Browse zstd specs (36 of 44)
Proofs / zstd / Earlier, longer properties
x_valid_stream
The same streamed in any pieces with any output room; the hint never asks for more than the frame holds.
- spec
- 92 lines of C
- with its headers
- 1,386 lines
- status
- Proved
- 36 of 44
On this page
The spec
The spec is the C program harness/x_valid_stream.c, 92 lines, shown whole as it is in the repository at 2e46017. It includes harness/writer.h (1,231 lines) and harness/zlimits.h (63 lines). Its first comment states the property in full, with every bound.
// Law valid_stream (PROMISES.md: V1-V6, S4, S5): ANY series of compliant frames (harness/writer.h) decoded by
// ZSTD_decompressStream with ANY input and output chunks.
//
// Claim (QuickProof.Contract.harness_safe of this program): no execution has undefined behaviour, and every gp_assert
// holds: every byte delivered is the series' content at that position; a call returns 0 only at the end of a frame
// with all of the frame's content delivered ("0 when a frame is completely decoded and fully flushed"); a positive
// return asks for no more input than remains of the current frame ("will never request more than the remaining
// content of the compressed frame"; at least 1 when only flushing remains); "0 <= pos <= size"; a call with no new
// input delivers at most ZSTD_BLOCKSIZE_MAX bytes; no call fails unless a frame's window is beyond the streaming
// default, memory cannot be allocated, or it is the 16th call in a row without progress (zlimits.h, stall_error:
// zstd's deliberate busy-loop guard). Each call gets fresh buffers of exactly its chunk sizes.
#include <stdlib.h>
#include "quickproof.h"
#include "writer.h"
#include "zlimits.h"
#define CALLS_MAX 4096
static wseries_t sr;
static size_t chunk(size_t max)
{
unsigned c = choose(4);
size_t lim = c == 0 ? 16 : c == 1 ? 512 : c == 2 ? 70000 : max;
return choose_in(0, lim < max ? lim : max);
}
int main(void)
{
size_t ipos = 0, got = 0, calls, stalled = 0; /* stalled: calls in a row that read and wrote nothing */
ZSTD_DStream *ds;
w_series(&sr, 0);
ds = ZSTD_createDStream();
if (ds == NULL)
return 0; /* out of memory: zstd.h allows it */
for (calls = 0; calls < CALLS_MAX; calls++) {
size_t ilen = chunk(sr.n - ipos), olen = 1 + chunk(W_CONTENT_MAX), j, r;
unsigned char *ib = exact_copy(sr.bytes + ipos, ilen), *ob = malloc(olen);
ZSTD_inBuffer in;
ZSTD_outBuffer out;
unsigned k;
if (ib == NULL || ob == NULL) {
free(ib);
free(ob);
break; /* harness out of memory: end the run */
}
in.src = ib;
in.size = ilen;
in.pos = 0;
out.dst = ob;
out.size = olen;
out.pos = 0;
r = ZSTD_decompressStream(ds, &out, &in);
gp_assert(in.pos <= in.size);
gp_assert(out.pos <= out.size);
if (ilen == 0)
gp_assert(out.pos <= ZSTD_BLOCKSIZE_MAX);
for (j = 0; j < out.pos; j++) {
gp_assert(got + j < sr.content_n);
gp_assert(ob[j] == sr.content[got + j]);
}
got += out.pos;
ipos += in.pos;
free(ib);
free(ob);
if (ZSTD_isError(r)) {
gp_assert(!within_stream(&sr) || ZSTD_getErrorCode(r) == ZSTD_error_memory_allocation
|| stall_error(ZSTD_getErrorCode(r), stalled, &in, &out, 0));
break;
}
stalled = in.pos == 0 && out.pos == 0 ? stalled + 1 : 0;
if (r == 0) {
int at_end = 0;
for (k = 0; k < sr.nframes; k++)
if (sr.f[k].start + sr.f[k].size == ipos && got == sr.f[k].cstart + sr.f[k].csize)
at_end = 1;
gp_assert(at_end);
if (ipos == sr.n)
break;
} else {
size_t end = sr.n;
for (k = sr.nframes; k > 0; k--) { /* the current frame: the first not yet decoded and delivered */
size_t e = sr.f[k - 1].start + sr.f[k - 1].size;
if (e > ipos || (e == ipos && got < sr.f[k - 1].cstart + sr.f[k - 1].csize))
end = e;
}
gp_assert(r <= (end - ipos > 0 ? end - ipos : 1));
}
}
ZSTD_freeDStream(ds);
return 0;
}harness/writer.h (1,231 lines) is too long to show here; it is in the repository.
harness/zlimits.h, 63 lines
// The limits under which zstd may refuse a compliant frame, as its documents state them (PROMISES.md V4): "a decoder
// is allowed to reject a compressed frame which requests a memory size beyond decoder's authorized range"
// (format), zstd's range being ZSTD_WINDOWLOG_MAX (31 on 64-bit: zstd.h) for any decoding and, for streaming,
// "By default, a decompression context accepts window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT)" (zstd.h);
// the memory allocation of its contexts; and, for streaming, zstd's deliberate busy-loop guard (stall_error).
