Skip to contentSkip to conversation

btrfs: implement send/receive of compressed extents without decompressing

PATCH Superseded Omar Sandoval 1 participant 17 messages Jan 22, 2021

Subsystems (4)

v3 of 7 Superseded Latest is v7 →

lore
Share & tools
lore
#1 lore raw

PATCH v3 1/11 btrfs-progs: receive: support v2 send stream larger tlv_len

In reply to Omar Sandoval

From: Boris Burkov <[email protected]>

An encoded extent can be up to 128K in length, which exceeds the largest value expressible by the current send stream format's 16 bit tlv_len field. Since encoded writes cannot be split into multiple writes by btrfs send, the send stream format must change to accommodate encoded writes.

Supporting this changed format requires retooling how we store the commands we have processed. Since we can no longer use btrfs_tlv_header to describe every attribute, we define a new struct btrfs_send_attribute which has a 32 bit length field, and use that to store the attribute information needed for receive processing. This is transparent to users of the various TLV_GET macros.

---
 common/send-stream.c | 34 +++++++++++++++++++++++++---------
 1 file changed, 25 insertions(+), 9 deletions(-)
common/send-stream.c +25 -9
index a0c52f79..cd5aa311 100644
@@ -24,13 +24,23 @@
 #include "crypto/crc32c.h"
 #include "common/utils.h"
 
+struct btrfs_send_attribute {
+	u16 tlv_type;
+	/*
+	 * Note: in btrfs_tlv_header, this is __le16, but we need 32 bits for
+	 * attributes with file data as of version 2 of the send stream format
+	 */
+	u32 tlv_len;
+	char *data;
+};
+
 struct btrfs_send_stream {
 	char read_buf[BTRFS_SEND_BUF_SIZE];
 	int fd;
 
 	int cmd;
 	struct btrfs_cmd_header *cmd_hdr;
-	struct btrfs_tlv_header *cmd_attrs[BTRFS_SEND_A_MAX + 1];
+	struct btrfs_send_attribute cmd_attrs[BTRFS_SEND_A_MAX + 1];
 	u32 version;
 
 	/*
@@ -152,6 +162,7 @@ static int read_cmd(struct btrfs_send_stream *sctx)
 		struct btrfs_tlv_header *tlv_hdr;
 		u16 tlv_type;
 		u16 tlv_len;
+		struct btrfs_send_attribute *send_attr;
 
 		tlv_hdr = (struct btrfs_tlv_header *)data;
 		tlv_type = le16_to_cpu(tlv_hdr->tlv_type);
@@ -164,10 +175,15 @@ static int read_cmd(struct btrfs_send_stream *sctx)
 			goto out;
 		}
 
-		sctx->cmd_attrs[tlv_type] = tlv_hdr;
+		send_attr = &sctx->cmd_attrs[tlv_type];
+		send_attr->tlv_type = tlv_type;
+		send_attr->tlv_len = tlv_len;
+		pos += sizeof(*tlv_hdr);
+		data += sizeof(*tlv_hdr);
 
-		data += sizeof(*tlv_hdr) + tlv_len;
-		pos += sizeof(*tlv_hdr) + tlv_len;
+		send_attr->data = data;
+		pos += send_attr->tlv_len;
+		data += send_attr->tlv_len;
 	}
 
 	sctx->cmd = cmd;
@@ -180,7 +196,7 @@ out:
 static int tlv_get(struct btrfs_send_stream *sctx, int attr, void **data, int *len)
 {
 	int ret;
-	struct btrfs_tlv_header *hdr;
+	struct btrfs_send_attribute *send_attr;
 
 	if (attr <= 0 || attr > BTRFS_SEND_A_MAX) {
 		error("invalid attribute requested, attr = %d", attr);
@@ -188,15 +204,15 @@ static int tlv_get(struct btrfs_send_stream *sctx, int attr, void **data, int *l
 		goto out;
 	}
 
-	hdr = sctx->cmd_attrs[attr];
-	if (!hdr) {
+	send_attr = &sctx->cmd_attrs[attr];
+	if (!send_attr->data) {
 		error("attribute %d requested but not present", attr);
 		ret = -ENOENT;
 		goto out;
 	}
 
-	*len = le16_to_cpu(hdr->tlv_len);
-	*data = hdr + 1;
+	*len = send_attr->tlv_len;
+	*data = send_attr->data;
 
 	ret = 0;
 
Signature · 1 line
2.30.0
#0 lore raw

v3 cover btrfs: implement send/receive of compressed extents without decompressing

From: Omar Sandoval <[email protected]>

This series uses the interface added in "fs: interface for directly reading/writing compressed data" to send and receive compressed data without wastefully decompressing and recompressing it. It does so by

1. Bumping the send stream protocol version to 2.
2. Adding a new command, BTRFS_SEND_C_ENCODED_WRITE, and its associated attributes that indicates a write using the new encoded I/O interface.
3. Sending compressed extents with BTRFS_SEND_C_ENCODED_WRITE when requested by the user.
4. Falling back to decompressing and writing the decompressed data if encoded I/O fails.

Benchmarks
==========

I ran some benchmarks on send and receive of a zstd (level 3) compressed snapshot of a server's root filesystem which is about 23GB when compressed and 50GB when decompressed.

Send v1:
0.41user 81.97system 2:21.71elapsed 58%CPU (0avgtext+0avgdata 2900maxresident)k 47182656inputs+0outputs (10major+119minor)pagefaults 0swaps

Send compressed:
0.43user 60.53system 2:20.62elapsed 43%CPU (0avgtext+0avgdata 2836maxresident)k 47778864inputs+0outputs (8major+117minor)pagefaults 0swaps

In this case, the bottleneck for send is reading the metadata trees and data from disk, so there's not much of a wall time improvement, but since the kernel doesn't have to decompress the data in the compressed case, it uses significantly less CPU and system time.

Receive v1 into a filesystem with compress=none:
15.58user 62.36system 7:34.44elapsed 17%CPU (0avgtext+0avgdata 3028maxresident)k 104719648inputs+105333248outputs (1major+140minor)pagefaults 0swaps

Receive v1 into a filesystem with compress-force=zstd:
15.45user 63.99system 5:11.57elapsed 25%CPU (0avgtext+0avgdata 3100maxresident)k 104587240inputs+105379328outputs (1major+143minor)pagefaults 0swaps

Receive compressed into a filesystem with compress-force=zstd:
7.95user 44.53system 3:42.79elapsed 23%CPU (0avgtext+0avgdata 2992maxresident)k 46909600inputs+21603216outputs (2major+176minor)pagefaults 0swaps

Without compressed receive, recompressing the data is still a wall time win because it requires much less I/O. However, compressed receive reduces the wall time even further.

The v1 send stream is 50GB, and the v2 send stream is 23 GB. The v1 send stream compresses down to 17GB with zstd (level 3), so compressed send gets pretty close with no extra CPU overhead (the reason that compressed send is still larger is of course that we compress extents individually, which does not compress as efficiently as compressing the entire filesystem representation in one go).

# ls -lh v1.send v1.send.zst compressed.send
-rw-r--r-- 1 root root 23G Aug 17 12:34 compressed.send                 
-rw-r--r-- 1 root root 50G Aug 17 12:13 v1.send                           
-rw-r--r-- 1 root root 17G Aug 17 12:28 v1.send.zst               

Protocol Updates
================

This series makes some changes to the send stream protocol beyond adding the encoded write command/attributes and bumping the version. Namely, v1 has a 64k limit on the size of a write due to the 16-bit attribute length. This is not enough for encoded writes, as compressed extents may be up to 128k and cannot be split up. To address this, the BTRFS_SEND_A_DATA is treated specially in v2: its length is implicitly the remaining length of the command (which has a 32-bit length). This was the least bad of the options I considered.

There are other commands that we've been wanting to add to the protocol:
fallocate and FS_IOC_SETFLAGS. This series reserves their command and attribute numbers but does not implement kernel support for emitting them. However, it does implement support in receive for them, so the kernel can start emitting those whenever we get around to implementing them.

Interface
=========

For the send ioctl, stream version 2 is opt-in, and compressed writes are opt-in separately (but dependent on) stream version 2.

Accordingly, btrfs send now accepts a --stream-version option and a --compressed-data option; the latter implies --stream-version 2.

btrfs receive also accepts a --force-decompress option that forces the fallback to decompressing and writing the decompressed data.

These options are provided to give the user flexibility in case they don't want their receiving filesytem to be compressed.

Patches
=======

The kernel patches are based on kdave/misc-next plus v7 of my "fs:
interface for directly reading/writing compressed data" series. Patches 1-3 do some preparation for stream v2 and compressed send. Patch 4 implements compressed send. Patch 5 modifies the ioctl to accept the new flags and enable the new feature.

