Resguardo inicial

linux-7.2.3/fs/ext4/.kunitconfig

@@ -0,0 +1,3 @@
+CONFIG_KUNIT=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_KUNIT_TESTS=y

linux-7.2.3/fs/ext4/Kconfig

@@ -0,0 +1,92 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config EXT4_FS
+	tristate "The Extended 4 (ext4) filesystem"
+	select BUFFER_HEAD
+	select JBD2
+	select CRC16
+	select CRC32
+	select FS_IOMAP
+	select FS_ENCRYPTION_ALGS if FS_ENCRYPTION
+	help
+	  This is the next generation of the ext3 filesystem.
+
+	  Unlike the change from ext2 filesystem to ext3 filesystem,
+	  the on-disk format of ext4 is not forwards compatible with
+	  ext3; it is based on extent maps and it supports 48-bit
+	  physical block numbers.  The ext4 filesystem also supports delayed
+	  allocation, persistent preallocation, high resolution time stamps,
+	  and a number of other features to improve performance and speed
+	  up fsck time.  For more information, please see the web pages at
+	  http://ext4.wiki.kernel.org.
+
+	  The ext4 filesystem supports mounting an ext3 filesystem; while there
+	  are some performance gains from the delayed allocation and inode
+	  table readahead, the best performance gains require enabling ext4
+	  features in the filesystem using tune2fs, or formatting a new
+	  filesystem as an ext4 filesystem initially. Without explicit enabling
+	  of ext4 features, the on disk filesystem format stays fully backward
+	  compatible.
+
+	  To compile this file system support as a module, choose M here. The
+	  module will be called ext4.
+
+	  If unsure, say N.
+
+config EXT4_USE_FOR_EXT2
+	bool "Use ext4 for ext2 file systems"
+	depends on EXT4_FS
+	depends on EXT2_FS=n
+	default y
+	help
+	  Allow the ext4 file system driver code to be used for ext2
+	  file system mounts.  This allows users to reduce their
+	  compiled kernel size by using one file system driver for
+	  ext2, ext3, and ext4 file systems.
+
+config EXT4_FS_POSIX_ACL
+	bool "Ext4 POSIX Access Control Lists"
+	depends on EXT4_FS
+	select FS_POSIX_ACL
+	help
+	  POSIX Access Control Lists (ACLs) support permissions for users and
+	  groups beyond the owner/group/world scheme.
+
+	  If you don't know what Access Control Lists are, say N
+
+config EXT4_FS_SECURITY
+	bool "Ext4 Security Labels"
+	depends on EXT4_FS
+	help
+	  Security labels support alternative access control models
+	  implemented by security modules like SELinux.  This option
+	  enables an extended attribute handler for file security
+	  labels in the ext4 filesystem.
+
+	  If you are not using a security module that requires using
+	  extended attributes for file security labels, say N.
+
+config EXT4_DEBUG
+	bool "Ext4 debugging support"
+	depends on EXT4_FS
+	help
+	  Enables run-time debugging support for the ext4 filesystem.
+
+	  If you select Y here, then you will be able to turn on debugging
+	  using dynamic debug control for mb_debug() / ext_debug() msgs.
+
+config EXT4_KUNIT_TESTS
+	tristate "KUnit tests for ext4" if !KUNIT_ALL_TESTS
+	depends on EXT4_FS && KUNIT
+	default KUNIT_ALL_TESTS
+	help
+	  This builds the ext4 KUnit tests.
+
+	  KUnit tests run during boot and output the results to the debug log
+	  in TAP format (https://testanything.org/). Only useful for kernel devs
+	  running KUnit test harness and are not for inclusion into a production
+	  build.
+
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.

linux-7.2.3/fs/ext4/Makefile

@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the linux ext4-filesystem routines.
+#
+
+obj-$(CONFIG_EXT4_FS) += ext4.o
+
+ext4-y	:= balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \
+		extents_status.o file.o fsmap.o fsync.o hash.o ialloc.o \
+		indirect.o inline.o inode.o ioctl.o mballoc.o migrate.o \
+		mmp.o move_extent.o namei.o page-io.o readpage.o resize.o \
+		super.o symlink.o sysfs.o xattr.o xattr_hurd.o xattr_trusted.o \
+		xattr_user.o fast_commit.o orphan.o
+
+ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
+ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o
+ext4-test-objs				+= inode-test.o mballoc-test.o \
+					   extents-test.o hash-test.o
+obj-$(CONFIG_EXT4_KUNIT_TESTS)		+= ext4-test.o
+ext4-$(CONFIG_FS_VERITY)		+= verity.o
+ext4-$(CONFIG_FS_ENCRYPTION)		+= crypto.o

linux-7.2.3/fs/ext4/acl.c

@@ -0,0 +1,304 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/fs/ext4/acl.c
+ *
+ * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
+ */
+
+#include <linux/quotaops.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * Convert from filesystem to in-memory representation.
+ */
+static struct posix_acl *
+ext4_acl_from_disk(const void *value, size_t size)
+{
+	const char *end = (char *)value + size;
+	int n, count;
+	struct posix_acl *acl;
+
+	if (!value)
+		return NULL;
+	if (size < sizeof(ext4_acl_header))
+		 return ERR_PTR(-EINVAL);
+	if (((ext4_acl_header *)value)->a_version !=
+	    cpu_to_le32(EXT4_ACL_VERSION))
+		return ERR_PTR(-EINVAL);
+	value = (char *)value + sizeof(ext4_acl_header);
+	count = ext4_acl_count(size);
+	if (count < 0)
+		return ERR_PTR(-EINVAL);
+	if (count == 0)
+		return NULL;
+	acl = posix_acl_alloc(count, GFP_NOFS);
+	if (!acl)
+		return ERR_PTR(-ENOMEM);
+	for (n = 0; n < count; n++) {
+		ext4_acl_entry *entry =
+			(ext4_acl_entry *)value;
+		if ((char *)value + sizeof(ext4_acl_entry_short) > end)
+			goto fail;
+		acl->a_entries[n].e_tag  = le16_to_cpu(entry->e_tag);
+		acl->a_entries[n].e_perm = le16_to_cpu(entry->e_perm);
+
+		switch (acl->a_entries[n].e_tag) {
+		case ACL_USER_OBJ:
+		case ACL_GROUP_OBJ:
+		case ACL_MASK:
+		case ACL_OTHER:
+			value = (char *)value +
+				sizeof(ext4_acl_entry_short);
+			break;
+
+		case ACL_USER:
+			value = (char *)value + sizeof(ext4_acl_entry);
+			if ((char *)value > end)
+				goto fail;
+			acl->a_entries[n].e_uid =
+				make_kuid(&init_user_ns,
+					  le32_to_cpu(entry->e_id));
+			break;
+		case ACL_GROUP:
+			value = (char *)value + sizeof(ext4_acl_entry);
+			if ((char *)value > end)
+				goto fail;
+			acl->a_entries[n].e_gid =
+				make_kgid(&init_user_ns,
+					  le32_to_cpu(entry->e_id));
+			break;
+
+		default:
+			goto fail;
+		}
+	}
+	if (value != end)
+		goto fail;
+	return acl;
+
+fail:
+	posix_acl_release(acl);
+	return ERR_PTR(-EINVAL);
+}
+
+/*
+ * Convert from in-memory to filesystem representation.
+ */
+static void *
+ext4_acl_to_disk(const struct posix_acl *acl, size_t *size)
+{
+	ext4_acl_header *ext_acl;
+	char *e;
+	size_t n;
+
+	*size = ext4_acl_size(acl->a_count);
+	ext_acl = kmalloc(sizeof(ext4_acl_header) + acl->a_count *
+			sizeof(ext4_acl_entry), GFP_NOFS);
+	if (!ext_acl)
+		return ERR_PTR(-ENOMEM);
+	ext_acl->a_version = cpu_to_le32(EXT4_ACL_VERSION);
+	e = (char *)ext_acl + sizeof(ext4_acl_header);
+	for (n = 0; n < acl->a_count; n++) {
+		const struct posix_acl_entry *acl_e = &acl->a_entries[n];
+		ext4_acl_entry *entry = (ext4_acl_entry *)e;
+		entry->e_tag  = cpu_to_le16(acl_e->e_tag);
+		entry->e_perm = cpu_to_le16(acl_e->e_perm);
+		switch (acl_e->e_tag) {
+		case ACL_USER:
+			entry->e_id = cpu_to_le32(
+				from_kuid(&init_user_ns, acl_e->e_uid));
+			e += sizeof(ext4_acl_entry);
+			break;
+		case ACL_GROUP:
+			entry->e_id = cpu_to_le32(
+				from_kgid(&init_user_ns, acl_e->e_gid));
+			e += sizeof(ext4_acl_entry);
+			break;
+
+		case ACL_USER_OBJ:
+		case ACL_GROUP_OBJ:
+		case ACL_MASK:
+		case ACL_OTHER:
+			e += sizeof(ext4_acl_entry_short);
+			break;
+
+		default:
+			goto fail;
+		}
+	}
+	return (char *)ext_acl;
+
+fail:
+	kfree(ext_acl);
+	return ERR_PTR(-EINVAL);
+}
+
+/*
+ * Inode operation get_posix_acl().
+ *
+ * inode->i_rwsem: don't care
+ */
+struct posix_acl *
+ext4_get_acl(struct inode *inode, int type, bool rcu)
+{
+	int name_index;
+	char *value = NULL;
+	struct posix_acl *acl;
+	int retval;
+
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT;
+		break;
+	default:
+		BUG();
+	}
+	retval = ext4_xattr_get(inode, name_index, "", NULL, 0);
+	if (retval > 0) {
+		value = kmalloc(retval, GFP_NOFS);
+		if (!value)
+			return ERR_PTR(-ENOMEM);
+		retval = ext4_xattr_get(inode, name_index, "", value, retval);
+	}
+	if (retval > 0)
+		acl = ext4_acl_from_disk(value, retval);
+	else if (retval == -ENODATA || retval == -ENOSYS)
+		acl = NULL;
+	else
+		acl = ERR_PTR(retval);
+	kfree(value);
+
+	return acl;
+}
+
+/*
+ * Set the access or default ACL of an inode.
+ *
+ * inode->i_rwsem: down unless called from ext4_new_inode
+ */
+static int
+__ext4_set_acl(handle_t *handle, struct inode *inode, int type,
+	     struct posix_acl *acl, int xattr_flags)
+{
+	int name_index;
+	void *value = NULL;
+	size_t size = 0;
+	int error;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
+		break;
+
+	case ACL_TYPE_DEFAULT:
+		name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT;
+		if (!S_ISDIR(inode->i_mode))
+			return acl ? -EACCES : 0;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+	if (acl) {
+		value = ext4_acl_to_disk(acl, &size);
+		if (IS_ERR(value))
+			return (int)PTR_ERR(value);
+	}
+
+	error = ext4_xattr_set_handle(handle, inode, name_index, "",
+				      value, size, xattr_flags);
+
+	kfree(value);
+	if (!error)
+		set_cached_acl(inode, type, acl);
+
+	return error;
+}
+
+int
+ext4_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
+	     struct posix_acl *acl, int type)
+{
+	handle_t *handle;
+	int error, credits, retries = 0;
+	size_t acl_size = acl ? ext4_acl_size(acl->a_count) : 0;
+	struct inode *inode = d_inode(dentry);
+	umode_t mode = inode->i_mode;
+	int update_mode = 0;
+
+	error = dquot_initialize(inode);
+	if (error)
+		return error;
+retry:
+	error = ext4_xattr_set_credits(inode, acl_size, false /* is_create */,
+				       &credits);
+	if (error)
+		return error;
+
+	handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	if ((type == ACL_TYPE_ACCESS) && acl) {
+		error = posix_acl_update_mode(idmap, inode, &mode, &acl);
+		if (error)
+			goto out_stop;
+		if (mode != inode->i_mode)
+			update_mode = 1;
+	}
+
+	error = __ext4_set_acl(handle, inode, type, acl, 0 /* xattr_flags */);
+	if (!error && update_mode) {
+		inode->i_mode = mode;
+		inode_set_ctime_current(inode);
+		error = ext4_mark_inode_dirty(handle, inode);
+	}
+out_stop:
+	ext4_journal_stop(handle);
+	if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+		goto retry;
+	return error;
+}
+
+/*
+ * Initialize the ACLs of a new inode. Called from ext4_new_inode.
+ *
+ * dir->i_rwsem: down
+ * inode->i_rwsem: up (access to inode is still exclusive)
+ */
+int
+ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
+{
+	struct posix_acl *default_acl, *acl;
+	int error;
+
+	error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
+	if (error)
+		return error;
+
+	if (default_acl) {
+		error = __ext4_set_acl(handle, inode, ACL_TYPE_DEFAULT,
+				       default_acl, XATTR_CREATE);
+		posix_acl_release(default_acl);
+	} else {
+		inode->i_default_acl = NULL;
+	}
+	if (acl) {
+		if (!error)
+			error = __ext4_set_acl(handle, inode, ACL_TYPE_ACCESS,
+					       acl, XATTR_CREATE);
+		posix_acl_release(acl);
+	} else {
+		inode->i_acl = NULL;
+	}
+	return error;
+}

linux-7.2.3/fs/ext4/acl.h

@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+  File: fs/ext4/acl.h
+
+  (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org>
+*/
+
+#include <linux/posix_acl_xattr.h>
+
+#define EXT4_ACL_VERSION	0x0001
+
+typedef struct {
+	__le16		e_tag;
+	__le16		e_perm;
+	__le32		e_id;
+} ext4_acl_entry;
+
+typedef struct {
+	__le16		e_tag;
+	__le16		e_perm;
+} ext4_acl_entry_short;
+
+typedef struct {
+	__le32		a_version;
+} ext4_acl_header;
+
+static inline size_t ext4_acl_size(int count)
+{
+	if (count <= 4) {
+		return sizeof(ext4_acl_header) +
+		       count * sizeof(ext4_acl_entry_short);
+	} else {
+		return sizeof(ext4_acl_header) +
+		       4 * sizeof(ext4_acl_entry_short) +
+		       (count - 4) * sizeof(ext4_acl_entry);
+	}
+}
+
+static inline int ext4_acl_count(size_t size)
+{
+	ssize_t s;
+	size -= sizeof(ext4_acl_header);
+	s = size - 4 * sizeof(ext4_acl_entry_short);
+	if (s < 0) {
+		if (size % sizeof(ext4_acl_entry_short))
+			return -1;
+		return size / sizeof(ext4_acl_entry_short);
+	} else {
+		if (s % sizeof(ext4_acl_entry))
+			return -1;
+		return s / sizeof(ext4_acl_entry) + 4;
+	}
+}
+
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
+
+/* acl.c */
+struct posix_acl *ext4_get_acl(struct inode *inode, int type, bool rcu);
+int ext4_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
+		 struct posix_acl *acl, int type);
+extern int ext4_init_acl(handle_t *, struct inode *, struct inode *);
+
+#else  /* CONFIG_EXT4_FS_POSIX_ACL */
+#include <linux/sched.h>
+#define ext4_get_acl NULL
+#define ext4_set_acl NULL
+
+static inline int
+ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
+{
+	return 0;
+}
+#endif  /* CONFIG_EXT4_FS_POSIX_ACL */
+

linux-7.2.3/fs/ext4/bitmap.c

@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/ext4/bitmap.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ */
+
+#include <linux/buffer_head.h>
+#include "ext4.h"
+
+unsigned int ext4_count_free(char *bitmap, unsigned int numchars)
+{
+	return numchars * BITS_PER_BYTE - memweight(bitmap, numchars);
+}
+
+int ext4_inode_bitmap_csum_verify(struct super_block *sb,
+				  struct ext4_group_desc *gdp,
+				  struct buffer_head *bh)
+{
+	__u32 hi;
+	__u32 provided, calculated;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int sz;
+
+	if (!ext4_has_feature_metadata_csum(sb))
+		return 1;
+
+	sz = EXT4_INODES_PER_GROUP(sb) >> 3;
+	provided = le16_to_cpu(gdp->bg_inode_bitmap_csum_lo);
+	calculated = ext4_chksum(sbi->s_csum_seed, (__u8 *)bh->b_data, sz);
+	if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END) {
+		hi = le16_to_cpu(gdp->bg_inode_bitmap_csum_hi);
+		provided |= (hi << 16);
+	} else
+		calculated &= 0xFFFF;
+
+	return provided == calculated;
+}
+
+void ext4_inode_bitmap_csum_set(struct super_block *sb,
+				struct ext4_group_desc *gdp,
+				struct buffer_head *bh)
+{
+	__u32 csum;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int sz;
+
+	if (!ext4_has_feature_metadata_csum(sb))
+		return;
+
+	sz = EXT4_INODES_PER_GROUP(sb) >> 3;
+	csum = ext4_chksum(sbi->s_csum_seed, (__u8 *)bh->b_data, sz);
+	gdp->bg_inode_bitmap_csum_lo = cpu_to_le16(csum & 0xFFFF);
+	if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END)
+		gdp->bg_inode_bitmap_csum_hi = cpu_to_le16(csum >> 16);
+}
+
+int ext4_block_bitmap_csum_verify(struct super_block *sb,
+				  struct ext4_group_desc *gdp,
+				  struct buffer_head *bh)
+{
+	__u32 hi;
+	__u32 provided, calculated;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8;
+
+	if (!ext4_has_feature_metadata_csum(sb))
+		return 1;
+
+	provided = le16_to_cpu(gdp->bg_block_bitmap_csum_lo);
+	calculated = ext4_chksum(sbi->s_csum_seed, (__u8 *)bh->b_data, sz);
+	if (sbi->s_desc_size >= EXT4_BG_BLOCK_BITMAP_CSUM_HI_END) {
+		hi = le16_to_cpu(gdp->bg_block_bitmap_csum_hi);
+		provided |= (hi << 16);
+	} else
+		calculated &= 0xFFFF;
+
+	return provided == calculated;
+}
+
+void ext4_block_bitmap_csum_set(struct super_block *sb,
+				struct ext4_group_desc *gdp,
+				struct buffer_head *bh)
+{
+	int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8;
+	__u32 csum;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (!ext4_has_feature_metadata_csum(sb))
+		return;
+
+	csum = ext4_chksum(sbi->s_csum_seed, (__u8 *)bh->b_data, sz);
+	gdp->bg_block_bitmap_csum_lo = cpu_to_le16(csum & 0xFFFF);
+	if (sbi->s_desc_size >= EXT4_BG_BLOCK_BITMAP_CSUM_HI_END)
+		gdp->bg_block_bitmap_csum_hi = cpu_to_le16(csum >> 16);
+}

linux-7.2.3/fs/ext4/block_validity.c

@@ -0,0 +1,370 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/ext4/block_validity.c
+ *
+ * Copyright (C) 2009
+ * Theodore Ts'o (tytso@mit.edu)
+ *
+ * Track which blocks in the filesystem are metadata blocks that
+ * should never be used as data blocks by files or directories.
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+#include <linux/swap.h>
+#include <linux/pagemap.h>
+#include <linux/blkdev.h>
+#include <linux/slab.h>
+#include "ext4.h"
+
+struct ext4_system_zone {
+	struct rb_node	node;
+	ext4_fsblk_t	start_blk;
+	unsigned int	count;
+	u32		ino;
+};
+
+static struct kmem_cache *ext4_system_zone_cachep;
+
+int __init ext4_init_system_zone(void)
+{
+	ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone, 0);
+	if (ext4_system_zone_cachep == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+void ext4_exit_system_zone(void)
+{
+	rcu_barrier();
+	kmem_cache_destroy(ext4_system_zone_cachep);
+}
+
+static inline int can_merge(struct ext4_system_zone *entry1,
+		     struct ext4_system_zone *entry2)
+{
+	if ((entry1->start_blk + entry1->count) == entry2->start_blk &&
+	    entry1->ino == entry2->ino)
+		return 1;
+	return 0;
+}
+
+static void release_system_zone(struct ext4_system_blocks *system_blks)
+{
+	struct ext4_system_zone	*entry, *n;
+
+	rbtree_postorder_for_each_entry_safe(entry, n,
+				&system_blks->root, node)
+		kmem_cache_free(ext4_system_zone_cachep, entry);
+}
+
+/*
+ * Mark a range of blocks as belonging to the "system zone" --- that
+ * is, filesystem metadata blocks which should never be used by
+ * inodes.
+ */
+static int add_system_zone(struct ext4_system_blocks *system_blks,
+			   ext4_fsblk_t start_blk,
+			   unsigned int count, u32 ino)
+{
+	struct ext4_system_zone *new_entry, *entry;
+	struct rb_node **n = &system_blks->root.rb_node, *node;
+	struct rb_node *parent = NULL, *new_node;
+
+	while (*n) {
+		parent = *n;
+		entry = rb_entry(parent, struct ext4_system_zone, node);
+		if (start_blk < entry->start_blk)
+			n = &(*n)->rb_left;
+		else if (start_blk >= (entry->start_blk + entry->count))
+			n = &(*n)->rb_right;
+		else	/* Unexpected overlap of system zones. */
+			return -EFSCORRUPTED;
+	}
+
+	new_entry = kmem_cache_alloc(ext4_system_zone_cachep,
+				     GFP_KERNEL);
+	if (!new_entry)
+		return -ENOMEM;
+	new_entry->start_blk = start_blk;
+	new_entry->count = count;
+	new_entry->ino = ino;
+	new_node = &new_entry->node;
+
+	rb_link_node(new_node, parent, n);
+	rb_insert_color(new_node, &system_blks->root);
+
+	/* Can we merge to the left? */
+	node = rb_prev(new_node);
+	if (node) {
+		entry = rb_entry(node, struct ext4_system_zone, node);
+		if (can_merge(entry, new_entry)) {
+			new_entry->start_blk = entry->start_blk;
+			new_entry->count += entry->count;
+			rb_erase(node, &system_blks->root);
+			kmem_cache_free(ext4_system_zone_cachep, entry);
+		}
+	}
+
+	/* Can we merge to the right? */
+	node = rb_next(new_node);
+	if (node) {
+		entry = rb_entry(node, struct ext4_system_zone, node);
+		if (can_merge(new_entry, entry)) {
+			new_entry->count += entry->count;
+			rb_erase(node, &system_blks->root);
+			kmem_cache_free(ext4_system_zone_cachep, entry);
+		}
+	}
+	return 0;
+}
+
+static void debug_print_tree(struct ext4_sb_info *sbi)
+{
+	struct rb_node *node;
+	struct ext4_system_zone *entry;
+	struct ext4_system_blocks *system_blks;
+	int first = 1;
+
+	printk(KERN_INFO "System zones: ");
+	rcu_read_lock();
+	system_blks = rcu_dereference(sbi->s_system_blks);
+	node = rb_first(&system_blks->root);
+	while (node) {
+		entry = rb_entry(node, struct ext4_system_zone, node);
+		printk(KERN_CONT "%s%llu-%llu", first ? "" : ", ",
+		       entry->start_blk, entry->start_blk + entry->count - 1);
+		first = 0;
+		node = rb_next(node);
+	}
+	rcu_read_unlock();
+	printk(KERN_CONT "\n");
+}
+
+static int ext4_protect_reserved_inode(struct super_block *sb,
+				       struct ext4_system_blocks *system_blks,
+				       u32 ino)
+{
+	struct inode *inode;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_map_blocks map;
+	u32 i = 0, num;
+	int err = 0, n;
+
+	if ((ino < EXT4_ROOT_INO) ||
+	    (ino > le32_to_cpu(sbi->s_es->s_inodes_count)))
+		return -EINVAL;
+	inode = ext4_iget(sb, ino, EXT4_IGET_SPECIAL);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+	num = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
+	while (i < num) {
+		cond_resched();
+		map.m_lblk = i;
+		map.m_len = num - i;
+		n = ext4_map_blocks(NULL, inode, &map, 0);
+		if (n < 0) {
+			err = n;
+			break;
+		}
+		if (n == 0) {
+			i++;
+		} else {
+			err = add_system_zone(system_blks, map.m_pblk, n, ino);
+			if (err < 0) {
+				if (err == -EFSCORRUPTED) {
+					EXT4_ERROR_INODE_ERR(inode, -err,
+						"blocks %llu-%llu from inode overlap system zone",
+						map.m_pblk,
+						map.m_pblk + map.m_len - 1);
+				}
+				break;
+			}
+			i += n;
+		}
+	}
+	iput(inode);
+	return err;
+}
+
+static void ext4_destroy_system_zone(struct rcu_head *rcu)
+{
+	struct ext4_system_blocks *system_blks;
+
+	system_blks = container_of(rcu, struct ext4_system_blocks, rcu);
+	release_system_zone(system_blks);
+	kfree(system_blks);
+}
+
+/*
+ * Build system zone rbtree which is used for block validity checking.
+ *
+ * The update of system_blks pointer in this function is protected by
+ * sb->s_umount semaphore. However we have to be careful as we can be
+ * racing with ext4_inode_block_valid() calls reading system_blks rbtree
+ * protected only by RCU. That's why we first build the rbtree and then
+ * swap it in place.
+ */
+int ext4_setup_system_zone(struct super_block *sb)
+{
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_system_blocks *system_blks;
+	struct ext4_group_desc *gdp;
+	ext4_group_t i;
+	int ret;
+
+	system_blks = kzalloc_obj(*system_blks);
+	if (!system_blks)
+		return -ENOMEM;
+
+	for (i=0; i < ngroups; i++) {
+		unsigned int meta_blks = ext4_num_base_meta_blocks(sb, i);
+
+		cond_resched();
+		if (meta_blks != 0) {
+			ret = add_system_zone(system_blks,
+					ext4_group_first_block_no(sb, i),
+					meta_blks, 0);
+			if (ret)
+				goto err;
+		}
+		gdp = ext4_get_group_desc(sb, i, NULL);
+		ret = add_system_zone(system_blks,
+				ext4_block_bitmap(sb, gdp), 1, 0);
+		if (ret)
+			goto err;
+		ret = add_system_zone(system_blks,
+				ext4_inode_bitmap(sb, gdp), 1, 0);
+		if (ret)
+			goto err;
+		ret = add_system_zone(system_blks,
+				ext4_inode_table(sb, gdp),
+				sbi->s_itb_per_group, 0);
+		if (ret)
+			goto err;
+	}
+	if (ext4_has_feature_journal(sb) && sbi->s_es->s_journal_inum) {
+		ret = ext4_protect_reserved_inode(sb, system_blks,
+				le32_to_cpu(sbi->s_es->s_journal_inum));
+		if (ret)
+			goto err;
+	}
+
+	/*
+	 * System blks rbtree complete, announce it once to prevent racing
+	 * with ext4_inode_block_valid() accessing the rbtree at the same
+	 * time.
+	 */
+	rcu_assign_pointer(sbi->s_system_blks, system_blks);
+
+	if (test_opt(sb, DEBUG))
+		debug_print_tree(sbi);
+	return 0;
+err:
+	release_system_zone(system_blks);
+	kfree(system_blks);
+	return ret;
+}
+
+/*
+ * Called when the filesystem is unmounted or when remounting it with
+ * noblock_validity specified.
+ *
+ * The update of system_blks pointer in this function is protected by
+ * sb->s_umount semaphore. However we have to be careful as we can be
+ * racing with ext4_inode_block_valid() calls reading system_blks rbtree
+ * protected only by RCU. So we first clear the system_blks pointer and
+ * then free the rbtree only after RCU grace period expires.
+ */
+void ext4_release_system_zone(struct super_block *sb)
+{
+	struct ext4_system_blocks *system_blks;
+
+	system_blks = rcu_dereference_protected(EXT4_SB(sb)->s_system_blks,
+					lockdep_is_held(&sb->s_umount));
+	rcu_assign_pointer(EXT4_SB(sb)->s_system_blks, NULL);
+
+	if (system_blks)
+		call_rcu(&system_blks->rcu, ext4_destroy_system_zone);
+}
+
+int ext4_sb_block_valid(struct super_block *sb, struct inode *inode,
+				ext4_fsblk_t start_blk, unsigned int count)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_system_blocks *system_blks;
+	struct ext4_system_zone *entry;
+	struct rb_node *n;
+	int ret = 1;
+
+	if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
+	    (start_blk + count < start_blk) ||
+	    (start_blk + count > ext4_blocks_count(sbi->s_es)))
+		return 0;
+
+	/*
+	 * Lock the system zone to prevent it being released concurrently
+	 * when doing a remount which inverse current "[no]block_validity"
+	 * mount option.
+	 */
+	rcu_read_lock();
+	system_blks = rcu_dereference(sbi->s_system_blks);
+	if (system_blks == NULL)
+		goto out_rcu;
+
+	n = system_blks->root.rb_node;
+	while (n) {
+		entry = rb_entry(n, struct ext4_system_zone, node);
+		if (start_blk + count - 1 < entry->start_blk)
+			n = n->rb_left;
+		else if (start_blk >= (entry->start_blk + entry->count))
+			n = n->rb_right;
+		else {
+			ret = 0;
+			if (inode)
+				ret = (entry->ino == inode->i_ino);
+			break;
+		}
+	}
+out_rcu:
+	rcu_read_unlock();
+	return ret;
+}
+
+/*
+ * Returns 1 if the passed-in block region (start_blk,
+ * start_blk+count) is valid; 0 if some part of the block region
+ * overlaps with some other filesystem metadata blocks.
+ */
+int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
+			  unsigned int count)
+{
+	return ext4_sb_block_valid(inode->i_sb, inode, start_blk, count);
+}
+
+int ext4_check_blockref(const char *function, unsigned int line,
+			struct inode *inode, __le32 *p, unsigned int max)
+{
+	__le32 *bref = p;
+	unsigned int blk;
+	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+
+	if (journal && inode == journal->j_inode)
+		return 0;
+
+	while (bref < p+max) {
+		blk = le32_to_cpu(*bref++);
+		if (blk &&
+		    unlikely(!ext4_inode_block_valid(inode, blk, 1))) {
+			ext4_error_inode(inode, function, line, blk,
+					 "invalid block");
+			return -EFSCORRUPTED;
+		}
+	}
+	return 0;
+}
+

linux-7.2.3/fs/ext4/crypto.c

@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/quotaops.h>
+#include <linux/uuid.h>
+
+#include "ext4.h"
+#include "xattr.h"
+#include "ext4_jbd2.h"
+
+static void ext4_fname_from_fscrypt_name(struct ext4_filename *dst,
+					 const struct fscrypt_name *src)
+{
+	memset(dst, 0, sizeof(*dst));
+
+	dst->usr_fname = src->usr_fname;
+	dst->disk_name = src->disk_name;
+	dst->hinfo.hash = src->hash;
+	dst->hinfo.minor_hash = src->minor_hash;
+	dst->crypto_buf = src->crypto_buf;
+}
+
+int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname,
+			      int lookup, struct ext4_filename *fname)
+{
+	struct fscrypt_name name;
+	int err;
+
+	err = fscrypt_setup_filename(dir, iname, lookup, &name);
+	if (err)
+		return err;
+
+	ext4_fname_from_fscrypt_name(fname, &name);
+
+	err = ext4_fname_setup_ci_filename(dir, iname, fname);
+	if (err)
+		ext4_fname_free_filename(fname);
+
+	return err;
+}
+
+int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry,
+			      struct ext4_filename *fname)
+{
+	struct fscrypt_name name;
+	int err;
+
+	err = fscrypt_prepare_lookup(dir, dentry, &name);
+	if (err)
+		return err;
+
+	ext4_fname_from_fscrypt_name(fname, &name);
+
+	err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname);
+	if (err)
+		ext4_fname_free_filename(fname);
+	return err;
+}
+
+void ext4_fname_free_filename(struct ext4_filename *fname)
+{
+	struct fscrypt_name name;
+
+	name.crypto_buf = fname->crypto_buf;
+	fscrypt_free_filename(&name);
+
+	fname->crypto_buf.name = NULL;
+	fname->usr_fname = NULL;
+	fname->disk_name.name = NULL;
+
+	ext4_fname_free_ci_filename(fname);
+}
+
+static bool uuid_is_zero(__u8 u[16])
+{
+	int i;
+
+	for (i = 0; i < 16; i++)
+		if (u[i])
+			return false;
+	return true;
+}
+
+int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg)
+{
+	struct super_block *sb = file_inode(filp)->i_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int err, err2;
+	handle_t *handle;
+
+	if (!ext4_has_feature_encrypt(sb))
+		return -EOPNOTSUPP;
+
+	if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) {
+		err = mnt_want_write_file(filp);
+		if (err)
+			return err;
+		handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
+		if (IS_ERR(handle)) {
+			err = PTR_ERR(handle);
+			goto pwsalt_err_exit;
+		}
+		err = ext4_journal_get_write_access(handle, sb, sbi->s_sbh,
+						    EXT4_JTR_NONE);
+		if (err)
+			goto pwsalt_err_journal;
+		lock_buffer(sbi->s_sbh);
+		generate_random_uuid(sbi->s_es->s_encrypt_pw_salt);
+		ext4_superblock_csum_set(sb);
+		unlock_buffer(sbi->s_sbh);
+		err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
+pwsalt_err_journal:
+		err2 = ext4_journal_stop(handle);
+		if (err2 && !err)
+			err = err2;
+pwsalt_err_exit:
+		mnt_drop_write_file(filp);
+		if (err)
+			return err;
+	}
+
+	if (copy_to_user(arg, sbi->s_es->s_encrypt_pw_salt, 16))
+		return -EFAULT;
+	return 0;
+}
+
+static int ext4_get_context(struct inode *inode, void *ctx, size_t len)
+{
+	return ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len);
+}
+
+static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
+							void *fs_data)
+{
+	handle_t *handle = fs_data;
+	int res, res2, credits, retries = 0;
+
+	/*
+	 * Encrypting the root directory is not allowed because e2fsck expects
+	 * lost+found to exist and be unencrypted, and encrypting the root
+	 * directory would imply encrypting the lost+found directory as well as
+	 * the filename "lost+found" itself.
+	 */
+	if (inode->i_ino == EXT4_ROOT_INO)
+		return -EPERM;
+
+	/*
+	 * For new encrypted inodes, S_DAX is never set in the first place.
+	 *
+	 * For existing inodes, this is called only on empty directories.  ext4
+	 * never sets S_DAX on directories.
+	 */
+	if (WARN_ON_ONCE(IS_DAX(inode)))
+		return -EINVAL;
+
+	if (ext4_test_inode_flag(inode, EXT4_INODE_DAX))
+		return -EOPNOTSUPP;
+
+	res = ext4_convert_inline_data(inode);
+	if (res)
+		return res;
+
+	/*
+	 * If a journal handle was specified, then the encryption context is
+	 * being set on a new inode via inheritance and is part of a larger
+	 * transaction to create the inode.  Otherwise the encryption context is
+	 * being set on an existing inode in its own transaction.  Only in the
+	 * latter case should the "retry on ENOSPC" logic be used.
+	 */
+
+	if (handle) {
+		/*
+		 * __ext4_new_inode() should have already set the encrypt flag
+		 * on the inode and avoided enabling inline data.
+		 */
+		if (WARN_ON_ONCE(!IS_ENCRYPTED(inode)))
+			return -EINVAL;
+		if (WARN_ON_ONCE(ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)))
+			return -EINVAL;
+		/*
+		 * Since the inode is new it is ok to pass the
+		 * XATTR_CREATE flag. This is necessary to match the
+		 * remaining journal credits check in the set_handle
+		 * function with the credits allocated for the new
+		 * inode.
+		 */
+		return ext4_xattr_set_handle(handle, inode,
+					     EXT4_XATTR_INDEX_ENCRYPTION,
+					     EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+					     ctx, len, XATTR_CREATE);
+	}
+
+	res = dquot_initialize(inode);
+	if (res)
+		return res;
+retry:
+	res = ext4_xattr_set_credits(inode, len, false /* is_create */,
+				     &credits);
+	if (res)
+		return res;
+
+	handle = ext4_journal_start(inode, EXT4_HT_MISC, credits);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION,
+				    EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+				    ctx, len, 0);
+	if (!res) {
+		ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
+		/* Update inode->i_flags to set S_ENCRYPTED. */
+		ext4_set_inode_flags(inode, false);
+		res = ext4_mark_inode_dirty(handle, inode);
+		if (res)
+			EXT4_ERROR_INODE(inode, "Failed to mark inode dirty");
+	}
+	res2 = ext4_journal_stop(handle);
+
+	if (res == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+		goto retry;
+	if (!res)
+		res = res2;
+	return res;
+}
+
+static const union fscrypt_policy *ext4_get_dummy_policy(struct super_block *sb)
+{
+	return EXT4_SB(sb)->s_dummy_enc_policy.policy;
+}
+
+static bool ext4_has_stable_inodes(struct super_block *sb)
+{
+	return ext4_has_feature_stable_inodes(sb);
+}
+
+const struct fscrypt_operations ext4_cryptops = {
+	.inode_info_offs	= (int)offsetof(struct ext4_inode_info, i_crypt_info) -
+				  (int)offsetof(struct ext4_inode_info, vfs_inode),
+	.needs_bounce_pages	= 1,
+	.has_32bit_inodes	= 1,
+	.supports_subblock_data_units = 1,
+	.legacy_key_prefix	= "ext4:",
+	.get_context		= ext4_get_context,
+	.set_context		= ext4_set_context,
+	.get_dummy_policy	= ext4_get_dummy_policy,
+	.empty_dir		= ext4_empty_dir,
+	.has_stable_inodes	= ext4_has_stable_inodes,
+};

linux-7.2.3/fs/ext4/dir.c

@@ -0,0 +1,694 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/ext4/dir.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  from
+ *
+ *  linux/fs/minix/dir.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  ext4 directory handling functions
+ *
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ *
+ * Hash Tree Directory indexing (c) 2001  Daniel Phillips
+ *
+ */
+
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/filelock.h>
+#include <linux/slab.h>
+#include <linux/iversion.h>
+#include <linux/unicode.h>
+#include "ext4.h"
+#include "xattr.h"
+
+static int ext4_dx_readdir(struct file *, struct dir_context *);
+
+/**
+ * is_dx_dir() - check if a directory is using htree indexing
+ * @inode: directory inode
+ *
+ * Check if the given dir-inode refers to an htree-indexed directory
+ * (or a directory which could potentially get converted to use htree
+ * indexing).
+ *
+ * Return 1 if it is a dx dir, 0 if not
+ */
+static int is_dx_dir(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+
+	if (ext4_has_feature_dir_index(inode->i_sb) &&
+	    ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) ||
+	     ((inode->i_size >> sb->s_blocksize_bits) == 1) ||
+	     ext4_has_inline_data(inode)))
+		return 1;
+
+	return 0;
+}
+
+static bool is_fake_dir_entry(struct ext4_dir_entry_2 *de)
+{
+	/* Check if . or .. , or skip if namelen is 0 */
+	if ((de->name_len > 0) && (de->name_len <= 2) && (de->name[0] == '.') &&
+	    (de->name[1] == '.' || de->name[1] == '\0'))
+		return true;
+	/* Check if this is a csum entry */
+	if (de->file_type == EXT4_FT_DIR_CSUM)
+		return true;
+	return false;
+}
+
+/*
+ * Return 0 if the directory entry is OK, and 1 if there is a problem
+ *
+ * Note: this is the opposite of what ext2 and ext3 historically returned...
+ *
+ * bh passed here can be an inode block or a dir data block, depending
+ * on the inode inline data flag.
+ */
+int __ext4_check_dir_entry(const char *function, unsigned int line,
+			   struct inode *dir, struct file *filp,
+			   struct ext4_dir_entry_2 *de,
+			   struct buffer_head *bh, char *buf, int size,
+			   unsigned int offset)
+{
+	const char *error_msg = NULL;
+	const int rlen = ext4_rec_len_from_disk(de->rec_len,
+						dir->i_sb->s_blocksize);
+	const int next_offset = ((char *) de - buf) + rlen;
+	bool fake = is_fake_dir_entry(de);
+	bool has_csum = ext4_has_feature_metadata_csum(dir->i_sb);
+
+	if (unlikely(rlen < ext4_dir_rec_len(1, fake ? NULL : dir)))
+		error_msg = "rec_len is smaller than minimal";
+	else if (unlikely(rlen % 4 != 0))
+		error_msg = "rec_len % 4 != 0";
+	else if (unlikely(rlen < ext4_dir_rec_len(de->name_len,
+							fake ? NULL : dir)))
+		error_msg = "rec_len is too small for name_len";
+	else if (unlikely(next_offset > size))
+		error_msg = "directory entry overrun";
+	else if (unlikely(next_offset > size - ext4_dir_rec_len(1,
+						  has_csum ? NULL : dir) &&
+			  next_offset != size))
+		error_msg = "directory entry too close to block end";
+	else if (unlikely(le32_to_cpu(de->inode) >
+			le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count)))
+		error_msg = "inode out of bounds";
+	else if (unlikely(next_offset == size && de->name_len == 1 &&
+			  de->name[0] == '.'))
+		error_msg = "'.' directory cannot be the last in data block";
+	else
+		return 0;
+
+	if (filp)
+		ext4_error_file(filp, function, line, bh->b_blocknr,
+				"bad entry in directory: %s - offset=%u, "
+				"inode=%u, rec_len=%d, size=%d fake=%d",
+				error_msg, offset, le32_to_cpu(de->inode),
+				rlen, size, fake);
+	else
+		ext4_error_inode(dir, function, line, bh->b_blocknr,
+				"bad entry in directory: %s - offset=%u, "
+				"inode=%u, rec_len=%d, size=%d fake=%d",
+				 error_msg, offset, le32_to_cpu(de->inode),
+				 rlen, size, fake);
+
+	return 1;
+}
+
+static int ext4_readdir(struct file *file, struct dir_context *ctx)
+{
+	unsigned int offset;
+	int i;
+	struct ext4_dir_entry_2 *de;
+	int err;
+	struct inode *inode = file_inode(file);
+	struct super_block *sb = inode->i_sb;
+	struct buffer_head *bh = NULL;
+	struct fscrypt_str fstr = FSTR_INIT(NULL, 0);
+	struct dir_private_info *info = file->private_data;
+
+	err = fscrypt_prepare_readdir(inode);
+	if (err)
+		return err;
+
+	if (is_dx_dir(inode)) {
+		err = ext4_dx_readdir(file, ctx);
+		if (err != ERR_BAD_DX_DIR)
+			return err;
+
+		/* Can we just clear INDEX flag to ignore htree information? */
+		if (!ext4_has_feature_metadata_csum(sb)) {
+			/*
+			 * We don't set the inode dirty flag since it's not
+			 * critical that it gets flushed back to the disk.
+			 */
+			ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
+		}
+	}
+
+	if (ext4_has_inline_data(inode)) {
+		int has_inline_data = 1;
+		err = ext4_read_inline_dir(file, ctx,
+					   &has_inline_data);
+		if (has_inline_data)
+			return err;
+	}
+
+	if (IS_ENCRYPTED(inode)) {
+		err = fscrypt_fname_alloc_buffer(EXT4_NAME_LEN, &fstr);
+		if (err < 0)
+			return err;
+	}
+
+	while (ctx->pos < inode->i_size) {
+		struct ext4_map_blocks map;
+
+		if (fatal_signal_pending(current)) {
+			err = -ERESTARTSYS;
+			goto errout;
+		}
+		cond_resched();
+		offset = ctx->pos & (sb->s_blocksize - 1);
+		map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb);
+		map.m_len = 1;
+		err = ext4_map_blocks(NULL, inode, &map, 0);
+		if (err == 0) {
+			/* m_len should never be zero but let's avoid
+			 * an infinite loop if it somehow is */
+			if (map.m_len == 0)
+				map.m_len = 1;
+			ctx->pos += map.m_len * sb->s_blocksize;
+			continue;
+		}
+		if (err > 0) {
+			pgoff_t index = map.m_pblk << inode->i_blkbits >>
+					PAGE_SHIFT;
+			if (!ra_has_index(&file->f_ra, index))
+				page_cache_sync_readahead(
+					sb->s_bdev->bd_mapping,
+					&file->f_ra, file, index,
+					1 << EXT4_SB(sb)->s_min_folio_order);
+			file->f_ra.prev_pos = (loff_t)index << PAGE_SHIFT;
+			bh = ext4_bread(NULL, inode, map.m_lblk, 0);
+			if (IS_ERR(bh)) {
+				err = PTR_ERR(bh);
+				bh = NULL;
+				goto errout;
+			}
+		}
+
+		if (!bh) {
+			/* corrupt size?  Maybe no more blocks to read */
+			if (ctx->pos > inode->i_blocks << 9)
+				break;
+			ctx->pos += sb->s_blocksize - offset;
+			continue;
+		}
+
+		/* Check the checksum */
+		if (!buffer_verified(bh) &&
+		    !ext4_dirblock_csum_verify(inode, bh)) {
+			EXT4_ERROR_FILE(file, 0, "directory fails checksum "
+					"at offset %llu",
+					(unsigned long long)ctx->pos);
+			ctx->pos += sb->s_blocksize - offset;
+			brelse(bh);
+			bh = NULL;
+			continue;
+		}
+		set_buffer_verified(bh);
+
+		/* If the dir block has changed since the last call to
+		 * readdir(2), then we might be pointing to an invalid
+		 * dirent right now.  Scan from the start of the block
+		 * to make sure. */
+		if (!inode_eq_iversion(inode, info->cookie)) {
+			for (i = 0; i < sb->s_blocksize && i < offset; ) {
+				de = (struct ext4_dir_entry_2 *)
+					(bh->b_data + i);
+				/* It's too expensive to do a full
+				 * dirent test each time round this
+				 * loop, but we do have to test at
+				 * least that it is non-zero.  A
+				 * failure will be detected in the
+				 * dirent test below. */
+				if (ext4_rec_len_from_disk(de->rec_len,
+					sb->s_blocksize) < ext4_dir_rec_len(1,
+									inode))
+					break;
+				i += ext4_rec_len_from_disk(de->rec_len,
+							    sb->s_blocksize);
+			}
+			offset = i;
+			ctx->pos = (ctx->pos & ~(sb->s_blocksize - 1))
+				| offset;
+			info->cookie = inode_query_iversion(inode);
+		}
+
+		while (ctx->pos < inode->i_size
+		       && offset < sb->s_blocksize) {
+			de = (struct ext4_dir_entry_2 *) (bh->b_data + offset);
+			if (ext4_check_dir_entry(inode, file, de, bh,
+						 bh->b_data, bh->b_size,
+						 offset)) {
+				/*
+				 * On error, skip to the next block
+				 */
+				ctx->pos = (ctx->pos |
+						(sb->s_blocksize - 1)) + 1;
+				break;
+			}
+			offset += ext4_rec_len_from_disk(de->rec_len,
+					sb->s_blocksize);
+			if (le32_to_cpu(de->inode)) {
+				if (!IS_ENCRYPTED(inode)) {
+					if (!dir_emit(ctx, de->name,
+					    de->name_len,
+					    le32_to_cpu(de->inode),
+					    get_dtype(sb, de->file_type)))
+						goto done;
+				} else {
+					int save_len = fstr.len;
+					struct fscrypt_str de_name =
+							FSTR_INIT(de->name,
+								de->name_len);
+					u32 hash;
+					u32 minor_hash;
+
+					if (IS_CASEFOLDED(inode)) {
+						hash = EXT4_DIRENT_HASH(de);
+						minor_hash = EXT4_DIRENT_MINOR_HASH(de);
+					} else {
+						hash = 0;
+						minor_hash = 0;
+					}
+
+					/* Directory is encrypted */
+					err = fscrypt_fname_disk_to_usr(inode,
+						hash, minor_hash, &de_name, &fstr);
+					de_name = fstr;
+					fstr.len = save_len;
+					if (err)
+						goto errout;
+					if (!dir_emit(ctx,
+					    de_name.name, de_name.len,
+					    le32_to_cpu(de->inode),
+					    get_dtype(sb, de->file_type)))
+						goto done;
+				}
+			}
+			ctx->pos += ext4_rec_len_from_disk(de->rec_len,
+						sb->s_blocksize);
+		}
+		if ((ctx->pos < inode->i_size) && !dir_relax_shared(inode))
+			goto done;
+		brelse(bh);
+		bh = NULL;
+	}
+done:
+	err = 0;
+errout:
+	fscrypt_fname_free_buffer(&fstr);
+	brelse(bh);
+	return err;
+}
+
+static inline int is_32bit_api(void)
+{
+#ifdef CONFIG_COMPAT
+	return in_compat_syscall();
+#else
+	return (BITS_PER_LONG == 32);
+#endif
+}
+
+/*
+ * These functions convert from the major/minor hash to an f_pos
+ * value for dx directories
+ *
+ * Upper layer (for example NFS) should specify FMODE_32BITHASH or
+ * FMODE_64BITHASH explicitly. On the other hand, we allow ext4 to be mounted
+ * directly on both 32-bit and 64-bit nodes, under such case, neither
+ * FMODE_32BITHASH nor FMODE_64BITHASH is specified.
+ */
+static inline loff_t hash2pos(struct file *filp, __u32 major, __u32 minor)
+{
+	if ((filp->f_mode & FMODE_32BITHASH) ||
+	    (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+		return major >> 1;
+	else
+		return ((__u64)(major >> 1) << 32) | (__u64)minor;
+}
+
+static inline __u32 pos2maj_hash(struct file *filp, loff_t pos)
+{
+	if ((filp->f_mode & FMODE_32BITHASH) ||
+	    (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+		return (pos << 1) & 0xffffffff;
+	else
+		return ((pos >> 32) << 1) & 0xffffffff;
+}
+
+static inline __u32 pos2min_hash(struct file *filp, loff_t pos)
+{
+	if ((filp->f_mode & FMODE_32BITHASH) ||
+	    (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+		return 0;
+	else
+		return pos & 0xffffffff;
+}
+
+/*
+ * Return 32- or 64-bit end-of-file for dx directories
+ */
+static inline loff_t ext4_get_htree_eof(struct file *filp)
+{
+	if ((filp->f_mode & FMODE_32BITHASH) ||
+	    (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+		return EXT4_HTREE_EOF_32BIT;
+	else
+		return EXT4_HTREE_EOF_64BIT;
+}
+
+
+/*
+ * ext4_dir_llseek() calls generic_file_llseek_size to handle htree
+ * directories, where the "offset" is in terms of the filename hash
+ * value instead of the byte offset.
+ *
+ * Because we may return a 64-bit hash that is well beyond offset limits,
+ * we need to pass the max hash as the maximum allowable offset in
+ * the htree directory case.
+ *
+ * For non-htree, ext4_llseek already chooses the proper max offset.
+ */
+static loff_t ext4_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct inode *inode = file->f_mapping->host;
+	struct dir_private_info *info = file->private_data;
+	int dx_dir = is_dx_dir(inode);
+	loff_t ret, htree_max = ext4_get_htree_eof(file);
+
+	if (likely(dx_dir))
+		ret = generic_file_llseek_size(file, offset, whence,
+						    htree_max, htree_max);
+	else
+		ret = ext4_llseek(file, offset, whence);
+	info->cookie = inode_peek_iversion(inode) - 1;
+	return ret;
+}
+
+/*
+ * This structure holds the nodes of the red-black tree used to store
+ * the directory entry in hash order.
+ */
+struct fname {
+	__u32		hash;
+	__u32		minor_hash;
+	struct rb_node	rb_hash;
+	struct fname	*next;
+	__u32		inode;
+	__u8		name_len;
+	__u8		file_type;
+	char		name[] __counted_by(name_len);
+};
+
+/*
+ * This function implements a non-recursive way of freeing all of the
+ * nodes in the red-black tree.
+ */
+static void free_rb_tree_fname(struct rb_root *root)
+{
+	struct fname *fname, *next;
+
+	rbtree_postorder_for_each_entry_safe(fname, next, root, rb_hash)
+		while (fname) {
+			struct fname *old = fname;
+			fname = fname->next;
+			kfree(old);
+		}
+
+	*root = RB_ROOT;
+}
+
+static void ext4_htree_init_dir_info(struct file *filp, loff_t pos)
+{
+	struct dir_private_info *p = filp->private_data;
+
+	if (is_dx_dir(file_inode(filp)) && !p->initialized) {
+		p->curr_hash = pos2maj_hash(filp, pos);
+		p->curr_minor_hash = pos2min_hash(filp, pos);
+		p->initialized = true;
+	}
+}
+
+void ext4_htree_free_dir_info(struct dir_private_info *p)
+{
+	free_rb_tree_fname(&p->root);
+	kfree(p);
+}
+
+/*
+ * Given a directory entry, enter it into the fname rb tree.
+ *
+ * When filename encryption is enabled, the dirent will hold the
+ * encrypted filename, while the htree will hold decrypted filename.
+ * The decrypted filename is passed in via ent_name.  parameter.
+ */
+int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
+			     __u32 minor_hash,
+			    struct ext4_dir_entry_2 *dirent,
+			    struct fscrypt_str *ent_name)
+{
+	struct rb_node **p, *parent = NULL;
+	struct fname *fname, *new_fn;
+	struct dir_private_info *info;
+
+	info = dir_file->private_data;
+	p = &info->root.rb_node;
+
+	/* Create and allocate the fname structure */
+	new_fn = kzalloc_flex(*new_fn, name, ent_name->len + 1);
+	if (!new_fn)
+		return -ENOMEM;
+	new_fn->hash = hash;
+	new_fn->minor_hash = minor_hash;
+	new_fn->inode = le32_to_cpu(dirent->inode);
+	new_fn->name_len = ent_name->len;
+	new_fn->file_type = dirent->file_type;
+	memcpy(new_fn->name, ent_name->name, ent_name->len);
+
+	while (*p) {
+		parent = *p;
+		fname = rb_entry(parent, struct fname, rb_hash);
+
+		/*
+		 * If the hash and minor hash match up, then we put
+		 * them on a linked list.  This rarely happens...
+		 */
+		if ((new_fn->hash == fname->hash) &&
+		    (new_fn->minor_hash == fname->minor_hash)) {
+			new_fn->next = fname->next;
+			fname->next = new_fn;
+			return 0;
+		}
+
+		if (new_fn->hash < fname->hash)
+			p = &(*p)->rb_left;
+		else if (new_fn->hash > fname->hash)
+			p = &(*p)->rb_right;
+		else if (new_fn->minor_hash < fname->minor_hash)
+			p = &(*p)->rb_left;
+		else /* if (new_fn->minor_hash > fname->minor_hash) */
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&new_fn->rb_hash, parent, p);
+	rb_insert_color(&new_fn->rb_hash, &info->root);
+	return 0;
+}
+
+
+
+/*
+ * This is a helper function for ext4_dx_readdir.  It calls filldir
+ * for all entries on the fname linked list.  (Normally there is only
+ * one entry on the linked list, unless there are 62 bit hash collisions.)
+ */
+static int call_filldir(struct file *file, struct dir_context *ctx,
+			struct fname *fname)
+{
+	struct dir_private_info *info = file->private_data;
+	struct inode *inode = file_inode(file);
+	struct super_block *sb = inode->i_sb;
+
+	if (!fname) {
+		ext4_msg(sb, KERN_ERR, "%s:%d: inode #%llu: comm %s: "
+			 "called with null fname?!?", __func__, __LINE__,
+			 inode->i_ino, current->comm);
+		return 0;
+	}
+	ctx->pos = hash2pos(file, fname->hash, fname->minor_hash);
+	while (fname) {
+		if (!dir_emit(ctx, fname->name,
+				fname->name_len,
+				fname->inode,
+				get_dtype(sb, fname->file_type))) {
+			info->extra_fname = fname;
+			return 1;
+		}
+		fname = fname->next;
+	}
+	return 0;
+}
+
+static int ext4_dx_readdir(struct file *file, struct dir_context *ctx)
+{
+	struct dir_private_info *info = file->private_data;
+	struct inode *inode = file_inode(file);
+	struct fname *fname;
+	int ret = 0;
+
+	ext4_htree_init_dir_info(file, ctx->pos);
+
+	if (ctx->pos == ext4_get_htree_eof(file))
+		return 0;	/* EOF */
+
+	/* Some one has messed with f_pos; reset the world */
+	if (info->last_pos != ctx->pos) {
+		free_rb_tree_fname(&info->root);
+		info->curr_node = NULL;
+		info->extra_fname = NULL;
+		info->curr_hash = pos2maj_hash(file, ctx->pos);
+		info->curr_minor_hash = pos2min_hash(file, ctx->pos);
+	}
+
+	/*
+	 * If there are any leftover names on the hash collision
+	 * chain, return them first.
+	 */
+	if (info->extra_fname) {
+		if (call_filldir(file, ctx, info->extra_fname))
+			goto finished;
+		info->extra_fname = NULL;
+		goto next_node;
+	} else if (!info->curr_node)
+		info->curr_node = rb_first(&info->root);
+
+	while (1) {
+		/*
+		 * Fill the rbtree if we have no more entries,
+		 * or the inode has changed since we last read in the
+		 * cached entries.
+		 */
+		if ((!info->curr_node) ||
+		    !inode_eq_iversion(inode, info->cookie)) {
+			info->curr_node = NULL;
+			free_rb_tree_fname(&info->root);
+			info->cookie = inode_query_iversion(inode);
+			ret = ext4_htree_fill_tree(file, info->curr_hash,
+						   info->curr_minor_hash,
+						   &info->next_hash);
+			if (ret < 0)
+				goto finished;
+			if (ret == 0) {
+				ctx->pos = ext4_get_htree_eof(file);
+				break;
+			}
+			info->curr_node = rb_first(&info->root);
+		}
+
+		fname = rb_entry(info->curr_node, struct fname, rb_hash);
+		info->curr_hash = fname->hash;
+		info->curr_minor_hash = fname->minor_hash;
+		if (call_filldir(file, ctx, fname))
+			break;
+	next_node:
+		info->curr_node = rb_next(info->curr_node);
+		if (info->curr_node) {
+			fname = rb_entry(info->curr_node, struct fname,
+					 rb_hash);
+			info->curr_hash = fname->hash;
+			info->curr_minor_hash = fname->minor_hash;
+		} else {
+			if (info->next_hash == ~0) {
+				ctx->pos = ext4_get_htree_eof(file);
+				break;
+			}
+			info->curr_hash = info->next_hash;
+			info->curr_minor_hash = 0;
+		}
+	}
+finished:
+	info->last_pos = ctx->pos;
+	return ret < 0 ? ret : 0;
+}
+
+static int ext4_release_dir(struct inode *inode, struct file *filp)
+{
+	if (filp->private_data)
+		ext4_htree_free_dir_info(filp->private_data);
+
+	return 0;
+}
+
+int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf,
+		      int buf_size)
+{
+	struct ext4_dir_entry_2 *de;
+	int rlen;
+	unsigned int offset = 0;
+	char *top;
+
+	de = buf;
+	top = buf + buf_size;
+	while ((char *) de < top) {
+		if (ext4_check_dir_entry(dir, NULL, de, bh,
+					 buf, buf_size, offset))
+			return -EFSCORRUPTED;
+		rlen = ext4_rec_len_from_disk(de->rec_len, buf_size);
+		de = (struct ext4_dir_entry_2 *)((char *)de + rlen);
+		offset += rlen;
+	}
+	if ((char *) de > top)
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+static int ext4_dir_open(struct inode *inode, struct file *file)
+{
+	struct dir_private_info *info;
+
+	info = kzalloc_obj(*info);
+	if (!info)
+		return -ENOMEM;
+	file->private_data = info;
+	return 0;
+}
+
+const struct file_operations ext4_dir_operations = {
+	.open		= ext4_dir_open,
+	.llseek		= ext4_dir_llseek,
+	.read		= generic_read_dir,
+	.iterate_shared	= ext4_readdir,
+	.unlocked_ioctl = ext4_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext4_compat_ioctl,
+#endif
+	.fsync		= ext4_sync_file,
+	.release	= ext4_release_dir,
+	.setlease	= generic_setlease,
+};

