Merge rsync://rsync.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

42 files changed, 867 insertions, 688 deletions

diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 8f146a4..bbea636 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -32,6 +32,7 @@
 #include <asm/leds.h>
 #include <asm/processor.h>
 #include <asm/uaccess.h>
+#include <asm/mach/time.h>
 
 extern const char *processor_modes[];
 extern void setup_mm_for_reboot(char mode);
@@ -85,8 +86,10 @@ EXPORT_SYMBOL(pm_power_off);
 void default_idle(void)
 {
 	local_irq_disable();
-	if (!need_resched() && !hlt_counter)
+	if (!need_resched() && !hlt_counter) {
+		timer_dyn_reprogram();
 		arch_idle();
+	}
 	local_irq_enable();
 }
 
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index 06054c9..1b7fcd5 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -424,15 +424,19 @@ static int timer_dyn_tick_disable(void)
 	return ret;
 }
 
+/*
+ * Reprogram the system timer for at least the calculated time interval.
+ * This function should be called from the idle thread with IRQs disabled,
+ * immediately before sleeping.
+ */
 void timer_dyn_reprogram(void)
 {
 	struct dyn_tick_timer *dyn_tick = system_timer->dyn_tick;
-	unsigned long flags;
 
-	write_seqlock_irqsave(&xtime_lock, flags);
+	write_seqlock(&xtime_lock);
 	if (dyn_tick->state & DYN_TICK_ENABLED)
 		dyn_tick->reprogram(next_timer_interrupt() - jiffies);
-	write_sequnlock_irqrestore(&xtime_lock, flags);
+	write_sequnlock(&xtime_lock);
 }
 
 static ssize_t timer_show_dyn_tick(struct sys_device *dev, char *buf)
diff --git a/arch/arm/mach-aaec2000/Makefile.boot b/arch/arm/mach-aaec2000/Makefile.boot
new file mode 100644
index 0000000..8f5a8b7
--- /dev/null
+++ b/arch/arm/mach-aaec2000/Makefile.boot
@@ -0,0 +1 @@
+	zreladdr-y := 0xf0008000
diff --git a/arch/arm/mach-omap/usb.c b/arch/arm/mach-omap/usb.c
index 6e805d4..7f37857 100644
--- a/arch/arm/mach-omap/usb.c
+++ b/arch/arm/mach-omap/usb.c
@@ -288,8 +288,8 @@ static void usb_release(struct device *dev)
 static struct resource udc_resources[] = {
 	/* order is significant! */
 	{		/* registers */
-		.start		= IO_ADDRESS(UDC_BASE),
-		.end		= IO_ADDRESS(UDC_BASE + 0xff),
+		.start		= UDC_BASE,
+		.end		= UDC_BASE + 0xff,
 		.flags		= IORESOURCE_MEM,
 	}, {		/* general IRQ */
 		.start		= IH2_BASE + 20,
@@ -355,8 +355,8 @@ static struct platform_device ohci_device = {
 static struct resource otg_resources[] = {
 	/* order is significant! */
 	{
-		.start		= IO_ADDRESS(OTG_BASE),
-		.end		= IO_ADDRESS(OTG_BASE + 0xff),
+		.start		= OTG_BASE,
+		.end		= OTG_BASE + 0xff,
 		.flags		= IORESOURCE_MEM,
 	}, {
 		.start		= IH2_BASE + 8,
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index c08710b..6dcb23d 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -522,6 +522,69 @@ static inline void free_area(unsigned long addr, unsigned long end, char *s)
 		printk(KERN_INFO "Freeing %s memory: %dK\n", s, size);
 }
 
+static inline void
+free_memmap(int node, unsigned long start_pfn, unsigned long end_pfn)
+{
+	struct page *start_pg, *end_pg;
+	unsigned long pg, pgend;
+
+	/*
+	 * Convert start_pfn/end_pfn to a struct page pointer.
+	 */
+	start_pg = pfn_to_page(start_pfn);
+	end_pg = pfn_to_page(end_pfn);
+
+	/*
+	 * Convert to physical addresses, and
+	 * round start upwards and end downwards.
+	 */
+	pg = PAGE_ALIGN(__pa(start_pg));
+	pgend = __pa(end_pg) & PAGE_MASK;
+
+	/*
+	 * If there are free pages between these,
+	 * free the section of the memmap array.
+	 */
+	if (pg < pgend)
+		free_bootmem_node(NODE_DATA(node), pg, pgend - pg);
+}
+
+/*
+ * The mem_map array can get very big.  Free the unused area of the memory map.
+ */
+static void __init free_unused_memmap_node(int node, struct meminfo *mi)
+{
+	unsigned long bank_start, prev_bank_end = 0;
+	unsigned int i;
+
+	/*
+	 * [FIXME] This relies on each bank being in address order.  This
+	 * may not be the case, especially if the user has provided the
+	 * information on the command line.
+	 */
+	for (i = 0; i < mi->nr_banks; i++) {
+		if (mi->bank[i].size == 0 || mi->bank[i].node != node)
+			continue;
+
+		bank_start = mi->bank[i].start >> PAGE_SHIFT;
+		if (bank_start < prev_bank_end) {
+			printk(KERN_ERR "MEM: unordered memory banks.  "
+				"Not freeing memmap.\n");
+			break;
+		}
+
+		/*
+		 * If we had a previous bank, and there is a space
+		 * between the current bank and the previous, free it.
+		 */
+		if (prev_bank_end && prev_bank_end != bank_start)
+			free_memmap(node, prev_bank_end, bank_start);
+
+		prev_bank_end = (mi->bank[i].start +
+				 mi->bank[i].size) >> PAGE_SHIFT;
+	}
+}
+
 /*
  * mem_init() marks the free areas in the mem_map and tells us how much
  * memory is free.  This is done after various parts of the system have
@@ -540,16 +603,12 @@ void __init mem_init(void)
 	max_mapnr   = virt_to_page(high_memory) - mem_map;
 #endif
 
-	/*
-	 * We may have non-contiguous memory.
-	 */
-	if (meminfo.nr_banks != 1)
-		create_memmap_holes(&meminfo);
-
 	/* this will put all unused low memory onto the freelists */
 	for_each_online_node(node) {
 		pg_data_t *pgdat = NODE_DATA(node);
 
+		free_unused_memmap_node(node, &meminfo);
+
 		if (pgdat->node_spanned_pages != 0)
 			totalram_pages += free_all_bootmem_node(pgdat);
 	}
diff --git a/arch/arm/mm/mm-armv.c b/arch/arm/mm/mm-armv.c
index 2c2b93d..052ab44 100644
--- a/arch/arm/mm/mm-armv.c
+++ b/arch/arm/mm/mm-armv.c
@@ -169,7 +169,14 @@ pgd_t *get_pgd_slow(struct mm_struct *mm)
 
 	memzero(new_pgd, FIRST_KERNEL_PGD_NR * sizeof(pgd_t));
 
+	/*
+	 * Copy over the kernel and IO PGD entries
+	 */
 	init_pgd = pgd_offset_k(0);
+	memcpy(new_pgd + FIRST_KERNEL_PGD_NR, init_pgd + FIRST_KERNEL_PGD_NR,
+		       (PTRS_PER_PGD - FIRST_KERNEL_PGD_NR) * sizeof(pgd_t));
+
+	clean_dcache_area(new_pgd, PTRS_PER_PGD * sizeof(pgd_t));
 
 	if (!vectors_high()) {
 		/*
@@ -198,14 +205,6 @@ pgd_t *get_pgd_slow(struct mm_struct *mm)
 		spin_unlock(&mm->page_table_lock);
 	}
 
-	/*
-	 * Copy over the kernel and IO PGD entries
-	 */
-	memcpy(new_pgd + FIRST_KERNEL_PGD_NR, init_pgd + FIRST_KERNEL_PGD_NR,
-		       (PTRS_PER_PGD - FIRST_KERNEL_PGD_NR) * sizeof(pgd_t));
-
-	clean_dcache_area(new_pgd, PTRS_PER_PGD * sizeof(pgd_t));
-
 	return new_pgd;
 
