[PATCH v5 0/9] fs: interface for directly reading/writing compressed data

@@ -221,8 +221,9 @@ On Linux, this command can change only the
 .BR O_ASYNC ,
 .BR O_DIRECT ,
 .BR O_NOATIME ,
+.BR O_NONBLOCK ,
 and
-.B O_NONBLOCK
+.B O_ALLOW_ENCODED
 flags.
 It is not possible to change the
 .BR O_DSYNC

@@ -1820,6 +1821,13 @@ Attempted to clear the
 flag on a file that has the append-only attribute set.
 .TP
 .B EPERM
+Attempted to set the
+.B O_ALLOW_ENCODED
+flag and the calling process did not have the
+.B CAP_SYS_ADMIN
+capability.
+.TP
+.B EPERM
 .I cmd
 was
 .BR F_ADD_SEALS ,

@@ -437,6 +437,14 @@ was followed by a call to
 .BR fdatasync (2)).
 .IR "See NOTES below" .
 .TP
+.B O_ALLOW_ENCODED
+Open the file with encoded I/O permissions;
+see
+.BR encoded_io (7).
+The caller must have the
+.B CAP_SYS_ADMIN
+capability.
+.TP
 .B O_EXCL
 Ensure that this call creates the file:
 if this flag is specified in conjunction with

@@ -1230,6 +1238,11 @@ did not match the owner of the file and the caller was not privileged.
 The operation was prevented by a file seal; see
 .BR fcntl (2).
 .TP
+.B EPERM
+The
+.B O_ALLOW_ENCODED
+flag was specified, but the caller was not privileged.
+.TP
 .B EROFS
 .I pathname
 refers to a file on a read-only filesystem and write access was

@@ -264,6 +264,11 @@ the data is always appended to the end of the file.
 However, if the
 .I offset
 argument is \-1, the current file offset is updated.
+.TP
+.BR RWF_ENCODED " (since Linux 5.8)"
+Read or write encoded (e.g., compressed) data.
+See
+.BR encoded_io (7).
 .SH RETURN VALUE
 On success,
 .BR readv (),

@@ -283,6 +288,13 @@ than requested (see
 and
 .BR write (2)).
 .PP
+If
+.B
+RWF_ENCODED
+was specified in
+.IR flags ,
+then the return value is the number of encoded bytes.
+.PP
 On error, \-1 is returned, and \fIerrno\fP is set appropriately.
 .SH ERRORS
 The errors are as given for

@@ -313,6 +325,58 @@ is less than zero or greater than the permitted maximum.
 .TP
 .B EOPNOTSUPP
 An unknown flag is specified in \fIflags\fP.
+.TP
+.B EOPNOTSUPP
+.B RWF_ENCODED
+is specified in
+.I flags
+and the filesystem does not implement encoded I/O.
+.TP
+.B EPERM
+.B RWF_ENCODED
+is specified in
+.I flags
+and the file was not opened with the
+.B O_ALLOW_ENCODED
+flag.
+.PP
+.BR preadv2 ()
+can fail for the following reasons:
+.TP
+.B E2BIG
+.B RWF_ENCODED
+is specified in
+.I flags
+and
+.I iov[0]
+is not large enough to return the encoding metadata.
+.TP
+.B ENOBUFS
+.B RWF_ENCODED
+is specified in
+.I flags
+and the buffers in
+.I iov
+are not big enough to return the encoded data.
+.PP
+.BR pwritev2 ()
+can fail for the following reasons:
+.TP
+.B E2BIG
+.B RWF_ENCODED
+is specified in
+.I flags
+and
+.I iov[0]
+contains non-zero fields
+after the kernel's
+.IR "sizeof(struct\ encoded_iov)" .
+.TP
+.B EINVAL
+.B RWF_ENCODED
+is specified in
+.I flags
+and the alignment and/or size requirements are not met.
 .SH VERSIONS
 .BR preadv ()
 and

