0.15.0 --- the atoms of openkal 0.17, the stop word given back, and SIGPIPE no longer fatal (#30)

Co-authored-by: speak-agent <248744407+speak-agent@users.noreply.github.com>

Author: Sunrisepeak

README.md

@@ -5,10 +5,10 @@ written on the kernel's own calls.
 
 ```toml
 [dependencies]
-openkal = "0.16.0"
+openkal = "0.17.0"
 
 [target.'cfg(os = "macos")'.dependencies]
-openkal-macos = "0.14.1"
+openkal-macos = "0.15.0"
 ```
 
 Its purpose is as much to test the specification as to be used. A specification

mcpp.toml

@@ -1,7 +1,7 @@
 [package]
 namespace   = "mcpplibs"
 name        = "openkal-macos"
-version     = "0.14.1"
+version     = "0.15.0"
 description = "An implementation of openkal for macOS, written on the kernel's own calls. Its purpose is as much to test the specification as to be used."
 license     = "Apache-2.0"
 
@@ -57,7 +57,7 @@ provides-interfaces = [
 ]
 
 [dependencies]
-openkal = "0.16.0"
+openkal = "0.17.0"
 
 [build]
 # The flags are attached to this package's own sources rather than to the whole

src/endpoint.h

@@ -106,6 +106,10 @@ inline int from_kernel(const ksockaddr_storage& in, kal_endpoint& out) {
         return kal_ok;
     }
 
+    // A connection made at a name (0.17) has no address and port to state; the
+    // kernel reports the local family, or an unnamed one for an accepted end.
+    if (family == 1 /* AF_UNIX */ || family == 0) return kal_err_not_supported;
+
     return kal_err_invalid;
 }
 

src/env.cpp

@@ -10,6 +10,9 @@ namespace okm {
 int    g_argc = 0;
 char** g_argv = nullptr;
 char** g_envp = nullptr;
+// Whether SIGPIPE was ignored HERE, at the default this program was started
+// with: a program it starts is given the default back (process.cpp).
+bool   g_pipe_ignored_here = false;
 
 void record(int argc, char** argv, char** envp) {
     g_argc = argc; g_argv = argv; g_envp = envp;
@@ -41,14 +44,33 @@ namespace {
 // mistake that shows up as a program dying in a way nobody can trace --- which is
 // the defect this note is about, arrived at from the other side.
 //
-// ⇒ It is left until it can be MEASURED on this system. This repository already
-// refuses to claim a facility it has not exercised, and a signal disposition
-// installed by guesswork is exactly that. The consequence meanwhile is stated:
-// a program above this implementation that writes to a stream whose far end has
-// gone is ended by SIGPIPE rather than told, and no layer between it and here
-// can name what happened.
+// ⇒ MEASURED SINCE (0.15): the stop word installs a handler through this
+// kernel's `sigaction' with this implementation's own trampoline, and the
+// conformance suite raises the signal and returns from it. Ignoring needs no
+// trampoline at all --- the kernel never enters one for an ignored signal ---
+// so the shape is the measured one and the trampoline field is left empty.
+//
+// ONLY WHERE NOTHING ELSE HAS CHOSEN. A program whose own runtime installed a
+// handler for SIGPIPE keeps it; a disposition still at its default is the one
+// that ends the program without telling it, and that is the one replaced.
+//
+// AND IT IS THIS PROGRAM'S, NOT PASSED ON. An ignored disposition survives
+// `execve', so a program started from here would begin with SIGPIPE ignored and
+// a shell it runs could not undo it. `kal_process_spawn' gives the default back
+// to the program it starts when the ignore was made here (process.cpp).
+void ignore_sigpipe() {
+    struct { void (*handler)(int); void* tramp; unsigned int mask; int flags; } act{};
+    struct { void (*handler)(int); unsigned int mask; int flags; } old{};
+    if (okm::failed(okm::sys(46 /* sigaction */, 13 /* SIGPIPE */, 0, reinterpret_cast<okm_long>(&old))))
+        return;
+    if (old.handler != nullptr) return;                 // not SIG_DFL
+    act.handler = reinterpret_cast<void (*)(int)>(1);   // SIG_IGN
+    if (!okm::failed(okm::sys(46 /* sigaction */, 13, reinterpret_cast<okm_long>(&act), 0)))
+        okm::g_pipe_ignored_here = true;
+}
 [[gnu::constructor(101)]] void capture(int argc, char** argv, char** envp) {
     if (okm::g_argv == nullptr) okm::record(argc, argv, envp);
+    ignore_sigpipe();
 }
 }  // namespace
 