 no_pte:
@@ -698,75 +697,3 @@ void __init iotable_init(struct map_desc *io_desc, int nr)
 	for (i = 0; i < nr; i++)
 		create_mapping(io_desc + i);
 }
-
-static inline void
-free_memmap(int node, unsigned long start_pfn, unsigned long end_pfn)
-{
-	struct page *start_pg, *end_pg;
-	unsigned long pg, pgend;
-
-	/*
-	 * Convert start_pfn/end_pfn to a struct page pointer.
-	 */
-	start_pg = pfn_to_page(start_pfn);
-	end_pg = pfn_to_page(end_pfn);
-
-	/*
-	 * Convert to physical addresses, and
-	 * round start upwards and end downwards.
-	 */
-	pg = PAGE_ALIGN(__pa(start_pg));
-	pgend = __pa(end_pg) & PAGE_MASK;
-
-	/*
-	 * If there are free pages between these,
-	 * free the section of the memmap array.
-	 */
-	if (pg < pgend)
-		free_bootmem_node(NODE_DATA(node), pg, pgend - pg);
-}
-
-static inline void free_unused_memmap_node(int node, struct meminfo *mi)
-{
-	unsigned long bank_start, prev_bank_end = 0;
-	unsigned int i;
-
-	/*
-	 * [FIXME] This relies on each bank being in address order.  This
-	 * may not be the case, especially if the user has provided the
-	 * information on the command line.
-	 */
-	for (i = 0; i < mi->nr_banks; i++) {
-		if (mi->bank[i].size == 0 || mi->bank[i].node != node)
-			continue;
-
-		bank_start = mi->bank[i].start >> PAGE_SHIFT;
-		if (bank_start < prev_bank_end) {
-			printk(KERN_ERR "MEM: unordered memory banks.  "
-				"Not freeing memmap.\n");
-			break;
-		}
-
-		/*
-		 * If we had a previous bank, and there is a space
-		 * between the current bank and the previous, free it.
-		 */
-		if (prev_bank_end && prev_bank_end != bank_start)
-			free_memmap(node, prev_bank_end, bank_start);
-
-		prev_bank_end = PAGE_ALIGN(mi->bank[i].start +
-					   mi->bank[i].size) >> PAGE_SHIFT;
-	}
-}
-
-/*
- * The mem_map array can get very big.  Free
- * the unused area of the memory map.
- */
-void __init create_memmap_holes(struct meminfo *mi)
-{
-	int node;
-
-	for_each_online_node(node)
-		free_unused_memmap_node(node, mi);
-}
diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types
index 30c1dfb..6d3a79e 100644
--- a/arch/arm/tools/mach-types
+++ b/arch/arm/tools/mach-types
@@ -6,7 +6,7 @@
 # To add an entry into this database, please see Documentation/arm/README,
 # or contact rmk@arm.linux.org.uk
 #
-# Last update: Thu Mar 24 14:34:50 2005
+# Last update: Thu Jun 23 20:19:33 2005
 #
 # machine_is_xxx	CONFIG_xxxx		MACH_TYPE_xxx		number
 #
@@ -243,7 +243,7 @@ yoho			ARCH_YOHO		YOHO			231
 jasper			ARCH_JASPER		JASPER			232
 dsc25			ARCH_DSC25		DSC25			233
 omap_innovator		MACH_OMAP_INNOVATOR	OMAP_INNOVATOR		234
-ramses			ARCH_RAMSES		RAMSES			235
+mnci			ARCH_RAMSES		RAMSES			235
 s28x			ARCH_S28X		S28X			236
 mport3			ARCH_MPORT3		MPORT3			237
 pxa_eagle250		ARCH_PXA_EAGLE250	PXA_EAGLE250		238
@@ -323,7 +323,7 @@ nimbra29x		ARCH_NIMBRA29X		NIMBRA29X		311
 nimbra210		ARCH_NIMBRA210		NIMBRA210		312
 hhp_d95xx		ARCH_HHP_D95XX		HHP_D95XX		313
 labarm			ARCH_LABARM		LABARM			314
-m825xx			ARCH_M825XX		M825XX			315
+comcerto		ARCH_M825XX		M825XX			315
 m7100			SA1100_M7100		M7100			316
 nipc2			ARCH_NIPC2		NIPC2			317
 fu7202			ARCH_FU7202		FU7202			318
@@ -724,3 +724,66 @@ lpc22xx			MACH_LPC22XX		LPC22XX			715
 omap_comet3		MACH_COMET3		COMET3			716
 omap_comet4		MACH_COMET4		COMET4			717
 csb625			MACH_CSB625		CSB625			718
+fortunet2		MACH_FORTUNET2		FORTUNET2		719
+s5h2200			MACH_S5H2200		S5H2200			720
+optorm920		MACH_OPTORM920		OPTORM920		721
+adsbitsyxb		MACH_ADSBITSYXB		ADSBITSYXB		722
+adssphere		MACH_ADSSPHERE		ADSSPHERE		723
+adsportal		MACH_ADSPORTAL		ADSPORTAL		724
+ln2410sbc		MACH_LN2410SBC		LN2410SBC		725
+cb3rufc			MACH_CB3RUFC		CB3RUFC			726
+mp2usb			MACH_MP2USB		MP2USB			727
+ntnp425c		MACH_NTNP425C		NTNP425C		728
+colibri			MACH_COLIBRI		COLIBRI			729
+pcm7220			MACH_PCM7220		PCM7220			730
+gateway7001		MACH_GATEWAY7001	GATEWAY7001		731
+pcm027			MACH_PCM027		PCM027			732
+cmpxa			MACH_CMPXA		CMPXA			733
+anubis			MACH_ANUBIS		ANUBIS			734
+ite8152			MACH_ITE8152		ITE8152			735
+lpc3xxx			MACH_LPC3XXX		LPC3XXX			736
+puppeteer		MACH_PUPPETEER		PUPPETEER		737
+vt001			MACH_MACH_VADATECH	MACH_VADATECH		738
+e570			MACH_E570		E570			739
+x50			MACH_X50		X50			740
+recon			MACH_RECON		RECON			741
+xboardgp8		MACH_XBOARDGP8		XBOARDGP8		742
+fpic2			MACH_FPIC2		FPIC2			743
+akita			MACH_AKITA		AKITA			744
+a81			MACH_A81		A81			745
+svm_sc25x		MACH_SVM_SC25X		SVM_SC25X		746
+vt020			MACH_VADATECH020	VADATECH020		747
+tli			MACH_TLI		TLI			748
+edb9315lc		MACH_EDB9315LC		EDB9315LC		749
+passec			MACH_PASSEC		PASSEC			750
+ds_tiger		MACH_DS_TIGER		DS_TIGER		751
+e310			MACH_E310		E310			752
+e330			MACH_E330		E330			753
+rt3000			MACH_RT3000		RT3000			754
+nokia770		MACH_NOKIA770		NOKIA770		755
+pnx0106			MACH_PNX0106		PNX0106			756
+hx21xx			MACH_HX21XX		HX21XX			757
+faraday			MACH_FARADAY		FARADAY			758
+sbc9312			MACH_SBC9312		SBC9312			759
+batman			MACH_BATMAN		BATMAN			760
+jpd201			MACH_JPD201		JPD201			761
+mipsa			MACH_MIPSA		MIPSA			762
+kacom			MACH_KACOM		KACOM			763
+swarcocpu		MACH_SWARCOCPU		SWARCOCPU		764
+swarcodsl		MACH_SWARCODSL		SWARCODSL		765
+blueangel		MACH_BLUEANGEL		BLUEANGEL		766
+hairygrama		MACH_HAIRYGRAMA		HAIRYGRAMA		767
+banff			MACH_BANFF		BANFF			768
+carmeva			MACH_CARMEVA		CARMEVA			769
+sam255			MACH_SAM255		SAM255			770
+ppm10			MACH_PPM10		PPM10			771
+edb9315a		MACH_EDB9315A		EDB9315A		772
+sunset			MACH_SUNSET		SUNSET			773
+stargate2		MACH_STARGATE2		STARGATE2		774
+intelmote2		MACH_INTELMOTE2		INTELMOTE2		775
+trizeps4		MACH_TRIZEPS4		TRIZEPS4		776
+mainstone2		MACH_MAINSTONE2		MAINSTONE2		777
+ez_ixp42x		MACH_EZ_IXP42X		EZ_IXP42X		778
+tapwave_zodiac		MACH_TAPWAVE_ZODIAC	TAPWAVE_ZODIAC		779
+universalmeter		MACH_UNIVERSALMETER	UNIVERSALMETER		780
+hicoarm9		MACH_HICOARM9		HICOARM9		781
diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c
index 3762f6b..fc8b175 100644
--- a/arch/i386/kernel/kprobes.c
+++ b/arch/i386/kernel/kprobes.c
@@ -127,48 +127,23 @@ static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 		regs->eip = (unsigned long)&p->ainsn.insn;
 }
 
-struct task_struct  *arch_get_kprobe_task(void *ptr)
-{
-	return ((struct thread_info *) (((unsigned long) ptr) &
-					(~(THREAD_SIZE -1))))->task;
-}
-
 void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
 {
 	unsigned long *sara = (unsigned long *)&regs->esp;
-	struct kretprobe_instance *ri;
-	static void *orig_ret_addr;
+        struct kretprobe_instance *ri;
+
+        if ((ri = get_free_rp_inst(rp)) != NULL) {
+                ri->rp = rp;
+                ri->task = current;
+		ri->ret_addr = (kprobe_opcode_t *) *sara;
 
-	/*
-	 * Save the return address when the return probe hits
-	 * the first time, and use it to populate the (krprobe
-	 * instance)->ret_addr for subsequent return probes at
-	 * the same addrress since stack address would have
-	 * the kretprobe_trampoline by then.
-	 */
-	if (((void*) *sara) != kretprobe_trampoline)
-		orig_ret_addr = (void*) *sara;
-
-	if ((ri = get_free_rp_inst(rp)) != NULL) {
-		ri->rp = rp;
-		ri->stack_addr = sara;
-		ri->ret_addr = orig_ret_addr;
-		add_rp_inst(ri);
 		/* Replace the return addr with trampoline addr */
 		*sara = (unsigned long) &kretprobe_trampoline;
-	} else {
-		rp->nmissed++;
-	}
-}
 
-void arch_kprobe_flush_task(struct task_struct *tk)
-{
-	struct kretprobe_instance *ri;
-	while ((ri = get_rp_inst_tsk(tk)) != NULL) {
-		*((unsigned long *)(ri->stack_addr)) =
-					(unsigned long) ri->ret_addr;
-		recycle_rp_inst(ri);
-	}
+                add_rp_inst(ri);
+        } else {
+                rp->nmissed++;
+        }
 }
 
 /*
@@ -286,36 +261,59 @@ no_kprobe:
  */
 int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 {
-	struct task_struct *tsk;
-	struct kretprobe_instance *ri;
-	struct hlist_head *head;
-	struct hlist_node *node;
-	unsigned long *sara = ((unsigned long *) &regs->esp) - 1;
-
-	tsk = arch_get_kprobe_task(sara);
-	head = kretprobe_inst_table_head(tsk);
-
-	hlist_for_each_entry(ri, node, head, hlist) {
-		if (ri->stack_addr == sara && ri->rp) {
-			if (ri->rp->handler)
-				ri->rp->handler(ri, regs);
-		}
-	}
-	return 0;
-}
+        struct kretprobe_instance *ri = NULL;
+        struct hlist_head *head;
+        struct hlist_node *node, *tmp;
+	unsigned long orig_ret_address = 0;
+	unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;
 
-void trampoline_post_handler(struct kprobe *p, struct pt_regs *regs,
-						unsigned long flags)
-{
-	struct kretprobe_instance *ri;
-	/* RA already popped */
-	unsigned long *sara = ((unsigned long *)&regs->esp) - 1;
+        head = kretprobe_inst_table_head(current);
 
-	while ((ri = get_rp_inst(sara))) {
-		regs->eip = (unsigned long)ri->ret_addr;
+	/*
+	 * It is possible to have multiple instances associated with a given
+	 * task either because an multiple functions in the call path
+	 * have a return probe installed on them, and/or more then one return
+	 * return probe was registered for a target function.
+	 *
+	 * We can handle this because:
+	 *     - instances are always inserted at the head of the list
+	 *     - when multiple return probes are registered for the same
+         *       function, the first instance's ret_addr will point to the
+	 *       real return address, and all the rest will point to
+	 *       kretprobe_trampoline
+	 */
+	hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+                if (ri->task != current)
+			/* another task is sharing our hash bucket */
+                        continue;
+
+		if (ri->rp && ri->rp->handler)
+			ri->rp->handler(ri, regs);
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
 		recycle_rp_inst(ri);
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
 	}
-	regs->eflags &= ~TF_MASK;
+
+	BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address));
+	regs->eip = orig_ret_address;
+
+	unlock_kprobes();
+	preempt_enable_no_resched();
+
+        /*
+         * By returning a non-zero value, we are telling
+         * kprobe_handler() that we have handled unlocking
+         * and re-enabling preemption.
+         */
+        return 1;
 }
 
 /*
@@ -403,8 +401,7 @@ static inline int post_kprobe_handler(struct pt_regs *regs)
 		current_kprobe->post_handler(current_kprobe, regs, 0);
 	}
 
-	if (current_kprobe->post_handler != trampoline_post_handler)
-		resume_execution(current_kprobe, regs);
+	resume_execution(current_kprobe, regs);
 	regs->eflags |= kprobe_saved_eflags;
 
 	/*Restore back the original saved kprobes variables and continue. */
@@ -534,3 +531,13 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	}
 	return 0;
 }
+
+static struct kprobe trampoline_p = {
+	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
+	.pre_handler = trampoline_probe_handler
+};
+
+int __init arch_init(void)
+{
+	return register_kprobe(&trampoline_p);
+}
diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index 5f8cfa6..ba243a4 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -617,6 +617,33 @@ handle_io_bitmap(struct thread_struct *next, struct tss_struct *tss)
 }
 
 /*
+ * This function selects if the context switch from prev to next
+ * has to tweak the TSC disable bit in the cr4.
+ */
+static inline void disable_tsc(struct task_struct *prev_p,
+			       struct task_struct *next_p)
+{
+	struct thread_info *prev, *next;
+
+	/*
+	 * gcc should eliminate the ->thread_info dereference if
+	 * has_secure_computing returns 0 at compile time (SECCOMP=n).
+	 */
+	prev = prev_p->thread_info;
+	next = next_p->thread_info;
+
+	if (has_secure_computing(prev) || has_secure_computing(next)) {
+		/* slow path here */
+		if (has_secure_computing(prev) &&
+		    !has_secure_computing(next)) {
+			write_cr4(read_cr4() & ~X86_CR4_TSD);
+		} else if (!has_secure_computing(prev) &&
+			   has_secure_computing(next))
+			write_cr4(read_cr4() | X86_CR4_TSD);
+	}
+}
+
+/*
  *	switch_to(x,yn) should switch tasks from x to y.
  *
  * We fsave/fwait so that an exception goes off at the right time
@@ -695,6 +722,8 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas
 	if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr))
 		handle_io_bitmap(next, tss);
 
+	disable_tsc(prev_p, next_p);
+
 	return prev_p;
 }
 
diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S
index 442a6e9..3db9a04 100644
--- a/arch/i386/kernel/syscall_table.S
+++ b/arch/i386/kernel/syscall_table.S
@@ -289,3 +289,5 @@ ENTRY(sys_call_table)
 	.long sys_add_key
 	.long sys_request_key
 	.long sys_keyctl
+	.long sys_ioprio_set
+	.long sys_ioprio_get		/* 290 */
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index b1d5d3d..785a51b 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1577,8 +1577,8 @@ sys_call_table:
 	data8 sys_add_key
 	data8 sys_request_key
 	data8 sys_keyctl
-	data8 sys_ni_syscall
-	data8 sys_ni_syscall			// 1275
+	data8 sys_ioprio_set
+	data8 sys_ioprio_get			// 1275
 	data8 sys_set_zone_reclaim
 	data8 sys_ni_syscall
 	data8 sys_ni_syscall
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index 5978823..3aa3167 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -34,6 +34,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/kdebug.h>
+#include <asm/sections.h>
 
 extern void jprobe_inst_return(void);
 
@@ -263,13 +264,33 @@ static inline void get_kprobe_inst(bundle_t *bundle, uint slot,
 	}
 }
 
