From: Adhemerval Zanella <adhemerval.zanella@linaro.org>
To: libc-alpha@sourceware.org
Subject: [PATCH 16/16] linux: Optimize fallback 32-bit clock_getres
Date: Tue, 17 Dec 2019 18:47:28 -0300 [thread overview]
Message-ID: <20191217214728.2886-16-adhemerval.zanella@linaro.org> (raw)
In-Reply-To: <20191217214728.2886-1-adhemerval.zanella@linaro.org>
This patch avoid probing the __NR_clock_getttime64 syscall each time
__clock_gettime64 is issued on a kernel without 64 bit time support.
Once ENOSYS is obtained, only 32-bit clock_gettime are used.
The following snippet:
clock_getres (CLOCK_REALTIME, &(struct timespec) { 0 });
clock_getres (CLOCK_MONOTONIC, &(struct timespec) { 0 });
clock_getres (CLOCK_BOOTTIME, &(struct timespec) { 0 });
clock_getres (20, &(struct timespec) { 0 });
On a kernel without 64 bit time support issues the syscalls:
syscall_0x196(0, 0xffb83330, [...]) = -1 ENOSYS (Function not implemented)
clock_getres(CLOCK_REALTIME, {tv_sec=0, tv_nsec=1}) = 0
clock_getres(CLOCK_MONOTONIC, {tv_sec=0, tv_nsec=1}) = 0
clock_getres(CLOCK_BOOTTIME, {tv_sec=0, tv_nsec=1}) = 0
Checked on i686-linux-gnu on 4.15 kernel.
---
sysdeps/unix/sysv/linux/clock_getres.c | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)
diff --git a/sysdeps/unix/sysv/linux/clock_getres.c b/sysdeps/unix/sysv/linux/clock_getres.c
index 3d59f11d71..c1e1cf60c6 100644
--- a/sysdeps/unix/sysv/linux/clock_getres.c
+++ b/sysdeps/unix/sysv/linux/clock_getres.c
@@ -42,13 +42,21 @@ __clock_getres64 (clockid_t clock_id, struct __timespec64 *res)
int r;
/* Old 32-bit ABI with possible 64-bit time_t support. */
# ifdef __NR_clock_getres_time64
+ /* Avoid issue a __NR_clock_getres_time64 syscall on kernels that do not
+ support 64-bit time_t. */
+ static int time64_support = 1;
+ if (atomic_load_relaxed (&time64_support) == 1)
+ {
# ifdef HAVE_CLOCK_GETRES64_VSYSCALL
- r = INLINE_VSYSCALL (clock_getres_time64, 2, clock_id, res);
+ r = INLINE_VSYSCALL (clock_getres_time64, 2, clock_id, res);
# else
- r = INLINE_SYSCALL_CALL (clock_getres_time64, clock_id, res);
+ r = INLINE_SYSCALL_CALL (clock_getres_time64, clock_id, res);
# endif
- if (r == 0 || errno != ENOSYS)
- return r;
+ if (r == 0 || errno != ENOSYS)
+ return r;
+
+ atomic_store_relaxed (&time64_support, 0);
+ }
# endif
/* Fallback code that uses 32-bit support. */
struct timespec ts32;
--
2.17.1
next prev parent reply other threads:[~2019-12-17 21:50 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-12-17 21:47 [PATCH v2 01/16] linux: Fix vDSO macros build with time64 interfaces Adhemerval Zanella
2019-12-17 21:47 ` [PATCH v2 02/16] x86: Make x32 use x86 time implementation Adhemerval Zanella
2020-01-02 12:07 ` Siddhesh Poyarekar
2019-12-17 21:47 ` [PATCH 03/16] Remove vDSO support from make-syscall.sh Adhemerval Zanella
