Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (25 commits)
  powerpc: Disable 64K hugetlb support when doing 64K SPU mappings
  powerpc/powermac: Fixup default serial port device for pmac_zilog
  powerpc/powermac: Use sane default baudrate for SCC debugging
  powerpc/mm: Implement _PAGE_SPECIAL & pte_special() for 64-bit
  powerpc: Show processor cache information in sysfs
  powerpc: Make core id information available to userspace
  powerpc: Make core sibling information available to userspace
  powerpc/vio: More fallout from dma_mapping_error API change
  ibmveth: Fix multiple errors with dma_mapping_error conversion
  powerpc/pseries: Fix CMO sysdev attribute API change fallout
  powerpc: Enable tracehook for the architecture
  powerpc: Add TIF_NOTIFY_RESUME support for tracehook
  powerpc: Add asm/syscall.h with the tracehook entry points
  powerpc: Make syscall tracing use tracehook.h helpers
  powerpc: Call tracehook_signal_handler() when setting up signal frames
  powerpc: Update cpu_sibling_maps dynamically
  powerpc: register_cpu_online should be __cpuinit
  powerpc: kill useless SMT code in prom_hold_cpus
  powerpc: Fix 8xx build failure
  powerpc: Fix vio build warnings
  ...

38 files changed, 1039 insertions, 260 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index fe88418167c..587da5e0990 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -117,6 +117,7 @@ config PPC
 	select HAVE_KPROBES
 	select HAVE_ARCH_KGDB
 	select HAVE_KRETPROBES
+	select HAVE_ARCH_TRACEHOOK
 	select HAVE_LMB
 	select HAVE_DMA_ATTRS if PPC64
 	select USE_GENERIC_SMP_HELPERS if SMP
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 81c8324a4a3..1cbbf703364 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -148,7 +148,7 @@ transfer_to_handler:
 	/* Check to see if the dbcr0 register is set up to debug.  Use the
 	   internal debug mode bit to do this. */
 	lwz	r12,THREAD_DBCR0(r12)
-	andis.	r12,r12,(DBCR0_IDM  | DBSR_DAC1R | DBSR_DAC1W)@h
+	andis.	r12,r12,DBCR0_IDM@h
 	beq+	3f
 	/* From user and task is ptraced - load up global dbcr0 */
 	li	r12,-1			/* clear all pending debug events */
@@ -292,7 +292,7 @@ syscall_exit_cont:
 	/* If the process has its own DBCR0 value, load it up.  The internal
 	   debug mode bit tells us that dbcr0 should be loaded. */
 	lwz	r0,THREAD+THREAD_DBCR0(r2)
-	andis.	r10,r0,(DBCR0_IDM  | DBSR_DAC1R | DBSR_DAC1W)@h
+	andis.	r10,r0,DBCR0_IDM@h
 	bnel-	load_dbcr0
 #endif
 #ifdef CONFIG_44x
@@ -343,7 +343,12 @@ syscall_dotrace:
 	stw	r0,_TRAP(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_syscall_trace_enter
-	lwz	r0,GPR0(r1)	/* Restore original registers */
+	/*
+	 * Restore argument registers possibly just changed.
+	 * We use the return value of do_syscall_trace_enter
+	 * for call number to look up in the table (r0).
+	 */
+	mr	r0,r3
 	lwz	r3,GPR3(r1)
 	lwz	r4,GPR4(r1)
 	lwz	r5,GPR5(r1)
@@ -720,7 +725,7 @@ restore_user:
 	/* Check whether this process has its own DBCR0 value.  The internal
 	   debug mode bit tells us that dbcr0 should be loaded. */
 	lwz	r0,THREAD+THREAD_DBCR0(r2)
-	andis.	r10,r0,(DBCR0_IDM  | DBSR_DAC1R | DBSR_DAC1W)@h
+	andis.	r10,r0,DBCR0_IDM@h
 	bnel-	load_dbcr0
 #endif
 