+/* Returns non-zero if the addr is in the Interrupt Vector Table */
+static inline int in_ivt_functions(unsigned long addr)
+{
+	return (addr >= (unsigned long)__start_ivt_text
+		&& addr < (unsigned long)__end_ivt_text);
+}
+
 static int valid_kprobe_addr(int template, int slot, unsigned long addr)
 {
 	if ((slot > 2) || ((bundle_encoding[template][1] == L) && slot > 1)) {
-		printk(KERN_WARNING "Attempting to insert unaligned kprobe at 0x%lx\n",
-				addr);
+		printk(KERN_WARNING "Attempting to insert unaligned kprobe "
+				"at 0x%lx\n", addr);
 		return -EINVAL;
 	}
+
+ 	if (in_ivt_functions(addr)) {
+ 		printk(KERN_WARNING "Kprobes can't be inserted inside "
+				"IVT functions at 0x%lx\n", addr);
+ 		return -EINVAL;
+ 	}
+
+	if (slot == 1 && bundle_encoding[template][1] != L) {
+		printk(KERN_WARNING "Inserting kprobes on slot #1 "
+		       "is not supported\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -290,6 +311,94 @@ static inline void set_current_kprobe(struct kprobe *p)
 	current_kprobe = p;
 }
 
+static void kretprobe_trampoline(void)
+{
+}
+
+/*
+ * At this point the target function has been tricked into
+ * returning into our trampoline.  Lookup the associated instance
+ * and then:
+ *    - call the handler function
+ *    - cleanup by marking the instance as unused
+ *    - long jump back to the original return address
+ */
+int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kretprobe_instance *ri = NULL;
+	struct hlist_head *head;
+	struct hlist_node *node, *tmp;
+	unsigned long orig_ret_address = 0;
+	unsigned long trampoline_address =
+		((struct fnptr *)kretprobe_trampoline)->ip;
+
+        head = kretprobe_inst_table_head(current);
+
+	/*
+	 * It is possible to have multiple instances associated with a given
+	 * task either because an multiple functions in the call path
+	 * have a return probe installed on them, and/or more then one return
+	 * return probe was registered for a target function.
+	 *
+	 * We can handle this because:
+	 *     - instances are always inserted at the head of the list
+	 *     - when multiple return probes are registered for the same
+	 *       function, the first instance's ret_addr will point to the
+	 *       real return address, and all the rest will point to
+	 *       kretprobe_trampoline
+	 */
+	hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+                if (ri->task != current)
+			/* another task is sharing our hash bucket */
+                        continue;
+
+		if (ri->rp && ri->rp->handler)
+			ri->rp->handler(ri, regs);
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
+		recycle_rp_inst(ri);
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address));
+	regs->cr_iip = orig_ret_address;
+
+	unlock_kprobes();
+	preempt_enable_no_resched();
+
+        /*
+         * By returning a non-zero value, we are telling
+         * kprobe_handler() that we have handled unlocking
+         * and re-enabling preemption.
+         */
+        return 1;
+}
+
+void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
+{
+	struct kretprobe_instance *ri;
+
+	if ((ri = get_free_rp_inst(rp)) != NULL) {
+		ri->rp = rp;
+		ri->task = current;
+		ri->ret_addr = (kprobe_opcode_t *)regs->b0;
+
+		/* Replace the return addr with trampoline addr */
+		regs->b0 = ((struct fnptr *)kretprobe_trampoline)->ip;
+
+		add_rp_inst(ri);
+	} else {
+		rp->nmissed++;
+	}
+}
+
 int arch_prepare_kprobe(struct kprobe *p)
 {
 	unsigned long addr = (unsigned long) p->addr;
@@ -492,8 +601,8 @@ static int pre_kprobes_handler(struct die_args *args)
 	if (p->pre_handler && p->pre_handler(p, regs))
 		/*
 		 * Our pre-handler is specifically requesting that we just
-		 * do a return.  This is handling the case where the
-		 * pre-handler is really our special jprobe pre-handler.
+		 * do a return.  This is used for both the jprobe pre-handler
+		 * and the kretprobe trampoline
 		 */
 		return 1;
 
@@ -599,3 +708,14 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	*regs = jprobe_saved_regs;
 	return 1;
 }
+
+static struct kprobe trampoline_p = {
+	.pre_handler = trampoline_probe_handler
+};
+
+int __init arch_init(void)
+{
+	trampoline_p.addr =
+		(kprobe_opcode_t *)((struct fnptr *)kretprobe_trampoline)->ip;
+	return register_kprobe(&trampoline_p);
+}
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index ebb71f3..6e35bff 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -27,6 +27,7 @@
 #include <linux/efi.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
+#include <linux/kprobes.h>
 
 #include <asm/cpu.h>
 #include <asm/delay.h>
@@ -707,6 +708,13 @@ kernel_thread_helper (int (*fn)(void *), void *arg)
 void
 flush_thread (void)
 {
+	/*
+	 * Remove function-return probe instances associated with this task
+	 * and put them back on the free list. Do not insert an exit probe for
+	 * this function, it will be disabled by kprobe_flush_task if you do.
+	 */
+	kprobe_flush_task(current);
+
 	/* drop floating-point and debug-register state if it exists: */
 	current->thread.flags &= ~(IA64_THREAD_FPH_VALID | IA64_THREAD_DBG_VALID);
 	ia64_drop_fpu(current);
@@ -721,6 +729,14 @@ flush_thread (void)
 void
 exit_thread (void)
 {
+
+	/*
+	 * Remove function-return probe instances associated with this task
+	 * and put them back on the free list. Do not insert an exit probe for
+	 * this function, it will be disabled by kprobe_flush_task if you do.
+	 */
+	kprobe_flush_task(current);
+
 	ia64_drop_fpu(current);
 #ifdef CONFIG_PERFMON
        /* if needed, stop monitoring and flush state to perfmon context */
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index b9f0db4..a676e79 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -8,6 +8,11 @@
 #define LOAD_OFFSET	(KERNEL_START - KERNEL_TR_PAGE_SIZE)
 #include <asm-generic/vmlinux.lds.h>
 
+#define IVT_TEXT							\
+		VMLINUX_SYMBOL(__start_ivt_text) = .;			\
+		*(.text.ivt)						\
+		VMLINUX_SYMBOL(__end_ivt_text) = .;
+
 OUTPUT_FORMAT("elf64-ia64-little")
 OUTPUT_ARCH(ia64)
 ENTRY(phys_start)
@@ -39,7 +44,7 @@ SECTIONS
 
   .text : AT(ADDR(.text) - LOAD_OFFSET)
     {
-	*(.text.ivt)
+	IVT_TEXT
 	*(.text)
 	SCHED_TEXT
 	LOCK_TEXT
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 508026a..65ee153 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -457,7 +457,7 @@ static int do_signal(sigset_t *oldset, struct pt_regs *regs)
 	if (!user_mode(regs))
 		return 1;
 
-	if (try_to_freeze(0))
+	if (try_to_freeze())
 		goto no_signal;
 
 	if (!oldset)
diff --git a/arch/ppc/kernel/misc.S b/arch/ppc/kernel/misc.S
index b6a63a4..191a8de 100644
--- a/arch/ppc/kernel/misc.S
+++ b/arch/ppc/kernel/misc.S
@@ -1449,3 +1449,5 @@ _GLOBAL(sys_call_table)
 	.long sys_request_key		/* 270 */
 	.long sys_keyctl
 	.long sys_waitid
+	.long sys_ioprio_set
+	.long sys_ioprio_get
diff --git a/arch/ppc/mm/init.c b/arch/ppc/mm/init.c
index 334ef41..6164a2b 100644
--- a/arch/ppc/mm/init.c
+++ b/arch/ppc/mm/init.c
@@ -606,9 +606,19 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
 		struct page *page = pfn_to_page(pfn);
 		if (!PageReserved(page)
 		    && !test_bit(PG_arch_1, &page->flags)) {
-			if (vma->vm_mm == current->active_mm)
+			if (vma->vm_mm == current->active_mm) {
+#ifdef CONFIG_8xx
+			/* On 8xx, cache control instructions (particularly 
+		 	 * "dcbst" from flush_dcache_icache) fault as write 
+			 * operation if there is an unpopulated TLB entry 
+			 * for the address in question. To workaround that, 
+			 * we invalidate the TLB here, thus avoiding dcbst 
+			 * misbehaviour.
+			 */
+				_tlbie(address);
+#endif
 				__flush_dcache_icache((void *) address);
-			else
+			} else
 				flush_dcache_icache_page(page);
 			set_bit(PG_arch_1, &page->flags);
 		}
diff --git a/arch/ppc/platforms/pmac_sleep.S b/arch/ppc/platforms/pmac_sleep.S
index f459ade..016a746 100644
--- a/arch/ppc/platforms/pmac_sleep.S
+++ b/arch/ppc/platforms/pmac_sleep.S
@@ -46,7 +46,7 @@
 	.section .text
 	.align	5
 
-#if defined(CONFIG_PMAC_PBOOK) || defined(CONFIG_CPU_FREQ_PMAC)
+#if defined(CONFIG_PM) || defined(CONFIG_CPU_FREQ_PMAC)
 
 /* This gets called by via-pmu.c late during the sleep process.
  * The PMU was already send the sleep command and will shut us down
@@ -382,7 +382,7 @@ turn_on_mmu:
 	isync
 	rfi
 
-#endif /* defined(CONFIG_PMAC_PBOOK) || defined(CONFIG_CPU_FREQ) */
+#endif /* defined(CONFIG_PM) || defined(CONFIG_CPU_FREQ) */
 
 	.section .data
 	.balign	L1_CACHE_LINE_SIZE
diff --git a/arch/ppc/platforms/pmac_time.c b/arch/ppc/platforms/pmac_time.c
index de60ccc..778ce4f 100644
--- a/arch/ppc/platforms/pmac_time.c
+++ b/arch/ppc/platforms/pmac_time.c
@@ -206,7 +206,7 @@ via_calibrate_decr(void)
 	return 1;
 }
 
-#ifdef CONFIG_PMAC_PBOOK
+#ifdef CONFIG_PM
 /*
  * Reset the time after a sleep.
  */
@@ -238,7 +238,7 @@ time_sleep_notify(struct pmu_sleep_notifier *self, int when)
 static struct pmu_sleep_notifier time_sleep_notifier __pmacdata = {
 	time_sleep_notify, SLEEP_LEVEL_MISC,
 };
-#endif /* CONFIG_PMAC_PBOOK */
+#endif /* CONFIG_PM */
 
 /*
  * Query the OF and get the decr frequency.
@@ -251,9 +251,9 @@ pmac_calibrate_decr(void)
 	struct device_node *cpu;
 	unsigned int freq, *fp;
 
-#ifdef CONFIG_PMAC_PBOOK
+#ifdef CONFIG_PM
 	pmu_register_sleep_notifier(&time_sleep_notifier);
-#endif /* CONFIG_PMAC_PBOOK */
+#endif /* CONFIG_PM */
 
 	/* We assume MacRISC2 machines have correct device-tree
 	 * calibration. That's better since the VIA itself seems
diff --git a/arch/ppc/platforms/sandpoint.c b/arch/ppc/platforms/sandpoint.c
index 70e58f4..8b149c2 100644
--- a/arch/ppc/platforms/sandpoint.c
+++ b/arch/ppc/platforms/sandpoint.c
@@ -324,6 +324,7 @@ sandpoint_setup_arch(void)
 			pdata[1].irq = 0;
 			pdata[1].mapbase = 0;
 		}
+	}
 
 	printk(KERN_INFO "Motorola SPS Sandpoint Test Platform\n");
 	printk(KERN_INFO "Port by MontaVista Software, Inc. (source@mvista.com)\n");
diff --git a/arch/ppc/syslib/open_pic.c b/arch/ppc/syslib/open_pic.c
index b45d826..ad39b86 100644
--- a/arch/ppc/syslib/open_pic.c
+++ b/arch/ppc/syslib/open_pic.c
@@ -370,8 +370,9 @@ void __init openpic_init(int offset)
 	/* Initialize IPI interrupts */
 	if ( ppc_md.progress ) ppc_md.progress("openpic: ipi",0x3bb);
 	for (i = 0; i < OPENPIC_NUM_IPI; i++) {
-		/* Disabled, Priority 10..13 */
-		openpic_initipi(i, 10+i, OPENPIC_VEC_IPI+i+offset);
+		/* Disabled, increased priorities 10..13 */
+		openpic_initipi(i, OPENPIC_PRIORITY_IPI_BASE+i,
+				OPENPIC_VEC_IPI+i+offset);
 		/* IPIs are per-CPU */
 		irq_desc[OPENPIC_VEC_IPI+i+offset].status |= IRQ_PER_CPU;
 		irq_desc[OPENPIC_VEC_IPI+i+offset].handler = &open_pic_ipi;
@@ -399,8 +400,9 @@ void __init openpic_init(int offset)
 		if (sense & IRQ_SENSE_MASK)
 			irq_desc[i+offset].status = IRQ_LEVEL;
 
