Merge

Documentation/io_ordering.txt

+On some platforms, so-called memory-mapped I/O is weakly ordered.  On such
+platforms, driver writers are responsible for ensuring that I/O writes to
+memory-mapped addresses on their device arrive in the order intended.  This is
+typically done by reading a 'safe' device or bridge register, causing the I/O
+chipset to flush pending writes to the device before any reads are posted.  A
+driver would usually use this technique immediately prior to the exit of a
+critical section of code protected by spinlocks.  This would ensure that
+subsequent writes to I/O space arrived only after all prior writes (much like a
+memory barrier op, mb(), only with respect to I/O).
+
+A more concrete example from a hypothetical device driver:
+
+        ...
+CPU A:  spin_lock_irqsave(&dev_lock, flags)
+CPU A:  val = readl(my_status);
+CPU A:  ...
+CPU A:  writel(newval, ring_ptr);
+CPU A:  spin_unlock_irqrestore(&dev_lock, flags)
+        ...
+CPU B:  spin_lock_irqsave(&dev_lock, flags)
+CPU B:  val = readl(my_status);
+CPU B:  ...
+CPU B:  writel(newval2, ring_ptr);
+CPU B:  spin_unlock_irqrestore(&dev_lock, flags)
+        ...
+
+In the case above, the device may receive newval2 before it receives newval,
+which could cause problems.  Fixing it is easy enough though:
+
+        ...
+CPU A:  spin_lock_irqsave(&dev_lock, flags)
+CPU A:  val = readl(my_status);
+CPU A:  ...
+CPU A:  writel(newval, ring_ptr);
+CPU A:  (void)readl(safe_register); /* maybe a config register? */
+CPU A:  spin_unlock_irqrestore(&dev_lock, flags)
+        ...
+CPU B:  spin_lock_irqsave(&dev_lock, flags)
+CPU B:  val = readl(my_status);
+CPU B:  ...
+CPU B:  writel(newval2, ring_ptr);
+CPU B:  (void)readl(safe_register); /* maybe a config register? */
+CPU B:  spin_unlock_irqrestore(&dev_lock, flags)
+
+Here, the reads from safe_register will cause the I/O chipset to flush any
+pending writes before actually posting the read to the chipset, preventing
+possible data corruption.

arch/ia64/Kconfig

@@ -401,6 +401,15 @@ config HUGETLB_PAGE_SIZE_256KB
 
 endchoice
 
+config IA64_PAL_IDLE
+	bool "Use PAL_HALT_LIGHT in idle loop"
+	---help---
+	  Say Y here to enable use of PAL_HALT_LIGHT in the cpu_idle loop.
+	  This allows the CPU to enter a low power state when idle.  You
+	  can enable CONFIG_IA64_PALINFO and check /proc/pal/cpu0/power_info
+	  to see the power consumption and latency for this state.  If you're
+	  unsure your firmware supports it, answer N.
+
 config SMP
 	bool "SMP support"
 	---help---

arch/ia64/Makefile

@@ -14,6 +14,7 @@ export AWK
 
 OBJCOPYFLAGS	:= --strip-all
 LDFLAGS_vmlinux	:= -static
+LDFLAGS_MODULE	+= -T arch/ia64/module.lds
 AFLAGS_KERNEL	:= -mconstant-gp
 EXTRA		:=
 
@@ -23,7 +24,7 @@ CFLAGS_KERNEL	:= -mconstant-gp
 
 GCC_VERSION=$(shell $(CC) -v 2>&1 | fgrep 'gcc version' | cut -f3 -d' ' | cut -f1 -d'.')
 
-GAS_STATUS=$(shell arch/ia64/scripts/check-gas $(CC))
+GAS_STATUS=$(shell arch/ia64/scripts/check-gas $(CC) $(OBJDUMP))
 
 ifeq ($(GAS_STATUS),buggy)
 $(error Sorry, you need a newer version of the assember, one that is built from	\
@@ -50,11 +51,8 @@ core-$(CONFIG_IA64_DIG) 	+= arch/ia64/dig/
 core-$(CONFIG_IA64_GENERIC) 	+= arch/ia64/dig/ arch/ia64/hp/common/ arch/ia64/hp/zx1/ \
 				   arch/ia64/hp/sim/
 core-$(CONFIG_IA64_HP_ZX1)	+= arch/ia64/dig/
-core-$(CONFIG_IA64_SGI_SN)	+= arch/ia64/sn/kernel/ \
-				   arch/ia64/sn/io/ \
-				   arch/ia64/sn/io/sn2/ \
-				   arch/ia64/sn/io/sn2/pcibr/ \
-				   arch/ia64/sn/kernel/sn2/
+core-$(CONFIG_IA64_SGI_SN)	+= arch/ia64/sn/
+
 drivers-$(CONFIG_PCI)		+= arch/ia64/pci/
 drivers-$(CONFIG_IA64_HP_SIM)	+= arch/ia64/hp/sim/
 drivers-$(CONFIG_IA64_HP_ZX1)	+= arch/ia64/hp/common/ arch/ia64/hp/zx1/

arch/ia64/boot/Makefile

@@ -9,7 +9,6 @@
 #
 
 targets-$(CONFIG_IA64_HP_SIM)  += bootloader
-targets-$(CONFIG_IA64_GENERIC) += bootloader
 targets := vmlinux.bin vmlinux.gz $(targets-y)
 
 quiet_cmd_cptotop = LN      $@

arch/ia64/hp/common/sba_iommu.c

@@ -1497,7 +1497,7 @@ static int sba_proc_info(char *buf, char **start, off_t offset, int len)
 		ioc = &sba_dev->ioc[0];	/* FIXME: Multi-IOC support! */
 		total_pages = (int) (ioc->res_size << 3); /* 8 bits per byte */
 
-		sprintf(buf, "%s rev %d.%d\n", "Hewlett Packard zx1 SBA",
+		sprintf(buf, "%s rev %d.%d\n", "Hewlett-Packard zx1 SBA",
 			((sba_dev->hw_rev >> 4) & 0xF), (sba_dev->hw_rev & 0xF));
 		sprintf(buf, "%sIO PDIR size    : %d bytes (%d entries)\n", buf,
 			(int) ((ioc->res_size << 3) * sizeof(u64)), /* 8 bits/byte */ total_pages);

arch/ia64/ia32/ia32_signal.c

@@ -148,6 +148,11 @@ copy_siginfo_to_user32 (siginfo_t32 *to, siginfo_t *from)
 			err |= __put_user(from->si_band, &to->si_band);
 			err |= __put_user(from->si_fd, &to->si_fd);
 			break;
+		case __SI_TIMER >> 16:
+			err |= __put_user(from->si_tid, &to->si_tid);
+			err |= __put_user(from->si_overrun, &to->si_overrun);
+			err |= __put_user(from->si_ptr, &to->si_ptr); /*XXX eric: not sure the size is correct because it contains pointer*/
+			break;
 		/* case __SI_RT: This is not generated by the kernel as of now.  */
 		}
 	}

arch/ia64/ia32/sys_ia32.c

@@ -119,10 +119,8 @@ nargs (unsigned int arg, char **ap)
 
 asmlinkage long
 sys32_execve (char *filename, unsigned int argv, unsigned int envp,
-	      int dummy3, int dummy4, int dummy5, int dummy6, int dummy7,
-	      int stack)
+	      struct pt_regs *regs)
 {
-	struct pt_regs *regs = (struct pt_regs *)&stack;
 	unsigned long old_map_base, old_task_size, tssd;
 	char **av, **ae;
 	int na, ne, len;
@@ -1701,7 +1699,7 @@ sys32_ipc (u32 call, int first, int second, int third, u32 ptr, u32 fifth)
 		return shmctl32(first, second, (void *)AA(ptr));
 
 	      default:
-		return -EINVAL;
+		return -ENOSYS;
 	}
 	return -EINVAL;
 }
@@ -2156,26 +2154,23 @@ sys32_ptrace (int request, pid_t pid, unsigned int addr, unsigned int data,
 	ret = -ESRCH;
 	read_lock(&tasklist_lock);
 	child = find_task_by_pid(pid);
+	if (child)
+		get_task_struct(child);
 	read_unlock(&tasklist_lock);
 	if (!child)
 		goto out;
 	ret = -EPERM;
 	if (pid == 1)		/* no messing around with init! */
-		goto out;
+		goto out_tsk;
 
 	if (request == PTRACE_ATTACH) {
 		ret = sys_ptrace(request, pid, addr, data, arg4, arg5, arg6, arg7, stack);
-		goto out;
-	}
-	ret = -ESRCH;
-	if (!(child->ptrace & PT_PTRACED))
-		goto out;
-	if (child->state != TASK_STOPPED) {
-		if (request != PTRACE_KILL)
-			goto out;
+		goto out_tsk;
 	}
-	if (child->parent != current)
-		goto out;
+
+	ret = ptrace_check_attach(child, request == PTRACE_KILL);
+	if (ret < 0)
+		goto out_tsk;
 
 	switch (request) {
 	      case PTRACE_PEEKTEXT:
@@ -2185,12 +2180,12 @@ sys32_ptrace (int request, pid_t pid, unsigned int addr, unsigned int data,
 			ret = put_user(value, (unsigned int *) A(data));
 		else
 			ret = -EIO;
-		goto out;
+		goto out_tsk;
 
 	      case PTRACE_POKETEXT:
 	      case PTRACE_POKEDATA:	/* write the word at location addr */
 		ret = ia32_poke(regs, child, addr, data);
-		goto out;
+		goto out_tsk;
 
 	      case PTRACE_PEEKUSR:	/* read word at addr in USER area */
 		ret = -EIO;
@@ -2265,6 +2260,8 @@ sys32_ptrace (int request, pid_t pid, unsigned int addr, unsigned int data,
 		break;
 
 	}
+  out_tsk:
+	free_task_struct(child);
   out:
 	unlock_kernel();
 	return ret;

arch/ia64/kernel/Makefile

@@ -4,16 +4,15 @@
 
 extra-y	:= head.o init_task.o
 
-obj-y := acpi.o entry.o gate.o efi.o efi_stub.o ia64_ksyms.o \
-	 irq.o irq_ia64.o irq_lsapic.o ivt.o \
-	 machvec.o pal.o process.o perfmon.o ptrace.o sal.o \
-	 semaphore.o setup.o	\
-	 signal.o sys_ia64.o traps.o time.o unaligned.o unwind.o
+obj-y := acpi.o entry.o efi.o efi_stub.o gate.o ia64_ksyms.o irq.o irq_ia64.o irq_lsapic.o	\
+	 ivt.o machvec.o pal.o perfmon.o process.o ptrace.o sal.o semaphore.o setup.o signal.o	\
+	 sys_ia64.o time.o traps.o unaligned.o unwind.o
 
+obj-$(CONFIG_EFI_VARS)		+= efivars.o
 obj-$(CONFIG_FSYS)		+= fsys.o
-obj-$(CONFIG_IOSAPIC) += iosapic.o
+obj-$(CONFIG_IA64_BRL_EMU)	+= brl_emu.o
+obj-$(CONFIG_IA64_MCA)		+= mca.o mca_asm.o
 obj-$(CONFIG_IA64_PALINFO)	+= palinfo.o
-obj-$(CONFIG_EFI_VARS) += efivars.o
+obj-$(CONFIG_IOSAPIC)		+= iosapic.o
+obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_SMP)		+= smp.o smpboot.o
-obj-$(CONFIG_IA64_MCA) += mca.o mca_asm.o
-obj-$(CONFIG_IA64_BRL_EMU) += brl_emu.o

arch/ia64/kernel/acpi-ext.c

+/*
+ * arch/ia64/kernel/acpi-ext.c
+ *
+ * Copyright (C) 2003 Hewlett-Packard
+ * Copyright (C) Alex Williamson
+ *
+ * Vendor specific extensions to ACPI.  These are used by both
+ * HP and NEC.
+ */
+
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/acpi.h>
+#include <linux/efi.h>
+
+#include <asm/acpi-ext.h>
+
+/*
+ * Note: Strictly speaking, this is only needed for HP and NEC machines.
+ *	 However, NEC machines identify themselves as DIG-compliant, so there is
+ *	 no easy way to #ifdef this out.
+ */
+acpi_status
+hp_acpi_csr_space (acpi_handle obj, u64 *csr_base, u64 *csr_length)
+{
+	int i, offset = 0;
+	acpi_status status;
+	struct acpi_buffer buf;
+	struct acpi_resource_vendor *res;
+	struct acpi_hp_vendor_long *hp_res;
+	efi_guid_t vendor_guid;
+
+	*csr_base = 0;
+	*csr_length = 0;
+
+	status = acpi_get_crs(obj, &buf);
+	if (ACPI_FAILURE(status)) {
+		printk(KERN_ERR PREFIX "Unable to get _CRS data on object\n");
+		return status;
+	}
+
+	res = (struct acpi_resource_vendor *)acpi_get_crs_type(&buf, &offset, ACPI_RSTYPE_VENDOR);
+	if (!res) {
+		printk(KERN_ERR PREFIX "Failed to find config space for device\n");
+		acpi_dispose_crs(&buf);
+		return AE_NOT_FOUND;
+	}
+
+	hp_res = (struct acpi_hp_vendor_long *)(res->reserved);
+
+	if (res->length != HP_CCSR_LENGTH || hp_res->guid_id != HP_CCSR_TYPE) {
+		printk(KERN_ERR PREFIX "Unknown Vendor data\n");
+		acpi_dispose_crs(&buf);
+		return AE_TYPE; /* Revisit error? */
+	}
+
+	memcpy(&vendor_guid, hp_res->guid, sizeof(efi_guid_t));
+	if (efi_guidcmp(vendor_guid, HP_CCSR_GUID) != 0) {
+		printk(KERN_ERR PREFIX "Vendor GUID does not match\n");
+		acpi_dispose_crs(&buf);
+		return AE_TYPE; /* Revisit error? */
+	}
+
+	for (i = 0 ; i < 8 ; i++) {
+		*csr_base |= ((u64)(hp_res->csr_base[i]) << (i * 8));
+		*csr_length |= ((u64)(hp_res->csr_length[i]) << (i * 8));
+	}
+
+	acpi_dispose_crs(&buf);
+	return AE_OK;
+}

arch/ia64/kernel/acpi.c

@@ -9,7 +9,7 @@
  *  Copyright (C) 2000,2001 J.I. Lee <jung-ik.lee@intel.com>
  *  Copyright (C) 2001 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
  *  Copyright (C) 2001 Jenna Hall <jenna.s.hall@intel.com>
- *  Copyright (C) 2001 Takayoshi Kochi <t-kouchi@cq.jp.nec.com>
+ *  Copyright (C) 2001 Takayoshi Kochi <t-kochi@bq.jp.nec.com>
  *  Copyright (C) 2002 Erich Focht <efocht@ess.nec.de>
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -109,8 +109,6 @@ acpi_get_sysname (void)
 	return "sn2";
 # elif defined (CONFIG_IA64_DIG)
 	return "dig";
-# elif defined (CONFIG_IA64_HP_ZX1)
-	return "hpzx1";
 # else
 #	error Unknown platform.  Fix acpi.c.
 # endif
@@ -176,6 +174,73 @@ acpi_dispose_crs (struct acpi_buffer *buf)
 	kfree(buf->pointer);
 }
 
+void
+acpi_get_crs_addr (struct acpi_buffer *buf, int type, u64 *base, u64 *size, u64 *tra)
+{
+	int offset = 0;
+	struct acpi_resource_address16 *addr16;
+	struct acpi_resource_address32 *addr32;
+	struct acpi_resource_address64 *addr64;
+
+	for (;;) {
+		struct acpi_resource *res = acpi_get_crs_next(buf, &offset);
+		if (!res)
+			return;
+		switch (res->id) {
+			case ACPI_RSTYPE_ADDRESS16:
+				addr16 = (struct acpi_resource_address16 *) &res->data;
+
+				if (type == addr16->resource_type) {
+					*base = addr16->min_address_range;
+					*size = addr16->address_length;
+					*tra = addr16->address_translation_offset;
+					return;
+				}
+				break;
+			case ACPI_RSTYPE_ADDRESS32:
+				addr32 = (struct acpi_resource_address32 *) &res->data;
+				if (type == addr32->resource_type) {
+					*base = addr32->min_address_range;
+					*size = addr32->address_length;
+					*tra = addr32->address_translation_offset;
+					return;
+				}
+				break;
+			case ACPI_RSTYPE_ADDRESS64:
+				addr64 = (struct acpi_resource_address64 *) &res->data;
+				if (type == addr64->resource_type) {
+					*base = addr64->min_address_range;
+					*size = addr64->address_length;
+					*tra = addr64->address_translation_offset;
+					return;
+				}
+				break;
+		}
+	}
+}
+
+int
+acpi_get_addr_space(void *obj, u8 type, u64 *base, u64 *length, u64 *tra)
+{
+	acpi_status status;
+	struct acpi_buffer buf;
+
+	*base = 0;
+	*length = 0;
+	*tra = 0;
+
+	status = acpi_get_crs((acpi_handle)obj, &buf);
+	if (ACPI_FAILURE(status)) {
+		printk(KERN_ERR PREFIX "Unable to get _CRS data on object\n");
+		return status;
+	}
+
+	acpi_get_crs_addr(&buf, type, base, length, tra);
+
+	acpi_dispose_crs(&buf);
+
+	return AE_OK;
+}
 #endif /* CONFIG_ACPI */
 
 #ifdef CONFIG_ACPI_BOOT
@@ -808,6 +873,7 @@ acpi_get_prt (struct pci_vector_struct **vectors, int *count)
 
 	list_for_each(node, &acpi_prt.entries) {
 		entry = (struct acpi_prt_entry *)node;
+		vector[i].segment = entry->id.segment;
 		vector[i].bus    = entry->id.bus;
 		vector[i].pci_id = ((u32) entry->id.device << 16) | 0xffff;
 		vector[i].pin    = entry->pin;

arch/ia64/kernel/entry.S

@@ -91,7 +91,7 @@ ENTRY(ia64_execve)
 END(ia64_execve)
 
 /*
- * sys_clone2(u64 flags, u64 ustack_base, u64 ustack_size, u64 child_tidptr, u64 parent_tidptr,
+ * sys_clone2(u64 flags, u64 ustack_base, u64 ustack_size, u64 parent_tidptr, u64 child_tidptr,
  *	      u64 tls)
  */
 GLOBAL_ENTRY(sys_clone2)
@@ -105,10 +105,10 @@ GLOBAL_ENTRY(sys_clone2)
 	mov out1=in1
 	mov out3=in2
 	tbit.nz p6,p0=in0,CLONE_SETTLS_BIT
-	mov out4=in3	// child_tidptr:  valid only w/CLONE_CHILD_SETTID or CLONE_CHILD_CLEARTID
+	mov out4=in3	// parent_tidptr: valid only w/CLONE_PARENT_SETTID
 	;;
 (p6)	st8 [r2]=in5				// store TLS in r16 for copy_thread()
-	mov out5=in4	// parent_tidptr: valid only w/CLONE_PARENT_SETTID
+	mov out5=in4	// child_tidptr:  valid only w/CLONE_CHILD_SETTID or CLONE_CHILD_CLEARTID
 	adds out2=IA64_SWITCH_STACK_SIZE+16,sp	// out2 = &regs
 	dep out0=0,in0,CLONE_IDLETASK_BIT,1	// out0 = clone_flags & ~CLONE_IDLETASK
 	br.call.sptk.many rp=do_fork
@@ -126,12 +126,12 @@ GLOBAL_ENTRY(sys_clone2)
 END(sys_clone2)
 
