Plumb a new call into the IO manager to support translating
ext2fs_zero_blocks calls into the equivalent kernel-level BLKZEROOUT
ioctl or FALLOC_FL_ZERO_RANGE fallocate flag primitives when possible.
Signed-off-by: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
---
lib/ext2fs/ext2_io.h | 7 ++-
lib/ext2fs/io_manager.c | 11 ++++
lib/ext2fs/mkjournal.c | 6 ++
lib/ext2fs/test_io.c | 21 ++++++++
lib/ext2fs/unix_io.c | 125 +++++++++++++++++++++++++++++++++++++++++++++++
5 files changed, 169 insertions(+), 1 deletion(-)
diff --git a/lib/ext2fs/ext2_io.h b/lib/ext2fs/ext2_io.h
index 4c5a5c5..1faa720 100644
--- a/lib/ext2fs/ext2_io.h
+++ b/lib/ext2fs/ext2_io.h
@@ -93,7 +93,9 @@ struct struct_io_manager {
errcode_t (*cache_readahead)(io_channel channel,
unsigned long long block,
unsigned long long count);
- long reserved[15];
+ errcode_t (*zeroout)(io_channel channel, unsigned long long block,
+ unsigned long long count);
+ long reserved[14];
};
#define IO_FLAG_RW 0x0001
@@ -125,6 +127,9 @@ extern errcode_t io_channel_write_blk64(io_channel channel,
extern errcode_t io_channel_discard(io_channel channel,
unsigned long long block,
unsigned long long count);
+extern errcode_t io_channel_zeroout(io_channel channel,
+ unsigned long long block,
+ unsigned long long count);
extern errcode_t io_channel_alloc_buf(io_channel channel,
int count, void *ptr);
extern errcode_t io_channel_cache_readahead(io_channel io,
diff --git a/lib/ext2fs/io_manager.c b/lib/ext2fs/io_manager.c
index dc5888d..c395d61 100644
--- a/lib/ext2fs/io_manager.c
+++ b/lib/ext2fs/io_manager.c
@@ -112,6 +112,17 @@ errcode_t io_channel_discard(io_channel channel, unsigned long long block,
return EXT2_ET_UNIMPLEMENTED;
}
+errcode_t io_channel_zeroout(io_channel channel, unsigned long long block,
+ unsigned long long count)
+{
+ EXT2_CHECK_MAGIC(channel, EXT2_ET_MAGIC_IO_CHANNEL);
+
+ if (channel->manager->zeroout)
+ return (channel->manager->zeroout)(channel, block, count);
+
+ return EXT2_ET_UNIMPLEMENTED;
+}
+
errcode_t io_channel_alloc_buf(io_channel io, int count, void *ptr)
{
size_t size;
diff --git a/lib/ext2fs/mkjournal.c b/lib/ext2fs/mkjournal.c
index 6f3a862..5be425c 100644
--- a/lib/ext2fs/mkjournal.c
+++ b/lib/ext2fs/mkjournal.c
@@ -164,6 +164,12 @@ errcode_t ext2fs_zero_blocks2(ext2_filsys fs, blk64_t blk, int num,
}
return 0;
}
+
+ /* Try a zero out command, if supported */
+ retval = io_channel_zeroout(fs->io, blk, num);
+ if (retval == 0)
+ return 0;
+
/* Allocate the zeroizing buffer if necessary */
if (!buf) {
buf = malloc(fs->blocksize * STRIDE_LENGTH);
diff --git a/lib/ext2fs/test_io.c b/lib/ext2fs/test_io.c
index b03a939..f7c50d1 100644
--- a/lib/ext2fs/test_io.c
+++ b/lib/ext2fs/test_io.c
@@ -86,6 +86,7 @@ void (*test_io_cb_write_byte)
#define TEST_FLAG_SET_OPTION 0x20
#define TEST_FLAG_DISCARD 0x40
#define TEST_FLAG_READAHEAD 0x80
+#define TEST_FLAG_ZEROOUT 0x100
static void test_dump_block(io_channel channel,
struct test_private_data *data,
@@ -507,6 +508,25 @@ static errcode_t test_cache_readahead(io_channel channel,
return retval;
}
+static errcode_t test_zeroout(io_channel channel, unsigned long long block,
+ unsigned long long count)
+{
+ struct test_private_data *data;
+ errcode_t retval = 0;
+
+ EXT2_CHECK_MAGIC(channel, EXT2_ET_MAGIC_IO_CHANNEL);
+ data = (struct test_private_data *) channel->private_data;
+ EXT2_CHECK_MAGIC(data, EXT2_ET_MAGIC_TEST_IO_CHANNEL);
+
+ if (data->real)
+ retval = io_channel_zeroout(data->real, block, count);
+ if (data->flags & TEST_FLAG_ZEROOUT)
+ fprintf(data->outfile,
+ "Test_io: zeroout(%llu, %llu) returned %s\n",
+ block, count, retval ? error_message(retval) : "OK");
+ return retval;
+}
+
static struct struct_io_manager struct_test_manager = {
.magic = EXT2_ET_MAGIC_IO_MANAGER,
.name = "Test I/O Manager",
@@ -523,6 +543,7 @@ static struct struct_io_manager struct_test_manager = {
.write_blk64 = test_write_blk64,
.discard = test_discard,
.cache_readahead = test_cache_readahead,
+ .zeroout = test_zeroout,
};
io_manager test_io_manager = &struct_test_manager;
diff --git a/lib/ext2fs/unix_io.c b/lib/ext2fs/unix_io.c
index c3a8ea5..6bc543b 100644
--- a/lib/ext2fs/unix_io.c
+++ b/lib/ext2fs/unix_io.c
@@ -987,6 +987,130 @@ unimplemented:
return EXT2_ET_UNIMPLEMENTED;
}
+#if defined(__linux__) && !defined(BLKZEROOUT)
+#define BLKZEROOUT _IO(0x12, 127)
+#endif
+
+#if defined(__linux__) && !defined(BLKFLSBUF)
+#define BLKFLSBUF _IO(0x12, 97)
+#endif
+
+#if defined(__linux__) && !defined(FALLOC_FL_ZERO_RANGE)
+#define FALLOC_FL_ZERO_RANGE 0x10
+#endif
+
+static errcode_t unix_zeroout(io_channel channel, unsigned long long block,
+ unsigned long long count)
+{
+ struct unix_private_data *data;
+ int ret;
+
+ EXT2_CHECK_MAGIC(channel, EXT2_ET_MAGIC_IO_CHANNEL);
+ data = (struct unix_private_data *) channel->private_data;
+ EXT2_CHECK_MAGIC(data, EXT2_ET_MAGIC_UNIX_IO_CHANNEL);
+
+ if (getenv("UNIX_IO_NOZEROOUT"))
+ goto unimplemented;
+
+ if (channel->flags & CHANNEL_FLAGS_BLOCK_DEVICE) {
+ __u64 range[2];
+
+ if (count == 0)
+ return 0;
+ /*
+ * This is a heavyweight operation. Refuse to
+ * zero-out a single block, and hope that the
+ * caller will fall back to io_channel_write().
