linux-btrfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Omar Sandoval <osandov@osandov.com>
To: linux-btrfs@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org, kernel-team@fb.com
Subject: [PATCH v2 09/13] btrfs-progs: receive: encoded_write fallback to explicit decode and write
Date: Wed, 18 Nov 2020 11:18:56 -0800	[thread overview]
Message-ID: <003ced29dccaac8e5bf41aa4f571f0154d011ae0.1605723745.git.osandov@osandov.com> (raw)
In-Reply-To: <cover.1605723600.git.osandov@fb.com>

From: Boris Burkov <boris@bur.io>

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.

Signed-off-by: Boris Burkov <boris@bur.io>
---
 Documentation/btrfs-receive.asciidoc |   4 +
 cmds/receive.c                       | 274 +++++++++++++++++++++++++--
 2 files changed, 265 insertions(+), 13 deletions(-)

diff --git a/Documentation/btrfs-receive.asciidoc b/Documentation/btrfs-receive.asciidoc
index e4c4d2c0..354a71dc 100644
--- a/Documentation/btrfs-receive.asciidoc
+++ b/Documentation/btrfs-receive.asciidoc
@@ -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
 +
diff --git a/cmds/receive.c b/cmds/receive.c
index 87f47a9a..361c7c8a 100644
--- a/cmds/receive.c
+++ b/cmds/receive.c
@@ -41,6 +41,10 @@
 #include <sys/xattr.h>
 #include <uuid/uuid.h>
 
+#include <lzo/lzo1x.h>
+#include <zlib.h>
+#include <zstd.h>
+
 #include "kernel-shared/ctree.h"
 #include "ioctl.h"
 #include "cmds/commands.h"
@@ -82,6 +86,8 @@ struct btrfs_receive
 
 	int honor_end_cmd;
 
+	int force_decompress;
+
 	/*
 	 * Buffer to store capabilities from security.capabilities xattr,
 	 * usually 20 bytes, but make same room for potentially larger
@@ -89,6 +95,10 @@ struct btrfs_receive
 	 */
 	char cached_capabilities[64];
 	int cached_capabilities_len;
+
+	/* Reuse stream objects for encoded_write decompression fallback */
+	ZSTD_DStream *zstd_dstream;
+	z_stream *zlib_stream;
 };
 
 static int finish_subvol(struct btrfs_receive *rctx)
@@ -1077,9 +1087,222 @@ static int process_update_extent(const char *path, u64 offset, u64 len,
 	return 0;
 }
 
