0.22.0 --- openkal 0.21: instructions from a file; an ended program's processor time; a program started without copying this one; kal_alloc carved as it is used

README.md

@@ -5,10 +5,10 @@ for Linux, written on the kernel's own system-call interface.
 
 ```toml
 [dependencies]
-openkal = "0.20.0"
+openkal = "0.21.0"
 
 [target.'cfg(os = "linux")'.dependencies]
-openkal-linux = "0.21.0"
+openkal-linux = "0.22.0"
 ```
 
 ## Why it does not use a C library
@@ -102,6 +102,38 @@ A program that carries a runtime of its own answers from that runtime instead
 (`pthread_getattr_np`), because in that arrangement the runtime is what owns the
 stacks and is what a program above openkal would ask for itself.
 
+## What 0.22 adds (openkal 0.21)
+
+**Instructions from a file.** `kal_exec_map_part` maps the file's pages over part
+of a region (`mmap` with `MAP_FIXED`, private), read, or read and executed;
+`KAL_EXEC_PROP_FILE` is claimed. A volume mounted without execution reports
+`kal_err_not_supported`.
+
+**An ended program's processor time.** `kal_process_info` reports `cpu_ns` of a
+started program that has ended from the same record as its peak memory
+(`waitid(WNOWAIT)`'s usage), until `kal_process_close` collects it.
+
+**A program is started without copying this one.** `kal_process_spawn` starts the
+program with `clone(CLONE_VM | CLONE_VFORK)` on a stack of its own, as a C
+library's `posix_spawn` does, and every request is held until it is replaced; the
+started image sets each handled request to its default before it takes the
+caller's mask. A copy of the address space (`clone` with `SIGCHLD` alone) copied
+the page tables of the whole program and made each page it wrote afterwards fault
+again: 1.4 ms in the kernel and about 1 900 faults for each worker a language
+server started.
+
+**An enquiry and an open read the name once.** `kal_fs_info` and `kal_fs_open`
+check the name and terminate it for the kernel in one pass, the volume each
+enquiry asks about is read without a lock (a sequence read before and after the
+slots), and the answer is written straight into the caller's structure: what an
+enquiry costs beyond the kernel's own fell from 28 ns to 19 ns.
+
+**A chunk of `kal_alloc` is carved as it is used.** A free list threaded through
+each 1 MiB chunk when it was mapped made the whole chunk resident; six classes in
+use made 6 MiB resident in every program. A block is now carved when it is
+handed out. An alignment wider than 4096 bytes is mapped, as a block of a class
+is aligned only to its size or to the page.
+
 ## What 0.21 adds (openkal 0.20)
 
 **Transfers at an offset.** `kal_fs_read_at` and `kal_fs_write_at` are the

mcpp.toml

@@ -1,7 +1,7 @@
 [package]
 namespace   = "mcpplibs"
 name        = "openkal-linux"
-version     = "0.21.0"
+version     = "0.22.0"
 description = "The reference implementation of openkal for Linux, written on the kernel's own system-call interface so that it can be placed beneath a C library as well as above one."
 license     = "Apache-2.0"
 
@@ -65,7 +65,7 @@ provides-interfaces = [
 ]
 
 [dependencies]
-openkal = "0.20.0"
+openkal = "0.21.0"
 
 # The package contributes definitions and no modules. The interface it
 # implements is declared by the specification package, which this package

src/exec.cpp

@@ -1,5 +1,7 @@
 #include "sys.h"
+#include "handle.h"
 #include <openkal/exec.h>
+#include <openkal/map.h>
 
 namespace okl { okl_ulong auxval(okl_ulong key); }
 
@@ -114,6 +116,40 @@ int kal_exec_publish_part(void* region, kal_uintptr offset, kal_uintptr size) {
 
