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:
  [IA64] Prevent people from directly including <asm/rwsem.h>.
  [IA64] remove time interpolator
  [IA64] Convert to generic timekeeping/clocksource
  [IA64] refresh some config files for 64K pagesize
  [IA64] Delete iosapic_free_rte()
  [IA64] fallocate system call
  [IA64] Enable percpu vector domain for IA64_DIG
  [IA64] Enable percpu vector domain for IA64_GENERIC
  [IA64] Support irq migration across domain
  [IA64] Add support for vector domain
  [IA64] Add mapping table between irq and vector
  [IA64] Check if irq is sharable
  [IA64] Fix invalid irq vector assumption for iosapic
  [IA64] Use dynamic irq for iosapic interrupts
  [IA64] Use per iosapic lock for indirect iosapic register access
  [IA64] Cleanup lock order in iosapic_register_intr
  [IA64] Remove duplicated members in iosapic_rte_info
  [IA64] Remove block structure for locking in iosapic.c

Documentation/kernel-parameters.txt

@@ -1154,6 +1154,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	nointroute	[IA-64]
 
+	nojitter	[IA64] Disables jitter checking for ITC timers.
+
 	nolapic		[IA-32,APIC] Do not enable or use the local APIC.
 
 	nolapic_timer	[IA-32,APIC] Do not use the local APIC timer.
@@ -1885,6 +1887,9 @@ and is between 256 and 4096 characters. It is defined in the file
 			vdso=1: enable VDSO (default)
 			vdso=0: disable VDSO mapping
 
+	vector=		[IA-64,SMP]
+			vector=percpu: enable percpu vector domain
+
 	video=		[FB] Frame buffer configuration
 			See Documentation/fb/modedb.txt.
 

Documentation/time_interpolators.txt

-Time Interpolators
-------------------
-
-Time interpolators are a base of time calculation between timer ticks and
-allow an accurate determination of time down to the accuracy of the time
-source in nanoseconds.
-
-The architecture specific code typically provides gettimeofday and
-settimeofday under Linux. The time interpolator provides both if an arch
-defines CONFIG_TIME_INTERPOLATION. The arch still must set up timer tick
-operations and call the necessary functions to advance the clock.
-
-With the time interpolator a standardized interface exists for time
-interpolation between ticks. The provided logic is highly scalable
-and has been tested in SMP situations of up to 512 CPUs.
-
-If CONFIG_TIME_INTERPOLATION is defined then the architecture specific code
-(or the device drivers - like HPET) may register time interpolators.
-These are typically defined in the following way:
-
-static struct time_interpolator my_interpolator {
-	.frequency = MY_FREQUENCY,
-	.source = TIME_SOURCE_MMIO32,
-	.shift = 8,		/* scaling for higher accuracy */
-	.drift = -1,		/* Unknown drift */
-	.jitter = 0		/* time source is stable */
-};
-
-void time_init(void)
-{
-	....
-	/* Initialization of the timer *.
-	my_interpolator.address = &my_timer;
-	register_time_interpolator(&my_interpolator);
-	....
-}
-
-For more details see include/linux/timex.h and kernel/timer.c.
-
-Christoph Lameter <christoph@lameter.com>, October 31, 2004
-

arch/ia64/Kconfig

@@ -62,7 +62,11 @@ config GENERIC_CALIBRATE_DELAY
 	bool
 	default y
 
-config TIME_INTERPOLATION
+config GENERIC_TIME
+	bool
+	default y
+
+config GENERIC_TIME_VSYSCALL
 	bool
 	default y
 

arch/ia64/configs/bigsur_defconfig

@@ -85,7 +85,7 @@ CONFIG_MMU=y
 CONFIG_SWIOTLB=y
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_TIME_INTERPOLATION=y
+CONFIG_GENERIC_TIME=y
 CONFIG_EFI=y
 CONFIG_GENERIC_IOMAP=y
 CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y

arch/ia64/configs/gensparse_defconfig

@@ -86,7 +86,7 @@ CONFIG_MMU=y
 CONFIG_SWIOTLB=y
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_TIME_INTERPOLATION=y
+CONFIG_GENERIC_TIME=y
 CONFIG_EFI=y
 CONFIG_GENERIC_IOMAP=y
 CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y

arch/ia64/configs/sim_defconfig

@@ -86,7 +86,7 @@ CONFIG_MMU=y
 CONFIG_SWIOTLB=y
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_TIME_INTERPOLATION=y
+CONFIG_GENERIC_TIME=y
 CONFIG_EFI=y
 CONFIG_GENERIC_IOMAP=y
 CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y

arch/ia64/configs/sn2_defconfig

@@ -93,7 +93,7 @@ CONFIG_SWIOTLB=y
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 CONFIG_GENERIC_FIND_NEXT_BIT=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_TIME_INTERPOLATION=y
+CONFIG_GENERIC_TIME=y
 CONFIG_DMI=y
 CONFIG_EFI=y
 CONFIG_GENERIC_IOMAP=y

arch/ia64/configs/zx1_defconfig

@@ -96,7 +96,7 @@ CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 # CONFIG_ARCH_HAS_ILOG2_U64 is not set
 CONFIG_GENERIC_FIND_NEXT_BIT=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_TIME_INTERPOLATION=y
+CONFIG_GENERIC_TIME=y
 CONFIG_DMI=y
 CONFIG_EFI=y
 CONFIG_GENERIC_IOMAP=y

arch/ia64/kernel/asm-offsets.c

@@ -7,6 +7,7 @@
 #define ASM_OFFSETS_C 1
 
 #include <linux/sched.h>
+#include <linux/clocksource.h>
 
 #include <asm-ia64/processor.h>
 #include <asm-ia64/ptrace.h>
@@ -15,6 +16,7 @@
 #include <asm-ia64/mca.h>
 
 #include "../kernel/sigframe.h"
+#include "../kernel/fsyscall_gtod_data.h"
 
 #define DEFINE(sym, val) \
         asm volatile("\n->" #sym " %0 " #val : : "i" (val))
@@ -256,17 +258,24 @@ void foo(void)
 	BLANK();
 
 	/* used by fsys_gettimeofday in arch/ia64/kernel/fsys.S */
-	DEFINE(IA64_TIME_INTERPOLATOR_ADDRESS_OFFSET, offsetof (struct time_interpolator, addr));
-	DEFINE(IA64_TIME_INTERPOLATOR_SOURCE_OFFSET, offsetof (struct time_interpolator, source));
-	DEFINE(IA64_TIME_INTERPOLATOR_SHIFT_OFFSET, offsetof (struct time_interpolator, shift));
-	DEFINE(IA64_TIME_INTERPOLATOR_NSEC_OFFSET, offsetof (struct time_interpolator, nsec_per_cyc));
-	DEFINE(IA64_TIME_INTERPOLATOR_OFFSET_OFFSET, offsetof (struct time_interpolator, offset));
-	DEFINE(IA64_TIME_INTERPOLATOR_LAST_CYCLE_OFFSET, offsetof (struct time_interpolator, last_cycle));
-	DEFINE(IA64_TIME_INTERPOLATOR_LAST_COUNTER_OFFSET, offsetof (struct time_interpolator, last_counter));
-	DEFINE(IA64_TIME_INTERPOLATOR_JITTER_OFFSET, offsetof (struct time_interpolator, jitter));
-	DEFINE(IA64_TIME_INTERPOLATOR_MASK_OFFSET, offsetof (struct time_interpolator, mask));
-	DEFINE(IA64_TIME_SOURCE_CPU, TIME_SOURCE_CPU);
-	DEFINE(IA64_TIME_SOURCE_MMIO64, TIME_SOURCE_MMIO64);
-	DEFINE(IA64_TIME_SOURCE_MMIO32, TIME_SOURCE_MMIO32);
-	DEFINE(IA64_TIMESPEC_TV_NSEC_OFFSET, offsetof (struct timespec, tv_nsec));
+	DEFINE(IA64_GTOD_LOCK_OFFSET,
+		offsetof (struct fsyscall_gtod_data_t, lock));
+	DEFINE(IA64_GTOD_WALL_TIME_OFFSET,
+		offsetof (struct fsyscall_gtod_data_t, wall_time));
+	DEFINE(IA64_GTOD_MONO_TIME_OFFSET,
+		offsetof (struct fsyscall_gtod_data_t, monotonic_time));
+	DEFINE(IA64_CLKSRC_MASK_OFFSET,
+		offsetof (struct fsyscall_gtod_data_t, clk_mask));
+	DEFINE(IA64_CLKSRC_MULT_OFFSET,
+		offsetof (struct fsyscall_gtod_data_t, clk_mult));
+	DEFINE(IA64_CLKSRC_SHIFT_OFFSET,
+		offsetof (struct fsyscall_gtod_data_t, clk_shift));
+	DEFINE(IA64_CLKSRC_MMIO_OFFSET,
+		offsetof (struct fsyscall_gtod_data_t, clk_fsys_mmio));
+	DEFINE(IA64_CLKSRC_CYCLE_LAST_OFFSET,
+		offsetof (struct fsyscall_gtod_data_t, clk_cycle_last));
+	DEFINE(IA64_ITC_JITTER_OFFSET,
+		offsetof (struct itc_jitter_data_t, itc_jitter));
+	DEFINE(IA64_ITC_LASTCYCLE_OFFSET,
+		offsetof (struct itc_jitter_data_t, itc_lastcycle));
 }