+static int decompress_zlib(struct btrfs_receive *rctx, const char *encoded_data,
+			   u64 encoded_len, char *unencoded_data,
+			   u64 unencoded_len)
+{
+	bool init = false;
+	int ret;
+
+	if (!rctx->zlib_stream) {
+		init = true;
+		rctx->zlib_stream = malloc(sizeof(z_stream));
+		if (!rctx->zlib_stream) {
+			error("failed to allocate zlib stream %m");
+			return -ENOMEM;
+		}
+	}
+	rctx->zlib_stream->next_in = (void *)encoded_data;
+	rctx->zlib_stream->avail_in = encoded_len;
+	rctx->zlib_stream->next_out = (void *)unencoded_data;
+	rctx->zlib_stream->avail_out = unencoded_len;
+
+	if (init) {
+		rctx->zlib_stream->zalloc = Z_NULL;
+		rctx->zlib_stream->zfree = Z_NULL;
+		rctx->zlib_stream->opaque = Z_NULL;
+		ret = inflateInit(rctx->zlib_stream);
+	} else {
+		ret = inflateReset(rctx->zlib_stream);
+	}
+	if (ret != Z_OK) {
+		error("zlib inflate init failed: %d", ret);
+		return -EIO;
+	}
+
+	while (rctx->zlib_stream->avail_in > 0 &&
+	       rctx->zlib_stream->avail_out > 0) {
+		ret = inflate(rctx->zlib_stream, Z_FINISH);
+		if (ret == Z_STREAM_END) {
+			break;
+		} else if (ret != Z_OK) {
+			error("zlib inflate failed: %d", ret);
+			return -EIO;
+		}
+	}
+	return 0;
+}
+
+static int decompress_zstd(struct btrfs_receive *rctx, const char *encoded_buf,
+			   u64 encoded_len, char *unencoded_buf,
+			   u64 unencoded_len)
+{
+	ZSTD_inBuffer in_buf = {
+		.src = encoded_buf,
+		.size = encoded_len
+	};
+	ZSTD_outBuffer out_buf = {
+		.dst = unencoded_buf,
+		.size = unencoded_len
+	};
+	size_t ret;
+
+	if (!rctx->zstd_dstream) {
+		rctx->zstd_dstream = ZSTD_createDStream();
+		if (!rctx->zstd_dstream) {
+			error("failed to create zstd dstream");
+			return -ENOMEM;
+		}
+	}
+	ret = ZSTD_initDStream(rctx->zstd_dstream);
+	if (ZSTD_isError(ret)) {
+		error("failed to init zstd stream: %s", ZSTD_getErrorName(ret));
+		return -EIO;
+	}
+	while (in_buf.pos < in_buf.size && out_buf.pos < out_buf.size) {
+		ret = ZSTD_decompressStream(rctx->zstd_dstream, &out_buf, &in_buf);
+		if (ret == 0) {
+			break;
+		} else if (ZSTD_isError(ret)) {
+			error("failed to decompress zstd stream: %s",
+			      ZSTD_getErrorName(ret));
+			return -EIO;
+		}
+	}
+	return 0;
+}
+
+static int decompress_lzo(const char *encoded_data, u64 encoded_len,
+			  char *unencoded_data, u64 unencoded_len,
+			  unsigned int page_size)
+{
+	uint32_t total_len;
+	size_t in_pos, out_pos;
+
+	if (encoded_len < 4) {
+		error("lzo header is truncated");
+		return -EIO;
+	}
+	memcpy(&total_len, encoded_data, 4);
+	total_len = le32toh(total_len);
+	if (total_len > encoded_len) {
+		error("lzo header is invalid");
+		return -EIO;
+	}
+
+	in_pos = 4;
+	out_pos = 0;
+	while (in_pos < total_len && out_pos < unencoded_len) {
+		size_t page_remaining;
+		uint32_t src_len;
+		lzo_uint dst_len;
+		int ret;
+
+		page_remaining = -in_pos % page_size;
+		if (page_remaining < 4) {
+			if (total_len - in_pos <= page_remaining)
+				break;
+			in_pos += page_remaining;
+		}
+
+		if (total_len - in_pos < 4) {
+			error("lzo segment header is truncated");
+			return -EIO;
+		}
+
+		memcpy(&src_len, encoded_data + in_pos, 4);
+		src_len = le32toh(src_len);
+		in_pos += 4;
+		if (src_len > total_len - in_pos) {
+			error("lzo segment header is invalid");
+			return -EIO;
+		}
+
+		dst_len = page_size;
+		ret = lzo1x_decompress_safe((void *)(encoded_data + in_pos),
+					    src_len,
+					    (void *)(unencoded_data + out_pos),
+					    &dst_len, NULL);
+		if (ret != LZO_E_OK) {
+			error("lzo1x_decompress_safe failed: %d", ret);
+			return -EIO;
+		}
+
+		in_pos += src_len;
+		out_pos += dst_len;
+	}
+	return 0;
+}
+
+static int decompress_and_write(struct btrfs_receive *rctx,
+				const char *encoded_data, u64 offset,
+				u64 encoded_len, u64 unencoded_file_len,
+				u64 unencoded_len, u64 unencoded_offset,
+				u32 compression)
+{
+	int ret = 0;
+	size_t pos;
+	ssize_t w;
+	char *unencoded_data;
+	int page_shift;
+
+	unencoded_data = calloc(unencoded_len, 1);
+	if (!unencoded_data) {
+		error("allocating space for unencoded data failed: %m");
+		return -errno;
+	}
+
+	switch (compression) {
+	case ENCODED_IOV_COMPRESSION_BTRFS_ZLIB:
+		ret = decompress_zlib(rctx, encoded_data, encoded_len,
+				      unencoded_data, unencoded_len);
+		if (ret)
+			goto out;
+		break;
+	case ENCODED_IOV_COMPRESSION_BTRFS_ZSTD:
+		ret = decompress_zstd(rctx, encoded_data, encoded_len,
+				      unencoded_data, unencoded_len);
+		if (ret)
+			goto out;
+		break;
+	case ENCODED_IOV_COMPRESSION_BTRFS_LZO_4K:
+	case ENCODED_IOV_COMPRESSION_BTRFS_LZO_8K:
+	case ENCODED_IOV_COMPRESSION_BTRFS_LZO_16K:
+	case ENCODED_IOV_COMPRESSION_BTRFS_LZO_32K:
+	case ENCODED_IOV_COMPRESSION_BTRFS_LZO_64K:
+		page_shift = compression - ENCODED_IOV_COMPRESSION_BTRFS_LZO_4K + 12;
+		ret = decompress_lzo(encoded_data, encoded_len, unencoded_data,
+				     unencoded_len, 1U << page_shift);
+		if (ret)
+			goto out;
+		break;
+	default:
+		error("unknown compression: %d", compression);
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
+	pos = unencoded_offset;
+	while (pos < unencoded_file_len) {
+		w = pwrite(rctx->write_fd, unencoded_data + pos,
+			   unencoded_file_len - pos, offset);
+		if (w < 0) {
+			ret = -errno;
+			error("writing unencoded data failed: %m");
+			goto out;
+		}
+		pos += w;
+		offset += w;
+	}
+out:
+	free(unencoded_data);
+	return ret;
+}
+
 static int process_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)
+				 u64 len, u64 unencoded_file_len,
+				 u64 unencoded_len, u64 unencoded_offset,
+				 u32 compression, u32 encryption, void *user)
 {
 	int ret;
 	ssize_t w;
@@ -1096,6 +1319,7 @@ static int process_encoded_write(const char *path, const void *data, u64 offset,
 		{ &encoded, sizeof(encoded) },
 		{ (char *)data, len }
 	};
+	bool encoded_write = !rctx->force_decompress;
 
