[PATCH 03/19] fuse2fs: implement iomap configuration

["Darrick J. Wong" <djwong@kernel.org>]

From: Darrick J. Wong <djwong@kernel.org>

Upload the filesystem geometry to the kernel when asked.

Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
---
 misc/fuse2fs.c |   96 ++++++++++++++++++++++++++++++++++++++++++++++++++++++--
 misc/fuse4fs.c |   96 ++++++++++++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 186 insertions(+), 6 deletions(-)


diff --git a/misc/fuse2fs.c b/misc/fuse2fs.c
index c63acd7a0ed155..5b17aadc006560 100644
--- a/misc/fuse2fs.c
+++ b/misc/fuse2fs.c
@@ -201,6 +201,10 @@ static inline uint64_t round_down(uint64_t b, unsigned int align)
 # define FL_ZERO_RANGE_FLAG (0)
 #endif
 
+#ifndef NSEC_PER_SEC
+# define NSEC_PER_SEC	(1000000000L)
+#endif
+
 errcode_t ext2fs_run_ext3_journal(ext2_filsys *fs);
 
 const char *err_shortdev;
@@ -655,9 +659,9 @@ static int update_atime(ext2_filsys fs, ext2_ino_t ino)
 	EXT4_INODE_GET_XTIME(i_mtime, &mtime, pinode);
 	get_now(&now);
 
-	datime = atime.tv_sec + ((double)atime.tv_nsec / 1000000000);
-	dmtime = mtime.tv_sec + ((double)mtime.tv_nsec / 1000000000);
-	dnow = now.tv_sec + ((double)now.tv_nsec / 1000000000);
+	datime = atime.tv_sec + ((double)atime.tv_nsec / NSEC_PER_SEC);
+	dmtime = mtime.tv_sec + ((double)mtime.tv_nsec / NSEC_PER_SEC);
+	dnow = now.tv_sec + ((double)now.tv_nsec / NSEC_PER_SEC);
 
 	/*
 	 * If atime is newer than mtime and atime hasn't been updated in thirty
@@ -5440,6 +5444,91 @@ static int op_iomap_end(const char *path, uint64_t nodeid, uint64_t attr_ino,
 
 	return 0;
 }
+
+/*
+ * Maximal extent format file size.
+ * Resulting logical blkno at s_maxbytes must fit in our on-disk
+ * extent format containers, within a sector_t, and within i_blocks
+ * in the vfs.  ext4 inode has 48 bits of i_block in fsblock units,
+ * so that won't be a limiting factor.
+ *
+ * However there is other limiting factor. We do store extents in the form
+ * of starting block and length, hence the resulting length of the extent
+ * covering maximum file size must fit into on-disk format containers as
+ * well. Given that length is always by 1 unit bigger than max unit (because
+ * we count 0 as well) we have to lower the s_maxbytes by one fs block.
+ *
+ * Note, this does *not* consider any metadata overhead for vfs i_blocks.
+ */
+static off_t fuse2fs_max_size(struct fuse2fs *ff, off_t upper_limit)
+{
+	off_t res;
+
+	if (!ext2fs_has_feature_huge_file(ff->fs->super)) {
+		upper_limit = (1LL << 32) - 1;
+
+		/* total blocks in file system block size */
+		upper_limit >>= (ff->blocklog - 9);
+		upper_limit <<= ff->blocklog;
+	}
+
+	/*
+	 * 32-bit extent-start container, ee_block. We lower the maxbytes
+	 * by one fs block, so ee_len can cover the extent of maximum file
+	 * size
+	 */
+	res = (1LL << 32) - 1;
+	res <<= ff->blocklog;
+
+	/* Sanity check against vm- & vfs- imposed limits */
+	if (res > upper_limit)
+		res = upper_limit;
+
+	return res;
+}
+
+static int op_iomap_config(uint64_t flags, off_t maxbytes,
+			   struct fuse_iomap_config *cfg)
+{
+	struct fuse2fs *ff = fuse2fs_get();
+	ext2_filsys fs;
+
+	FUSE2FS_CHECK_CONTEXT(ff);
+
+	dbg_printf(ff, "%s: flags=0x%llx maxbytes=0x%llx\n", __func__,
+		   (unsigned long long)flags,
+		   (unsigned long long)maxbytes);
+	fs = fuse2fs_start(ff);
+
+	cfg->flags |= FUSE_IOMAP_CONFIG_UUID;
+	memcpy(cfg->s_uuid, fs->super->s_uuid, sizeof(cfg->s_uuid));
+	cfg->s_uuid_len = sizeof(fs->super->s_uuid);
+
+	cfg->flags |= FUSE_IOMAP_CONFIG_BLOCKSIZE;
+	cfg->s_blocksize = FUSE2FS_FSB_TO_B(ff, 1);
+
+	/*
+	 * If there inode is large enough to house i_[acm]time_extra then we
+	 * can turn on nanosecond timestamps; i_crtime was the next field added
+	 * after i_atime_extra.
+	 */
+	cfg->flags |= FUSE_IOMAP_CONFIG_TIME;
+	if (fs->super->s_inode_size >=
+	    offsetof(struct ext2_inode_large, i_crtime)) {
+		cfg->s_time_gran = 1;
+		cfg->s_time_max = EXT4_EXTRA_TIMESTAMP_MAX;
+	} else {
+		cfg->s_time_gran = NSEC_PER_SEC;
+		cfg->s_time_max = EXT4_NON_EXTRA_TIMESTAMP_MAX;
+	}
+	cfg->s_time_min = EXT4_TIMESTAMP_MIN;
+
+	cfg->flags |= FUSE_IOMAP_CONFIG_MAXBYTES;
+	cfg->s_maxbytes = fuse2fs_max_size(ff, maxbytes);
+
+	fuse2fs_finish(ff, 0);
+	return 0;
+}
 #endif /* HAVE_FUSE_IOMAP */
 
