[GIT PULL, v2] core kernel fixes

[GIT PULL, v2] core kernel fixes

[Ingo Molnar]

Linus,

Please pull the latest core-fixes-for-linus-2 git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-fixes-for-linus-2

This excludes the "futex: futex mapping needs to be writable" commit 
you objected to. Test-built and test-booted.

 Thanks,

	Ingo

------------------>
Ingo Molnar (1):
      lockdep: increase MAX_LOCKDEP_ENTRIES and MAX_LOCKDEP_CHAINS


 kernel/lockdep_internals.h |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h
index a2cc7e9..699a2ac 100644
--- a/kernel/lockdep_internals.h
+++ b/kernel/lockdep_internals.h
@@ -54,9 +54,9 @@ enum {
  * table (if it's not there yet), and we check it for lock order
  * conflicts and deadlocks.
  */
-#define MAX_LOCKDEP_ENTRIES	8192UL
+#define MAX_LOCKDEP_ENTRIES	16384UL
 
-#define MAX_LOCKDEP_CHAINS_BITS	14
+#define MAX_LOCKDEP_CHAINS_BITS	15
 #define MAX_LOCKDEP_CHAINS	(1UL << MAX_LOCKDEP_CHAINS_BITS)
 
 #define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5)

[GIT PULL, v2] core kernel fixes

[Ingo Molnar]

Linus,

Please pull the latest core-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-fixes-for-linus

Left out the futex commit, it's being worked on.

 Thanks,

	Ingo

------------------>
Joerg Roedel (2):
      dma-debug: check for sg_call_ents in best-fit algorithm too
      dma-debug: be more careful when building reference entries

Peter Zijlstra (1):
      lockdep: Select frame pointers on x86


 lib/Kconfig.debug |    2 +-
 lib/dma-debug.c   |  149 +++++++++++++++++++++++++++++++++++------------------
 2 files changed, 99 insertions(+), 52 deletions(-)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 6cdcf38..3be4b7c 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -440,7 +440,7 @@ config LOCKDEP
 	bool
 	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
 	select STACKTRACE
-	select FRAME_POINTER if !X86 && !MIPS && !PPC && !ARM_UNWIND && !S390
+	select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390
 	select KALLSYMS
 	select KALLSYMS_ALL
 
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index ad65fc0..3b93129 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -262,11 +262,12 @@ static struct dma_debug_entry *hash_bucket_find(struct hash_bucket *bucket,
 		 */
 		matches += 1;
 		match_lvl = 0;
-		entry->size      == ref->size      ? ++match_lvl : match_lvl;
-		entry->type      == ref->type      ? ++match_lvl : match_lvl;
-		entry->direction == ref->direction ? ++match_lvl : match_lvl;
+		entry->size         == ref->size         ? ++match_lvl : 0;
+		entry->type         == ref->type         ? ++match_lvl : 0;
+		entry->direction    == ref->direction    ? ++match_lvl : 0;
+		entry->sg_call_ents == ref->sg_call_ents ? ++match_lvl : 0;
 
-		if (match_lvl == 3) {
+		if (match_lvl == 4) {
 			/* perfect-fit - return the result */
 			return entry;
 		} else if (match_lvl > last_lvl) {
@@ -873,72 +874,68 @@ static void check_for_illegal_area(struct device *dev, void *addr, u64 size)
 				"[addr=%p] [size=%llu]\n", addr, size);
 }
 
-static void check_sync(struct device *dev, dma_addr_t addr,
-		       u64 size, u64 offset, int direction, bool to_cpu)
+static void check_sync(struct device *dev,
+		       struct dma_debug_entry *ref,
+		       bool to_cpu)
 {
-	struct dma_debug_entry ref = {
-		.dev            = dev,
-		.dev_addr       = addr,
-		.size           = size,
-		.direction      = direction,
-	};
 	struct dma_debug_entry *entry;
 	struct hash_bucket *bucket;
 	unsigned long flags;
 