-		/* Enabled, Priority 8 */
-		openpic_initirq(i, 8, i+offset, (sense & IRQ_POLARITY_MASK),
+		/* Enabled, Default priority */
+		openpic_initirq(i, OPENPIC_PRIORITY_DEFAULT, i+offset,
+				(sense & IRQ_POLARITY_MASK),
 				(sense & IRQ_SENSE_MASK));
 		/* Processor 0 */
 		openpic_mapirq(i, CPU_MASK_CPU0, CPU_MASK_NONE);
@@ -656,6 +658,18 @@ static void __init openpic_maptimer(u_int timer, cpumask_t cpumask)
 }
 
 /*
+ * Change the priority of an interrupt
+ */
+void __init
+openpic_set_irq_priority(u_int irq, u_int pri)
+{
+	check_arg_irq(irq);
+	openpic_safe_writefield(&ISR[irq - open_pic_irq_offset]->Vector_Priority,
+				OPENPIC_PRIORITY_MASK,
+				pri << OPENPIC_PRIORITY_SHIFT);
+}
+
+/*
  * Initalize the interrupt source which will generate an NMI.
  * This raises the interrupt's priority from 8 to 9.
  *
@@ -665,9 +679,7 @@ void __init
 openpic_init_nmi_irq(u_int irq)
 {
 	check_arg_irq(irq);
-	openpic_safe_writefield(&ISR[irq - open_pic_irq_offset]->Vector_Priority,
-				OPENPIC_PRIORITY_MASK,
-				9 << OPENPIC_PRIORITY_SHIFT);
+	openpic_set_irq_priority(irq, OPENPIC_PRIORITY_NMI);
 }
 
 /*
diff --git a/arch/ppc64/kernel/kprobes.c b/arch/ppc64/kernel/kprobes.c
index 782ce3e..1d2ff6d 100644
--- a/arch/ppc64/kernel/kprobes.c
+++ b/arch/ppc64/kernel/kprobes.c
@@ -36,6 +36,8 @@
 #include <asm/kdebug.h>
 #include <asm/sstep.h>
 
+static DECLARE_MUTEX(kprobe_mutex);
+
 static struct kprobe *current_kprobe;
 static unsigned long kprobe_status, kprobe_saved_msr;
 static struct kprobe *kprobe_prev;
@@ -54,6 +56,15 @@ int arch_prepare_kprobe(struct kprobe *p)
 		printk("Cannot register a kprobe on rfid or mtmsrd\n");
 		ret = -EINVAL;
 	}
+
+	/* insn must be on a special executable page on ppc64 */
+	if (!ret) {
+		up(&kprobe_mutex);
+		p->ainsn.insn = get_insn_slot();
+		down(&kprobe_mutex);
+		if (!p->ainsn.insn)
+			ret = -ENOMEM;
+	}
 	return ret;
 }
 
@@ -79,16 +90,22 @@ void arch_disarm_kprobe(struct kprobe *p)
 
 void arch_remove_kprobe(struct kprobe *p)
 {
+	up(&kprobe_mutex);
+	free_insn_slot(p->ainsn.insn);
+	down(&kprobe_mutex);
 }
 
 static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 {
+	kprobe_opcode_t insn = *p->ainsn.insn;
+
 	regs->msr |= MSR_SE;
-	/*single step inline if it a breakpoint instruction*/
-	if (p->opcode == BREAKPOINT_INSTRUCTION)
+
+	/* single step inline if it is a trap variant */
+	if (IS_TW(insn) || IS_TD(insn) || IS_TWI(insn) || IS_TDI(insn))
 		regs->nip = (unsigned long)p->addr;
 	else
-		regs->nip = (unsigned long)&p->ainsn.insn;
+		regs->nip = (unsigned long)p->ainsn.insn;
 }
 
 static inline void save_previous_kprobe(void)
@@ -105,6 +122,23 @@ static inline void restore_previous_kprobe(void)
 	kprobe_saved_msr = kprobe_saved_msr_prev;
 }
 
+void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
+{
+	struct kretprobe_instance *ri;
+
+	if ((ri = get_free_rp_inst(rp)) != NULL) {
+		ri->rp = rp;
+		ri->task = current;
+		ri->ret_addr = (kprobe_opcode_t *)regs->link;
+
+		/* Replace the return addr with trampoline addr */
+		regs->link = (unsigned long)kretprobe_trampoline;
+		add_rp_inst(ri);
+	} else {
+		rp->nmissed++;
+	}
+}
+
 static inline int kprobe_handler(struct pt_regs *regs)
 {
 	struct kprobe *p;
@@ -195,6 +229,78 @@ no_kprobe:
 }
 
 /*
+ * Function return probe trampoline:
+ * 	- init_kprobes() establishes a probepoint here
+ * 	- When the probed function returns, this probe
+ * 		causes the handlers to fire
+ */
+void kretprobe_trampoline_holder(void)
+{
+	asm volatile(".global kretprobe_trampoline\n"
+			"kretprobe_trampoline:\n"
+			"nop\n");
+}
+
+/*
+ * Called when the probe at kretprobe trampoline is hit
+ */
+int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
+{
+        struct kretprobe_instance *ri = NULL;
+        struct hlist_head *head;
+        struct hlist_node *node, *tmp;
+	unsigned long orig_ret_address = 0;
+	unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;
+
+        head = kretprobe_inst_table_head(current);
+
+	/*
+	 * It is possible to have multiple instances associated with a given
+	 * task either because an multiple functions in the call path
+	 * have a return probe installed on them, and/or more then one return
+	 * return probe was registered for a target function.
+	 *
+	 * We can handle this because:
+	 *     - instances are always inserted at the head of the list
+	 *     - when multiple return probes are registered for the same
+         *       function, the first instance's ret_addr will point to the
+	 *       real return address, and all the rest will point to
+	 *       kretprobe_trampoline
+	 */
+	hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+                if (ri->task != current)
+			/* another task is sharing our hash bucket */
+                        continue;
+
+		if (ri->rp && ri->rp->handler)
+			ri->rp->handler(ri, regs);
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
+		recycle_rp_inst(ri);
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address));
+	regs->nip = orig_ret_address;
+
+	unlock_kprobes();
+
+        /*
+         * By returning a non-zero value, we are telling
+         * kprobe_handler() that we have handled unlocking
+         * and re-enabling preemption.
+         */
+        return 1;
+}
+
+/*
  * Called after single-stepping.  p->addr is the address of the
  * instruction whose first byte has been replaced by the "breakpoint"
  * instruction.  To avoid the SMP problems that can occur when we
@@ -205,9 +311,10 @@ no_kprobe:
 static void resume_execution(struct kprobe *p, struct pt_regs *regs)
 {
 	int ret;
+	unsigned int insn = *p->ainsn.insn;
 
 	regs->nip = (unsigned long)p->addr;
-	ret = emulate_step(regs, p->ainsn.insn[0]);
+	ret = emulate_step(regs, insn);
 	if (ret == 0)
 		regs->nip = (unsigned long)p->addr + 4;
 }
@@ -331,3 +438,13 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	memcpy(regs, &jprobe_saved_regs, sizeof(struct pt_regs));
 	return 1;
 }
+
+static struct kprobe trampoline_p = {
+	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
+	.pre_handler = trampoline_probe_handler
+};
+
+int __init arch_init(void)
+{
+	return register_kprobe(&trampoline_p);
+}
diff --git a/arch/ppc64/kernel/ppc_ksyms.c b/arch/ppc64/kernel/ppc_ksyms.c
index b230a63..705742f 100644
--- a/arch/ppc64/kernel/ppc_ksyms.c
+++ b/arch/ppc64/kernel/ppc_ksyms.c
@@ -75,6 +75,7 @@ EXPORT_SYMBOL(giveup_fpu);
 EXPORT_SYMBOL(giveup_altivec);
 #endif
 EXPORT_SYMBOL(__flush_icache_range);
+EXPORT_SYMBOL(flush_dcache_range);
 
 #ifdef CONFIG_SMP
 #ifdef CONFIG_PPC_ISERIES
diff --git a/arch/ppc64/kernel/process.c b/arch/ppc64/kernel/process.c
index aba8955..f7cae05 100644
--- a/arch/ppc64/kernel/process.c
+++ b/arch/ppc64/kernel/process.c
@@ -36,6 +36,7 @@
 #include <linux/kallsyms.h>
 #include <linux/interrupt.h>
 #include <linux/utsname.h>
+#include <linux/kprobes.h>
 
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
@@ -307,6 +308,8 @@ void show_regs(struct pt_regs * regs)
 
 void exit_thread(void)
 {
+	kprobe_flush_task(current);
+
 #ifndef CONFIG_SMP
 	if (last_task_used_math == current)
 		last_task_used_math = NULL;
@@ -321,6 +324,7 @@ void flush_thread(void)
 {
 	struct thread_info *t = current_thread_info();
 
+	kprobe_flush_task(current);
 	if (t->flags & _TIF_ABI_PENDING)
 		t->flags ^= (_TIF_ABI_PENDING | _TIF_32BIT);
 
diff --git a/arch/ppc64/kernel/time.c b/arch/ppc64/kernel/time.c
index 2348a75..2a532db 100644
--- a/arch/ppc64/kernel/time.c
+++ b/arch/ppc64/kernel/time.c
@@ -91,6 +91,7 @@ unsigned long tb_to_xs;
 unsigned      tb_to_us;
 unsigned long processor_freq;
 DEFINE_SPINLOCK(rtc_lock);
+EXPORT_SYMBOL_GPL(rtc_lock);
 
 unsigned long tb_to_ns_scale;
 unsigned long tb_to_ns_shift;
diff --git a/arch/sparc64/kernel/auxio.c b/arch/sparc64/kernel/auxio.c
index a0716cc..8852c20 100644
--- a/arch/sparc64/kernel/auxio.c
+++ b/arch/sparc64/kernel/auxio.c
@@ -16,7 +16,7 @@
 #include <asm/ebus.h>
 #include <asm/auxio.h>
 
-/* This cannot be static, as it is referenced in entry.S */
+/* This cannot be static, as it is referenced in irq.c */
 void __iomem *auxio_register = NULL;
 
 enum auxio_type {
diff --git a/arch/sparc64/kernel/entry.S b/arch/sparc64/kernel/entry.S
index a47f2d0..eee516a 100644
--- a/arch/sparc64/kernel/entry.S
+++ b/arch/sparc64/kernel/entry.S
@@ -271,8 +271,9 @@ cplus_fptrap_insn_1:
 	fmuld		%f0, %f2, %f26
 	faddd		%f0, %f2, %f28
 	fmuld		%f0, %f2, %f30
+	membar		#Sync
 	b,pt		%xcc, fpdis_exit
-	 membar		#Sync
+	 nop
 2:	andcc		%g5, FPRS_DU, %g0
 	bne,pt		%icc, 3f
 	 fzero		%f32
@@ -301,8 +302,9 @@ cplus_fptrap_insn_2:
 	fmuld		%f32, %f34, %f58
 	faddd		%f32, %f34, %f60
 	fmuld		%f32, %f34, %f62
+	membar		#Sync
 	ba,pt		%xcc, fpdis_exit
-	 membar		#Sync
+	 nop
 3:	mov		SECONDARY_CONTEXT, %g3
 	add		%g6, TI_FPREGS, %g1
 	ldxa		[%g3] ASI_DMMU, %g5
@@ -699,116 +701,6 @@ utrap_ill:
 	ba,pt		%xcc, rtrap
 	 clr		%l6
 
