 0;
 }
 
···
 	return iomap_dio_complete(dio);
 }
 EXPORT_SYMBOL_GPL(iomap_dio_rw);
-
-static int __init iomap_dio_init(void)
-{
-	zero_page = alloc_pages(GFP_KERNEL | __GFP_ZERO,
-				IOMAP_ZERO_PAGE_ORDER);
-
-	if (!zero_page)
-		return -ENOMEM;
-
-	return 0;
-}
-fs_initcall(iomap_dio_init);

fs/jfs/jfs_incore.h

···
 		struct {
 			unchar _unused[16];	/* 16: */
 			dxd_t _dxd;		/* 16: */
-			/* _inline may overflow into _inline_ea when needed */
+			/* _inline_sym may overflow into _inline_ea when needed */
 			/* _inline_ea may overlay the last part of
 			 * file._xtroot if maxentry = XTROOTINITSLOT
 			 */
 			union {
 				struct {
 					/* 128: inline symlink */
-					unchar _inline[128];
+					unchar _inline_sym[128];
 					/* 128: inline extended attr */
 					unchar _inline_ea[128];
 				};
···
 #define i_imap u.file._imap
 #define i_dirtable u.dir._table
 #define i_dtroot u.dir._dtroot
-#define i_inline u.link._inline
+#define i_inline u.link._inline_sym
 #define i_inline_ea u.link._inline_ea
 #define i_inline_all u.link._inline_all
 

fs/namei.c

···
 		return;
 
 	refcnt = atomic_read(&name->refcnt);
-	if (refcnt != 1) {
+	if (unlikely(refcnt != 1)) {
 		if (WARN_ON_ONCE(!refcnt))
 			return;
 
···
 			return;
 	}
 
-	if (name->name != name->iname) {
+	if (unlikely(name->name != name->iname)) {
 		__putname(name->name);
 		kfree(name);
 	} else
···
  * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
  *
  * Separate out file-system wide checks from inode-specific permission checks.
+ *
+ * Note: lookup_inode_permission_may_exec() does not call here. If you add
+ * MAY_EXEC checks, adjust it.
  */
 static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
 {
-	if (unlikely(mask & MAY_WRITE)) {
+	if (mask & MAY_WRITE) {
 		umode_t mode = inode->i_mode;
 
 		/* Nobody gets write access to a read-only fs. */
···
 	if (unlikely(retval))
 		return retval;
 
-	if (unlikely(mask & MAY_WRITE)) {
+	if (mask & MAY_WRITE) {
 		/*
 		 * Nobody gets write access to an immutable file.
 		 */
···
 	return security_inode_permission(inode, mask);
 }
 EXPORT_SYMBOL(inode_permission);
+
+/*
+ * lookup_inode_permission_may_exec - Check traversal right for given inode
+ *
+ * This is a special case routine for may_lookup() making assumptions specific
+ * to path traversal. Use inode_permission() if you are doing something else.
+ *
+ * Work is shaved off compared to inode_permission() as follows:
+ * - we know for a fact there is no MAY_WRITE to worry about
+ * - it is an invariant the inode is a directory
+ *
+ * Since majority of real-world traversal happens on inodes which grant it for
+ * everyone, we check it upfront and only resort to more expensive work if it
+ * fails.
+ *
+ * Filesystems which have their own ->permission hook and consequently miss out
+ * on IOP_FASTPERM can still get the optimization if they set IOP_FASTPERM_MAY_EXEC
+ * on their directory inodes.
+ */
+static __always_inline int lookup_inode_permission_may_exec(struct mnt_idmap *idmap,
+	struct inode *inode, int mask)
+{
+	/* Lookup already checked this to return -ENOTDIR */
+	VFS_BUG_ON_INODE(!S_ISDIR(inode->i_mode), inode);
+	VFS_BUG_ON((mask & ~MAY_NOT_BLOCK) != 0);
+
+	mask |= MAY_EXEC;
+
+	if (unlikely(!(inode->i_opflags & (IOP_FASTPERM | IOP_FASTPERM_MAY_EXEC))))
+		return inode_permission(idmap, inode, mask);
+
+	if (unlikely(((inode->i_mode & 0111) != 0111) || !no_acl_inode(inode)))
+		return inode_permission(idmap, inode, mask);
+
+	return security_inode_permission(inode, mask);
+}
 
 /**
  * path_get - get a reference to a path
···
 
 static void terminate_walk(struct nameidata *nd)
 {
-	drop_links(nd);
+	if (unlikely(nd->depth))
+		drop_links(nd);
 	if (!(nd->flags & LOOKUP_RCU)) {
 		int i;
 		path_put(&nd->path);
···
 