linux-7.2.3/fs/ext4/ext4_extents.h

@@ -0,0 +1,280 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com
+ * Written by Alex Tomas <alex@clusterfs.com>
+ */
+
+#ifndef _EXT4_EXTENTS
+#define _EXT4_EXTENTS
+
+#include "ext4.h"
+
+/*
+ * With AGGRESSIVE_TEST defined, the capacity of index/leaf blocks
+ * becomes very small, so index split, in-depth growing and
+ * other hard changes happen much more often.
+ * This is for debug purposes only.
+ */
+#define AGGRESSIVE_TEST_
+
+/*
+ * With EXTENTS_STATS defined, the number of blocks and extents
+ * are collected in the truncate path. They'll be shown at
+ * umount time.
+ */
+#define EXTENTS_STATS__
+
+/*
+ * If CHECK_BINSEARCH is defined, then the results of the binary search
+ * will also be checked by linear search.
+ */
+#define CHECK_BINSEARCH__
+
+/*
+ * ext4_inode has i_block array (60 bytes total).
+ * The first 12 bytes store ext4_extent_header;
+ * the remainder stores an array of ext4_extent.
+ * For non-inode extent blocks, ext4_extent_tail
+ * follows the array.
+ */
+
+/*
+ * This is the extent tail on-disk structure.
+ * All other extent structures are 12 bytes long.  It turns out that
+ * block_size % 12 >= 4 for at least all powers of 2 greater than 512, which
+ * covers all valid ext4 block sizes.  Therefore, this tail structure can be
+ * crammed into the end of the block without having to rebalance the tree.
+ */
+struct ext4_extent_tail {
+	__le32	et_checksum;	/* crc32c(uuid+inum+extent_block) */
+};
+
+/*
+ * This is the extent on-disk structure.
+ * It's used at the bottom of the tree.
+ */
+struct ext4_extent {
+	__le32	ee_block;	/* first logical block extent covers */
+	__le16	ee_len;		/* number of blocks covered by extent */
+	__le16	ee_start_hi;	/* high 16 bits of physical block */
+	__le32	ee_start_lo;	/* low 32 bits of physical block */
+};
+
+/*
+ * This is index on-disk structure.
+ * It's used at all the levels except the bottom.
+ */
+struct ext4_extent_idx {
+	__le32	ei_block;	/* index covers logical blocks from 'block' */
+	__le32	ei_leaf_lo;	/* pointer to the physical block of the next *
+				 * level. leaf or next index could be there */
+	__le16	ei_leaf_hi;	/* high 16 bits of physical block */
+	__u16	ei_unused;
+};
+
+/*
+ * Each block (leaves and indexes), even inode-stored has header.
+ */
+struct ext4_extent_header {
+	__le16	eh_magic;	/* probably will support different formats */
+	__le16	eh_entries;	/* number of valid entries */
+	__le16	eh_max;		/* capacity of store in entries */
+	__le16	eh_depth;	/* has tree real underlying blocks? */
+	__le32	eh_generation;	/* generation of the tree */
+};
+
+#define EXT4_EXT_MAGIC		cpu_to_le16(0xf30a)
+#define EXT4_MAX_EXTENT_DEPTH 5
+
+#define EXT4_EXTENT_TAIL_OFFSET(hdr) \
+	(sizeof(struct ext4_extent_header) + \
+	 (sizeof(struct ext4_extent) * le16_to_cpu((hdr)->eh_max)))
+
+static inline struct ext4_extent_tail *
+find_ext4_extent_tail(struct ext4_extent_header *eh)
+{
+	return (struct ext4_extent_tail *)(((void *)eh) +
+					   EXT4_EXTENT_TAIL_OFFSET(eh));
+}
+
+/*
+ * Array of ext4_ext_path contains path to some extent.
+ * Creation/lookup routines use it for traversal/splitting/etc.
+ * Truncate uses it to simulate recursive walking.
+ */
+struct ext4_ext_path {
+	ext4_fsblk_t			p_block;
+	__u16				p_depth;
+	__u16				p_maxdepth;
+	struct ext4_extent		*p_ext;
+	struct ext4_extent_idx		*p_idx;
+	struct ext4_extent_header	*p_hdr;
+	struct buffer_head		*p_bh;
+};
+
+/*
+ * Used to record a portion of a cluster found at the beginning or end
+ * of an extent while traversing the extent tree during space removal.
+ * A partial cluster may be removed if it does not contain blocks shared
+ * with extents that aren't being deleted (tofree state).  Otherwise,
+ * it cannot be removed (nofree state).
+ */
+struct partial_cluster {
+	ext4_fsblk_t pclu;  /* physical cluster number */
+	ext4_lblk_t lblk;   /* logical block number within logical cluster */
+	enum {initial, tofree, nofree} state;
+};
+
+/*
+ * structure for external API
+ */
+
+/*
+ * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an
+ * initialized extent. This is 2^15 and not (2^16 - 1), since we use the
+ * MSB of ee_len field in the extent datastructure to signify if this
+ * particular extent is an initialized extent or an unwritten (i.e.
+ * preallocated).
+ * EXT_UNWRITTEN_MAX_LEN is the maximum number of blocks we can have in an
+ * unwritten extent.
+ * If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an
+ * unwritten one. In other words, if MSB of ee_len is set, it is an
+ * unwritten extent with only one special scenario when ee_len = 0x8000.
+ * In this case we can not have an unwritten extent of zero length and
+ * thus we make it as a special case of initialized extent with 0x8000 length.
+ * This way we get better extent-to-group alignment for initialized extents.
+ * Hence, the maximum number of blocks we can have in an *initialized*
+ * extent is 2^15 (32768) and in an *unwritten* extent is 2^15-1 (32767).
+ */
+#define EXT_INIT_MAX_LEN	(1UL << 15)
+#define EXT_UNWRITTEN_MAX_LEN	(EXT_INIT_MAX_LEN - 1)
+
+
+#define EXT_FIRST_EXTENT(__hdr__) \
+	((struct ext4_extent *) (((char *) (__hdr__)) +		\
+				 sizeof(struct ext4_extent_header)))
+#define EXT_FIRST_INDEX(__hdr__) \
+	((struct ext4_extent_idx *) (((char *) (__hdr__)) +	\
+				     sizeof(struct ext4_extent_header)))
+#define EXT_HAS_FREE_INDEX(__path__) \
+	(le16_to_cpu((__path__)->p_hdr->eh_entries) \
+				     < le16_to_cpu((__path__)->p_hdr->eh_max))
+#define EXT_LAST_EXTENT(__hdr__) \
+	(EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
+#define EXT_LAST_INDEX(__hdr__) \
+	(EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
+#define EXT_MAX_EXTENT(__hdr__)	\
+	((le16_to_cpu((__hdr__)->eh_max)) ? \
+	((EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) \
+					: NULL)
+#define EXT_MAX_INDEX(__hdr__) \
+	((le16_to_cpu((__hdr__)->eh_max)) ? \
+	((EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) \
+					: NULL)
+
+static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode)
+{
+	return (struct ext4_extent_header *) EXT4_I(inode)->i_data;
+}
+
+static inline struct ext4_extent_header *ext_block_hdr(struct buffer_head *bh)
+{
+	return (struct ext4_extent_header *) bh->b_data;
+}
+
+static inline unsigned short ext_depth(struct inode *inode)
+{
+	return le16_to_cpu(ext_inode_hdr(inode)->eh_depth);
+}
+
+static inline void ext4_ext_mark_unwritten(struct ext4_extent *ext)
+{
+	/* We can not have an unwritten extent of zero length! */
+	BUG_ON((le16_to_cpu(ext->ee_len) & ~EXT_INIT_MAX_LEN) == 0);
+	ext->ee_len |= cpu_to_le16(EXT_INIT_MAX_LEN);
+}
+
+static inline int ext4_ext_is_unwritten(struct ext4_extent *ext)
+{
+	/* Extent with ee_len of 0x8000 is treated as an initialized extent */
+	return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN);
+}
+
+static inline int ext4_ext_get_actual_len(struct ext4_extent *ext)
+{
+	return (le16_to_cpu(ext->ee_len) <= EXT_INIT_MAX_LEN ?
+		le16_to_cpu(ext->ee_len) :
+		(le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN));
+}
+
+static inline void ext4_ext_mark_initialized(struct ext4_extent *ext)
+{
+	ext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ext));
+}
+
+/*
+ * ext4_ext_pblock:
+ * combine low and high parts of physical block number into ext4_fsblk_t
+ */
+static inline ext4_fsblk_t ext4_ext_pblock(struct ext4_extent *ex)
+{
+	ext4_fsblk_t block;
+
+	block = le32_to_cpu(ex->ee_start_lo);
+	block |= ((ext4_fsblk_t) le16_to_cpu(ex->ee_start_hi) << 31) << 1;
+	return block;
+}
+
+/*
+ * ext4_idx_pblock:
+ * combine low and high parts of a leaf physical block number into ext4_fsblk_t
+ */
+static inline ext4_fsblk_t ext4_idx_pblock(struct ext4_extent_idx *ix)
+{
+	ext4_fsblk_t block;
+
+	block = le32_to_cpu(ix->ei_leaf_lo);
+	block |= ((ext4_fsblk_t) le16_to_cpu(ix->ei_leaf_hi) << 31) << 1;
+	return block;
+}
+
+/*
+ * ext4_ext_store_pblock:
+ * stores a large physical block number into an extent struct,
+ * breaking it into parts
+ */
+static inline void ext4_ext_store_pblock(struct ext4_extent *ex,
+					 ext4_fsblk_t pb)
+{
+	ex->ee_start_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
+	ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) &
+				      0xffff);
+}
+
+/*
+ * ext4_idx_store_pblock:
+ * stores a large physical block number into an index struct,
+ * breaking it into parts
+ */
+static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix,
+					 ext4_fsblk_t pb)
+{
+	ix->ei_leaf_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
+	ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) &
+				     0xffff);
+}
+
+extern int __ext4_ext_dirty(const char *where, unsigned int line,
+			    handle_t *handle, struct inode *inode,
+			    struct ext4_ext_path *path);
+extern int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex);
+#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS)
+extern int ext4_ext_space_root_idx_test(struct inode *inode, int check);
+extern struct ext4_ext_path *ext4_split_convert_extents_test(
+				handle_t *handle, struct inode *inode,
+				struct ext4_map_blocks *map,
+				struct ext4_ext_path *path,
+				int flags, unsigned int *allocated);
+#endif
+#endif /* _EXT4_EXTENTS */
+

linux-7.2.3/fs/ext4/ext4_jbd2.c

@@ -0,0 +1,408 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Interface between ext4 and JBD
+ */
+
+#include "ext4_jbd2.h"
+
+#include <trace/events/ext4.h>
+
+int ext4_inode_journal_mode(struct inode *inode)
+{
+	if (EXT4_JOURNAL(inode) == NULL)
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	/* We do not support data journalling with delayed allocation */
+	if (!S_ISREG(inode->i_mode) ||
+	    ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) ||
+	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+	    (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+	    !test_opt(inode->i_sb, DELALLOC))) {
+		/* We do not support data journalling for encrypted data */
+		if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode))
+			return EXT4_INODE_ORDERED_DATA_MODE;  /* ordered */
+		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
+	}
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+		return EXT4_INODE_ORDERED_DATA_MODE;	/* ordered */
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	BUG();
+}
+
+/* Just increment the non-pointer handle value */
+static handle_t *ext4_get_nojournal(void)
+{
+	handle_t *handle = current->journal_info;
+	unsigned long ref_cnt = (unsigned long)handle;
+
+	BUG_ON(ref_cnt >= EXT4_NOJOURNAL_MAX_REF_COUNT);
+
+	ref_cnt++;
+	handle = (handle_t *)ref_cnt;
+
+	current->journal_info = handle;
+	return handle;
+}
+
+
+/* Decrement the non-pointer handle value */
+static void ext4_put_nojournal(handle_t *handle)
+{
+	unsigned long ref_cnt = (unsigned long)handle;
+
+	BUG_ON(ref_cnt == 0);
+
+	ref_cnt--;
+	handle = (handle_t *)ref_cnt;
+
+	current->journal_info = handle;
+}
+
+/*
+ * Wrappers for jbd2_journal_start/end.
+ */
+static int ext4_journal_check_start(struct super_block *sb)
+{
+	int ret;
+	journal_t *journal;
+
+	might_sleep();
+
+	ret = ext4_emergency_state(sb);
+	if (unlikely(ret))
+		return ret;
+
+	if (WARN_ON_ONCE(sb_rdonly(sb)))
+		return -EROFS;
+
+	WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
+	journal = EXT4_SB(sb)->s_journal;
+	/*
+	 * Special case here: if the journal has aborted behind our
+	 * backs (eg. EIO in the commit thread), then we still need to
+	 * take the FS itself readonly cleanly.
+	 */
+	if (journal && is_journal_aborted(journal)) {
+		ext4_abort(sb, -journal->j_errno, "Detected aborted journal");
+		return -EROFS;
+	}
+	return 0;
+}
+
+handle_t *__ext4_journal_start_sb(struct inode *inode,
+				  struct super_block *sb, unsigned int line,
+				  int type, int blocks, int rsv_blocks,
+				  int revoke_creds)
+{
+	journal_t *journal;
+	int err;
+	if (inode)
+		trace_ext4_journal_start_inode(inode, blocks, rsv_blocks,
+					revoke_creds, type,
+					_RET_IP_);
+	else
+		trace_ext4_journal_start_sb(sb, blocks, rsv_blocks,
+					revoke_creds, type,
+					_RET_IP_);
+	err = ext4_journal_check_start(sb);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	journal = EXT4_SB(sb)->s_journal;
+	if (!journal || (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
+		return ext4_get_nojournal();
+	return jbd2__journal_start(journal, blocks, rsv_blocks, revoke_creds,
+				   GFP_NOFS, type, line);
+}
+
+int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
+{
+	struct super_block *sb;
+	int err;
+	int rc;
+
+	if (!ext4_handle_valid(handle)) {
+		ext4_put_nojournal(handle);
+		return 0;
+	}
+
+	err = handle->h_err;
+	if (!handle->h_transaction) {
+		rc = jbd2_journal_stop(handle);
+		return err ? err : rc;
+	}
+
+	sb = handle->h_transaction->t_journal->j_private;
+	rc = jbd2_journal_stop(handle);
+
+	if (!err)
+		err = rc;
+	if (err)
+		__ext4_std_error(sb, where, line, err);
+	return err;
+}
+
+handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
+					int type)
+{
+	struct super_block *sb;
+	int err;
+
+	if (!ext4_handle_valid(handle))
+		return ext4_get_nojournal();
+
+	sb = handle->h_journal->j_private;
+	trace_ext4_journal_start_reserved(sb,
+				jbd2_handle_buffer_credits(handle), _RET_IP_);
+	err = ext4_journal_check_start(sb);
+	if (err < 0) {
+		jbd2_journal_free_reserved(handle);
+		return ERR_PTR(err);
+	}
+
+	err = jbd2_journal_start_reserved(handle, type, line);
+	if (err < 0)
+		return ERR_PTR(err);
+	return handle;
+}
+
+int __ext4_journal_ensure_credits(handle_t *handle, int check_cred,
+				  int extend_cred, int revoke_cred)
+{
+	if (!ext4_handle_valid(handle))
+		return 0;
+	if (is_handle_aborted(handle))
+		return -EROFS;
+	if (jbd2_handle_buffer_credits(handle) >= check_cred &&
+	    handle->h_revoke_credits >= revoke_cred)
+		return 0;
+	extend_cred = max(0, extend_cred - jbd2_handle_buffer_credits(handle));
+	revoke_cred = max(0, revoke_cred - handle->h_revoke_credits);
+	return ext4_journal_extend(handle, extend_cred, revoke_cred);
+}
+
+static void ext4_journal_abort_handle(const char *caller, unsigned int line,
+				      const char *err_fn,
+				      struct buffer_head *bh,
+				      handle_t *handle, int err)
+{
+	char nbuf[16];
+	const char *errstr = ext4_decode_error(NULL, err, nbuf);
+
+	BUG_ON(!ext4_handle_valid(handle));
+
+	if (bh)
+		BUFFER_TRACE(bh, "abort");
+
+	if (!handle->h_err)
+		handle->h_err = err;
+
+	if (is_handle_aborted(handle))
+		return;
+
+	printk(KERN_ERR "EXT4-fs: %s:%d: aborting transaction: %s in %s\n",
+	       caller, line, errstr, err_fn);
+
+	jbd2_journal_abort_handle(handle);
+}
+
+static void ext4_check_bdev_write_error(struct super_block *sb)
+{
+	struct address_space *mapping = sb->s_bdev->bd_mapping;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int err;
+
+	/*
+	 * If the block device has write error flag, it may have failed to
+	 * async write out metadata buffers in the background. In this case,
+	 * we could read old data from disk and write it out again, which
+	 * may lead to on-disk filesystem inconsistency.
+	 */
+	if (errseq_check(&mapping->wb_err, READ_ONCE(sbi->s_bdev_wb_err))) {
+		spin_lock(&sbi->s_bdev_wb_lock);
+		err = errseq_check_and_advance(&mapping->wb_err, &sbi->s_bdev_wb_err);
+		spin_unlock(&sbi->s_bdev_wb_lock);
+		if (err)
+			ext4_error_err(sb, -err,
+				       "Error while async write back metadata");
+	}
+}
+
+int __ext4_journal_get_write_access(const char *where, unsigned int line,
+				    handle_t *handle, struct super_block *sb,
+				    struct buffer_head *bh,
+				    enum ext4_journal_trigger_type trigger_type)
+{
+	int err;
+
+	might_sleep();
+
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_get_write_access(handle, bh);
+		if (err) {
+			ext4_journal_abort_handle(where, line, __func__, bh,
+						  handle, err);
+			return err;
+		}
+	} else
+		ext4_check_bdev_write_error(sb);
+	if (trigger_type == EXT4_JTR_NONE ||
+	    !ext4_has_feature_metadata_csum(sb))
+		return 0;
+	BUG_ON(trigger_type >= EXT4_JOURNAL_TRIGGER_COUNT);
+	jbd2_journal_set_triggers(bh,
+		&EXT4_SB(sb)->s_journal_triggers[trigger_type].tr_triggers);
+	return 0;
+}
+
+/*
+ * The ext4 forget function must perform a revoke if we are freeing data
+ * which has been journaled.  Metadata (eg. indirect blocks) must be
+ * revoked in all cases.
+ *
+ * "bh" may be NULL: a metadata block may have been freed from memory
+ * but there may still be a record of it in the journal, and that record
+ * still needs to be revoked.
+ */
+int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
+		  int is_metadata, struct inode *inode,
+		  struct buffer_head *bh, ext4_fsblk_t blocknr)
+{
+	int err;
+
+	might_sleep();
+
+	trace_ext4_forget(inode, is_metadata, blocknr);
+	BUFFER_TRACE(bh, "enter");
+
+	ext4_debug("forgetting bh %p: is_metadata=%d, mode %o, data mode %x\n",
+		  bh, is_metadata, inode->i_mode,
+		  test_opt(inode->i_sb, DATA_FLAGS));
+
+	/*
+	 * In the no journal case, we should wait for the ongoing buffer
+	 * to complete and do a forget.
+	 */
+	if (!ext4_handle_valid(handle)) {
+		if (bh) {
+			clear_buffer_dirty(bh);
+			wait_on_buffer(bh);
+			__bforget(bh);
+		}
+		return 0;
+	}
+
+	/* Never use the revoke function if we are doing full data
+	 * journaling: there is no need to, and a V1 superblock won't
+	 * support it.  Otherwise, only skip the revoke on un-journaled
+	 * data blocks. */
+
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+	    (!is_metadata && !ext4_should_journal_data(inode))) {
+		if (bh) {
+			BUFFER_TRACE(bh, "call jbd2_journal_forget");
+			err = jbd2_journal_forget(handle, bh);
+			if (err)
+				ext4_journal_abort_handle(where, line, __func__,
+							  bh, handle, err);
+			return err;
+		}
+		return 0;
+	}
+
+	/*
+	 * data!=journal && (is_metadata || should_journal_data(inode))
+	 */
+	BUFFER_TRACE(bh, "call jbd2_journal_revoke");
+	err = jbd2_journal_revoke(handle, blocknr, bh);
+	if (err) {
+		ext4_journal_abort_handle(where, line, __func__,
+					  bh, handle, err);
+		__ext4_error(inode->i_sb, where, line, true, -err, 0,
+			     "error %d when attempting revoke", err);
+	}
+	BUFFER_TRACE(bh, "exit");
+	return err;
+}
+
+int __ext4_journal_get_create_access(const char *where, unsigned int line,
+				handle_t *handle, struct super_block *sb,
+				struct buffer_head *bh,
+				enum ext4_journal_trigger_type trigger_type)
+{
+	int err;
+
+	if (!ext4_handle_valid(handle))
+		return 0;
+
+	err = jbd2_journal_get_create_access(handle, bh);
+	if (err) {
+		ext4_journal_abort_handle(where, line, __func__, bh, handle,
+					  err);
+		return err;
+	}
+	if (trigger_type == EXT4_JTR_NONE ||
+	    !ext4_has_feature_metadata_csum(sb))
+		return 0;
+	BUG_ON(trigger_type >= EXT4_JOURNAL_TRIGGER_COUNT);
+	jbd2_journal_set_triggers(bh,
+		&EXT4_SB(sb)->s_journal_triggers[trigger_type].tr_triggers);
+	return 0;
+}
+
+int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
+				 handle_t *handle, struct inode *inode,
+				 struct buffer_head *bh)
+{
+	int err = 0;
+
+	might_sleep();
+
+	set_buffer_meta(bh);
+	set_buffer_prio(bh);
+	set_buffer_uptodate(bh);
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_dirty_metadata(handle, bh);
+		/* Errors can only happen due to aborted journal or a nasty bug */
+		if (!is_handle_aborted(handle) && WARN_ON_ONCE(err)) {
+			ext4_journal_abort_handle(where, line, __func__, bh,
+						  handle, err);
+			if (inode == NULL) {
+				pr_err("EXT4: jbd2_journal_dirty_metadata "
+				       "failed: handle type %u started at "
+				       "line %u, credits %u/%u, errcode %d",
+				       handle->h_type,
+				       handle->h_line_no,
+				       handle->h_requested_credits,
+				       jbd2_handle_buffer_credits(handle), err);
+				return err;
+			}
+			ext4_error_inode(inode, where, line,
+					 bh->b_blocknr,
+					 "journal_dirty_metadata failed: "
+					 "handle type %u started at line %u, "
+					 "credits %u/%u, errcode %d",
+					 handle->h_type,
+					 handle->h_line_no,
+					 handle->h_requested_credits,
+					 jbd2_handle_buffer_credits(handle),
+					 err);
+		}
+	} else {
+		if (inode)
+			mmb_mark_buffer_dirty(bh,
+					      &EXT4_I(inode)->i_metadata_bhs);
+		else
+			mark_buffer_dirty(bh);
+		if (inode && inode_needs_sync(inode)) {
+			sync_dirty_buffer(bh);
+			if (buffer_req(bh) && !buffer_uptodate(bh)) {
+				ext4_error_inode_err(inode, where, line,
+						     bh->b_blocknr, EIO,
+					"IO error syncing itable block");
+				err = -EIO;
+			}
+		}
+	}
+	return err;
+}

linux-7.2.3/fs/ext4/ext4_jbd2.h

@@ -0,0 +1,461 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * ext4_jbd2.h
+ *
+ * Written by Stephen C. Tweedie <sct@redhat.com>, 1999
+ *
+ * Copyright 1998--1999 Red Hat corp --- All Rights Reserved
+ *
+ * Ext4-specific journaling extensions.
+ */
+
+#ifndef _EXT4_JBD2_H
+#define _EXT4_JBD2_H
+
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include "ext4.h"
+
+#define EXT4_JOURNAL(inode)	(EXT4_SB((inode)->i_sb)->s_journal)
+
+/* Define the number of blocks we need to account to a transaction to
+ * modify one block of data.
+ *
+ * We may have to touch one inode, one bitmap buffer, up to three
+ * indirection blocks, the group and superblock summaries, and the data
+ * block to complete the transaction.
+ *
+ * For extents-enabled fs we may have to allocate and modify up to
+ * 5 levels of tree, data block (for each of these we need bitmap + group
+ * summaries), root which is stored in the inode, sb
+ */
+
+#define EXT4_SINGLEDATA_TRANS_BLOCKS(sb)				\
+	(ext4_has_feature_extents(sb) ? 20U : 8U)
+
+/* Extended attribute operations touch at most two data buffers,
+ * two bitmap buffers, and two group summaries, in addition to the inode
+ * and the superblock, which are already accounted for. */
+
+#define EXT4_XATTR_TRANS_BLOCKS		6U
+
+/* Define the minimum size for a transaction which modifies data.  This
+ * needs to take into account the fact that we may end up modifying two
+ * quota files too (one for the group, one for the user quota).  The
+ * superblock only gets updated once, of course, so don't bother
+ * counting that again for the quota updates. */
+
+#define EXT4_DATA_TRANS_BLOCKS(sb)	(EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \
+					 EXT4_XATTR_TRANS_BLOCKS - 2 + \
+					 EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
+
+/*
+ * Define the number of metadata blocks we need to account to modify data.
+ *
+ * This include super block, inode block, quota blocks and xattr blocks
+ */
+#define EXT4_META_TRANS_BLOCKS(sb)	(EXT4_XATTR_TRANS_BLOCKS + \
+					EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
+
+/* Define an arbitrary limit for the amount of data we will anticipate
+ * writing to any given transaction.  For unbounded transactions such as
+ * write(2) and truncate(2) we can write more than this, but we always
+ * start off at the maximum transaction size and grow the transaction
+ * optimistically as we go. */
+
+#define EXT4_MAX_TRANS_DATA		64U
+
+/* We break up a large truncate or write transaction once the handle's
+ * buffer credits gets this low, we need either to extend the
+ * transaction or to start a new one.  Reserve enough space here for
+ * inode, bitmap, superblock, group and indirection updates for at least
+ * one block, plus two quota updates.  Quota allocations are not
+ * needed. */
+
+#define EXT4_RESERVE_TRANS_BLOCKS	12U
+
+/*
+ * Number of credits needed if we need to insert an entry into a
+ * directory.  For each new index block, we need 4 blocks (old index
+ * block, new index block, bitmap block, bg summary).  For normal
+ * htree directories there are 2 levels; if the largedir feature
+ * enabled it's 3 levels.
+ */
+#define EXT4_INDEX_EXTRA_TRANS_BLOCKS	12U
+
+#ifdef CONFIG_QUOTA
+/* Amount of blocks needed for quota update - we know that the structure was
+ * allocated so we need to update only data block */
+#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((ext4_quota_capable(sb)) ? 1 : 0)
+/* Amount of blocks needed for quota insert/delete - we do some block writes
+ * but inode, sb and group updates are done only once */
+#define EXT4_QUOTA_INIT_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\
+		(DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
+		 +3+DQUOT_INIT_REWRITE) : 0)
+
+#define EXT4_QUOTA_DEL_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\
+		(DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
+		 +3+DQUOT_DEL_REWRITE) : 0)
+#else
+#define EXT4_QUOTA_TRANS_BLOCKS(sb) 0
+#define EXT4_QUOTA_INIT_BLOCKS(sb) 0
+#define EXT4_QUOTA_DEL_BLOCKS(sb) 0
+#endif
+#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
+
+/*
+ * Ext4 handle operation types -- for logging purposes
+ */
+#define EXT4_HT_MISC             0
+#define EXT4_HT_INODE            1
+#define EXT4_HT_WRITE_PAGE       2
+#define EXT4_HT_MAP_BLOCKS       3
+#define EXT4_HT_DIR              4
+#define EXT4_HT_TRUNCATE         5
+#define EXT4_HT_QUOTA            6
+#define EXT4_HT_RESIZE           7
+#define EXT4_HT_MIGRATE          8
+#define EXT4_HT_MOVE_EXTENTS     9
+#define EXT4_HT_XATTR           10
+#define EXT4_HT_EXT_CONVERT     11
+#define EXT4_HT_MAX             12
+
+int
+ext4_mark_iloc_dirty(handle_t *handle,
+		     struct inode *inode,
+		     struct ext4_iloc *iloc);
+
+/*
+ * On success, We end up with an outstanding reference count against
+ * iloc->bh.  This _must_ be cleaned up later.
+ */
+
+int ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
+			struct ext4_iloc *iloc);
+
+#define ext4_mark_inode_dirty(__h, __i)					\
+		__ext4_mark_inode_dirty((__h), (__i), __func__, __LINE__)
+int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode,
+				const char *func, unsigned int line);
+
+int ext4_expand_extra_isize(struct inode *inode,
+			    unsigned int new_extra_isize,
+			    struct ext4_iloc *iloc);
+/*
+ * Wrapper functions with which ext4 calls into JBD.
+ */
+int __ext4_journal_get_write_access(const char *where, unsigned int line,
+				    handle_t *handle, struct super_block *sb,
+				    struct buffer_head *bh,
+				    enum ext4_journal_trigger_type trigger_type);
+
+int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
+		  int is_metadata, struct inode *inode,
+		  struct buffer_head *bh, ext4_fsblk_t blocknr);
+
+int __ext4_journal_get_create_access(const char *where, unsigned int line,
+				handle_t *handle, struct super_block *sb,
+				struct buffer_head *bh,
+				enum ext4_journal_trigger_type trigger_type);
+
+int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
+				 handle_t *handle, struct inode *inode,
+				 struct buffer_head *bh);
+
+#define ext4_journal_get_write_access(handle, sb, bh, trigger_type) \
+	__ext4_journal_get_write_access(__func__, __LINE__, (handle), (sb), \
+					(bh), (trigger_type))
+#define ext4_forget(handle, is_metadata, inode, bh, block_nr) \
+	__ext4_forget(__func__, __LINE__, (handle), (is_metadata), (inode), \
+		      (bh), (block_nr))
+#define ext4_journal_get_create_access(handle, sb, bh, trigger_type) \
+	__ext4_journal_get_create_access(__func__, __LINE__, (handle), (sb), \
+					 (bh), (trigger_type))
+#define ext4_handle_dirty_metadata(handle, inode, bh) \
+	__ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \
+				     (bh))
+
+handle_t *__ext4_journal_start_sb(struct inode *inode, struct super_block *sb,
+				  unsigned int line, int type, int blocks,
+				  int rsv_blocks, int revoke_creds);
+int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle);
+
+#define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096)
+
+/* Note:  Do not use this for NULL handles.  This is only to determine if
+ * a properly allocated handle is using a journal or not. */
+static inline int ext4_handle_valid(handle_t *handle)
+{
+	if ((unsigned long)handle < EXT4_NOJOURNAL_MAX_REF_COUNT)
+		return 0;
+	return 1;
+}
+
+static inline void ext4_handle_sync(handle_t *handle)
+{
+	if (ext4_handle_valid(handle))
+		handle->h_sync = 1;
+}
+
+static inline int ext4_handle_is_aborted(handle_t *handle)
+{
+	if (ext4_handle_valid(handle))
+		return is_handle_aborted(handle);
+	return 0;
+}
+
+static inline int ext4_free_metadata_revoke_credits(struct super_block *sb,
+						    int blocks)
+{
+	/* Freeing each metadata block can result in freeing one cluster */
+	return blocks * EXT4_SB(sb)->s_cluster_ratio;
+}
+
+static inline int ext4_trans_default_revoke_credits(struct super_block *sb)
+{
+	return ext4_free_metadata_revoke_credits(sb, 8);
+}
+
+#define ext4_journal_start_sb(sb, type, nblocks)			\
+	__ext4_journal_start_sb(NULL, (sb), __LINE__, (type), (nblocks), 0,\
+				ext4_trans_default_revoke_credits(sb))
+
+#define ext4_journal_start(inode, type, nblocks)			\
+	__ext4_journal_start((inode), __LINE__, (type), (nblocks), 0,	\
+			     ext4_trans_default_revoke_credits((inode)->i_sb))
+
+#define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks)\
+	__ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks),\
+			     ext4_trans_default_revoke_credits((inode)->i_sb))
+
+#define ext4_journal_start_with_revoke(inode, type, blocks, revoke_creds) \
+	__ext4_journal_start((inode), __LINE__, (type), (blocks), 0,	\
+			     (revoke_creds))
+
+static inline handle_t *__ext4_journal_start(struct inode *inode,
+					     unsigned int line, int type,
+					     int blocks, int rsv_blocks,
+					     int revoke_creds)
+{
+	return __ext4_journal_start_sb(inode, inode->i_sb, line, type, blocks,
+				       rsv_blocks, revoke_creds);
+}
+
+#define ext4_journal_stop(handle) \
+	__ext4_journal_stop(__func__, __LINE__, (handle))
+
+#define ext4_journal_start_reserved(handle, type) \
+	__ext4_journal_start_reserved((handle), __LINE__, (type))
+
+handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
+					int type);
+
+static inline handle_t *ext4_journal_current_handle(void)
+{
+	return journal_current_handle();
+}
+
+static inline int ext4_journal_extend(handle_t *handle, int nblocks, int revoke)
+{
+	if (ext4_handle_valid(handle))
+		return jbd2_journal_extend(handle, nblocks, revoke);
+	return 0;
+}
+
+static inline int ext4_journal_restart(handle_t *handle, int nblocks,
+				       int revoke)
+{
+	if (ext4_handle_valid(handle))
+		return jbd2__journal_restart(handle, nblocks, revoke, GFP_NOFS);
+	return 0;
+}
+
+int __ext4_journal_ensure_credits(handle_t *handle, int check_cred,
+				  int extend_cred, int revoke_cred);
+
+
+/*
+ * Ensure @handle has at least @check_creds credits available. If not,
+ * transaction will be extended or restarted to contain at least @extend_cred
+ * credits. Before restarting transaction @fn is executed to allow for cleanup
+ * before the transaction is restarted.
+ *
+ * The return value is < 0 in case of error, 0 in case the handle has enough
+ * credits or transaction extension succeeded, 1 in case transaction had to be
+ * restarted.
+ */
+#define ext4_journal_ensure_credits_fn(handle, check_cred, extend_cred,	\
+				       revoke_cred, fn) \
+({									\
+	__label__ __ensure_end;						\
+	int err = __ext4_journal_ensure_credits((handle), (check_cred),	\
+					(extend_cred), (revoke_cred));	\
+									\
+	if (err <= 0)							\
+		goto __ensure_end;					\
+	err = (fn);							\
+	if (err < 0)							\
+		goto __ensure_end;					\
+	err = ext4_journal_restart((handle), (extend_cred), (revoke_cred)); \
+	if (err == 0)							\
+		err = 1;						\
+__ensure_end:								\
+	err;								\
+})
+
+/*
+ * Ensure given handle has at least requested amount of credits available,
+ * possibly restarting transaction if needed. We also make sure the transaction
+ * has space for at least ext4_trans_default_revoke_credits(sb) revoke records
+ * as freeing one or two blocks is very common pattern and requesting this is
+ * very cheap.
+ */
+static inline int ext4_journal_ensure_credits(handle_t *handle, int credits,
+					      int revoke_creds)
+{
+	return ext4_journal_ensure_credits_fn(handle, credits, credits,
+				revoke_creds, 0);
+}
+
+static inline int ext4_journal_blocks_per_folio(struct inode *inode)
+{
+	if (EXT4_JOURNAL(inode) != NULL)
+		return jbd2_journal_blocks_per_folio(inode);
+	return 0;
+}
+
+static inline int ext4_journal_force_commit(journal_t *journal)
+{
+	if (journal)
+		return jbd2_journal_force_commit(journal);
+	return 0;
+}
+
+static inline int ext4_jbd2_inode_add_write(handle_t *handle,
+		struct inode *inode, loff_t start_byte, loff_t length)
+{
+	if (ext4_handle_valid(handle))
+		return jbd2_journal_inode_ranged_write(handle,
+				EXT4_I(inode)->jinode, start_byte, length);
+	return 0;
+}
+
+static inline int ext4_jbd2_inode_add_wait(handle_t *handle,
+		struct inode *inode, loff_t start_byte, loff_t length)
+{
+	if (ext4_handle_valid(handle))
+		return jbd2_journal_inode_ranged_wait(handle,
+				EXT4_I(inode)->jinode, start_byte, length);
+	return 0;
+}
+
+static inline void ext4_update_inode_fsync_trans(handle_t *handle,
+						 struct inode *inode,
+						 int datasync)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	if (ext4_handle_valid(handle) && !is_handle_aborted(handle)) {
+		ei->i_sync_tid = handle->h_transaction->t_tid;
+		if (datasync)
+			ei->i_datasync_tid = handle->h_transaction->t_tid;
+	}
+}
+
+/* super.c */
+int ext4_force_commit(struct super_block *sb);
+
+/*
+ * Ext4 inode journal modes
+ */
+#define EXT4_INODE_JOURNAL_DATA_MODE	0x01 /* journal data mode */
+#define EXT4_INODE_ORDERED_DATA_MODE	0x02 /* ordered data mode */
+#define EXT4_INODE_WRITEBACK_DATA_MODE	0x04 /* writeback data mode */
+
+int ext4_inode_journal_mode(struct inode *inode);
+
+static inline int ext4_should_journal_data(struct inode *inode)
+{
+	return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE;
+}
+
+static inline int ext4_should_order_data(struct inode *inode)
+{
+	return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE;
+}
+
+static inline int ext4_should_writeback_data(struct inode *inode)
+{
+	return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE;
+}
+
+static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks)
+{
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+		return 0;
+	if (!ext4_should_journal_data(inode))
+		return 0;
+	/*
+	 * Data blocks in one extent are contiguous, just account for partial
+	 * clusters at extent boundaries
+	 */
+	return blocks + 2*(EXT4_SB(inode->i_sb)->s_cluster_ratio - 1);
+}
+
+/*
+ * This function controls whether or not we should try to go down the
+ * dioread_nolock code paths, which makes it safe to avoid taking
+ * i_rwsem for direct I/O reads.  This only works for extent-based
+ * files, and it doesn't work if data journaling is enabled, since the
+ * dioread_nolock code uses b_private to pass information back to the
+ * I/O completion handler, and this conflicts with the jbd's use of
+ * b_private.
+ */
+static inline int ext4_should_dioread_nolock(struct inode *inode)
+{
+	if (!test_opt(inode->i_sb, DIOREAD_NOLOCK))
+		return 0;
+	if (!S_ISREG(inode->i_mode))
+		return 0;
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+		return 0;
+	if (ext4_should_journal_data(inode))
+		return 0;
+	/* temporary fix to prevent generic/422 test failures */
+	if (!test_opt(inode->i_sb, DELALLOC))
+		return 0;
+	return 1;
+}
+
+/*
+ * Pass journal explicitly as it may not be cached in the sbi->s_journal in some
+ * cases
+ */
+static inline int ext4_journal_destroy(struct ext4_sb_info *sbi, journal_t *journal)
+{
+	int err = 0;
+
+	/*
+	 * At this point only two things can be operating on the journal.
+	 * JBD2 thread performing transaction commit and s_sb_upd_work
+	 * issuing sb update through the journal. Once we set
+	 * EXT4_JOURNAL_DESTROY, new ext4_handle_error() calls will not
+	 * queue s_sb_upd_work and ext4_force_commit() makes sure any
+	 * ext4_handle_error() calls from the running transaction commit are
+	 * finished. Hence no new s_sb_upd_work can be queued after we
+	 * flush it here.
+	 */
+	ext4_set_mount_flag(sbi->s_sb, EXT4_MF_JOURNAL_DESTROY);
+
+	ext4_force_commit(sbi->s_sb);
+	flush_work(&sbi->s_sb_upd_work);
+
+	err = jbd2_journal_destroy(journal);
+	sbi->s_journal = NULL;
+
+	return err;
+}
+
+#endif	/* _EXT4_JBD2_H */