-	bucket = get_hash_bucket(&ref, &flags);
+	bucket = get_hash_bucket(ref, &flags);
 
-	entry = hash_bucket_find(bucket, &ref);
+	entry = hash_bucket_find(bucket, ref);
 
 	if (!entry) {
 		err_printk(dev, NULL, "DMA-API: device driver tries "
 				"to sync DMA memory it has not allocated "
 				"[device address=0x%016llx] [size=%llu bytes]\n",
-				(unsigned long long)addr, size);
+				(unsigned long long)ref->dev_addr, ref->size);
 		goto out;
 	}
 
-	if ((offset + size) > entry->size) {
+	if (ref->size > entry->size) {
 		err_printk(dev, entry, "DMA-API: device driver syncs"
 				" DMA memory outside allocated range "
 				"[device address=0x%016llx] "
-				"[allocation size=%llu bytes] [sync offset=%llu] "
-				"[sync size=%llu]\n", entry->dev_addr, entry->size,
-				offset, size);
+				"[allocation size=%llu bytes] "
+				"[sync offset+size=%llu]\n",
+				entry->dev_addr, entry->size,
+				ref->size);
 	}
 
-	if (direction != entry->direction) {
+	if (ref->direction != entry->direction) {
 		err_printk(dev, entry, "DMA-API: device driver syncs "
 				"DMA memory with different direction "
 				"[device address=0x%016llx] [size=%llu bytes] "
 				"[mapped with %s] [synced with %s]\n",
-				(unsigned long long)addr, entry->size,
+				(unsigned long long)ref->dev_addr, entry->size,
 				dir2name[entry->direction],
-				dir2name[direction]);
+				dir2name[ref->direction]);
 	}
 
 	if (entry->direction == DMA_BIDIRECTIONAL)
 		goto out;
 
 	if (to_cpu && !(entry->direction == DMA_FROM_DEVICE) &&
-		      !(direction == DMA_TO_DEVICE))
+		      !(ref->direction == DMA_TO_DEVICE))
 		err_printk(dev, entry, "DMA-API: device driver syncs "
 				"device read-only DMA memory for cpu "
 				"[device address=0x%016llx] [size=%llu bytes] "
 				"[mapped with %s] [synced with %s]\n",
-				(unsigned long long)addr, entry->size,
+				(unsigned long long)ref->dev_addr, entry->size,
 				dir2name[entry->direction],
-				dir2name[direction]);
+				dir2name[ref->direction]);
 
 	if (!to_cpu && !(entry->direction == DMA_TO_DEVICE) &&
-		       !(direction == DMA_FROM_DEVICE))
+		       !(ref->direction == DMA_FROM_DEVICE))
 		err_printk(dev, entry, "DMA-API: device driver syncs "
 				"device write-only DMA memory to device "
 				"[device address=0x%016llx] [size=%llu bytes] "
 				"[mapped with %s] [synced with %s]\n",
-				(unsigned long long)addr, entry->size,
+				(unsigned long long)ref->dev_addr, entry->size,
 				dir2name[entry->direction],
-				dir2name[direction]);
+				dir2name[ref->direction]);
 
 out:
 	put_hash_bucket(bucket, &flags);
@@ -1036,19 +1033,16 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
 }
 EXPORT_SYMBOL(debug_dma_map_sg);
 
-static int get_nr_mapped_entries(struct device *dev, struct scatterlist *s)
+static int get_nr_mapped_entries(struct device *dev,
+				 struct dma_debug_entry *ref)
 {
-	struct dma_debug_entry *entry, ref;
+	struct dma_debug_entry *entry;
 	struct hash_bucket *bucket;
 	unsigned long flags;
 	int mapped_ents;
 
