[POWERPC] irqtrace support for 64-bit powerpc

This adds the low level irq tracing hooks to the powerpc architecture
needed to enable full lockdep functionality.

This is partly based on Johannes Berg's initial version.  I removed
the asm trampoline that isn't needed (thus improving performance) and
modified all sorts of bits and pieces, reworking most of the assembly,
etc...

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>

11 files changed, 134 insertions, 52 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index ecca20d17a7b..4bb2e9310a56 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -53,6 +53,15 @@ config STACKTRACE_SUPPORT
         bool
         default y
 
+config TRACE_IRQFLAGS_SUPPORT
+        bool
+        depends on PPC64
+        default y
+
+config LOCKDEP_SUPPORT
+        bool
+        default y
+
 config RWSEM_GENERIC_SPINLOCK
         bool
 
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 13019845536b..c0db5b769e55 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -30,6 +30,7 @@
 #include <asm/firmware.h>
 #include <asm/bug.h>
 #include <asm/ptrace.h>
+#include <asm/irqflags.h>
 
 /*
  * System calls.
@@ -89,6 +90,14 @@ system_call_common:
         addi    r9,r1,STACK_FRAME_OVERHEAD
         ld      r11,exception_marker@toc(r2)
         std     r11,-16(r9)             /* "regshere" marker */
+#ifdef CONFIG_TRACE_IRQFLAGS
+        bl      .trace_hardirqs_on
+        REST_GPR(0,r1)
+        REST_4GPRS(3,r1)
+        REST_2GPRS(7,r1)
+        addi    r9,r1,STACK_FRAME_OVERHEAD
+        ld      r12,_MSR(r1)
+#endif /* CONFIG_TRACE_IRQFLAGS */
         li      r10,1
         stb     r10,PACASOFTIRQEN(r13)
         stb     r10,PACAHARDIRQEN(r13)
@@ -103,7 +112,7 @@ BEGIN_FW_FTR_SECTION
         b       hardware_interrupt_entry
 2:
 END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif
+#endif /* CONFIG_PPC_ISERIES */
         mfmsr   r11
         ori     r11,r11,MSR_EE
         mtmsrd  r11,1
@@ -505,6 +514,10 @@ BEGIN_FW_FTR_SECTION
 
         li      r3,0
         stb     r3,PACASOFTIRQEN(r13)   /* ensure we are soft-disabled */
+#ifdef CONFIG_TRACE_IRQFLAGS
+        bl      .trace_hardirqs_off
+        mfmsr   r10
+#endif
         ori     r10,r10,MSR_EE
         mtmsrd  r10                     /* hard-enable again */
         addi    r3,r1,STACK_FRAME_OVERHEAD
@@ -513,7 +526,7 @@ BEGIN_FW_FTR_SECTION
 4:
 END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
 #endif
-        stb     r5,PACASOFTIRQEN(r13)
+        TRACE_AND_RESTORE_IRQ(r5);
 
         /* extract EE bit and use it to restore paca->hard_enabled */
         ld      r3,_MSR(r1)
@@ -581,6 +594,16 @@ do_work:
         bne     restore
         /* here we are preempting the current task */
 1:
+#ifdef CONFIG_TRACE_IRQFLAGS
+        bl      .trace_hardirqs_on
+        /* Note: we just clobbered r10 which used to contain the previous
+         * MSR before the hard-disabling done by the caller of do_work.
+         * We don't have that value anymore, but it doesn't matter as
+         * we will hard-enable unconditionally, we can just reload the
+         * current MSR into r10
+         */
+        mfmsr   r10
+#endif /* CONFIG_TRACE_IRQFLAGS */
         li      r0,1
         stb     r0,PACASOFTIRQEN(r13)
         stb     r0,PACAHARDIRQEN(r13)
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 44229c3749ac..215973a2c8d5 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -36,8 +36,7 @@
 #include <asm/firmware.h>
 #include <asm/page_64.h>
 #include <asm/exception.h>
-
-#define DO_SOFT_DISABLE
+#include <asm/irqflags.h>
 
 /*
  * We layout physical memory as follows:
@@ -450,8 +449,8 @@ bad_stack:
  */
 fast_exc_return_irq:                    /* restores irq state too */
         ld      r3,SOFTE(r1)
+        TRACE_AND_RESTORE_IRQ(r3);
         ld      r12,_MSR(r1)
-        stb     r3,PACASOFTIRQEN(r13)   /* restore paca->soft_enabled */
         rldicl  r4,r12,49,63            /* get MSR_EE to LSB */
         stb     r4,PACAHARDIRQEN(r13)   /* restore paca->hard_enabled */
         b       1f
@@ -824,7 +823,7 @@ _STATIC(load_up_altivec)
  * Hash table stuff
  */
         .align  7
-_GLOBAL(do_hash_page)
+_STATIC(do_hash_page)
         std     r3,_DAR(r1)
         std     r4,_DSISR(r1)
 
