Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1373496
| From | Mathieu Desnoyers <mathieu.desnoyers@efficios.com> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread |
| Date | 2016-04-07 18:00 +0200 |
| Message-ID | <rlkvE-692-1@gated-at.bofh.it> (permalink) |
| References | (3 earlier) <rlfvY-2qa-1@gated-at.bofh.it> <rlfvY-2qa-15@gated-at.bofh.it> <rlgin-34z-19@gated-at.bofh.it> <rlgV6-3zm-59@gated-at.bofh.it> <rlheq-3Ig-21@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
----- On Apr 7, 2016, at 8:25 AM, Peter Zijlstra peterz@infradead.org wrote:
> On Thu, Apr 07, 2016 at 02:03:53PM +0200, Florian Weimer wrote:
>> > struct tlabi {
>> > union {
>> > __u8[64] __foo;
>> > struct {
>> > /* fields go here */
>> > };
>> > };
>> > } __aligned__(64);
>>
>> That's not really “fixed size” as far as an ABI is concerned, due to the
>> possibility of future extensions.
>
> sizeof(struct tlabi) is always the same, right? How is that not fixed?
>
>> > People objected against the fixed size scheme, but it being possible to
>> > get a fixed TCB offset and reduce indirections is a big win IMO.
>>
>> It's a difficult trade-off. It's not an indirection as such, it's avoid
>> loading the dynamic TLS offset.
>
> What we _want_ is being able to use %[gf]s:offset and have it work (I
> forever forget which segment register userspace TLS uses).
>
>> Let me repeat that the ELF TLS GNU ABI has very limited support for
>> static offsets at present, and it is difficult to make them available
>> more widely without code generation at run time (in the form of text
>> relocations, but still).
>
> Do you have a pointer to something I can read? Because I'm clearly not
> understanding the full issue here.
For what is is worth, here are a couple of objdump snippet of my
test program without and with -fPIC:
* Compiled with -O2, *without* -fPIC, x86-64:
__thread __attribute__((weak)) volatile struct thread_local_abi __thread_local_abi;
static
int32_t read_cpu_id(void)
{
if (unlikely(!(__thread_local_abi.features & TLABI_FEATURE_CPU_ID)))
40064e: 64 8b 04 25 c0 ff ff mov %fs:0xffffffffffffffc0,%eax
400655: ff
400656: a8 01 test $0x1,%al
400658: 74 71 je 4006cb <main+0xab>
return sched_getcpu();
return __thread_local_abi.cpu_id;
40065a: 64 8b 14 25 c4 ff ff mov %fs:0xffffffffffffffc4,%edx
400661: ff
}
* Compiled with -O2, with -fPIC, x86_64:
__thread __attribute__((weak)) volatile struct thread_local_abi __thread_local_abi;
4006de: 64 48 8b 04 25 00 00 mov %fs:0x0,%rax
4006e5: 00 00
static
int32_t read_cpu_id(void)
{
if (unlikely(!(__thread_local_abi.features & TLABI_FEATURE_CPU_ID)))
4006e7: 48 8d 80 c0 ff ff ff lea -0x40(%rax),%rax
4006ee: 8b 10 mov (%rax),%edx
4006f0: 83 e2 01 and $0x1,%edx
4006f3: 0f 84 80 00 00 00 je 400779 <main+0xc9>
return sched_getcpu();
return __thread_local_abi.cpu_id;
4006f9: 8b 50 04 mov 0x4(%rax),%edx
}
So with -fPIC (libraries), TLS adds an extra indirection. However,
it just needs to load the base address once, and can then access
both "features" and "cpu_id" fields as offsets from that base.
For executables compiled without -fPIC, there is no indirection.
This justifies the following paragraph in the proposed man page:
The symbol __thread_local_abi is recommended to be used across
libraries and applications wishing to register a the thread-local
ABI structure for tlabi_nr 0. The attribute "weak" is recommended
when declaring this variable in libraries. Applications can
choose to define their own version of this symbol without the weak
attribute as a performance improvement.
Thoughts ?
Thanks,
Mathieu
--
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[RFC PATCH v6 0/5] Thread-local ABI system call (CPU number cache) Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-04-04 19:10 +0200
[RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-04-04 19:10 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread "H. Peter Anvin" <hpa@zytor.com> - 2016-04-04 19:20 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-04-04 21:50 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-04-04 22:50 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Florian Weimer <fweimer@redhat.com> - 2016-04-05 18:10 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Peter Zijlstra <peterz@infradead.org> - 2016-04-05 18:50 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Florian Weimer <fweimer@redhat.com> - 2016-04-07 11:10 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Peter Zijlstra <peterz@infradead.org> - 2016-04-07 12:40 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Florian Weimer <fweimer@redhat.com> - 2016-04-07 12:40 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Peter Zijlstra <peterz@infradead.org> - 2016-04-07 13:30 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Florian Weimer <fweimer@redhat.com> - 2016-04-07 14:10 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Peter Zijlstra <peterz@infradead.org> - 2016-04-07 14:30 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Florian Weimer <fweimer@redhat.com> - 2016-04-07 14:40 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-04-07 18:00 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-04-07 14:40 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Linus Torvalds <torvalds@linux-foundation.org> - 2016-04-07 18:40 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Andy Lutomirski <luto@amacapital.net> - 2016-04-07 18:50 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Linus Torvalds <torvalds@linux-foundation.org> - 2016-04-07 19:00 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Florian Weimer <fweimer@redhat.com> - 2016-04-07 19:00 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Linus Torvalds <torvalds@linux-foundation.org> - 2016-04-07 19:00 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-04-07 20:50 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Andi Kleen <andi@firstfloor.org> - 2016-04-07 22:30 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-04-07 23:00 +0200
Re: [RFC PATCH v6 1/5] Thread-local ABI system call: cache CPU number of running thread Florian Weimer <fweimer@redhat.com> - 2016-04-07 12:50 +0200
[RFC PATCH v6 5/5] Thread-local ABI: wire up x86 32/64 system call Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-04-04 19:10 +0200
[RFC PATCH v6 3/5] Thread-local ABI: wire up ARM system call Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-04-04 19:10 +0200
[RFC PATCH v6 4/5] Thread-local ABI cpu_id: x86 32/64 resume notifier Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-04-04 19:10 +0200
csiph-web