-	ref.dev      = dev;
-	ref.dev_addr = sg_dma_address(s);
-	ref.size     = sg_dma_len(s),
-
-	bucket       = get_hash_bucket(&ref, &flags);
-	entry        = hash_bucket_find(bucket, &ref);
+	bucket       = get_hash_bucket(ref, &flags);
+	entry        = hash_bucket_find(bucket, ref);
 	mapped_ents  = 0;
 
 	if (entry)
@@ -1076,16 +1070,14 @@ void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 			.dev_addr       = sg_dma_address(s),
 			.size           = sg_dma_len(s),
 			.direction      = dir,
-			.sg_call_ents   = 0,
+			.sg_call_ents   = nelems,
 		};
 
 		if (mapped_ents && i >= mapped_ents)
 			break;
 
-		if (!i) {
-			ref.sg_call_ents = nelems;
-			mapped_ents = get_nr_mapped_entries(dev, s);
-		}
+		if (!i)
+			mapped_ents = get_nr_mapped_entries(dev, &ref);
 
 		check_unmap(&ref);
 	}
@@ -1140,10 +1132,19 @@ EXPORT_SYMBOL(debug_dma_free_coherent);
 void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
 				   size_t size, int direction)
 {
+	struct dma_debug_entry ref;
+
 	if (unlikely(global_disable))
 		return;
 
-	check_sync(dev, dma_handle, size, 0, direction, true);
+	ref.type         = dma_debug_single;
+	ref.dev          = dev;
+	ref.dev_addr     = dma_handle;
+	ref.size         = size;
+	ref.direction    = direction;
+	ref.sg_call_ents = 0;
+
+	check_sync(dev, &ref, true);
 }
 EXPORT_SYMBOL(debug_dma_sync_single_for_cpu);
 
@@ -1151,10 +1152,19 @@ void debug_dma_sync_single_for_device(struct device *dev,
 				      dma_addr_t dma_handle, size_t size,
 				      int direction)
 {
+	struct dma_debug_entry ref;
+
 	if (unlikely(global_disable))
 		return;
 
-	check_sync(dev, dma_handle, size, 0, direction, false);
+	ref.type         = dma_debug_single;
+	ref.dev          = dev;
+	ref.dev_addr     = dma_handle;
+	ref.size         = size;
+	ref.direction    = direction;
+	ref.sg_call_ents = 0;
+
+	check_sync(dev, &ref, false);
 }
 EXPORT_SYMBOL(debug_dma_sync_single_for_device);
 
@@ -1163,10 +1173,19 @@ void debug_dma_sync_single_range_for_cpu(struct device *dev,
 					 unsigned long offset, size_t size,
 					 int direction)
 {
+	struct dma_debug_entry ref;
+
 	if (unlikely(global_disable))
 		return;
 
-	check_sync(dev, dma_handle, size, offset, direction, true);
+	ref.type         = dma_debug_single;
+	ref.dev          = dev;
+	ref.dev_addr     = dma_handle;
+	ref.size         = offset + size;
+	ref.direction    = direction;
+	ref.sg_call_ents = 0;
+
+	check_sync(dev, &ref, true);
 }
 EXPORT_SYMBOL(debug_dma_sync_single_range_for_cpu);
 
@@ -1175,10 +1194,19 @@ void debug_dma_sync_single_range_for_device(struct device *dev,
 					    unsigned long offset,
 					    size_t size, int direction)
 {
+	struct dma_debug_entry ref;
+
 	if (unlikely(global_disable))
 		return;
 
-	check_sync(dev, dma_handle, size, offset, direction, false);
+	ref.type         = dma_debug_single;
+	ref.dev          = dev;
+	ref.dev_addr     = dma_handle;
+	ref.size         = offset + size;
+	ref.direction    = direction;
+	ref.sg_call_ents = 0;
+
+	check_sync(dev, &ref, false);
 }
 EXPORT_SYMBOL(debug_dma_sync_single_range_for_device);
 