@@ -1055,8 +1060,8 @@ do_user_signal:			/* r10 contains MSR_KERNEL here */
 	SAVE_NVGPRS(r1)
 	rlwinm	r3,r3,0,0,30
 	stw	r3,_TRAP(r1)
-2:	li	r3,0
-	addi	r4,r1,STACK_FRAME_OVERHEAD
+2:	addi	r3,r1,STACK_FRAME_OVERHEAD
+	mr	r4,r9
 	bl	do_signal
 	REST_NVGPRS(r1)
 	b	recheck
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index d7369243ae4..2d802e97097 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -214,7 +214,12 @@ syscall_dotrace:
 	bl	.save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	.do_syscall_trace_enter
-	ld	r0,GPR0(r1)	/* Restore original registers */
+	/*
+	 * Restore argument registers possibly just changed.
+	 * We use the return value of do_syscall_trace_enter
+	 * for the call number to look up in the table (r0).
+	 */
+	mr	r0,r3
 	ld	r3,GPR3(r1)
 	ld	r4,GPR4(r1)
 	ld	r5,GPR5(r1)
@@ -638,8 +643,7 @@ user_work:
 	b	.ret_from_except_lite
 
 1:	bl	.save_nvgprs
-	li	r3,0
-	addi	r4,r1,STACK_FRAME_OVERHEAD
+	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	.do_signal
 	b	.ret_from_except
 
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 4d96e1db55e..9ddfaef1a18 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -493,18 +493,18 @@ static int __init serial_dev_init(void)
 device_initcall(serial_dev_init);
 
 
+#ifdef CONFIG_SERIAL_8250_CONSOLE
 /*
  * This is called very early, as part of console_init() (typically just after
  * time_init()). This function is respondible for trying to find a good
  * default console on serial ports. It tries to match the open firmware
- * default output with one of the available serial console drivers, either
- * one of the platform serial ports that have been probed earlier by
- * find_legacy_serial_ports() or some more platform specific ones.
+ * default output with one of the available serial console drivers that have
+ * been probed earlier by find_legacy_serial_ports()
  */
 static int __init check_legacy_serial_console(void)
 {
 	struct device_node *prom_stdout = NULL;
-	int speed = 0, offset = 0;
+	int i, speed = 0, offset = 0;
 	const char *name;
 	const u32 *spd;
 
@@ -548,31 +548,20 @@ static int __init check_legacy_serial_console(void)
 	if (spd)
 		speed = *spd;
 
-	if (0)
-		;
-#ifdef CONFIG_SERIAL_8250_CONSOLE
-	else if (strcmp(name, "serial") == 0) {
-		int i;
-		/* Look for it in probed array */
-		for (i = 0; i < legacy_serial_count; i++) {
-			if (prom_stdout != legacy_serial_infos[i].np)
-				continue;
-			offset = i;
-			speed = legacy_serial_infos[i].speed;
-			break;
-		}
-		if (i >= legacy_serial_count)
-			goto not_found;
+	if (strcmp(name, "serial") != 0)
+		goto not_found;
+
+	/* Look for it in probed array */
+	for (i = 0; i < legacy_serial_count; i++) {
+		if (prom_stdout != legacy_serial_infos[i].np)
+			continue;
+		offset = i;
+		speed = legacy_serial_infos[i].speed;
+		break;
 	}
-#endif /* CONFIG_SERIAL_8250_CONSOLE */
-#ifdef CONFIG_SERIAL_PMACZILOG_CONSOLE
-	else if (strcmp(name, "ch-a") == 0)
-		offset = 0;
-	else if (strcmp(name, "ch-b") == 0)
-		offset = 1;
-#endif /* CONFIG_SERIAL_PMACZILOG_CONSOLE */
-	else
+	if (i >= legacy_serial_count)
 		goto not_found;
+
 	of_node_put(prom_stdout);
 
 	DBG("Found serial console at ttyS%d\n", offset);
@@ -591,3 +580,4 @@ static int __init check_legacy_serial_console(void)
 }
 console_initcall(check_legacy_serial_console);
 
+#endif /* CONFIG_SERIAL_8250_CONSOLE */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index db2497ccc11..e030f3bd502 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -254,7 +254,7 @@ void do_dabr(struct pt_regs *regs, unsigned long address,
 		return;
 