linux-7.2.3/fs/ext4/extents_status.h

@@ -0,0 +1,254 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  fs/ext4/extents_status.h
+ *
+ * Written by Yongqiang Yang <xiaoqiangnk@gmail.com>
+ * Modified by
+ *	Allison Henderson <achender@linux.vnet.ibm.com>
+ *	Zheng Liu <wenqing.lz@taobao.com>
+ *
+ */
+
+#ifndef _EXT4_EXTENTS_STATUS_H
+#define _EXT4_EXTENTS_STATUS_H
+
+/*
+ * Turn on ES_DEBUG__ to get lots of info about extent status operations.
+ */
+#ifdef ES_DEBUG__
+#define es_debug(fmt, ...)	printk(fmt, ##__VA_ARGS__)
+#else
+#define es_debug(fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
+#endif
+
+/*
+ * With ES_AGGRESSIVE_TEST defined, the result of es caching will be
+ * checked with old map_block's result.
+ */
+#define ES_AGGRESSIVE_TEST__
+
+/*
+ * These flags live in the high bits of extent_status.es_pblk
+ */
+enum {
+	ES_WRITTEN_B,
+	ES_UNWRITTEN_B,
+	ES_DELAYED_B,
+	ES_HOLE_B,
+	ES_REFERENCED_B,
+	ES_FLAGS
+};
+
+#define ES_SHIFT (sizeof(ext4_fsblk_t)*8 - ES_FLAGS)
+#define ES_MASK (~((ext4_fsblk_t)0) << ES_SHIFT)
+
+/*
+ * Besides EXTENT_STATUS_REFERENCED, all these extent type masks
+ * are exclusive, only one type can be set at a time.
+ */
+#define EXTENT_STATUS_WRITTEN	(1 << ES_WRITTEN_B)
+#define EXTENT_STATUS_UNWRITTEN (1 << ES_UNWRITTEN_B)
+#define EXTENT_STATUS_DELAYED	(1 << ES_DELAYED_B)
+#define EXTENT_STATUS_HOLE	(1 << ES_HOLE_B)
+#define EXTENT_STATUS_REFERENCED	(1 << ES_REFERENCED_B)
+
+#define ES_TYPE_MASK	((ext4_fsblk_t)(EXTENT_STATUS_WRITTEN | \
+			  EXTENT_STATUS_UNWRITTEN | \
+			  EXTENT_STATUS_DELAYED | \
+			  EXTENT_STATUS_HOLE))
+
+#define ES_TYPE_VALID(type)	((type) && !((type) & ((type) - 1)))
+
+struct ext4_sb_info;
+struct ext4_extent;
+
+struct extent_status {
+	struct rb_node rb_node;
+	ext4_lblk_t es_lblk;	/* first logical block extent covers */
+	ext4_lblk_t es_len;	/* length of extent in block */
+	ext4_fsblk_t es_pblk;	/* first physical block */
+};
+
+struct ext4_es_tree {
+	struct rb_root root;
+	struct extent_status *cache_es;	/* recently accessed extent */
+};
+
+struct ext4_es_stats {
+	unsigned long es_stats_shrunk;
+	struct percpu_counter es_stats_cache_hits;
+	struct percpu_counter es_stats_cache_misses;
+	u64 es_stats_scan_time;
+	u64 es_stats_max_scan_time;
+	struct percpu_counter es_stats_all_cnt;
+	struct percpu_counter es_stats_shk_cnt;
+};
+
+/*
+ * Pending cluster reservations for bigalloc file systems
+ *
+ * A cluster with a pending reservation is a logical cluster shared by at
+ * least one extent in the extents status tree with delayed and unwritten
+ * status and at least one other written or unwritten extent.  The
+ * reservation is said to be pending because a cluster reservation would
+ * have to be taken in the event all blocks in the cluster shared with
+ * written or unwritten extents were deleted while the delayed and
+ * unwritten blocks remained.
+ *
+ * The set of pending cluster reservations is an auxiliary data structure
+ * used with the extents status tree to implement reserved cluster/block
+ * accounting for bigalloc file systems.  The set is kept in memory and
+ * records all pending cluster reservations.
+ *
+ * Its primary function is to avoid the need to read extents from the
+ * disk when invalidating pages as a result of a truncate, punch hole, or
+ * collapse range operation.  Page invalidation requires a decrease in the
+ * reserved cluster count if it results in the removal of all delayed
+ * and unwritten extents (blocks) from a cluster that is not shared with a
+ * written or unwritten extent, and no decrease otherwise.  Determining
+ * whether the cluster is shared can be done by searching for a pending
+ * reservation on it.
+ *
+ * Secondarily, it provides a potentially faster method for determining
+ * whether the reserved cluster count should be increased when a physical
+ * cluster is deallocated as a result of a truncate, punch hole, or
+ * collapse range operation.  The necessary information is also present
+ * in the extents status tree, but might be more rapidly accessed in
+ * the pending reservation set in many cases due to smaller size.
+ *
+ * The pending cluster reservation set is implemented as a red-black tree
+ * with the goal of minimizing per page search time overhead.
+ */
+
+struct pending_reservation {
+	struct rb_node rb_node;
+	ext4_lblk_t lclu;
+};
+
+struct ext4_pending_tree {
+	struct rb_root root;
+};
+
+extern int __init ext4_init_es(void);
+extern void ext4_exit_es(void);
+extern void ext4_es_init_tree(struct ext4_es_tree *tree);
+
+extern void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
+				  ext4_lblk_t len, ext4_fsblk_t pblk,
+				  unsigned int status,
+				  bool delalloc_reserve_used);
+extern void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
+				 ext4_lblk_t len, ext4_fsblk_t pblk,
+				 unsigned int status);
+extern void ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
+				  ext4_lblk_t len);
+extern void ext4_es_find_extent_range(struct inode *inode,
+				      int (*match_fn)(struct extent_status *es),
+				      ext4_lblk_t lblk, ext4_lblk_t end,
+				      struct extent_status *es);
+extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
+				 ext4_lblk_t *next_lblk,
+				 struct extent_status *es, u64 *pseq);
+extern bool ext4_es_scan_range(struct inode *inode,
+			       int (*matching_fn)(struct extent_status *es),
+			       ext4_lblk_t lblk, ext4_lblk_t end);
+extern bool ext4_es_scan_clu(struct inode *inode,
+			     int (*matching_fn)(struct extent_status *es),
+			     ext4_lblk_t lblk);
+
+static inline unsigned int ext4_es_status(struct extent_status *es)
+{
+	return es->es_pblk >> ES_SHIFT;
+}
+
+static inline unsigned int ext4_es_type(struct extent_status *es)
+{
+	return (es->es_pblk >> ES_SHIFT) & ES_TYPE_MASK;
+}
+
+static inline int ext4_es_is_written(struct extent_status *es)
+{
+	return (ext4_es_type(es) & EXTENT_STATUS_WRITTEN) != 0;
+}
+
+static inline int ext4_es_is_unwritten(struct extent_status *es)
+{
+	return (ext4_es_type(es) & EXTENT_STATUS_UNWRITTEN) != 0;
+}
+
+static inline int ext4_es_is_delayed(struct extent_status *es)
+{
+	return (ext4_es_type(es) & EXTENT_STATUS_DELAYED) != 0;
+}
+
+static inline int ext4_es_is_hole(struct extent_status *es)
+{
+	return (ext4_es_type(es) & EXTENT_STATUS_HOLE) != 0;
+}
+
+static inline int ext4_es_is_mapped(struct extent_status *es)
+{
+	return (ext4_es_is_written(es) || ext4_es_is_unwritten(es));
+}
+
+static inline void ext4_es_set_referenced(struct extent_status *es)
+{
+	es->es_pblk |= ((ext4_fsblk_t)EXTENT_STATUS_REFERENCED) << ES_SHIFT;
+}
+
+static inline void ext4_es_clear_referenced(struct extent_status *es)
+{
+	es->es_pblk &= ~(((ext4_fsblk_t)EXTENT_STATUS_REFERENCED) << ES_SHIFT);
+}
+
+static inline int ext4_es_is_referenced(struct extent_status *es)
+{
+	return (ext4_es_status(es) & EXTENT_STATUS_REFERENCED) != 0;
+}
+
+static inline ext4_fsblk_t ext4_es_pblock(struct extent_status *es)
+{
+	return es->es_pblk & ~ES_MASK;
+}
+
+static inline ext4_fsblk_t ext4_es_show_pblock(struct extent_status *es)
+{
+	ext4_fsblk_t pblock = ext4_es_pblock(es);
+	return pblock == ~ES_MASK ? 0 : pblock;
+}
+
+static inline void ext4_es_store_pblock(struct extent_status *es,
+					ext4_fsblk_t pb)
+{
+	ext4_fsblk_t block;
+
+	block = (pb & ~ES_MASK) | (es->es_pblk & ES_MASK);
+	es->es_pblk = block;
+}
+
+static inline void ext4_es_store_pblock_status(struct extent_status *es,
+					       ext4_fsblk_t pb,
+					       unsigned int status)
+{
+	WARN_ON_ONCE(!ES_TYPE_VALID(status & ES_TYPE_MASK));
+
+	es->es_pblk = (((ext4_fsblk_t)status << ES_SHIFT) & ES_MASK) |
+		      (pb & ~ES_MASK);
+}
+
+extern int ext4_es_register_shrinker(struct ext4_sb_info *sbi);
+extern void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi);
+
+extern int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v);
+
+extern int __init ext4_init_pending(void);
+extern void ext4_exit_pending(void);
+extern void ext4_init_pending_tree(struct ext4_pending_tree *tree);
+extern void ext4_remove_pending(struct inode *inode, ext4_lblk_t lblk);
+extern bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk);
+extern void ext4_es_insert_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
+					  ext4_lblk_t len, bool lclu_allocated,
+					  bool end_allocated);
+extern void ext4_clear_inode_es(struct inode *inode);
+
+#endif /* _EXT4_EXTENTS_STATUS_H */

linux-7.2.3/fs/ext4/fast_commit.h

@@ -0,0 +1,189 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __FAST_COMMIT_H__
+#define __FAST_COMMIT_H__
+
+/*
+ * Note this file is present in e2fsprogs/lib/ext2fs/fast_commit.h and
+ * linux/fs/ext4/fast_commit.h. These file should always be byte identical.
+ */
+
+/* Fast commit tags */
+#define EXT4_FC_TAG_ADD_RANGE		0x0001
+#define EXT4_FC_TAG_DEL_RANGE		0x0002
+#define EXT4_FC_TAG_CREAT		0x0003
+#define EXT4_FC_TAG_LINK		0x0004
+#define EXT4_FC_TAG_UNLINK		0x0005
+#define EXT4_FC_TAG_INODE		0x0006
+#define EXT4_FC_TAG_PAD			0x0007
+#define EXT4_FC_TAG_TAIL		0x0008
+#define EXT4_FC_TAG_HEAD		0x0009
+
+#define EXT4_FC_SUPPORTED_FEATURES	0x0
+
+/* On disk fast commit tlv value structures */
+
+/* Fast commit on disk tag length structure */
+struct ext4_fc_tl {
+	__le16 fc_tag;
+	__le16 fc_len;
+};
+
+/* Value structure for tag EXT4_FC_TAG_HEAD. */
+struct ext4_fc_head {
+	__le32 fc_features;
+	__le32 fc_tid;
+};
+
+/* Value structure for EXT4_FC_TAG_ADD_RANGE. */
+struct ext4_fc_add_range {
+	__le32 fc_ino;
+	__u8 fc_ex[12];
+};
+
+/* Value structure for tag EXT4_FC_TAG_DEL_RANGE. */
+struct ext4_fc_del_range {
+	__le32 fc_ino;
+	__le32 fc_lblk;
+	__le32 fc_len;
+};
+
+/*
+ * This is the value structure for tags EXT4_FC_TAG_CREAT, EXT4_FC_TAG_LINK
+ * and EXT4_FC_TAG_UNLINK.
+ */
+struct ext4_fc_dentry_info {
+	__le32 fc_parent_ino;
+	__le32 fc_ino;
+	__u8 fc_dname[];
+};
+
+/* Value structure for EXT4_FC_TAG_INODE. */
+struct ext4_fc_inode {
+	__le32 fc_ino;
+	__u8 fc_raw_inode[];
+};
+
+/* Value structure for tag EXT4_FC_TAG_TAIL. */
+struct ext4_fc_tail {
+	__le32 fc_tid;
+	__le32 fc_crc;
+};
+
+/* Tag base length */
+#define EXT4_FC_TAG_BASE_LEN (sizeof(struct ext4_fc_tl))
+
+/*
+ * Fast commit status codes
+ */
+enum {
+	EXT4_FC_STATUS_OK = 0,
+	EXT4_FC_STATUS_INELIGIBLE,
+	EXT4_FC_STATUS_SKIPPED,
+	EXT4_FC_STATUS_FAILED,
+};
+
+/*
+ * Fast commit ineligiblity reasons:
+ */
+enum {
+	EXT4_FC_REASON_XATTR = 0,
+	EXT4_FC_REASON_CROSS_RENAME,
+	EXT4_FC_REASON_JOURNAL_FLAG_CHANGE,
+	EXT4_FC_REASON_NOMEM,
+	EXT4_FC_REASON_SWAP_BOOT,
+	EXT4_FC_REASON_RESIZE,
+	EXT4_FC_REASON_RENAME_DIR,
+	EXT4_FC_REASON_FALLOC_RANGE,
+	EXT4_FC_REASON_INODE_JOURNAL_DATA,
+	EXT4_FC_REASON_ENCRYPTED_FILENAME,
+	EXT4_FC_REASON_MIGRATE,
+	EXT4_FC_REASON_VERITY,
+	EXT4_FC_REASON_MOVE_EXT,
+	EXT4_FC_REASON_MAX
+};
+
+#ifdef __KERNEL__
+/*
+ * In memory list of dentry updates that are performed on the file
+ * system used by fast commit code.
+ */
+struct ext4_fc_dentry_update {
+	int fcd_op;		/* Type of update create / unlink / link */
+	int fcd_parent;		/* Parent inode number */
+	int fcd_ino;		/* Inode number */
+	struct name_snapshot fcd_name;	/* Dirent name */
+	struct list_head fcd_list;
+	struct list_head fcd_dilist;
+};
+
+struct ext4_fc_stats {
+	unsigned int fc_ineligible_reason_count[EXT4_FC_REASON_MAX];
+	unsigned long fc_num_commits;
+	unsigned long fc_ineligible_commits;
+	unsigned long fc_failed_commits;
+	unsigned long fc_skipped_commits;
+	unsigned long fc_numblks;
+	u64 s_fc_avg_commit_time;
+};
+
+#define EXT4_FC_REPLAY_REALLOC_INCREMENT	4
+
+/*
+ * Physical block regions added to different inodes due to fast commit
+ * recovery. These are set during the SCAN phase. During the replay phase,
+ * our allocator excludes these from its allocation. This ensures that
+ * we don't accidentally allocating a block that is going to be used by
+ * another inode.
+ */
+struct ext4_fc_alloc_region {
+	ext4_lblk_t lblk;
+	ext4_fsblk_t pblk;
+	int ino, len;
+};
+
+/*
+ * Fast commit replay state.
+ */
+struct ext4_fc_replay_state {
+	int fc_replay_num_tags;
+	int fc_replay_expected_off;
+	int fc_current_pass;
+	int fc_cur_tag;
+	int fc_crc;
+	struct ext4_fc_alloc_region *fc_regions;
+	int fc_regions_size, fc_regions_used, fc_regions_valid;
+	int *fc_modified_inodes;
+	int fc_modified_inodes_used, fc_modified_inodes_size;
+};
+
+#define region_last(__region) (((__region)->lblk) + ((__region)->len) - 1)
+#endif
+
+static inline const char *tag2str(__u16 tag)
+{
+	switch (tag) {
+	case EXT4_FC_TAG_LINK:
+		return "ADD_ENTRY";
+	case EXT4_FC_TAG_UNLINK:
+		return "DEL_ENTRY";
+	case EXT4_FC_TAG_ADD_RANGE:
+		return "ADD_RANGE";
+	case EXT4_FC_TAG_CREAT:
+		return "CREAT_DENTRY";
+	case EXT4_FC_TAG_DEL_RANGE:
+		return "DEL_RANGE";
+	case EXT4_FC_TAG_INODE:
+		return "INODE";
+	case EXT4_FC_TAG_PAD:
+		return "PAD";
+	case EXT4_FC_TAG_TAIL:
+		return "TAIL";
+	case EXT4_FC_TAG_HEAD:
+		return "HEAD";
+	default:
+		return "ERROR";
+	}
+}
+
+#endif /* __FAST_COMMIT_H__ */

linux-7.2.3/fs/ext4/fsmap.c

@@ -0,0 +1,792 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2017 Oracle.  All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ */
+#include "ext4.h"
+#include <linux/fsmap.h>
+#include "fsmap.h"
+#include "mballoc.h"
+#include <linux/sort.h>
+#include <linux/list_sort.h>
+#include <trace/events/ext4.h>
+
+/* Convert an ext4_fsmap to an fsmap. */
+void ext4_fsmap_from_internal(struct super_block *sb, struct fsmap *dest,
+			      struct ext4_fsmap *src)
+{
+	dest->fmr_device = src->fmr_device;
+	dest->fmr_flags = src->fmr_flags;
+	dest->fmr_physical = src->fmr_physical << sb->s_blocksize_bits;
+	dest->fmr_owner = src->fmr_owner;
+	dest->fmr_offset = 0;
+	dest->fmr_length = src->fmr_length << sb->s_blocksize_bits;
+	dest->fmr_reserved[0] = 0;
+	dest->fmr_reserved[1] = 0;
+	dest->fmr_reserved[2] = 0;
+}
+
+/* Convert an fsmap to an ext4_fsmap. */
+void ext4_fsmap_to_internal(struct super_block *sb, struct ext4_fsmap *dest,
+			    struct fsmap *src)
+{
+	dest->fmr_device = src->fmr_device;
+	dest->fmr_flags = src->fmr_flags;
+	dest->fmr_physical = src->fmr_physical >> sb->s_blocksize_bits;
+	dest->fmr_owner = src->fmr_owner;
+	dest->fmr_length = src->fmr_length >> sb->s_blocksize_bits;
+}
+
+/* getfsmap query state */
+struct ext4_getfsmap_info {
+	struct ext4_fsmap_head	*gfi_head;
+	ext4_fsmap_format_t	gfi_formatter;	/* formatting fn */
+	void			*gfi_format_arg;/* format buffer */
+	ext4_fsblk_t		gfi_next_fsblk;	/* next fsblock we expect */
+	u32			gfi_dev;	/* device id */
+	ext4_group_t		gfi_agno;	/* bg number, if applicable */
+	struct ext4_fsmap	gfi_low;	/* low rmap key */
+	struct ext4_fsmap	gfi_high;	/* high rmap key */
+	struct ext4_fsmap	gfi_lastfree;	/* free ext at end of last bg */
+	struct list_head	gfi_meta_list;	/* fixed metadata list */
+	bool			gfi_last;	/* last extent? */
+};
+
+/* Associate a device with a getfsmap handler. */
+struct ext4_getfsmap_dev {
+	int			(*gfd_fn)(struct super_block *sb,
+				      struct ext4_fsmap *keys,
+				      struct ext4_getfsmap_info *info);
+	u32			gfd_dev;
+};
+
+/* Compare two getfsmap device handlers. */
+static int ext4_getfsmap_dev_compare(const void *p1, const void *p2)
+{
+	const struct ext4_getfsmap_dev *d1 = p1;
+	const struct ext4_getfsmap_dev *d2 = p2;
+
+	return d1->gfd_dev - d2->gfd_dev;
+}
+
+/* Compare a record against our starting point */
+static bool ext4_getfsmap_rec_before_low_key(struct ext4_getfsmap_info *info,
+					     struct ext4_fsmap *rec)
+{
+	return rec->fmr_physical + rec->fmr_length <=
+	       info->gfi_low.fmr_physical;
+}
+
+/*
+ * Format a reverse mapping for getfsmap, having translated rm_startblock
+ * into the appropriate daddr units.
+ */
+static int ext4_getfsmap_helper(struct super_block *sb,
+				struct ext4_getfsmap_info *info,
+				struct ext4_fsmap *rec)
+{
+	struct ext4_fsmap fmr;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_fsblk_t rec_fsblk = rec->fmr_physical;
+	ext4_group_t agno;
+	ext4_grpblk_t cno;
+	int error;
+
+	if (fatal_signal_pending(current))
+		return -EINTR;
+
+	/*
+	 * Filter out records that start before our startpoint, if the
+	 * caller requested that.
+	 */
+	if (ext4_getfsmap_rec_before_low_key(info, rec)) {
+		rec_fsblk += rec->fmr_length;
+		if (info->gfi_next_fsblk < rec_fsblk)
+			info->gfi_next_fsblk = rec_fsblk;
+		return EXT4_QUERY_RANGE_CONTINUE;
+	}
+
+	/* Are we just counting mappings? */
+	if (info->gfi_head->fmh_count == 0) {
+		if (info->gfi_head->fmh_entries == UINT_MAX)
+			return EXT4_QUERY_RANGE_ABORT;
+
+		if (rec_fsblk > info->gfi_next_fsblk)
+			info->gfi_head->fmh_entries++;
+
+		if (info->gfi_last)
+			return EXT4_QUERY_RANGE_CONTINUE;
+
+		info->gfi_head->fmh_entries++;
+
+		rec_fsblk += rec->fmr_length;
+		if (info->gfi_next_fsblk < rec_fsblk)
+			info->gfi_next_fsblk = rec_fsblk;
+		return EXT4_QUERY_RANGE_CONTINUE;
+	}
+
+	/*
+	 * If the record starts past the last physical block we saw,
+	 * then we've found a gap.  Report the gap as being owned by
+	 * whatever the caller specified is the missing owner.
+	 */
+	if (rec_fsblk > info->gfi_next_fsblk) {
+		if (info->gfi_head->fmh_entries >= info->gfi_head->fmh_count)
+			return EXT4_QUERY_RANGE_ABORT;
+
+		ext4_get_group_no_and_offset(sb, info->gfi_next_fsblk,
+				&agno, &cno);
+		trace_ext4_fsmap_mapping(sb, info->gfi_dev, agno,
+				EXT4_C2B(sbi, cno),
+				rec_fsblk - info->gfi_next_fsblk,
+				EXT4_FMR_OWN_UNKNOWN);
+
+		fmr.fmr_device = info->gfi_dev;
+		fmr.fmr_physical = info->gfi_next_fsblk;
+		fmr.fmr_owner = EXT4_FMR_OWN_UNKNOWN;
+		fmr.fmr_length = rec_fsblk - info->gfi_next_fsblk;
+		fmr.fmr_flags = FMR_OF_SPECIAL_OWNER;
+		error = info->gfi_formatter(&fmr, info->gfi_format_arg);
+		if (error)
+			return error;
+		info->gfi_head->fmh_entries++;
+	}
+
+	if (info->gfi_last)
+		goto out;
+
+	/* Fill out the extent we found */
+	if (info->gfi_head->fmh_entries >= info->gfi_head->fmh_count)
+		return EXT4_QUERY_RANGE_ABORT;
+
+	ext4_get_group_no_and_offset(sb, rec_fsblk, &agno, &cno);
+	trace_ext4_fsmap_mapping(sb, info->gfi_dev, agno, EXT4_C2B(sbi, cno),
+			rec->fmr_length, rec->fmr_owner);
+
+	fmr.fmr_device = info->gfi_dev;
+	fmr.fmr_physical = rec_fsblk;
+	fmr.fmr_owner = rec->fmr_owner;
+	fmr.fmr_flags = FMR_OF_SPECIAL_OWNER;
+	fmr.fmr_length = rec->fmr_length;
+	error = info->gfi_formatter(&fmr, info->gfi_format_arg);
+	if (error)
+		return error;
+	info->gfi_head->fmh_entries++;
+
+out:
+	rec_fsblk += rec->fmr_length;
+	if (info->gfi_next_fsblk < rec_fsblk)
+		info->gfi_next_fsblk = rec_fsblk;
+	return EXT4_QUERY_RANGE_CONTINUE;
+}
+
+static inline ext4_fsblk_t ext4_fsmap_next_pblk(struct ext4_fsmap *fmr)
+{
+	return fmr->fmr_physical + fmr->fmr_length;
+}
+
+static int ext4_getfsmap_meta_helper(struct super_block *sb,
+				     ext4_group_t agno, ext4_grpblk_t start,
+				     ext4_grpblk_t len, void *priv)
+{
+	struct ext4_getfsmap_info *info = priv;
+	struct ext4_fsmap *p;
+	struct ext4_fsmap *tmp;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_fsblk_t fsb, fs_start, fs_end;
+	int error;
+
+	fs_start = fsb = (EXT4_C2B(sbi, start) +
+			  ext4_group_first_block_no(sb, agno));
+	fs_end = fs_start + EXT4_C2B(sbi, len);
+
+	/*
+	 * Return relevant extents from the meta_list. We emit all extents that
+	 * partially/fully overlap with the query range
+	 */
+	list_for_each_entry_safe(p, tmp, &info->gfi_meta_list, fmr_list) {
+		if (p->fmr_physical + p->fmr_length <= info->gfi_next_fsblk) {
+			list_del(&p->fmr_list);
+			kfree(p);
+			continue;
+		}
+		if (p->fmr_physical <= fs_end &&
+		    p->fmr_physical + p->fmr_length > fs_start) {
+			/* Emit the retained free extent record if present */
+			if (info->gfi_lastfree.fmr_owner) {
+				error = ext4_getfsmap_helper(sb, info,
+							&info->gfi_lastfree);
+				if (error)
+					return error;
+				info->gfi_lastfree.fmr_owner = 0;
+			}
+			error = ext4_getfsmap_helper(sb, info, p);
+			if (error)
+				return error;
+			fsb = p->fmr_physical + p->fmr_length;
+			if (info->gfi_next_fsblk < fsb)
+				info->gfi_next_fsblk = fsb;
+			list_del(&p->fmr_list);
+			kfree(p);
+			continue;
+		}
+	}
+	if (info->gfi_next_fsblk < fsb)
+		info->gfi_next_fsblk = fsb;
+
+	return 0;
+}
+
+
+/* Transform a blockgroup's free record into a fsmap */
+static int ext4_getfsmap_datadev_helper(struct super_block *sb,
+					ext4_group_t agno, ext4_grpblk_t start,
+					ext4_grpblk_t len, void *priv)
+{
+	struct ext4_fsmap irec;
+	struct ext4_getfsmap_info *info = priv;
+	struct ext4_fsmap *p;
+	struct ext4_fsmap *tmp;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_fsblk_t fsb;
+	ext4_fsblk_t fslen;
+	int error;
+
+	fsb = (EXT4_C2B(sbi, start) + ext4_group_first_block_no(sb, agno));
+	fslen = EXT4_C2B(sbi, len);
+
+	/* If the retained free extent record is set... */
+	if (info->gfi_lastfree.fmr_owner) {
+		/* ...and abuts this one, lengthen it and return. */
+		if (ext4_fsmap_next_pblk(&info->gfi_lastfree) == fsb) {
+			info->gfi_lastfree.fmr_length += fslen;
+			return 0;
+		}
+
+		/*
+		 * There's a gap between the two free extents; emit the
+		 * retained extent prior to merging the meta_list.
+		 */
+		error = ext4_getfsmap_helper(sb, info, &info->gfi_lastfree);
+		if (error)
+			return error;
+		info->gfi_lastfree.fmr_owner = 0;
+	}
+
+	/* Merge in any relevant extents from the meta_list */
+	list_for_each_entry_safe(p, tmp, &info->gfi_meta_list, fmr_list) {
+		if (p->fmr_physical + p->fmr_length <= info->gfi_next_fsblk) {
+			list_del(&p->fmr_list);
+			kfree(p);
+		} else if (p->fmr_physical < fsb) {
+			error = ext4_getfsmap_helper(sb, info, p);
+			if (error)
+				return error;
+
+			list_del(&p->fmr_list);
+			kfree(p);
+		}
+	}
+
+	irec.fmr_device = 0;
+	irec.fmr_physical = fsb;
+	irec.fmr_length = fslen;
+	irec.fmr_owner = EXT4_FMR_OWN_FREE;
+	irec.fmr_flags = 0;
+
+	/* If this is a free extent at the end of a bg, buffer it. */
+	if (ext4_fsmap_next_pblk(&irec) ==
+			ext4_group_first_block_no(sb, agno + 1)) {
+		info->gfi_lastfree = irec;
+		return 0;
+	}
+
+	/* Otherwise, emit it */
+	return ext4_getfsmap_helper(sb, info, &irec);
+}
+
+/* Execute a getfsmap query against the log device. */
+static int ext4_getfsmap_logdev(struct super_block *sb, struct ext4_fsmap *keys,
+				struct ext4_getfsmap_info *info)
+{
+	journal_t *journal = EXT4_SB(sb)->s_journal;
+	struct ext4_fsmap irec;
+
+	/* Set up search keys */
+	info->gfi_low = keys[0];
+	info->gfi_low.fmr_length = 0;
+
+	memset(&info->gfi_high, 0xFF, sizeof(info->gfi_high));
+
+	trace_ext4_fsmap_low_key(sb, info->gfi_dev, 0,
+			info->gfi_low.fmr_physical,
+			info->gfi_low.fmr_length,
+			info->gfi_low.fmr_owner);
+
+	trace_ext4_fsmap_high_key(sb, info->gfi_dev, 0,
+			info->gfi_high.fmr_physical,
+			info->gfi_high.fmr_length,
+			info->gfi_high.fmr_owner);
+
+	if (keys[0].fmr_physical > 0)
+		return 0;
+
+	/* Fabricate an rmap entry for the external log device. */
+	irec.fmr_physical = journal->j_blk_offset;
+	irec.fmr_length = journal->j_total_len;
+	irec.fmr_owner = EXT4_FMR_OWN_LOG;
+	irec.fmr_flags = 0;
+
+	return ext4_getfsmap_helper(sb, info, &irec);
+}
+
+/* Helper to fill out an ext4_fsmap. */
+static inline int ext4_getfsmap_fill(struct list_head *meta_list,
+				     ext4_fsblk_t fsb, ext4_fsblk_t len,
+				     uint64_t owner)
+{
+	struct ext4_fsmap *fsm;
+
+	fsm = kmalloc_obj(*fsm, GFP_NOFS);
+	if (!fsm)
+		return -ENOMEM;
+	fsm->fmr_device = 0;
+	fsm->fmr_flags = 0;
+	fsm->fmr_physical = fsb;
+	fsm->fmr_owner = owner;
+	fsm->fmr_length = len;
+	list_add_tail(&fsm->fmr_list, meta_list);
+
+	return 0;
+}
+
+/*
+ * This function returns the number of file system metadata blocks at
+ * the beginning of a block group, including the reserved gdt blocks.
+ */
+static unsigned int ext4_getfsmap_find_sb(struct super_block *sb,
+					  ext4_group_t agno,
+					  struct list_head *meta_list)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_fsblk_t fsb = ext4_group_first_block_no(sb, agno);
+	ext4_fsblk_t len;
+	unsigned long first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);
+	unsigned long metagroup = agno / EXT4_DESC_PER_BLOCK(sb);
+	int error;
+
+	/* Record the superblock. */
+	if (ext4_bg_has_super(sb, agno)) {
+		error = ext4_getfsmap_fill(meta_list, fsb, 1, EXT4_FMR_OWN_FS);
+		if (error)
+			return error;
+		fsb++;
+	}
+
+	/* Record the group descriptors. */
+	len = ext4_bg_num_gdb(sb, agno);
+	if (!len)
+		return 0;
+	error = ext4_getfsmap_fill(meta_list, fsb, len,
+				   EXT4_FMR_OWN_GDT);
+	if (error)
+		return error;
+	fsb += len;
+
+	/* Reserved GDT blocks */
+	if (!ext4_has_feature_meta_bg(sb) || metagroup < first_meta_bg) {
+		len = le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
+
+		/*
+		 * mkfs.ext4 can set s_reserved_gdt_blocks as 0 in some cases,
+		 * check for that.
+		 */
+		if (!len)
+			return 0;
+
+		error = ext4_getfsmap_fill(meta_list, fsb, len,
+					   EXT4_FMR_OWN_RESV_GDT);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/* Compare two fsmap items. */
+static int ext4_getfsmap_compare(void *priv,
+				 const struct list_head *a,
+				 const struct list_head *b)
+{
+	struct ext4_fsmap *fa;
+	struct ext4_fsmap *fb;
+
+	fa = container_of(a, struct ext4_fsmap, fmr_list);
+	fb = container_of(b, struct ext4_fsmap, fmr_list);
+	if (fa->fmr_physical < fb->fmr_physical)
+		return -1;
+	else if (fa->fmr_physical > fb->fmr_physical)
+		return 1;
+	return 0;
+}
+
+/* Merge adjacent extents of fixed metadata. */
+static void ext4_getfsmap_merge_fixed_metadata(struct list_head *meta_list)
+{
+	struct ext4_fsmap *p;
+	struct ext4_fsmap *prev = NULL;
+	struct ext4_fsmap *tmp;
+
+	list_for_each_entry_safe(p, tmp, meta_list, fmr_list) {
+		if (!prev) {
+			prev = p;
+			continue;
+		}
+
+		if (prev->fmr_owner == p->fmr_owner &&
+		    prev->fmr_physical + prev->fmr_length == p->fmr_physical) {
+			prev->fmr_length += p->fmr_length;
+			list_del(&p->fmr_list);
+			kfree(p);
+		} else
+			prev = p;
+	}
+}
+
+/* Free a list of fixed metadata. */
+static void ext4_getfsmap_free_fixed_metadata(struct list_head *meta_list)
+{
+	struct ext4_fsmap *p;
+	struct ext4_fsmap *tmp;
+
+	list_for_each_entry_safe(p, tmp, meta_list, fmr_list) {
+		list_del(&p->fmr_list);
+		kfree(p);
+	}
+}
+
+/* Find all the fixed metadata in the filesystem. */
+static int ext4_getfsmap_find_fixed_metadata(struct super_block *sb,
+					     struct list_head *meta_list)
+{
+	struct ext4_group_desc *gdp;
+	ext4_group_t agno;
+	int error;
+
+	INIT_LIST_HEAD(meta_list);
+
+	/* Collect everything. */
+	for (agno = 0; agno < EXT4_SB(sb)->s_groups_count; agno++) {
+		gdp = ext4_get_group_desc(sb, agno, NULL);
+		if (!gdp) {
+			error = -EFSCORRUPTED;
+			goto err;
+		}
+
+		/* Superblock & GDT */
+		error = ext4_getfsmap_find_sb(sb, agno, meta_list);
+		if (error)
+			goto err;
+
+		/* Block bitmap */
+		error = ext4_getfsmap_fill(meta_list,
+					   ext4_block_bitmap(sb, gdp), 1,
+					   EXT4_FMR_OWN_BLKBM);
+		if (error)
+			goto err;
+
+		/* Inode bitmap */
+		error = ext4_getfsmap_fill(meta_list,
+					   ext4_inode_bitmap(sb, gdp), 1,
+					   EXT4_FMR_OWN_INOBM);
+		if (error)
+			goto err;
+
+		/* Inodes */
+		error = ext4_getfsmap_fill(meta_list,
+					   ext4_inode_table(sb, gdp),
+					   EXT4_SB(sb)->s_itb_per_group,
+					   EXT4_FMR_OWN_INODES);
+		if (error)
+			goto err;
+	}
+
+	/* Sort the list */
+	list_sort(NULL, meta_list, ext4_getfsmap_compare);
+
+	/* Merge adjacent extents */
+	ext4_getfsmap_merge_fixed_metadata(meta_list);
+
+	return 0;
+err:
+	ext4_getfsmap_free_fixed_metadata(meta_list);
+	return error;
+}
+
+/* Execute a getfsmap query against the buddy bitmaps */
+static int ext4_getfsmap_datadev(struct super_block *sb,
+				 struct ext4_fsmap *keys,
+				 struct ext4_getfsmap_info *info)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_fsblk_t start_fsb;
+	ext4_fsblk_t end_fsb;
+	ext4_fsblk_t bofs;
+	ext4_fsblk_t eofs;
+	ext4_group_t start_ag;
+	ext4_group_t end_ag;
+	ext4_grpblk_t first_cluster;
+	ext4_grpblk_t last_cluster;
+	struct ext4_fsmap irec;
+	int error = 0;
+
+	bofs = le32_to_cpu(sbi->s_es->s_first_data_block);
+	eofs = ext4_blocks_count(sbi->s_es);
+	if (keys[0].fmr_physical >= eofs)
+		return 0;
+	else if (keys[0].fmr_physical < bofs)
+		keys[0].fmr_physical = bofs;
+	if (keys[1].fmr_physical >= eofs)
+		keys[1].fmr_physical = eofs - 1;
+	if (keys[1].fmr_physical < keys[0].fmr_physical)
+		return 0;
+	start_fsb = keys[0].fmr_physical;
+	end_fsb = keys[1].fmr_physical;
+
+	/* Determine first and last group to examine based on start and end */
+	ext4_get_group_no_and_offset(sb, start_fsb, &start_ag, &first_cluster);
+	ext4_get_group_no_and_offset(sb, end_fsb, &end_ag, &last_cluster);
+
+	/*
+	 * Convert the fsmap low/high keys to bg based keys.  Initialize
+	 * low to the fsmap low key and max out the high key to the end
+	 * of the bg.
+	 */
+	info->gfi_low = keys[0];
+	info->gfi_low.fmr_physical = EXT4_C2B(sbi, first_cluster);
+	info->gfi_low.fmr_length = 0;
+
+	memset(&info->gfi_high, 0xFF, sizeof(info->gfi_high));
+
+	/* Assemble a list of all the fixed-location metadata. */
+	error = ext4_getfsmap_find_fixed_metadata(sb, &info->gfi_meta_list);
+	if (error)
+		goto err;
+
+	/* Query each bg */
+	for (info->gfi_agno = start_ag;
+	     info->gfi_agno <= end_ag;
+	     info->gfi_agno++) {
+		/*
+		 * Set the bg high key from the fsmap high key if this
+		 * is the last bg that we're querying.
+		 */
+		if (info->gfi_agno == end_ag) {
+			info->gfi_high = keys[1];
+			info->gfi_high.fmr_physical = EXT4_C2B(sbi,
+					last_cluster);
+			info->gfi_high.fmr_length = 0;
+		}
+
+		trace_ext4_fsmap_low_key(sb, info->gfi_dev, info->gfi_agno,
+				info->gfi_low.fmr_physical,
+				info->gfi_low.fmr_length,
+				info->gfi_low.fmr_owner);
+
+		trace_ext4_fsmap_high_key(sb, info->gfi_dev, info->gfi_agno,
+				info->gfi_high.fmr_physical,
+				info->gfi_high.fmr_length,
+				info->gfi_high.fmr_owner);
+
+		error = ext4_mballoc_query_range(sb, info->gfi_agno,
+				EXT4_B2C(sbi, info->gfi_low.fmr_physical),
+				EXT4_B2C(sbi, info->gfi_high.fmr_physical),
+				ext4_getfsmap_meta_helper,
+				ext4_getfsmap_datadev_helper, info);
+		if (error)
+			goto err;
+
+		/*
+		 * Set the bg low key to the start of the bg prior to
+		 * moving on to the next bg.
+		 */
+		if (info->gfi_agno == start_ag)
+			memset(&info->gfi_low, 0, sizeof(info->gfi_low));
+	}
+
+	/* Do we have a retained free extent? */
+	if (info->gfi_lastfree.fmr_owner) {
+		error = ext4_getfsmap_helper(sb, info, &info->gfi_lastfree);
+		if (error)
+			goto err;
+	}
+
+	/*
+	 * The dummy record below will cause ext4_getfsmap_helper() to report
+	 * any allocated blocks at the end of the range.
+	 */
+	irec.fmr_device = 0;
+	irec.fmr_physical = end_fsb + 1;
+	irec.fmr_length = 0;
+	irec.fmr_owner = EXT4_FMR_OWN_FREE;
+	irec.fmr_flags = 0;
+
+	info->gfi_last = true;
+	error = ext4_getfsmap_helper(sb, info, &irec);
+	if (error)
+		goto err;
+
+err:
+	ext4_getfsmap_free_fixed_metadata(&info->gfi_meta_list);
+	return error;
+}
+
+/* Do we recognize the device? */
+static bool ext4_getfsmap_is_valid_device(struct super_block *sb,
+					  struct ext4_fsmap *fm)
+{
+	if (fm->fmr_device == 0 || fm->fmr_device == UINT_MAX ||
+	    fm->fmr_device == new_encode_dev(sb->s_bdev->bd_dev))
+		return true;
+	if (EXT4_SB(sb)->s_journal_bdev_file &&
+	    fm->fmr_device ==
+	    new_encode_dev(file_bdev(EXT4_SB(sb)->s_journal_bdev_file)->bd_dev))
+		return true;
+	return false;
+}
+
+/* Ensure that the low key is less than the high key. */
+static bool ext4_getfsmap_check_keys(struct ext4_fsmap *low_key,
+				     struct ext4_fsmap *high_key)
+{
+	if (low_key->fmr_device > high_key->fmr_device)
+		return false;
+	if (low_key->fmr_device < high_key->fmr_device)
+		return true;
+
+	if (low_key->fmr_physical > high_key->fmr_physical)
+		return false;
+	if (low_key->fmr_physical < high_key->fmr_physical)
+		return true;
+
+	if (low_key->fmr_owner > high_key->fmr_owner)
+		return false;
+	if (low_key->fmr_owner < high_key->fmr_owner)
+		return true;
+
+	return false;
+}
+
+#define EXT4_GETFSMAP_DEVS	2
+/*
+ * Get filesystem's extents as described in head, and format for
+ * output.  Calls formatter to fill the user's buffer until all
+ * extents are mapped, until the passed-in head->fmh_count slots have
+ * been filled, or until the formatter short-circuits the loop, if it
+ * is tracking filled-in extents on its own.
+ *
+ * Key to Confusion
+ * ----------------
+ * There are multiple levels of keys and counters at work here:
+ * _fsmap_head.fmh_keys		-- low and high fsmap keys passed in;
+ * 				   these reflect fs-wide block addrs.
+ * dkeys			-- fmh_keys used to query each device;
+ * 				   these are fmh_keys but w/ the low key
+ * 				   bumped up by fmr_length.
+ * _getfsmap_info.gfi_next_fsblk-- next fs block we expect to see; this
+ *				   is how we detect gaps in the fsmap
+ *				   records and report them.
+ * _getfsmap_info.gfi_low/high	-- per-bg low/high keys computed from
+ * 				   dkeys; used to query the free space.
+ */
+int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head,
+		  ext4_fsmap_format_t formatter, void *arg)
+{
+	struct ext4_fsmap dkeys[2];	/* per-dev keys */
+	struct ext4_getfsmap_dev handlers[EXT4_GETFSMAP_DEVS];
+	struct ext4_getfsmap_info info = { NULL };
+	int i;
+	int error = 0;
+
+	if (head->fmh_iflags & ~FMH_IF_VALID)
+		return -EINVAL;
+	if (!ext4_getfsmap_is_valid_device(sb, &head->fmh_keys[0]) ||
+	    !ext4_getfsmap_is_valid_device(sb, &head->fmh_keys[1]))
+		return -EINVAL;
+
+	head->fmh_entries = 0;
+
+	/* Set up our device handlers. */
+	memset(handlers, 0, sizeof(handlers));
+	handlers[0].gfd_dev = new_encode_dev(sb->s_bdev->bd_dev);
+	handlers[0].gfd_fn = ext4_getfsmap_datadev;
+	if (EXT4_SB(sb)->s_journal_bdev_file) {
+		handlers[1].gfd_dev = new_encode_dev(
+			file_bdev(EXT4_SB(sb)->s_journal_bdev_file)->bd_dev);
+		handlers[1].gfd_fn = ext4_getfsmap_logdev;
+	}
+
+	sort(handlers, EXT4_GETFSMAP_DEVS, sizeof(struct ext4_getfsmap_dev),
+			ext4_getfsmap_dev_compare, NULL);
+
+	/*
+	 * To continue where we left off, we allow userspace to use the
+	 * last mapping from a previous call as the low key of the next.
+	 * This is identified by a non-zero length in the low key. We
+	 * have to increment the low key in this scenario to ensure we
+	 * don't return the same mapping again, and instead return the
+	 * very next mapping.
+	 *
+	 * Bump the physical offset as there can be no other mapping for
+	 * the same physical block range.
+	 */
+	dkeys[0] = head->fmh_keys[0];
+	dkeys[0].fmr_physical += dkeys[0].fmr_length;
+	dkeys[0].fmr_owner = 0;
+	dkeys[0].fmr_length = 0;
+	memset(&dkeys[1], 0xFF, sizeof(struct ext4_fsmap));
+
+	if (!ext4_getfsmap_check_keys(dkeys, &head->fmh_keys[1]))
+		return -EINVAL;
+
+	info.gfi_next_fsblk = head->fmh_keys[0].fmr_physical +
+			  head->fmh_keys[0].fmr_length;
+	info.gfi_formatter = formatter;
+	info.gfi_format_arg = arg;
+	info.gfi_head = head;
+
+	/* For each device we support... */
+	for (i = 0; i < EXT4_GETFSMAP_DEVS; i++) {
+		/* Is this device within the range the user asked for? */
+		if (!handlers[i].gfd_fn)
+			continue;
+		if (head->fmh_keys[0].fmr_device > handlers[i].gfd_dev)
+			continue;
+		if (head->fmh_keys[1].fmr_device < handlers[i].gfd_dev)
+			break;
+
+		/*
+		 * If this device number matches the high key, we have
+		 * to pass the high key to the handler to limit the
+		 * query results.  If the device number exceeds the
+		 * low key, zero out the low key so that we get
+		 * everything from the beginning.
+		 */
+		if (handlers[i].gfd_dev == head->fmh_keys[1].fmr_device)
+			dkeys[1] = head->fmh_keys[1];
+		if (handlers[i].gfd_dev > head->fmh_keys[0].fmr_device)
+			memset(&dkeys[0], 0, sizeof(struct ext4_fsmap));
+
+		info.gfi_dev = handlers[i].gfd_dev;
+		info.gfi_last = false;
+		info.gfi_agno = -1;
+		error = handlers[i].gfd_fn(sb, dkeys, &info);
+		if (error)
+			break;
+		info.gfi_next_fsblk = 0;
+	}
+
+	head->fmh_oflags = FMH_OF_DEV_T;
+	return error;
+}