arch/ia64/kernel/cyclone.c

@@ -3,6 +3,7 @@
 #include <linux/time.h>
 #include <linux/errno.h>
 #include <linux/timex.h>
+#include <linux/clocksource.h>
 #include <asm/io.h>
 
 /* IBM Summit (EXA) Cyclone counter code*/
@@ -18,13 +19,21 @@ void __init cyclone_setup(void)
 	use_cyclone = 1;
 }
 
+static void __iomem *cyclone_mc;
 
-struct time_interpolator cyclone_interpolator = {
-	.source =	TIME_SOURCE_MMIO64,
-	.shift =	16,
-	.frequency =	CYCLONE_TIMER_FREQ,
-	.drift =	-100,
-	.mask =		(1LL << 40) - 1
+static cycle_t read_cyclone(void)
+{
+	return (cycle_t)readq((void __iomem *)cyclone_mc);
+}
+
+static struct clocksource clocksource_cyclone = {
+        .name           = "cyclone",
+        .rating         = 300,
+        .read           = read_cyclone,
+        .mask           = (1LL << 40) - 1,
+        .mult           = 0, /*to be caluclated*/
+        .shift          = 16,
+        .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 int __init init_cyclone_clock(void)
@@ -44,13 +53,15 @@ int __init init_cyclone_clock(void)
 	offset = (CYCLONE_CBAR_ADDR);
 	reg = (u64*)ioremap_nocache(offset, sizeof(u64));
 	if(!reg){
-		printk(KERN_ERR "Summit chipset: Could not find valid CBAR register.\n");
+		printk(KERN_ERR "Summit chipset: Could not find valid CBAR"
+				" register.\n");
 		use_cyclone = 0;
 		return -ENODEV;
 	}
 	base = readq(reg);
 	if(!base){
-		printk(KERN_ERR "Summit chipset: Could not find valid CBAR value.\n");
+		printk(KERN_ERR "Summit chipset: Could not find valid CBAR"
+				" value.\n");
 		use_cyclone = 0;
 		return -ENODEV;
 	}
@@ -60,7 +71,8 @@ int __init init_cyclone_clock(void)
 	offset = (base + CYCLONE_PMCC_OFFSET);
 	reg = (u64*)ioremap_nocache(offset, sizeof(u64));
 	if(!reg){
-		printk(KERN_ERR "Summit chipset: Could not find valid PMCC register.\n");
+		printk(KERN_ERR "Summit chipset: Could not find valid PMCC"
+				" register.\n");
 		use_cyclone = 0;
 		return -ENODEV;
 	}
@@ -71,7 +83,8 @@ int __init init_cyclone_clock(void)
 	offset = (base + CYCLONE_MPCS_OFFSET);
 	reg = (u64*)ioremap_nocache(offset, sizeof(u64));
 	if(!reg){
-		printk(KERN_ERR "Summit chipset: Could not find valid MPCS register.\n");
+		printk(KERN_ERR "Summit chipset: Could not find valid MPCS"
+				" register.\n");
 		use_cyclone = 0;
 		return -ENODEV;
 	}
@@ -82,7 +95,8 @@ int __init init_cyclone_clock(void)
 	offset = (base + CYCLONE_MPMC_OFFSET);
 	cyclone_timer = (u32*)ioremap_nocache(offset, sizeof(u32));
 	if(!cyclone_timer){
-		printk(KERN_ERR "Summit chipset: Could not find valid MPMC register.\n");
+		printk(KERN_ERR "Summit chipset: Could not find valid MPMC"
+				" register.\n");
 		use_cyclone = 0;
 		return -ENODEV;
 	}
@@ -93,7 +107,8 @@ int __init init_cyclone_clock(void)
 		int stall = 100;
 		while(stall--) barrier();
 		if(readl(cyclone_timer) == old){
-			printk(KERN_ERR "Summit chipset: Counter not counting! DISABLED\n");
+			printk(KERN_ERR "Summit chipset: Counter not counting!"
+					" DISABLED\n");
 			iounmap(cyclone_timer);
 			cyclone_timer = 0;
 			use_cyclone = 0;
@@ -101,8 +116,11 @@ int __init init_cyclone_clock(void)
 		}
 	}
 	/* initialize last tick */
-	cyclone_interpolator.addr = cyclone_timer;
-	register_time_interpolator(&cyclone_interpolator);
+	cyclone_mc = cyclone_timer;
+	clocksource_cyclone.fsys_mmio = cyclone_timer;
+	clocksource_cyclone.mult = clocksource_hz2mult(CYCLONE_TIMER_FREQ,
+						clocksource_cyclone.shift);
+	clocksource_register(&clocksource_cyclone);
 
 	return 0;
 }

arch/ia64/kernel/entry.S

@@ -1581,7 +1581,7 @@ sys_call_table:
 	data8 sys_sync_file_range		// 1300
 	data8 sys_tee
 	data8 sys_vmsplice
-	data8 sys_ni_syscall			// reserved for move_pages
+	data8 sys_fallocate
 	data8 sys_getcpu
 	data8 sys_epoll_pwait			// 1305
 	data8 sys_utimensat

arch/ia64/kernel/fsyscall_gtod_data.h

+/*
+ * (c) Copyright 2007 Hewlett-Packard Development Company, L.P.
+ *        Contributed by Peter Keilty <peter.keilty@hp.com>
+ *
+ * fsyscall gettimeofday data
+ */
+
+struct fsyscall_gtod_data_t {
+	seqlock_t	lock;
+	struct timespec	wall_time;
+	struct timespec monotonic_time;
+	cycle_t		clk_mask;
+	u32		clk_mult;
+	u32		clk_shift;
+	void		*clk_fsys_mmio;
+	cycle_t		clk_cycle_last;
+} __attribute__ ((aligned (L1_CACHE_BYTES)));
+
+struct itc_jitter_data_t {
+	int		itc_jitter;
+	cycle_t		itc_lastcycle;
+} __attribute__ ((aligned (L1_CACHE_BYTES)));
+

arch/ia64/kernel/irq.c

@@ -35,7 +35,7 @@ void ack_bad_irq(unsigned int irq)
 #ifdef CONFIG_IA64_GENERIC
 unsigned int __ia64_local_vector_to_irq (ia64_vector vec)
 {
-	return (unsigned int) vec;
+	return __get_cpu_var(vector_irq)[vec];
 }
 #endif
 

arch/ia64/kernel/irq_ia64.c

@@ -46,6 +46,12 @@
 
 #define IRQ_DEBUG	0
 
+#define IRQ_VECTOR_UNASSIGNED	(0)
+
+#define IRQ_UNUSED		(0)
+#define IRQ_USED		(1)
+#define IRQ_RSVD		(2)
+
 /* These can be overridden in platform_irq_init */
 int ia64_first_device_vector = IA64_DEF_FIRST_DEVICE_VECTOR;
 int ia64_last_device_vector = IA64_DEF_LAST_DEVICE_VECTOR;
@@ -54,6 +60,8 @@ int ia64_last_device_vector = IA64_DEF_LAST_DEVICE_VECTOR;
 void __iomem *ipi_base_addr = ((void __iomem *)
 			       (__IA64_UNCACHED_OFFSET | IA64_IPI_DEFAULT_BASE_ADDR));
 