+ */
+ else if (count == 1)
+ goto unimplemented;
+
+ range[0] = (__u64)(block) * channel->block_size;
+ range[1] = (__u64)(count) * channel->block_size;
+
+ errno = EOPNOTSUPP;
+ ret = -1;
+#if defined(BLKZEROOUT) && (defined(POSIX_FADV_DONTNEED) || defined(BLKFLSBUF))
+ /*
+ * BLKZEROOUT doesn't invalidate the page cache. Therefore,
+ * we need to flush dirty pages to disk prior to calling the
+ * ioctl and invalidate at least those same pages from the page
+ * cache afterwards. If we're using direct IO we can skip all
+ * that wrangling.
+ */
+ if (!(data->flags & IO_FLAG_DIRECT_IO)) {
+ ret = fsync(data->dev);
+ if (ret)
+ goto err;
+ }
+ ret = ioctl(data->dev, BLKZEROOUT, range);
+ if (ret)
+ goto err;
+ if (!(data->flags & IO_FLAG_DIRECT_IO)) {
+#ifdef POSIX_FADV_DONTNEED
+ ret = posix_fadvise(data->dev, range[0], range[1],
+ POSIX_FADV_DONTNEED);
+ if (ret == 0)
+ goto err;
+#endif
+#ifdef BLKFLSBUF
+ ret = ioctl(data->dev, BLKFLSBUF, 0);
+#endif
+ }
+#elif defined(BLKZEROOUT)
+ if (data->flags & IO_FLAG_DIRECT_IO)
+ ret = ioctl(data->dev, BLKZEROOUT, range);
+#endif
+ } else {
+ /* Regular file, try to use truncate/punch/zero. */
+#if defined(HAVE_FALLOCATE) && (defined(FALLOC_FL_ZERO_RANGE) || \
+ (defined(FALLOC_FL_PUNCH_HOLE) && defined(FALLOC_FL_KEEP_SIZE)))
+ struct stat statbuf;
+
+ if (count == 0)
+ return 0;
+ /*
+ * If we're trying to zero a range past the end of the file,
+ * extend the file size, then punch (or zero_range) everything.
+ */
+ ret = fstat(data->dev, &statbuf);
+ if (ret)
+ goto err;
+ if (statbuf.st_size < (block + count) * channel->block_size) {
+ ret = ftruncate(data->dev,
+ (block + count) * channel->block_size);
+ if (ret)
+ goto err;
+ }
+#if defined(FALLOC_FL_PUNCH_HOLE) && defined(FALLOC_FL_KEEP_SIZE)
+ ret = fallocate(data->dev,
+ FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+ (off_t)(block) * channel->block_size,
+ (off_t)(count) * channel->block_size);
+ if (ret == 0)
+ goto err;
+#endif
+#ifdef FALLOC_FL_ZERO_RANGE
+ ret = fallocate(data->dev,
+ FALLOC_FL_ZERO_RANGE,
+ (off_t)(block) * channel->block_size,
+ (off_t)(count) * channel->block_size);
+#endif
+#else
+ goto unimplemented;
+#endif /* HAVE_FALLOCATE && (ZERO_RANGE || (PUNCH_HOLE && KEEP_SIZE)) */
+ }
+err:
+ if (ret < 0) {
+ if (errno == EOPNOTSUPP)
+ goto unimplemented;
+ return errno;
+ }
+ return 0;
+unimplemented:
+ return EXT2_ET_UNIMPLEMENTED;
+}
+
static struct struct_io_manager struct_unix_manager = {
.magic = EXT2_ET_MAGIC_IO_MANAGER,
.name = "Unix I/O Manager",
@@ -1003,6 +1127,7 @@ static struct struct_io_manager struct_unix_manager = {
.write_blk64 = unix_write_blk64,
.discard = unix_discard,
.cache_readahead = unix_cache_readahead,
+ .zeroout = unix_zeroout,
};
io_manager unix_io_manager = &struct_unix_manager;
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