linux-7.2.3/fs/ext4/fsmap.h

@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2017 Oracle.  All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ */
+#ifndef __EXT4_FSMAP_H__
+#define	__EXT4_FSMAP_H__
+
+struct fsmap;
+
+/* internal fsmap representation */
+struct ext4_fsmap {
+	struct list_head	fmr_list;
+	dev_t		fmr_device;	/* device id */
+	uint32_t	fmr_flags;	/* mapping flags */
+	uint64_t	fmr_physical;	/* device offset of segment */
+	uint64_t	fmr_owner;	/* owner id */
+	uint64_t	fmr_length;	/* length of segment, blocks */
+};
+
+struct ext4_fsmap_head {
+	uint32_t	fmh_iflags;	/* control flags */
+	uint32_t	fmh_oflags;	/* output flags */
+	unsigned int	fmh_count;	/* # of entries in array incl. input */
+	unsigned int	fmh_entries;	/* # of entries filled in (output). */
+
+	struct ext4_fsmap fmh_keys[2];	/* low and high keys */
+};
+
+void ext4_fsmap_from_internal(struct super_block *sb, struct fsmap *dest,
+		struct ext4_fsmap *src);
+void ext4_fsmap_to_internal(struct super_block *sb, struct ext4_fsmap *dest,
+		struct fsmap *src);
+
+/* fsmap to userspace formatter - copy to user & advance pointer */
+typedef int (*ext4_fsmap_format_t)(struct ext4_fsmap *, void *);
+
+int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head,
+		ext4_fsmap_format_t formatter, void *arg);
+
+#define EXT4_QUERY_RANGE_ABORT		1
+#define EXT4_QUERY_RANGE_CONTINUE	0
+
+/*	fmr_owner special values for FS_IOC_GETFSMAP; some share w/ XFS */
+#define EXT4_FMR_OWN_FREE	FMR_OWN_FREE      /* free space */
+#define EXT4_FMR_OWN_UNKNOWN	FMR_OWN_UNKNOWN   /* unknown owner */
+#define EXT4_FMR_OWN_FS		FMR_OWNER('X', 1) /* static fs metadata */
+#define EXT4_FMR_OWN_LOG	FMR_OWNER('X', 2) /* journalling log */
+#define EXT4_FMR_OWN_INODES	FMR_OWNER('X', 5) /* inodes */
+#define EXT4_FMR_OWN_GDT	FMR_OWNER('f', 1) /* group descriptors */
+#define EXT4_FMR_OWN_RESV_GDT	FMR_OWNER('f', 2) /* reserved gdt blocks */
+#define EXT4_FMR_OWN_BLKBM	FMR_OWNER('f', 3) /* block bitmap */
+#define EXT4_FMR_OWN_INOBM	FMR_OWNER('f', 4) /* inode bitmap */
+
+#endif /* __EXT4_FSMAP_H__ */

linux-7.2.3/fs/ext4/fsync.c

@@ -0,0 +1,190 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/ext4/fsync.c
+ *
+ *  Copyright (C) 1993  Stephen Tweedie (sct@redhat.com)
+ *  from
+ *  Copyright (C) 1992  Remy Card (card@masi.ibp.fr)
+ *                      Laboratoire MASI - Institut Blaise Pascal
+ *                      Universite Pierre et Marie Curie (Paris VI)
+ *  from
+ *  linux/fs/minix/truncate.c   Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  ext4fs fsync primitive
+ *
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ *
+ *  Removed unnecessary code duplication for little endian machines
+ *  and excessive __inline__s.
+ *        Andi Kleen, 1997
+ *
+ * Major simplications and cleanup - we only need to do the metadata, because
+ * we can depend on generic_block_fdatasync() to sync the data blocks.
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/writeback.h>
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+
+#include "ext4.h"
+#include "ext4_jbd2.h"
+
+#include <trace/events/ext4.h>
+
+/*
+ * If we're not journaling and this is a just-created file, we have to
+ * sync our parent directory (if it was freshly created) since
+ * otherwise it will only be written by writeback, leaving a huge
+ * window during which a crash may lose the file.  This may apply for
+ * the parent directory's parent as well, and so on recursively, if
+ * they are also freshly created.
+ */
+static int ext4_sync_parent(struct inode *inode)
+{
+	struct dentry *dentry, *next;
+	int ret = 0;
+
+	if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY))
+		return 0;
+	dentry = d_find_any_alias(inode);
+	if (!dentry)
+		return 0;
+	while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
+		ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
+
+		next = dget_parent(dentry);
+		dput(dentry);
+		dentry = next;
+		inode = dentry->d_inode;
+
+		/*
+		 * The directory inode may have gone through rmdir by now. But
+		 * the inode itself and its blocks are still allocated (we hold
+		 * a reference to the inode via its dentry), so it didn't go
+		 * through ext4_evict_inode()) and so we are safe to flush
+		 * metadata blocks and the inode.
+		 */
+		ret = mmb_sync(&EXT4_I(inode)->i_metadata_bhs);
+		if (ret)
+			break;
+		ret = sync_inode_metadata(inode, 1);
+		if (ret)
+			break;
+	}
+	dput(dentry);
+	return ret;
+}
+
+static int ext4_fsync_nojournal(struct file *file, loff_t start, loff_t end,
+				int datasync, bool *needs_barrier)
+{
+	struct inode *inode = file->f_inode;
+	struct writeback_control wbc = {
+		.sync_mode = WB_SYNC_ALL,
+		.nr_to_write = 0,
+	};
+	int ret;
+
+	ret = mmb_fsync_noflush(file, &EXT4_I(inode)->i_metadata_bhs,
+				start, end, datasync);
+	if (ret)
+		return ret;
+
+	/* Force writeout of inode table buffer to disk */
+	ret = ext4_write_inode(inode, &wbc);
+	if (ret)
+		return ret;
+
+	ret = ext4_sync_parent(inode);
+
+	if (test_opt(inode->i_sb, BARRIER))
+		*needs_barrier = true;
+
+	return ret;
+}
+
+static int ext4_fsync_journal(struct inode *inode, bool datasync,
+			     bool *needs_barrier)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+	tid_t commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
+
+	/*
+	 * Fastcommit does not really support fsync on directories or other
+	 * special files. Force a full commit.
+	 */
+	if (!S_ISREG(inode->i_mode))
+		return ext4_force_commit(inode->i_sb);
+
+	if (journal->j_flags & JBD2_BARRIER &&
+	    !jbd2_trans_will_send_data_barrier(journal, commit_tid))
+		*needs_barrier = true;
+
+	return ext4_fc_commit(journal, commit_tid);
+}
+
+/*
+ * akpm: A new design for ext4_sync_file().
+ *
+ * This is only called from sys_fsync(), sys_fdatasync() and sys_msync().
+ * There cannot be a transaction open by this task.
+ * Another task could have dirtied this inode.  Its data can be in any
+ * state in the journalling system.
+ *
+ * What we do is just kick off a commit and wait on it.  This will snapshot the
+ * inode to disk.
+ */
+int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	int ret = 0, err;
+	bool needs_barrier = false;
+	struct inode *inode = file->f_mapping->host;
+
+	ret = ext4_emergency_state(inode->i_sb);
+	if (unlikely(ret))
+		return ret;
+
+	ASSERT(ext4_journal_current_handle() == NULL);
+
+	trace_ext4_sync_file_enter(file, datasync);
+
+	if (sb_rdonly(inode->i_sb))
+		goto out;
+
+	if (!EXT4_SB(inode->i_sb)->s_journal) {
+		ret = ext4_fsync_nojournal(file, start, end, datasync,
+					   &needs_barrier);
+		if (needs_barrier)
+			goto issue_flush;
+		goto out;
+	}
+
+	ret = file_write_and_wait_range(file, start, end);
+	if (ret)
+		goto out;
+
+	/*
+	 *  The caller's filemap_fdatawrite()/wait will sync the data.
+	 *  Metadata is in the journal, we wait for proper transaction to
+	 *  commit here.
+	 */
+	ret = ext4_fsync_journal(inode, datasync, &needs_barrier);
+
+issue_flush:
+	if (needs_barrier) {
+		err = blkdev_issue_flush(inode->i_sb->s_bdev);
+		if (!ret)
+			ret = err;
+	}
+out:
+	err = file_check_and_advance_wb_err(file);
+	if (ret == 0)
+		ret = err;
+	trace_ext4_sync_file_exit(inode, ret);
+	return ret;
+}

linux-7.2.3/fs/ext4/hash-test.c

@@ -0,0 +1,567 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnit tests for ext4 directory hash computation.
+ */
+
+#include <kunit/test.h>
+#include <kunit/resource.h>
+#include <linux/fs.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/unicode.h>
+#include "ext4.h"
+
+static void ext4_hash_init_fake_dir(struct inode *dir, struct super_block *sb)
+{
+	memset(sb, 0, sizeof(*sb));
+	memset(dir, 0, sizeof(*dir));
+	dir->i_sb = sb;
+	strscpy(sb->s_id, "kunit-ext4", sizeof(sb->s_id));
+}
+
+static void ext4_hash_init_fake_dir_with_sbi(struct inode *dir,
+					     struct super_block *sb,
+					     struct ext4_sb_info *sbi)
+{
+	ext4_hash_init_fake_dir(dir, sb);
+	memset(sbi, 0, sizeof(*sbi));
+	sb->s_fs_info = sbi;
+	sbi->s_sb = sb;
+}
+
+#ifdef CONFIG_FS_ENCRYPTION
+static const struct fscrypt_operations ext4_hash_test_cryptops = {
+	.inode_info_offs =
+		(int)offsetof(struct ext4_inode_info, i_crypt_info) -
+		(int)offsetof(struct ext4_inode_info, vfs_inode),
+};
+#endif
+
+static void ext4_hash_init_fake_ext4_dir(struct ext4_inode_info *ei,
+					 struct super_block *sb,
+					 struct ext4_sb_info *sbi)
+{
+	struct inode *dir = &ei->vfs_inode;
+
+	memset(sb, 0, sizeof(*sb));
+	memset(ei, 0, sizeof(*ei));
+	memset(sbi, 0, sizeof(*sbi));
+
+	strscpy(sb->s_id, "kunit-ext4", sizeof(sb->s_id));
+	sb->s_fs_info = sbi;
+	sbi->s_sb = sb;
+
+	dir->i_sb = sb;
+	dir->i_mode = S_IFDIR;
+
+#ifdef CONFIG_FS_ENCRYPTION
+	fscrypt_set_ops(sb, &ext4_hash_test_cryptops);
+#endif
+}
+
+struct ext4_dirhash_test_case {
+	const char *name;
+	u32 hash_version;
+	const char *input;
+	int len;
+	u32 seed[4];
+	bool use_seed;
+	u32 expected_hash;
+	u32 expected_minor_hash;
+};
+
+static const struct ext4_dirhash_test_case ext4_dirhash_test_cases[] = {
+	{
+		.name = "legacy_abc",
+		.hash_version = DX_HASH_LEGACY,
+		.input = "abc",
+		.len = 3,
+		.use_seed = false,
+		.expected_hash = 0x75afd992,
+		.expected_minor_hash = 0x00000000,
+	},
+	{
+		.name = "legacy_unsigned_abc",
+		.hash_version = DX_HASH_LEGACY_UNSIGNED,
+		.input = "abc",
+		.len = 3,
+		.use_seed = false,
+		.expected_hash = 0x75afd992,
+		.expected_minor_hash = 0x00000000,
+	},
+	{
+		.name = "half_md4_abc",
+		.hash_version = DX_HASH_HALF_MD4,
+		.input = "abc",
+		.len = 3,
+		.use_seed = false,
+		.expected_hash = 0xd196a868,
+		.expected_minor_hash = 0xc420eb28,
+	},
+	{
+		.name = "half_md4_unsigned_abc",
+		.hash_version = DX_HASH_HALF_MD4_UNSIGNED,
+		.input = "abc",
+		.len = 3,
+		.use_seed = false,
+		.expected_hash = 0xd196a868,
+		.expected_minor_hash = 0xc420eb28,
+	},
+	{
+		.name = "tea_abc",
+		.hash_version = DX_HASH_TEA,
+		.input = "abc",
+		.len = 3,
+		.use_seed = false,
+		.expected_hash = 0xb1435ec4,
+		.expected_minor_hash = 0x3f7eaa0e,
+	},
+	{
+		.name = "tea_unsigned_abc",
+		.hash_version = DX_HASH_TEA_UNSIGNED,
+		.input = "abc",
+		.len = 3,
+		.use_seed = false,
+		.expected_hash = 0xb1435ec4,
+		.expected_minor_hash = 0x3f7eaa0e,
+	},
+	{
+		.name = "empty_half_md4",
+		.hash_version = DX_HASH_HALF_MD4,
+		.input = "",
+		.len = 0,
+		.use_seed = false,
+		.expected_hash = 0xefcdab88,
+		.expected_minor_hash = 0x98badcfe,
+	},
+	{
+		.name = "half_md4_31bytes",
+		.hash_version = DX_HASH_HALF_MD4,
+		.input = "1234567890123456789012345678901",
+		.len = 31,
+		.use_seed = false,
+		.expected_hash = 0xc4db1f78,
+		.expected_minor_hash = 0xea23921b,
+	},
+	{
+		.name = "half_md4_32bytes",
+		.hash_version = DX_HASH_HALF_MD4,
+		.input = "12345678901234567890123456789012",
+		.len = 32,
+		.use_seed = false,
+		.expected_hash = 0xfa6cc63e,
+		.expected_minor_hash = 0x2f77bd1c,
+	},
+	{
+		.name = "half_md4_33bytes",
+		.hash_version = DX_HASH_HALF_MD4,
+		.input = "123456789012345678901234567890123",
+		.len = 33,
+		.use_seed = false,
+		.expected_hash = 0xdc0c2dec,
+		.expected_minor_hash = 0x5ca23365,
+	},
+	{
+		.name = "half_md4_unsigned_31bytes",
+		.hash_version = DX_HASH_HALF_MD4_UNSIGNED,
+		.input = "1234567890123456789012345678901",
+		.len = 31,
+		.use_seed = false,
+		.expected_hash = 0xc4db1f78,
+		.expected_minor_hash = 0xea23921b,
+	},
+	{
+		.name = "half_md4_unsigned_32bytes",
+		.hash_version = DX_HASH_HALF_MD4_UNSIGNED,
+		.input = "12345678901234567890123456789012",
+		.len = 32,
+		.use_seed = false,
+		.expected_hash = 0xfa6cc63e,
+		.expected_minor_hash = 0x2f77bd1c,
+	},
+	{
+		.name = "half_md4_unsigned_33bytes",
+		.hash_version = DX_HASH_HALF_MD4_UNSIGNED,
+		.input = "123456789012345678901234567890123",
+		.len = 33,
+		.use_seed = false,
+		.expected_hash = 0xdc0c2dec,
+		.expected_minor_hash = 0x5ca23365,
+	},
+	{
+		.name = "tea_15bytes",
+		.hash_version = DX_HASH_TEA,
+		.input = "123456789abcdef",
+		.len = 15,
+		.use_seed = false,
+		.expected_hash = 0xa562903a,
+		.expected_minor_hash = 0x6174a00f,
+	},
+	{
+		.name = "tea_16bytes",
+		.hash_version = DX_HASH_TEA,
+		.input = "1234567890abcdef",
+		.len = 16,
+		.use_seed = false,
+		.expected_hash = 0x8449f258,
+		.expected_minor_hash = 0x49a16d46,
+	},
+	{
+		.name = "tea_17bytes",
+		.hash_version = DX_HASH_TEA,
+		.input = "123456789abcdefgh",
+		.len = 17,
+		.use_seed = false,
+		.expected_hash = 0xf32ec10c,
+		.expected_minor_hash = 0x58ceae61,
+	},
+	{
+		.name = "half_md4_seeded",
+		.hash_version = DX_HASH_HALF_MD4,
+		.input = "same-name",
+		.len = 9,
+		.seed = { 0x11111111, 0x22222222, 0x33333333, 0x44444444 },
+		.use_seed = true,
+		.expected_hash = 0x8aebf604,
+		.expected_minor_hash = 0x66ce48fe,
+	},
+	{
+		.name = "half_md4_non_ascii_signed",
+		.hash_version = DX_HASH_HALF_MD4,
+		.input = "\x80\x81\x82\x83\x84",
+		.len = 5,
+		.use_seed = false,
+		.expected_hash = 0x8bab0498,
+		.expected_minor_hash = 0xc326632d,
+	},
+	{
+		.name = "half_md4_non_ascii_unsigned",
+		.hash_version = DX_HASH_HALF_MD4_UNSIGNED,
+		.input = "\x80\x81\x82\x83\x84",
+		.len = 5,
+		.use_seed = false,
+		.expected_hash = 0xbc48596e,
+		.expected_minor_hash = 0xde0fad41,
+	},
+	{
+		.name = "tea_non_ascii_signed",
+		.hash_version = DX_HASH_TEA,
+		.input = "\x80\x81\x82\x83\x84",
+		.len = 5,
+		.use_seed = false,
+		.expected_hash = 0x21e3a154,
+		.expected_minor_hash = 0x90112c3d,
+	},
+	{
+		.name = "tea_non_ascii_unsigned",
+		.hash_version = DX_HASH_TEA_UNSIGNED,
+		.input = "\x80\x81\x82\x83\x84",
+		.len = 5,
+		.use_seed = false,
+		.expected_hash = 0x9b648616,
+		.expected_minor_hash = 0x011dd507,
+	},
+};
+
+static void test_ext4fs_dirhash_vectors(struct kunit *test)
+{
+	struct super_block *sb;
+	struct inode *dir;
+	int i;
+
+	sb = kunit_kzalloc(test, sizeof(*sb), GFP_KERNEL);
+	dir = kunit_kzalloc(test, sizeof(*dir), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_NULL(test, sb);
+	KUNIT_ASSERT_NOT_NULL(test, dir);
+
+	ext4_hash_init_fake_dir(dir, sb);
+
+	for (i = 0; i < ARRAY_SIZE(ext4_dirhash_test_cases); i++) {
+		const struct ext4_dirhash_test_case *tc =
+			&ext4_dirhash_test_cases[i];
+		struct dx_hash_info hinfo;
+		int ret;
+
+		memset(&hinfo, 0, sizeof(hinfo));
+		hinfo.hash_version = tc->hash_version;
+		hinfo.seed = tc->use_seed ? (u32 *)tc->seed : NULL;
+
+		ret = ext4fs_dirhash(dir, tc->input, tc->len, &hinfo);
+
+		KUNIT_ASSERT_EQ_MSG(test, ret, 0, "case=%s", tc->name);
+		KUNIT_EXPECT_EQ_MSG(test, hinfo.hash, tc->expected_hash,
+				    "case=%s", tc->name);
+		KUNIT_EXPECT_EQ_MSG(test, hinfo.minor_hash,
+				    tc->expected_minor_hash,
+				    "case=%s", tc->name);
+	}
+}
+
+static void test_ext4fs_dirhash_seed_changes_result(struct kunit *test)
+{
+	struct super_block *sb;
+	struct inode *dir;
+	u32 seed[4] = { 0x11111111, 0x22222222, 0x33333333, 0x44444444 };
+	struct dx_hash_info plain = {
+		.hash_version = DX_HASH_HALF_MD4,
+	};
+	struct dx_hash_info seeded = {
+		.hash_version = DX_HASH_HALF_MD4,
+		.seed = seed,
+	};
+	int ret_plain, ret_seeded;
+
+	sb = kunit_kzalloc(test, sizeof(*sb), GFP_KERNEL);
+	dir = kunit_kzalloc(test, sizeof(*dir), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_NULL(test, sb);
+	KUNIT_ASSERT_NOT_NULL(test, dir);
+
+	ext4_hash_init_fake_dir(dir, sb);
+
+	ret_plain = ext4fs_dirhash(dir, "same-name", 9, &plain);
+	ret_seeded = ext4fs_dirhash(dir, "same-name", 9, &seeded);
+
+	KUNIT_ASSERT_EQ(test, ret_plain, 0);
+	KUNIT_ASSERT_EQ(test, ret_seeded, 0);
+
+	KUNIT_EXPECT_TRUE(test,
+			  plain.hash != seeded.hash ||
+			  plain.minor_hash != seeded.minor_hash);
+}
+
+static void test_ext4fs_dirhash_invalid_version_returns_einval(struct kunit *test)
+{
+	struct super_block *sb;
+	struct inode *dir;
+	struct ext4_sb_info *sbi;
+	struct dx_hash_info hinfo = {
+		.hash = 0xdeadbeef,
+		.minor_hash = 0xcafebabe,
+		.hash_version = DX_HASH_LAST + 1,
+	};
+	int ret;
+
+	sb = kunit_kzalloc(test, sizeof(*sb), GFP_KERNEL);
+	dir = kunit_kzalloc(test, sizeof(*dir), GFP_KERNEL);
+	sbi = kunit_kzalloc(test, sizeof(*sbi), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_NULL(test, sb);
+	KUNIT_ASSERT_NOT_NULL(test, dir);
+	KUNIT_ASSERT_NOT_NULL(test, sbi);
+
+	ext4_hash_init_fake_dir_with_sbi(dir, sb, sbi);
+
+	ret = ext4fs_dirhash(dir, "abc", 3, &hinfo);
+
+	KUNIT_EXPECT_EQ(test, ret, -EINVAL);
+	KUNIT_EXPECT_EQ(test, hinfo.hash, 0);
+	KUNIT_EXPECT_EQ(test, hinfo.minor_hash, 0);
+}
+
+static void test_ext4fs_dirhash_siphash_without_key_returns_einval(struct kunit *test)
+{
+	struct super_block *sb;
+	struct ext4_inode_info *ei;
+	struct inode *dir;
+	struct ext4_sb_info *sbi;
+	struct dx_hash_info hinfo = {
+		.hash_version = DX_HASH_SIPHASH,
+	};
+	int ret;
+
+	sb = kunit_kzalloc(test, sizeof(*sb), GFP_KERNEL);
+	ei = kunit_kzalloc(test, sizeof(*ei), GFP_KERNEL);
+	sbi = kunit_kzalloc(test, sizeof(*sbi), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_NULL(test, sb);
+	KUNIT_ASSERT_NOT_NULL(test, ei);
+	KUNIT_ASSERT_NOT_NULL(test, sbi);
+
+	ext4_hash_init_fake_ext4_dir(ei, sb, sbi);
+	dir = &ei->vfs_inode;
+
+	ret = ext4fs_dirhash(dir, "name", strlen("name"), &hinfo);
+
+	KUNIT_EXPECT_EQ(test, ret, -EINVAL);
+}
+
+static void test_ext4fs_dirhash_signed_unsigned_differ_on_nonascii(struct kunit *test)
+{
+	struct super_block *sb;
+	struct inode *dir;
+	static const char input[] = "\x80\xff\x81\xfe\101bc";
+	struct dx_hash_info legacy_signed = {
+		.hash_version = DX_HASH_LEGACY,
+	};
+	struct dx_hash_info legacy_unsigned = {
+		.hash_version = DX_HASH_LEGACY_UNSIGNED,
+	};
+	struct dx_hash_info md4_signed = {
+		.hash_version = DX_HASH_HALF_MD4,
+	};
+	struct dx_hash_info md4_unsigned = {
+		.hash_version = DX_HASH_HALF_MD4_UNSIGNED,
+	};
+	struct dx_hash_info tea_signed = {
+		.hash_version = DX_HASH_TEA,
+	};
+	struct dx_hash_info tea_unsigned = {
+		.hash_version = DX_HASH_TEA_UNSIGNED,
+	};
+	int ret;
+
+	sb = kunit_kzalloc(test, sizeof(*sb), GFP_KERNEL);
+	dir = kunit_kzalloc(test, sizeof(*dir), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_NULL(test, sb);
+	KUNIT_ASSERT_NOT_NULL(test, dir);
+
+	ext4_hash_init_fake_dir(dir, sb);
+
+	ret = ext4fs_dirhash(dir, input, sizeof(input) - 1, &legacy_signed);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+	ret = ext4fs_dirhash(dir, input, sizeof(input) - 1, &legacy_unsigned);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+	KUNIT_EXPECT_NE(test, legacy_signed.hash, legacy_unsigned.hash);
+
+	ret = ext4fs_dirhash(dir, input, sizeof(input) - 1, &md4_signed);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+	ret = ext4fs_dirhash(dir, input, sizeof(input) - 1, &md4_unsigned);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+	KUNIT_EXPECT_TRUE(test,
+			  md4_signed.hash != md4_unsigned.hash ||
+			  md4_signed.minor_hash != md4_unsigned.minor_hash);
+
+	ret = ext4fs_dirhash(dir, input, sizeof(input) - 1, &tea_signed);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+	ret = ext4fs_dirhash(dir, input, sizeof(input) - 1, &tea_unsigned);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+	KUNIT_EXPECT_TRUE(test,
+			  tea_signed.hash != tea_unsigned.hash ||
+			  tea_signed.minor_hash != tea_unsigned.minor_hash);
+}
+
+#if IS_ENABLED(CONFIG_UNICODE)
+KUNIT_DEFINE_ACTION_WRAPPER(utf8_unload_action, utf8_unload,
+			    struct unicode_map *);
+static void test_ext4fs_dirhash_casefolded_names_hash_consistently(struct kunit *test)
+{
+	struct super_block *sb;
+	struct ext4_inode_info *ei;
+	struct ext4_sb_info *sbi;
+	struct unicode_map *um;
+	struct dx_hash_info h1 = {
+		.hash_version = DX_HASH_HALF_MD4,
+	};
+	struct dx_hash_info h2 = {
+		.hash_version = DX_HASH_HALF_MD4,
+	};
+	int ret, ret1, ret2;
+
+	sb = kunit_kzalloc(test, sizeof(*sb), GFP_KERNEL);
+	ei = kunit_kzalloc(test, sizeof(*ei), GFP_KERNEL);
+	sbi = kunit_kzalloc(test, sizeof(*sbi), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_NULL(test, sb);
+	KUNIT_ASSERT_NOT_NULL(test, ei);
+	KUNIT_ASSERT_NOT_NULL(test, sbi);
+
+	um = utf8_load(UTF8_LATEST);
+	if (IS_ERR(um)) {
+		kunit_skip(test, "utf8_load(UTF8_LATEST) failed: %pe",
+			   um);
+		return;
+	}
+
+	ret = kunit_add_action_or_reset(test, utf8_unload_action, um);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
+	ext4_hash_init_fake_ext4_dir(ei, sb, sbi);
+	sb->s_encoding = um;
+	ei->vfs_inode.i_flags |= S_CASEFOLD;
+
+	KUNIT_ASSERT_TRUE(test, IS_CASEFOLDED(&ei->vfs_inode));
+
+	ret1 = ext4fs_dirhash(&ei->vfs_inode, "Alpha", 5, &h1);
+	ret2 = ext4fs_dirhash(&ei->vfs_inode, "aLPHa", 5, &h2);
+
+	KUNIT_ASSERT_EQ(test, ret1, 0);
+	KUNIT_ASSERT_EQ(test, ret2, 0);
+	KUNIT_EXPECT_EQ(test, h1.hash, h2.hash);
+	KUNIT_EXPECT_EQ(test, h1.minor_hash, h2.minor_hash);
+}
+
+static void test_ext4fs_dirhash_casefold_fallback(struct kunit *test)
+{
+	struct super_block *sb_cf, *sb_plain;
+	struct ext4_inode_info *ei;
+	struct ext4_sb_info *sbi;
+	struct inode *plain_dir;
+	struct unicode_map *um;
+	static const char invalid_utf8[] = "\xc3\x28";
+	struct dx_hash_info folded_dir = {
+		.hash_version = DX_HASH_HALF_MD4,
+	};
+	struct dx_hash_info plain = {
+		.hash_version = DX_HASH_HALF_MD4,
+	};
+	int ret, ret_cf, ret_plain;
+
+	sb_cf = kunit_kzalloc(test, sizeof(*sb_cf), GFP_KERNEL);
+	sb_plain = kunit_kzalloc(test, sizeof(*sb_plain), GFP_KERNEL);
+	ei = kunit_kzalloc(test, sizeof(*ei), GFP_KERNEL);
+	sbi = kunit_kzalloc(test, sizeof(*sbi), GFP_KERNEL);
+	plain_dir = kunit_kzalloc(test, sizeof(*plain_dir), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_NULL(test, sb_cf);
+	KUNIT_ASSERT_NOT_NULL(test, sb_plain);
+	KUNIT_ASSERT_NOT_NULL(test, ei);
+	KUNIT_ASSERT_NOT_NULL(test, sbi);
+	KUNIT_ASSERT_NOT_NULL(test, plain_dir);
+
+	um = utf8_load(UTF8_LATEST);
+	if (IS_ERR(um)) {
+		kunit_skip(test, "utf8_load(UTF8_LATEST) failed: %pe",
+			   um);
+		return;
+	}
+
+	ret = kunit_add_action_or_reset(test, utf8_unload_action, um);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
+	ext4_hash_init_fake_ext4_dir(ei, sb_cf, sbi);
+	sb_cf->s_encoding = um;
+	ei->vfs_inode.i_flags |= S_CASEFOLD;
+
+	KUNIT_ASSERT_TRUE(test, IS_CASEFOLDED(&ei->vfs_inode));
+
+	ext4_hash_init_fake_dir(plain_dir, sb_plain);
+
+	ret_cf = ext4fs_dirhash(&ei->vfs_inode, invalid_utf8,
+				sizeof(invalid_utf8) - 1, &folded_dir);
+	ret_plain = ext4fs_dirhash(plain_dir, invalid_utf8,
+				   sizeof(invalid_utf8) - 1, &plain);
+
+	KUNIT_ASSERT_EQ(test, ret_cf, 0);
+	KUNIT_ASSERT_EQ(test, ret_plain, 0);
+	KUNIT_EXPECT_EQ(test, folded_dir.hash, plain.hash);
+	KUNIT_EXPECT_EQ(test, folded_dir.minor_hash, plain.minor_hash);
+}
+#endif
+
+static struct kunit_case ext4_hash_test_cases[] = {
+	KUNIT_CASE(test_ext4fs_dirhash_vectors),
+	KUNIT_CASE(test_ext4fs_dirhash_seed_changes_result),
+	KUNIT_CASE(test_ext4fs_dirhash_invalid_version_returns_einval),
+	KUNIT_CASE(test_ext4fs_dirhash_siphash_without_key_returns_einval),
+	KUNIT_CASE(test_ext4fs_dirhash_signed_unsigned_differ_on_nonascii),
+#if IS_ENABLED(CONFIG_UNICODE)
+	KUNIT_CASE(test_ext4fs_dirhash_casefolded_names_hash_consistently),
+	KUNIT_CASE(test_ext4fs_dirhash_casefold_fallback),
+#endif
+	{}
+};
+
+static struct kunit_suite ext4_hash_test_suite = {
+	.name = "ext4_hash",
+	.test_cases = ext4_hash_test_cases,
+};
+
+kunit_test_suites(&ext4_hash_test_suite);
+
+MODULE_LICENSE("GPL");

linux-7.2.3/fs/ext4/hash.c

@@ -0,0 +1,347 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/ext4/hash.c
+ *
+ * Copyright (C) 2002 by Theodore Ts'o
+ */
+
+#include <linux/fs.h>
+#include <linux/unicode.h>
+#include <linux/compiler.h>
+#include <linux/bitops.h>
+#include <linux/unaligned.h>
+#include "ext4.h"
+
+#define DELTA 0x9E3779B9
+
+static void TEA_transform(__u32 buf[4], __u32 const in[])
+{
+	__u32	sum = 0;
+	__u32	b0 = buf[0], b1 = buf[1];
+	__u32	a = in[0], b = in[1], c = in[2], d = in[3];
+	int	n = 16;
+
+	do {
+		sum += DELTA;
+		b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);
+		b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);
+	} while (--n);
+
+	buf[0] += b0;
+	buf[1] += b1;
+}
+
+/* F, G and H are basic MD4 functions: selection, majority, parity */
+#define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z))))
+#define G(x, y, z) (((x) & (y)) + (((x) ^ (y)) & (z)))
+#define H(x, y, z) ((x) ^ (y) ^ (z))
+
+/*
+ * The generic round function.  The application is so specific that
+ * we don't bother protecting all the arguments with parens, as is generally
+ * good macro practice, in favor of extra legibility.
+ * Rotation is separate from addition to prevent recomputation
+ */
+#define ROUND(f, a, b, c, d, x, s)	\
+	(a += f(b, c, d) + x, a = rol32(a, s))
+#define K1 0
+#define K2 013240474631UL
+#define K3 015666365641UL
+
+/*
+ * Basic cut-down MD4 transform.  Returns only 32 bits of result.
+ */
+static __u32 half_md4_transform(__u32 buf[4], __u32 const in[8])
+{
+	__u32 a = buf[0], b = buf[1], c = buf[2], d = buf[3];
+
+	/* Round 1 */
+	ROUND(F, a, b, c, d, in[0] + K1,  3);
+	ROUND(F, d, a, b, c, in[1] + K1,  7);
+	ROUND(F, c, d, a, b, in[2] + K1, 11);
+	ROUND(F, b, c, d, a, in[3] + K1, 19);
+	ROUND(F, a, b, c, d, in[4] + K1,  3);
+	ROUND(F, d, a, b, c, in[5] + K1,  7);
+	ROUND(F, c, d, a, b, in[6] + K1, 11);
+	ROUND(F, b, c, d, a, in[7] + K1, 19);
+
+	/* Round 2 */
+	ROUND(G, a, b, c, d, in[1] + K2,  3);
+	ROUND(G, d, a, b, c, in[3] + K2,  5);
+	ROUND(G, c, d, a, b, in[5] + K2,  9);
+	ROUND(G, b, c, d, a, in[7] + K2, 13);
+	ROUND(G, a, b, c, d, in[0] + K2,  3);
+	ROUND(G, d, a, b, c, in[2] + K2,  5);
+	ROUND(G, c, d, a, b, in[4] + K2,  9);
+	ROUND(G, b, c, d, a, in[6] + K2, 13);
+
+	/* Round 3 */
+	ROUND(H, a, b, c, d, in[3] + K3,  3);
+	ROUND(H, d, a, b, c, in[7] + K3,  9);
+	ROUND(H, c, d, a, b, in[2] + K3, 11);
+	ROUND(H, b, c, d, a, in[6] + K3, 15);
+	ROUND(H, a, b, c, d, in[1] + K3,  3);
+	ROUND(H, d, a, b, c, in[5] + K3,  9);
+	ROUND(H, c, d, a, b, in[0] + K3, 11);
+	ROUND(H, b, c, d, a, in[4] + K3, 15);
+
+	buf[0] += a;
+	buf[1] += b;
+	buf[2] += c;
+	buf[3] += d;
+
+	return buf[1]; /* "most hashed" word */
+}
+#undef ROUND
+#undef K1
+#undef K2
+#undef K3
+#undef F
+#undef G
+#undef H
+
+/* The old legacy hash */
+static __u32 dx_hack_hash_unsigned(const char *name, int len)
+{
+	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	const unsigned char *ucp = (const unsigned char *) name;
+
+	while (len--) {
+		hash = hash1 + (hash0 ^ (((int) *ucp++) * 7152373));
+
+		if (hash & 0x80000000)
+			hash -= 0x7fffffff;
+		hash1 = hash0;
+		hash0 = hash;
+	}
+	return hash0 << 1;
+}
+
+static __u32 dx_hack_hash_signed(const char *name, int len)
+{
+	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	const signed char *scp = (const signed char *) name;
+
+	while (len--) {
+		hash = hash1 + (hash0 ^ (((int) *scp++) * 7152373));
+
+		if (hash & 0x80000000)
+			hash -= 0x7fffffff;
+		hash1 = hash0;
+		hash0 = hash;
+	}
+	return hash0 << 1;
+}
+
+static void str2hashbuf_signed(const char *msg, int len, __u32 *buf, int num)
+{
+	__u32	pad, val;
+	int	i;
+	const signed char *scp = (const signed char *) msg;
+
+	pad = (__u32)len | ((__u32)len << 8);
+	pad |= pad << 16;
+
+	if (len > num*4)
+		len = num * 4;
+
+	while (len >= 4) {
+		val = ((__u32)scp[0] << 24) + ((__u32)scp[1] << 16) + ((__u32)scp[2] << 8) + scp[3];
+		*buf++ = val;
+		scp += 4;
+		len -= 4;
+		num--;
+	}
+
+	val = pad;
+
+	for (i = 0; i < len; i++)
+		val = scp[i] + (val << 8);
+
+	if (--num >= 0)
+		*buf++ = val;
+
+	while (--num >= 0)
+		*buf++ = pad;
+
+}
+
+static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num)
+{
+	__u32	pad, val;
+	int	i;
+	const unsigned char *ucp = (const unsigned char *) msg;
+
+	pad = (__u32)len | ((__u32)len << 8);
+	pad |= pad << 16;
+
+	if (len > num*4)
+		len = num * 4;
+
+	while (len >= 4) {
+		val = get_unaligned_be32(ucp);
+		*buf++ = val;
+		ucp += 4;
+		len -= 4;
+		num--;
+	}
+
+	val = pad;
+
+	for (i = 0; i < len; i++)
+		val = ucp[i] + (val << 8);
+
+	if (--num >= 0)
+		*buf++ = val;
+
+	while (--num >= 0)
+		*buf++ = pad;
+
+}
+
+/*
+ * Returns the hash of a filename.  If len is 0 and name is NULL, then
+ * this function can be used to test whether or not a hash version is
+ * supported.
+ *
+ * The seed is an 4 longword (32 bits) "secret" which can be used to
+ * uniquify a hash.  If the seed is all zero's, then some default seed
+ * may be used.
+ *
+ * A particular hash version specifies whether or not the seed is
+ * represented, and whether or not the returned hash is 32 bits or 64
+ * bits.  32 bit hashes will return 0 for the minor hash.
+ */
+static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len,
+			    struct dx_hash_info *hinfo)
+{
+	__u32	hash;
+	__u32	minor_hash = 0;
+	const char	*p;
+	int		i;
+	__u32		in[8], buf[4];
+	bool use_unsigned = false;
+
+	/* Initialize the default seed for the hash checksum functions */
+	buf[0] = 0x67452301;
+	buf[1] = 0xefcdab89;
+	buf[2] = 0x98badcfe;
+	buf[3] = 0x10325476;
+
+	/* Check to see if the seed is all zero's */
+	if (hinfo->seed) {
+		for (i = 0; i < 4; i++) {
+			if (hinfo->seed[i]) {
+				memcpy(buf, hinfo->seed, sizeof(buf));
+				break;
+			}
+		}
+	}
+
+	switch (hinfo->hash_version) {
+	case DX_HASH_LEGACY_UNSIGNED:
+		hash = dx_hack_hash_unsigned(name, len);
+		break;
+	case DX_HASH_LEGACY:
+		hash = dx_hack_hash_signed(name, len);
+		break;
+	case DX_HASH_HALF_MD4_UNSIGNED:
+		use_unsigned = true;
+		fallthrough;
+	case DX_HASH_HALF_MD4:
+		p = name;
+		while (len > 0) {
+			if (use_unsigned)
+				str2hashbuf_unsigned(p, len, in, 8);
+			else
+				str2hashbuf_signed(p, len, in, 8);
+			half_md4_transform(buf, in);
+			len -= 32;
+			p += 32;
+		}
+		minor_hash = buf[2];
+		hash = buf[1];
+		break;
+	case DX_HASH_TEA_UNSIGNED:
+		use_unsigned = true;
+		fallthrough;
+	case DX_HASH_TEA:
+		p = name;
+		while (len > 0) {
+			if (use_unsigned)
+				str2hashbuf_unsigned(p, len, in, 4);
+			else
+				str2hashbuf_signed(p, len, in, 4);
+			TEA_transform(buf, in);
+			len -= 16;
+			p += 16;
+		}
+		hash = buf[0];
+		minor_hash = buf[1];
+		break;
+	case DX_HASH_SIPHASH:
+	{
+		struct qstr qname = QSTR_INIT(name, len);
+		__u64	combined_hash;
+
+		if (fscrypt_has_encryption_key(dir)) {
+			combined_hash = fscrypt_fname_siphash(dir, &qname);
+		} else {
+			ext4_warning_inode(dir, "Siphash requires key");
+			return -EINVAL;
+		}
+
+		hash = (__u32)(combined_hash >> 32);
+		minor_hash = (__u32)combined_hash;
+		break;
+	}
+	default:
+		hinfo->hash = 0;
+		hinfo->minor_hash = 0;
+		ext4_warning(dir->i_sb,
+			     "invalid/unsupported hash tree version %u",
+			     hinfo->hash_version);
+		return -EINVAL;
+	}
+	hash = hash & ~1;
+	if (hash == (EXT4_HTREE_EOF_32BIT << 1))
+		hash = (EXT4_HTREE_EOF_32BIT - 1) << 1;
+	hinfo->hash = hash;
+	hinfo->minor_hash = minor_hash;
+	return 0;
+}
+
+int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
+		   struct dx_hash_info *hinfo)
+{
+#if IS_ENABLED(CONFIG_UNICODE)
+	const struct unicode_map *um = dir->i_sb->s_encoding;
+	int r, dlen;
+	unsigned char *buff;
+	struct qstr qstr = {.name = name, .len = len };
+
+	if (len && IS_CASEFOLDED(dir) &&
+	   (!IS_ENCRYPTED(dir) || fscrypt_has_encryption_key(dir))) {
+		buff = kzalloc(PATH_MAX, GFP_KERNEL);
+		if (!buff)
+			return -ENOMEM;
+
+		dlen = utf8_casefold(um, &qstr, buff, PATH_MAX);
+		if (dlen < 0) {
+			kfree(buff);
+			goto opaque_seq;
+		}
+
+		r = __ext4fs_dirhash(dir, buff, dlen, hinfo);
+
+		kfree(buff);
+		return r;
+	}
+opaque_seq:
+#endif
+	return __ext4fs_dirhash(dir, name, len, hinfo);
+}
+
+#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS)
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4fs_dirhash);
+#endif

linux-7.2.3/fs/ext4/inode-test.c

@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnit test of ext4 inode that verify the seconds part of [a/c/m]
+ * timestamps in ext4 inode structs are decoded correctly.
+ */
+
+#include <kunit/test.h>
+#include <linux/kernel.h>
+#include <linux/time64.h>
+
+#include "ext4.h"
+
+/*
+ * For constructing the nonnegative timestamp lower bound value.
+ * binary: 00000000 00000000 00000000 00000000
+ */
+#define LOWER_MSB_0 0L
+/*
+ * For constructing the nonnegative timestamp upper bound value.
+ * binary: 01111111 11111111 11111111 11111111
+ *
+ */
+#define UPPER_MSB_0 0x7fffffffL
+/*
+ * For constructing the negative timestamp lower bound value.
+ * binary: 10000000 00000000 00000000 00000000
+ */
+#define LOWER_MSB_1 (-(UPPER_MSB_0) - 1L)  /* avoid overflow */
+/*
+ * For constructing the negative timestamp upper bound value.
+ * binary: 11111111 11111111 11111111 11111111
+ */
+#define UPPER_MSB_1 (-1L)
+/*
+ * Upper bound for nanoseconds value supported by the encoding.
+ * binary: 00111111 11111111 11111111 11111111
+ */
+#define MAX_NANOSECONDS ((1L << 30) - 1)
+
+#define CASE_NAME_FORMAT "%s: msb:%x lower_bound:%x extra_bits: %x"
+
+#define LOWER_BOUND_NEG_NO_EXTRA_BITS_CASE\
+	"1901-12-13 Lower bound of 32bit < 0 timestamp, no extra bits"
+#define UPPER_BOUND_NEG_NO_EXTRA_BITS_CASE\
+	"1969-12-31 Upper bound of 32bit < 0 timestamp, no extra bits"
+#define LOWER_BOUND_NONNEG_NO_EXTRA_BITS_CASE\
+	"1970-01-01 Lower bound of 32bit >=0 timestamp, no extra bits"
+#define UPPER_BOUND_NONNEG_NO_EXTRA_BITS_CASE\
+	"2038-01-19 Upper bound of 32bit >=0 timestamp, no extra bits"
+#define LOWER_BOUND_NEG_LO_1_CASE\
+	"2038-01-19 Lower bound of 32bit <0 timestamp, lo extra sec bit on"
+#define UPPER_BOUND_NEG_LO_1_CASE\
+	"2106-02-07 Upper bound of 32bit <0 timestamp, lo extra sec bit on"
+#define LOWER_BOUND_NONNEG_LO_1_CASE\
+	"2106-02-07 Lower bound of 32bit >=0 timestamp, lo extra sec bit on"
+#define UPPER_BOUND_NONNEG_LO_1_CASE\
+	"2174-02-25 Upper bound of 32bit >=0 timestamp, lo extra sec bit on"
+#define LOWER_BOUND_NEG_HI_1_CASE\
+	"2174-02-25 Lower bound of 32bit <0 timestamp, hi extra sec bit on"
+#define UPPER_BOUND_NEG_HI_1_CASE\
+	"2242-03-16 Upper bound of 32bit <0 timestamp, hi extra sec bit on"
+#define LOWER_BOUND_NONNEG_HI_1_CASE\
+	"2242-03-16 Lower bound of 32bit >=0 timestamp, hi extra sec bit on"
+#define UPPER_BOUND_NONNEG_HI_1_CASE\
+	"2310-04-04 Upper bound of 32bit >=0 timestamp, hi extra sec bit on"
+#define UPPER_BOUND_NONNEG_HI_1_NS_1_CASE\
+	"2310-04-04 Upper bound of 32bit>=0 timestamp, hi extra sec bit 1. 1 ns"
+#define LOWER_BOUND_NONNEG_HI_1_NS_MAX_CASE\
+	"2378-04-22 Lower bound of 32bit>= timestamp. Extra sec bits 1. Max ns"
+#define LOWER_BOUND_NONNEG_EXTRA_BITS_1_CASE\
+	"2378-04-22 Lower bound of 32bit >=0 timestamp. All extra sec bits on"
+#define UPPER_BOUND_NONNEG_EXTRA_BITS_1_CASE\
+	"2446-05-10 Upper bound of 32bit >=0 timestamp. All extra sec bits on"
+
+struct timestamp_expectation {
+	const char *test_case_name;
+	struct timespec64 expected;
+	u32 extra_bits;
+	bool msb_set;
+	bool lower_bound;
+};
+
+static const struct timestamp_expectation test_data[] = {
+	{
+		.test_case_name = LOWER_BOUND_NEG_NO_EXTRA_BITS_CASE,
+		.msb_set = true,
+		.lower_bound = true,
+		.extra_bits = 0,
+		.expected = {.tv_sec = -0x80000000LL, .tv_nsec = 0L},
+	},
+
+	{
+		.test_case_name = UPPER_BOUND_NEG_NO_EXTRA_BITS_CASE,
+		.msb_set = true,
+		.lower_bound = false,
+		.extra_bits = 0,
+		.expected = {.tv_sec = -1LL, .tv_nsec = 0L},
+	},
+
+	{
+		.test_case_name = LOWER_BOUND_NONNEG_NO_EXTRA_BITS_CASE,
+		.msb_set = false,
+		.lower_bound = true,
+		.extra_bits = 0,
+		.expected = {0LL, 0L},
+	},
+
+	{
+		.test_case_name = UPPER_BOUND_NONNEG_NO_EXTRA_BITS_CASE,
+		.msb_set = false,
+		.lower_bound = false,
+		.extra_bits = 0,
+		.expected = {.tv_sec = 0x7fffffffLL, .tv_nsec = 0L},
+	},
+
+	{
+		.test_case_name = LOWER_BOUND_NEG_LO_1_CASE,
+		.msb_set = true,
+		.lower_bound = true,
+		.extra_bits = 1,
+		.expected = {.tv_sec = 0x80000000LL, .tv_nsec = 0L},
+	},
+
+	{
+		.test_case_name = UPPER_BOUND_NEG_LO_1_CASE,
+		.msb_set = true,
+		.lower_bound = false,
+		.extra_bits = 1,
+		.expected = {.tv_sec = 0xffffffffLL, .tv_nsec = 0L},
+	},
+
+	{
+		.test_case_name = LOWER_BOUND_NONNEG_LO_1_CASE,
+		.msb_set = false,
+		.lower_bound = true,
+		.extra_bits = 1,
+		.expected = {.tv_sec = 0x100000000LL, .tv_nsec = 0L},
+	},
+
+	{
+		.test_case_name = UPPER_BOUND_NONNEG_LO_1_CASE,
+		.msb_set = false,
+		.lower_bound = false,
+		.extra_bits = 1,
+		.expected = {.tv_sec = 0x17fffffffLL, .tv_nsec = 0L},
+	},
+
+	{
+		.test_case_name = LOWER_BOUND_NEG_HI_1_CASE,
+		.msb_set = true,
+		.lower_bound = true,
+		.extra_bits =  2,
+		.expected = {.tv_sec = 0x180000000LL, .tv_nsec = 0L},
+	},
+
+	{
+		.test_case_name = UPPER_BOUND_NEG_HI_1_CASE,
+		.msb_set = true,
+		.lower_bound = false,
+		.extra_bits = 2,
+		.expected = {.tv_sec = 0x1ffffffffLL, .tv_nsec = 0L},
+	},
+
+	{
+		.test_case_name = LOWER_BOUND_NONNEG_HI_1_CASE,
+		.msb_set = false,
+		.lower_bound = true,
+		.extra_bits = 2,
+		.expected = {.tv_sec = 0x200000000LL, .tv_nsec = 0L},
+	},
+
+	{
+		.test_case_name = UPPER_BOUND_NONNEG_HI_1_CASE,
+		.msb_set = false,
+		.lower_bound = false,
+		.extra_bits = 2,
+		.expected = {.tv_sec = 0x27fffffffLL, .tv_nsec = 0L},
+	},
+
+	{
+		.test_case_name = UPPER_BOUND_NONNEG_HI_1_NS_1_CASE,
+		.msb_set = false,
+		.lower_bound = false,
+		.extra_bits = 6,
+		.expected = {.tv_sec = 0x27fffffffLL, .tv_nsec = 1L},
+	},
+
+	{
+		.test_case_name = LOWER_BOUND_NONNEG_HI_1_NS_MAX_CASE,
+		.msb_set = false,
+		.lower_bound = true,
+		.extra_bits = 0xFFFFFFFF,
+		.expected = {.tv_sec = 0x300000000LL,
+			     .tv_nsec = MAX_NANOSECONDS},
+	},
+
+	{
+		.test_case_name = LOWER_BOUND_NONNEG_EXTRA_BITS_1_CASE,
+		.msb_set = false,
+		.lower_bound = true,
+		.extra_bits = 3,
+		.expected = {.tv_sec = 0x300000000LL, .tv_nsec = 0L},
+	},
+
+	{
+		.test_case_name = UPPER_BOUND_NONNEG_EXTRA_BITS_1_CASE,
+		.msb_set = false,
+		.lower_bound = false,
+		.extra_bits = 3,
+		.expected = {.tv_sec = 0x37fffffffLL, .tv_nsec = 0L},
+	}
+};
+
+static void timestamp_expectation_to_desc(const struct timestamp_expectation *t,
+					  char *desc)
+{
+	strscpy(desc, t->test_case_name, KUNIT_PARAM_DESC_SIZE);
+}
+
+KUNIT_ARRAY_PARAM(ext4_inode, test_data, timestamp_expectation_to_desc);
+
+static time64_t get_32bit_time(const struct timestamp_expectation * const test)
+{
+	if (test->msb_set) {
+		if (test->lower_bound)
+			return LOWER_MSB_1;
+
+		return UPPER_MSB_1;
+	}
+
+	if (test->lower_bound)
+		return LOWER_MSB_0;
+	return UPPER_MSB_0;
+}
+
+
+/*
+ *  Test data is derived from the table in the Inode Timestamps section of
+ *  Documentation/filesystems/ext4/inodes.rst.
+ */
+static void inode_test_xtimestamp_decoding(struct kunit *test)
+{
+	struct timespec64 timestamp;
+
+	struct timestamp_expectation *test_param =
+			(struct timestamp_expectation *)(test->param_value);
+
+	timestamp = ext4_decode_extra_time(
+				cpu_to_le32(get_32bit_time(test_param)),
+				cpu_to_le32(test_param->extra_bits));
+
+	KUNIT_EXPECT_EQ_MSG(test,
+			    test_param->expected.tv_sec,
+			    timestamp.tv_sec,
+			    CASE_NAME_FORMAT,
+			    test_param->test_case_name,
+			    test_param->msb_set,
+			    test_param->lower_bound,
+			    test_param->extra_bits);
+	KUNIT_EXPECT_EQ_MSG(test,
+			    test_param->expected.tv_nsec,
+			    timestamp.tv_nsec,
+			    CASE_NAME_FORMAT,
+			    test_param->test_case_name,
+			    test_param->msb_set,
+			    test_param->lower_bound,
+			    test_param->extra_bits);
+}
+
+static struct kunit_case ext4_inode_test_cases[] = {
+	KUNIT_CASE_PARAM(inode_test_xtimestamp_decoding, ext4_inode_gen_params),
+	{}
+};
+
+static struct kunit_suite ext4_inode_test_suite = {
+	.name = "ext4_inode_test",
+	.test_cases = ext4_inode_test_cases,
+};
+
+kunit_test_suites(&ext4_inode_test_suite);
+
+MODULE_DESCRIPTION("KUnit test of ext4 inode timestamp decoding");
+MODULE_LICENSE("GPL v2");