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
 
-	if (unlikely(!legitimize_links(nd)))
+	if (unlikely(nd->depth && !legitimize_links(nd)))
 		goto out1;
 	if (unlikely(!legitimize_path(nd, &nd->path, nd->seq)))
 		goto out;
···
 	int res;
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
 
-	if (unlikely(!legitimize_links(nd)))
+	if (unlikely(nd->depth && !legitimize_links(nd)))
 		goto out2;
 	res = __legitimize_mnt(nd->path.mnt, nd->m_seq);
 	if (unlikely(res)) {
···
 		 * We don't want to zero nd->root for scoped-lookups or
 		 * externally-managed nd->root.
 		 */
-		if (!(nd->state & ND_ROOT_PRESET))
-			if (!(nd->flags & LOOKUP_IS_SCOPED))
+		if (likely(!(nd->state & ND_ROOT_PRESET)))
+			if (likely(!(nd->flags & LOOKUP_IS_SCOPED)))
 				nd->root.mnt = NULL;
 		nd->flags &= ~LOOKUP_CACHED;
 		if (!try_to_unlazy(nd))
···
 	}
 	if (!nd->root.mnt) {
 		int error = set_root(nd);
-		if (error)
+		if (unlikely(error))
 			return error;
 	}
 	if (nd->flags & LOOKUP_RCU) {
···
 	path->dentry = dentry;
 	if (nd->flags & LOOKUP_RCU) {
 		unsigned int seq = nd->next_seq;
+		if (likely(!d_managed(dentry)))
+			return 0;
 		if (likely(__follow_mount_rcu(nd, path)))
 			return 0;
 		// *path and nd->next_seq might've been clobbered
 		path->mnt = nd->path.mnt;
 		path->dentry = dentry;
 		nd->next_seq = seq;
-		if (!try_to_unlazy_next(nd, dentry))
+		if (unlikely(!try_to_unlazy_next(nd, dentry)))
 			return -ECHILD;
 	}
 	ret = traverse_mounts(path, &jumped, &nd->total_link_count, nd->flags);
···
 	return dentry;
 }
 
-static struct dentry *lookup_slow(const struct qstr *name,
+static noinline struct dentry *lookup_slow(const struct qstr *name,
 				  struct dentry *dir,
 				  unsigned int flags)
 {
···
 	int err, mask;
 
 	mask = nd->flags & LOOKUP_RCU ? MAY_NOT_BLOCK : 0;
-	err = inode_permission(idmap, nd->inode, mask | MAY_EXEC);
+	err = lookup_inode_permission_may_exec(idmap, nd->inode, mask);
 	if (likely(!err))
 		return 0;
 
···
 	if (err != -ECHILD)	// hard error
 		return err;
 
-	return inode_permission(idmap, nd->inode, MAY_EXEC);
+	return lookup_inode_permission_may_exec(idmap, nd->inode, 0);
 }
 
 static int reserve_stack(struct nameidata *nd, struct path *link)
···
 
 enum {WALK_TRAILING = 1, WALK_MORE = 2, WALK_NOFOLLOW = 4};
 
-static const char *pick_link(struct nameidata *nd, struct path *link,
+static noinline const char *pick_link(struct nameidata *nd, struct path *link,
 		     struct inode *inode, int flags)
 {
 	struct saved *last;
 	const char *res;
-	int error = reserve_stack(nd, link);
+	int error;
 
+	if (nd->flags & LOOKUP_RCU) {
+		/* make sure that d_is_symlink from step_into_slowpath() matches the inode */
+		if (read_seqcount_retry(&link->dentry->d_seq, nd->next_seq))
+			return ERR_PTR(-ECHILD);
+	} else {
+		if (link->mnt == nd->path.mnt)
+			mntget(link->mnt);
+	}
+
+	error = reserve_stack(nd, link);
 	if (unlikely(error)) {
 		if (!(nd->flags & LOOKUP_RCU))
 			path_put(link);
···
  *
  * NOTE: dentry must be what nd->next_seq had been sampled from.
  */
-static const char *step_into(struct nameidata *nd, int flags,
+static noinline const char *step_into_slowpath(struct nameidata *nd, int flags,
 		     struct dentry *dentry)
 {
 	struct path path;
 	struct inode *inode;
-	int err = handle_mounts(nd, dentry, &path);
+	int err;
 
