All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ingo Molnar <mingo@kernel.org>
To: linux-kernel@vger.kernel.org
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Eric Biggers <ebiggers3@gmail.com>,
	Andy Lutomirski <luto@amacapital.net>,
	Borislav Petkov <bp@alien8.de>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Fenghua Yu <fenghua.yu@intel.com>,
	"H . Peter Anvin" <hpa@zytor.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Oleg Nesterov <oleg@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Rik van Riel <riel@redhat.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Yu-cheng Yu <yu-cheng.yu@intel.com>
Subject: [PATCH 31/33] x86/fpu: Simplify and speed up fpu__copy()
Date: Sat, 23 Sep 2017 15:00:14 +0200	[thread overview]
Message-ID: <20170923130016.21448-32-mingo@kernel.org> (raw)
In-Reply-To: <20170923130016.21448-1-mingo@kernel.org>

fpu__copy() has a preempt_disable()/enable() pair, which it had to do to
be able to atomically unlazy the current task when doing an FNSAVE.

But we don't unlazy tasks anymore, we always do direct saves/restores of
FPU context.

So remove both the unnecessary critical section, and update the comments.

Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Eric Biggers <ebiggers3@gmail.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/fpu/core.c | 15 +++------------
 1 file changed, 3 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 4acfc0ebc160..e935f8faf287 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -206,22 +206,13 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	 * Save current FPU registers directly into the child
 	 * FPU context, without any memory-to-memory copying.
 	 *
-	 * We have to do all this with preemption disabled,
-	 * mostly because of the FNSAVE case, because in that
-	 * case we must not allow preemption in the window
-	 * between the FNSAVE and us marking the context lazy.
-	 *
-	 * It shouldn't be an issue as even FNSAVE is plenty
-	 * fast in terms of critical section length.
+	 * ( The function 'fails' in the FNSAVE case, which destroys
+	 *   register contents so we have to copy them back. )
 	 */
-	preempt_disable();
 	if (!copy_fpregs_to_fpstate(dst_fpu)) {
-		memcpy(&src_fpu->state, &dst_fpu->state,
-		       fpu_kernel_xstate_size);
-
+		memcpy(&src_fpu->state, &dst_fpu->state, fpu_kernel_xstate_size);
 		copy_kernel_to_fpregs(&src_fpu->state);
 	}
-	preempt_enable();
 
 	trace_x86_fpu_copy_src(src_fpu);
 	trace_x86_fpu_copy_dst(dst_fpu);
-- 
2.11.0

  parent reply	other threads:[~2017-09-23 13:01 UTC|newest]