-#ifdef CONFIG_BLK_DEV_FD
-	.globl		floppy_hardint
-floppy_hardint:
-	wr		%g0, (1 << 11), %clear_softint
-	sethi		%hi(doing_pdma), %g1
-	ld		[%g1 + %lo(doing_pdma)], %g2
-	brz,pn		%g2, floppy_dosoftint
-	 sethi		%hi(fdc_status), %g3
-	ldx		[%g3 + %lo(fdc_status)], %g3
-	sethi		%hi(pdma_vaddr), %g5
-	ldx		[%g5 + %lo(pdma_vaddr)], %g4
-	sethi		%hi(pdma_size), %g5
-	ldx		[%g5 + %lo(pdma_size)], %g5
-
-next_byte:
-	lduba		[%g3] ASI_PHYS_BYPASS_EC_E, %g7
-	andcc		%g7, 0x80, %g0
-	be,pn		%icc, floppy_fifo_emptied
-	 andcc		%g7, 0x20, %g0
-	be,pn		%icc, floppy_overrun
-	 andcc		%g7, 0x40, %g0
-	be,pn		%icc, floppy_write
-	 sub		%g5, 1, %g5
-
-	inc		%g3
-	lduba		[%g3] ASI_PHYS_BYPASS_EC_E, %g7
-	dec		%g3
-	orcc		%g0, %g5, %g0
-	stb		%g7, [%g4]
-	bne,pn		%xcc, next_byte
-	 add		%g4, 1, %g4
-
-	b,pt		%xcc, floppy_tdone
-	 nop
-
-floppy_write:
-	ldub		[%g4], %g7
-	orcc		%g0, %g5, %g0
-	inc		%g3
-	stba		%g7, [%g3] ASI_PHYS_BYPASS_EC_E
-	dec		%g3
-	bne,pn		%xcc, next_byte
-	 add		%g4, 1, %g4
-
-floppy_tdone:
-	sethi		%hi(pdma_vaddr), %g1
-	stx		%g4, [%g1 + %lo(pdma_vaddr)]
-	sethi		%hi(pdma_size), %g1
-	stx		%g5, [%g1 + %lo(pdma_size)]
-	sethi		%hi(auxio_register), %g1
-	ldx		[%g1 + %lo(auxio_register)], %g7
-	lduba		[%g7] ASI_PHYS_BYPASS_EC_E, %g5
-	or		%g5, AUXIO_AUX1_FTCNT, %g5
-/*	andn		%g5, AUXIO_AUX1_MASK, %g5 */
-	stba		%g5, [%g7] ASI_PHYS_BYPASS_EC_E
-	andn		%g5, AUXIO_AUX1_FTCNT, %g5
-/*	andn		%g5, AUXIO_AUX1_MASK, %g5 */
-
-	nop; nop;  nop; nop;  nop; nop;
-	nop; nop;  nop; nop;  nop; nop;
-
-	stba		%g5, [%g7] ASI_PHYS_BYPASS_EC_E
-	sethi		%hi(doing_pdma), %g1
-	b,pt		%xcc, floppy_dosoftint
-	 st		%g0, [%g1 + %lo(doing_pdma)]
-
-floppy_fifo_emptied:
-	sethi		%hi(pdma_vaddr), %g1
-	stx		%g4, [%g1 + %lo(pdma_vaddr)]
-	sethi		%hi(pdma_size), %g1
-	stx		%g5, [%g1 + %lo(pdma_size)]
-	sethi		%hi(irq_action), %g1
-	or		%g1, %lo(irq_action), %g1
-	ldx		[%g1 + (11 << 3)], %g3		! irqaction[floppy_irq]
-	ldx		[%g3 + 0x08], %g4		! action->flags>>48==ino
-	sethi		%hi(ivector_table), %g3
-	srlx		%g4, 48, %g4
-	or		%g3, %lo(ivector_table), %g3
-	sllx		%g4, 5, %g4
-	ldx		[%g3 + %g4], %g4		! &ivector_table[ino]
-	ldx		[%g4 + 0x10], %g4		! bucket->iclr
-	stwa		%g0, [%g4] ASI_PHYS_BYPASS_EC_E	! ICLR_IDLE
-	membar		#Sync				! probably not needed...
-	retry
-
-floppy_overrun:
-	sethi		%hi(pdma_vaddr), %g1
-	stx		%g4, [%g1 + %lo(pdma_vaddr)]
-	sethi		%hi(pdma_size), %g1
-	stx		%g5, [%g1 + %lo(pdma_size)]
-	sethi		%hi(doing_pdma), %g1
-	st		%g0, [%g1 + %lo(doing_pdma)]
-
-floppy_dosoftint:
-	rdpr		%pil, %g2
-	wrpr		%g0, 15, %pil
-	sethi		%hi(109f), %g7
-	b,pt		%xcc, etrap_irq
-109:	 or		%g7, %lo(109b), %g7
-
-	mov		11, %o0
-	mov		0, %o1
-	call		sparc_floppy_irq
-	 add		%sp, PTREGS_OFF, %o2
-
-	b,pt		%xcc, rtrap_irq
-	 nop
-
-#endif /* CONFIG_BLK_DEV_FD */
-
 	/* XXX Here is stuff we still need to write... -DaveM XXX */
 	.globl		netbsd_syscall
 netbsd_syscall:
diff --git a/arch/sparc64/kernel/irq.c b/arch/sparc64/kernel/irq.c
index 4dcb8af..4247125 100644
--- a/arch/sparc64/kernel/irq.c
+++ b/arch/sparc64/kernel/irq.c
@@ -37,6 +37,7 @@
 #include <asm/uaccess.h>
 #include <asm/cache.h>
 #include <asm/cpudata.h>
+#include <asm/auxio.h>
 
 #ifdef CONFIG_SMP
 static void distribute_irqs(void);
@@ -834,137 +835,65 @@ void handler_irq(int irq, struct pt_regs *regs)
 }
 
 #ifdef CONFIG_BLK_DEV_FD
-extern void floppy_interrupt(int irq, void *dev_cookie, struct pt_regs *regs);
+extern irqreturn_t floppy_interrupt(int, void *, struct pt_regs *);;
 
-void sparc_floppy_irq(int irq, void *dev_cookie, struct pt_regs *regs)
-{
-	struct irqaction *action = *(irq + irq_action);
-	struct ino_bucket *bucket;
-	int cpu = smp_processor_id();
-
-	irq_enter();
-	kstat_this_cpu.irqs[irq]++;
-
-	*(irq_work(cpu, irq)) = 0;
-	bucket = get_ino_in_irqaction(action) + ivector_table;
-
-	bucket->flags |= IBF_INPROGRESS;
-
-	floppy_interrupt(irq, dev_cookie, regs);
-	upa_writel(ICLR_IDLE, bucket->iclr);
-
-	bucket->flags &= ~IBF_INPROGRESS;
-
-	irq_exit();
-}
-#endif
-
-/* The following assumes that the branch lies before the place we
- * are branching to.  This is the case for a trap vector...
- * You have been warned.
- */
-#define SPARC_BRANCH(dest_addr, inst_addr) \
-          (0x10800000 | ((((dest_addr)-(inst_addr))>>2)&0x3fffff))
-
-#define SPARC_NOP (0x01000000)
+/* XXX No easy way to include asm/floppy.h XXX */
+extern unsigned char *pdma_vaddr;
+extern unsigned long pdma_size;
+extern volatile int doing_pdma;
+extern unsigned long fdc_status;
 
-static void install_fast_irq(unsigned int cpu_irq,
-			     irqreturn_t (*handler)(int, void *, struct pt_regs *))
+irqreturn_t sparc_floppy_irq(int irq, void *dev_cookie, struct pt_regs *regs)
 {
-	extern unsigned long sparc64_ttable_tl0;
-	unsigned long ttent = (unsigned long) &sparc64_ttable_tl0;
-	unsigned int *insns;
-
-	ttent += 0x820;
-	ttent += (cpu_irq - 1) << 5;
-	insns = (unsigned int *) ttent;
-	insns[0] = SPARC_BRANCH(((unsigned long) handler),
-				((unsigned long)&insns[0]));
-	insns[1] = SPARC_NOP;
-	__asm__ __volatile__("membar #StoreStore; flush %0" : : "r" (ttent));
-}
-
-int request_fast_irq(unsigned int irq,
-		     irqreturn_t (*handler)(int, void *, struct pt_regs *),
-		     unsigned long irqflags, const char *name, void *dev_id)
-{
-	struct irqaction *action;
-	struct ino_bucket *bucket = __bucket(irq);
-	unsigned long flags;
-
-	/* No pil0 dummy buckets allowed here. */
-	if (bucket < &ivector_table[0] ||
-	    bucket >= &ivector_table[NUM_IVECS]) {
-		unsigned int *caller;
-
-		__asm__ __volatile__("mov %%i7, %0" : "=r" (caller));
-		printk(KERN_CRIT "request_fast_irq: Old style IRQ registry attempt "
-		       "from %p, irq %08x.\n", caller, irq);
-		return -EINVAL;
-	}	
-	
-	if (!handler)
-		return -EINVAL;
+	if (likely(doing_pdma)) {
+		void __iomem *stat = (void __iomem *) fdc_status;
+		unsigned char *vaddr = pdma_vaddr;
+		unsigned long size = pdma_size;
+		u8 val;
+
+		while (size) {
+			val = readb(stat);
+			if (unlikely(!(val & 0x80))) {
+				pdma_vaddr = vaddr;
+				pdma_size = size;
+				return IRQ_HANDLED;
+			}
+			if (unlikely(!(val & 0x20))) {
+				pdma_vaddr = vaddr;
+				pdma_size = size;
+				doing_pdma = 0;
+				goto main_interrupt;
+			}
+			if (val & 0x40) {
+				/* read */
+				*vaddr++ = readb(stat + 1);
+			} else {
+				unsigned char data = *vaddr++;
 
-	if ((bucket->pil == 0) || (bucket->pil == 14)) {
-		printk("request_fast_irq: Trying to register shared IRQ 0 or 14.\n");
-		return -EBUSY;
-	}
+				/* write */
+				writeb(data, stat + 1);
+			}
+			size--;
+		}
 
-	spin_lock_irqsave(&irq_action_lock, flags);
+		pdma_vaddr = vaddr;
+		pdma_size = size;
 
-	action = *(bucket->pil + irq_action);
-	if (action) {
-		if (action->flags & SA_SHIRQ)
-			panic("Trying to register fast irq when already shared.\n");
-		if (irqflags & SA_SHIRQ)
-			panic("Trying to register fast irq as shared.\n");
-		printk("request_fast_irq: Trying to register yet already owned.\n");
-		spin_unlock_irqrestore(&irq_action_lock, flags);
-		return -EBUSY;
-	}
+		/* Send Terminal Count pulse to floppy controller. */
+		val = readb(auxio_register);
+		val |= AUXIO_AUX1_FTCNT;
+		writeb(val, auxio_register);
+		val &= AUXIO_AUX1_FTCNT;
+		writeb(val, auxio_register);
 
-	/*
-	 * We do not check for SA_SAMPLE_RANDOM in this path. Neither do we
-	 * support smp intr affinity in this path.
-	 */
-	if (irqflags & SA_STATIC_ALLOC) {
-		if (static_irq_count < MAX_STATIC_ALLOC)
-			action = &static_irqaction[static_irq_count++];
-		else
-			printk("Request for IRQ%d (%s) SA_STATIC_ALLOC failed "
-			       "using kmalloc\n", bucket->pil, name);
-	}
-	if (action == NULL)
-		action = (struct irqaction *)kmalloc(sizeof(struct irqaction),
-						     GFP_ATOMIC);
-	if (!action) {
-		spin_unlock_irqrestore(&irq_action_lock, flags);
-		return -ENOMEM;
+		doing_pdma = 0;
 	}
-	install_fast_irq(bucket->pil, handler);
 
-	bucket->irq_info = action;
-	bucket->flags |= IBF_ACTIVE;
-
-	action->handler = handler;
-	action->flags = irqflags;
-	action->dev_id = NULL;
-	action->name = name;
-	action->next = NULL;
-	put_ino_in_irqaction(action, irq);
-	put_smpaff_in_irqaction(action, CPU_MASK_NONE);
-
-	*(bucket->pil + irq_action) = action;
-	enable_irq(irq);
-
-	spin_unlock_irqrestore(&irq_action_lock, flags);
-
-#ifdef CONFIG_SMP
-	distribute_irqs();
-#endif
-	return 0;
+main_interrupt:
+	return floppy_interrupt(irq, dev_cookie, regs);
 }
+EXPORT_SYMBOL(sparc_floppy_irq);
+#endif
 
