[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>

1 files changed, 86 insertions, 105 deletions

diff --git a/include/asm-ppc64/spinlock.h b/include/asm-ppc64/spinlock.h
index acd11564dd75..14cb895bb607 100644
--- a/include/asm-ppc64/spinlock.h
+++ b/include/asm-ppc64/spinlock.h
@@ -15,36 +15,42 @@
  * modify it under the terms of the GNU General Public License
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
+ *
+ * (the type definitions are in asm/spinlock_types.h)
  */
 #include <linux/config.h>
 #include <asm/paca.h>
 #include <asm/hvcall.h>
 #include <asm/iSeries/HvCall.h>
 
-typedef struct {
-        volatile unsigned int lock;
-#ifdef CONFIG_PREEMPT
-        unsigned int break_lock;
-#endif
-} spinlock_t;
+#define __raw_spin_is_locked(x)         ((x)->slock != 0)
 
-typedef struct {
-        volatile signed int lock;
-#ifdef CONFIG_PREEMPT
-        unsigned int break_lock;
-#endif
-} rwlock_t;
+/*
+ * This returns the old value in the lock, so we succeeded
+ * in getting the lock if the return value is 0.
+ */
+static __inline__ unsigned long __spin_trylock(raw_spinlock_t *lock)
+{
+        unsigned long tmp, tmp2;
 
-#ifdef __KERNEL__
-#define SPIN_LOCK_UNLOCKED      (spinlock_t) { 0 }
+        __asm__ __volatile__(
+"       lwz             %1,%3(13)               # __spin_trylock\n\
+1:      lwarx           %0,0,%2\n\
+        cmpwi           0,%0,0\n\
+        bne-            2f\n\
+        stwcx.          %1,0,%2\n\
+        bne-            1b\n\
+        isync\n\
+2:"     : "=&r" (tmp), "=&r" (tmp2)
+        : "r" (&lock->slock), "i" (offsetof(struct paca_struct, lock_token))
+        : "cr0", "memory");
 
-#define spin_is_locked(x)       ((x)->lock != 0)
-#define spin_lock_init(x)       do { *(x) = SPIN_LOCK_UNLOCKED; } while(0)
+        return tmp;
+}
 
-static __inline__ void _raw_spin_unlock(spinlock_t *lock)
+static int __inline__ __raw_spin_trylock(raw_spinlock_t *lock)
 {
-        __asm__ __volatile__("lwsync    # spin_unlock": : :"memory");
-        lock->lock = 0;
+        return __spin_trylock(lock) == 0;
 }
 
 /*
@@ -64,44 +70,15 @@ static __inline__ void _raw_spin_unlock(spinlock_t *lock)
 #if defined(CONFIG_PPC_SPLPAR) || defined(CONFIG_PPC_ISERIES)
 /* We only yield to the hypervisor if we are in shared processor mode */
 #define SHARED_PROCESSOR (get_paca()->lppaca.shared_proc)
-extern void __spin_yield(spinlock_t *lock);
-extern void __rw_yield(rwlock_t *lock);
+extern void __spin_yield(raw_spinlock_t *lock);
+extern void __rw_yield(raw_rwlock_t *lock);
 #else /* SPLPAR || ISERIES */
 #define __spin_yield(x) barrier()
 #define __rw_yield(x)   barrier()
 #define SHARED_PROCESSOR        0
 #endif
-extern void spin_unlock_wait(spinlock_t *lock);
-
-/*
- * This returns the old value in the lock, so we succeeded
- * in getting the lock if the return value is 0.
- */
-static __inline__ unsigned long __spin_trylock(spinlock_t *lock)
-{
-        unsigned long tmp, tmp2;
-
-        __asm__ __volatile__(
-"       lwz             %1,%3(13)               # __spin_trylock\n\
-1:      lwarx           %0,0,%2\n\
-        cmpwi           0,%0,0\n\
-        bne-            2f\n\
-        stwcx.          %1,0,%2\n\
-        bne-            1b\n\
-        isync\n\
-2:"     : "=&r" (tmp), "=&r" (tmp2)
-        : "r" (&lock->lock), "i" (offsetof(struct paca_struct, lock_token))
-        : "cr0", "memory");
-
-        return tmp;
-}
-
-static int __inline__ _raw_spin_trylock(spinlock_t *lock)
-{
-        return __spin_trylock(lock) == 0;
-}
 
-static void __inline__ _raw_spin_lock(spinlock_t *lock)
+static void __inline__ __raw_spin_lock(raw_spinlock_t *lock)
 {
         while (1) {
                 if (likely(__spin_trylock(lock) == 0))
@@ -110,12 +87,12 @@ static void __inline__ _raw_spin_lock(spinlock_t *lock)
                         HMT_low();
                         if (SHARED_PROCESSOR)
                                 __spin_yield(lock);
-                } while (unlikely(lock->lock != 0));
+                } while (unlikely(lock->slock != 0));
                 HMT_medium();
         }
 }
 
-static void __inline__ _raw_spin_lock_flags(spinlock_t *lock, unsigned long flags)
+static void __inline__ __raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long flags)
 {
         unsigned long flags_dis;
 
