kernel-fxtec-pro1x/Documentation/ia64
Xie XiuQi 83d435dd6e Fix example error_injection_tool
I got a "sched_setaffinity:: Invalid argument" error when using
err_injection_tool to inject error on a system with over 32 cpus.

Error information when injecting an error on a system with over 32 cpus:
$ ./err_injection_tool -i
/sys/devices/system/cpu/cpu0/err_inject//err_type_info
Begine at Tue Mar 26 11:20:08 2013
Configurations:
On cpu32: loop=10, interval=5(s) err_type_info=4101,err_struct_info=95
Error sched_setaffinity:: Invalid argument
All done

This because there is overflow when calculating the cpumask: the
type of (1<<k) is int, while mask[j] is unsigned long. When k > 31,
(1<<k) is truncated to ZERO, resulting in a unexpected cpumask.

Signed-off-by: Xie XiuQi <xiexiuqi@huawei.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
2013-04-02 09:39:55 -07:00
..
.gitignore
aliasing-test.c
aliasing.txt
efirtc.txt
err_inject.txt Fix example error_injection_tool 2013-04-02 09:39:55 -07:00
fsys.txt
IRQ-redir.txt
kvm.txt
Makefile
mca.txt
paravirt_ops.txt
README
serial.txt
xen.txt

        Linux kernel release 2.4.xx for the IA-64 Platform

   These are the release notes for Linux version 2.4 for IA-64
   platform.  This document provides information specific to IA-64
   ONLY, to get additional information about the Linux kernel also
   read the original Linux README provided with the kernel.

INSTALLING the kernel:

 - IA-64 kernel installation is the same as the other platforms, see
   original README for details.


SOFTWARE REQUIREMENTS

   Compiling and running this kernel requires an IA-64 compliant GCC
   compiler.  And various software packages also compiled with an
   IA-64 compliant GCC compiler.


CONFIGURING the kernel:

   Configuration is the same, see original README for details.


COMPILING the kernel:

 - Compiling this kernel doesn't differ from other platform so read
   the original README for details BUT make sure you have an IA-64
   compliant GCC compiler.

IA-64 SPECIFICS

 - General issues:

    o Hardly any performance tuning has been done. Obvious targets
      include the library routines (IP checksum, etc.). Less
      obvious targets include making sure we don't flush the TLB
      needlessly, etc.

    o SMP locks cleanup/optimization

    o IA32 support.  Currently experimental.  It mostly works.