+static cpumask_t vector_allocation_domain(int cpu);
+
 /*
  * Legacy IRQ to IA-64 vector translation table.
  */
@@ -64,46 +72,269 @@ __u8 isa_irq_to_vector_map[16] = {
 };
 EXPORT_SYMBOL(isa_irq_to_vector_map);
 
-static unsigned long ia64_vector_mask[BITS_TO_LONGS(IA64_MAX_DEVICE_VECTORS)];
+DEFINE_SPINLOCK(vector_lock);
+
+struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
+	[0 ... NR_IRQS - 1] = {
+		.vector = IRQ_VECTOR_UNASSIGNED,
+		.domain = CPU_MASK_NONE
+	}
+};
+
+DEFINE_PER_CPU(int[IA64_NUM_VECTORS], vector_irq) = {
+	[0 ... IA64_NUM_VECTORS - 1] = IA64_SPURIOUS_INT_VECTOR
+};
+
+static cpumask_t vector_table[IA64_MAX_DEVICE_VECTORS] = {
+	[0 ... IA64_MAX_DEVICE_VECTORS - 1] = CPU_MASK_NONE
+};
+
+static int irq_status[NR_IRQS] = {
+	[0 ... NR_IRQS -1] = IRQ_UNUSED
+};
+
+int check_irq_used(int irq)
+{
+	if (irq_status[irq] == IRQ_USED)
+		return 1;
+
+	return -1;
+}
+
+static void reserve_irq(unsigned int irq)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&vector_lock, flags);
+	irq_status[irq] = IRQ_RSVD;
+	spin_unlock_irqrestore(&vector_lock, flags);
+}
+
+static inline int find_unassigned_irq(void)
+{
+	int irq;
+
+	for (irq = IA64_FIRST_DEVICE_VECTOR; irq < NR_IRQS; irq++)
+		if (irq_status[irq] == IRQ_UNUSED)
+			return irq;
+	return -ENOSPC;
+}
+
+static inline int find_unassigned_vector(cpumask_t domain)
+{
+	cpumask_t mask;
+	int pos;
+
+	cpus_and(mask, domain, cpu_online_map);
+	if (cpus_empty(mask))
+		return -EINVAL;
+
+	for (pos = 0; pos < IA64_NUM_DEVICE_VECTORS; pos++) {
+		cpus_and(mask, domain, vector_table[pos]);
+		if (!cpus_empty(mask))
+			continue;
+		return IA64_FIRST_DEVICE_VECTOR + pos;
+	}
+	return -ENOSPC;
+}
+
+static int __bind_irq_vector(int irq, int vector, cpumask_t domain)
+{
+	cpumask_t mask;
+	int cpu, pos;
+	struct irq_cfg *cfg = &irq_cfg[irq];
+
+	cpus_and(mask, domain, cpu_online_map);
+	if (cpus_empty(mask))
+		return -EINVAL;
+	if ((cfg->vector == vector) && cpus_equal(cfg->domain, domain))
+		return 0;
+	if (cfg->vector != IRQ_VECTOR_UNASSIGNED)
+		return -EBUSY;
+	for_each_cpu_mask(cpu, mask)
+		per_cpu(vector_irq, cpu)[vector] = irq;
+	cfg->vector = vector;
+	cfg->domain = domain;
+	irq_status[irq] = IRQ_USED;
+	pos = vector - IA64_FIRST_DEVICE_VECTOR;
+	cpus_or(vector_table[pos], vector_table[pos], domain);
+	return 0;
+}
+
+int bind_irq_vector(int irq, int vector, cpumask_t domain)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&vector_lock, flags);
+	ret = __bind_irq_vector(irq, vector, domain);
+	spin_unlock_irqrestore(&vector_lock, flags);
+	return ret;
+}
+
+static void __clear_irq_vector(int irq)
+{
+	int vector, cpu, pos;
+	cpumask_t mask;
+	cpumask_t domain;
+	struct irq_cfg *cfg = &irq_cfg[irq];
+
+	BUG_ON((unsigned)irq >= NR_IRQS);
+	BUG_ON(cfg->vector == IRQ_VECTOR_UNASSIGNED);
+	vector = cfg->vector;
+	domain = cfg->domain;
+	cpus_and(mask, cfg->domain, cpu_online_map);
+	for_each_cpu_mask(cpu, mask)
+		per_cpu(vector_irq, cpu)[vector] = IA64_SPURIOUS_INT_VECTOR;
+	cfg->vector = IRQ_VECTOR_UNASSIGNED;
+	cfg->domain = CPU_MASK_NONE;
+	irq_status[irq] = IRQ_UNUSED;
+	pos = vector - IA64_FIRST_DEVICE_VECTOR;
+	cpus_andnot(vector_table[pos], vector_table[pos], domain);
+}
+
+static void clear_irq_vector(int irq)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&vector_lock, flags);
+	__clear_irq_vector(irq);
+	spin_unlock_irqrestore(&vector_lock, flags);
+}
 
 int
 assign_irq_vector (int irq)
 {
-	int pos, vector;
- again:
-	pos = find_first_zero_bit(ia64_vector_mask, IA64_NUM_DEVICE_VECTORS);
-	vector = IA64_FIRST_DEVICE_VECTOR + pos;
-	if (vector > IA64_LAST_DEVICE_VECTOR)
-		return -ENOSPC;
-	if (test_and_set_bit(pos, ia64_vector_mask))
-		goto again;
+	unsigned long flags;
+	int vector, cpu;
+	cpumask_t domain;
+
+	vector = -ENOSPC;
+
+	spin_lock_irqsave(&vector_lock, flags);
+	if (irq < 0) {
+		goto out;
+	}
+	for_each_online_cpu(cpu) {
+		domain = vector_allocation_domain(cpu);
+		vector = find_unassigned_vector(domain);
+		if (vector >= 0)
+			break;
+	}
+	if (vector < 0)
+		goto out;
+	BUG_ON(__bind_irq_vector(irq, vector, domain));
+ out:
+	spin_unlock_irqrestore(&vector_lock, flags);
 	return vector;
 }
 
 void
 free_irq_vector (int vector)
 {
-	int pos;
-
-	if (vector < IA64_FIRST_DEVICE_VECTOR || vector > IA64_LAST_DEVICE_VECTOR)
+	if (vector < IA64_FIRST_DEVICE_VECTOR ||
+	    vector > IA64_LAST_DEVICE_VECTOR)
 		return;
-
-	pos = vector - IA64_FIRST_DEVICE_VECTOR;
-	if (!test_and_clear_bit(pos, ia64_vector_mask))
-		printk(KERN_WARNING "%s: double free!\n", __FUNCTION__);
+	clear_irq_vector(vector);
 }
 
 int
 reserve_irq_vector (int vector)
 {
-	int pos;
-
 	if (vector < IA64_FIRST_DEVICE_VECTOR ||
 	    vector > IA64_LAST_DEVICE_VECTOR)
 		return -EINVAL;
+	return !!bind_irq_vector(vector, vector, CPU_MASK_ALL);
+}
 
