Merge branch 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6

* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6: (27 commits)
  [IA64] kdump: Add crash_save_vmcoreinfo for INIT
  [IA64] Fix NUMA configuration issue
  [IA64] Itanium Spec updates
  [IA64] Untangle sync_icache_dcache() page size determination
  [IA64] arch/ia64/kernel/: use time_* macros
  [IA64] remove redundant display of free swap space in show_mem()
  [IA64] make IOMMU respect the segment boundary limits
  [IA64] kprobes: kprobe-booster for ia64
  [IA64] fix getpid and set_tid_address fast system calls for pid namespaces
  [IA64] Replace explicit jiffies tests with time_* macros.
  [IA64] use goto to jump out do/while_each_thread
  [IA64] Fix unlock ordering in smp_callin
  [IA64] pgd_offset() constfication.
  [IA64] kdump: crash.c coding style fix
  [IA64] kdump: add kdump_on_fatal_mca
  [IA64] Minimize per_cpu reservations.
  [IA64] Correct pernodesize calculation.
  [IA64] Kernel parameter for max number of concurrent global TLB purges
  [IA64] Multiple outstanding ptc.g instruction support
  [IA64] Implement smp_call_function_mask for ia64
  ...

23 files changed, 1595 insertions, 437 deletions

diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 78f28d825f3..c7467f863c7 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -423,6 +423,7 @@ static u32 __devinitdata pxm_flag[PXM_FLAG_LEN];
 #define pxm_bit_set(bit)	(set_bit(bit,(void *)pxm_flag))
 #define pxm_bit_test(bit)	(test_bit(bit,(void *)pxm_flag))
 static struct acpi_table_slit __initdata *slit_table;
+cpumask_t early_cpu_possible_map = CPU_MASK_NONE;
 
 static int get_processor_proximity_domain(struct acpi_srat_cpu_affinity *pa)
 {
@@ -482,6 +483,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 	    (pa->apic_id << 8) | (pa->local_sapic_eid);
 	/* nid should be overridden as logical node id later */
 	node_cpuid[srat_num_cpus].nid = pxm;
+	cpu_set(srat_num_cpus, early_cpu_possible_map);
 	srat_num_cpus++;
 }
 
@@ -559,7 +561,7 @@ void __init acpi_numa_arch_fixup(void)
 	}
 
 	/* set logical node id in cpu structure */
-	for (i = 0; i < srat_num_cpus; i++)
+	for_each_possible_early_cpu(i)
 		node_cpuid[i].nid = pxm_to_node(node_cpuid[i].nid);
 
 	printk(KERN_INFO "Number of logical nodes in system = %d\n",
diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c
index 0aebc6f79e9..230a6f92367 100644
--- a/arch/ia64/kernel/asm-offsets.c
+++ b/arch/ia64/kernel/asm-offsets.c
@@ -7,6 +7,7 @@
 #define ASM_OFFSETS_C 1
 
 #include <linux/sched.h>
+#include <linux/pid.h>
 #include <linux/clocksource.h>
 
 #include <asm-ia64/processor.h>
@@ -34,17 +35,29 @@ void foo(void)
 	DEFINE(SIGFRAME_SIZE, sizeof (struct sigframe));
 	DEFINE(UNW_FRAME_INFO_SIZE, sizeof (struct unw_frame_info));
 
+	BUILD_BUG_ON(sizeof(struct upid) != 32);
+	DEFINE(IA64_UPID_SHIFT, 5);
+
 	BLANK();
 
 	DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
 	DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
 	DEFINE(TI_PRE_COUNT, offsetof(struct thread_info, preempt_count));
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+	DEFINE(TI_AC_STAMP, offsetof(struct thread_info, ac_stamp));
+	DEFINE(TI_AC_LEAVE, offsetof(struct thread_info, ac_leave));
+	DEFINE(TI_AC_STIME, offsetof(struct thread_info, ac_stime));
+	DEFINE(TI_AC_UTIME, offsetof(struct thread_info, ac_utime));
+#endif
 
 	BLANK();
 
 	DEFINE(IA64_TASK_BLOCKED_OFFSET,offsetof (struct task_struct, blocked));
 	DEFINE(IA64_TASK_CLEAR_CHILD_TID_OFFSET,offsetof (struct task_struct, clear_child_tid));
 	DEFINE(IA64_TASK_GROUP_LEADER_OFFSET, offsetof (struct task_struct, group_leader));
+	DEFINE(IA64_TASK_TGIDLINK_OFFSET, offsetof (struct task_struct, pids[PIDTYPE_PID].pid));
+	DEFINE(IA64_PID_LEVEL_OFFSET, offsetof (struct pid, level));
+	DEFINE(IA64_PID_UPID_OFFSET, offsetof (struct pid, numbers[0]));
 	DEFINE(IA64_TASK_PENDING_OFFSET,offsetof (struct task_struct, pending));
 	DEFINE(IA64_TASK_PID_OFFSET, offsetof (struct task_struct, pid));
 	DEFINE(IA64_TASK_REAL_PARENT_OFFSET, offsetof (struct task_struct, real_parent));
diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c
index fbe742ad2fd..90ef338cf46 100644
--- a/arch/ia64/kernel/crash.c
+++ b/arch/ia64/kernel/crash.c
@@ -24,6 +24,7 @@ int kdump_status[NR_CPUS];
 static atomic_t kdump_cpu_frozen;
 atomic_t kdump_in_progress;
 static int kdump_on_init = 1;
+static int kdump_on_fatal_mca = 1;
 