Changes since v2 [1]:

- Added reviewed-bys.

Omar Sandoval (5):
btrfs: add send stream v2 definitions
btrfs: send: write larger chunks when using stream v2
btrfs: send: allocate send buffer with alloc_page() and vmap() for v2
btrfs: send: send compressed extents with encoded writes
btrfs: send: enable support for stream v2 and compressed writes

 fs/btrfs/ctree.h           |   4 +
 fs/btrfs/inode.c           |   6 +-
 fs/btrfs/send.c            | 307 +++++++++++++++++++++++++++++++++----
 fs/btrfs/send.h            |  32 +++-
 include/uapi/linux/btrfs.h |  17 +-
 5 files changed, 332 insertions(+), 34 deletions(-)

The btrfs-progs patches were written by Boris Burkov with some updates from me. Patches 1-5 are preparation. Patch 6 implements encoded writes. Patch 7 implements the fallback to decompressing. Patches 9 and 10 implement the other commands. Patch 10 adds the new btrfs send options. Patch 11 adds a test case.

Changes since v2 [1]:

- Dropped O_CLOEXEC addition now that the requirement was dropped in the kernel.
- Updated encoded I/O definitions to match the new ones in the kernel.

Boris Burkov (11):
btrfs-progs: receive: support v2 send stream larger tlv_len
btrfs-progs: receive: dynamically allocate sctx->read_buf
btrfs-progs: receive: support v2 send stream DATA tlv format
btrfs-progs: receive: add send stream v2 cmds and attrs to send.h
btrfs-progs: receive: add stub implementation for pwritev2
btrfs-progs: receive: process encoded_write commands
btrfs-progs: receive: encoded_write fallback to explicit decode and
write
btrfs-progs: receive: process fallocate commands
btrfs-progs: receive: process setflags ioctl commands
btrfs-progs: send: stream v2 ioctl flags
btrfs-progs: receive: add tests for basic encoded_write send/receive

 Documentation/btrfs-receive.asciidoc          |   4 +
 Documentation/btrfs-send.asciidoc             |  16 +-
 Makefile                                      |   4 +-
 cmds/receive-dump.c                           |  31 +-
 cmds/receive.c                                | 403 +++++++++++++++++-
 cmds/send.c                                   |  54 ++-
 common/send-stream.c                          | 157 +++++--
 common/send-stream.h                          |   7 +
 configure.ac                                  |   1 +
 ioctl.h                                       |  17 +-
 libbtrfsutil/btrfs.h                          |  17 +-
 send.h                                        |  19 +-
 stubs.c                                       |  24 ++
 stubs.h                                       |  57 +++
 .../043-receive-write-encoded/test.sh         | 114 +++++
 15 files changed, 874 insertions(+), 51 deletions(-)
 create mode 100644 stubs.c
 create mode 100644 stubs.h
 create mode 100755 tests/misc-tests/043-receive-write-encoded/test.sh

1: https://lore.kernel.org/linux-btrfs/[email protected]/

Signature · 1 line
2.30.0
#2 lore raw

PATCH v3 1/5 btrfs: add send stream v2 definitions

From: Omar Sandoval <[email protected]>

This adds the definitions of the new commands for send stream version 2 and their respective attributes: fallocate, FS_IOC_SETFLAGS (a.k.a. chattr), and encoded writes. It also documents two changes to the send stream format in v2: the receiver shouldn't assume a maximum command size, and the DATA attribute is encoded differently to allow for writes larger than 64k. These will be implemented in subsequent changes, and then the ioctl will accept the new flags.

---
 fs/btrfs/send.c            |  2 +-
 fs/btrfs/send.h            | 30 +++++++++++++++++++++++++++++-
 include/uapi/linux/btrfs.h | 13 +++++++++++++
 3 files changed, 43 insertions(+), 2 deletions(-)
fs/btrfs/send.c +1 -1
index 3bcbf2bcb869..d07570588a16 100644
@@ -7267,7 +7267,7 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 
 	sctx->clone_roots_cnt = arg->clone_sources_count;
 
-	sctx->send_max_size = BTRFS_SEND_BUF_SIZE;
+	sctx->send_max_size = BTRFS_SEND_BUF_SIZE_V1;
 	sctx->send_buf = kvmalloc(sctx->send_max_size, GFP_KERNEL);
 	if (!sctx->send_buf) {
 		ret = -ENOMEM;
fs/btrfs/send.h +29 -1
index de91488b7cd0..9f4f7b96b1eb 100644
@@ -12,7 +12,11 @@
 #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream"
 #define BTRFS_SEND_STREAM_VERSION 1
 
-#define BTRFS_SEND_BUF_SIZE SZ_64K
+/*
+ * In send stream v1, no command is larger than 64k. In send stream v2, no limit
+ * should be assumed.
+ */
+#define BTRFS_SEND_BUF_SIZE_V1 SZ_64K
 
 enum btrfs_tlv_type {
 	BTRFS_TLV_U8,
@@ -76,6 +80,13 @@ enum btrfs_send_cmd {
 
 	BTRFS_SEND_C_END,
 	BTRFS_SEND_C_UPDATE_EXTENT,
+
+	/* The following commands were added in send stream v2. */
+
+	BTRFS_SEND_C_FALLOCATE,
+	BTRFS_SEND_C_SETFLAGS,
+	BTRFS_SEND_C_ENCODED_WRITE,
+
 	__BTRFS_SEND_C_MAX,
 };
 #define BTRFS_SEND_C_MAX (__BTRFS_SEND_C_MAX - 1)
@@ -106,6 +117,11 @@ enum {
 	BTRFS_SEND_A_PATH_LINK,
 
 	BTRFS_SEND_A_FILE_OFFSET,
+	/*
+	 * In send stream v2, this attribute is special: it must be the last
+	 * attribute in a command, its header contains only the type, and its
+	 * length is implicitly the remaining length of the command.
+	 */
 	BTRFS_SEND_A_DATA,
 
 	BTRFS_SEND_A_CLONE_UUID,
@@ -114,6 +130,18 @@ enum {
 	BTRFS_SEND_A_CLONE_OFFSET,
 	BTRFS_SEND_A_CLONE_LEN,
 
+	/* The following attributes were added in send stream v2. */
+
+	BTRFS_SEND_A_FALLOCATE_MODE,
+
+	BTRFS_SEND_A_SETFLAGS_FLAGS,
+
+	BTRFS_SEND_A_UNENCODED_FILE_LEN,
+	BTRFS_SEND_A_UNENCODED_LEN,
+	BTRFS_SEND_A_UNENCODED_OFFSET,
+	BTRFS_SEND_A_COMPRESSION,
+	BTRFS_SEND_A_ENCRYPTION,
+
 	__BTRFS_SEND_A_MAX,
 };
 #define BTRFS_SEND_A_MAX (__BTRFS_SEND_A_MAX - 1)
include/uapi/linux/btrfs.h +13 -0
index 5df73001aad4..93aa0932234e 100644
@@ -770,6 +770,19 @@ struct btrfs_ioctl_received_subvol_args {
  */
 #define BTRFS_SEND_FLAG_OMIT_END_CMD		0x4
 
+/*
+ * Use version 2 of the send stream, which adds new commands and supports larger
+ * writes.
+ */
+#define BTRFS_SEND_FLAG_STREAM_V2		0x8
+
+/*
+ * Send compressed data using the ENCODED_WRITE command instead of decompressing
+ * the data and sending it with the WRITE command. This requires
+ * BTRFS_SEND_FLAG_STREAM_V2.
+ */
+#define BTRFS_SEND_FLAG_COMPRESSED		0x10
+
 #define BTRFS_SEND_FLAG_MASK \
 	(BTRFS_SEND_FLAG_NO_FILE_DATA | \
 	 BTRFS_SEND_FLAG_OMIT_STREAM_HEADER | \
Signature · 1 line
2.30.0
#3 lore raw

PATCH v3 2/5 btrfs: send: write larger chunks when using stream v2

In reply to Omar Sandoval

From: Omar Sandoval <[email protected]>

The length field of the send stream TLV header is 16 bits. This means that the maximum amount of data that can be sent for one write is 64k minus one. However, encoded writes must be able to send the maximum compressed extent (128k) in one command. To support this, send stream version 2 encodes the DATA attribute differently: it has no length field, and the length is implicitly up to the end of containing command (which has a 32-bit length field). Although this is necessary for encoded writes, normal writes can benefit from it, too.

For v2, let's bump up the send buffer to the maximum compressed extent size plus 16k for the other metadata (144k total). Since this will most likely be vmalloc'd (and always will be after the next commit), we round it up to the next page since we might as well use the rest of the page on systems with >16k pages.