-	pos = vector - IA64_FIRST_DEVICE_VECTOR;
-	return test_and_set_bit(pos, ia64_vector_mask);
+/*
+ * Initialize vector_irq on a new cpu. This function must be called
+ * with vector_lock held.
+ */
+void __setup_vector_irq(int cpu)
+{
+	int irq, vector;
+
+	/* Clear vector_irq */
+	for (vector = 0; vector < IA64_NUM_VECTORS; ++vector)
+		per_cpu(vector_irq, cpu)[vector] = IA64_SPURIOUS_INT_VECTOR;
+	/* Mark the inuse vectors */
+	for (irq = 0; irq < NR_IRQS; ++irq) {
+		if (!cpu_isset(cpu, irq_cfg[irq].domain))
+			continue;
+		vector = irq_to_vector(irq);
+		per_cpu(vector_irq, cpu)[vector] = irq;
+	}
+}
+
+#if defined(CONFIG_SMP) && (defined(CONFIG_IA64_GENERIC) || defined(CONFIG_IA64_DIG))
+static enum vector_domain_type {
+	VECTOR_DOMAIN_NONE,
+	VECTOR_DOMAIN_PERCPU
+} vector_domain_type = VECTOR_DOMAIN_NONE;
+
+static cpumask_t vector_allocation_domain(int cpu)
+{
+	if (vector_domain_type == VECTOR_DOMAIN_PERCPU)
+		return cpumask_of_cpu(cpu);
+	return CPU_MASK_ALL;
+}
+
+static int __init parse_vector_domain(char *arg)
+{
+	if (!arg)
+		return -EINVAL;
+	if (!strcmp(arg, "percpu")) {
+		vector_domain_type = VECTOR_DOMAIN_PERCPU;
+		no_int_routing = 1;
+	}
+	return 1;
+}
+early_param("vector", parse_vector_domain);
+#else
+static cpumask_t vector_allocation_domain(int cpu)
+{
+	return CPU_MASK_ALL;
+}
+#endif
+
+
+void destroy_and_reserve_irq(unsigned int irq)
+{
+	dynamic_irq_cleanup(irq);
+
+	clear_irq_vector(irq);
+	reserve_irq(irq);
+}
+
+static int __reassign_irq_vector(int irq, int cpu)
+{
+	struct irq_cfg *cfg = &irq_cfg[irq];
+	int vector;
+	cpumask_t domain;
+
+	if (cfg->vector == IRQ_VECTOR_UNASSIGNED || !cpu_online(cpu))
+		return -EINVAL;
+	if (cpu_isset(cpu, cfg->domain))
+		return 0;
+	domain = vector_allocation_domain(cpu);
+	vector = find_unassigned_vector(domain);
+	if (vector < 0)
+		return -ENOSPC;
+	__clear_irq_vector(irq);
+	BUG_ON(__bind_irq_vector(irq, vector, domain));
+	return 0;
+}
+
+int reassign_irq_vector(int irq, int cpu)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&vector_lock, flags);
+	ret = __reassign_irq_vector(irq, cpu);
+	spin_unlock_irqrestore(&vector_lock, flags);
+	return ret;
 }
 
 /*
@@ -111,18 +342,35 @@ reserve_irq_vector (int vector)
  */
 int create_irq(void)
 {
-	int vector = assign_irq_vector(AUTO_ASSIGN);
-
-	if (vector >= 0)
-		dynamic_irq_init(vector);
-
-	return vector;
+	unsigned long flags;
+	int irq, vector, cpu;
+	cpumask_t domain;
+
+	irq = vector = -ENOSPC;
+	spin_lock_irqsave(&vector_lock, flags);
+	for_each_online_cpu(cpu) {
+		domain = vector_allocation_domain(cpu);
+		vector = find_unassigned_vector(domain);
+		if (vector >= 0)
+			break;
+	}
+	if (vector < 0)
+		goto out;
+	irq = find_unassigned_irq();
+	if (irq < 0)
+		goto out;
+	BUG_ON(__bind_irq_vector(irq, vector, domain));
+ out:
+	spin_unlock_irqrestore(&vector_lock, flags);
+	if (irq >= 0)
+		dynamic_irq_init(irq);
+	return irq;
 }
 
 void destroy_irq(unsigned int irq)
 {
 	dynamic_irq_cleanup(irq);
-	free_irq_vector(irq);
+	clear_irq_vector(irq);
 }
 
 #ifdef CONFIG_SMP
@@ -301,14 +549,13 @@ register_percpu_irq (ia64_vector vec, struct irqaction *action)
 	irq_desc_t *desc;
 	unsigned int irq;
 
-	for (irq = 0; irq < NR_IRQS; ++irq)
-		if (irq_to_vector(irq) == vec) {
-			desc = irq_desc + irq;
-			desc->status |= IRQ_PER_CPU;
-			desc->chip = &irq_type_ia64_lsapic;
-			if (action)
-				setup_irq(irq, action);
-		}
+	irq = vec;
+	BUG_ON(bind_irq_vector(irq, vec, CPU_MASK_ALL));
+	desc = irq_desc + irq;
+	desc->status |= IRQ_PER_CPU;
+	desc->chip = &irq_type_ia64_lsapic;
+	if (action)
+		setup_irq(irq, action);
 }
 
 void __init

arch/ia64/kernel/msi_ia64.c

@@ -13,6 +13,7 @@
 
 #define MSI_DATA_VECTOR_SHIFT		0
 #define	    MSI_DATA_VECTOR(v)		(((u8)v) << MSI_DATA_VECTOR_SHIFT)
+#define MSI_DATA_VECTOR_MASK		0xffffff00
 
 #define MSI_DATA_DELIVERY_SHIFT		8
 #define     MSI_DATA_DELIVERY_FIXED	(0 << MSI_DATA_DELIVERY_SHIFT)
@@ -50,17 +51,29 @@ static struct irq_chip	ia64_msi_chip;
 static void ia64_set_msi_irq_affinity(unsigned int irq, cpumask_t cpu_mask)
 {
 	struct msi_msg msg;
-	u32 addr;
+	u32 addr, data;
+	int cpu = first_cpu(cpu_mask);
+
+	if (!cpu_online(cpu))
+		return;
+
+	if (reassign_irq_vector(irq, cpu))
+		return;
 
 	read_msi_msg(irq, &msg);
 
 	addr = msg.address_lo;
 	addr &= MSI_ADDR_DESTID_MASK;
-	addr |= MSI_ADDR_DESTID_CPU(cpu_physical_id(first_cpu(cpu_mask)));
+	addr |= MSI_ADDR_DESTID_CPU(cpu_physical_id(cpu));
 	msg.address_lo = addr;
 
+	data = msg.data;
+	data &= MSI_DATA_VECTOR_MASK;
+	data |= MSI_DATA_VECTOR(irq_to_vector(irq));
+	msg.data = data;
+
 	write_msi_msg(irq, &msg);
-	irq_desc[irq].affinity = cpu_mask;
+	irq_desc[irq].affinity = cpumask_of_cpu(cpu);
 }
 #endif /* CONFIG_SMP */
 
@@ -69,13 +82,15 @@ int ia64_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc)
 	struct msi_msg	msg;
 	unsigned long	dest_phys_id;
 	int	irq, vector;
+	cpumask_t mask;
 
 	irq = create_irq();
 	if (irq < 0)
 		return irq;
 
 	set_irq_msi(irq, desc);
-	dest_phys_id = cpu_physical_id(first_cpu(cpu_online_map));
+	cpus_and(mask, irq_to_domain(irq), cpu_online_map);
+	dest_phys_id = cpu_physical_id(first_cpu(mask));
 	vector = irq_to_vector(irq);
 
 	msg.address_hi = 0;

arch/ia64/kernel/smpboot.c

@@ -395,9 +395,13 @@ smp_callin (void)
 	fix_b0_for_bsp();
 
 	lock_ipi_calllock();
+	spin_lock(&vector_lock);
+	/* Setup the per cpu irq handling data structures */
+	__setup_vector_irq(cpuid);
 	cpu_set(cpuid, cpu_online_map);
 	unlock_ipi_calllock();
 	per_cpu(cpu_state, cpuid) = CPU_ONLINE;
+	spin_unlock(&vector_lock);
 
 	smp_setup_percpu_timer();
 

arch/ia64/kernel/time.c

@@ -19,6 +19,7 @@
 #include <linux/interrupt.h>
 #include <linux/efi.h>
 #include <linux/timex.h>
+#include <linux/clocksource.h>
 
 #include <asm/machvec.h>
 #include <asm/delay.h>
@@ -28,6 +29,16 @@
 #include <asm/sections.h>
 #include <asm/system.h>
 
