From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754951AbbATMzj (ORCPT ); Tue, 20 Jan 2015 07:55:39 -0500 Received: from terminus.zytor.com ([198.137.202.10]:57182 "EHLO terminus.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753683AbbATMzg (ORCPT ); Tue, 20 Jan 2015 07:55:36 -0500 Date: Tue, 20 Jan 2015 04:55:22 -0800 From: tip-bot for Oleg Nesterov Message-ID: Cc: riel@redhat.com, hpa@zytor.com, mingo@kernel.org, tglx@linutronix.de, linux-kernel@vger.kernel.org, oleg@redhat.com, torvalds@linux-foundation.org, sbsiddha@gmail.com Reply-To: torvalds@linux-foundation.org, sbsiddha@gmail.com, hpa@zytor.com, riel@redhat.com, oleg@redhat.com, linux-kernel@vger.kernel.org, mingo@kernel.org, tglx@linutronix.de In-Reply-To: <20150115192028.GD27332@redhat.com> References: <20150115192028.GD27332@redhat.com> To: linux-tip-commits@vger.kernel.org Subject: [tip:x86/fpu] x86, fpu: Fix math_state_restore() race with kernel_fpu_begin() Git-Commit-ID: 7575637ab293861a799f3bbafe0d8c597389f4e9 X-Mailer: tip-git-log-daemon Robot-ID: Robot-Unsubscribe: Contact to get blacklisted from these emails MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=UTF-8 Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Commit-ID: 7575637ab293861a799f3bbafe0d8c597389f4e9 Gitweb: http://git.kernel.org/tip/7575637ab293861a799f3bbafe0d8c597389f4e9 Author: Oleg Nesterov AuthorDate: Thu, 15 Jan 2015 20:20:28 +0100 Committer: Thomas Gleixner CommitDate: Tue, 20 Jan 2015 13:53:07 +0100 x86, fpu: Fix math_state_restore() race with kernel_fpu_begin() math_state_restore() can race with kernel_fpu_begin() if irq comes right after __thread_fpu_begin(), __save_init_fpu() will overwrite fpu->state we are going to restore. Add 2 simple helpers, kernel_fpu_disable() and kernel_fpu_enable() which simply set/clear in_kernel_fpu, and change math_state_restore() to exclude kernel_fpu_begin() in between. Alternatively we could use local_irq_save/restore, but probably these new helpers can have more users. Perhaps they should disable/enable preemption themselves, in this case we can remove preempt_disable() in __restore_xstate_sig(). Signed-off-by: Oleg Nesterov Reviewed-by: Rik van Riel Cc: matt.fleming@intel.com Cc: bp@suse.de Cc: pbonzini@redhat.com Cc: luto@amacapital.net Cc: Linus Torvalds Cc: Suresh Siddha Link: http://lkml.kernel.org/r/20150115192028.GD27332@redhat.com Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/i387.h | 4 ++++ arch/x86/kernel/i387.c | 11 +++++++++++ arch/x86/kernel/traps.c | 12 +++++------- 3 files changed, 20 insertions(+), 7 deletions(-) diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 5e275d3..6eb6fcb 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -51,6 +51,10 @@ static inline void kernel_fpu_end(void) preempt_enable(); } +/* Must be called with preempt disabled */ +extern void kernel_fpu_disable(void); +extern void kernel_fpu_enable(void); + /* * Some instructions like VIA's padlock instructions generate a spurious * DNA fault but don't modify SSE registers. And these instructions diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 12088a3..81049ff 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -21,6 +21,17 @@ static DEFINE_PER_CPU(bool, in_kernel_fpu); +void kernel_fpu_disable(void) +{ + WARN_ON(this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, true); +} + +void kernel_fpu_enable(void) +{ + this_cpu_write(in_kernel_fpu, false); +} + /* * Were we in an interrupt that interrupted kernel mode? * diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 88900e2..fb4cb6a 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -788,18 +788,16 @@ void math_state_restore(void) local_irq_disable(); } + /* Avoid __kernel_fpu_begin() right after __thread_fpu_begin() */ + kernel_fpu_disable(); __thread_fpu_begin(tsk); - - /* - * Paranoid restore. send a SIGSEGV if we fail to restore the state. - */ if (unlikely(restore_fpu_checking(tsk))) { drop_init_fpu(tsk); force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk); - return; + } else { + tsk->thread.fpu_counter++; } - - tsk->thread.fpu_counter++; + kernel_fpu_enable(); } EXPORT_SYMBOL_GPL(math_state_restore);