-	if (err < 0)
+	err = handle_mounts(nd, dentry, &path);
+	if (unlikely(err < 0))
 		return ERR_PTR(err);
 	inode = path.dentry->d_inode;
 	if (likely(!d_is_symlink(path.dentry)) ||
···
 		nd->seq = nd->next_seq;
 		return NULL;
 	}
-	if (nd->flags & LOOKUP_RCU) {
-		/* make sure that d_is_symlink above matches inode */
-		if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq))
-			return ERR_PTR(-ECHILD);
-	} else {
-		if (path.mnt == nd->path.mnt)
-			mntget(path.mnt);
-	}
 	return pick_link(nd, &path, inode, flags);
+}
+
+static __always_inline const char *step_into(struct nameidata *nd, int flags,
+                    struct dentry *dentry)
+{
+	/*
+	 * In the common case we are in rcu-walk and traversing over a non-mounted on
+	 * directory (as opposed to e.g., a symlink).
+	 *
+	 * We can handle that and negative entries with the checks below.
+	 */
+	if (likely((nd->flags & LOOKUP_RCU) &&
+	    !d_managed(dentry) && !d_is_symlink(dentry))) {
+		struct inode *inode = dentry->d_inode;
+		if (read_seqcount_retry(&dentry->d_seq, nd->next_seq))
+			return ERR_PTR(-ECHILD);
+		if (unlikely(!inode))
+			return ERR_PTR(-ENOENT);
+		nd->path.dentry = dentry;
+		/* nd->path.mnt is retained on purpose */
+		nd->inode = inode;
+		nd->seq = nd->next_seq;
+		return NULL;
+	}
+	return step_into_slowpath(nd, flags, dentry);
 }
 
 static struct dentry *follow_dotdot_rcu(struct nameidata *nd)
···
 
 		if (!nd->root.mnt) {
 			error = ERR_PTR(set_root(nd));
-			if (error)
+			if (unlikely(error))
 				return error;
 		}
 		if (nd->flags & LOOKUP_RCU)
···
 	return NULL;
 }
 
-static const char *walk_component(struct nameidata *nd, int flags)
+static __always_inline const char *walk_component(struct nameidata *nd, int flags)
 {
 	struct dentry *dentry;
 	/*
···
 	 * parent relationships.
 	 */
 	if (unlikely(nd->last_type != LAST_NORM)) {
-		if (!(flags & WALK_MORE) && nd->depth)
+		if (unlikely(nd->depth) && !(flags & WALK_MORE))
 			put_link(nd);
 		return handle_dots(nd, nd->last_type);
 	}
···
 		if (IS_ERR(dentry))
 			return ERR_CAST(dentry);
 	}
-	if (!(flags & WALK_MORE) && nd->depth)
+	if (unlikely(nd->depth) && !(flags & WALK_MORE))
 		put_link(nd);
 	return step_into(nd, flags, dentry);
 }
···
 		if (unlikely(!*name)) {
 OK:
 			/* pathname or trailing symlink, done */
-			if (!depth) {
+			if (likely(!depth)) {
 				nd->dir_vfsuid = i_uid_into_vfsuid(idmap, nd->inode);
 				nd->dir_mode = nd->inode->i_mode;
 				nd->flags &= ~LOOKUP_PARENT;
···
 	const char *s = nd->pathname;
 
 	/* LOOKUP_CACHED requires RCU, ask caller to retry */
-	if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED)
+	if (unlikely((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED))
 		return ERR_PTR(-EAGAIN);
 
-	if (!*s)
+	if (unlikely(!*s))
 		flags &= ~LOOKUP_RCU;
 	if (flags & LOOKUP_RCU)
 		rcu_read_lock();
···
 	nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount);
 	smp_rmb();
 
-	if (nd->state & ND_ROOT_PRESET) {
+	if (unlikely(nd->state & ND_ROOT_PRESET)) {
 		struct dentry *root = nd->root.dentry;
 		struct inode *inode = root->d_inode;
 		if (*s && unlikely(!d_can_lookup(root)))
···
 	nd->root.mnt = NULL;
 
 	/* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */
-	if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) {
+	if (*s == '/' && likely(!(flags & LOOKUP_IN_ROOT))) {
 		error = nd_jump_root(nd);
 		if (unlikely(error))
 			return ERR_PTR(error);
···
 	}
 
 	/* For scoped-lookups we need to set the root to the dirfd as well. */
-	if (flags & LOOKUP_IS_SCOPED) {
+	if (unlikely(flags & LOOKUP_IS_SCOPED)) {
 		nd->root = nd->path;
 		if (flags & LOOKUP_RCU) {
 			nd->root_seq = nd->seq;

fs/namespace.c

···
 }
 static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput);
 
-static void mntput_no_expire(struct mount *mnt)
+static void noinline mntput_no_expire_slowpath(struct mount *mnt)
 {
 	LIST_HEAD(list);
 	int count;
 
