compressed data will be usually loaded into last pages of
the extent (the last page for 4k) for in-place decompression
(more specifically, in-place IO), as ilustration below,

         start of compressed logical extent
           |                          end of this logical extent
           |                           |
     ______v___________________________v________
... |  page 6  |  page 7  |  page 8  |  page 9  | ...
    |__________|__________|__________|__________|
           .                         ^ .        ^
           .                         |compressed|
           .                         |   data   |
           .                           .        .
           |<          dstsize        >|<margin>|
                                       oend     iend
           op                        ip

Therefore, it's possible to do decompression inplace (thus no
memcpy at all) if the margin is sufficient and safe enough [1],
and it can be implemented only for fixed-size output compression
compared with fixed-size input compression.

No memcpy for most of in-place IO (about 99% of enwik9) after
decompression inplace is implemented and sequential read will
be improved of course (see the following patches for test results).

[1] https://github.com/lz4/lz4/commit/b17f578a919b7e6b078cede2d52be29dd48c8e8c
    https://github.com/lz4/lz4/commit/5997e139f53169fa3a1c1b4418d2452a90b01602

Signed-off-by: Gao Xiang <gaoxian...@huawei.com>
---
 fs/erofs/decompressor.c | 36 ++++++++++++++++++++++++++++++++----
 fs/erofs/erofs_fs.h     |  2 +-
 2 files changed, 33 insertions(+), 5 deletions(-)

diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 244afb29907d..1e9e1359e40c 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -15,6 +15,9 @@
 #endif
 
 #define LZ4_MAX_DISTANCE_PAGES (DIV_ROUND_UP(LZ4_DISTANCE_MAX, PAGE_SIZE) + 1)
+#ifndef LZ4_DECOMPRESS_INPLACE_MARGIN
+#define LZ4_DECOMPRESS_INPLACE_MARGIN(srcsize)  (((srcsize) >> 8) + 32)
+#endif
 
 struct z_erofs_decompressor {
        /*
@@ -117,7 +120,7 @@ static int lz4_decompress(struct z_erofs_decompress_req 
*rq, u8 *out)
 {
        unsigned int inputmargin, inlen;
        u8 *src;
-       bool copied;
+       bool copied, support_0padding;
        int ret;
 
        if (rq->inputsize > PAGE_SIZE)
@@ -125,13 +128,38 @@ static int lz4_decompress(struct z_erofs_decompress_req 
*rq, u8 *out)
 
        src = kmap_atomic(*rq->in);
        inputmargin = 0;
+       support_0padding = false;
+
+       /* decompression inplace is only safe when 0padding is enabled */
+       if (EROFS_SB(rq->sb)->requirements & EROFS_REQUIREMENT_LZ4_0PADDING) {
+               support_0padding = true;
+
+               while (!src[inputmargin & ~PAGE_MASK])
+                       if (!(++inputmargin & ~PAGE_MASK))
+                               break;
+
+               if (inputmargin >= rq->inputsize) {
+                       kunmap_atomic(src);
+                       return -EIO;
+               }
+       }
 
        copied = false;
        inlen = rq->inputsize - inputmargin;
        if (rq->inplace_io) {
-               src = generic_copy_inplace_data(rq, src, inputmargin);
-               inputmargin = 0;
-               copied = true;
+               const uint oend = (rq->pageofs_out +
+                                  rq->outputsize) & ~PAGE_MASK;
+               const uint nr = PAGE_ALIGN(rq->pageofs_out +
+                                          rq->outputsize) >> PAGE_SHIFT;
+
+               if (rq->partial_decoding || !support_0padding ||
+                   rq->out[nr - 1] != rq->in[0] ||
+                   rq->inputsize - oend <
+                     LZ4_DECOMPRESS_INPLACE_MARGIN(inlen)) {
+                       src = generic_copy_inplace_data(rq, src, inputmargin);
+                       inputmargin = 0;
+                       copied = true;
+               }
        }
 
        ret = LZ4_decompress_safe_partial(src + inputmargin, out,
diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index 230fcba1099d..c0fb7d6ebfcb 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -17,7 +17,7 @@
  * incompatible with this kernel version.
  */
 #define EROFS_REQUIREMENT_LZ4_0PADDING 0x00000001
-#define EROFS_ALL_REQUIREMENTS         0
+#define EROFS_ALL_REQUIREMENTS         EROFS_REQUIREMENT_LZ4_0PADDING
 
 struct erofs_super_block {
 /*  0 */__le32 magic;           /* in the little endian */
-- 
2.17.1

Reply via email to