#ifndef ZSTD_HARNESS_ZLIMITS_H
#define ZSTD_HARNESS_ZLIMITS_H
#include "writer.h"
#ifndef ZSTD_STATIC_LINKING_ONLY
#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_WINDOWLOG_MAX, ZSTD_WINDOWLOG_LIMIT_DEFAULT */
#endif
#include "zstd.h"
#include "zstd_errors.h"
/* every Zstandard frame of the series is within zstd's window range (single-segment: Window_Size = content size) */
static int within_oneshot(const wseries_t *sr)
{
unsigned k;
for (k = 0; k < sr->nframes; k++)
if (!sr->f[k].skippable && !sr->f[k].single && sr->f[k].window_log > ZSTD_WINDOWLOG_MAX)
return 0;
return 1;
}
/* ... and within the streaming default */
static int within_stream(const wseries_t *sr)
{
unsigned k;
for (k = 0; k < sr->nframes; k++)
if (!sr->f[k].skippable && sr->f[k].window > (1ULL << ZSTD_WINDOWLOG_LIMIT_DEFAULT))
return 0;
return within_oneshot(sr);
}
/* zstd's busy-loop guard, deliberate (commit 31769ce70 "error on no forward progress": a caller "may be caught in an
infinite loop, calling the streaming decompression function again and again, without making any progress";
db18a62f8 gave it its error codes): ZSTD_decompressStream fails on the ZSTD_NO_FORWARD_PROGRESS_MAX-th (16 by
default) call in a row that reads no input and writes no output, with noForwardProgress_destFull if the output is
full, else noForwardProgress_inputEmpty (the input is then empty). zstd.h does not document it. True iff error
code e is that error, legitimately: this call (fresh input, output position opos0 before it) read and wrote
nothing, and so did the `stalled` calls in a row before it. */
#define NO_PROGRESS_MAX 16
static int stall_error(ZSTD_ErrorCode e, size_t stalled, const ZSTD_inBuffer *in, const ZSTD_outBuffer *out,
size_t opos0)
{
if (stalled + 1 < NO_PROGRESS_MAX || in->pos != 0 || out->pos != opos0)
return 0;
if (e == ZSTD_error_noForwardProgress_destFull)
return out->pos == out->size;
return e == ZSTD_error_noForwardProgress_inputEmpty && out->pos < out->size && in->pos == in->size;
}
/* a copy of b[0..n) in a buffer of exactly n bytes (NULL: out of memory) */
static unsigned char *exact_copy(const unsigned char *b, size_t n)
{
unsigned char *p = malloc(n > 0 ? n : 1);
size_t i;
if (p != NULL)
for (i = 0; i < n; i++)
p[i] = b[i];
return p;
}
#endifThe theorem
QuickProof generated this statement from the spec, in src/contracts/x_valid_stream.v:
Theorem x_valid_stream : harness_safe whole_prog.src/contracts/laws.v states it on the spec's own program, whole_prog (the spec linked with the code under test), with its proof:
Theorem x_valid_stream : harness_safe Zstd.contracts.x_valid_stream.whole_prog.
Proof. exact (proj2 (proj2 (proj2 (proj2 (proj2 (proj2 (proj2 (proj2 (proj2 (proj2 (proj2 (proj2 (proj2 (proj2 (proj2 (proj2 (proj2 (proj2 Zstd.contracts.suite.suite_x)))))))))))))))))). Qed.Read as a statement about runs, it says that no run of the program has undefined behaviour or a failing check, for every value the spec can draw. That reading rests on VST's adequacy theorem, which is not yet instantiated in Rocq (formerly Coq) for QuickProof's environment.
The C files (units) its program links
patch/decoder.cquickproof/libc/libc.cquickproof/libc/malloc_unit.c
What it leaves out
- What the first comment of the spec excludes, and its bounds.
- Like every spec of this proof: termination (a run that never returns is not a counterexample), one thread, and binaries built by a compiler (the theorem is about the code as CompCert defines C for x86_64, LP64).
- Other configurations of zstd (flags, legacy formats, assembly) and the compressor.
- The edits to zstd's code, listed in the repository, are checked against the original by testing, not proved.
The summary page says what the proof as a whole covers.
How it was proved
AI agents wrote the proof, and Rocq checks it. qp verify passes on this repository: this statement is the one generated from the spec at the contract commit, and its proof uses only Rocq's standard axioms and VST's abstract malloc library.