-	rcu_read_lock();
-	if (likely(READ_ONCE(mnt->mnt_ns))) {
-		/*
-		 * Since we don't do lock_mount_hash() here,
-		 * ->mnt_ns can change under us.  However, if it's
-		 * non-NULL, then there's a reference that won't
-		 * be dropped until after an RCU delay done after
-		 * turning ->mnt_ns NULL.  So if we observe it
-		 * non-NULL under rcu_read_lock(), the reference
-		 * we are dropping is not the final one.
-		 */
-		mnt_add_count(mnt, -1);
-		rcu_read_unlock();
-		return;
-	}
+	VFS_BUG_ON(mnt->mnt_ns);
 	lock_mount_hash();
 	/*
 	 * make sure that if __legitimize_mnt() has not seen us grab
···
 		return;
 	}
 	cleanup_mnt(mnt);
+}
+
+static void mntput_no_expire(struct mount *mnt)
+{
+	rcu_read_lock();
+	if (likely(READ_ONCE(mnt->mnt_ns))) {
+		/*
+		 * Since we don't do lock_mount_hash() here,
+		 * ->mnt_ns can change under us.  However, if it's
+		 * non-NULL, then there's a reference that won't
+		 * be dropped until after an RCU delay done after
+		 * turning ->mnt_ns NULL.  So if we observe it
+		 * non-NULL under rcu_read_lock(), the reference
+		 * we are dropping is not the final one.
+		 */
+		mnt_add_count(mnt, -1);
+		rcu_read_unlock();
+		return;
+	}
+	mntput_no_expire_slowpath(mnt);
 }
 
 void mntput(struct vfsmount *mnt)

fs/open.c

···
 	}
 
 	error = security_file_open(f);
-	if (error)
+	if (unlikely(error))
 		goto cleanup_all;
 
 	/*
···
 	 * pseudo file, this call will not change the mode.
 	 */
 	error = fsnotify_open_perm_and_set_mode(f);
-	if (error)
+	if (unlikely(error))
 		goto cleanup_all;
 
 	error = break_lease(file_inode(f), f->f_flags);
-	if (error)
+	if (unlikely(error))
 		goto cleanup_all;
 
 	/* normally all 3 are set; ->open() can clear them if needed */

fs/orangefs/inode.c

···
 
 	gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_update_time: %pU\n",
 	    get_khandle_from_ino(inode));
-	flags = generic_update_time(inode, flags);
+
+	flags = inode_update_timestamps(inode, flags);
+
 	memset(&iattr, 0, sizeof iattr);
         if (flags & S_ATIME)
 		iattr.ia_valid |= ATTR_ATIME;

fs/splice.c

···
 
 /*
  * For lack of a better implementation, implement vmsplice() to userspace
- * as a simple copy of the pipes pages to the user iov.
+ * as a simple copy of the pipe's pages to the user iov.
  */
 static ssize_t vmsplice_to_user(struct file *file, struct iov_iter *iter,
 				unsigned int flags)

fs/sync.c

···
 static void do_sync_work(struct work_struct *work)
 {
 	int nowait = 0;
+	int wait = 1;
 
 	/*
 	 * Sync twice to reduce the possibility we skipped some inodes / pages
 	 * because they were temporarily locked
 	 */
-	iterate_supers(sync_inodes_one_sb, &nowait);
+	iterate_supers(sync_inodes_one_sb, NULL);
 	iterate_supers(sync_fs_one_sb, &nowait);
 	sync_bdevs(false);
-	iterate_supers(sync_inodes_one_sb, &nowait);
-	iterate_supers(sync_fs_one_sb, &nowait);
+	iterate_supers(sync_inodes_one_sb, NULL);
+	iterate_supers(sync_fs_one_sb, &wait);
 	sync_bdevs(false);
 	printk("Emergency Sync complete\n");
 	kfree(work);

fs/utimes.c

···
 out:
 	return error;
 }
+EXPORT_SYMBOL_GPL(vfs_utimes);
 
 static int do_utimes_path(int dfd, const char __user *filename,
 		struct timespec64 *times, int flags)

include/asm-generic/vmlinux.lds.h

···
 
 #define RUNTIME_CONST_VARIABLES						\
 		RUNTIME_CONST(shift, d_hash_shift)			\
-		RUNTIME_CONST(ptr, dentry_hashtable)
+		RUNTIME_CONST(ptr, dentry_hashtable)			\
+		RUNTIME_CONST(ptr, __dentry_cache)
 