Thread overview: 99+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-09-23 12:59 [PATCH 00/33] x86 FPU fixes and cleanups for v4.14 Ingo Molnar
2017-09-23 12:59 ` [PATCH 01/33] x86/fpu: Rename copyin_to_xsaves()/copyout_from_xsaves() to copy_user_to_xstate()/copy_xstate_to_user() Ingo Molnar
2017-09-26  8:21   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 12:59 ` [PATCH 02/33] x86/fpu: Split copy_xstate_to_user() into copy_xstate_to_kernel() & copy_xstate_to_user() Ingo Molnar
2017-09-26  8:22   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 12:59 ` [PATCH 03/33] x86/fpu: Remove 'ubuf' parameter from the copy_xstate_to_kernel() APIs Ingo Molnar
2017-09-26  8:22   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 12:59 ` [PATCH 04/33] x86/fpu: Remove 'kbuf' parameter from the copy_xstate_to_user() APIs Ingo Molnar
2017-09-26  8:23   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 12:59 ` [PATCH 05/33] x86/fpu: Clean up parameter order in the copy_xstate_to_*() APIs Ingo Molnar
2017-09-26  8:23   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 12:59 ` [PATCH 06/33] x86/fpu: Clean up the parameter definitions of copy_xstate_to_*() Ingo Molnar
2017-09-26  8:23   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 12:59 ` [PATCH 07/33] x86/fpu: Remove the 'start_pos' parameter from the __copy_xstate_to_*() functions Ingo Molnar
2017-09-26  8:24   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 12:59 ` [PATCH 08/33] x86/fpu: Clarify parameter names in the copy_xstate_to_*() methods Ingo Molnar
2017-09-25 19:56   ` Thomas Gleixner
2017-09-25 20:01     ` Thomas Gleixner
2017-09-26  8:24   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 12:59 ` [PATCH 09/33] x86/fpu: Change 'size_total' parameter to unsigned and standardize the size checks in copy_xstate_to_*() Ingo Molnar
2017-09-26  8:25   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 12:59 ` [PATCH 10/33] x86/fpu: Simplify __copy_xstate_to_kernel() return values Ingo Molnar
2017-09-26  8:25   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 12:59 ` [PATCH 11/33] x86/fpu: Split copy_user_to_xstate() into copy_kernel_to_xstate() & copy_user_to_xstate() Ingo Molnar
2017-09-26  8:25   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 12:59 ` [PATCH 12/33] x86/fpu: Remove 'ubuf' parameter from the copy_kernel_to_xstate() API Ingo Molnar
2017-09-26  8:26   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 12:59 ` [PATCH 13/33] x86/fpu: Remove 'kbuf' parameter from the copy_user_to_xstate() API Ingo Molnar
2017-09-26  8:26   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 12:59 ` [PATCH 14/33] x86/fpu: Flip the parameter order in copy_*_to_xstate() Ingo Molnar
2017-09-26  8:27   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 12:59 ` [PATCH 15/33] x86/fpu: Simplify fpu->fpregs_active use Ingo Molnar
2017-09-26  8:27   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 12:59 ` [PATCH 16/33] x86/fpu: Make the fpu state change in fpu__clear() scheduler-atomic Ingo Molnar
2017-09-26  8:27   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 13:00 ` [PATCH 17/33] x86/fpu: Split the state handling in fpu__drop() Ingo Molnar
2017-09-26  8:28   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 13:00 ` [PATCH 18/33] x86/fpu: Change fpu->fpregs_active users to fpu->fpstate_active Ingo Molnar
2017-09-26  8:28   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 13:00 ` [PATCH 19/33] x86/fpu: Decouple fpregs_activate()/fpregs_deactivate() from fpu->fpregs_active Ingo Molnar
2017-09-26  8:28   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 13:00 ` [PATCH 20/33] x86/fpu: Remove struct fpu::fpregs_active Ingo Molnar
2017-09-26  8:29   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 13:00 ` [PATCH 21/33] x86/fpu: Add FPU state copying quirk to handle XRSTOR failure on Intel Skylake CPUs Ingo Molnar
2017-09-26  8:29   ` [tip:x86/fpu] " tip-bot for Rik van Riel
2017-09-23 13:00 ` [PATCH 22/33] x86/fpu: Fix boolreturn.cocci warnings Ingo Molnar
2017-09-26  8:30   ` [tip:x86/fpu] " tip-bot for kbuild test robot
2017-09-23 13:00 ` [PATCH 23/33] x86/fpu: Turn WARN_ON() in context switch into WARN_ON_FPU() Ingo Molnar
2017-09-26  8:30   ` [tip:x86/fpu] " tip-bot for Andi Kleen
2017-09-23 13:00 ` [PATCH 24/33] x86/fpu: Don't let userspace set bogus xcomp_bv Ingo Molnar