@@ -0,0 +1,347 @@
+.\" Copyright (c) 2019 by Omar Sandoval <osandov@fb.com>
+.\"
+.\" %%%LICENSE_START(VERBATIM)
+.\" Permission is granted to make and distribute verbatim copies of this
+.\" manual provided the copyright notice and this permission notice are
+.\" preserved on all copies.
+.\"
+.\" Permission is granted to copy and distribute modified versions of this
+.\" manual under the conditions for verbatim copying, provided that the
+.\" entire resulting derived work is distributed under the terms of a
+.\" permission notice identical to this one.
+.\"
+.\" Since the Linux kernel and libraries are constantly changing, this
+.\" manual page may be incorrect or out-of-date.  The author(s) assume no
+.\" responsibility for errors or omissions, or for damages resulting from
+.\" the use of the information contained herein.  The author(s) may not
+.\" have taken the same level of care in the production of this manual,
+.\" which is licensed free of charge, as they might when working
+.\" professionally.
+.\"
+.\" Formatted or processed versions of this manual, if unaccompanied by
+.\" the source, must acknowledge the copyright and authors of this work.
+.\" %%%LICENSE_END
+.\"
+.\"
+.TH ENCODED_IO  7 2019-10-14 "Linux" "Linux Programmer's Manual"
+.SH NAME
+encoded_io \- overview of encoded I/O
+.SH DESCRIPTION
+Several filesystems (e.g., Btrfs) support transparent encoding
+(e.g., compression, encryption) of data on disk:
+written data is encoded by the kernel before it is written to disk,
+and read data is decoded before being returned to the user.
+In some cases, it is useful to skip this encoding step.
+For example, the user may want to read the compressed contents of a file
+or write pre-compressed data directly to a file.
+This is referred to as "encoded I/O".
+.SS Encoded I/O API
+Encoded I/O is specified with the
+.B RWF_ENCODED
+flag to
+.BR preadv2 (2)
+and
+.BR pwritev2 (2).
+If
+.B RWF_ENCODED
+is specified, then
+.I iov[0].iov_base
+points to an
+.I
+encoded_iov
+structure, defined in
+.I <linux/fs.h>
+as:
+.PP
+.in +4n
+.EX
+struct encoded_iov {
+    __aligned_u64 len;
+    __aligned_u64 unencoded_len;
+    __aligned_u64 unencoded_offset;
+    __u32 compression;
+    __u32 encryption;
+};
+.EE
+.in
+.PP
+This may be extended in the future, so
+.I iov[0].iov_len
+must be set to
+.I "sizeof(struct\ encoded_iov)"
+for forward/backward compatibility.
+The remaining buffers contain the encoded data.
+.PP
+.I compression
+and
+.I encryption
+are the encoding fields.
+.I compression
+is one of
+.B ENCODED_IOV_COMPRESSION_NONE
+(zero),
+.BR ENCODED_IOV_COMPRESSION_ZLIB ,
+.BR ENCODED_IOV_COMPRESSION_LZO ,
+or
+.BR ENCODED_IOV_COMPRESSION_ZSTD .
+.I encryption
+is currently always
+.B ENCODED_IOV_ENCRYPTION_NONE
+(zero).
+.PP
+.I unencoded_len
+is the length of the unencoded (i.e., decrypted and decompressed) data.
+.I unencoded_offset
+is the offset into the unencoded data where the data in the file begins
+(less than or equal to
+.IR unencoded_len ).
+.I len
+is the length of the data in the file
+(less than or equal to
+.I unencoded_len
+-
+.IR unencoded_offset ).
+See
+.B Extent layout
+below for some examples.
+.I
+.PP
+If the unencoded data is actually longer than
+.IR unencoded_len ,
+then it is truncated;
+if it is shorter, then it is extended with zeroes.
+.PP
+
+.BR pwritev2 ()
+uses the metadata specified in
+.IR iov[0] ,
+writes the encoded data from the remaining buffers,
+and returns the number of encoded bytes written
+(that is, the sum of
+.I iov[n].iov_len
+for 1 <=
+.I n
+<
+.IR iovcnt ;
+partial writes will not occur).
+At least one encoding field must be non-zero.
+Note that the encoded data is not validated when it is written;
+if it is not valid (e.g., it cannot be decompressed),
+then a subsequent read may return an error.
+If the
+.I offset
+argument to
+.BR pwritev2 ()
+is -1, then the file offset is incremented by
+.IR len .
+If
+.I iov[0].iov_len
+is less than
+.I "sizeof(struct\ encoded_iov)"
+in the kernel,
+then any fields unknown to userspace are treated as if they were zero;
+if it is greater and any fields unknown to the kernel are non-zero,
+then this returns -1 and sets
+.I errno
+to
+.BR E2BIG .
+.PP
+.BR preadv2 ()
+populates the metadata in
+.IR iov[0] ,
+the encoded data in the remaining buffers,
+and returns the number of encoded bytes read.
+This will only return one extent per call.
+This can also read data which is not encoded;
+all encoding fields will be zero in that case.
+If the
+.I offset
+argument to
+.BR preadv2 ()
+is -1, then the file offset is incremented by