 /*
- * sys_clone(u64 flags, u64 ustack_base, u64 user_tid, u64 tls)
+ * sys_clone(u64 flags, u64 ustack_base, u64 parent_tidptr, u64 child_tidptr, u64 tls)
  *	Deprecated.  Use sys_clone2() instead.
  */
 GLOBAL_ENTRY(sys_clone)
 	.prologue ASM_UNW_PRLG_RP|ASM_UNW_PRLG_PFS, ASM_UNW_PRLG_GRSAVE(2)
-	alloc r16=ar.pfs,4,2,5,0
+	alloc r16=ar.pfs,5,2,6,0
 	DO_SAVE_SWITCH_STACK
 	adds r2=PT(R16)+IA64_SWITCH_STACK_SIZE+16,sp
 	mov loc0=rp
@@ -140,9 +140,10 @@ GLOBAL_ENTRY(sys_clone)
 	mov out1=in1
 	mov out3=16				// stacksize (compensates for 16-byte scratch area)
 	tbit.nz p6,p0=in0,CLONE_SETTLS_BIT
-	mov out4=in2				// out4 = user_tid (optional)
+	mov out4=in2	// parent_tidptr: valid only w/CLONE_PARENT_SETTID
 	;;
-(p6)	st8 [r2]=in3				// store TLS in r13 (tp)
+(p6)	st8 [r2]=in4				// store TLS in r13 (tp)
+	mov out5=in3	// child_tidptr:  valid only w/CLONE_CHILD_SETTID or CLONE_CHILD_CLEARTID
 	adds out2=IA64_SWITCH_STACK_SIZE+16,sp	// out2 = &regs
 	dep out0=0,in0,CLONE_IDLETASK_BIT,1	// out0 = clone_flags & ~CLONE_IDLETASK
 	br.call.sptk.many rp=do_fork

arch/ia64/kernel/fsys.S

@@ -533,15 +533,15 @@ fsyscall_table:
 	data8 fsys_fallback_syscall	// epoll_wait		// 1245
 	data8 fsys_fallback_syscall	// restart_syscall
 	data8 fsys_fallback_syscall	// semtimedop
-	data8 fsys_fallback_syscall
-	data8 fsys_fallback_syscall
-	data8 fsys_fallback_syscall				// 1250
-	data8 fsys_fallback_syscall
-	data8 fsys_fallback_syscall
-	data8 fsys_fallback_syscall
-	data8 fsys_fallback_syscall
-	data8 fsys_fallback_syscall				// 1255
-	data8 fsys_fallback_syscall
+	data8 fsys_fallback_syscall	// timer_create
+	data8 fsys_fallback_syscall	// timer_settime
+	data8 fsys_fallback_syscall	// timer_gettime 	// 1250
+	data8 fsys_fallback_syscall	// timer_getoverrun
+	data8 fsys_fallback_syscall	// timer_delete
+	data8 fsys_fallback_syscall	// clock_settime
+	data8 fsys_fallback_syscall	// clock_gettime
+	data8 fsys_fallback_syscall	// clock_getres		// 1255
+	data8 fsys_fallback_syscall	// clock_nanosleep
 	data8 fsys_fallback_syscall
 	data8 fsys_fallback_syscall
 	data8 fsys_fallback_syscall

arch/ia64/kernel/head.S

@@ -733,73 +733,3 @@ SET_REG(b4);
 SET_REG(b5);
 
 #endif /* CONFIG_IA64_BRL_EMU */
-
-#ifdef CONFIG_SMP
-
-	/*
-	 * This routine handles spinlock contention.  It uses a simple exponential backoff
-	 * algorithm to reduce unnecessary bus traffic.  The initial delay is selected from
-	 * the low-order bits of the cycle counter (a cheap "randomizer").  I'm sure this
-	 * could use additional tuning, especially on systems with a large number of CPUs.
-	 * Also, I think the maximum delay should be made a function of the number of CPUs in
-	 * the system. --davidm 00/08/05
-	 *
-	 * WARNING: This is not a normal procedure.  It gets called from C code without
-	 * the compiler knowing about it.  Thus, we must not use any scratch registers
-	 * beyond those that were declared "clobbered" at the call-site (see spin_lock()
-	 * macro).  We may not even use the stacked registers, because that could overwrite
-	 * output registers.  Similarly, we can't use the scratch stack area as it may be
-	 * in use, too.
-	 *
-	 * Inputs:
-	 *	ar.ccv = 0 (and available for use)
-	 *	r28 = available for use
-	 *	r29 = available for use
-	 *	r30 = non-zero (and available for use)
-	 *	r31 = address of lock we're trying to acquire
-	 *	p15 = available for use
-	 */
-
-#	define delay	r28
-#	define timeout	r29
-#	define tmp	r30
-
-GLOBAL_ENTRY(ia64_spinlock_contention)
-	mov tmp=ar.itc
-	;;
-	and delay=0x3f,tmp
-	;;
-
-.retry:	add timeout=tmp,delay
-	shl delay=delay,1
-	;;
-	dep delay=delay,r0,0,13	// limit delay to 8192 cycles
-	;;
-	// delay a little...
-.wait:	sub tmp=tmp,timeout
-	or delay=0xf,delay	// make sure delay is non-zero (otherwise we get stuck with 0)
-	;;
-	cmp.lt p15,p0=tmp,r0
-	mov tmp=ar.itc
-(p15)	br.cond.sptk .wait
-	;;
-	ld4 tmp=[r31]
-	;;
-	cmp.ne p15,p0=tmp,r0
-	mov tmp=ar.itc
-(p15)	br.cond.sptk .retry	// lock is still busy
-	;;
-	// try acquiring lock (we know ar.ccv is still zero!):
-	mov tmp=1
-	;;
-	cmpxchg4.acq tmp=[r31],tmp,ar.ccv
-	;;
-	cmp.eq p15,p0=tmp,r0
-
-	mov tmp=ar.itc
-(p15)	br.ret.sptk.many b7	// got lock -> return
-	br .retry		// still no luck, retry
-
-END(ia64_spinlock_contention)
-
-#endif

arch/ia64/kernel/ia64_ksyms.c

@@ -57,9 +57,7 @@ EXPORT_SYMBOL_NOVERS(__up);
 EXPORT_SYMBOL(clear_page);
 
 #include <asm/processor.h>
-# ifndef CONFIG_NUMA
 EXPORT_SYMBOL(cpu_info__per_cpu);
-# endif
 EXPORT_SYMBOL(kernel_thread);
 
 #include <asm/system.h>
@@ -147,3 +145,19 @@ EXPORT_SYMBOL(machvec_noop);
 EXPORT_SYMBOL(pfm_install_alternate_syswide_subsystem);
 EXPORT_SYMBOL(pfm_remove_alternate_syswide_subsystem);
 #endif
+
+#ifdef CONFIG_NUMA
+#include <asm/numa.h>
+EXPORT_SYMBOL(cpu_to_node_map);
+#endif
+
+#include <asm/unwind.h>
+EXPORT_SYMBOL(unw_init_from_blocked_task);
+EXPORT_SYMBOL(unw_init_running);
+EXPORT_SYMBOL(unw_unwind);
+EXPORT_SYMBOL(unw_unwind_to_user);
+EXPORT_SYMBOL(unw_access_gr);
+EXPORT_SYMBOL(unw_access_br);
+EXPORT_SYMBOL(unw_access_fr);
+EXPORT_SYMBOL(unw_access_ar);
+EXPORT_SYMBOL(unw_access_pr);

arch/ia64/kernel/mca.c

@@ -42,6 +42,10 @@
 #include <linux/smp_lock.h>
 #include <linux/bootmem.h>
 #include <linux/acpi.h>
+#include <linux/timer.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/smp.h>
 
 #include <asm/machvec.h>
 #include <asm/page.h>
@@ -67,7 +71,7 @@ u64				ia64_mca_proc_state_dump[512];
 u64				ia64_mca_stack[1024] __attribute__((aligned(16)));
 u64				ia64_mca_stackframe[32];
 u64				ia64_mca_bspstore[1024];
-u64				ia64_init_stack[KERNEL_STACK_SIZE] __attribute__((aligned(16)));
+u64				ia64_init_stack[KERNEL_STACK_SIZE/8] __attribute__((aligned(16)));
 u64				ia64_mca_sal_data_area[1356];
 u64				ia64_tlb_functional;
 u64				ia64_os_mca_recovery_successful;
@@ -105,6 +109,19 @@ static struct irqaction mca_cpe_irqaction = {
 	.name =		"cpe_hndlr"
 };
 
+#define MAX_CPE_POLL_INTERVAL (15*60*HZ) /* 15 minutes */
+#define MIN_CPE_POLL_INTERVAL (2*60*HZ)  /* 2 minutes */
+#define CMC_POLL_INTERVAL     (1*60*HZ)  /* 1 minute */
+#define CMC_HISTORY_LENGTH    5
+
+static struct timer_list cpe_poll_timer;
+static struct timer_list cmc_poll_timer;
+/*
+ * Start with this in the wrong state so we won't play w/ timers
+ * before the system is ready.
+ */
+static int cmc_polling_enabled = 1;
+
 /*
  *  ia64_mca_log_sal_error_record
  *
@@ -152,7 +169,8 @@ mca_handler_platform (void)
 void
 ia64_mca_cpe_int_handler (int cpe_irq, void *arg, struct pt_regs *ptregs)
 {
-	IA64_MCA_DEBUG("ia64_mca_cpe_int_handler: received interrupt. vector = %#x\n", cpe_irq);
+	IA64_MCA_DEBUG("ia64_mca_cpe_int_handler: received interrupt. CPU:%d vector = %#x\n",
+		       smp_processor_id(), cpe_irq);
 
 	/* Get the CMC error record and log it */
 	ia64_mca_log_sal_error_record(SAL_INFO_TYPE_CPE, 0);
@@ -295,6 +313,60 @@ ia64_mca_cmc_vector_setup (void)
 		       smp_processor_id(), ia64_get_cmcv());
 }
 
+/*
+ * ia64_mca_cmc_vector_disable
+ *
+ *  Mask the corrected machine check vector register in the processor.
+ *  This function is invoked on a per-processor basis.
+ *
+ * Inputs
+ *      dummy(unused)
+ *
+ * Outputs
+ *	None
+ */
+void
+ia64_mca_cmc_vector_disable (void *dummy)
+{
+	cmcv_reg_t	cmcv;
+	
+	cmcv = (cmcv_reg_t)ia64_get_cmcv();
+
+	cmcv.cmcv_mask = 1; /* Mask/disable interrupt */
+	ia64_set_cmcv(cmcv.cmcv_regval);
+
+	IA64_MCA_DEBUG("ia64_mca_cmc_vector_disable: CPU %d corrected "
+		       "machine check vector %#x disabled.\n",
+		       smp_processor_id(), cmcv.cmcv_vector);
+}
+
+/*
+ * ia64_mca_cmc_vector_enable
+ *
+ *  Unmask the corrected machine check vector register in the processor.
+ *  This function is invoked on a per-processor basis.
+ *
+ * Inputs
+ *      dummy(unused)
+ *
+ * Outputs
+ *	None
+ */
+void
+ia64_mca_cmc_vector_enable (void *dummy)
+{
+	cmcv_reg_t	cmcv;
+	
+	cmcv = (cmcv_reg_t)ia64_get_cmcv();
+
+	cmcv.cmcv_mask = 0; /* Unmask/enable interrupt */
+	ia64_set_cmcv(cmcv.cmcv_regval);
+
+	IA64_MCA_DEBUG("ia64_mca_cmc_vector_enable: CPU %d corrected "
+		       "machine check vector %#x enabled.\n",
+		       smp_processor_id(), cmcv.cmcv_vector);
+}
+
 
 #if defined(MCA_TEST)
 
@@ -396,7 +468,7 @@ ia64_mca_init(void)
 					 SAL_MC_PARAM_MECHANISM_INT,
 					 IA64_MCA_RENDEZ_VECTOR,
 					 IA64_MCA_RENDEZ_TIMEOUT,
-					 0)))
+					 SAL_MC_PARAM_RZ_ALWAYS)))
 	{
 		printk(KERN_ERR "ia64_mca_init: Failed to register rendezvous interrupt "
 		       "with SAL.  rc = %ld\n", rc);
@@ -494,9 +566,7 @@ ia64_mca_init(void)
 					setup_irq(irq, &mca_cpe_irqaction);
 				}
 			ia64_mca_register_cpev(cpev);
-		} else
-			printk(KERN_ERR
-			       "ia64_mca_init: Failed to get routed CPEI vector from ACPI.\n");
+		}
 	}
 
 	/* Initialize the areas set aside by the OS to buffer the
@@ -610,14 +680,11 @@ void
 ia64_mca_rendez_int_handler(int rendez_irq, void *arg, struct pt_regs *ptregs)
 {
 	unsigned long flags;
-	int cpu = 0;
+	int cpu = smp_processor_id();
 
 	/* Mask all interrupts */
 	local_irq_save(flags);
 
-#ifdef CONFIG_SMP
-	cpu = cpu_logical_id(hard_smp_processor_id());
-#endif
 	ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_DONE;
 	/* Register with the SAL monarch that the slave has
 	 * reached SAL
@@ -751,11 +818,68 @@ ia64_mca_ucmc_handler(void)
 void
 ia64_mca_cmc_int_handler(int cmc_irq, void *arg, struct pt_regs *ptregs)
 {
+	static unsigned long	cmc_history[CMC_HISTORY_LENGTH];
+	static int		index;
+	static spinlock_t	cmc_history_lock = SPIN_LOCK_UNLOCKED;
+
 	IA64_MCA_DEBUG("ia64_mca_cmc_int_handler: received interrupt vector = %#x on CPU %d\n",
 		       cmc_irq, smp_processor_id());
 
 	/* Get the CMC error record and log it */
 	ia64_mca_log_sal_error_record(SAL_INFO_TYPE_CMC, 0);
+
+	spin_lock(&cmc_history_lock);
+	if (!cmc_polling_enabled) {
+		int i, count = 1; /* we know 1 happened now */
+		unsigned long now = jiffies;
+		
+		for (i = 0; i < CMC_HISTORY_LENGTH; i++) {
+			if (now - cmc_history[i] <= HZ)
+				count++;
+		}
+
+		IA64_MCA_DEBUG(KERN_INFO "CMC threshold %d/%d\n", count, CMC_HISTORY_LENGTH);
+		if (count >= CMC_HISTORY_LENGTH) {
+			/*
+			 * CMC threshold exceeded, clear the history
+			 * so we have a fresh start when we return
+			 */
+			for (index = 0 ; index < CMC_HISTORY_LENGTH; index++)
+				cmc_history[index] = 0;
+			index = 0;
+
+			/* Switch to polling mode */
+			cmc_polling_enabled = 1;
+
+			/*
+			 * Unlock & enable interrupts  before
+			 * smp_call_function or risk deadlock
+			 */
+			spin_unlock(&cmc_history_lock);
+			ia64_mca_cmc_vector_disable(NULL);
+
+			local_irq_enable();
+			smp_call_function(ia64_mca_cmc_vector_disable, NULL, 1, 1);
+
+			/*
+			 * Corrected errors will still be corrected, but
+			 * make sure there's a log somewhere that indicates
+			 * something is generating more than we can handle.
+			 */
+			printk(KERN_WARNING "ia64_mca_cmc_int_handler: WARNING: Switching to polling CMC handler, error records may be lost\n");
+			
+
+			mod_timer(&cmc_poll_timer, jiffies + CMC_POLL_INTERVAL);
+
+			/* lock already released, get out now */
+			return;
+		} else {
+			cmc_history[index++] = now;
+			if (index == CMC_HISTORY_LENGTH)
+				index = 0;
+		}
+	}
+	spin_unlock(&cmc_history_lock);
 }
 
 /*
@@ -768,6 +892,7 @@ typedef struct ia64_state_log_s
 {
 	spinlock_t	isl_lock;
 	int		isl_index;
+	unsigned long	isl_count;
 	ia64_err_rec_t  *isl_log[IA64_MAX_LOGS]; /* need space to store header + error log */
 } ia64_state_log_t;
 
@@ -784,11 +909,145 @@ static ia64_state_log_t ia64_state_log[IA64_MAX_LOG_TYPES];
 #define IA64_LOG_NEXT_INDEX(it)    ia64_state_log[it].isl_index
 #define IA64_LOG_CURR_INDEX(it)    1 - ia64_state_log[it].isl_index
 #define IA64_LOG_INDEX_INC(it) \
-    ia64_state_log[it].isl_index = 1 - ia64_state_log[it].isl_index
+    {ia64_state_log[it].isl_index = 1 - ia64_state_log[it].isl_index; \
+    ia64_state_log[it].isl_count++;}
 #define IA64_LOG_INDEX_DEC(it) \
     ia64_state_log[it].isl_index = 1 - ia64_state_log[it].isl_index
 #define IA64_LOG_NEXT_BUFFER(it)   (void *)((ia64_state_log[it].isl_log[IA64_LOG_NEXT_INDEX(it)]))
 #define IA64_LOG_CURR_BUFFER(it)   (void *)((ia64_state_log[it].isl_log[IA64_LOG_CURR_INDEX(it)]))
+#define IA64_LOG_COUNT(it)         ia64_state_log[it].isl_count
+
+/*
+ *  ia64_mca_cmc_int_caller
+ *
+ * 	Call CMC interrupt handler, only purpose is to have a
+ * 	smp_call_function callable entry.
+ *
+ * Inputs   :	dummy(unused)
+ * Outputs  :	None
+ * */
+static void
+ia64_mca_cmc_int_caller(void *dummy)
+{
+	ia64_mca_cmc_int_handler(0, NULL, NULL);
+}
+
+/*
+ *  ia64_mca_cmc_poll
+ *
+ *	Poll for Corrected Machine Checks (CMCs)
+ *
+ * Inputs   :   dummy(unused)
+ * Outputs  :   None
+ *
+ */
+static void
+ia64_mca_cmc_poll (unsigned long dummy)
+{
+	int start_count;
+
+	start_count = IA64_LOG_COUNT(SAL_INFO_TYPE_CMC);
+
+	/* Call the interrupt handler */
+	smp_call_function(ia64_mca_cmc_int_caller, NULL, 1, 1);
+	local_irq_disable();
+	ia64_mca_cmc_int_caller(NULL);
+	local_irq_enable();
+
+	/*
+	 * If no log recored, switch out of polling mode.
+	 */
+	if (start_count == IA64_LOG_COUNT(SAL_INFO_TYPE_CMC)) {
+		printk(KERN_WARNING "ia64_mca_cmc_poll: Returning to interrupt driven CMC handler\n");
+		cmc_polling_enabled = 0;
+		smp_call_function(ia64_mca_cmc_vector_enable, NULL, 1, 1);
+		ia64_mca_cmc_vector_enable(NULL);
+	} else {
+		mod_timer(&cmc_poll_timer, jiffies + CMC_POLL_INTERVAL);
+	}
+}
+
+/*
+ *  ia64_mca_cpe_int_caller
+ *
+ * 	Call CPE interrupt handler, only purpose is to have a
+ * 	smp_call_function callable entry.
+ *
+ * Inputs   :	dummy(unused)
+ * Outputs  :	None
+ * */
+static void
+ia64_mca_cpe_int_caller(void *dummy)
+{
+	ia64_mca_cpe_int_handler(0, NULL, NULL);
+}
+
+/*
+ *  ia64_mca_cpe_poll
+ *
+ *	Poll for Corrected Platform Errors (CPEs), dynamically adjust
+ *	polling interval based on occurance of an event.
+ *
+ * Inputs   :   dummy(unused)
+ * Outputs  :   None
+ *
+ */
+static void
+ia64_mca_cpe_poll (unsigned long dummy)
+{
+	int start_count;
+	static int poll_time = MAX_CPE_POLL_INTERVAL;
+
+	start_count = IA64_LOG_COUNT(SAL_INFO_TYPE_CPE);
+
+	/* Call the interrupt handler */
+	smp_call_function(ia64_mca_cpe_int_caller, NULL, 1, 1);
+	local_irq_disable();
+	ia64_mca_cpe_int_caller(NULL);
+	local_irq_enable();
+
+	/*
+	 * If a log was recorded, increase our polling frequency,
+	 * otherwise, backoff.
+	 */
+	if (start_count != IA64_LOG_COUNT(SAL_INFO_TYPE_CPE)) {
+		poll_time = max(MIN_CPE_POLL_INTERVAL, poll_time/2);
+	} else {
+		poll_time = min(MAX_CPE_POLL_INTERVAL, poll_time * 2);
+	}
+	mod_timer(&cpe_poll_timer, jiffies + poll_time);
+}
+
+/*
+ * ia64_mca_late_init
+ *
+ *	Opportunity to setup things that require initialization later
+ *	than ia64_mca_init.  Setup a timer to poll for CPEs if the
+ *	platform doesn't support an interrupt driven mechanism.
+ *
+ *  Inputs  :   None
+ *  Outputs :   Status
+ */
+static int __init
+ia64_mca_late_init(void)
+{
+	init_timer(&cmc_poll_timer);
+	cmc_poll_timer.function = ia64_mca_cmc_poll;
+
+	/* Reset to the correct state */
+	cmc_polling_enabled = 0;
+
+	init_timer(&cpe_poll_timer);
+	cpe_poll_timer.function = ia64_mca_cpe_poll;
+
+	/* If platform doesn't support CPEI, get the timer going. */
+	if (acpi_request_vector(ACPI_INTERRUPT_CPEI) < 0)
+		ia64_mca_cpe_poll(0UL);
+
+	return 0;
+}
+
+device_initcall(ia64_mca_late_init);
 