 static inline Elf64_Word
 *append_elf_note(Elf64_Word *buf, char *name, unsigned type, void *data,
@@ -118,6 +119,7 @@ machine_crash_shutdown(struct pt_regs *pt)
 static void
 machine_kdump_on_init(void)
 {
+	crash_save_vmcoreinfo();
 	local_irq_disable();
 	kexec_disable_iosapic();
 	machine_kexec(ia64_kimage);
@@ -148,7 +150,7 @@ kdump_init_notifier(struct notifier_block *self, unsigned long val, void *data)
 	struct ia64_mca_notify_die *nd;
 	struct die_args *args = data;
 
-	if (!kdump_on_init)
+	if (!kdump_on_init && !kdump_on_fatal_mca)
 		return NOTIFY_DONE;
 
 	if (!ia64_kimage) {
@@ -173,32 +175,38 @@ kdump_init_notifier(struct notifier_block *self, unsigned long val, void *data)
 		return NOTIFY_DONE;
 
 	switch (val) {
-		case DIE_INIT_MONARCH_PROCESS:
+	case DIE_INIT_MONARCH_PROCESS:
+		if (kdump_on_init) {
 			atomic_set(&kdump_in_progress, 1);
 			*(nd->monarch_cpu) = -1;
-			break;
-		case DIE_INIT_MONARCH_LEAVE:
+		}
+		break;
+	case DIE_INIT_MONARCH_LEAVE:
+		if (kdump_on_init)
 			machine_kdump_on_init();
-			break;
-		case DIE_INIT_SLAVE_LEAVE:
-			if (atomic_read(&kdump_in_progress))
-				unw_init_running(kdump_cpu_freeze, NULL);
-			break;
-		case DIE_MCA_RENDZVOUS_LEAVE:
-			if (atomic_read(&kdump_in_progress))
-				unw_init_running(kdump_cpu_freeze, NULL);
-			break;
-		case DIE_MCA_MONARCH_LEAVE:
-		     /* die_register->signr indicate if MCA is recoverable */
-			if (!args->signr)
-				machine_kdump_on_init();
-			break;
+		break;
+	case DIE_INIT_SLAVE_LEAVE:
+		if (atomic_read(&kdump_in_progress))
+			unw_init_running(kdump_cpu_freeze, NULL);
+		break;
+	case DIE_MCA_RENDZVOUS_LEAVE:
+		if (atomic_read(&kdump_in_progress))
+			unw_init_running(kdump_cpu_freeze, NULL);
+		break;
+	case DIE_MCA_MONARCH_LEAVE:
+		/* die_register->signr indicate if MCA is recoverable */
+		if (kdump_on_fatal_mca && !args->signr) {
+			atomic_set(&kdump_in_progress, 1);
+			*(nd->monarch_cpu) = -1;
+			machine_kdump_on_init();
+		}
+		break;
 	}
 	return NOTIFY_DONE;
 }
 
 #ifdef CONFIG_SYSCTL
-static ctl_table kdump_on_init_table[] = {
+static ctl_table kdump_ctl_table[] = {
 	{
 		.ctl_name = CTL_UNNUMBERED,
 		.procname = "kdump_on_init",
@@ -207,6 +215,14 @@ static ctl_table kdump_on_init_table[] = {
 		.mode = 0644,
 		.proc_handler = &proc_dointvec,
 	},
+	{
+		.ctl_name = CTL_UNNUMBERED,
+		.procname = "kdump_on_fatal_mca",
+		.data = &kdump_on_fatal_mca,
+		.maxlen = sizeof(int),
+		.mode = 0644,
+		.proc_handler = &proc_dointvec,
+	},
 	{ .ctl_name = 0 }
 };
 
@@ -215,7 +231,7 @@ static ctl_table sys_table[] = {
 	  .ctl_name = CTL_KERN,
 	  .procname = "kernel",
 	  .mode = 0555,
-	  .child = kdump_on_init_table,
+	  .child = kdump_ctl_table,
 	},
 	{ .ctl_name = 0 }
 };
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index 728d7247a1a..d45f215bc8f 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -37,6 +37,7 @@
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/mca.h>
+#include <asm/tlbflush.h>
 
