Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc-2.6

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc-2.6:
  sparc64: Fix clock event multiplier printf format.
  sparc64: Use clock{source,events}_calc_mult_shift().
  sparc64: Use free_bootmem_late() in mdesc_lmb_free().
  sparc: Add alignment and emulation fault perf events.
  sparc64: Add syscall tracepoint support.
  sparc: Stop trying to be so fancy and use __builtin_{memcpy,memset}()
  sparc: Use __builtin_object_size() to validate the buffer size for copy_from_user()
  sparc64: Add some missing __kprobes annotations to kernel fault paths.
  sparc64: Use kprobes_built_in() to avoid ifdefs in fault_64.c
  sparc: Validate that kprobe address is 4-byte aligned.
  sparc64: Don't specify IRQF_SHARED for LDC interrupts.
  sparc64: Fix stack debugging IRQ stack regression.
  sparc64: Fix overly strict range type matching for PCI devices.

31 files changed, 154 insertions, 210 deletions

diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 33ac1a9..108197a 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -43,6 +43,7 @@ config SPARC64
 	select HAVE_SYSCALL_WRAPPERS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_SYSCALL_TRACEPOINTS
 	select USE_GENERIC_SMP_HELPERS if SMP
 	select RTC_DRV_CMOS
 	select RTC_DRV_BQ4802
diff --git a/arch/sparc/Kconfig.debug b/arch/sparc/Kconfig.debug
index 90d5fe2..9d3c889 100644
--- a/arch/sparc/Kconfig.debug
+++ b/arch/sparc/Kconfig.debug
@@ -33,4 +33,18 @@ config FRAME_POINTER
 	depends on MCOUNT
 	default y
 
+config DEBUG_STRICT_USER_COPY_CHECKS
+	bool "Strict copy size checks"
+	depends on DEBUG_KERNEL && !TRACE_BRANCH_PROFILING
+	---help---
+	  Enabling this option turns a certain set of sanity checks for user
+	  copy operations into compile time failures.
+
+	  The copy_from_user() etc checks are there to help test if there
+	  are sufficient security checks on the length argument of
+	  the copy operation, by having gcc prove that the argument is
+	  within bounds.
+
+	  If unsure, or if you run an older (pre 4.4) gcc, say N.
+
 endmenu
diff --git a/arch/sparc/include/asm/string_32.h b/arch/sparc/include/asm/string_32.h
index 6c5fddb..edf196e 100644
--- a/arch/sparc/include/asm/string_32.h
+++ b/arch/sparc/include/asm/string_32.h
@@ -16,8 +16,6 @@
 #ifdef __KERNEL__
 
 extern void __memmove(void *,const void *,__kernel_size_t);
-extern __kernel_size_t __memcpy(void *,const void *,__kernel_size_t);
-extern __kernel_size_t __memset(void *,int,__kernel_size_t);
 
 #ifndef EXPORT_SYMTAB_STROPS
 
@@ -32,82 +30,10 @@ extern __kernel_size_t __memset(void *,int,__kernel_size_t);
 })
 
 #define __HAVE_ARCH_MEMCPY
-
-static inline void *__constant_memcpy(void *to, const void *from, __kernel_size_t n)
-{
-	extern void __copy_1page(void *, const void *);
-
-	if(n <= 32) {
-		__builtin_memcpy(to, from, n);
-	} else if (((unsigned int) to & 7) != 0) {
-		/* Destination is not aligned on the double-word boundary */
-		__memcpy(to, from, n);
-	} else {
-		switch(n) {
-		case PAGE_SIZE:
-			__copy_1page(to, from);
-			break;
-		default:
-			__memcpy(to, from, n);
-			break;
-		}
-	}
-	return to;
-}
-
-static inline void *__nonconstant_memcpy(void *to, const void *from, __kernel_size_t n)
-{
-	__memcpy(to, from, n);
-	return to;
-}
-
-#undef memcpy
-#define memcpy(t, f, n) \
-(__builtin_constant_p(n) ? \
- __constant_memcpy((t),(f),(n)) : \
- __nonconstant_memcpy((t),(f),(n)))
+#define memcpy(t, f, n) __builtin_memcpy(t, f, n)
 