 /* Alignment must be consistent with (kunit_suite *) in include/kunit/test.h */
 #define KUNIT_TABLE()							\

include/linux/fs.h

···
 	return (long)acl & 1;
 }
 
-#define IOP_FASTPERM	0x0001
-#define IOP_LOOKUP	0x0002
-#define IOP_NOFOLLOW	0x0004
-#define IOP_XATTR	0x0008
+#define IOP_FASTPERM		0x0001
+#define IOP_LOOKUP		0x0002
+#define IOP_NOFOLLOW		0x0004
+#define IOP_XATTR		0x0008
 #define IOP_DEFAULT_READLINK	0x0010
-#define IOP_MGTIME	0x0020
-#define IOP_CACHED_LINK	0x0040
+#define IOP_MGTIME		0x0020
+#define IOP_CACHED_LINK		0x0040
+#define IOP_FASTPERM_MAY_EXEC	0x0080
 
 /*
  * Inode state bits.  Protected by inode->i_lock
···
  * file_start_write - get write access to a superblock for regular file io
  * @file: the file we want to write to
  *
- * This is a variant of sb_start_write() which is a noop on non-regualr file.
+ * This is a variant of sb_start_write() which is a noop on non-regular file.
  * Should be matched with a call to file_end_write().
  */
 static inline void file_start_write(struct file *file)

include/linux/pipe_fs_i.h

···
 typedef unsigned short pipe_index_t;
 #endif
 
-/*
- * We have to declare this outside 'struct pipe_inode_info',
- * but then we can't use 'union pipe_index' for an anonymous
- * union, so we end up having to duplicate this declaration
- * below. Annoying.
+/**
+ *	struct pipe_index - pipe indeces
+ *	@head: The point of buffer production
+ *	@tail: The point of buffer consumption
+ *	@head_tail: unsigned long union of @head and @tail
  */
 union pipe_index {
 	unsigned long head_tail;
···
  *	@mutex: mutex protecting the whole thing
  *	@rd_wait: reader wait point in case of empty pipe
  *	@wr_wait: writer wait point in case of full pipe
- *	@head: The point of buffer production
- *	@tail: The point of buffer consumption
- *	@head_tail: unsigned long union of @head and @tail
+ *	@pipe_index: the pipe indeces
  *	@note_loss: The next read() should insert a data-lost message
  *	@max_usage: The maximum number of slots that may be used in the ring
  *	@ring_size: total number of buffers (should be a power of 2)
···
 	struct mutex mutex;
 	wait_queue_head_t rd_wait, wr_wait;
 
-	/* This has to match the 'union pipe_index' above */
-	union {
-		unsigned long head_tail;
-		struct {
-			pipe_index_t head;
-			pipe_index_t tail;
-		};
-	};
+	union pipe_index;
 
 	unsigned int max_usage;
 	unsigned int ring_size;

init/do_mounts.c

···
 static unsigned int __initdata root_delay;
 static int __init root_delay_setup(char *str)
 {
-	root_delay = simple_strtoul(str, NULL, 0);
+	if (kstrtouint(str, 0, &root_delay))
+		return 0;
 	return 1;
 }
 

init/do_mounts_rd.c

···
 
 static int __init ramdisk_start_setup(char *str)
 {
-	rd_image_start = simple_strtol(str,NULL,0);
-	return 1;
+	return kstrtoint(str, 0, &rd_image_start) == 0;
 }
 __setup("ramdisk_start=", ramdisk_start_setup);
 

kernel/watch_queue.c

···
 	offset = note % WATCH_QUEUE_NOTES_PER_PAGE * WATCH_QUEUE_NOTE_SIZE;
 	get_page(page);
 	len = n->info & WATCH_INFO_LENGTH;
-	p = kmap_atomic(page);
+	p = kmap_local_page(page);
 	memcpy(p + offset, n, len);
-	kunmap_atomic(p);
+	kunmap_local(p);
 
 	buf = pipe_buf(pipe, head);
 	buf->page = page;

scripts/Makefile.extrawarn

···
 KBUILD_CFLAGS-$(CONFIG_CC_NO_ARRAY_BOUNDS) += -Wno-array-bounds
 
 ifdef CONFIG_CC_IS_CLANG
-# The kernel builds with '-std=gnu11' so use of GNU extensions is acceptable.
+# The kernel builds with '-std=gnu11' and '-fms-extensions' so use of GNU and
+# Microsoft extensions is acceptable.
 KBUILD_CFLAGS += -Wno-gnu
+KBUILD_CFLAGS += -Wno-microsoft-anon-tag
 
 # Clang checks for overflow/truncation with '%p', while GCC does not:
 # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111219