diff mbox series

[2/6] composefs: Add on-disk layout

Message ID cbe0d67a97c8b5157de06cedb67c88794c9c304e.1669631086.git.alexl@redhat.com (mailing list archive)
State New, archived
Headers show
Series Composefs: an opportunistically sharing verified image filesystem | expand

Commit Message

Alexander Larsson Nov. 28, 2022, 11:16 a.m. UTC
This commit adds the on-disk layout header file of composefs.

Signed-off-by: Alexander Larsson <alexl@redhat.com>
Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>
---
 fs/composefs/cfs.h | 242 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 242 insertions(+)
 create mode 100644 fs/composefs/cfs.h

Comments

Brian Masney Jan. 5, 2023, 3:55 p.m. UTC | #1
On Mon, Nov 28, 2022 at 12:16:23PM +0100, Alexander Larsson wrote:
> This commit adds the on-disk layout header file of composefs.
> 
> Signed-off-by: Alexander Larsson <alexl@redhat.com>
> Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>

Add Co-Developed-By: Giuseppe ... ?

Full disclosure: I'm not a file system developer but I'll attempt to
help with the review of this series.

> ---
>  fs/composefs/cfs.h | 242 +++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 242 insertions(+)
>  create mode 100644 fs/composefs/cfs.h
> 
> diff --git a/fs/composefs/cfs.h b/fs/composefs/cfs.h
> new file mode 100644
> index 000000000000..8f001fd28d6b
> --- /dev/null
> +++ b/fs/composefs/cfs.h
> @@ -0,0 +1,242 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +/*
> + * composefs
> + *
> + * Copyright (C) 2021 Giuseppe Scrivano
> + * Copyright (C) 2022 Alexander Larsson
> + *
> + * This file is released under the GPL.
> + */
> +
> +#ifndef _CFS_H
> +#define _CFS_H
> +
> +#include <asm/byteorder.h>
> +#include <crypto/sha2.h>
> +#include <linux/fs.h>
> +#include <linux/stat.h>
> +#include <linux/types.h>
> +
> +#define CFS_VERSION 1
> +
> +#define CFS_MAGIC 0xc078629aU
> +
> +#define CFS_MAX_DIR_CHUNK_SIZE 4096
> +#define CFS_MAX_XATTRS_SIZE 4096
> +
> +static inline u16 cfs_u16_to_file(u16 val)
> +{
> +	return cpu_to_le16(val);
> +}
> +
> +static inline u32 cfs_u32_to_file(u32 val)
> +{
> +	return cpu_to_le32(val);
> +}
> +
> +static inline u64 cfs_u64_to_file(u64 val)
> +{
> +	return cpu_to_le64(val);
> +}
> +
> +static inline u16 cfs_u16_from_file(u16 val)
> +{
> +	return le16_to_cpu(val);
> +}
> +
> +static inline u32 cfs_u32_from_file(u32 val)
> +{
> +	return le32_to_cpu(val);
> +}
> +
> +static inline u64 cfs_u64_from_file(u64 val)
> +{
> +	return le64_to_cpu(val);
> +}

I don't see where the cfs_xxx_{to,from}_file() approach is used in other
filesystems. Instead, move the cpu() functions directly into the code.

> +static inline int cfs_xdigit_value(char c)
> +{
> +	if (c >= '0' && c <= '9')
> +		return c - '0';
> +	if (c >= 'A' && c <= 'F')
> +		return c - 'A' + 10;
> +	if (c >= 'a' && c <= 'f')
> +		return c - 'a' + 10;
> +	return -1;
> +}

There's some utilities in lib/hexdump.c that you can use. hex_to_bin()
will convert a single character and hex2bin() will convert a string for
you.

> +static inline int cfs_digest_from_payload(const char *payload,
> +					  size_t payload_len,
> +					  u8 digest_out[SHA256_DIGEST_SIZE])
> +{
> +	const char *p, *end;
> +	u8 last_digit = 0;
> +	int digit = 0;
> +	size_t n_nibbles = 0;

Put in reverse Christmas tree order.

> +
> +	end = payload + payload_len;
> +	for (p = payload; p != end; p++) {
> +		/* Skip subdir structure */
> +		if (*p == '/')
> +			continue;
> +
> +		/* Break at (and ignore) extension */
> +		if (*p == '.')
> +			break;

A comment would be helpful in this area that shows what the payload is
expected to be.