 #define __HAVE_ARCH_MEMSET
-
-static inline void *__constant_c_and_count_memset(void *s, char c, __kernel_size_t count)
-{
-	extern void bzero_1page(void *);
-	extern __kernel_size_t __bzero(void *, __kernel_size_t);
-
-	if(!c) {
-		if(count == PAGE_SIZE)
-			bzero_1page(s);
-		else
-			__bzero(s, count);
-	} else {
-		__memset(s, c, count);
-	}
-	return s;
-}
-
-static inline void *__constant_c_memset(void *s, char c, __kernel_size_t count)
-{
-	extern __kernel_size_t __bzero(void *, __kernel_size_t);
-
-	if(!c)
-		__bzero(s, count);
-	else
-		__memset(s, c, count);
-	return s;
-}
-
-static inline void *__nonconstant_memset(void *s, char c, __kernel_size_t count)
-{
-	__memset(s, c, count);
-	return s;
-}
-
-#undef memset
-#define memset(s, c, count) \
-(__builtin_constant_p(c) ? (__builtin_constant_p(count) ? \
-                            __constant_c_and_count_memset((s), (c), (count)) : \
-                            __constant_c_memset((s), (c), (count))) \
-                          : __nonconstant_memset((s), (c), (count)))
+#define memset(s, c, count) __builtin_memset(s, c, count)
 
 #define __HAVE_ARCH_MEMSCAN
 
diff --git a/arch/sparc/include/asm/string_64.h b/arch/sparc/include/asm/string_64.h
index 43161f2..9623bc2 100644
--- a/arch/sparc/include/asm/string_64.h
+++ b/arch/sparc/include/asm/string_64.h
@@ -15,8 +15,6 @@
 
 #include <asm/asi.h>
 
-extern void *__memset(void *,int,__kernel_size_t);
-
 #ifndef EXPORT_SYMTAB_STROPS
 
 /* First the mem*() things. */
@@ -24,29 +22,10 @@ extern void *__memset(void *,int,__kernel_size_t);
 extern void *memmove(void *, const void *, __kernel_size_t);
 
 #define __HAVE_ARCH_MEMCPY
-extern void *memcpy(void *, const void *, __kernel_size_t);
+#define memcpy(t, f, n) __builtin_memcpy(t, f, n)
 
 #define __HAVE_ARCH_MEMSET
-extern void *__builtin_memset(void *,int,__kernel_size_t);
-
-static inline void *__constant_memset(void *s, int c, __kernel_size_t count)
-{
-	extern __kernel_size_t __bzero(void *, __kernel_size_t);
-
-	if (!c) {
-		__bzero(s, count);
-		return s;
-	} else
-		return __memset(s, c, count);
-}
-
-#undef memset
-#define memset(s, c, count) \
-((__builtin_constant_p(count) && (count) <= 32) ? \
- __builtin_memset((s), (c), (count)) : \
- (__builtin_constant_p(c) ? \
-  __constant_memset((s), (c), (count)) : \
-  __memset((s), (c), (count))))
+#define memset(s, c, count) __builtin_memset(s, c, count)
 
 #define __HAVE_ARCH_MEMSCAN
 
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index 1b45a7b..7257ebb 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -227,6 +227,7 @@ register struct thread_info *current_thread_info_reg asm("g6");
 /* flag bit 8 is available */
 #define TIF_SECCOMP		9	/* secure computing */
 #define TIF_SYSCALL_AUDIT	10	/* syscall auditing active */
+#define TIF_SYSCALL_TRACEPOINT	11	/* syscall tracepoint instrumentation */
 /* flag bit 11 is available */
 /* NOTE: Thread flags >= 12 should be ones we have no interest
  *       in using in assembly, else we can't use the mask as
@@ -246,6 +247,7 @@ register struct thread_info *current_thread_info_reg asm("g6");
 #define _TIF_32BIT		(1<<TIF_32BIT)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
+#define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_ABI_PENDING	(1<<TIF_ABI_PENDING)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_FREEZE		(1<<TIF_FREEZE)
diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h
index 8303ac4..489d2ba 100644
--- a/arch/sparc/include/asm/uaccess_32.h
+++ b/arch/sparc/include/asm/uaccess_32.h
@@ -260,8 +260,23 @@ static inline unsigned long __copy_to_user(void __user *to, const void *from, un
 	return __copy_user(to, (__force void __user *) from, n);
 }
 
+extern void copy_from_user_overflow(void)
+#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
+	__compiletime_error("copy_from_user() buffer size is not provably correct")
+#else
+	__compiletime_warning("copy_from_user() buffer size is not provably correct")
+#endif
+;
+
 static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n)
 {
+	int sz = __compiletime_object_size(to);
+
+	if (unlikely(sz != -1 && sz < n)) {
+		copy_from_user_overflow();
+		return -EFAULT;
+	}
+
 	if (n && __access_ok((unsigned long) from, n))
 		return __copy_user((__force void __user *) to, from, n);
 	else
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index 9ea271e..dbc1416 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -6,6 +6,7 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/errno.h>
 #include <linux/compiler.h>
 #include <linux/string.h>
 #include <linux/thread_info.h>
@@ -204,6 +205,14 @@ __asm__ __volatile__(							\
 
 extern int __get_user_bad(void);
 