linux-7.2.3/fs/ext4/mballoc.h

@@ -0,0 +1,303 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  fs/ext4/mballoc.h
+ *
+ *  Written by: Alex Tomas <alex@clusterfs.com>
+ *
+ */
+#ifndef _EXT4_MBALLOC_H
+#define _EXT4_MBALLOC_H
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/proc_fs.h>
+#include <linux/pagemap.h>
+#include <linux/seq_file.h>
+#include <linux/blkdev.h>
+#include <linux/mutex.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"
+
+/*
+ * mb_debug() dynamic printk msgs could be used to debug mballoc code.
+ */
+#ifdef CONFIG_EXT4_DEBUG
+#define mb_debug(sb, fmt, ...)						\
+	pr_debug("[%s/%d] EXT4-fs (%s): (%s, %d): %s: " fmt,		\
+		current->comm, task_pid_nr(current), sb->s_id,		\
+	       __FILE__, __LINE__, __func__, ##__VA_ARGS__)
+#else
+#define mb_debug(sb, fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
+#endif
+
+#define EXT4_MB_HISTORY_ALLOC		1	/* allocation */
+#define EXT4_MB_HISTORY_PREALLOC	2	/* preallocated blocks used */
+
+/*
+ * How long mballoc can look for a best extent (in found extents)
+ */
+#define MB_DEFAULT_MAX_TO_SCAN		200
+
+/*
+ * How long mballoc must look for a best extent
+ */
+#define MB_DEFAULT_MIN_TO_SCAN		10
+
+/*
+ * with 's_mb_stats' allocator will collect stats that will be
+ * shown at umount. The collecting costs though!
+ */
+#define MB_DEFAULT_STATS		0
+
+/*
+ * files smaller than MB_DEFAULT_STREAM_THRESHOLD are served
+ * by the stream allocator, which purpose is to pack requests
+ * as close each to other as possible to produce smooth I/O traffic
+ * We use locality group prealloc space for stream request.
+ * We can tune the same via /proc/fs/ext4/<partition>/stream_req
+ */
+#define MB_DEFAULT_STREAM_THRESHOLD	16	/* 64K */
+
+/*
+ * for which requests use 2^N search using buddies
+ */
+#define MB_DEFAULT_ORDER2_REQS		2
+
+/*
+ * default group prealloc size 512 blocks
+ */
+#define MB_DEFAULT_GROUP_PREALLOC	512
+
+/*
+ * Number of groups to search linearly before performing group scanning
+ * optimization.
+ */
+#define MB_DEFAULT_LINEAR_LIMIT		4
+
+/*
+ * Minimum number of groups that should be present in the file system to perform
+ * group scanning optimizations.
+ */
+#define MB_DEFAULT_LINEAR_SCAN_THRESHOLD	16
+
+/*
+ * The maximum order upto which CR_BEST_AVAIL_LEN can trim a particular
+ * allocation request. Example, if we have an order 7 request and max trim order
+ * of 3, we can trim this request upto order 4.
+ */
+#define MB_DEFAULT_BEST_AVAIL_TRIM_ORDER	3
+
+/*
+ * Number of valid buddy orders
+ */
+#define MB_NUM_ORDERS(sb)		((sb)->s_blocksize_bits + 2)
+
+struct ext4_free_data {
+	/* this links the free block information from sb_info */
+	struct list_head		efd_list;
+
+	/* this links the free block information from group_info */
+	struct rb_node			efd_node;
+
+	/* group which free block extent belongs */
+	ext4_group_t			efd_group;
+
+	/* free block extent */
+	ext4_grpblk_t			efd_start_cluster;
+	ext4_grpblk_t			efd_count;
+
+	/* transaction which freed this extent */
+	tid_t				efd_tid;
+};
+
+struct ext4_prealloc_space {
+	union {
+		struct rb_node	inode_node;		/* for inode PA rbtree */
+		struct list_head	lg_list;	/* for lg PAs */
+	} pa_node;
+	struct list_head	pa_group_list;
+	union {
+		struct list_head pa_tmp_list;
+		struct rcu_head	pa_rcu;
+	} u;
+	spinlock_t		pa_lock;
+	atomic_t		pa_count;
+	unsigned		pa_deleted;
+	ext4_fsblk_t		pa_pstart;	/* phys. block */
+	ext4_lblk_t		pa_lstart;	/* log. block */
+	ext4_grpblk_t		pa_len;		/* len of preallocated chunk */
+	ext4_grpblk_t		pa_free;	/* how many blocks are free */
+	unsigned short		pa_type;	/* pa type. inode or group */
+	union {
+		rwlock_t		*inode_lock;	/* locks the rbtree holding this PA */
+		spinlock_t		*lg_lock;	/* locks the lg list holding this PA */
+	} pa_node_lock;
+	struct inode		*pa_inode;	/* used to get the inode during group discard */
+};
+
+enum {
+	MB_INODE_PA = 0,
+	MB_GROUP_PA = 1
+};
+
+struct ext4_free_extent {
+	ext4_lblk_t fe_logical;
+	ext4_grpblk_t fe_start;	/* In cluster units */
+	ext4_group_t fe_group;
+	ext4_grpblk_t fe_len;	/* In cluster units */
+};
+
+/*
+ * Locality group:
+ *   we try to group all related changes together
+ *   so that writeback can flush/allocate them together as well
+ *   Size of lg_prealloc_list hash is determined by MB_DEFAULT_GROUP_PREALLOC
+ *   (512). We store prealloc space into the hash based on the pa_free blocks
+ *   order value.ie, fls(pa_free)-1;
+ */
+#define PREALLOC_TB_SIZE 10
+struct ext4_locality_group {
+	/* for allocator */
+	/* to serialize allocates */
+	struct mutex		lg_mutex;
+	/* list of preallocations */
+	struct list_head	lg_prealloc_list[PREALLOC_TB_SIZE];
+	spinlock_t		lg_prealloc_lock;
+};
+
+struct ext4_allocation_context {
+	struct inode *ac_inode;
+	struct super_block *ac_sb;
+
+	/* original request */
+	struct ext4_free_extent ac_o_ex;
+
+	/* goal request (normalized ac_o_ex) */
+	struct ext4_free_extent ac_g_ex;
+
+	/* the best found extent */
+	struct ext4_free_extent ac_b_ex;
+
+	/* copy of the best found extent taken before preallocation efforts */
+	struct ext4_free_extent ac_f_ex;
+
+	/*
+	 * goal len can change in CR_BEST_AVAIL_LEN, so save the original len.
+	 * This is used while adjusting the PA window and for accounting.
+	 */
+	ext4_grpblk_t	ac_orig_goal_len;
+
+	ext4_group_t ac_prefetch_grp;
+	unsigned int ac_prefetch_ios;
+	unsigned int ac_prefetch_nr;
+
+	int ac_first_err;
+
+	__u32 ac_flags;		/* allocation hints */
+	__u16 ac_groups_scanned;
+	__u16 ac_found;
+	__u16 ac_cX_found[EXT4_MB_NUM_CRS];
+	__u16 ac_tail;
+	__u16 ac_buddy;
+	__u8 ac_status;
+	__u8 ac_criteria;
+	__u8 ac_2order;		/* if request is to allocate 2^N blocks and
+				 * N > 0, the field stores N, otherwise 0 */
+	__u8 ac_op;		/* operation, for history only */
+
+	struct ext4_buddy *ac_e4b;
+	struct folio *ac_bitmap_folio;
+	struct folio *ac_buddy_folio;
+	struct ext4_prealloc_space *ac_pa;
+	struct ext4_locality_group *ac_lg;
+};
+
+#define AC_STATUS_CONTINUE	1
+#define AC_STATUS_FOUND		2
+#define AC_STATUS_BREAK		3
+
+struct ext4_buddy {
+	struct folio *bd_buddy_folio;
+	void *bd_buddy;
+	struct folio *bd_bitmap_folio;
+	void *bd_bitmap;
+	struct ext4_group_info *bd_info;
+	struct super_block *bd_sb;
+	__u16 bd_blkbits;
+	ext4_group_t bd_group;
+};
+
+static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
+					struct ext4_free_extent *fex)
+{
+	return ext4_group_first_block_no(sb, fex->fe_group) +
+		(fex->fe_start << EXT4_SB(sb)->s_cluster_bits);
+}
+
+static inline loff_t extent_logical_end(struct ext4_sb_info *sbi,
+					struct ext4_free_extent *fex)
+{
+	/* Use loff_t to avoid end exceeding ext4_lblk_t max. */
+	return (loff_t)fex->fe_logical + EXT4_C2B(sbi, fex->fe_len);
+}
+
+static inline loff_t pa_logical_end(struct ext4_sb_info *sbi,
+				    struct ext4_prealloc_space *pa)
+{
+	/* Use loff_t to avoid end exceeding ext4_lblk_t max. */
+	return (loff_t)pa->pa_lstart + EXT4_C2B(sbi, pa->pa_len);
+}
+
+typedef int (*ext4_mballoc_query_range_fn)(
+	struct super_block		*sb,
+	ext4_group_t			agno,
+	ext4_grpblk_t			start,
+	ext4_grpblk_t			len,
+	void				*priv);
+
+int
+ext4_mballoc_query_range(
+	struct super_block		*sb,
+	ext4_group_t			agno,
+	ext4_grpblk_t			start,
+	ext4_grpblk_t			end,
+	ext4_mballoc_query_range_fn	meta_formatter,
+	ext4_mballoc_query_range_fn	formatter,
+	void				*priv);
+
+extern int ext4_mb_mark_context(handle_t *handle,
+		struct super_block *sb, bool state,
+		ext4_group_t group, ext4_grpblk_t blkoff,
+		ext4_grpblk_t len, int flags,
+		ext4_grpblk_t *ret_changed);
+#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS)
+extern void mb_clear_bits_test(void *bm, int cur, int len);
+extern ext4_fsblk_t
+ext4_mb_new_blocks_simple_test(struct ext4_allocation_request *ar,
+			       int *errp);
+extern int mb_find_next_zero_bit_test(void *addr, int max, int start);
+extern int mb_find_next_bit_test(void *addr, int max, int start);
+extern void mb_clear_bit_test(int bit, void *addr);
+extern int mb_test_bit_test(int bit, void *addr);
+extern int
+ext4_mb_mark_diskspace_used_test(struct ext4_allocation_context *ac,
+				 handle_t *handle);
+extern int mb_mark_used_test(struct ext4_buddy *e4b,
+			     struct ext4_free_extent *ex);
+extern void ext4_mb_generate_buddy_test(struct super_block *sb,
+		void *buddy, void *bitmap, ext4_group_t group,
+		struct ext4_group_info *grp);
+extern int ext4_mb_load_buddy_test(struct super_block *sb,
+		ext4_group_t group, struct ext4_buddy *e4b);
+extern void ext4_mb_unload_buddy_test(struct ext4_buddy *e4b);
+extern void mb_free_blocks_test(struct inode *inode,
+		struct ext4_buddy *e4b, int first, int count);
+extern void ext4_free_blocks_simple_test(struct inode *inode,
+		ext4_fsblk_t block, unsigned long count);
+#endif
+#endif

linux-7.2.3/fs/ext4/migrate.c

@@ -0,0 +1,684 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright IBM Corporation, 2007
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ */
+
+#include <linux/slab.h>
+#include "ext4_jbd2.h"
+#include "ext4_extents.h"
+
+/*
+ * The contiguous blocks details which can be
+ * represented by a single extent
+ */
+struct migrate_struct {
+	ext4_lblk_t first_block, last_block, curr_block;
+	ext4_fsblk_t first_pblock, last_pblock;
+};
+
+static int finish_range(handle_t *handle, struct inode *inode,
+				struct migrate_struct *lb)
+
+{
+	int retval = 0, needed;
+	struct ext4_extent newext;
+	struct ext4_ext_path *path;
+	if (lb->first_pblock == 0)
+		return 0;
+
+	/* Add the extent to temp inode*/
+	newext.ee_block = cpu_to_le32(lb->first_block);
+	newext.ee_len   = cpu_to_le16(lb->last_block - lb->first_block + 1);
+	ext4_ext_store_pblock(&newext, lb->first_pblock);
+	/* Locking only for convenience since we are operating on temp inode */
+	down_write(&EXT4_I(inode)->i_data_sem);
+	path = ext4_find_extent(inode, lb->first_block, NULL, 0);
+	if (IS_ERR(path)) {
+		retval = PTR_ERR(path);
+		goto err_out;
+	}
+
+	/*
+	 * Calculate the credit needed to inserting this extent
+	 * Since we are doing this in loop we may accumulate extra
+	 * credit. But below we try to not accumulate too much
+	 * of them by restarting the journal.
+	 */
+	needed = ext4_ext_calc_credits_for_single_extent(inode,
+		    lb->last_block - lb->first_block + 1, path);
+
+	retval = ext4_datasem_ensure_credits(handle, inode, needed, needed, 0);
+	if (retval < 0)
+		goto err_out;
+	path = ext4_ext_insert_extent(handle, inode, path, &newext, 0);
+	if (IS_ERR(path))
+		retval = PTR_ERR(path);
+err_out:
+	up_write((&EXT4_I(inode)->i_data_sem));
+	ext4_free_ext_path(path);
+	lb->first_pblock = 0;
+	return retval;
+}
+
+static int update_extent_range(handle_t *handle, struct inode *inode,
+			       ext4_fsblk_t pblock, struct migrate_struct *lb)
+{
+	int retval;
+	/*
+	 * See if we can add on to the existing range (if it exists)
+	 */
+	if (lb->first_pblock &&
+		(lb->last_pblock+1 == pblock) &&
+		(lb->last_block+1 == lb->curr_block)) {
+		lb->last_pblock = pblock;
+		lb->last_block = lb->curr_block;
+		lb->curr_block++;
+		return 0;
+	}
+	/*
+	 * Start a new range.
+	 */
+	retval = finish_range(handle, inode, lb);
+	lb->first_pblock = lb->last_pblock = pblock;
+	lb->first_block = lb->last_block = lb->curr_block;
+	lb->curr_block++;
+	return retval;
+}
+
+static int update_ind_extent_range(handle_t *handle, struct inode *inode,
+				   ext4_fsblk_t pblock,
+				   struct migrate_struct *lb)
+{
+	struct buffer_head *bh;
+	__le32 *i_data;
+	int i, retval = 0;
+	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+
+	bh = ext4_sb_bread(inode->i_sb, pblock, 0);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
+
+	i_data = (__le32 *)bh->b_data;
+	for (i = 0; i < max_entries; i++) {
+		if (i_data[i]) {
+			retval = update_extent_range(handle, inode,
+						le32_to_cpu(i_data[i]), lb);
+			if (retval)
+				break;
+		} else {
+			lb->curr_block++;
+		}
+	}
+	put_bh(bh);
+	return retval;
+
+}
+
+static int update_dind_extent_range(handle_t *handle, struct inode *inode,
+				    ext4_fsblk_t pblock,
+				    struct migrate_struct *lb)
+{
+	struct buffer_head *bh;
+	__le32 *i_data;
+	int i, retval = 0;
+	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+
+	bh = ext4_sb_bread(inode->i_sb, pblock, 0);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
+
+	i_data = (__le32 *)bh->b_data;
+	for (i = 0; i < max_entries; i++) {
+		if (i_data[i]) {
+			retval = update_ind_extent_range(handle, inode,
+						le32_to_cpu(i_data[i]), lb);
+			if (retval)
+				break;
+		} else {
+			/* Only update the file block number */
+			lb->curr_block += max_entries;
+		}
+	}
+	put_bh(bh);
+	return retval;
+
+}
+
+static int update_tind_extent_range(handle_t *handle, struct inode *inode,
+				    ext4_fsblk_t pblock,
+				    struct migrate_struct *lb)
+{
+	struct buffer_head *bh;
+	__le32 *i_data;
+	int i, retval = 0;
+	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+
+	bh = ext4_sb_bread(inode->i_sb, pblock, 0);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
+
+	i_data = (__le32 *)bh->b_data;
+	for (i = 0; i < max_entries; i++) {
+		if (i_data[i]) {
+			retval = update_dind_extent_range(handle, inode,
+						le32_to_cpu(i_data[i]), lb);
+			if (retval)
+				break;
+		} else {
+			/* Only update the file block number */
+			lb->curr_block += max_entries * max_entries;
+		}
+	}
+	put_bh(bh);
+	return retval;
+
+}
+
+static int free_dind_blocks(handle_t *handle,
+				struct inode *inode, __le32 i_data)
+{
+	int i;
+	__le32 *tmp_idata;
+	struct buffer_head *bh;
+	struct super_block *sb = inode->i_sb;
+	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+	int err;
+
+	bh = ext4_sb_bread(sb, le32_to_cpu(i_data), 0);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
+
+	tmp_idata = (__le32 *)bh->b_data;
+	for (i = 0; i < max_entries; i++) {
+		if (tmp_idata[i]) {
+			err = ext4_journal_ensure_credits(handle,
+				EXT4_RESERVE_TRANS_BLOCKS,
+				ext4_free_metadata_revoke_credits(sb, 1));
+			if (err < 0) {
+				put_bh(bh);
+				return err;
+			}
+			ext4_free_blocks(handle, inode, NULL,
+					 le32_to_cpu(tmp_idata[i]), 1,
+					 EXT4_FREE_BLOCKS_METADATA |
+					 EXT4_FREE_BLOCKS_FORGET);
+		}
+	}
+	put_bh(bh);
+	err = ext4_journal_ensure_credits(handle, EXT4_RESERVE_TRANS_BLOCKS,
+				ext4_free_metadata_revoke_credits(sb, 1));
+	if (err < 0)
+		return err;
+	ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1,
+			 EXT4_FREE_BLOCKS_METADATA |
+			 EXT4_FREE_BLOCKS_FORGET);
+	return 0;
+}
+
+static int free_tind_blocks(handle_t *handle,
+				struct inode *inode, __le32 i_data)
+{
+	int i, retval = 0;
+	__le32 *tmp_idata;
+	struct buffer_head *bh;
+	unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
+
+	bh = ext4_sb_bread(inode->i_sb, le32_to_cpu(i_data), 0);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
+
+	tmp_idata = (__le32 *)bh->b_data;
+	for (i = 0; i < max_entries; i++) {
+		if (tmp_idata[i]) {
+			retval = free_dind_blocks(handle,
+					inode, tmp_idata[i]);
+			if (retval) {
+				put_bh(bh);
+				return retval;
+			}
+		}
+	}
+	put_bh(bh);
+	retval = ext4_journal_ensure_credits(handle, EXT4_RESERVE_TRANS_BLOCKS,
+			ext4_free_metadata_revoke_credits(inode->i_sb, 1));
+	if (retval < 0)
+		return retval;
+	ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1,
+			 EXT4_FREE_BLOCKS_METADATA |
+			 EXT4_FREE_BLOCKS_FORGET);
+	return 0;
+}
+
+static int free_ind_block(handle_t *handle, struct inode *inode, __le32 *i_data)
+{
+	int retval;
+
+	/* ei->i_data[EXT4_IND_BLOCK] */
+	if (i_data[0]) {
+		retval = ext4_journal_ensure_credits(handle,
+			EXT4_RESERVE_TRANS_BLOCKS,
+			ext4_free_metadata_revoke_credits(inode->i_sb, 1));
+		if (retval < 0)
+			return retval;
+		ext4_free_blocks(handle, inode, NULL,
+				le32_to_cpu(i_data[0]), 1,
+				 EXT4_FREE_BLOCKS_METADATA |
+				 EXT4_FREE_BLOCKS_FORGET);
+	}
+
+	/* ei->i_data[EXT4_DIND_BLOCK] */
+	if (i_data[1]) {
+		retval = free_dind_blocks(handle, inode, i_data[1]);
+		if (retval)
+			return retval;
+	}
+
+	/* ei->i_data[EXT4_TIND_BLOCK] */
+	if (i_data[2]) {
+		retval = free_tind_blocks(handle, inode, i_data[2]);
+		if (retval)
+			return retval;
+	}
+	return 0;
+}
+
+static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
+						struct inode *tmp_inode)
+{
+	int retval, retval2 = 0;
+	__le32	i_data[3];
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_inode_info *tmp_ei = EXT4_I(tmp_inode);
+
+	/*
+	 * One credit accounted for writing the
+	 * i_data field of the original inode
+	 */
+	retval = ext4_journal_ensure_credits(handle, 1, 0);
+	if (retval < 0)
+		goto err_out;
+
+	i_data[0] = ei->i_data[EXT4_IND_BLOCK];
+	i_data[1] = ei->i_data[EXT4_DIND_BLOCK];
+	i_data[2] = ei->i_data[EXT4_TIND_BLOCK];
+
+	down_write(&EXT4_I(inode)->i_data_sem);
+	/*
+	 * if EXT4_STATE_EXT_MIGRATE is cleared a block allocation
+	 * happened after we started the migrate. We need to
+	 * fail the migrate
+	 */
+	if (!ext4_test_inode_state(inode, EXT4_STATE_EXT_MIGRATE)) {
+		retval = -EAGAIN;
+		up_write(&EXT4_I(inode)->i_data_sem);
+		goto err_out;
+	} else
+		ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
+	/*
+	 * We have the extent map build with the tmp inode.
+	 * Now copy the i_data across
+	 */
+	ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS);
+	memcpy(ei->i_data, tmp_ei->i_data, sizeof(ei->i_data));
+
+	/*
+	 * Update i_blocks with the new blocks that got
+	 * allocated while adding extents for extent index
+	 * blocks.
+	 *
+	 * While converting to extents we need not
+	 * update the original inode i_blocks for extent blocks
+	 * via quota APIs. The quota update happened via tmp_inode already.
+	 */
+	spin_lock(&inode->i_lock);
+	inode->i_blocks += tmp_inode->i_blocks;
+	spin_unlock(&inode->i_lock);
+	up_write(&EXT4_I(inode)->i_data_sem);
+
+	/*
+	 * We mark the inode dirty after, because we decrement the
+	 * i_blocks when freeing the indirect meta-data blocks
+	 */
+	retval = free_ind_block(handle, inode, i_data);
+	retval2 = ext4_mark_inode_dirty(handle, inode);
+	if (unlikely(retval2 && !retval))
+		retval = retval2;
+
+err_out:
+	return retval;
+}
+
+static int free_ext_idx(handle_t *handle, struct inode *inode,
+					struct ext4_extent_idx *ix)
+{
+	int i, retval = 0;
+	ext4_fsblk_t block;
+	struct buffer_head *bh;
+	struct ext4_extent_header *eh;
+
+	block = ext4_idx_pblock(ix);
+	bh = ext4_sb_bread(inode->i_sb, block, 0);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
+
+	eh = (struct ext4_extent_header *)bh->b_data;
+	if (eh->eh_depth != 0) {
+		ix = EXT_FIRST_INDEX(eh);
+		for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ix++) {
+			retval = free_ext_idx(handle, inode, ix);
+			if (retval) {
+				put_bh(bh);
+				return retval;
+			}
+		}
+	}
+	put_bh(bh);
+	retval = ext4_journal_ensure_credits(handle, EXT4_RESERVE_TRANS_BLOCKS,
+			ext4_free_metadata_revoke_credits(inode->i_sb, 1));
+	if (retval < 0)
+		return retval;
+	ext4_free_blocks(handle, inode, NULL, block, 1,
+			 EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
+	return 0;
+}
+
+/*
+ * Free the extent meta data blocks only
+ */
+static int free_ext_block(handle_t *handle, struct inode *inode)
+{
+	int i, retval = 0;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_extent_header *eh = (struct ext4_extent_header *)ei->i_data;
+	struct ext4_extent_idx *ix;
+	if (eh->eh_depth == 0)
+		/*
+		 * No extra blocks allocated for extent meta data
+		 */
+		return 0;
+	ix = EXT_FIRST_INDEX(eh);
+	for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ix++) {
+		retval = free_ext_idx(handle, inode, ix);
+		if (retval)
+			return retval;
+	}
+	return retval;
+}
+
+int ext4_ext_migrate(struct inode *inode)
+{
+	handle_t *handle;
+	int retval = 0, i;
+	__le32 *i_data;
+	struct ext4_inode_info *ei;
+	struct inode *tmp_inode = NULL;
+	struct migrate_struct lb;
+	unsigned long max_entries;
+	__u32 goal, tmp_csum_seed;
+	uid_t owner[2];
+	int alloc_ctx;
+
+	/*
+	 * If the filesystem does not support extents, or the inode
+	 * already is extent-based, error out.
+	 */
+	if (!ext4_has_feature_extents(inode->i_sb) ||
+	    ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) ||
+	    ext4_has_inline_data(inode))
+		return -EINVAL;
+
+	if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0)
+		/*
+		 * don't migrate fast symlink
+		 */
+		return retval;
+
+	alloc_ctx = ext4_writepages_down_write(inode->i_sb);
+
+	/*
+	 * Worst case we can touch the allocation bitmaps and a block
+	 * group descriptor block.  We do need to worry about
+	 * credits for modifying the quota inode.
+	 */
+	handle = ext4_journal_start(inode, EXT4_HT_MIGRATE,
+		3 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb));
+
+	if (IS_ERR(handle)) {
+		retval = PTR_ERR(handle);
+		goto out_unlock;
+	}
+	/*
+	 * This operation rewrites the inode's block mapping layout
+	 * (indirect to extents) and is not tracked in the fast commit
+	 * log, so disable fast commits for this transaction.
+	 */
+	ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_MIGRATE, handle);
+	goal = ((((u32)inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
+		EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;
+	owner[0] = i_uid_read(inode);
+	owner[1] = i_gid_read(inode);
+	tmp_inode = ext4_new_inode(handle, d_inode(inode->i_sb->s_root),
+				   S_IFREG, NULL, goal, owner, 0);
+	if (IS_ERR(tmp_inode)) {
+		retval = PTR_ERR(tmp_inode);
+		ext4_journal_stop(handle);
+		goto out_unlock;
+	}
+	/*
+	 * Use the correct seed for checksum (i.e. the seed from 'inode').  This
+	 * is so that the metadata blocks will have the correct checksum after
+	 * the migration.
+	 */
+	ei = EXT4_I(inode);
+	tmp_csum_seed = EXT4_I(tmp_inode)->i_csum_seed;
+	EXT4_I(tmp_inode)->i_csum_seed = ei->i_csum_seed;
+	i_size_write(tmp_inode, i_size_read(inode));
+	/*
+	 * Set the i_nlink to zero so it will be deleted later
+	 * when we drop inode reference.
+	 */
+	clear_nlink(tmp_inode);
+
+	ext4_ext_tree_init(handle, tmp_inode);
+	ext4_journal_stop(handle);
+
+	/*
+	 * start with one credit accounted for
+	 * superblock modification.
+	 *
+	 * For the tmp_inode we already have committed the
+	 * transaction that created the inode. Later as and
+	 * when we add extents we extent the journal
+	 */
+	/*
+	 * Even though we take i_rwsem we can still cause block
+	 * allocation via mmap write to holes. If we have allocated
+	 * new blocks we fail migrate.  New block allocation will
+	 * clear EXT4_STATE_EXT_MIGRATE flag.  The flag is updated
+	 * with i_data_sem held to prevent racing with block
+	 * allocation.
+	 */
+	down_read(&EXT4_I(inode)->i_data_sem);
+	ext4_set_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
+	up_read((&EXT4_I(inode)->i_data_sem));
+
+	handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
+	if (IS_ERR(handle)) {
+		retval = PTR_ERR(handle);
+		goto out_tmp_inode;
+	}
+
+	i_data = ei->i_data;
+	memset(&lb, 0, sizeof(lb));
+
+	/* 32 bit block address 4 bytes */
+	max_entries = inode->i_sb->s_blocksize >> 2;
+	for (i = 0; i < EXT4_NDIR_BLOCKS; i++) {
+		if (i_data[i]) {
+			retval = update_extent_range(handle, tmp_inode,
+						le32_to_cpu(i_data[i]), &lb);
+			if (retval)
+				goto err_out;
+		} else
+			lb.curr_block++;
+	}
+	if (i_data[EXT4_IND_BLOCK]) {
+		retval = update_ind_extent_range(handle, tmp_inode,
+				le32_to_cpu(i_data[EXT4_IND_BLOCK]), &lb);
+		if (retval)
+			goto err_out;
+	} else
+		lb.curr_block += max_entries;
+	if (i_data[EXT4_DIND_BLOCK]) {
+		retval = update_dind_extent_range(handle, tmp_inode,
+				le32_to_cpu(i_data[EXT4_DIND_BLOCK]), &lb);
+		if (retval)
+			goto err_out;
+	} else
+		lb.curr_block += max_entries * max_entries;
+	if (i_data[EXT4_TIND_BLOCK]) {
+		retval = update_tind_extent_range(handle, tmp_inode,
+				le32_to_cpu(i_data[EXT4_TIND_BLOCK]), &lb);
+		if (retval)
+			goto err_out;
+	}
+	/*
+	 * Build the last extent
+	 */
+	retval = finish_range(handle, tmp_inode, &lb);
+err_out:
+	if (retval)
+		/*
+		 * Failure case delete the extent information with the
+		 * tmp_inode
+		 */
+		free_ext_block(handle, tmp_inode);
+	else {
+		retval = ext4_ext_swap_inode_data(handle, inode, tmp_inode);
+		if (retval)
+			/*
+			 * if we fail to swap inode data free the extent
+			 * details of the tmp inode
+			 */
+			free_ext_block(handle, tmp_inode);
+	}
+
+	/* We mark the tmp_inode dirty via ext4_ext_tree_init. */
+	retval = ext4_journal_ensure_credits(handle, 1, 0);
+	if (retval < 0)
+		goto out_stop;
+	/*
+	 * Mark the tmp_inode as of size zero
+	 */
+	i_size_write(tmp_inode, 0);
+
+	/*
+	 * set the  i_blocks count to zero
+	 * so that the ext4_evict_inode() does the
+	 * right job
+	 *
+	 * We don't need to take the i_lock because
+	 * the inode is not visible to user space.
+	 */
+	tmp_inode->i_blocks = 0;
+	EXT4_I(tmp_inode)->i_csum_seed = tmp_csum_seed;
+
+	/* Reset the extent details */
+	ext4_ext_tree_init(handle, tmp_inode);
+out_stop:
+	ext4_journal_stop(handle);
+out_tmp_inode:
+	unlock_new_inode(tmp_inode);
+	iput(tmp_inode);
+out_unlock:
+	ext4_writepages_up_write(inode->i_sb, alloc_ctx);
+	return retval;
+}
+
+/*
+ * Migrate a simple extent-based inode to use the i_blocks[] array
+ */
+int ext4_ind_migrate(struct inode *inode)
+{
+	struct ext4_extent_header	*eh;
+	struct ext4_sb_info		*sbi = EXT4_SB(inode->i_sb);
+	struct ext4_super_block		*es = sbi->s_es;
+	struct ext4_inode_info		*ei = EXT4_I(inode);
+	struct ext4_extent		*ex;
+	unsigned int			i, len;
+	ext4_lblk_t			start, end;
+	ext4_fsblk_t			blk;
+	handle_t			*handle;
+	int				ret, ret2 = 0;
+	int				alloc_ctx;
+
+	if (!ext4_has_feature_extents(inode->i_sb) ||
+	    (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+		return -EINVAL;
+
+	if (ext4_has_feature_bigalloc(inode->i_sb))
+		return -EOPNOTSUPP;
+
+	/*
+	 * In order to get correct extent info, force all delayed allocation
+	 * blocks to be allocated, otherwise delayed allocation blocks may not
+	 * be reflected and bypass the checks on extent header.
+	 */
+	if (test_opt(inode->i_sb, DELALLOC))
+		ext4_alloc_da_blocks(inode);
+
+	alloc_ctx = ext4_writepages_down_write(inode->i_sb);
+
+	handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out_unlock;
+	}
+	/*
+	 * This operation rewrites the inode's block mapping layout
+	 * (extents to indirect blocks) and is not tracked in the fast
+	 * commit log, so disable fast commits for this transaction.
+	 */
+	ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_MIGRATE, handle);
+
+	down_write(&EXT4_I(inode)->i_data_sem);
+	ret = ext4_ext_check_inode(inode);
+	if (ret)
+		goto errout;
+
+	eh = ext_inode_hdr(inode);
+	ex  = EXT_FIRST_EXTENT(eh);
+	if (ext4_blocks_count(es) > EXT4_MAX_BLOCK_FILE_PHYS ||
+	    eh->eh_depth != 0 || le16_to_cpu(eh->eh_entries) > 1) {
+		ret = -EOPNOTSUPP;
+		goto errout;
+	}
+	if (eh->eh_entries == 0)
+		blk = len = start = end = 0;
+	else {
+		len = le16_to_cpu(ex->ee_len);
+		blk = ext4_ext_pblock(ex);
+		start = le32_to_cpu(ex->ee_block);
+		end = start + len - 1;
+		if (end >= EXT4_NDIR_BLOCKS) {
+			ret = -EOPNOTSUPP;
+			goto errout;
+		}
+	}
+
+	ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
+	memset(ei->i_data, 0, sizeof(ei->i_data));
+	for (i = start; i <= end; i++)
+		ei->i_data[i] = cpu_to_le32(blk++);
+	ret2 = ext4_mark_inode_dirty(handle, inode);
+	if (unlikely(ret2 && !ret))
+		ret = ret2;
+errout:
+	up_write(&EXT4_I(inode)->i_data_sem);
+	ext4_journal_stop(handle);
+out_unlock:
+	ext4_writepages_up_write(inode->i_sb, alloc_ctx);
+	return ret;
+}

linux-7.2.3/fs/ext4/mmp.c

@@ -0,0 +1,403 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fs.h>
+#include <linux/random.h>
+#include <linux/buffer_head.h>
+#include <linux/utsname.h>
+#include <linux/kthread.h>
+
+#include "ext4.h"
+
+/* Checksumming functions */
+static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int offset = offsetof(struct mmp_struct, mmp_checksum);
+	__u32 csum;
+
+	csum = ext4_chksum(sbi->s_csum_seed, (char *)mmp, offset);
+
+	return cpu_to_le32(csum);
+}
+
+static int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
+{
+	if (!ext4_has_feature_metadata_csum(sb))
+		return 1;
+
+	return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp);
+}
+
+static void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
+{
+	if (!ext4_has_feature_metadata_csum(sb))
+		return;
+
+	mmp->mmp_checksum = ext4_mmp_csum(sb, mmp);
+}
+
+/*
+ * Write the MMP block using REQ_SYNC to try to get the block on-disk
+ * faster.
+ */
+static int write_mmp_block_thawed(struct super_block *sb,
+				  struct buffer_head *bh)
+{
+	struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data);
+
+	ext4_mmp_csum_set(sb, mmp);
+	lock_buffer(bh);
+	bh_submit(bh, REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO,
+			bh_end_write);
+	wait_on_buffer(bh);
+	if (unlikely(!buffer_uptodate(bh)))
+		return -EIO;
+	return 0;
+}
+
+static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
+{
+	/*
+	 * We protect against freezing so that we don't create dirty buffers
+	 * on frozen filesystem.
+	 */
+	scoped_guard(super_write, sb)
+		return write_mmp_block_thawed(sb, bh);
+}
+
+/*
+ * Read the MMP block. It _must_ be read from disk and hence we clear the
+ * uptodate flag on the buffer.
+ */
+static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
+			  ext4_fsblk_t mmp_block)
+{
+	struct mmp_struct *mmp;
+	int ret;
+
+	if (*bh)
+		clear_buffer_uptodate(*bh);
+
+	/* This would be sb_bread(sb, mmp_block), except we need to be sure
+	 * that the MD RAID device cache has been bypassed, and that the read
+	 * is not blocked in the elevator. */
+	if (!*bh) {
+		*bh = sb_getblk(sb, mmp_block);
+		if (!*bh) {
+			ret = -ENOMEM;
+			goto warn_exit;
+		}
+	}
+
+	lock_buffer(*bh);
+	ret = ext4_read_bh(*bh, REQ_META | REQ_PRIO, NULL, false);
+	if (ret)
+		goto warn_exit;
+
+	mmp = (struct mmp_struct *)((*bh)->b_data);
+	if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC) {
+		ret = -EFSCORRUPTED;
+		goto warn_exit;
+	}
+	if (!ext4_mmp_csum_verify(sb, mmp)) {
+		ret = -EFSBADCRC;
+		goto warn_exit;
+	}
+	return 0;
+warn_exit:
+	brelse(*bh);
+	*bh = NULL;
+	ext4_warning(sb, "Error %d while reading MMP block %llu",
+		     ret, mmp_block);
+	return ret;
+}
+
+/*
+ * Dump as much information as possible to help the admin.
+ */
+void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp,
+		    const char *function, unsigned int line, const char *msg)
+{
+	__ext4_warning(sb, function, line, "%s", msg);
+	__ext4_warning(sb, function, line,
+		       "MMP failure info: last update time: %llu, last update node: %.*s, last update device: %.*s",
+		       (unsigned long long)le64_to_cpu(mmp->mmp_time),
+		       (int)sizeof(mmp->mmp_nodename), mmp->mmp_nodename,
+		       (int)sizeof(mmp->mmp_bdevname), mmp->mmp_bdevname);
+}
+
+/*
+ * kmmpd will update the MMP sequence every s_mmp_update_interval seconds
+ */
+static int kmmpd(void *data)
+{
+	struct super_block *sb = data;
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	struct buffer_head *bh = EXT4_SB(sb)->s_mmp_bh;
+	struct mmp_struct *mmp;
+	ext4_fsblk_t mmp_block;
+	u32 seq = 0;
+	unsigned long failed_writes = 0;
+	int mmp_update_interval = le16_to_cpu(es->s_mmp_update_interval);
+	unsigned mmp_check_interval;
+	unsigned long last_update_time;
+	unsigned long diff;
+	int retval = 0;
+
+	mmp_block = le64_to_cpu(es->s_mmp_block);
+	mmp = (struct mmp_struct *)(bh->b_data);
+	mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
+	/*
+	 * Start with the higher mmp_check_interval and reduce it if
+	 * the MMP block is being updated on time.
+	 */
+	mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval,
+				 EXT4_MMP_MIN_CHECK_INTERVAL);
+	mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
+
+	memcpy(mmp->mmp_nodename, init_utsname()->nodename,
+	       sizeof(mmp->mmp_nodename));
+
+	while (!kthread_should_stop() && !ext4_emergency_state(sb)) {
+		if (!ext4_has_feature_mmp(sb)) {
+			ext4_warning(sb, "kmmpd being stopped since MMP feature"
+				     " has been disabled.");
+			goto wait_to_exit;
+		}
+		if (++seq > EXT4_MMP_SEQ_MAX)
+			seq = 1;
+
+		mmp->mmp_seq = cpu_to_le32(seq);
+		mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
+		last_update_time = jiffies;
+
+		retval = write_mmp_block(sb, bh);
+		/*
+		 * Don't spew too many error messages. Print one every
+		 * (s_mmp_update_interval * 60) seconds.
+		 */
+		if (retval) {
+			if ((failed_writes % 60) == 0) {
+				ext4_error_err(sb, -retval,
+					       "Error writing to MMP block");
+			}
+			failed_writes++;
+		}
+
+		diff = jiffies - last_update_time;
+		if (diff < mmp_update_interval * HZ)
+			schedule_timeout_interruptible(mmp_update_interval *
+						       HZ - diff);
+
+		/*
+		 * We need to make sure that more than mmp_check_interval
+		 * seconds have not passed since writing. If that has happened
+		 * we need to check if the MMP block is as we left it.
+		 */
+		diff = jiffies - last_update_time;
+		if (diff > mmp_check_interval * HZ) {
+			struct buffer_head *bh_check = NULL;
+			struct mmp_struct *mmp_check;
+
+			retval = read_mmp_block(sb, &bh_check, mmp_block);
+			if (retval) {
+				ext4_error_err(sb, -retval,
+					       "error reading MMP data: %d",
+					       retval);
+				goto wait_to_exit;
+			}
+
+			mmp_check = (struct mmp_struct *)(bh_check->b_data);
+			if (mmp->mmp_seq != mmp_check->mmp_seq ||
+			    memcmp(mmp->mmp_nodename, mmp_check->mmp_nodename,
+				   sizeof(mmp->mmp_nodename))) {
+				dump_mmp_msg(sb, mmp_check,
+					     "Error while updating MMP info. "
+					     "The filesystem seems to have been"
+					     " multiply mounted.");
+				ext4_error_err(sb, EBUSY, "abort");
+				put_bh(bh_check);
+				retval = -EBUSY;
+				goto wait_to_exit;
+			}
+			put_bh(bh_check);
+		}
+
+		 /*
+		 * Adjust the mmp_check_interval depending on how much time
+		 * it took for the MMP block to be written.
+		 */
+		mmp_check_interval = clamp(EXT4_MMP_CHECK_MULT * diff / HZ,
+					   EXT4_MMP_MIN_CHECK_INTERVAL,
+					   EXT4_MMP_MAX_CHECK_INTERVAL);
+		mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
+	}
+
+	/*
+	 * Unmount seems to be clean.
+	 */
+	mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN);
+	mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
+
+	retval = write_mmp_block(sb, bh);
+
+wait_to_exit:
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (!kthread_should_stop())
+			schedule();
+	}
+	set_current_state(TASK_RUNNING);
+	return retval;
+}
+
+void ext4_stop_mmpd(struct ext4_sb_info *sbi)
+{
+	if (sbi->s_mmp_tsk) {
+		kthread_stop(sbi->s_mmp_tsk);
+		brelse(sbi->s_mmp_bh);
+		sbi->s_mmp_tsk = NULL;
+	}
+}
+
+/*
+ * Get a random new sequence number but make sure it is not greater than
+ * EXT4_MMP_SEQ_MAX.
+ */
+static unsigned int mmp_new_seq(void)
+{
+	return get_random_u32_below(EXT4_MMP_SEQ_MAX + 1);
+}
+
+/*
+ * Protect the filesystem from being mounted more than once.
+ */
+int ext4_multi_mount_protect(struct super_block *sb,
+				    ext4_fsblk_t mmp_block)
+{
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	struct buffer_head *bh = NULL;
+	struct mmp_struct *mmp = NULL;
+	u32 seq;
+	unsigned int mmp_check_interval = le16_to_cpu(es->s_mmp_update_interval);
+	unsigned int wait_time = 0;
+	int retval;
+
+	if (mmp_block < le32_to_cpu(es->s_first_data_block) ||
+	    mmp_block >= ext4_blocks_count(es)) {
+		ext4_warning(sb, "Invalid MMP block in superblock");
+		retval = -EINVAL;
+		goto failed;
+	}
+
+	retval = read_mmp_block(sb, &bh, mmp_block);
+	if (retval)
+		goto failed;
+
+	mmp = (struct mmp_struct *)(bh->b_data);
+
+	if (mmp_check_interval < EXT4_MMP_MIN_CHECK_INTERVAL)
+		mmp_check_interval = EXT4_MMP_MIN_CHECK_INTERVAL;
+
+	/*
+	 * If check_interval in MMP block is larger, use that instead of
+	 * update_interval from the superblock.
+	 */
+	if (le16_to_cpu(mmp->mmp_check_interval) > mmp_check_interval)
+		mmp_check_interval = le16_to_cpu(mmp->mmp_check_interval);
+
+	seq = le32_to_cpu(mmp->mmp_seq);
+	if (seq == EXT4_MMP_SEQ_CLEAN)
+		goto skip;
+
+	if (seq == EXT4_MMP_SEQ_FSCK) {
+		dump_mmp_msg(sb, mmp, "fsck is running on the filesystem");
+		retval = -EBUSY;
+		goto failed;
+	}
+
+	wait_time = min(mmp_check_interval * 2 + 1,
+			mmp_check_interval + 60);
+
+	/* Print MMP interval if more than 20 secs. */
+	if (wait_time > EXT4_MMP_MIN_CHECK_INTERVAL * 4)
+		ext4_warning(sb, "MMP interval %u higher than expected, please"
+			     " wait.\n", wait_time * 2);
+
+	if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
+		ext4_warning(sb, "MMP startup interrupted, failing mount\n");
+		retval = -ETIMEDOUT;
+		goto failed;
+	}
+
+	retval = read_mmp_block(sb, &bh, mmp_block);
+	if (retval)
+		goto failed;
+	mmp = (struct mmp_struct *)(bh->b_data);
+	if (seq != le32_to_cpu(mmp->mmp_seq)) {
+		dump_mmp_msg(sb, mmp,
+			     "Device is already active on another node.");
+		retval = -EBUSY;
+		goto failed;
+	}
+
+skip:
+	/*
+	 * write a new random sequence number.
+	 */
+	seq = mmp_new_seq();
+	mmp->mmp_seq = cpu_to_le32(seq);
+
+	/*
+	 * On mount / remount we are protected against fs freezing (by s_umount
+	 * semaphore) and grabbing freeze protection upsets lockdep
+	 */
+	retval = write_mmp_block_thawed(sb, bh);
+	if (retval)
+		goto failed;
+
+	/*
+	 * wait for MMP interval and check mmp_seq.
+	 */
+	if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
+		ext4_warning(sb, "MMP startup interrupted, failing mount");
+		retval = -ETIMEDOUT;
+		goto failed;
+	}
+
+	retval = read_mmp_block(sb, &bh, mmp_block);
+	if (retval)
+		goto failed;
+	mmp = (struct mmp_struct *)(bh->b_data);
+	if (seq != le32_to_cpu(mmp->mmp_seq)) {
+		dump_mmp_msg(sb, mmp,
+			     "Device is already active on another node.");
+		retval = -EBUSY;
+		goto failed;
+	}
+
+	EXT4_SB(sb)->s_mmp_bh = bh;
+
+	BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE);
+	snprintf(mmp->mmp_bdevname, sizeof(mmp->mmp_bdevname),
+		 "%pg", bh->b_bdev);
+
+	/*
+	 * Start a kernel thread to update the MMP block periodically.
+	 */
+	EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, sb, "kmmpd-%.*s",
+					     (int)sizeof(mmp->mmp_bdevname),
+					     mmp->mmp_bdevname);
+	if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) {
+		EXT4_SB(sb)->s_mmp_tsk = NULL;
+		ext4_warning(sb, "Unable to create kmmpd thread for %s.",
+			     sb->s_id);
+		retval = -ENOMEM;
+		goto failed;
+	}
+
+	return 0;
+
+failed:
+	brelse(bh);
+	return retval;
+}