 	/* Clear the DAC and struct entries.  One shot trigger */
-#if (defined(CONFIG_44x) || defined(CONFIG_BOOKE))
+#if defined(CONFIG_BOOKE)
 	mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~(DBSR_DAC1R | DBSR_DAC1W
 							| DBCR0_IDM));
 #endif
@@ -286,7 +286,7 @@ int set_dabr(unsigned long dabr)
 	mtspr(SPRN_DABR, dabr);
 #endif
 
-#if defined(CONFIG_44x) || defined(CONFIG_BOOKE)
+#if defined(CONFIG_BOOKE)
 	mtspr(SPRN_DAC1, dabr);
 #endif
 
@@ -373,7 +373,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr))
 		set_dabr(new->thread.dabr);
 
-#if defined(CONFIG_44x) || defined(CONFIG_BOOKE)
+#if defined(CONFIG_BOOKE)
 	/* If new thread DAC (HW breakpoint) is the same then leave it */
 	if (new->thread.dabr)
 		set_dabr(new->thread.dabr);
@@ -568,7 +568,7 @@ void flush_thread(void)
 		current->thread.dabr = 0;
 		set_dabr(0);
 
-#if defined(CONFIG_44x) || defined(CONFIG_BOOKE)
+#if defined(CONFIG_BOOKE)
 		current->thread.dbcr0 &= ~(DBSR_DAC1R | DBSR_DAC1W);
 #endif
 	}
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index c4ab2195b9c..b72849ac7db 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -205,8 +205,6 @@ static int __initdata mem_reserve_cnt;
 static cell_t __initdata regbuf[1024];
 
 
-#define MAX_CPU_THREADS 2
-
 /*
  * Error results ... some OF calls will return "-1" on error, some
  * will return 0, some will return either. To simplify, here are
@@ -1339,10 +1337,6 @@ static void __init prom_hold_cpus(void)
 	unsigned int reg;
 	phandle node;
 	char type[64];
-	int cpuid = 0;
-	unsigned int interrupt_server[MAX_CPU_THREADS];
-	unsigned int cpu_threads, hw_cpu_num;
-	int propsize;
 	struct prom_t *_prom = &RELOC(prom);
 	unsigned long *spinloop
 		= (void *) LOW_ADDR(__secondary_hold_spinloop);
@@ -1386,7 +1380,6 @@ static void __init prom_hold_cpus(void)
 		reg = -1;
 		prom_getprop(node, "reg", &reg, sizeof(reg));
 
-		prom_debug("\ncpuid        = 0x%x\n", cpuid);
 		prom_debug("cpu hw idx   = 0x%x\n", reg);
 
 		/* Init the acknowledge var which will be reset by
@@ -1395,28 +1388,9 @@ static void __init prom_hold_cpus(void)
 		 */
 		*acknowledge = (unsigned long)-1;
 
-		propsize = prom_getprop(node, "ibm,ppc-interrupt-server#s",
-					&interrupt_server,
-					sizeof(interrupt_server));
-		if (propsize < 0) {
-			/* no property.  old hardware has no SMT */
-			cpu_threads = 1;
-			interrupt_server[0] = reg; /* fake it with phys id */
-		} else {
-			/* We have a threaded processor */
-			cpu_threads = propsize / sizeof(u32);
-			if (cpu_threads > MAX_CPU_THREADS) {
-				prom_printf("SMT: too many threads!\n"
-					    "SMT: found %x, max is %x\n",
-					    cpu_threads, MAX_CPU_THREADS);
-				cpu_threads = 1; /* ToDo: panic? */
-			}
-		}
-
-		hw_cpu_num = interrupt_server[0];
-		if (hw_cpu_num != _prom->cpu) {
+		if (reg != _prom->cpu) {
 			/* Primary Thread of non-boot cpu */
-			prom_printf("%x : starting cpu hw idx %x... ", cpuid, reg);
+			prom_printf("starting cpu hw idx %x... ", reg);
 			call_prom("start-cpu", 3, 0, node,
 				  secondary_hold, reg);
 