+extern void copy_from_user_overflow(void)
+#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
+	__compiletime_error("copy_from_user() buffer size is not provably correct")
+#else
+	__compiletime_warning("copy_from_user() buffer size is not provably correct")
+#endif
+;
+
 extern unsigned long __must_check ___copy_from_user(void *to,
 						    const void __user *from,
 						    unsigned long size);
@@ -212,10 +221,16 @@ extern unsigned long copy_from_user_fixup(void *to, const void __user *from,
 static inline unsigned long __must_check
 copy_from_user(void *to, const void __user *from, unsigned long size)
 {
-	unsigned long ret = ___copy_from_user(to, from, size);
-
-	if (unlikely(ret))
-		ret = copy_from_user_fixup(to, from, size);
+	unsigned long ret = (unsigned long) -EFAULT;
+	int sz = __compiletime_object_size(to);
+
+	if (likely(sz == -1 || sz >= size)) {
+		ret = ___copy_from_user(to, from, size);
+		if (unlikely(ret))
+			ret = copy_from_user_fixup(to, from, size);
+	} else {
+		copy_from_user_overflow();
+	}
 	return ret;
 }
 #define __copy_from_user copy_from_user
diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h
index d8d25bd..cb4b9bf 100644
--- a/arch/sparc/include/asm/unistd.h
+++ b/arch/sparc/include/asm/unistd.h
@@ -398,7 +398,7 @@
 #define __NR_perf_event_open	327
 #define __NR_recvmmsg		328
 
-#define NR_SYSCALLS		329
+#define NR_syscalls		329
 
 #ifdef __32bit_syscall_numbers__
 /* Sparc 32-bit only has the "setresuid32", "getresuid32" variants,
diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S
index ec9c7bc..1504df8 100644
--- a/arch/sparc/kernel/entry.S
+++ b/arch/sparc/kernel/entry.S
@@ -1294,7 +1294,7 @@ linux_sparc_syscall:
 	sethi	%hi(PSR_SYSCALL), %l4
 	or	%l0, %l4, %l0
 	/* Direct access to user regs, must faster. */
-	cmp	%g1, NR_SYSCALLS
+	cmp	%g1, NR_syscalls
 	bgeu	linux_sparc_ni_syscall
 	 sll	%g1, 2, %l4
 	ld	[%l7 + %l4], %l7
diff --git a/arch/sparc/kernel/ftrace.c b/arch/sparc/kernel/ftrace.c
index d3b1a30..29973da 100644
--- a/arch/sparc/kernel/ftrace.c
+++ b/arch/sparc/kernel/ftrace.c
@@ -4,6 +4,7 @@
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <linux/list.h>
+#include <trace/syscall.h>
 
 #include <asm/ftrace.h>
 
@@ -91,3 +92,13 @@ int __init ftrace_dyn_arch_init(void *data)
 }
 #endif
 
+#ifdef CONFIG_FTRACE_SYSCALLS
+
+extern unsigned int sys_call_table[];
+
+unsigned long __init arch_syscall_addr(int nr)
+{
+	return (unsigned long)sys_call_table[nr];
+}
+
+#endif
diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index 3bc6527..6716584 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -46,6 +46,9 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = {{NULL, NULL}};
 
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
 {
+	if ((unsigned long) p->addr & 0x3UL)
+		return -EILSEQ;
+
 	p->ainsn.insn[0] = *p->addr;
 	flushi(&p->ainsn.insn[0]);
 
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index cb3c72c..e0ba898 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -1242,13 +1242,13 @@ int ldc_bind(struct ldc_channel *lp, const char *name)
 	snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name);
 
 	err = request_irq(lp->cfg.rx_irq, ldc_rx,
-			  IRQF_SAMPLE_RANDOM | IRQF_DISABLED | IRQF_SHARED,
+			  IRQF_SAMPLE_RANDOM | IRQF_DISABLED,
 			  lp->rx_irq_name, lp);
 	if (err)
 		return err;
 
 	err = request_irq(lp->cfg.tx_irq, ldc_tx,
-			  IRQF_SAMPLE_RANDOM | IRQF_DISABLED | IRQF_SHARED,
+			  IRQF_SAMPLE_RANDOM | IRQF_DISABLED,
 			  lp->tx_irq_name, lp);
 	if (err) {
 		free_irq(lp->cfg.rx_irq, lp);
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index 938da19..cdc91d9 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/miscdevice.h>
+#include <linux/bootmem.h>
 
 #include <asm/cpudata.h>
 #include <asm/hypervisor.h>
@@ -108,25 +109,15 @@ static struct mdesc_handle * __init mdesc_lmb_alloc(unsigned int mdesc_size)
 
 static void mdesc_lmb_free(struct mdesc_handle *hp)
 {
-	unsigned int alloc_size, handle_size = hp->handle_size;
-	unsigned long start, end;
+	unsigned int alloc_size;
+	unsigned long start;
 
