From: catalin.marinas@arm.com (Catalin Marinas)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH resend 03/15] arm64: defer reloading a task's FPSIMD state to userland resume
Date: Tue, 6 May 2014 17:08:26 +0100 [thread overview]
Message-ID: <20140506160826.GI23957@arm.com> (raw)
In-Reply-To: <1398959381-8126-4-git-send-email-ard.biesheuvel@linaro.org>
On Thu, May 01, 2014 at 04:49:35PM +0100, Ard Biesheuvel wrote:
> @@ -153,12 +252,11 @@ static int fpsimd_cpu_pm_notifier(struct notifier_block *self,
> {
> switch (cmd) {
> case CPU_PM_ENTER:
> - if (current->mm)
> + if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE))
> fpsimd_save_state(¤t->thread.fpsimd_state);
> break;
> case CPU_PM_EXIT:
> - if (current->mm)
> - fpsimd_load_state(¤t->thread.fpsimd_state);
> + set_thread_flag(TIF_FOREIGN_FPSTATE);
I think we could enter a PM state on a kernel thread (idle), so we
should preserve the current->mm check as well.
> break;
> case CPU_PM_ENTER_FAILED:
> default:
> diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
> index 06448a77ff53..882f01774365 100644
> --- a/arch/arm64/kernel/signal.c
> +++ b/arch/arm64/kernel/signal.c
> @@ -413,4 +413,8 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
> clear_thread_flag(TIF_NOTIFY_RESUME);
> tracehook_notify_resume(regs);
> }
> +
> + if (thread_flags & _TIF_FOREIGN_FPSTATE)
> + fpsimd_restore_current_state();
I think this should be safe. Even if we get preempted here, ret_to_user
would loop over TI_FLAGS with interrupts disabled until no work pending.
--
Catalin
next prev parent reply other threads:[~2014-05-06 16:08 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-05-01 15:49 [PATCH resend 00/15] arm64 crypto roundup Ard Biesheuvel
2014-05-01 15:49 ` [PATCH resend 01/15] asm-generic: allow generic unaligned access if the arch supports it Ard Biesheuvel
2014-05-06 14:31 ` Catalin Marinas
2014-05-06 14:34 ` Ard Biesheuvel
2014-05-06 15:14 ` Catalin Marinas
2014-05-01 15:49 ` [PATCH resend 02/15] arm64: add abstractions for FPSIMD state manipulation Ard Biesheuvel
2014-05-06 14:43 ` Catalin Marinas
2014-05-06 14:48 ` Ard Biesheuvel
2014-05-06 15:12 ` Catalin Marinas
2014-05-06 15:42 ` Catalin Marinas
2014-05-01 15:49 ` [PATCH resend 03/15] arm64: defer reloading a task's FPSIMD state to userland resume Ard Biesheuvel
2014-05-06 16:08 ` Catalin Marinas [this message]
2014-05-06 16:25 ` Ard Biesheuvel
2014-05-06 16:31 ` Catalin Marinas
2014-05-01 15:49 ` [PATCH resend 04/15] arm64: add support for kernel mode NEON in interrupt context Ard Biesheuvel
2014-05-06 16:49 ` Catalin Marinas
2014-05-06 17:09 ` Ard Biesheuvel
2014-05-01 15:49 ` [PATCH resend 05/15] arm64/crypto: SHA-1 using ARMv8 Crypto Extensions Ard Biesheuvel
2014-05-01 15:49 ` [PATCH resend 06/15] arm64/crypto: SHA-224/SHA-256 " Ard Biesheuvel
2014-05-01 15:49 ` [PATCH resend 07/15] arm64/crypto: GHASH secure hash " Ard Biesheuvel
2014-05-01 15:49 ` [PATCH resend 08/15] arm64/crypto: AES " Ard Biesheuvel
2014-05-01 15:49 ` [PATCH resend 09/15] arm64/crypto: AES in CCM mode " Ard Biesheuvel
2014-05-07 14:45 ` [PATCH resend 00/15] arm64 crypto roundup Catalin Marinas
2014-05-07 19:58 ` Ard Biesheuvel
2014-05-08 11:22 ` Ard Biesheuvel
2014-05-08 21:50 ` Catalin Marinas
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=20140506160826.GI23957@arm.com \
--to=catalin.marinas@arm.com \
--cc=linux-arm-kernel@lists.infradead.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 NNTP newsgroup(s).