> +
> +		if (n_nibbles == SHA256_DIGEST_SIZE * 2)
> +			return -1; /* Too long */

return -EINVAL; ?

> +
> +		digit = cfs_xdigit_value(*p);
> +		if (digit == -1)
> +			return -1; /* Not hex digit */

-EINVAL here as well

> +
> +		n_nibbles++;
> +		if ((n_nibbles % 2) == 0) {
> +			digest_out[n_nibbles / 2 - 1] =
> +				(last_digit << 4) | digit;
> +		}
> +		last_digit = digit;
> +	}
> +
> +	if (n_nibbles != SHA256_DIGEST_SIZE * 2)
> +		return -1; /* Too short */

-EINVAL here as well

> +
> +	return 0;
> +}
> +
> +struct cfs_vdata_s {
> +	u64 off;
> +	u32 len;
> +} __packed;
> +
> +struct cfs_header_s {
> +	u8 version;
> +	u8 unused1;
> +	u16 unused2;
> +
> +	u32 magic;

Should the magic number appear first?

> +	u64 data_offset;
> +	u64 root_inode;
> +
> +	u64 unused3[2];
> +} __packed;
> +
> +enum cfs_inode_flags {
> +	CFS_INODE_FLAGS_NONE = 0,
> +	CFS_INODE_FLAGS_PAYLOAD = 1 << 0,
> +	CFS_INODE_FLAGS_MODE = 1 << 1,
> +	CFS_INODE_FLAGS_NLINK = 1 << 2,
> +	CFS_INODE_FLAGS_UIDGID = 1 << 3,
> +	CFS_INODE_FLAGS_RDEV = 1 << 4,
> +	CFS_INODE_FLAGS_TIMES = 1 << 5,
> +	CFS_INODE_FLAGS_TIMES_NSEC = 1 << 6,
> +	CFS_INODE_FLAGS_LOW_SIZE = 1 << 7, /* Low 32bit of st_size */
> +	CFS_INODE_FLAGS_HIGH_SIZE = 1 << 8, /* High 32bit of st_size */
> +	CFS_INODE_FLAGS_XATTRS = 1 << 9,
> +	CFS_INODE_FLAGS_DIGEST = 1
> +				 << 10, /* fs-verity sha256 digest of content */

Include << 10 on line above

Brian
Alexander Larsson Jan. 10, 2023, 4:19 p.m. UTC | #2
On Thu, 2023-01-05 at 10:55 -0500, Brian Masney wrote:
> On Mon, Nov 28, 2022 at 12:16:23PM +0100, Alexander Larsson wrote:
> > This commit adds the on-disk layout header file of composefs.
> > 
> > Signed-off-by: Alexander Larsson <alexl@redhat.com>
> > Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>
> 
> Add Co-Developed-By: Giuseppe ... ?
> 
> Full disclosure: I'm not a file system developer but I'll attempt to
> help with the review of this series.
> 

Thanks. I did various changes to the github repo based on your review,
here are the outstanding comments:

> 
> > +struct cfs_header_s {
> > +       u8 version;
> > +       u8 unused1;
> > +       u16 unused2;
> > +
> > +       u32 magic;
> 
> Should the magic number appear first?

I don't think so, the version number is essentially part of the full
magic string.
> 

