Viewing: ext4-fiemap-kernel-data.patch
commit 5cd5a49c7213315d83bca54a2eee97ba57d256cc
Author: Shaun Tancheff <shaun.tancheff@hpe.com>
AuthorDate: Fri Dec 2 04:19:59 2022 -0600
LU-16321 osd: Allow fiemap on kernel allocated buffers
When KERNEL_DS gone lustre needs an alternative for fiemap to
copy extents to kernel space memory.
Direct in-kernel calls to inode->f_ops->fiemap() can utilize
an otherwise unused flag on fiemap_extent_info fi_flags
to indicate the fiemap extent buffer is allocated in kernel space.
Include ldiskfs patches for ldiskfs_fiemap() to
define EXT4_FIEMAP_FLAG_MEMCPY and utilize it.
The patch pulls some common code into ext4:
ext4_fiemap_fill_next_extent <--- fiemap_fill_next_extent
ext4_iomap_to_fiemap <----------- iomap_to_fiemap
ext4_iomap_fiemap_actor <-------- iomap_fiemap_actor
ext4_iomap_apply <--------------- iomap_apply
_ext4_iomap_fiemap <------------- iomap_fiemap
and changes ext4_fiemap_fill_next_extent to conditionally
use memcpy instead of copy_to_user.
Linux-commit: v5.17-rc3-19-g967747bbc084
uaccess: remove CONFIG_SET_FS
HPE-bug-id: LUS-11337
Fixes: d0337cab8e ("LU-14195 osd: don't use set_fs() for ->fiemap() calls.")
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Reviewed-by: Neil Brown <neilb@suse.de>
Reviewed-by: Alexander Boyko <alexander.boyko@hpe.com>
Reviewed-by: Petros Koutoupis <petros.koutoupis@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Change-Id: I7a8edb481833fd1bdcf7b6cd6e08397c1754baee
Reviewed-on: https://review.whamcloud.com/49190
---
fs/ext4/ext4.h | 3 +
fs/ext4/extents.c | 239 +++++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 238 insertions(+), 4 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index c4d59e5..0739f10 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -772,6 +772,9 @@ enum {
*/
#define EXT4_FIEMAP_EXTENT_HOLE 0x08000000
+/* Otherwise unused fi_flags ext4 use memcpy instead of copy_[to|from]_uiser */
+#define EXT4_FIEMAP_FLAG_MEMCPY 0x80000000
+
/* Max physical block we can address w/o extents */
#define EXT4_MAX_BLOCK_FILE_PHYS 0xFFFFFFFF
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index c148bb9..b97a328 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2175,6 +2175,238 @@ cleanup:
return err;
}
+#ifdef KERNEL_DS
+#define ext4_iomap_fiemap(i, f, s, l, ops) \
+ iomap_fiemap((i), (f), (s), (l), (ops))
+#else
+/*
+ * linux:
+ * ext4_fiemap_fill_next_extent <--- fiemap_fill_next_extent
+ * _ext4_iomap_fiemap <------------- iomap_fiemap
+ * ext4_iomap_to_fiemap <----------- iomap_to_fiemap
+ */
+/**
+ * ext4_fiemap_fill_next_extent - Fiemap helper function
+ * @fieinfo: Fiemap context passed into ->fiemap
+ * @logical: Extent logical start offset, in bytes
+ * @phys: Extent physical start offset, in bytes
+ * @len: Extent length, in bytes
+ * @flags: FIEMAP_EXTENT flags that describe this extent
+ *
+ * Called from file system ->fiemap callback. Will populate extent
+ * info as passed in via arguments and copy to user memory. On
+ * success, extent count on fieinfo is incremented.
+ *
+ * Returns 0 on success, -errno on error, 1 if this was the last
+ * extent that will fit in user array.