 /*
  * C portion of the OS INIT handler
@@ -949,7 +1208,6 @@ ia64_log_get(int sal_info_type, prfunc_t prfunc)
 		return total_len;
 	} else {
 		IA64_LOG_UNLOCK(sal_info_type);
-		prfunc("ia64_log_get: No SAL error record available for type %d\n", sal_info_type);
 		return 0;
 	}
 }

arch/ia64/kernel/module.c

+/*
+ * IA-64-specific support for kernel module loader.
+ *
+ * Copyright (C) 2003 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ *
+ * Loosely based on patch by Rusty Russell.
+ */
+
+/* relocs tested so far:
+
+   DIR64LSB
+   FPTR64LSB
+   GPREL22
+   LDXMOV
+   LDXMOV
+   LTOFF22
+   LTOFF22X
+   LTOFF22X
+   LTOFF_FPTR22
+   PCREL21B
+   PCREL64LSB
+   SECREL32LSB
+   SEGREL64LSB
+ */
+
+#include <linux/config.h>
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/elf.h>
+#include <linux/moduleloader.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
+
+#include <asm/unaligned.h>
+
+#define ARCH_MODULE_DEBUG 0
+
+#if ARCH_MODULE_DEBUG
+# define DEBUGP printk
+# define inline
+#else
+# define DEBUGP(fmt , a...)
+#endif
+
+#ifdef CONFIG_ITANIUM
+# define USE_BRL	0
+#else
+# define USE_BRL	1
+#endif
+
+#define MAX_LTOFF	((uint64_t) (1 << 22))	/* max. allowable linkage-table offset */
+
+/* Define some relocation helper macros/types: */
+
+#define FORMAT_SHIFT	0
+#define FORMAT_BITS	3
+#define FORMAT_MASK	((1 << FORMAT_BITS) - 1)
+#define VALUE_SHIFT	3
+#define VALUE_BITS	5
+#define VALUE_MASK	((1 << VALUE_BITS) - 1)
+
+enum reloc_target_format {
+	/* direct encoded formats: */
+	RF_NONE = 0,
+	RF_INSN14 = 1,
+	RF_INSN22 = 2,
+	RF_INSN64 = 3,
+	RF_32MSB = 4,
+	RF_32LSB = 5,
+	RF_64MSB = 6,
+	RF_64LSB = 7,
+
+	/* formats that cannot be directly decoded: */
+	RF_INSN60,
+	RF_INSN21B,	/* imm21 form 1 */
+	RF_INSN21M,	/* imm21 form 2 */
+	RF_INSN21F	/* imm21 form 3 */
+};
+
+enum reloc_value_formula {
+	RV_DIRECT = 4,		/* S + A */
+	RV_GPREL = 5,		/* @gprel(S + A) */
+	RV_LTREL = 6,		/* @ltoff(S + A) */
+	RV_PLTREL = 7,		/* @pltoff(S + A) */
+	RV_FPTR = 8,		/* @fptr(S + A) */
+	RV_PCREL = 9,		/* S + A - P */
+	RV_LTREL_FPTR = 10,	/* @ltoff(@fptr(S + A)) */
+	RV_SEGREL = 11,		/* @segrel(S + A) */
+	RV_SECREL = 12,		/* @secrel(S + A) */
+	RV_BDREL = 13,		/* BD + A */
+	RV_LTV = 14,		/* S + A (like RV_DIRECT, except frozen at static link-time) */
+	RV_PCREL2 = 15,		/* S + A - P */
+	RV_SPECIAL = 16,	/* various (see below) */
+	RV_RSVD17 = 17,
+	RV_TPREL = 18,		/* @tprel(S + A) */
+	RV_LTREL_TPREL = 19,	/* @ltoff(@tprel(S + A)) */
+	RV_DTPMOD = 20,		/* @dtpmod(S + A) */
+	RV_LTREL_DTPMOD = 21,	/* @ltoff(@dtpmod(S + A)) */
+	RV_DTPREL = 22,		/* @dtprel(S + A) */
+	RV_LTREL_DTPREL = 23,	/* @ltoff(@dtprel(S + A)) */
+	RV_RSVD24 = 24,
+	RV_RSVD25 = 25,
+	RV_RSVD26 = 26,
+	RV_RSVD27 = 27
+	/* 28-31 reserved for implementation-specific purposes.  */
+};
+
+#define N(reloc)	[R_IA64_##reloc] = #reloc
+
+static const char *reloc_name[256] = {
+	N(NONE),		N(IMM14),		N(IMM22),		N(IMM64),
+	N(DIR32MSB),		N(DIR32LSB),		N(DIR64MSB),		N(DIR64LSB),
+	N(GPREL22),		N(GPREL64I),		N(GPREL32MSB),		N(GPREL32LSB),
+	N(GPREL64MSB),		N(GPREL64LSB),		N(LTOFF22),		N(LTOFF64I),
+	N(PLTOFF22),		N(PLTOFF64I),		N(PLTOFF64MSB),		N(PLTOFF64LSB),
+	N(FPTR64I),		N(FPTR32MSB),		N(FPTR32LSB),		N(FPTR64MSB),
+	N(FPTR64LSB),		N(PCREL60B),		N(PCREL21B),		N(PCREL21M),
+	N(PCREL21F),		N(PCREL32MSB),		N(PCREL32LSB),		N(PCREL64MSB),
+	N(PCREL64LSB),		N(LTOFF_FPTR22),	N(LTOFF_FPTR64I),	N(LTOFF_FPTR32MSB),
+	N(LTOFF_FPTR32LSB),	N(LTOFF_FPTR64MSB),	N(LTOFF_FPTR64LSB),	N(SEGREL32MSB),
+	N(SEGREL32LSB),		N(SEGREL64MSB),		N(SEGREL64LSB),		N(SECREL32MSB),
+	N(SECREL32LSB),		N(SECREL64MSB),		N(SECREL64LSB),		N(REL32MSB),
+	N(REL32LSB),		N(REL64MSB),		N(REL64LSB),		N(LTV32MSB),
+	N(LTV32LSB),		N(LTV64MSB),		N(LTV64LSB),		N(PCREL21BI),
+	N(PCREL22),		N(PCREL64I),		N(IPLTMSB),		N(IPLTLSB),
+	N(COPY),		N(LTOFF22X),		N(LDXMOV),		N(TPREL14),
+	N(TPREL22),		N(TPREL64I),		N(TPREL64MSB),		N(TPREL64LSB),
+	N(LTOFF_TPREL22),	N(DTPMOD64MSB),		N(DTPMOD64LSB),		N(LTOFF_DTPMOD22),
+	N(DTPREL14),		N(DTPREL22),		N(DTPREL64I),		N(DTPREL32MSB),
+	N(DTPREL32LSB),		N(DTPREL64MSB),		N(DTPREL64LSB),		N(LTOFF_DTPREL22)
+};
+
+#undef N
+
+struct got_entry {
+	uint64_t val;
+};
+
+struct fdesc {
+	uint64_t ip;
+	uint64_t gp;
+};
+
+/* Opaque struct for insns, to protect against derefs. */
+struct insn;
+
+static inline uint64_t
+bundle (const struct insn *insn)
+{
+	return (uint64_t) insn & ~0xfUL;
+}
+
+static inline int
+slot (const struct insn *insn)
+{
+	return (uint64_t) insn & 0x3;
+}
+
+/* Patch instruction with "val" where "mask" has 1 bits. */
+static void
+apply (struct insn *insn, uint64_t mask, uint64_t val)
+{
+	uint64_t m0, m1, v0, v1, b0, b1, *b = (uint64_t *) bundle(insn);
+#	define insn_mask ((1UL << 41) - 1)
+	unsigned long shift;
+
+	b0 = b[0]; b1 = b[1];
+	shift = 5 + 41 * slot(insn); /* 5 bits of template, then 3 x 41-bit instructions */
+	if (shift >= 64) {
+		m1 = mask << (shift - 64);
+		v1 = val << (shift - 64);
+	} else {
+		m0 = mask << shift; m1 = mask >> (64 - shift);
+		v0 = val  << shift; v1 = val >> (64 - shift);
+		b[0] = (b0 & ~m0) | (v0 & m0);
+	}
+	b[1] = (b1 & ~m1) | (v1 & m1);
+}
+
+static int
+apply_imm64 (struct module *mod, struct insn *insn, uint64_t val)
+{
+	if (slot(insn) != 2) {
+		printk(KERN_ERR "%s: illegal slot number %d for IMM64\n",
+		       mod->name, slot(insn));
+		return 0;
+	}
+	apply(insn, 0x01fffefe000, (  ((val & 0x8000000000000000) >> 27) /* bit 63 -> 36 */
+				    | ((val & 0x0000000000200000) <<  0) /* bit 21 -> 21 */
+				    | ((val & 0x00000000001f0000) <<  6) /* bit 16 -> 22 */
+				    | ((val & 0x000000000000ff80) << 20) /* bit  7 -> 27 */
+				    | ((val & 0x000000000000007f) << 13) /* bit  0 -> 13 */));
+	apply((void *) insn - 1, 0x1ffffffffff, val >> 22);
+	return 1;
+}
+
+static int
+apply_imm60 (struct module *mod, struct insn *insn, uint64_t val)
+{
+	if (slot(insn) != 2) {
+		printk(KERN_ERR "%s: illegal slot number %d for IMM60\n",
+		       mod->name, slot(insn));
+		return 0;
+	}
+	if (val + ((uint64_t) 1 << 59) >= (1UL << 60)) {
+		printk(KERN_ERR "%s: value %ld out of IMM60 range\n", mod->name, (int64_t) val);
+		return 0;
+	}
+	apply(insn, 0x011ffffe000, (  ((val & 0x1000000000000000) >> 24) /* bit 60 -> 36 */
+				    | ((val & 0x00000000000fffff) << 13) /* bit  0 -> 13 */));
+	apply((void *) insn - 1, 0x1fffffffffc, val >> 18);
+	return 1;
+}
+
+static int
+apply_imm22 (struct module *mod, struct insn *insn, uint64_t val)
+{
+	if (val + (1 << 21) >= (1 << 22)) {
+		printk(KERN_ERR "%s: value %li out of IMM22 range\n", mod->name, (int64_t)val);
+		return 0;
+	}
+	apply(insn, 0x01fffcfe000, (  ((val & 0x200000) << 15) /* bit 21 -> 36 */
+				    | ((val & 0x1f0000)	<<  6) /* bit 16 -> 22 */
+				    | ((val & 0x00ff80) << 20) /* bit  7 -> 27 */
+				    | ((val & 0x00007f)	<< 13) /* bit  0 -> 13 */));
+	return 1;
+}
+
+static int
+apply_imm21b (struct module *mod, struct insn *insn, uint64_t val)
+{
+	if (val + (1 << 20) >= (1 << 21)) {
+		printk(KERN_ERR "%s: value %li out of IMM21b range\n", mod->name, (int64_t)val);
+		return 0;
+	}
+	apply(insn, 0x11ffffe000, (  ((val & 0x100000) << 16) /* bit 20 -> 36 */
+				   | ((val & 0x0fffff) << 13) /* bit  0 -> 13 */));
+	return 1;
+}
+
+#if USE_BRL
+
+struct plt_entry {
+	/* Three instruction bundles in PLT. */
+ 	unsigned char bundle[2][16];
+};
+
+static const struct plt_entry ia64_plt_template = {
+	{
+		{
+			0x04, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MLX] nop.m 0 */
+			0x00, 0x00, 0x00, 0x00, 0x00, 0x20, /*	     movl gp=TARGET_GP */
+			0x00, 0x00, 0x00, 0x60
+		},
+		{
+			0x05, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MLX] nop.m 0 */
+			0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /*	     brl.many gp=TARGET_GP */
+			0x08, 0x00, 0x00, 0xc0
+		}
+	}
+};
+
+static int
+patch_plt (struct module *mod, struct plt_entry *plt, long target_ip, unsigned long target_gp)
+{
+	if (apply_imm64(mod, (struct insn *) (plt->bundle[0] + 2), target_gp)
+	    && apply_imm60(mod, (struct insn *) (plt->bundle[1] + 2),
+			   (target_ip - (int64_t) plt->bundle[1]) / 16))
+		return 1;
+	return 0;
+}
+
+unsigned long
+plt_target (struct plt_entry *plt)
+{
+	uint64_t b0, b1, *b = (uint64_t *) plt->bundle[1];
+	long off;
+
+	b0 = b[0]; b1 = b[1];
+	off = (  ((b1 & 0x00fffff000000000) >> 36)		/* imm20b -> bit 0 */
+	       | ((b0 >> 48) << 20) | ((b1 & 0x7fffff) << 36)	/* imm39 -> bit 20 */
+	       | ((b1 & 0x0800000000000000) << 1));		/* i -> bit 60 */
+	return (long) plt->bundle[1] + 16*off;
+}
+
+#else /* !USE_BRL */
+
+struct plt_entry {
+	/* Three instruction bundles in PLT. */
+ 	unsigned char bundle[3][16];
+};
+
+static const struct plt_entry ia64_plt_template = {
+	{
+		{
+			0x05, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MLX] nop.m 0 */
+			0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /*	     movl r16=TARGET_IP */
+			0x02, 0x00, 0x00, 0x60
+		},
+		{
+			0x04, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MLX] nop.m 0 */
+			0x00, 0x00, 0x00, 0x00, 0x00, 0x20, /*	     movl gp=TARGET_GP */
+			0x00, 0x00, 0x00, 0x60
+		},
+		{
+			0x11, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MIB] nop.m 0 */
+			0x60, 0x80, 0x04, 0x80, 0x03, 0x00, /*	     mov b6=r16 */
+			0x60, 0x00, 0x80, 0x00		    /*	     br.few b6 */
+		}
+	}
+};
+
+static int
+patch_plt (struct module *mod, struct plt_entry *plt, long target_ip, unsigned long target_gp)
+{
+	if (apply_imm64(mod, (struct insn *) (plt->bundle[0] + 2), target_ip)
+	    && apply_imm64(mod, (struct insn *) (plt->bundle[1] + 2), target_gp))
+		return 1;
+	return 0;
+}
+
+unsigned long
+plt_target (struct plt_entry *plt)
+{
+	uint64_t b0, b1, *b = (uint64_t *) plt->bundle[0];
+
+	b0 = b[0]; b1 = b[1];
+	return (  ((b1 & 0x000007f000000000) >> 36)		/* imm7b -> bit 0 */
+		| ((b1 & 0x07fc000000000000) >> 43)		/* imm9d -> bit 7 */
+		| ((b1 & 0x0003e00000000000) >> 29)		/* imm5c -> bit 16 */
+		| ((b1 & 0x0000100000000000) >> 23)		/* ic -> bit 21 */
+		| ((b0 >> 46) << 22) | ((b1 & 0x7fffff) << 40)	/* imm41 -> bit 22 */
+		| ((b1 & 0x0800000000000000) <<  4));		/* i -> bit 63 */
+}
+
+#endif /* !USE_BRL */
+
+void *
+module_alloc (unsigned long size)
+{
+	if (!size)
+		return NULL;
+	return vmalloc(size);
+}
+
+void
+module_free (struct module *mod, void *module_region)
+{
+	vfree(module_region);
+}
+
+/* Have we already seen one of these relocations? */
+/* FIXME: we could look in other sections, too --RR */
+static int
+duplicate_reloc (const Elf64_Rela *rela, unsigned int num)
+{
+	unsigned int i;
+
+	for (i = 0; i < num; i++) {
+		if (rela[i].r_info == rela[num].r_info && rela[i].r_addend == rela[num].r_addend)
+			return 1;
+	}
+	return 0;
+}
+
+/* Count how many GOT entries we may need */
+static unsigned int
+count_gots (const Elf64_Rela *rela, unsigned int num)
+{
+	unsigned int i, ret = 0;
+
+	/* Sure, this is order(n^2), but it's usually short, and not
+           time critical */
+	for (i = 0; i < num; i++) {
+		switch (ELF64_R_TYPE(rela[i].r_info)) {
+		      case R_IA64_LTOFF22:
+		      case R_IA64_LTOFF22X:
+		      case R_IA64_LTOFF64I:
+		      case R_IA64_LTOFF_FPTR22:
+		      case R_IA64_LTOFF_FPTR64I:
+		      case R_IA64_LTOFF_FPTR32MSB:
+		      case R_IA64_LTOFF_FPTR32LSB:
+		      case R_IA64_LTOFF_FPTR64MSB:
+		      case R_IA64_LTOFF_FPTR64LSB:
+			if (!duplicate_reloc(rela, i))
+				ret++;
+			break;
+		}
+	}
+	return ret;
+}
+
+/* Count how many PLT entries we may need */
+static unsigned int
+count_plts (const Elf64_Rela *rela, unsigned int num)
+{
+	unsigned int i, ret = 0;
+
+	/* Sure, this is order(n^2), but it's usually short, and not
+           time critical */
+	for (i = 0; i < num; i++) {
+		switch (ELF64_R_TYPE(rela[i].r_info)) {
+		      case R_IA64_PCREL21B:
+		      case R_IA64_PLTOFF22:
+		      case R_IA64_PLTOFF64I:
+		      case R_IA64_PLTOFF64MSB:
+		      case R_IA64_PLTOFF64LSB:
+		      case R_IA64_IPLTMSB:
+		      case R_IA64_IPLTLSB:
+			if (!duplicate_reloc(rela, i))
+				ret++;
+			break;
+		}
+	}
+	return ret;
+}
+
+/* We need to create an function-descriptors for any internal function
+   which is referenced. */
+static unsigned int
+count_fdescs (const Elf64_Rela *rela, unsigned int num)
+{
+	unsigned int i, ret = 0;
+
+	/* Sure, this is order(n^2), but it's usually short, and not time critical.  */
+	for (i = 0; i < num; i++) {
+		switch (ELF64_R_TYPE(rela[i].r_info)) {
+		      case R_IA64_FPTR64I:
+		      case R_IA64_FPTR32LSB:
+		      case R_IA64_FPTR32MSB:
+		      case R_IA64_FPTR64LSB:
+		      case R_IA64_FPTR64MSB:
+		      case R_IA64_LTOFF_FPTR22:
+		      case R_IA64_LTOFF_FPTR32LSB:
+		      case R_IA64_LTOFF_FPTR32MSB:
+		      case R_IA64_LTOFF_FPTR64I:
+		      case R_IA64_LTOFF_FPTR64LSB:
+		      case R_IA64_LTOFF_FPTR64MSB:
+		      case R_IA64_IPLTMSB:
+		      case R_IA64_IPLTLSB:
+			/*
+			 * Jumps to static functions sometimes go straight to their
+			 * offset.  Of course, that may not be possible if the jump is
+			 * from init -> core or vice. versa, so we need to generate an
+			 * FDESC (and PLT etc) for that.
+			 */
+		      case R_IA64_PCREL21B:
+			if (!duplicate_reloc(rela, i))
+				ret++;
+			break;
+		}
+	}
+	return ret;
+}
+
+int
+module_frob_arch_sections (Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings,
+			   struct module *mod)
+{
+	unsigned long core_plts = 0, init_plts = 0, gots = 0, fdescs = 0;
+	Elf64_Shdr *s, *sechdrs_end = sechdrs + ehdr->e_shnum;
+
+	/*
+	 * To store the PLTs and function-descriptors, we expand the .text section for
+	 * core module-code and the .init.text section for initialization code.
+	 */
+	for (s = sechdrs; s < sechdrs_end; ++s)
+		if (strcmp(".core.plt", secstrings + s->sh_name) == 0)
+			mod->arch.core_plt = s;
+		else if (strcmp(".init.plt", secstrings + s->sh_name) == 0)
+			mod->arch.init_plt = s;
+		else if (strcmp(".got", secstrings + s->sh_name) == 0)
+			mod->arch.got = s;
+		else if (strcmp(".opd", secstrings + s->sh_name) == 0)
+			mod->arch.opd = s;
+		else if (strcmp(".IA_64.unwind", secstrings + s->sh_name) == 0)
+			mod->arch.unwind = s;
+
+	if (!mod->arch.core_plt || !mod->arch.init_plt || !mod->arch.got || !mod->arch.opd) {
+		printk(KERN_ERR "%s: sections missing\n", mod->name);
+		return -ENOEXEC;
+	}
+
+	/* GOT and PLTs can occur in any relocated section... */
+	for (s = sechdrs + 1; s < sechdrs_end; ++s) {
+		const Elf64_Rela *rels = (void *)ehdr + s->sh_offset;
+		unsigned long numrels = s->sh_size/sizeof(Elf64_Rela);
+
+		if (s->sh_type != SHT_RELA)
+			continue;
+
+		gots += count_gots(rels, numrels);
+		fdescs += count_fdescs(rels, numrels);
+		if (strstr(secstrings + s->sh_name, ".init"))
+			init_plts += count_plts(rels, numrels);
+		else
+			core_plts += count_plts(rels, numrels);
+	}
+
+	mod->arch.core_plt->sh_type = SHT_NOBITS;
+	mod->arch.core_plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	mod->arch.core_plt->sh_addralign = 16;
+	mod->arch.core_plt->sh_size = core_plts * sizeof(struct plt_entry);
+	mod->arch.init_plt->sh_type = SHT_NOBITS;
+	mod->arch.init_plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	mod->arch.init_plt->sh_addralign = 16;
+	mod->arch.init_plt->sh_size = init_plts * sizeof(struct plt_entry);
+	mod->arch.got->sh_type = SHT_NOBITS;
+	mod->arch.got->sh_flags = ARCH_SHF_SMALL | SHF_ALLOC;
+	mod->arch.got->sh_addralign = 8;
+	mod->arch.got->sh_size = gots * sizeof(struct got_entry);
+	mod->arch.opd->sh_type = SHT_NOBITS;
+	mod->arch.opd->sh_flags = SHF_ALLOC;
+	mod->arch.opd->sh_addralign = 8;
+	mod->arch.opd->sh_size = fdescs * sizeof(struct fdesc);
+	DEBUGP("%s: core.plt=%lx, init.plt=%lx, got=%lx, fdesc=%lx\n",
+	       __FUNCTION__, mod->arch.core_plt->sh_size, mod->arch.init_plt->sh_size,
+	       mod->arch.got->sh_size, mod->arch.opd->sh_size);
+	return 0;
+}
+
+static inline int
+in_init (const struct module *mod, uint64_t addr)
+{
+	return addr - (uint64_t) mod->module_init < mod->init_size;
+}
+
+static inline int
+in_core (const struct module *mod, uint64_t addr)
+{
+	return addr - (uint64_t) mod->module_core < mod->core_size;
+}
+
+static inline int
+is_internal (const struct module *mod, uint64_t value)
+{
+	return in_init(mod, value) || in_core(mod, value);
+}
+
+/*
+ * Get gp-relative offset for the linkage-table entry of VALUE.
+ */
+static uint64_t
+get_ltoff (struct module *mod, uint64_t value, int *okp)
+{
+	struct got_entry *got, *e;
+
+	if (!*okp)
+		return 0;
+
+	got = (void *) mod->arch.got->sh_addr;
+	for (e = got; e < got + mod->arch.next_got_entry; ++e)
+		if (e->val == value)
+			goto found;
+
+	/* Not enough GOT entries? */
+	if (e >= (struct got_entry *) (mod->arch.got->sh_addr + mod->arch.got->sh_size))
+		BUG();
+
+	e->val = value;
+	++mod->arch.next_got_entry;
+  found:
+	return (uint64_t) e - mod->arch.gp;
+}
+
+static inline int
+gp_addressable (struct module *mod, uint64_t value)
+{
+	return value - mod->arch.gp + MAX_LTOFF/2 < MAX_LTOFF;
+}
+
+/* Get PC-relative PLT entry for this value.  Returns 0 on failure. */
+static uint64_t
+get_plt (struct module *mod, const struct insn *insn, uint64_t value, int *okp)
+{
+	struct plt_entry *plt, *plt_end;
+	uint64_t target_ip, target_gp;
+
+	if (!*okp)
+		return 0;
+
+	if (in_init(mod, (uint64_t) insn)) {
+		plt = (void *) mod->arch.init_plt->sh_addr;
+		plt_end = (void *) plt + mod->arch.init_plt->sh_size;
+	} else {
+		plt = (void *) mod->arch.core_plt->sh_addr;
+		plt_end = (void *) plt + mod->arch.core_plt->sh_size;
+	}
+
+	/* "value" is a pointer to a function-descriptor; fetch the target ip/gp from it: */
+	target_ip = ((uint64_t *) value)[0];
+	target_gp = ((uint64_t *) value)[1];
+
+	/* Look for existing PLT entry. */
+	while (plt->bundle[0][0]) {
+		if (plt_target(plt) == target_ip)
+			goto found;
+		if (++plt >= plt_end)
+			BUG();
+	}
+	*plt = ia64_plt_template;
+	if (!patch_plt(mod, plt, target_ip, target_gp)) {
+		*okp = 0;
+		return 0;
+	}
+#if ARCH_MODULE_DEBUG
+	if (plt_target(plt) != target_ip) {
+		printk("%s: mistargeted PLT: wanted %lx, got %lx\n",
+		       __FUNCTION__, target_ip, plt_target(plt));
+		*okp = 0;
+		return 0;
+	}
+#endif
+  found:
+	return (uint64_t) plt;
+}
+
+/* Get function descriptor for VALUE. */
+static uint64_t
+get_fdesc (struct module *mod, uint64_t value, int *okp)
+{
+	struct fdesc *fdesc = (void *) mod->arch.opd->sh_addr;
+
+	if (!*okp)
+		return 0;
+
+	if (!value) {
+		printk(KERN_ERR "%s: fdesc for zero requested!\n", mod->name);
+		return 0;
+	}
+
+	if (!is_internal(mod, value))
+		/*
+		 * If it's not a module-local entry-point, "value" already points to a
+		 * function-descriptor.
+		 */
+		return value;
+
+	/* Look for existing function descriptor. */
+	while (fdesc->ip) {
+		if (fdesc->ip == value)
+			return (uint64_t)fdesc;
+		if ((uint64_t) ++fdesc >= mod->arch.opd->sh_addr + mod->arch.opd->sh_size)
+			BUG();
+	}
+
+	/* Create new one */
+	fdesc->ip = value;
+	fdesc->gp = mod->arch.gp;
+	return (uint64_t) fdesc;
+}
+
+static inline int
+do_reloc (struct module *mod, uint8_t r_type, Elf64_Sym *sym, uint64_t addend,
+	  Elf64_Shdr *sec, void *location)
+{
+	enum reloc_target_format format = (r_type >> FORMAT_SHIFT) & FORMAT_MASK;
+	enum reloc_value_formula formula = (r_type >> VALUE_SHIFT) & VALUE_MASK;
+	uint64_t val;
+	int ok = 1;
+
+	val = sym->st_value + addend;
+
+	switch (formula) {
+	      case RV_SEGREL:	/* segment base is arbitrarily chosen to be 0 for kernel modules */
+	      case RV_DIRECT:
+		break;
+
+	      case RV_GPREL:	  val -= mod->arch.gp; break;
+	      case RV_LTREL:	  val = get_ltoff(mod, val, &ok); break;
+	      case RV_PLTREL:	  val = get_plt(mod, location, val, &ok); break;
+	      case RV_FPTR:	  val = get_fdesc(mod, val, &ok); break;
+	      case RV_SECREL:	  val -= sec->sh_addr; break;
+	      case RV_LTREL_FPTR: val = get_ltoff(mod, get_fdesc(mod, val, &ok), &ok); break;
+
+	      case RV_PCREL:
+		switch (r_type) {
+		      case R_IA64_PCREL21B:
+			/* special because it can cross into other module/kernel-core.  */
+			if (!is_internal(mod, val))
+				val = get_plt(mod, location, val, &ok);
+			/* FALL THROUGH */
+		      default:
+			val -= bundle(location);
+			break;
+
+		      case R_IA64_PCREL32MSB:
+		      case R_IA64_PCREL32LSB:
+		      case R_IA64_PCREL64MSB:
+		      case R_IA64_PCREL64LSB:
+			val -= (uint64_t) location;
+			break;
+
+		}
+		switch (r_type) {
+		      case R_IA64_PCREL60B: format = RF_INSN60; break;
+		      case R_IA64_PCREL21B: format = RF_INSN21B; break;
+		      case R_IA64_PCREL21M: format = RF_INSN21M; break;
+		      case R_IA64_PCREL21F: format = RF_INSN21F; break;
+		      default: break;
+		}
+		break;
+
+	      case RV_BDREL:
+		val -= (uint64_t) (in_init(mod, val) ? mod->module_init : mod->module_core);
+		break;
+
+	      case RV_LTV:
+		/* can link-time value relocs happen here?  */
+		BUG();
+		break;
+
+	      case RV_PCREL2:
+		if (r_type == R_IA64_PCREL21BI) {
+			if (!is_internal(mod, val)) {
+				printk(KERN_ERR "%s: %s reloc against non-local symbol (%lx)\n",
+				       __FUNCTION__, reloc_name[r_type], val);
+				return -ENOEXEC;
+			}
+			format = RF_INSN21B;
+		}
+		val -= bundle(location);
+		break;
+
+	      case RV_SPECIAL:
+		switch (r_type) {
+		      case R_IA64_IPLTMSB:
+		      case R_IA64_IPLTLSB:
+			val = get_fdesc(mod, get_plt(mod, location, val, &ok), &ok);
+			format = RF_64LSB;
+			if (r_type == R_IA64_IPLTMSB)
+				format = RF_64MSB;
+			break;
+
+		      case R_IA64_SUB:
+			val = addend - sym->st_value;
+			format = RF_INSN64;
+			break;
+
+		      case R_IA64_LTOFF22X:
+			if (gp_addressable(mod, val))
+				val -= mod->arch.gp;
+			else
+				val = get_ltoff(mod, val, &ok);
+			format = RF_INSN22;
+			break;
+
+		      case R_IA64_LDXMOV:
+			if (gp_addressable(mod, val)) {
+				/* turn "ld8" into "mov": */
+				DEBUGP("%s: patching ld8 at %p to mov\n", __FUNCTION__, location);
+				apply(location, 0x1fff80fe000, 0x10000000000);
+			}
+			return 0;
+
+		      default:
+			if (reloc_name[r_type])
+				printk(KERN_ERR "%s: special reloc %s not supported",
+				       mod->name, reloc_name[r_type]);
+			else
+				printk(KERN_ERR "%s: unknown special reloc %x\n",
+				       mod->name, r_type);
+			return -ENOEXEC;
+		}
+		break;
+
+	      case RV_TPREL:
+	      case RV_LTREL_TPREL:
+	      case RV_DTPMOD:
+	      case RV_LTREL_DTPMOD:
+	      case RV_DTPREL:
+	      case RV_LTREL_DTPREL:
+		printk(KERN_ERR "%s: %s reloc not supported\n",
+		       mod->name, reloc_name[r_type] ? reloc_name[r_type] : "?");
+		return -ENOEXEC;
+
+	      default:
+		printk(KERN_ERR "%s: unknown reloc %x\n", mod->name, r_type);
+		return -ENOEXEC;
+	}
+
+	if (!ok)
+		return -ENOEXEC;
+
+	DEBUGP("%s: [%p]<-%016lx = %s(%lx)\n", __FUNCTION__, location, val,
+	       reloc_name[r_type] ? reloc_name[r_type] : "?", sym->st_value + addend);
+
+	switch (format) {
+	      case RF_INSN21B:	ok = apply_imm21b(mod, location, (int64_t) val / 16); break;
+	      case RF_INSN22:	ok = apply_imm22(mod, location, val); break;
+	      case RF_INSN64:	ok = apply_imm64(mod, location, val); break;
+	      case RF_INSN60:	ok = apply_imm60(mod, location, (int64_t) val / 16); break;
+	      case RF_32LSB:	put_unaligned(val, (uint32_t *) location); break;
+	      case RF_64LSB:	put_unaligned(val, (uint64_t *) location); break;
+	      case RF_32MSB:	/* ia64 Linux is little-endian... */
+	      case RF_64MSB:	/* ia64 Linux is little-endian... */
+	      case RF_INSN14:	/* must be within-module, i.e., resolved by "ld -r" */
+	      case RF_INSN21M:	/* must be within-module, i.e., resolved by "ld -r" */
+	      case RF_INSN21F:	/* must be within-module, i.e., resolved by "ld -r" */
+		printk(KERN_ERR "%s: format %u needed by %s reloc is not supported\n",
+		       mod->name, format, reloc_name[r_type] ? reloc_name[r_type] : "?");
+		return -ENOEXEC;
+
+	      default:
+		printk(KERN_ERR "%s: relocation %s resulted in unknown format %u\n",
+		       mod->name, reloc_name[r_type] ? reloc_name[r_type] : "?", format);
+		return -ENOEXEC;
+	}
+	return ok ? 0 : -ENOEXEC;
+}
+
+int
+apply_relocate_add (Elf64_Shdr *sechdrs, const char *strtab, unsigned int symindex,
+		    unsigned int relsec, struct module *mod)
+{
+	unsigned int i, n = sechdrs[relsec].sh_size / sizeof(Elf64_Rela);
+	Elf64_Rela *rela = (void *) sechdrs[relsec].sh_addr;
+	Elf64_Shdr *target_sec;
+	int ret;
+
+	DEBUGP("%s: applying section %u (%u relocs) to %u\n", __FUNCTION__,
+	       relsec, n, sechdrs[relsec].sh_info);
+
+	target_sec = sechdrs + sechdrs[relsec].sh_info;
+
+	if (target_sec->sh_entsize == ~0UL)
+		/*
+		 * If target section wasn't allocated, we don't need to relocate it.
+		 * Happens, e.g., for debug sections.
+		 */
+		return 0;
+
+	if (!mod->arch.gp) {
+		/*
+		 * XXX Should have an arch-hook for running this after final section
+		 *     addresses have been selected...
+		 */
+		/* See if gp can cover the entire core module:  */
+		uint64_t gp = (uint64_t) mod->module_core + MAX_LTOFF / 2;
+		if (mod->core_size >= MAX_LTOFF)
+			/*
+			 * This takes advantage of fact that SHF_ARCH_SMALL gets allocated
+			 * at the end of the module.
+			 */
+			gp = (uint64_t) mod->module_core + mod->core_size - MAX_LTOFF / 2;
+		mod->arch.gp = gp;
+		DEBUGP("%s: placing gp at 0x%lx\n", __FUNCTION__, gp);
+	}
+
+	for (i = 0; i < n; i++) {
+		ret = do_reloc(mod, ELF64_R_TYPE(rela[i].r_info),
+			       ((Elf64_Sym *) sechdrs[symindex].sh_addr
+				+ ELF64_R_SYM(rela[i].r_info)),
+			       rela[i].r_addend, target_sec,
+			       (void *) target_sec->sh_addr + rela[i].r_offset);
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
+int
+apply_relocate (Elf64_Shdr *sechdrs, const char *strtab, unsigned int symindex,
+		unsigned int relsec, struct module *mod)
+{
+	printk(KERN_ERR "module %s: REL relocs in section %u unsupported\n", mod->name, relsec);
+	return -ENOEXEC;
+}
+
+int
+module_finalize (const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod)
+{
+	DEBUGP("%s: init: entry=%p\n", __FUNCTION__, mod->init);
+	if (mod->arch.unwind)
+		mod->arch.unw_table = unw_add_unwind_table(mod->name, 0, mod->arch.gp,
+							   (void *) mod->arch.unwind->sh_addr,
+							   ((void *) mod->arch.unwind->sh_addr
+							    + mod->arch.unwind->sh_size));
+	return 0;
+}
+
+void
+module_arch_cleanup (struct module *mod)
+{
+	if (mod->arch.unwind)
+		unw_remove_unwind_table(mod->arch.unw_table);
+}