 kal_uintptr kal_exec_granularity(void) { return page(); }
 
+// A PART THAT IS A FILE'S (0.21): the file's pages mapped over the part,
+// private, and executable where asked. MAP_FIXED replaces what the part held in
+// one call, so there is no moment at which the addresses are free for another
+// mapping to take. The arguments are checked first: a refused part leaves the
+// region as it was.
+int kal_exec_map_part(void* region, kal_uintptr offset, kal_uintptr size, kal_file f, kal_u64 at,
+                      kal_uintptr how) {
+    const okl_uptr g = page();
+    const int fd = okl::unpack(f.h);
+    if (region == nullptr || size == 0 || fd < 0 || (offset & (g - 1)) != 0 || (size & (g - 1)) != 0
+        || (reinterpret_cast<okl_uptr>(region) & (g - 1)) != 0 || at % KAL_MAP_ALIGNMENT != 0
+        || (how & ~KAL_EXEC_MAP_EXECUTE) != 0)
+        return kal_err_invalid;
+    okl::kstat st{};
+    const okl_long s = okl::sys(okl::nr_fstat, fd, reinterpret_cast<okl_long>(&st));
+    if (okl::failed(s)) return okl::translate(s);
+    if ((st.mode & okl::s_ifmt) != okl::s_ifreg) return kal_err_not_supported;
+    const kal_u64 length = st.size > 0 ? static_cast<kal_u64>(st.size) : 0;
+    if (at > length || static_cast<kal_u64>(size) > length - at) return kal_err_invalid;
+    const okl_long prot = okl::prot_read | ((how & KAL_EXEC_MAP_EXECUTE) ? okl::prot_exec : 0);
+    const okl_long r = okl::sys(okl::nr_mmap,
+                                reinterpret_cast<okl_long>(static_cast<char*>(region) + offset),
+                                static_cast<okl_long>(size), prot, okl::map_private | okl::map_fixed, fd,
+                                static_cast<okl_long>(at));
+    if (okl::failed(r)) {
+        // ENODEV: the file system does not map. EPERM: its files are not
+        // executed (a volume mounted noexec). The resource refuses, not the
+        // implementation (exec.h).
+        if (-r == okl::e_nodev || -r == okl::e_perm) return kal_err_not_supported;
+        return okl::translate(r);
+    }
+    return kal_ok;
+}
+
 void kal_exec_free(void* p, kal_uintptr size) {
     if (p == nullptr || size == 0) return;
     const okl_uptr bytes = round_up(static_cast<okl_uptr>(size), page());
@@ -127,7 +163,7 @@ void kal_exec_free(void* p, kal_uintptr size) {
 kal_uintptr kal_exec_props(void) {
     // Executable memory is available to every artifact on this kernel: nothing
     // here is granted only to a program produced in a particular way.
-    return KAL_EXEC_PROP_REPUBLISH | KAL_EXEC_PROP_AVAILABLE;
+    return KAL_EXEC_PROP_REPUBLISH | KAL_EXEC_PROP_AVAILABLE | KAL_EXEC_PROP_FILE;
 }
 
 }  // extern "C"

src/fs.cpp

@@ -228,23 +228,49 @@ kal_uintptr volume_props_of(int fd) { return volume_props(fd); }
 // A volume's format does not change under a device number while it is mounted,
 // so the answer is kept by the device the kernel reports for the node; a slot
 // a later device needs is taken over (eight are kept).
+//
+// READ WITHOUT A LOCK (0.22): the slots change only when a ninth device is
+// asked about, so a reader takes the sequence before and after reading them and
+// reads again if a writer was between; writers take the lock. The lock taken on
+// every enquiry was a fifth of what an enquiry cost beyond the kernel's own.
 struct volume_answer { okl_u64 dev; kal_uintptr props; bool known; };
 volume_answer g_volumes[8];
 unsigned g_volume_next = 0;
 volatile int g_volume_lock = 0;
+unsigned g_volume_sequence = 0;   // odd while a writer changes a slot
+
+bool volume_known(okl_u64 dev, kal_uintptr& props) {
+    for (;;) {
+        const unsigned before = __atomic_load_n(&g_volume_sequence, __ATOMIC_ACQUIRE);
+        if (before & 1u) { okl::sys(okl::nr_sched_yield); continue; }
+        bool found = false;
+        kal_uintptr p = 0;
+        for (auto const& v : g_volumes)
+            if (__atomic_load_n(&v.known, __ATOMIC_RELAXED) && __atomic_load_n(&v.dev, __ATOMIC_RELAXED) == dev) {
+                p = __atomic_load_n(&v.props, __ATOMIC_RELAXED);
+                found = true;
+                break;
+            }
+        __atomic_thread_fence(__ATOMIC_ACQUIRE);
+        if (__atomic_load_n(&g_volume_sequence, __ATOMIC_RELAXED) != before) continue;
+        props = p;
+        return found;
+    }
+}
 