+#include "fsyscall_gtod_data.h"
+
+static cycle_t itc_get_cycles(void);
+
+struct fsyscall_gtod_data_t fsyscall_gtod_data = {
+	.lock = SEQLOCK_UNLOCKED,
+};
+
+struct itc_jitter_data_t itc_jitter_data;
+
 volatile int time_keeper_id = 0; /* smp_processor_id() of time-keeper */
 
 #ifdef CONFIG_IA64_DEBUG_IRQ
@@ -37,11 +48,16 @@ EXPORT_SYMBOL(last_cli_ip);
 
 #endif
 
-static struct time_interpolator itc_interpolator = {
-	.shift = 16,
-	.mask = 0xffffffffffffffffLL,
-	.source = TIME_SOURCE_CPU
+static struct clocksource clocksource_itc = {
+        .name           = "itc",
+        .rating         = 350,
+        .read           = itc_get_cycles,
+        .mask           = 0xffffffffffffffff,
+        .mult           = 0, /*to be caluclated*/
+        .shift          = 16,
+        .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
 };
+static struct clocksource *itc_clocksource;
 
 static irqreturn_t
 timer_interrupt (int irq, void *dev_id)
@@ -210,8 +226,6 @@ ia64_init_itm (void)
 					+ itc_freq/2)/itc_freq;
 
 	if (!(sal_platform_features & IA64_SAL_PLATFORM_FEATURE_ITC_DRIFT)) {
-		itc_interpolator.frequency = local_cpu_data->itc_freq;
-		itc_interpolator.drift = itc_drift;
 #ifdef CONFIG_SMP
 		/* On IA64 in an SMP configuration ITCs are never accurately synchronized.
 		 * Jitter compensation requires a cmpxchg which may limit
@@ -223,15 +237,50 @@ ia64_init_itm (void)
 		 * even going backward) if the ITC offsets between the individual CPUs
 		 * are too large.
 		 */
-		if (!nojitter) itc_interpolator.jitter = 1;
+		if (!nojitter)
+			itc_jitter_data.itc_jitter = 1;
 #endif
-		register_time_interpolator(&itc_interpolator);
 	}
 
 	/* Setup the CPU local timer tick */
 	ia64_cpu_local_tick();
+
+	if (!itc_clocksource) {
+		/* Sort out mult/shift values: */
+		clocksource_itc.mult =
+			clocksource_hz2mult(local_cpu_data->itc_freq,
+						clocksource_itc.shift);
+		clocksource_register(&clocksource_itc);
+		itc_clocksource = &clocksource_itc;
+	}
 }
 
+static cycle_t itc_get_cycles()
+{
+	u64 lcycle, now, ret;
+
+	if (!itc_jitter_data.itc_jitter)
+		return get_cycles();
+
+	lcycle = itc_jitter_data.itc_lastcycle;
+	now = get_cycles();
+	if (lcycle && time_after(lcycle, now))
+		return lcycle;
+
+	/*
+	 * Keep track of the last timer value returned.
+	 * In an SMP environment, you could lose out in contention of
+	 * cmpxchg. If so, your cmpxchg returns new value which the
+	 * winner of contention updated to. Use the new value instead.
+	 */
+	ret = cmpxchg(&itc_jitter_data.itc_lastcycle, lcycle, now);
+	if (unlikely(ret != lcycle))
+		return ret;
+
+	return now;
+}
+
+
 static struct irqaction timer_irqaction = {
 	.handler =	timer_interrupt,
 	.flags =	IRQF_DISABLED | IRQF_IRQPOLL,
@@ -307,3 +356,34 @@ ia64_setup_printk_clock(void)
 	if (!(sal_platform_features & IA64_SAL_PLATFORM_FEATURE_ITC_DRIFT))
 		ia64_printk_clock = ia64_itc_printk_clock;
 }
+
+void update_vsyscall(struct timespec *wall, struct clocksource *c)
+{
+        unsigned long flags;
+
+        write_seqlock_irqsave(&fsyscall_gtod_data.lock, flags);
+
+        /* copy fsyscall clock data */
+        fsyscall_gtod_data.clk_mask = c->mask;
+        fsyscall_gtod_data.clk_mult = c->mult;
+        fsyscall_gtod_data.clk_shift = c->shift;
+        fsyscall_gtod_data.clk_fsys_mmio = c->fsys_mmio;
+        fsyscall_gtod_data.clk_cycle_last = c->cycle_last;
+
+	/* copy kernel time structures */
+        fsyscall_gtod_data.wall_time.tv_sec = wall->tv_sec;
+        fsyscall_gtod_data.wall_time.tv_nsec = wall->tv_nsec;
+        fsyscall_gtod_data.monotonic_time.tv_sec = wall_to_monotonic.tv_sec
+							+ wall->tv_sec;
+        fsyscall_gtod_data.monotonic_time.tv_nsec = wall_to_monotonic.tv_nsec
+							+ wall->tv_nsec;
+
+	/* normalize */
+	while (fsyscall_gtod_data.monotonic_time.tv_nsec >= NSEC_PER_SEC) {
+		fsyscall_gtod_data.monotonic_time.tv_nsec -= NSEC_PER_SEC;
+		fsyscall_gtod_data.monotonic_time.tv_sec++;
+	}
+
+        write_sequnlock_irqrestore(&fsyscall_gtod_data.lock, flags);
+}
+

arch/ia64/sn/kernel/sn2/timer.c

@@ -11,6 +11,7 @@
 #include <linux/sched.h>
 #include <linux/time.h>
 #include <linux/interrupt.h>
+#include <linux/clocksource.h>
 
 #include <asm/hw_irq.h>
 #include <asm/system.h>
@@ -22,11 +23,21 @@
 
 extern unsigned long sn_rtc_cycles_per_second;
 
-static struct time_interpolator sn2_interpolator = {
-	.drift = -1,
-	.shift = 10,
-	.mask = (1LL << 55) - 1,
-	.source = TIME_SOURCE_MMIO64
+static void __iomem *sn2_mc;
+
+static cycle_t read_sn2(void)
+{
+	return (cycle_t)readq(sn2_mc);
+}
+
+static struct clocksource clocksource_sn2 = {
+        .name           = "sn2_rtc",
+        .rating         = 300,
+        .read           = read_sn2,
+        .mask           = (1LL << 55) - 1,
+        .mult           = 0,
+        .shift          = 10,
+        .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 /*
@@ -47,9 +58,11 @@ ia64_sn_udelay (unsigned long usecs)
 
 void __init sn_timer_init(void)
 {
-	sn2_interpolator.frequency = sn_rtc_cycles_per_second;
-	sn2_interpolator.addr = RTC_COUNTER_ADDR;
-	register_time_interpolator(&sn2_interpolator);
+	sn2_mc = RTC_COUNTER_ADDR;
+	clocksource_sn2.fsys_mmio = RTC_COUNTER_ADDR;
+	clocksource_sn2.mult = clocksource_hz2mult(sn_rtc_cycles_per_second,
+							clocksource_sn2.shift);
+	clocksource_register(&clocksource_sn2);
 
 	ia64_udelay = &ia64_sn_udelay;
 }

drivers/acpi/processor_idle.c

@@ -475,7 +475,7 @@ static void acpi_processor_idle(void)
 		/* Get end time (ticks) */
 		t2 = inl(acpi_gbl_FADT.xpm_timer_block.address);
 
-#ifdef CONFIG_GENERIC_TIME
+#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC)
 		/* TSC halts in C2, so notify users */
 		mark_tsc_unstable("possible TSC halt in C2");
 #endif
@@ -517,7 +517,7 @@ static void acpi_processor_idle(void)
 			acpi_set_register(ACPI_BITREG_ARB_DISABLE, 0);
 		}
 
-#ifdef CONFIG_GENERIC_TIME
+#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC)
 		/* TSC halts in C3, so notify users */
 		mark_tsc_unstable("TSC halts in C3");
 #endif

drivers/char/hpet.c

@@ -29,6 +29,7 @@
 #include <linux/bcd.h>
 #include <linux/seq_file.h>
 #include <linux/bitops.h>
+#include <linux/clocksource.h>
 
