lib: zstd: update to latest Linux zstd 1.5.2

Update the zstd implementation to match Linux zstd 1.5.2 from commit
2aa14b1ab2.

This was motivated by running into decompression corruption issues when
trying to uncompress files compressed with newer versions of zstd. zstd
users also claim significantly improved decompression times with newer
zstd versions which is a side benefit.

Original zstd code was copied from Linux commit 2aa14b1ab2 which is a
custom-built implementation based on zstd 1.3.1. Linux switched to an
implementation that is a copy of the upstream zstd code in Linux commit
e0c1b49f5b, this results in a large code diff. However this should make
future updates easier along with other benefits[1].

This commit is a straight mirror of the Linux zstd code, except to:
- update a few #include that do not translate cleanly
  - linux/swab.h -> asm/byteorder.h
  - linux/limits.h -> linux/kernel.h
  - linux/module.h -> linux/compat.h
- remove assert() from debug.h so it doesn't conflict with u-boot's
  assert()
- strip out the compressor code as was done in the previous u-boot zstd
- update existing zstd users to the new Linux zstd API
- change the #define for MEM_STATIC to use INLINE_KEYWORD for codesize
- add a new KConfig option that sets zstd build options to minify code
  based on zstd's ZSTD_LIB_MINIFY[2].

These changes were tested by booting a zstd 1.5.2 compressed kernel inside a
FIT. And the squashfs changes by loading a file from zstd compressed squashfs
with sqfsload. buildman was used to compile test other boards and check for
binary bloat, as follows:

> $ buildman -b zstd2 --boards dh_imx6,m53menlo,mvebu_espressobin-88f3720,sandbox,sandbox64,stm32mp15_dhcom_basic,stm32mp15_dhcor_basic,turris_mox,turris_omnia -sS
> Summary of 6 commits for 9 boards (8 threads, 1 job per thread)
> 01: Merge branch '2023-01-10-platform-updates'
>        arm:  w+   m53menlo dh_imx6
> 02: lib: zstd: update to latest Linux zstd 1.5.2
>    aarch64: (for 2/2 boards) all -3186.0 rodata +920.0 text -4106.0
>        arm: (for 5/5 boards) all +1254.4 rodata +940.0 text +314.4
>    sandbox: (for 2/2 boards) all -4452.0 data -16.0 rodata +640.0 text -5076.0

[1] https://github.com/torvalds/linux/commit/e0c1b49f5b674cca7b10549c53b3791d0bbc90a8
[2] https://github.com/facebook/zstd/blob/f302ad8811643c428c4e3498e28f53a0578020d3/lib/libzstd.mk#L31

Signed-off-by: Brandon Maier <brandon.maier@collins.com>
[trini: Set ret to -EINVAL for the error of "failed to detect
compressed" to fix warning, drop ZSTD_SRCSIZEHINT_MAX for non-Linux host
tool builds]
Signed-off-by: Tom Rini <trini@konsulko.com>

1 files changed, 25 insertions, 28 deletions

diff --git a/lib/zstd/zstd.c b/lib/zstd/zstd.c
index bf9cd19cfa..3a2abc8367 100644
--- a/lib/zstd/zstd.c
+++ b/lib/zstd/zstd.c
@@ -13,14 +13,12 @@
 
 int zstd_decompress(struct abuf *in, struct abuf *out)
 {
-	ZSTD_DStream *dstream;
-	ZSTD_inBuffer in_buf;
-	ZSTD_outBuffer out_buf;
+	zstd_dctx *ctx;
+	size_t wsize, len;
 	void *workspace;
-	size_t wsize;
 	int ret;
 
-	wsize = ZSTD_DStreamWorkspaceBound(abuf_size(in));
+	wsize = zstd_dctx_workspace_bound();
 	workspace = malloc(wsize);
 	if (!workspace) {
 		debug("%s: cannot allocate workspace of size %zu\n", __func__,
@@ -28,36 +26,35 @@ int zstd_decompress(struct abuf *in, struct abuf *out)
 		return -ENOMEM;
 	}
 
-	dstream = ZSTD_initDStream(abuf_size(in), workspace, wsize);
-	if (!dstream) {
-		log_err("%s: ZSTD_initDStream failed\n", __func__);
+	ctx = zstd_init_dctx(workspace, wsize);
+	if (!ctx) {
+		log_err("%s: zstd_init_dctx() failed\n", __func__);
 		ret = -EPERM;
 		goto do_free;
 	}
 
-	in_buf.src = abuf_data(in);
-	in_buf.pos = 0;
-	in_buf.size = abuf_size(in);
-
-	out_buf.dst = abuf_data(out);
-	out_buf.pos = 0;
-	out_buf.size = abuf_size(out);
-
-	while (1) {
-		size_t res;
-
-		res = ZSTD_decompressStream(dstream, &out_buf, &in_buf);
-		if (ZSTD_isError(res)) {
-			ret = ZSTD_getErrorCode(res);
-			log_err("ZSTD_decompressStream error %d\n", ret);
-			goto do_free;
-		}
+	/*
+	 * Find out how large the frame actually is, there may be junk at
+	 * the end of the frame that zstd_decompress_dctx() can't handle.
+	 */
+	len = zstd_find_frame_compressed_size(abuf_data(in), abuf_size(in));
+	if (zstd_is_error(len)) {
+		log_err("%s: failed to detect compressed size: %d\n", __func__,
+			zstd_get_error_code(len));
+		ret = -EINVAL;
+		goto do_free;
+	}
 
-		if (in_buf.pos >= abuf_size(in) || !res)
-			break;
+	len = zstd_decompress_dctx(ctx, abuf_data(out), abuf_size(out),
+				   abuf_data(in), len);
+	if (zstd_is_error(len)) {
+		log_err("%s: failed to decompress: %d\n", __func__,
+			zstd_get_error_code(len));
+		ret = -EINVAL;
+		goto do_free;
 	}
 
-	ret = out_buf.pos;
+	ret = len;
 do_free:
 	free(workspace);
 	return ret;