 	BUG_ON(atomic_read(&hp->refcnt) != 0);
 	BUG_ON(!list_empty(&hp->list));
 
-	alloc_size = PAGE_ALIGN(handle_size);
-
-	start = (unsigned long) hp;
-	end = start + alloc_size;
-
-	while (start < end) {
-		struct page *p;
-
-		p = virt_to_page(start);
-		ClearPageReserved(p);
-		__free_page(p);
-		start += PAGE_SIZE;
-	}
+	alloc_size = PAGE_ALIGN(hp->handle_size);
+	start = __pa(hp);
+	free_bootmem_late(start, alloc_size);
 }
 
 static struct mdesc_mem_ops lmb_mdesc_ops = {
diff --git a/arch/sparc/kernel/of_device_64.c b/arch/sparc/kernel/of_device_64.c
index 881947e..0a6f2d1 100644
--- a/arch/sparc/kernel/of_device_64.c
+++ b/arch/sparc/kernel/of_device_64.c
@@ -104,9 +104,19 @@ static int of_bus_pci_map(u32 *addr, const u32 *range,
 	int i;
 
 	/* Check address type match */
-	if ((addr[0] ^ range[0]) & 0x03000000)
-		return -EINVAL;
+	if (!((addr[0] ^ range[0]) & 0x03000000))
+		goto type_match;
+
+	/* Special exception, we can map a 64-bit address into
+	 * a 32-bit range.
+	 */
+	if ((addr[0] & 0x03000000) == 0x03000000 &&
+	    (range[0] & 0x03000000) == 0x02000000)
+		goto type_match;
+
+	return -EINVAL;
 
+type_match:
 	if (of_out_of_range(addr + 1, range + 1, range + na + pna,
 			    na - 1, ns))
 		return -EINVAL;
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index 4ae91dc..2f6524d 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -23,6 +23,7 @@
 #include <linux/signal.h>
 #include <linux/regset.h>
 #include <linux/tracehook.h>
+#include <trace/syscall.h>
 #include <linux/compat.h>
 #include <linux/elf.h>
 
@@ -37,6 +38,9 @@
 #include <asm/cpudata.h>
 #include <asm/cacheflush.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
 #include "entry.h"
 
 /* #define ALLOW_INIT_TRACING */
@@ -1059,6 +1063,9 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs)
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		ret = tracehook_report_syscall_entry(regs);
 
+	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+		trace_sys_enter(regs, regs->u_regs[UREG_G1]);
+
 	if (unlikely(current->audit_context) && !ret)
 		audit_syscall_entry((test_thread_flag(TIF_32BIT) ?
 				     AUDIT_ARCH_SPARC :
@@ -1084,6 +1091,9 @@ asmlinkage void syscall_trace_leave(struct pt_regs *regs)
 		audit_syscall_exit(result, regs->u_regs[UREG_I0]);
 	}
 
+	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+		trace_sys_exit(regs, regs->u_regs[UREG_G1]);
+
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, 0);
 }
diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S
index d150c2a..dc4a458 100644
--- a/arch/sparc/kernel/syscalls.S
+++ b/arch/sparc/kernel/syscalls.S
@@ -62,7 +62,7 @@ sys32_rt_sigreturn:
 #endif
 	.align	32
 1:	ldx	[%g6 + TI_FLAGS], %l5
-	andcc	%l5, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT), %g0
+	andcc	%l5, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %g0
 	be,pt	%icc, rtrap
 	 nop
 	call	syscall_trace_leave
@@ -187,7 +187,7 @@ linux_syscall_trace:
 	.globl	linux_sparc_syscall32
 linux_sparc_syscall32:
 	/* Direct access to user regs, much faster. */
-	cmp	%g1, NR_SYSCALLS			! IEU1	Group
+	cmp	%g1, NR_syscalls			! IEU1	Group
 	bgeu,pn	%xcc, linux_sparc_ni_syscall		! CTI
 	 srl	%i0, 0, %o0				! IEU0
 	sll	%g1, 2, %l4				! IEU0	Group
@@ -198,7 +198,7 @@ linux_sparc_syscall32:
 
 	srl	%i5, 0, %o5				! IEU1
 	srl	%i2, 0, %o2				! IEU0	Group
-	andcc	%l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT), %g0
+	andcc	%l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %g0
 	bne,pn	%icc, linux_syscall_trace32		! CTI
 	 mov	%i0, %l5				! IEU1
 	call	%l7					! CTI	Group brk forced
@@ -210,7 +210,7 @@ linux_sparc_syscall32:
 	.globl	linux_sparc_syscall
 linux_sparc_syscall:
 	/* Direct access to user regs, much faster. */
-	cmp	%g1, NR_SYSCALLS			! IEU1	Group
+	cmp	%g1, NR_syscalls			! IEU1	Group
 	bgeu,pn	%xcc, linux_sparc_ni_syscall		! CTI
 	 mov	%i0, %o0				! IEU0
 	sll	%g1, 2, %l4				! IEU0	Group
@@ -221,7 +221,7 @@ linux_sparc_syscall:
 