 #define EFI_DEBUG	0
 
@@ -403,6 +404,41 @@ efi_get_pal_addr (void)
 	return NULL;
 }
 
+
+static u8 __init palo_checksum(u8 *buffer, u32 length)
+{
+	u8 sum = 0;
+	u8 *end = buffer + length;
+
+	while (buffer < end)
+		sum = (u8) (sum + *(buffer++));
+
+	return sum;
+}
+
+/*
+ * Parse and handle PALO table which is published at:
+ * http://www.dig64.org/home/DIG64_PALO_R1_0.pdf
+ */
+static void __init handle_palo(unsigned long palo_phys)
+{
+	struct palo_table *palo = __va(palo_phys);
+	u8  checksum;
+
+	if (strncmp(palo->signature, PALO_SIG, sizeof(PALO_SIG) - 1)) {
+		printk(KERN_INFO "PALO signature incorrect.\n");
+		return;
+	}
+
+	checksum = palo_checksum((u8 *)palo, palo->length);
+	if (checksum) {
+		printk(KERN_INFO "PALO checksum incorrect.\n");
+		return;
+	}
+
+	setup_ptcg_sem(palo->max_tlb_purges, NPTCG_FROM_PALO);
+}
+
 void
 efi_map_pal_code (void)
 {
@@ -432,6 +468,7 @@ efi_init (void)
 	u64 efi_desc_size;
 	char *cp, vendor[100] = "unknown";
 	int i;
+	unsigned long palo_phys;
 
 	/*
 	 * It's too early to be able to use the standard kernel command line
@@ -496,6 +533,8 @@ efi_init (void)
 	efi.hcdp       = EFI_INVALID_TABLE_ADDR;
 	efi.uga        = EFI_INVALID_TABLE_ADDR;
 
+	palo_phys      = EFI_INVALID_TABLE_ADDR;
+
 	for (i = 0; i < (int) efi.systab->nr_tables; i++) {
 		if (efi_guidcmp(config_tables[i].guid, MPS_TABLE_GUID) == 0) {
 			efi.mps = config_tables[i].table;
@@ -515,10 +554,17 @@ efi_init (void)
 		} else if (efi_guidcmp(config_tables[i].guid, HCDP_TABLE_GUID) == 0) {
 			efi.hcdp = config_tables[i].table;
 			printk(" HCDP=0x%lx", config_tables[i].table);
+		} else if (efi_guidcmp(config_tables[i].guid,
+			 PROCESSOR_ABSTRACTION_LAYER_OVERWRITE_GUID) == 0) {
+			palo_phys = config_tables[i].table;
+			printk(" PALO=0x%lx", config_tables[i].table);
 		}
 	}
 	printk("\n");
 
+	if (palo_phys != EFI_INVALID_TABLE_ADDR)
+		handle_palo(palo_phys);
+
 	runtime = __va(efi.systab->runtime);
 	efi.get_time = phys_get_time;
 	efi.set_time = phys_set_time;
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index 3c331c464b4..b0be4a28017 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -710,6 +710,16 @@ ENTRY(ia64_leave_syscall)
 (pUStk)	cmp.eq.unc p6,p0=r0,r0		// p6 <- pUStk
 #endif
 .work_processed_syscall:
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+	adds r2=PT(LOADRS)+16,r12
+(pUStk)	mov.m r22=ar.itc			// fetch time at leave
+	adds r18=TI_FLAGS+IA64_TASK_SIZE,r13
+	;;
+(p6)	ld4 r31=[r18]				// load current_thread_info()->flags
+	ld8 r19=[r2],PT(B6)-PT(LOADRS)		// load ar.rsc value for "loadrs"
+	adds r3=PT(AR_BSPSTORE)+16,r12		// deferred
+	;;
+#else
 	adds r2=PT(LOADRS)+16,r12
 	adds r3=PT(AR_BSPSTORE)+16,r12
 	adds r18=TI_FLAGS+IA64_TASK_SIZE,r13
@@ -718,6 +728,7 @@ ENTRY(ia64_leave_syscall)
 	ld8 r19=[r2],PT(B6)-PT(LOADRS)		// load ar.rsc value for "loadrs"
 	nop.i 0
 	;;
+#endif
 	mov r16=ar.bsp				// M2  get existing backing store pointer
 	ld8 r18=[r2],PT(R9)-PT(B6)		// load b6
 (p6)	and r15=TIF_WORK_MASK,r31		// any work other than TIF_SYSCALL_TRACE?
@@ -737,12 +748,21 @@ ENTRY(ia64_leave_syscall)
 