>
diff mbox series

Patch

diff --git a/fs/composefs/cfs.h b/fs/composefs/cfs.h
new file mode 100644
index 000000000000..8f001fd28d6b
--- /dev/null
+++ b/fs/composefs/cfs.h
@@ -0,0 +1,242 @@ 
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * composefs
+ *
+ * Copyright (C) 2021 Giuseppe Scrivano
+ * Copyright (C) 2022 Alexander Larsson
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef _CFS_H
+#define _CFS_H
+
+#include <asm/byteorder.h>
+#include <crypto/sha2.h>
+#include <linux/fs.h>
+#include <linux/stat.h>
+#include <linux/types.h>
+
+#define CFS_VERSION 1
+
+#define CFS_MAGIC 0xc078629aU
+
+#define CFS_MAX_DIR_CHUNK_SIZE 4096
+#define CFS_MAX_XATTRS_SIZE 4096
+
+static inline u16 cfs_u16_to_file(u16 val)
+{
+	return cpu_to_le16(val);
+}
+
+static inline u32 cfs_u32_to_file(u32 val)
+{
+	return cpu_to_le32(val);
+}
+
+static inline u64 cfs_u64_to_file(u64 val)
+{
+	return cpu_to_le64(val);
+}
+
+static inline u16 cfs_u16_from_file(u16 val)
+{
+	return le16_to_cpu(val);
+}
+
+static inline u32 cfs_u32_from_file(u32 val)
+{
+	return le32_to_cpu(val);
+}
+
+static inline u64 cfs_u64_from_file(u64 val)
+{
+	return le64_to_cpu(val);
+}
+
+static inline int cfs_xdigit_value(char c)
+{
+	if (c >= '0' && c <= '9')
+		return c - '0';
+	if (c >= 'A' && c <= 'F')
+		return c - 'A' + 10;
+	if (c >= 'a' && c <= 'f')
+		return c - 'a' + 10;
+	return -1;
+}
+
+static inline int cfs_digest_from_payload(const char *payload,
+					  size_t payload_len,
+					  u8 digest_out[SHA256_DIGEST_SIZE])
+{
+	const char *p, *end;
+	u8 last_digit = 0;
+	int digit = 0;
+	size_t n_nibbles = 0;
+
+	end = payload + payload_len;
+	for (p = payload; p != end; p++) {
+		/* Skip subdir structure */
+		if (*p == '/')
+			continue;
+
+		/* Break at (and ignore) extension */
+		if (*p == '.')
+			break;
+
+		if (n_nibbles == SHA256_DIGEST_SIZE * 2)
+			return -1; /* Too long */
+
+		digit = cfs_xdigit_value(*p);
+		if (digit == -1)
+			return -1; /* Not hex digit */
+
+		n_nibbles++;
+		if ((n_nibbles % 2) == 0) {
+			digest_out[n_nibbles / 2 - 1] =
+				(last_digit << 4) | digit;
+		}
+		last_digit = digit;
+	}
+
+	if (n_nibbles != SHA256_DIGEST_SIZE * 2)
+		return -1; /* Too short */
+
+	return 0;
+}
+
+struct cfs_vdata_s {
+	u64 off;
+	u32 len;
+} __packed;
+
+struct cfs_header_s {
+	u8 version;
+	u8 unused1;
+	u16 unused2;
+
+	u32 magic;
+	u64 data_offset;
+	u64 root_inode;
+
+	u64 unused3[2];
+} __packed;
+
+enum cfs_inode_flags {
+	CFS_INODE_FLAGS_NONE = 0,
+	CFS_INODE_FLAGS_PAYLOAD = 1 << 0,
+	CFS_INODE_FLAGS_MODE = 1 << 1,
+	CFS_INODE_FLAGS_NLINK = 1 << 2,
+	CFS_INODE_FLAGS_UIDGID = 1 << 3,
+	CFS_INODE_FLAGS_RDEV = 1 << 4,
+	CFS_INODE_FLAGS_TIMES = 1 << 5,
+	CFS_INODE_FLAGS_TIMES_NSEC = 1 << 6,
+	CFS_INODE_FLAGS_LOW_SIZE = 1 << 7, /* Low 32bit of st_size */
+	CFS_INODE_FLAGS_HIGH_SIZE = 1 << 8, /* High 32bit of st_size */
+	CFS_INODE_FLAGS_XATTRS = 1 << 9,
+	CFS_INODE_FLAGS_DIGEST = 1
+				 << 10, /* fs-verity sha256 digest of content */
+	CFS_INODE_FLAGS_DIGEST_FROM_PAYLOAD =
+		1 << 11, /* Compute digest from payload */
+};
+
+#define CFS_INODE_FLAG_CHECK(_flag, _name)                                     \