linux-7.2.3/fs/ext4/move_extent.c

@@ -0,0 +1,658 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright (c) 2008,2009 NEC Software Tohoku, Ltd.
+ * Written by Takashi Sato <t-sato@yk.jp.nec.com>
+ *            Akira Fujita <a-fujita@rs.jp.nec.com>
+ */
+
+#include <linux/fs.h>
+#include <linux/quotaops.h>
+#include <linux/slab.h>
+#include <linux/sched/mm.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"
+#include "ext4_extents.h"
+
+#include <trace/events/ext4.h>
+
+struct mext_data {
+	struct inode *orig_inode;	/* Origin file inode */
+	struct inode *donor_inode;	/* Donor file inode */
+	struct ext4_map_blocks orig_map;/* Origin file's move mapping */
+	ext4_lblk_t donor_lblk;		/* Start block of the donor file */
+};
+
+/**
+ * ext4_double_down_write_data_sem() - write lock two inodes's i_data_sem
+ * @first: inode to be locked
+ * @second: inode to be locked
+ *
+ * Acquire write lock of i_data_sem of the two inodes
+ */
+void
+ext4_double_down_write_data_sem(struct inode *first, struct inode *second)
+{
+	if (first < second) {
+		down_write(&EXT4_I(first)->i_data_sem);
+		down_write_nested(&EXT4_I(second)->i_data_sem, I_DATA_SEM_OTHER);
+	} else {
+		down_write(&EXT4_I(second)->i_data_sem);
+		down_write_nested(&EXT4_I(first)->i_data_sem, I_DATA_SEM_OTHER);
+	}
+}
+
+/**
+ * ext4_double_up_write_data_sem - Release two inodes' write lock of i_data_sem
+ *
+ * @orig_inode:		original inode structure to be released its lock first
+ * @donor_inode:	donor inode structure to be released its lock second
+ * Release write lock of i_data_sem of two inodes (orig and donor).
+ */
+void
+ext4_double_up_write_data_sem(struct inode *orig_inode,
+			      struct inode *donor_inode)
+{
+	up_write(&EXT4_I(orig_inode)->i_data_sem);
+	up_write(&EXT4_I(donor_inode)->i_data_sem);
+}
+
+/* Grab and lock folio on both @inode1 and @inode2 by inode order. */
+static int mext_folio_double_lock(struct inode *inode1, struct inode *inode2,
+				  pgoff_t index1, pgoff_t index2, size_t len,
+				  struct folio *folio[2])
+{
+	struct address_space *mapping[2];
+	unsigned int flags;
+	fgf_t fgp_flags = FGP_WRITEBEGIN;
+
+	BUG_ON(!inode1 || !inode2);
+	if (inode1 < inode2) {
+		mapping[0] = inode1->i_mapping;
+		mapping[1] = inode2->i_mapping;
+	} else {
+		swap(index1, index2);
+		mapping[0] = inode2->i_mapping;
+		mapping[1] = inode1->i_mapping;
+	}
+
+	flags = memalloc_nofs_save();
+	fgp_flags |= fgf_set_order(len);
+	folio[0] = __filemap_get_folio(mapping[0], index1, fgp_flags,
+			mapping_gfp_mask(mapping[0]));
+	if (IS_ERR(folio[0])) {
+		memalloc_nofs_restore(flags);
+		return PTR_ERR(folio[0]);
+	}
+
+	folio[1] = __filemap_get_folio(mapping[1], index2, fgp_flags,
+			mapping_gfp_mask(mapping[1]));
+	memalloc_nofs_restore(flags);
+	if (IS_ERR(folio[1])) {
+		folio_unlock(folio[0]);
+		folio_put(folio[0]);
+		return PTR_ERR(folio[1]);
+	}
+	/*
+	 * __filemap_get_folio() may not wait on folio's writeback if
+	 * BDI not demand that. But it is reasonable to be very conservative
+	 * here and explicitly wait on folio's writeback
+	 */
+	folio_wait_writeback(folio[0]);
+	folio_wait_writeback(folio[1]);
+	if (inode1 > inode2)
+		swap(folio[0], folio[1]);
+
+	return 0;
+}
+
+static void mext_folio_double_unlock(struct folio *folio[2])
+{
+	folio_unlock(folio[0]);
+	folio_put(folio[0]);
+	folio_unlock(folio[1]);
+	folio_put(folio[1]);
+}
+
+/* Force folio buffers uptodate w/o dropping folio's lock */
+static int mext_folio_mkuptodate(struct folio *folio, size_t from, size_t to)
+{
+	struct inode *inode = folio->mapping->host;
+	sector_t block;
+	struct buffer_head *bh, *head;
+	unsigned int blocksize, block_start, block_end;
+	int nr = 0;
+	bool partial = false;
+
+	BUG_ON(!folio_test_locked(folio));
+	BUG_ON(folio_test_writeback(folio));
+
+	if (folio_test_uptodate(folio))
+		return 0;
+
+	blocksize = i_blocksize(inode);
+	head = folio_buffers(folio);
+	if (!head)
+		head = create_empty_buffers(folio, blocksize, 0);
+
+	block = folio_pos(folio) >> inode->i_blkbits;
+	block_end = 0;
+	bh = head;
+	do {
+		block_start = block_end;
+		block_end = block_start + blocksize;
+		if (block_end <= from || block_start >= to) {
+			if (!buffer_uptodate(bh))
+				partial = true;
+			continue;
+		}
+		if (buffer_uptodate(bh))
+			continue;
+		if (!buffer_mapped(bh)) {
+			int err = ext4_get_block(inode, block, bh, 0);
+			if (err)
+				return err;
+			if (!buffer_mapped(bh)) {
+				folio_zero_range(folio, block_start, blocksize);
+				set_buffer_uptodate(bh);
+				continue;
+			}
+		}
+		lock_buffer(bh);
+		if (buffer_uptodate(bh)) {
+			unlock_buffer(bh);
+			continue;
+		}
+		ext4_read_bh_nowait(bh, 0, NULL, false);
+		nr++;
+	} while (block++, (bh = bh->b_this_page) != head);
+
+	/* No io required */
+	if (!nr)
+		goto out;
+
+	bh = head;
+	do {
+		if (bh_offset(bh) + blocksize <= from)
+			continue;
+		if (bh_offset(bh) >= to)
+			break;
+		wait_on_buffer(bh);
+		if (buffer_uptodate(bh))
+			continue;
+		return -EIO;
+	} while ((bh = bh->b_this_page) != head);
+out:
+	if (!partial)
+		folio_mark_uptodate(folio);
+	return 0;
+}
+
+enum mext_move_type {MEXT_SKIP_EXTENT, MEXT_MOVE_EXTENT, MEXT_COPY_DATA};
+
+/*
+ * Start to move extent between the origin inode and the donor inode,
+ * hold one folio for each inode and check the candidate moving extent
+ * mapping status again.
+ */
+static int mext_move_begin(struct mext_data *mext, struct folio *folio[2],
+			   enum mext_move_type *move_type)
+{
+	struct inode *orig_inode = mext->orig_inode;
+	struct inode *donor_inode = mext->donor_inode;
+	unsigned int blkbits = orig_inode->i_blkbits;
+	struct ext4_map_blocks donor_map = {0};
+	loff_t orig_pos, donor_pos;
+	size_t move_len;
+	int ret;
+
+	orig_pos = ((loff_t)mext->orig_map.m_lblk) << blkbits;
+	donor_pos = ((loff_t)mext->donor_lblk) << blkbits;
+	ret = mext_folio_double_lock(orig_inode, donor_inode,
+			orig_pos >> PAGE_SHIFT, donor_pos >> PAGE_SHIFT,
+			((size_t)mext->orig_map.m_len) << blkbits, folio);
+	if (ret)
+		return ret;
+
+	/*
+	 * Check the origin inode's mapping information again under the
+	 * folio lock, as we do not hold the i_data_sem at all times, and
+	 * it may change during the concurrent write-back operation.
+	 */
+	if (mext->orig_map.m_seq != READ_ONCE(EXT4_I(orig_inode)->i_es_seq)) {
+		ret = -ESTALE;
+		goto error;
+	}
+
+	/* Adjust the moving length according to the length of shorter folio. */
+	move_len = umin(folio_next_pos(folio[0]) - orig_pos,
+			folio_next_pos(folio[1]) - donor_pos);
+	move_len >>= blkbits;
+	if (move_len < mext->orig_map.m_len)
+		mext->orig_map.m_len = move_len;
+
+	donor_map.m_lblk = mext->donor_lblk;
+	donor_map.m_len = mext->orig_map.m_len;
+	donor_map.m_flags = 0;
+	ret = ext4_map_blocks(NULL, donor_inode, &donor_map, 0);
+	if (ret < 0)
+		goto error;
+
+	/* Adjust the moving length according to the donor mapping length. */
+	mext->orig_map.m_len = donor_map.m_len;
+
+	/* Skip moving if the donor range is a hole or a delalloc extent. */
+	if (!(donor_map.m_flags & (EXT4_MAP_MAPPED | EXT4_MAP_UNWRITTEN)))
+		*move_type = MEXT_SKIP_EXTENT;
+	/* If both mapping ranges are unwritten, no need to copy data. */
+	else if ((mext->orig_map.m_flags & EXT4_MAP_UNWRITTEN) &&
+		 (donor_map.m_flags & EXT4_MAP_UNWRITTEN))
+		*move_type = MEXT_MOVE_EXTENT;
+	else
+		*move_type = MEXT_COPY_DATA;
+
+	return 0;
+error:
+	mext_folio_double_unlock(folio);
+	return ret;
+}
+
+/*
+ * Re-create the new moved mapping buffers of the original inode and commit
+ * the entire written range.
+ */
+static int mext_folio_mkwrite(struct inode *inode, struct folio *folio,
+			      size_t from, size_t to)
+{
+	unsigned int blocksize = i_blocksize(inode);
+	struct buffer_head *bh, *head;
+	size_t block_start, block_end;
+	sector_t block;
+	int ret;
+
+	head = folio_buffers(folio);
+	if (!head)
+		head = create_empty_buffers(folio, blocksize, 0);
+
+	block = folio_pos(folio) >> inode->i_blkbits;
+	block_end = 0;
+	bh = head;
+	do {
+		block_start = block_end;
+		block_end = block_start + blocksize;
+		if (block_end <= from || block_start >= to)
+			continue;
+
+		ret = ext4_get_block(inode, block, bh, 0);
+		if (ret)
+			return ret;
+	} while (block++, (bh = bh->b_this_page) != head);
+
+	block_commit_write(folio, from, to);
+	return 0;
+}
+
+/*
+ * Save the data in original inode extent blocks and replace one folio size
+ * aligned original inode extent with one or one partial donor inode extent,
+ * and then write out the saved data in new original inode blocks. Pass out
+ * the replaced block count through m_len. Return 0 on success, and an error
+ * code otherwise.
+ */
+static int mext_move_extent(struct mext_data *mext, u64 *m_len)
+{
+	struct inode *orig_inode = mext->orig_inode;
+	struct inode *donor_inode = mext->donor_inode;
+	struct ext4_map_blocks *orig_map = &mext->orig_map;
+	unsigned int blkbits = orig_inode->i_blkbits;
+	struct folio *folio[2] = {NULL, NULL};
+	loff_t from, length;
+	enum mext_move_type move_type = 0;
+	handle_t *handle;
+	u64 r_len = 0;
+	unsigned int credits;
+	int ret, ret2;
+
+	*m_len = 0;
+	trace_ext4_move_extent_enter(orig_inode, orig_map, donor_inode,
+				     mext->donor_lblk);
+	credits = ext4_chunk_trans_extent(orig_inode, 0) * 2;
+	handle = ext4_journal_start(orig_inode, EXT4_HT_MOVE_EXTENTS, credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out;
+	}
+	ext4_fc_mark_ineligible(orig_inode->i_sb, EXT4_FC_REASON_MOVE_EXT,
+				handle);
+
+	ret = mext_move_begin(mext, folio, &move_type);
+	if (ret)
+		goto stop_handle;
+
+	if (move_type == MEXT_SKIP_EXTENT)
+		goto unlock;
+
+	/*
+	 * Copy the data. First, read the original inode data into the page
+	 * cache. Then, release the existing mapping relationships and swap
+	 * the extent. Finally, re-establish the new mapping relationships
+	 * and dirty the page cache.
+	 */
+	if (move_type == MEXT_COPY_DATA) {
+		from = offset_in_folio(folio[0],
+				((loff_t)orig_map->m_lblk) << blkbits);
+		length = ((loff_t)orig_map->m_len) << blkbits;
+
+		ret = mext_folio_mkuptodate(folio[0], from, from + length);
+		if (ret)
+			goto unlock;
+	}
+
+	if (!filemap_release_folio(folio[0], 0) ||
+	    !filemap_release_folio(folio[1], 0)) {
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	/* Move extent */
+	ext4_double_down_write_data_sem(orig_inode, donor_inode);
+	*m_len = ext4_swap_extents(handle, orig_inode, donor_inode,
+				   orig_map->m_lblk, mext->donor_lblk,
+				   orig_map->m_len, 1, &ret);
+	ext4_double_up_write_data_sem(orig_inode, donor_inode);
+
+	/* A short-length swap cannot occur after a successful swap extent. */
+	if (WARN_ON_ONCE(!ret && (*m_len != orig_map->m_len)))
+		ret = -EIO;
+
+	if (!(*m_len) || (move_type == MEXT_MOVE_EXTENT))
+		goto unlock;
+
+	/* Copy data */
+	length = (*m_len) << blkbits;
+	ret2 = mext_folio_mkwrite(orig_inode, folio[0], from, from + length);
+	if (ret2) {
+		if (!ret)
+			ret = ret2;
+		goto repair_branches;
+	}
+	/*
+	 * Even in case of data=writeback it is reasonable to pin
+	 * inode to transaction, to prevent unexpected data loss.
+	 */
+	ret2 = ext4_jbd2_inode_add_write(handle, orig_inode,
+			((loff_t)orig_map->m_lblk) << blkbits, length);
+	if (!ret)
+		ret = ret2;
+unlock:
+	mext_folio_double_unlock(folio);
+stop_handle:
+	ext4_journal_stop(handle);
+out:
+	trace_ext4_move_extent_exit(orig_inode, orig_map->m_lblk, donor_inode,
+				    mext->donor_lblk, orig_map->m_len, *m_len,
+				    move_type, ret);
+	return ret;
+
+repair_branches:
+	ret2 = 0;
+	ext4_double_down_write_data_sem(orig_inode, donor_inode);
+	r_len = ext4_swap_extents(handle, donor_inode, orig_inode,
+				  mext->donor_lblk, orig_map->m_lblk,
+				  *m_len, 0, &ret2);
+	ext4_double_up_write_data_sem(orig_inode, donor_inode);
+	if (ret2 || r_len != *m_len) {
+		ext4_error_inode_block(orig_inode, (sector_t)(orig_map->m_lblk),
+				       EIO, "Unable to copy data block, data will be lost!");
+		ret = -EIO;
+	}
+	*m_len = 0;
+	goto unlock;
+}
+
+/*
+ * Check the validity of the basic filesystem environment and the
+ * inodes' support status.
+ */
+static int mext_check_validity(struct inode *orig_inode,
+			       struct inode *donor_inode)
+{
+	struct super_block *sb = orig_inode->i_sb;
+
+	/* origin and donor should be different inodes */
+	if (orig_inode == donor_inode) {
+		ext4_debug("ext4 move extent: The argument files should not be same inode [ino:orig %llu, donor %llu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	/* origin and donor should belone to the same filesystem */
+	if (orig_inode->i_sb != donor_inode->i_sb) {
+		ext4_debug("ext4 move extent: The argument files should be in same FS [ino:orig %llu, donor %llu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	/* Regular file check */
+	if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) {
+		ext4_debug("ext4 move extent: The argument files should be regular file [ino:orig %llu, donor %llu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	if (ext4_has_feature_bigalloc(sb)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Online defrag not supported with bigalloc");
+		return -EOPNOTSUPP;
+	}
+
+	if (IS_DAX(orig_inode)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Online defrag not supported with DAX");
+		return -EOPNOTSUPP;
+	}
+
+	/*
+	 * TODO: it's not obvious how to swap blocks for inodes with full
+	 * journaling enabled.
+	 */
+	if (ext4_should_journal_data(orig_inode) ||
+	    ext4_should_journal_data(donor_inode)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Online defrag not supported with data journaling");
+		return -EOPNOTSUPP;
+	}
+
+	if (IS_ENCRYPTED(orig_inode) || IS_ENCRYPTED(donor_inode)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Online defrag not supported for encrypted files");
+		return -EOPNOTSUPP;
+	}
+
+	/* Ext4 move extent supports only extent based file */
+	if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS)) ||
+	    !(ext4_test_inode_flag(donor_inode, EXT4_INODE_EXTENTS))) {
+		ext4_msg(sb, KERN_ERR,
+			 "Online defrag not supported for non-extent files");
+		return -EOPNOTSUPP;
+	}
+
+	if (donor_inode->i_mode & (S_ISUID|S_ISGID)) {
+		ext4_debug("ext4 move extent: suid or sgid is set to donor file [ino:orig %llu, donor %llu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	if (IS_IMMUTABLE(donor_inode) || IS_APPEND(donor_inode)) {
+		ext4_debug("ext4 move extent: donor should not be immutable or append file [ino:orig %llu, donor %llu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
+		return -EPERM;
+	}
+
+	/* Ext4 move extent does not support swap files */
+	if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) {
+		ext4_debug("ext4 move extent: The argument files should not be swap files [ino:orig %llu, donor %llu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
+		return -ETXTBSY;
+	}
+
+	if (ext4_is_quota_file(orig_inode) || ext4_is_quota_file(donor_inode)) {
+		ext4_debug("ext4 move extent: The argument files should not be quota files [ino:orig %llu, donor %llu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
+		return -EOPNOTSUPP;
+	}
+
+	if ((!orig_inode->i_size) || (!donor_inode->i_size)) {
+		ext4_debug("ext4 move extent: File size is 0 byte\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Check the moving range of ext4_move_extents() whether the files can be
+ * exchanged with each other, and adjust the length to fit within the file
+ * size. Return 0 on success, or a negative error value on failure.
+ */
+static int mext_check_adjust_range(struct inode *orig_inode,
+				   struct inode *donor_inode, __u64 orig_start,
+				   __u64 donor_start, __u64 *len)
+{
+	__u64 orig_eof, donor_eof;
+
+	/* Start offset should be same */
+	if ((orig_start & ~(PAGE_MASK >> orig_inode->i_blkbits)) !=
+	    (donor_start & ~(PAGE_MASK >> orig_inode->i_blkbits))) {
+		ext4_debug("ext4 move extent: orig and donor's start offsets are not aligned [ino:orig %llu, donor %llu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	if ((orig_start >= EXT_MAX_BLOCKS) ||
+	    (donor_start >= EXT_MAX_BLOCKS) ||
+	    (*len > EXT_MAX_BLOCKS) ||
+	    (donor_start + *len >= EXT_MAX_BLOCKS) ||
+	    (orig_start + *len >= EXT_MAX_BLOCKS))  {
+		ext4_debug("ext4 move extent: Can't handle over [%u] blocks [ino:orig %llu, donor %llu]\n",
+			   EXT_MAX_BLOCKS,
+			   orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	orig_eof = EXT4_B_TO_LBLK(orig_inode, i_size_read(orig_inode));
+	donor_eof = EXT4_B_TO_LBLK(donor_inode, i_size_read(donor_inode));
+	if (orig_eof <= orig_start)
+		*len = 0;
+	else if (orig_eof < orig_start + *len - 1)
+		*len = orig_eof - orig_start;
+	if (donor_eof <= donor_start)
+		*len = 0;
+	else if (donor_eof < donor_start + *len - 1)
+		*len = donor_eof - donor_start;
+	if (!*len) {
+		ext4_debug("ext4 move extent: len should not be 0 [ino:orig %llu, donor %llu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * ext4_move_extents - Exchange the specified range of a file
+ *
+ * @o_filp:		file structure of the original file
+ * @d_filp:		file structure of the donor file
+ * @orig_blk:		start offset in block for orig
+ * @donor_blk:		start offset in block for donor
+ * @len:		the number of blocks to be moved
+ * @moved_len:		moved block length
+ *
+ * This function returns 0 and moved block length is set in moved_len
+ * if succeed, otherwise returns error value.
+ */
+int ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
+		      __u64 donor_blk, __u64 len, __u64 *moved_len)
+{
+	struct inode *orig_inode = file_inode(o_filp);
+	struct inode *donor_inode = file_inode(d_filp);
+	struct mext_data mext;
+	struct super_block *sb = orig_inode->i_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int retries = 0;
+	u64 m_len;
+	int ret;
+
+	*moved_len = 0;
+
+	/* Protect orig and donor inodes against a truncate */
+	lock_two_nondirectories(orig_inode, donor_inode);
+
+	ret = mext_check_validity(orig_inode, donor_inode);
+	if (ret)
+		goto out;
+
+	/* Wait for all existing dio workers */
+	inode_dio_wait(orig_inode);
+	inode_dio_wait(donor_inode);
+
+	/* Check and adjust the specified move_extent range. */
+	ret = mext_check_adjust_range(orig_inode, donor_inode, orig_blk,
+				      donor_blk, &len);
+	if (ret)
+		goto out;
+
+	mext.orig_inode = orig_inode;
+	mext.donor_inode = donor_inode;
+	while (len) {
+		mext.orig_map.m_lblk = orig_blk;
+		mext.orig_map.m_len = len;
+		mext.orig_map.m_flags = 0;
+		mext.donor_lblk = donor_blk;
+
+		ret = ext4_map_blocks(NULL, orig_inode, &mext.orig_map, 0);
+		if (ret < 0)
+			goto out;
+
+		/* Skip moving if it is a hole or a delalloc extent. */
+		if (mext.orig_map.m_flags &
+		    (EXT4_MAP_MAPPED | EXT4_MAP_UNWRITTEN)) {
+			ret = mext_move_extent(&mext, &m_len);
+			*moved_len += m_len;
+			if (!ret)
+				goto next;
+
+			/* Move failed or partially failed. */
+			if (m_len) {
+				orig_blk += m_len;
+				donor_blk += m_len;
+				len -= m_len;
+			}
+			if (ret == -ESTALE)
+				continue;
+			if (ret == -ENOSPC &&
+			    ext4_should_retry_alloc(sb, &retries))
+				continue;
+			if (ret == -EBUSY &&
+			    sbi->s_journal && retries++ < 4 &&
+			    jbd2_journal_force_commit_nested(sbi->s_journal))
+				continue;
+
+			goto out;
+		}
+next:
+		orig_blk += mext.orig_map.m_len;
+		donor_blk += mext.orig_map.m_len;
+		len -= mext.orig_map.m_len;
+		retries = 0;
+	}
+
+out:
+	if (*moved_len) {
+		ext4_discard_preallocations(orig_inode);
+		ext4_discard_preallocations(donor_inode);
+	}
+
+	unlock_two_nondirectories(orig_inode, donor_inode);
+	return ret;
+}

linux-7.2.3/fs/ext4/orphan.c

@@ -0,0 +1,659 @@
+/*
+ * Ext4 orphan inode handling
+ */
+#include <linux/fs.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+
+#include "ext4.h"
+#include "ext4_jbd2.h"
+
+#define EXT4_MAX_ORPHAN_FILE_BLOCKS 512
+
+static int ext4_orphan_file_add(handle_t *handle, struct inode *inode)
+{
+	int i, j, start;
+	struct ext4_orphan_info *oi = &EXT4_SB(inode->i_sb)->s_orphan_info;
+	int ret = 0;
+	bool found = false;
+	__le32 *bdata;
+	int inodes_per_ob = ext4_inodes_per_orphan_block(inode->i_sb);
+	int looped = 0;
+
+	/*
+	 * Find block with free orphan entry. Use CPU number for a naive hash
+	 * for a search start in the orphan file
+	 */
+	start = raw_smp_processor_id()*13 % oi->of_blocks;
+	i = start;
+	do {
+		if (atomic_dec_if_positive(&oi->of_binfo[i].ob_free_entries)
+		    >= 0) {
+			found = true;
+			break;
+		}
+		if (++i >= oi->of_blocks)
+			i = 0;
+	} while (i != start);
+
+	if (!found) {
+		/*
+		 * For now we don't grow or shrink orphan file. We just use
+		 * whatever was allocated at mke2fs time. The additional
+		 * credits we would have to reserve for each orphan inode
+		 * operation just don't seem worth it.
+		 */
+		return -ENOSPC;
+	}
+
+	ret = ext4_journal_get_write_access(handle, inode->i_sb,
+				oi->of_binfo[i].ob_bh, EXT4_JTR_ORPHAN_FILE);
+	if (ret) {
+		atomic_inc(&oi->of_binfo[i].ob_free_entries);
+		return ret;
+	}
+
+	bdata = (__le32 *)(oi->of_binfo[i].ob_bh->b_data);
+	/* Find empty slot in a block */
+	j = 0;
+	do {
+		if (looped) {
+			/*
+			 * Did we walk through the block several times without
+			 * finding free entry? It is theoretically possible
+			 * if entries get constantly allocated and freed or
+			 * if the block is corrupted. Avoid indefinite looping
+			 * and bail. We'll use orphan list instead.
+			 */
+			if (looped > 3) {
+				atomic_inc(&oi->of_binfo[i].ob_free_entries);
+				return -ENOSPC;
+			}
+			cond_resched();
+		}
+		while (bdata[j]) {
+			if (++j >= inodes_per_ob) {
+				j = 0;
+				looped++;
+			}
+		}
+	} while (cmpxchg(&bdata[j], (__le32)0, cpu_to_le32(inode->i_ino)) !=
+		 (__le32)0);
+
+	EXT4_I(inode)->i_orphan_idx = i * inodes_per_ob + j;
+	ext4_set_inode_state(inode, EXT4_STATE_ORPHAN_FILE);
+
+	return ext4_handle_dirty_metadata(handle, NULL, oi->of_binfo[i].ob_bh);
+}
+
+/*
+ * ext4_orphan_add() links an unlinked or truncated inode into a list of
+ * such inodes, starting at the superblock, in case we crash before the
+ * file is closed/deleted, or in case the inode truncate spans multiple
+ * transactions and the last transaction is not recovered after a crash.
+ *
+ * At filesystem recovery time, we walk this list deleting unlinked
+ * inodes and truncating linked inodes in ext4_orphan_cleanup().
+ *
+ * Orphan list manipulation functions must be called under i_rwsem unless
+ * we are just creating the inode or deleting it.
+ */
+int ext4_orphan_add(handle_t *handle, struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_iloc iloc;
+	int err = 0, rc;
+	bool dirty = false;
+
+	if (!sbi->s_journal || is_bad_inode(inode))
+		return 0;
+
+	WARN_ON_ONCE(!(inode_state_read_once(inode) & (I_NEW | I_FREEING)) &&
+		     !inode_is_locked(inode));
+	if (ext4_inode_orphan_tracked(inode))
+		return 0;
+
+	/*
+	 * Orphan handling is only valid for files with data blocks
+	 * being truncated, or files being unlinked. Note that we either
+	 * hold i_rwsem, or the inode can not be referenced from outside,
+	 * so i_nlink should not be bumped due to race
+	 */
+	ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+		  S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
+
+	if (sbi->s_orphan_info.of_blocks) {
+		err = ext4_orphan_file_add(handle, inode);
+		/*
+		 * Fallback to normal orphan list of orphan file is
+		 * out of space
+		 */
+		if (err != -ENOSPC)
+			return err;
+	}
+
+	BUFFER_TRACE(sbi->s_sbh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, sb, sbi->s_sbh,
+					    EXT4_JTR_NONE);
+	if (err)
+		goto out;
+
+	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (err)
+		goto out;
+
+	mutex_lock(&sbi->s_orphan_lock);
+	/*
+	 * Due to previous errors inode may be already a part of on-disk
+	 * orphan list. If so skip on-disk list modification.
+	 */
+	if (!NEXT_ORPHAN(inode) || NEXT_ORPHAN(inode) >
+	    (le32_to_cpu(sbi->s_es->s_inodes_count))) {
+		/* Insert this inode at the head of the on-disk orphan list */
+		NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan);
+		lock_buffer(sbi->s_sbh);
+		sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
+		ext4_superblock_csum_set(sb);
+		unlock_buffer(sbi->s_sbh);
+		dirty = true;
+	}
+	list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan);
+	mutex_unlock(&sbi->s_orphan_lock);
+
+	if (dirty) {
+		err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
+		rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
+		if (!err)
+			err = rc;
+		if (err) {
+			/*
+			 * We have to remove inode from in-memory list if
+			 * addition to on disk orphan list failed. Stray orphan
+			 * list entries can cause panics at unmount time.
+			 */
+			mutex_lock(&sbi->s_orphan_lock);
+			list_del_init(&EXT4_I(inode)->i_orphan);
+			mutex_unlock(&sbi->s_orphan_lock);
+		}
+	} else
+		brelse(iloc.bh);
+
+	ext4_debug("superblock will point to %llu\n", inode->i_ino);
+	ext4_debug("orphan inode %llu will point to %d\n",
+			inode->i_ino, NEXT_ORPHAN(inode));
+out:
+	ext4_std_error(sb, err);
+	return err;
+}
+
+static int ext4_orphan_file_del(handle_t *handle, struct inode *inode)
+{
+	struct ext4_orphan_info *oi = &EXT4_SB(inode->i_sb)->s_orphan_info;
+	__le32 *bdata;
+	int blk, off;
+	int inodes_per_ob = ext4_inodes_per_orphan_block(inode->i_sb);
+	int ret = 0;
+
+	if (!handle)
+		goto out;
+	blk = EXT4_I(inode)->i_orphan_idx / inodes_per_ob;
+	off = EXT4_I(inode)->i_orphan_idx % inodes_per_ob;
+	if (WARN_ON_ONCE(blk >= oi->of_blocks))
+		goto out;
+
+	ret = ext4_journal_get_write_access(handle, inode->i_sb,
+				oi->of_binfo[blk].ob_bh, EXT4_JTR_ORPHAN_FILE);
+	if (ret)
+		goto out;
+
+	bdata = (__le32 *)(oi->of_binfo[blk].ob_bh->b_data);
+	bdata[off] = 0;
+	atomic_inc(&oi->of_binfo[blk].ob_free_entries);
+	ret = ext4_handle_dirty_metadata(handle, NULL, oi->of_binfo[blk].ob_bh);
+out:
+	ext4_clear_inode_state(inode, EXT4_STATE_ORPHAN_FILE);
+	INIT_LIST_HEAD(&EXT4_I(inode)->i_orphan);
+
+	return ret;
+}
+
+/*
+ * ext4_orphan_del() removes an unlinked or truncated inode from the list
+ * of such inodes stored on disk, because it is finally being cleaned up.
+ */
+int ext4_orphan_del(handle_t *handle, struct inode *inode)
+{
+	struct list_head *prev;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	__u32 ino_next;
+	struct ext4_iloc iloc;
+	int err = 0;
+
+	if (!sbi->s_journal && !(sbi->s_mount_state & EXT4_ORPHAN_FS))
+		return 0;
+
+	WARN_ON_ONCE(!(inode_state_read_once(inode) & (I_NEW | I_FREEING)) &&
+		     !inode_is_locked(inode));
+	if (ext4_test_inode_state(inode, EXT4_STATE_ORPHAN_FILE))
+		return ext4_orphan_file_del(handle, inode);
+
+	/* Do this quick check before taking global s_orphan_lock. */
+	if (list_empty(&ei->i_orphan))
+		return 0;
+
+	if (handle) {
+		/* Grab inode buffer early before taking global s_orphan_lock */
+		err = ext4_reserve_inode_write(handle, inode, &iloc);
+	}
+
+	mutex_lock(&sbi->s_orphan_lock);
+	ext4_debug("remove inode %llu from orphan list\n", inode->i_ino);
+
+	prev = ei->i_orphan.prev;
+	list_del_init(&ei->i_orphan);
+
+	/* If we're on an error path, we may not have a valid
+	 * transaction handle with which to update the orphan list on
+	 * disk, but we still need to remove the inode from the linked
+	 * list in memory. */
+	if (!handle || err) {
+		mutex_unlock(&sbi->s_orphan_lock);
+		goto out_err;
+	}
+
+	ino_next = NEXT_ORPHAN(inode);
+	if (prev == &sbi->s_orphan) {
+		ext4_debug("superblock will point to %u\n", ino_next);
+		BUFFER_TRACE(sbi->s_sbh, "get_write_access");
+		err = ext4_journal_get_write_access(handle, inode->i_sb,
+						    sbi->s_sbh, EXT4_JTR_NONE);
+		if (err) {
+			mutex_unlock(&sbi->s_orphan_lock);
+			goto out_brelse;
+		}
+		lock_buffer(sbi->s_sbh);
+		sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
+		ext4_superblock_csum_set(inode->i_sb);
+		unlock_buffer(sbi->s_sbh);
+		mutex_unlock(&sbi->s_orphan_lock);
+		err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
+	} else {
+		struct ext4_iloc iloc2;
+		struct inode *i_prev =
+			&list_entry(prev, struct ext4_inode_info, i_orphan)->vfs_inode;
+
+		ext4_debug("orphan inode %llu will point to %u\n",
+			  i_prev->i_ino, ino_next);
+		err = ext4_reserve_inode_write(handle, i_prev, &iloc2);
+		if (err) {
+			mutex_unlock(&sbi->s_orphan_lock);
+			goto out_brelse;
+		}
+		NEXT_ORPHAN(i_prev) = ino_next;
+		err = ext4_mark_iloc_dirty(handle, i_prev, &iloc2);
+		mutex_unlock(&sbi->s_orphan_lock);
+	}
+	if (err)
+		goto out_brelse;
+	NEXT_ORPHAN(inode) = 0;
+	err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+out_err:
+	ext4_std_error(inode->i_sb, err);
+	return err;
+
+out_brelse:
+	brelse(iloc.bh);
+	goto out_err;
+}
+
+#ifdef CONFIG_QUOTA
+static int ext4_quota_on_mount(struct super_block *sb, int type)
+{
+	return dquot_quota_on_mount(sb,
+		rcu_dereference_protected(EXT4_SB(sb)->s_qf_names[type],
+					  lockdep_is_held(&sb->s_umount)),
+		EXT4_SB(sb)->s_jquota_fmt, type);
+}
+#endif
+
+static void ext4_process_orphan(struct inode *inode,
+				int *nr_truncates, int *nr_orphans)
+{
+	struct super_block *sb = inode->i_sb;
+	int ret;
+
+	dquot_initialize(inode);
+	if (inode->i_nlink) {
+		if (test_opt(sb, DEBUG))
+			ext4_msg(sb, KERN_DEBUG,
+				"%s: truncating inode %llu to %lld bytes",
+				__func__, inode->i_ino, inode->i_size);
+		ext4_debug("truncating inode %llu to %lld bytes\n",
+			   inode->i_ino, inode->i_size);
+		inode_lock(inode);
+		truncate_inode_pages(inode->i_mapping, inode->i_size);
+		ret = ext4_truncate(inode);
+		if (ret) {
+			/*
+			 * We need to clean up the in-core orphan list
+			 * manually if ext4_truncate() failed to get a
+			 * transaction handle.
+			 */
+			ext4_orphan_del(NULL, inode);
+			ext4_std_error(inode->i_sb, ret);
+		}
+		inode_unlock(inode);
+		(*nr_truncates)++;
+	} else {
+		if (test_opt(sb, DEBUG))
+			ext4_msg(sb, KERN_DEBUG,
+				"%s: deleting unreferenced inode %llu",
+				__func__, inode->i_ino);
+		ext4_debug("deleting unreferenced inode %llu\n",
+			   inode->i_ino);
+		(*nr_orphans)++;
+	}
+	iput(inode);  /* The delete magic happens here! */
+}
+
+/* ext4_orphan_cleanup() walks a singly-linked list of inodes (starting at
+ * the superblock) which were deleted from all directories, but held open by
+ * a process at the time of a crash.  We walk the list and try to delete these
+ * inodes at recovery time (only with a read-write filesystem).
+ *
+ * In order to keep the orphan inode chain consistent during traversal (in
+ * case of crash during recovery), we link each inode into the superblock
+ * orphan list_head and handle it the same way as an inode deletion during
+ * normal operation (which journals the operations for us).
+ *
+ * We only do an iget() and an iput() on each inode, which is very safe if we
+ * accidentally point at an in-use or already deleted inode.  The worst that
+ * can happen in this case is that we get a "bit already cleared" message from
+ * ext4_free_inode().  The only reason we would point at a wrong inode is if
+ * e2fsck was run on this filesystem, and it must have already done the orphan
+ * inode cleanup for us, so we can safely abort without any further action.
+ */
+void ext4_orphan_cleanup(struct super_block *sb, struct ext4_super_block *es)
+{
+	unsigned int s_flags = sb->s_flags;
+	int nr_orphans = 0, nr_truncates = 0;
+	struct inode *inode;
+	int i, j;
+#ifdef CONFIG_QUOTA
+	int quota_update = 0;
+#endif
+	__le32 *bdata;
+	struct ext4_orphan_info *oi = &EXT4_SB(sb)->s_orphan_info;
+	int inodes_per_ob = ext4_inodes_per_orphan_block(sb);
+
+	if (!es->s_last_orphan && !oi->of_blocks) {
+		ext4_debug("no orphan inodes to clean up\n");
+		return;
+	}
+
+	if (bdev_read_only(sb->s_bdev)) {
+		ext4_msg(sb, KERN_ERR, "write access "
+			"unavailable, skipping orphan cleanup");
+		return;
+	}
+
+	/* Check if feature set would not allow a r/w mount */
+	if (!ext4_feature_set_ok(sb, 0)) {
+		ext4_msg(sb, KERN_INFO, "Skipping orphan cleanup due to "
+			 "unknown ROCOMPAT features");
+		return;
+	}
+
+	if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
+		/* don't clear list on RO mount w/ errors */
+		if (es->s_last_orphan && !(s_flags & SB_RDONLY)) {
+			ext4_msg(sb, KERN_INFO, "Errors on filesystem, "
+				  "clearing orphan list.");
+			es->s_last_orphan = 0;
+		}
+		ext4_debug("Skipping orphan recovery on fs with errors.\n");
+		return;
+	}
+
+	if (s_flags & SB_RDONLY) {
+		ext4_msg(sb, KERN_INFO, "orphan cleanup on readonly fs");
+		sb->s_flags &= ~SB_RDONLY;
+	}
+#ifdef CONFIG_QUOTA
+	/*
+	 * Turn on quotas which were not enabled for read-only mounts if
+	 * filesystem has quota feature, so that they are updated correctly.
+	 */
+	if (ext4_has_feature_quota(sb) && (s_flags & SB_RDONLY)) {
+		int ret = ext4_enable_quotas(sb);
+
+		if (!ret)
+			quota_update = 1;
+		else
+			ext4_msg(sb, KERN_ERR,
+				"Cannot turn on quotas: error %d", ret);
+	}
+
+	/* Turn on journaled quotas used for old sytle */
+	for (i = 0; i < EXT4_MAXQUOTAS; i++) {
+		if (EXT4_SB(sb)->s_qf_names[i]) {
+			int ret = ext4_quota_on_mount(sb, i);
+
+			if (!ret)
+				quota_update = 1;
+			else
+				ext4_msg(sb, KERN_ERR,
+					"Cannot turn on journaled "
+					"quota: type %d: error %d", i, ret);
+		}
+	}
+#endif
+
+	while (es->s_last_orphan) {
+		/*
+		 * We may have encountered an error during cleanup; if
+		 * so, skip the rest.
+		 */
+		if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
+			ext4_debug("Skipping orphan recovery on fs with errors.\n");
+			es->s_last_orphan = 0;
+			break;
+		}
+
+		inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan));
+		if (IS_ERR(inode)) {
+			es->s_last_orphan = 0;
+			break;
+		}
+
+		list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
+		ext4_process_orphan(inode, &nr_truncates, &nr_orphans);
+	}
+
+	for (i = 0; i < oi->of_blocks; i++) {
+		bdata = (__le32 *)(oi->of_binfo[i].ob_bh->b_data);
+		for (j = 0; j < inodes_per_ob; j++) {
+			if (!bdata[j])
+				continue;
+			inode = ext4_orphan_get(sb, le32_to_cpu(bdata[j]));
+			if (IS_ERR(inode))
+				continue;
+			ext4_set_inode_state(inode, EXT4_STATE_ORPHAN_FILE);
+			EXT4_I(inode)->i_orphan_idx = i * inodes_per_ob + j;
+			ext4_process_orphan(inode, &nr_truncates, &nr_orphans);
+		}
+	}
+
+#define PLURAL(x) (x), ((x) == 1) ? "" : "s"
+
+	if (nr_orphans)
+		ext4_msg(sb, KERN_INFO, "%d orphan inode%s deleted",
+		       PLURAL(nr_orphans));
+	if (nr_truncates)
+		ext4_msg(sb, KERN_INFO, "%d truncate%s cleaned up",
+		       PLURAL(nr_truncates));
+#ifdef CONFIG_QUOTA
+	/* Turn off quotas if they were enabled for orphan cleanup */
+	if (quota_update) {
+		for (i = 0; i < EXT4_MAXQUOTAS; i++) {
+			if (sb_dqopt(sb)->files[i])
+				dquot_quota_off(sb, i);
+		}
+	}
+#endif
+	sb->s_flags = s_flags; /* Restore SB_RDONLY status */
+}
+
+void ext4_release_orphan_info(struct super_block *sb)
+{
+	int i;
+	struct ext4_orphan_info *oi = &EXT4_SB(sb)->s_orphan_info;
+
+	if (!oi->of_blocks)
+		return;
+	for (i = 0; i < oi->of_blocks; i++)
+		brelse(oi->of_binfo[i].ob_bh);
+	kvfree(oi->of_binfo);
+}
+
+static struct ext4_orphan_block_tail *ext4_orphan_block_tail(
+						struct super_block *sb,
+						struct buffer_head *bh)
+{
+	return (struct ext4_orphan_block_tail *)(bh->b_data + sb->s_blocksize -
+				sizeof(struct ext4_orphan_block_tail));
+}
+
+static int ext4_orphan_file_block_csum_verify(struct super_block *sb,
+					      struct buffer_head *bh)
+{
+	__u32 calculated;
+	int inodes_per_ob = ext4_inodes_per_orphan_block(sb);
+	struct ext4_orphan_info *oi = &EXT4_SB(sb)->s_orphan_info;
+	struct ext4_orphan_block_tail *ot;
+	__le64 dsk_block_nr = cpu_to_le64(bh->b_blocknr);
+
+	if (!ext4_has_feature_metadata_csum(sb))
+		return 1;
+
+	ot = ext4_orphan_block_tail(sb, bh);
+	calculated = ext4_chksum(oi->of_csum_seed, (__u8 *)&dsk_block_nr,
+				 sizeof(dsk_block_nr));
+	calculated = ext4_chksum(calculated, (__u8 *)bh->b_data,
+				 inodes_per_ob * sizeof(__u32));
+	return le32_to_cpu(ot->ob_checksum) == calculated;
+}
+
+/* This gets called only when checksumming is enabled */
+void ext4_orphan_file_block_trigger(struct jbd2_buffer_trigger_type *triggers,
+				    struct buffer_head *bh,
+				    void *data, size_t size)
+{
+	struct super_block *sb = EXT4_TRIGGER(triggers)->sb;
+	__u32 csum;
+	int inodes_per_ob = ext4_inodes_per_orphan_block(sb);
+	struct ext4_orphan_info *oi = &EXT4_SB(sb)->s_orphan_info;
+	struct ext4_orphan_block_tail *ot;
+	__le64 dsk_block_nr = cpu_to_le64(bh->b_blocknr);
+
+	csum = ext4_chksum(oi->of_csum_seed, (__u8 *)&dsk_block_nr,
+			   sizeof(dsk_block_nr));
+	csum = ext4_chksum(csum, (__u8 *)data, inodes_per_ob * sizeof(__u32));
+	ot = ext4_orphan_block_tail(sb, bh);
+	ot->ob_checksum = cpu_to_le32(csum);
+}
+
+int ext4_init_orphan_info(struct super_block *sb)
+{
+	struct ext4_orphan_info *oi = &EXT4_SB(sb)->s_orphan_info;
+	struct inode *inode;
+	int i, j;
+	int ret;
+	int free;
+	__le32 *bdata;
+	int inodes_per_ob = ext4_inodes_per_orphan_block(sb);
+	struct ext4_orphan_block_tail *ot;
+	ino_t orphan_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_orphan_file_inum);
+
+	if (!ext4_has_feature_orphan_file(sb))
+		return 0;
+
+	inode = ext4_iget(sb, orphan_ino, EXT4_IGET_SPECIAL);
+	if (IS_ERR(inode)) {
+		ext4_msg(sb, KERN_ERR, "get orphan inode failed");
+		return PTR_ERR(inode);
+	}
+	/*
+	 * This is just an artificial limit to prevent corrupted fs from
+	 * consuming absurd amounts of memory when pinning blocks of orphan
+	 * file in memory.
+	 */
+	if (inode->i_size > (EXT4_MAX_ORPHAN_FILE_BLOCKS << inode->i_blkbits)) {
+		ext4_msg(sb, KERN_ERR, "orphan file too big: %llu",
+			 (unsigned long long)inode->i_size);
+		ret = -EFSCORRUPTED;
+		goto out_put;
+	}
+	oi->of_blocks = inode->i_size >> sb->s_blocksize_bits;
+	oi->of_csum_seed = EXT4_I(inode)->i_csum_seed;
+	oi->of_binfo = kvmalloc_objs(struct ext4_orphan_block, oi->of_blocks);
+	if (!oi->of_binfo) {
+		ret = -ENOMEM;
+		goto out_put;
+	}
+	for (i = 0; i < oi->of_blocks; i++) {
+		oi->of_binfo[i].ob_bh = ext4_bread(NULL, inode, i, 0);
+		if (IS_ERR(oi->of_binfo[i].ob_bh)) {
+			ret = PTR_ERR(oi->of_binfo[i].ob_bh);
+			goto out_free;
+		}
+		if (!oi->of_binfo[i].ob_bh) {
+			ret = -EIO;
+			goto out_free;
+		}
+		ot = ext4_orphan_block_tail(sb, oi->of_binfo[i].ob_bh);
+		if (le32_to_cpu(ot->ob_magic) != EXT4_ORPHAN_BLOCK_MAGIC) {
+			ext4_error(sb, "orphan file block %d: bad magic", i);
+			ret = -EIO;
+			goto out_free;
+		}
+		if (!ext4_orphan_file_block_csum_verify(sb,
+						oi->of_binfo[i].ob_bh)) {
+			ext4_error(sb, "orphan file block %d: bad checksum", i);
+			ret = -EIO;
+			goto out_free;
+		}
+		bdata = (__le32 *)(oi->of_binfo[i].ob_bh->b_data);
+		free = 0;
+		for (j = 0; j < inodes_per_ob; j++)
+			if (bdata[j] == 0)
+				free++;
+		atomic_set(&oi->of_binfo[i].ob_free_entries, free);
+	}
+	iput(inode);
+	return 0;
+out_free:
+	for (i--; i >= 0; i--)
+		brelse(oi->of_binfo[i].ob_bh);
+	kvfree(oi->of_binfo);
+out_put:
+	iput(inode);
+	return ret;
+}
+
+int ext4_orphan_file_empty(struct super_block *sb)
+{
+	struct ext4_orphan_info *oi = &EXT4_SB(sb)->s_orphan_info;
+	int i;
+	int inodes_per_ob = ext4_inodes_per_orphan_block(sb);
+
+	if (!ext4_has_feature_orphan_file(sb))
+		return 1;
+	for (i = 0; i < oi->of_blocks; i++)
+		if (atomic_read(&oi->of_binfo[i].ob_free_entries) !=
+		    inodes_per_ob)
+			return 0;
+	return 1;
+}