arch/ia64/kernel/palinfo.c

@@ -27,9 +27,7 @@
 #include <asm/sal.h>
 #include <asm/page.h>
 #include <asm/processor.h>
-#ifdef CONFIG_SMP
 #include <linux/smp.h>
-#endif
 
 MODULE_AUTHOR("Stephane Eranian <eranian@hpl.hp.com>");
 MODULE_DESCRIPTION("/proc interface to IA-64 PAL");
@@ -37,12 +35,6 @@ MODULE_LICENSE("GPL");
 
 #define PALINFO_VERSION "0.5"
 
-#ifdef CONFIG_SMP
-#define cpu_is_online(i) (cpu_online_map & (1UL << i))
-#else
-#define cpu_is_online(i)	1
-#endif
-
 typedef int (*palinfo_func_t)(char*);
 
 typedef struct {
@@ -933,7 +925,7 @@ palinfo_init(void)
 	 */
 	for (i=0; i < NR_CPUS; i++) {
 
-		if (!cpu_is_online(i)) continue;
+		if (!cpu_online(i)) continue;
 
 		sprintf(cpustr,CPUSTR, i);
 

arch/ia64/kernel/perfmon.c

@@ -24,6 +24,7 @@
 #include <linux/wrapper.h>
 #include <linux/mm.h>
 #include <linux/sysctl.h>
+#include <linux/smp.h>
 
 #include <asm/bitops.h>
 #include <asm/errno.h>
@@ -134,12 +135,6 @@
 #define PFM_CPUINFO_CLEAR(v)	__get_cpu_var(pfm_syst_info) &= ~(v)
 #define PFM_CPUINFO_SET(v)	__get_cpu_var(pfm_syst_info) |= (v)
 
-#ifdef CONFIG_SMP
-#define cpu_is_online(i) (cpu_online_map & (1UL << i))
-#else
-#define cpu_is_online(i)        (i==0)
-#endif
-
 /*
  * debugging
  */
@@ -1082,7 +1077,7 @@ pfx_is_sane(struct task_struct *task, pfarg_context_t *pfx)
 		 * and it must be a valid CPU
 		 */
 		cpu = ffz(~pfx->ctx_cpu_mask);
-		if (cpu_is_online(cpu) == 0) {
+		if (cpu_online(cpu) == 0) {
 			DBprintk(("CPU%d is not online\n", cpu));
 			return -EINVAL;
 		}
@@ -3153,7 +3148,7 @@ pfm_proc_info(char *page)
 	p += sprintf(p, "ovfl_mask              : 0x%lx\n", pmu_conf.ovfl_val);
 
 	for(i=0; i < NR_CPUS; i++) {
-		if (cpu_is_online(i) == 0) continue;
+		if (cpu_online(i) == 0) continue;
 		p += sprintf(p, "CPU%-2d overflow intrs   : %lu\n", i, pfm_stats[i].pfm_ovfl_intr_count);
 		p += sprintf(p, "CPU%-2d spurious intrs   : %lu\n", i, pfm_stats[i].pfm_spurious_ovfl_intr_count);
 		p += sprintf(p, "CPU%-2d recorded samples : %lu\n", i, pfm_stats[i].pfm_recorded_samples_count);

arch/ia64/kernel/process.c

@@ -66,10 +66,7 @@ do_show_stack (struct unw_frame_info *info, void *arg)
 void
 show_trace_task (struct task_struct *task)
 {
-	struct unw_frame_info info;
-
-	unw_init_from_blocked_task(&info, task);
-	do_show_stack(&info, 0);
+	show_stack(task);
 }
 
 void
@@ -169,7 +166,10 @@ do_notify_resume_user (sigset_t *oldset, struct sigscratch *scr, long in_syscall
 void
 default_idle (void)
 {
-	/* may want to do PAL_LIGHT_HALT here... */
+#ifdef CONFIG_IA64_PAL_IDLE
+	if (!need_resched())
+		safe_halt();
+#endif
 }
 
 void __attribute__((noreturn))
@@ -177,6 +177,10 @@ cpu_idle (void *unused)
 {
 	/* endless idle loop with no priority at all */
 	while (1) {
+		void (*idle)(void) = pm_idle;
+		if (!idle)
+			idle = default_idle;
+
 #ifdef CONFIG_SMP
 		if (!need_resched())
 			min_xtp();
@@ -186,10 +190,7 @@ cpu_idle (void *unused)
 #ifdef CONFIG_IA64_SGI_SN
 			snidle();
 #endif
-			if (pm_idle)
-				(*pm_idle)();
-			else
-				default_idle();
+			(*idle)();
 		}
 
