0.3.5

This release adds support for reading compressed files of arbitrary
on-disk size, which is becoming more and more necessary in recent ipsw
images.

A number of bugs are addressed for systems with little ram, reported by
Gilgamesh via email.

Support is added for the 6.6 kernel version, mainly thanks to Woody
Suwalski. I'm afraid the driver sometimes triggers a warning for recent
kernels, but I didn't manage to fix it in time for the new upstream
release, and it's better to at least get things to build.

Signed-off-by: Ernesto A. Fernández <ernesto@corellium.com>

apfs.h

@@ -299,6 +299,7 @@ struct apfs_sb_info {
 	struct apfs_crypto_state_val *s_dflt_pfk; /* default per-file key */
 
 	struct apfs_vol_transaction s_transaction;
+	int s_trans_buffers_max;
 
 	struct inode *s_private_dir;	/* Inode for the private directory */
 };
@@ -319,8 +320,10 @@ static inline bool apfs_is_sealed(struct super_block *sb)
  * apfs_vol_is_encrypted - Check if a volume is encrypting files
  * @sb: superblock
  */
-static inline bool apfs_vol_is_encrypted(struct super_block *sb) {
+static inline bool apfs_vol_is_encrypted(struct super_block *sb)
+{
 	struct apfs_superblock *vsb_raw = APFS_SB(sb)->s_vsb_raw;
+
 	return (vsb_raw->apfs_fs_flags & cpu_to_le64(APFS_FS_UNENCRYPTED)) == 0;
 }
 
@@ -646,7 +649,9 @@ static inline u32 apfs_query_storage(struct apfs_query *query)
 		return APFS_OBJ_PHYSICAL;
 	if (query->flags & APFS_QUERY_OMAP_SNAP)
 		return APFS_OBJ_PHYSICAL;
-	BUG();
+
+	/* Absurd, but don't panic: let the callers fail and report it */
+	return -1;
 }
 
 /*
@@ -774,6 +779,15 @@ struct apfs_xattr {
 	bool has_dstream;
 };
 
+struct apfs_compressed_data {
+	bool has_dstream;
+	u64 size;
+	union {
+		struct apfs_dstream_info *dstream;
+		void *data;
+	};
+};
+
 /*
  * Report function name and line number for the message types that are likely
  * to signal a bug, to make things easier for reporters. Don't do this for the
@@ -788,7 +802,7 @@ struct apfs_xattr {
 #define apfs_info(sb, fmt, ...) apfs_msg(sb, KERN_INFO, NULL, 0, fmt, ##__VA_ARGS__)
 
 #ifdef CONFIG_APFS_DEBUG
-#define ASSERT(expr)	BUG_ON(!(expr))
+#define ASSERT(expr)	WARN_ON(!(expr))
 #define apfs_debug(sb, fmt, ...) apfs_msg(sb, KERN_DEBUG, __func__, __LINE__, fmt, ##__VA_ARGS__)
 #else
 #define ASSERT(expr)	((void)0)
@@ -891,8 +905,11 @@ extern loff_t apfs_remap_file_range(struct file *src_file, loff_t off, struct fi
 extern int apfs_clone_file_range(struct file *src_file, loff_t off, struct file *dst_file, loff_t destoff, u64 len);
 #endif
 extern int apfs_clone_extents(struct apfs_dstream_info *dstream, u64 new_id);
+extern int apfs_nonsparse_dstream_read(struct apfs_dstream_info *dstream, void *buf, size_t count, u64 offset);
+extern void apfs_nonsparse_dstream_preread(struct apfs_dstream_info *dstream);
 
 /* file.c */
+extern int apfs_file_mmap(struct file *file, struct vm_area_struct *vma);
 extern int apfs_fsync(struct file *file, loff_t start, loff_t end, int datasync);
 
 /* inode.c */
@@ -920,7 +937,11 @@ extern int apfs_setattr(struct mnt_idmap *idmap,
 			struct dentry *dentry, struct iattr *iattr);
 #endif
 
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 extern int apfs_update_time(struct inode *inode, struct timespec64 *time, int flags);
+#else
+extern int apfs_update_time(struct inode *inode, int flags);
+#endif
 long apfs_dir_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 long apfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 
@@ -1033,6 +1054,9 @@ extern int apfs_xattr_set(struct inode *inode, const char *name, const void *val
 			  size_t size, int flags);
 extern int APFS_XATTR_SET_MAXOPS(void);
 extern ssize_t apfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
+extern int apfs_xattr_get_compressed_data(struct inode *inode, const char *name, struct apfs_compressed_data *cdata);
+extern void apfs_release_compressed_data(struct apfs_compressed_data *cdata);
+extern int apfs_compressed_data_read(struct apfs_compressed_data *cdata, void *buf, size_t count, u64 offset);
 
 /* xfield.c */
 extern int apfs_find_xfield(u8 *xfields, int len, u8 xtype, char **xval);
@@ -1046,6 +1070,7 @@ extern int apfs_insert_xfield(u8 *buffer, int buflen,
  */
 
 /* compress.c */
+extern const struct address_space_operations apfs_compress_aops;
 extern const struct file_operations apfs_compress_file_operations;
 
 /* dir.c */

apfs_raw.h

@@ -306,7 +306,7 @@ struct apfs_wrapped_crypto_state {
 	__le32 key_os_version;
 	__le16 key_revision;
 	__le16 key_len;
-	u8 persistent_key[0];
+	u8 persistent_key[];
 } __packed;
 
 /*
@@ -503,7 +503,7 @@ struct apfs_dir_stats_val {
 struct apfs_sibling_val {
 	__le64 parent_id;
 	__le16 name_len;
-	u8 name[0];
+	u8 name[];
 } __packed;
 
 /*
@@ -622,7 +622,7 @@ enum {
 struct apfs_drec_key {
 	struct apfs_key_header hdr;
 	__le16 name_len;
-	u8 name[0];
+	u8 name[];
 } __packed;
 
 /*
@@ -632,7 +632,7 @@ struct apfs_drec_key {
 struct apfs_drec_hashed_key {
 	struct apfs_key_header hdr;
 	__le32 name_len_and_hash;
-	u8 name[0];
+	u8 name[];
 } __packed;
 
 /*
@@ -641,7 +641,7 @@ struct apfs_drec_hashed_key {
 struct apfs_xattr_key {
 	struct apfs_key_header hdr;
 	__le16 name_len;
-	u8 name[0];
+	u8 name[];
 } __packed;
 
 /*
@@ -660,7 +660,7 @@ struct apfs_snap_metadata_key {
 struct apfs_snap_name_key {
 	struct apfs_key_header hdr;
 	__le16 name_len;
-	u8 name[0];
+	u8 name[];
 } __packed;
 
 /*
@@ -1278,7 +1278,7 @@ enum {
 struct apfs_xattr_val {
 	__le16 flags;
 	__le16 xdata_len;
-	u8 xdata[0];
+	u8 xdata[];
 } __packed;
 
 /*
@@ -1372,7 +1372,7 @@ struct apfs_file_info_key {
 struct apfs_file_data_hash_val {
 	__le16	hashed_len;
 	u8	hash_size;
-	u8	hash[0];
+	u8	hash[];
 } __packed;
 