 	ld8 r29=[r2],16		// M0|1 load cr.ipsr
 	ld8 r28=[r3],16		// M0|1 load cr.iip
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+(pUStk) add r14=TI_AC_LEAVE+IA64_TASK_SIZE,r13
+	;;
+	ld8 r30=[r2],16		// M0|1 load cr.ifs
+	ld8 r25=[r3],16		// M0|1 load ar.unat
+(pUStk) add r15=IA64_TASK_THREAD_ON_USTACK_OFFSET,r13
+	;;
+#else
 	mov r22=r0		// A    clear r22
 	;;
 	ld8 r30=[r2],16		// M0|1 load cr.ifs
 	ld8 r25=[r3],16		// M0|1 load ar.unat
 (pUStk) add r14=IA64_TASK_THREAD_ON_USTACK_OFFSET,r13
 	;;
+#endif
 	ld8 r26=[r2],PT(B0)-PT(AR_PFS)	// M0|1 load ar.pfs
 (pKStk)	mov r22=psr			// M2   read PSR now that interrupts are disabled
 	nop 0
@@ -759,7 +779,11 @@ ENTRY(ia64_leave_syscall)
 	ld8.fill r1=[r3],16			// M0|1 load r1
 (pUStk) mov r17=1				// A
 	;;
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+(pUStk) st1 [r15]=r17				// M2|3
+#else
 (pUStk) st1 [r14]=r17				// M2|3
+#endif
 	ld8.fill r13=[r3],16			// M0|1
 	mov f8=f0				// F    clear f8
 	;;
@@ -775,12 +799,22 @@ ENTRY(ia64_leave_syscall)
 	shr.u r18=r19,16		// I0|1 get byte size of existing "dirty" partition
 	cover				// B    add current frame into dirty partition & set cr.ifs
 	;;
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+	mov r19=ar.bsp			// M2   get new backing store pointer
+	st8 [r14]=r22			// M	save time at leave
+	mov f10=f0			// F    clear f10
+
+	mov r22=r0			// A	clear r22
+	movl r14=__kernel_syscall_via_epc // X
+	;;
+#else
 	mov r19=ar.bsp			// M2   get new backing store pointer
 	mov f10=f0			// F    clear f10
 
 	nop.m 0
 	movl r14=__kernel_syscall_via_epc // X
 	;;
+#endif
 	mov.m ar.csd=r0			// M2   clear ar.csd
 	mov.m ar.ccv=r0			// M2   clear ar.ccv
 	mov b7=r14			// I0   clear b7 (hint with __kernel_syscall_via_epc)
@@ -913,10 +947,18 @@ GLOBAL_ENTRY(ia64_leave_kernel)
 	adds r16=PT(CR_IPSR)+16,r12
 	adds r17=PT(CR_IIP)+16,r12
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+	.pred.rel.mutex pUStk,pKStk
+(pKStk)	mov r22=psr		// M2 read PSR now that interrupts are disabled
+(pUStk)	mov.m r22=ar.itc	// M  fetch time at leave
+	nop.i 0
+	;;
+#else
 (pKStk)	mov r22=psr		// M2 read PSR now that interrupts are disabled
 	nop.i 0
 	nop.i 0
 	;;
+#endif
 	ld8 r29=[r16],16	// load cr.ipsr
 	ld8 r28=[r17],16	// load cr.iip
 	;;
@@ -938,15 +980,37 @@ GLOBAL_ENTRY(ia64_leave_kernel)
 	;;
 	ld8.fill r12=[r16],16
 	ld8.fill r13=[r17],16
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+(pUStk)	adds r3=TI_AC_LEAVE+IA64_TASK_SIZE,r18
+#else
 (pUStk)	adds r18=IA64_TASK_THREAD_ON_USTACK_OFFSET,r18
+#endif
 	;;
 	ld8 r20=[r16],16	// ar.fpsr
 	ld8.fill r15=[r17],16
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+(pUStk)	adds r18=IA64_TASK_THREAD_ON_USTACK_OFFSET,r18	// deferred
+#endif
 	;;
 	ld8.fill r14=[r16],16
 	ld8.fill r2=[r17]
 (pUStk)	mov r17=1
 	;;
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+	//  mmi_ :  ld8 st1 shr;;         mmi_ : st8 st1 shr;;
+	//  mib  :  mov add br        ->  mib  : ld8 add br
+	//  bbb_ :  br  nop cover;;       mbb_ : mov br  cover;;
+	//
+	//  no one require bsp in r16 if (pKStk) branch is selected.
+(pUStk)	st8 [r3]=r22		// save time at leave
+(pUStk)	st1 [r18]=r17		// restore current->thread.on_ustack
+	shr.u r18=r19,16	// get byte size of existing "dirty" partition
+	;;
+	ld8.fill r3=[r16]	// deferred
+	LOAD_PHYS_STACK_REG_SIZE(r17)
+(pKStk)	br.cond.dpnt skip_rbs_switch
+	mov r16=ar.bsp		// get existing backing store pointer
+#else
 	ld8.fill r3=[r16]
 (pUStk)	st1 [r18]=r17		// restore current->thread.on_ustack
 	shr.u r18=r19,16	// get byte size of existing "dirty" partition
@@ -954,6 +1018,7 @@ GLOBAL_ENTRY(ia64_leave_kernel)
 	mov r16=ar.bsp		// get existing backing store pointer
 	LOAD_PHYS_STACK_REG_SIZE(r17)
 (pKStk)	br.cond.dpnt skip_rbs_switch
+#endif
 