@@ -108,4 +130,42 @@ kal_intptr kal_env_var_at(kal_uintptr index, char* out, kal_uintptr cap) {
     return -kal_err_not_found;
 }
 
+// THE IMAGE THE KERNEL STARTED (0.17): what `proc_pidpath' answers, the
+// kernel's record of the file it mapped (`proc_info', PROC_PIDPATHINFO);
+// where that is refused, `executable_path=' from the vector this kernel passes
+// after the environment, which is the name the kernel was given.
+// A program built for its environment was loaded by nothing the interface
+// names (clause 12: only an image has a loader to name).
+kal_intptr kal_env_loader(char* out, kal_uintptr cap) {
+    (void)out; (void)cap;
+    return -kal_err_not_found;
+}
+
+kal_intptr kal_env_image(char* out, kal_uintptr cap) {
+    char buf[4096];
+    const okm_long n = okm::sys(okm::nr_proc_info, 2 /* PROC_INFO_CALL_PIDINFO */,
+                                okm::sys(okm::nr_getpid), 11 /* PROC_PIDPATHINFO */, 0,
+                                reinterpret_cast<okm_long>(buf), sizeof buf);
+    if (!okm::failed(n) && n > 0) {
+        kal_uintptr len = 0; while (len < sizeof buf && buf[len] != '\0') ++len;
+        if (len > 0) return give(buf, len, out, cap);
+    }
+    if (okm::g_envp != nullptr) {
+        char** a = okm::g_envp;
+        while (*a) ++a;
+        for (++a; *a; ++a) {
+            const char key[] = "executable_path=";
+            kal_uintptr i = 0;
+            while (key[i] != '\0' && (*a)[i] == key[i]) ++i;
+            if (key[i] == '\0') return give(*a + i, okm::length(*a + i), out, cap);
+        }
+    }
+    return -kal_err_not_found;
+}
+
+// For conventions only, as the declaration restricts it.
+kal_intptr kal_env_system(char* out, kal_uintptr cap) {
+    return give("macos", 5, out, cap);
+}
+
 }

src/exec.cpp

@@ -169,6 +169,22 @@ int kal_exec_publish(void* p, kal_uintptr size) {
     return kal_ok;
 }
 
+// PART OF A REGION (0.17): a run of whole pages made executable, the rest left
+// writable. A part that is not whole pages is refused rather than rounded.
+int kal_exec_publish_part(void* region, kal_uintptr offset, kal_uintptr size) {
+    const okm_uptr g = granularity();
+    if (region == nullptr || size == 0 || (offset & (g - 1)) != 0 || (size & (g - 1)) != 0
+        || (reinterpret_cast<okm_uptr>(region) & (g - 1)) != 0)
+        return kal_err_invalid;
+    const okm_long r = okm::sys(okm::nr_mprotect,
+                                reinterpret_cast<okm_long>(static_cast<char*>(region) + offset),
+                                static_cast<okm_long>(size), okm::prot_read | okm::prot_exec);
+    return okm::failed(r) ? okm::translate(r) : kal_ok;
+}
+
+// The page this kernel protects in, which is also what it reserves in.
+kal_uintptr kal_exec_granularity(void) { return granularity(); }
+
 void kal_exec_free(void* p, kal_uintptr size) {
     if (p == nullptr || size == 0) return;
     const okm_uptr bytes = round_up(static_cast<okm_uptr>(size), granularity());