linux-7.2.3/fs/ext4/page-io.c

@@ -0,0 +1,613 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/fs/ext4/page-io.c
+ *
+ * This contains the new page_io functions for ext4
+ *
+ * Written by Theodore Ts'o, 2010.
+ */
+
+#include <linux/blk-crypto.h>
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/highuid.h>
+#include <linux/pagemap.h>
+#include <linux/quotaops.h>
+#include <linux/string.h>
+#include <linux/buffer_head.h>
+#include <linux/writeback.h>
+#include <linux/mpage.h>
+#include <linux/namei.h>
+#include <linux/uio.h>
+#include <linux/bio.h>
+#include <linux/workqueue.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/sched/mm.h>
+
+#include "ext4_jbd2.h"
+#include "xattr.h"
+#include "acl.h"
+
+static struct kmem_cache *io_end_cachep;
+static struct kmem_cache *io_end_vec_cachep;
+
+int __init ext4_init_pageio(void)
+{
+	io_end_cachep = KMEM_CACHE(ext4_io_end, SLAB_RECLAIM_ACCOUNT);
+	if (io_end_cachep == NULL)
+		return -ENOMEM;
+
+	io_end_vec_cachep = KMEM_CACHE(ext4_io_end_vec, 0);
+	if (io_end_vec_cachep == NULL) {
+		kmem_cache_destroy(io_end_cachep);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void ext4_exit_pageio(void)
+{
+	kmem_cache_destroy(io_end_cachep);
+	kmem_cache_destroy(io_end_vec_cachep);
+}
+
+struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end)
+{
+	struct ext4_io_end_vec *io_end_vec;
+
+	io_end_vec = kmem_cache_zalloc(io_end_vec_cachep, GFP_NOFS);
+	if (!io_end_vec)
+		return ERR_PTR(-ENOMEM);
+	INIT_LIST_HEAD(&io_end_vec->list);
+	list_add_tail(&io_end_vec->list, &io_end->list_vec);
+	return io_end_vec;
+}
+
+static void ext4_free_io_end_vec(ext4_io_end_t *io_end)
+{
+	struct ext4_io_end_vec *io_end_vec, *tmp;
+
+	if (list_empty(&io_end->list_vec))
+		return;
+	list_for_each_entry_safe(io_end_vec, tmp, &io_end->list_vec, list) {
+		list_del(&io_end_vec->list);
+		kmem_cache_free(io_end_vec_cachep, io_end_vec);
+	}
+}
+
+struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end)
+{
+	BUG_ON(list_empty(&io_end->list_vec));
+	return list_last_entry(&io_end->list_vec, struct ext4_io_end_vec, list);
+}
+
+/*
+ * Print an buffer I/O error compatible with the fs/buffer.c.  This
+ * provides compatibility with dmesg scrapers that look for a specific
+ * buffer I/O error message.  We really need a unified error reporting
+ * structure to userspace ala Digital Unix's uerf system, but it's
+ * probably not going to happen in my lifetime, due to LKML politics...
+ */
+static void buffer_io_error(struct buffer_head *bh)
+{
+	printk_ratelimited(KERN_ERR "Buffer I/O error on device %pg, logical block %llu\n",
+		       bh->b_bdev,
+			(unsigned long long)bh->b_blocknr);
+}
+
+static void ext4_finish_bio(struct bio *bio)
+{
+	struct folio_iter fi;
+
+	bio_for_each_folio_all(fi, bio) {
+		struct folio *folio = fi.folio;
+		struct folio *io_folio = NULL;
+		struct buffer_head *bh, *head;
+		size_t bio_start = fi.offset;
+		size_t bio_end = bio_start + fi.length;
+		unsigned under_io = 0;
+		unsigned long flags;
+
+		if (fscrypt_is_bounce_folio(folio)) {
+			io_folio = folio;
+			folio = fscrypt_pagecache_folio(folio);
+		}
+
+		if (bio->bi_status) {
+			int err = blk_status_to_errno(bio->bi_status);
+			mapping_set_error(folio->mapping, err);
+		}
+		bh = head = folio_buffers(folio);
+		/*
+		 * We check all buffers in the folio under b_uptodate_lock
+		 * to avoid races with other end io clearing async_write flags
+		 */
+		spin_lock_irqsave(&head->b_uptodate_lock, flags);
+		do {
+			if (bh_offset(bh) < bio_start ||
+			    bh_offset(bh) + bh->b_size > bio_end) {
+				if (buffer_async_write(bh))
+					under_io++;
+				continue;
+			}
+			clear_buffer_async_write(bh);
+			if (bio->bi_status) {
+				set_buffer_write_io_error(bh);
+				buffer_io_error(bh);
+			}
+		} while ((bh = bh->b_this_page) != head);
+		spin_unlock_irqrestore(&head->b_uptodate_lock, flags);
+		if (!under_io) {
+			fscrypt_free_bounce_page(&io_folio->page);
+			folio_end_writeback(folio);
+		}
+	}
+}
+
+static void ext4_release_io_end(ext4_io_end_t *io_end)
+{
+	struct bio *bio, *next_bio;
+
+	BUG_ON(!list_empty(&io_end->list));
+	BUG_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
+	WARN_ON(io_end->handle);
+
+	for (bio = io_end->bio; bio; bio = next_bio) {
+		next_bio = bio->bi_private;
+		ext4_finish_bio(bio);
+		bio_put(bio);
+	}
+	ext4_free_io_end_vec(io_end);
+	kmem_cache_free(io_end_cachep, io_end);
+}
+
+/*
+ * On successful IO, check a range of space and convert unwritten extents to
+ * written. On IO failure, check if journal abort is needed. Note that
+ * we are protected from truncate touching same part of extent tree by the
+ * fact that truncate code waits for all DIO to finish (thus exclusion from
+ * direct IO is achieved) and also waits for writeback to complete. Thus we
+ * cannot get to ext4_ext_truncate() before all IOs overlapping that range are
+ * completed (happens from ext4_free_ioend()).
+ */
+static int ext4_end_io_end(ext4_io_end_t *io_end)
+{
+	struct inode *inode = io_end->inode;
+	handle_t *handle = io_end->handle;
+	struct super_block *sb = inode->i_sb;
+	int ret = 0;
+
+	ext4_debug("ext4_end_io_nolock: io_end 0x%p from inode %llu,list->next 0x%p,"
+		   "list->prev 0x%p\n",
+		   io_end, inode->i_ino, io_end->list.next, io_end->list.prev);
+
+	/*
+	 * Do not convert the unwritten extents if data writeback fails,
+	 * or stale data may be exposed.
+	 */
+	io_end->handle = NULL;  /* Following call will use up the handle */
+	if (unlikely(io_end->flag & EXT4_IO_END_FAILED)) {
+		ret = -EIO;
+		if (handle)
+			jbd2_journal_free_reserved(handle);
+
+		if (test_opt(sb, DATA_ERR_ABORT))
+			jbd2_journal_abort(EXT4_SB(sb)->s_journal, ret);
+	} else {
+		ret = ext4_convert_unwritten_io_end_vec(handle, io_end);
+	}
+	if (ret < 0 && !ext4_emergency_state(sb) &&
+	    io_end->flag & EXT4_IO_END_UNWRITTEN) {
+		ext4_msg(sb, KERN_EMERG,
+			 "failed to convert unwritten extents to written "
+			 "extents -- potential data loss!  "
+			 "(inode %llu, error %d)", inode->i_ino, ret);
+	}
+
+	ext4_clear_io_unwritten_flag(io_end);
+	ext4_release_io_end(io_end);
+	return ret;
+}
+
+static void dump_completed_IO(struct inode *inode, struct list_head *head)
+{
+#ifdef	EXT4FS_DEBUG
+	struct list_head *cur, *before, *after;
+	ext4_io_end_t *io_end, *io_end0, *io_end1;
+
+	if (list_empty(head))
+		return;
+
+	ext4_debug("Dump inode %llu completed io list\n", inode->i_ino);
+	list_for_each_entry(io_end, head, list) {
+		cur = &io_end->list;
+		before = cur->prev;
+		io_end0 = container_of(before, ext4_io_end_t, list);
+		after = cur->next;
+		io_end1 = container_of(after, ext4_io_end_t, list);
+
+		ext4_debug("io 0x%p from inode %llu,prev 0x%p,next 0x%p\n",
+			    io_end, inode->i_ino, io_end0, io_end1);
+	}
+#endif
+}
+
+static bool ext4_io_end_defer_completion(ext4_io_end_t *io_end)
+{
+	if (io_end->flag & EXT4_IO_END_UNWRITTEN &&
+	    !list_empty(&io_end->list_vec))
+		return true;
+	if (test_opt(io_end->inode->i_sb, DATA_ERR_ABORT) &&
+	    io_end->flag & EXT4_IO_END_FAILED &&
+	    !ext4_emergency_state(io_end->inode->i_sb))
+		return true;
+	return false;
+}
+
+/* Add the io_end to per-inode completed end_io list. */
+static void ext4_add_complete_io(ext4_io_end_t *io_end)
+{
+	struct ext4_inode_info *ei = EXT4_I(io_end->inode);
+	struct ext4_sb_info *sbi = EXT4_SB(io_end->inode->i_sb);
+	struct workqueue_struct *wq;
+	unsigned long flags;
+
+	/* Only reserved conversions or pending IO errors will enter here. */
+	WARN_ON(!(io_end->flag & EXT4_IO_END_DEFER_COMPLETION));
+	WARN_ON(io_end->flag & EXT4_IO_END_UNWRITTEN &&
+		!io_end->handle && sbi->s_journal);
+	WARN_ON(!io_end->bio);
+
+	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+	wq = sbi->rsv_conversion_wq;
+	if (list_empty(&ei->i_rsv_conversion_list))
+		queue_work(wq, &ei->i_rsv_conversion_work);
+	list_add_tail(&io_end->list, &ei->i_rsv_conversion_list);
+	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+}
+
+static int ext4_do_flush_completed_IO(struct inode *inode,
+				      struct list_head *head)
+{
+	ext4_io_end_t *io_end;
+	struct list_head unwritten;
+	unsigned long flags;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	int err, ret = 0;
+
+	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+	dump_completed_IO(inode, head);
+	list_replace_init(head, &unwritten);
+	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+
+	while (!list_empty(&unwritten)) {
+		io_end = list_entry(unwritten.next, ext4_io_end_t, list);
+		BUG_ON(!(io_end->flag & EXT4_IO_END_DEFER_COMPLETION));
+		list_del_init(&io_end->list);
+
+		err = ext4_end_io_end(io_end);
+		if (unlikely(!ret && err))
+			ret = err;
+	}
+	return ret;
+}
+
+/*
+ * Used to convert unwritten extents to written extents upon IO completion,
+ * or used to abort the journal upon IO errors.
+ */
+void ext4_end_io_rsv_work(struct work_struct *work)
+{
+	struct ext4_inode_info *ei = container_of(work, struct ext4_inode_info,
+						  i_rsv_conversion_work);
+	ext4_do_flush_completed_IO(&ei->vfs_inode, &ei->i_rsv_conversion_list);
+}
+
+ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
+{
+	ext4_io_end_t *io_end = kmem_cache_zalloc(io_end_cachep, flags);
+
+	if (io_end) {
+		io_end->inode = inode;
+		INIT_LIST_HEAD(&io_end->list);
+		INIT_LIST_HEAD(&io_end->list_vec);
+		refcount_set(&io_end->count, 1);
+	}
+	return io_end;
+}
+
+void ext4_put_io_end_defer(ext4_io_end_t *io_end)
+{
+	if (refcount_dec_and_test(&io_end->count)) {
+		if (ext4_io_end_defer_completion(io_end))
+			return ext4_add_complete_io(io_end);
+
+		ext4_release_io_end(io_end);
+	}
+}
+
+int ext4_put_io_end(ext4_io_end_t *io_end)
+{
+	if (refcount_dec_and_test(&io_end->count)) {
+		if (ext4_io_end_defer_completion(io_end))
+			return ext4_end_io_end(io_end);
+
+		ext4_release_io_end(io_end);
+	}
+	return 0;
+}
+
+ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end)
+{
+	refcount_inc(&io_end->count);
+	return io_end;
+}
+
+/* BIO completion function for page writeback */
+static void ext4_end_bio(struct bio *bio)
+{
+	ext4_io_end_t *io_end = bio->bi_private;
+	sector_t bi_sector = bio->bi_iter.bi_sector;
+
+	if (WARN_ONCE(!io_end, "io_end is NULL: %pg: sector %Lu len %u err %d\n",
+		      bio->bi_bdev,
+		      (long long) bio->bi_iter.bi_sector,
+		      (unsigned) bio_sectors(bio),
+		      bio->bi_status)) {
+		ext4_finish_bio(bio);
+		bio_put(bio);
+		return;
+	}
+	bio->bi_end_io = NULL;
+
+	if (bio->bi_status) {
+		struct inode *inode = io_end->inode;
+
+		ext4_warning(inode->i_sb, "I/O error %d writing to inode %llu "
+			     "starting block %llu)",
+			     bio->bi_status, inode->i_ino,
+			     (unsigned long long)
+			     bi_sector >> (inode->i_blkbits - 9));
+		io_end->flag |= EXT4_IO_END_FAILED;
+		mapping_set_error(inode->i_mapping,
+				blk_status_to_errno(bio->bi_status));
+	}
+
+	if (ext4_io_end_defer_completion(io_end)) {
+		/*
+		 * Link bio into list hanging from io_end. We have to do it
+		 * atomically as bio completions can be racing against each
+		 * other.
+		 */
+		bio->bi_private = xchg(&io_end->bio, bio);
+		ext4_put_io_end_defer(io_end);
+	} else {
+		/*
+		 * Drop io_end reference early. Inode can get freed once
+		 * we finish the bio.
+		 */
+		ext4_put_io_end_defer(io_end);
+		ext4_finish_bio(bio);
+		bio_put(bio);
+	}
+}
+
+void ext4_io_submit(struct ext4_io_submit *io)
+{
+	struct bio *bio = io->io_bio;
+
+	if (bio) {
+		if (io->io_wbc->sync_mode == WB_SYNC_ALL)
+			io->io_bio->bi_opf |= REQ_SYNC;
+		blk_crypto_submit_bio(io->io_bio);
+	}
+	io->io_bio = NULL;
+}
+
+void ext4_io_submit_init(struct ext4_io_submit *io,
+			 struct writeback_control *wbc)
+{
+	io->io_wbc = wbc;
+	io->io_bio = NULL;
+	io->io_end = NULL;
+}
+
+static void io_submit_init_bio(struct ext4_io_submit *io,
+			       struct inode *inode,
+			       struct folio *folio,
+			       struct buffer_head *bh)
+{
+	struct bio *bio;
+
+	/*
+	 * bio_alloc will _always_ be able to allocate a bio if
+	 * __GFP_DIRECT_RECLAIM is set, see comments for bio_alloc_bioset().
+	 */
+	bio = bio_alloc(bh->b_bdev, BIO_MAX_VECS, REQ_OP_WRITE, GFP_NOIO);
+	fscrypt_set_bio_crypt_ctx(bio, inode, folio_pos(folio) + bh_offset(bh),
+				  GFP_NOIO);
+	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+	bio->bi_end_io = ext4_end_bio;
+	bio->bi_private = ext4_get_io_end(io->io_end);
+	bio->bi_write_hint = inode->i_write_hint;
+	io->io_bio = bio;
+	io->io_next_block = bh->b_blocknr;
+	wbc_init_bio(io->io_wbc, bio);
+}
+
+static bool io_submit_need_new_bio(struct ext4_io_submit *io,
+				   struct inode *inode,
+				   struct folio *folio,
+				   struct buffer_head *bh)
+{
+	if (bh->b_blocknr != io->io_next_block)
+		return true;
+	if (!fscrypt_mergeable_bio(io->io_bio, inode,
+			folio_pos(folio) + bh_offset(bh)))
+		return true;
+	return false;
+}
+
+static void io_submit_add_bh(struct ext4_io_submit *io,
+			     struct inode *inode,
+			     struct folio *folio,
+			     struct folio *io_folio,
+			     struct buffer_head *bh)
+{
+	if (io->io_bio && io_submit_need_new_bio(io, inode, folio, bh)) {
+submit_and_retry:
+		ext4_io_submit(io);
+	}
+	if (io->io_bio == NULL)
+		io_submit_init_bio(io, inode, folio, bh);
+	if (!bio_add_folio(io->io_bio, io_folio, bh->b_size, bh_offset(bh)))
+		goto submit_and_retry;
+	wbc_account_cgroup_owner(io->io_wbc, folio, bh->b_size);
+	io->io_next_block++;
+}
+
+int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *folio,
+		size_t len)
+{
+	struct folio *io_folio = folio;
+	struct inode *inode = folio->mapping->host;
+	unsigned block_start;
+	struct buffer_head *bh, *head;
+	int ret = 0;
+	int nr_to_submit = 0;
+	struct writeback_control *wbc = io->io_wbc;
+	bool keep_towrite = false;
+
+	BUG_ON(!folio_test_locked(folio));
+	BUG_ON(folio_test_writeback(folio));
+
+	/*
+	 * Comments copied from block_write_full_folio:
+	 *
+	 * The folio straddles i_size.  It must be zeroed out on each and every
+	 * writepage invocation because it may be mmapped.  "A file is mapped
+	 * in multiples of the page size.  For a file that is not a multiple of
+	 * the page size, the remaining memory is zeroed when mapped, and
+	 * writes to that region are not written out to the file."
+	 */
+	if (len < folio_size(folio))
+		folio_zero_segment(folio, len, folio_size(folio));
+	/*
+	 * In the first loop we prepare and mark buffers to submit. We have to
+	 * mark all buffers in the folio before submitting so that
+	 * folio_end_writeback() cannot be called from ext4_end_bio() when IO
+	 * on the first buffer finishes and we are still working on submitting
+	 * the second buffer.
+	 */
+	bh = head = folio_buffers(folio);
+	do {
+		block_start = bh_offset(bh);
+		if (block_start >= len) {
+			clear_buffer_dirty(bh);
+			set_buffer_uptodate(bh);
+			continue;
+		}
+		if (!buffer_dirty(bh) || buffer_delay(bh) ||
+		    !buffer_mapped(bh) || buffer_unwritten(bh)) {
+			/* A hole? We can safely clear the dirty bit */
+			if (!buffer_mapped(bh))
+				clear_buffer_dirty(bh);
+			/*
+			 * Keeping dirty some buffer we cannot write? Make sure
+			 * to redirty the folio and keep TOWRITE tag so that
+			 * racing WB_SYNC_ALL writeback does not skip the folio.
+			 * This happens e.g. when doing writeout for
+			 * transaction commit or when journalled data is not
+			 * yet committed.
+			 */
+			if (buffer_dirty(bh) ||
+			    (buffer_jbd(bh) && buffer_jbddirty(bh))) {
+				if (!folio_test_dirty(folio))
+					folio_redirty_for_writepage(wbc, folio);
+				keep_towrite = true;
+			}
+			continue;
+		}
+		if (buffer_new(bh))
+			clear_buffer_new(bh);
+		set_buffer_async_write(bh);
+		clear_buffer_dirty(bh);
+		nr_to_submit++;
+	} while ((bh = bh->b_this_page) != head);
+
+	if (!nr_to_submit) {
+		/*
+		 * We have nothing to submit. Just cycle the folio through
+		 * writeback state to properly update xarray tags.
+		 */
+		__folio_start_writeback(folio, keep_towrite);
+		folio_end_writeback(folio);
+		return 0;
+	}
+
+	bh = head = folio_buffers(folio);
+
+	/*
+	 * If any blocks are being written to an encrypted file, encrypt them
+	 * into a bounce page.  For simplicity, just encrypt until the last
+	 * block which might be needed.  This may cause some unneeded blocks
+	 * (e.g. holes) to be unnecessarily encrypted, but this is rare and
+	 * can't happen in the common case of blocksize == PAGE_SIZE.
+	 */
+	if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
+		gfp_t gfp_flags = GFP_NOFS;
+		unsigned int enc_bytes = round_up(len, i_blocksize(inode));
+		struct page *bounce_page;
+
+		/*
+		 * Since bounce page allocation uses a mempool, we can only use
+		 * a waiting mask (i.e. request guaranteed allocation) on the
+		 * first page of the bio.  Otherwise it can deadlock.
+		 */
+		if (io->io_bio)
+			gfp_flags = GFP_NOWAIT;
+	retry_encrypt:
+		bounce_page = fscrypt_encrypt_pagecache_blocks(folio,
+					enc_bytes, 0, gfp_flags);
+		if (IS_ERR(bounce_page)) {
+			ret = PTR_ERR(bounce_page);
+			if (ret == -ENOMEM &&
+			    (io->io_bio || wbc->sync_mode == WB_SYNC_ALL)) {
+				gfp_t new_gfp_flags = GFP_NOFS;
+				if (io->io_bio)
+					ext4_io_submit(io);
+				else
+					new_gfp_flags |= __GFP_NOFAIL;
+				memalloc_retry_wait(gfp_flags);
+				gfp_flags = new_gfp_flags;
+				goto retry_encrypt;
+			}
+
+			printk_ratelimited(KERN_ERR "%s: ret = %d\n", __func__, ret);
+			folio_redirty_for_writepage(wbc, folio);
+			do {
+				if (buffer_async_write(bh)) {
+					clear_buffer_async_write(bh);
+					set_buffer_dirty(bh);
+				}
+				bh = bh->b_this_page;
+			} while (bh != head);
+
+			return ret;
+		}
+		io_folio = page_folio(bounce_page);
+	}
+
+	__folio_start_writeback(folio, keep_towrite);
+
+	/* Now submit buffers to write */
+	do {
+		if (!buffer_async_write(bh))
+			continue;
+		io_submit_add_bh(io, inode, folio, io_folio, bh);
+	} while ((bh = bh->b_this_page) != head);
+
+	return 0;
+}

linux-7.2.3/fs/ext4/readpage.c

@@ -0,0 +1,455 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/fs/ext4/readpage.c
+ *
+ * Copyright (C) 2002, Linus Torvalds.
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This was originally taken from fs/mpage.c
+ *
+ * The ext4_mpage_readpages() function here is intended to
+ * replace mpage_readahead() in the general case, not just for
+ * encrypted files.  It has some limitations (see below), where it
+ * will fall back to read_block_full_page(), but these limitations
+ * should only be hit when page_size != block_size.
+ *
+ * This will allow us to attach a callback function to support ext4
+ * encryption.
+ *
+ * If anything unusual happens, such as:
+ *
+ * - encountering a page which has buffers
+ * - encountering a page which has a non-hole after a hole
+ * - encountering a page with non-contiguous blocks
+ *
+ * then this code just gives up and calls the buffer_head-based read function.
+ * It does handle a page which has holes at the end - that is a common case:
+ * the end-of-file on blocksize < PAGE_SIZE setups.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/kdev_t.h>
+#include <linux/gfp.h>
+#include <linux/bio.h>
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/blk-crypto.h>
+#include <linux/blkdev.h>
+#include <linux/highmem.h>
+#include <linux/prefetch.h>
+#include <linux/mpage.h>
+#include <linux/writeback.h>
+#include <linux/backing-dev.h>
+
+#include "ext4.h"
+#include <trace/events/ext4.h>
+
+#define NUM_PREALLOC_POST_READ_CTXS	128
+
+static struct kmem_cache *bio_post_read_ctx_cache;
+static mempool_t *bio_post_read_ctx_pool;
+
+/* postprocessing steps for read bios */
+enum bio_post_read_step {
+	STEP_INITIAL = 0,
+	STEP_DECRYPT,
+	STEP_VERITY,
+	STEP_MAX,
+};
+
+struct bio_post_read_ctx {
+	struct bio *bio;
+	struct fsverity_info *vi;
+	struct work_struct work;
+	unsigned int cur_step;
+	unsigned int enabled_steps;
+};
+
+static void __read_end_io(struct bio *bio)
+{
+	struct folio_iter fi;
+
+	bio_for_each_folio_all(fi, bio)
+		folio_end_read(fi.folio, bio->bi_status == 0);
+	if (bio->bi_private)
+		mempool_free(bio->bi_private, bio_post_read_ctx_pool);
+	bio_put(bio);
+}
+
+static void bio_post_read_processing(struct bio_post_read_ctx *ctx);
+
+static void decrypt_work(struct work_struct *work)
+{
+	struct bio_post_read_ctx *ctx =
+		container_of(work, struct bio_post_read_ctx, work);
+	struct bio *bio = ctx->bio;
+
+	if (fscrypt_decrypt_bio(bio))
+		bio_post_read_processing(ctx);
+	else
+		__read_end_io(bio);
+}
+
+static void verity_work(struct work_struct *work)
+{
+	struct bio_post_read_ctx *ctx =
+		container_of(work, struct bio_post_read_ctx, work);
+	struct bio *bio = ctx->bio;
+	struct fsverity_info *vi = ctx->vi;
+
+	/*
+	 * fsverity_verify_bio() may call readahead() again, and although verity
+	 * will be disabled for that, decryption may still be needed, causing
+	 * another bio_post_read_ctx to be allocated.  So to guarantee that
+	 * mempool_alloc() never deadlocks we must free the current ctx first.
+	 * This is safe because verity is the last post-read step.
+	 */
+	BUILD_BUG_ON(STEP_VERITY + 1 != STEP_MAX);
+	mempool_free(ctx, bio_post_read_ctx_pool);
+	bio->bi_private = NULL;
+
+	fsverity_verify_bio(vi, bio);
+
+	__read_end_io(bio);
+}
+
+static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
+{
+	/*
+	 * We use different work queues for decryption and for verity because
+	 * verity may require reading metadata pages that need decryption, and
+	 * we shouldn't recurse to the same workqueue.
+	 */
+	switch (++ctx->cur_step) {
+	case STEP_DECRYPT:
+		if (ctx->enabled_steps & (1 << STEP_DECRYPT)) {
+			INIT_WORK(&ctx->work, decrypt_work);
+			fscrypt_enqueue_decrypt_work(&ctx->work);
+			return;
+		}
+		ctx->cur_step++;
+		fallthrough;
+	case STEP_VERITY:
+		if (IS_ENABLED(CONFIG_FS_VERITY) &&
+		    ctx->enabled_steps & (1 << STEP_VERITY)) {
+			INIT_WORK(&ctx->work, verity_work);
+			fsverity_enqueue_verify_work(&ctx->work);
+			return;
+		}
+		ctx->cur_step++;
+		fallthrough;
+	default:
+		__read_end_io(ctx->bio);
+	}
+}
+
+static bool bio_post_read_required(struct bio *bio)
+{
+	return bio->bi_private && !bio->bi_status;
+}
+
+/*
+ * I/O completion handler for multipage BIOs.
+ *
+ * The mpage code never puts partial pages into a BIO (except for end-of-file).
+ * If a page does not map to a contiguous run of blocks then it simply falls
+ * back to block_read_full_folio().
+ *
+ * Why is this?  If a page's completion depends on a number of different BIOs
+ * which can complete in any order (or at the same time) then determining the
+ * status of that page is hard.  See end_buffer_async_read() for the details.
+ * There is no point in duplicating all that complexity.
+ */
+static void mpage_end_io(struct bio *bio)
+{
+	if (bio_post_read_required(bio)) {
+		struct bio_post_read_ctx *ctx = bio->bi_private;
+
+		ctx->cur_step = STEP_INITIAL;
+		bio_post_read_processing(ctx);
+		return;
+	}
+	__read_end_io(bio);
+}
+
+static void ext4_set_bio_post_read_ctx(struct bio *bio,
+				       const struct inode *inode,
+				       struct fsverity_info *vi)
+{
+	unsigned int post_read_steps = 0;
+
+	if (fscrypt_inode_uses_fs_layer_crypto(inode))
+		post_read_steps |= 1 << STEP_DECRYPT;
+
+	if (vi)
+		post_read_steps |= 1 << STEP_VERITY;
+
+	if (post_read_steps) {
+		/* Due to the mempool, this never fails. */
+		struct bio_post_read_ctx *ctx =
+			mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS);
+
+		ctx->bio = bio;
+		ctx->vi = vi;
+		ctx->enabled_steps = post_read_steps;
+		bio->bi_private = ctx;
+	}
+}
+
+static inline loff_t ext4_readpage_limit(struct inode *inode)
+{
+	if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode))
+		return inode->i_sb->s_maxbytes;
+
+	return i_size_read(inode);
+}
+
+static int ext4_mpage_readpages(struct inode *inode, struct fsverity_info *vi,
+		struct readahead_control *rac, struct folio *folio)
+{
+	struct bio *bio = NULL;
+	sector_t last_block_in_bio = 0;
+	const unsigned blkbits = inode->i_blkbits;
+	const unsigned blocksize = 1 << blkbits;
+	sector_t block_in_file;
+	sector_t last_block;
+	sector_t last_block_in_file;
+	sector_t first_block;
+	loff_t pos;
+	unsigned page_block;
+	struct block_device *bdev = inode->i_sb->s_bdev;
+	int length;
+	unsigned relative_block = 0;
+	struct ext4_map_blocks map;
+	unsigned int nr_pages, folio_pages;
+
+	map.m_pblk = 0;
+	map.m_lblk = 0;
+	map.m_len = 0;
+	map.m_flags = 0;
+
+	nr_pages = rac ? readahead_count(rac) : folio_nr_pages(folio);
+	for (; nr_pages; nr_pages -= folio_pages) {
+		int fully_mapped = 1;
+		unsigned int first_hole;
+		unsigned int blocks_per_folio;
+
+		if (rac)
+			folio = readahead_folio(rac);
+
+		folio_pages = folio_nr_pages(folio);
+		prefetchw(&folio->flags);
+
+		if (folio_buffers(folio))
+			goto confused;
+
+		blocks_per_folio = folio_size(folio) >> blkbits;
+		first_hole = blocks_per_folio;
+		pos = folio_pos(folio);
+		block_in_file = pos >> blkbits;
+		last_block = EXT4_PG_TO_LBLK(inode, folio->index + nr_pages);
+		last_block_in_file = (ext4_readpage_limit(inode) +
+				      blocksize - 1) >> blkbits;
+		if (last_block > last_block_in_file)
+			last_block = last_block_in_file;
+		page_block = 0;
+
+		/*
+		 * Map blocks using the previous result first.
+		 */
+		if ((map.m_flags & EXT4_MAP_MAPPED) &&
+		    block_in_file > map.m_lblk &&
+		    block_in_file < (map.m_lblk + map.m_len)) {
+			unsigned map_offset = block_in_file - map.m_lblk;
+			unsigned last = map.m_len - map_offset;
+
+			first_block = map.m_pblk + map_offset;
+			for (relative_block = 0; ; relative_block++) {
+				if (relative_block == last) {
+					/* needed? */
+					map.m_flags &= ~EXT4_MAP_MAPPED;
+					break;
+				}
+				if (page_block == blocks_per_folio)
+					break;
+				page_block++;
+				block_in_file++;
+			}
+		}
+
+		/*
+		 * Then do more ext4_map_blocks() calls until we are
+		 * done with this folio.
+		 */
+		while (page_block < blocks_per_folio) {
+			if (block_in_file < last_block) {
+				map.m_lblk = block_in_file;
+				map.m_len = last_block - block_in_file;
+
+				if (ext4_map_blocks(NULL, inode, &map, 0) < 0) {
+				set_error_page:
+					folio_zero_segment(folio, 0,
+							  folio_size(folio));
+					folio_unlock(folio);
+					goto next_page;
+				}
+			}
+			if ((map.m_flags & EXT4_MAP_MAPPED) == 0) {
+				fully_mapped = 0;
+				if (first_hole == blocks_per_folio)
+					first_hole = page_block;
+				page_block++;
+				block_in_file++;
+				continue;
+			}
+			if (first_hole != blocks_per_folio)
+				goto confused;		/* hole -> non-hole */
+
+			/* Contiguous blocks? */
+			if (!page_block)
+				first_block = map.m_pblk;
+			else if (first_block + page_block != map.m_pblk)
+				goto confused;
+			for (relative_block = 0; ; relative_block++) {
+				if (relative_block == map.m_len) {
+					/* needed? */
+					map.m_flags &= ~EXT4_MAP_MAPPED;
+					break;
+				} else if (page_block == blocks_per_folio)
+					break;
+				page_block++;
+				block_in_file++;
+			}
+		}
+		if (first_hole != blocks_per_folio) {
+			folio_zero_segment(folio, first_hole << blkbits,
+					  folio_size(folio));
+			if (first_hole == 0) {
+				if (vi && !fsverity_verify_folio(vi, folio))
+					goto set_error_page;
+				folio_end_read(folio, true);
+				continue;
+			}
+		} else if (fully_mapped) {
+			folio_set_mappedtodisk(folio);
+		}
+
+		/*
+		 * This folio will go to BIO.  Do we need to send this
+		 * BIO off first?
+		 */
+		if (bio && (last_block_in_bio != first_block - 1 ||
+			    !fscrypt_mergeable_bio(bio, inode, pos))) {
+		submit_and_realloc:
+			blk_crypto_submit_bio(bio);
+			bio = NULL;
+		}
+		if (bio == NULL) {
+			/*
+			 * bio_alloc will _always_ be able to allocate a bio if
+			 * __GFP_DIRECT_RECLAIM is set, see bio_alloc_bioset().
+			 */
+			bio = bio_alloc(bdev, bio_max_segs(nr_pages),
+					REQ_OP_READ, GFP_KERNEL);
+			fscrypt_set_bio_crypt_ctx(bio, inode, pos, GFP_KERNEL);
+			ext4_set_bio_post_read_ctx(bio, inode, vi);
+			bio->bi_iter.bi_sector = first_block << (blkbits - 9);
+			bio->bi_end_io = mpage_end_io;
+			if (rac)
+				bio->bi_opf |= REQ_RAHEAD;
+		}
+
+		length = first_hole << blkbits;
+		if (!bio_add_folio(bio, folio, length, 0))
+			goto submit_and_realloc;
+
+		if (((map.m_flags & EXT4_MAP_BOUNDARY) &&
+		     (relative_block == map.m_len)) ||
+		    (first_hole != blocks_per_folio)) {
+			blk_crypto_submit_bio(bio);
+			bio = NULL;
+		} else
+			last_block_in_bio = first_block + blocks_per_folio - 1;
+		continue;
+	confused:
+		if (bio) {
+			blk_crypto_submit_bio(bio);
+			bio = NULL;
+		}
+		if (!folio_test_uptodate(folio))
+			block_read_full_folio(folio, ext4_get_block);
+		else
+			folio_unlock(folio);
+next_page:
+		; /* A label shall be followed by a statement until C23 */
+	}
+	if (bio)
+		blk_crypto_submit_bio(bio);
+	return 0;
+}
+
+int ext4_read_folio(struct file *file, struct folio *folio)
+{
+	struct inode *inode = folio->mapping->host;
+	struct fsverity_info *vi = NULL;
+	int ret;
+
+	trace_ext4_read_folio(inode, folio);
+
+	if (ext4_has_inline_data(inode)) {
+		ret = ext4_readpage_inline(inode, folio);
+		if (ret != -EAGAIN)
+			return ret;
+	}
+
+	if (folio->index < DIV_ROUND_UP(inode->i_size, PAGE_SIZE))
+		vi = fsverity_get_info(inode);
+	if (vi)
+		fsverity_readahead(vi, folio->index, folio_nr_pages(folio));
+	return ext4_mpage_readpages(inode, vi, NULL, folio);
+}
+
+void ext4_readahead(struct readahead_control *rac)
+{
+	struct inode *inode = rac->mapping->host;
+	struct fsverity_info *vi = NULL;
+
+	/* If the file has inline data, no need to do readahead. */
+	if (ext4_has_inline_data(inode))
+		return;
+
+	if (readahead_index(rac) < DIV_ROUND_UP(inode->i_size, PAGE_SIZE))
+		vi = fsverity_get_info(inode);
+	if (vi)
+		fsverity_readahead(vi, readahead_index(rac),
+				   readahead_count(rac));
+	ext4_mpage_readpages(inode, vi, rac, NULL);
+}
+
+int __init ext4_init_post_read_processing(void)
+{
+	bio_post_read_ctx_cache = KMEM_CACHE(bio_post_read_ctx, SLAB_RECLAIM_ACCOUNT);
+
+	if (!bio_post_read_ctx_cache)
+		goto fail;
+	bio_post_read_ctx_pool =
+		mempool_create_slab_pool(NUM_PREALLOC_POST_READ_CTXS,
+					 bio_post_read_ctx_cache);
+	if (!bio_post_read_ctx_pool)
+		goto fail_free_cache;
+	return 0;
+
+fail_free_cache:
+	kmem_cache_destroy(bio_post_read_ctx_cache);
+fail:
+	return -ENOMEM;
+}
+
+void ext4_exit_post_read_processing(void)
+{
+	mempool_destroy(bio_post_read_ctx_pool);
+	kmem_cache_destroy(bio_post_read_ctx_cache);
+}

linux-7.2.3/fs/ext4/symlink.c

@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/ext4/symlink.c
+ *
+ * Only fast symlinks left here - the rest is done by generic code. AV, 1999
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  from
+ *
+ *  linux/fs/minix/symlink.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  ext4 symlink handling code
+ */
+
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include "ext4.h"
+#include "xattr.h"
+
+static const char *ext4_encrypted_get_link(struct dentry *dentry,
+					   struct inode *inode,
+					   struct delayed_call *done)
+{
+	struct buffer_head *bh = NULL;
+	const void *caddr;
+	unsigned int max_size;
+	const char *paddr;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	if (ext4_inode_is_fast_symlink(inode)) {
+		caddr = EXT4_I(inode)->i_data;
+		max_size = sizeof(EXT4_I(inode)->i_data);
+	} else {
+		bh = ext4_bread(NULL, inode, 0, 0);
+		if (IS_ERR(bh))
+			return ERR_CAST(bh);
+		if (!bh) {
+			EXT4_ERROR_INODE(inode, "bad symlink.");
+			return ERR_PTR(-EFSCORRUPTED);
+		}
+		caddr = bh->b_data;
+		max_size = inode->i_sb->s_blocksize;
+	}
+
+	paddr = fscrypt_get_symlink(inode, caddr, max_size, done);
+	brelse(bh);
+	return paddr;
+}
+
+static int ext4_encrypted_symlink_getattr(struct mnt_idmap *idmap,
+					  const struct path *path,
+					  struct kstat *stat, u32 request_mask,
+					  unsigned int query_flags)
+{
+	ext4_getattr(idmap, path, stat, request_mask, query_flags);
+
+	return fscrypt_symlink_getattr(path, stat);
+}
+
+static void ext4_free_link(void *bh)
+{
+	brelse(bh);
+}
+
+static const char *ext4_get_link(struct dentry *dentry, struct inode *inode,
+				 struct delayed_call *callback)
+{
+	struct buffer_head *bh;
+	char *inline_link;
+
+	/*
+	 * Create a new inlined symlink is not supported, just provide a
+	 * method to read the leftovers.
+	 */
+	if (ext4_has_inline_data(inode)) {
+		if (!dentry)
+			return ERR_PTR(-ECHILD);
+
+		inline_link = ext4_read_inline_link(inode);
+		if (!IS_ERR(inline_link))
+			set_delayed_call(callback, kfree_link, inline_link);
+		return inline_link;
+	}
+
+	if (!dentry) {
+		bh = ext4_getblk(NULL, inode, 0, EXT4_GET_BLOCKS_CACHED_NOWAIT);
+		if (IS_ERR_OR_NULL(bh))
+			return ERR_PTR(-ECHILD);
+		if (!ext4_buffer_uptodate(bh)) {
+			brelse(bh);
+			return ERR_PTR(-ECHILD);
+		}
+	} else {
+		bh = ext4_bread(NULL, inode, 0, 0);
+		if (IS_ERR(bh))
+			return ERR_CAST(bh);
+		if (!bh) {
+			EXT4_ERROR_INODE(inode, "bad symlink.");
+			return ERR_PTR(-EFSCORRUPTED);
+		}
+	}
+
+	set_delayed_call(callback, ext4_free_link, bh);
+	nd_terminate_link(bh->b_data, inode->i_size,
+			  inode->i_sb->s_blocksize - 1);
+	return bh->b_data;
+}
+
+const struct inode_operations ext4_encrypted_symlink_inode_operations = {
+	.get_link	= ext4_encrypted_get_link,
+	.setattr	= ext4_setattr,
+	.getattr	= ext4_encrypted_symlink_getattr,
+	.listxattr	= ext4_listxattr,
+};
+
+const struct inode_operations ext4_symlink_inode_operations = {
+	.get_link	= ext4_get_link,
+	.setattr	= ext4_setattr,
+	.getattr	= ext4_getattr,
+	.listxattr	= ext4_listxattr,
+};
+
+const struct inode_operations ext4_fast_symlink_inode_operations = {
+	.get_link	= simple_get_link,
+	.setattr	= ext4_setattr,
+	.getattr	= ext4_getattr,
+	.listxattr	= ext4_listxattr,
+};