 #define APFS_FILE_INFO_DATA_HASH	1
@@ -1435,7 +1435,7 @@ struct apfs_compress_rsrc_data {
 	struct apfs_compress_rsrc_block {
 		__le32 offs;
 		__le32 size;
-	} __packed block[0];
+	} __packed block[];
 } __packed;
 
 /*
@@ -1456,7 +1456,7 @@ struct apfs_snap_metadata_val {
 	__le32 extentref_tree_type;
 	__le32 flags;
 	__le16 name_len;
-	u8 name[0];
+	u8 name[];
 } __packed;
 
 /*
@@ -1475,7 +1475,7 @@ struct apfs_snap_meta_ext {
 	__le32	sme_version;
 	__le32	sme_flags;
 	__le64	sme_snap_xid;
-	char 	sme_uuid[UUID_SIZE];
+	char	sme_uuid[UUID_SIZE];
 	__le64	sme_token;
 } __packed;
 
@@ -1503,11 +1503,11 @@ enum {
  * Structure of a single entry in the keybag
  */
 struct apfs_keybag_entry {
-	char 	ke_uuid[UUID_SIZE];
+	char	ke_uuid[UUID_SIZE];
 	__le16	ke_tag;
 	__le16	ke_keylen;
 	__le32	padding;
-	u8	ke_keydata[0];
+	u8	ke_keydata[];
 } __packed;
 
 #define APFS_KEYBAG_VERSION	2
@@ -1520,7 +1520,7 @@ struct apfs_kb_locker {
 	__le16				kl_nkeys;
 	__le32				kl_nbytes;
 	__le64				padding;
-	struct apfs_keybag_entry	kl_entries[0];
+	struct apfs_keybag_entry	kl_entries[];
 } __packed;
 
 #endif	/* _APFS_RAW_H */

btree.c

@@ -842,11 +842,10 @@ int apfs_btree_remove(struct apfs_query *query)
 		if (query->parent) {
 			/* Just get rid of the node */
 			return apfs_delete_node(query);
-		} else {
-			/* All descendants are gone, root is the whole tree */
-			node_raw->btn_level = 0;
-			node->flags |= APFS_BTNODE_LEAF;
 		}
+		/* All descendants are gone, root is the whole tree */
+		node_raw->btn_level = 0;
+		node->flags |= APFS_BTNODE_LEAF;
 	}
 
 	/* The first key in a node must match the parent record's */
@@ -956,7 +955,7 @@ again:
 		if (!query->parent && !apfs_node_is_root(node)) {
 			if (node->records == 1) {
 				/* Node is defragmented, ENOSPC is absurd */
-				WARN_ON(1);
+				apfs_alert(sb, "absurd ENOSPC in empty node");
 				return -EFSCORRUPTED;
 			}
 			err = apfs_query_refresh(query);

dir.c

@@ -268,7 +268,7 @@ static int apfs_build_dentry_unhashed_key(struct qstr *qname, u64 parent_id,
 
 	apfs_key_set_hdr(APFS_TYPE_DIR_REC, parent_id, key);
 	key->name_len = cpu_to_le16(namelen);
-	strcpy(key->name, qname->name);
+	strscpy(key->name, qname->name, namelen);
 
 	*key_p = key;
 	return key_len;
@@ -297,7 +297,7 @@ static int apfs_build_dentry_hashed_key(struct qstr *qname, u64 hash, u64 parent
 
 	apfs_key_set_hdr(APFS_TYPE_DIR_REC, parent_id, key);
 	key->name_len_and_hash = cpu_to_le32(namelen | hash);
-	strcpy(key->name, qname->name);
+	strscpy(key->name, qname->name, namelen);
 
 	*key_p = key;
 	return key_len;
@@ -434,7 +434,7 @@ static int apfs_build_sibling_val(struct dentry *dentry,
 
 	val->parent_id = cpu_to_le64(apfs_ino(parent));
 	val->name_len = cpu_to_le16(namelen);
-	strcpy(val->name, qname->name);
+	strscpy(val->name, qname->name, namelen);
 
 	*val_p = val;
 	return val_len;
@@ -601,7 +601,11 @@ static int apfs_create_dentry(struct dentry *dentry, struct inode *inode)
 	}
 
 	/* Now update the parent inode */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 	parent->i_mtime = parent->i_ctime = current_time(inode);
+#else
+	parent->i_mtime = inode_set_ctime_current(parent);
+#endif
 	++APFS_I(parent)->i_nchildren;
 	apfs_inode_join_transaction(parent->i_sb, parent);
 	return 0;
@@ -841,7 +845,11 @@ static int __apfs_link(struct dentry *old_dentry, struct dentry *dentry)
 
 	/* First update the inode's link count */
 	inc_nlink(inode);
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 	inode->i_ctime = current_time(inode);
+#else
+	inode_set_ctime_current(inode);
+#endif
 	apfs_inode_join_transaction(inode->i_sb, inode);
 
 	if (inode->i_nlink == 2) {
@@ -1030,7 +1038,11 @@ static int apfs_delete_dentry(struct dentry *dentry)
 	}
 
 	/* Now update the parent inode */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 	parent->i_mtime = parent->i_ctime = current_time(parent);
+#else
+	parent->i_mtime = inode_set_ctime_current(parent);
+#endif
 	--APFS_I(parent)->i_nchildren;
 	apfs_inode_join_transaction(sb, parent);
 	return err;
@@ -1089,7 +1101,7 @@ static int apfs_sibling_link_from_query(struct apfs_query *query,
 	*name = kmalloc(namelen, GFP_KERNEL);
 	if (!*name)
 		return -ENOMEM;
-	strcpy(*name, siblink->name);
+	strscpy(*name, siblink->name, namelen);
 	*parent = le64_to_cpu(siblink->parent_id);
 	return 0;
 }
@@ -1194,7 +1206,11 @@ static int apfs_create_orphan_link(struct inode *inode)
 	}
 
 	/* Now update the child count for private-dir */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 	priv_dir->i_mtime = priv_dir->i_ctime = current_time(priv_dir);
+#else
+	priv_dir->i_mtime = inode_set_ctime_current(priv_dir);
+#endif
 	++APFS_I(priv_dir)->i_nchildren;
 	apfs_inode_join_transaction(sb, priv_dir);
 
@@ -1239,7 +1255,11 @@ int apfs_delete_orphan_link(struct inode *inode)
 	}
 
 	/* Now update the child count for private-dir */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 	priv_dir->i_mtime = priv_dir->i_ctime = current_time(priv_dir);
+#else
+	priv_dir->i_mtime = inode_set_ctime_current(priv_dir);
+#endif
 	--APFS_I(priv_dir)->i_nchildren;
 	apfs_inode_join_transaction(sb, priv_dir);
 
@@ -1330,7 +1350,11 @@ static int __apfs_unlink(struct inode *dir, struct dentry *dentry)
 	if (err)
 		goto fail;
 
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 	inode->i_ctime = dir->i_ctime;
+#else
+	inode_set_ctime_to_ts(inode, inode_get_ctime(dir));
+#endif
 	/* TODO: defer write of the primary name? */
 	err = apfs_update_inode(inode, primary_name);
 	if (err)

dkms.conf

@@ -1,5 +1,5 @@
 PACKAGE_NAME="linux-apfs-rw"
-PACKAGE_VERSION="0.3.3"
+PACKAGE_VERSION="0.3.5"
 
