[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20091120053609.GA6821@elte.hu>
Date: Fri, 20 Nov 2009 06:36:09 +0100
From: Ingo Molnar <mingo@...e.hu>
To: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Thomas Gleixner <tglx@...utronix.de>, Jeff Law <law@...hat.com>,
rostedt@...dmis.org, "H. Peter Anvin" <hpa@...or.com>,
David Daney <ddaney@...iumnetworks.com>,
Andrew Haley <aph@...hat.com>,
Richard Guenther <richard.guenther@...il.com>,
LKML <linux-kernel@...r.kernel.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Heiko Carstens <heiko.carstens@...ibm.com>,
feng.tang@...el.com, Fr??d??ric Weisbecker <fweisbec@...il.com>,
Peter Zijlstra <peterz@...radead.org>, jakub@...hat.com,
gcc@....gnu.org
Subject: Re: BUG: GCC-4.4.x changes the function frame on some functions
* Linus Torvalds <torvalds@...ux-foundation.org> wrote:
> [ Btw, looking at that, why are X86_L1_CACHE_BYTES and X86_L1_CACHE_SHIFT
> totally unrelated numbers? Very confusing. ]
incidentally (or maybe not so incidentally) that got fixed yesterday in
-tip - at around the time i triggered that crash:
350f8f5: x86: Eliminate redundant/contradicting cache line size config options
See the full commit below. The config that triggered the crash for me
has:
CONFIG_X86_L1_CACHE_SHIFT=4
so it's 16 bytes - and it's consistent now, which is a new angle. So i
think this explains why it stayed dormant for such a long time - it was
hidden by the cacheline-size config value inconsistencies.
Ingo
----------------->
>From 350f8f5631922c7848ec4b530c111cb8c2ff7caa Mon Sep 17 00:00:00 2001
From: Jan Beulich <JBeulich@...ell.com>
Date: Fri, 13 Nov 2009 11:54:40 +0000
Subject: [PATCH] x86: Eliminate redundant/contradicting cache line size config options
Rather than having X86_L1_CACHE_BYTES and X86_L1_CACHE_SHIFT
(with inconsistent defaults), just having the latter suffices as
the former can be easily calculated from it.
To be consistent, also change X86_INTERNODE_CACHE_BYTES to
X86_INTERNODE_CACHE_SHIFT, and set it to 7 (128 bytes) for NUMA
to account for last level cache line size (which here matters
more than L1 cache line size).
Finally, make sure the default value for X86_L1_CACHE_SHIFT,
when X86_GENERIC is selected, is being seen before that for the
individual CPU model options (other than on x86-64, where
GENERIC_CPU is part of the choice construct, X86_GENERIC is a
separate option on ix86).
Signed-off-by: Jan Beulich <jbeulich@...ell.com>
Acked-by: Ravikiran Thirumalai <kiran@...lex86.org>
Acked-by: Nick Piggin <npiggin@...e.de>
LKML-Reference: <4AFD5710020000780001F8F0@....id2.novell.com>
Signed-off-by: Ingo Molnar <mingo@...e.hu>
---
arch/x86/Kconfig.cpu | 14 +++++---------
arch/x86/boot/compressed/vmlinux.lds.S | 3 ++-
arch/x86/include/asm/cache.h | 7 ++++---
arch/x86/kernel/vmlinux.lds.S | 10 +++++-----
arch/x86/mm/tlb.c | 3 ++-
5 files changed, 18 insertions(+), 19 deletions(-)
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index f2824fb..621f2bd 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -301,15 +301,11 @@ config X86_CPU
#
# Define implied options from the CPU selection here
-config X86_L1_CACHE_BYTES
+config X86_INTERNODE_CACHE_SHIFT
int
- default "128" if MPSC
- default "64" if GENERIC_CPU || MK8 || MCORE2 || MATOM || X86_32
-
-config X86_INTERNODE_CACHE_BYTES
- int
- default "4096" if X86_VSMP
