Mark rdtsc as sync only for netburst, not for core2
PATCH 1/1 Mark rdtsc as sync only for netburst, not for core2
Hi,
On the Core2 cpus, the rdtsc instruction is not serializing (as defined in the architecture reference since rdtsc exists) and due to the deep speculation of these cores, it's possible that you can observe time go backwards between cores due to this speculation. Since the kernel already deals with this with the SYNC_RDTSC flag, the solution is simple, only assume that the instruction is serializing on family 15...
The price one pays for this is a slightly slower gettimeofday (by a dozen or two cycles), but that increase is quite small to pay for a really-going-forward tsc counter.
arch/x86_64/kernel/setup.c renamed from arch/x86_64/kernel/setup.c.org +4 -1
@@ -854,7 +854,10 @@ static void __cpuinit init_intel(structset_bit (X86_FEATURE_CONSTANT_TSC , &c->x86_capability);if (c->x86 ==6 )set_bit (X86_FEATURE_REP_GOOD , &c->x86_capability); -set_bit (X86_FEATURE_SYNC_RDTSC , &c->x86_capability); +if (c->x86 ==15 ) +set_bit (X86_FEATURE_SYNC_RDTSC , &c->x86_capability); +else +clear_bit (X86_FEATURE_SYNC_RDTSC , &c->x86_capability); c->x86_max_cores =intel_num_cpu_cores (c);srat_detect_node ();
Quoted 9 lines · Arjan van de Ven
Hi,
On the Core2 cpus, the rdtsc instruction is not serializing (as defined in the architecture reference since rdtsc exists) and due to the deep speculation of these cores, it's possible that you can observe time go backwards between cores due to this speculation. Since the kernel already deals with this with the
SYNC_RDTSCflag, the solution is simple, only assume that the instruction is serializing on family 15...
Quoted 3 lines
The price one pays for this is a slightly slower gettimeofday (by a dozen or two cycles), but that increase is quite small to pay for a really-going-forward tsc counter.
Added thanks
-Andi
A message that is not in the archive (sent off-list or not yet received): 1164774239.15257.5.camel@ymzhang
Quoted 2 lines · Yanmin
If it's a single processor, the go backwards issue doesn't exist. Below is my patch based on Arjan's. It's against 2.6.19-rc5-mm2.
Hi,
this patch is incorrect
arch/x86_64/kernel/setup.c static void __cpuinit init_intel(struct · line 865
Quoted 9 lines
arch/x86_64/kernel/setup.c +1
-1@@ -861,7 +861,7 @@ static void __cpuinit init_intel(structset_bit (X86_FEATURE_CONSTANT_TSC , &c->x86_capability);if (c->x86 ==6 )set_bit (X86_FEATURE_REP_GOOD , &c->x86_capability); -if (c->x86 ==15 ) +if (c->x86 ==15 &&num_possible_cpus () !=1 )set_bit (X86_FEATURE_SYNC_RDTSC , &c->x86_capability);
first of all, you probably meant "|| num_possible_cpus() == 1"
but second of all, the core2 cpus are dual core so.. .what does it bring you at all?
Quoted 24 lines · Arjan van de Ven
Quoted 2 lines · Yanmin
If it's a single processor, the go backwards issue doesn't exist. Below is my patch based on Arjan's. It's against 2.6.19-rc5-mm2.
Hi,
this patch is incorrect
arch/x86_64/kernel/setup.c static void __cpuinit init_intel(struct · line 865
Quoted 11 lines
---
linux-2.6.19-rc5-mm2_arjan/arch/x86_64/kernel/setup.c2006-11-29 10:41:21.000000000 +0800 +++ linux-2.6.19-rc5-mm2_arjan_fix/arch/x86_64/kernel/setup.c 2006-11-29 10:42:28.000000000 +0800arch/x86_64/kernel/setup.c renamed from arch/x86_64/kernel/setup.c.org +1
-1@@ -861,7 +861,7 @@ static void __cpuinit init_intel(structset_bit (X86_FEATURE_CONSTANT_TSC , &c->x86_capability);if (c->x86 ==6 )set_bit (X86_FEATURE_REP_GOOD , &c->x86_capability); -if (c->x86 ==15 ) +if (c->x86 ==15 &&num_possible_cpus () !=1 )set_bit (X86_FEATURE_SYNC_RDTSC , &c->x86_capability);first of all, you probably meant "||
num_possible_cpus()== 1"
Quoted 1 line
but second of all, the core2 cpus are dual core so.. .what does it bring you at all?
I guess you could boot with a UP kernel or maxcpus=1?
Signature · 2 lines
SUSE Labs, Novell Inc. Send instant messages to your online friends http://au.messenger.yahoo.com
Quoted 26 lines · Nick Piggin
Quoted 25 lines · Arjan van de Ven
Quoted 3 lines · Yanmin
If it's a single processor, the go backwards issue doesn't exist. Below is
my patch based on Arjan's. It's against 2.6.19-rc5-mm2.Hi,
this patch is incorrect
arch/x86_64/kernel/setup.c static void __cpuinit init_intel(struct · line 865
Quoted 11 lines
---
linux-2.6.19-rc5-mm2_arjan/arch/x86_64/kernel/setup.c2006-11-29 10:41:21.000000000 +0800 +++ linux-2.6.19-rc5-mm2_arjan_fix/arch/x86_64/kernel/setup.c 2006-11-29 10:42:28.000000000 +0800arch/x86_64/kernel/setup.c renamed from arch/x86_64/kernel/setup.c.org +1
-1@@ -861,7 +861,7 @@ static void __cpuinit init_intel(structset_bit (X86_FEATURE_CONSTANT_TSC , &c->x86_capability);if (c->x86 ==6 )set_bit (X86_FEATURE_REP_GOOD , &c->x86_capability); -if (c->x86 ==15 ) +if (c->x86 ==15 &&num_possible_cpus () !=1 )set_bit (X86_FEATURE_SYNC_RDTSC , &c->x86_capability);first of all, you probably meant "||
num_possible_cpus()== 1"
Quoted 4 lines
Quoted 2 lines
but second of all, the core2 cpus are dual core so.. .what does it bring you at all?
I guess you could boot with a UP kernel or maxcpus=1?
Yes, with the new patch. My reply email to Arjan was lost in LKML because my email client was crazy to set the email as HTML format.
Quoted 1 line
A message that is not in the archive (sent off-list or not yet received): 1164787104.2899.7.camel@ymzhang
Quoted 3 lines · Yanmin
Quoted 1 line
but second of all, the core2 cpus are dual core so.. .what does it bring you at all?
When there is only one cpu (or UP), the go backwards issue doesn't exist,
it does exist for single-socket dual core already. And core2 is dual core...
Quoted 3 lines
so
don't use cpuid here for UP. Another functioninit_amdalready does so.
not anymore.. that got fixed very recently...
(but you are right; on AMD the speculation is even bigger so there even on single core you need cpuid)
Quoted 6 lines · Arjan van de Ven
Quoted 4 lines · Yanmin
Quoted 2 lines
but second of all, the core2 cpus are dual core so.. .what does it bring you at all?
When there is only one cpu (or UP), the go backwards issue doesn't exist,
Quoted 7 lines
it does exist for single-socket dual core already. And core2 is dual core...
Quoted 3 lines
so
don't use cpuid here for UP. Another functioninit_amdalready does so.not anymore.. that got fixed very recently...
Thanks.
Quoted 2 lines
(but you are right; on AMD the speculation is even bigger so there even on single core you need cpuid)