---
 fs/btrfs/send.c | 34 ++++++++++++++++++++++++++--------
 1 file changed, 26 insertions(+), 8 deletions(-)
fs/btrfs/send.c +26 -8
index d07570588a16..98948568017c 100644
@@ -4915,14 +4915,27 @@ static inline u64 max_send_read_size(const struct send_ctx *sctx)
 
 static int put_data_header(struct send_ctx *sctx, u32 len)
 {
-	struct btrfs_tlv_header *hdr;
+	if (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2) {
+		/*
+		 * In v2, the data attribute header doesn't include a length; it
+		 * is implicitly to the end of the command.
+		 */
+		if (sctx->send_max_size - sctx->send_size < 2 + len)
+			return -EOVERFLOW;
+		put_unaligned_le16(BTRFS_SEND_A_DATA,
+				   sctx->send_buf + sctx->send_size);
+		sctx->send_size += 2;
+	} else {
+		struct btrfs_tlv_header *hdr;
 
-	if (sctx->send_max_size - sctx->send_size < sizeof(*hdr) + len)
-		return -EOVERFLOW;
-	hdr = (struct btrfs_tlv_header *)(sctx->send_buf + sctx->send_size);
-	put_unaligned_le16(BTRFS_SEND_A_DATA, &hdr->tlv_type);
-	put_unaligned_le16(len, &hdr->tlv_len);
-	sctx->send_size += sizeof(*hdr);
+		if (sctx->send_max_size - sctx->send_size < sizeof(*hdr) + len)
+			return -EOVERFLOW;
+		hdr = (struct btrfs_tlv_header *)(sctx->send_buf +
+						  sctx->send_size);
+		put_unaligned_le16(BTRFS_SEND_A_DATA, &hdr->tlv_type);
+		put_unaligned_le16(len, &hdr->tlv_len);
+		sctx->send_size += sizeof(*hdr);
+	}
 	return 0;
 }
 
@@ -7267,7 +7280,12 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 
 	sctx->clone_roots_cnt = arg->clone_sources_count;
 
-	sctx->send_max_size = BTRFS_SEND_BUF_SIZE_V1;
+	if (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2) {
+		sctx->send_max_size = ALIGN(SZ_16K + BTRFS_MAX_COMPRESSED,
+					    PAGE_SIZE);
+	} else {
+		sctx->send_max_size = BTRFS_SEND_BUF_SIZE_V1;
+	}
 	sctx->send_buf = kvmalloc(sctx->send_max_size, GFP_KERNEL);
 	if (!sctx->send_buf) {
 		ret = -ENOMEM;
Signature · 1 line
2.30.0
#4 lore raw

PATCH v3 2/11 btrfs-progs: receive: dynamically allocate sctx->read_buf

In reply to Omar Sandoval

From: Boris Burkov <[email protected]>

In send stream v2, write commands can now be an arbitrary size. For that reason, we can no longer allocate a fixed array in sctx for read_cmd. Instead, read_cmd dynamically allocates sctx->read_buf. To avoid needless reallocations, we reuse read_buf between read_cmd calls by also keeping track of the size of the allocated buffer in sctx->read_buf_sz.

We do the first allocation of the old default size at the start of processing the stream, and we only reallocate if we encounter a command that needs a larger buffer.

---
 common/send-stream.c | 55 ++++++++++++++++++++++++++++----------------
 send.h               |  2 +-
 2 files changed, 36 insertions(+), 21 deletions(-)
common/send-stream.c +35 -20
index cd5aa311..3d3585c3 100644
@@ -35,11 +35,11 @@ struct btrfs_send_attribute {
 };
 
 struct btrfs_send_stream {
-	char read_buf[BTRFS_SEND_BUF_SIZE];
+	char *read_buf;
+	size_t read_buf_sz;
 	int fd;
 
 	int cmd;
-	struct btrfs_cmd_header *cmd_hdr;
 	struct btrfs_send_attribute cmd_attrs[BTRFS_SEND_A_MAX + 1];
 	u32 version;
 
@@ -111,11 +111,12 @@ static int read_cmd(struct btrfs_send_stream *sctx)
 	u32 pos;
 	u32 crc;
 	u32 crc2;
+	struct btrfs_cmd_header *cmd_hdr;
+	size_t buf_len;
 
 	memset(sctx->cmd_attrs, 0, sizeof(sctx->cmd_attrs));
 
-	ASSERT(sizeof(*sctx->cmd_hdr) <= sizeof(sctx->read_buf));
-	ret = read_buf(sctx, sctx->read_buf, sizeof(*sctx->cmd_hdr));
+	ret = read_buf(sctx, sctx->read_buf, sizeof(*cmd_hdr));
 	if (ret < 0)
 		goto out;
 	if (ret) {
@@ -124,18 +125,22 @@ static int read_cmd(struct btrfs_send_stream *sctx)
 		goto out;
 	}
 
-	sctx->cmd_hdr = (struct btrfs_cmd_header *)sctx->read_buf;
-	cmd = le16_to_cpu(sctx->cmd_hdr->cmd);
-	cmd_len = le32_to_cpu(sctx->cmd_hdr->len);
-
-	if (cmd_len + sizeof(*sctx->cmd_hdr) >= sizeof(sctx->read_buf)) {
-		ret = -EINVAL;
-		error("command length %u too big for buffer %zu",
-				cmd_len, sizeof(sctx->read_buf));
-		goto out;
+	cmd_hdr = (struct btrfs_cmd_header *)sctx->read_buf;
+	cmd_len = le32_to_cpu(cmd_hdr->len);
+	cmd = le16_to_cpu(cmd_hdr->cmd);
+	buf_len = sizeof(*cmd_hdr) + cmd_len;
+	if (sctx->read_buf_sz < buf_len) {
+		sctx->read_buf = realloc(sctx->read_buf, buf_len);
+		if (!sctx->read_buf) {
+			ret = -ENOMEM;
+			error("failed to reallocate read buffer for cmd");
+			goto out;
+		}
+		sctx->read_buf_sz = buf_len;
+		/* We need to reset cmd_hdr after realloc of sctx->read_buf */
+		cmd_hdr = (struct btrfs_cmd_header *)sctx->read_buf;
 	}
-
-	data = sctx->read_buf + sizeof(*sctx->cmd_hdr);
+	data = sctx->read_buf + sizeof(*cmd_hdr);
 	ret = read_buf(sctx, data, cmd_len);
 	if (ret < 0)
 		goto out;
@@ -145,11 +150,12 @@ static int read_cmd(struct btrfs_send_stream *sctx)
 		goto out;
 	}
 
-	crc = le32_to_cpu(sctx->cmd_hdr->crc);
-	sctx->cmd_hdr->crc = 0;
+	crc = le32_to_cpu(cmd_hdr->crc);
+	/* in send, crc is computed with header crc = 0, replicate that */
+	cmd_hdr->crc = 0;
 
 	crc2 = crc32c(0, (unsigned char*)sctx->read_buf,
-			sizeof(*sctx->cmd_hdr) + cmd_len);
+			sizeof(*cmd_hdr) + cmd_len);
 
 	if (crc != crc2) {
 		ret = -EINVAL;
@@ -524,19 +530,28 @@ int btrfs_read_and_process_send_stream(int fd,
 		goto out;
 	}
 
+	sctx.read_buf = malloc(BTRFS_SEND_BUF_SIZE_V1);
+	if (!sctx.read_buf) {
+		ret = -ENOMEM;
+		error("unable to allocate send stream read buffer");
+		goto out;
+	}
+	sctx.read_buf_sz = BTRFS_SEND_BUF_SIZE_V1;
+
 	while (1) {
 		ret = read_and_process_cmd(&sctx);
 		if (ret < 0) {
 			last_err = ret;
 			errors++;
 			if (max_errors > 0 && errors >= max_errors)
-				goto out;
+				break;
 		} else if (ret > 0) {
 			if (!honor_end_cmd)
 				ret = 0;
-			goto out;
+			break;
 		}
 	}
+	free(sctx.read_buf);
 
 out:
 	if (last_err && !ret)
send.h +1 -1
index 8dd865ec..228928a0 100644
@@ -33,7 +33,7 @@ extern "C" {
 #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream"
 #define BTRFS_SEND_STREAM_VERSION 1
 
-#define BTRFS_SEND_BUF_SIZE SZ_64K
+#define BTRFS_SEND_BUF_SIZE_V1 SZ_64K
 #define BTRFS_SEND_READ_SIZE (1024 * 48)
 
 enum btrfs_tlv_type {
Signature · 1 line
2.30.0
#5 lore raw

PATCH v3 3/11 btrfs-progs: receive: support v2 send stream DATA tlv format

In reply to Omar Sandoval

From: Boris Burkov <[email protected]>

The new format privileges the BTRFS_SEND_A_DATA attribute by guaranteeing it will always be the last attribute in any command that needs it, and by implicitly encoding the data length as the difference between the total command length in the command header and the sizes of the rest of the attributes (and of course the tlv_type identifying the DATA attribute). To parse the new stream, we must read the tlv_type and if it is not DATA, we proceed normally, but if it is DATA, we don't parse a tlv_len but simply compute the length.