+.IR len .
+If
+.I iov[0].iov_len
+is less than
+.I "sizeof(struct\ encoded_iov)"
+in the kernel and any fields unknown to userspace are non-zero,
+then
+.BR preadv2 ()
+returns -1 and sets
+.I errno
+to
+.BR E2BIG ;
+if it is greater,
+then any fields unknown to the kernel are returned as zero.
+If the provided buffers are not large enough to return an entire encoded
+extent,
+then
+.BR preadv2 ()
+returns -1 and sets
+.I errno
+to
+.BR ENOBUFS .
+.PP
+As the filesystem page cache typically contains decoded data,
+encoded I/O bypasses the page cache.
+.SS Extent layout
+By using
+.IR len ,
+.IR unencoded_len ,
+and
+.IR unencoded_offset ,
+it is possible to refer to a subset of an unencoded extent.
+.PP
+In the simplest case,
+.I len
+is equal to
+.I unencoded_len
+and
+.I unencoded_offset
+is zero.
+This means that the entire unencoded extent is used.
+.PP
+However, suppose we read 50 bytes into a file
+which contains a single compressed extent.
+The filesystem must still return the entire compressed extent
+for us to be able to decompress it,
+so
+.I unencoded_len
+would be the length of the entire decompressed extent.
+However, because the read was at offset 50,
+the first 50 bytes should be ignored.
+Therefore,
+.I unencoded_offset
+would be 50,
+and
+.I len
+would accordingly be
+.IR unencoded_len\ -\ 50 .
+.PP
+Additionally, suppose we want to create an encrypted file with length 500,
+but the file is encrypted with a block cipher using a block size of 4096.
+The unencoded data would therefore include the appropriate padding,
+and
+.I unencoded_len
+would be 4096.
+However, to represent the logical size of the file,
+.I len
+would be 500
+(and
+.I unencoded_offset
+would be 0).
+.PP
+Similar situations can arise in other cases:
+.IP * 3
+If the filesystem pads data to the filesystem block size before compressing,
+then compressed files with a size unaligned to the filesystem block size will
+end with an extent with
+.I len
+<
+.IR unencoded_len .
+.IP *
+Extents cloned from the middle of a larger encoded extent with
+.B FICLONERANGE
+may have a non-zero
+.I unencoded_offset
+and/or
+.I len
+<
+.IR unencoded_len .
+.IP *
+If the middle of an encoded extent is overwritten,
+the filesystem may create extents with a non-zero
+.I unencoded_offset
+and/or
+.I len
+<
+.I unencoded_len
+for the parts that were not overwritten.
+.SS Security
+Encoded I/O creates the potential for some security issues:
+.IP * 3
+Encoded writes allow writing arbitrary data which the kernel will decode on
+a subsequent read. Decompression algorithms are complex and may have bugs
+which can be exploited by maliciously crafted data.
+.IP *
+Encoded reads may return data which is not logically present in the file
+(see the discussion of
+.I len
+vs.
+.I unencoded_len
+above).
+It may not be intended for this data to be readable.
+.PP
+Therefore, encoded I/O requires privilege.
+Namely, the
+.B RWF_ENCODED
+flag may only be used when the file was opened with the
+.B O_ALLOW_ENCODED
+flag to
+.BR open (2),
+which requires the
+.B CAP_SYS_ADMIN
+capability.
+.B O_ALLOW_ENCODED
+may be set and cleared with
+.BR fcntl (2).
+Note that it is not cleared on
+.BR fork (2)
+or
+.BR execve (2);
+one may wish to use
+.B O_CLOEXEC
+with
+.BR O_ALLOW_ENCODED .
+.SS Filesystem support
+Encoded I/O is supported on the following filesystems:
+.TP
+Btrfs (since Linux 5.10)
+.IP
+Btrfs supports encoded reads and writes of compressed data.
+The data is encoded as follows:
+.RS
+.IP * 3
+If
+.I compression
+is
+.BR ENCODED_IOV_COMPRESSION_ZLIB ,
+then the encoded data is a single zlib stream.
+.IP *
+If
+.I compression
+is
+.BR ENCODED_IOV_COMPRESSION_LZO ,
+then the encoded data is compressed page by page with LZO1X
+and wrapped in the format documented in the Linux kernel source file
+.IR fs/btrfs/lzo.c .
+.IP *
+If
+.I compression
+is
+.BR ENCODED_IOV_COMPRESSION_ZSTD ,
+then the encoded data is a single zstd frame compressed with the
+.I windowLog
+compression parameter set to no more than 17.
+.RE
+.IP
+Additionally, there are some restrictions on
+.BR pwritev2 ():
+.RS
+.IP * 3
+.I offset
+(or the current file offset if
+.I offset
+is -1) must be aligned to the sector size of the filesystem.
+.IP *
+.I len
+must be aligned to the sector size of the filesystem
+unless the data ends at or beyond the current end of the file.
+.IP *
+.I unencoded_len
+and the length of the encoded data must each be no more than 128 KiB.
+This limit may increase in the future.
+.IP *
+The length of the encoded data must be less than or equal to
+.IR unencoded_len .
+.RE