 	if (encryption) {
 		error("encoded_write: encryption not supported");
@@ -1112,17 +1336,25 @@ static int process_encoded_write(const char *path, const void *data, u64 offset,
 	if (ret < 0)
 		return ret;
 
-	/*
-	 * NOTE: encoded writes guarantee no partial writes, so we don't need to
-	 * handle that possibility.
-	 */
-	w = pwritev2(rctx->write_fd, iov, 2, offset, RWF_ENCODED);
-	if (w < 0) {
-		ret = -errno;
-		error("encoded_write: writing to %s failed: %m", path);
-		return ret;
+	if (encoded_write) {
+		/*
+		 * NOTE: encoded writes guarantee no partial writes, so we don't
+		 * need to handle that possibility.
+		 */
+		w = pwritev2(rctx->write_fd, iov, 2, offset, RWF_ENCODED);
+		if (w >= 0)
+			return 0;
+		/* Fall back for these errors, fail hard for anything else. */
+		if (errno != ENOSPC && errno != EOPNOTSUPP && errno != EINVAL) {
+			ret = -errno;
+			error("encoded_write: writing to %s failed: %m", path);
+			return ret;
+		}
 	}
-	return 0;
+
+	return decompress_and_write(rctx, data, offset, len, unencoded_file_len,
+				    unencoded_len, unencoded_offset,
+				    compression);
 }
 
 static struct btrfs_send_ops send_ops = {
@@ -1310,6 +1542,12 @@ out:
 		close(rctx->dest_dir_fd);
 		rctx->dest_dir_fd = -1;
 	}
+	if (rctx->zstd_dstream)
+		ZSTD_freeDStream(rctx->zstd_dstream);
+	if (rctx->zlib_stream) {
+		inflateEnd(rctx->zlib_stream);
+		free(rctx->zlib_stream);
+	}
 