In addition, we add some bounds checking when parsing each chunk of data, as well as for the tlv_len itself.

---
 common/send-stream.c | 36 ++++++++++++++++++++++++++----------
 1 file changed, 26 insertions(+), 10 deletions(-)
common/send-stream.c +26 -10
index 3d3585c3..4d819185 100644
@@ -165,28 +165,44 @@ static int read_cmd(struct btrfs_send_stream *sctx)
 
 	pos = 0;
 	while (pos < cmd_len) {
-		struct btrfs_tlv_header *tlv_hdr;
 		u16 tlv_type;
-		u16 tlv_len;
 		struct btrfs_send_attribute *send_attr;
 
-		tlv_hdr = (struct btrfs_tlv_header *)data;
-		tlv_type = le16_to_cpu(tlv_hdr->tlv_type);
-		tlv_len = le16_to_cpu(tlv_hdr->tlv_len);
+		if (cmd_len - pos < sizeof(__le16)) {
+			error("send stream is truncated");
+			ret = -EINVAL;
+			goto out;
+		}
+		tlv_type = le16_to_cpu(*(__le16 *)data);
 
 		if (tlv_type == 0 || tlv_type > BTRFS_SEND_A_MAX) {
-			error("invalid tlv in cmd tlv_type = %hu, tlv_len = %hu",
-					tlv_type, tlv_len);
+			error("invalid tlv in cmd tlv_type = %hu", tlv_type);
 			ret = -EINVAL;
 			goto out;
 		}
 
 		send_attr = &sctx->cmd_attrs[tlv_type];
 		send_attr->tlv_type = tlv_type;
-		send_attr->tlv_len = tlv_len;
-		pos += sizeof(*tlv_hdr);
-		data += sizeof(*tlv_hdr);
 
+		pos += sizeof(tlv_type);
+		data += sizeof(tlv_type);
+		if (sctx->version == 2 && tlv_type == BTRFS_SEND_A_DATA) {
+			send_attr->tlv_len = cmd_len - pos;
+		} else {
+			if (cmd_len - pos < sizeof(__le16)) {
+				error("send stream is truncated");
+				ret = -EINVAL;
+				goto out;
+			}
+			send_attr->tlv_len = le16_to_cpu(*(__le16 *)data);
+			pos += sizeof(__le16);
+			data += sizeof(__le16);
+		}
+		if (cmd_len - pos < send_attr->tlv_len) {
+			error("send stream is truncated");
+			ret = -EINVAL;
+			goto out;
+		}
 		send_attr->data = data;
 		pos += send_attr->tlv_len;
 		data += send_attr->tlv_len;
Signature · 1 line
2.30.0
#6 lore raw

PATCH v3 3/5 btrfs: send: allocate send buffer with alloc_page() and vmap() for v2

In reply to Omar Sandoval

From: Omar Sandoval <[email protected]>

For encoded writes, we need the raw pages for reading compressed data directly via a bio. So, replace kvmalloc() with vmap() so we have access to the raw pages. 144k is large enough that it usually gets allocated with vmalloc(), anyways.

---
 fs/btrfs/send.c | 33 +++++++++++++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)
fs/btrfs/send.c +31 -2
index 98948568017c..25b1a60a568c 100644
@@ -81,6 +81,7 @@ struct send_ctx {
 	char *send_buf;
 	u32 send_size;
 	u32 send_max_size;
+	struct page **send_buf_pages;
 	u64 total_send_size;
 	u64 cmd_send_size[BTRFS_SEND_C_MAX + 1];
 	u64 flags;	/* 'flags' member of btrfs_ioctl_send_args is u64 */
@@ -7203,6 +7204,7 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 	struct btrfs_root *clone_root;
 	struct send_ctx *sctx = NULL;
 	u32 i;
+	u32 send_buf_num_pages = 0;
 	u64 *clone_sources_tmp = NULL;
 	int clone_sources_to_rollback = 0;
 	size_t alloc_size;
@@ -7283,10 +7285,28 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 	if (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2) {
 		sctx->send_max_size = ALIGN(SZ_16K + BTRFS_MAX_COMPRESSED,
 					    PAGE_SIZE);
+		send_buf_num_pages = sctx->send_max_size >> PAGE_SHIFT;
+		sctx->send_buf_pages = kcalloc(send_buf_num_pages,
+					       sizeof(*sctx->send_buf_pages),
+					       GFP_KERNEL);
+		if (!sctx->send_buf_pages) {
+			send_buf_num_pages = 0;
+			ret = -ENOMEM;
+			goto out;
+		}
+		for (i = 0; i < send_buf_num_pages; i++) {
+			sctx->send_buf_pages[i] = alloc_page(GFP_KERNEL);
+			if (!sctx->send_buf_pages[i]) {
+				ret = -ENOMEM;
+				goto out;
+			}
+		}
+		sctx->send_buf = vmap(sctx->send_buf_pages, send_buf_num_pages,
+				      VM_MAP, PAGE_KERNEL);
 	} else {
 		sctx->send_max_size = BTRFS_SEND_BUF_SIZE_V1;
+		sctx->send_buf = kvmalloc(sctx->send_max_size, GFP_KERNEL);
 	}
-	sctx->send_buf = kvmalloc(sctx->send_max_size, GFP_KERNEL);
 	if (!sctx->send_buf) {
 		ret = -ENOMEM;
 		goto out;
@@ -7495,7 +7515,16 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 			fput(sctx->send_filp);
 
 		kvfree(sctx->clone_roots);
-		kvfree(sctx->send_buf);
+		if (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2) {
+			vunmap(sctx->send_buf);
+			for (i = 0; i < send_buf_num_pages; i++) {
+				if (sctx->send_buf_pages[i])
+					__free_page(sctx->send_buf_pages[i]);
+			}
+			kfree(sctx->send_buf_pages);
+		} else {
+			kvfree(sctx->send_buf);
+		}
 
 		name_cache_free(sctx);
 
Signature · 1 line
2.30.0
#7 lore raw

PATCH v3 4/11 btrfs-progs: receive: add send stream v2 cmds and attrs to send.h

In reply to Omar Sandoval

From: Boris Burkov <[email protected]>

Send stream v2 adds three commands and several attributes associated to those commands. Before we implement processing them, add all the commands and attributes. This avoids leaving the enums in an intermediate state that doesn't correspond to any version of send stream.

---
 send.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)
send.h +15 -0
index 228928a0..3c47e0c7 100644
@@ -98,6 +98,11 @@ enum btrfs_send_cmd {
 
 	BTRFS_SEND_C_END,
 	BTRFS_SEND_C_UPDATE_EXTENT,
+
+	BTRFS_SEND_C_FALLOCATE,
+	BTRFS_SEND_C_SETFLAGS,
+	BTRFS_SEND_C_ENCODED_WRITE,
+
 	__BTRFS_SEND_C_MAX,
 };
 #define BTRFS_SEND_C_MAX (__BTRFS_SEND_C_MAX - 1)
@@ -136,6 +141,16 @@ enum {
 	BTRFS_SEND_A_CLONE_OFFSET,
 	BTRFS_SEND_A_CLONE_LEN,
 
+	BTRFS_SEND_A_FALLOCATE_MODE,
+
+	BTRFS_SEND_A_SETFLAGS_FLAGS,
+
+	BTRFS_SEND_A_UNENCODED_FILE_LEN,
+	BTRFS_SEND_A_UNENCODED_LEN,
+	BTRFS_SEND_A_UNENCODED_OFFSET,
+	BTRFS_SEND_A_COMPRESSION,
+	BTRFS_SEND_A_ENCRYPTION,
+
 	__BTRFS_SEND_A_MAX,
 };
 #define BTRFS_SEND_A_MAX (__BTRFS_SEND_A_MAX - 1)
Signature · 1 line
2.30.0
#15 lore raw

PATCH v3 11/11 btrfs-progs: receive: add tests for basic encoded_write send/receive

In reply to Omar Sandoval

From: Boris Burkov <[email protected]>

Adapt the existing send/receive tests by passing '-o --force-compress' to the mount commands in a new test. After writing a few files in the various compression formats, send/receive them with and without --force-decompress to test both the encoded_write path and the fallback to decode+write.

