[PATCH] spinlock consolidation

This patch (written by me and also containing many suggestions of Arjan van
de Ven) does a major cleanup of the spinlock code.  It does the following
things:

 - consolidates and enhances the spinlock/rwlock debugging code

 - simplifies the asm/spinlock.h files

 - encapsulates the raw spinlock type and moves generic spinlock
   features (such as ->break_lock) into the generic code.

 - cleans up the spinlock code hierarchy to get rid of the spaghetti.

Most notably there's now only a single variant of the debugging code,
located in lib/spinlock_debug.c.  (previously we had one SMP debugging
variant per architecture, plus a separate generic one for UP builds)

Also, i've enhanced the rwlock debugging facility, it will now track
write-owners.  There is new spinlock-owner/CPU-tracking on SMP builds too.
All locks have lockup detection now, which will work for both soft and hard
spin/rwlock lockups.

The arch-level include files now only contain the minimally necessary
subset of the spinlock code - all the rest that can be generalized now
lives in the generic headers:

 include/asm-i386/spinlock_types.h       |   16
 include/asm-x86_64/spinlock_types.h     |   16

I have also split up the various spinlock variants into separate files,
making it easier to see which does what. The new layout is:

   SMP                         |  UP
   ----------------------------|-----------------------------------
   asm/spinlock_types_smp.h    |  linux/spinlock_types_up.h
   linux/spinlock_types.h      |  linux/spinlock_types.h
   asm/spinlock_smp.h          |  linux/spinlock_up.h
   linux/spinlock_api_smp.h    |  linux/spinlock_api_up.h
   linux/spinlock.h            |  linux/spinlock.h

/*
 * here's the role of the various spinlock/rwlock related include files:
 *
 * on SMP builds:
 *
 *  asm/spinlock_types.h: contains the raw_spinlock_t/raw_rwlock_t and the
 *                        initializers
 *
 *  linux/spinlock_types.h:
 *                        defines the generic type and initializers
 *
 *  asm/spinlock.h:       contains the __raw_spin_*()/etc. lowlevel
 *                        implementations, mostly inline assembly code
 *
 *   (also included on UP-debug builds:)
 *
 *  linux/spinlock_api_smp.h:
 *                        contains the prototypes for the _spin_*() APIs.
 *
 *  linux/spinlock.h:     builds the final spin_*() APIs.
 *
 * on UP builds:
 *
 *  linux/spinlock_type_up.h:
 *                        contains the generic, simplified UP spinlock type.
 *                        (which is an empty structure on non-debug builds)
 *
 *  linux/spinlock_types.h:
 *                        defines the generic type and initializers
 *
 *  linux/spinlock_up.h:
 *                        contains the __raw_spin_*()/etc. version of UP
 *                        builds. (which are NOPs on non-debug, non-preempt
 *                        builds)
 *
 *   (included on UP-non-debug builds:)
 *
 *  linux/spinlock_api_up.h:
 *                        builds the _spin_*() APIs.
 *
 *  linux/spinlock.h:     builds the final spin_*() APIs.
 */

All SMP and UP architectures are converted by this patch.

arm, i386, ia64, ppc, ppc64, s390/s390x, x64 was build-tested via
crosscompilers.  m32r, mips, sh, sparc, have not been tested yet, but should
be mostly fine.

From: Grant Grundler <grundler@parisc-linux.org>

  Booted and lightly tested on a500-44 (64-bit, SMP kernel, dual CPU).
  Builds 32-bit SMP kernel (not booted or tested).  I did not try to build
  non-SMP kernels.  That should be trivial to fix up later if necessary.

  I converted bit ops atomic_hash lock to raw_spinlock_t.  Doing so avoids
  some ugly nesting of linux/*.h and asm/*.h files.  Those particular locks
  are well tested and contained entirely inside arch specific code.  I do NOT
  expect any new issues to arise with them.

 If someone does ever need to use debug/metrics with them, then they will
  need to unravel this hairball between spinlocks, atomic ops, and bit ops
  that exist only because parisc has exactly one atomic instruction: LDCW
  (load and clear word).