- default X86_L1_CACHE_BYTES if !X86_VSMP
+ default "12" if X86_VSMP
+ default "7" if NUMA
+ default X86_L1_CACHE_SHIFT
config X86_CMPXCHG
def_bool X86_64 || (X86_32 && !M386)
@@ -317,9 +313,9 @@ config X86_CMPXCHG
config X86_L1_CACHE_SHIFT
int
default "7" if MPENTIUM4 || MPSC
+ default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
default "4" if X86_ELAN || M486 || M386 || MGEODEGX1
default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
- default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
config X86_XADD
def_bool y
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index f4193bb..a6f1a59 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -4,6 +4,7 @@ OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT)
#undef i386
+#include <asm/cache.h>
#include <asm/page_types.h>
#ifdef CONFIG_X86_64
@@ -46,7 +47,7 @@ SECTIONS
*(.data.*)
_edata = . ;
}
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+ . = ALIGN(L1_CACHE_BYTES);
.bss : {
_bss = . ;
*(.bss)
diff --git a/arch/x86/include/asm/cache.h b/arch/x86/include/asm/cache.h
index 549860d..2f9047c 100644
--- a/arch/x86/include/asm/cache.h
+++ b/arch/x86/include/asm/cache.h
@@ -9,12 +9,13 @@
#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+#define INTERNODE_CACHE_SHIFT CONFIG_X86_INTERNODE_CACHE_SHIFT
+#define INTERNODE_CACHE_BYTES (1 << INTERNODE_CACHE_SHIFT)
+
#ifdef CONFIG_X86_VSMP
-/* vSMP Internode cacheline shift */
-#define INTERNODE_CACHE_SHIFT (12)
#ifdef CONFIG_SMP
#define __cacheline_aligned_in_smp \
- __attribute__((__aligned__(1 << (INTERNODE_CACHE_SHIFT)))) \
+ __attribute__((__aligned__(INTERNODE_CACHE_BYTES))) \
__page_aligned_data
#endif
#endif
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index fd2dabe..eeb4f5f 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -135,13 +135,13 @@ SECTIONS
PAGE_ALIGNED_DATA(PAGE_SIZE)
- CACHELINE_ALIGNED_DATA(CONFIG_X86_L1_CACHE_BYTES)
+ CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
DATA_DATA
CONSTRUCTORS
/* rarely changed data like cpu maps */
- READ_MOSTLY_DATA(CONFIG_X86_INTERNODE_CACHE_BYTES)
+ READ_MOSTLY_DATA(INTERNODE_CACHE_BYTES)
/* End of data section */
_edata = .;
@@ -165,12 +165,12 @@ SECTIONS
*(.vsyscall_0)
} :user
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+ . = ALIGN(L1_CACHE_BYTES);
.vsyscall_fn : AT(VLOAD(.vsyscall_fn)) {
*(.vsyscall_fn)
}
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+ . = ALIGN(L1_CACHE_BYTES);
.vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data)) {
*(.vsyscall_gtod_data)
}
@@ -194,7 +194,7 @@ SECTIONS
}
vgetcpu_mode = VVIRT(.vgetcpu_mode);
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+ . = ALIGN(L1_CACHE_BYTES);
.jiffies : AT(VLOAD(.jiffies)) {
*(.jiffies)
}
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 36fe08e..65b58e4 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -8,6 +8,7 @@
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
+#include <asm/cache.h>
#include <asm/apic.h>
#include <asm/uv/uv.h>
@@ -43,7 +44,7 @@ union smp_flush_state {
spinlock_t tlbstate_lock;
DECLARE_BITMAP(flush_cpumask, NR_CPUS);
};
- char pad[CONFIG_X86_INTERNODE_CACHE_BYTES];
+ char pad[INTERNODE_CACHE_BYTES];
} ____cacheline_internodealigned_in_smp;
/* State is put into the per CPU data section, but padded
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists