linux_dsm_epyc7002/arch/x86
Dave Hansen 5dfd486c47 x86, kvm: Fix kvm's use of __pa() on percpu areas
In short, it is illegal to call __pa() on an address holding
a percpu variable.  This replaces those __pa() calls with
slow_virt_to_phys().  All of the cases in this patch are
in boot time (or CPU hotplug time at worst) code, so the
slow pagetable walking in slow_virt_to_phys() is not expected
to have a performance impact.

The times when this actually matters are pretty obscure
(certain 32-bit NUMA systems), but it _does_ happen.  It is
important to keep KVM guests working on these systems because
the real hardware is getting harder and harder to find.

This bug manifested first by me seeing a plain hang at boot
after this message:

	CPU 0 irqstacks, hard=f3018000 soft=f301a000

or, sometimes, it would actually make it out to the console:

[    0.000000] BUG: unable to handle kernel paging request at ffffffff

I eventually traced it down to the KVM async pagefault code.
This can be worked around by disabling that code either at
compile-time, or on the kernel command-line.

The kvm async pagefault code was injecting page faults in
to the guest which the guest misinterpreted because its
"reason" was not being properly sent from the host.

The guest passes a physical address of an per-cpu async page
fault structure via an MSR to the host.  Since __pa() is
broken on percpu data, the physical address it sent was
bascially bogus and the host went scribbling on random data.
The guest never saw the real reason for the page fault (it
was injected by the host), assumed that the kernel had taken
a _real_ page fault, and panic()'d.  The behavior varied,
though, depending on what got corrupted by the bad write.

Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20130122212435.4905663F@kernel.stglabs.ibm.com
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2013-01-25 16:34:55 -08:00
..
boot x86, efi: correct precedence of operators in setup_efi_pci 2012-12-20 11:47:14 -08:00
configs x86/Kconfig: Turn off DEBUG_NX_TEST module in defconfigs 2012-09-05 10:43:12 +02:00
crypto Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 2012-12-15 12:35:19 -08:00
ia32 new helpers: __save_altstack/__compat_save_altstack, switch x86 and um to those 2012-12-19 18:07:41 -05:00
include x86, mm: Create slow_virt_to_phys() 2013-01-25 16:33:23 -08:00
kernel x86, kvm: Fix kvm's use of __pa() on percpu areas 2013-01-25 16:34:55 -08:00
kvm KVM: x86: use dynamic percpu allocations for shared msrs area 2013-01-08 12:51:56 -02:00
lguest Linux 3.8-rc5 2013-01-25 16:31:21 -08:00
lib X86: drivers: remove __dev* attributes. 2013-01-03 15:57:04 -08:00
math-emu x86: Rename trap_no to trap_nr in thread_struct 2012-03-13 06:24:09 +01:00
mm x86, mm: Create slow_virt_to_phys() 2013-01-25 16:33:23 -08:00
net x86: bpf_jit_comp: add vlan tag support 2012-10-31 14:00:15 -04:00
oprofile oprofile, x86: Fix wrapping bug in op_x86_get_ctrl() 2012-10-15 14:38:24 +02:00
pci X86: drivers: remove __dev* attributes. 2013-01-03 15:57:04 -08:00
platform Linux 3.8-rc5 2013-01-25 16:31:21 -08:00
power x86, topology: Debug CPU0 hotplug 2012-11-14 15:28:11 -08:00
realmode Revert "x86, mm: Include the entire kernel memory map in trampoline_pgd" 2012-12-15 12:29:54 -08:00
syscalls Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/signal 2012-12-20 18:05:28 -08:00
tools x86: Fix the error of using "const" in gen-insn-attr-x86.awk 2012-12-10 10:31:24 -08:00
um Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/signal 2012-12-20 18:05:28 -08:00
vdso Merge tag 'kvm-3.8-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm 2012-12-13 15:31:08 -08:00
video x86: Use vga_default_device() when determining whether an fb is primary 2012-04-24 09:50:17 +01:00
xen Fixes: 2013-01-18 12:02:52 -08:00
.gitignore x86/kprobes: Add arch/x86/tools/insn_sanity to .gitignore 2012-01-16 08:21:59 +01:00
Kbuild x86, realmode: realmode.bin infrastructure 2012-05-08 11:41:48 -07:00
Kconfig Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/signal 2012-12-20 18:05:28 -08:00
Kconfig.cpu x86, 386 removal: Document Nx586 as a 386 and thus unsupported 2012-11-29 13:28:39 -08:00
Kconfig.debug x86/tlb: add tlb_flushall_shift knob into debugfs 2012-06-27 19:29:10 -07:00
Makefile md update for 3.8 2012-12-18 09:32:44 -08:00
Makefile_32.cpu x86, 386 removal: Remove CONFIG_M386 from Kconfig 2012-11-29 13:23:01 -08:00
Makefile.um um: fix linker script generation 2012-04-09 13:59:00 -04:00