@@ -121,6 +121,8 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
 size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
+int copy_struct_from_iter(void *dst, size_t ksize, struct iov_iter *i,
+			  size_t usize);
 
 size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
 size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i);

@@ -944,6 +944,88 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 }
 EXPORT_SYMBOL(copy_page_from_iter);
 
+/**
+ * copy_struct_from_iter - copy a struct from an iov_iter
+ * @dst: Destination buffer.
+ * @ksize: Size of @dst struct.
+ * @i: Source iterator.
+ * @usize: (Alleged) size of struct in @i.
+ *
+ * Copies a struct from an iov_iter in a way that guarantees
+ * backwards-compatibility for struct arguments in an iovec (as long as the
+ * rules for copy_struct_from_user() are followed).
+ *
+ * The recommended usage is that @usize be taken from the current segment:
+ *
+ *   int do_foo(struct iov_iter *i)
+ *   {
+ *     size_t usize = iov_iter_single_seg_count(i);
+ *     struct foo karg;
+ *     int err;
+ *
+ *     if (usize > PAGE_SIZE)
+ *       return -E2BIG;
+ *     if (usize < FOO_SIZE_VER0)
+ *       return -EINVAL;
+ *     err = copy_struct_from_iter(&karg, sizeof(karg), i, usize);
+ *     if (err)
+ *       return err;
+ *
+ *     // ...
+ *   }
+ *
+ * Return: 0 on success, -errno on error (see copy_struct_from_user()).
+ *
+ * On success, the iterator is advanced @usize bytes. On error, the iterator is
+ * not advanced.
+ */
+int copy_struct_from_iter(void *dst, size_t ksize, struct iov_iter *i,
+			  size_t usize)
+{
+	if (usize <= ksize) {
+		if (!copy_from_iter_full(dst, usize, i))
+			return -EFAULT;
+		memset(dst + usize, 0, ksize - usize);
+	} else {
+		size_t copied = 0, copy;
+		int ret;
+
+		if (WARN_ON(iov_iter_is_pipe(i)) || unlikely(i->count < usize))
+			return -EFAULT;
+		if (iter_is_iovec(i))
+			might_fault();
+		iterate_all_kinds(i, usize, v, ({
+			copy = min(ksize - copied, v.iov_len);
+			if (copy && copyin(dst + copied, v.iov_base, copy))
+				return -EFAULT;
+			copied += copy;
+			ret = check_zeroed_user(v.iov_base + copy,
+						v.iov_len - copy);
+			if (ret <= 0)
+				return ret ?: -E2BIG;
+			0;}), ({
+			char *addr = kmap_atomic(v.bv_page);
+			copy = min_t(size_t, ksize - copied, v.bv_len);
+			memcpy(dst + copied, addr + v.bv_offset, copy);
+			copied += copy;
+			ret = memchr_inv(addr + v.bv_offset + copy, 0,
+					 v.bv_len - copy) ? -E2BIG : 0;
+			kunmap_atomic(addr);
+			if (ret)
+				return ret;
+			}), ({
+			copy = min(ksize - copied, v.iov_len);
+			memcpy(dst + copied, v.iov_base, copy);
+			if (memchr_inv(v.iov_base, 0, v.iov_len))
+				return -E2BIG;
+			})
+		)
+		iov_iter_advance(i, usize);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(copy_struct_from_iter);
+
 static size_t pipe_zero(size_t bytes, struct iov_iter *i)
 {
 	struct pipe_inode_info *pipe = i->pipe;

@@ -34,6 +34,7 @@
 
 #define O_PATH		040000000
 #define __O_TMPFILE	0100000000
+#define O_ALLOW_ENCODED	0200000000
 
 #define F_GETLK		7
 #define F_SETLK		8

@@ -22,6 +22,7 @@
 
 #define O_PATH		020000000
 #define __O_TMPFILE	040000000
+#define O_ALLOW_ENCODED	100000000
 
 #define F_GETLK64	8
 #define F_SETLK64	9

@@ -37,6 +37,7 @@
 
 #define O_PATH		0x1000000
 #define __O_TMPFILE	0x2000000
+#define O_ALLOW_ENCODED	0x8000000
 
 #define F_GETOWN	5	/*  for sockets. */
 #define F_SETOWN	6	/*  for sockets. */

@@ -30,7 +30,8 @@
 #include <asm/siginfo.h>
 #include <linux/uaccess.h>
 
-#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
+#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME | \
+		    O_ALLOW_ENCODED)
 
 static int setfl(int fd, struct file * filp, unsigned long arg)
 {

@@ -49,6 +50,11 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 		if (!inode_owner_or_capable(inode))
 			return -EPERM;
 
+	/* O_ALLOW_ENCODED can only be set by superuser */
+	if ((arg & O_ALLOW_ENCODED) && !(filp->f_flags & O_ALLOW_ENCODED) &&
+	    !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	/* required for strict SunOS emulation */
 	if (O_NONBLOCK != O_NDELAY)
 	       if (arg & O_NDELAY)

@@ -1033,7 +1039,7 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ !=
+	BUILD_BUG_ON(22 - 1 /* for O_RDONLY being 0 */ !=
 		HWEIGHT32(
 			(VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) |
 			__FMODE_EXEC | __FMODE_NONOTIFY));

@@ -2889,6 +2889,10 @@ static int may_open(const struct path *path, int acc_mode, int flag)
 	if (flag & O_NOATIME && !inode_owner_or_capable(inode))
 		return -EPERM;
 
+	/* O_ALLOW_ENCODED can only be set by superuser */
+	if ((flag & O_ALLOW_ENCODED) && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	return 0;
 }
 

@@ -10,7 +10,7 @@
 	(O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | \
 	 O_APPEND | O_NDELAY | O_NONBLOCK | O_NDELAY | __O_SYNC | O_DSYNC | \
 	 FASYNC	| O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \
-	 O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE)
+	 O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE | O_ALLOW_ENCODED)
 
 /* List of all valid flags for the how->upgrade_mask argument: */
 #define VALID_UPGRADE_FLAGS \

@@ -89,6 +89,10 @@
 #define __O_TMPFILE	020000000
 #endif
 
+#ifndef O_ALLOW_ENCODED
+#define O_ALLOW_ENCODED	040000000
+#endif
+
 /* a horrid kludge trying to make sure that this will fail on old kernels */
 #define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
 #define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT)      