@@ -1192,14 +1220,24 @@ void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 		return;
 
 	for_each_sg(sg, s, nelems, i) {
+
+		struct dma_debug_entry ref = {
+			.type           = dma_debug_sg,
+			.dev            = dev,
+			.paddr          = sg_phys(s),
+			.dev_addr       = sg_dma_address(s),
+			.size           = sg_dma_len(s),
+			.direction      = direction,
+			.sg_call_ents   = nelems,
+		};
+
 		if (!i)
-			mapped_ents = get_nr_mapped_entries(dev, s);
+			mapped_ents = get_nr_mapped_entries(dev, &ref);
 
 		if (i >= mapped_ents)
 			break;
 
-		check_sync(dev, sg_dma_address(s), sg_dma_len(s), 0,
-			   direction, true);
+		check_sync(dev, &ref, true);
 	}
 }
 EXPORT_SYMBOL(debug_dma_sync_sg_for_cpu);
@@ -1214,14 +1252,23 @@ void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 		return;
 
 	for_each_sg(sg, s, nelems, i) {
+
+		struct dma_debug_entry ref = {
+			.type           = dma_debug_sg,
+			.dev            = dev,
+			.paddr          = sg_phys(s),
+			.dev_addr       = sg_dma_address(s),
+			.size           = sg_dma_len(s),
+			.direction      = direction,
+			.sg_call_ents   = nelems,
+		};
 		if (!i)
-			mapped_ents = get_nr_mapped_entries(dev, s);
+			mapped_ents = get_nr_mapped_entries(dev, &ref);
 
 		if (i >= mapped_ents)
 			break;
 
-		check_sync(dev, sg_dma_address(s), sg_dma_len(s), 0,
-			   direction, false);
+		check_sync(dev, &ref, false);
 	}
 }
 EXPORT_SYMBOL(debug_dma_sync_sg_for_device);

[GIT PULL, v2] core kernel fixes

[Ingo Molnar]

Linus,

Please pull the v2 core-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-fixes-for-linus-2

This has the overlap() bug(s) fixed. [ You might want to hold off on 
pulling this for a few hours, just in case the fresh dma-debug.c fix 
has any unexpected (and unprecedented) breakages. ]

 Thanks,

	Ingo

------------------>
Arnd Bergmann (1):
      signals: declare sys_rt_tgsigqueueinfo in syscalls.h

Ingo Molnar (2):
      dma-debug: Put all hash-chain locks into the same lock class
      dma-debug: Fix the overlap() function to be correct and readable

Joerg Roedel (1):
      dma-debug: fix off-by-one error in overlap function

Maynard Johnson (1):
      oprofile: reset bt_lost_no_mapping with other stats

Paul E. McKenney (1):
      rcu: Mark Hierarchical RCU no longer experimental

Robert Richter (1):
      x86/oprofile: rename kernel parameter for architectural perfmon to arch_perfmon


 Documentation/kernel-parameters.txt |    4 ++--
 arch/x86/oprofile/nmi_int.c         |    2 +-
 drivers/oprofile/oprofile_stats.c   |    1 +
 include/linux/syscalls.h            |    2 ++
 kernel/rcutree.c                    |    3 +--
 lib/dma-debug.c                     |   26 +++++++++++++-------------
 6 files changed, 20 insertions(+), 18 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 92e1ab8..c59e965 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1728,8 +1728,8 @@ and is between 256 and 4096 characters. It is defined in the file
 	oprofile.cpu_type=	Force an oprofile cpu type
 			This might be useful if you have an older oprofile
 			userland or if you want common events.
-			Format: { archperfmon }
-			archperfmon: [X86] Force use of architectural
+			Format: { arch_perfmon }
+			arch_perfmon: [X86] Force use of architectural
 				perfmon on Intel CPUs instead of the
 				CPU specific event set.
 