@@ -128,12 +105,20 @@ static void __inline__ _raw_spin_lock_flags(spinlock_t *lock, unsigned long flag
                         HMT_low();
                         if (SHARED_PROCESSOR)
                                 __spin_yield(lock);
-                } while (unlikely(lock->lock != 0));
+                } while (unlikely(lock->slock != 0));
                 HMT_medium();
                 local_irq_restore(flags_dis);
         }
 }
 
+static __inline__ void __raw_spin_unlock(raw_spinlock_t *lock)
+{
+        __asm__ __volatile__("lwsync    # __raw_spin_unlock": : :"memory");
+        lock->slock = 0;
+}
+
+extern void __raw_spin_unlock_wait(raw_spinlock_t *lock);
+
 /*
  * Read-write spinlocks, allowing multiple readers
  * but only one writer.
@@ -144,24 +129,15 @@ static void __inline__ _raw_spin_lock_flags(spinlock_t *lock, unsigned long flag
  * irq-safe write-lock, but readers can get non-irqsafe
  * read-locks.
  */
-#define RW_LOCK_UNLOCKED (rwlock_t) { 0 }
 
-#define rwlock_init(x)          do { *(x) = RW_LOCK_UNLOCKED; } while(0)
-
-#define read_can_lock(rw)       ((rw)->lock >= 0)
-#define write_can_lock(rw)      (!(rw)->lock)
-
-static __inline__ void _raw_write_unlock(rwlock_t *rw)
-{
-        __asm__ __volatile__("lwsync            # write_unlock": : :"memory");
-        rw->lock = 0;
-}
+#define __raw_read_can_lock(rw)         ((rw)->lock >= 0)
+#define __raw_write_can_lock(rw)        (!(rw)->lock)
 
 /*
  * This returns the old value in the lock + 1,
  * so we got a read lock if the return value is > 0.
  */
-static long __inline__ __read_trylock(rwlock_t *rw)
+static long __inline__ __read_trylock(raw_rwlock_t *rw)
 {
         long tmp;
 
@@ -180,45 +156,11 @@ static long __inline__ __read_trylock(rwlock_t *rw)
         return tmp;
 }
 
-static int __inline__ _raw_read_trylock(rwlock_t *rw)
-{
-        return __read_trylock(rw) > 0;
-}
-
-static void __inline__ _raw_read_lock(rwlock_t *rw)
-{
-        while (1) {
-                if (likely(__read_trylock(rw) > 0))
-                        break;
-                do {
-                        HMT_low();
-                        if (SHARED_PROCESSOR)
-                                __rw_yield(rw);
-                } while (unlikely(rw->lock < 0));
-                HMT_medium();
-        }
-}
-
-static void __inline__ _raw_read_unlock(rwlock_t *rw)
-{
-        long tmp;
-
-        __asm__ __volatile__(
-        "eieio                          # read_unlock\n\
-1:      lwarx           %0,0,%1\n\
-        addic           %0,%0,-1\n\
-        stwcx.          %0,0,%1\n\
-        bne-            1b"
-        : "=&r"(tmp)
-        : "r"(&rw->lock)
-        : "cr0", "memory");
-}
-
 /*
  * This returns the old value in the lock,
  * so we got the write lock if the return value is 0.
  */
-static __inline__ long __write_trylock(rwlock_t *rw)
+static __inline__ long __write_trylock(raw_rwlock_t *rw)
 {
         long tmp, tmp2;
 
@@ -237,12 +179,21 @@ static __inline__ long __write_trylock(rwlock_t *rw)
         return tmp;
 }
 
-static int __inline__ _raw_write_trylock(rwlock_t *rw)
+static void __inline__ __raw_read_lock(raw_rwlock_t *rw)
 {
-        return __write_trylock(rw) == 0;
+        while (1) {
+                if (likely(__read_trylock(rw) > 0))
+                        break;
+                do {
+                        HMT_low();
+                        if (SHARED_PROCESSOR)
+                                __rw_yield(rw);
+                } while (unlikely(rw->lock < 0));
+                HMT_medium();
+        }
 }
 
-static void __inline__ _raw_write_lock(rwlock_t *rw)
+static void __inline__ __raw_write_lock(raw_rwlock_t *rw)
 {
         while (1) {
                 if (likely(__write_trylock(rw) == 0))
@@ -256,5 +207,35 @@ static void __inline__ _raw_write_lock(rwlock_t *rw)
         }
 }
 
-#endif /* __KERNEL__ */
+static int __inline__ __raw_read_trylock(raw_rwlock_t *rw)
+{
+        return __read_trylock(rw) > 0;
+}
+
+static int __inline__ __raw_write_trylock(raw_rwlock_t *rw)
+{
+        return __write_trylock(rw) == 0;
+}
+
+static void __inline__ __raw_read_unlock(raw_rwlock_t *rw)
+{
+        long tmp;
+
+        __asm__ __volatile__(
+        "eieio                          # read_unlock\n\
+1:      lwarx           %0,0,%1\n\
+        addic           %0,%0,-1\n\
+        stwcx.          %0,0,%1\n\
+        bne-            1b"
+        : "=&r"(tmp)
+        : "r"(&rw->lock)
+        : "cr0", "memory");
+}
+
+static __inline__ void __raw_write_unlock(raw_rwlock_t *rw)
+{
+        __asm__ __volatile__("lwsync    # write_unlock": : :"memory");
+        rw->lock = 0;
+}
+
 #endif /* __ASM_SPINLOCK_H */