8 files changed, 200 insertions, 24 deletions

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 4dd38f129153..3cadba60a4b6 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -191,11 +191,49 @@ transfer_to_handler_cont:
         mflr    r9
         lwz     r11,0(r9)               /* virtual address of handler */
         lwz     r9,4(r9)                /* where to go when done */
+#ifdef CONFIG_TRACE_IRQFLAGS
+        lis     r12,reenable_mmu@h
+        ori     r12,r12,reenable_mmu@l
+        mtspr   SPRN_SRR0,r12
+        mtspr   SPRN_SRR1,r10
+        SYNC
+        RFI
+reenable_mmu:                           /* re-enable mmu so we can */
+        mfmsr   r10
+        lwz     r12,_MSR(r1)
+        xor     r10,r10,r12
+        andi.   r10,r10,MSR_EE          /* Did EE change? */
+        beq     1f
+
+        /* Save handler and return address into the 2 unused words
+         * of the STACK_FRAME_OVERHEAD (sneak sneak sneak). Everything
+         * else can be recovered from the pt_regs except r3 which for
+         * normal interrupts has been set to pt_regs and for syscalls
+         * is an argument, so we temporarily use ORIG_GPR3 to save it
+         */
+        stw     r9,8(r1)
+        stw     r11,12(r1)
+        stw     r3,ORIG_GPR3(r1)
+        bl      trace_hardirqs_off
+        lwz     r0,GPR0(r1)
+        lwz     r3,ORIG_GPR3(r1)
+        lwz     r4,GPR4(r1)
+        lwz     r5,GPR5(r1)
+        lwz     r6,GPR6(r1)
+        lwz     r7,GPR7(r1)
+        lwz     r8,GPR8(r1)
+        lwz     r9,8(r1)
+        lwz     r11,12(r1)
+1:      mtctr   r11
+        mtlr    r9
+        bctr                            /* jump to handler */
+#else /* CONFIG_TRACE_IRQFLAGS */
         mtspr   SPRN_SRR0,r11
         mtspr   SPRN_SRR1,r10
         mtlr    r9
         SYNC
         RFI                             /* jump to handler, enable MMU */
+#endif /* CONFIG_TRACE_IRQFLAGS */
 
 #if defined (CONFIG_6xx) || defined(CONFIG_E500)
 4:      rlwinm  r12,r12,0,~_TLF_NAPPING
@@ -251,6 +289,31 @@ _GLOBAL(DoSyscall)
 #ifdef SHOW_SYSCALLS
         bl      do_show_syscall
 #endif /* SHOW_SYSCALLS */
+#ifdef CONFIG_TRACE_IRQFLAGS
+        /* Return from syscalls can (and generally will) hard enable
+         * interrupts. You aren't supposed to call a syscall with
+         * interrupts disabled in the first place. However, to ensure
+         * that we get it right vs. lockdep if it happens, we force
+         * that hard enable here with appropriate tracing if we see
+         * that we have been called with interrupts off
+         */
+        mfmsr   r11
+        andi.   r12,r11,MSR_EE
+        bne+    1f
+        /* We came in with interrupts disabled, we enable them now */
+        bl      trace_hardirqs_on
+        mfmsr   r11
+        lwz     r0,GPR0(r1)
+        lwz     r3,GPR3(r1)
+        lwz     r4,GPR4(r1)
+        ori     r11,r11,MSR_EE
+        lwz     r5,GPR5(r1)
+        lwz     r6,GPR6(r1)
+        lwz     r7,GPR7(r1)
+        lwz     r8,GPR8(r1)
+        mtmsr   r11
+1:
+#endif /* CONFIG_TRACE_IRQFLAGS */
         rlwinm  r10,r1,0,0,(31-THREAD_SHIFT)    /* current_thread_info() */
         lwz     r11,TI_FLAGS(r10)
         andi.   r11,r11,_TIF_SYSCALL_T_OR_A
@@ -275,6 +338,7 @@ ret_from_syscall:
         rlwinm  r12,r1,0,0,(31-THREAD_SHIFT)    /* current_thread_info() */
         /* disable interrupts so current_thread_info()->flags can't change */
         LOAD_MSR_KERNEL(r10,MSR_KERNEL) /* doesn't include MSR_EE */
+        /* Note: We don't bother telling lockdep about it */
         SYNC
         MTMSRD(r10)
         lwz     r9,TI_FLAGS(r12)
@@ -288,6 +352,19 @@ ret_from_syscall:
         oris    r11,r11,0x1000  /* Set SO bit in CR */
         stw     r11,_CCR(r1)
 syscall_exit_cont:
+        lwz     r8,_MSR(r1)
+#ifdef CONFIG_TRACE_IRQFLAGS
+        /* If we are going to return from the syscall with interrupts
+         * off, we trace that here. It shouldn't happen though but we
+         * want to catch the bugger if it does right ?
+         */
+        andi.   r10,r8,MSR_EE
+        bne+    1f
+        stw     r3,GPR3(r1)
+        bl      trace_hardirqs_off
+        lwz     r3,GPR3(r1)
+1:
+#endif /* CONFIG_TRACE_IRQFLAGS */
 #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
         /* If the process has its own DBCR0 value, load it up.  The internal
            debug mode bit tells us that dbcr0 should be loaded. */
@@ -311,7 +388,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
         mtlr    r4
         mtcr    r5
         lwz     r7,_NIP(r1)
-        lwz     r8,_MSR(r1)
         FIX_SRR1(r8, r0)
         lwz     r2,GPR2(r1)
         lwz     r1,GPR1(r1)
@@ -394,7 +470,9 @@ syscall_exit_work:
         andi.   r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
         beq     ret_from_except
 
