From 929bcf0e7493509f772eb0b82e9e8b177796699b Mon Sep 17 00:00:00 2001
From: Gregory Lirent <opensource@lirent.ru>
Date: Wed, 24 Jun 2026 15:08:07 +0300
Subject: [PATCH] fix(discovery): tolerate CRLF line endings in mtree parsing

mtree_low_split anchored the system flatview on "Root memory region: system"
followed by LF/space/EOF, but QEMU's HMP `info mtree -f` output is CRLF, so the
byte after "system" is '\r'. The anchor was rejected, the parser returned 0
(fail-closed), and on a real guest the daemon never attached the VM (low=0 =>
ok=0). The synthetic LF-only fixture hid this; the fix is verified against the
real CRLF output.

Accept '\r' in the anchor check (LF-only input still works) and add a regression
test that re-encodes the fixture as CRLF in memory.

Bump 0.3.7.
---
 CMakeLists.txt              |  2 +-
 src/discovery/linux/mtree.c |  7 ++++---
 src/test/test_mtree.c       | 22 ++++++++++++++++++++++
 3 files changed, 27 insertions(+), 4 deletions(-)

diff --git a/CMakeLists.txt b/CMakeLists.txt
index 28f22d9..0cbc5bc 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -1,7 +1,7 @@
 cmake_minimum_required(VERSION 3.16)
 # Single source of truth for the version: CI passes -DVMSIG_VERSION=${TAG#v}, so the project
 # version (-> libvgpu-perception SONAME/.so version) and the .deb version come from one tag.
-set(VMSIG_VERSION "0.3.6" CACHE STRING "Release version (MAJOR.MINOR.PATCH); CI passes the tag")
+set(VMSIG_VERSION "0.3.7" CACHE STRING "Release version (MAJOR.MINOR.PATCH); CI passes the tag")
 project(vmsig VERSION ${VMSIG_VERSION} LANGUAGES C)
 
 set(CMAKE_C_STANDARD 17)
diff --git a/src/discovery/linux/mtree.c b/src/discovery/linux/mtree.c
index 1a49d1d..62f51bf 100644
--- a/src/discovery/linux/mtree.c
+++ b/src/discovery/linux/mtree.c
@@ -95,10 +95,11 @@ static const char* find_system_flatview(const char* text, const char** body_end)
     const char* anchor = "Root memory region: system";
     const char* p = text;
     while ((p = strstr(p, anchor)) != NULL) {
-        /* The root name must end the token (newline/EOF) — reject "system.flash0" etc.,
-         * and reject roots that merely contain the word elsewhere. */
+        /* The root name must end the token (CR/LF/space/EOF) — reject "system.flash0" etc.,
+         * and reject roots that merely contain the word elsewhere. QEMU's HMP output is
+         * CRLF, so the byte after "system" is '\r'; accept it (LF-only input also works). */
         const char* after = p + strlen(anchor);
-        if (*after == '\n' || *after == '\0' || *after == ' ') {
+        if (*after == '\n' || *after == '\0' || *after == ' ' || *after == '\r') {
             const char* body = strchr(p, '\n');
             if (!body) return NULL;
             body++;                                  /* first region line                */
diff --git a/src/test/test_mtree.c b/src/test/test_mtree.c
index c69f20d..d3478c6 100644
--- a/src/test/test_mtree.c
+++ b/src/test/test_mtree.c
@@ -32,6 +32,18 @@ static char* slurp(const char* path) {
     return buf;
 }
 
+/* Re-encode every '\n' as '\r\n' (QEMU's HMP output is CRLF). Caller frees; NULL on OOM. */
+static char* to_crlf(const char* lf) {
+    size_t n = 0, extra = 0;
+    for (const char* p = lf; *p; p++) { n++; if (*p == '\n') extra++; }
+    char* out = malloc(n + extra + 1);
+    if (!out) return NULL;
+    char* o = out;
+    for (const char* p = lf; *p; p++) { if (*p == '\n') *o++ = '\r'; *o++ = *p; }
+    *o = 0;
+    return out;
+}
+
 /* Case B: a minimal, NON-fragmented system flatview — one big GPA-0 ram run plus high-RAM
  * carrying @<low>. Must not be broken by the new parser. */
 static const char* k_happy =
@@ -65,6 +77,16 @@ int main(void) {
         /* E: the decoy (non-system) flatview comes FIRST and carries @0x40000000; the
          * function must select the SYSTEM flatview (@0x80000000), not the decoy. */
         CHECK(low != 0x40000000ull, "E: decoy flatview @offset rejected (system AS chosen)");
+        /* F: real QEMU HMP output is CRLF. The parser MUST tolerate '\r' — a synthetic
+         * LF-only fixture hid this, so the shipped parser returned 0 on the real VM mtree
+         * (-> low=0 -> VM never attached). Regression guard, independent of how git stores
+         * the fixture's line endings. */
+        char* frag_crlf = to_crlf(frag);
+        CHECK(frag_crlf != NULL, "F: CRLF copy allocated");
+        if (frag_crlf) {
+            CHECK(mtree_low_split(frag_crlf) == 0x80000000ull, "F: CRLF fragmented split == 0x80000000");
+            free(frag_crlf);
+        }
         free(frag);
     }