 /* We really don't need these at all on the Sparc.  We only have
  * stubs here because they are exported to modules.
diff --git a/arch/sparc64/kernel/semaphore.c b/arch/sparc64/kernel/semaphore.c
index 63496c4..a809e63 100644
--- a/arch/sparc64/kernel/semaphore.c
+++ b/arch/sparc64/kernel/semaphore.c
@@ -32,8 +32,9 @@ static __inline__ int __sem_update_count(struct semaphore *sem, int incr)
 "	add	%1, %4, %1\n"
 "	cas	[%3], %0, %1\n"
 "	cmp	%0, %1\n"
+"	membar	#StoreLoad | #StoreStore\n"
 "	bne,pn	%%icc, 1b\n"
-"	 membar #StoreLoad | #StoreStore\n"
+"	 nop\n"
 	: "=&r" (old_count), "=&r" (tmp), "=m" (sem->count)
 	: "r" (&sem->count), "r" (incr), "m" (sem->count)
 	: "cc");
@@ -71,8 +72,9 @@ void up(struct semaphore *sem)
 "	cmp	%%g1, %%g7\n"
 "	bne,pn	%%icc, 1b\n"
 "	 addcc	%%g7, 1, %%g0\n"
+"	membar	#StoreLoad | #StoreStore\n"
 "	ble,pn	%%icc, 3f\n"
-"	 membar	#StoreLoad | #StoreStore\n"
+"	 nop\n"
 "2:\n"
 "	.subsection 2\n"
 "3:	mov	%0, %%g1\n"
@@ -128,8 +130,9 @@ void __sched down(struct semaphore *sem)
 "	cmp	%%g1, %%g7\n"
 "	bne,pn	%%icc, 1b\n"
 "	 cmp	%%g7, 1\n"
+"	membar	#StoreLoad | #StoreStore\n"
 "	bl,pn	%%icc, 3f\n"
-"	 membar	#StoreLoad | #StoreStore\n"
+"	 nop\n"
 "2:\n"
 "	.subsection 2\n"
 "3:	mov	%0, %%g1\n"
@@ -233,8 +236,9 @@ int __sched down_interruptible(struct semaphore *sem)
 "	cmp	%%g1, %%g7\n"
 "	bne,pn	%%icc, 1b\n"
 "	 cmp	%%g7, 1\n"
+"	membar	#StoreLoad | #StoreStore\n"
 "	bl,pn	%%icc, 3f\n"
-"	 membar	#StoreLoad | #StoreStore\n"
+"	 nop\n"
 "2:\n"
 "	.subsection 2\n"
 "3:	mov	%2, %%g1\n"
diff --git a/arch/sparc64/kernel/sparc64_ksyms.c b/arch/sparc64/kernel/sparc64_ksyms.c
index e78cc53..56cd96f 100644
--- a/arch/sparc64/kernel/sparc64_ksyms.c
+++ b/arch/sparc64/kernel/sparc64_ksyms.c
@@ -227,7 +227,6 @@ EXPORT_SYMBOL(__flush_dcache_range);
 
 EXPORT_SYMBOL(mostek_lock);
 EXPORT_SYMBOL(mstk48t02_regs);
-EXPORT_SYMBOL(request_fast_irq);
 #ifdef CONFIG_SUN_AUXIO
 EXPORT_SYMBOL(auxio_set_led);
 EXPORT_SYMBOL(auxio_set_lte);
diff --git a/arch/sparc64/kernel/trampoline.S b/arch/sparc64/kernel/trampoline.S
index 2c8f934..3a145fc 100644
--- a/arch/sparc64/kernel/trampoline.S
+++ b/arch/sparc64/kernel/trampoline.S
@@ -98,8 +98,9 @@ startup_continue:
 
 	sethi		%hi(prom_entry_lock), %g2
 1:	ldstub		[%g2 + %lo(prom_entry_lock)], %g1
+	membar		#StoreLoad | #StoreStore
 	brnz,pn		%g1, 1b
-	 membar		#StoreLoad | #StoreStore
+	 nop
 
 	sethi		%hi(p1275buf), %g2
 	or		%g2, %lo(p1275buf), %g2
diff --git a/arch/sparc64/lib/U1memcpy.S b/arch/sparc64/lib/U1memcpy.S
index da9b520..bafd2fc 100644
--- a/arch/sparc64/lib/U1memcpy.S
+++ b/arch/sparc64/lib/U1memcpy.S
@@ -87,14 +87,17 @@
 #define LOOP_CHUNK3(src, dest, len, branch_dest)		\
 	MAIN_LOOP_CHUNK(src, dest, f32, f48, len, branch_dest)
 
+#define DO_SYNC			membar	#Sync;
 #define STORE_SYNC(dest, fsrc)				\
 	EX_ST(STORE_BLK(%fsrc, %dest));			\
-	add			%dest, 0x40, %dest;
+	add			%dest, 0x40, %dest;	\
+	DO_SYNC
 
 #define STORE_JUMP(dest, fsrc, target)			\
 	EX_ST(STORE_BLK(%fsrc, %dest));			\
 	add			%dest, 0x40, %dest;	\
-	ba,pt			%xcc, target;
+	ba,pt			%xcc, target;		\
+	 nop;
 
 #define FINISH_VISCHUNK(dest, f0, f1, left)	\
 	subcc			%left, 8, %left;\
@@ -239,17 +242,17 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f0, %f2, %f48
 1:	FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0)
-	STORE_JUMP(o0, f48, 40f) membar #Sync
+	STORE_JUMP(o0, f48, 40f)
 2:	FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16)
-	STORE_JUMP(o0, f48, 48f) membar #Sync
+	STORE_JUMP(o0, f48, 48f)
 3:	FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)
-	STORE_JUMP(o0, f48, 56f) membar #Sync
+	STORE_JUMP(o0, f48, 56f)
 
 1:	FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)
 	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
@@ -260,17 +263,17 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f2, %f4, %f48
 1:	FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2)
-	STORE_JUMP(o0, f48, 41f) membar #Sync
+	STORE_JUMP(o0, f48, 41f)
 2:	FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)
-	STORE_JUMP(o0, f48, 49f) membar #Sync
+	STORE_JUMP(o0, f48, 49f)
 3:	FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)
-	STORE_JUMP(o0, f48, 57f) membar #Sync
+	STORE_JUMP(o0, f48, 57f)
 
 1:	FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)
 	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
@@ -281,17 +284,17 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f4, %f6, %f48
 1:	FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)
-	STORE_JUMP(o0, f48, 42f) membar #Sync
+	STORE_JUMP(o0, f48, 42f)
 2:	FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)
-	STORE_JUMP(o0, f48, 50f) membar #Sync
+	STORE_JUMP(o0, f48, 50f)
 3:	FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)
-	STORE_JUMP(o0, f48, 58f) membar #Sync
+	STORE_JUMP(o0, f48, 58f)
 
 1:	FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)
 	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
@@ -302,17 +305,17 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f6, %f8, %f48
 1:	FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6)
-	STORE_JUMP(o0, f48, 43f) membar #Sync
+	STORE_JUMP(o0, f48, 43f)
 2:	FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)
-	STORE_JUMP(o0, f48, 51f) membar #Sync
+	STORE_JUMP(o0, f48, 51f)
 3:	FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)
-	STORE_JUMP(o0, f48, 59f) membar #Sync
+	STORE_JUMP(o0, f48, 59f)
 
 1:	FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)
 	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
@@ -323,17 +326,17 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f8, %f10, %f48
 1:	FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)
-	STORE_JUMP(o0, f48, 44f) membar #Sync
+	STORE_JUMP(o0, f48, 44f)
 2:	FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)
-	STORE_JUMP(o0, f48, 52f) membar #Sync
+	STORE_JUMP(o0, f48, 52f)
 3:	FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)
-	STORE_JUMP(o0, f48, 60f) membar #Sync
+	STORE_JUMP(o0, f48, 60f)
 
 1:	FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)
 	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
@@ -344,17 +347,17 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f10, %f12, %f48
 1:	FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)
-	STORE_JUMP(o0, f48, 45f) membar #Sync
+	STORE_JUMP(o0, f48, 45f)
 2:	FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)
-	STORE_JUMP(o0, f48, 53f) membar #Sync
+	STORE_JUMP(o0, f48, 53f)
 3:	FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)
-	STORE_JUMP(o0, f48, 61f) membar #Sync
+	STORE_JUMP(o0, f48, 61f)
 
 1:	FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)
 	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
@@ -365,17 +368,17 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f12, %f14, %f48
 1:	FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)
-	STORE_JUMP(o0, f48, 46f) membar #Sync
+	STORE_JUMP(o0, f48, 46f)
 2:	FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)
-	STORE_JUMP(o0, f48, 54f) membar #Sync
+	STORE_JUMP(o0, f48, 54f)
 3:	FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)
-	STORE_JUMP(o0, f48, 62f) membar #Sync
+	STORE_JUMP(o0, f48, 62f)
 
 1:	FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)
 	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
@@ -386,17 +389,17 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f14, %f16, %f48
 1:	FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)
-	STORE_JUMP(o0, f48, 47f) membar #Sync
+	STORE_JUMP(o0, f48, 47f)
 2:	FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)
-	STORE_JUMP(o0, f48, 55f) membar #Sync
+	STORE_JUMP(o0, f48, 55f)
 3:	FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)
-	STORE_SYNC(o0, f48) membar #Sync
+	STORE_SYNC(o0, f48)
 	FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
-	STORE_JUMP(o0, f48, 63f) membar #Sync
+	STORE_JUMP(o0, f48, 63f)
 
 40:	FINISH_VISCHUNK(o0, f0,  f2,  g3)
 41:	FINISH_VISCHUNK(o0, f2,  f4,  g3)
diff --git a/arch/sparc64/lib/VISsave.S b/arch/sparc64/lib/VISsave.S
index 65e328d..4e18989 100644
--- a/arch/sparc64/lib/VISsave.S
+++ b/arch/sparc64/lib/VISsave.S
@@ -72,7 +72,11 @@ vis1:	ldub		[%g6 + TI_FPSAVED], %g3
 
 	stda		%f48, [%g3 + %g1] ASI_BLK_P
 5:	membar		#Sync
-	jmpl		%g7 + %g0, %g0
+	ba,pt		%xcc, 80f
+	 nop
+
+	.align		32
+80:	jmpl		%g7 + %g0, %g0
 	 nop
 
 6:	ldub		[%g3 + TI_FPSAVED], %o5
@@ -87,8 +91,11 @@ vis1:	ldub		[%g6 + TI_FPSAVED], %g3
 	stda		%f32, [%g2 + %g1] ASI_BLK_P
 	stda		%f48, [%g3 + %g1] ASI_BLK_P
 	membar		#Sync
-	jmpl		%g7 + %g0, %g0
+	ba,pt		%xcc, 80f
+	 nop
 
+	.align		32
+80:	jmpl		%g7 + %g0, %g0
 	 nop
 
 	.align		32
@@ -126,6 +133,10 @@ VISenterhalf:
 	stda		%f0, [%g2 + %g1] ASI_BLK_P
 	stda		%f16, [%g3 + %g1] ASI_BLK_P
 	membar		#Sync
+	ba,pt		%xcc, 4f
+	 nop
+
+	.align		32
 4:	and		%o5, FPRS_DU, %o5
 	jmpl		%g7 + %g0, %g0
 	 wr		%o5, FPRS_FEF, %fprs
diff --git a/arch/sparc64/lib/atomic.S b/arch/sparc64/lib/atomic.S
index e528b8d..faf87c3 100644
--- a/arch/sparc64/lib/atomic.S
+++ b/arch/sparc64/lib/atomic.S
@@ -7,18 +7,6 @@
 #include <linux/config.h>
 #include <asm/asi.h>
 
-	/* On SMP we need to use memory barriers to ensure
-	 * correct memory operation ordering, nop these out
-	 * for uniprocessor.
-	 */
-#ifdef CONFIG_SMP
-#define ATOMIC_PRE_BARRIER	membar #StoreLoad | #LoadLoad
-#define ATOMIC_POST_BARRIER	membar #StoreLoad | #StoreStore
-#else
-#define ATOMIC_PRE_BARRIER	nop
-#define ATOMIC_POST_BARRIER	nop
-#endif
-
 	.text
 