 #ifdef CONFIG_IA64_SGI_SN
@@ -581,6 +582,15 @@ kernel_thread (int (*fn)(void *), void *arg, unsigned long flags)
 
 	tid = clone(flags | CLONE_VM | CLONE_UNTRACED, 0);
 	if (parent != current) {
+#ifdef CONFIG_IA32_SUPPORT
+		if (IS_IA32_PROCESS(ia64_task_regs(current))) {
+			/* A kernel thread is always a 64-bit process. */
+			current->thread.map_base  = DEFAULT_MAP_BASE;
+			current->thread.task_size = DEFAULT_TASK_SIZE;
+			ia64_set_kr(IA64_KR_IO_BASE, current->thread.old_iob);
+			ia64_set_kr(IA64_KR_TSSD, current->thread.old_k1);
+		}
+#endif
 		result = (*fn)(arg);
 		_exit(result);
 	}
@@ -751,7 +761,7 @@ dup_task_struct(struct task_struct *orig)
 }
 
 void
-__put_task_struct (struct task_struct *tsk)
+free_task_struct (struct task_struct *tsk)
 {
 	free_pages((unsigned long) tsk, KERNEL_STACK_SIZE_ORDER);
 }

arch/ia64/kernel/signal.c

@@ -191,6 +191,10 @@ copy_siginfo_to_user (siginfo_t *to, siginfo_t *from)
 				err |= __put_user(from->si_pfm_ovfl[2], &to->si_pfm_ovfl[2]);
 				err |= __put_user(from->si_pfm_ovfl[3], &to->si_pfm_ovfl[3]);
 			}
+		      case __SI_TIMER >> 16:
+			err |= __put_user(from->si_tid, &to->si_tid);
+			err |= __put_user(from->si_overrun, &to->si_overrun);
+			err |= __put_user(from->si_value, &to->si_value);
 			break;
 		      default:
 			err |= __put_user(from->si_uid, &to->si_uid);

arch/ia64/kernel/smpboot.c

@@ -279,12 +279,15 @@ smp_callin (void)
 
 	smp_setup_percpu_timer();
 
+	if (!(sal_platform_features & IA64_SAL_PLATFORM_FEATURE_ITC_DRIFT)) {
 		/*
 		 * Synchronize the ITC with the BP
 		 */
 		Dprintk("Going to syncup ITC with BP.\n");
 
 		ia64_sync_itc(0);
+	}
+
 	/*
 	 * Get our bogomips.
 	 */

arch/ia64/kernel/time.c

@@ -60,7 +60,7 @@ do_profile (unsigned long ip)
 }
 
 /*
- * Return the number of micro-seconds that elapsed since the last update to jiffy.  The
+ * Return the number of nano-seconds that elapsed since the last update to jiffy.  The
  * xtime_lock must be at least read-locked when calling this routine.
  */
 static inline unsigned long
@@ -86,6 +86,9 @@ gettimeoffset (void)
 void
 do_settimeofday (struct timeval *tv)
 {
+	time_t sec = tv->tv_sec;
+	long nsec = tv->tv_usec * 1000;
+
 	write_seqlock_irq(&xtime_lock);
 	{
 		/*
@@ -94,22 +97,22 @@ do_settimeofday (struct timeval *tv)
 		 * Discover what correction gettimeofday would have done, and then undo
 		 * it!
 		 */
-		tv->tv_usec -= gettimeoffset();
-		tv->tv_usec -= (jiffies - wall_jiffies) * (1000000 / HZ);
+		nsec -= gettimeoffset();
 
-		while (tv->tv_usec < 0) {
-			tv->tv_usec += 1000000;
-			tv->tv_sec--;
+		while (nsec < 0) {
+			nsec += 1000000000;
+			sec--;
 		}
 
-		xtime.tv_sec = tv->tv_sec;
-		xtime.tv_nsec = 1000 * tv->tv_usec;
+		xtime.tv_sec = sec;
+		xtime.tv_nsec = nsec;
 		time_adjust = 0;		/* stop active adjtime() */
 		time_status |= STA_UNSYNC;
 		time_maxerror = NTP_PHASE_LIMIT;
 		time_esterror = NTP_PHASE_LIMIT;
 	}
 	write_sequnlock_irq(&xtime_lock);
+	clock_was_set();
 }
 
 void

arch/ia64/kernel/traps.c

@@ -338,8 +338,8 @@ handle_fpu_swa (int fp_fault, struct pt_regs *regs, unsigned long isr)
 		fpu_swa_count = 0;
 	if ((++fpu_swa_count < 5) && !(current->thread.flags & IA64_THREAD_FPEMU_NOPRINT)) {
 		last_time = jiffies;
-		printk(KERN_WARNING "%s(%d): floating-point assist fault at ip %016lx\n",
-		       current->comm, current->pid, regs->cr_iip + ia64_psr(regs)->ri);
+		printk(KERN_WARNING "%s(%d): floating-point assist fault at ip %016lx, isr %016lx\n",
+		       current->comm, current->pid, regs->cr_iip + ia64_psr(regs)->ri, isr);
 	}
 
 	exception = fp_emulate(fp_fault, bundle, &regs->cr_ipsr, &regs->ar_fpsr, &isr, &regs->pr,

arch/ia64/kernel/unwind.c

@@ -253,6 +253,11 @@ unw_access_gr (struct unw_frame_info *info, int regnum, unsigned long *val, char
 	struct pt_regs *pt;
 
 	if ((unsigned) regnum - 1 >= 127) {
+		if (regnum == 0 && !write) {
+			*val = 0;	/* read r0 always returns 0 */
+			*nat = 0;
+			return 0;
+		}
 		UNW_DPRINT(0, "unwind.%s: trying to access non-existent r%u\n",
 			   __FUNCTION__, regnum);
 		return -1;
@@ -318,13 +323,8 @@ unw_access_gr (struct unw_frame_info *info, int regnum, unsigned long *val, char
 			}
 		} else {
 			/* access a scratch register */
-			if (!info->pt) {
-				UNW_DPRINT(0, "unwind.%s: no pt-regs; cannot access r%d\n",
-					   __FUNCTION__, regnum);
-				return -1;
-			}
 			pt = get_scratch_regs(info);
-			addr = (unsigned long *) (pt + pt_regs_off(regnum));
+			addr = (unsigned long *) ((unsigned long)pt + pt_regs_off(regnum));
 			if (info->pri_unat_loc)
 				nat_addr = info->pri_unat_loc;
 			else

arch/ia64/lib/io.c

@@ -87,12 +87,31 @@ ia64_outl (unsigned int val, unsigned long port)
 	__ia64_outl(val, port);
 }
 
-void
-ia64_mmiob (void)
+unsigned char
+ia64_readb (void *addr)
+{
+	return __ia64_readb (addr);
+}
+
+unsigned short
+ia64_readw (void *addr)
 {
-	__ia64_mmiob();
+	return __ia64_readw (addr);
 }
 
+unsigned int
+ia64_readl (void *addr)
+{
+	return __ia64_readl (addr);
+}
+
+unsigned long
+ia64_readq (void *addr)
+{
+	return __ia64_readq (addr)
+}
+
+
 /* define aliases: */
 
 asm (".global __ia64_inb, __ia64_inw, __ia64_inl");
@@ -105,7 +124,11 @@ asm ("__ia64_outb = ia64_outb");
 asm ("__ia64_outw = ia64_outw");
 asm ("__ia64_outl = ia64_outl");
 
-asm (".global __ia64_mmiob");
-asm ("__ia64_mmiob = ia64_mmiob");
+asm (".global __ia64_readb, __ia64_readw, __ia64_readl, __ia64_readq");
+asm ("__ia64_readb = ia64_readb");
+asm ("__ia64_readw = ia64_readw");
+asm ("__ia64_readl = ia64_readl");
+asm ("__ia64_readq = ia64_readq");
+
 
 #endif /* CONFIG_IA64_GENERIC */

arch/ia64/lib/swiotlb.c

@@ -473,12 +473,6 @@ swiotlb_sync_sg (struct pci_dev *hwdev, struct scatterlist *sg, int nelems, int
 			sync_single(hwdev, (void *) sg->dma_address, sg->dma_length, direction);
 }
 
-unsigned long
-swiotlb_dma_address (struct scatterlist *sg)
-{
-	return sg->dma_address;
-}
-
 /*
  * Return whether the given PCI device DMA address mask can be supported properly.  For
  * example, if your device can only drive the low 24-bits during PCI bus mastering, then
@@ -497,7 +491,6 @@ EXPORT_SYMBOL(swiotlb_map_sg);
 EXPORT_SYMBOL(swiotlb_unmap_sg);
 EXPORT_SYMBOL(swiotlb_sync_single);
 EXPORT_SYMBOL(swiotlb_sync_sg);
-EXPORT_SYMBOL(swiotlb_dma_address);
 EXPORT_SYMBOL(swiotlb_alloc_consistent);
 EXPORT_SYMBOL(swiotlb_free_consistent);
 EXPORT_SYMBOL(swiotlb_pci_dma_supported);

arch/ia64/module.lds

+SECTIONS {
+	/* Group unwind sections into a single section: */
+	.IA_64.unwind_info : { *(.IA_64.unwind_info*) }
+	.IA_64.unwind : { *(.IA_64.unwind*) }
+	/*
+	 * Create place-holder sections to hold the PLTs, GOT, and
+	 * official procedure-descriptors (.opd).
+	 */
+	.core.plt : { BYTE(0) }
+	.init.plt : { BYTE(0) }
+	.got : { BYTE(0) }
+	.opd : { BYTE(0) }
+}

arch/ia64/pci/pci.c

@@ -49,11 +49,13 @@ struct pci_fixup pcibios_fixups[1];
 /*
  * Low-level SAL-based PCI configuration access functions. Note that SAL
  * calls are already serialized (via sal_lock), so we don't need another
- * synchronization mechanism here.  Not using segment number (yet).
+ * synchronization mechanism here.
  */
 
-#define PCI_SAL_ADDRESS(bus, dev, fn, reg) \
-	((u64)(bus << 16) | (u64)(dev << 11) | (u64)(fn << 8) | (u64)(reg))
+#define PCI_SAL_ADDRESS(seg, bus, dev, fn, reg) \
+	((u64)(seg << 24) | (u64)(bus << 16) | \
+	 (u64)(dev << 11) | (u64)(fn << 8) | (u64)(reg))
+
 
 static int
 __pci_sal_read (int seg, int bus, int dev, int fn, int reg, int len, u32 *value)
@@ -61,10 +63,10 @@ __pci_sal_read (int seg, int bus, int dev, int fn, int reg, int len, u32 *value)
 	int result = 0;
 	u64 data = 0;
 
-	if (!value || (bus > 255) || (dev > 31) || (fn > 7) || (reg > 255))
+	if (!value || (seg > 255) || (bus > 255) || (dev > 31) || (fn > 7) || (reg > 255))
 		return -EINVAL;
 
-	result = ia64_sal_pci_config_read(PCI_SAL_ADDRESS(bus, dev, fn, reg), len, &data);
+	result = ia64_sal_pci_config_read(PCI_SAL_ADDRESS(seg, bus, dev, fn, reg), len, &data);
 
 	*value = (u32) data;
 
@@ -74,24 +76,24 @@ __pci_sal_read (int seg, int bus, int dev, int fn, int reg, int len, u32 *value)
 static int
 __pci_sal_write (int seg, int bus, int dev, int fn, int reg, int len, u32 value)
 {
-	if ((bus > 255) || (dev > 31) || (fn > 7) || (reg > 255))
+	if ((seg > 255) || (bus > 255) || (dev > 31) || (fn > 7) || (reg > 255))
 		return -EINVAL;
 
-	return ia64_sal_pci_config_write(PCI_SAL_ADDRESS(bus, dev, fn, reg), len, value);
+	return ia64_sal_pci_config_write(PCI_SAL_ADDRESS(seg, bus, dev, fn, reg), len, value);
 }
 
 
 static int
 pci_sal_read (struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *value)
 {
-	return __pci_sal_read(0, bus->number, PCI_SLOT(devfn), PCI_FUNC(devfn),
+	return __pci_sal_read(PCI_SEGMENT(bus), bus->number, PCI_SLOT(devfn), PCI_FUNC(devfn),
 			      where, size, value);
 }
 
 static int
 pci_sal_write (struct pci_bus *bus, unsigned int devfn, int where, int size, u32 value)
 {
-	return __pci_sal_write(0, bus->number, PCI_SLOT(devfn), PCI_FUNC(devfn),
+	return __pci_sal_write(PCI_SEGMENT(bus), bus->number, PCI_SLOT(devfn), PCI_FUNC(devfn),
 			       where, size, value);
 }
 
@@ -114,24 +116,91 @@ pci_acpi_init (void)
 
 subsys_initcall(pci_acpi_init);
 
+static void __init
+pcibios_fixup_resource(struct resource *res, u64 offset)
+{
+	res->start += offset;
+	res->end += offset;
+}
+
+void __init
+pcibios_fixup_device_resources(struct pci_dev *dev, struct pci_bus *bus)
+{
+	int i;
+
+	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+		if (!dev->resource[i].start)
+			continue;
+		if (dev->resource[i].flags & IORESOURCE_MEM)
+			pcibios_fixup_resource(&dev->resource[i],
+			                       PCI_CONTROLLER(dev)->mem_offset);
+	}
+}
+
 /* Called by ACPI when it finds a new root bus.  */
+
+static struct pci_controller *
+alloc_pci_controller(int seg)
+{
+	struct pci_controller *controller;
+
+	controller = kmalloc(sizeof(*controller), GFP_KERNEL);
+	if (!controller)
+		return NULL;
+
+	memset(controller, 0, sizeof(*controller));
+	controller->segment = seg;
+	return controller;
+}
+
 struct pci_bus *
-pcibios_scan_root (int bus)
+scan_root_bus(int bus, struct pci_ops *ops, void *sysdata)
 {
-	struct list_head *list;
-	struct pci_bus *pci_bus;
-
-	list_for_each(list, &pci_root_buses) {
-		pci_bus = pci_bus_b(list);
-		if (pci_bus->number == bus) {
-			/* Already scanned */
-			printk("PCI: Bus (%02x) already probed\n", bus);
-			return pci_bus;
-		}
-	}
+	struct pci_bus *b;
 
-	printk("PCI: Probing PCI hardware on bus (%02x)\n", bus);
-	return pci_scan_bus(bus, pci_root_ops, NULL);
+	/*
+	 * We know this is a new root bus we haven't seen before, so
+	 * scan it, even if we've seen the same bus number in a different
+	 * segment.
+	 */
+	b = kmalloc(sizeof(*b), GFP_KERNEL);
+	if (!b)
+		return NULL;
+
+	memset(b, 0, sizeof(*b));
+	INIT_LIST_HEAD(&b->children);
+	INIT_LIST_HEAD(&b->devices);
+
+	list_add_tail(&b->node, &pci_root_buses);
+
+	b->number = b->secondary = bus;
+	b->resource[0] = &ioport_resource;
+	b->resource[1] = &iomem_resource;
+
+	b->sysdata = sysdata;
+	b->ops = ops;
+	b->subordinate = pci_do_scan_bus(b);
+
+	return b;
+}
+
+struct pci_bus *
+pcibios_scan_root(void *handle, int seg, int bus)
+{
+	struct pci_controller *controller;
+	u64 base, size, offset;
+
+	printk("PCI: Probing PCI hardware on bus (%02x:%02x)\n", seg, bus);
+	controller = alloc_pci_controller(seg);
+	if (!controller)
+		return NULL;
+
+	controller->acpi_handle = handle;
+
+	acpi_get_addr_space(handle, ACPI_MEMORY_RANGE, &base, &size, &offset);
+	controller->mem_offset = offset;
+
+	return scan_root_bus(bus, pci_root_ops, controller);
 }
 
 /*
@@ -140,6 +209,11 @@ pcibios_scan_root (int bus)
 void __devinit
 pcibios_fixup_bus (struct pci_bus *b)
 {
+	struct list_head *ln;
+
+	for (ln = b->devices.next; ln != &b->devices; ln = ln->next)
+		pcibios_fixup_device_resources(pci_dev_b(ln), b);
+
 	return;
 }
 

arch/ia64/scripts/check-gas

 #!/bin/sh
 dir=$(dirname $0)
 CC=$1
+OBJDUMP=$2
 $CC -c $dir/check-gas-asm.S
-res=$(objdump -r --section .data check-gas-asm.o | fgrep 00004 | tr -s ' ' |cut -f3 -d' ')
+res=$($OBJDUMP -r --section .data check-gas-asm.o | fgrep 00004 | tr -s ' ' |cut -f3 -d' ')
 if [ $res != ".text" ]; then
 	echo buggy
 else

arch/ia64/sn/Makefile

+# arch/ia64/sn/Makefile
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 2003 Silicon Graphics, Inc.  All Rights Reserved.
+#
+# Makefile for the sn ia64 subplatform
+#
+
+EXTRA_CFLAGS := -DLITTLE_ENDIAN
+
+obj-y += kernel/ # io/

arch/ia64/sn/fakeprom/Makefile

+# arch/ia64/sn/fakeprom/Makefile
 #
 # This file is subject to the terms and conditions of the GNU General Public
 # License.  See the file "COPYING" in the main directory of this archive
 # for more details.
 #
-#  Copyright (c) 2000-2001 Silicon Graphics, Inc.  All rights reserved.
+#  Copyright (c) 2000-2003 Silicon Graphics, Inc.  All rights reserved.
 #
+# Medusa fake PROM support
+#
+
+EXTRA_TARGETS := fpromasm.o main.o fw-emu.o fpmem.o klgraph_init.o \
+		 fprom vmlinux.sym
+
+OBJS := $(obj)/fpromasm.o $(obj)/main.o $(obj)/fw-emu.o $(obj)/fpmem.o \
+	$(obj)/klgraph_init.o
+
+LDFLAGS_fprom = -static -T
 
-obj-y=fpromasm.o main.o fw-emu.o fpmem.o klgraph_init.o
+.PHONY: fprom
 
-fprom: $(OBJ)
-	$(LD) -static -Tfprom.lds -o fprom $(OBJ) $(LIB)
+fprom: $(obj)/fprom
 
-.S.o:
-	$(CC)  -D__ASSEMBLY__ $(AFLAGS) $(AFLAGS_KERNEL) -c -o $*.o $<
-.c.o:
-	$(CC)  $(CFLAGS) $(CFLAGS_KERNEL) -c -o $*.o $<
+$(obj)/fprom: $(src)/fprom.lds $(OBJS) arch/ia64/lib/lib.a FORCE
+	$(call if_changed,ld)
 
-clean:
-	rm -f *.o fprom
+$(obj)/vmlinux.sym: $(src)/make_textsym System.map
+	$(src)/make_textsym vmlinux > vmlinux.sym
+	$(call cmd,cptotop)

arch/ia64/sn/fakeprom/README

+/*
+ * Copyright (c) 2002-2003 Silicon Graphics, Inc.  All Rights Reserved.
+ * 
+ * This program is free software; you can redistribute it and/or modify it 
+ * under the terms of version 2 of the GNU General Public License 
+ * as published by the Free Software Foundation.
+ * 
+ * This program is distributed in the hope that it would be useful, but 
+ * WITHOUT ANY WARRANTY; without even the implied warranty of 
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. 
+ * 
+ * Further, this software is distributed without any warranty that it is 
+ * free of the rightful claim of any third person regarding infringement 
+ * or the like.  Any license provided herein, whether implied or 
+ * otherwise, applies only to this software file.  Patent licenses, if 
+ * any, provided herein do not apply to combinations of this program with 
+ * other software, or any other product whatsoever.
+ * 
+ * You should have received a copy of the GNU General Public 
+ * License along with this program; if not, write the Free Software 
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
+ * 
+ * Contact information:  Silicon Graphics, Inc., 1600 Amphitheatre Pkwy, 
+ * Mountain View, CA  94043, or:
+ * 
+ * http://www.sgi.com 
+ * 
+ * For further information regarding this notice, see: 
+ * 
+ * http://oss.sgi.com/projects/GenInfo/NoticeExplan
+ */
+
 This directory contains the files required to build
 the fake PROM image that is currently being used to
 boot IA64 kernels running under the SGI Medusa kernel.