@@ -0,0 +1,74 @@
+===========
+Encoded I/O
+===========
+
+Encoded I/O is a mechanism for reading and writing encoded (e.g., compressed
+and/or encrypted) data directly from/to the filesystem. The userspace interface
+is thoroughly described in the :manpage:`encoded_io(7)` man page; this document
+describes the requirements for filesystem support.
+
+First of all, a filesystem supporting encoded I/O must indicate this by setting
+the ``FMODE_ENCODED_IO`` flag in its ``file_open`` file operation::
+
+    static int foo_file_open(struct inode *inode, struct file *filp)
+    {
+            ...
+            filep->f_mode |= FMODE_ENCODED_IO;
+            ...
+    }
+
+Encoded I/O goes through ``read_iter`` and ``write_iter``, designated by the
+``IOCB_ENCODED`` flag in ``kiocb->ki_flags``.
+
+Reads
+=====
+
+Encoded ``read_iter`` should:
+
+1. Call ``generic_encoded_read_checks()`` to validate the file and buffers
+   provided by userspace.
+2. Initialize the ``encoded_iov`` appropriately.
+3. Copy it to the user with ``copy_encoded_iov_to_iter()``.
+4. Copy the encoded data to the user.
+5. Advance ``kiocb->ki_pos`` by ``encoded_iov->len``.
+6. Return the size of the encoded data read, not including the ``encoded_iov``.
+
+There are a few details to be aware of:
+
+* Encoded ``read_iter`` should support reading unencoded data if the extent is
+  not encoded.
+* If the buffers provided by the user are not large enough to contain an entire
+  encoded extent, then ``read_iter`` should return ``-ENOBUFS``. This is to
+  avoid confusing userspace with truncated data that cannot be properly
+  decoded.
+* Reads in the middle of an encoded extent can be returned by setting
+  ``encoded_iov->unencoded_offset`` to non-zero.
+* Truncated unencoded data (e.g., because the file does not end on a block
+  boundary) may be returned by setting ``encoded_iov->len`` to a value smaller
+  value than ``encoded_iov->unencoded_len - encoded_iov->unencoded_offset``.
+
+Writes
+======
+
+Encoded ``write_iter`` should (in addition to the usual accounting/checks done
+by ``write_iter``):
+
+1. Call ``copy_encoded_iov_from_iter()`` to get and validate the
+   ``encoded_iov``.
+2. Call ``generic_encoded_write_checks()`` instead of
+   ``generic_write_checks()``.
+3. Check that the provided encoding in ``encoded_iov`` is supported.
+4. Advance ``kiocb->ki_pos`` by ``encoded_iov->len``.
+5. Return the size of the encoded data written.
+
+Again, there are a few details:
+
+* Encoded ``write_iter`` doesn't need to support writing unencoded data.
+* ``write_iter`` should either write all of the encoded data or none of it; it
+  must not do partial writes.
+* ``write_iter`` doesn't need to validate the encoded data; a subsequent read
+  may return, e.g., ``-EIO`` if the data is not valid.
+* The user may lie about the unencoded size of the data; a subsequent read
+  should truncate or zero-extend the unencoded data rather than returning an
+  error.
+* Be careful of page cache coherency.

@@ -55,6 +55,7 @@ filesystem implementations.
    journalling
    fscrypt
    fsverity
+   encoded_io
 
 Filesystems
 ===========

@@ -178,6 +178,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File supports async buffered reads */
 #define FMODE_BUF_RASYNC	((__force fmode_t)0x40000000)
 
+/* File supports encoded IO */
+#define FMODE_ENCODED_IO	((__force fmode_t)0x80000000)
+
 /*
  * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
  * that indicates that they should check the contents of the iovec are

@@ -321,6 +324,7 @@ enum rw_hint {
 /* iocb->ki_waitq is valid */
 #define IOCB_WAITQ		(1 << 8)
 #define IOCB_NOIO		(1 << 9)
+#define IOCB_ENCODED		(1 << 10)
 
 struct kiocb {
 	struct file		*ki_filp;

@@ -3006,6 +3010,13 @@ extern int sb_min_blocksize(struct super_block *, int);
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
 extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
+struct encoded_iov;
+extern int generic_encoded_write_checks(struct kiocb *,
+					const struct encoded_iov *);
+extern int copy_encoded_iov_from_iter(struct encoded_iov *, struct iov_iter *);
+extern ssize_t generic_encoded_read_checks(struct kiocb *, struct iov_iter *);
+extern int copy_encoded_iov_to_iter(const struct encoded_iov *,
+				    struct iov_iter *);
 extern int generic_remap_checks(struct file *file_in, loff_t pos_in,
 				struct file *file_out, loff_t pos_out,
 				loff_t *count, unsigned int remap_flags);

@@ -3324,6 +3335,11 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 			return -EOPNOTSUPP;
 		kiocb_flags |= IOCB_NOWAIT | IOCB_NOIO;
 	}
+	if (flags & RWF_ENCODED) {
+		if (!(ki->ki_filp->f_mode & FMODE_ENCODED_IO))
+			return -EOPNOTSUPP;
+		kiocb_flags |= IOCB_ENCODED;
+	}
 	if (flags & RWF_HIPRI)
 		kiocb_flags |= IOCB_HIPRI;
 	if (flags & RWF_DSYNC)

