nexoniarz/SchOS
nexoniarz/SchOS
Watch
1
0
Fork
You've already forked SchOS
 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions

smp: 64 processors, and say how many there are

Browse source 
NCPU was 16, under what a desktop has today. 64 costs 48 more TSS
I/O bitmaps and scheduler stacks, about 800 KB of BSS. Past 254 the
APIC would need x2APIC mode, which is a separate change.

With more than 16 there were two other ceilings. sched_getaffinity
wrote "CPU 0" and returned 0, and musl clears every byte past the
count returned -- so the mask came back empty and nproc, make -j and
sysconf(_SC_NPROCESSORS_ONLN) all said 1, on any machine. It returns
the mask of processors that started, and its size, now. And /proc
rendered every file into 2 KB, which /proc/cpuinfo ran out of at the
eighteenth processor without a word; /proc/pci, /proc/interrupts and
/proc/mounts were each one bigger machine from the same cut. There is
one 64 KB buffer for it now behind a sleeplock, since there is no
allocator for contiguous pages, and the generators that write raw
are given the real capacity instead of a constant.

Checked under QEMU with -smp 24: nproc 24, /proc/cpuinfo whole.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01S1giNvrHTrPMPw7V6x1kQ4
This commit is contained in:
Nexoniarz 2026-10-23 13:50:08 +02:00
commit c1af31f75a
5 changed files with 69 additions and 36 deletions
Download patch file Download diff file Expand all files Collapse all files

23
kernel/fs/procfs.c
View file

@ -53,12 +53,6 @@
// readable in a debugger, which matters more than density here.
// ---------------------------------------------------------------------------
// Size of the scratch buffer every generator renders into. Must stay equal to
// PROC_BUFSZ in kernel/dev/procfs.c: the SchFS and PCI generators there write
// up to PROC_BUFSZ regardless of the cap they are handed, so a smaller value
// here would be a buffer overrun rather than a truncation.
#define PROCFS_GENBUF 2048
#define PROCFS_ROOT 1ULL
#define PROCFS_GLOBAL 0x10000ULL
@ -378,15 +372,14 @@ procfs_read(struct inode *ip, int user_dst, uint64 dst, uint64 off, uint n)
return r;
}
// kmalloc, not kalloc: this buffer is PROCFS_GENBUF and kalloc's unit is a
// whole 4 KB page. The comment above about a page not being wasteful was
// written when a page was the only thing there was to ask for.
if ((buf = kmalloc(PROCFS_GENBUF)) == 0)
return -ENOMEM;
len = gen_file(ip->inum, buf, PROCFS_GENBUF);
// The shared buffer in kernel/dev/procfs.c, 64 KB, held until the copy out
// is done. It was 2 KB from kmalloc, which cut /proc/cpuinfo off at the
// eighteenth processor.
int cap;
buf = proc_genbuf_get(&cap);
len = gen_file(ip->inum, buf, cap);
if (off >= (uint64)len) {
kmfree(buf);
proc_genbuf_put();
return 0;
}
if (off + n > (uint64)len)
@ -400,7 +393,7 @@ procfs_read(struct inode *ip, int user_dst, uint64 dst, uint64 off, uint n)
memmove((char *)dst, buf + off, n);
}
kmfree(buf);
proc_genbuf_put();
return r;
}