 BUILT_MODULE_NAME[0]="apfs"
 DEST_MODULE_LOCATION[0]="/extra"

extents.c

@@ -5,6 +5,7 @@
 
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
+#include <linux/blk_types.h>
 #include "apfs.h"
 
 #define MAX(X, Y)	((X) <= (Y) ? (Y) : (X))
@@ -46,7 +47,7 @@ int apfs_extent_from_query(struct apfs_query *query,
 	char *raw = query->node->object.data;
 	u64 ext_len;
 
-	if(!apfs_is_sealed(sb)) {
+	if (!apfs_is_sealed(sb)) {
 		struct apfs_file_extent_val *ext = NULL;
 		struct apfs_file_extent_key *ext_key = NULL;
 
@@ -601,7 +602,7 @@ static int apfs_update_mid_extent(struct apfs_dstream_info *dstream, const struc
 	raw_key.logical_addr = cpu_to_le64(extent->logical_addr);
 	raw_val.len_and_flags = cpu_to_le64(extent->len);
 	raw_val.phys_block_num = cpu_to_le64(extent->phys_block_num);
-	if(apfs_vol_is_encrypted(sb))
+	if (apfs_vol_is_encrypted(sb))
 		new_crypto = extent_id;
 	else
 		new_crypto = 0;
@@ -1703,7 +1704,11 @@ int apfs_clone_file_range(struct file *src_file, loff_t off, struct file *dst_fi
 	}
 	src_ds->ds_shared = true;
 
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 	dst_inode->i_mtime = dst_inode->i_ctime = current_time(dst_inode);
+#else
+	dst_inode->i_mtime = inode_set_ctime_current(dst_inode);
+#endif
 	dst_inode->i_size = src_inode->i_size;
 	dst_ai->i_key_class = src_ai->i_key_class;
 	dst_ai->i_int_flags = src_ai->i_int_flags;
@@ -2130,3 +2135,139 @@ int apfs_clone_extents(struct apfs_dstream_info *dstream, u64 new_id)
 	}
 	return 0;
 }
+
+/**
+ * apfs_nonsparse_dstream_read - Read from a dstream without holes
+ * @dstream:	dstream to read
+ * @buf:	destination buffer
+ * @count:	exact number of bytes to read
+ * @offset:	dstream offset to read from
+ *
+ * Returns 0 on success or a negative error code in case of failure.
+ */
+int apfs_nonsparse_dstream_read(struct apfs_dstream_info *dstream, void *buf, size_t count, u64 offset)
+{
+	struct super_block *sb = dstream->ds_sb;
+	u64 logical_start_block, logical_end_block, log_bno, blkcnt, idx;
+	struct buffer_head **bhs = NULL;
+	int ret = 0;
+
+	/* Save myself from thinking about overflow here */
+	if (count >= APFS_MAX_FILE_SIZE || offset >= APFS_MAX_FILE_SIZE) {
+		apfs_err(sb, "dstream read overflow (0x%llx-0x%llx)", offset, (unsigned long long)count);
+		return -EFBIG;
+	}
+
+	if (offset + count > dstream->ds_size) {
+		apfs_err(sb, "reading past the end (0x%llx-0x%llx)", offset, (unsigned long long)count);
+		/* No caller is expected to legitimately read out-of-bounds */
+		return -EFSCORRUPTED;
+	}
+
+	logical_start_block = offset >> sb->s_blocksize_bits;
+	logical_end_block = (offset + count + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
+	blkcnt = logical_end_block - logical_start_block;
+	bhs = kcalloc(blkcnt, sizeof(*bhs), GFP_KERNEL);
+	if (!bhs)
+		return -ENOMEM;
+
+	for (log_bno = logical_start_block; log_bno < logical_end_block; log_bno++) {
+		struct buffer_head *bh = NULL;
+		u64 bno = 0;
+
+		idx = log_bno - logical_start_block;
+
+		ret = apfs_logic_to_phys_bno(dstream, log_bno, &bno);
+		if (ret)
+			goto out;
+		if (bno == 0) {
+			apfs_err(sb, "nonsparse dstream has a hole");
+			ret = -EFSCORRUPTED;
+			goto out;
+		}
+
+		bhs[idx] = __getblk_gfp(APFS_NXI(sb)->nx_bdev, bno, sb->s_blocksize, __GFP_MOVABLE);
+		if (!bhs[idx]) {
+			apfs_err(sb, "failed to map block 0x%llx", bno);
+			ret = -EIO;
+			goto out;
+		}
+
+		bh = bhs[idx];
+		if (!buffer_uptodate(bh)) {
+			get_bh(bh);
+			lock_buffer(bh);
+			bh->b_end_io = end_buffer_read_sync;
+			apfs_submit_bh(REQ_OP_READ, 0, bh);
+		}
+	}
+
+	for (log_bno = logical_start_block; log_bno < logical_end_block; log_bno++) {
+		int off_in_block, left_in_block;
+
+		idx = log_bno - logical_start_block;
+		wait_on_buffer(bhs[idx]);
+		if (!buffer_uptodate(bhs[idx])) {
+			apfs_err(sb, "failed to read a block");
+			ret = -EIO;
+			goto out;
+		}
+
+		if (log_bno == logical_start_block)
+			off_in_block = offset & (sb->s_blocksize - 1);
+		else
+			off_in_block = 0;
+
+		if (log_bno == logical_end_block - 1)
+			left_in_block = count + offset - (log_bno << sb->s_blocksize_bits) - off_in_block;
+		else
+			left_in_block = sb->s_blocksize - off_in_block;
+
+		memcpy(buf, bhs[idx]->b_data + off_in_block, left_in_block);
+		buf += left_in_block;
+	}
+
+out:
+	if (bhs) {
+		for (idx = 0; idx < blkcnt; idx++)
+			brelse(bhs[idx]);
+		kfree(bhs);
+	}
+	return ret;
+}
+
+/**
+ * apfs_nonsparse_dstream_preread - Attempt to preread a dstream without holes
+ * @dstream:	dstream to preread
+ *
+ * Requests reads for all blocks of a dstream, but doesn't wait for the result.
+ */
+void apfs_nonsparse_dstream_preread(struct apfs_dstream_info *dstream)
+{
+	struct super_block *sb = dstream->ds_sb;
+	u64 logical_end_block, log_bno;
+
+	logical_end_block = (dstream->ds_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
+
+	for (log_bno = 0; log_bno < logical_end_block; log_bno++) {
+		struct buffer_head *bh = NULL;
+		u64 bno = 0;
+		int ret;
+
+		ret = apfs_logic_to_phys_bno(dstream, log_bno, &bno);
+		if (ret || bno == 0)
+			return;
+
+		bh = __getblk_gfp(APFS_NXI(sb)->nx_bdev, bno, sb->s_blocksize, __GFP_MOVABLE);
+		if (!bh)
+			return;
+		if (!buffer_uptodate(bh)) {
+			get_bh(bh);
+			lock_buffer(bh);
+			bh->b_end_io = end_buffer_read_sync;
+			apfs_submit_bh(REQ_OP_READ, 0, bh);
+		}
+		brelse(bh);
+		bh = NULL;
+	}
+}

file.c

@@ -99,7 +99,11 @@ out_abort:
 	apfs_transaction_abort(sb);
 out:
 	if (err)
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 		ret = block_page_mkwrite_return(err);
+#else
+		ret = vmf_fs_error(err);
+#endif
 	sb_end_pagefault(inode->i_sb);
 	return ret;
 }
@@ -110,7 +114,7 @@ static const struct vm_operations_struct apfs_file_vm_ops = {
 	.page_mkwrite	= apfs_page_mkwrite,
 };
 
