Previously, AcpiOsMemory was using pmap_mapbios which would always map
the requested address Write-Back (WB). For several AMD Ryzen laptops,
the BIOS uses AcpiOsMemory to directly access the PCI MCFG region in
order to access PCI config registers. This has the side effect of
remapping the MCFG region in the direct map as WB instead of UC
hanging the laptops during boot.
On the one laptop I examined in detail, the _PIC global method used to
switch from 8259A PICs to I/O APICs uses a pair of PCI config space
registers at offset 0x84 in the device at 0:0:0 to as a pair of
address/data registers to access an indirect register in the chipset
and clear a single bit to switch modes.
To fix, alter the semantics of pmap_mapbios() such that it does not
modify the attributes of any existing mappings and instead uses the
existing attributes. If a new mapping is created, this new mapping
uses WB (the default memory attribute).
Special thanks to the gentleman whose name I don't have who brought
two affected laptops to the hacker lounge at BSDCan. Direct access to
the affected systems permitted finding the root cause within an hour
or so.
PR: 231760, 236899
Reviewed by: kib, alc
MFC after: 2 weeks
Differential Revision: https://reviews.freebsd.org/D20327
Effectively all i386 kernels now have two pmaps compiled in: one
managing PAE pagetables, and another non-PAE. The implementation is
selected at cold time depending on the CPU features. The vm_paddr_t is
always 64bit now. As result, nx bit can be used on all capable CPUs.
Option PAE only affects the bus_addr_t: it is still 32bit for non-PAE
configs, for drivers compatibility. Kernel layout, esp. max kernel
address, low memory PDEs and max user address (same as trampoline
start) are now same for PAE and for non-PAE regardless of the type of
page tables used.
Non-PAE kernel (when using PAE pagetables) can handle physical memory
up to 24G now, larger memory requires re-tuning the KVA consumers and
instead the code caps the maximum at 24G. Unfortunately, a lot of
drivers do not use busdma(9) properly so by default even 4G barrier is
not easy. There are two tunables added: hw.above4g_allow and
hw.above24g_allow, the first one is kept enabled for now to evaluate
the status on HEAD, second is only for dev use.
i386 now creates three freelists if there is any memory above 4G, to
allow proper bounce pages allocation. Also, VM_KMEM_SIZE_SCALE changed
from 3 to 1.
The PAE_TABLES kernel config option is retired.
In collaboarion with: pho
Discussed with: emaste
Reviewed by: markj
MFC after: 2 weeks
Sponsored by: The FreeBSD Foundation
Differential revision: https://reviews.freebsd.org/D18894