journal/compress: fix zstd decompression with capped output size

decompress_blob_zstd() would allocate ever bigger buffers in a loop trying to
get a buffer big enough to decompress the input data. This is wasteful, since
we can just query the size of the decompressed data from the compressed header.
Worse, it doesn't work when the output size is capped, i.e. when dst_max != 0.
If the decompressed blob happened to be bigger than dst_max, decompression
would fail with -ENOBUFS. We need to use "stream decompression" instead, and
only get min(uncompressed size, dst_max) bytes of output.

Fixes https://bugzilla.redhat.com/show_bug.cgi?id=1856037 in a second way.

diff --git a/src/journal/compress.c b/src/journal/compress.c
index 1b0c01a8fb32e98b6c002c517dbb2e005626fb26..626e079fefba3a3f800b132d29b647558fe2ffd8 100644 (file)
--- a/src/journal/compress.c
+++ b/src/journal/compress.c
@@ -259,10 +259,10 @@ int decompress_blob_lz4(const void *src, uint64_t src_size,
 
 int decompress_blob_zstd(
                 const void *src, uint64_t src_size,
-                void **dst, size_t *dst_alloc_size, size_t* dst_size, size_t dst_max) {
+                void **dst, size_t *dst_alloc_size, size_t *dst_size, size_t dst_max) {
 
 #if HAVE_ZSTD
-        size_t space;
+        uint64_t size;
 
         assert(src);
         assert(src_size > 0);
@@ -271,38 +271,40 @@ int decompress_blob_zstd(
         assert(dst_size);
         assert(*dst_alloc_size == 0 || *dst);
 
-        if (src_size > SIZE_MAX/2) /* Overflow? */
-                return -ENOBUFS;
-        space = src_size * 2;
-        if (dst_max > 0 && space > dst_max)
-                space = dst_max;
-
-        if (!greedy_realloc(dst, dst_alloc_size, space, 1))
-                return -ENOMEM;
+        size = ZSTD_getFrameContentSize(src, src_size);
+        if (IN_SET(size, ZSTD_CONTENTSIZE_ERROR, ZSTD_CONTENTSIZE_UNKNOWN))
+                return -EBADMSG;
 
-        for (;;) {
-                size_t k;
+        if (dst_max > 0 && size > dst_max)
+                size = dst_max;
+        if (size > SIZE_MAX)
+                return -E2BIG;
 
-                k = ZSTD_decompress(*dst, *dst_alloc_size, src, src_size);
-                if (!ZSTD_isError(k)) {
-                        *dst_size = k;
-                        return 0;
-                }
-                if (ZSTD_getErrorCode(k) != ZSTD_error_dstSize_tooSmall)
-                        return zstd_ret_to_errno(k);
+        if (!(greedy_realloc(dst, dst_alloc_size, MAX(ZSTD_DStreamOutSize(), size), 1)))
+                return -ENOMEM;
 
-                if (dst_max > 0 && space >= dst_max) /* Already at max? */
-                        return -ENOBUFS;
-                if (space > SIZE_MAX / 2) /* Overflow? */
-                        return -ENOBUFS;
+        _cleanup_(ZSTD_freeDCtxp) ZSTD_DCtx *dctx = ZSTD_createDCtx();
+        if (!dctx)
+                return -ENOMEM;
 
-                space *= 2;
-                if (dst_max > 0 && space > dst_max)
-                        space = dst_max;
+        ZSTD_inBuffer input = {
+                .src = src,
+                .size = src_size,
+        };
+        ZSTD_outBuffer output = {
+                .dst = *dst,
+                .size = *dst_alloc_size,
+        };
 
-                if (!greedy_realloc(dst, dst_alloc_size, space, 1))
-                        return -ENOMEM;
+        size_t k = ZSTD_decompressStream(dctx, &output, &input);
+        if (ZSTD_isError(k)) {
+                log_debug("ZSTD decoder failed: %s", ZSTD_getErrorName(k));
+                return zstd_ret_to_errno(k);
         }
+        assert(output.pos >= size);
+
+        *dst_size = size;
+        return 0;
 #else
         return -EPROTONOSUPPORT;
 #endif