 	/*
 	 * Restore user backing store.
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index 44841971f07..c1625c7e177 100644
--- a/arch/ia64/kernel/fsys.S
+++ b/arch/ia64/kernel/fsys.S
@@ -61,13 +61,29 @@ ENTRY(fsys_getpid)
 	.prologue
 	.altrp b6
 	.body
+	add r17=IA64_TASK_GROUP_LEADER_OFFSET,r16
+	;;
+	ld8 r17=[r17]				// r17 = current->group_leader
 	add r9=TI_FLAGS+IA64_TASK_SIZE,r16
 	;;
 	ld4 r9=[r9]
-	add r8=IA64_TASK_TGID_OFFSET,r16
+	add r17=IA64_TASK_TGIDLINK_OFFSET,r17
 	;;
 	and r9=TIF_ALLWORK_MASK,r9
-	ld4 r8=[r8]				// r8 = current->tgid
+	ld8 r17=[r17]				// r17 = current->group_leader->pids[PIDTYPE_PID].pid
+	;;
+	add r8=IA64_PID_LEVEL_OFFSET,r17
+	;;
+	ld4 r8=[r8]				// r8 = pid->level
+	add r17=IA64_PID_UPID_OFFSET,r17	// r17 = &pid->numbers[0]
+	;;
+	shl r8=r8,IA64_UPID_SHIFT
+	;;
+	add r17=r17,r8				// r17 = &pid->numbers[pid->level]
+	;;
+	ld4 r8=[r17]				// r8 = pid->numbers[pid->level].nr
+	;;
+	mov r17=0
 	;;
 	cmp.ne p8,p0=0,r9
 (p8)	br.spnt.many fsys_fallback_syscall
@@ -126,15 +142,25 @@ ENTRY(fsys_set_tid_address)
 	.altrp b6
 	.body
 	add r9=TI_FLAGS+IA64_TASK_SIZE,r16
+	add r17=IA64_TASK_TGIDLINK_OFFSET,r16
 	;;
 	ld4 r9=[r9]
 	tnat.z p6,p7=r32		// check argument register for being NaT
+	ld8 r17=[r17]				// r17 = current->pids[PIDTYPE_PID].pid
 	;;
 	and r9=TIF_ALLWORK_MASK,r9
-	add r8=IA64_TASK_PID_OFFSET,r16
+	add r8=IA64_PID_LEVEL_OFFSET,r17
 	add r18=IA64_TASK_CLEAR_CHILD_TID_OFFSET,r16
 	;;
-	ld4 r8=[r8]
+	ld4 r8=[r8]				// r8 = pid->level
+	add r17=IA64_PID_UPID_OFFSET,r17	// r17 = &pid->numbers[0]
+	;;
+	shl r8=r8,IA64_UPID_SHIFT
+	;;
+	add r17=r17,r8				// r17 = &pid->numbers[pid->level]
+	;;
+	ld4 r8=[r17]				// r8 = pid->numbers[pid->level].nr
+	;;
 	cmp.ne p8,p0=0,r9
 	mov r17=-1
 	;;
@@ -210,27 +236,25 @@ ENTRY(fsys_gettimeofday)
 	// Note that instructions are optimized for McKinley. McKinley can
 	// process two bundles simultaneously and therefore we continuously
 	// try to feed the CPU two bundles and then a stop.
-	//
-	// Additional note that code has changed a lot. Optimization is TBD.
-	// Comments begin with "?" are maybe outdated.
-	tnat.nz p6,p0 = r31	// ? branch deferred to fit later bundle
-	mov pr = r30,0xc000	// Set predicates according to function
+
 	add r2 = TI_FLAGS+IA64_TASK_SIZE,r16
+	tnat.nz p6,p0 = r31		// guard against Nat argument
+(p6)	br.cond.spnt.few .fail_einval
 	movl r20 = fsyscall_gtod_data // load fsyscall gettimeofday data address
 	;;
+	ld4 r2 = [r2]			// process work pending flags
 	movl r29 = itc_jitter_data	// itc_jitter
 	add r22 = IA64_GTOD_WALL_TIME_OFFSET,r20	// wall_time
-	ld4 r2 = [r2]		// process work pending flags
-	;;
-(p15)	add r22 = IA64_GTOD_MONO_TIME_OFFSET,r20	// monotonic_time
 	add r21 = IA64_CLKSRC_MMIO_OFFSET,r20
-	add r19 = IA64_ITC_LASTCYCLE_OFFSET,r29
+	mov pr = r30,0xc000	// Set predicates according to function
+	;;
 	and r2 = TIF_ALLWORK_MASK,r2
-(p6)    br.cond.spnt.few .fail_einval	// ? deferred branch
+	add r19 = IA64_ITC_LASTCYCLE_OFFSET,r29
+(p15)	add r22 = IA64_GTOD_MONO_TIME_OFFSET,r20	// monotonic_time
 	;;
-	add r26 = IA64_CLKSRC_CYCLE_LAST_OFFSET,r20 // clksrc_cycle_last
+	add r26 = IA64_CLKSRC_CYCLE_LAST_OFFSET,r20	// clksrc_cycle_last
 	cmp.ne p6, p0 = 0, r2	// Fallback if work is scheduled
-(p6)    br.cond.spnt.many fsys_fallback_syscall
+(p6)	br.cond.spnt.many fsys_fallback_syscall
 	;;
 	// Begin critical section
 .time_redo:
@@ -258,7 +282,6 @@ ENTRY(fsys_gettimeofday)
 (p8)	mov r2 = ar.itc		// CPU_TIMER. 36 clocks latency!!!
 (p9)	ld8 r2 = [r30]		// MMIO_TIMER. Could also have latency issues..
