SchOS/kernel/arch/x86_64/mp.c
Nexoniarz 94c936ed98 boot: stop assuming the machine is an emulator
Every one of these works under QEMU and stops a real machine:

- MADT processors that are "online capable" but not enabled were
  counted as CPUs. AMD firmware lists absent cores that way (so does
  QEMU with maxcpus), and startothers() then waited for ever for an
  AP that does not exist. Only enabled entries count now, x2APIC
  (type 9) entries are read too, and the wait is bounded to a second;
  an AP that misses it is parked with INIT and the boot goes on.
- The PIT calibration loop had no bound. Recent boards clock-gate the
  8254: the output never rises (a hang) or floats high (TSC "0 MHz"
  and every clock thousands of times fast). The loop is bounded and
  checked, and falls back to the ACPI PM timer, then CPUID 0x15/0x16.
  Under QEMU pit=off the PM timer gives the same figures the PIT did.
- Firmware that hands over in x2APIC mode left lapic[] reading
  garbage: cpunum() panicked or the timer never started. Each CPU is
  switched back to xAPIC first (x2APIC -> disabled -> xAPIC).
- The IOAPIC was always at 0xFEC00000 and interrupts were aimed at
  APIC ID "0". Both now come from the firmware's tables.
- INIT-to-STARTUP was 100 us ("Bochs is slow"); it is the 10 ms the
  MP specification asks for.
- mouseinit() drained the 8042 with an unbounded loop. With no
  controller the port reads 0xFF and the loop never ends. It now
  notices there is no controller and skips the mouse.

Tested in QEMU: i440fx and q35, -smp 4, -smp 2,maxcpus=4, pit=off.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HH7xukt4aaiGj1nQEAoQf1
2026-10-22 10:29:12 +02:00

167 lines
4.9 KiB
C

// Multiprocessor support
// Search memory for MP description structures.
// http://developer.intel.com/design/pentium/datashts/24201606.pdf
#include "types.h"
#include "defs.h"
#include "param.h"
#include "memlayout.h"
#include "mp.h"
#include "x86.h"
#include "mmu.h"
#include "proc.h"
struct cpu cpus[NCPU];
// Processors the firmware says exist.
int ncpu;
// Processors actually running, which is not the same number and must not be
// confused with it. Enumeration is cheap and startup is where the difficulty
// is: right now the APs are found and deliberately not started, so this stays
// at 1 while ncpu is 2, 4 or 16.
//
// /proc/cpuinfo reports *this* one, matching Linux, where cpuinfo lists online
// CPUs. Reporting ncpu there told a VM with four processors that it had four
// working ones, which was a comfortable thing to read and false.
int ncpu_online = 1;
uchar ioapicid;
// Where the I/O APIC's registers are. Every source that describes it -- the
// MADT, or this table -- says so, and ioapicinit() maps whatever they said.
uint64 ioapic_phys = IOAPIC_DEFAULT_PHYS;
static uchar
sum(uchar *addr, int len)
{
int i, sum;
sum = 0;
for(i=0; i<len; i++)
sum += addr[i];
return sum;
}
// Look for an MP structure in the len bytes at addr.
static struct mp*
mpsearch1(addr_t a, int len)
{
uchar *e, *p, *addr;
addr = P2V(a);
e = addr+len;
for(p = addr; p < e; p += sizeof(struct mp))
if(memcmp(p, "_MP_", 4) == 0 && sum(p, sizeof(struct mp)) == 0)
return (struct mp*)p;
return 0;
}
// Search for the MP Floating Pointer Structure, which according to the
// spec is in one of the following three locations:
// 1) in the first KB of the EBDA;
// 2) in the last KB of system base memory;
// 3) in the BIOS ROM between 0xE0000 and 0xFFFFF.
static struct mp*
mpsearch(void)
{
uchar *bda;
uint p;
struct mp *mp;
bda = (uchar *) P2V(0x400);
if((p = ((bda[0x0F]<<8)| bda[0x0E]) << 4)){
if((mp = mpsearch1(p, 1024)))
return mp;
} else {
p = ((bda[0x14]<<8)|bda[0x13])*1024;
if((mp = mpsearch1(p-1024, 1024)))
return mp;
}
return mpsearch1(0xF0000, 0x10000);
}
// Search for an MP configuration table. For now,
// don't accept the default configurations (physaddr == 0).
// Check for correct signature, calculate the checksum and,
// if correct, check the version.
// To do: check extended table checksum.
static struct mpconf*
mpconfig(struct mp **pmp)
{
struct mpconf *conf;
struct mp *mp;
if((mp = mpsearch()) == 0 || mp->physaddr == 0)
return 0;
conf = (struct mpconf*) P2V((addr_t) mp->physaddr);
if(memcmp(conf, "PCMP", 4) != 0)
return 0;
if(conf->version != 1 && conf->version != 4)
return 0;
if(sum((uchar*)conf, conf->length) != 0)
return 0;
*pmp = mp;
return conf;
}
void
mpinit(void)
{
uchar *p, *e;
struct mp *mp;
struct mpconf *conf;
struct mpproc *mproc;
struct mpioapic *ioapic;
if((conf = mpconfig(&mp)) == 0) {
cprintf("No other CPUs found.\n");
return;
}
lapic = (uint*)P2V(conf->lapicaddr_p);
for(p=(uchar*)(conf+1), e=(uchar*)conf+conf->length; p<e; ){
switch(*p){
case MPPROC:
mproc = (struct mpproc*)p;
// Bit 0 is "usable". A disabled entry is a processor that is not
// there, and starting it means waiting for an answer that never comes.
if((mproc->flags & 0x01) && ncpu < NCPU) {
cpus[ncpu].apicid = mproc->apicid; // apicid may differ from ncpu
ncpu++;
}
p += sizeof(struct mpproc);
continue;
case MPIOAPIC:
ioapic = (struct mpioapic*)p;
if(ioapic_phys == IOAPIC_DEFAULT_PHYS || ioapic->addr_p == IOAPIC_DEFAULT_PHYS){
ioapicid = ioapic->apicno;
ioapic_phys = ioapic->addr_p;
}
p += sizeof(struct mpioapic);
continue;
case MPBUS:
case MPIOINTR:
case MPLINTR:
p += 8;
continue;
default:
panic("Major problem parsing mp config.");
break;
}
}
// "Seems we are" is doing a lot of work here, and the number is usually
// wrong. This walks the *legacy Intel MP table* (1994), which modern firmware
// fills in minimally or not at all -- QEMU/SeaBIOS emits exactly one
// processor entry regardless of -smp, because it expects the OS to enumerate
// CPUs from the ACPI MADT instead. Verified 2026-08-08: with -smp 4 the table
// is 208 bytes and contains one type-0 entry, then buses, an I/O APIC and
// interrupt assignments. So ncpu is 1 on QEMU no matter what, and SMP is
// silently never exercised there.
//
// See docs/architecture/boot.md -- this is half of the SMP bug, and the
// reason the other half (AP startup triple-faulting) cannot be reproduced
// under QEMU until the MADT is parsed.
cprintf("Seems we are SMP, ncpu = %d\n",ncpu);
if(mp->imcrp){
// Bochs doesn't support IMCR, so this doesn't run on Bochs.
// But it would on real hardware.
outb(0x22, 0x70); // Select IMCR
outb(0x23, inb(0x23) | 1); // Mask external interrupts.
}
}