-static int apfs_file_mmap(struct file * file, struct vm_area_struct * vma)
+int apfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct address_space *mapping = file->f_mapping;
 
@@ -155,6 +159,13 @@ const struct file_operations apfs_file_operations = {
 #else
 	.clone_file_range	= apfs_clone_file_range,
 #endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 5, 0)
+	.splice_read		= generic_file_splice_read,
+#else
+	.splice_read		= filemap_splice_read,
+#endif
+	.splice_write		= iter_file_splice_write,
 };
 
 #if LINUX_VERSION_CODE == KERNEL_VERSION(5, 3, 0)

inode.c

@@ -288,14 +288,16 @@ static int apfs_create_crypto_rec(struct inode *inode)
 		goto out;
 
 	apfs_key_set_hdr(APFS_TYPE_CRYPTO_STATE, dstream->ds_id, &raw_key);
-	if(sbi->s_dflt_pfk) {
+	if (sbi->s_dflt_pfk) {
 		struct apfs_crypto_state_val *raw_val = sbi->s_dflt_pfk;
-		unsigned key_len = le16_to_cpu(raw_val->state.key_len);
+		unsigned int key_len = le16_to_cpu(raw_val->state.key_len);
+
 		ret = apfs_btree_insert(query, &raw_key, sizeof(raw_key), raw_val, sizeof(*raw_val) + key_len);
 		if (ret)
 			apfs_err(sb, "insertion failed for id 0x%llx", dstream->ds_id);
 	} else {
 		struct apfs_crypto_state_val raw_val;
+
 		raw_val.refcnt = cpu_to_le32(1);
 		raw_val.state.major_version = cpu_to_le16(APFS_WMCS_MAJOR_VERSION);
 		raw_val.state.minor_version = cpu_to_le16(APFS_WMCS_MINOR_VERSION);
@@ -318,7 +320,7 @@ out:
  * apfs_dflt_key_class - Returns default key class for files in volume
  * @sb: volume superblock
  */
-static unsigned apfs_dflt_key_class(struct super_block *sb)
+static unsigned int apfs_dflt_key_class(struct super_block *sb)
 {
 	struct apfs_sb_info *sbi = APFS_SB(sb);
 
@@ -399,7 +401,7 @@ static int apfs_crypto_set_key(struct super_block *sb, u64 crypto_id, struct apf
 	struct apfs_crypto_state_val *raw_val;
 	char *raw;
 	int ret;
-	unsigned pfk_len;
+	unsigned int pfk_len;
 
 	if (!crypto_id)
 		return 0;
@@ -441,7 +443,7 @@ out:
  * @max_len: maximum allowed value of val->state.key_len
  */
 static int apfs_crypto_get_key(struct super_block *sb, u64 crypto_id, struct apfs_crypto_state_val *val,
-			       unsigned max_len)
+			       unsigned int max_len)
 {
 	struct apfs_sb_info *sbi = APFS_SB(sb);
 	struct apfs_key key;
@@ -449,7 +451,7 @@ static int apfs_crypto_get_key(struct super_block *sb, u64 crypto_id, struct apf
 	struct apfs_crypto_state_val *raw_val;
 	char *raw;
 	int ret;
-	unsigned pfk_len;
+	unsigned int pfk_len;
 
 	if (!crypto_id)
 		return -ENOENT;
@@ -468,7 +470,7 @@ static int apfs_crypto_get_key(struct super_block *sb, u64 crypto_id, struct apf
 	raw_val = (void *)raw + query->off;
 
 	pfk_len = le16_to_cpu(raw_val->state.key_len);
-	if(pfk_len > max_len) {
+	if (pfk_len > max_len) {
 		ret = -ENOSPC;
 		goto out;
 	}
@@ -501,7 +503,7 @@ int __apfs_write_begin(struct file *file, struct address_space *mapping, loff_t
 		return err;
 	}
 
-	if(apfs_vol_is_encrypted(sb)) {
+	if (apfs_vol_is_encrypted(sb)) {
 		err = apfs_create_crypto_rec(inode);
 		if (err) {
 			apfs_err(sb, "crypto creation failed for ino 0x%llx", apfs_ino(inode));
@@ -679,6 +681,12 @@ static void apfs_noop_invalidate_folio(struct folio *folio, size_t offset, size_
 
 /* bmap is not implemented to avoid issues with CoW on swapfiles */
 static const struct address_space_operations apfs_aops = {
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 18, 0)
+	.dirty_folio	= block_dirty_folio,
+#elif LINUX_VERSION_CODE >= KERNEL_VERSION(5, 14, 0)
+	.set_page_dirty	= __set_page_dirty_buffers,
+#endif
+
 #if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 19, 0)
 	.read_folio	= apfs_read_folio,
 #else
@@ -716,11 +724,13 @@ static void apfs_inode_set_ops(struct inode *inode, dev_t rdev, bool compressed)
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
 		inode->i_op = &apfs_file_inode_operations;
-		if (compressed)
+		if (compressed) {
 			inode->i_fop = &apfs_compress_file_operations;
-		else
+			inode->i_mapping->a_ops = &apfs_compress_aops;
+		} else {
 			inode->i_fop = &apfs_file_operations;
-		inode->i_mapping->a_ops = &apfs_aops;
+			inode->i_mapping->a_ops = &apfs_aops;
+		}
 		break;
 	case S_IFDIR:
 		inode->i_op = &apfs_dir_inode_operations;
@@ -790,7 +800,11 @@ static int apfs_inode_from_query(struct apfs_query *query, struct inode *inode)
 	}
 
 	inode->i_atime = ns_to_timespec64(le64_to_cpu(inode_val->access_time));
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 	inode->i_ctime = ns_to_timespec64(le64_to_cpu(inode_val->change_time));
+#else
+	inode_set_ctime_to_ts(inode, ns_to_timespec64(le64_to_cpu(inode_val->change_time)));
+#endif
 	inode->i_mtime = ns_to_timespec64(le64_to_cpu(inode_val->mod_time));
 	ai->i_crtime = ns_to_timespec64(le64_to_cpu(inode_val->create_time));
 