2020-01-02 12:07 ` Siddhesh Poyarekar
2019-12-17 21:47 ` [PATCH 04/16] linux: Update x86 vDSO symbols Adhemerval Zanella
2020-01-02 12:07 ` Siddhesh Poyarekar
2019-12-17 21:47 ` [PATCH 05/16] linux: Update mips " Adhemerval Zanella
2020-01-02 12:08 ` Siddhesh Poyarekar
2019-12-17 21:47 ` [PATCH 06/16] linux: Consolidate Linux gettimeofday Adhemerval Zanella
2019-12-18 8:46 ` Andreas Schwab
2019-12-18 14:50 ` Adhemerval Zanella
2020-01-02 12:07 ` Siddhesh Poyarekar
2019-12-17 21:47 ` [PATCH 07/16] linux: Consolidate time implementation Adhemerval Zanella
2020-01-02 12:51 ` Siddhesh Poyarekar
2019-12-17 21:47 ` [PATCH v3 08/16] elf: Enable relro for static build Adhemerval Zanella
2020-01-02 12:07 ` Siddhesh Poyarekar
2019-12-17 21:47 ` [PATCH v3 09/16] elf: Move vDSO setup to rtld (BZ#24967) Adhemerval Zanella
2020-01-02 12:55 ` Siddhesh Poyarekar
2020-01-02 13:00 ` Adhemerval Zanella
2020-01-07 16:13 ` [PATCH v3 09/16] elf: Move vDSO setup to rtld (BZ#24967) - regression found Lukasz Majewski
2020-01-07 19:40 ` Adhemerval Zanella
2019-12-17 21:47 ` [PATCH v2 10/16] linux: Add support for clock_gettime64 vDSO Adhemerval Zanella
2020-01-02 13:03 ` Siddhesh Poyarekar
2019-12-17 21:47 ` [PATCH 11/16] linux: Optimize fallback 32-bit clock_gettime Adhemerval Zanella
2019-12-18 8:53 ` Andreas Schwab
2019-12-18 14:58 ` Adhemerval Zanella
2020-01-02 13:07 ` Siddhesh Poyarekar
2019-12-17 21:47 ` [PATCH 12/16] linux: Enable vDSO clock_gettime64 for i386 Adhemerval Zanella
2020-01-02 13:08 ` Siddhesh Poyarekar
2020-01-02 13:08 ` Siddhesh Poyarekar
2019-12-17 21:47 ` [PATCH 13/16] linux: Enable vDSO clock_gettime64 for arm Adhemerval Zanella
2020-01-02 13:08 ` Siddhesh Poyarekar
2019-12-17 21:47 ` [PATCH 14/16] linux: Enable vDSO clock_gettime64 for mips Adhemerval Zanella
2019-12-18 15:33 ` Florian Weimer
2020-01-02 13:13 ` Siddhesh Poyarekar
2020-01-02 13:50 ` Adhemerval Zanella
2020-01-02 14:09 ` Siddhesh Poyarekar
2019-12-17 21:47 ` [PATCH v2 15/16] linux: Add support for clock_getres64 vDSO Adhemerval Zanella
2020-01-02 13:15 ` Siddhesh Poyarekar
2019-12-17 21:47 ` Adhemerval Zanella [this message]
2019-12-18 8:56 ` [PATCH 16/16] linux: Optimize fallback 32-bit clock_getres Andreas Schwab
2019-12-18 14:58 ` Adhemerval Zanella
2019-12-18 15:02 ` Adhemerval Zanella
2020-01-02 13:16 ` Siddhesh Poyarekar
2020-01-02 12:07 ` [PATCH v2 01/16] linux: Fix vDSO macros build with time64 interfaces Siddhesh Poyarekar
2020-01-02 12:55 ` Adhemerval Zanella
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
List information: https://www.gnu.org/software/libc/involved.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20191217214728.2886-16-adhemerval.zanella@linaro.org \
--to=adhemerval.zanella@linaro.org \
--cc=libc-alpha@sourceware.org \
/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).