---
 .../043-receive-write-encoded/test.sh         | 114 ++++++++++++++++++
 1 file changed, 114 insertions(+)
 create mode 100755 tests/misc-tests/043-receive-write-encoded/test.sh
tests/misc-tests/043-receive-write-encoded/test.sh new file +114 -0
new file mode 100755
index 00000000..b9390e88
@@ -0,0 +1,114 @@
+#!/bin/bash
+#
+# test that we can send and receive encoded writes for three modes of
+# transparent compression: zlib, lzo, and zstd.
+
+source "$TEST_TOP/common"
+
+check_prereq mkfs.btrfs
+check_prereq btrfs
+
+setup_root_helper
+prepare_test_dev
+
+here=`pwd`
+
+# assumes the filesystem exists, and does mount, write, snapshot, send, unmount
+# for the specified encoding option
+send_one() {
+	local str
+	local subv
+	local snap
+
+	algorithm="$1"
+	shift
+	str="$1"
+	shift
+
+	subv="subv-$algorithm"
+	snap="snap-$algorithm"
+
+	run_check_mount_test_dev "-o" "compress-force=$algorithm"
+	cd "$TEST_MNT" || _fail "cannot chdir to TEST_MNT"
+
+	run_check $SUDO_HELPER "$TOP/btrfs" subvolume create "$subv"
+	run_check $SUDO_HELPER dd if=/dev/zero of="$subv/file1" bs=1M count=1
+	run_check $SUDO_HELPER dd if=/dev/zero of="$subv/file2" bs=500K count=1
+	run_check $SUDO_HELPER "$TOP/btrfs" subvolume snapshot -r "$subv" "$snap"
+	run_check $SUDO_HELPER "$TOP/btrfs" send -f "$str" "$snap" "$@"
+
+	cd "$here" || _fail "cannot chdir back to test directory"
+	run_check_umount_test_dev
+}
+
+receive_one() {
+	local str
+	str="$1"
+	shift
+
+	run_check_mkfs_test_dev
+	run_check_mount_test_dev
+	run_check $SUDO_HELPER "$TOP/btrfs" receive "$@" -v -f "$str" "$TEST_MNT"
+	run_check_umount_test_dev
+	run_check rm -f -- "$str"
+}
+
+test_one_write_encoded() {
+	local str
+	local algorithm
+	algorithm="$1"
+	shift
+	str="$here/stream-$algorithm.stream"
+
+	run_check_mkfs_test_dev
+	send_one "$algorithm" "$str" --compressed-data
+	receive_one "$str" "$@"
+}
+
+test_one_stream_v1() {
+	local str
+	local algorithm
+	algorithm="$1"
+	shift
+	str="$here/stream-$algorithm.stream"
+
+	run_check_mkfs_test_dev
+	send_one "$algorithm" "$str" --stream-version 1
+	receive_one "$str" "$@"
+}
+
+test_mix_write_encoded() {
+	local strzlib
+	local strlzo
+	local strzstd
+	strzlib="$here/stream-zlib.stream"
+	strlzo="$here/stream-lzo.stream"
+	strzstd="$here/stream-zstd.stream"
+
+	run_check_mkfs_test_dev
+
+	send_one "zlib" "$strzlib" --compressed-data
+	send_one "lzo" "$strlzo" --compressed-data
+	send_one "zstd" "$strzstd" --compressed-data
+
+	receive_one "$strzlib"
+	receive_one "$strlzo"
+	receive_one "$strzstd"
+}
+
+test_one_write_encoded "zlib"
+test_one_write_encoded "lzo"
+test_one_write_encoded "zstd"
+
+# with decompression forced
+test_one_write_encoded "zlib" "--force-decompress"
+test_one_write_encoded "lzo" "--force-decompress"
+test_one_write_encoded "zstd" "--force-decompress"
+
+# send stream v1
+test_one_stream_v1 "zlib"
+test_one_stream_v1 "lzo"
+test_one_stream_v1 "zstd"
+
+# files use a mix of compression algorithms
+test_mix_write_encoded
Signature · 1 line
2.30.0
#13 lore raw

PATCH v3 10/11 btrfs-progs: send: stream v2 ioctl flags

In reply to Omar Sandoval

From: Boris Burkov <[email protected]>

To make the btrfs send ioctl use the stream v2 format requires passing BTRFS_SEND_FLAG_STREAM_V2 in flags. Further, to cause the ioctl to emit encoded_write commands for encoded extents, we must set that flag as well as BTRFS_SEND_FLAG_COMPRESSED. Finally, we bump up the version in send.h as well, since we are now fully compatible with v2.

Add two command line arguments to btrfs send: --stream-version and --compressed-data. --stream-version requires an argument which it parses as an integer and sets STREAM_V2 if the argument is 2. --compressed-data does not require an argument and automatically implies STREAM_V2 as well (COMPRESSED alone causes the ioctl to error out).

Some examples to illustrate edge cases:

// v1, old format and no encoded_writes
btrfs send subvol
btrfs send --stream-version 1 subvol

// v2 and compressed, we will see encoded_writes btrfs send --compressed-data subvol
btrfs send --compressed-data --stream-version 2 subvol

// v2 only, new format but no encoded_writes
btrfs send --stream-version 2 subvol

// error: compressed needs version >= 2
btrfs send --compressed-data --stream-version 1 subvol

// error: invalid version (not 1 or 2)
btrfs send --stream-version 3 subvol
btrfs send --compressed-data --stream-version 0 subvol btrfs send --compressed-data --stream-version 10 subvol

---
 Documentation/btrfs-send.asciidoc | 16 ++++++++-
 cmds/send.c                       | 54 ++++++++++++++++++++++++++++++-
 ioctl.h                           | 17 +++++++++-
 libbtrfsutil/btrfs.h              | 17 +++++++++-
 send.h                            |  2 +-
 5 files changed, 101 insertions(+), 5 deletions(-)
Documentation/btrfs-send.asciidoc +15 -1
index c4a05672..202bcd97 100644
@@ -55,7 +55,21 @@ send in 'NO_FILE_DATA' mode
 The output stream does not contain any file
 data and thus cannot be used to transfer changes. This mode is faster and
 is useful to show the differences in metadata.
--q|--quiet::::
+
+--stream-version <1|2>::
+Use the given send stream version. The default is 1. Version 2 encodes file
+data slightly more efficiently; it is also required for sending compressed data
+directly (see '--compressed-data'). Version 2 requires at least btrfs-progs
+5.12 on both the sender and receiver and at least Linux 5.12 on the sender.
+
+--compressed-data::
+Send data that is compressed on the filesystem directly without decompressing
+it. If the receiver supports encoded I/O (see `encoded_io`(7)), it can also
+write it directly without decompressing it. Otherwise, the receiver will fall
+back to decompressing it and writing it normally. This implies
+'--stream-version 2'.
+
+-q|--quiet::
 (deprecated) alias for global '-q' option
 -v|--verbose::
 (deprecated) alias for global '-v' option
cmds/send.c +53 -1

92 lines not on this page · raw message

ioctl.h +16 -1
index ade6dcb9..46de8ac8 100644
@@ -653,10 +653,25 @@ BUILD_ASSERT(sizeof(struct btrfs_ioctl_received_subvol_args_32) == 192);
  */
 #define BTRFS_SEND_FLAG_OMIT_END_CMD		0x4
 
+/*
+ * Use version 2 of the send stream, which adds new commands and supports larger
+ * writes.
+ */
+#define BTRFS_SEND_FLAG_STREAM_V2		0x8
+
+/*
+ * Send compressed data using the ENCODED_WRITE command instead of decompressing
+ * the data and sending it with the WRITE command. This requires
+ * BTRFS_SEND_FLAG_STREAM_V2.
+ */
+#define BTRFS_SEND_FLAG_COMPRESSED		0x10
+
 #define BTRFS_SEND_FLAG_MASK \
 	(BTRFS_SEND_FLAG_NO_FILE_DATA | \
 	 BTRFS_SEND_FLAG_OMIT_STREAM_HEADER | \
-	 BTRFS_SEND_FLAG_OMIT_END_CMD)
+	 BTRFS_SEND_FLAG_OMIT_END_CMD | \
+	 BTRFS_SEND_FLAG_STREAM_V2 | \
+	 BTRFS_SEND_FLAG_COMPRESSED)
 
 struct btrfs_ioctl_send_args {
 	__s64 send_fd;			/* in */
libbtrfsutil/btrfs.h +16 -1
index 60d51ff6..8430a40d 100644
@@ -731,10 +731,25 @@ struct btrfs_ioctl_received_subvol_args {
  */
 #define BTRFS_SEND_FLAG_OMIT_END_CMD		0x4
 