From: "Luck, Tony" <tony.luck@intel.com>

   ia64 fix

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjanv@infradead.org>
Signed-off-by: Grant Grundler <grundler@parisc-linux.org>
Cc: Matthew Wilcox <willy@debian.org>
Signed-off-by: Hirokazu Takata <takata@linux-m32r.org>
Signed-off-by: Mikael Pettersson <mikpe@csd.uu.se>
Signed-off-by: Benoit Boissinot <benoit.boissinot@ens-lyon.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

4 files changed, 259 insertions, 5 deletions

diff --git a/lib/Makefile b/lib/Makefile
index d9c38ba..44a4675 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -16,6 +16,7 @@ CFLAGS_kobject.o += -DDEBUG
 CFLAGS_kobject_uevent.o += -DDEBUG
 endif
 
+obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
 lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_SEMAPHORE_SLEEPERS) += semaphore-sleepers.o
diff --git a/lib/dec_and_lock.c b/lib/dec_and_lock.c
index 6658d81..2377af0 100644
--- a/lib/dec_and_lock.c
+++ b/lib/dec_and_lock.c
@@ -25,8 +25,6 @@
  * this is trivially done efficiently using a load-locked
  * store-conditional approach, for example.
  */
-
-#ifndef ATOMIC_DEC_AND_LOCK
 int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock)
 {
 	spin_lock(lock);
@@ -37,4 +35,3 @@ int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock)
 }
 
 EXPORT_SYMBOL(_atomic_dec_and_lock);
-#endif
diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c
index bd2bc5d..cb5490e 100644
--- a/lib/kernel_lock.c
+++ b/lib/kernel_lock.c
@@ -177,8 +177,7 @@ static inline void __lock_kernel(void)
 
 static inline void __unlock_kernel(void)
 {
-	_raw_spin_unlock(&kernel_flag);
-	preempt_enable();
+	spin_unlock(&kernel_flag);
 }
 