@@ -1073,8 +1087,10 @@ int apfs_getattr(struct mnt_idmap *idmap,
 	generic_fillattr(inode, stat);
 #elif LINUX_VERSION_CODE < KERNEL_VERSION(6, 3, 0)
 	generic_fillattr(mnt_userns, inode, stat);
-#else
+#elif LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 	generic_fillattr(idmap, inode, stat);
+#else
+	generic_fillattr(idmap, request_mask, inode, stat);
 #endif
 
 	stat->ino = apfs_ino(inode);
@@ -1225,7 +1241,7 @@ static int apfs_create_dstream_xfield(struct inode *inode,
 
 	dstream_raw.size = cpu_to_le64(inode->i_size);
 	dstream_raw.alloced_size = cpu_to_le64(apfs_alloced_size(dstream));
-	if(apfs_vol_is_encrypted(inode->i_sb))
+	if (apfs_vol_is_encrypted(inode->i_sb))
 		dstream_raw.default_crypto_id = cpu_to_le64(dstream->ds_id);
 
 	/* TODO: can we assume that all inode records have an xfield blob? */
@@ -1477,7 +1493,12 @@ int apfs_update_inode(struct inode *inode, char *new_name)
 		inode_raw->group = cpu_to_le32(ai->i_saved_gid);
 
 	inode_raw->access_time = cpu_to_le64(timespec64_to_ns(&inode->i_atime));
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 	inode_raw->change_time = cpu_to_le64(timespec64_to_ns(&inode->i_ctime));
+#else
+	struct timespec64 ictime = inode_get_ctime(inode);
+	inode_raw->change_time = cpu_to_le64(timespec64_to_ns(&ictime));
+#endif
 	inode_raw->mod_time = cpu_to_le64(timespec64_to_ns(&inode->i_mtime));
 	inode_raw->create_time = cpu_to_le64(timespec64_to_ns(&ai->i_crtime));
 
@@ -1657,7 +1678,12 @@ struct inode *apfs_new_inode(struct inode *dir, umode_t mode, dev_t rdev)
 	dstream->ds_shared = false;
 
 	now = current_time(inode);
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 	inode->i_atime = inode->i_mtime = inode->i_ctime = ai->i_crtime = now;
+#else
+	inode_set_ctime_to_ts(inode, now);
+	inode->i_atime = inode->i_mtime = ai->i_crtime = now;
+#endif
 	vsb_raw->apfs_last_mod_time = cpu_to_le64(timespec64_to_ns(&now));
 
 	if (S_ISREG(mode))
@@ -1751,7 +1777,11 @@ static int apfs_setsize(struct inode *inode, loff_t new_size)
 
 	if (new_size == inode->i_size)
 		return 0;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 	inode->i_mtime = inode->i_ctime = current_time(inode);
+#else
+	inode->i_mtime = inode_set_ctime_current(inode);
+#endif
 
 	err = apfs_inode_create_dstream_rec(inode);
 	if (err) {
@@ -1837,7 +1867,11 @@ fail:
 }
 
 /* TODO: this only seems to be necessary because ->write_inode() isn't firing */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 int apfs_update_time(struct inode *inode, struct timespec64 *time, int flags)
+#else
+int apfs_update_time(struct inode *inode, int flags)
+#endif
 {
 	struct super_block *sb = inode->i_sb;
 	struct apfs_max_ops maxops;
@@ -1851,9 +1885,11 @@ int apfs_update_time(struct inode *inode, struct timespec64 *time, int flags)
 		return err;
 	apfs_inode_join_transaction(sb, inode);
 
-	err = generic_update_time(inode, time, flags);
-	if (err)
-		goto fail;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
+	generic_update_time(inode, time, flags);
+#else
+	generic_update_time(inode, flags);
+#endif
 
 	err = apfs_transaction_commit(sb);
 	if (err)
@@ -1873,7 +1909,7 @@ static int apfs_ioc_set_dflt_pfk(struct file *file, void __user *user_pfk)
 	struct apfs_nxsb_info *nxi = APFS_NXI(sb);
 	struct apfs_wrapped_crypto_state pfk_hdr;
 	struct apfs_crypto_state_val *pfk;
-	unsigned key_len;
+	unsigned int key_len;
 
 	if (__copy_from_user(&pfk_hdr, user_pfk, sizeof(pfk_hdr)))
 		return -EFAULT;
@@ -1940,7 +1976,7 @@ static int apfs_ioc_set_pfk(struct file *file, void __user *user_pfk)
 	struct apfs_inode_info *ai = APFS_I(inode);
 	struct apfs_dstream_info *dstream = &ai->i_dstream;
 	struct apfs_max_ops maxops;
-	unsigned key_len, key_class;
+	unsigned int key_len, key_class;
 	int err;
 
 	if (__copy_from_user(&pfk_hdr, user_pfk, sizeof(pfk_hdr)))
@@ -2007,7 +2043,7 @@ static int apfs_ioc_get_pfk(struct file *file, void __user *user_pfk)
 	struct apfs_nxsb_info *nxi = APFS_NXI(sb);
 	struct apfs_wrapped_crypto_state pfk_hdr;
 	struct apfs_crypto_state_val *pfk;
-	unsigned max_len, key_len;
+	unsigned int max_len, key_len;
 	struct apfs_dstream_info *dstream = &APFS_I(inode)->i_dstream;
 	int err;
 
@@ -2274,7 +2310,11 @@ int apfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fil
 
 	apfs_inode_join_transaction(sb, inode);
 	apfs_setflags(inode, fa->flags);
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 6, 0)
 	inode->i_ctime = current_time(inode);
+#else
+	inode_set_ctime_current(inode);
+#endif
 
 	err = apfs_transaction_commit(sb);
 	if (err)

node.c

@@ -108,6 +108,9 @@ struct apfs_node *apfs_read_node(struct super_block *sb, u64 oid, u32 storage,
 			return (void *)bh;
 		}
 		break;
+	default:
+		apfs_alert(sb, "invalid storage type %u - bug!", storage);
+		return ERR_PTR(-EINVAL);
 	}
 	raw = (struct apfs_btree_node_phys *) bh->b_data;
 
@@ -374,8 +377,8 @@ static struct apfs_node *apfs_create_node(struct super_block *sb, u32 storage)
 		}
 		break;
 	default:
-		ASSERT(false);
-		return ERR_PTR(-EINVAL); /* Prevent compiler warnings */
+		apfs_alert(sb, "invalid storage type %u - bug!", storage);
+		return ERR_PTR(-EINVAL);
 	}
 
 	bh = apfs_getblk(sb, bno);
@@ -869,6 +872,7 @@ int apfs_node_query(struct super_block *sb, struct apfs_query *query)
 	left = 0;
 	do {
 		struct apfs_key curr_key;
+
 		if (cmp > 0) {
 			right = query->index - 1;
 			if (right < left) {

snapshot.c

@@ -116,7 +116,7 @@ static int apfs_create_snap_metadata_rec(struct inode *mntpoint, struct apfs_nod
 	raw_val->extentref_tree_type = vsb_raw->apfs_extentref_tree_type;
 	raw_val->flags = 0;
 	raw_val->name_len = cpu_to_le16(name_len + 1); /* Count the null byte */
-	strcpy(raw_val->name, name);
+	strscpy(raw_val->name, name, name_len + 1);
 
 	apfs_assert_in_transaction(sb, &vsb_raw->apfs_o);
 	raw_val->inum = vsb_raw->apfs_next_obj_id;
@@ -173,7 +173,7 @@ static int apfs_create_snap_name_rec(struct apfs_node *snap_root, const char *na
 	}
 	apfs_key_set_hdr(APFS_TYPE_SNAP_NAME, APFS_SNAP_NAME_OBJ_ID, raw_key);
 	raw_key->name_len = cpu_to_le16(name_len + 1); /* Count the null byte */
-	strcpy(raw_key->name, name);
+	strscpy(raw_key->name, name, name_len + 1);
 