 	return ret;
 }
@@ -1340,6 +1578,9 @@ static const char * const cmd_receive_usage[] = {
 	"-m ROOTMOUNT     the root mount point of the destination filesystem.",
 	"                 If /proc is not accessible, use this to tell us where",
 	"                 this file system is mounted.",
+	"--force-decompress",
+	"                 if the stream contains compressed data, always",
+	"                 decompress it instead of writing it with encoded I/O",
 	"--dump           dump stream metadata, one line per operation,",
 	"                 does not require the MOUNT parameter",
 	"-v               deprecated, alias for global -v option",
@@ -1383,12 +1624,16 @@ static int cmd_receive(const struct cmd_struct *cmd, int argc, char **argv)
 	optind = 0;
 	while (1) {
 		int c;
-		enum { GETOPT_VAL_DUMP = 257 };
+		enum {
+			GETOPT_VAL_DUMP = 257,
+			GETOPT_VAL_FORCE_DECOMPRESS,
+		};
 		static const struct option long_opts[] = {
 			{ "max-errors", required_argument, NULL, 'E' },
 			{ "chroot", no_argument, NULL, 'C' },
 			{ "dump", no_argument, NULL, GETOPT_VAL_DUMP },
 			{ "quiet", no_argument, NULL, 'q' },
+			{ "force-decompress", no_argument, NULL, GETOPT_VAL_FORCE_DECOMPRESS },
 			{ NULL, 0, NULL, 0 }
 		};
 
@@ -1431,6 +1676,9 @@ static int cmd_receive(const struct cmd_struct *cmd, int argc, char **argv)
 		case GETOPT_VAL_DUMP:
 			dump = 1;
 			break;
+		case GETOPT_VAL_FORCE_DECOMPRESS:
+			rctx.force_decompress = 1;
+			break;
 		default:
 			usage_unknown_option(cmd, argv);
 		}
-- 
2.29.2


  parent reply	other threads:[~2020-11-18 19:19 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-18 19:18 [PATCH v2 0/5] btrfs: implement send/receive of compressed extents without decompressing Omar Sandoval
2020-11-18 19:18 ` [PATCH v2 1/5] btrfs: add send stream v2 definitions Omar Sandoval
2020-11-18 19:18 ` [PATCH v2 01/13] btrfs-progs: send: fix crash on unknown option Omar Sandoval
2020-12-16 16:20   ` David Sterba
2020-11-18 19:18 ` [PATCH v2 02/13] btrfs-progs: receive: support v2 send stream larger tlv_len Omar Sandoval
2020-11-18 19:18 ` [PATCH v2 2/5] btrfs: send: write larger chunks when using stream v2 Omar Sandoval
2020-11-18 19:18 ` [PATCH v2 03/13] btrfs-progs: receive: dynamically allocate sctx->read_buf Omar Sandoval
2020-11-18 19:18 ` [PATCH v2 3/5] btrfs: send: allocate send buffer with alloc_page() and vmap() for v2 Omar Sandoval
2020-11-18 19:18 ` [PATCH v2 04/13] btrfs-progs: receive: support v2 send stream DATA tlv format Omar Sandoval
2020-11-18 19:18 ` [PATCH v2 4/5] btrfs: send: send compressed extents with encoded writes Omar Sandoval
2020-11-18 19:18 ` [PATCH v2 05/13] btrfs-progs: receive: add send stream v2 cmds and attrs to send.h Omar Sandoval
2020-11-18 19:18 ` [PATCH v2 5/5] btrfs: send: enable support for stream v2 and compressed writes Omar Sandoval
2020-11-18 19:18 ` [PATCH v2 06/13] btrfs-progs: receive: add stub implementation for pwritev2 Omar Sandoval
2020-11-18 19:18 ` [PATCH v2 07/13] btrfs-progs: receive: open files with O_CLOEXEC Omar Sandoval
2020-11-18 19:18 ` [PATCH v2 08/13] btrfs-progs: receive: process encoded_write commands Omar Sandoval
2020-11-18 19:18 ` Omar Sandoval [this message]
2020-11-18 19:18 ` [PATCH v2 10/13] btrfs-progs: receive: process fallocate commands Omar Sandoval
2020-11-18 19:18 ` [PATCH v2 11/13] btrfs-progs: receive: process setflags ioctl commands Omar Sandoval
2020-11-18 19:18 ` [PATCH v2 12/13] btrfs-progs: send: stream v2 ioctl flags Omar Sandoval
2020-11-18 19:19 ` [PATCH v2 13/13] btrfs-progs: receive: add tests for basic encoded_write send/receive Omar Sandoval

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=003ced29dccaac8e5bf41aa4f571f0154d011ae0.1605723745.git.osandov@osandov.com \
    --to=osandov@osandov.com \
    --cc=kernel-team@fb.com \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).