 /*
diff --git a/lib/spinlock_debug.c b/lib/spinlock_debug.c
new file mode 100644
index 0000000..906ad10
--- /dev/null
+++ b/lib/spinlock_debug.c
@@ -0,0 +1,257 @@
+/*
+ * Copyright 2005, Red Hat, Inc., Ingo Molnar
+ * Released under the General Public License (GPL).
+ *
+ * This file contains the spinlock/rwlock implementations for
+ * DEBUG_SPINLOCK.
+ */
+
+#include <linux/config.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+
+static void spin_bug(spinlock_t *lock, const char *msg)
+{
+	static long print_once = 1;
+	struct task_struct *owner = NULL;
+
+	if (xchg(&print_once, 0)) {
+		if (lock->owner && lock->owner != SPINLOCK_OWNER_INIT)
+			owner = lock->owner;
+		printk("BUG: spinlock %s on CPU#%d, %s/%d\n",
+			msg, smp_processor_id(), current->comm, current->pid);
+		printk(" lock: %p, .magic: %08x, .owner: %s/%d, .owner_cpu: %d\n",
+			lock, lock->magic,
+			owner ? owner->comm : "<none>",
+			owner ? owner->pid : -1,
+			lock->owner_cpu);
+		dump_stack();
+#ifdef CONFIG_SMP
+		/*
+		 * We cannot continue on SMP:
+		 */
+//		panic("bad locking");
+#endif
+	}
+}
+
+#define SPIN_BUG_ON(cond, lock, msg) if (unlikely(cond)) spin_bug(lock, msg)
+
+static inline void debug_spin_lock_before(spinlock_t *lock)
+{
+	SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic");
+	SPIN_BUG_ON(lock->owner == current, lock, "recursion");
+	SPIN_BUG_ON(lock->owner_cpu == raw_smp_processor_id(),
+							lock, "cpu recursion");
+}
+
+static inline void debug_spin_lock_after(spinlock_t *lock)
+{
+	lock->owner_cpu = raw_smp_processor_id();
+	lock->owner = current;
+}
+
+static inline void debug_spin_unlock(spinlock_t *lock)
+{
+	SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic");
+	SPIN_BUG_ON(!spin_is_locked(lock), lock, "already unlocked");
+	SPIN_BUG_ON(lock->owner != current, lock, "wrong owner");
+	SPIN_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
+							lock, "wrong CPU");
+	lock->owner = SPINLOCK_OWNER_INIT;
+	lock->owner_cpu = -1;
+}
+
+static void __spin_lock_debug(spinlock_t *lock)
+{
+	int print_once = 1;
+	u64 i;
+
+	for (;;) {
+		for (i = 0; i < loops_per_jiffy * HZ; i++) {
+			cpu_relax();
+			if (__raw_spin_trylock(&lock->raw_lock))
+				return;
+		}
+		/* lockup suspected: */
+		if (print_once) {
+			print_once = 0;
+			printk("BUG: spinlock lockup on CPU#%d, %s/%d, %p\n",
+				smp_processor_id(), current->comm, current->pid,
+					lock);
+			dump_stack();
+		}
+	}
+}
+
+void _raw_spin_lock(spinlock_t *lock)
+{
+	debug_spin_lock_before(lock);
+	if (unlikely(!__raw_spin_trylock(&lock->raw_lock)))
+		__spin_lock_debug(lock);
+	debug_spin_lock_after(lock);
+}
+
+int _raw_spin_trylock(spinlock_t *lock)
+{
+	int ret = __raw_spin_trylock(&lock->raw_lock);
+
+	if (ret)
+		debug_spin_lock_after(lock);
+#ifndef CONFIG_SMP
+	/*
+	 * Must not happen on UP:
+	 */
+	SPIN_BUG_ON(!ret, lock, "trylock failure on UP");
+#endif
+	return ret;
+}
+
+void _raw_spin_unlock(spinlock_t *lock)
+{
+	debug_spin_unlock(lock);
+	__raw_spin_unlock(&lock->raw_lock);
+}
+
+static void rwlock_bug(rwlock_t *lock, const char *msg)
+{
+	static long print_once = 1;
+
+	if (xchg(&print_once, 0)) {
+		printk("BUG: rwlock %s on CPU#%d, %s/%d, %p\n", msg,
+			smp_processor_id(), current->comm, current->pid, lock);
+		dump_stack();
+#ifdef CONFIG_SMP
+		/*
+		 * We cannot continue on SMP:
+		 */
+		panic("bad locking");
+#endif
+	}
+}
+
+#define RWLOCK_BUG_ON(cond, lock, msg) if (unlikely(cond)) rwlock_bug(lock, msg)
+
+static void __read_lock_debug(rwlock_t *lock)
+{
+	int print_once = 1;
+	u64 i;
+
+	for (;;) {
+		for (i = 0; i < loops_per_jiffy * HZ; i++) {
+			cpu_relax();
+			if (__raw_read_trylock(&lock->raw_lock))
+				return;
+		}
+		/* lockup suspected: */
+		if (print_once) {
+			print_once = 0;
+			printk("BUG: read-lock lockup on CPU#%d, %s/%d, %p\n",
+				smp_processor_id(), current->comm, current->pid,
+					lock);
+			dump_stack();
+		}
+	}
+}
+
+void _raw_read_lock(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	if (unlikely(!__raw_read_trylock(&lock->raw_lock)))
+		__read_lock_debug(lock);
+}
+
+int _raw_read_trylock(rwlock_t *lock)
+{
+	int ret = __raw_read_trylock(&lock->raw_lock);
+
+#ifndef CONFIG_SMP
+	/*
+	 * Must not happen on UP:
+	 */
+	RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP");
+#endif
+	return ret;
+}
+
+void _raw_read_unlock(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	__raw_read_unlock(&lock->raw_lock);
+}
+
+static inline void debug_write_lock_before(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	RWLOCK_BUG_ON(lock->owner == current, lock, "recursion");
+	RWLOCK_BUG_ON(lock->owner_cpu == raw_smp_processor_id(),
+							lock, "cpu recursion");
+}
+
+static inline void debug_write_lock_after(rwlock_t *lock)
+{
+	lock->owner_cpu = raw_smp_processor_id();
+	lock->owner = current;
+}
+
+static inline void debug_write_unlock(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	RWLOCK_BUG_ON(lock->owner != current, lock, "wrong owner");
+	RWLOCK_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
+							lock, "wrong CPU");
+	lock->owner = SPINLOCK_OWNER_INIT;
+	lock->owner_cpu = -1;
+}
+
+static void __write_lock_debug(rwlock_t *lock)
+{
+	int print_once = 1;
+	u64 i;
+
+	for (;;) {
+		for (i = 0; i < loops_per_jiffy * HZ; i++) {
+			cpu_relax();
+			if (__raw_write_trylock(&lock->raw_lock))
+				return;
+		}
+		/* lockup suspected: */
+		if (print_once) {
+			print_once = 0;
+			printk("BUG: write-lock lockup on CPU#%d, %s/%d, %p\n",
+				smp_processor_id(), current->comm, current->pid,
+					lock);
+			dump_stack();
+		}
+	}
+}
+
+void _raw_write_lock(rwlock_t *lock)
+{
+	debug_write_lock_before(lock);
+	if (unlikely(!__raw_write_trylock(&lock->raw_lock)))
+		__write_lock_debug(lock);
+	debug_write_lock_after(lock);
+}
+
+int _raw_write_trylock(rwlock_t *lock)
+{
+	int ret = __raw_write_trylock(&lock->raw_lock);
+
+	if (ret)
+		debug_write_lock_after(lock);
+#ifndef CONFIG_SMP
+	/*
+	 * Must not happen on UP:
+	 */
+	RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP");
+#endif
+	return ret;
+}
+
+void _raw_write_unlock(rwlock_t *lock)
+{
+	debug_write_unlock(lock);
+	__raw_write_unlock(&lock->raw_lock);
+}