-        /* Re-enable interrupts */
+        /* Re-enable interrupts. There is no need to trace that with
+         * lockdep as we are supposed to have IRQs on at this point
+         */
         ori     r10,r10,MSR_EE
         SYNC
         MTMSRD(r10)
@@ -705,6 +783,7 @@ ret_from_except:
         /* Hard-disable interrupts so that current_thread_info()->flags
          * can't change between when we test it and when we return
          * from the interrupt. */
+        /* Note: We don't bother telling lockdep about it */
         LOAD_MSR_KERNEL(r10,MSR_KERNEL)
         SYNC                    /* Some chip revs have problems here... */
         MTMSRD(r10)             /* disable interrupts */
@@ -744,11 +823,24 @@ resume_kernel:
         beq+    restore
         andi.   r0,r3,MSR_EE    /* interrupts off? */
         beq     restore         /* don't schedule if so */
+#ifdef CONFIG_TRACE_IRQFLAGS
+        /* Lockdep thinks irqs are enabled, we need to call
+         * preempt_schedule_irq with IRQs off, so we inform lockdep
+         * now that we -did- turn them off already
+         */
+        bl      trace_hardirqs_off
+#endif
 1:      bl      preempt_schedule_irq
         rlwinm  r9,r1,0,0,(31-THREAD_SHIFT)
         lwz     r3,TI_FLAGS(r9)
         andi.   r0,r3,_TIF_NEED_RESCHED
         bne-    1b
+#ifdef CONFIG_TRACE_IRQFLAGS
+        /* And now, to properly rebalance the above, we tell lockdep they
+         * are being turned back on, which will happen when we return
+         */
+        bl      trace_hardirqs_on
+#endif
 #else
 resume_kernel:
 #endif /* CONFIG_PREEMPT */
@@ -765,6 +857,28 @@ restore:
         stw     r6,icache_44x_need_flush@l(r4)
 1:
 #endif  /* CONFIG_44x */
+
+        lwz     r9,_MSR(r1)
+#ifdef CONFIG_TRACE_IRQFLAGS
+        /* Lockdep doesn't know about the fact that IRQs are temporarily turned
+         * off in this assembly code while peeking at TI_FLAGS() and such. However
+         * we need to inform it if the exception turned interrupts off, and we
+         * are about to trun them back on.
+         *
+         * The problem here sadly is that we don't know whether the exceptions was
+         * one that turned interrupts off or not. So we always tell lockdep about
+         * turning them on here when we go back to wherever we came from with EE
+         * on, even if that may meen some redudant calls being tracked. Maybe later
+         * we could encode what the exception did somewhere or test the exception
+         * type in the pt_regs but that sounds overkill
+         */
+        andi.   r10,r9,MSR_EE
+        beq     1f
+        bl      trace_hardirqs_on
+        lwz     r9,_MSR(r1)
+1:
+#endif /* CONFIG_TRACE_IRQFLAGS */
+
         lwz     r0,GPR0(r1)
         lwz     r2,GPR2(r1)
         REST_4GPRS(3, r1)
@@ -782,7 +896,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
         stwcx.  r0,0,r1                 /* to clear the reservation */
 
 #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
-        lwz     r9,_MSR(r1)
         andi.   r10,r9,MSR_RI           /* check if this exception occurred */
         beql    nonrecoverable          /* at a bad place (MSR:RI = 0) */
 