linux-7.2.3/fs/ext4/sysfs.c

@@ -0,0 +1,698 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/ext4/sysfs.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Theodore Ts'o (tytso@mit.edu)
+ *
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/proc_fs.h>
+#include <linux/part_stat.h>
+
+#include "ext4.h"
+#include "ext4_jbd2.h"
+
+typedef enum {
+	attr_noop,
+	attr_delayed_allocation_blocks,
+	attr_session_write_kbytes,
+	attr_lifetime_write_kbytes,
+	attr_reserved_clusters,
+	attr_sra_exceeded_retry_limit,
+	attr_inode_readahead,
+	attr_trigger_test_error,
+	attr_first_error_time,
+	attr_last_error_time,
+	attr_clusters_in_group,
+	attr_mb_order,
+	attr_feature,
+	attr_pointer_pi,
+	attr_pointer_ui,
+	attr_pointer_ul,
+	attr_pointer_u64,
+	attr_pointer_u8,
+	attr_pointer_string,
+	attr_pointer_atomic,
+	attr_journal_task,
+	attr_err_report_sec,
+} attr_id_t;
+
+typedef enum {
+	ptr_explicit,
+	ptr_ext4_sb_info_offset,
+	ptr_ext4_super_block_offset,
+} attr_ptr_t;
+
+static const char proc_dirname[] = "fs/ext4";
+static struct proc_dir_entry *ext4_proc_root;
+
+struct ext4_attr {
+	struct attribute attr;
+	short attr_id;
+	short attr_ptr;
+	unsigned short attr_size;
+	union {
+		int offset;
+		void *explicit_ptr;
+	} u;
+};
+
+static ssize_t session_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
+{
+	struct super_block *sb = sbi->s_buddy_cache->i_sb;
+
+	return sysfs_emit(buf, "%lu\n",
+			(part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
+			 sbi->s_sectors_written_start) >> 1);
+}
+
+static ssize_t lifetime_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
+{
+	struct super_block *sb = sbi->s_buddy_cache->i_sb;
+
+	return sysfs_emit(buf, "%llu\n",
+			(unsigned long long)(sbi->s_kbytes_written +
+			((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
+			  EXT4_SB(sb)->s_sectors_written_start) >> 1)));
+}
+
+static ssize_t inode_readahead_blks_store(struct ext4_sb_info *sbi,
+					  const char *buf, size_t count)
+{
+	unsigned long t;
+	int ret;
+
+	ret = kstrtoul(skip_spaces(buf), 0, &t);
+	if (ret)
+		return ret;
+
+	if (t && (!is_power_of_2(t) || t > 0x40000000))
+		return -EINVAL;
+
+	sbi->s_inode_readahead_blks = t;
+	return count;
+}
+
+static ssize_t reserved_clusters_store(struct ext4_sb_info *sbi,
+				   const char *buf, size_t count)
+{
+	unsigned long long val;
+	ext4_fsblk_t clusters = (ext4_blocks_count(sbi->s_es) >>
+				 sbi->s_cluster_bits);
+	int ret;
+
+	ret = kstrtoull(skip_spaces(buf), 0, &val);
+	if (ret || val >= clusters || (s64)val < 0)
+		return -EINVAL;
+
+	atomic64_set(&sbi->s_resv_clusters, val);
+	return count;
+}
+
+static ssize_t trigger_test_error(struct ext4_sb_info *sbi,
+				  const char *buf, size_t count)
+{
+	int len = count;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (len && buf[len-1] == '\n')
+		len--;
+
+	if (len)
+		ext4_error(sbi->s_sb, "%.*s", len, buf);
+	return count;
+}
+
+static ssize_t err_report_sec_store(struct ext4_sb_info *sbi,
+				    const char *buf, size_t count)
+{
+	unsigned long t;
+	int ret;
+
+	ret = kstrtoul(skip_spaces(buf), 0, &t);
+	if (ret)
+		return ret;
+
+	/*the maximum time interval must not exceed one year.*/
+	if (t > (365*24*60*60))
+		return -EINVAL;
+
+	if (sbi->s_err_report_sec == t)		/*nothing to do*/
+		goto out;
+	else if (!sbi->s_err_report_sec && t) {
+		timer_setup(&sbi->s_err_report, print_daily_error_info, 0);
+	} else if (sbi->s_err_report_sec && !t) {
+		timer_delete_sync(&sbi->s_err_report);
+		goto out;
+	}
+
+	sbi->s_err_report_sec = t;
+	mod_timer(&sbi->s_err_report, jiffies + secs_to_jiffies(sbi->s_err_report_sec));
+
+out:
+	return count;
+}
+
+static ssize_t journal_task_show(struct ext4_sb_info *sbi, char *buf)
+{
+	if (!sbi->s_journal)
+		return sysfs_emit(buf, "<none>\n");
+	return sysfs_emit(buf, "%d\n",
+			task_pid_vnr(sbi->s_journal->j_task));
+}
+
+#define EXT4_ATTR(_name,_mode,_id)					\
+static struct ext4_attr ext4_attr_##_name = {				\
+	.attr = {.name = __stringify(_name), .mode = _mode },		\
+	.attr_id = attr_##_id,						\
+}
+
+#define EXT4_ATTR_FUNC(_name,_mode)  EXT4_ATTR(_name,_mode,_name)
+
+#define EXT4_ATTR_FEATURE(_name)   EXT4_ATTR(_name, 0444, feature)
+
+#define EXT4_ATTR_OFFSET(_name,_mode,_id,_struct,_elname)	\
+static struct ext4_attr ext4_attr_##_name = {			\
+	.attr = {.name = __stringify(_name), .mode = _mode },	\
+	.attr_id = attr_##_id,					\
+	.attr_ptr = ptr_##_struct##_offset,			\
+	.u = {							\
+		.offset = offsetof(struct _struct, _elname),\
+	},							\
+}
+
+#define EXT4_ATTR_STRING(_name,_mode,_size,_struct,_elname)	\
+static struct ext4_attr ext4_attr_##_name = {			\
+	.attr = {.name = __stringify(_name), .mode = _mode },	\
+	.attr_id = attr_pointer_string,				\
+	.attr_size = _size,					\
+	.attr_ptr = ptr_##_struct##_offset,			\
+	.u = {							\
+		.offset = offsetof(struct _struct, _elname),\
+	},							\
+}
+
+#define EXT4_RO_ATTR_ES_UI(_name,_elname)				\
+	EXT4_ATTR_OFFSET(_name, 0444, pointer_ui, ext4_super_block, _elname)
+
+#define EXT4_RO_ATTR_ES_U8(_name,_elname)				\
+	EXT4_ATTR_OFFSET(_name, 0444, pointer_u8, ext4_super_block, _elname)
+
+#define EXT4_RO_ATTR_ES_U64(_name,_elname)				\
+	EXT4_ATTR_OFFSET(_name, 0444, pointer_u64, ext4_super_block, _elname)
+
+#define EXT4_RO_ATTR_ES_STRING(_name,_elname,_size)			\
+	EXT4_ATTR_STRING(_name, 0444, _size, ext4_super_block, _elname)
+
+#define EXT4_RW_ATTR_SBI_PI(_name,_elname)      \
+	EXT4_ATTR_OFFSET(_name, 0644, pointer_pi, ext4_sb_info, _elname)
+
+#define EXT4_RW_ATTR_SBI_UI(_name,_elname)	\
+	EXT4_ATTR_OFFSET(_name, 0644, pointer_ui, ext4_sb_info, _elname)
+
+#define EXT4_RW_ATTR_SBI_UL(_name,_elname)	\
+	EXT4_ATTR_OFFSET(_name, 0644, pointer_ul, ext4_sb_info, _elname)
+
+#define EXT4_RO_ATTR_SBI_ATOMIC(_name,_elname)	\
+	EXT4_ATTR_OFFSET(_name, 0444, pointer_atomic, ext4_sb_info, _elname)
+
+#define EXT4_ATTR_PTR(_name,_mode,_id,_ptr) \
+static struct ext4_attr ext4_attr_##_name = {			\
+	.attr = {.name = __stringify(_name), .mode = _mode },	\
+	.attr_id = attr_##_id,					\
+	.attr_ptr = ptr_explicit,				\
+	.u = {							\
+		.explicit_ptr = _ptr,				\
+	},							\
+}
+
+#define ATTR_LIST(name) &ext4_attr_##name.attr
+
+EXT4_ATTR_FUNC(delayed_allocation_blocks, 0444);
+EXT4_ATTR_FUNC(session_write_kbytes, 0444);
+EXT4_ATTR_FUNC(lifetime_write_kbytes, 0444);
+EXT4_ATTR_FUNC(reserved_clusters, 0644);
+EXT4_ATTR_FUNC(sra_exceeded_retry_limit, 0444);
+
+EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, inode_readahead,
+		 ext4_sb_info, s_inode_readahead_blks);
+EXT4_ATTR_OFFSET(mb_group_prealloc, 0644, clusters_in_group,
+		 ext4_sb_info, s_mb_group_prealloc);
+EXT4_ATTR_OFFSET(mb_best_avail_max_trim_order, 0644, mb_order,
+		 ext4_sb_info, s_mb_best_avail_max_trim_order);
+EXT4_ATTR_OFFSET(err_report_sec, 0644, err_report_sec, ext4_sb_info, s_err_report_sec);
+EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal);
+EXT4_RW_ATTR_SBI_UI(mb_stats, s_mb_stats);
+EXT4_RW_ATTR_SBI_UI(mb_max_to_scan, s_mb_max_to_scan);
+EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan);
+EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
+EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
+EXT4_RW_ATTR_SBI_UI(mb_max_linear_groups, s_mb_max_linear_groups);
+EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
+EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error);
+EXT4_RW_ATTR_SBI_PI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval);
+EXT4_RW_ATTR_SBI_PI(err_ratelimit_burst, s_err_ratelimit_state.burst);
+EXT4_RW_ATTR_SBI_PI(warning_ratelimit_interval_ms, s_warning_ratelimit_state.interval);
+EXT4_RW_ATTR_SBI_PI(warning_ratelimit_burst, s_warning_ratelimit_state.burst);
+EXT4_RW_ATTR_SBI_PI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval);
+EXT4_RW_ATTR_SBI_PI(msg_ratelimit_burst, s_msg_ratelimit_state.burst);
+#ifdef CONFIG_EXT4_DEBUG
+EXT4_RW_ATTR_SBI_UL(simulate_fail, s_simulate_fail);
+#endif
+EXT4_RO_ATTR_SBI_ATOMIC(warning_count, s_warning_count);
+EXT4_RO_ATTR_SBI_ATOMIC(msg_count, s_msg_count);
+EXT4_RO_ATTR_ES_UI(errors_count, s_error_count);
+EXT4_RO_ATTR_ES_U8(first_error_errcode, s_first_error_errcode);
+EXT4_RO_ATTR_ES_U8(last_error_errcode, s_last_error_errcode);
+EXT4_RO_ATTR_ES_UI(first_error_ino, s_first_error_ino);
+EXT4_RO_ATTR_ES_UI(last_error_ino, s_last_error_ino);
+EXT4_RO_ATTR_ES_U64(first_error_block, s_first_error_block);
+EXT4_RO_ATTR_ES_U64(last_error_block, s_last_error_block);
+EXT4_RO_ATTR_ES_UI(first_error_line, s_first_error_line);
+EXT4_RO_ATTR_ES_UI(last_error_line, s_last_error_line);
+EXT4_RO_ATTR_ES_STRING(first_error_func, s_first_error_func, 32);
+EXT4_RO_ATTR_ES_STRING(last_error_func, s_last_error_func, 32);
+EXT4_ATTR(first_error_time, 0444, first_error_time);
+EXT4_ATTR(last_error_time, 0444, last_error_time);
+EXT4_ATTR(journal_task, 0444, journal_task);
+EXT4_RW_ATTR_SBI_UI(mb_prefetch, s_mb_prefetch);
+EXT4_RW_ATTR_SBI_UI(mb_prefetch_limit, s_mb_prefetch_limit);
+EXT4_RW_ATTR_SBI_UL(last_trim_minblks, s_last_trim_minblks);
+EXT4_RW_ATTR_SBI_UI(sb_update_sec, s_sb_update_sec);
+EXT4_RW_ATTR_SBI_UI(sb_update_kb, s_sb_update_kb);
+
+static unsigned int old_bump_val = 128;
+EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val);
+
+static struct attribute *ext4_attrs[] = {
+	ATTR_LIST(delayed_allocation_blocks),
+	ATTR_LIST(session_write_kbytes),
+	ATTR_LIST(lifetime_write_kbytes),
+	ATTR_LIST(reserved_clusters),
+	ATTR_LIST(sra_exceeded_retry_limit),
+	ATTR_LIST(inode_readahead_blks),
+	ATTR_LIST(inode_goal),
+	ATTR_LIST(mb_stats),
+	ATTR_LIST(mb_max_to_scan),
+	ATTR_LIST(mb_min_to_scan),
+	ATTR_LIST(mb_order2_req),
+	ATTR_LIST(mb_stream_req),
+	ATTR_LIST(mb_group_prealloc),
+	ATTR_LIST(mb_max_linear_groups),
+	ATTR_LIST(max_writeback_mb_bump),
+	ATTR_LIST(extent_max_zeroout_kb),
+	ATTR_LIST(trigger_fs_error),
+	ATTR_LIST(err_ratelimit_interval_ms),
+	ATTR_LIST(err_ratelimit_burst),
+	ATTR_LIST(warning_ratelimit_interval_ms),
+	ATTR_LIST(warning_ratelimit_burst),
+	ATTR_LIST(msg_ratelimit_interval_ms),
+	ATTR_LIST(msg_ratelimit_burst),
+	ATTR_LIST(mb_best_avail_max_trim_order),
+	ATTR_LIST(errors_count),
+	ATTR_LIST(warning_count),
+	ATTR_LIST(msg_count),
+	ATTR_LIST(first_error_ino),
+	ATTR_LIST(last_error_ino),
+	ATTR_LIST(first_error_block),
+	ATTR_LIST(last_error_block),
+	ATTR_LIST(first_error_line),
+	ATTR_LIST(last_error_line),
+	ATTR_LIST(first_error_func),
+	ATTR_LIST(last_error_func),
+	ATTR_LIST(first_error_errcode),
+	ATTR_LIST(last_error_errcode),
+	ATTR_LIST(first_error_time),
+	ATTR_LIST(last_error_time),
+	ATTR_LIST(journal_task),
+#ifdef CONFIG_EXT4_DEBUG
+	ATTR_LIST(simulate_fail),
+#endif
+	ATTR_LIST(mb_prefetch),
+	ATTR_LIST(mb_prefetch_limit),
+	ATTR_LIST(last_trim_minblks),
+	ATTR_LIST(sb_update_sec),
+	ATTR_LIST(sb_update_kb),
+	ATTR_LIST(err_report_sec),
+	NULL,
+};
+ATTRIBUTE_GROUPS(ext4);
+
+/* Features this copy of ext4 supports */
+EXT4_ATTR_FEATURE(lazy_itable_init);
+EXT4_ATTR_FEATURE(batched_discard);
+EXT4_ATTR_FEATURE(meta_bg_resize);
+#ifdef CONFIG_FS_ENCRYPTION
+EXT4_ATTR_FEATURE(encryption);
+EXT4_ATTR_FEATURE(test_dummy_encryption_v2);
+#endif
+#if IS_ENABLED(CONFIG_UNICODE)
+EXT4_ATTR_FEATURE(casefold);
+#endif
+#ifdef CONFIG_FS_VERITY
+EXT4_ATTR_FEATURE(verity);
+#endif
+EXT4_ATTR_FEATURE(metadata_csum_seed);
+EXT4_ATTR_FEATURE(fast_commit);
+#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION)
+EXT4_ATTR_FEATURE(encrypted_casefold);
+#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+EXT4_ATTR_FEATURE(blocksize_gt_pagesize);
+#endif
+
+static struct attribute *ext4_feat_attrs[] = {
+	ATTR_LIST(lazy_itable_init),
+	ATTR_LIST(batched_discard),
+	ATTR_LIST(meta_bg_resize),
+#ifdef CONFIG_FS_ENCRYPTION
+	ATTR_LIST(encryption),
+	ATTR_LIST(test_dummy_encryption_v2),
+#endif
+#if IS_ENABLED(CONFIG_UNICODE)
+	ATTR_LIST(casefold),
+#endif
+#ifdef CONFIG_FS_VERITY
+	ATTR_LIST(verity),
+#endif
+	ATTR_LIST(metadata_csum_seed),
+	ATTR_LIST(fast_commit),
+#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION)
+	ATTR_LIST(encrypted_casefold),
+#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	ATTR_LIST(blocksize_gt_pagesize),
+#endif
+	NULL,
+};
+ATTRIBUTE_GROUPS(ext4_feat);
+
+static void *calc_ptr(struct ext4_attr *a, struct ext4_sb_info *sbi)
+{
+	switch (a->attr_ptr) {
+	case ptr_explicit:
+		return a->u.explicit_ptr;
+	case ptr_ext4_sb_info_offset:
+		return (void *) (((char *) sbi) + a->u.offset);
+	case ptr_ext4_super_block_offset:
+		return (void *) (((char *) sbi->s_es) + a->u.offset);
+	}
+	return NULL;
+}
+
+static ssize_t __print_tstamp(char *buf, __le32 lo, __u8 hi)
+{
+	return sysfs_emit(buf, "%lld\n",
+			((time64_t)hi << 32) + le32_to_cpu(lo));
+}
+
+#define print_tstamp(buf, es, tstamp) \
+	__print_tstamp(buf, (es)->tstamp, (es)->tstamp ## _hi)
+
+static ssize_t ext4_generic_attr_show(struct ext4_attr *a,
+				      struct ext4_sb_info *sbi, char *buf)
+{
+	void *ptr = calc_ptr(a, sbi);
+
+	if (!ptr)
+		return 0;
+
+	switch (a->attr_id) {
+	case attr_inode_readahead:
+	case attr_clusters_in_group:
+	case attr_mb_order:
+	case attr_pointer_pi:
+	case attr_pointer_ui:
+		if (a->attr_ptr == ptr_ext4_super_block_offset)
+			return sysfs_emit(buf, "%u\n", le32_to_cpup(ptr));
+		return sysfs_emit(buf, "%u\n", *((unsigned int *) ptr));
+	case attr_pointer_ul:
+	case attr_err_report_sec:
+		return sysfs_emit(buf, "%lu\n", *((unsigned long *) ptr));
+	case attr_pointer_u8:
+		return sysfs_emit(buf, "%u\n", *((unsigned char *) ptr));
+	case attr_pointer_u64:
+		if (a->attr_ptr == ptr_ext4_super_block_offset)
+			return sysfs_emit(buf, "%llu\n", le64_to_cpup(ptr));
+		return sysfs_emit(buf, "%llu\n", *((unsigned long long *) ptr));
+	case attr_pointer_string:
+		return sysfs_emit(buf, "%.*s\n", a->attr_size, (char *) ptr);
+	case attr_pointer_atomic:
+		return sysfs_emit(buf, "%d\n", atomic_read((atomic_t *) ptr));
+	}
+	return 0;
+}
+
+static ssize_t ext4_attr_show(struct kobject *kobj,
+			      struct attribute *attr, char *buf)
+{
+	struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info,
+						s_kobj);
+	struct ext4_attr *a = container_of(attr, struct ext4_attr, attr);
+
+	switch (a->attr_id) {
+	case attr_delayed_allocation_blocks:
+		return sysfs_emit(buf, "%llu\n",
+				(s64) EXT4_C2B(sbi,
+		       percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
+	case attr_session_write_kbytes:
+		return session_write_kbytes_show(sbi, buf);
+	case attr_lifetime_write_kbytes:
+		return lifetime_write_kbytes_show(sbi, buf);
+	case attr_reserved_clusters:
+		return sysfs_emit(buf, "%llu\n",
+				(unsigned long long)
+				atomic64_read(&sbi->s_resv_clusters));
+	case attr_sra_exceeded_retry_limit:
+		return sysfs_emit(buf, "%llu\n",
+				(unsigned long long)
+			percpu_counter_sum(&sbi->s_sra_exceeded_retry_limit));
+	case attr_feature:
+		return sysfs_emit(buf, "supported\n");
+	case attr_first_error_time:
+		return print_tstamp(buf, sbi->s_es, s_first_error_time);
+	case attr_last_error_time:
+		return print_tstamp(buf, sbi->s_es, s_last_error_time);
+	case attr_journal_task:
+		return journal_task_show(sbi, buf);
+	default:
+		return ext4_generic_attr_show(a, sbi, buf);
+	}
+}
+
+static ssize_t ext4_generic_attr_store(struct ext4_attr *a,
+				       struct ext4_sb_info *sbi,
+				       const char *buf, size_t len)
+{
+	int ret;
+	unsigned int t;
+	unsigned long lt;
+	void *ptr = calc_ptr(a, sbi);
+
+	if (!ptr)
+		return 0;
+
+	switch (a->attr_id) {
+	case attr_pointer_pi:
+		ret = kstrtouint(skip_spaces(buf), 0, &t);
+		if (ret)
+			return ret;
+		if ((int)t < 0)
+			return -EINVAL;
+		*((unsigned int *) ptr) = t;
+		return len;
+	case attr_pointer_ui:
+		ret = kstrtouint(skip_spaces(buf), 0, &t);
+		if (ret)
+			return ret;
+		if (a->attr_ptr == ptr_ext4_super_block_offset)
+			*((__le32 *) ptr) = cpu_to_le32(t);
+		else
+			*((unsigned int *) ptr) = t;
+		return len;
+	case attr_mb_order:
+		ret = kstrtouint(skip_spaces(buf), 0, &t);
+		if (ret)
+			return ret;
+		if (t > 64)
+			return -EINVAL;
+		*((unsigned int *) ptr) = t;
+		return len;
+	case attr_clusters_in_group:
+		ret = kstrtouint(skip_spaces(buf), 0, &t);
+		if (ret)
+			return ret;
+		if (t > sbi->s_clusters_per_group)
+			return -EINVAL;
+		*((unsigned int *) ptr) = t;
+		return len;
+	case attr_pointer_ul:
+		ret = kstrtoul(skip_spaces(buf), 0, &lt);
+		if (ret)
+			return ret;
+		*((unsigned long *) ptr) = lt;
+		return len;
+	}
+	return 0;
+}
+
+static ssize_t ext4_attr_store(struct kobject *kobj,
+			       struct attribute *attr,
+			       const char *buf, size_t len)
+{
+	struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info,
+						s_kobj);
+	struct ext4_attr *a = container_of(attr, struct ext4_attr, attr);
+
+	switch (a->attr_id) {
+	case attr_reserved_clusters:
+		return reserved_clusters_store(sbi, buf, len);
+	case attr_inode_readahead:
+		return inode_readahead_blks_store(sbi, buf, len);
+	case attr_trigger_test_error:
+		return trigger_test_error(sbi, buf, len);
+	case attr_err_report_sec:
+		return err_report_sec_store(sbi, buf, len);
+	default:
+		return ext4_generic_attr_store(a, sbi, buf, len);
+	}
+}
+
+static void ext4_sb_release(struct kobject *kobj)
+{
+	struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info,
+						s_kobj);
+	complete(&sbi->s_kobj_unregister);
+}
+
+static void ext4_feat_release(struct kobject *kobj)
+{
+	kfree(kobj);
+}
+
+static const struct sysfs_ops ext4_attr_ops = {
+	.show	= ext4_attr_show,
+	.store	= ext4_attr_store,
+};
+
+static const struct kobj_type ext4_sb_ktype = {
+	.default_groups = ext4_groups,
+	.sysfs_ops	= &ext4_attr_ops,
+	.release	= ext4_sb_release,
+};
+
+static const struct kobj_type ext4_feat_ktype = {
+	.default_groups = ext4_feat_groups,
+	.sysfs_ops	= &ext4_attr_ops,
+	.release	= ext4_feat_release,
+};
+
+void ext4_notify_error_sysfs(struct ext4_sb_info *sbi)
+{
+	mutex_lock(&sbi->s_error_notify_mutex);
+	if (sbi->s_kobj.state_in_sysfs)
+		sysfs_notify(&sbi->s_kobj, NULL, "errors_count");
+	mutex_unlock(&sbi->s_error_notify_mutex);
+}
+
+static struct kobject *ext4_root;
+
+static struct kobject *ext4_feat;
+
+int ext4_register_sysfs(struct super_block *sb)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int err;
+
+	init_completion(&sbi->s_kobj_unregister);
+	mutex_lock(&sbi->s_error_notify_mutex);
+	err = kobject_init_and_add(&sbi->s_kobj, &ext4_sb_ktype, ext4_root,
+				   "%s", sb->s_id);
+	mutex_unlock(&sbi->s_error_notify_mutex);
+	if (err) {
+		kobject_put(&sbi->s_kobj);
+		wait_for_completion(&sbi->s_kobj_unregister);
+		return err;
+	}
+
+	if (ext4_proc_root)
+		sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
+	if (sbi->s_proc) {
+		proc_create_single_data("options", S_IRUGO, sbi->s_proc,
+				ext4_seq_options_show, sb);
+		proc_create_single_data("es_shrinker_info", S_IRUGO,
+				sbi->s_proc, ext4_seq_es_shrinker_info_show,
+				sb);
+		proc_create_single_data("fc_info", 0444, sbi->s_proc,
+					ext4_fc_info_show, sb);
+		proc_create_seq_data("mb_groups", S_IRUGO, sbi->s_proc,
+				&ext4_mb_seq_groups_ops, sb);
+		proc_create_single_data("mb_stats", 0444, sbi->s_proc,
+				ext4_seq_mb_stats_show, sb);
+		proc_create_seq_data("mb_structs_summary", 0444, sbi->s_proc,
+				&ext4_mb_seq_structs_summary_ops, sb);
+	}
+	return 0;
+}
+
+void ext4_unregister_sysfs(struct super_block *sb)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (sbi->s_proc)
+		remove_proc_subtree(sb->s_id, ext4_proc_root);
+
+	mutex_lock(&sbi->s_error_notify_mutex);
+	kobject_del(&sbi->s_kobj);
+	mutex_unlock(&sbi->s_error_notify_mutex);
+}
+
+int __init ext4_init_sysfs(void)
+{
+	int ret;
+
+	ext4_root = kobject_create_and_add("ext4", fs_kobj);
+	if (!ext4_root)
+		return -ENOMEM;
+
+	ext4_feat = kzalloc_obj(*ext4_feat);
+	if (!ext4_feat) {
+		ret = -ENOMEM;
+		goto root_err;
+	}
+
+	ret = kobject_init_and_add(ext4_feat, &ext4_feat_ktype,
+				   ext4_root, "features");
+	if (ret)
+		goto feat_err;
+
+	ext4_proc_root = proc_mkdir(proc_dirname, NULL);
+	return ret;
+
+feat_err:
+	kobject_put(ext4_feat);
+	ext4_feat = NULL;
+root_err:
+	kobject_put(ext4_root);
+	ext4_root = NULL;
+	return ret;
+}
+
+void ext4_exit_sysfs(void)
+{
+	kobject_put(ext4_feat);
+	ext4_feat = NULL;
+	kobject_put(ext4_root);
+	ext4_root = NULL;
+	remove_proc_entry(proc_dirname, NULL);
+	ext4_proc_root = NULL;
+}
+

linux-7.2.3/fs/ext4/truncate.h

@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/fs/ext4/truncate.h
+ *
+ * Common inline functions needed for truncate support
+ */
+
+/*
+ * Truncate blocks that were not used by write. We have to truncate the
+ * pagecache as well so that corresponding buffers get properly unmapped.
+ */
+static inline void ext4_truncate_failed_write(struct inode *inode)
+{
+	struct address_space *mapping = inode->i_mapping;
+
+	/*
+	 * We don't need to call ext4_break_layouts() because the blocks we
+	 * are truncating were never visible to userspace.
+	 */
+	filemap_invalidate_lock(mapping);
+	truncate_inode_pages(mapping, inode->i_size);
+	ext4_truncate(inode);
+	filemap_invalidate_unlock(mapping);
+}
+
+/*
+ * Work out how many blocks we need to proceed with the next chunk of a
+ * truncate transaction.
+ */
+static inline unsigned long ext4_blocks_for_truncate(struct inode *inode)
+{
+	ext4_lblk_t needed;
+
+	needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9);
+
+	/* Give ourselves just enough room to cope with inodes in which
+	 * i_blocks is corrupt: we've seen disk corruptions in the past
+	 * which resulted in random data in an inode which looked enough
+	 * like a regular file for ext4 to try to delete it.  Things
+	 * will go a bit crazy if that happens, but at least we should
+	 * try not to panic the whole kernel. */
+	if (needed < 2)
+		needed = 2;
+
+	/* But we need to bound the transaction so we don't overflow the
+	 * journal. */
+	if (needed > EXT4_MAX_TRANS_DATA)
+		needed = EXT4_MAX_TRANS_DATA;
+
+	return EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + needed;
+}
+

linux-7.2.3/fs/ext4/verity.c

@@ -0,0 +1,391 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fs/ext4/verity.c: fs-verity support for ext4
+ *
+ * Copyright 2019 Google LLC
+ */
+
+/*
+ * Implementation of fsverity_operations for ext4.
+ *
+ * ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past
+ * the end of the file, starting at the first 64K boundary beyond i_size.  This
+ * approach works because (a) verity files are readonly, and (b) pages fully
+ * beyond i_size aren't visible to userspace but can be read/written internally
+ * by ext4 with only some relatively small changes to ext4.  This approach
+ * avoids having to depend on the EA_INODE feature and on rearchitecturing
+ * ext4's xattr support to support paging multi-gigabyte xattrs into memory, and
+ * to support encrypting xattrs.  Note that the verity metadata *must* be
+ * encrypted when the file is, since it contains hashes of the plaintext data.
+ *
+ * Using a 64K boundary rather than a 4K one keeps things ready for
+ * architectures with 64K pages, and it doesn't necessarily waste space on-disk
+ * since there can be a hole between i_size and the start of the Merkle tree.
+ */
+
+#include <linux/quotaops.h>
+
+#include "ext4.h"
+#include "ext4_extents.h"
+#include "ext4_jbd2.h"
+
+static inline loff_t ext4_verity_metadata_pos(const struct inode *inode)
+{
+	return round_up(inode->i_size, 65536);
+}
+
+/*
+ * Read some verity metadata from the inode.  __vfs_read() can't be used because
+ * we need to read beyond i_size.
+ */
+static int pagecache_read(struct inode *inode, void *buf, size_t count,
+			  loff_t pos)
+{
+	while (count) {
+		struct folio *folio;
+		size_t n;
+
+		folio = read_mapping_folio(inode->i_mapping, pos >> PAGE_SHIFT,
+					 NULL);
+		if (IS_ERR(folio))
+			return PTR_ERR(folio);
+
+		n = memcpy_from_file_folio(buf, folio, pos, count);
+		folio_put(folio);
+
+		buf += n;
+		pos += n;
+		count -= n;
+	}
+	return 0;
+}
+
+/*
+ * Write some verity metadata to the inode for FS_IOC_ENABLE_VERITY.
+ * kernel_write() can't be used because the file descriptor is readonly.
+ */
+static int pagecache_write(struct inode *inode, const void *buf, size_t count,
+			   loff_t pos)
+{
+	struct address_space *mapping = inode->i_mapping;
+	const struct address_space_operations *aops = mapping->a_ops;
+
+	if (pos + count > inode->i_sb->s_maxbytes)
+		return -EFBIG;
+
+	while (count) {
+		size_t n = min_t(size_t, count,
+				 PAGE_SIZE - offset_in_page(pos));
+		struct folio *folio;
+		void *fsdata = NULL;
+		int res;
+
+		res = aops->write_begin(NULL, mapping, pos, n, &folio, &fsdata);
+		if (res)
+			return res;
+
+		memcpy_to_folio(folio, offset_in_folio(folio, pos), buf, n);
+
+		res = aops->write_end(NULL, mapping, pos, n, n, folio, fsdata);
+		if (res < 0)
+			return res;
+		if (res != n)
+			return -EIO;
+
+		buf += n;
+		pos += n;
+		count -= n;
+	}
+	return 0;
+}
+
+static int ext4_begin_enable_verity(struct file *filp)
+{
+	struct inode *inode = file_inode(filp);
+	const int credits = 2; /* superblock and inode for ext4_orphan_add() */
+	handle_t *handle;
+	int err;
+
+	if (IS_DAX(inode) || ext4_test_inode_flag(inode, EXT4_INODE_DAX))
+		return -EINVAL;
+
+	if (ext4_verity_in_progress(inode))
+		return -EBUSY;
+
+	/*
+	 * Since the file was opened readonly, we have to initialize the jbd
+	 * inode and quotas here and not rely on ->open() doing it.  This must
+	 * be done before evicting the inline data.
+	 */
+
+	err = ext4_inode_attach_jinode(inode);
+	if (err)
+		return err;
+
+	err = dquot_initialize(inode);
+	if (err)
+		return err;
+
+	err = ext4_convert_inline_data(inode);
+	if (err)
+		return err;
+
+	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+		ext4_warning_inode(inode,
+				   "verity is only allowed on extent-based files");
+		return -EOPNOTSUPP;
+	}
+
+	/*
+	 * ext4 uses the last allocated block to find the verity descriptor, so
+	 * we must remove any other blocks past EOF which might confuse things.
+	 */
+	err = ext4_truncate(inode);
+	if (err)
+		return err;
+
+	handle = ext4_journal_start(inode, EXT4_HT_INODE, credits);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	err = ext4_orphan_add(handle, inode);
+	if (err == 0)
+		ext4_set_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
+
+	ext4_journal_stop(handle);
+	return err;
+}
+
+/*
+ * ext4 stores the verity descriptor beginning on the next filesystem block
+ * boundary after the Merkle tree.  Then, the descriptor size is stored in the
+ * last 4 bytes of the last allocated filesystem block --- which is either the
+ * block in which the descriptor ends, or the next block after that if there
+ * weren't at least 4 bytes remaining.
+ *
+ * We can't simply store the descriptor in an xattr because it *must* be
+ * encrypted when ext4 encryption is used, but ext4 encryption doesn't encrypt
+ * xattrs.  Also, if the descriptor includes a large signature blob it may be
+ * too large to store in an xattr without the EA_INODE feature.
+ */
+static int ext4_write_verity_descriptor(struct inode *inode, const void *desc,
+					size_t desc_size, u64 merkle_tree_size)
+{
+	const u64 desc_pos = round_up(ext4_verity_metadata_pos(inode) +
+				      merkle_tree_size, i_blocksize(inode));
+	const u64 desc_end = desc_pos + desc_size;
+	const __le32 desc_size_disk = cpu_to_le32(desc_size);
+	const u64 desc_size_pos = round_up(desc_end + sizeof(desc_size_disk),
+					   i_blocksize(inode)) -
+				  sizeof(desc_size_disk);
+	int err;
+
+	err = pagecache_write(inode, desc, desc_size, desc_pos);
+	if (err)
+		return err;
+
+	return pagecache_write(inode, &desc_size_disk, sizeof(desc_size_disk),
+			       desc_size_pos);
+}
+
+static int ext4_end_enable_verity(struct file *filp, const void *desc,
+				  size_t desc_size, u64 merkle_tree_size)
+{
+	struct inode *inode = file_inode(filp);
+	const int credits = 2; /* superblock and inode for ext4_orphan_del() */
+	handle_t *handle;
+	struct ext4_iloc iloc;
+	int err = 0;
+
+	/*
+	 * If an error already occurred (which fs/verity/ signals by passing
+	 * desc == NULL), then only clean-up is needed.
+	 */
+	if (desc == NULL)
+		goto cleanup;
+
+	/* Append the verity descriptor. */
+	err = ext4_write_verity_descriptor(inode, desc, desc_size,
+					   merkle_tree_size);
+	if (err)
+		goto cleanup;
+
+	/*
+	 * Write all pages (both data and verity metadata).  Note that this must
+	 * happen before clearing EXT4_STATE_VERITY_IN_PROGRESS; otherwise pages
+	 * beyond i_size won't be written properly.  For crash consistency, this
+	 * also must happen before the verity inode flag gets persisted.
+	 */
+	err = filemap_write_and_wait(inode->i_mapping);
+	if (err)
+		goto cleanup;
+
+	/*
+	 * Finally, set the verity inode flag and remove the inode from the
+	 * orphan list (in a single transaction).
+	 */
+
+	handle = ext4_journal_start(inode, EXT4_HT_INODE, credits);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		goto cleanup;
+	}
+
+	ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_VERITY, handle);
+
+	err = ext4_orphan_del(handle, inode);
+	if (err)
+		goto stop_and_cleanup;
+
+	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (err)
+		goto stop_and_cleanup;
+
+	ext4_set_inode_flag(inode, EXT4_INODE_VERITY);
+	ext4_set_inode_flags(inode, false);
+	err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+	if (err)
+		goto stop_and_cleanup;
+
+	ext4_journal_stop(handle);
+
+	ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
+	return 0;
+
+stop_and_cleanup:
+	ext4_journal_stop(handle);
+cleanup:
+	/*
+	 * Verity failed to be enabled, so clean up by truncating any verity
+	 * metadata that was written beyond i_size (both from cache and from
+	 * disk), removing the inode from the orphan list (if it wasn't done
+	 * already), and clearing EXT4_STATE_VERITY_IN_PROGRESS.
+	 */
+	truncate_inode_pages(inode->i_mapping, inode->i_size);
+	ext4_truncate(inode);
+	ext4_orphan_del(NULL, inode);
+	ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
+	return err;
+}
+
+static int ext4_get_verity_descriptor_location(struct inode *inode,
+					       size_t *desc_size_ret,
+					       u64 *desc_pos_ret)
+{
+	struct ext4_ext_path *path;
+	struct ext4_extent *last_extent;
+	u32 end_lblk;
+	u64 desc_size_pos;
+	__le32 desc_size_disk;
+	u32 desc_size;
+	u64 desc_pos;
+	int err;
+
+	/*
+	 * Descriptor size is in last 4 bytes of last allocated block.
+	 * See ext4_write_verity_descriptor().
+	 */
+
+	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+		EXT4_ERROR_INODE(inode, "verity file doesn't use extents");
+		return -EFSCORRUPTED;
+	}
+
+	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	last_extent = path[path->p_depth].p_ext;
+	if (!last_extent) {
+		EXT4_ERROR_INODE(inode, "verity file has no extents");
+		ext4_free_ext_path(path);
+		return -EFSCORRUPTED;
+	}
+
+	end_lblk = le32_to_cpu(last_extent->ee_block) +
+		   ext4_ext_get_actual_len(last_extent);
+	desc_size_pos = EXT4_LBLK_TO_B(inode, end_lblk);
+	ext4_free_ext_path(path);
+
+	if (desc_size_pos < sizeof(desc_size_disk))
+		goto bad;
+	desc_size_pos -= sizeof(desc_size_disk);
+
+	err = pagecache_read(inode, &desc_size_disk, sizeof(desc_size_disk),
+			     desc_size_pos);
+	if (err)
+		return err;
+	desc_size = le32_to_cpu(desc_size_disk);
+
+	/*
+	 * The descriptor is stored just before the desc_size_disk, but starting
+	 * on a filesystem block boundary.
+	 */
+
+	if (desc_size > INT_MAX || desc_size > desc_size_pos)
+		goto bad;
+
+	desc_pos = round_down(desc_size_pos - desc_size, i_blocksize(inode));
+	if (desc_pos < ext4_verity_metadata_pos(inode))
+		goto bad;
+
+	*desc_size_ret = desc_size;
+	*desc_pos_ret = desc_pos;
+	return 0;
+
+bad:
+	EXT4_ERROR_INODE(inode, "verity file corrupted; can't find descriptor");
+	return -EFSCORRUPTED;
+}
+
+static int ext4_get_verity_descriptor(struct inode *inode, void *buf,
+				      size_t buf_size)
+{
+	size_t desc_size = 0;
+	u64 desc_pos = 0;
+	int err;
+
+	err = ext4_get_verity_descriptor_location(inode, &desc_size, &desc_pos);
+	if (err)
+		return err;
+
+	if (buf_size) {
+		if (desc_size > buf_size)
+			return -ERANGE;
+		err = pagecache_read(inode, buf, desc_size, desc_pos);
+		if (err)
+			return err;
+	}
+	return desc_size;
+}
+
+static struct page *ext4_read_merkle_tree_page(struct inode *inode,
+					       pgoff_t index)
+{
+	index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT;
+	return generic_read_merkle_tree_page(inode, index);
+}
+
+static void ext4_readahead_merkle_tree(struct inode *inode, pgoff_t index,
+				       unsigned long nr_pages)
+{
+	index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT;
+	generic_readahead_merkle_tree(inode, index, nr_pages);
+}
+
+static int ext4_write_merkle_tree_block(struct file *file, const void *buf,
+					u64 pos, unsigned int size)
+{
+	pos += ext4_verity_metadata_pos(file_inode(file));
+
+	return pagecache_write(file_inode(file), buf, size, pos);
+}
+
+const struct fsverity_operations ext4_verityops = {
+	.begin_enable_verity	= ext4_begin_enable_verity,
+	.end_enable_verity	= ext4_end_enable_verity,
+	.get_verity_descriptor	= ext4_get_verity_descriptor,
+	.read_merkle_tree_page	= ext4_read_merkle_tree_page,
+	.readahead_merkle_tree	= ext4_readahead_merkle_tree,
+	.write_merkle_tree_block = ext4_write_merkle_tree_block,
+};

linux-7.2.3/fs/ext4/xattr.h

@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+  File: fs/ext4/xattr.h
+
+  On-disk format of extended attributes for the ext4 filesystem.
+
+  (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org>
+*/
+
+#include <linux/xattr.h>
+
+/* Magic value in attribute blocks */
+#define EXT4_XATTR_MAGIC		0xEA020000
+
+/* Maximum number of references to one attribute block */
+#define EXT4_XATTR_REFCOUNT_MAX		1024
+
+/* Name indexes */
+#define EXT4_XATTR_INDEX_USER			1
+#define EXT4_XATTR_INDEX_POSIX_ACL_ACCESS	2
+#define EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT	3
+#define EXT4_XATTR_INDEX_TRUSTED		4
+#define	EXT4_XATTR_INDEX_LUSTRE			5
+#define EXT4_XATTR_INDEX_SECURITY	        6
+#define EXT4_XATTR_INDEX_SYSTEM			7
+#define EXT4_XATTR_INDEX_RICHACL		8
+#define EXT4_XATTR_INDEX_ENCRYPTION		9
+#define EXT4_XATTR_INDEX_HURD			10 /* Reserved for Hurd */
+
+struct ext4_xattr_header {
+	__le32	h_magic;	/* magic number for identification */
+	__le32	h_refcount;	/* reference count */
+	__le32	h_blocks;	/* number of disk blocks used */
+	__le32	h_hash;		/* hash value of all attributes */
+	__le32	h_checksum;	/* crc32c(uuid+blknum+xattrblock) */
+	__u32	h_reserved[3];	/* zero right now */
+};
+
+struct ext4_xattr_ibody_header {
+	__le32	h_magic;	/* magic number for identification */
+};
+
+struct ext4_xattr_entry {
+	__u8	e_name_len;	/* length of name */
+	__u8	e_name_index;	/* attribute name index */
+	__le16	e_value_offs;	/* offset in disk block of value */
+	__le32	e_value_inum;	/* inode in which the value is stored */
+	__le32	e_value_size;	/* size of attribute value */
+	__le32	e_hash;		/* hash value of name and value */
+	char	e_name[];	/* attribute name */
+};
+
+#define EXT4_XATTR_PAD_BITS		2
+#define EXT4_XATTR_PAD		(1<<EXT4_XATTR_PAD_BITS)
+#define EXT4_XATTR_ROUND		(EXT4_XATTR_PAD-1)
+#define EXT4_XATTR_LEN(name_len) \
+	(((name_len) + EXT4_XATTR_ROUND + \
+	sizeof(struct ext4_xattr_entry)) & ~EXT4_XATTR_ROUND)
+#define EXT4_XATTR_NEXT(entry) \
+	((struct ext4_xattr_entry *)( \
+	 (char *)(entry) + EXT4_XATTR_LEN((entry)->e_name_len)))
+#define EXT4_XATTR_SIZE(size) \
+	(((size) + EXT4_XATTR_ROUND) & ~EXT4_XATTR_ROUND)
+
+#define IHDR(inode, raw_inode) \
+	((struct ext4_xattr_ibody_header *) \
+		((void *)raw_inode + \
+		EXT4_GOOD_OLD_INODE_SIZE + \
+		EXT4_I(inode)->i_extra_isize))
+#define ITAIL(inode, raw_inode) \
+	((void *)(raw_inode) + \
+	 EXT4_SB((inode)->i_sb)->s_inode_size)
+#define IFIRST(hdr) ((struct ext4_xattr_entry *)((hdr)+1))
+
+/*
+ * XATTR_SIZE_MAX is currently 64k, but for the purposes of checking
+ * for file system consistency errors, we use a somewhat bigger value.
+ * This allows XATTR_SIZE_MAX to grow in the future, but by using this
+ * instead of INT_MAX for certain consistency checks, we don't need to
+ * worry about arithmetic overflows.  (Actually XATTR_SIZE_MAX is
+ * defined in include/uapi/linux/limits.h, so changing it is going
+ * not going to be trivial....)
+ */
+#define EXT4_XATTR_SIZE_MAX (1 << 24)
+
+/*
+ * The minimum size of EA value when you start storing it in an external inode
+ * size of block - size of header - size of 1 entry - 4 null bytes
+ */
+#define EXT4_XATTR_MIN_LARGE_EA_SIZE(b)					\
+	((b) - EXT4_XATTR_LEN(3) - sizeof(struct ext4_xattr_header) - 4)
+
+#define BHDR(bh) ((struct ext4_xattr_header *)((bh)->b_data))
+#define ENTRY(ptr) ((struct ext4_xattr_entry *)(ptr))
+#define BFIRST(bh) ENTRY(BHDR(bh)+1)
+#define IS_LAST_ENTRY(entry) (*(__u32 *)(entry) == 0)
+
+#define EXT4_ZERO_XATTR_VALUE ((void *)-1)
+
+/*
+ * If we want to add an xattr to the inode, we should make sure that
+ * i_extra_isize is not 0 and that the inode size is not less than
+ * EXT4_GOOD_OLD_INODE_SIZE + extra_isize + pad.
+ *   EXT4_GOOD_OLD_INODE_SIZE   extra_isize header   entry   pad  data
+ * |--------------------------|------------|------|---------|---|-------|
+ */
+#define EXT4_INODE_HAS_XATTR_SPACE(inode)				\
+	((EXT4_I(inode)->i_extra_isize != 0) &&				\
+	 (EXT4_GOOD_OLD_INODE_SIZE + EXT4_I(inode)->i_extra_isize +	\
+	  sizeof(struct ext4_xattr_ibody_header) + EXT4_XATTR_PAD <=	\
+	  EXT4_INODE_SIZE((inode)->i_sb)))
+
+struct ext4_xattr_info {
+	const char *name;
+	const void *value;
+	size_t value_len;
+	int name_index;
+	int in_inode;
+};
+
+struct ext4_xattr_search {
+	struct ext4_xattr_entry *first;
+	void *base;
+	void *end;
+	struct ext4_xattr_entry *here;
+	int not_found;
+};
+
+struct ext4_xattr_ibody_find {
+	struct ext4_xattr_search s;
+	struct ext4_iloc iloc;
+};
+
+struct ext4_xattr_inode_array {
+	unsigned int count;
+	struct inode *inodes[] __counted_by(count);
+};
+
+extern const struct xattr_handler ext4_xattr_user_handler;
+extern const struct xattr_handler ext4_xattr_trusted_handler;
+extern const struct xattr_handler ext4_xattr_security_handler;
+extern const struct xattr_handler ext4_xattr_hurd_handler;
+
+#define EXT4_XATTR_NAME_ENCRYPTION_CONTEXT "c"
+
+/*
+ * The EXT4_STATE_NO_EXPAND is overloaded and used for two purposes.
+ * The first is to signal that there the inline xattrs and data are
+ * taking up so much space that we might as well not keep trying to
+ * expand it.  The second is that xattr_sem is taken for writing, so
+ * we shouldn't try to recurse into the inode expansion.  For this
+ * second case, we need to make sure that we take save and restore the
+ * NO_EXPAND state flag appropriately.
+ */
+static inline void ext4_write_lock_xattr(struct inode *inode, int *save)
+{
+	down_write(&EXT4_I(inode)->xattr_sem);
+	*save = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
+}
+
+static inline int ext4_write_trylock_xattr(struct inode *inode, int *save)
+{
+	if (down_write_trylock(&EXT4_I(inode)->xattr_sem) == 0)
+		return 0;
+	*save = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	return 1;
+}
+
+static inline void ext4_write_unlock_xattr(struct inode *inode, int *save)
+{
+	if (*save == 0)
+		ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	up_write(&EXT4_I(inode)->xattr_sem);
+}
+
+extern ssize_t ext4_listxattr(struct dentry *, char *, size_t);
+
+extern int ext4_xattr_get(struct inode *, int, const char *, void *, size_t);
+extern int ext4_xattr_set(struct inode *, int, const char *, const void *, size_t, int);
+extern int ext4_xattr_set_handle(handle_t *, struct inode *, int, const char *, const void *, size_t, int);
+extern int ext4_xattr_set_credits(struct inode *inode, size_t value_len,
+				  bool is_create, int *credits);
+extern int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode,
+				struct buffer_head *block_bh, size_t value_len,
+				bool is_create);
+
+extern int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
+				   struct ext4_xattr_inode_array **array,
+				   int extra_credits);
+extern void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *array);
+
+extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
+			    struct ext4_inode *raw_inode, handle_t *handle);
+extern void ext4_evict_ea_inode(struct inode *inode);
+
+extern const struct xattr_handler * const ext4_xattr_handlers[];
+
+extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
+				 struct ext4_xattr_ibody_find *is);
+extern int ext4_xattr_ibody_get(struct inode *inode, int name_index,
+				const char *name,
+				void *buffer, size_t buffer_size);
+extern int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
+				struct ext4_xattr_info *i,
+				struct ext4_xattr_ibody_find *is);
+
+extern struct mb_cache *ext4_xattr_create_cache(void);
+extern void ext4_xattr_destroy_cache(struct mb_cache *);
+
+extern int
+__xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header,
+		    void *end, const char *function, unsigned int line);
+
+#define xattr_check_inode(inode, header, end) \
+	__xattr_check_inode((inode), (header), (end), __func__, __LINE__)
+
+#ifdef CONFIG_EXT4_FS_SECURITY
+extern int ext4_init_security(handle_t *handle, struct inode *inode,
+			      struct inode *dir, const struct qstr *qstr);
+#else
+static inline int ext4_init_security(handle_t *handle, struct inode *inode,
+				     struct inode *dir, const struct qstr *qstr)
+{
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_LOCKDEP
+extern void ext4_xattr_inode_set_class(struct inode *ea_inode);
+#else
+static inline void ext4_xattr_inode_set_class(struct inode *ea_inode) { }
+#endif
+
+extern int ext4_get_inode_usage(struct inode *inode, qsize_t *usage);

linux-7.2.3/fs/ext4/xattr_hurd.c

@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/fs/ext4/xattr_hurd.c
+ * Handler for extended gnu attributes for the Hurd.
+ *
+ * Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
+ * Copyright (C) 2020 by Jan (janneke) Nieuwenhuizen, <janneke@gnu.org>
+ */
+
+#include <linux/init.h>
+#include <linux/string.h>
+#include "ext4.h"
+#include "xattr.h"
+
+static bool
+ext4_xattr_hurd_list(struct dentry *dentry)
+{
+	return test_opt(dentry->d_sb, XATTR_USER);
+}
+
+static int
+ext4_xattr_hurd_get(const struct xattr_handler *handler,
+		    struct dentry *unused, struct inode *inode,
+		    const char *name, void *buffer, size_t size)
+{
+	if (!test_opt(inode->i_sb, XATTR_USER))
+		return -EOPNOTSUPP;
+
+	return ext4_xattr_get(inode, EXT4_XATTR_INDEX_HURD,
+			      name, buffer, size);
+}
+
+static int
+ext4_xattr_hurd_set(const struct xattr_handler *handler,
+		    struct mnt_idmap *idmap,
+		    struct dentry *unused, struct inode *inode,
+		    const char *name, const void *value,
+		    size_t size, int flags)
+{
+	if (!test_opt(inode->i_sb, XATTR_USER))
+		return -EOPNOTSUPP;
+
+	return ext4_xattr_set(inode, EXT4_XATTR_INDEX_HURD,
+			      name, value, size, flags);
+}
+
+const struct xattr_handler ext4_xattr_hurd_handler = {
+	.prefix	= XATTR_HURD_PREFIX,
+	.list	= ext4_xattr_hurd_list,
+	.get	= ext4_xattr_hurd_get,
+	.set	= ext4_xattr_hurd_set,
+};

linux-7.2.3/fs/ext4/xattr_security.c

@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/fs/ext4/xattr_security.c
+ * Handler for storing security labels as extended attributes.
+ */
+
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/security.h>
+#include <linux/slab.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"
+#include "xattr.h"
+
+static int
+ext4_xattr_security_get(const struct xattr_handler *handler,
+			struct dentry *unused, struct inode *inode,
+			const char *name, void *buffer, size_t size)
+{
+	return ext4_xattr_get(inode, EXT4_XATTR_INDEX_SECURITY,
+			      name, buffer, size);
+}
+
+static int
+ext4_xattr_security_set(const struct xattr_handler *handler,
+			struct mnt_idmap *idmap,
+			struct dentry *unused, struct inode *inode,
+			const char *name, const void *value,
+			size_t size, int flags)
+{
+	return ext4_xattr_set(inode, EXT4_XATTR_INDEX_SECURITY,
+			      name, value, size, flags);
+}
+
+static int
+ext4_initxattrs(struct inode *inode, const struct xattr *xattr_array,
+		void *fs_info)
+{
+	const struct xattr *xattr;
+	handle_t *handle = fs_info;
+	int err = 0;
+
+	for (xattr = xattr_array; xattr->name != NULL; xattr++) {
+		err = ext4_xattr_set_handle(handle, inode,
+					    EXT4_XATTR_INDEX_SECURITY,
+					    xattr->name, xattr->value,
+					    xattr->value_len, XATTR_CREATE);
+		if (err < 0)
+			break;
+	}
+	return err;
+}
+
+int
+ext4_init_security(handle_t *handle, struct inode *inode, struct inode *dir,
+		   const struct qstr *qstr)
+{
+	return security_inode_init_security(inode, dir, qstr,
+					    &ext4_initxattrs, handle);
+}
+
+const struct xattr_handler ext4_xattr_security_handler = {
+	.prefix	= XATTR_SECURITY_PREFIX,
+	.get	= ext4_xattr_security_get,
+	.set	= ext4_xattr_security_set,
+};

linux-7.2.3/fs/ext4/xattr_trusted.c

@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/fs/ext4/xattr_trusted.c
+ * Handler for trusted extended attributes.
+ *
+ * Copyright (C) 2003 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
+ */
+
+#include <linux/string.h>
+#include <linux/capability.h>
+#include <linux/fs.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"
+#include "xattr.h"
+
+static bool
+ext4_xattr_trusted_list(struct dentry *dentry)
+{
+	return capable(CAP_SYS_ADMIN);
+}
+
+static int
+ext4_xattr_trusted_get(const struct xattr_handler *handler,
+		       struct dentry *unused, struct inode *inode,
+		       const char *name, void *buffer, size_t size)
+{
+	return ext4_xattr_get(inode, EXT4_XATTR_INDEX_TRUSTED,
+			      name, buffer, size);
+}
+
+static int
+ext4_xattr_trusted_set(const struct xattr_handler *handler,
+		       struct mnt_idmap *idmap,
+		       struct dentry *unused, struct inode *inode,
+		       const char *name, const void *value,
+		       size_t size, int flags)
+{
+	return ext4_xattr_set(inode, EXT4_XATTR_INDEX_TRUSTED,
+			      name, value, size, flags);
+}
+
+const struct xattr_handler ext4_xattr_trusted_handler = {
+	.prefix	= XATTR_TRUSTED_PREFIX,
+	.list	= ext4_xattr_trusted_list,
+	.get	= ext4_xattr_trusted_get,
+	.set	= ext4_xattr_trusted_set,
+};

linux-7.2.3/fs/ext4/xattr_user.c

@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/fs/ext4/xattr_user.c
+ * Handler for extended user attributes.
+ *
+ * Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
+ */
+
+#include <linux/string.h>
+#include <linux/fs.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"
+#include "xattr.h"
+
+static bool
+ext4_xattr_user_list(struct dentry *dentry)
+{
+	return test_opt(dentry->d_sb, XATTR_USER);
+}
+
+static int
+ext4_xattr_user_get(const struct xattr_handler *handler,
+		    struct dentry *unused, struct inode *inode,
+		    const char *name, void *buffer, size_t size)
+{
+	if (!test_opt(inode->i_sb, XATTR_USER))
+		return -EOPNOTSUPP;
+	return ext4_xattr_get(inode, EXT4_XATTR_INDEX_USER,
+			      name, buffer, size);
+}
+
+static int
+ext4_xattr_user_set(const struct xattr_handler *handler,
+		    struct mnt_idmap *idmap,
+		    struct dentry *unused, struct inode *inode,
+		    const char *name, const void *value,
+		    size_t size, int flags)
+{
+	if (!test_opt(inode->i_sb, XATTR_USER))
+		return -EOPNOTSUPP;
+	return ext4_xattr_set(inode, EXT4_XATTR_INDEX_USER,
+			      name, value, size, flags);
+}
+
+const struct xattr_handler ext4_xattr_user_handler = {
+	.prefix	= XATTR_USER_PREFIX,
+	.list	= ext4_xattr_user_list,
+	.get	= ext4_xattr_user_get,
+	.set	= ext4_xattr_user_set,
+};