 kal_uintptr volume_props_on(okl_u64 dev, int fd) {
+    kal_uintptr props = 0;
+    if (volume_known(dev, props)) return props;
+    props = volume_props(fd);
     while (__atomic_exchange_n(&g_volume_lock, 1, __ATOMIC_ACQUIRE)) okl::sys(okl::nr_sched_yield);
-    for (auto const& v : g_volumes)
-        if (v.known && v.dev == dev) {
-            const kal_uintptr props = v.props;
-            __atomic_store_n(&g_volume_lock, 0, __ATOMIC_RELEASE);
-            return props;
-        }
-    __atomic_store_n(&g_volume_lock, 0, __ATOMIC_RELEASE);
-    const kal_uintptr props = volume_props(fd);
-    while (__atomic_exchange_n(&g_volume_lock, 1, __ATOMIC_ACQUIRE)) okl::sys(okl::nr_sched_yield);
-    g_volumes[g_volume_next++ % 8] = volume_answer{ dev, props, true };
+    __atomic_store_n(&g_volume_sequence, g_volume_sequence + 1, __ATOMIC_RELAXED);
+    __atomic_thread_fence(__ATOMIC_RELEASE);
+    volume_answer& slot = g_volumes[g_volume_next++ % 8];
+    __atomic_store_n(&slot.known, false, __ATOMIC_RELAXED);
+    __atomic_store_n(&slot.dev, dev, __ATOMIC_RELAXED);
+    __atomic_store_n(&slot.props, props, __ATOMIC_RELAXED);
+    __atomic_store_n(&slot.known, true, __ATOMIC_RELAXED);
+    __atomic_store_n(&g_volume_sequence, g_volume_sequence + 1, __ATOMIC_RELEASE);
     __atomic_store_n(&g_volume_lock, 0, __ATOMIC_RELEASE);
     return props;
 }
@@ -293,8 +319,8 @@ void fill_info(const okl::kstat& st, kal_u32 wanted, kal_node_info* out,
         v.executable = (st.mode & 0111u) != 0 ? 1 : 0;
     }
 
-    const kal_u32 n = self < sizeof v ? self : (kal_u32)sizeof v;
-    okl::copy(reinterpret_cast<char*>(out), reinterpret_cast<const char*>(&v), n);
+    if (self >= sizeof v) { *out = v; out->self_size = self; return; }
+    okl::copy(reinterpret_cast<char*>(out), reinterpret_cast<const char*>(&v), self);
 }
 
 // A node that refers to nothing, in the same shape.
@@ -453,8 +479,8 @@ int kal_fs_open_dir(kal_dir base, const char* name, kal_uintptr len, kal_dir* ou
 int kal_fs_open(kal_dir base, const char* name, kal_uintptr len,
                 kal_uintptr flags, kal_file* out) {
     const int b = okl::unpack(base.h);
-    if (b < 0 || out == nullptr || !okl::acceptable(name, len)) return kal_err_invalid;
-    okl::terminated t(name, len); if (!t.ok) return kal_err_invalid;
+    if (b < 0 || out == nullptr) return kal_err_invalid;
+    okl::accepted_name t(name, len); if (!t.ok) return kal_err_invalid;
 