+ */
+#define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC)
+#define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED)
+#define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE)
+static int ext4_fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo,
+ u64 logical, u64 phys, u64 len,
+ u32 flags)
+{
+ struct fiemap_extent extent;
+ struct fiemap_extent __user *dest = fieinfo->fi_extents_start;
+
+ /* only count the extents */
+ if (fieinfo->fi_extents_max == 0) {
+ fieinfo->fi_extents_mapped++;
+ return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
+ }
+
+ if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max)
+ return 1;
+
+ if (flags & SET_UNKNOWN_FLAGS)
+ flags |= FIEMAP_EXTENT_UNKNOWN;
+ if (flags & SET_NO_UNMOUNTED_IO_FLAGS)
+ flags |= FIEMAP_EXTENT_ENCODED;
+ if (flags & SET_NOT_ALIGNED_FLAGS)
+ flags |= FIEMAP_EXTENT_NOT_ALIGNED;
+
+ memset(&extent, 0, sizeof(extent));
+ extent.fe_logical = logical;
+ extent.fe_physical = phys;
+ extent.fe_length = len;
+ extent.fe_flags = flags;
+
+ dest += fieinfo->fi_extents_mapped;
+ if (fieinfo->fi_flags & EXT4_FIEMAP_FLAG_MEMCPY)
+ memcpy((__force void *)dest, &extent, sizeof(extent));
+ else if (copy_to_user(dest, &extent, sizeof(extent)))
+ return -EFAULT;
+
+ fieinfo->fi_extents_mapped++;
+ if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max)
+ return 1;
+ return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
+}
+
+static int ext4_iomap_to_fiemap(struct fiemap_extent_info *fi,
+ struct iomap *iomap, u32 flags)
+{
+ switch (iomap->type) {
+ case IOMAP_HOLE:
+ /* skip holes */
+ return 0;
+ case IOMAP_DELALLOC:
+ flags |= FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN;
+ break;
+ case IOMAP_MAPPED:
+ break;
+ case IOMAP_UNWRITTEN:
+ flags |= FIEMAP_EXTENT_UNWRITTEN;
+ break;
+ case IOMAP_INLINE:
+ flags |= FIEMAP_EXTENT_DATA_INLINE;
+ break;
+ }
+
+ if (iomap->flags & IOMAP_F_MERGED)
+ flags |= FIEMAP_EXTENT_MERGED;
+ if (iomap->flags & IOMAP_F_SHARED)
+ flags |= FIEMAP_EXTENT_SHARED;
+
+ return ext4_fiemap_fill_next_extent(fi, iomap->offset,
+ iomap->addr != IOMAP_NULL_ADDR ? iomap->addr : 0,
+ iomap->length, flags);
+}
+
+/* iomap_iter */
+static inline int iomap_iter_advance(struct iomap_iter *iter)
+{
+ /* handle the previous iteration (if any) */
+ if (iter->iomap.length) {
+ if (iter->processed <= 0)
+ return iter->processed;
+ if (WARN_ON_ONCE(iter->processed > iomap_length(iter)))
+ return -EIO;
+ iter->pos += iter->processed;
+ iter->len -= iter->processed;
+ if (!iter->len)
+ return 0;
+ }
+
+ /* clear the state for the next iteration */
+ iter->processed = 0;
+ memset(&iter->iomap, 0, sizeof(iter->iomap));
+ memset(&iter->srcmap, 0, sizeof(iter->srcmap));
+ return 1;
+}
+
+static inline void iomap_iter_done(struct iomap_iter *iter)
+{
+ WARN_ON_ONCE(iter->iomap.offset > iter->pos);
+ WARN_ON_ONCE(iter->iomap.length == 0);
+ WARN_ON_ONCE(iter->iomap.offset + iter->iomap.length <= iter->pos);
+ WARN_ON_ONCE(iter->srcmap.type != IOMAP_HOLE);
+}
+
+/**
+ * iomap_iter - iterate over a ranges in a file
+ * @iter: iteration structue
+ * @ops: iomap ops provided by the file system
+ *
+ * Iterate over filesystem-provided space mappings for the provided file range.