 #include <asm/current.h>
 #include <asm/uaccess.h>
@@ -51,8 +52,34 @@
 
 #define HPET_RANGE_SIZE		1024	/* from HPET spec */
 
+#if BITS_PER_LONG == 64
+#define	write_counter(V, MC)	writeq(V, MC)
+#define	read_counter(MC)	readq(MC)
+#else
+#define	write_counter(V, MC)	writel(V, MC)
+#define	read_counter(MC)	readl(MC)
+#endif
+
 static u32 hpet_nhpet, hpet_max_freq = HPET_USER_FREQ;
 
+static void __iomem *hpet_mctr;
+
+static cycle_t read_hpet(void)
+{
+	return (cycle_t)read_counter((void __iomem *)hpet_mctr);
+}
+
+static struct clocksource clocksource_hpet = {
+        .name           = "hpet",
+        .rating         = 250,
+        .read           = read_hpet,
+        .mask           = 0xffffffffffffffff,
+        .mult           = 0, /*to be caluclated*/
+        .shift          = 10,
+        .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+static struct clocksource *hpet_clocksource;
+
 /* A lock for concurrent access by app and isr hpet activity. */
 static DEFINE_SPINLOCK(hpet_lock);
 /* A lock for concurrent intermodule access to hpet and isr hpet activity. */
@@ -79,7 +106,7 @@ struct hpets {
 	struct hpets *hp_next;
 	struct hpet __iomem *hp_hpet;
 	unsigned long hp_hpet_phys;
-	struct time_interpolator *hp_interpolator;
+	struct clocksource *hp_clocksource;
 	unsigned long long hp_tick_freq;
 	unsigned long hp_delta;
 	unsigned int hp_ntimer;
@@ -94,13 +121,6 @@ static struct hpets *hpets;
 #define	HPET_PERIODIC		0x0004
 #define	HPET_SHARED_IRQ		0x0008
 
-#if BITS_PER_LONG == 64
-#define	write_counter(V, MC)	writeq(V, MC)
-#define	read_counter(MC)	readq(MC)
-#else
-#define	write_counter(V, MC) 	writel(V, MC)
-#define	read_counter(MC)	readl(MC)
-#endif
 
 #ifndef readq
 static inline unsigned long long readq(void __iomem *addr)
@@ -737,27 +757,6 @@ static ctl_table dev_root[] = {
 
 static struct ctl_table_header *sysctl_header;
 
-static void hpet_register_interpolator(struct hpets *hpetp)
-{
-#ifdef	CONFIG_TIME_INTERPOLATION
-	struct time_interpolator *ti;
-
-	ti = kzalloc(sizeof(*ti), GFP_KERNEL);
-	if (!ti)
-		return;
-
-	ti->source = TIME_SOURCE_MMIO64;
-	ti->shift = 10;
-	ti->addr = &hpetp->hp_hpet->hpet_mc;
-	ti->frequency = hpetp->hp_tick_freq;
-	ti->drift = HPET_DRIFT;
-	ti->mask = -1;
-
-	hpetp->hp_interpolator = ti;
-	register_time_interpolator(ti);
-#endif
-}
-
 /*
  * Adjustment for when arming the timer with
  * initial conditions.  That is, main counter
@@ -909,7 +908,16 @@ int hpet_alloc(struct hpet_data *hdp)
 	}
 
 	hpetp->hp_delta = hpet_calibrate(hpetp);
-	hpet_register_interpolator(hpetp);
+
+	if (!hpet_clocksource) {
+		hpet_mctr = (void __iomem *)&hpetp->hp_hpet->hpet_mc;
+		CLKSRC_FSYS_MMIO_SET(clocksource_hpet.fsys_mmio, hpet_mctr);
+		clocksource_hpet.mult = clocksource_hz2mult(hpetp->hp_tick_freq,
+						clocksource_hpet.shift);
+		clocksource_register(&clocksource_hpet);
+		hpetp->hp_clocksource = &clocksource_hpet;
+		hpet_clocksource = &clocksource_hpet;
+	}
 
 	return 0;
 }
@@ -995,7 +1003,7 @@ static int hpet_acpi_add(struct acpi_device *device)
 
 static int hpet_acpi_remove(struct acpi_device *device, int type)
 {
-	/* XXX need to unregister interpolator, dealloc mem, etc */
+	/* XXX need to unregister clocksource, dealloc mem, etc */
 	return -EINVAL;
 }
 

include/asm-ia64/hw_irq.h

@@ -90,13 +90,27 @@ enum {
 extern __u8 isa_irq_to_vector_map[16];
 #define isa_irq_to_vector(x)	isa_irq_to_vector_map[(x)]
 
+struct irq_cfg {
+	ia64_vector vector;
+	cpumask_t domain;
+};
+extern spinlock_t vector_lock;
+extern struct irq_cfg irq_cfg[NR_IRQS];
+#define irq_to_domain(x)	irq_cfg[(x)].domain
+DECLARE_PER_CPU(int[IA64_NUM_VECTORS], vector_irq);
+
 extern struct hw_interrupt_type irq_type_ia64_lsapic;	/* CPU-internal interrupt controller */
 
+extern int bind_irq_vector(int irq, int vector, cpumask_t domain);
 extern int assign_irq_vector (int irq);	/* allocate a free vector */
 extern void free_irq_vector (int vector);
 extern int reserve_irq_vector (int vector);
+extern void __setup_vector_irq(int cpu);
+extern int reassign_irq_vector(int irq, int cpu);
 extern void ia64_send_ipi (int cpu, int vector, int delivery_mode, int redirect);
 extern void register_percpu_irq (ia64_vector vec, struct irqaction *action);
+extern int check_irq_used (int irq);
+extern void destroy_and_reserve_irq (unsigned int irq);
 
 static inline void ia64_resend_irq(unsigned int vector)
 {
@@ -113,7 +127,7 @@ extern irq_desc_t irq_desc[NR_IRQS];
 static inline unsigned int
 __ia64_local_vector_to_irq (ia64_vector vec)
 {
-	return (unsigned int) vec;
+	return __get_cpu_var(vector_irq)[vec];
 }
 #endif
 
@@ -131,7 +145,7 @@ __ia64_local_vector_to_irq (ia64_vector vec)
 static inline ia64_vector
 irq_to_vector (int irq)
 {
-	return (ia64_vector) irq;
+	return irq_cfg[irq].vector;
 }
 
 /*

include/asm-ia64/iosapic.h

@@ -47,19 +47,21 @@
 #define	IOSAPIC_MASK_SHIFT		16
 #define	IOSAPIC_MASK			(1<<IOSAPIC_MASK_SHIFT)
 
+#define IOSAPIC_VECTOR_MASK		0xffffff00
+
 #ifndef __ASSEMBLY__
 
 #ifdef CONFIG_IOSAPIC
 
 #define NR_IOSAPICS			256
 
-static inline unsigned int iosapic_read(char __iomem *iosapic, unsigned int reg)
+static inline unsigned int __iosapic_read(char __iomem *iosapic, unsigned int reg)
 {
 	writel(reg, iosapic + IOSAPIC_REG_SELECT);
 	return readl(iosapic + IOSAPIC_WINDOW);
 }
 
-static inline void iosapic_write(char __iomem *iosapic, unsigned int reg, u32 val)
+static inline void __iosapic_write(char __iomem *iosapic, unsigned int reg, u32 val)
 {
 	writel(reg, iosapic + IOSAPIC_REG_SELECT);
 	writel(val, iosapic + IOSAPIC_WINDOW);

include/asm-ia64/irq.h

@@ -14,8 +14,13 @@
 #include <linux/types.h>
 #include <linux/cpumask.h>
 
-#define NR_IRQS		256
-#define NR_IRQ_VECTORS	NR_IRQS
+#define NR_VECTORS	256
+
+#if (NR_VECTORS + 32 * NR_CPUS) < 1024
+#define NR_IRQS (NR_VECTORS + 32 * NR_CPUS)
+#else
+#define NR_IRQS 1024
+#endif
 
 static __inline__ int
 irq_canonicalize (int irq)

include/asm-ia64/rwsem.h

@@ -21,6 +21,10 @@
 #ifndef _ASM_IA64_RWSEM_H
 #define _ASM_IA64_RWSEM_H
 
+#ifndef _LINUX_RWSEM_H
+#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
+#endif
+
 #include <linux/list.h>
 #include <linux/spinlock.h>
 

include/asm-ia64/unistd.h

@@ -292,7 +292,7 @@
 #define __NR_sync_file_range		1300
 #define __NR_tee			1301
 #define __NR_vmsplice			1302
-/* 1303 reserved for move_pages */
+#define __NR_fallocate			1303
 #define __NR_getcpu			1304
 #define __NR_epoll_pwait		1305
 #define __NR_utimensat			1306

include/linux/clocksource.h

@@ -67,6 +67,12 @@ struct clocksource {
 	unsigned long flags;
 	cycle_t (*vread)(void);
 	void (*resume)(void);
+#ifdef CONFIG_IA64
+	void *fsys_mmio;        /* used by fsyscall asm code */
+#define CLKSRC_FSYS_MMIO_SET(mmio, addr)      ((mmio) = (addr))
+#else
+#define CLKSRC_FSYS_MMIO_SET(mmio, addr)      do { } while (0)
+#endif
 