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index b07dd8d..89b9a5c 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -390,7 +390,7 @@ static int __init p4_init(char **cpu_type)
 static int force_arch_perfmon;
 static int force_cpu_type(const char *str, struct kernel_param *kp)
 {
-	if (!strcmp(str, "archperfmon")) {
+	if (!strcmp(str, "arch_perfmon")) {
 		force_arch_perfmon = 1;
 		printk(KERN_INFO "oprofile: forcing architectural perfmon\n");
 	}
diff --git a/drivers/oprofile/oprofile_stats.c b/drivers/oprofile/oprofile_stats.c
index e1f6ce0..3c2270a 100644
--- a/drivers/oprofile/oprofile_stats.c
+++ b/drivers/oprofile/oprofile_stats.c
@@ -33,6 +33,7 @@ void oprofile_reset_stats(void)
 	atomic_set(&oprofile_stats.sample_lost_no_mm, 0);
 	atomic_set(&oprofile_stats.sample_lost_no_mapping, 0);
 	atomic_set(&oprofile_stats.event_lost_overflow, 0);
+	atomic_set(&oprofile_stats.bt_lost_no_mapping, 0);
 }
 
 
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index fa4242c..80de700 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -321,6 +321,8 @@ asmlinkage long sys_rt_sigtimedwait(const sigset_t __user *uthese,
 				siginfo_t __user *uinfo,
 				const struct timespec __user *uts,
 				size_t sigsetsize);
+asmlinkage long sys_rt_tgsigqueueinfo(pid_t tgid, pid_t  pid, int sig,
+		siginfo_t __user *uinfo);
 asmlinkage long sys_kill(int pid, int sig);
 asmlinkage long sys_tgkill(int tgid, int pid, int sig);
 asmlinkage long sys_tkill(int pid, int sig);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 0dccfbb..7717b95 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1533,7 +1533,7 @@ void __init __rcu_init(void)
 	int j;
 	struct rcu_node *rnp;
 
-	printk(KERN_WARNING "Experimental hierarchical RCU implementation.\n");
+	printk(KERN_INFO "Hierarchical RCU implementation.\n");
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 	printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
@@ -1546,7 +1546,6 @@ void __init __rcu_init(void)
 		rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE, (void *)(long)i);
 	/* Register notifier for non-boot CPUs */
 	register_cpu_notifier(&rcu_nb);
-	printk(KERN_WARNING "Experimental hierarchical RCU init done.\n");
 }
 
 module_param(blimit, int, 0);
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 3b93129..65b0d99 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -716,7 +716,7 @@ void dma_debug_init(u32 num_entries)
 
 	for (i = 0; i < HASH_SIZE; ++i) {
 		INIT_LIST_HEAD(&dma_entry_hash[i].list);
-		dma_entry_hash[i].lock = SPIN_LOCK_UNLOCKED;
+		spin_lock_init(&dma_entry_hash[i].lock);
 	}
 
 	if (dma_debug_fs_init() != 0) {
@@ -856,22 +856,21 @@ static void check_for_stack(struct device *dev, void *addr)
 				"stack [addr=%p]\n", addr);
 }
 
-static inline bool overlap(void *addr, u64 size, void *start, void *end)
+static inline bool overlap(void *addr, unsigned long len, void *start, void *end)
 {
-	void *addr2 = (char *)addr + size;
+	unsigned long a1 = (unsigned long)addr;
+	unsigned long b1 = a1 + len;
+	unsigned long a2 = (unsigned long)start;
+	unsigned long b2 = (unsigned long)end;
 
-	return ((addr >= start && addr < end) ||
-		(addr2 >= start && addr2 < end) ||
-		((addr < start) && (addr2 >= end)));
+	return !(b1 <= a2 || a1 >= b2);
 }
 