+/*
+ * Use version 2 of the send stream, which adds new commands and supports larger
+ * writes.
+ */
+#define BTRFS_SEND_FLAG_STREAM_V2		0x8
+
+/*
+ * Send compressed data using the ENCODED_WRITE command instead of decompressing
+ * the data and sending it with the WRITE command. This requires
+ * BTRFS_SEND_FLAG_STREAM_V2.
+ */
+#define BTRFS_SEND_FLAG_COMPRESSED		0x10
+
 #define BTRFS_SEND_FLAG_MASK \
 	(BTRFS_SEND_FLAG_NO_FILE_DATA | \
 	 BTRFS_SEND_FLAG_OMIT_STREAM_HEADER | \
-	 BTRFS_SEND_FLAG_OMIT_END_CMD)
+	 BTRFS_SEND_FLAG_OMIT_END_CMD | \
+	 BTRFS_SEND_FLAG_STREAM_V2 | \
+	 BTRFS_SEND_FLAG_COMPRESSED)
 
 struct btrfs_ioctl_send_args {
 	__s64 send_fd;			/* in */
send.h +1 -1
index 3c47e0c7..fac90588 100644
@@ -31,7 +31,7 @@ extern "C" {
 #endif
 
 #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream"
-#define BTRFS_SEND_STREAM_VERSION 1
+#define BTRFS_SEND_STREAM_VERSION 2
 
 #define BTRFS_SEND_BUF_SIZE_V1 SZ_64K
 #define BTRFS_SEND_READ_SIZE (1024 * 48)
Signature · 1 line
2.30.0
#12 lore raw

PATCH v3 9/11 btrfs-progs: receive: process setflags ioctl commands

In reply to Omar Sandoval

From: Boris Burkov <[email protected]>

In send stream v2, send can emit a command for setting inode flags via the setflags ioctl. Pass the flags attribute through to the ioctl call in receive.

---
 cmds/receive-dump.c  |  6 ++++++
 cmds/receive.c       | 24 ++++++++++++++++++++++++
 common/send-stream.c |  7 +++++++
 common/send-stream.h |  1 +
 4 files changed, 38 insertions(+)
cmds/receive-dump.c +6 -0
index acc0ba32..40f07ad4 100644
@@ -337,6 +337,11 @@ static int print_fallocate(const char *path, int mode, u64 offset, u64 len,
 			  mode, offset, len);
 }
 
+static int print_setflags(const char *path, int flags, void *user)
+{
+	return PRINT_DUMP(user, path, "setflags", "flags=%d", flags);
+}
+
 struct btrfs_send_ops btrfs_print_send_ops = {
 	.subvol = print_subvol,
 	.snapshot = print_snapshot,
@@ -361,4 +366,5 @@ struct btrfs_send_ops btrfs_print_send_ops = {
 	.update_extent = print_update_extent,
 	.encoded_write = print_encoded_write,
 	.fallocate = print_fallocate,
+	.setflags = print_setflags,
 };
cmds/receive.c +24 -0
index 897da372..61d3cecb 100644
@@ -1377,6 +1377,29 @@ static int process_fallocate(const char *path, int mode, u64 offset, u64 len,
 	return 0;
 }
 
+static int process_setflags(const char *path, int flags, void *user)
+{
+	int ret;
+	struct btrfs_receive *rctx = user;
+	char full_path[PATH_MAX];
+
+	ret = path_cat_out(full_path, rctx->full_subvol_path, path);
+	if (ret < 0) {
+		error("setflags: path invalid: %s", path);
+		return ret;
+	}
+	ret = open_inode_for_write(rctx, full_path, false);
+	if (ret < 0)
+		return ret;
+	ret = ioctl(rctx->write_fd, FS_IOC_SETFLAGS, &flags);
+	if (ret < 0) {
+		ret = -errno;
+		error("setflags: setflags ioctl on %s failed: %m", path);
+		return ret;
+	}
+	return 0;
+}
+
 static struct btrfs_send_ops send_ops = {
 	.subvol = process_subvol,
 	.snapshot = process_snapshot,
@@ -1401,6 +1424,7 @@ static struct btrfs_send_ops send_ops = {
 	.update_extent = process_update_extent,
 	.encoded_write = process_encoded_write,
 	.fallocate = process_fallocate,
+	.setflags = process_setflags,
 };
 
 static int do_receive(struct btrfs_receive *rctx, const char *tomnt,
common/send-stream.c +7 -0
index bc41396e..b9d35a34 100644
@@ -370,6 +370,7 @@ static int read_and_process_cmd(struct btrfs_send_stream *sctx)
 	int len;
 	int xattr_len;
 	int fallocate_mode;
+	int setflags_flags;
 
 	ret = read_cmd(sctx);
 	if (ret)
@@ -523,8 +524,14 @@ static int read_and_process_cmd(struct btrfs_send_stream *sctx)
 		ret = sctx->ops->fallocate(path, fallocate_mode, offset, tmp,
 					   sctx->user);
 		break;
+	case BTRFS_SEND_C_SETFLAGS:
+		TLV_GET_STRING(sctx, BTRFS_SEND_A_PATH, &path);
+		TLV_GET_U32(sctx, BTRFS_SEND_A_SETFLAGS_FLAGS, &setflags_flags);
+		ret = sctx->ops->setflags(path, setflags_flags, sctx->user);
+		break;
 	}
 
+
 tlv_get_failed:
 out:
 	free(path);
common/send-stream.h +1 -0
index a58739bb..5373bf69 100644
@@ -72,6 +72,7 @@ struct btrfs_send_ops {
 			     u32 encryption, void *user);
 	int (*fallocate)(const char *path, int mode, u64 offset, u64 len,
 			 void *user);
+	int (*setflags)(const char *path, int flags, void *user);
 };
 
 int btrfs_read_and_process_send_stream(int fd,
Signature · 1 line
2.30.0
#11 lore raw

PATCH v3 8/11 btrfs-progs: receive: process fallocate commands

In reply to Omar Sandoval

From: Boris Burkov <[email protected]>

Send stream v2 can emit fallocate commands, so receive must support them as well. The implementation simply passes along the arguments to the syscall. Note that mode is encoded as a u32 in send stream but fallocate takes an int, so there is a unsigned->signed conversion there.

---
 cmds/receive-dump.c  |  9 +++++++++
 cmds/receive.c       | 25 +++++++++++++++++++++++++
 common/send-stream.c |  9 +++++++++
 common/send-stream.h |  2 ++
 4 files changed, 45 insertions(+)
cmds/receive-dump.c +9 -0
index 20ec2b70..acc0ba32 100644
@@ -329,6 +329,14 @@ static int print_encoded_write(const char *path, const void *data, u64 offset,
 			  unencoded_offset, compression, encryption);
 }
 
+static int print_fallocate(const char *path, int mode, u64 offset, u64 len,
+			   void *user)
+{
+	return PRINT_DUMP(user, path, "fallocate",
+			  "mode=%d offset=%llu len=%llu",
+			  mode, offset, len);
+}
+
 struct btrfs_send_ops btrfs_print_send_ops = {
 	.subvol = print_subvol,
 	.snapshot = print_snapshot,
@@ -352,4 +360,5 @@ struct btrfs_send_ops btrfs_print_send_ops = {
 	.utimes = print_utimes,
 	.update_extent = print_update_extent,
 	.encoded_write = print_encoded_write,
+	.fallocate = print_fallocate,
 };
cmds/receive.c +25 -0
index 27e5c003..897da372 100644
@@ -1353,6 +1353,30 @@ static int process_encoded_write(const char *path, const void *data, u64 offset,
 				    compression);
 }
 
+static int process_fallocate(const char *path, int mode, u64 offset, u64 len,
+			     void *user)
+{
+	int ret;
+	struct btrfs_receive *rctx = user;
+	char full_path[PATH_MAX];
+
+	ret = path_cat_out(full_path, rctx->full_subvol_path, path);
+	if (ret < 0) {
+		error("fallocate: path invalid: %s", path);
+		return ret;
+	}
+	ret = open_inode_for_write(rctx, full_path, false);
+	if (ret < 0)
+		return ret;
+	ret = fallocate(rctx->write_fd, mode, offset, len);
+	if (ret < 0) {
+		ret = -errno;
+		error("fallocate: fallocate on %s failed: %m", path);
+		return ret;
+	}
+	return 0;
+}
+
 static struct btrfs_send_ops send_ops = {
 	.subvol = process_subvol,
 	.snapshot = process_snapshot,
@@ -1376,6 +1400,7 @@ static struct btrfs_send_ops send_ops = {
 	.utimes = process_utimes,
 	.update_extent = process_update_extent,
 	.encoded_write = process_encoded_write,
+	.fallocate = process_fallocate,
 };
 
 static int do_receive(struct btrfs_receive *rctx, const char *tomnt,
common/send-stream.c +9 -0
index 044e101b..bc41396e 100644
@@ -369,6 +369,7 @@ static int read_and_process_cmd(struct btrfs_send_stream *sctx)
 	u64 unencoded_offset;
 	int len;
 	int xattr_len;
+	int fallocate_mode;
 
