1
linux/arch/i386
James Cleverdon 6004e1b7ef [PATCH] i386/x86-64: Share interrupt vectors when there is a large number of interrupt sources
Here's a patch that builds on Natalie Protasevich's IRQ compression
patch and tries to work for MPS boots as well as ACPI.  It is meant for
a 4-node IBM x460 NUMA box, which was dying because it had interrupt
pins with GSI numbers > NR_IRQS and thus overflowed irq_desc.

The problem is that this system has 270 GSIs (which are 1:1 mapped with
I/O APIC RTEs) and an 8-node box would have 540.  This is much bigger
than NR_IRQS (224 for both i386 and x86_64).  Also, there aren't enough
vectors to go around.  There are about 190 usable vectors, not counting
the reserved ones and the unused vectors at 0x20 to 0x2F.  So, my patch
attempts to compress the GSI range and share vectors by sharing IRQs.

Cc: "Protasevich, Natalie" <Natalie.Protasevich@unisys.com>

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-14 19:55:13 -08:00
..
boot [PATCH] fbdev: Resurrect hooks to get EDID from firmware 2005-09-09 13:57:59 -07:00
crypto [PATCH] arch/i386/crypto/aes.c: fix sparse warnings 2005-06-25 16:24:59 -07:00
kernel [PATCH] i386/x86-64: Share interrupt vectors when there is a large number of interrupt sources 2005-11-14 19:55:13 -08:00
lib [LIB]: Consolidate _atomic_dec_and_lock() 2005-09-14 21:47:01 -07:00
mach-default [PATCH] useless includes of linux/irq.h in arch/i386 2005-09-26 18:29:50 -07:00
mach-es7000 [PATCH] ES7000 platform update 2005-10-30 17:37:12 -08:00
mach-generic [PATCH] x86: sutomatically enable bigsmp when we have more than 8 CPUs 2005-09-05 00:06:10 -07:00
mach-visws [PATCH] useless includes of linux/irq.h in arch/i386 2005-09-26 18:29:50 -07:00
mach-voyager [PATCH] useless includes of linux/irq.h in arch/i386 2005-09-26 18:29:50 -07:00
math-emu [PATCH] i386: inline assembler: cleanup and encapsulate descriptor and task register management 2005-09-05 00:06:11 -07:00
mm [PATCH] x86: add an accessor function for getting the per-CPU gdt 2005-10-30 17:37:12 -08:00
oprofile [PATCH] mm: kill check_user_page_readable 2005-10-29 21:40:41 -07:00
pci [PATCH] toshiba_ohci1394_dmi_table should be __devinitdata, not __devinit 2005-11-01 21:27:22 -08:00
power [PATCH] FPU context corrupted after resume 2005-10-30 17:37:11 -08:00
defconfig [ACPI] delete CONFIG_ACPI_PCI 2005-08-25 12:40:44 -04:00
Kconfig [PATCH] i386: CONFIG_PC removal 2005-10-31 09:20:54 -08:00
Kconfig.cpu [PATCH] uml: reuse i386 cpu-specific tuning 2005-10-30 17:37:16 -08:00
Kconfig.debug [PATCH] i386: add missing Kconfig help text 2005-07-27 16:25:58 -07:00
Makefile [PATCH] uml: reuse i386 cpu-specific tuning 2005-10-30 17:37:16 -08:00
Makefile.cpu [PATCH] i386: use -mcpu, not -mtune, for GCCs older than 3.4 2005-10-30 17:37:16 -08:00