@@ -279,6 +279,34 @@ struct fsxattr {
 					 SYNC_FILE_RANGE_WAIT_BEFORE | \
 					 SYNC_FILE_RANGE_WAIT_AFTER)
 
+enum {
+	ENCODED_IOV_COMPRESSION_NONE,
+#define ENCODED_IOV_COMPRESSION_NONE ENCODED_IOV_COMPRESSION_NONE
+	ENCODED_IOV_COMPRESSION_ZLIB,
+#define ENCODED_IOV_COMPRESSION_ZLIB ENCODED_IOV_COMPRESSION_ZLIB
+	ENCODED_IOV_COMPRESSION_LZO,
+#define ENCODED_IOV_COMPRESSION_LZO ENCODED_IOV_COMPRESSION_LZO
+	ENCODED_IOV_COMPRESSION_ZSTD,
+#define ENCODED_IOV_COMPRESSION_ZSTD ENCODED_IOV_COMPRESSION_ZSTD
+	ENCODED_IOV_COMPRESSION_TYPES = ENCODED_IOV_COMPRESSION_ZSTD,
+};
+
+enum {
+	ENCODED_IOV_ENCRYPTION_NONE,
+#define ENCODED_IOV_ENCRYPTION_NONE ENCODED_IOV_ENCRYPTION_NONE
+	ENCODED_IOV_ENCRYPTION_TYPES = ENCODED_IOV_ENCRYPTION_NONE,
+};
+
+struct encoded_iov {
+	__aligned_u64 len;
+	__aligned_u64 unencoded_len;
+	__aligned_u64 unencoded_offset;
+	__u32 compression;
+	__u32 encryption;
+};
+
+#define ENCODED_IOV_SIZE_VER0 32
+
 /*
  * Flags for preadv2/pwritev2:
  */

@@ -300,8 +328,11 @@ typedef int __bitwise __kernel_rwf_t;
 /* per-IO O_APPEND */
 #define RWF_APPEND	((__force __kernel_rwf_t)0x00000010)
 
+/* encoded (e.g., compressed and/or encrypted) IO */
+#define RWF_ENCODED	((__force __kernel_rwf_t)0x00000020)
+
 /* mask of flags supported by the kernel */
 #define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
-			 RWF_APPEND)
+			 RWF_APPEND | RWF_ENCODED)
 
 #endif /* _UAPI_LINUX_FS_H */

@@ -3022,24 +3022,15 @@ static int generic_write_check_limits(struct file *file, loff_t pos,
 	return 0;
 }
 
-/*
- * Performs necessary checks before doing a write
- *
- * Can adjust writing position or amount of bytes to write.
- * Returns appropriate error code that caller should return or
- * zero in case that write should be allowed.
- */
-inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
+static int generic_write_checks_common(struct kiocb *iocb, loff_t *count)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
-	loff_t count;
-	int ret;
 
 	if (IS_SWAPFILE(inode))
 		return -ETXTBSY;
 
-	if (!iov_iter_count(from))
+	if (!*count)
 		return 0;
 
 	/* FIXME: this is for backwards compatibility with 2.4 */

@@ -3049,8 +3040,21 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
 	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
 		return -EINVAL;
 
-	count = iov_iter_count(from);
-	ret = generic_write_check_limits(file, iocb->ki_pos, &count);
+	return generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, count);
+}
+
+/*
+ * Performs necessary checks before doing a write
+ *
+ * Can adjust writing position or amount of bytes to write.
+ * Returns a negative errno or the new number of bytes to write.
+ */
+inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+	loff_t count = iov_iter_count(from);
+	int ret;
+
+	ret = generic_write_checks_common(iocb, &count);
 	if (ret)
 		return ret;
 

@@ -3059,6 +3063,142 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
 }
 EXPORT_SYMBOL(generic_write_checks);
 