 	ret = read_cmd(sctx);
 	if (ret)
@@ -514,6 +515,14 @@ static int read_and_process_cmd(struct btrfs_send_stream *sctx)
 	case BTRFS_SEND_C_END:
 		ret = 1;
 		break;
+	case BTRFS_SEND_C_FALLOCATE:
+		TLV_GET_STRING(sctx, BTRFS_SEND_A_PATH, &path);
+		TLV_GET_U32(sctx, BTRFS_SEND_A_FALLOCATE_MODE, &fallocate_mode);
+		TLV_GET_U64(sctx, BTRFS_SEND_A_FILE_OFFSET, &offset);
+		TLV_GET_U64(sctx, BTRFS_SEND_A_SIZE, &tmp);
+		ret = sctx->ops->fallocate(path, fallocate_mode, offset, tmp,
+					   sctx->user);
+		break;
 	}
 
 tlv_get_failed:
common/send-stream.h +2 -0
index 607bc007..a58739bb 100644
@@ -70,6 +70,8 @@ struct btrfs_send_ops {
 			     u64 len, u64 unencoded_file_len, u64 unencoded_len,
 			     u64 unencoded_offset, u32 compression,
 			     u32 encryption, void *user);
+	int (*fallocate)(const char *path, int mode, u64 offset, u64 len,
+			 void *user);
 };
 
 int btrfs_read_and_process_send_stream(int fd,
Signature · 1 line
2.30.0
#10 lore raw

PATCH v3 7/11 btrfs-progs: receive: encoded_write fallback to explicit decode and write

In reply to Omar Sandoval

From: Boris Burkov <[email protected]>

An encoded_write can fail if the file system it is being applied to does not support encoded writes or if it can't find enough contiguous space to accommodate the encoded extent. In those cases, we can likely still process an encoded_write by explicitly decoding the data and doing a normal write.

Add the necessary fallback path for decoding data compressed with zlib, lzo, or zstd. zlib and zstd have reusable decoding context data structures which we cache in the receive context so that we don't have to recreate them on every encoded_write.

Finally, add a command line flag for force-decompress which causes receive to always use the fallback path rather than first attempting the encoded write.

---
 Documentation/btrfs-receive.asciidoc |   4 +
 cmds/receive.c                       | 274 +++++++++++++++++++++++++--
 2 files changed, 265 insertions(+), 13 deletions(-)
Documentation/btrfs-receive.asciidoc +4 -0
index e4c4d2c0..354a71dc 100644
@@ -60,6 +60,10 @@ By default the mountpoint is searched in '/proc/self/mounts'.
 If '/proc' is not accessible, eg. in a chroot environment, use this option to
 tell us where this filesystem is mounted.
 
+--force-decompress::
+if the stream contains compressed data (see '--compressed-data' in
+`btrfs-send`(8)), always decompress it instead of writing it with encoded I/O.
+
 --dump::
 dump the stream metadata, one line per operation
 +
cmds/receive.c +261 -13

341 lines not on this page · raw message

Signature · 1 line
2.30.0
#9 lore raw

PATCH v3 6/11 btrfs-progs: receive: process encoded_write commands

In reply to Omar Sandoval

From: Boris Burkov <[email protected]>

Add a new btrfs_send_op and support for both dumping and proper receive processing which does actual encoded writes.

Encoded writes are only allowed on a file descriptor opened with an extra flag that allows encoded writes, so we also add support for this flag when opening or reusing a file for writing.

---
 cmds/receive-dump.c  |  16 ++++++-
 cmds/receive.c       | 104 ++++++++++++++++++++++++++++++++++++++++---
 common/send-stream.c |  22 +++++++++
 common/send-stream.h |   4 ++
 stubs.h              |  46 +++++++++++++++++++
 5 files changed, 186 insertions(+), 6 deletions(-)
cmds/receive-dump.c +15 -1
index 648d9314..20ec2b70 100644
@@ -316,6 +316,19 @@ static int print_update_extent(const char *path, u64 offset, u64 len,
 			  offset, len);
 }
 
+static int print_encoded_write(const char *path, const void *data, u64 offset,
+			       u64 len, u64 unencoded_file_len,
+			       u64 unencoded_len, u64 unencoded_offset,
+			       u32 compression, u32 encryption, void *user)
+{
+	return PRINT_DUMP(user, path, "encoded_write",
+			  "offset=%llu len=%llu, unencoded_file_len=%llu, "
+			  "unencoded_len=%llu, unencoded_offset=%llu, "
+			  "compression=%u, encryption=%u",
+			  offset, len, unencoded_file_len, unencoded_len,
+			  unencoded_offset, compression, encryption);
+}
+
 struct btrfs_send_ops btrfs_print_send_ops = {
 	.subvol = print_subvol,
 	.snapshot = print_snapshot,
@@ -337,5 +350,6 @@ struct btrfs_send_ops btrfs_print_send_ops = {
 	.chmod = print_chmod,
 	.chown = print_chown,
 	.utimes = print_utimes,
-	.update_extent = print_update_extent
+	.update_extent = print_update_extent,
+	.encoded_write = print_encoded_write,
 };
cmds/receive.c +99 -5

173 lines not on this page · raw message

common/send-stream.c +22 -0
index 4d819185..044e101b 100644
@@ -354,6 +354,8 @@ static int read_and_process_cmd(struct btrfs_send_stream *sctx)
 	struct timespec mt;
 	u8 uuid[BTRFS_UUID_SIZE];
 	u8 clone_uuid[BTRFS_UUID_SIZE];
+	u32 compression;
+	u32 encryption;
 	u64 tmp;
 	u64 tmp2;
 	u64 ctransid;
@@ -362,6 +364,9 @@ static int read_and_process_cmd(struct btrfs_send_stream *sctx)
 	u64 dev;
 	u64 clone_offset;
 	u64 offset;
+	u64 unencoded_file_len;
+	u64 unencoded_len;
+	u64 unencoded_offset;
 	int len;
 	int xattr_len;
 
@@ -436,6 +441,23 @@ static int read_and_process_cmd(struct btrfs_send_stream *sctx)
 		TLV_GET(sctx, BTRFS_SEND_A_DATA, &data, &len);
 		ret = sctx->ops->write(path, data, offset, len, sctx->user);
 		break;
+	case BTRFS_SEND_C_ENCODED_WRITE:
+		TLV_GET_STRING(sctx, BTRFS_SEND_A_PATH, &path);
+		TLV_GET_U64(sctx, BTRFS_SEND_A_FILE_OFFSET, &offset);
+		TLV_GET_U64(sctx, BTRFS_SEND_A_UNENCODED_FILE_LEN,
+			    &unencoded_file_len);
+		TLV_GET_U64(sctx, BTRFS_SEND_A_UNENCODED_LEN, &unencoded_len);
+		TLV_GET_U64(sctx, BTRFS_SEND_A_UNENCODED_OFFSET,
+			    &unencoded_offset);
+		TLV_GET_U32(sctx, BTRFS_SEND_A_COMPRESSION, &compression);
+		TLV_GET_U32(sctx, BTRFS_SEND_A_ENCRYPTION, &encryption);
+		TLV_GET(sctx, BTRFS_SEND_A_DATA, &data, &len);
+		ret = sctx->ops->encoded_write(path, data, offset, len,
+					       unencoded_file_len,
+					       unencoded_len, unencoded_offset,
+					       compression, encryption,
+					       sctx->user);
+		break;
 	case BTRFS_SEND_C_CLONE:
 		TLV_GET_STRING(sctx, BTRFS_SEND_A_PATH, &path);
 		TLV_GET_U64(sctx, BTRFS_SEND_A_FILE_OFFSET, &offset);
common/send-stream.h +4 -0
index 39901f86..607bc007 100644
@@ -66,6 +66,10 @@ struct btrfs_send_ops {
 		      struct timespec *mt, struct timespec *ct,
 		      void *user);
 	int (*update_extent)(const char *path, u64 offset, u64 len, void *user);
+	int (*encoded_write)(const char *path, const void *data, u64 offset,
+			     u64 len, u64 unencoded_file_len, u64 unencoded_len,
+			     u64 unencoded_offset, u32 compression,
+			     u32 encryption, void *user);
 };
 
 int btrfs_read_and_process_send_stream(int fd,
stubs.h +46 -0

56 lines not on this page · raw message

Signature · 1 line
2.30.0
#16 lore raw

PATCH v3 5/5 btrfs: send: enable support for stream v2 and compressed writes

In reply to Omar Sandoval

From: Omar Sandoval <[email protected]>

Now that the new support is implemented, allow the ioctl to accept the flags and update the version in sysfs.