 	mov	%i3, %o3				! IEU1
 	mov	%i4, %o4				! IEU0	Group
-	andcc	%l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT), %g0
+	andcc	%l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %g0
 	bne,pn	%icc, linux_syscall_trace		! CTI	Group
 	 mov	%i0, %l5				! IEU0
 2:	call	%l7					! CTI	Group brk forced
@@ -245,7 +245,7 @@ ret_sys_call:
 
 	cmp	%o0, -ERESTART_RESTARTBLOCK
 	bgeu,pn	%xcc, 1f
-	 andcc	%l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT), %l6
+	 andcc	%l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %l6
 80:
 	/* System call success, clear Carry condition code. */
 	andn	%g3, %g2, %g3
@@ -260,7 +260,7 @@ ret_sys_call:
 	/* System call failure, set Carry condition code.
 	 * Also, get abs(errno) to return to the process.
 	 */
-	andcc	%l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT), %l6	
+	andcc	%l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %l6	
 	sub	%g0, %o0, %o0
 	or	%g3, %g2, %g3
 	stx	%o0, [%sp + PTREGS_OFF + PT_V9_I0]
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
index 63f73ae..67e1651 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -774,26 +774,9 @@ void __devinit setup_sparc64_timer(void)
 static struct clocksource clocksource_tick = {
 	.rating		= 100,
 	.mask		= CLOCKSOURCE_MASK(64),
-	.shift		= 16,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static void __init setup_clockevent_multiplier(unsigned long hz)
-{
-	unsigned long mult, shift = 32;
-
-	while (1) {
-		mult = div_sc(hz, NSEC_PER_SEC, shift);
-		if (mult && (mult >> 32UL) == 0UL)
-			break;
-
-		shift--;
-	}
-
-	sparc64_clockevent.shift = shift;
-	sparc64_clockevent.mult = mult;
-}
-
 static unsigned long tb_ticks_per_usec __read_mostly;
 
 void __delay(unsigned long loops)
@@ -828,9 +811,7 @@ void __init time_init(void)
 		clocksource_hz2mult(freq, SPARC64_NSEC_PER_CYC_SHIFT);
 
 	clocksource_tick.name = tick_ops->name;
-	clocksource_tick.mult =
-		clocksource_hz2mult(freq,
-				    clocksource_tick.shift);
+	clocksource_calc_mult_shift(&clocksource_tick, freq, 4);
 	clocksource_tick.read = clocksource_tick_read;
 
 	printk("clocksource: mult[%x] shift[%d]\n",
@@ -839,15 +820,14 @@ void __init time_init(void)
 	clocksource_register(&clocksource_tick);
 
 	sparc64_clockevent.name = tick_ops->name;
-
-	setup_clockevent_multiplier(freq);
+	clockevents_calc_mult_shift(&sparc64_clockevent, freq, 4);
 
 	sparc64_clockevent.max_delta_ns =
 		clockevent_delta2ns(0x7fffffffffffffffUL, &sparc64_clockevent);
 	sparc64_clockevent.min_delta_ns =
 		clockevent_delta2ns(0xF, &sparc64_clockevent);
 
-	printk("clockevent: mult[%ux] shift[%d]\n",
+	printk("clockevent: mult[%x] shift[%d]\n",
 	       sparc64_clockevent.mult, sparc64_clockevent.shift);
 
 	setup_sparc64_timer();
diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c
index 6b1e6cd..f8514e2 100644
--- a/arch/sparc/kernel/unaligned_32.c
+++ b/arch/sparc/kernel/unaligned_32.c
@@ -17,8 +17,7 @@
 #include <asm/uaccess.h>
 #include <linux/smp.h>
 #include <linux/smp_lock.h>
-
-/* #define DEBUG_MNA */
+#include <linux/perf_event.h>
 
 enum direction {
 	load,    /* ld, ldd, ldh, ldsh */
@@ -29,12 +28,6 @@ enum direction {
 	invalid,
 };
 
-#ifdef DEBUG_MNA
-static char *dirstrings[] = {
-  "load", "store", "both", "fpload", "fpstore", "invalid"
-};
-#endif
-
 static inline enum direction decode_direction(unsigned int insn)
 {
 	unsigned long tmp = (insn >> 21) & 1;
@@ -255,10 +248,7 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 		unsigned long addr = compute_effective_address(regs, insn);
 		int err;
 