@@ -836,6 +835,27 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
 
         /*
+         * On iSeries, we soft-disable interrupts here, then
+         * hard-enable interrupts so that the hash_page code can spin on
+         * the hash_table_lock without problems on a shared processor.
+         */
+        DISABLE_INTS
+
+        /*
+         * Currently, trace_hardirqs_off() will be called by DISABLE_INTS
+         * and will clobber volatile registers when irq tracing is enabled
+         * so we need to reload them. It may be possible to be smarter here
+         * and move the irq tracing elsewhere but let's keep it simple for
+         * now
+         */
+#ifdef CONFIG_TRACE_IRQFLAGS
+        ld      r3,_DAR(r1)
+        ld      r4,_DSISR(r1)
+        ld      r5,_TRAP(r1)
+        ld      r12,_MSR(r1)
+        clrrdi  r5,r5,4
+#endif /* CONFIG_TRACE_IRQFLAGS */
+        /*
          * We need to set the _PAGE_USER bit if MSR_PR is set or if we are
          * accessing a userspace segment (even from the kernel). We assume
          * kernel addresses always have the high bit set.
@@ -848,13 +868,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
         rlwimi  r4,r5,22+2,31-2,31-2    /* Set _PAGE_EXEC if trap is 0x400 */
 
         /*
-         * On iSeries, we soft-disable interrupts here, then
-         * hard-enable interrupts so that the hash_page code can spin on
-         * the hash_table_lock without problems on a shared processor.
-         */
-        DISABLE_INTS
-
-        /*
          * r3 contains the faulting address
          * r4 contains the required access permissions
          * r5 contains the trap number
@@ -864,7 +877,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
         bl      .hash_page              /* build HPTE if possible */
         cmpdi   r3,0                    /* see if hash_page succeeded */
 
-#ifdef DO_SOFT_DISABLE
 BEGIN_FW_FTR_SECTION
         /*
          * If we had interrupts soft-enabled at the point where the
@@ -876,7 +888,7 @@ BEGIN_FW_FTR_SECTION
          */
         beq     13f
 END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif
+
 BEGIN_FW_FTR_SECTION
         /*
          * Here we have interrupts hard-disabled, so it is sufficient
@@ -890,11 +902,12 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
 
         /*
          * hash_page couldn't handle it, set soft interrupt enable back
-         * to what it was before the trap.  Note that .local_irq_restore
+         * to what it was before the trap.  Note that .raw_local_irq_restore
          * handles any interrupts pending at this point.
          */
         ld      r3,SOFTE(r1)
-        bl      .local_irq_restore
+        TRACE_AND_RESTORE_IRQ_PARTIAL(r3, 11f)
+        bl      .raw_local_irq_restore
         b       11f
 
 /* Here we have a page fault that hash_page can't handle. */
@@ -1493,6 +1506,10 @@ _INIT_STATIC(start_here_multiplatform)
         addi    r2,r2,0x4000
         add     r2,r2,r26
 
+        /* Set initial ptr to current */
+        LOAD_REG_IMMEDIATE(r4, init_task)
+        std     r4,PACACURRENT(r13)
+
         /* Do very early kernel initializations, including initial hash table,
          * stab and slb setup before we turn on relocation.     */
 
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 4617b65d464d..425616f92d18 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -114,7 +114,7 @@ static inline void set_soft_enabled(unsigned long enable)
         : : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled)));
 }
 
-void local_irq_restore(unsigned long en)
+void raw_local_irq_restore(unsigned long en)
 {
         /*
          * get_paca()->soft_enabled = en;
@@ -174,6 +174,7 @@ void local_irq_restore(unsigned long en)
 
         __hard_irq_enable();
 }
+EXPORT_SYMBOL(raw_local_irq_restore);
 #endif /* CONFIG_PPC64 */
 
 int show_interrupts(struct seq_file *p, void *v)
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 5a4c76eada48..b9b765c7d1a7 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -45,10 +45,6 @@
 #include <asm/signal.h>
 #include <asm/dcr.h>
 
