linux-kernel - [PATCH RFC 01/15] uaccess: count pagefault_disable() levels in pagefault

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1430934639-2131-2-git-send-email-dahi@linux.vnet.ibm.com>
Date:	Wed,  6 May 2015 19:50:25 +0200
From:	David Hildenbrand <dahi@...ux.vnet.ibm.com>
To:	linux-kernel@...r.kernel.org
Cc:	dahi@...ux.vnet.ibm.com, mingo@...hat.com, peterz@...radead.org,
	yang.shi@...driver.com, bigeasy@...utronix.de,
	benh@...nel.crashing.org, paulus@...ba.org,
	akpm@...ux-foundation.org, heiko.carstens@...ibm.com,
	schwidefsky@...ibm.com, borntraeger@...ibm.com, mst@...hat.com,
	tglx@...utronix.de, David.Laight@...LAB.COM, hughd@...gle.com,
	hocko@...e.cz, ralf@...ux-mips.org, herbert@...dor.apana.org.au,
	linux@....linux.org.uk, airlied@...ux.ie, daniel.vetter@...el.com,
	linux-mm@...ck.org, linux-arch@...r.kernel.org
Subject: [PATCH RFC 01/15] uaccess: count pagefault_disable() levels in pagefault_disabled

Until now, pagefault_disable()/pagefault_enabled() used the preempt
count to track whether in an environment with pagefaults disabled (can
be queried via in_atomic()).

This patch introduces a separate counter in task_struct to count the
level of pagefault_disable() calls. We'll keep manipulating the preempt
count to retain compatibility to existing pagefault handlers.

It is now possible to verify whether in a pagefault_disable() envionment
by calling pagefault_disabled(). In contrast to in_atomic() it will not
be influenced by preempt_enable()/preempt_disable().

This patch is based on a patch from Ingo Molnar.

Signed-off-by: David Hildenbrand <dahi@...ux.vnet.ibm.com>
---
 include/linux/sched.h   |  1 +
 include/linux/uaccess.h | 36 +++++++++++++++++++++++++++++-------
 kernel/fork.c           |  3 +++
 3 files changed, 33 insertions(+), 7 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index ede26ca..75778cb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1724,6 +1724,7 @@ struct task_struct {
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 	unsigned long	task_state_change;
 #endif
+	int pagefault_disabled;
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index ecd3319..23290cc 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -2,20 +2,36 @@
 #define __LINUX_UACCESS_H__
 
 #include <linux/preempt.h>
+#include <linux/sched.h>
 #include <asm/uaccess.h>
 
+static __always_inline void pagefault_disabled_inc(void)
+{
+	current->pagefault_disabled++;
+}
+
+static __always_inline void pagefault_disabled_dec(void)
+{
+	current->pagefault_disabled--;
+	WARN_ON(current->pagefault_disabled < 0);
+}
+
 /*
- * These routines enable/disable the pagefault handler in that
- * it will not take any locks and go straight to the fixup table.
+ * These routines enable/disable the pagefault handler. If disabled, it will
+ * not take any locks and go straight to the fixup table.
+ *
+ * We increase the preempt and the pagefault count, to be able to distinguish
+ * whether we run in simple atomic context or in a real pagefault_disable()
+ * context.
+ *
+ * For now, after pagefault_disabled() has been called, we run in atomic
+ * context. User access methods will not sleep.
  *
- * They have great resemblance to the preempt_disable/enable calls
- * and in fact they are identical; this is because currently there is
- * no other way to make the pagefault handlers do this. So we do
- * disable preemption but we don't necessarily care about that.
  */
 static inline void pagefault_disable(void)
 {
 	preempt_count_inc();
+	pagefault_disabled_inc();
 	/*
 	 * make sure to have issued the store before a pagefault
 	 * can hit.
@@ -25,18 +41,24 @@ static inline void pagefault_disable(void)
 
 static inline void pagefault_enable(void)
 {
-#ifndef CONFIG_PREEMPT
 	/*
 	 * make sure to issue those last loads/stores before enabling
 	 * the pagefault handler again.
 	 */
 	barrier();
+	pagefault_disabled_dec();
+#ifndef CONFIG_PREEMPT
 	preempt_count_dec();
 #else
 	preempt_enable();
 #endif
 }
 
+/*
+ * Is the pagefault handler disabled? If so, user access methods will not sleep.
+ */
+#define pagefault_disabled() (current->pagefault_disabled != 0)
+
 #ifndef ARCH_HAS_NOCACHE_UACCESS
 
 static inline unsigned long __copy_from_user_inatomic_nocache(void *to,
diff --git a/kernel/fork.c b/kernel/fork.c
index 03c1eaa..c344d27 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1396,6 +1396,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->hardirq_context = 0;
 	p->softirq_context = 0;
 #endif
+
+	p->pagefault_disabled = 0;
+
 #ifdef CONFIG_LOCKDEP
 	p->lockdep_depth = 0; /* no locks held yet */
 	p->curr_chain_key = 0;
-- 
2.1.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/