src/fs.cpp

@@ -146,6 +146,12 @@ kal_uintptr volume_props(int fd) {
     const kal_uintptr conservative =
         KAL_FS_PROP_MODIFIED_TIME | KAL_FS_PROP_ATOMIC_RENAME
         | KAL_FS_PROP_LOCKS | KAL_FS_PROP_CAPACITY;
+    // A NAME HELD OPEN IS REMOVED AT ONCE (0.17, clause 7.14) on the formats
+    // whose names this kernel keeps: `unlink' drops the entry and the file
+    // lives on until its last descriptor closes. A network volume's client
+    // renames a held file to a hidden name instead, so the directory that held
+    // it is not empty until the close, and the position is not claimed there.
+    const kal_uintptr local = conservative | KAL_FS_PROP_REMOVE_OPEN;
     if (fd < 0) return 0;
 
     okm::kstatfs64 sf{};
@@ -162,9 +168,13 @@ kal_uintptr volume_props(int fd) {
 
     // Nodes whose content is another name, on a format that stores a mode.
     // This is the ordinary volume of this system.
+    //
+    // Both implement `renameatx_np' with RENAME_EXCL (0.17), and both store a
+    // socket bound to a name.
     if (named("apfs") || named("hfs"))
-        return conservative | KAL_FS_PROP_LINKS | KAL_FS_PROP_MAKE_LINKS
-             | KAL_FS_PROP_EXECUTABLE;
+        return local | KAL_FS_PROP_LINKS | KAL_FS_PROP_MAKE_LINKS
+             | KAL_FS_PROP_EXECUTABLE
+             | KAL_FS_PROP_RENAME_NO_REPLACE | KAL_FS_PROP_LOCAL_ENDPOINT;
 
     // The automounter's own namespace: links, and no mode of its own.
     if (named("autofs"))
@@ -179,7 +189,7 @@ kal_uintptr volume_props(int fd) {
     // The FAT family stores neither a case distinction nor a node that names
     // another, nor a mode. `symlinkat' on such a volume reports a refusal, and
     // this is where a caller learns it before it tries.
-    if (named("msdos") || named("exfat")) return conservative;
+    if (named("msdos") || named("exfat")) return local;
 
     return conservative;
 }
@@ -659,6 +669,25 @@ int kal_fs_rename(kal_dir from, const char* a, kal_uintptr alen,
     return okm::failed(r) ? okm::translate(r) : kal_ok;
 }
 
+// A RENAME THAT DOES NOT REPLACE (0.17): `renameatx_np' with RENAME_EXCL, the
+// kernel's own test-and-rename. A format that does not implement the flag
+// answers ENOTSUP, which is a volume that cannot.
+int kal_fs_rename_flags(kal_dir from, const char* a, kal_uintptr alen,
+                        kal_dir to, const char* b, kal_uintptr blen, kal_uintptr flags) {
+    if ((flags & ~static_cast<kal_uintptr>(KAL_RENAME_NO_REPLACE)) != 0) return kal_err_invalid;
+    if (flags == 0) return kal_fs_rename(from, a, alen, to, b, blen);
+    const int f = okm::unpack(from.h), t2 = okm::unpack(to.h);
+    if (f < 0 || t2 < 0 || !okm::acceptable(a, alen) || !okm::acceptable(b, blen))
+        return kal_err_invalid;
+    if ((volume_props(t2) & KAL_FS_PROP_RENAME_NO_REPLACE) == 0) return kal_err_not_supported;
+    okm::terminated ta(a, alen), tb(b, blen);
+    if (!ta.ok || !tb.ok) return kal_err_invalid;
+    const okm_long r = okm::sys(okm::nr_renameatx_np, f, reinterpret_cast<okm_long>(ta.buf),
+                                t2, reinterpret_cast<okm_long>(tb.buf), 0x4 /* RENAME_EXCL */);
+    if (r == -45 /* ENOTSUP */) return kal_err_not_supported;
+    return okm::failed(r) ? okm::translate(r) : kal_ok;
+}
+
 int kal_fs_list_begin(kal_dir d, kal_uintptr* iter) {
     const int fd = okm::unpack(d.h);
     if (fd < 0 || iter == nullptr) return kal_err_invalid;
@@ -720,6 +749,15 @@ int kal_fs_list_next(kal_dir d, kal_uintptr* iter,
 // the position reports it in advance, which no operation could.
 kal_uintptr kal_fs_props(kal_dir d) { return volume_props(okm::unpack(d.h)); }
 
