linux_dsm_epyc7002/arch
Hirokazu Takata cf535ea52e [PATCH] m32r: update sys_tas() routine
This patch updates and fixes sys_tas() routine for m32r.

In the previous implementation, a lockup rarely caused at sys_tas()
routine in SMP environment.

> > The problem is that touching *addr will generate an oops if that page isn't
> > paged in.  If we convert it to use get_user() then that's an improvement,
> > but we must not run get_user() under spinlock or local_irq_disable().

I rewrote sys_tas() routine by using "lock -> unlock" instructions, and
utilizing the m32r's interrupt handling characteristics; the m32r processor
can accept interrupts only at the 32-bit instruction boundary.  So, the
"unlock" instruction can be executed continuously after the "lock"
instruction execution without any interruptions.

In addition, to solve such a page_fault problem, I use a fixup code like
get_user().

And, as for the kernel lockup problem, we found that a calling
do_page_fault() routine with disabling interrupts might cause a lockup at
flush_tlb_others(), because we checked a completion of IPI handler's
operations in a spin-locked critical section.

Therefore, by using "lock -> unlock" code, we can implement the sys_tas()
rouitine without disabling interrupts explicitly, then no lockups would
happen at flush_tlb_others(), I hope.

Compile check and some working test in SMP environment have done.

Signed-off-by: Hirokazu Takata <takata@linux-m32r.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-02-20 20:00:12 -08:00
..
alpha [PATCH] alpha: set cpu_possible_map much earlier 2006-02-08 07:57:37 -08:00
arm [ARM] 3338/1: old ABI compat: sys_socketcall 2006-02-16 22:36:13 +00:00
arm26 [PATCH] arm26: select BLK_DEV_FD only on A5K 2006-02-01 08:53:22 -08:00
cris [PATCH] fallout from ptrace consolidation patch: cris/arch-v10 2006-02-07 20:57:19 -05:00
frv [PATCH] FRV: Use virtual interrupt disablement 2006-02-14 16:09:35 -08:00
h8300 [PATCH] hrtimer: round up relative start time on low-res arches 2006-02-14 16:09:35 -08:00
i386 [PATCH] i386: need to pass virtual address to smp_read_mpc() 2006-02-20 20:00:09 -08:00
ia64 [IA64] Count disabled cpus as potential hot-pluggable CPUs 2006-02-16 14:10:50 -08:00
m32r [PATCH] m32r: update sys_tas() routine 2006-02-20 20:00:12 -08:00
m68k [PATCH] hrtimer: round up relative start time on low-res arches 2006-02-14 16:09:35 -08:00
m68knommu [PATCH] hrtimer: round up relative start time on low-res arches 2006-02-14 16:09:35 -08:00
mips [MIPS] Fix typo in _sys32_rt_sigreturn and _sysn32_rt_sigreturn. 2006-02-14 19:13:26 +00:00
parisc [PATCH] hrtimer: round up relative start time on low-res arches 2006-02-14 16:09:35 -08:00
powerpc [PATCH] powermac: Fix loss of ethernet PHY on sleep 2006-02-20 20:00:11 -08:00
ppc ppc: Use the system call table from arch/powerpc/kernel/systbl.S 2006-02-10 16:02:20 +11:00
s390 [PATCH] s390: sys32_fstatat -> sys32_fstatat64 2006-02-17 13:59:27 -08:00
sh [PATCH] arch/sh/Kconfig: fix the ISA_DMA_API dependencies 2006-02-17 13:59:26 -08:00
sh64 [PATCH] drive_info removal outside of arch/i386 2006-02-07 20:56:47 -05:00
sparc [SPARC]: sys_newfstatat --> sys_fstatat64 2006-02-12 23:30:11 -08:00
sparc64 [SPARC]: sys_newfstatat --> sys_fstatat64 2006-02-12 23:30:11 -08:00
um [PATCH] uml: remove a dead file 2006-02-07 16:12:32 -08:00
v850 [PATCH] hrtimer: round up relative start time on low-res arches 2006-02-14 16:09:35 -08:00
x86_64 [PATCH] x86_64: Don't set CONFIG_DEBUG_INFO in defconfig 2006-02-20 20:00:10 -08:00
xtensa [PATCH] Fix some ucLinux breakage from the tty updates 2006-02-03 08:32:04 -08:00