From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756948Ab3EVUjv (ORCPT ); Wed, 22 May 2013 16:39:51 -0400 Received: from mx1.redhat.com ([209.132.183.28]:34339 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753389Ab3EVUjs (ORCPT ); Wed, 22 May 2013 16:39:48 -0400 Date: Wed, 22 May 2013 23:38:31 +0300 From: "Michael S. Tsirkin" To: Peter Zijlstra Cc: linux-kernel@vger.kernel.org, Catalin Marinas , Will Deacon , David Howells , Hirokazu Takata , Michal Simek , Koichi Yasutake , Benjamin Herrenschmidt , Paul Mackerras , Chris Metcalf , Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , x86@kernel.org, Arnd Bergmann , linux-arm-kernel@lists.infradead.org, linux-m32r@ml.linux-m32r.org, linux-m32r-ja@ml.linux-m32r.org, microblaze-uclinux@itee.uq.edu.au, linux-am33-list@redhat.com, linuxppc-dev@lists.ozlabs.org, linux-arch@vger.kernel.org, linux-mm@kvack.org, kvm@vger.kernel.org, rostedt@goodmis.org Subject: Re: [PATCH v2 10/10] kernel: might_fault does not imply might_sleep Message-ID: <20130522203831.GB28296@redhat.com> References: <1f85dc8e6a0149677563a2dfb4cef9a9c7eaa391.1368702323.git.mst@redhat.com> <20130516184041.GP19669@dyad.programming.kicks-ass.net> <20130519093526.GD19883@redhat.com> <20130521115734.GA9554@twins.programming.kicks-ass.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20130521115734.GA9554@twins.programming.kicks-ass.net> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, May 21, 2013 at 01:57:34PM +0200, Peter Zijlstra wrote: > On Sun, May 19, 2013 at 12:35:26PM +0300, Michael S. Tsirkin wrote: > > > > --- a/include/linux/kernel.h > > > > +++ b/include/linux/kernel.h > > > > @@ -198,7 +198,6 @@ void might_fault(void); > > > > #else > > > > static inline void might_fault(void) > > > > { > > > > - might_sleep(); > > > > > > This removes potential resched points for PREEMPT_VOLUNTARY -- was that > > > intentional? > > > > No it's a bug. Thanks for pointing this out. > > OK so I guess it should be might_sleep_if(!in_atomic()) > > and this means might_fault would have to move from linux/kernel.h to > > linux/uaccess.h, since in_atomic() is in linux/hardirq.h > > > > Makes sense? > > So the only difference between PROVE_LOCKING and not should be the > might_lock_read() thing; so how about something like this? So the problem with the below is that might_fault is needed in asm/uaccess.h. I'm still trying various approaches but the dependencies there are very complex. > --- > include/linux/kernel.h | 7 ++----- > include/linux/uaccess.h | 26 ++++++++++++++++++++++++++ > mm/memory.c | 14 ++------------ > 3 files changed, 30 insertions(+), 17 deletions(-) > > diff --git a/include/linux/kernel.h b/include/linux/kernel.h > index e96329c..70812f4 100644 > --- a/include/linux/kernel.h > +++ b/include/linux/kernel.h > @@ -194,12 +194,9 @@ extern int _cond_resched(void); > }) > > #ifdef CONFIG_PROVE_LOCKING > -void might_fault(void); > +void might_fault_lockdep(void); > #else > -static inline void might_fault(void) > -{ > - might_sleep(); > -} > +static inline void might_fault_lockdep(void) { } > #endif > > extern struct atomic_notifier_head panic_notifier_list; > diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h > index 5ca0951..50a2cc9 100644 > --- a/include/linux/uaccess.h > +++ b/include/linux/uaccess.h > @@ -38,6 +38,32 @@ static inline void pagefault_enable(void) > preempt_check_resched(); > } > > +static inline bool __can_fault(void) > +{ > + /* > + * Some code (nfs/sunrpc) uses socket ops on kernel memory while > + * holding the mmap_sem, this is safe because kernel memory doesn't > + * get paged out, therefore we'll never actually fault, and the > + * below annotations will generate false positives. > + */ > + if (segment_eq(get_fs(), KERNEL_DS)) > + return false; > + > + if (in_atomic() /* || pagefault_disabled() */) > + return false; > + > + return true; > +} > + > +static inline void might_fault(void) > +{ > + if (!