-#ifdef CONFIG_PPC64
-EXPORT_SYMBOL(local_irq_restore);
-#endif
-
 #ifdef CONFIG_PPC32
 extern void transfer_to_handler(void);
 extern void do_IRQ(struct pt_regs *regs);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 0205d408d2ed..31ada9fdfc5c 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -33,6 +33,7 @@
 #include <linux/serial_8250.h>
 #include <linux/bootmem.h>
 #include <linux/pci.h>
+#include <linux/lockdep.h>
 #include <linux/lmb.h>
 #include <asm/io.h>
 #include <asm/kdump.h>
@@ -178,6 +179,9 @@ void __init early_setup(unsigned long dt_ptr)
         /* Enable early debugging if any specified (see udbg.h) */
         udbg_early_init();
 
+        /* Initialize lockdep early or else spinlocks will blow */
+        lockdep_init();
+
         DBG(" -> early_setup(), dt_ptr: 0x%lx\n", dt_ptr);
 
         /*
diff --git a/include/asm-powerpc/exception.h b/include/asm-powerpc/exception.h
index 39abdb02fdef..329148b5acc6 100644
--- a/include/asm-powerpc/exception.h
+++ b/include/asm-powerpc/exception.h
@@ -228,18 +228,18 @@ label##_pSeries:							\
 BEGIN_FW_FTR_SECTION;                           \
         stb     r11,PACAHARDIRQEN(r13);         \
 END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES);   \
+        TRACE_DISABLE_INTS;                     \
 BEGIN_FW_FTR_SECTION;                           \
         mfmsr   r10;                            \
         ori     r10,r10,MSR_EE;                 \
         mtmsrd  r10,1;                          \
 END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-
 #else
 #define DISABLE_INTS                            \
         li      r11,0;                          \
         stb     r11,PACASOFTIRQEN(r13);         \
-        stb     r11,PACAHARDIRQEN(r13)
-
+        stb     r11,PACAHARDIRQEN(r13);         \
+        TRACE_DISABLE_INTS
 #endif /* CONFIG_PPC_ISERIES */
 
 #define ENABLE_INTS                             \
diff --git a/include/asm-powerpc/hw_irq.h b/include/asm-powerpc/hw_irq.h
index a7b60bf639e0..ad8c9f7fd0e3 100644
--- a/include/asm-powerpc/hw_irq.h
+++ b/include/asm-powerpc/hw_irq.h
@@ -27,7 +27,7 @@ static inline unsigned long local_get_flags(void)
         return flags;
 }
 
-static inline unsigned long local_irq_disable(void)
+static inline unsigned long raw_local_irq_disable(void)
 {
         unsigned long flags, zero;
 
@@ -39,14 +39,15 @@ static inline unsigned long local_irq_disable(void)
         return flags;
 }
 
-extern void local_irq_restore(unsigned long);
+extern void raw_local_irq_restore(unsigned long);
 extern void iseries_handle_interrupts(void);
 
-#define local_irq_enable()      local_irq_restore(1)
-#define local_save_flags(flags) ((flags) = local_get_flags())
-#define local_irq_save(flags)   ((flags) = local_irq_disable())
+#define raw_local_irq_enable()          raw_local_irq_restore(1)
+#define raw_local_save_flags(flags)     ((flags) = local_get_flags())
+#define raw_local_irq_save(flags)       ((flags) = raw_local_irq_disable())
 
-#define irqs_disabled()         (local_get_flags() == 0)
+#define raw_irqs_disabled()             (local_get_flags() == 0)
+#define raw_irqs_disabled_flags(flags)  ((flags) == 0)
 
 #define __hard_irq_enable()     __mtmsrd(mfmsr() | MSR_EE, 1)
 #define __hard_irq_disable()    __mtmsrd(mfmsr() & ~MSR_EE, 1)
diff --git a/include/asm-powerpc/irqflags.h b/include/asm-powerpc/irqflags.h
index 7970cbaeaa54..cc6fdba33660 100644
--- a/include/asm-powerpc/irqflags.h
+++ b/include/asm-powerpc/irqflags.h
@@ -2,30 +2,43 @@
  * include/asm-powerpc/irqflags.h
  *
  * IRQ flags handling
- *
- * This file gets included from lowlevel asm headers too, to provide
- * wrapped versions of the local_irq_*() APIs, based on the
- * raw_local_irq_*() macros from the lowlevel headers.
  */
 #ifndef _ASM_IRQFLAGS_H
 #define _ASM_IRQFLAGS_H
 