@@ -805,7 +918,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
         MTMSRD(r10)             /* clear the RI bit */
         .globl exc_exit_restart
 exc_exit_restart:
-        lwz     r9,_MSR(r1)
         lwz     r12,_NIP(r1)
         FIX_SRR1(r9,r10)
         mtspr   SPRN_SRR0,r12
@@ -1035,11 +1147,18 @@ do_work:			/* r10 contains MSR_KERNEL here */
         beq     do_user_signal
 
 do_resched:                     /* r10 contains MSR_KERNEL here */
+        /* Note: We don't need to inform lockdep that we are enabling
+         * interrupts here. As far as it knows, they are already enabled
+         */
         ori     r10,r10,MSR_EE
         SYNC
         MTMSRD(r10)             /* hard-enable interrupts */
         bl      schedule
 recheck:
+        /* Note: And we don't tell it we are disabling them again
+         * neither. Those disable/enable cycles used to peek at
+         * TI_FLAGS aren't advertised.
+         */
         LOAD_MSR_KERNEL(r10,MSR_KERNEL)
         SYNC
         MTMSRD(r10)             /* disable interrupts */
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 48469463f89e..fc2132942754 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -1124,9 +1124,8 @@ mmu_off:
         RFI
 
 /*
- * Use the first pair of BAT registers to map the 1st 16MB
- * of RAM to PAGE_OFFSET.  From this point on we can't safely
- * call OF any more.
+ * On 601, we use 3 BATs to map up to 24M of RAM at _PAGE_OFFSET
+ * (we keep one for debugging) and on others, we use one 256M BAT.
  */
 initial_bats:
         lis     r11,PAGE_OFFSET@h
@@ -1136,12 +1135,16 @@ initial_bats:
         bne     4f
         ori     r11,r11,4               /* set up BAT registers for 601 */
         li      r8,0x7f                 /* valid, block length = 8MB */
-        oris    r9,r11,0x800000@h       /* set up BAT reg for 2nd 8M */
-        oris    r10,r8,0x800000@h       /* set up BAT reg for 2nd 8M */
         mtspr   SPRN_IBAT0U,r11         /* N.B. 601 has valid bit in */
         mtspr   SPRN_IBAT0L,r8          /* lower BAT register */
-        mtspr   SPRN_IBAT1U,r9
-        mtspr   SPRN_IBAT1L,r10
+        addis   r11,r11,0x800000@h
+        addis   r8,r8,0x800000@h
+        mtspr   SPRN_IBAT1U,r11
+        mtspr   SPRN_IBAT1L,r8
+        addis   r11,r11,0x800000@h
+        addis   r8,r8,0x800000@h
+        mtspr   SPRN_IBAT2U,r11
+        mtspr   SPRN_IBAT2L,r8
         isync
         blr
 
diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c
index fa983a59c4ce..a359cb08e900 100644
--- a/arch/powerpc/kernel/of_device.c
+++ b/arch/powerpc/kernel/of_device.c
@@ -76,7 +76,7 @@ struct of_device *of_device_alloc(struct device_node *np,
         dev->dev.archdata.of_node = np;
 
         if (bus_id)
-                dev_set_name(&dev->dev, bus_id);
+                dev_set_name(&dev->dev, "%s", bus_id);
         else
                 of_device_make_bus_id(dev);
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 3e7135bbe40f..892a9f2e6d76 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -528,7 +528,7 @@ void show_regs(struct pt_regs * regs)
 
         for (i = 0;  i < 32;  i++) {
                 if ((i % REGS_PER_LINE) == 0)
-                        printk("\n" KERN_INFO "GPR%02d: ", i);
+                        printk("\nGPR%02d: ", i);
                 printk(REG " ", regs->gpr[i]);
                 if (i == LAST_VOLATILE && !FULL_REGS(regs))
                         break;
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index ee4c7609b649..c434823b8c83 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -38,9 +38,10 @@
 #include <asm/syscalls.h>
 #include <asm/smp.h>
 #include <asm/atomic.h>
+#include <asm/time.h>
 
 struct rtas_t rtas = {
-        .lock = SPIN_LOCK_UNLOCKED
+        .lock = __RAW_SPIN_LOCK_UNLOCKED
 };
 EXPORT_SYMBOL(rtas);
 
@@ -67,6 +68,28 @@ unsigned long rtas_rmo_buf;
 void (*rtas_flash_term_hook)(int);
 EXPORT_SYMBOL(rtas_flash_term_hook);
 