---
 fs/btrfs/send.c            | 10 +++++++++-
 fs/btrfs/send.h            |  2 +-
 include/uapi/linux/btrfs.h |  4 +++-
 3 files changed, 13 insertions(+), 3 deletions(-)
fs/btrfs/send.c +9 -1
index 7516eba701af..cb824d1271fa 100644
@@ -671,7 +671,10 @@ static int send_header(struct send_ctx *sctx)
 	struct btrfs_stream_header hdr;
 
 	strcpy(hdr.magic, BTRFS_SEND_STREAM_MAGIC);
-	hdr.version = cpu_to_le32(BTRFS_SEND_STREAM_VERSION);
+	if (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2)
+		hdr.version = cpu_to_le32(2);
+	else
+		hdr.version = cpu_to_le32(1);
 
 	return write_buf(sctx->send_filp, &hdr, sizeof(hdr),
 					&sctx->send_off);
@@ -7446,6 +7449,11 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 		ret = -EINVAL;
 		goto out;
 	}
+	if ((arg->flags & BTRFS_SEND_FLAG_COMPRESSED) &&
+	    !(arg->flags & BTRFS_SEND_FLAG_STREAM_V2)) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	sctx = kzalloc(sizeof(struct send_ctx), GFP_KERNEL);
 	if (!sctx) {
fs/btrfs/send.h +1 -1
index 9f4f7b96b1eb..9c83e14a43b2 100644
@@ -10,7 +10,7 @@
 #include "ctree.h"
 
 #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream"
-#define BTRFS_SEND_STREAM_VERSION 1
+#define BTRFS_SEND_STREAM_VERSION 2
 
 /*
  * In send stream v1, no command is larger than 64k. In send stream v2, no limit
include/uapi/linux/btrfs.h +3 -1
index 93aa0932234e..b12a9a1a106c 100644
@@ -786,7 +786,9 @@ struct btrfs_ioctl_received_subvol_args {
 #define BTRFS_SEND_FLAG_MASK \
 	(BTRFS_SEND_FLAG_NO_FILE_DATA | \
 	 BTRFS_SEND_FLAG_OMIT_STREAM_HEADER | \
-	 BTRFS_SEND_FLAG_OMIT_END_CMD)
+	 BTRFS_SEND_FLAG_OMIT_END_CMD | \
+	 BTRFS_SEND_FLAG_STREAM_V2 | \
+	 BTRFS_SEND_FLAG_COMPRESSED)
 
 struct btrfs_ioctl_send_args {
 	__s64 send_fd;			/* in */
Signature · 1 line
2.30.0
#8 lore raw

PATCH v3 5/11 btrfs-progs: receive: add stub implementation for pwritev2

In reply to Omar Sandoval

From: Boris Burkov <[email protected]>

Encoded writes in receive will use pwritev2. It is possible that the system libc does not export this function, so we stub it out and detect whether to build the stub code with autoconf.

This syscall has special semantics in x32 (no hi lo, just takes loff_t) so we have to detect that case and use the appropriate arguments.

---
 Makefile     |  4 ++--
 configure.ac |  1 +
 stubs.c      | 24 ++++++++++++++++++++++++
 stubs.h      | 11 +++++++++++
 4 files changed, 38 insertions(+), 2 deletions(-)
 create mode 100644 stubs.c
 create mode 100644 stubs.h
Makefile +2 -2
index e288a336..7c0971f7 100644
@@ -173,12 +173,12 @@ libbtrfs_objects = common/send-stream.o common/send-utils.o kernel-lib/rbtree.o
 		   kernel-lib/raid56.o kernel-lib/tables.o \
 		   common/device-scan.o common/path-utils.o \
 		   common/utils.o libbtrfsutil/subvolume.o libbtrfsutil/stubs.o \
-		   crypto/hash.o crypto/xxhash.o $(CRYPTO_OBJECTS)
+		   crypto/hash.o crypto/xxhash.o $(CRYPTO_OBJECTS) stubs.o
 libbtrfs_headers = common/send-stream.h common/send-utils.h send.h kernel-lib/rbtree.h btrfs-list.h \
 	       crypto/crc32c.h kernel-lib/list.h kerncompat.h \
 	       kernel-lib/radix-tree.h kernel-lib/sizes.h kernel-lib/raid56.h \
 	       common/extent-cache.h kernel-shared/extent_io.h ioctl.h \
-	       kernel-shared/ctree.h btrfsck.h version.h
+	       kernel-shared/ctree.h btrfsck.h version.h stubs.h
 libbtrfsutil_major := $(shell sed -rn 's/^\#define BTRFS_UTIL_VERSION_MAJOR ([0-9])+$$/\1/p' libbtrfsutil/btrfsutil.h)
 libbtrfsutil_minor := $(shell sed -rn 's/^\#define BTRFS_UTIL_VERSION_MINOR ([0-9])+$$/\1/p' libbtrfsutil/btrfsutil.h)
 libbtrfsutil_patch := $(shell sed -rn 's/^\#define BTRFS_UTIL_VERSION_PATCH ([0-9])+$$/\1/p' libbtrfsutil/btrfsutil.h)
configure.ac +1 -0
index 39f93040..d43eb91f 100644
@@ -57,6 +57,7 @@ AC_CHECK_FUNCS([openat], [],
 	[AC_MSG_ERROR([cannot find openat() function])])
 
 AC_CHECK_FUNCS([reallocarray])
+AC_CHECK_FUNCS([pwritev2])
 
 m4_ifndef([PKG_PROG_PKG_CONFIG],
   [m4_fatal([Could not locate the pkg-config autoconf
stubs.c new file +24 -0
new file mode 100644
index 00000000..ab68a411
@@ -0,0 +1,24 @@
+#if HAVE_PWRITEV2 != 1
+
+#include "stubs.h"
+
+#include "kerncompat.h"
+
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/uio.h>
+
+ssize_t pwritev2(int fd, const struct iovec *iov, int iovcnt, off_t offset,
+		 int flags)
+{
+/* these conditions indicate an x32 system, which has a different pwritev2 */
+#if defined(__x86_64__) && defined(__ILP32__)
+	return syscall(SYS_pwritev2, fd, iov, iovcnt, offset, flags);
+#else
+	unsigned long hi = offset >> (BITS_PER_LONG / 2) >> (BITS_PER_LONG / 2);
+	unsigned long lo = offset;
+
+	return syscall(SYS_pwritev2, fd, iov, iovcnt, lo, hi, flags);
+#endif // X32
+}
+#endif /* HAVE_PWRIVEV2 */
stubs.h new file +11 -0
new file mode 100644
index 00000000..b39f8a69
@@ -0,0 +1,11 @@
+#ifndef _BTRFS_STUBS_H
+#define _BTRFS_STUBS_H
+
+#include <sys/types.h>
+
+struct iovec;
+
+ssize_t pwritev2(int fd, const struct iovec *iov, int iovcnt, off_t offset,
+		 int flags);
+
+#endif
Signature · 1 line
2.30.0
#14 lore raw

PATCH v3 4/5 btrfs: send: send compressed extents with encoded writes

In reply to Omar Sandoval

From: Omar Sandoval <[email protected]>

Now that all of the pieces are in place, we can use the ENCODED_WRITE command to send compressed extents when appropriate.

---
 fs/btrfs/ctree.h |   4 +
 fs/btrfs/inode.c |   6 +-
 fs/btrfs/send.c  | 230 +++++++++++++++++++++++++++++++++++++++++++----
 3 files changed, 220 insertions(+), 20 deletions(-)
fs/btrfs/ctree.h +4 -0
index 33a08ab5cb0e..402ffdce81ac 100644
@@ -3157,6 +3157,10 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page
 int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end);
 void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
 					  u64 end, int uptodate);
+int encoded_iov_compression_from_btrfs(unsigned int compress_type);
+int btrfs_encoded_read_regular_fill_pages(struct inode *inode, u64 offset,
+					  u64 disk_io_size,
+					  struct page **pages);
 ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter);
 ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 			       struct encoded_iov *encoded);
fs/btrfs/inode.c +3 -3
index c2fe76f57bf5..3c1c8879a9e1 100644
@@ -9984,7 +9984,7 @@ void btrfs_set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
 	}
 }
 
-static int encoded_iov_compression_from_btrfs(unsigned int compress_type)
+int encoded_iov_compression_from_btrfs(unsigned int compress_type)
 {
 	switch (compress_type) {
 	case BTRFS_COMPRESS_NONE:
@@ -10190,8 +10190,8 @@ static void btrfs_encoded_read_endio(struct bio *bio)
 	bio_put(bio);
 }
 
-static int btrfs_encoded_read_regular_fill_pages(struct inode *inode, u64 offset,
-						 u64 disk_io_size, struct page **pages)
+int btrfs_encoded_read_regular_fill_pages(struct inode *inode, u64 offset,
+					  u64 disk_io_size, struct page **pages)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_encoded_read_private priv = {
fs/btrfs/send.c +213 -17

292 lines not on this page · raw message

Signature · 1 line
2.30.0