__can_fault()) > + return; > + > + might_sleep(); > + might_fault_lockdep(); > +} > + > #ifndef ARCH_HAS_NOCACHE_UACCESS > > static inline unsigned long __copy_from_user_inatomic_nocache(void *to, > diff --git a/mm/memory.c b/mm/memory.c > index 6dc1882..266610c 100644 > --- a/mm/memory.c > +++ b/mm/memory.c > @@ -4211,19 +4211,9 @@ void print_vma_addr(char *prefix, unsigned long ip) > } > > #ifdef CONFIG_PROVE_LOCKING > -void might_fault(void) > +void might_fault_lockdep(void) > { > /* > - * Some code (nfs/sunrpc) uses socket ops on kernel memory while > - * holding the mmap_sem, this is safe because kernel memory doesn't > - * get paged out, therefore we'll never actually fault, and the > - * below annotations will generate false positives. > - */ > - if (segment_eq(get_fs(), KERNEL_DS)) > - return; > - > - might_sleep(); > - /* > * it would be nicer only to annotate paths which are not under > * pagefault_disable, however that requires a larger audit and > * providing helpers like get_user_atomic. > @@ -4231,7 +4221,7 @@ void might_fault(void) > if (!in_atomic() && current->mm) > might_lock_read(¤t->mm->mmap_sem); > } > -EXPORT_SYMBOL(might_fault); > +EXPORT_SYMBOL(might_fault_lockdep); > #endif > > #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Michael S. Tsirkin" Subject: Re: [PATCH v2 10/10] kernel: might_fault does not imply might_sleep Date: Wed, 22 May 2013 23:38:31 +0300 Message-ID: <20130522203831.GB28296@redhat.com> References: <1f85dc8e6a0149677563a2dfb4cef9a9c7eaa391.1368702323.git.mst@redhat.com> <20130516184041.GP19669@dyad.programming.kicks-ass.net> <20130519093526.GD19883@redhat.com> <20130521115734.GA9554@twins.programming.kicks-ass.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20130521115734.GA9554@twins.programming.kicks-ass.net> Sender: owner-linux-mm@kvack.org To: Peter Zijlstra Cc: linux-kernel@vger.kernel.org, Catalin Marinas , Will Deacon , David Howells , Hirokazu Takata , Michal Simek , Koichi Yasutake , Benjamin Herrenschmidt , Paul Mackerras , Chris Metcalf , Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , x86@kernel.org, Arnd Bergmann , linux-arm-kernel@lists.infradead.org, linux-m32r@ml.linux-m32r.org, linux-m32r-ja@ml.linux-m32r.org, microblaze-uclinux@itee.uq.edu.au, linux-am33-list@redhat.com, linuxppc-dev@lists.ozlabs.org, linux-arch@vger.kernel.org, linux-mm@kvack.org, kvm@ List-Id: linux-arch.vger.kernel.org On Tue, May 21, 2013 at 01:57:34PM +0200, Peter Zijlstra wrote: > On Sun, May 19, 2013 at 12:35:26PM +0300, Michael S. Tsirkin wrote: > > > > --- a/include/linux/kernel.h > > > > +++ b/include/linux/kernel.h > > > > @@ -198,7 +198,6 @@ void might_fault(void); > > > > #else > > > > static inline void might_fault(void) > > > > { > > > > - might_sleep(); > > > > > > This removes potential resched points for PREEMPT_VOLUNTARY -- was that > > > intentional? > > > > No it's a bug. Thanks for pointing this out. > > OK so I guess it should be might_sleep_if(!in_atomic()) > > and this means might_fault would have to move from linux/kernel.h to > > linux/uaccess.h, since in_atomic() is in