 static struct fuse_operations fs_ops = {
@@ -5505,6 +5594,7 @@ static struct fuse_operations fs_ops = {
 #ifdef HAVE_FUSE_IOMAP
 	.iomap_begin = op_iomap_begin,
 	.iomap_end = op_iomap_end,
+	.iomap_config = op_iomap_config,
 #endif /* HAVE_FUSE_IOMAP */
 };
 
diff --git a/misc/fuse4fs.c b/misc/fuse4fs.c
index 2bc25ff37055d5..5876af19387c96 100644
--- a/misc/fuse4fs.c
+++ b/misc/fuse4fs.c
@@ -196,6 +196,10 @@ static inline uint64_t round_down(uint64_t b, unsigned int align)
 # define FL_ZERO_RANGE_FLAG (0)
 #endif
 
+#ifndef NSEC_PER_SEC
+# define NSEC_PER_SEC	(1000000000L)
+#endif
+
 errcode_t ext2fs_run_ext3_journal(ext2_filsys *fs);
 
 const char *err_shortdev;
@@ -808,9 +812,9 @@ static int update_atime(ext2_filsys fs, ext2_ino_t ino)
 	EXT4_INODE_GET_XTIME(i_mtime, &mtime, pinode);
 	get_now(&now);
 
-	datime = atime.tv_sec + ((double)atime.tv_nsec / 1000000000);
-	dmtime = mtime.tv_sec + ((double)mtime.tv_nsec / 1000000000);
-	dnow = now.tv_sec + ((double)now.tv_nsec / 1000000000);
+	datime = atime.tv_sec + ((double)atime.tv_nsec / NSEC_PER_SEC);
+	dmtime = mtime.tv_sec + ((double)mtime.tv_nsec / NSEC_PER_SEC);
+	dnow = now.tv_sec + ((double)now.tv_nsec / NSEC_PER_SEC);
 