-#ifdef DEBUG_MNA
-		printk("KMNA: pc=%08lx [dir=%s addr=%08lx size=%d] retpc[%08lx]\n",
-		       regs->pc, dirstrings[dir], addr, size, regs->u_regs[UREG_RETPC]);
-#endif
+		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, addr);
 		switch (dir) {
 		case load:
 			err = do_int_load(fetch_reg_addr(((insn>>25)&0x1f),
@@ -350,6 +340,7 @@ asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 		}
 
 		addr = compute_effective_address(regs, insn);
+		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, addr);
 		switch(dir) {
 		case load:
 			err = do_int_load(fetch_reg_addr(((insn>>25)&0x1f),
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index 3792099..378ca82 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -20,10 +20,9 @@
 #include <asm/uaccess.h>
 #include <linux/smp.h>
 #include <linux/bitops.h>
+#include <linux/perf_event.h>
 #include <asm/fpumacro.h>
 
-/* #define DEBUG_MNA */
-
 enum direction {
 	load,    /* ld, ldd, ldh, ldsh */
 	store,   /* st, std, sth, stsh */
@@ -33,12 +32,6 @@ enum direction {
 	invalid,
 };
 
-#ifdef DEBUG_MNA
-static char *dirstrings[] = {
-  "load", "store", "both", "fpload", "fpstore", "invalid"
-};
-#endif
-
 static inline enum direction decode_direction(unsigned int insn)
 {
 	unsigned long tmp = (insn >> 21) & 1;
@@ -327,12 +320,7 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 
 		addr = compute_effective_address(regs, insn,
 						 ((insn >> 25) & 0x1f));
-#ifdef DEBUG_MNA
-		printk("KMNA: pc=%016lx [dir=%s addr=%016lx size=%d] "
-		       "retpc[%016lx]\n",
-		       regs->tpc, dirstrings[dir], addr, size,
-		       regs->u_regs[UREG_RETPC]);
-#endif
+		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, addr);
 		switch (asi) {
 		case ASI_NL:
 		case ASI_AIUPL:
@@ -399,6 +387,7 @@ int handle_popc(u32 insn, struct pt_regs *regs)
 	int ret, i, rd = ((insn >> 25) & 0x1f);
 	int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
 	                        
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0);
 	if (insn & 0x2000) {
 		maybe_flush_windows(0, 0, rd, from_kernel);
 		value = sign_extend_imm13(insn);
@@ -445,6 +434,8 @@ int handle_ldf_stq(u32 insn, struct pt_regs *regs)
 	int asi = decode_asi(insn, regs);
 	int flag = (freg < 32) ? FPRS_DL : FPRS_DU;
 
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0);
+
 	save_and_clear_fpu();
 	current_thread_info()->xfsr[0] &= ~0x1c000;
 	if (freg & 3) {
@@ -566,6 +557,8 @@ void handle_ld_nf(u32 insn, struct pt_regs *regs)
 	int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
 	unsigned long *reg;
 	                        
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0);
+
 	maybe_flush_windows(0, 0, rd, from_kernel);
 	reg = fetch_reg_addr(rd, regs);
 	if (from_kernel || rd < 16) {
@@ -596,6 +589,7 @@ void handle_lddfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr
 
 	if (tstate & TSTATE_PRIV)
 		die_if_kernel("lddfmna from kernel", regs);
+	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, sfar);
 	if (test_thread_flag(TIF_32BIT))
 		pc = (u32)pc;
 	if (get_user(insn, (u32 __user *) pc) != -EFAULT) {
@@ -657,6 +651,7 @@ void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr
 
 	if (tstate & TSTATE_PRIV)
 		die_if_kernel("stdfmna from kernel", regs);
+	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, sfar);
 	if (test_thread_flag(TIF_32BIT))
 		pc = (u32)pc;
 	if (get_user(insn, (u32 __user *) pc) != -EFAULT) {
diff --git a/arch/sparc/kernel/visemul.c b/arch/sparc/kernel/visemul.c
index d231cbd..9dfd2eb 100644
--- a/arch/sparc/kernel/visemul.c
+++ b/arch/sparc/kernel/visemul.c
@@ -5,6 +5,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/thread_info.h>
+#include <linux/perf_event.h>
 
 #include <asm/ptrace.h>
 #include <asm/pstate.h>
@@ -801,6 +802,8 @@ int vis_emul(struct pt_regs *regs, unsigned int insn)
 
 	BUG_ON(regs->tstate & TSTATE_PRIV);
 
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0);
+
 	if (test_thread_flag(TIF_32BIT))
 		pc = (u32)pc;
 