 	/* timekeeping specific data, ignore */
 	cycle_t cycle_interval;

include/linux/timex.h

@@ -224,66 +224,6 @@ static inline int ntp_synced(void)
 	__x < 0 ? -(-__x >> __s) : __x >> __s;	\
 })
 
-
-#ifdef CONFIG_TIME_INTERPOLATION
-
-#define TIME_SOURCE_CPU 0
-#define TIME_SOURCE_MMIO64 1
-#define TIME_SOURCE_MMIO32 2
-#define TIME_SOURCE_FUNCTION 3
-
-/* For proper operations time_interpolator clocks must run slightly slower
- * than the standard clock since the interpolator may only correct by having
- * time jump forward during a tick. A slower clock is usually a side effect
- * of the integer divide of the nanoseconds in a second by the frequency.
- * The accuracy of the division can be increased by specifying a shift.
- * However, this may cause the clock not to be slow enough.
- * The interpolator will self-tune the clock by slowing down if no
- * resets occur or speeding up if the time jumps per analysis cycle
- * become too high.
- *
- * Setting jitter compensates for a fluctuating timesource by comparing
- * to the last value read from the timesource to insure that an earlier value
- * is not returned by a later call. The price to pay
- * for the compensation is that the timer routines are not as scalable anymore.
- */
-
-struct time_interpolator {
-	u16 source;			/* time source flags */
-	u8 shift;			/* increases accuracy of multiply by shifting. */
-				/* Note that bits may be lost if shift is set too high */
-	u8 jitter;			/* if set compensate for fluctuations */
-	u32 nsec_per_cyc;		/* set by register_time_interpolator() */
-	void *addr;			/* address of counter or function */
-	cycles_t mask;			/* mask the valid bits of the counter */
-	unsigned long offset;		/* nsec offset at last update of interpolator */
-	u64 last_counter;		/* counter value in units of the counter at last update */
-	cycles_t last_cycle;		/* Last timer value if TIME_SOURCE_JITTER is set */
-	u64 frequency;			/* frequency in counts/second */
-	long drift;			/* drift in parts-per-million (or -1) */
-	unsigned long skips;		/* skips forward */
-	unsigned long ns_skipped;	/* nanoseconds skipped */
-	struct time_interpolator *next;
-};
-
-extern void register_time_interpolator(struct time_interpolator *);
-extern void unregister_time_interpolator(struct time_interpolator *);
-extern void time_interpolator_reset(void);
-extern unsigned long time_interpolator_get_offset(void);
-extern void time_interpolator_update(long delta_nsec);
-
-#else /* !CONFIG_TIME_INTERPOLATION */
-
-static inline void time_interpolator_reset(void)
-{
-}
-
-static inline void time_interpolator_update(long delta_nsec)
-{
-}
-
-#endif /* !CONFIG_TIME_INTERPOLATION */
-
 #define TICK_LENGTH_SHIFT	32
 
 #ifdef CONFIG_NO_HZ

kernel/time.c

@@ -136,7 +136,6 @@ static inline void warp_clock(void)
 	write_seqlock_irq(&xtime_lock);
 	wall_to_monotonic.tv_sec -= sys_tz.tz_minuteswest * 60;
 	xtime.tv_sec += sys_tz.tz_minuteswest * 60;
-	time_interpolator_reset();
 	write_sequnlock_irq(&xtime_lock);
 	clock_was_set();
 }
@@ -309,92 +308,6 @@ struct timespec timespec_trunc(struct timespec t, unsigned gran)
 }
 EXPORT_SYMBOL(timespec_trunc);
 
-#ifdef CONFIG_TIME_INTERPOLATION
-void getnstimeofday (struct timespec *tv)
-{
-	unsigned long seq,sec,nsec;
-
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		sec = xtime.tv_sec;
-		nsec = xtime.tv_nsec+time_interpolator_get_offset();
-	} while (unlikely(read_seqretry(&xtime_lock, seq)));
-
-	while (unlikely(nsec >= NSEC_PER_SEC)) {
-		nsec -= NSEC_PER_SEC;
-		++sec;
-	}
-	tv->tv_sec = sec;
-	tv->tv_nsec = nsec;
-}
-EXPORT_SYMBOL_GPL(getnstimeofday);
-
-int do_settimeofday (struct timespec *tv)
-{
-	time_t wtm_sec, sec = tv->tv_sec;
-	long wtm_nsec, nsec = tv->tv_nsec;
-
-	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
-		return -EINVAL;
-
-	write_seqlock_irq(&xtime_lock);
-	{
-		wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
-		wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);
-
-		set_normalized_timespec(&xtime, sec, nsec);
-		set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
-
-		time_adjust = 0;		/* stop active adjtime() */
-		time_status |= STA_UNSYNC;
-		time_maxerror = NTP_PHASE_LIMIT;
-		time_esterror = NTP_PHASE_LIMIT;
-		time_interpolator_reset();
-	}
-	write_sequnlock_irq(&xtime_lock);
-	clock_was_set();
-	return 0;
-}
-EXPORT_SYMBOL(do_settimeofday);
-
-void do_gettimeofday (struct timeval *tv)
-{
-	unsigned long seq, nsec, usec, sec, offset;
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		offset = time_interpolator_get_offset();
-		sec = xtime.tv_sec;
-		nsec = xtime.tv_nsec;
-	} while (unlikely(read_seqretry(&xtime_lock, seq)));
-
-	usec = (nsec + offset) / 1000;
-
-	while (unlikely(usec >= USEC_PER_SEC)) {
-		usec -= USEC_PER_SEC;
-		++sec;
-	}
-
-	tv->tv_sec = sec;
-	tv->tv_usec = usec;
-
-	/*
-	 * Make sure xtime.tv_sec [returned by sys_time()] always
-	 * follows the gettimeofday() result precisely. This
-	 * condition is extremely unlikely, it can hit at most
-	 * once per second:
-	 */
-	if (unlikely(xtime.tv_sec != tv->tv_sec)) {
-		unsigned long flags;
-
-		write_seqlock_irqsave(&xtime_lock, flags);
-		update_wall_time();
-		write_sequnlock_irqrestore(&xtime_lock, flags);
-	}
-}
-EXPORT_SYMBOL(do_gettimeofday);
-
-#else	/* CONFIG_TIME_INTERPOLATION */
-
 #ifndef CONFIG_GENERIC_TIME
 /*
  * Simulate gettimeofday using do_gettimeofday which only allows a timeval
@@ -410,7 +323,6 @@ void getnstimeofday(struct timespec *tv)
 }
 EXPORT_SYMBOL_GPL(getnstimeofday);
 #endif
-#endif	/* CONFIG_TIME_INTERPOLATION */
 