linux/hardirq.h > > > > Makes sense? > > So the only difference between PROVE_LOCKING and not should be the > might_lock_read() thing; so how about something like this? So the problem with the below is that might_fault is needed in asm/uaccess.h. I'm still trying various approaches but the dependencies there are very complex. > --- > include/linux/kernel.h | 7 ++----- > include/linux/uaccess.h | 26 ++++++++++++++++++++++++++ > mm/memory.c | 14 ++------------ > 3 files changed, 30 insertions(+), 17 deletions(-) > > diff --git a/include/linux/kernel.h b/include/linux/kernel.h > index e96329c..70812f4 100644 > --- a/include/linux/kernel.h > +++ b/include/linux/kernel.h > @@ -194,12 +194,9 @@ extern int _cond_resched(void); > }) > > #ifdef CONFIG_PROVE_LOCKING > -void might_fault(void); > +void might_fault_lockdep(void); > #else > -static inline void might_fault(void) > -{ > - might_sleep(); > -} > +static inline void might_fault_lockdep(void) { } > #endif > > extern struct atomic_notifier_head panic_notifier_list; > diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h > index 5ca0951..50a2cc9 100644 > --- a/include/linux/uaccess.h > +++ b/include/linux/uaccess.h > @@ -38,6 +38,32 @@ static inline void pagefault_enable(void) > preempt_check_resched(); > } > > +static inline bool __can_fault(void) > +{ > + /* > + * Some code (nfs/sunrpc) uses socket ops on kernel memory while > + * holding the mmap_sem, this is safe because kernel memory doesn't > + * get paged out, therefore we'll never actually fault, and the > + * below annotations will generate false positives. > + */ > + if (segment_eq(get_fs(), KERNEL_DS)) > + return false; > + > + if (in_atomic() /* || pagefault_disabled() */) > + return false; > + > + return true; > +} > + > +static inline void might_fault(void) > +{ > + if (!__can_fault()) > + return; > + > + might_sleep(); > + might_fault_lockdep(); > +} > + > #ifndef ARCH_HAS_NOCACHE_UACCESS > > static inline unsigned long __copy_from_user_inatomic_nocache(void *to, > diff --git a/mm/memory.c b/mm/memory.c > index 6dc1882..266610c 100644 > --- a/mm/memory.c > +++ b/mm/memory.c > @@ -4211,19 +4211,9 @@ void print_vma_addr(char *prefix, unsigned long ip) > } > > #ifdef CONFIG_PROVE_LOCKING > -void might_fault(void) > +void might_fault_lockdep(void) > { > /* > - * Some code (nfs/sunrpc) uses socket ops on kernel memory while > - * holding the mmap_sem, this is safe because kernel memory doesn't > - * get paged out, therefore we'll never actually fault, and the > - * below annotations will generate false positives. > - */ > - if (segment_eq(get_fs(), KERNEL_DS)) > - return; > - > - might_sleep(); > - /* > * it would be nicer only to annotate paths which are not under > * pagefault_disable, however that requires a larger audit and > * providing helpers like get_user_atomic. > @@ -4231,7 +4221,7 @@ void might_fault(void) > if (!in_atomic() && current->mm) > might_lock_read(¤t->mm->mmap_sem); > } > -EXPORT_SYMBOL(might_fault); > +EXPORT_SYMBOL(might_fault_lockdep); > #endif > > #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from psmtp.com (na3sys010amx155.postini.com [74.125.245.155]) by kanga.kvack.org (Postfix) with SMTP id D34276B0002 for ; Wed, 22 May 2013 16:38:57 -0400 (EDT) Date: Wed, 22 May 2013 23:38:31 +0300 From: "Michael S. Tsirkin" Subject: Re: [PATCH v2 10/10] kernel: might_fault does not imply might_sleep Message-ID: <20130522203831.GB28296@redhat.com> References: <1f85dc8e6a0149677563a2dfb4cef9a9c7eaa391.1368702323.git.mst@redhat.com> <20130516184041.GP19669@dyad.programming.kicks-ass.net> <20130519093526.GD19883@redhat.com> <20130521115734.GA9554@twins.programming.kicks-ass.