+/**
+ * generic_encoded_write_checks() - check an encoded write
+ * @iocb: I/O context.
+ * @encoded: Encoding metadata.
+ *
+ * This should be called by RWF_ENCODED write implementations rather than
+ * generic_write_checks(). Unlike generic_write_checks(), it returns -EFBIG
+ * instead of adjusting the size of the write.
+ *
+ * Return: 0 on success, -errno on error.
+ */
+int generic_encoded_write_checks(struct kiocb *iocb,
+				 const struct encoded_iov *encoded)
+{
+	loff_t count = encoded->len;
+	int ret;
+
+	if (!(iocb->ki_filp->f_flags & O_ALLOW_ENCODED))
+		return -EPERM;
+
+	ret = generic_write_checks_common(iocb, &count);
+	if (ret)
+		return ret;
+
+	if (count != encoded->len) {
+		/*
+		 * The write got truncated by generic_write_checks_common(). We
+		 * can't do a partial encoded write.
+		 */
+		return -EFBIG;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(generic_encoded_write_checks);
+
+/**
+ * copy_encoded_iov_from_iter() - copy a &struct encoded_iov from userspace
+ * @encoded: Returned encoding metadata.
+ * @from: Source iterator.
+ *
+ * This copies in the &struct encoded_iov and does some basic sanity checks.
+ * This should always be used rather than a plain copy_from_iter(), as it does
+ * the proper handling for backward- and forward-compatibility.
+ *
+ * Return: 0 on success, -EFAULT if access to userspace failed, -E2BIG if the
+ *         copied structure contained non-zero fields that this kernel doesn't
+ *         support, -EINVAL if the copied structure was invalid.
+ */
+int copy_encoded_iov_from_iter(struct encoded_iov *encoded,
+			       struct iov_iter *from)
+{
+	size_t usize;
+	int ret;
+
+	usize = iov_iter_single_seg_count(from);
+	if (usize > PAGE_SIZE)
+		return -E2BIG;
+	if (usize < ENCODED_IOV_SIZE_VER0)
+		return -EINVAL;
+	ret = copy_struct_from_iter(encoded, sizeof(*encoded), from, usize);
+	if (ret)
+		return ret;
+
+	if (encoded->compression == ENCODED_IOV_COMPRESSION_NONE &&
+	    encoded->encryption == ENCODED_IOV_ENCRYPTION_NONE)
+		return -EINVAL;
+	if (encoded->compression > ENCODED_IOV_COMPRESSION_TYPES ||
+	    encoded->encryption > ENCODED_IOV_ENCRYPTION_TYPES)
+		return -EINVAL;
+	if (encoded->unencoded_offset > encoded->unencoded_len)
+		return -EINVAL;
+	if (encoded->len > encoded->unencoded_len - encoded->unencoded_offset)
+		return -EINVAL;
+	return 0;
+}
+EXPORT_SYMBOL(copy_encoded_iov_from_iter);
+
+/**
+ * generic_encoded_read_checks() - sanity check an RWF_ENCODED read
+ * @iocb: I/O context.
+ * @iter: Destination iterator for read.
+ *
+ * This should always be called by RWF_ENCODED read implementations before
+ * returning any data.
+ *
+ * Return: Number of bytes available to return encoded data in @iter on success,
+ *         -EPERM if the file was not opened with O_ALLOW_ENCODED, -EINVAL if
+ *         the size of the &struct encoded_iov iovec is invalid.
+ */
+ssize_t generic_encoded_read_checks(struct kiocb *iocb, struct iov_iter *iter)
+{
+	size_t usize;
+
+	if (!(iocb->ki_filp->f_flags & O_ALLOW_ENCODED))
+		return -EPERM;
+	usize = iov_iter_single_seg_count(iter);
+	if (usize > PAGE_SIZE || usize < ENCODED_IOV_SIZE_VER0)
+		return -EINVAL;
+	return iov_iter_count(iter) - usize;
+}
+EXPORT_SYMBOL(generic_encoded_read_checks);
+
+/**
+ * copy_encoded_iov_to_iter() - copy a &struct encoded_iov to userspace
+ * @encoded: Encoding metadata to return.
+ * @to: Destination iterator.
+ *
+ * This should always be used by RWF_ENCODED read implementations rather than a
+ * plain copy_to_iter(), as it does the proper handling for backward- and
+ * forward-compatibility. The iterator must be sanity-checked with
+ * generic_encoded_read_checks() before this is called.
+ *
+ * Return: 0 on success, -EFAULT if access to userspace failed, -E2BIG if there
+ *         were non-zero fields in @encoded that the user buffer could not
+ *         accommodate.
+ */
+int copy_encoded_iov_to_iter(const struct encoded_iov *encoded,
+			     struct iov_iter *to)
+{
+	size_t ksize = sizeof(*encoded);
+	size_t usize = iov_iter_single_seg_count(to);
+	size_t size = min(ksize, usize);
+
+	/* We already sanity-checked usize in generic_encoded_read_checks(). */
+
+	if (usize < ksize &&
+	    memchr_inv((char *)encoded + usize, 0, ksize - usize))
+		return -E2BIG;
+	if (copy_to_iter(encoded, size, to) != size ||
+	    (usize > ksize &&
+	     iov_iter_zero(usize - ksize, to) != usize - ksize))
+		return -EFAULT;
+	return 0;
+}
+EXPORT_SYMBOL(copy_encoded_iov_to_iter);
+
 /*
  * Performs necessary checks before doing a clone.
  *

@@ -438,7 +438,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 			BUG_ON(ret); /* -ENOMEM */
 
 			if (!skip_sum) {
-				ret = btrfs_csum_one_bio(inode, bio, start, 1);
+				ret = btrfs_csum_one_bio(inode, bio, start,
+							 true);
 				BUG_ON(ret); /* -ENOMEM */
 			}
 

@@ -470,7 +471,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 	BUG_ON(ret); /* -ENOMEM */
 
 	if (!skip_sum) {
-		ret = btrfs_csum_one_bio(inode, bio, start, 1);
+		ret = btrfs_csum_one_bio(inode, bio, start, true);
 		BUG_ON(ret); /* -ENOMEM */
 	}
 

@@ -2917,7 +2917,7 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct btrfs_ordered_sum *sums);
 blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
-				u64 file_start, int contig);
+				u64 offset, bool one_ordered);
 int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 			     struct list_head *list, int search_commit);
 void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,