@@ -1431,17 +1405,10 @@ static void __init prom_hold_cpus(void)
 		}
 #ifdef CONFIG_SMP
 		else
-			prom_printf("%x : boot cpu     %x\n", cpuid, reg);
+			prom_printf("boot cpu hw idx %x\n", reg);
 #endif /* CONFIG_SMP */
-
-		/* Reserve cpu #s for secondary threads.   They start later. */
-		cpuid += cpu_threads;
 	}
 
-	if (cpuid > NR_CPUS)
-		prom_printf("WARNING: maximum CPUs (" __stringify(NR_CPUS)
-			    ") exceeded: ignoring extras\n");
-
 	prom_debug("prom_hold_cpus: end...\n");
 }
 
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index a5d0e78779c..6b66cd85b43 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -22,6 +22,7 @@
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/regset.h>
+#include <linux/tracehook.h>
 #include <linux/elf.h>
 #include <linux/user.h>
 #include <linux/security.h>
@@ -717,7 +718,7 @@ void user_disable_single_step(struct task_struct *task)
 	struct pt_regs *regs = task->thread.regs;
 
 
-#if defined(CONFIG_44x) || defined(CONFIG_BOOKE)
+#if defined(CONFIG_BOOKE)
 	/* If DAC then do not single step, skip */
 	if (task->thread.dabr)
 		return;
@@ -744,10 +745,11 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 	if (addr > 0)
 		return -EINVAL;
 
+	/* The bottom 3 bits in dabr are flags */
 	if ((data & ~0x7UL) >= TASK_SIZE)
 		return -EIO;
 
-#ifdef CONFIG_PPC64
+#ifndef CONFIG_BOOKE
 
 	/* For processors using DABR (i.e. 970), the bottom 3 bits are flags.
 	 *  It was assumed, on previous implementations, that 3 bits were
@@ -769,7 +771,7 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 	task->thread.dabr = data;
 
 #endif
-#if defined(CONFIG_44x) || defined(CONFIG_BOOKE)
+#if defined(CONFIG_BOOKE)
 
 	/* As described above, it was assumed 3 bits were passed with the data
 	 *  address, but we will assume only the mode bits will be passed
@@ -1013,31 +1015,24 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 	return ret;
 }
 
-static void do_syscall_trace(void)
+/*
+ * We must return the syscall number to actually look up in the table.
+ * This can be -1L to skip running any syscall at all.
+ */
+long do_syscall_trace_enter(struct pt_regs *regs)
 {
-	/* the 0x80 provides a way for the tracing parent to distinguish
-	   between a syscall stop and SIGTRAP delivery */
-	ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
-				 ? 0x80 : 0));
-
-	/*
-	 * this isn't the same as continuing with a signal, but it will do
-	 * for normal use.  strace only continues with a signal if the
-	 * stopping signal is not SIGTRAP.  -brl
-	 */
-	if (current->exit_code) {
-		send_sig(current->exit_code, current, 1);
-		current->exit_code = 0;
-	}
-}
+	long ret = 0;
 
-void do_syscall_trace_enter(struct pt_regs *regs)
-{
 	secure_computing(regs->gpr[0]);
 
-	if (test_thread_flag(TIF_SYSCALL_TRACE)
-	    && (current->ptrace & PT_PTRACED))
-		do_syscall_trace();
+	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
+	    tracehook_report_syscall_entry(regs))
+		/*
+		 * Tracing decided this syscall should not happen.
+		 * We'll return a bogus call number to get an ENOSYS
+		 * error, but leave the original number in regs->gpr[0].
+		 */
+		ret = -1L;
 
 	if (unlikely(current->audit_context)) {
 #ifdef CONFIG_PPC64
@@ -1055,16 +1050,19 @@ void do_syscall_trace_enter(struct pt_regs *regs)
 					    regs->gpr[5] & 0xffffffff,
 					    regs->gpr[6] & 0xffffffff);
 	}
+
+	return ret ?: regs->gpr[0];
 }
 
 void do_syscall_trace_leave(struct pt_regs *regs)
 {
+	int step;
+
 	if (unlikely(current->audit_context))
 		audit_syscall_exit((regs->ccr&0x10000000)?AUDITSC_FAILURE:AUDITSC_SUCCESS,
 				   regs->result);
 