 	/*
 	 * If atime is newer than mtime and atime hasn't been updated in thirty
@@ -5850,6 +5854,91 @@ static void op_iomap_end(fuse_req_t req, fuse_ino_t fino, uint64_t dontcare,
 
 	fuse_reply_err(req, 0);
 }
+
+/*
+ * Maximal extent format file size.
+ * Resulting logical blkno at s_maxbytes must fit in our on-disk
+ * extent format containers, within a sector_t, and within i_blocks
+ * in the vfs.  ext4 inode has 48 bits of i_block in fsblock units,
+ * so that won't be a limiting factor.
+ *
+ * However there is other limiting factor. We do store extents in the form
+ * of starting block and length, hence the resulting length of the extent
+ * covering maximum file size must fit into on-disk format containers as
+ * well. Given that length is always by 1 unit bigger than max unit (because
+ * we count 0 as well) we have to lower the s_maxbytes by one fs block.
+ *
+ * Note, this does *not* consider any metadata overhead for vfs i_blocks.
+ */
+static off_t fuse4fs_max_size(struct fuse4fs *ff, off_t upper_limit)
+{
+	off_t res;
+
+	if (!ext2fs_has_feature_huge_file(ff->fs->super)) {
+		upper_limit = (1LL << 32) - 1;
+
+		/* total blocks in file system block size */
+		upper_limit >>= (ff->blocklog - 9);
+		upper_limit <<= ff->blocklog;
+	}
+
+	/*
+	 * 32-bit extent-start container, ee_block. We lower the maxbytes
+	 * by one fs block, so ee_len can cover the extent of maximum file
+	 * size
+	 */
+	res = (1LL << 32) - 1;
+	res <<= ff->blocklog;
+
+	/* Sanity check against vm- & vfs- imposed limits */
+	if (res > upper_limit)
+		res = upper_limit;
+
+	return res;
+}
+
+static void op_iomap_config(fuse_req_t req, uint64_t flags, uint64_t maxbytes)
+{
+	struct fuse_iomap_config cfg = { };
+	struct fuse4fs *ff = fuse4fs_get(req);
+	ext2_filsys fs;
+
+	FUSE4FS_CHECK_CONTEXT(req);
+
+	dbg_printf(ff, "%s: flags=0x%llx maxbytes=0x%llx\n", __func__,
+		   (unsigned long long)flags,
+		   (unsigned long long)maxbytes);
+	fs = fuse4fs_start(ff);
+
+	cfg.flags |= FUSE_IOMAP_CONFIG_UUID;
+	memcpy(cfg.s_uuid, fs->super->s_uuid, sizeof(cfg.s_uuid));
+	cfg.s_uuid_len = sizeof(fs->super->s_uuid);
+
+	cfg.flags |= FUSE_IOMAP_CONFIG_BLOCKSIZE;
+	cfg.s_blocksize = FUSE4FS_FSB_TO_B(ff, 1);
+
+	/*
+	 * If there inode is large enough to house i_[acm]time_extra then we
+	 * can turn on nanosecond timestamps; i_crtime was the next field added
+	 * after i_atime_extra.
+	 */
+	cfg.flags |= FUSE_IOMAP_CONFIG_TIME;
+	if (fs->super->s_inode_size >=
+	    offsetof(struct ext2_inode_large, i_crtime)) {
+		cfg.s_time_gran = 1;
+		cfg.s_time_max = EXT4_EXTRA_TIMESTAMP_MAX;
+	} else {
+		cfg.s_time_gran = NSEC_PER_SEC;
+		cfg.s_time_max = EXT4_NON_EXTRA_TIMESTAMP_MAX;
+	}
+	cfg.s_time_min = EXT4_TIMESTAMP_MIN;
+
+	cfg.flags |= FUSE_IOMAP_CONFIG_MAXBYTES;
+	cfg.s_maxbytes = fuse4fs_max_size(ff, maxbytes);
+
+	fuse4fs_finish(ff, 0);
+	fuse_reply_iomap_config(req, &cfg);
+}
 #endif /* HAVE_FUSE_IOMAP */
 
 static struct fuse_lowlevel_ops fs_ops = {
@@ -5898,6 +5987,7 @@ static struct fuse_lowlevel_ops fs_ops = {
 #ifdef HAVE_FUSE_IOMAP
 	.iomap_begin = op_iomap_begin,
 	.iomap_end = op_iomap_end,
+	.iomap_config = op_iomap_config,
 #endif /* HAVE_FUSE_IOMAP */
 };