arch/ia64/sn/fakeprom/fpmem.c

@@ -4,7 +4,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (C) 2000-2002 Silicon Graphics, Inc.  All rights reserved.
+ * Copyright (C) 2000-2003 Silicon Graphics, Inc.  All rights reserved.
  */
 
 
@@ -168,13 +168,13 @@ GetBankSize(int index, node_memmap_t nmemmap)
 #endif
 
 void
-build_mem_desc(efi_memory_desc_t *md, int type, long paddr, long numbytes)
+build_mem_desc(efi_memory_desc_t *md, int type, long paddr, long numbytes, long attr)
 {
         md->type = type;
         md->phys_addr = paddr;
         md->virt_addr = 0;
         md->num_pages = numbytes >> 12;
-        md->attribute = EFI_MEMORY_WB;
+        md->attribute = attr;
 }
 
 int
@@ -236,28 +236,40 @@ build_efi_memmap(void *md, int mdsize)
                                  */
                                 if (bank == 0) {
 					if (cnode == 0) {
+						hole = 2*1024*1024;
+						build_mem_desc(md, EFI_PAL_CODE, paddr, hole, EFI_MEMORY_WB|EFI_MEMORY_WB);
+						numbytes -= hole;
+                                        	paddr += hole;
+			        		count++ ;
+                                        	md += mdsize;
 						hole = 1*1024*1024;
-						build_mem_desc(md, EFI_PAL_CODE, paddr, hole);
+						build_mem_desc(md, EFI_CONVENTIONAL_MEMORY, paddr, hole, EFI_MEMORY_UC);
 						numbytes -= hole;
                                         	paddr += hole;
 			        		count++ ;
                                         	md += mdsize;
-						hole = 3*1024*1024;
-						build_mem_desc(md, EFI_RUNTIME_SERVICES_DATA, paddr, hole);
+						hole = 1*1024*1024;
+						build_mem_desc(md, EFI_RUNTIME_SERVICES_DATA, paddr, hole, EFI_MEMORY_WB|EFI_MEMORY_WB);
 						numbytes -= hole;
                                         	paddr += hole;
 			        		count++ ;
                                         	md += mdsize;
 					} else {
-						hole = PROMRESERVED_SIZE;
-                                        	build_mem_desc(md, EFI_RUNTIME_SERVICES_DATA, paddr, hole);
+						hole = 2*1024*1024;
+                                        	build_mem_desc(md, EFI_RUNTIME_SERVICES_DATA, paddr, hole, EFI_MEMORY_WB|EFI_MEMORY_WB);
+						numbytes -= hole;
+                                        	paddr += hole;
+			        		count++ ;
+                                        	md += mdsize;
+						hole = 2*1024*1024;
+                                        	build_mem_desc(md, EFI_RUNTIME_SERVICES_DATA, paddr, hole, EFI_MEMORY_UC);
 						numbytes -= hole;
                                         	paddr += hole;
 			        		count++ ;
                                         	md += mdsize;
 					}
                                 }
-                                build_mem_desc(md, EFI_CONVENTIONAL_MEMORY, paddr, numbytes);
+                                build_mem_desc(md, EFI_CONVENTIONAL_MEMORY, paddr, numbytes, EFI_MEMORY_WB|EFI_MEMORY_WB);
 
 			        md += mdsize ;
 			        count++ ;

arch/ia64/sn/fakeprom/fprom.lds

+/*
+ * Copyright (c) 2002-2003 Silicon Graphics, Inc.  All Rights Reserved.
+ * 
+ * This program is free software; you can redistribute it and/or modify it 
+ * under the terms of version 2 of the GNU General Public License 
+ * as published by the Free Software Foundation.
+ * 
+ * This program is distributed in the hope that it would be useful, but 
+ * WITHOUT ANY WARRANTY; without even the implied warranty of 
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. 
+ * 
+ * Further, this software is distributed without any warranty that it is 
+ * free of the rightful claim of any third person regarding infringement 
+ * or the like.  Any license provided herein, whether implied or 
+ * otherwise, applies only to this software file.  Patent licenses, if 
+ * any, provided herein do not apply to combinations of this program with 
+ * other software, or any other product whatsoever.
+ * 
+ * You should have received a copy of the GNU General Public 
+ * License along with this program; if not, write the Free Software 
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
+ * 
+ * Contact information:  Silicon Graphics, Inc., 1600 Amphitheatre Pkwy, 
+ * Mountain View, CA  94043, or:
+ * 
+ * http://www.sgi.com 
+ * 
+ * For further information regarding this notice, see: 
+ * 
+ * http://oss.sgi.com/projects/GenInfo/NoticeExplan
+ */
 
 OUTPUT_FORMAT("elf64-ia64-little")
 OUTPUT_ARCH(ia64)

arch/ia64/sn/io/Makefile

+# arch/ia64/sn/io/Makefile
 #
 # This file is subject to the terms and conditions of the GNU General Public
 # License.  See the file "COPYING" in the main directory of this archive
@@ -5,7 +6,8 @@
 #
 # Copyright (C) 2000-2002 Silicon Graphics, Inc.  All Rights Reserved.
 #
-# Makefile for the sn kernel routines.
+# Makefile for the sn io routines.
+#
 
 EXTRA_CFLAGS    := -DLITTLE_ENDIAN
 
@@ -19,4 +21,6 @@ obj-$(CONFIG_IA64_SGI_SN) += stubs.o sgi_if.o xswitch.o klgraph_hack.o \
 		alenlist.o pci.o pci_dma.o ate_utils.o \
 		ifconfig_net.o io.o ioconfig_bus.o
 
+obj-$(CONFIG_IA64_SGI_SN2) += sn2/
+
 obj-$(CONFIG_PCIBA) += pciba.o

arch/ia64/sn/io/sn2/Makefile

+# arch/ia64/sn/io/sn2/Makefile
 #
 # This file is subject to the terms and conditions of the GNU General Public
 # License.  See the file "COPYING" in the main directory of this archive
@@ -6,14 +7,14 @@
 # Copyright (C) 2002-2003 Silicon Graphics, Inc.  All Rights Reserved.
 #
 # Makefile for the sn2 specific io routines.
+#
 
 EXTRA_CFLAGS := -DLITTLE_ENDIAN
 
-obj-y += bte_error.o geo_op.o klconflib.o klgraph.o l1.o \
+obj-y += pcibr/ bte_error.o geo_op.o klconflib.o klgraph.o l1.o \
 	 l1_command.o ml_iograph.o ml_SN_init.o ml_SN_intr.o module.o \
 	 pci_bus_cvlink.o pciio.o pic.o sgi_io_init.o shub.o shuberror.o \
 	 shub_intr.o shubio.o xbow.o xtalk.o
 
 obj-$(CONFIG_KDB) += kdba_io.o 
-
 obj-$(CONFIG_SHUB_1_0_SPECIFIC) += efi-rtc.o

arch/ia64/sn/io/sn2/l1_command.c

@@ -154,7 +154,7 @@ int iobrick_module_get(nasid_t nasid)
 
     return ret;
 }
-
+#ifdef CONFIG_PCI
 /*
  * iobrick_module_get_nasid() returns a module_id which has the brick
  * type encoded in bits 15-12, but this is not the true brick type...
@@ -185,7 +185,7 @@ iobrick_type_get_nasid(nasid_t nasid)
 
     return -1;    /* unknown brick */
 }
-
+#endif
 int iobrick_module_get_nasid(nasid_t nasid)
 {
     int io_moduleid;

arch/ia64/sn/io/sn2/pcibr/Makefile

+# arch/ia64/sn/io/sn2/pcibr/Makefile
 #
 # This file is subject to the terms and conditions of the GNU General Public
 # License.  See the file "COPYING" in the main directory of this archive
@@ -6,6 +7,7 @@
 # Copyright (C) 2002-2003 Silicon Graphics, Inc.  All Rights Reserved.
 #
 # Makefile for the sn2 specific pci bridge routines.
+#
 
 EXTRA_CFLAGS    := -DLITTLE_ENDIAN
 

arch/ia64/sn/kernel/Makefile

 # arch/ia64/sn/kernel/Makefile
 #
-# Copyright (C) 1999,2001-2002 Silicon Graphics, Inc.  All Rights Reserved.
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
 #
-# This program is free software; you can redistribute it and/or modify it 
-# under the terms of version 2 of the GNU General Public License 
-# as published by the Free Software Foundation.
-# 
-# This program is distributed in the hope that it would be useful, but 
-# WITHOUT ANY WARRANTY; without even the implied warranty of 
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. 
-# 
-# Further, this software is distributed without any warranty that it is 
-# free of the rightful claim of any third person regarding infringement 
-# or the like.  Any license provided herein, whether implied or 
-# otherwise, applies only to this software file.  Patent licenses, if 
-# any, provided herein do not apply to combinations of this program with 
-# other software, or any other product whatsoever.
-# 
-# You should have received a copy of the GNU General Public 
-# License along with this program; if not, write the Free Software 
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
-# 
-# Contact information:  Silicon Graphics, Inc., 1600 Amphitheatre Pkwy, 
-# Mountain View, CA  94043, or:
-# 
-# http://www.sgi.com 
-# 
-# For further information regarding this notice, see: 
-# 
-# http://oss.sgi.com/projects/GenInfo/NoticeExplan
+# Copyright (C) 1999,2001-2003 Silicon Graphics, Inc.  All Rights Reserved.
 #
 
 EXTRA_CFLAGS := -DLITTLE_ENDIAN
 
-.S.s:
-	$(CPP) $(AFLAGS) $(AFLAGS_KERNEL) -o $*.s $<
-.S.o:
-	$(CC) $(AFLAGS) $(AFLAGS_KERNEL) -c -o $*.o $<
+obj-y				:= probe.o setup.o sn_asm.o sv.o bte.o iomv.o \
+				   irq.o mca.o
 
-obj-y		= probe.o setup.o sn_asm.o sv.o bte.o iomv.o
-obj-$(CONFIG_IA64_SGI_SN1)      += irq.o mca.o
-obj-$(CONFIG_IA64_SGI_SN2)      += irq.o mca.o
+obj-$(CONFIG_IA64_SGI_SN2)      += sn2/
 obj-$(CONFIG_IA64_SGI_AUTOTEST) += llsc4.o misctest.o
 obj-$(CONFIG_IA64_GENERIC)      += machvec.o
 obj-$(CONFIG_MODULES)           += sn_ksyms.o

arch/ia64/sn/kernel/setup.c

@@ -237,7 +237,7 @@ sn_setup(char **cmdline_p)
 		       "%x.%02x\n", SN_SAL_MIN_MAJOR, SN_SAL_MIN_MINOR);
 		panic("PROM version too old\n");
 	}
-
+#ifdef CONFIG_PCI
 #ifdef CONFIG_IA64_SGI_SN2
 	{
 		extern void io_sh_swapper(int, int);
@@ -253,7 +253,7 @@ sn_setup(char **cmdline_p)
 		(void)get_master_baseio_nasid();
 	}
 #endif
-
+#endif /* CONFIG_PCI */
 	status = ia64_sal_freq_base(SAL_FREQ_BASE_REALTIME_CLOCK, &ticks_per_sec, &drift);
 	if (status != 0 || ticks_per_sec < 100000) {
 		printk(KERN_WARNING "unable to determine platform RTC clock frequency, guessing.\n");
@@ -349,7 +349,7 @@ sn_init_pdas(char **cmdline_p)
         for (cnode=0; cnode < numnodes; cnode++)
 		memcpy(nodepdaindr[cnode]->pernode_pdaindr, nodepdaindr, sizeof(nodepdaindr));
 
-
+#ifdef CONFIG_PCI
 	/*
 	 * Set up IO related platform-dependent nodepda fields.
 	 * The following routine actually sets up the hubinfo struct
@@ -359,6 +359,7 @@ sn_init_pdas(char **cmdline_p)
 		init_platform_nodepda(nodepdaindr[cnode], cnode);
 		bte_init_node (nodepdaindr[cnode], cnode);
 	}
+#endif
 }
 
 /**

arch/ia64/sn/kernel/sn2/Makefile

-#
 # arch/ia64/sn/kernel/sn2/Makefile
 #
-# Copyright (C) 1999,2001-2002 Silicon Graphics, Inc. All rights reserved.
-#
-# This program is free software; you can redistribute it and/or modify it 
-# under the terms of version 2 of the GNU General Public License 
-# as published by the Free Software Foundation.
-# 
-# This program is distributed in the hope that it would be useful, but 
-# WITHOUT ANY WARRANTY; without even the implied warranty of 
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. 
-# 
-# Further, this software is distributed without any warranty that it is 
-# free of the rightful claim of any third person regarding infringement 
-# or the like.  Any license provided herein, whether implied or 
-# otherwise, applies only to this software file.  Patent licenses, if 
-# any, provided herein do not apply to combinations of this program with 
-# other software, or any other product whatsoever.
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
 #
-# You should have received a copy of the GNU General Public 
-# License along with this program; if not, write the Free Software 
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
-# 
-# Contact information:  Silicon Graphics, Inc., 1600 Amphitheatre Pkwy, 
-# Mountain View, CA  94043, or:
-# 
-# http://www.sgi.com 
-# 
-# For further information regarding this notice, see: 
+# Copyright (C) 1999,2001-2002 Silicon Graphics, Inc. All rights reserved.
 #
-# http://oss.sgi.com/projects/GenInfo/NoticeExplan
+# sn2 specific kernel files
 #
 
 EXTRA_CFLAGS := -DLITTLE_ENDIAN
 
-obj-y += cache.o iomv.o ptc_deadlock.o sn2_smp.o \
-         sn_proc_fs.o
+obj-y += cache.o iomv.o ptc_deadlock.o sn2_smp.o sn_proc_fs.o

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

+/* 
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2003 Silicon Graphics, Inc. All rights reserved.
+ *
+ * The generic kernel requires function pointers to these routines, so
+ * we wrap the inlines from asm/ia64/sn/sn2/io.h here.
+ */
+
+#include <linux/config.h>
+#include <linux/types.h>
+
+#include <asm/sn/sn2/io.h>
+
+#ifdef CONFIG_IA64_GENERIC
+
+unsigned int
+sn_inb (unsigned long port)
+{
+	return __sn_inb(port);
+}
+
+unsigned int
+sn_inw (unsigned long port)
+{
+	return __sn_inw(port);
+}
+
+unsigned int
+sn_inl (unsigned long port)
+{
+	return __sn_inl(port);
+}
+
+void
+sn_outb (unsigned char val, unsigned long port)
+{
+	__sn_outb(val, port);
+}
+
+void
+sn_outw (unsigned short val, unsigned long port)
+{
+	__sn_outw(val, port);
+}
+
+void
+sn_outl (unsigned int val, unsigned long port)
+{
+	__sn_outl(val, port);
+}
+
+unsigned char
+sn_readb (void *addr)
+{
+	return __sn_readb (addr);
+}
+
+unsigned short
+sn_readw (void *addr)
+{
+	return __sn_readw (addr);
+}
+
+unsigned int
+sn_readl (void *addr)
+{
+	return __sn_readl (addr);
+}
+
+unsigned long
+sn_readq (void *addr)
+{
+	return __sn_readq (addr)
+}
+
+
+/* define aliases: */
+
+asm (".global __sn_inb, __sn_inw, __sn_inl");
+asm ("__sn_inb = sn_inb");
+asm ("__sn_inw = sn_inw");
+asm ("__sn_inl = sn_inl");
+
+asm (".global __sn_outb, __sn_outw, __sn_outl");
+asm ("__sn_outb = sn_outb");
+asm ("__sn_outw = sn_outw");
+asm ("__sn_outl = sn_outl");
+
+asm (".global __sn_readb, __sn_readw, __sn_readl, __sn_readq");
+asm ("__sn_readb = sn_readb");
+asm ("__sn_readw = sn_readw");
+asm ("__sn_readl = sn_readl");
+asm ("__sn_readq = sn_readq");
+
+#endif /* CONFIG_IA64_GENERIC */

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

@@ -3,10 +3,11 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (C) 2000-2002 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2000-2003 Silicon Graphics, Inc. All rights reserved.
  */
 
 #include <linux/pci.h>
+#include <linux/module.h>
 #include <asm/io.h>
 #include <asm/delay.h>
 #include <asm/sn/simulator.h>
@@ -46,8 +47,10 @@ sn_io_addr(unsigned long port)
 	}
 }
 
+EXPORT_SYMBOL(sn_io_addr);
+
 /**
- * sn2_mmiob - I/O space memory barrier
+ * sn_mmiob - I/O space memory barrier
  *
  * Acts as a memory mapped I/O barrier for platforms that queue writes to 
  * I/O space.  This ensures that subsequent writes to I/O space arrive after
@@ -60,9 +63,9 @@ sn_io_addr(unsigned long port)
  *
  */
 void
-sn2_mmiob (void)
+sn_mmiob (void)
 {
-	while ((((volatile unsigned long) (*pda->pio_write_status_addr)) & SH_PIO_WRITE_STATUS_0_PENDING_WRITE_COUNT_MASK) != 
+	while ((((volatile unsigned long) (*pda.pio_write_status_addr)) & SH_PIO_WRITE_STATUS_0_PENDING_WRITE_COUNT_MASK) != 
 				SH_PIO_WRITE_STATUS_0_PENDING_WRITE_COUNT_MASK)
 		udelay(1);
 }

include/asm-ia64/acpi-ext.h

+/*
+ * ia64/platform/hp/common/hp_acpi.h
+ *
+ * Copyright (C) 2003 Hewlett-Packard
+ * Copyright (C) Alex Williamson
+ *
+ * Vendor specific extensions to ACPI.  The HP-specific extensiosn are also used by NEC.
+ */
+#ifndef _ASM_IA64_ACPI_EXT_H
+#define _ASM_IA64_ACPI_EXT_H
+
+#include <linux/types.h>
+
+#define HP_CCSR_LENGTH	0x21
+#define HP_CCSR_TYPE	0x2
+#define HP_CCSR_GUID	EFI_GUID(0x69e9adf9, 0x924f, 0xab5f, \
+				 0xf6, 0x4a, 0x24, 0xd2, 0x01, 0x37, 0x0e, 0xad)
+
+struct acpi_hp_vendor_long {
+	u8      guid_id;
+	u8      guid[16];
+	u8      csr_base[8];
+	u8      csr_length[8];
+};
+
+extern acpi_status hp_acpi_csr_space (acpi_handle, u64 *base, u64 *length);
+extern acpi_status acpi_get_crs (acpi_handle, struct acpi_buffer *);
+extern struct acpi_resource *acpi_get_crs_next (struct acpi_buffer *, int *);
+extern union acpi_resource_data *acpi_get_crs_type (struct acpi_buffer *, int *, int);
+extern void acpi_dispose_crs (struct acpi_buffer *);
+
+#endif /* _ASM_IA64_ACPI_EXT_H */

include/asm-ia64/acpi.h

@@ -100,7 +100,9 @@ const char *acpi_get_sysname (void);
 int acpi_request_vector (u32 int_type);
 int acpi_get_prt (struct pci_vector_struct **vectors, int *count);
 int acpi_get_interrupt_model (int *type);
+int acpi_register_irq (u32 gsi, u32 polarity, u32 trigger);
 int acpi_irq_to_vector (u32 irq);
+int acpi_get_addr_space (void *obj, u8 type, u64 *base, u64 *length,u64 *tra);
 
 #ifdef CONFIG_ACPI_NUMA
 #include <asm/numa.h>

include/asm-ia64/atomic.h

@@ -55,6 +55,13 @@ ia64_atomic_sub (int i, atomic_t *v)
 	return new;
 }
 
+#define atomic_add_return(i,v)						\
+	((__builtin_constant_p(i) &&					\
+	  (   (i ==  1) || (i ==  4) || (i ==  8) || (i ==  16)		\
+	   || (i == -1) || (i == -4) || (i == -8) || (i == -16)))	\
+	 ? ia64_fetch_and_add(i, &(v)->counter)				\
+	 : ia64_atomic_add(i, v))
+
 /*
  * Atomically add I to V and return TRUE if the resulting value is
  * negative.
@@ -62,15 +69,9 @@ ia64_atomic_sub (int i, atomic_t *v)
 static __inline__ int
 atomic_add_negative (int i, atomic_t *v)
 {
-	return ia64_atomic_add(i, v) < 0;
+	return atomic_add_return(i, v) < 0;
 }
 
