From: Dave Martin <Dave.Martin@arm.com>
To: linux-arm-kernel@lists.infradead.org
Cc: "Catalin Marinas" <catalin.marinas@arm.com>,
"Will Deacon" <will.deacon@arm.com>,
"Ard Biesheuvel" <ard.biesheuvel@linaro.org>,
"Alex Bennée" <alex.bennee@linaro.org>,
"Szabolcs Nagy" <szabolcs.nagy@arm.com>,
"Okamoto Takayuki" <tokamoto@jp.fujitsu.com>,
kvmarm@lists.cs.columbia.edu, libc-alpha@sourceware.org,
linux-arch@vger.kernel.org
Subject: [PATCH v4 21/28] arm64/sve: Add sysctl to set the default vector length for new processes
Date: Fri, 27 Oct 2017 11:51:03 +0100 [thread overview]
Message-ID: <1509101470-7881-22-git-send-email-Dave.Martin@arm.com> (raw)
In-Reply-To: <1509101470-7881-1-git-send-email-Dave.Martin@arm.com>
Because of the effect of SVE on the size of the signal frame, the
default vector length used for new processes involves a tradeoff
between performance of SVE-enabled software on the one hand, and
reliability of non-SVE-aware software on the other hand.
For this reason, the best choice depends on the repertoire of
userspace software in use and is thus best left up to distro
maintainers, sysadmins and developers.
If CONFIG_SYSCTL and CONFIG_PROC_SYSCTL are enabled, this patch
exposes the default vector length in
/proc/sys/abi/sve_default_vector_length, where boot scripts or the
adventurous can poke it.
In common with other arm64 ABI sysctls, this control is currently
global: setting it requires CAP_SYS_ADMIN in the root user
namespace, but the value set is effective for subsequent execs in
all namespaces. The control only affects _new_ processes, however:
changing it does not affect the vector length of any existing
process.
The intended usage model is that if userspace is known to be fully
SVE-tolerant (or a developer is curious to find out) then this
parameter can be cranked up during system startup.
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
---
arch/arm64/kernel/fpsimd.c | 62 +++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 61 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 7465622..f9d3287 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -35,6 +35,7 @@
#include <linux/sched/signal.h>
#include <linux/signal.h>
#include <linux/slab.h>
+#include <linux/sysctl.h>
#include <asm/fpsimd.h>
#include <asm/cputype.h>
@@ -333,6 +334,65 @@ static unsigned int find_supported_vector_length(unsigned int vl)
return sve_vl_from_vq(bit_to_vq(bit));
}
+#ifdef CONFIG_SYSCTL
+
+static int sve_proc_do_default_vl(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret;
+ int vl = sve_default_vl;
+ struct ctl_table tmp_table = {
+ .data = &vl,
+ .maxlen = sizeof(vl),
+ };
+
+ ret = proc_dointvec(&tmp_table, write, buffer, lenp, ppos);
+ if (ret || !write)
+ return ret;
+
+ /* Writing -1 has the special meaning "set to max": */
+ if (vl == -1) {
+ /* Fail safe if sve_max_vl wasn't initialised */
+ if (WARN_ON(!sve_vl_valid(sve_max_vl)))
+ vl = SVE_VL_MIN;
+ else
+ vl = sve_max_vl;
+
+ goto chosen;
+ }
+
+ if (!sve_vl_valid(vl))
+ return -EINVAL;
+
+ vl = find_supported_vector_length(vl);
+chosen:
+ sve_default_vl = vl;
+ return 0;
+}
+
+static struct ctl_table sve_default_vl_table[] = {
+ {
+ .procname = "sve_default_vector_length",
+ .mode = 0644,
+ .proc_handler = sve_proc_do_default_vl,
+ },
+ { }
+};
+
+static int __init sve_sysctl_init(void)
+{
+ if (system_supports_sve())
+ if (!register_sysctl("abi", sve_default_vl_table))
+ return -EINVAL;
+
+ return 0;
+}
+
+#else /* ! CONFIG_SYSCTL */
+static int __init sve_sysctl_init(void) { return 0; }
+#endif /* ! CONFIG_SYSCTL */
+
#define ZREG(sve_state, vq, n) ((char *)(sve_state) + \
(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
@@ -1207,6 +1267,6 @@ static int __init fpsimd_init(void)
if (!(elf_hwcap & HWCAP_ASIMD))
pr_notice("Advanced SIMD is not implemented\n");
- return 0;
+ return sve_sysctl_init();
}
core_initcall(fpsimd_init);
--
2.1.4
next prev parent reply other threads:[~2017-10-27 10:52 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-27 10:50 [PATCH v4 00/28] ARM Scalable Vector Extension (SVE) Dave Martin
2017-10-27 10:50 ` [PATCH v4 01/28] regset: Add support for dynamically sized regsets Dave Martin
2017-10-27 10:50 ` Dave Martin