@@ -516,28 +516,28 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
  * btrfs_csum_one_bio - Calculates checksums of the data contained inside a bio
  * @inode:	 Owner of the data inside the bio
  * @bio:	 Contains the data to be checksummed
- * @file_start:  offset in file this bio begins to describe
- * @contig:	 Boolean. If true/1 means all bio vecs in this bio are
- *		 contiguous and they begin at @file_start in the file. False/0
- *		 means this bio can contains potentially discontigous bio vecs
- *		 so the logical offset of each should be calculated separately.
+ * @offset:      If (u64)-1, @bio may contain discontiguous bio vecs, so the
+ *               file offsets are determined from the page offsets in the bio.
+ *               Otherwise, this is the starting file offset of the bio vecs in
+ *               @bio, which must be contiguous.
+ * @one_ordered: If true, @bio only refers to one ordered extent.
  */
 blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
-		       u64 file_start, int contig)
+				u64 offset, bool one_ordered)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
 	struct btrfs_ordered_sum *sums;
 	struct btrfs_ordered_extent *ordered = NULL;
+	const bool page_offsets = (offset == (u64)-1);
 	char *data;
 	struct bvec_iter iter;
 	struct bio_vec bvec;
 	int index;
-	int nr_sectors;
+	int blockcount;
 	unsigned long total_bytes = 0;
 	unsigned long this_sum_bytes = 0;
 	int i;
-	u64 offset;
 	unsigned nofs_flag;
 	const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
 

@@ -552,18 +552,13 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
 	sums->len = bio->bi_iter.bi_size;
 	INIT_LIST_HEAD(&sums->list);
 
-	if (contig)
-		offset = file_start;
-	else
-		offset = 0; /* shut up gcc */
-
 	sums->bytenr = (u64)bio->bi_iter.bi_sector << 9;
 	index = 0;
 
 	shash->tfm = fs_info->csum_shash;
 
 	bio_for_each_segment(bvec, bio, iter) {
-		if (!contig)
+		if (page_offsets)
 			offset = page_offset(bvec.bv_page) + bvec.bv_offset;
 
 		if (!ordered) {

@@ -571,13 +566,14 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
 			BUG_ON(!ordered); /* Logic error */
 		}
 
-		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info,
+		blockcount = BTRFS_BYTES_TO_BLKS(fs_info,
 						 bvec.bv_len + fs_info->sectorsize
 						 - 1);
 
-		for (i = 0; i < nr_sectors; i++) {
-			if (offset >= ordered->file_offset + ordered->num_bytes ||
-			    offset < ordered->file_offset) {
+		for (i = 0; i < blockcount; i++) {
+			if (!one_ordered &&
+			    (offset >= ordered->file_offset + ordered->num_bytes ||
+			     offset < ordered->file_offset)) {
 				unsigned long bytes_left;
 
 				sums->len = this_sum_bytes;

@@ -608,7 +604,8 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
 					    sums->sums + index);
 			kunmap_atomic(data);
 			index += csum_size;
-			offset += fs_info->sectorsize;
+			if (!one_ordered)
+				offset += fs_info->sectorsize;
 			this_sum_bytes += fs_info->sectorsize;
 			total_bytes += fs_info->sectorsize;
 		}

@@ -2162,7 +2162,7 @@ static blk_status_t btrfs_submit_bio_start(void *private_data, struct bio *bio,
 {
 	struct inode *inode = private_data;
 
-	return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0);
+	return btrfs_csum_one_bio(BTRFS_I(inode), bio, (u64)-1, false);
 }
 
 /*

@@ -2225,7 +2225,7 @@ static blk_status_t btrfs_submit_bio_hook(struct inode *inode, struct bio *bio,
 					  0, inode, btrfs_submit_bio_start);
 		goto out;
 	} else if (!skip_sum) {
-		ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0);
+		ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, (u64)-1, false);
 		if (ret)
 			goto out;
 	}

@@ -7609,7 +7609,7 @@ static blk_status_t btrfs_submit_bio_start_direct_io(void *private_data,
 {
 	struct inode *inode = private_data;
 
-	return btrfs_csum_one_bio(BTRFS_I(inode), bio, offset, 1);
+	return btrfs_csum_one_bio(BTRFS_I(inode), bio, offset, false);
 }
 
 static void btrfs_end_dio_bio(struct bio *bio)

@@ -7668,7 +7668,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio,
 		 * If we aren't doing async submit, calculate the csum of the
 		 * bio now.
 		 */
-		ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, file_offset, 1);
+		ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, file_offset, false);
 		if (ret)
 			goto err;
 	} else {

@@ -869,13 +869,12 @@ static noinline void submit_compressed_extents(struct async_chunk *async_chunk)
 			goto out_free_reserve;
 		free_extent_map(em);
 
-		ret = btrfs_add_ordered_extent_compress(inode,
-						async_extent->start,
-						ins.objectid,
-						async_extent->ram_size,
-						ins.offset,
-						BTRFS_ORDERED_COMPRESSED,
-						async_extent->compress_type);
+		ret = btrfs_add_ordered_extent(inode, async_extent->start,
+					       async_extent->ram_size,
+					       async_extent->ram_size,
+					       ins.objectid, ins.offset, 0,
+					       1 << BTRFS_ORDERED_COMPRESSED,
+					       async_extent->compress_type);
 		if (ret) {
 			btrfs_drop_extent_cache(inode, async_extent->start,
 						async_extent->start +