public inbox for libc-alpha@sourceware.org
 help / color / mirror / Atom feed
From: Michael Jeanson <mjeanson@efficios.com>
To: libc-alpha@sourceware.org
Cc: Michael Jeanson <mjeanson@efficios.com>,
	Florian Weimer <fweimer@redhat.com>,
	Carlos O'Donell <carlos@redhat.com>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Subject: [PATCH v7 8/8] Linux: Use rseq to accelerate getcpu
Date: Thu,  1 Feb 2024 14:36:48 -0500	[thread overview]
Message-ID: <20240201193648.584917-9-mjeanson@efficios.com> (raw)
In-Reply-To: <20240201193648.584917-1-mjeanson@efficios.com>

On architectures that implement rseq_load32_load32_relaxed() (and thus
define RSEQ_HAS_LOAD32_LOAD32_RELAXED), when the node_id feature is
available, use rseq to fetch the cpu_id and node_id atomically with
respect to preemption and signal delivery to speed up getcpu() compared
to a vsyscall or system call implementation.

Loading both cpu_id and node_id atomically with respect to preemption
is required to ensure consistency of the topology mapping between cpu_id
and node_id due to migration between both loads.

On an aarch64 system (Snapdragon 8cx Gen 3) which lacks a vDSO for
getcpu() we measured an improvement from 130 ns to 1 ns while on x86_64
(i7-8550U) which has a vDSO we measured a more modest improvement from
10 ns to 2 ns.

Co-authored-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
---
 sysdeps/unix/sysv/linux/getcpu.c | 32 ++++++++++++++++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

diff --git a/sysdeps/unix/sysv/linux/getcpu.c b/sysdeps/unix/sysv/linux/getcpu.c
index 0e7c3238c9..7e34d6d1eb 100644
--- a/sysdeps/unix/sysv/linux/getcpu.c
+++ b/sysdeps/unix/sysv/linux/getcpu.c
@@ -19,9 +19,10 @@
 #include <sched.h>
 #include <sysdep.h>
 #include <sysdep-vdso.h>
+#include <rseq-internal.h>
 
-int
-__getcpu (unsigned int *cpu, unsigned int *node)
+static int
+vsyscall_getcpu (unsigned int *cpu, unsigned int *node)
 {
 #ifdef HAVE_GETCPU_VSYSCALL
   return INLINE_VSYSCALL (getcpu, 3, cpu, node, NULL);
@@ -29,5 +30,32 @@ __getcpu (unsigned int *cpu, unsigned int *node)
   return INLINE_SYSCALL_CALL (getcpu, cpu, node, NULL);
 #endif
 }
+
+#if defined (RSEQ_SIG) && defined (RSEQ_HAS_LOAD32_LOAD32_RELAXED)
+int
+__getcpu (unsigned int *cpu, unsigned int *node)
+{
+  /* Check if rseq is registered and the node_id feature is available.  */
+  if (__glibc_likely (rseq_node_id_available()))
+  {
+    struct rseq_area *rseq_area = rseq_get_area();
+
+    if (rseq_load32_load32_relaxed(cpu, &rseq_area->cpu_id,
+                                   node, &rseq_area->node_id) == 0)
+    {
+      /* The critical section was not aborted, return 0.  */
+      return 0;
+    }
+  }
+
+  return vsyscall_getcpu (cpu, node);
+}
+#else
+int
+__getcpu (unsigned int *cpu, unsigned int *node)
+{
+  return vsyscall_getcpu (cpu, node);
+}
+#endif
 weak_alias (__getcpu, getcpu)
 libc_hidden_def (__getcpu)
-- 
2.34.1


  parent reply	other threads:[~2024-02-01 19:37 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-01 19:36 [PATCH v7 0/8] Extend rseq support Michael Jeanson
2024-02-01 19:36 ` [PATCH v7 1/8] nptl: fix potential merge of __rseq_* relro symbols Michael Jeanson
2024-02-01 19:36 ` [PATCH v7 2/8] Add rseq extensible ABI support Michael Jeanson
2024-02-01 19:36 ` [PATCH v7 3/8] nptl: Add public __rseq_feature_size symbol Michael Jeanson
2024-02-01 19:36 ` [PATCH v7 4/8] nptl: Add features to internal 'struct rseq_area' Michael Jeanson
2024-02-01 19:36 ` [PATCH v7 5/8] nptl: Add rseq internal utils Michael Jeanson
2024-02-01 19:36 ` [PATCH v7 6/8] x86-64: Add rseq_load32_load32_relaxed Michael Jeanson
2024-02-01 19:36 ` [PATCH v7 7/8] aarch64: " Michael Jeanson
2024-02-01 19:36 ` Michael Jeanson [this message]
2024-02-02 15:40 ` [PATCH v7 0/8] Extend rseq support Michael Jeanson
2024-02-02 16:18   ` Adhemerval Zanella Netto

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20240201193648.584917-9-mjeanson@efficios.com \
    --to=mjeanson@efficios.com \
    --cc=carlos@redhat.com \
    --cc=fweimer@redhat.com \
    --cc=libc-alpha@sourceware.org \
    --cc=mathieu.desnoyers@efficios.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).