 (p13)	ld8 r25 = [r19]		// get itc_lastcycle value
-	;;		// ? could be removed by moving the last add upward
 	ld8 r9 = [r22],IA64_TIMESPEC_TV_NSEC_OFFSET	// tv_sec
 	;;
 	ld8 r8 = [r22],-IA64_TIMESPEC_TV_NSEC_OFFSET	// tv_nsec
@@ -285,13 +308,12 @@ ENTRY(fsys_gettimeofday)
 EX(.fail_efault, probe.w.fault r31, 3)
 	xmpy.l f8 = f8,f7	// nsec_per_cyc*(counter-last_counter)
 	;;
-	// ? simulate tbit.nz.or p7,p0 = r28,0
 	getf.sig r2 = f8
 	mf
 	;;
 	ld4 r10 = [r20]		// gtod_lock.sequence
 	shr.u r2 = r2,r23	// shift by factor
-	;;		// ? overloaded 3 bundles!
+	;;
 	add r8 = r8,r2		// Add xtime.nsecs
 	cmp4.ne p7,p0 = r28,r10
 (p7)	br.cond.dpnt.few .time_redo	// sequence number changed, redo
@@ -319,9 +341,9 @@ EX(.fail_efault, probe.w.fault r31, 3)
 EX(.fail_efault, probe.w.fault r23, 3)	// This also costs 5 cycles
 (p14)	xmpy.hu f8 = f8, f7		// xmpy has 5 cycles latency so use it
 	;;
-	mov r8 = r0
 (p14)	getf.sig r2 = f8
 	;;
+	mov r8 = r0
 (p14)	shr.u r21 = r2, 4
 	;;
 EX(.fail_efault, st8 [r31] = r9)
@@ -660,7 +682,11 @@ GLOBAL_ENTRY(fsys_bubble_down)
 	nop.i 0
 	;;
 	mov ar.rsc=0				// M2   set enforced lazy mode, pl 0, LE, loadrs=0
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+	mov.m r30=ar.itc			// M    get cycle for accounting
+#else
 	nop.m 0
+#endif
 	nop.i 0
 	;;
 	mov r23=ar.bspstore			// M2 (12 cyc) save ar.bspstore
@@ -682,6 +708,28 @@ GLOBAL_ENTRY(fsys_bubble_down)
 	cmp.ne pKStk,pUStk=r0,r0		// A    set pKStk <- 0, pUStk <- 1
 	br.call.sptk.many b7=ia64_syscall_setup	// B
 	;;
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+	// mov.m r30=ar.itc is called in advance
+	add r16=TI_AC_STAMP+IA64_TASK_SIZE,r2
+	add r17=TI_AC_LEAVE+IA64_TASK_SIZE,r2
+	;;
+	ld8 r18=[r16],TI_AC_STIME-TI_AC_STAMP	// time at last check in kernel
+	ld8 r19=[r17],TI_AC_UTIME-TI_AC_LEAVE	// time at leave kernel
+	;;
+	ld8 r20=[r16],TI_AC_STAMP-TI_AC_STIME	// cumulated stime
+	ld8 r21=[r17]				// cumulated utime
+	sub r22=r19,r18				// stime before leave kernel
+	;;
+	st8 [r16]=r30,TI_AC_STIME-TI_AC_STAMP	// update stamp
+	sub r18=r30,r19				// elapsed time in user mode
+	;;
+	add r20=r20,r22				// sum stime
+	add r21=r21,r18				// sum utime
+	;;
+	st8 [r16]=r20				// update stime
+	st8 [r17]=r21				// update utime
+	;;
+#endif
 	mov ar.rsc=0x3				// M2   set eager mode, pl 0, LE, loadrs=0
 	mov rp=r14				// I0   set the real return addr
 	and r3=_TIF_SYSCALL_TRACEAUDIT,r3	// A
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index d3a41d5f8d1..ddeab4e36fd 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -1002,6 +1002,26 @@ GLOBAL_ENTRY(sched_clock)
 	br.ret.sptk.many rp
 END(sched_clock)
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+GLOBAL_ENTRY(cycle_to_cputime)
+	alloc r16=ar.pfs,1,0,0,0
+	addl r8=THIS_CPU(cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
+	;;
+	ldf8 f8=[r8]
+	;;
+	setf.sig f9=r32
+	;;
+	xmpy.lu f10=f9,f8	// calculate low 64 bits of 128-bit product	(4 cyc)
+	xmpy.hu f11=f9,f8	// calculate high 64 bits of 128-bit product
+	;;
+	getf.sig r8=f10		//						(5 cyc)
+	getf.sig r9=f11
+	;;
+	shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT
+	br.ret.sptk.many rp
+END(cycle_to_cputime)
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
+
 GLOBAL_ENTRY(start_kernel_thread)
 	.prologue
 	.save rp, r0				// this is the end of the call-chain
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index d8be23fbe6b..5538471e8d6 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -472,7 +472,7 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs)
 			static unsigned char count;
 			static long last_time;
 