+	(((_flag) & (CFS_INODE_FLAGS_##_name)) != 0)
+#define CFS_INODE_FLAG_CHECK_SIZE(_flag, _name, _size)                         \
+	(CFS_INODE_FLAG_CHECK(_flag, _name) ? (_size) : 0)
+
+#define CFS_INODE_DEFAULT_MODE 0100644
+#define CFS_INODE_DEFAULT_NLINK 1
+#define CFS_INODE_DEFAULT_NLINK_DIR 2
+#define CFS_INODE_DEFAULT_UIDGID 0
+#define CFS_INODE_DEFAULT_RDEV 0
+#define CFS_INODE_DEFAULT_TIMES 0
+
+struct cfs_inode_s {
+	u32 flags;
+
+	/* Optional data: (selected by flags) */
+
+	/* This is the size of the type specific data that comes directly after
+	 * the inode in the file. Of this type:
+	 *
+	 * directory: cfs_dir_s
+	 * regular file: the backing filename
+	 * symlink: the target link
+	 *
+	 * Canonically payload_length is 0 for empty dir/file/symlink.
+	 */
+	u32 payload_length;
+
+	u32 st_mode; /* File type and mode.  */
+	u32 st_nlink; /* Number of hard links, only for regular files.  */
+	u32 st_uid; /* User ID of owner.  */
+	u32 st_gid; /* Group ID of owner.  */
+	u32 st_rdev; /* Device ID (if special file).  */
+	u64 st_size; /* Size of file, only used for regular files */
+
+	struct cfs_vdata_s xattrs; /* ref to variable data */
+
+	u8 digest[SHA256_DIGEST_SIZE]; /* fs-verity digest */
+
+	struct timespec64 st_mtim; /* Time of last modification.  */
+	struct timespec64 st_ctim; /* Time of last status change.  */
+};
+
+static inline u32 cfs_inode_encoded_size(u32 flags)
+{
+	return sizeof(u32) /* flags */ +
+	       CFS_INODE_FLAG_CHECK_SIZE(flags, PAYLOAD, sizeof(u32)) +
+	       CFS_INODE_FLAG_CHECK_SIZE(flags, MODE, sizeof(u32)) +
+	       CFS_INODE_FLAG_CHECK_SIZE(flags, NLINK, sizeof(u32)) +
+	       CFS_INODE_FLAG_CHECK_SIZE(flags, UIDGID,
+					 sizeof(u32) + sizeof(u32)) +
+	       CFS_INODE_FLAG_CHECK_SIZE(flags, RDEV, sizeof(u32)) +
+	       CFS_INODE_FLAG_CHECK_SIZE(flags, TIMES, sizeof(u64) * 2) +
+	       CFS_INODE_FLAG_CHECK_SIZE(flags, TIMES_NSEC, sizeof(u32) * 2) +
+	       CFS_INODE_FLAG_CHECK_SIZE(flags, LOW_SIZE, sizeof(u32)) +
+	       CFS_INODE_FLAG_CHECK_SIZE(flags, HIGH_SIZE, sizeof(u32)) +
+	       CFS_INODE_FLAG_CHECK_SIZE(flags, XATTRS,
+					 sizeof(u64) + sizeof(u32)) +
+	       CFS_INODE_FLAG_CHECK_SIZE(flags, DIGEST, SHA256_DIGEST_SIZE);
+}
+
+struct cfs_dentry_s {
+	/* Index of struct cfs_inode_s */
+	u64 inode_index;
+	u8 d_type;
+	u8 name_len;
+	u16 name_offset;
+} __packed;
+
+struct cfs_dir_chunk_s {
+	u16 n_dentries;
+	u16 chunk_size;
+	u64 chunk_offset;
+} __packed;
+
+struct cfs_dir_s {
+	u32 n_chunks;
+	struct cfs_dir_chunk_s chunks[];
+} __packed;
+
+#define cfs_dir_size(_n_chunks)                                                \
+	(sizeof(struct cfs_dir_s) +                                            \
+	 (_n_chunks) * sizeof(struct cfs_dir_chunk_s))
+
+/* xattr representation.  */
+struct cfs_xattr_element_s {
+	u16 key_length;
+	u16 value_length;
+} __packed;
+
+struct cfs_xattr_header_s {
+	u16 n_attr;
+	struct cfs_xattr_element_s attr[0];
+} __packed;
+
+#define cfs_xattr_header_size(_n_element)                                      \
+	(sizeof(struct cfs_xattr_header_s) +                                   \
+	 (_n_element) * sizeof(struct cfs_xattr_element_s))
+
+#endif