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20130521115734.GA9554@twins.programming.kicks-ass.net> Sender: owner-linux-mm@kvack.org List-ID: To: Peter Zijlstra Cc: linux-kernel@vger.kernel.org, Catalin Marinas , Will Deacon , David Howells , Hirokazu Takata , Michal Simek , Koichi Yasutake , Benjamin Herrenschmidt , Paul Mackerras , Chris Metcalf , Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , x86@kernel.org, Arnd Bergmann , linux-arm-kernel@lists.infradead.org, linux-m32r@ml.linux-m32r.org, linux-m32r-ja@ml.linux-m32r.org, microblaze-uclinux@itee.uq.edu.au, linux-am33-list@redhat.com, linuxppc-dev@lists.ozlabs.org, linux-arch@vger.kernel.org, linux-mm@kvack.org, kvm@vger.kernel.org, rostedt@goodmis.org On Tue, May 21, 2013 at 01:57:34PM +0200, Peter Zijlstra wrote: > On Sun, May 19, 2013 at 12:35:26PM +0300, Michael S. Tsirkin wrote: > > > > --- a/include/linux/kernel.h > > > > +++ b/include/linux/kernel.h > > > > @@ -198,7 +198,6 @@ void might_fault(void); > > > > #else > > > > static inline void might_fault(void) > > > > { > > > > - might_sleep(); > > > > > > This removes potential resched points for PREEMPT_VOLUNTARY -- was that > > > intentional? > > > > No it's a bug. Thanks for pointing this out. > > OK so I guess it should be might_sleep_if(!in_atomic()) > > and this means might_fault would have to move from linux/kernel.h to > > linux/uaccess.h, since in_atomic() is in linux/hardirq.h > > > > Makes sense? > > So the only difference between PROVE_LOCKING and not should be the > might_lock_read() thing; so how about something like this? So the problem with the below is that might_fault is needed in asm/uaccess.h. I'm still trying various approaches but the dependencies there are very complex. > --- > include/linux/kernel.h | 7 ++----- > include/linux/uaccess.h | 26 ++++++++++++++++++++++++++ > mm/memory.c | 14 ++------------ > 3 files changed, 30 insertions(+), 17 deletions(-) > > diff --git a/include/linux/kernel.h b/include/linux/kernel.h > index e96329c..70812f4 100644 > --- a/include/linux/kernel.h > +++ b/include/linux/kernel.h > @@ -194,12 +194,9 @@ extern int _cond_resched(void); > }) > > #ifdef CONFIG_PROVE_LOCKING > -void might_fault(void); > +void might_fault_lockdep(void); > #else > -static inline void might_fault(void) > -{ > - might_sleep(); > -} > +static inline void might_fault_lockdep(void) { } > #endif > > extern struct atomic_notifier_head panic_notifier_list; > diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h > index 5ca0951..50a2cc9 100644 > --- a/include/linux/uaccess.h > +++ b/include/linux/uaccess.h > @@ -38,6 +38,32 @@ static inline void pagefault_enable(void) > preempt_check_resched(); > } > > +static inline bool __can_fault(void) > +{ > + /* > + * Some code (nfs/sunrpc) uses socket ops on kernel memory while > + * holding the mmap_sem, this is safe because kernel memory doesn't > + * get paged out, therefore we'll never actually fault, and the > + * below annotations will generate false positives. > + */ > + if (segment_eq(get_fs(), KERNEL_DS)) > + return false; > + > + if (in_atomic() /* || pagefault_disabled() */) > + return false; > + > + return true; > +} > + > +static inline void might_fault(void) > +{ > + if (!