-			if (jiffies - last_time > 5*HZ)
+			if (time_after(jiffies, last_time + 5 * HZ))
 				count = 0;
 			if (++count < 5) {
 				last_time = jiffies;
diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S
index 34f44d8be00..6678c49daba 100644
--- a/arch/ia64/kernel/ivt.S
+++ b/arch/ia64/kernel/ivt.S
@@ -805,8 +805,13 @@ ENTRY(break_fault)
 
 (p8)	adds r28=16,r28				// A    switch cr.iip to next bundle
 (p9)	adds r8=1,r8				// A    increment ei to next slot
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+	;;
+	mov b6=r30				// I0   setup syscall handler branch reg early
+#else
 	nop.i 0
 	;;
+#endif
 
 	mov.m r25=ar.unat			// M2 (5 cyc)
 	dep r29=r8,r29,41,2			// I0   insert new ei into cr.ipsr
@@ -817,7 +822,11 @@ ENTRY(break_fault)
 	//
 ///////////////////////////////////////////////////////////////////////
 	st1 [r16]=r0				// M2|3 clear current->thread.on_ustack flag
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+	mov.m r30=ar.itc			// M    get cycle for accounting
+#else
 	mov b6=r30				// I0   setup syscall handler branch reg early
+#endif
 	cmp.eq pKStk,pUStk=r0,r17		// A    were we on kernel stacks already?
 
 	and r9=_TIF_SYSCALL_TRACEAUDIT,r9	// A    mask trace or audit
@@ -829,6 +838,30 @@ ENTRY(break_fault)
 	cmp.eq p14,p0=r9,r0			// A    are syscalls being traced/audited?
 	br.call.sptk.many b7=ia64_syscall_setup	// B
 1:
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+	// mov.m r30=ar.itc is called in advance, and r13 is current
+	add r16=TI_AC_STAMP+IA64_TASK_SIZE,r13	// A
+	add r17=TI_AC_LEAVE+IA64_TASK_SIZE,r13	// A
+(pKStk)	br.cond.spnt .skip_accounting		// B	unlikely skip
+	;;
+	ld8 r18=[r16],TI_AC_STIME-TI_AC_STAMP	// M  get last stamp
+	ld8 r19=[r17],TI_AC_UTIME-TI_AC_LEAVE	// M  time at leave
+	;;
+	ld8 r20=[r16],TI_AC_STAMP-TI_AC_STIME	// M  cumulated stime
+	ld8 r21=[r17]				// M  cumulated utime
+	sub r22=r19,r18				// A  stime before leave
+	;;
+	st8 [r16]=r30,TI_AC_STIME-TI_AC_STAMP	// M  update stamp
+	sub r18=r30,r19				// A  elapsed time in user
+	;;
+	add r20=r20,r22				// A  sum stime
+	add r21=r21,r18				// A  sum utime
+	;;
+	st8 [r16]=r20				// M  update stime
+	st8 [r17]=r21				// M  update utime
+	;;
+.skip_accounting:
+#endif
 	mov ar.rsc=0x3				// M2   set eager mode, pl 0, LE, loadrs=0
 	nop 0
 	bsw.1					// B (6 cyc) regs are saved, switch to bank 1
@@ -928,6 +961,7 @@ END(interrupt)
 	 *	- r27: saved ar.rsc
 	 *	- r28: saved cr.iip
 	 *	- r29: saved cr.ipsr
+	 *	- r30: ar.itc for accounting (don't touch)
 	 *	- r31: saved pr
 	 *	-  b0: original contents (to be saved)
 	 * On exit:
@@ -1090,6 +1124,41 @@ END(dispatch_illegal_op_fault)
 	DBG_FAULT(16)
 	FAULT(16)
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+	/*
+	 * There is no particular reason for this code to be here, other than
+	 * that there happens to be space here that would go unused otherwise.
+	 * If this fault ever gets "unreserved", simply moved the following
+	 * code to a more suitable spot...
+	 *
+	 * account_sys_enter is called from SAVE_MIN* macros if accounting is
+	 * enabled and if the macro is entered from user mode.
+	 */
+ENTRY(account_sys_enter)
+	// mov.m r20=ar.itc is called in advance, and r13 is current
+	add r16=TI_AC_STAMP+IA64_TASK_SIZE,r13
+	add r17=TI_AC_LEAVE+IA64_TASK_SIZE,r13
+	;;
+	ld8 r18=[r16],TI_AC_STIME-TI_AC_STAMP	// time at last check in kernel
+	ld8 r19=[r17],TI_AC_UTIME-TI_AC_LEAVE	// time at left from kernel
+        ;;
+	ld8 r23=[r16],TI_AC_STAMP-TI_AC_STIME	// cumulated stime
+	ld8 r21=[r17]				// cumulated utime
+	sub r22=r19,r18				// stime before leave kernel
+	;;
+	st8 [r16]=r20,TI_AC_STIME-TI_AC_STAMP	// update stamp
+	sub r18=r20,r19				// elapsed time in user mode
+	;;
+	add r23=r23,r22				// sum stime
+	add r21=r21,r18				// sum utime
+	;;
+	st8 [r16]=r23				// update stime
+	st8 [r17]=r21				// update utime
+	;;
+	br.ret.sptk.many rp
+END(account_sys_enter)
+#endif
+
 	.org ia64_ivt+0x4400
 /////////////////////////////////////////////////////////////////////////////////////////
 // 0x4400 Entry 17 (size 64 bundles) Reserved
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index 8d9a446a0d1..233434f4f88 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -78,6 +78,20 @@ static enum instruction_type bundle_encoding[32][3] = {
   { u, u, u },  			/* 1F */
 };
 