 	raw_val.snap_xid = cpu_to_le64(APFS_NXI(sb)->nx_xid);
 

spaceman.c

@@ -361,7 +361,7 @@ static int apfs_flush_fq_rec(struct apfs_node *root, u64 xid, u64 *len)
 	}
 
 	for (bno = fqrec.bno; bno < fqrec.bno + fqrec.len; ++bno) {
-		if(apfs_block_in_ip(sm, bno))
+		if (apfs_block_in_ip(sm, bno))
 			err = apfs_ip_mark_free(sb, bno);
 		else
 			err = apfs_main_free(sb, bno);
@@ -406,7 +406,7 @@ static u64 apfs_free_queue_oldest_xid(struct apfs_node *root)
  *
  * Returns 0 on success or a negative error code in case of failure.
  */
-static int apfs_flush_free_queue(struct super_block *sb, unsigned qid)
+static int apfs_flush_free_queue(struct super_block *sb, unsigned int qid)
 {
 	struct apfs_nxsb_info *nxi = APFS_NXI(sb);
 	struct apfs_spaceman *sm = APFS_SM(sb);
@@ -829,7 +829,7 @@ static int apfs_chunk_alloc_free(struct super_block *sb,
 	if (!ci->ci_bitmap_addr) {
 		u64 bmap_bno;
 
-		if(!is_alloc) {
+		if (!is_alloc) {
 			apfs_err(sb, "attempt to free block in all-free chunk");
 			return -EFSCORRUPTED;
 		}
@@ -930,10 +930,9 @@ static int apfs_chunk_alloc_free(struct super_block *sb,
 	ci->ci_bitmap_addr = cpu_to_le64(bmap_bh->b_blocknr);
 	ASSERT(buffer_trans(*cib_bh));
 	set_buffer_csum(*cib_bh);
-	mark_buffer_dirty(*cib_bh);
 
 	/* Finally, allocate / free the actual block that was requested */
-	if(is_alloc) {
+	if (is_alloc) {
 		*bno = apfs_chunk_find_free(sb, bmap, le64_to_cpu(ci->ci_addr));
 		if (!*bno) {
 			apfs_err(sb, "no free blocks in chunk");
@@ -943,11 +942,10 @@ static int apfs_chunk_alloc_free(struct super_block *sb,
 		apfs_chunk_mark_used(sb, bmap, *bno);
 		sm->sm_free_count -= 1;
 	} else {
-		if(!apfs_chunk_mark_free(sb, bmap, *bno)) {
+		if (!apfs_chunk_mark_free(sb, bmap, *bno)) {
 			apfs_err(sb, "block already marked as free (0x%llx)", *bno);
 			le32_add_cpu(&ci->ci_free_count, -1);
 			set_buffer_csum(*cib_bh);
-			mark_buffer_dirty(*cib_bh);
 			err = -EFSCORRUPTED;
 		} else
 			sm->sm_free_count += 1;
@@ -1102,7 +1100,7 @@ static int apfs_main_free(struct super_block *sb, u64 bno)
 	u64 cib_bno;
 	int err;
 
-	if(!sm_raw->sm_blocks_per_chunk || !sm_raw->sm_chunks_per_cib) {
+	if (!sm_raw->sm_blocks_per_chunk || !sm_raw->sm_chunks_per_cib) {
 		apfs_err(sb, "block or chunk count not set");
 		return -EINVAL;
 	}

super.c

@@ -272,11 +272,13 @@ static void apfs_update_software_info(struct super_block *sb)
 	memmove(mod_by + 1, mod_by, (APFS_MAX_HIST - 1) * sizeof(*mod_by));
 
 	memset(mod_by->id, 0, sizeof(mod_by->id));
-	strcpy(mod_by->id, APFS_MODULE_ID_STRING);
+	strscpy(mod_by->id, APFS_MODULE_ID_STRING, sizeof(mod_by->id));
 	mod_by->timestamp = cpu_to_le64(ktime_get_real_ns());
 	mod_by->last_xid = cpu_to_le64(APFS_NXI(sb)->nx_xid);
 }
 
+static struct file_system_type apfs_fs_type;
+
 /**
  * apfs_unmap_main_super - Clean up apfs_map_main_super()
  * @sbi:	in-memory superblock info
@@ -286,11 +288,15 @@ static void apfs_update_software_info(struct super_block *sb)
 static inline void apfs_unmap_main_super(struct apfs_sb_info *sbi)
 {
 	struct apfs_nxsb_info *nxi = sbi->s_nxi;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 5, 0)
 	fmode_t mode = FMODE_READ | FMODE_EXCL;
+#endif
 	struct apfs_object *obj = NULL;
 
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 5, 0)
 	if (nxi->nx_flags & APFS_READWRITE)
 		mode |= FMODE_WRITE;
+#endif
 
 	lockdep_assert_held(&nxs_mutex);
 
@@ -304,7 +310,12 @@ static inline void apfs_unmap_main_super(struct apfs_sb_info *sbi)
 	obj->o_bh = NULL;
 	obj = NULL;
 
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 5, 0)
+	blkdev_put(nxi->nx_bdev, &apfs_fs_type);
+#else
 	blkdev_put(nxi->nx_bdev, mode);
+#endif
+
 	list_del(&nxi->nx_list);
 	kfree(nxi);
 out:
@@ -959,12 +970,15 @@ static int apfs_show_options(struct seq_file *seq, struct dentry *root)
 	return 0;
 }
 
-/* TODO: don't ignore @wait */
 int apfs_sync_fs(struct super_block *sb, int wait)
 {
 	struct apfs_max_ops maxops = {0};
 	int err;
 
+	/* TODO: actually start the commit and return without waiting? */
+	if (wait == 0)
+		return 0;
+
 	err = apfs_transaction_start(sb, maxops);
 	if (err)
 		return err;
@@ -1320,6 +1334,27 @@ static int apfs_setup_bdi(struct super_block *sb)
 
 #endif
 
+static void apfs_set_trans_buffer_limit(struct super_block *sb)
+{
+	struct apfs_sb_info *sbi = APFS_SB(sb);
+	unsigned long memsize_in_blocks;
+	struct sysinfo info = {0};
+
+	si_meminfo(&info);
+	memsize_in_blocks = info.totalram << (PAGE_SHIFT - sb->s_blocksize_bits);
+
+	/*
+	 * Buffer heads are not reclaimed while they are part of the current
+	 * transaction, so systems with little memory will crash if we don't
+	 * commit often enough. This hack should make that happen in general,
+	 * but I still need to get the reclaim to work eventually (TODO).
+	 */
+	if (memsize_in_blocks >= 16 * TRANSACTION_BUFFERS_MAX)
+		sbi->s_trans_buffers_max = TRANSACTION_BUFFERS_MAX;
+	else
+		sbi->s_trans_buffers_max = memsize_in_blocks / 16;
+}
+
 static int apfs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct apfs_sb_info *sbi = APFS_SB(sb);
@@ -1333,6 +1368,8 @@ static int apfs_fill_super(struct super_block *sb, void *data, int silent)
 	if (err)
 		return err;
 