__can_fault()) > + return; > + > + might_sleep(); > + might_fault_lockdep(); > +} > + > #ifndef ARCH_HAS_NOCACHE_UACCESS > > static inline unsigned long __copy_from_user_inatomic_nocache(void *to, > diff --git a/mm/memory.c b/mm/memory.c > index 6dc1882..266610c 100644 > --- a/mm/memory.c > +++ b/mm/memory.c > @@ -4211,19 +4211,9 @@ void print_vma_addr(char *prefix, unsigned long ip) > } > > #ifdef CONFIG_PROVE_LOCKING > -void might_fault(void) > +void might_fault_lockdep(void) > { > /* > - * Some code (nfs/sunrpc) uses socket ops on kernel memory while > - * holding the mmap_sem, this is safe because kernel memory doesn't > - * get paged out, therefore we'll never actually fault, and the > - * below annotations will generate false positives. > - */ > - if (segment_eq(get_fs(), KERNEL_DS)) > - return; > - > - might_sleep(); > - /* > * it would be nicer only to annotate paths which are not under > * pagefault_disable, however that requires a larger audit and > * providing helpers like get_user_atomic. > @@ -4231,7 +4221,7 @@ void might_fault(void) > if (!in_atomic() && current->mm) > might_lock_read(¤t->mm->mmap_sem); > } > -EXPORT_SYMBOL(might_fault); > +EXPORT_SYMBOL(might_fault_lockdep); > #endif > > #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mx1.redhat.com (mx1.redhat.com [209.132.183.28]) by ozlabs.org (Postfix) with ESMTP id 4C3062C00A2 for ; Thu, 23 May 2013 06:39:33 +1000 (EST) Date: Wed, 22 May 2013 23:38:31 +0300 From: "Michael S. Tsirkin" To: Peter Zijlstra Subject: Re: [PATCH v2 10/10] kernel: might_fault does not imply might_sleep Message-ID: <20130522203831.GB28296@redhat.com> References: <1f85dc8e6a0149677563a2dfb4cef9a9c7eaa391.1368702323.git.mst@redhat.com> <20130516184041.GP19669@dyad.programming.kicks-ass.net> <20130519093526.GD19883@redhat.com> <20130521115734.GA9554@twins.programming.kicks-ass.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <20130521115734.GA9554@twins.programming.kicks-ass.net> Cc: linux-m32r-ja@ml.linux-m32r.org, kvm@vger.kernel.org, Catalin Marinas , Will Deacon , David Howells , linux-mm@kvack.org, Paul Mackerras , "H. Peter Anvin" , linux-arch@vger.kernel.org, linux-am33-list@redhat.com, Hirokazu Takata , x86@kernel.org, Ingo Molnar , Arnd Bergmann , microblaze-uclinux@itee.uq.edu.au, Chris Metcalf , rostedt@goodmis.org, Thomas Gleixner , linux-arm-kernel@lists.infradead.org, Michal Simek , linux-m32r@ml.linux-m32r.org, linux-kernel@vger.kernel.org, Koichi Yasutake , linuxppc-dev@lists.ozlabs.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Tue, May 21, 2013 at 01:57:34PM +0200, Peter Zijlstra wrote: > On Sun, May 19, 2013 at 12:35:26PM +0300, Michael S. Tsirkin wrote: > > > > --- a/include/linux/kernel.h > > > > +++ b/include/linux/kernel.h > > > > @@ -198,7 +198,6 @@ void might_fault(void); > > > > #else > > > > static inline void might_fault(void) > > > > { > > > > - might_sleep(); > > > > > > This removes potential resched points for PREEMPT_VOLUNTARY -- was that > > > intentional? > > > > No it's a bug. Thanks for pointing this out. > > OK so I guess it should be might_sleep_if(!in_atomic()) > > and this means might_fault would have to move from linux/kernel.h to > > linux/uaccess.h, since in_atomic() is in linux/hardirq.h > > > > Makes sense? > > So the only difference between PROVE_LOCKING and not should be the > might_lock_read() thing; so how about something like this? So the problem with the below is that might_fault is needed in asm/uaccess.h. I'm still trying various approaches but the dependencies there are very complex. > --- > include/linux/kernel.h | 7 ++----- > include/linux/uaccess.h | 26 ++++++++++++++++++++++++++ > mm/memory.c | 14 ++------------ > 3 files changed, 30 insertions(+), 17 deletions(-) > > diff --git a/include/linux/kernel.h b/include/linux/kernel.h > index e96329c..70812f4 100644 > --- a/include/linux/kernel.h > +++ b/include/linux/kernel.h > @@ -194,12 +194,9 @@ extern int _cond_resched(void); > }) > > #ifdef CONFIG_PROVE_LOCKING > -void might_fault(void); > +void might_fault_lockdep(void); > #else > -static inline void might_fault(void) > -{ > - might_sleep(); > -} > +static inline void might_fault_lockdep(void) { } > #endif > > extern struct atomic_notifier_head panic_notifier_list; > diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h > index 5ca0951..50a2cc9 100644 > --- a/include/linux/uaccess.h > +++ b/include/linux/uaccess.h > @@ -38,6 +38,32 @@ static inline void pagefault_enable(void) > preempt_check_resched(); > } > > +static inline bool __can_fault(void) > +{ > + /* > + * Some code (nfs/sunrpc) uses socket ops on kernel memory while > + * holding the mmap_sem, this is safe because kernel memory doesn't > + * get paged out, therefore we'll never actually fault, and the > + * below annotations will generate false positives. > + */ > + if (segment_eq(get_fs(), KERNEL_DS)) > + return false; > + > + if (in_atomic() /* || pagefault_disabled() */) > + return false; > + > + return true; > +} > + > +static inline void might_fault(void) > +{ > + if (!__can_fault()) > + return; > + > + might_sleep(); > + might_fault_lockdep(); > +} > + > #ifndef ARCH_HAS_NOCACHE_UACCESS > > static inline unsigned long __copy_from_user_inatomic_nocache(void *to, > diff --git a/mm/memory.c b/mm/memory.c > index 6dc1882..266610c 100644 > --- a/mm/memory.c > +++ b/mm/memory.c > @@ -4211,19 +4211,9 @@ void print_vma_addr(char *prefix, unsigned long ip) > } > > #ifdef CONFIG_PROVE_LOCKING > -void might_fault(void) > +void might_fault_lockdep(void) > { > /* > - * Some code (nfs/sunrpc) uses socket ops on kernel memory while > - * holding the mmap_sem, this is safe because kernel memory doesn't > - * get paged out, therefore we'll never actually fault, and the > - * below annotations will generate false positives. > - */ > - if (segment_eq(get_fs(), KERNEL_DS)) > - return; > - > - might_sleep(); > - /* > * it would be nicer only to annotate paths which are not under > * pagefault_disable, however that requires a larger audit and > * providing helpers like get_user_atomic. > @@ -4231,7 +4221,7 @@ void might_fault(void) > if (!in_atomic() && current->mm) > might_lock_read(¤t->mm->mmap_sem); > } > -EXPORT_SYMBOL(might_fault); > +EXPORT_SYMBOL(might_fault_lockdep); > #endif > > #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) From mboxrd@z Thu Jan 1 00:00:00 1970 From: mst@redhat.com (Michael S. Tsirkin) Date: Wed, 22 May 2013 23:38:31 +0300 Subject: [PATCH v2 10/10] kernel: might_fault does not imply might_sleep In-Reply-To: <20130521115734.GA9554@twins.programming.kicks-ass.net> References: <1f85dc8e6a0149677563a2dfb4cef9a9c7eaa391.1368702323.git.mst@redhat.com> <20130516184041.GP19669@dyad.programming.kicks-ass.net> <20130519093526.GD19883@redhat.com> <20130521115734.GA9554@twins.programming.kicks-ass.net> Message-ID: <20130522203831.GB28296@redhat.com> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Tue, May 21, 2013 at 01:57:34PM +0200, Peter Zijlstra wrote: > On Sun, May 19, 2013 at 12:35:26PM +0300, Michael S. Tsirkin wrote: > > > > --- a/include/linux/kernel.h > > > > +++ b/include/linux/kernel.h > > > > @@ -198,7 +198,6 @@ void might_fault(void); > > > > #else > > > > static inline void might_fault(void) > > > > { > > > > - might_sleep(); > > > > > > This removes potential resched points for PREEMPT_VOLUNTARY -- was that > > > intentional? > > > > No it's a bug. Thanks for pointing this out. > > OK so I guess it should be might_sleep_if(!in_atomic()) > > and this means might_fault would have to move from linux/kernel.h to > > linux/uaccess.h, since in_atomic() is in linux/hardirq.h > > > > Makes sense? > > So the only difference between PROVE_LOCKING and not should be the > might_lock_read() thing; so how about something like this? So the problem with the below is that might_fault is needed in asm/uaccess.h. I'm still trying various approaches but the dependencies there are very complex. > --- > include/linux/kernel.h | 7 ++----- > include/linux/uaccess.h | 26 ++++++++++++++++++++++++++ > mm/memory.c | 14 ++------------ > 3 files changed, 30 insertions(+), 17 deletions(-) > > diff --git a/include/linux/kernel.h b/include/linux/kernel.h > index e96329c..70812f4 100644 > --- a/include/linux/kernel.h > +++ b/include/linux/kernel.h > @@ -194,12 +194,9 @@ extern int _cond_resched(void); > }) > > #ifdef CONFIG_PROVE_LOCKING > -void might_fault(void); > +void might_fault_lockdep(void); > #else > -static inline void might_fault(void) > -{ > - might_sleep(); > -} > +static inline void might_fault_lockdep(void) { } > #endif > > extern struct atomic_notifier_head panic_notifier_list; > diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h > index 5ca0951..50a2cc9 100644 > --- a/include/linux/uaccess.h > +++ b/include/linux/uaccess.h > @@ -38,6 +38,32 @@ static inline void pagefault_enable(void) > preempt_check_resched(); > } > > +static inline bool __can_fault(void) > +{ > + /* > + * Some code (nfs/sunrpc) uses socket ops on kernel memory while > + * holding the mmap_sem, this is safe because kernel memory doesn't > + * get paged out, therefore we'll never actually fault, and the > + * below annotations will generate false positives. > + */ > + if (segment_eq(get_fs(), KERNEL_DS)) > + return false; > + > + if (in_atomic() /* || pagefault_disabled() */) > + return false; > + > + return true; > +} > + > +static inline void might_fault(void) > +{ > + if (!__can_fault()) > + return; > + > + might_sleep(); > + might_fault_lockdep(); > +} > + > #ifndef ARCH_HAS_NOCACHE_UACCESS > > static inline unsigned long __copy_from_user_inatomic_nocache(void *to, > diff --git a/mm/memory.c b/mm/memory.c > index 6dc1882..266610c 100644 > --- a/mm/memory.c > +++ b/mm/memory.c > @@ -4211,19 +4211,9 @@ void print_vma_addr(char *prefix, unsigned long ip) > } > > #ifdef CONFIG_PROVE_LOCKING > -void might_fault(void) > +void might_fault_lockdep(void) > { > /* > - * Some code (nfs/sunrpc) uses socket ops on kernel memory while > - * holding the mmap_sem, this is safe because kernel memory doesn't > - * get paged out, therefore we'll never actually fault, and the > - * below annotations will generate false positives. > - */ > - if (segment_eq(get_fs(), KERNEL_DS)) > - return; > - > - might_sleep(); > - /* > * it would be nicer only to annotate paths which are not under > * pagefault_disable, however that requires a larger audit and > * providing helpers like get_user_atomic. > @@ -4231,7 +4221,7 @@ void might_fault(void) > if (!in_atomic() && current->mm) > might_lock_read(¤t->mm->mmap_sem); > } > -EXPORT_SYMBOL(might_fault); > +EXPORT_SYMBOL(might_fault_lockdep); > #endif > > #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)