-static void check_for_illegal_area(struct device *dev, void *addr, u64 size)
+static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len)
 {
-	if (overlap(addr, size, _text, _etext) ||
-	    overlap(addr, size, __start_rodata, __end_rodata))
-		err_printk(dev, NULL, "DMA-API: device driver maps "
-				"memory from kernel text or rodata "
-				"[addr=%p] [size=%llu]\n", addr, size);
+	if (overlap(addr, len, _text, _etext) ||
+	    overlap(addr, len, __start_rodata, __end_rodata))
+		err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len);
 }
 
 static void check_sync(struct device *dev,
@@ -969,7 +968,8 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
 		entry->type = dma_debug_single;
 
 	if (!PageHighMem(page)) {
-		void *addr = ((char *)page_address(page)) + offset;
+		void *addr = page_address(page) + offset;
+
 		check_for_stack(dev, addr);
 		check_for_illegal_area(dev, addr, size);
 	}

[GIT PULL, v2] core kernel fixes

[Ingo Molnar]

* Darren Hart <dvhltc@us.ibm.com> wrote:

> Ingo Molnar wrote:
>> Linus,
>>
>> Please pull the latest core-fixes-for-linus git tree from:
>>
>>    git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-fixes-for-linus
>>
>>  Thanks,
>>
>> 	Ingo
>>
>> ------------------>
>> Darren Hart (2):
>>       rtmutex: Avoid deadlock in rt_mutex_start_proxy_lock()
>>       futex: Update woken requeued futex_q lock_ptr
>
> Ingo, this still has the older version of:
>
> "futex: Update woken requeued futex_q lock_ptr"
>
> Please update to the resend on Aug 7:

Resend usual means 'same stuff again' and since i already had the 
first patch i skipped it. The usual way is to put 'v2' into the 
subject or something. Anyway - v2 needs re-testing.

Linus, please pull this shortened tree instead (it has the final 
commit removed):

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-fixes-for-linus-2

 Thanks,

	Ingo

------------------>
Darren Hart (1):
      rtmutex: Avoid deadlock in rt_mutex_start_proxy_lock()

Li Zefan (2):
      lockdep: Fix file mode of lock_stat
      lockdep: Fix typos in documentation


 Documentation/lockdep-design.txt |    6 +++---
 kernel/lockdep_proc.c            |    3 ++-
 kernel/rtmutex.c                 |    4 +---
 3 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/Documentation/lockdep-design.txt b/Documentation/lockdep-design.txt
index e20d913..abf768c 100644
--- a/Documentation/lockdep-design.txt
+++ b/Documentation/lockdep-design.txt
@@ -30,9 +30,9 @@ State
 The validator tracks lock-class usage history into 4n + 1 separate state bits:
 
 - 'ever held in STATE context'
-- 'ever head as readlock in STATE context'
-- 'ever head with STATE enabled'
-- 'ever head as readlock with STATE enabled'
+- 'ever held as readlock in STATE context'
+- 'ever held with STATE enabled'
+- 'ever held as readlock with STATE enabled'
 
 Where STATE can be either one of (kernel/lockdep_states.h)
  - hardirq
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index d7135aa..e94caa6 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -758,7 +758,8 @@ static int __init lockdep_proc_init(void)
 		    &proc_lockdep_stats_operations);
 
 #ifdef CONFIG_LOCK_STAT
-	proc_create("lock_stat", S_IRUSR, NULL, &proc_lock_stat_operations);
+	proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL,
+		    &proc_lock_stat_operations);
 #endif
 
 	return 0;
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index fcd107a..29bd4ba 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -1039,16 +1039,14 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 	if (!rt_mutex_owner(lock) || try_to_steal_lock(lock, task)) {
 		/* We got the lock for task. */
 		debug_rt_mutex_lock(lock);
-
 		rt_mutex_set_owner(lock, task, 0);
-
+		spin_unlock(&lock->wait_lock);
 		rt_mutex_deadlock_account_lock(lock, task);
 		return 1;
 	}
 
 	ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
 
-
 	if (ret && !waiter->task) {
 		/*
 		 * Reset the return value. We might have