+/* RTAS use home made raw locking instead of spin_lock_irqsave
+ * because those can be called from within really nasty contexts
+ * such as having the timebase stopped which would lockup with
+ * normal locks and spinlock debugging enabled
+ */
+static unsigned long lock_rtas(void)
+{
+        unsigned long flags;
+
+        local_irq_save(flags);
+        preempt_disable();
+        __raw_spin_lock_flags(&rtas.lock, flags);
+        return flags;
+}
+
+static void unlock_rtas(unsigned long flags)
+{
+        __raw_spin_unlock(&rtas.lock);
+        local_irq_restore(flags);
+        preempt_enable();
+}
+
 /*
  * call_rtas_display_status and call_rtas_display_status_delay
  * are designed only for very early low-level debugging, which
@@ -79,7 +102,7 @@ static void call_rtas_display_status(char c)
 
         if (!rtas.base)
                 return;
-        spin_lock_irqsave(&rtas.lock, s);
+        s = lock_rtas();
 
         args->token = 10;
         args->nargs = 1;
@@ -89,7 +112,7 @@ static void call_rtas_display_status(char c)
 
         enter_rtas(__pa(args));
 
-        spin_unlock_irqrestore(&rtas.lock, s);
+        unlock_rtas(s);
 }
 
 static void call_rtas_display_status_delay(char c)
@@ -411,8 +434,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
         if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE)
                 return -1;
 
-        /* Gotta do something different here, use global lock for now... */
-        spin_lock_irqsave(&rtas.lock, s);
+        s = lock_rtas();
         rtas_args = &rtas.args;
 
         rtas_args->token = token;
@@ -439,8 +461,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
                         outputs[i] = rtas_args->rets[i+1];
         ret = (nret > 0)? rtas_args->rets[0]: 0;
 
-        /* Gotta do something different here, use global lock for now... */
-        spin_unlock_irqrestore(&rtas.lock, s);
+        unlock_rtas(s);
 
         if (buff_copy) {
                 log_error(buff_copy, ERR_TYPE_RTAS_LOG, 0);
@@ -837,7 +858,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 
         buff_copy = get_errorlog_buffer();
 
-        spin_lock_irqsave(&rtas.lock, flags);
+        flags = lock_rtas();
 
         rtas.args = args;
         enter_rtas(__pa(&rtas.args));
@@ -848,7 +869,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
         if (args.rets[0] == -1)
                 errbuf = __fetch_rtas_last_error(buff_copy);
 
-        spin_unlock_irqrestore(&rtas.lock, flags);
+        unlock_rtas(flags);
 
         if (buff_copy) {
                 if (errbuf)
@@ -951,3 +972,33 @@ int __init early_init_dt_scan_rtas(unsigned long node,
         /* break now */
         return 1;
 }
+
+static raw_spinlock_t timebase_lock;
+static u64 timebase = 0;
+
+void __cpuinit rtas_give_timebase(void)
+{
+        unsigned long flags;
+
+        local_irq_save(flags);
+        hard_irq_disable();
+        __raw_spin_lock(&timebase_lock);
+        rtas_call(rtas_token("freeze-time-base"), 0, 1, NULL);
+        timebase = get_tb();
+        __raw_spin_unlock(&timebase_lock);
+
+        while (timebase)
+                barrier();
+        rtas_call(rtas_token("thaw-time-base"), 0, 1, NULL);
+        local_irq_restore(flags);
+}
+
+void __cpuinit rtas_take_timebase(void)
+{
+        while (!timebase)
+                barrier();
+        __raw_spin_lock(&timebase_lock);
+        set_tb(timebase >> 32, timebase & 0xffffffff);
+        timebase = 0;
+        __raw_spin_unlock(&timebase_lock);
+}
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 1d154248cf40..e1e3059cf34b 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -119,6 +119,8 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
  */
 notrace void __init machine_init(unsigned long dt_ptr)
 {
+        lockdep_init();
+
         /* Enable early debugging if any specified (see udbg.h) */
         udbg_early_init();
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 65484b2200b3..0b47de07302d 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -68,7 +68,8 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 /* SMP operations for this machine */
 struct smp_ops_t *smp_ops;
 
-static volatile unsigned int cpu_callin_map[NR_CPUS];
+/* Can't be static due to PowerMac hackery */
+volatile unsigned int cpu_callin_map[NR_CPUS];
 
 int smt_enabled_at_boot = 1;
 
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 0362a891e54e..acb74a17bbbf 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -219,7 +219,7 @@ void udbg_init_pas_realmode(void)
 #ifdef CONFIG_PPC_EARLY_DEBUG_44x
 #include <platforms/44x/44x.h>
 
-static int udbg_44x_as1_flush(void)
+static void udbg_44x_as1_flush(void)
 {
         if (udbg_comport) {
                 while ((as1_readb(&udbg_comport->lsr) & LSR_THRE) == 0)