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index e75faf0..c4b5e03 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -44,3 +44,4 @@ obj-y                 += iomap.o
 obj-$(CONFIG_SPARC32) += atomic32.o
 obj-y                 += ksyms.o
 obj-$(CONFIG_SPARC64) += PeeCeeI.o
+obj-y                 += usercopy.o
diff --git a/arch/sparc/lib/bzero.S b/arch/sparc/lib/bzero.S
index b655729..615f401 100644
--- a/arch/sparc/lib/bzero.S
+++ b/arch/sparc/lib/bzero.S
@@ -6,10 +6,6 @@
 
 	.text
 
-	.globl	__memset
-	.type	__memset, #function
-__memset:		/* %o0=buf, %o1=pat, %o2=len */
-
 	.globl	memset
 	.type	memset, #function
 memset:			/* %o0=buf, %o1=pat, %o2=len */
@@ -83,7 +79,6 @@ __bzero_done:
 	retl
 	 mov		%o3, %o0
 	.size		__bzero, .-__bzero
-	.size		__memset, .-__memset
 	.size		memset, .-memset
 
 #define EX_ST(x,y)		\
diff --git a/arch/sparc/lib/checksum_32.S b/arch/sparc/lib/checksum_32.S
index 77f2285..3632cb3 100644
--- a/arch/sparc/lib/checksum_32.S
+++ b/arch/sparc/lib/checksum_32.S
@@ -560,7 +560,7 @@ __csum_partial_copy_end:
 	 mov	%i0, %o1
 	mov	%i1, %o0
 5:
-	call	__memcpy
+	call	memcpy
 	 mov	%i2, %o2
 	tst	%o0
 	bne,a	2f
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 704b126..1b30bb3 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -30,7 +30,6 @@ EXPORT_SYMBOL(__memscan_generic);
 EXPORT_SYMBOL(memcmp);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(__memset);
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(__bzero);
 
@@ -81,7 +80,6 @@ EXPORT_SYMBOL(__csum_partial_copy_sparc_generic);
 
 /* Special internal versions of library functions. */
 EXPORT_SYMBOL(__copy_1page);
-EXPORT_SYMBOL(__memcpy);
 EXPORT_SYMBOL(__memmove);
 EXPORT_SYMBOL(bzero_1page);
 
diff --git a/arch/sparc/lib/mcount.S b/arch/sparc/lib/mcount.S
index 7ce9c65..24b8b12 100644
--- a/arch/sparc/lib/mcount.S
+++ b/arch/sparc/lib/mcount.S
@@ -64,8 +64,9 @@ mcount:
 2:	 sethi		%hi(softirq_stack), %g3
 	or		%g3, %lo(softirq_stack), %g3
 	ldx		[%g3 + %g1], %g7
+	sub		%g7, STACK_BIAS, %g7
 	cmp		%sp, %g7
-	bleu,pt		%xcc, 2f
+	bleu,pt		%xcc, 3f
 	 sethi		%hi(THREAD_SIZE), %g3
 	add		%g7, %g3, %g7
 	cmp		%sp, %g7
@@ -75,7 +76,7 @@ mcount:
 	 * again, we are already trying to output the stack overflow
 	 * message.
 	 */
-	sethi		%hi(ovstack), %g7		! cant move to panic stack fast enough
+3:	sethi		%hi(ovstack), %g7		! cant move to panic stack fast enough
 	 or		%g7, %lo(ovstack), %g7
 	add		%g7, OVSTACKSIZE, %g3
 	sub		%g3, STACK_BIAS + 192, %g3
diff --git a/arch/sparc/lib/memcpy.S b/arch/sparc/lib/memcpy.S
index ce10bc8..34fe657 100644
--- a/arch/sparc/lib/memcpy.S
+++ b/arch/sparc/lib/memcpy.S
@@ -543,9 +543,6 @@ FUNC(memmove)
 	b		3f
 	 add		%o0, 2, %o0
 
-#ifdef __KERNEL__
-FUNC(__memcpy)
-#endif
 FUNC(memcpy)	/* %o0=dst %o1=src %o2=len */
 
 	sub		%o0, %o1, %o4
diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S
index 1c37ea89..99c017b 100644
--- a/arch/sparc/lib/memset.S
+++ b/arch/sparc/lib/memset.S
@@ -60,11 +60,10 @@
         .globl  __bzero_begin
 __bzero_begin:
 