+#ifndef __ASSEMBLY__
 /*
  * Get definitions for raw_local_save_flags(x), etc.
  */
 #include <asm-powerpc/hw_irq.h>
 
+#else
+#ifdef CONFIG_TRACE_IRQFLAGS
 /*
- * Do the CPU's IRQ-state tracing from assembly code. We call a
- * C function, so save all the C-clobbered registers:
+ * Most of the CPU's IRQ-state tracing is done from assembly code; we
+ * have to call a C function so call a wrapper that saves all the
+ * C-clobbered registers.
  */
-#ifdef CONFIG_TRACE_IRQFLAGS
-
-#error No support on PowerPC yet for CONFIG_TRACE_IRQFLAGS
-
+#define TRACE_ENABLE_INTS       bl .trace_hardirqs_on
+#define TRACE_DISABLE_INTS      bl .trace_hardirqs_off
+#define TRACE_AND_RESTORE_IRQ_PARTIAL(en,skip)  \
+        cmpdi   en, 0;                          \
+        bne     95f;                            \
+        stb     en,PACASOFTIRQEN(r13);          \
+        bl      .trace_hardirqs_off;            \
+        b       skip;                           \
+95:     bl      .trace_hardirqs_on;             \
+        li      en,1;
+#define TRACE_AND_RESTORE_IRQ(en)               \
+        TRACE_AND_RESTORE_IRQ_PARTIAL(en,96f);  \
+96:     stb     en,PACASOFTIRQEN(r13)
 #else
-# define TRACE_IRQS_ON
-# define TRACE_IRQS_OFF
+#define TRACE_ENABLE_INTS
+#define TRACE_DISABLE_INTS
+#define TRACE_AND_RESTORE_IRQ_PARTIAL(en,skip)
+#define TRACE_AND_RESTORE_IRQ(en)               \
+        stb     en,PACASOFTIRQEN(r13)
+#endif
 #endif
 
 #endif
diff --git a/include/asm-powerpc/rwsem.h b/include/asm-powerpc/rwsem.h
index cefc14728cc5..a6cc93b78b98 100644
--- a/include/asm-powerpc/rwsem.h
+++ b/include/asm-powerpc/rwsem.h
@@ -32,11 +32,20 @@ struct rw_semaphore {
 #define RWSEM_ACTIVE_WRITE_BIAS         (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
         spinlock_t              wait_lock;
         struct list_head        wait_list;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+        struct lockdep_map      dep_map;
+#endif
 };
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
+#else
+# define __RWSEM_DEP_MAP_INIT(lockname)
+#endif
+
 #define __RWSEM_INITIALIZER(name) \
-        { RWSEM_UNLOCKED_VALUE, SPIN_LOCK_UNLOCKED, \
-          LIST_HEAD_INIT((name).wait_list) }
+        { RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
+          LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
 
 #define DECLARE_RWSEM(name)             \
         struct rw_semaphore name = __RWSEM_INITIALIZER(name)
@@ -46,12 +55,15 @@ extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
 
-static inline void init_rwsem(struct rw_semaphore *sem)
-{
-        sem->count = RWSEM_UNLOCKED_VALUE;
-        spin_lock_init(&sem->wait_lock);
-        INIT_LIST_HEAD(&sem->wait_list);
-}
+extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
+                         struct lock_class_key *key);
+
+#define init_rwsem(sem)                                 \
+        do {                                            \
+                static struct lock_class_key __key;     \
+                                                        \
+                __init_rwsem((sem), #sem, &__key);      \
+        } while (0)
 
 /*
  * lock for reading
@@ -78,7 +90,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 /*
  * lock for writing
  */
-static inline void __down_write(struct rw_semaphore *sem)
+static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
 {
         int tmp;
 
@@ -88,6 +100,11 @@ static inline void __down_write(struct rw_semaphore *sem)
                 rwsem_down_write_failed(sem);
 }
 
+static inline void __down_write(struct rw_semaphore *sem)
+{
+        __down_write_nested(sem, 0);
+}
+
 static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
         int tmp;
diff --git a/include/asm-powerpc/spinlock.h b/include/asm-powerpc/spinlock.h
index cc4cfceac67c..258c93993190 100644
--- a/include/asm-powerpc/spinlock.h
+++ b/include/asm-powerpc/spinlock.h
@@ -19,6 +19,7 @@
  *
  * (the type definitions are in asm/spinlock_types.h)
  */
+#include <linux/irqflags.h>
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 #include <asm/hvcall.h>