+}  // extern "C" (reopened below)
+
+namespace okm {
+// For openkal.net's rendezvous at a name.
+kal_uintptr volume_props_of(int fd) { return volume_props(fd); }
+}  // namespace okm
+
+extern "C" {
+
 // Nodes whose content is another name.
 int kal_fs_link_create(kal_dir base, const char* name, kal_uintptr len,
                        const char* target, kal_uintptr target_len,

src/net.cpp

@@ -46,8 +46,64 @@ int report_address(okm_long call, int fd, kal_endpoint* out) {
 
 }  // namespace
 
+namespace okm { kal_uintptr volume_props_of(int fd); }   // fs.cpp
+
+namespace {
+// A RENDEZVOUS AT A NAME (0.17). This kernel binds a local socket to a path and
+// has no call that binds beneath a descriptor; it does have a working
+// directory per THREAD (`__pthread_fchdir'), so the name is bound relative to
+// the directory the caller holds by entering it on this thread alone and
+// leaving it again --- no other context's names change meaning meanwhile. The
+// address holds 104 bytes.
+int at_name(kal_dir base, const char* name, kal_uintptr len, bool listen, kal_uintptr& out) {
+    const int dir = okm::unpack(base.h);
+    if (dir < 0 || len == 0 || len > 103 || !okm::acceptable(name, len)) return kal_err_invalid;
+    for (kal_uintptr i = 0; i < len; ++i) if (name[i] == '/') return kal_err_invalid;
+    if ((okm::volume_props_of(dir) & KAL_FS_PROP_LOCAL_ENDPOINT) == 0) return kal_err_not_supported;
+    unsigned char addr[106] = {};
+    addr[0] = static_cast<unsigned char>(2 + len + 1);  // sun_len
+    addr[1] = 1;                                         // AF_UNIX
+    for (kal_uintptr i = 0; i < len; ++i) addr[2 + i] = static_cast<unsigned char>(name[i]);
+    const okm_long fd = okm::sys(okm::nr_socket, 1 /* AF_UNIX */, okm::sock_stream, 0);
+    if (okm::failed(fd)) return okm::translate(fd);
+    close_on_exec(fd);
+    if (const okm_long r = okm::sys(okm::nr_pthread_fchdir, dir); okm::failed(r)) {
+        okm::sys(okm::nr_close, fd);
+        return okm::translate(r);
+    }
+    okm_long r = 0;
+    if (listen) {
+        r = okm::sys(okm::nr_bind, fd, reinterpret_cast<okm_long>(addr), addr[0]);
+    } else {
+        do r = okm::sys(okm::nr_connect, fd, reinterpret_cast<okm_long>(addr), addr[0]);
+        while (okm::interrupted(r));
+    }
+    okm::sys(okm::nr_pthread_fchdir, -1);                // back to the process's directory
+    if (!okm::failed(r) && listen) r = okm::sys(okm::nr_listen, fd, 128);
+    if (okm::failed(r)) {
+        okm::sys(okm::nr_close, fd);
+        if (listen && r == -48 /* EADDRINUSE */) return kal_err_exists;
+        if (!listen && (r == -2 /* ENOENT */ || r == -61 /* ECONNREFUSED */)) return kal_err_not_found;
+        return okm::translate(r);
+    }
+    out = okm::pack(static_cast<int>(fd));
+    if (out == 0) { okm::sys(okm::nr_close, fd); return kal_err_no_memory; }
+    return kal_ok;
+}
+}  // namespace
+
 extern "C" {
 
+int kal_net_listen_at(kal_dir base, const char* name, kal_uintptr len, kal_net_listener* out) {
+    if (out == nullptr) return kal_err_invalid;
+    return at_name(base, name, len, true, out->h);
+}
+
+int kal_net_connect_at(kal_dir base, const char* name, kal_uintptr len, kal_net_conn* out) {
+    if (out == nullptr) return kal_err_invalid;
+    return at_name(base, name, len, false, out->h);
+}
+
 int kal_net_connect(const kal_endpoint* to, kal_net_conn* out) {
     if (to == nullptr || out == nullptr) return kal_err_invalid;
     const okm_long family = okm::family_of(*to);