+ *
+ * This function handles cleanup of resources acquired for iteration when the
+ * filesystem indicates there are no more space mappings, which means that this
+ * function must be called in a loop that continues as long it returns a
+ * positive value. If 0 or a negative value is returned, the caller must not
+ * return to the loop body. Within a loop body, there are two ways to break out
+ * of the loop body: leave @iter.processed unchanged, or set it to a negative
+ * errno.
+ */
+int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops)
+{
+ int ret;
+
+ if (iter->iomap.length && ops->iomap_end) {
+ ret = ops->iomap_end(iter->inode, iter->pos, iomap_length(iter),
+ iter->processed > 0 ? iter->processed : 0,
+ iter->flags, &iter->iomap);
+ if (ret < 0 && !iter->processed)
+ return ret;
+ }
+
+ ret = iomap_iter_advance(iter);
+ if (ret <= 0)
+ return ret;
+
+ ret = ops->iomap_begin(iter->inode, iter->pos, iter->len, iter->flags,
+ &iter->iomap, &iter->srcmap);
+ if (ret < 0)
+ return ret;
+ iomap_iter_done(iter);
+ return 1;
+}
+
+static loff_t iomap_fiemap_iter(const struct iomap_iter *iter,
+ struct fiemap_extent_info *fi, struct iomap *prev)
+{
+ int ret;
+
+ if (iter->iomap.type == IOMAP_HOLE)
+ return iomap_length(iter);
+
+ ret = ext4_iomap_to_fiemap(fi, prev, 0);
+ *prev = iter->iomap;
+ switch (ret) {
+ case 0: /* success */
+ return iomap_length(iter);
+ case 1: /* extent array full */
+ return 0;
+ default: /* error */
+ return ret;
+ }
+}
+
+static
+int _ext4_iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
+ u64 start, u64 len, const struct iomap_ops *ops)
+{
+ struct iomap_iter iter = {
+ .inode = inode,
+ .pos = start,
+ .len = len,
+ .flags = IOMAP_REPORT,
+ };
+ struct iomap prev = {
+ .type = IOMAP_HOLE,
+ };
+ int ret;
+ bool in_kernel = fi->fi_flags & EXT4_FIEMAP_FLAG_MEMCPY;
+
+ fi->fi_flags &= ~EXT4_FIEMAP_FLAG_MEMCPY;
+ ret = fiemap_prep(inode, fi, start, &iter.len, 0);
+ if (in_kernel)
+ fi->fi_flags |= EXT4_FIEMAP_FLAG_MEMCPY;
+ if (ret) {
+ return ret;
+ }
+
+ while ((ret = iomap_iter(&iter, ops)) > 0)
+ iter.processed = iomap_fiemap_iter(&iter, fi, &prev);
+
+ if (prev.type != IOMAP_HOLE) {
+ ret = ext4_iomap_to_fiemap(fi, &prev, FIEMAP_EXTENT_LAST);
+ if (ret < 0) {
+ return ret;
+ }
+ }
+
+ /* inode with no (attribute) mapping will give ENOENT */
+ if (ret < 0 && ret != -ENOENT)
+ return ret;
+ return 0;
+}
+
+#define ext4_iomap_fiemap(i, f, s, l, ops) \
+ _ext4_iomap_fiemap((i), (f), (s), (l), (ops))
+#endif /* KERNEL_DS */
+
static int ext4_fill_es_cache_info(struct inode *inode,
ext4_lblk_t block, ext4_lblk_t num,
struct fiemap_extent_info *fieinfo)
@@ -4959,11 +5191,10 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR;
- return iomap_fiemap(inode, fieinfo, start, len,
- &ext4_iomap_xattr_ops);
+ return ext4_iomap_fiemap(inode, fieinfo, start, len,
+ &ext4_iomap_xattr_ops);
}
-
- return iomap_fiemap(inode, fieinfo, start, len, &ext4_iomap_report_ops);
+ return ext4_iomap_fiemap(inode, fieinfo, start, len, &ext4_iomap_report_ops);
}
int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo,
--
2.34.1