     const bool r = (flags & KAL_OPEN_READ)  != 0;
     const bool w = (flags & KAL_OPEN_WRITE) != 0;
@@ -556,8 +582,8 @@ kal_intptr kal_fs_write_at(kal_file f, const void* buf, kal_uintptr len, kal_u64
 int kal_fs_info(kal_dir base, const char* name, kal_uintptr len,
                 kal_uintptr flags, kal_u32 wanted, kal_node_info* out) {
     const int b = okl::unpack(base.h);
-    if (b < 0 || !info_ok(out) || !okl::acceptable(name, len)) return kal_err_invalid;
-    okl::terminated t(name, len); if (!t.ok) return kal_err_invalid;
+    if (b < 0 || !info_ok(out)) return kal_err_invalid;
+    okl::accepted_name t(name, len); if (!t.ok) return kal_err_invalid;
     okl::kstat st{};
     // RESOLVES BY DEFAULT, SO THAT ASKING AND OPENING ANSWER THE SAME QUESTION.
     //

src/memory.cpp

@@ -43,6 +43,9 @@ struct spin {
 
 spin  g_lock;
 void* g_free[kClasses];
+// The part of each class's newest chunk no block has been carved from yet.
+unsigned char* g_next[kClasses];
+unsigned char* g_end[kClasses];
 
 int class_of(okl_uptr n) {
     okl_uptr s = kMinBlock; int c = 0;
@@ -66,19 +69,29 @@ void unmap(void* p, okl_uptr bytes) {
 okl_uptr round_up(okl_uptr n, okl_uptr to) { return (n + to - 1) & ~(to - 1); }
 
 // A chunk is page-aligned and a block size is a power of two no larger than a
-// chunk, so a block at a multiple of its size is aligned to its size. That is
-// why an alignment request is satisfied by choosing a larger class rather than
-// by padding: no metadata is needed, and none is kept.
-bool refill(int c) {
+// chunk, so a block at a multiple of its size is aligned to its size or to the
+// page, whichever is smaller. That is why an alignment request up to 4096 bytes
+// (the smallest page among the environments) is satisfied by choosing a larger
+// class rather than by padding: no metadata is needed, and none is kept. A
+// wider alignment is mapped (below), as a block of a class would not have it.
+//
+// A CHUNK IS CARVED AS ITS BLOCKS ARE HANDED OUT, NOT WHEN IT IS MAPPED. A free
+// list threaded through the whole chunk at once wrote a pointer into each of
+// its blocks, so every page of every chunk was made resident before a block of
+// it was used: measured, six classes and six mebibytes resident, 1 500 page
+// faults, in each program an ok image's loader started --- three quarters of
+// what such a program paid before its first instruction.
+void* carve(int c) {
     const okl_uptr bs = size_of(c);
-    auto* base = static_cast<unsigned char*>(map(kChunk));
-    if (!base) return false;
-    for (okl_uptr off = kChunk; off >= bs; off -= bs) {
-        auto* b = base + off - bs;
-        *reinterpret_cast<void**>(b) = g_free[c];
-        g_free[c] = b;
+    if (g_next[c] == g_end[c]) {
+        auto* base = static_cast<unsigned char*>(map(kChunk));
+        if (!base) return nullptr;
+        g_next[c] = base;
+        g_end[c] = base + kChunk;
     }
-    return true;
+    void* b = g_next[c];
+    g_next[c] += bs;
+    return b;
 }
 
 }  // namespace
@@ -90,12 +103,12 @@ void* kal_alloc(kal_uintptr size, kal_uintptr align) {
     if (align < kMinBlock) align = kMinBlock;
 
     okl_uptr want = size < align ? align : size;
-    if (want <= kMaxSmall) {
+    if (want <= kMaxSmall && align <= 4096) {
         const int c = class_of(want);
         g_lock.lock();
-        if (!g_free[c] && !refill(c)) { g_lock.unlock(); return nullptr; }
         void* b = g_free[c];
-        g_free[c] = *reinterpret_cast<void**>(b);
+        if (b) g_free[c] = *reinterpret_cast<void**>(b);
+        else b = carve(c);
         g_lock.unlock();
         return b;
     }
@@ -128,7 +141,7 @@ void kal_free(void* p, kal_uintptr size, kal_uintptr align) {
     if (align < kMinBlock) align = kMinBlock;
 
     const okl_uptr want = size < align ? align : size;
-    if (want <= kMaxSmall) {
+    if (want <= kMaxSmall && align <= 4096) {
         const int c = class_of(want);
         g_lock.lock();
         *reinterpret_cast<void**>(p) = g_free[c];