+	apfs_set_trans_buffer_limit(sb);
+
 	sbi->s_uid = INVALID_UID;
 	sbi->s_gid = INVALID_GID;
 	err = parse_options(sb, data);
@@ -1445,13 +1482,12 @@ static int apfs_test_super(struct super_block *sb, void *data)
 static int apfs_set_super(struct super_block *sb, void *data)
 {
 	int err = set_anon_super(sb, data);
+
 	if (!err)
 		sb->s_fs_info = data;
 	return err;
 }
 
-static struct file_system_type apfs_fs_type;
-
 /*
  * Wrapper for lookup_bdev() that supports older kernels.
  */
@@ -1480,7 +1516,11 @@ static int apfs_lookup_bdev(const char *pathname, dev_t *dev)
  *
  * Returns 0 on success, or a negative error code in case of failure.
  */
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 5, 0)
+static int apfs_attach_nxi(struct apfs_sb_info *sbi, const char *dev_name, blk_mode_t mode)
+#else
 static int apfs_attach_nxi(struct apfs_sb_info *sbi, const char *dev_name, fmode_t mode)
+#endif
 {
 	struct apfs_nxsb_info *nxi;
 	dev_t dev = 0;
@@ -1500,7 +1540,11 @@ static int apfs_attach_nxi(struct apfs_sb_info *sbi, const char *dev_name, fmode
 		if (!nxi)
 			return -ENOMEM;
 
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 5, 0)
+		bdev = blkdev_get_by_path(dev_name, mode, &apfs_fs_type, NULL);
+#else
 		bdev = blkdev_get_by_path(dev_name, mode, &apfs_fs_type);
+#endif
 		if (IS_ERR(bdev)) {
 			kfree(nxi);
 			return PTR_ERR(bdev);
@@ -1527,7 +1571,11 @@ static struct dentry *apfs_mount(struct file_system_type *fs_type, int flags,
 	struct apfs_nxsb_info *nxi;
 	struct super_block *sb;
 	struct apfs_sb_info *sbi;
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 5, 0)
+	blk_mode_t mode = sb_open_mode(flags);
+#else
 	fmode_t mode = FMODE_READ | FMODE_EXCL;
+#endif
 	int error = 0;
 
 	mutex_lock(&nxs_mutex);
@@ -1544,8 +1592,10 @@ static struct dentry *apfs_mount(struct file_system_type *fs_type, int flags,
 	if (sbi->s_snap_name)
 		flags |= SB_RDONLY;
 
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 5, 0)
 	if (!(flags & SB_RDONLY))
 		mode |= FMODE_WRITE;
+#endif
 
 	error = apfs_attach_nxi(sbi, dev_name, mode);
 	if (error)
@@ -1572,7 +1622,9 @@ static struct dentry *apfs_mount(struct file_system_type *fs_type, int flags,
 		error = apfs_map_main_super(sb);
 		if (error)
 			goto out_deactivate_super;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(6, 5, 0)
 		sb->s_mode = mode;
+#endif
 		snprintf(sb->s_id, sizeof(sb->s_id), "%xg", sb->s_dev);
 		error = apfs_fill_super(sb, data, flags & SB_SILENT ? 1 : 0);
 		if (error)

transaction.c

@@ -531,7 +531,7 @@ fail:
 static void apfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate)
 {
 	struct page *page = NULL;
-	bool must_unlock, is_metadata;
+	bool is_metadata;
 
 	page = bh->b_page;
 	get_page(page);
@@ -542,7 +542,7 @@ static void apfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate)
 	bh = NULL;
 
 	/* Future writes to mmapped areas should fault for CoW */
-	must_unlock = trylock_page(page);
+	lock_page(page);
 	page_mkclean(page);
 
 	/* XXX: otherwise, the page cache fills up and crashes the machine */
@@ -554,8 +554,7 @@ static void apfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate)
 #endif
 	}
 
-	if (must_unlock)
-		unlock_page(page);
+	unlock_page(page);
 	put_page(page);
 }
 
@@ -686,6 +685,7 @@ static int apfs_transaction_commit_nx(struct super_block *sb)
 
 	list_for_each_entry(sbi, &nxi->vol_list, list) {
 		struct apfs_vol_transaction *vol_trans = &sbi->s_transaction;
+
 		if (!vol_trans->t_old_vsb)
 			continue;
 
@@ -736,7 +736,7 @@ static bool apfs_transaction_need_commit(struct super_block *sb)
 		struct apfs_spaceman_phys *sm_raw = sm->sm_raw;
 		struct apfs_spaceman_free_queue *fq_ip = &sm_raw->sm_fq[APFS_SFQ_IP];
 		struct apfs_spaceman_free_queue *fq_main = &sm_raw->sm_fq[APFS_SFQ_MAIN];
-		int buffers_max = TRANSACTION_BUFFERS_MAX;
+		int buffers_max = APFS_SB(sb)->s_trans_buffers_max;
 		int starts_max = TRANSACTION_STARTS_MAX;
 		int mq_max = TRANSACTION_MAIN_QUEUE_MAX;
 
@@ -751,7 +751,7 @@ static bool apfs_transaction_need_commit(struct super_block *sb)
 			mq_max += 20;
 		}
 
-		if(nx_trans->t_buffers_count > buffers_max)
+		if (nx_trans->t_buffers_count > buffers_max)
 			return true;
 		if (nx_trans->t_starts_count > starts_max)
 			return true;
@@ -761,11 +761,11 @@ static bool apfs_transaction_need_commit(struct super_block *sb)
 		 * exactly 3 times. Don't allow large transactions if we can't
 		 * be sure the bitmap changes will all fit.
 		 */
-		if(le64_to_cpu(fq_ip->sfq_count) * 3 > le64_to_cpu(sm_raw->sm_ip_block_count))
+		if (le64_to_cpu(fq_ip->sfq_count) * 3 > le64_to_cpu(sm_raw->sm_ip_block_count))
 			return true;
 
 		/* Don't let the main queue get too full either */
-		if(le64_to_cpu(fq_main->sfq_count) > mq_max)
+		if (le64_to_cpu(fq_main->sfq_count) > mq_max)
 			return true;
 	}
 
@@ -845,7 +845,7 @@ int apfs_transaction_join(struct super_block *sb, struct buffer_head *bh)
 	get_bh(bh);
 	bhi->bh = bh;
 	list_add(&bhi->list, &nx_trans->t_buffers);
-	nx_trans->t_buffers_count ++;
+	nx_trans->t_buffers_count++;
 
 	set_buffer_trans(bh);
 	bh->b_private = bhi;
@@ -923,6 +923,7 @@ void apfs_transaction_abort(struct super_block *sb)
 
 	list_for_each_entry(sbi, &nxi->vol_list, list) {
 		struct apfs_vol_transaction *vol_trans = &sbi->s_transaction;
+
 		if (!vol_trans->t_old_vsb)
 			continue;
 

xattr.c

@@ -112,9 +112,7 @@ static int apfs_xattr_extents_read(struct inode *parent,
 {
 	struct super_block *sb = parent->i_sb;
 	struct apfs_dstream_info *dstream;
-	int length, blkcnt, i;
-	struct buffer_head **bhs = NULL;
-	int ret;
+	int length, ret;
 
 	dstream = kzalloc(sizeof(*dstream), GFP_KERNEL);
 	if (!dstream)
@@ -146,59 +144,11 @@ static int apfs_xattr_extents_read(struct inode *parent,
 			length = size;
 	}
 
