Re: Increasing KVM on amd64



On Sun, Jun 08, 2008 at 12:39:43AM -0500, Alan Cox wrote:
Kostik Belousov wrote:

On Sat, Jun 07, 2008 at 06:59:35PM -0500, Alan Cox wrote:


You can download a patch from
http://www.cs.rice.edu/~alc/amd64_kvm_6GB.patch that increases amd64's
kernel virtual address space to 6GB. This patch also increases the
default for the kmem map to almost 2GB. I believe that kernel loadable
modules still work. However, I suspect that mini-dumps are broken.


The amd64 modules text/data/bss virtual addresses are allocated from the
kernel_map (link_elf_obj.c, link_elf_load_file). Now, the lower end
of the kernel_map is top-6Gb.

Kernel code (both kernel proper and modules) is compiled for "kernel memory
model", according to the gcc info:
`-mcmodel=kernel'
Generate code for the kernel code model. The kernel runs in the
negative 2 GB of the address space. This model has to be used for
Linux kernel code.

I suspect we have a problem there.




The change to link_elf_obj.c is supposed to ensure allocation of an
address in the upper 2GB of the kernel map for the module.

Ah, I overlooked it, sorry.

Attachment: pgpygdKcbdjZU.pgp
Description: PGP signature



Relevant Pages

  • Re: [RFC: 2.6 patch] let GROUP_SCHED depend on BROKEN
    ... kernel developers. ... you've never before written a _single_ Linux kernel feature ... have no desire _at all_ to write true kernel code. ... the level of trivialities. ...
    (Linux-Kernel)
  • Re: [patch 4/4] KVM-trace port to tracepoints
    ... Tracepoints allow dormat instrumentation, like the kernel markers, but also ... This patch depends on the "Tracepoints" patch. ... Is it a specific property of KVM-trace that causes this LOC blow-up? ... strings into the kernel code, which, to some, looks like debugging code. ...
    (Linux-Kernel)
  • Re: Kernel oops with 2.6.26, padlock and ipsec: probably problem with fpu state changes
    ... If XCRYPT may be interrupted and the interrupt code again uses this optimized ... How could any kernel code use MMX/SSE/FPU when the interrupt case isn't ... Or is your argument that its lazy allocation itself is the problem: ... If this were right than any kernel code executing SSE may trigger now a oops ...
    (Linux-Kernel)
  • Re: When was /dev/cua* depreciated?
    ... so it has a kernel module in it. ... The installer shell script has no shebang at the top. ... so perhaps they no what needs to be done for the kernel code. ... to the serial/ethernet converter on the network, ...
    (uk.comp.os.linux)
  • Re: 2.6.6-rc3-mm2 (4KSTACK)
    ... It won't break applications it will break kernel first. ... You need to fix kernel code not the user space. ... > And what better way to detect it than to release it in a stable kernel. ... [BTW wasn't the corruption only seen with nvidia module? ...
    (Linux-Kernel)