2017-09-26  8:30   ` [tip:x86/fpu] " tip-bot for Eric Biggers
2017-09-23 13:00 ` [PATCH 25/33] x86/fpu: Tighten validation of user-supplied xstate_header Ingo Molnar
2017-09-23 13:00 ` [PATCH 26/33] x86/fpu: Reinitialize FPU registers if restoring FPU state fails Ingo Molnar
2017-09-26  8:31   ` [tip:x86/fpu] " tip-bot for Eric Biggers
2017-09-23 13:00 ` [PATCH 27/33] x86/fpu: Simplify fpu__activate_fpstate_read() Ingo Molnar
2017-09-26  8:31   ` [tip:x86/fpu] x86/fpu: Fix fpu__activate_fpstate_read() and update comments tip-bot for Ingo Molnar
2017-09-23 13:00 ` [PATCH 28/33] x86/fpu: Remove fpu__current_fpstate_write_begin/end() Ingo Molnar
2017-09-26  8:32   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 13:00 ` [PATCH 29/33] x86/fpu: Rename fpu::fpstate_active to fpu::initialized Ingo Molnar
2017-09-26  8:32   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 13:00 ` [PATCH 30/33] x86/fpu: Fix stale comments about lazy FPU logic Ingo Molnar
2017-09-26  8:32   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 13:00 ` Ingo Molnar [this message]
2017-09-26  8:33   ` [tip:x86/fpu] x86/fpu: Simplify and speed up fpu__copy() tip-bot for Ingo Molnar
2017-09-23 13:00 ` [PATCH 32/33] x86/fpu: Rename fpu__activate_curr() to fpu__initialize() Ingo Molnar
2017-09-26  8:33   ` [tip:x86/fpu] " tip-bot for Ingo Molnar
2017-09-23 13:00 ` [PATCH 33/33] x86/fpu: Rename fpu__activate_fpstate_read/write() to fpu__read/write() Ingo Molnar
2017-09-23 13:02 ` [PATCH 00/33] x86 FPU fixes and cleanups for v4.14 Ingo Molnar
2017-09-23 15:03   ` Juergen Gross
2017-09-23 23:27     ` Ingo Molnar
  -- strict thread matches above, loose matches on Subject: below --
2017-09-22 17:41 [kernel-hardening] [PATCH v4 0/3] x86/fpu: prevent leaking FPU registers via invalid FPU state Eric Biggers
2017-09-22 17:41 ` Eric Biggers
2017-09-22 17:41 ` [kernel-hardening] [PATCH v4 1/3] x86/fpu: don't let userspace set bogus xcomp_bv Eric Biggers
2017-09-22 17:41   ` Eric Biggers
2017-09-22 17:41 ` [kernel-hardening] [PATCH v4 2/3] x86/fpu: tighten validation of user-supplied xstate_header Eric Biggers
2017-09-22 17:41   ` Eric Biggers
2017-09-22 17:41 ` [kernel-hardening] [PATCH v4 3/3] x86/fpu: reinitialize FPU registers if restoring FPU state fails Eric Biggers
2017-09-22 17:41   ` Eric Biggers
2017-09-23  9:09 ` [kernel-hardening] Re: [PATCH v4 0/3] x86/fpu: prevent leaking FPU registers via invalid FPU state Ingo Molnar
2017-09-23  9:09   ` Ingo Molnar
2017-03-29  6:26 [PATCH] x86/fpu: Turn WARN_ON in context switch into WARN_ON_FPU Andi Kleen
2017-04-24 21:00 ` [tip:perf/core] x86/fpu: Turn WARN_ON() in context switch into WARN_ON_FPU() tip-bot for Andi Kleen
2017-03-06  0:45 [tip:WIP.x86/fpu 31/31] arch/x86/kernel/fpu/xstate.c:931:9-10: WARNING: return of 0/1 in function 'xfeatures_mxcsr_quirk' with return type bool kbuild test robot
2017-03-06  0:45 ` [PATCH] x86/fpu: fix boolreturn.cocci warnings kbuild test robot
2017-03-07  7:23   ` Ingo Molnar
2017-03-07  8:33     ` Thomas Gleixner
2017-03-07  9:01       ` Ingo Molnar
2017-03-07 12:01         ` Joe Perches
2017-04-24 20:54   ` [tip:perf/core] x86/fpu: Fix " tip-bot for kbuild test robot
2017-02-09 23:43 [PATCH v2] x86/fpu: copy MXCSR & MXCSR_FLAGS with SSE/YMM state Rik van Riel
2017-02-10  0:02 ` Borislav Petkov
2017-02-10  0:51   ` Rik van Riel
2017-02-10  8:00     ` Ingo Molnar
2017-02-10 13:54       ` [PATCH v3] " Rik van Riel
2017-02-11 10:02         ` Ingo Molnar
2017-04-24 20:54         ` [tip:perf/core] x86/fpu: Add FPU state copying quirk to handle XRSTOR failure on Intel Skylake CPUs tip-bot for Rik van Riel
2017-02-10  0:45 ` [PATCH v2] x86/fpu: copy MXCSR & MXCSR_FLAGS with SSE/YMM state Yu-cheng Yu
2017-02-10  1:00   ` Rik van Riel
2017-02-10 17:18     ` Yu-cheng Yu

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=20170923130016.21448-32-mingo@kernel.org \
    --to=mingo@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=ebiggers3@gmail.com \
    --cc=fenghua.yu@intel.com \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@amacapital.net \
    --cc=oleg@redhat.com \
    --cc=peterz@infradead.org \
    --cc=riel@redhat.com \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=yu-cheng.yu@intel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.