+/* Insert a long branch code */
+static void __kprobes set_brl_inst(void *from, void *to)
+{
+	s64 rel = ((s64) to - (s64) from) >> 4;
+	bundle_t *brl;
+	brl = (bundle_t *) ((u64) from & ~0xf);
+	brl->quad0.template = 0x05;	/* [MLX](stop) */
+	brl->quad0.slot0 = NOP_M_INST;	/* nop.m 0x0 */
+	brl->quad0.slot1_p0 = ((rel >> 20) & 0x7fffffffff) << 2;
+	brl->quad1.slot1_p1 = (((rel >> 20) & 0x7fffffffff) << 2) >> (64 - 46);
+	/* brl.cond.sptk.many.clr rel<<4 (qp=0) */
+	brl->quad1.slot2 = BRL_INST(rel >> 59, rel & 0xfffff);
+}
+
 /*
  * In this function we check to see if the instruction
  * is IP relative instruction and update the kprobe
@@ -496,6 +510,77 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 	regs->b0 = ((struct fnptr *)kretprobe_trampoline)->ip;
 }
 
+/* Check the instruction in the slot is break */
+static int __kprobes __is_ia64_break_inst(bundle_t *bundle, uint slot)
+{
+	unsigned int major_opcode;
+	unsigned int template = bundle->quad0.template;
+	unsigned long kprobe_inst;
+
+	/* Move to slot 2, if bundle is MLX type and kprobe slot is 1 */
+	if (slot == 1 && bundle_encoding[template][1] == L)
+		slot++;
+
+	/* Get Kprobe probe instruction at given slot*/
+	get_kprobe_inst(bundle, slot, &kprobe_inst, &major_opcode);
+
+	/* For break instruction,
+	 * Bits 37:40 Major opcode to be zero
+	 * Bits 27:32 X6 to be zero
+	 * Bits 32:35 X3 to be zero
+	 */
+	if (major_opcode || ((kprobe_inst >> 27) & 0x1FF)) {
+		/* Not a break instruction */
+		return 0;
+	}
+
+	/* Is a break instruction */
+	return 1;
+}
+
+/*
+ * In this function, we check whether the target bundle modifies IP or
+ * it triggers an exception. If so, it cannot be boostable.
+ */
+static int __kprobes can_boost(bundle_t *bundle, uint slot,
+			       unsigned long bundle_addr)
+{
+	unsigned int template = bundle->quad0.template;
+
+	do {
+		if (search_exception_tables(bundle_addr + slot) ||
+		    __is_ia64_break_inst(bundle, slot))
+			return 0;	/* exception may occur in this bundle*/
+	} while ((++slot) < 3);
+	template &= 0x1e;
+	if (template >= 0x10 /* including B unit */ ||
+	    template == 0x04 /* including X unit */ ||
+	    template == 0x06) /* undefined */
+		return 0;
+
+	return 1;
+}
+
+/* Prepare long jump bundle and disables other boosters if need */
+static void __kprobes prepare_booster(struct kprobe *p)
+{
+	unsigned long addr = (unsigned long)p->addr & ~0xFULL;
+	unsigned int slot = (unsigned long)p->addr & 0xf;
+	struct kprobe *other_kp;
+
+	if (can_boost(&p->ainsn.insn[0].bundle, slot, addr)) {
+		set_brl_inst(&p->ainsn.insn[1].bundle, (bundle_t *)addr + 1);
+		p->ainsn.inst_flag |= INST_FLAG_BOOSTABLE;
+	}
+
+	/* disables boosters in previous slots */
+	for (; addr < (unsigned long)p->addr; addr++) {
+		other_kp = get_kprobe((void *)addr)