-	if ((test_thread_flag(TIF_SYSCALL_TRACE)
-	     || test_thread_flag(TIF_SINGLESTEP))
-	    && (current->ptrace & PT_PTRACED))
-		do_syscall_trace();
+	step = test_thread_flag(TIF_SINGLESTEP);
+	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
+		tracehook_report_syscall_exit(regs, step);
 }
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 61a3f413208..9cc5a52711e 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -367,7 +367,6 @@ static void __init cpu_init_thread_core_maps(int tpc)
  * setup_cpu_maps - initialize the following cpu maps:
  *                  cpu_possible_map
  *                  cpu_present_map
- *                  cpu_sibling_map
  *
  * Having the possible map set up early allows us to restrict allocations
  * of things like irqstacks to num_possible_cpus() rather than NR_CPUS.
@@ -475,29 +474,6 @@ void __init smp_setup_cpu_maps(void)
 	 */
 	cpu_init_thread_core_maps(nthreads);
 }
-
-/*
- * Being that cpu_sibling_map is now a per_cpu array, then it cannot
- * be initialized until the per_cpu areas have been created.  This
- * function is now called from setup_per_cpu_areas().
- */
-void __init smp_setup_cpu_sibling_map(void)
-{
-#ifdef CONFIG_PPC64
-	int i, cpu, base;
-
-	for_each_possible_cpu(cpu) {
-		DBG("Sibling map for CPU %d:", cpu);
-		base = cpu_first_thread_in_core(cpu);
-		for (i = 0; i < threads_per_core; i++) {
-			cpu_set(base + i, per_cpu(cpu_sibling_map, cpu));
-			DBG(" %d", base + i);
-		}
-		DBG("\n");
-	}
-
-#endif /* CONFIG_PPC64 */
-}
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_PCSPKR_PLATFORM
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 04d8de9f0fc..8b25f51f03b 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -611,9 +611,6 @@ void __init setup_per_cpu_areas(void)
 		paca[i].data_offset = ptr - __per_cpu_start;
 		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
 	}
-
-	/* Now that per_cpu is setup, initialize cpu_sibling_map */
-	smp_setup_cpu_sibling_map();
 }
 #endif
 
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 7aada783ec6..a54405ebd7b 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -9,7 +9,7 @@
  * this archive for more details.
  */
 
-#include <linux/ptrace.h>
+#include <linux/tracehook.h>
 #include <linux/signal.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -112,7 +112,7 @@ static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka,
 	}
 }
 
-int do_signal(sigset_t *oldset, struct pt_regs *regs)
+static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs)
 {
 	siginfo_t info;
 	int signr;
@@ -147,7 +147,7 @@ int do_signal(sigset_t *oldset, struct pt_regs *regs)
 	 */
 	if (current->thread.dabr) {
 		set_dabr(current->thread.dabr);
-#if defined(CONFIG_44x) || defined(CONFIG_BOOKE)
+#if defined(CONFIG_BOOKE)
 		mtspr(SPRN_DBCR0, current->thread.dbcr0);
 #endif
 	}
@@ -177,11 +177,28 @@ int do_signal(sigset_t *oldset, struct pt_regs *regs)
 		 * its frame, and we can clear the TLF_RESTORE_SIGMASK flag.
 		 */
 		current_thread_info()->local_flags &= ~_TLF_RESTORE_SIGMASK;
+
+		/*
+		 * Let tracing know that we've done the handler setup.
+		 */
+		tracehook_signal_handler(signr, &info, &ka, regs,
+					 test_thread_flag(TIF_SINGLESTEP));
 	}
 