 	/* Two versions of the atomic routines, one that
@@ -52,6 +40,24 @@ atomic_sub: /* %o0 = decrement, %o1 = atomic_ptr */
 	 nop
 	.size	atomic_sub, .-atomic_sub
 
+	/* On SMP we need to use memory barriers to ensure
+	 * correct memory operation ordering, nop these out
+	 * for uniprocessor.
+	 */
+#ifdef CONFIG_SMP
+
+#define ATOMIC_PRE_BARRIER	membar #StoreLoad | #LoadLoad;
+#define ATOMIC_POST_BARRIER	\
+	ba,pt %xcc, 80b;	\
+	membar #StoreLoad | #StoreStore
+
+80:	retl
+	 nop
+#else
+#define ATOMIC_PRE_BARRIER
+#define ATOMIC_POST_BARRIER
+#endif
+
 	.globl	atomic_add_ret
 	.type	atomic_add_ret,#function
 atomic_add_ret: /* %o0 = increment, %o1 = atomic_ptr */
@@ -62,9 +68,10 @@ atomic_add_ret: /* %o0 = increment, %o1 = atomic_ptr */
 	cmp	%g1, %g7
 	bne,pn	%icc, 1b
 	 add	%g7, %o0, %g7
+	sra	%g7, 0, %o0
 	ATOMIC_POST_BARRIER
 	retl
-	 sra	%g7, 0, %o0
+	 nop
 	.size	atomic_add_ret, .-atomic_add_ret
 
 	.globl	atomic_sub_ret
@@ -77,9 +84,10 @@ atomic_sub_ret: /* %o0 = decrement, %o1 = atomic_ptr */
 	cmp	%g1, %g7
 	bne,pn	%icc, 1b
 	 sub	%g7, %o0, %g7
+	sra	%g7, 0, %o0
 	ATOMIC_POST_BARRIER
 	retl
-	 sra	%g7, 0, %o0
+	 nop
 	.size	atomic_sub_ret, .-atomic_sub_ret
 
 	.globl	atomic64_add
@@ -118,9 +126,10 @@ atomic64_add_ret: /* %o0 = increment, %o1 = atomic_ptr */
 	cmp	%g1, %g7
 	bne,pn	%xcc, 1b
 	 add	%g7, %o0, %g7
+	mov	%g7, %o0
 	ATOMIC_POST_BARRIER
 	retl
-	 mov	%g7, %o0
+	 nop
 	.size	atomic64_add_ret, .-atomic64_add_ret
 
 	.globl	atomic64_sub_ret
@@ -133,7 +142,8 @@ atomic64_sub_ret: /* %o0 = decrement, %o1 = atomic_ptr */
 	cmp	%g1, %g7
 	bne,pn	%xcc, 1b
 	 sub	%g7, %o0, %g7
+	mov	%g7, %o0
 	ATOMIC_POST_BARRIER
 	retl
-	 mov	%g7, %o0
+	 nop
 	.size	atomic64_sub_ret, .-atomic64_sub_ret
diff --git a/arch/sparc64/lib/bitops.S b/arch/sparc64/lib/bitops.S
index 886dcd2..31afbfe 100644
--- a/arch/sparc64/lib/bitops.S
+++ b/arch/sparc64/lib/bitops.S
@@ -7,20 +7,26 @@
 #include <linux/config.h>
 #include <asm/asi.h>
 
+	.text
+
 	/* On SMP we need to use memory barriers to ensure
 	 * correct memory operation ordering, nop these out
 	 * for uniprocessor.
 	 */
+
 #ifdef CONFIG_SMP
 #define BITOP_PRE_BARRIER	membar #StoreLoad | #LoadLoad
-#define BITOP_POST_BARRIER	membar #StoreLoad | #StoreStore
+#define BITOP_POST_BARRIER	\
+	ba,pt	%xcc, 80b;	\
+	membar #StoreLoad | #StoreStore
+
+80:	retl
+	 nop
 #else
-#define BITOP_PRE_BARRIER	nop
-#define BITOP_POST_BARRIER	nop
+#define BITOP_PRE_BARRIER
+#define BITOP_POST_BARRIER
 #endif
 
-	.text
-
 	.globl	test_and_set_bit
 	.type	test_and_set_bit,#function
 test_and_set_bit:	/* %o0=nr, %o1=addr */
@@ -37,10 +43,11 @@ test_and_set_bit:	/* %o0=nr, %o1=addr */
 	cmp	%g7, %g1
 	bne,pn	%xcc, 1b
 	 and	%g7, %o2, %g2
-	BITOP_POST_BARRIER
 	clr	%o0
+	movrne	%g2, 1, %o0
+	BITOP_POST_BARRIER
 	retl
-	 movrne	%g2, 1, %o0
+	 nop
 	.size	test_and_set_bit, .-test_and_set_bit
 
 	.globl	test_and_clear_bit
@@ -59,10 +66,11 @@ test_and_clear_bit:	/* %o0=nr, %o1=addr */
 	cmp	%g7, %g1
 	bne,pn	%xcc, 1b
 	 and	%g7, %o2, %g2
-	BITOP_POST_BARRIER
 	clr	%o0
+	movrne	%g2, 1, %o0
+	BITOP_POST_BARRIER
 	retl
-	 movrne	%g2, 1, %o0
+	 nop
 	.size	test_and_clear_bit, .-test_and_clear_bit
 
 	.globl	test_and_change_bit
@@ -81,10 +89,11 @@ test_and_change_bit:	/* %o0=nr, %o1=addr */
 	cmp	%g7, %g1
 	bne,pn	%xcc, 1b
 	 and	%g7, %o2, %g2
-	BITOP_POST_BARRIER
 	clr	%o0
+	movrne	%g2, 1, %o0
+	BITOP_POST_BARRIER
 	retl
-	 movrne	%g2, 1, %o0
+	 nop
 	.size	test_and_change_bit, .-test_and_change_bit
 
 	.globl	set_bit
diff --git a/arch/sparc64/lib/debuglocks.c b/arch/sparc64/lib/debuglocks.c
index c421e0c..f03344c 100644
--- a/arch/sparc64/lib/debuglocks.c
+++ b/arch/sparc64/lib/debuglocks.c
@@ -252,8 +252,9 @@ wlock_again:
 "		andn	%%g1, %%g3, %%g7\n"
 "		casx	[%0], %%g1, %%g7\n"
 "		cmp	%%g1, %%g7\n"
+"		membar	#StoreLoad | #StoreStore\n"
 "		bne,pn	%%xcc, 1b\n"
-"		 membar	#StoreLoad | #StoreStore"
+"		 nop"
 		: /* no outputs */
 		: "r" (&(rw->lock))
 		: "g3", "g1", "g7", "cc", "memory");
@@ -351,8 +352,9 @@ int _do_write_trylock (rwlock_t *rw, char *str)
 "		andn	%%g1, %%g3, %%g7\n"
 "		casx	[%0], %%g1, %%g7\n"
 "		cmp	%%g1, %%g7\n"
+"		membar	#StoreLoad | #StoreStore\n"
 "		bne,pn	%%xcc, 1b\n"
-"		 membar	#StoreLoad | #StoreStore"
+"		 nop"
 		: /* no outputs */
 		: "r" (&(rw->lock))
 		: "g3", "g1", "g7", "cc", "memory");
diff --git a/arch/sparc64/lib/dec_and_lock.S b/arch/sparc64/lib/dec_and_lock.S
index 7e6fdae..8ee288d 100644
--- a/arch/sparc64/lib/dec_and_lock.S
+++ b/arch/sparc64/lib/dec_and_lock.S
@@ -48,8 +48,9 @@ start_to_zero:
 #endif
 to_zero:
 	ldstub	[%o1], %g3
+	membar	#StoreLoad | #StoreStore
 	brnz,pn	%g3, spin_on_lock
-	 membar	#StoreLoad | #StoreStore
+	 nop
 loop2:	cas	[%o0], %g2, %g7		/* ASSERT(g7 == 0) */
 	cmp	%g2, %g7
 
@@ -71,8 +72,9 @@ loop2:	cas	[%o0], %g2, %g7		/* ASSERT(g7 == 0) */
 	 nop
 spin_on_lock:
 	ldub	[%o1], %g3
+	membar	#LoadLoad
 	brnz,pt	%g3, spin_on_lock
-	 membar	#LoadLoad
+	 nop
 	ba,pt	%xcc, to_zero
 	 nop
 	nop
diff --git a/arch/sparc64/lib/rwsem.S b/arch/sparc64/lib/rwsem.S
index 174ff7b..75f0e6b 100644
--- a/arch/sparc64/lib/rwsem.S
+++ b/arch/sparc64/lib/rwsem.S
@@ -17,8 +17,9 @@ __down_read:
 	bne,pn		%icc, 1b
 	 add		%g7, 1, %g7
 	cmp		%g7, 0
+	membar		#StoreLoad | #StoreStore
 	bl,pn		%icc, 3f
-	 membar		#StoreLoad | #StoreStore
+	 nop
 2:
 	retl
 	 nop
@@ -57,8 +58,9 @@ __down_write:
 	cmp		%g3, %g7
 	bne,pn		%icc, 1b
 	 cmp		%g7, 0
+	membar		#StoreLoad | #StoreStore
 	bne,pn		%icc, 3f
-	 membar		#StoreLoad | #StoreStore
+	 nop
 2:	retl
 	 nop
 3:
@@ -97,8 +99,9 @@ __up_read:
 	cmp		%g1, %g7
 	bne,pn		%icc, 1b
 	 cmp		%g7, 0
+	membar		#StoreLoad | #StoreStore
 	bl,pn		%icc, 3f
-	 membar		#StoreLoad | #StoreStore
+	 nop
 2:	retl
 	 nop
 3:	sethi		%hi(RWSEM_ACTIVE_MASK), %g1
@@ -126,8 +129,9 @@ __up_write:
 	bne,pn		%icc, 1b
 	 sub		%g7, %g1, %g7
 	cmp		%g7, 0
+	membar		#StoreLoad | #StoreStore
 	bl,pn		%icc, 3f
-	 membar		#StoreLoad | #StoreStore
+	 nop
 2:
 	retl
 	 nop
@@ -151,8 +155,9 @@ __downgrade_write:
 	bne,pn		%icc, 1b
 	 sub		%g7, %g1, %g7
 	cmp		%g7, 0
+	membar		#StoreLoad | #StoreStore
 	bl,pn		%icc, 3f
-	 membar		#StoreLoad | #StoreStore
+	 nop
 2:
 	retl
 	 nop
diff --git a/arch/sparc64/mm/init.c b/arch/sparc64/mm/init.c
index 9c52220..8fc413c 100644
--- a/arch/sparc64/mm/init.c
+++ b/arch/sparc64/mm/init.c
@@ -136,8 +136,9 @@ static __inline__ void set_dcache_dirty(struct page *page, int this_cpu)
 			     "or	%%g1, %0, %%g1\n\t"
 			     "casx	[%2], %%g7, %%g1\n\t"
 			     "cmp	%%g7, %%g1\n\t"
+			     "membar	#StoreLoad | #StoreStore\n\t"
 			     "bne,pn	%%xcc, 1b\n\t"
-			     " membar	#StoreLoad | #StoreStore"
+			     " nop"
 			     : /* no outputs */
 			     : "r" (mask), "r" (non_cpu_bits), "r" (&page->flags)
 			     : "g1", "g7");
@@ -157,8 +158,9 @@ static __inline__ void clear_dcache_dirty_cpu(struct page *page, unsigned long c
 			     " andn	%%g7, %1, %%g1\n\t"
 			     "casx	[%2], %%g7, %%g1\n\t"
 			     "cmp	%%g7, %%g1\n\t"
+			     "membar	#StoreLoad | #StoreStore\n\t"
 			     "bne,pn	%%xcc, 1b\n\t"
-			     " membar	#StoreLoad | #StoreStore\n"
+			     " nop\n"
 			     "2:"
 			     : /* no outputs */
 			     : "r" (cpu), "r" (mask), "r" (&page->flags),
diff --git a/arch/sparc64/mm/ultra.S b/arch/sparc64/mm/ultra.S
index 7a09343..7a2431d 100644
--- a/arch/sparc64/mm/ultra.S
+++ b/arch/sparc64/mm/ultra.S
@@ -266,8 +266,9 @@ __cheetah_flush_tlb_pending:	/* 22 insns */
 	 andn		%o3, 1, %o3
 	stxa		%g0, [%o3] ASI_IMMU_DEMAP
 2:	stxa		%g0, [%o3] ASI_DMMU_DEMAP	
+	membar		#Sync
 	brnz,pt		%o1, 1b
-	 membar		#Sync
+	 nop
 	stxa		%g2, [%o4] ASI_DMMU
 	flush		%g6
 	wrpr		%g0, 0, %tl
diff --git a/arch/x86_64/kernel/kprobes.c b/arch/x86_64/kernel/kprobes.c
index 4e680f8..acd2a77 100644
--- a/arch/x86_64/kernel/kprobes.c
+++ b/arch/x86_64/kernel/kprobes.c
@@ -38,7 +38,7 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/preempt.h>
-#include <linux/moduleloader.h>
+
 #include <asm/cacheflush.h>
 #include <asm/pgtable.h>
 #include <asm/kdebug.h>
@@ -51,8 +51,6 @@ static struct kprobe *kprobe_prev;
 static unsigned long kprobe_status_prev, kprobe_old_rflags_prev, kprobe_saved_rflags_prev;
 static struct pt_regs jprobe_saved_regs;
 static long *jprobe_saved_rsp;
-static kprobe_opcode_t *get_insn_slot(void);
-static void free_insn_slot(kprobe_opcode_t *slot);
 void jprobe_return_end(void);
 