-#define atomic_add_return(i,v)						\
-	((__builtin_constant_p(i) &&					\
-	  (   (i ==  1) || (i ==  4) || (i ==  8) || (i ==  16)		\
-	   || (i == -1) || (i == -4) || (i == -8) || (i == -16)))	\
-	 ? ia64_fetch_and_add(i, &(v)->counter)				\
-	 : ia64_atomic_add(i, v))
 
 #define atomic_sub_return(i,v)						\
 	((__builtin_constant_p(i) &&					\

include/asm-ia64/bitops.h

@@ -275,7 +275,7 @@ __test_and_change_bit (int nr, void *addr)
 }
 
 static __inline__ int
-test_bit (int nr, volatile void *addr)
+test_bit (int nr, const volatile void *addr)
 {
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }

include/asm-ia64/fpu.h

@@ -2,7 +2,7 @@
 #define _ASM_IA64_FPU_H
 
 /*
- * Copyright (C) 1998, 1999, 2002 Hewlett-Packard Co
+ * Copyright (C) 1998, 1999, 2002, 2003 Hewlett-Packard Co
  *	David Mosberger-Tang <davidm@hpl.hp.com>
  */
 
@@ -57,8 +57,9 @@
 struct ia64_fpreg {
 	union {
 		unsigned long bits[2];
+		long double __dummy;	/* force 16-byte alignment */
 	} u;
-} __attribute__ ((aligned (16)));
+};
 
 # endif /* __ASSEMBLY__ */
 

include/asm-ia64/ia32.h

@@ -214,8 +214,11 @@ typedef struct siginfo32 {
 
 		/* POSIX.1b timers */
 		struct {
-			unsigned int _timer1;
-			unsigned int _timer2;
+			timer_t _tid;		/* timer id */
+			int _overrun;		/* overrun count */
+			char _pad[sizeof(unsigned int) - sizeof(int)];
+			sigval_t32 _sigval;	/* same as below */
+			int _sys_private;       /* not to be passed to user */
 		} _timer;
 
 		/* POSIX.1b signals */

include/asm-ia64/intrinsics.h

@@ -46,14 +46,10 @@ extern unsigned long __bad_increment_for_ia64_fetch_and_add (void);
 		IA64_FETCHADD(_tmp, _v, -8, sizeof(*(v)));				\
 	else if ((i) == -4)								\
 		IA64_FETCHADD(_tmp, _v, -4, sizeof(*(v)));				\
-	else if ((i) == -2)								\
-		IA64_FETCHADD(_tmp, _v, -2, sizeof(*(v)));				\
 	else if ((i) == -1)								\
 		IA64_FETCHADD(_tmp, _v, -1, sizeof(*(v)));				\
 	else if ((i) == 1)								\
 		IA64_FETCHADD(_tmp, _v, 1, sizeof(*(v)));				\
-	else if ((i) == 2)								\
-		IA64_FETCHADD(_tmp, _v, 2, sizeof(*(v)));				\
 	else if ((i) == 4)								\
 		IA64_FETCHADD(_tmp, _v, 4, sizeof(*(v)));				\
 	else if ((i) == 8)								\

include/asm-ia64/io.h

@@ -69,22 +69,6 @@ phys_to_virt (unsigned long address)
  */
 #define __ia64_mf_a()	__asm__ __volatile__ ("mf.a" ::: "memory")
 
-/**
- * __ia64_mmiob - I/O space memory barrier
- *
- * Acts as a memory mapped I/O barrier for platforms that queue writes to
- * I/O space.  This ensures that subsequent writes to I/O space arrive after
- * all previous writes.  For most ia64 platforms, this is a simple
- * 'mf.a' instruction, so the address is ignored.  For other platforms,
- * the address may be required to ensure proper ordering of writes to I/O space
- * since a 'dummy' read might be necessary to barrier the write operation.
- */
-static inline void
-__ia64_mmiob (void)
-{
-	__ia64_mf_a();
-}
-
 static inline const unsigned long
 __ia64_get_io_port_base (void)
 {
@@ -287,7 +271,6 @@ __outsl (unsigned long port, void *src, unsigned long count)
 #define __outb		platform_outb
 #define __outw		platform_outw
 #define __outl		platform_outl
-#define __mmiob         platform_mmiob
 
 #define inb(p)		__inb(p)
 #define inw(p)		__inw(p)
@@ -301,31 +284,35 @@ __outsl (unsigned long port, void *src, unsigned long count)
 #define outsb(p,s,c)	__outsb(p,s,c)
 #define outsw(p,s,c)	__outsw(p,s,c)
 #define outsl(p,s,c)	__outsl(p,s,c)
-#define mmiob()		__mmiob()
 
 /*
  * The address passed to these functions are ioremap()ped already.
+ *
+ * We need these to be machine vectors since some platforms don't provide
+ * DMA coherence via PIO reads (PCI drivers and the spec imply that this is
+ * a good idea).  Writes are ok though for all existing ia64 platforms (and
+ * hopefully it'll stay that way).
  */
 static inline unsigned char
-__readb (void *addr)
+__ia64_readb (void *addr)
 {
 	return *(volatile unsigned char *)addr;
 }
 
 static inline unsigned short
-__readw (void *addr)
+__ia64_readw (void *addr)
 {
 	return *(volatile unsigned short *)addr;
 }
 
 static inline unsigned int
-__readl (void *addr)
+__ia64_readl (void *addr)
 {
 	return *(volatile unsigned int *) addr;
 }
 
 static inline unsigned long
-__readq (void *addr)
+__ia64_readq (void *addr)
 {
 	return *(volatile unsigned long *) addr;
 }
@@ -354,6 +341,11 @@ __writeq (unsigned long val, void *addr)
 	*(volatile unsigned long *) addr = val;
 }
 
+#define __readb		platform_readb
+#define __readw		platform_readw
+#define __readl		platform_readl
+#define __readq		platform_readq
+
 #define readb(a)	__readb((void *)(a))
 #define readw(a)	__readw((void *)(a))
 #define readl(a)	__readl((void *)(a))

include/asm-ia64/machvec.h

@@ -43,7 +43,6 @@ typedef int ia64_mv_pci_map_sg (struct pci_dev *, struct scatterlist *, int, int
 typedef void ia64_mv_pci_unmap_sg (struct pci_dev *, struct scatterlist *, int, int);
 typedef void ia64_mv_pci_dma_sync_single (struct pci_dev *, dma_addr_t, size_t, int);
 typedef void ia64_mv_pci_dma_sync_sg (struct pci_dev *, struct scatterlist *, int, int);
-typedef unsigned long ia64_mv_pci_dma_address (struct scatterlist *);
 typedef int ia64_mv_pci_dma_supported (struct pci_dev *, u64);
 
 /*
@@ -61,7 +60,10 @@ typedef unsigned int ia64_mv_inl_t (unsigned long);
 typedef void ia64_mv_outb_t (unsigned char, unsigned long);
 typedef void ia64_mv_outw_t (unsigned short, unsigned long);
 typedef void ia64_mv_outl_t (unsigned int, unsigned long);
-typedef void ia64_mv_mmiob_t (void);
+typedef unsigned char ia64_mv_readb_t (void *);
+typedef unsigned short ia64_mv_readw_t (void *);
+typedef unsigned int ia64_mv_readl_t (void *);
+typedef unsigned long ia64_mv_readq_t (void *);
 
 extern void machvec_noop (void);
 
@@ -99,7 +101,6 @@ extern void machvec_noop (void);
 #  define platform_pci_unmap_sg		ia64_mv.unmap_sg
 #  define platform_pci_dma_sync_single	ia64_mv.sync_single
 #  define platform_pci_dma_sync_sg	ia64_mv.sync_sg
-#  define platform_pci_dma_address	ia64_mv.dma_address
 #  define platform_pci_dma_supported	ia64_mv.dma_supported
 #  define platform_irq_desc		ia64_mv.irq_desc
 #  define platform_irq_to_vector	ia64_mv.irq_to_vector
@@ -110,7 +111,10 @@ extern void machvec_noop (void);
 #  define platform_outb		ia64_mv.outb
 #  define platform_outw		ia64_mv.outw
 #  define platform_outl		ia64_mv.outl
-#  define platofrm_mmiob        ia64_mv.mmiob
+#  define platform_readb        ia64_mv.readb
+#  define platform_readw        ia64_mv.readw
+#  define platform_readl        ia64_mv.readl
+#  define platform_readq        ia64_mv.readq
 # endif
 
 /* __attribute__((__aligned__(16))) is required to make size of the
@@ -138,7 +142,6 @@ struct ia64_machine_vector {
 	ia64_mv_pci_unmap_sg *unmap_sg;
 	ia64_mv_pci_dma_sync_single *sync_single;
 	ia64_mv_pci_dma_sync_sg *sync_sg;
-	ia64_mv_pci_dma_address *dma_address;
 	ia64_mv_pci_dma_supported *dma_supported;
 	ia64_mv_irq_desc *irq_desc;
 	ia64_mv_irq_to_vector *irq_to_vector;
@@ -149,8 +152,11 @@ struct ia64_machine_vector {
 	ia64_mv_outb_t *outb;
 	ia64_mv_outw_t *outw;
 	ia64_mv_outl_t *outl;
-	ia64_mv_mmiob_t *mmiob;
-} __attribute__((__aligned__(16)));
+	ia64_mv_readb_t *readb;
+	ia64_mv_readw_t *readw;
+	ia64_mv_readl_t *readl;
+	ia64_mv_readq_t *readq;
+};
 
 #define MACHVEC_INIT(name)			\
 {						\
@@ -173,7 +179,6 @@ struct ia64_machine_vector {
 	platform_pci_unmap_sg,			\
 	platform_pci_dma_sync_single,		\
 	platform_pci_dma_sync_sg,		\
-	platform_pci_dma_address,		\
 	platform_pci_dma_supported,		\
 	platform_irq_desc,			\
 	platform_irq_to_vector,			\
@@ -184,7 +189,10 @@ struct ia64_machine_vector {
 	platform_outb,				\
 	platform_outw,				\
 	platform_outl,				\
-        platform_mmiob                          \
+	platform_readb,				\
+	platform_readw,				\
+	platform_readl,				\
+	platform_readq,				\
 }
 
 extern struct ia64_machine_vector ia64_mv;
@@ -206,7 +214,6 @@ extern ia64_mv_pci_map_sg swiotlb_map_sg;
 extern ia64_mv_pci_unmap_sg swiotlb_unmap_sg;
 extern ia64_mv_pci_dma_sync_single swiotlb_sync_single;
 extern ia64_mv_pci_dma_sync_sg swiotlb_sync_sg;
-extern ia64_mv_pci_dma_address swiotlb_dma_address;
 extern ia64_mv_pci_dma_supported swiotlb_pci_dma_supported;
 
 /*
@@ -267,9 +274,6 @@ extern ia64_mv_pci_dma_supported swiotlb_pci_dma_supported;
 #ifndef platform_pci_dma_sync_sg
 # define platform_pci_dma_sync_sg	swiotlb_sync_sg
 #endif
-#ifndef platform_pci_dma_address
-# define  platform_pci_dma_address	swiotlb_dma_address
-#endif
 #ifndef platform_pci_dma_supported
 # define  platform_pci_dma_supported	swiotlb_pci_dma_supported
 #endif
@@ -300,8 +304,17 @@ extern ia64_mv_pci_dma_supported swiotlb_pci_dma_supported;
 #ifndef platform_outl
 # define platform_outl		__ia64_outl
 #endif
-#ifndef platform_mmiob
-# define platform_mmiob         __ia64_mmiob
+#ifndef platform_readb
+# define platform_readb		__ia64_readb
+#endif
+#ifndef platform_readw
+# define platform_readw		__ia64_readw
+#endif
+#ifndef platform_readl
+# define platform_readl		__ia64_readl
+#endif
+#ifndef platform_readq
+# define platform_readq		__ia64_readq
 #endif
 
 #endif /* _ASM_IA64_MACHVEC_H */

include/asm-ia64/machvec_hpzx1.h

@@ -8,7 +8,6 @@ extern ia64_mv_pci_map_single sba_map_single;
 extern ia64_mv_pci_unmap_single sba_unmap_single;
 extern ia64_mv_pci_map_sg sba_map_sg;
 extern ia64_mv_pci_unmap_sg sba_unmap_sg;
-extern ia64_mv_pci_dma_address sba_dma_address;
 extern ia64_mv_pci_dma_supported sba_dma_supported;
 
 /*
@@ -29,7 +28,6 @@ extern ia64_mv_pci_dma_supported sba_dma_supported;
 #define platform_pci_unmap_sg		sba_unmap_sg
 #define platform_pci_dma_sync_single	((ia64_mv_pci_dma_sync_single *) machvec_noop)
 #define platform_pci_dma_sync_sg	((ia64_mv_pci_dma_sync_sg *) machvec_noop)
-#define platform_pci_dma_address	sba_dma_address
 #define platform_pci_dma_supported	sba_dma_supported
 
 #endif /* _ASM_IA64_MACHVEC_HPZX1_h */

include/asm-ia64/machvec_init.h

@@ -16,7 +16,6 @@ extern ia64_mv_inl_t __ia64_inl;
 extern ia64_mv_outb_t __ia64_outb;
 extern ia64_mv_outw_t __ia64_outw;
 extern ia64_mv_outl_t __ia64_outl;
-extern ia64_mv_mmiob_t __ia64_mmiob;
 
 #define MACHVEC_HELPER(name)									\
  struct ia64_machine_vector machvec_##name __attribute__ ((unused, __section__ (".machvec")))	\

include/asm-ia64/machvec_sn1.h

@@ -44,7 +44,6 @@ extern ia64_mv_inl_t sn1_inl;
 extern ia64_mv_outb_t sn1_outb;
 extern ia64_mv_outw_t sn1_outw;
 extern ia64_mv_outl_t sn1_outl;
-extern ia64_mv_mmiob_t sn_mmiob;
 extern ia64_mv_pci_alloc_consistent	sn1_pci_alloc_consistent;
 extern ia64_mv_pci_free_consistent	sn1_pci_free_consistent;
 extern ia64_mv_pci_map_single		sn1_pci_map_single;
@@ -53,7 +52,6 @@ extern ia64_mv_pci_map_sg		sn1_pci_map_sg;
 extern ia64_mv_pci_unmap_sg		sn1_pci_unmap_sg;
 extern ia64_mv_pci_dma_sync_single	sn1_pci_dma_sync_single;
 extern ia64_mv_pci_dma_sync_sg		sn1_pci_dma_sync_sg;
-extern ia64_mv_pci_dma_address		sn1_dma_address;
 
 /*
  * This stuff has dual use!
@@ -74,7 +72,6 @@ extern ia64_mv_pci_dma_address		sn1_dma_address;
 #define platform_outb		sn1_outb
 #define platform_outw		sn1_outw
 #define platform_outl		sn1_outl
-#define platform_mmiob          sn_mmiob
 #define platform_pci_dma_init	machvec_noop
 #define platform_pci_alloc_consistent	sn1_pci_alloc_consistent
 #define platform_pci_free_consistent	sn1_pci_free_consistent
@@ -84,6 +81,5 @@ extern ia64_mv_pci_dma_address		sn1_dma_address;
 #define platform_pci_unmap_sg		sn1_pci_unmap_sg
 #define platform_pci_dma_sync_single	sn1_pci_dma_sync_single
 #define platform_pci_dma_sync_sg	sn1_pci_dma_sync_sg
-#define platform_pci_dma_address	sn1_dma_address
 
 #endif /* _ASM_IA64_MACHVEC_SN1_h */

include/asm-ia64/machvec_sn2.h

 /*
- * Copyright (c) 2002 Silicon Graphics, Inc.  All Rights Reserved.
+ * Copyright (c) 2002-2003 Silicon Graphics, Inc.  All Rights Reserved.
  * 
  * This program is free software; you can redistribute it and/or modify it 
  * under the terms of version 2 of the GNU General Public License 
@@ -41,13 +41,16 @@ extern ia64_mv_global_tlb_purge_t sn2_global_tlb_purge;
 extern ia64_mv_irq_desc sn_irq_desc;
 extern ia64_mv_irq_to_vector sn_irq_to_vector;
 extern ia64_mv_local_vector_to_irq sn_local_vector_to_irq;
-extern ia64_mv_inb_t sn_inb;
-extern ia64_mv_inw_t sn_inw;
-extern ia64_mv_inl_t sn_inl;
-extern ia64_mv_outb_t sn_outb;
-extern ia64_mv_outw_t sn_outw;
-extern ia64_mv_outl_t sn_outl;
-extern ia64_mv_mmiob_t			sn2_mmiob;
+extern ia64_mv_inb_t __sn_inb;
+extern ia64_mv_inw_t __sn_inw;
+extern ia64_mv_inl_t __sn_inl;
+extern ia64_mv_outb_t __sn_outb;
+extern ia64_mv_outw_t __sn_outw;
+extern ia64_mv_outl_t __sn_outl;
+extern ia64_mv_readb_t __sn_readb;
+extern ia64_mv_readw_t __sn_readw;
+extern ia64_mv_readl_t __sn_readl;
+extern ia64_mv_readq_t __sn_readq;
 extern ia64_mv_pci_alloc_consistent	sn_pci_alloc_consistent;
 extern ia64_mv_pci_free_consistent	sn_pci_free_consistent;
 extern ia64_mv_pci_map_single		sn_pci_map_single;
@@ -56,7 +59,6 @@ extern ia64_mv_pci_map_sg		sn_pci_map_sg;
 extern ia64_mv_pci_unmap_sg		sn_pci_unmap_sg;
 extern ia64_mv_pci_dma_sync_single	sn_pci_dma_sync_single;
 extern ia64_mv_pci_dma_sync_sg		sn_pci_dma_sync_sg;
-extern ia64_mv_pci_dma_address		sn_dma_address;
 extern ia64_mv_pci_dma_supported	sn_pci_dma_supported;
 
 /*
@@ -72,13 +74,17 @@ extern ia64_mv_pci_dma_supported	sn_pci_dma_supported;
 #define platform_irq_init		sn_irq_init
 #define platform_send_ipi		sn2_send_IPI
 #define platform_global_tlb_purge       sn2_global_tlb_purge
-#define platform_inb			sn_inb
-#define platform_inw			sn_inw
-#define platform_inl			sn_inl
-#define platform_outb			sn_outb
-#define platform_outw			sn_outw
-#define platform_outl			sn_outl
-#define platform_mmiob			sn2_mmiob
+#define platform_pci_fixup		sn_pci_fixup
+#define platform_inb			__sn_inb
+#define platform_inw			__sn_inw
+#define platform_inl			__sn_inl
+#define platform_outb			__sn_outb
+#define platform_outw			__sn_outw
+#define platform_outl			__sn_outl
+#define platform_readb			__sn_readb
+#define platform_readw			__sn_readw
+#define platform_readl			__sn_readl
+#define platform_readq			__sn_readq
 #define platform_irq_desc		sn_irq_desc
 #define platform_irq_to_vector		sn_irq_to_vector
 #define platform_local_vector_to_irq	sn_local_vector_to_irq
@@ -91,7 +97,6 @@ extern ia64_mv_pci_dma_supported	sn_pci_dma_supported;
 #define platform_pci_unmap_sg		sn_pci_unmap_sg
 #define platform_pci_dma_sync_single	sn_pci_dma_sync_single
 #define platform_pci_dma_sync_sg	sn_pci_dma_sync_sg
-#define platform_pci_dma_address	sn_dma_address
 #define platform_pci_dma_supported	sn_pci_dma_supported
 
 #endif /* _ASM_IA64_MACHVEC_SN2_H */

include/asm-ia64/mca.h

@@ -24,7 +24,7 @@ enum {
 	IA64_MCA_FAILURE	=	1
 };
 
-#define IA64_MCA_RENDEZ_TIMEOUT		(100 * HZ)	/* 1000 milliseconds */
+#define IA64_MCA_RENDEZ_TIMEOUT		(20 * 1000)	/* value in milliseconds - 20 seconds */
 