 	return ret;
 }
 
+void do_signal(struct pt_regs *regs, unsigned long thread_info_flags)
+{
+	if (thread_info_flags & _TIF_SIGPENDING)
+		do_signal_pending(NULL, regs);
+
+	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+		clear_thread_flag(TIF_NOTIFY_RESUME);
+		tracehook_notify_resume(regs);
+	}
+}
+
 long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
 		unsigned long r5, unsigned long r6, unsigned long r7,
 		unsigned long r8, struct pt_regs *regs)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index f5ae9fa222e..5337ca7bb64 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -41,6 +41,7 @@
 #include <asm/smp.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
+#include <asm/cputhreads.h>
 #include <asm/cputable.h>
 #include <asm/system.h>
 #include <asm/mpic.h>
@@ -62,10 +63,12 @@ struct thread_info *secondary_ti;
 cpumask_t cpu_possible_map = CPU_MASK_NONE;
 cpumask_t cpu_online_map = CPU_MASK_NONE;
 DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
+DEFINE_PER_CPU(cpumask_t, cpu_core_map) = CPU_MASK_NONE;
 
 EXPORT_SYMBOL(cpu_online_map);
 EXPORT_SYMBOL(cpu_possible_map);
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
+EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 
 /* SMP operations for this machine */
 struct smp_ops_t *smp_ops;
@@ -228,6 +231,8 @@ void __devinit smp_prepare_boot_cpu(void)
 	BUG_ON(smp_processor_id() != boot_cpuid);
 
 	cpu_set(boot_cpuid, cpu_online_map);
+	cpu_set(boot_cpuid, per_cpu(cpu_sibling_map, boot_cpuid));
+	cpu_set(boot_cpuid, per_cpu(cpu_core_map, boot_cpuid));
 #ifdef CONFIG_PPC64
 	paca[boot_cpuid].__current = current;
 #endif
@@ -375,11 +380,60 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	return 0;
 }
 
+/* Return the value of the reg property corresponding to the given
+ * logical cpu.
+ */
+int cpu_to_core_id(int cpu)
+{
+	struct device_node *np;
+	const int *reg;
+	int id = -1;
+
+	np = of_get_cpu_node(cpu, NULL);
+	if (!np)
+		goto out;
+
+	reg = of_get_property(np, "reg", NULL);
+	if (!reg)
+		goto out;
+
+	id = *reg;
+out:
+	of_node_put(np);
+	return id;
+}
+
+/* Must be called when no change can occur to cpu_present_map,
+ * i.e. during cpu online or offline.
+ */
+static struct device_node *cpu_to_l2cache(int cpu)
+{
+	struct device_node *np;
+	const phandle *php;
+	phandle ph;
+
+	if (!cpu_present(cpu))
+		return NULL;
+
+	np = of_get_cpu_node(cpu, NULL);
+	if (np == NULL)
+		return NULL;
+
+	php = of_get_property(np, "l2-cache", NULL);
+	if (php == NULL)
+		return NULL;
+	ph = *php;
+	of_node_put(np);
+
+	return of_find_node_by_phandle(ph);
+}
 
 /* Activate a secondary processor. */
 int __devinit start_secondary(void *unused)
 {
 	unsigned int cpu = smp_processor_id();
+	struct device_node *l2_cache;
+	int i, base;
 
 	atomic_inc(&init_mm.mm_count);
 	current->active_mm = &init_mm;
@@ -400,6 +454,33 @@ int __devinit start_secondary(void *unused)
 
 	ipi_call_lock();
 	cpu_set(cpu, cpu_online_map);
+	/* Update sibling maps */
+	base = cpu_first_thread_in_core(cpu);
+	for (i = 0; i < threads_per_core; i++) {
+		if (cpu_is_offline(base + i))
+			continue;
+		cpu_set(cpu, per_cpu(cpu_sibling_map, base + i));
+		cpu_set(base + i, per_cpu(cpu_sibling_map, cpu));
+
+		/* cpu_core_map should be a superset of
+		 * cpu_sibling_map even if we don't have cache
+		 * information, so update the former here, too.
+		 */
+		cpu_set(cpu, per_cpu(cpu_core_map, base +i));
+		cpu_set(base + i, per_cpu(cpu_core_map, cpu));
+	}
+	l2_cache = cpu_to_l2cache(cpu);
+	for_each_online_cpu(i) {
+		struct device_node *np = cpu_to_l2cache(i);
+		if (!np)
+			continue;
+		if (np == l2_cache) {
+			cpu_set(cpu, per_cpu(cpu_core_map, i));
+			cpu_set(i, per_cpu(cpu_core_map, cpu));
+		}
+		of_node_put(np);
+	}
+	of_node_put(l2_cache);
 	ipi_call_unlock();
 
