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

mm: the loader jumped out from under itself, and 3 GB was never the limit

Browse source 
Three things, and the first one is the freeze.

**The loader jumped out from under itself.** A machine with a lot of RAM
stopped at "Starting the kernel" with the splash still up: no panic, no reset,
nothing. The firmware's own exception handler had the answer the whole time,
once a machine was found that printed it:

    X64 Exception Type - 0E(#PF - Page-Fault)
    ExceptionData - 0x10   I:1 P:0
    RIP - 0000000140004DEE      <- the loader's own code, at 5.4 GB
    RAX - 0000000000001000      <- the page tables it had just installed
    RCX - 00000000001000F0      <- the kernel it was about to jump to

I:1 P:0 is an instruction fetch from a page that is not present. The loader
built page tables covering four gigabytes, loaded cr3 -- and the firmware had
placed the loader image *above* four gigabytes, so the next instruction fetch
was unmapped. It reproduces exactly on `-m 8G` and never on `-m 1G`, which is
why every test here passed.

The PDPT is one page whether four entries are filled or all 512, so all 512
are: 512 GB of identity map, replaced by kvmalloc() a few hundred instructions
later.

**And 3 GB was never the limit, it was a circle.** PHYSTOP_MAX was 0xC0000000
because kvmalloc() mapped exactly four 1 GB pages, and kvmalloc mapped four
because that was the cap -- each holding the other up, throwing away thirteen
gigabytes of a sixteen gigabyte machine. kvmalloc now maps as many gigabytes as
the machine has RAM and tells ioremap where the direct map stopped, instead of
ioremap assuming it stopped at four.

Freeing memory becomes two passes, and the ordering is forced rather than
chosen: kinit1() runs *before* kvmalloc because kvmalloc calls kalloc for its
own page tables, and freeing a page means writing into it -- so kinit1 can only
touch what the loader mapped. kinit_high() adds the rest afterwards.
`phystop` and the new `lowtop` are now two different numbers: the DMA arena
stays below 4 GB because a device is not obliged to reach the top of memory,
and an RTL8139's buffer address register is thirty-two bits wide.

**And the 0 MB.** The System Information screen reported "0 MB usable" on a
machine with sixteen gigabytes in it, because memory_mb() had its own 16 KB
guess at how big a memory map gets, and returned zero when GetMemoryMap said
EFI_BUFFER_TOO_SMALL. That is the same bug as the previous commit's, in a
second copy, and this one failed silently. There is one buffer and one
map_read() now.

Verified at 1 GB, 8 GB and 16 GB: all three boot, no traps, no panics, socktest
and memfdtest green in each. 8 GB and 16 GB did not boot at all before -- and
16 GB now reports 17408 MB with "mem: 13312 MB above 4 GB added to the
allocator", where the old kernel would have used three. Both display
configurations still clean.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
Nexoniarz 2026-09-25 15:23:38 +02:00
commit 3b26575b4a
9 changed files with 246 additions and 55 deletions
Download patch file Download diff file Expand all files Collapse all files

56
kernel/arch/x86_64/e820.c
View file

@ -23,6 +23,11 @@
// than in some new way.
uint64 phystop = PHYSTOP_FALLBACK;
// The top of the low region. See memlayout.h: the DMA arena and everything
// kinit1() frees live below this, because that is all the loader's page tables
// map and all a 32-bit device can reach.
uint64 lowtop = PHYSTOP_FALLBACK;
#include "schboot.h" /* the hand-off block */
#define E820_USABLE 1
@ -44,6 +49,8 @@ assume_fallback(void)
mem_usable[0].base = EXTMEM;
mem_usable[0].end = PHYSTOP_FALLBACK;
nmem_usable = 1;
phystop = PHYSTOP_FALLBACK;
lowtop = PHYSTOP_FALLBACK;
}
struct e820entry {
@ -81,7 +88,7 @@ e820_init(void)
// 8 MB, and every byte above it was lost. kalloc now frees region by region,
// so the holes are skipped instead of being either freed or fatal.
uint64 largest = 0;
uint64 top = 0;
uint64 phys_top = 0, low_top = 0;
nmem_usable = 0;
for (uint32 i = 0; i < count; i++) {
if (e[i].type != E820_USABLE)
@ -91,7 +98,8 @@ e820_init(void)
uint64 base = (e[i].base + PGSIZE - 1) & ~(uint64)(PGSIZE - 1);
uint64 end = (e[i].base + e[i].length) & ~(uint64)(PGSIZE - 1);
// Above PHYSTOP_MAX the direct map is device memory, not RAM (see below).
// More than the direct map will ever cover. Clipped rather than refused:
// a machine with more RAM than this should use what it can.
if (end > PHYSTOP_MAX)
end = PHYSTOP_MAX;
if (base >= end)
@ -101,16 +109,23 @@ e820_init(void)
mem_usable[nmem_usable].end = end;
nmem_usable++;
// phystop comes from the largest region, not the highest. It has to be a
// region that can hold the DMA arena, which is carved off the top of
// PHYSTOP and must be physically contiguous; the largest is the only one
// that is certain to have room. A small usable region above it is left
// unfreed rather than raising the bound past a hole -- kfree() rejects
// anything at or above PHYSTOP, and that check is worth more than the
// stray page it costs.
if (end - base > largest) {
largest = end - base;
top = end;
// Two different questions, which used to be one and should not have been.
//
// `phystop` is how far RAM goes, and it is simply the highest end: kfree()
// uses it as a bound and kvmalloc() maps up to it.
if (end > phys_top)
phys_top = end;
// `lowtop` is where the DMA arena goes, and it has to be the largest
// region *below the boot direct map* -- contiguous, reachable by a 32-bit
// device, and mapped before kvmalloc has run. The largest such region is
// the only one certain to have room.
{
uint64 lo_end = end > DIRECTMAP_BOOT ? DIRECTMAP_BOOT : end;
if (base < lo_end && lo_end - base > largest) {
largest = lo_end - base;
low_top = lo_end;
}
}
}
@ -121,18 +136,12 @@ e820_init(void)
return;
}
// The PHYSTOP_MAX ceiling is applied per region above, when each one is
// clipped. kvmalloc() maps physical 0-4 GB with four 1 GB pages and marks the
// top one uncached because that is where PCI BARs and the framebuffer live,
// so 3 GB is the ceiling for anything the kernel will treat as RAM: above it
// the direct map either does not exist or is device memory that would be
// catastrophically slow to allocate from and is not ours to hand out.
// Below this the kernel image, its page tables and the DMA arena do not fit,
// and continuing produces a failure much harder to read than this line.
if (top < PHYSTOP_MIN) {
cprintf("e820: only %d MB usable; SchOS needs at least %d MB\n",
(int)(top / (1024 * 1024)), (int)(PHYSTOP_MIN / (1024 * 1024)));
if (low_top < PHYSTOP_MIN) {
cprintf("e820: only %d MB usable below 4 GB; SchOS needs at least %d MB "
"there\n",
(int)(low_top / (1024 * 1024)), (int)(PHYSTOP_MIN / (1024 * 1024)));
// Left at the fallback deliberately rather than lowered: a machine this
// small is going to fail, and it should fail having said why.
assume_fallback();
@ -154,7 +163,8 @@ e820_init(void)
return;
}
phystop = top;
phystop = phys_top;
lowtop = low_top;
// Report what is actually usable, not phystop: with a fragmented map those
// are different numbers, and printing the top address as though it were the