-	.globl	__bzero, __memset, 
+	.globl	__bzero
 	.globl	memset
 	.globl	__memset_start, __memset_end
 __memset_start:
-__memset:
 memset:
 	and	%o1, 0xff, %g3
 	sll	%g3, 8, %g2
diff --git a/arch/sparc/lib/usercopy.c b/arch/sparc/lib/usercopy.c
new file mode 100644
index 0000000..14b363f
--- /dev/null
+++ b/arch/sparc/lib/usercopy.c
@@ -0,0 +1,8 @@
+#include <linux/module.h>
+#include <linux/bug.h>
+
+void copy_from_user_overflow(void)
+{
+	WARN(1, "Buffer overflow detected!\n");
+}
+EXPORT_SYMBOL(copy_from_user_overflow);
diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c
index e13f65d..a3fccde 100644
--- a/arch/sparc/math-emu/math_32.c
+++ b/arch/sparc/math-emu/math_32.c
@@ -67,6 +67,7 @@
 #include <linux/types.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/perf_event.h>
 #include <asm/uaccess.h>
 
 #include "sfp-util_32.h"
@@ -163,6 +164,8 @@ int do_mathemu(struct pt_regs *regs, struct task_struct *fpt)
 	int retcode = 0;                               /* assume all succeed */
 	unsigned long insn;
 
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0);
+
 #ifdef DEBUG_MATHEMU
 	printk("In do_mathemu()... pc is %08lx\n", regs->pc);
 	printk("fpqdepth is %ld\n", fpt->thread.fpqdepth);
diff --git a/arch/sparc/math-emu/math_64.c b/arch/sparc/math-emu/math_64.c
index 6863c9b..56d2c44 100644
--- a/arch/sparc/math-emu/math_64.c
+++ b/arch/sparc/math-emu/math_64.c
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include <linux/sched.h>
 #include <linux/errno.h>
+#include <linux/perf_event.h>
 
 #include <asm/fpumacro.h>
 #include <asm/ptrace.h>
@@ -183,6 +184,7 @@ int do_mathemu(struct pt_regs *regs, struct fpustate *f)
 
 	if (tstate & TSTATE_PRIV)
 		die_if_kernel("unfinished/unimplemented FPop from kernel", regs);
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0);
 	if (test_thread_flag(TIF_32BIT))
 		pc = (u32)pc;
 	if (get_user(insn, (u32 __user *) pc) != -EFAULT) {
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 43b0da9..6081936 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -31,13 +31,12 @@
 #include <asm/sections.h>
 #include <asm/mmu_context.h>
 
-#ifdef CONFIG_KPROBES
-static inline int notify_page_fault(struct pt_regs *regs)
+static inline __kprobes int notify_page_fault(struct pt_regs *regs)
 {
 	int ret = 0;
 
 	/* kprobe_running() needs smp_processor_id() */
-	if (!user_mode(regs)) {
+	if (kprobes_built_in() && !user_mode(regs)) {
 		preempt_disable();
 		if (kprobe_running() && kprobe_fault_handler(regs, 0))
 			ret = 1;
@@ -45,12 +44,6 @@ static inline int notify_page_fault(struct pt_regs *regs)
 	}
 	return ret;
 }
-#else
-static inline int notify_page_fault(struct pt_regs *regs)
-{
-	return 0;
-}
-#endif
 
 static void __kprobes unhandled_fault(unsigned long address,
 				      struct task_struct *tsk,
@@ -73,7 +66,7 @@ static void __kprobes unhandled_fault(unsigned long address,
 	die_if_kernel("Oops", regs);
 }
 
-static void bad_kernel_pc(struct pt_regs *regs, unsigned long vaddr)
+static void __kprobes bad_kernel_pc(struct pt_regs *regs, unsigned long vaddr)
 {
 	printk(KERN_CRIT "OOPS: Bogus kernel PC [%016lx] in fault handler\n",
 	       regs->tpc);
@@ -170,8 +163,9 @@ static unsigned int get_fault_insn(struct pt_regs *regs, unsigned int insn)
 	return insn;
 }
 
-static void do_kernel_fault(struct pt_regs *regs, int si_code, int fault_code,
-			    unsigned int insn, unsigned long address)
+static void __kprobes do_kernel_fault(struct pt_regs *regs, int si_code,
+				      int fault_code, unsigned int insn,
+				      unsigned long address)
 {
 	unsigned char asi = ASI_P;
  
@@ -225,7 +219,7 @@ cannot_handle:
 	unhandled_fault (address, current, regs);
 }
 
-static void noinline bogus_32bit_fault_tpc(struct pt_regs *regs)
+static void noinline __kprobes bogus_32bit_fault_tpc(struct pt_regs *regs)
 {
 	static int times;
 
@@ -237,8 +231,8 @@ static void noinline bogus_32bit_fault_tpc(struct pt_regs *regs)
 	show_regs(regs);
 }
 
-static void noinline bogus_32bit_fault_address(struct pt_regs *regs,
-					       unsigned long addr)
+static void noinline __kprobes bogus_32bit_fault_address(struct pt_regs *regs,
+							 unsigned long addr)
 {
 	static int times;