 /* copy of the kernel stack at the probe fire time */
@@ -274,48 +272,23 @@ static void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 		regs->rip = (unsigned long)p->ainsn.insn;
 }
 
-struct task_struct  *arch_get_kprobe_task(void *ptr)
-{
-	return ((struct thread_info *) (((unsigned long) ptr) &
-					(~(THREAD_SIZE -1))))->task;
-}
-
 void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
 {
 	unsigned long *sara = (unsigned long *)regs->rsp;
-	struct kretprobe_instance *ri;
-	static void *orig_ret_addr;
+        struct kretprobe_instance *ri;
+
+        if ((ri = get_free_rp_inst(rp)) != NULL) {
+                ri->rp = rp;
+                ri->task = current;
+		ri->ret_addr = (kprobe_opcode_t *) *sara;
 
-	/*
-	 * Save the return address when the return probe hits
-	 * the first time, and use it to populate the (krprobe
-	 * instance)->ret_addr for subsequent return probes at
-	 * the same addrress since stack address would have
-	 * the kretprobe_trampoline by then.
-	 */
-	if (((void*) *sara) != kretprobe_trampoline)
-		orig_ret_addr = (void*) *sara;
-
-	if ((ri = get_free_rp_inst(rp)) != NULL) {
-		ri->rp = rp;
-		ri->stack_addr = sara;
-		ri->ret_addr = orig_ret_addr;
-		add_rp_inst(ri);
 		/* Replace the return addr with trampoline addr */
 		*sara = (unsigned long) &kretprobe_trampoline;
-	} else {
-		rp->nmissed++;
-	}
-}
 
-void arch_kprobe_flush_task(struct task_struct *tk)
-{
-	struct kretprobe_instance *ri;
-	while ((ri = get_rp_inst_tsk(tk)) != NULL) {
-		*((unsigned long *)(ri->stack_addr)) =
-					(unsigned long) ri->ret_addr;
-		recycle_rp_inst(ri);
-	}
+                add_rp_inst(ri);
+        } else {
+                rp->nmissed++;
+        }
 }
 
 /*
@@ -428,36 +401,59 @@ no_kprobe:
  */
 int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 {
-	struct task_struct *tsk;
-	struct kretprobe_instance *ri;
-	struct hlist_head *head;
-	struct hlist_node *node;
-	unsigned long *sara = (unsigned long *)regs->rsp - 1;
-
-	tsk = arch_get_kprobe_task(sara);
-	head = kretprobe_inst_table_head(tsk);
-
-	hlist_for_each_entry(ri, node, head, hlist) {
-		if (ri->stack_addr == sara && ri->rp) {
-			if (ri->rp->handler)
-				ri->rp->handler(ri, regs);
-		}
-	}
-	return 0;
-}
+        struct kretprobe_instance *ri = NULL;
+        struct hlist_head *head;
+        struct hlist_node *node, *tmp;
+	unsigned long orig_ret_address = 0;
+	unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;
 
-void trampoline_post_handler(struct kprobe *p, struct pt_regs *regs,
-						unsigned long flags)
-{
-	struct kretprobe_instance *ri;
-	/* RA already popped */
-	unsigned long *sara = ((unsigned long *)regs->rsp) - 1;
+        head = kretprobe_inst_table_head(current);
 
-	while ((ri = get_rp_inst(sara))) {
-		regs->rip = (unsigned long)ri->ret_addr;
+	/*
+	 * It is possible to have multiple instances associated with a given
+	 * task either because an multiple functions in the call path
+	 * have a return probe installed on them, and/or more then one return
+	 * return probe was registered for a target function.
+	 *
+	 * We can handle this because:
+	 *     - instances are always inserted at the head of the list
+	 *     - when multiple return probes are registered for the same
+         *       function, the first instance's ret_addr will point to the
+	 *       real return address, and all the rest will point to
+	 *       kretprobe_trampoline
+	 */
+	hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+                if (ri->task != current)
+			/* another task is sharing our hash bucket */
+                        continue;
+
+		if (ri->rp && ri->rp->handler)
+			ri->rp->handler(ri, regs);
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
 		recycle_rp_inst(ri);
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
 	}
-	regs->eflags &= ~TF_MASK;
+
+	BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address));
+	regs->rip = orig_ret_address;
+
+	unlock_kprobes();
+	preempt_enable_no_resched();
+
+        /*
+         * By returning a non-zero value, we are telling
+         * kprobe_handler() that we have handled unlocking
+         * and re-enabling preemption.
+         */
+        return 1;
 }
 
 /*
@@ -550,8 +546,7 @@ int post_kprobe_handler(struct pt_regs *regs)
 		current_kprobe->post_handler(current_kprobe, regs, 0);
 	}
 
-	if (current_kprobe->post_handler != trampoline_post_handler)
-		resume_execution(current_kprobe, regs);
+	resume_execution(current_kprobe, regs);
 	regs->eflags |= kprobe_saved_rflags;
 
 	/* Restore the original saved kprobes variables and continue. */
@@ -682,111 +677,12 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	return 0;
 }
 
-/*
- * kprobe->ainsn.insn points to the copy of the instruction to be single-stepped.
- * By default on x86_64, pages we get from kmalloc or vmalloc are not
- * executable.  Single-stepping an instruction on such a page yields an
- * oops.  So instead of storing the instruction copies in their respective
- * kprobe objects, we allocate a page, map it executable, and store all the
- * instruction copies there.  (We can allocate additional pages if somebody
- * inserts a huge number of probes.)  Each page can hold up to INSNS_PER_PAGE
- * instruction slots, each of which is MAX_INSN_SIZE*sizeof(kprobe_opcode_t)
- * bytes.
- */
-#define INSNS_PER_PAGE (PAGE_SIZE/(MAX_INSN_SIZE*sizeof(kprobe_opcode_t)))
-struct kprobe_insn_page {
-	struct hlist_node hlist;
-	kprobe_opcode_t *insns;		/* page of instruction slots */
-	char slot_used[INSNS_PER_PAGE];
-	int nused;
+static struct kprobe trampoline_p = {
+	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
+	.pre_handler = trampoline_probe_handler
 };
 
-static struct hlist_head kprobe_insn_pages;
-
-/**
- * get_insn_slot() - Find a slot on an executable page for an instruction.
- * We allocate an executable page if there's no room on existing ones.
- */
-static kprobe_opcode_t *get_insn_slot(void)
-{
-	struct kprobe_insn_page *kip;
-	struct hlist_node *pos;
-
-	hlist_for_each(pos, &kprobe_insn_pages) {
-		kip = hlist_entry(pos, struct kprobe_insn_page, hlist);
-		if (kip->nused < INSNS_PER_PAGE) {
-			int i;
-			for (i = 0; i < INSNS_PER_PAGE; i++) {
-				if (!kip->slot_used[i]) {
-					kip->slot_used[i] = 1;
-					kip->nused++;
-					return kip->insns + (i*MAX_INSN_SIZE);
-				}
-			}
-			/* Surprise!  No unused slots.  Fix kip->nused. */
-			kip->nused = INSNS_PER_PAGE;
-		}
-	}
-
-	/* All out of space.  Need to allocate a new page. Use slot 0.*/
-	kip = kmalloc(sizeof(struct kprobe_insn_page), GFP_KERNEL);
-	if (!kip) {
-		return NULL;
-	}
-
-	/*
-	 * For the %rip-relative displacement fixups to be doable, we
-	 * need our instruction copy to be within +/- 2GB of any data it
-	 * might access via %rip.  That is, within 2GB of where the
-	 * kernel image and loaded module images reside.  So we allocate
-	 * a page in the module loading area.
-	 */
-	kip->insns = module_alloc(PAGE_SIZE);
-	if (!kip->insns) {
-		kfree(kip);
-		return NULL;
-	}
-	INIT_HLIST_NODE(&kip->hlist);
-	hlist_add_head(&kip->hlist, &kprobe_insn_pages);
-	memset(kip->slot_used, 0, INSNS_PER_PAGE);
-	kip->slot_used[0] = 1;
-	kip->nused = 1;
-	return kip->insns;
-}
-
-/**
- * free_insn_slot() - Free instruction slot obtained from get_insn_slot().
- */
-static void free_insn_slot(kprobe_opcode_t *slot)
+int __init arch_init(void)
 {
-	struct kprobe_insn_page *kip;
-	struct hlist_node *pos;
-
-	hlist_for_each(pos, &kprobe_insn_pages) {
-		kip = hlist_entry(pos, struct kprobe_insn_page, hlist);
-		if (kip->insns <= slot
-		    && slot < kip->insns+(INSNS_PER_PAGE*MAX_INSN_SIZE)) {
-			int i = (slot - kip->insns) / MAX_INSN_SIZE;
-			kip->slot_used[i] = 0;
-			kip->nused--;
-			if (kip->nused == 0) {
-				/*
-				 * Page is no longer in use.  Free it unless
-				 * it's the last one.  We keep the last one
-				 * so as not to have to set it up again the
-				 * next time somebody inserts a probe.
-				 */
-				hlist_del(&kip->hlist);
-				if (hlist_empty(&kprobe_insn_pages)) {
-					INIT_HLIST_NODE(&kip->hlist);
-					hlist_add_head(&kip->hlist,
-						&kprobe_insn_pages);
-				} else {
-					module_free(NULL, kip->insns);
-					kfree(kip);
-				}
-			}
-			return;
-		}
-	}
+	return register_kprobe(&trampoline_p);
 }
diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index 1d91271..7577f9d 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -482,6 +482,33 @@ out:
 }
 
 /*
+ * This function selects if the context switch from prev to next
+ * has to tweak the TSC disable bit in the cr4.
+ */
+static inline void disable_tsc(struct task_struct *prev_p,
+			       struct task_struct *next_p)
+{
+	struct thread_info *prev, *next;
+
+	/*
+	 * gcc should eliminate the ->thread_info dereference if
+	 * has_secure_computing returns 0 at compile time (SECCOMP=n).
+	 */
+	prev = prev_p->thread_info;
+	next = next_p->thread_info;
+
+	if (has_secure_computing(prev) || has_secure_computing(next)) {
+		/* slow path here */
+		if (has_secure_computing(prev) &&
+		    !has_secure_computing(next)) {
+			write_cr4(read_cr4() & ~X86_CR4_TSD);
+		} else if (!has_secure_computing(prev) &&
+			   has_secure_computing(next))
+			write_cr4(read_cr4() | X86_CR4_TSD);
+	}
+}
+
+/*
  * This special macro can be used to load a debugging register
  */
 #define loaddebug(thread,r) set_debug(thread->debugreg ## r, r)
@@ -599,6 +626,8 @@ struct task_struct *__switch_to(struct task_struct *prev_p, struct task_struct *
 		}
 	}
 
+	disable_tsc(prev_p, next_p);
+
 	return prev_p;
 }