41
kernel/arch/x86_64/vm.c
View file

@ -32,6 +32,16 @@ _Static_assert(PERCPU_SELF == 0 && PERCPU_SCRATCH == 8 && PERCPU_CPU == 16 &&
"per-CPU block layout changed -- update kernel/arch/x86_64/trapasm.S");
static pml4e_t *kpml4;
// Where the device windows begin is now decided by kvmalloc(), which knows how
// much of the address space the direct map took. The constant that used to be
// here said 4, and would have handed out windows on top of RAM the moment the
// direct map grew past four gigabytes.
#define IOREMAP_LAST_PDPT 511
#define GIGABYTE (1ULL << 30)
// The first PDPT entry the direct map did not take. Set by kvmalloc().
static int ioremap_next = 4;
static pdpe_t *kpdpt;
struct tassdesc {
@ -231,14 +241,34 @@ kvmalloc(void)
kpml4[0] = v2p(kpdpt) | PTE_P | PTE_W;
kpml4[PMX(KERNBASE)] = v2p(kpdpt) | PTE_P | PTE_W;
for(uint64 i = 0; i < 4; i++) {
// As many gigabytes as the machine has RAM, not four.
//
// Four was the number for as long as PHYSTOP was capped at 3 GB, and the cap
// existed because this loop stopped at four -- each holding the other up. A
// laptop with sixteen gigabytes lost thirteen of them to that circle.
//
// The 3-4 GB entry stays uncached because that is where the PCI hole is and
// always has been. Everything above 4 GB is RAM -- the hole is below it on
// every machine this runs on -- so those are cached, and a device BAR up
// there still gets its own uncached window from ioremap().
uint64 gigs = (phystop + GIGABYTE - 1) / GIGABYTE;
if (gigs < 4)
gigs = 4; // always map the low four
if (gigs > IOREMAP_LAST_PDPT - 8)
gigs = IOREMAP_LAST_PDPT - 8; // leave room for device windows
for(uint64 i = 0; i < gigs; i++) {
uint64 flags = PTE_PS | PTE_P | PTE_W;
if(i >= 3) {
if(i == 3) {
flags |= PTE_PCD | PTE_PWT;
}
kpdpt[i] = (i << 30) | flags;
}
// ioremap takes what is left. It used to start at a constant 4, which was
// correct only while the direct map was exactly four gigabytes.
ioremap_next = (int)gigs;
switchkvm();
}
@ -261,11 +291,6 @@ kvmalloc(void)
// Cache-disabled and write-through, for the same reason the top GB of the
// direct map is: these are registers, and a write that sits in a cache line
// waiting for company is a write the device never sees.
#define IOREMAP_FIRST_PDPT 4
#define IOREMAP_LAST_PDPT 511
#define GIGABYTE (1ULL << 30)
static int ioremap_next = IOREMAP_FIRST_PDPT;
void *
ioremap(uint64 pa, uint64 size)
@ -285,7 +310,7 @@ ioremap(uint64 pa, uint64 size)
// Already mapped? A second BAR in the same gigabyte should not consume a
// second window, and drivers do re-map the same device.
for (int i = IOREMAP_FIRST_PDPT; i < ioremap_next; i++) {
for (int i = 4; i < ioremap_next; i++) {
// Clearing the low 30 bits drops every flag as well, leaving the frame.
if ((kpdpt[i] & PTE_P) && (kpdpt[i] & ~(GIGABYTE - 1)) == base)
return (void *)(KERNBASE + ((uint64)i << 30) + (pa - base));