diff --git a/implementations/main.cpp b/implementations/main.cpp
index 7ecb1d1..8283f97 100644
--- a/implementations/main.cpp
+++ b/implementations/main.cpp
@@ -55,6 +55,7 @@ bool g_verbose = false;
 bool g_listeners = false;
 bool g_auth = false;
 bool g_enrol = false;
+bool g_calSave = false;
 int g_frames = 40;
 int g_frameGapMs = 500;
 int g_samples = 10;         // common.max_enrolling_samples, as shipped
@@ -326,7 +327,8 @@ void ServeGpFile(std::span<std::byte> sb) {
         f.read(reinterpret_cast<char*>(sb.data() + sfs::ReadDataOff),
                static_cast<std::streamsize>(want));
         auto got = static_cast<std::uint32_t>(f.gcount());
-        std::println("      read {} bytes into +0x{:03x}", got, sfs::ReadDataOff);
+        std::println("      -> errno=0 count={} (asked {}, capacity {})", got,
+                     req->length, sfs::Capacity(sb, sfs::Action::Read));
         sfs::WriteReply(sb, 0, got);
         return;
     }
@@ -357,14 +359,19 @@ void ServeGpFile(std::span<std::byte> sb) {
         std::size_t want = std::min<std::size_t>(req->length,
                                                  sfs::Capacity(sb, sfs::Action::Write));
         std::size_t done = 0;
+        int werr = 0;
         while (done < want) {   // short writes are real; the reference loops
             ssize_t n = ::write(fd, sb.data() + sfs::WriteDataOff + done, want - done);
-            if (n <= 0) break;
+            if (n < 0) { werr = errno; break; }
+            if (n == 0) break;
             done += static_cast<std::size_t>(n);
         }
         ::fsync(fd);
         ::close(fd);
-        sfs::WriteReply(sb, 0, static_cast<std::uint32_t>(done));
+        std::println("      -> errno={} count={} (asked {}, capacity {})", werr, done,
+                     req->length, sfs::Capacity(sb, sfs::Action::Write));
+        sfs::WriteReply(sb, static_cast<std::uint32_t>(werr),
+                        static_cast<std::uint32_t>(done));
         return;
     }
     case sfs::Action::Unlink:
@@ -515,30 +522,45 @@ void ServeRpmb(std::span<std::byte> sb) {
         // A remainder is refused rather than partially committed. The
         // reference silently drops one, which would leave the store
         // inconsistent with a counter that cannot be moved back.
-        auto plan = rp::PlanChunks(req->nblocks, req->blocksPerOp);
+        // req+0x14 is the chunk size, but it is not always usable: the
+        // reference falls back to the whole block count when it is zero or
+        // larger than nblocks.
+        std::uint32_t bpo = req->blocksPerOp;
+        if (bpo == 0 || bpo > req->nblocks) {
+            std::println("    rpmb: chunk size {} unusable, using nblocks={}", bpo,
+                         req->nblocks);
+            bpo = req->nblocks;
+        }
+        auto plan = rp::PlanChunks(req->nblocks, bpo);
         if (!plan.exact) {
             std::println("    rpmb: {} blocks is not a whole number of {}-block chunks"
-                         " -- refusing", req->nblocks, req->blocksPerOp);
+                         " -- refusing", req->nblocks, bpo);
         } else {
             std::array<std::byte, rp::FrameSize> rrq{};
             rp::BuildResultReadRequest(rrq);
-            std::array<std::byte, rp::FrameSize> result{};
             rc = 0;
             for (std::uint32_t k = 0; k < plan.chunks && rc == 0; k++) {
                 std::byte* chunk = frames + static_cast<std::size_t>(k)
-                                 * req->blocksPerOp * rp::FrameSize;
-                std::uint32_t bytes = req->blocksPerOp
-                                    * static_cast<std::uint32_t>(rp::FrameSize);
+                                 * bpo * rp::FrameSize;
+                std::uint32_t bytes = bpo * static_cast<std::uint32_t>(rp::FrameSize);
+                // The RESULT FRAME GOES BACK INTO THE SHARED BUFFER, at the
+                // data offset -- QTEE reads it at req + req[0x0c], which is
+                // exactly where the request frames were. Collecting it into a
+                // local means QTEE never sees the device's answer and fails
+                // the whole transaction with an I/O error, having already
+                // committed the counter.
+                std::byte* result = frames;
                 if (SecurityProtocolRetry(fd, false, chunk, bytes) != 0 ||
                     SecurityProtocolRetry(fd, false, rrq.data(), rp::FrameSize) != 0 ||
-                    SecurityProtocolRetry(fd, true, result.data(), rp::FrameSize) != 0) {
+                    SecurityProtocolRetry(fd, true, result, rp::FrameSize) != 0) {
                     rc = -1;
                     break;
                 }
-                std::uint16_t res = rp::ResultOf(result);
+                std::span<const std::byte> rf(result, rp::FrameSize);
+                std::uint16_t res = rp::ResultOf(rf);
                 std::println("      rpmb write chunk {}/{}: result=0x{:04x} ({}) counter={}",
                              k + 1, plan.chunks, res, rp::ResultString(res),
-                             rp::WriteCounterOf(result));
+                             rp::WriteCounterOf(rf));
                 // Anything non-zero aborts rather than continuing into further
                 // chunks: the device rejected the frame and the counter state
                 // is not what we think it is.
@@ -1232,6 +1254,25 @@ int Probe() {
         std::println("    {}", tally.Identified() ? "FINGER IDENTIFIED" : "no match");
     }
 
+    // ---- Calibration save
+    //
+    // SAVE_DATA with bit 30 CLEAR takes the calibration path, which writes a
+    // real container through the whole storage stack and needs NO FINGER. That
+    // makes it the way to debug the write path without a person present.
+    if (g_calSave) {
+        namespace ta = fingerprintd::ta;
+        if (g_sfsReadOnly) {
+            std::println(std::cerr, "a calibration save writes; pass --sfs-writable");
+            return 1;
+        }
+        std::vector<std::byte> sd(0x10, std::byte{0});
+        for (std::size_t k = 0; k < 4; k++)
+            sd[k] = static_cast<std::byte>((ta::SaveMaskCalibration >> (8 * k)) & 0xFF);
+        std::println("\n=== SAVE_DATA (calibration, no finger needed) ===");
+        auto sv = SendCommand(app, ta::Cmd::SaveData, sd);
+        Report(ta::Cmd::SaveData, sv);
+    }
+
     // ---- Enrolment
     //
     // The first thing here that WRITES: template containers through the gpfile
@@ -1390,6 +1431,7 @@ int main(int argc, char** argv) {
         if (a == "--rpmb-write") g_rpmbWrite = true;
         if (a == "--auth") { g_auth = true; g_listeners = true; }
         if (a == "--enrol") { g_enrol = true; g_listeners = true; }
+        if (a == "--cal-save") { g_calSave = true; g_listeners = true; g_verbose = true; }
         if (a.starts_with("--frames=")) g_frames = std::stoi(std::string(a.substr(9)));
         if (a.starts_with("--log-dir=")) g_logDir = a.substr(10);
         if (a.starts_with("--rescan=")) g_rescan = std::stoi(std::string(a.substr(9)));