2017-10-27 10:50 ` [PATCH v4 02/28] arm64: KVM: Hide unsupported AArch64 CPU features from guests Dave Martin
2017-10-27 10:50 ` Dave Martin
2017-10-31 10:57 ` Alex Bennée
2017-10-31 10:57 ` Alex Bennée
2017-10-27 10:50 ` [PATCH v4 03/28] arm64: efi: Add missing Kconfig dependency on KERNEL_MODE_NEON Dave Martin
2017-10-27 10:50 ` [PATCH v4 04/28] arm64: Port deprecated instruction emulation to new sysctl interface Dave Martin
2017-10-27 10:50 ` Dave Martin
2017-10-27 10:50 ` [PATCH v4 05/28] arm64: fpsimd: Simplify uses of {set, clear}_ti_thread_flag() Dave Martin
2017-10-27 10:50 ` [PATCH v4 05/28] arm64: fpsimd: Simplify uses of {set,clear}_ti_thread_flag() Dave Martin
2017-10-27 10:50 ` [PATCH v4 06/28] arm64/sve: System register and exception syndrome definitions Dave Martin
2017-10-27 10:50 ` [PATCH v4 07/28] arm64/sve: Low-level SVE architectural state manipulation functions Dave Martin
2017-10-27 10:50 ` [PATCH v4 08/28] arm64/sve: Kconfig update and conditional compilation support Dave Martin
2017-10-27 10:50 ` [PATCH v4 09/28] arm64/sve: Signal frame and context structure definition Dave Martin
2017-10-27 10:50 ` Dave Martin
2017-10-27 10:50 ` [PATCH v4 10/28] arm64/sve: Low-level CPU setup Dave Martin
2017-10-27 10:50 ` [PATCH v4 11/28] arm64/sve: Core task context handling Dave Martin
2017-10-27 10:50 ` Dave Martin
2017-10-27 12:45 ` Catalin Marinas
2017-10-27 12:45 ` Catalin Marinas
2017-10-27 10:50 ` [PATCH v4 12/28] arm64/sve: Support vector length resetting for new processes Dave Martin
2017-10-27 10:50 ` [PATCH v4 13/28] arm64/sve: Signal handling support Dave Martin
2017-10-27 10:50 ` Dave Martin
2017-10-27 12:54 ` Catalin Marinas
2017-10-27 10:50 ` [PATCH v4 14/28] arm64/sve: Backend logic for setting the vector length Dave Martin
2017-10-27 10:50 ` [PATCH v4 15/28] arm64: cpufeature: Move sys_caps_initialised declarations Dave Martin
2017-10-27 10:50 ` [PATCH v4 16/28] arm64/sve: Probe SVE capabilities and usable vector lengths Dave Martin
2017-10-27 10:50 ` Dave Martin
2017-10-27 12:56 ` Catalin Marinas
2017-10-27 12:56 ` Catalin Marinas
2017-10-27 10:50 ` [PATCH v4 17/28] arm64/sve: Preserve SVE registers around kernel-mode NEON use Dave Martin
2017-10-27 10:50 ` Dave Martin
2017-10-27 10:51 ` [PATCH v4 18/28] arm64/sve: Preserve SVE registers around EFI runtime service calls Dave Martin
2017-10-27 10:51 ` Dave Martin
2017-10-27 10:51 ` [PATCH v4 19/28] arm64/sve: ptrace and ELF coredump support Dave Martin
2017-10-27 13:04 ` Catalin Marinas
2017-10-27 13:04 ` Catalin Marinas
2017-10-27 10:51 ` [PATCH v4 20/28] arm64/sve: Add prctl controls for userspace vector length management Dave Martin
2017-10-27 10:51 ` Dave Martin
2017-10-27 17:52 ` Alex Bennée
2017-10-27 17:52 ` Alex Bennée
2017-10-28 16:05 ` Dave Martin
2017-10-30 16:12 ` Alex Bennée
2017-10-30 16:12 ` Alex Bennée
2017-10-30 16:17 ` Dave Martin
2017-10-30 16:17 ` Dave Martin
2017-10-27 10:51 ` Dave Martin [this message]
2017-10-27 10:51 ` [PATCH v4 22/28] arm64/sve: KVM: Prevent guests from using SVE Dave Martin
2017-10-27 10:51 ` [PATCH v4 23/28] arm64/sve: KVM: Treat guest SVE use as undefined instruction execution Dave Martin
2017-10-27 10:51 ` Dave Martin
2017-10-27 10:51 ` [PATCH v4 24/28] arm64/sve: KVM: Hide SVE from CPU features exposed to guests Dave Martin
2017-10-27 10:51 ` [PATCH v4 25/28] arm64/sve: Detect SVE and activate runtime support Dave Martin
2017-10-27 13:05 ` Catalin Marinas
2017-10-27 10:51 ` [PATCH v4 26/28] arm64/sve: Add documentation Dave Martin
2017-10-27 13:06 ` Catalin Marinas
2017-10-27 10:51 ` [RFC PATCH v4 27/28] arm64: signal: Report signal frame size to userspace via auxv Dave Martin
2017-10-27 10:51 ` Dave Martin
2017-10-27 10:51 ` [RFC PATCH v4 28/28] arm64/sve: signal: Include SVE when computing AT_MINSIGSTKSZ Dave Martin
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=1509101470-7881-22-git-send-email-Dave.Martin@arm.com \
--to=dave.martin@arm.com \
--cc=alex.bennee@linaro.org \
--cc=ard.biesheuvel@linaro.org \
--cc=catalin.marinas@arm.com \
--cc=kvmarm@lists.cs.columbia.edu \
--cc=libc-alpha@sourceware.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=szabolcs.nagy@arm.com \
--cc=tokamoto@jp.fujitsu.com \
--cc=will.deacon@arm.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 NNTP newsgroup(s).