linux/arch/x86_64
Andi Kleen 1584b89c92 [PATCH] x86_64: Validate SLIT table
A lot of Opteron BIOS just pass 10 in all SLIT entries (10 is the
normalized unit). This is actually worse than the default heuristic
because it leads to pci_distance not knowing the difference between
local and remote nodes anymore. This messes up some NUMA
heuristics in generic code.

In this case it's better to fall back to the default heuristic
which just does nodea == nodeb ? 10 : 20.

This patch does some basic sanity checking on the SLIT and only accepts
the SLIT when it passes.

Invariants enforced are:
- Node to itself shall be 10
- Any other distance shouldn't be 10
- Distances smaller than 10 are illegal

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-11 19:04:51 -08:00
..
boot Merge ssh://master.kernel.org/pub/scm/linux/kernel/git/sam/kbuild 2006-01-10 08:21:33 -08:00
crypto [CRYPTO] Allow AES C/ASM implementations to coexist 2006-01-09 14:15:39 -08:00
ia32 [PATCH] x86_64: fix single step handling for 32bit processes 2006-01-11 19:04:50 -08:00
kernel [PATCH] x86_64: Generalize DMI and enable for x86-64 2006-01-11 19:04:51 -08:00
lib [PATCH] x86_64: Remove optimization for B stepping AMD K8 2005-11-14 19:55:17 -08:00
mm [PATCH] x86_64: Validate SLIT table 2006-01-11 19:04:51 -08:00
oprofile [PATCH] Move Kprobes and Oprofile to "Instrumentation Support" menu 2005-11-07 07:53:35 -08:00
pci [PATCH] x86_64: Remove bogus file in arch/x86_64/pci 2006-01-11 19:04:51 -08:00
Kconfig [PATCH] x86_64: Generalize DMI and enable for x86-64 2006-01-11 19:04:51 -08:00
Kconfig.debug [PATCH] x86/x86_64: mark rodata section read-only: x86-64 support 2006-01-06 08:33:36 -08:00
Makefile [PATCH] x86_64: Separate CONFIG_UNWIND_INFO from CONFIG_DEBUG_INFO 2006-01-11 19:01:10 -08:00
defconfig [PATCH] x86_64: Update defconfig 2006-01-11 19:01:09 -08:00