-	blkcnt = (length + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
-	bhs = kcalloc(blkcnt, sizeof(*bhs), GFP_KERNEL);
-	for (i = 0; i < blkcnt; i++) {
-		struct buffer_head *bh = NULL;
-		u64 bno = 0;
-
-		ret = apfs_logic_to_phys_bno(dstream, i, &bno);
-		if (ret)
-			goto out;
-		if (bno == 0) {
-			/* No holes in xattr dstreams, I believe */
-			apfs_err(sb, "xattr dstream has a hole");
-			ret = -EFSCORRUPTED;
-			goto out;
-		}
-
-		bhs[i] = __getblk_gfp(APFS_NXI(sb)->nx_bdev, bno, sb->s_blocksize, __GFP_MOVABLE);
-		if (!bhs[i]) {
-			apfs_err(sb, "failed to map block 0x%llx", bno);
-			ret = -EIO;
-			goto out;
-		}
-
-		bh = bhs[i];
-		if (!buffer_uptodate(bh)) {
-			get_bh(bh);
-			lock_buffer(bh);
-			bh->b_end_io = end_buffer_read_sync;
-			apfs_submit_bh(REQ_OP_READ, 0, bh);
-		}
-	}
-	for (i = 0; i < blkcnt; i++) {
-		int off, tocopy;
-
-		wait_on_buffer(bhs[i]);
-		if (!buffer_uptodate(bhs[i])) {
-			apfs_err(sb, "failed to read a block");
-			ret = -EIO;
-			goto out;
-		}
-
-		off = i << sb->s_blocksize_bits;
-		tocopy = min(sb->s_blocksize, (unsigned long)(length - off));
-		memcpy(buffer + off, bhs[i]->b_data, tocopy);
-	}
-	ret = length;
+	ret = apfs_nonsparse_dstream_read(dstream, buffer, length, 0 /* offset */);
+	if (ret == 0)
+		ret = length;
 
 out:
-	if (bhs) {
-		for (i = 0; i < blkcnt; i++)
-			brelse(bhs[i]);
-		kfree(bhs);
-	}
 	kfree(dstream);
 	return ret;
 }
@@ -233,6 +183,125 @@ static int apfs_xattr_inline_read(struct apfs_xattr *xattr, void *buffer, size_t
 	return length;
 }
 
+/**
+ * apfs_xattr_get_compressed_data - Get the compressed data in a named attribute
+ * @inode:	inode the attribute belongs to
+ * @name:	name of the attribute
+ * @cdata:	compressed data struct to set on return
+ *
+ * Returns 0 on success or a negative error code in case of failure.
+ */
+int apfs_xattr_get_compressed_data(struct inode *inode, const char *name, struct apfs_compressed_data *cdata)
+{
+	struct super_block *sb = inode->i_sb;
+	struct apfs_sb_info *sbi = APFS_SB(sb);
+	struct apfs_key key;
+	struct apfs_query *query;
+	struct apfs_xattr xattr;
+	u64 cnid = apfs_ino(inode);
+	int ret;
+
+	apfs_init_xattr_key(cnid, name, &key);
+
+	query = apfs_alloc_query(sbi->s_cat_root, NULL /* parent */);
+	if (!query)
+		return -ENOMEM;
+	query->key = &key;
+	query->flags |= APFS_QUERY_CAT | APFS_QUERY_EXACT;
+
+	ret = apfs_btree_query(sb, &query);
+	if (ret) {
+		apfs_err(sb, "query failed for id 0x%llx (%s)", cnid, name);
+		goto done;
+	}
+
+	ret = apfs_xattr_from_query(query, &xattr);
+	if (ret) {
+		apfs_err(sb, "bad xattr record in inode 0x%llx", cnid);
+		goto done;
+	}
+
+	cdata->has_dstream = xattr.has_dstream;
+	if (cdata->has_dstream) {
+		struct apfs_dstream_info *dstream = NULL;
+
+		dstream = kzalloc(sizeof(*dstream), GFP_KERNEL);
+		if (!dstream) {
+			ret = -ENOMEM;
+			goto done;
+		}
+		apfs_dstream_from_xattr(sb, &xattr, dstream);
+
+		cdata->dstream = dstream;
+		cdata->size = dstream->ds_size;
+	} else {
+		void *data = NULL;
+		int len;
+
+		len = xattr.xdata_len;
+		if (len > APFS_XATTR_MAX_EMBEDDED_SIZE) {
+			apfs_err(sb, "inline xattr too big");
+			ret = -EFSCORRUPTED;
+			goto done;
+		}
+		data = kzalloc(len, GFP_KERNEL);
+		if (!data) {
+			ret = -ENOMEM;
+			goto done;
+		}
+		memcpy(data, xattr.xdata, len);
+
+		cdata->data = data;
+		cdata->size = len;
+	}
+	ret = 0;
+
+done:
+	apfs_free_query(query);
+	return ret;
+}
+
+/**
+ * apfs_release_compressed_data - Clean up a compressed data struct
+ * @cdata: struct to clean up (but not free)
+ */
+void apfs_release_compressed_data(struct apfs_compressed_data *cdata)
+{
+	if (!cdata)
+		return;
+
+	if (cdata->has_dstream) {
+		kfree(cdata->dstream);
+		cdata->dstream = NULL;
+	} else {
+		kfree(cdata->data);
+		cdata->data = NULL;
+	}
+}
+
+/**
+ * apfs_compressed_data_read - Read from a compressed data struct
+ * @cdata:	compressed data struct
+ * @buf:	destination buffer
+ * @count:	exact number of bytes to read
+ * @offset:	dstream offset to read from
+ *
+ * Returns 0 on success or a negative error code in case of failure.
+ */
+int apfs_compressed_data_read(struct apfs_compressed_data *cdata, void *buf, size_t count, u64 offset)
+{
+	if (cdata->has_dstream)
+		return apfs_nonsparse_dstream_read(cdata->dstream, buf, count, offset);
+
+	if (offset > cdata->size || count > cdata->size - offset) {
+		apfs_err(NULL, "reading past the end (0x%llx-0x%llx)", offset, (unsigned long long)count);
+		/* No caller is expected to legitimately read out-of-bounds */
+		return -EFSCORRUPTED;
+	}
+	memcpy(buf, cdata->data + offset, count);
+	return 0;
+}
+
 /**
  * __apfs_xattr_get - Find and read a named attribute
  * @inode:	inode the attribute belongs to
@@ -465,7 +534,7 @@ static int apfs_build_xattr_key(const char *name, u64 ino, struct apfs_xattr_key
 
 	apfs_key_set_hdr(APFS_TYPE_XATTR, ino, key);
 	key->name_len = cpu_to_le16(namelen);
-	strcpy(key->name, name);
+	strscpy(key->name, name, namelen);
 
 	*key_p = key;
 	return key_len;