 /* Converts Gregorian date to seconds since 1970-01-01 00:00:00.
  * Assumes input in normal date format, i.e. 1980-12-31 23:59:59

kernel/time/ntp.c

@@ -116,11 +116,6 @@ void second_overflow(void)
 		if (xtime.tv_sec % 86400 == 0) {
 			xtime.tv_sec--;
 			wall_to_monotonic.tv_sec++;
-			/*
-			 * The timer interpolator will make time change
-			 * gradually instead of an immediate jump by one second
-			 */
-			time_interpolator_update(-NSEC_PER_SEC);
 			time_state = TIME_OOP;
 			printk(KERN_NOTICE "Clock: inserting leap second "
 					"23:59:60 UTC\n");
@@ -130,11 +125,6 @@ void second_overflow(void)
 		if ((xtime.tv_sec + 1) % 86400 == 0) {
 			xtime.tv_sec++;
 			wall_to_monotonic.tv_sec--;
-			/*
-			 * Use of time interpolator for a gradual change of
-			 * time
-			 */
-			time_interpolator_update(NSEC_PER_SEC);
 			time_state = TIME_WAIT;
 			printk(KERN_NOTICE "Clock: deleting leap second "
 					"23:59:59 UTC\n");

kernel/time/timekeeping.c

@@ -466,10 +466,6 @@ void update_wall_time(void)
 			second_overflow();
 		}
 
-		/* interpolator bits */
-		time_interpolator_update(clock->xtime_interval
-						>> clock->shift);
-
 		/* accumulate error between NTP and clock interval */
 		clock->error += current_tick_length();
 		clock->error -= clock->xtime_interval << (TICK_LENGTH_SHIFT - clock->shift);

kernel/timer.c

@@ -1349,194 +1349,6 @@ void __init init_timers(void)
 	open_softirq(TIMER_SOFTIRQ, run_timer_softirq, NULL);
 }
 
-#ifdef CONFIG_TIME_INTERPOLATION
-
-struct time_interpolator *time_interpolator __read_mostly;
-static struct time_interpolator *time_interpolator_list __read_mostly;
-static DEFINE_SPINLOCK(time_interpolator_lock);
-
-static inline cycles_t time_interpolator_get_cycles(unsigned int src)
-{
-	unsigned long (*x)(void);
-
-	switch (src)
-	{
-		case TIME_SOURCE_FUNCTION:
-			x = time_interpolator->addr;
-			return x();
-
-		case TIME_SOURCE_MMIO64	:
-			return readq_relaxed((void __iomem *)time_interpolator->addr);
-
-		case TIME_SOURCE_MMIO32	:
-			return readl_relaxed((void __iomem *)time_interpolator->addr);
-
-		default: return get_cycles();
-	}
-}
-
-static inline u64 time_interpolator_get_counter(int writelock)
-{
-	unsigned int src = time_interpolator->source;
-
-	if (time_interpolator->jitter)
-	{
-		cycles_t lcycle;
-		cycles_t now;
-
-		do {
-			lcycle = time_interpolator->last_cycle;
-			now = time_interpolator_get_cycles(src);
-			if (lcycle && time_after(lcycle, now))
-				return lcycle;
-
-			/* When holding the xtime write lock, there's no need
-			 * to add the overhead of the cmpxchg.  Readers are
-			 * force to retry until the write lock is released.
-			 */
-			if (writelock) {
-				time_interpolator->last_cycle = now;
-				return now;
-			}
-			/* Keep track of the last timer value returned. The use of cmpxchg here
-			 * will cause contention in an SMP environment.
-			 */
-		} while (unlikely(cmpxchg(&time_interpolator->last_cycle, lcycle, now) != lcycle));
-		return now;
-	}
-	else
-		return time_interpolator_get_cycles(src);
-}
-
-void time_interpolator_reset(void)
-{
-	time_interpolator->offset = 0;
-	time_interpolator->last_counter = time_interpolator_get_counter(1);
-}
-
-#define GET_TI_NSECS(count,i) (((((count) - i->last_counter) & (i)->mask) * (i)->nsec_per_cyc) >> (i)->shift)
-
-unsigned long time_interpolator_get_offset(void)
-{
-	/* If we do not have a time interpolator set up then just return zero */
-	if (!time_interpolator)
-		return 0;
-
-	return time_interpolator->offset +
-		GET_TI_NSECS(time_interpolator_get_counter(0), time_interpolator);
-}
-
-#define INTERPOLATOR_ADJUST 65536
-#define INTERPOLATOR_MAX_SKIP 10*INTERPOLATOR_ADJUST
-
-void time_interpolator_update(long delta_nsec)
-{
-	u64 counter;
-	unsigned long offset;
-
-	/* If there is no time interpolator set up then do nothing */
-	if (!time_interpolator)
-		return;
-
-	/*
-	 * The interpolator compensates for late ticks by accumulating the late
-	 * time in time_interpolator->offset. A tick earlier than expected will
-	 * lead to a reset of the offset and a corresponding jump of the clock
-	 * forward. Again this only works if the interpolator clock is running
-	 * slightly slower than the regular clock and the tuning logic insures
-	 * that.
-	 */
-
-	counter = time_interpolator_get_counter(1);
-	offset = time_interpolator->offset +
-			GET_TI_NSECS(counter, time_interpolator);
-
-	if (delta_nsec < 0 || (unsigned long) delta_nsec < offset)
-		time_interpolator->offset = offset - delta_nsec;
-	else {
-		time_interpolator->skips++;
-		time_interpolator->ns_skipped += delta_nsec - offset;
-		time_interpolator->offset = 0;
-	}
-	time_interpolator->last_counter = counter;
-
-	/* Tuning logic for time interpolator invoked every minute or so.
-	 * Decrease interpolator clock speed if no skips occurred and an offset is carried.
-	 * Increase interpolator clock speed if we skip too much time.
-	 */
-	if (jiffies % INTERPOLATOR_ADJUST == 0)
-	{
-		if (time_interpolator->skips == 0 && time_interpolator->offset > tick_nsec)
-			time_interpolator->nsec_per_cyc--;
-		if (time_interpolator->ns_skipped > INTERPOLATOR_MAX_SKIP && time_interpolator->offset == 0)
-			time_interpolator->nsec_per_cyc++;
-		time_interpolator->skips = 0;
-		time_interpolator->ns_skipped = 0;
-	}
-}
-
-static inline int
-is_better_time_interpolator(struct time_interpolator *new)
-{
-	if (!time_interpolator)
-		return 1;
-	return new->frequency > 2*time_interpolator->frequency ||
-	    (unsigned long)new->drift < (unsigned long)time_interpolator->drift;
-}
-
-void
-register_time_interpolator(struct time_interpolator *ti)
-{
-	unsigned long flags;
-
-	/* Sanity check */
-	BUG_ON(ti->frequency == 0 || ti->mask == 0);
-
-	ti->nsec_per_cyc = ((u64)NSEC_PER_SEC << ti->shift) / ti->frequency;
-	spin_lock(&time_interpolator_lock);
-	write_seqlock_irqsave(&xtime_lock, flags);
-	if (is_better_time_interpolator(ti)) {
-		time_interpolator = ti;
-		time_interpolator_reset();
-	}
-	write_sequnlock_irqrestore(&xtime_lock, flags);
-
-	ti->next = time_interpolator_list;
-	time_interpolator_list = ti;
-	spin_unlock(&time_interpolator_lock);
-}
-
-void
-unregister_time_interpolator(struct time_interpolator *ti)
-{
-	struct time_interpolator *curr, **prev;
-	unsigned long flags;
-
-	spin_lock(&time_interpolator_lock);
-	prev = &time_interpolator_list;
-	for (curr = *prev; curr; curr = curr->next) {
-		if (curr == ti) {
-			*prev = curr->next;
-			break;
-		}
-		prev = &curr->next;
-	}
-
-	write_seqlock_irqsave(&xtime_lock, flags);
-	if (ti == time_interpolator) {
-		/* we lost the best time-interpolator: */
-		time_interpolator = NULL;
-		/* find the next-best interpolator */
-		for (curr = time_interpolator_list; curr; curr = curr->next)
-			if (is_better_time_interpolator(curr))
-				time_interpolator = curr;
-		time_interpolator_reset();
-	}
-	write_sequnlock_irqrestore(&xtime_lock, flags);
-	spin_unlock(&time_interpolator_lock);
-}
-#endif /* CONFIG_TIME_INTERPOLATION */
-
 /**
  * msleep - sleep safely even with waitqueue interruptions
  * @msecs: Time in milliseconds to sleep for