 	local_irq_enable();
@@ -437,10 +518,42 @@ void __init smp_cpus_done(unsigned int max_cpus)
 #ifdef CONFIG_HOTPLUG_CPU
 int __cpu_disable(void)
 {
-	if (smp_ops->cpu_disable)
-		return smp_ops->cpu_disable();
+	struct device_node *l2_cache;
+	int cpu = smp_processor_id();
+	int base, i;
+	int err;
 
-	return -ENOSYS;
+	if (!smp_ops->cpu_disable)
+		return -ENOSYS;
+
+	err = smp_ops->cpu_disable();
+	if (err)
+		return err;
+
+	/* Update sibling maps */
+	base = cpu_first_thread_in_core(cpu);
+	for (i = 0; i < threads_per_core; i++) {
+		cpu_clear(cpu, per_cpu(cpu_sibling_map, base + i));
+		cpu_clear(base + i, per_cpu(cpu_sibling_map, cpu));
+		cpu_clear(cpu, per_cpu(cpu_core_map, base +i));
+		cpu_clear(base + i, per_cpu(cpu_core_map, cpu));
+	}
+
+	l2_cache = cpu_to_l2cache(cpu);
+	for_each_present_cpu(i) {
+		struct device_node *np = cpu_to_l2cache(i);
+		if (!np)
+			continue;
+		if (np == l2_cache) {
+			cpu_clear(cpu, per_cpu(cpu_core_map, i));
+			cpu_clear(i, per_cpu(cpu_core_map, cpu));
+		}
+		of_node_put(np);
+	}
+	of_node_put(l2_cache);
+
+
+	return 0;
 }
 
 void __cpu_die(unsigned int cpu)
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index f2589645870..b0dbb1daa4d 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -13,7 +13,6 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/stacktrace.h>
-#include <linux/module.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
 
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 800e5e9a087..56d172d16e5 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -22,6 +22,8 @@
 
 static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
+static DEFINE_PER_CPU(struct kobject *, cache_toplevel);
+
 /* SMT stuff */
 
 #ifdef CONFIG_PPC_MULTIPLATFORM
@@ -297,8 +299,289 @@ static struct sysdev_attribute pa6t_attrs[] = {
 #endif /* CONFIG_DEBUG_KERNEL */
 };
 
+struct cache_desc {
+	struct kobject kobj;
+	struct cache_desc *next;
+	const char *type;	/* Instruction, Data, or Unified */
+	u32 size;		/* total cache size in KB */
+	u32 line_size;		/* in bytes */
+	u32 nr_sets;		/* number of sets */
+	u32 level;		/* e.g. 1, 2, 3... */
+	u32 associativity;	/* e.g. 8-way... 0 is fully associative */
+};
+
+DEFINE_PER_CPU(struct cache_desc *, cache_desc);
+
+static struct cache_desc *kobj_to_cache_desc(struct kobject *k)
+{
+	return container_of(k, struct cache_desc, kobj);
+}
+
+static void cache_desc_release(struct kobject *k)
+{
+	struct cache_desc *desc = kobj_to_cache_desc(k);
+
+	pr_debug("%s: releasing %s\n", __func__, kobject_name(k));
+
+	if (desc->next)
+		kobject_put(&desc->next->kobj);
+
+	kfree(kobj_to_cache_desc(k));
+}
+
+static ssize_t cache_desc_show(struct kobject *k, struct attribute *attr, char *buf)
+{
+	struct kobj_attribute *kobj_attr;
+
+	kobj_attr = container_of(attr, struct kobj_attribute, attr);