 #define IA64_CMC_INT_DISABLE		0
 #define IA64_CMC_INT_ENABLE		1

include/asm-ia64/module.h

 #ifndef _ASM_IA64_MODULE_H
 #define _ASM_IA64_MODULE_H
 
-/* Module support currently broken (due to in-kernel module loader).  */
+/*
+ * IA-64-specific support for kernel module loader.
+ *
+ * Copyright (C) 2003 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ */
+
+struct elf64_shdr;			/* forward declration */
+
+struct mod_arch_specific {
+	struct elf64_shdr *core_plt;	/* core PLT section */
+	struct elf64_shdr *init_plt;	/* init PLT section */
+	struct elf64_shdr *got;		/* global offset table */
+	struct elf64_shdr *opd;		/* official procedure descriptors */
+	struct elf64_shdr *unwind;	/* unwind-table section */
+	unsigned long gp;		/* global-pointer for module */
+
+	void *unw_table;		/* unwind-table cookie returned by unwinder */
+	unsigned int next_got_entry;	/* index of next available got entry */
+};
+
+#define Elf_Shdr	Elf64_Shdr
+#define Elf_Sym		Elf64_Sym
+#define Elf_Ehdr	Elf64_Ehdr
+
+#define MODULE_PROC_FAMILY	"ia64"
+#define MODULE_ARCH_VERMAGIC	MODULE_PROC_FAMILY
+
+#define ARCH_SHF_SMALL	SHF_IA_64_SHORT
 
 #endif /* _ASM_IA64_MODULE_H */

include/asm-ia64/pci.h

@@ -21,7 +21,7 @@
 #define PCIBIOS_MIN_MEM		0x10000000
 
 void pcibios_config_init(void);
-struct pci_bus * pcibios_scan_root(int bus);
+struct pci_bus * pcibios_scan_root(void *acpi_handle, int segment, int bus);
 
 struct pci_dev;
 
@@ -58,7 +58,6 @@ extern int pcibios_prep_mwi (struct pci_dev *);
 #define pci_unmap_sg			platform_pci_unmap_sg
 #define pci_dma_sync_single		platform_pci_dma_sync_single
 #define pci_dma_sync_sg			platform_pci_dma_sync_sg
-#define sg_dma_address			platform_pci_dma_address
 #define pci_dma_supported		platform_pci_dma_supported
 
 /* pci_unmap_{single,page} is not a nop, thus... */
@@ -92,11 +91,23 @@ extern int pcibios_prep_mwi (struct pci_dev *);
 #define pci_controller_num(PDEV)	(0)
 
 #define sg_dma_len(sg)		((sg)->dma_length)
+#define sg_dma_address(sg)	((sg)->dma_address)
 
 #define HAVE_PCI_MMAP
 extern int pci_mmap_page_range (struct pci_dev *dev, struct vm_area_struct *vma,
 				enum pci_mmap_state mmap_state, int write_combine);
 
+struct pci_controller {
+	void *acpi_handle;
+	void *iommu;
+	int segment;
+
+	u64 mem_offset;
+};
+
+#define PCI_CONTROLLER(busdev) ((struct pci_controller *) busdev->sysdata)
+#define PCI_SEGMENT(busdev)    (PCI_CONTROLLER(busdev)->segment)
+
 /* generic pci stuff */
 #include <asm-generic/pci.h>
 

include/asm-ia64/processor.h

@@ -379,7 +379,7 @@ extern unsigned long get_wchan (struct task_struct *p);
 static inline unsigned long
 ia64_get_kr (unsigned long regnum)
 {
-	unsigned long r;
+	unsigned long r = 0;
 
 	switch (regnum) {
 	      case 0: asm volatile ("mov %0=ar.k0" : "=r"(r)); break;

include/asm-ia64/sal.h

@@ -37,13 +37,23 @@ extern spinlock_t sal_lock;
 	result = (*ia64_sal)(a0,a1,a2,a3,a4,a5,a6,a7)
 
 # define SAL_CALL(result,args...) do {				\
-	unsigned long flags;				\
-	struct ia64_fpreg fr[6];                        \
-	ia64_save_scratch_fpregs(fr);                   \
-	spin_lock_irqsave(&sal_lock, flags);		\
-	__SAL_CALL(result,args);			\
-	spin_unlock_irqrestore(&sal_lock, flags);	\
-	ia64_load_scratch_fpregs(fr);                   \
+	unsigned long __ia64_sc_flags;				\
+	struct ia64_fpreg __ia64_sc_fr[6];			\
+	ia64_save_scratch_fpregs(__ia64_sc_fr);			\
+	spin_lock_irqsave(&sal_lock, __ia64_sc_flags);		\
+	__SAL_CALL(result, args);				\
+	spin_unlock_irqrestore(&sal_lock, __ia64_sc_flags);	\
+	ia64_load_scratch_fpregs(__ia64_sc_fr);			\
+} while (0)
+
+# define SAL_CALL_NOLOCK(result,args...) do {		\
+	unsigned long __ia64_scn_flags;			\
+	struct ia64_fpreg __ia64_scn_fr[6];		\
+	ia64_save_scratch_fpregs(__ia64_scn_fr);	\
+	local_irq_save(__ia64_scn_flags);		\
+	__SAL_CALL(result, args);			\
+	local_irq_restore(__ia64_scn_flags);		\
+	ia64_load_scratch_fpregs(__ia64_scn_fr);	\
 } while (0)
 
 #define SAL_SET_VECTORS			0x01000000
@@ -686,13 +696,14 @@ ia64_sal_get_state_info_size (u64 sal_info_type)
 
 /*
  * Causes the processor to go into a spin loop within SAL where SAL awaits a wakeup from
- * the monarch processor.
+ * the monarch processor.  Must not lock, because it will not return on any cpu until the
+ * monarch processor sends a wake up.
  */
 static inline s64
 ia64_sal_mc_rendez (void)
 {
 	struct ia64_sal_retval isrv;
-	SAL_CALL(isrv, SAL_MC_RENDEZ, 0, 0, 0, 0, 0, 0, 0);
+	SAL_CALL_NOLOCK(isrv, SAL_MC_RENDEZ, 0, 0, 0, 0, 0, 0, 0);
 	return isrv.status;
 }
 

include/asm-ia64/smp.h

@@ -3,7 +3,7 @@
  *
  * Copyright (C) 1999 VA Linux Systems
  * Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
- * Copyright (C) 2001-2002 Hewlett-Packard Co
+ * Copyright (C) 2001-2003 Hewlett-Packard Co
  *	David Mosberger-Tang <davidm@hpl.hp.com>
  */
 #ifndef _ASM_IA64_SMP_H
@@ -74,7 +74,7 @@ cpu_logical_id (int cpuid)
 	int i;
 
 	for (i = 0; i < NR_CPUS; ++i)
-		if (cpu_physical_id(i) == (__u32) cpuid)
+		if (cpu_physical_id(i) == cpuid)
 			break;
 	return i;
 }

include/asm-ia64/sn/io.h

@@ -3,8 +3,8 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
+ * Copyright (C) 2000-2003 Silicon Graphics, Inc.  All Rights Reserved.
  * Copyright (C) 2000 Ralf Baechle
- * Copyright (C) 2000-2001 Silicon Graphics, Inc.
  */
 #ifndef _ASM_IA64_SN_IO_H
 #define _ASM_IA64_SN_IO_H
@@ -78,4 +78,9 @@
 #include <asm/sn/sn2/shubio.h>
 #endif
 
+/*
+ * Used to ensure write ordering (like mb(), but for I/O space)
+ */
+extern void sn_mmiob(void);
+
 #endif /* _ASM_IA64_SN_IO_H */

include/asm-ia64/sn/sn2/io.h

+/* 
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2000-2003 Silicon Graphics, Inc. All rights reserved.
+ */
+
+#ifndef _ASM_SN_SN2_IO_H
+#define _ASM_SN_SN2_IO_H
+
+extern void * sn_io_addr(unsigned long port); /* Forward definition */
+extern void sn_mmiob(void); /* Forward definition */
+
+#define __sn_mf_a()   __asm__ __volatile__ ("mf.a" ::: "memory")
+
+extern void sn_dma_flush(unsigned long);
+
+/*
+ * The following routines are SN Platform specific, called when
+ * a reference is made to inX/outX set macros.  SN Platform
+ * inX set of macros ensures that Posted DMA writes on the
+ * Bridge is flushed.
+ *
+ * The routines should be self explainatory.
+ */
+
+static inline unsigned int
+__sn_inb (unsigned long port)
+{
+	volatile unsigned char *addr = sn_io_addr(port);
+	unsigned char ret;
+
+	ret = *addr;
+	sn_dma_flush((unsigned long)addr);
+	__sn_mf_a();
+	return ret;
+}
+
+static inline unsigned int
+__sn_inw (unsigned long port)
+{
+	volatile unsigned short *addr = sn_io_addr(port);
+	unsigned short ret;
+
+	ret = *addr;
+	sn_dma_flush((unsigned long)addr);
+	__sn_mf_a();
+	return ret;
+}
+
+static inline unsigned int
+__sn_inl (unsigned long port)
+{
+	volatile unsigned int *addr = sn_io_addr(port);
+	unsigned int ret;
+
+	ret = *addr;
+	sn_dma_flush((unsigned long)addr);
+	__sn_mf_a();
+	return ret;
+}
+
+static inline void
+__sn_outb (unsigned char val, unsigned long port)
+{
+	volatile unsigned char *addr = sn_io_addr(port);
+
+	*addr = val;
+	sn_mmiob();
+}
+
+static inline void
+__sn_outw (unsigned short val, unsigned long port)
+{
+	volatile unsigned short *addr = sn_io_addr(port);
+
+	*addr = val;
+	sn_mmiob();
+}
+
+static inline void
+__sn_outl (unsigned int val, unsigned long port)
+{
+	volatile unsigned int *addr = sn_io_addr(port);
+
+	*addr = val;
+	sn_mmiob();
+}
+
+/*
+ * The following routines are SN Platform specific, called when 
+ * a reference is made to readX/writeX set macros.  SN Platform 
+ * readX set of macros ensures that Posted DMA writes on the 
+ * Bridge is flushed.
+ * 
+ * The routines should be self explainatory.
+ */
+
+static inline unsigned char
+__sn_readb (void *addr)
+{
+	unsigned char val;
+
+	val = *(volatile unsigned char *)addr;
+	sn_dma_flush((unsigned long)addr);
+        return val;
+}
+
+static inline unsigned short
+__sn_readw (void *addr)
+{
+	unsigned short val;
+
+	val = *(volatile unsigned short *)addr;
+	sn_dma_flush((unsigned long)addr);
+        return val;
+}
+
+static inline unsigned int
+__sn_readl (void *addr)
+{
+	unsigned int val;
+
+	val = *(volatile unsigned int *) addr;
+	sn_dma_flush((unsigned long)addr);
+        return val;
+}
+
+static inline unsigned long
+__sn_readq (void *addr)
+{
+	unsigned long val;
+
+	val = *(volatile unsigned long *) addr;
+	sn_dma_flush((unsigned long)addr);
+        return val;
+}
+
+/*
+ * For generic and SN2 kernels, we have a set of fast access
+ * PIO macros.	These macros are provided on SN Platform
+ * because the normal inX and readX macros perform an
+ * additional task of flushing Post DMA request on the Bridge.
+ *
+ * These routines should be self explainatory.
+ */
+
+static inline unsigned int
+sn_inb_fast (unsigned long port)
+{
+	volatile unsigned char *addr = (unsigned char *)port;
+	unsigned char ret;
+
+	ret = *addr;
+	__sn_mf_a();
+	return ret;
+}
+
+static inline unsigned int
+sn_inw_fast (unsigned long port)
+{
+	volatile unsigned short *addr = (unsigned short *)port;
+	unsigned short ret;
+
+	ret = *addr;
+	__sn_mf_a();
+	return ret;
+}
+
+static inline unsigned int
+sn_inl_fast (unsigned long port)
+{
+	volatile unsigned int *addr = (unsigned int *)port;
+	unsigned int ret;
+
+	ret = *addr;
+	__sn_mf_a();
+	return ret;
+}
+
+static inline unsigned char
+sn_readb_fast (void *addr)
+{
+	return *(volatile unsigned char *)addr;
+}
+
+static inline unsigned short
+sn_readw_fast (void *addr)
+{
+	return *(volatile unsigned short *)addr;
+}
+
+static inline unsigned int
+sn_readl_fast (void *addr)
+{
+	return *(volatile unsigned int *) addr;
+}
+
+static inline unsigned long
+sn_readq_fast (void *addr)
+{
+	return *(volatile unsigned long *) addr;
+}
+
+#endif

include/asm-ia64/spinlock.h

@@ -2,7 +2,7 @@
 #define _ASM_IA64_SPINLOCK_H
 
 /*
- * Copyright (C) 1998-2002 Hewlett-Packard Co
+ * Copyright (C) 1998-2003 Hewlett-Packard Co
  *	David Mosberger-Tang <davidm@hpl.hp.com>
  * Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
  *
@@ -15,58 +15,6 @@
 #include <asm/bitops.h>
 #include <asm/atomic.h>
 
-#undef NEW_LOCK
-
-#ifdef NEW_LOCK
-
-typedef struct {
-	volatile unsigned int lock;
-} spinlock_t;
-
-#define SPIN_LOCK_UNLOCKED			(spinlock_t) { 0 }
-#define spin_lock_init(x)			((x)->lock = 0)
-
-/*
- * Streamlined test_and_set_bit(0, (x)).  We use test-and-test-and-set
- * rather than a simple xchg to avoid writing the cache-line when
- * there is contention.
- */
-#define _raw_spin_lock(x)								\
-{											\
-	register char *addr __asm__ ("r31") = (char *) &(x)->lock;			\
-											\
-	__asm__ __volatile__ (								\
-		"mov r30=1\n"								\
-		"mov ar.ccv=r0\n"							\
-		";;\n"									\
-		"cmpxchg4.acq r30=[%0],r30,ar.ccv\n"					\
-		";;\n"									\
-		"cmp.ne p15,p0=r30,r0\n"						\
-		"(p15) br.call.spnt.few b7=ia64_spinlock_contention\n"			\
-		";;\n"									\
-		"1:\n"				/* force a new bundle */		\
-		:: "r"(addr)								\
-		: "ar.ccv", "ar.pfs", "b7", "p15", "r28", "r29", "r30", "memory");	\
-}
-
-#define _raw_spin_trylock(x)								\
-({											\
-	register long result;								\
-											\
-	__asm__ __volatile__ (								\
-		"mov ar.ccv=r0\n"							\
-		";;\n"									\
-		"cmpxchg4.acq %0=[%2],%1,ar.ccv\n"					\
-		: "=r"(result) : "r"(1), "r"(&(x)->lock) : "ar.ccv", "memory");		\
-	(result == 0);									\
-})
-
-#define spin_is_locked(x)	((x)->lock != 0)
-#define _raw_spin_unlock(x)	do { barrier(); ((spinlock_t *) x)->lock = 0;} while (0)
-#define spin_unlock_wait(x)	do { barrier(); } while ((x)->lock)
-
-#else /* !NEW_LOCK */
-
 typedef struct {
 	volatile unsigned int lock;
 } spinlock_t;
@@ -123,8 +71,6 @@ do {											\
 #define _raw_spin_trylock(x)	(cmpxchg_acq(&(x)->lock, 0, 1) == 0)
 #define spin_unlock_wait(x)	do { barrier(); } while ((x)->lock)
 
-#endif /* !NEW_LOCK */
-
 typedef struct {
 	volatile int read_counter:31;
 	volatile int write_lock:1;
@@ -136,7 +82,7 @@ typedef struct {
 
 #define _raw_read_lock(rw)							\
 do {										\
-	int tmp = 0;								\
+	int __read_lock_tmp = 0;						\
 	__asm__ __volatile__ ("1:\tfetchadd4.acq %0 = [%1], 1\n"		\
 			      ";;\n"						\
 			      "tbit.nz p6,p0 = %0, 31\n"			\
@@ -151,15 +97,15 @@ do {										\
 			      "br.cond.sptk.few 1b\n"				\
 			      ";;\n"						\
 			      ".previous\n"					\
-			      : "=&r" (tmp)					\
+			      : "=&r" (__read_lock_tmp)				\
 			      : "r" (rw) : "p6", "memory");			\
 } while(0)
 
 #define _raw_read_unlock(rw)							\
 do {										\
-	int tmp = 0;								\
+	int __read_unlock_tmp = 0;						\
 	__asm__ __volatile__ ("fetchadd4.rel %0 = [%1], -1\n"			\
-			      : "=r" (tmp)					\
+			      : "=r" (__read_unlock_tmp)			\
 			      : "r" (rw)					\
 			      : "memory");					\
 } while(0)

include/asm-ia64/system.h

@@ -31,6 +31,7 @@
 #include <linux/types.h>
 
 struct pci_vector_struct {
+	__u16 segment;	/* PCI Segment number */
 	__u16 bus;	/* PCI Bus number */
 	__u32 pci_id;	/* ACPI split 16 bits device, 16 bits function (see section 6.1.1) */
 	__u8 pin;	/* PCI PIN (0 = A, 1 = B, 2 = C, 3 = D) */
@@ -108,7 +109,7 @@ ia64_insn_group_barrier (void)
 #define set_mb(var, value)	do { (var) = (value); mb(); } while (0)
 #define set_wmb(var, value)	do { (var) = (value); mb(); } while (0)
 
-#define safe_halt()         ia64_pal_halt(1)                /* PAL_HALT */
+#define safe_halt()         ia64_pal_halt_light()    /* PAL_HALT_LIGHT */
 
 /*
  * The group barrier in front of the rsm & ssm are necessary to ensure

include/asm-ia64/unaligned.h

@@ -7,8 +7,8 @@
  * The main single-value unaligned transfer routines.  Derived from
  * the Linux/Alpha version.
  *
- * Copyright (C) 1998, 1999 Hewlett-Packard Co
- * Copyright (C) 1998, 1999 David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 1998, 1999, 2003 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
  */
 #define get_unaligned(ptr) \
 	((__typeof__(*(ptr)))ia64_get_unaligned((ptr), sizeof(*(ptr))))
@@ -16,106 +16,101 @@
 #define put_unaligned(x,ptr) \
 	ia64_put_unaligned((unsigned long)(x), (ptr), sizeof(*(ptr)))
 
-/*
- * EGCS 1.1 knows about arbitrary unaligned loads.  Define some
- * packed structures to talk about such things with.
- */
 struct __una_u64 { __u64 x __attribute__((packed)); };
 struct __una_u32 { __u32 x __attribute__((packed)); };
 struct __una_u16 { __u16 x __attribute__((packed)); };
 
 static inline unsigned long
-__uldq (const unsigned long * r11)
+__uld8 (const unsigned long * addr)
 {
-	const struct __una_u64 *ptr = (const struct __una_u64 *) r11;
+	const struct __una_u64 *ptr = (const struct __una_u64 *) addr;
 	return ptr->x;
 }
 
 static inline unsigned long
-__uldl (const unsigned int * r11)
+__uld4 (const unsigned int * addr)
 {
-	const struct __una_u32 *ptr = (const struct __una_u32 *) r11;
+	const struct __una_u32 *ptr = (const struct __una_u32 *) addr;
 	return ptr->x;
 }
 
 static inline unsigned long
-__uldw (const unsigned short * r11)
+__uld2 (const unsigned short * addr)
 {
-	const struct __una_u16 *ptr = (const struct __una_u16 *) r11;
+	const struct __una_u16 *ptr = (const struct __una_u16 *) addr;
 	return ptr->x;
 }
 
 static inline void
-__ustq (unsigned long r5, unsigned long * r11)
+__ust8 (unsigned long val, unsigned long * addr)
 {
-	struct __una_u64 *ptr = (struct __una_u64 *) r11;
-	ptr->x = r5;
+	struct __una_u64 *ptr = (struct __una_u64 *) addr;
+	ptr->x = val;
 }
 
 static inline void
-__ustl (unsigned long r5, unsigned int * r11)
+__ust4 (unsigned long val, unsigned int * addr)
 {
-	struct __una_u32 *ptr = (struct __una_u32 *) r11;
-	ptr->x = r5;
+	struct __una_u32 *ptr = (struct __una_u32 *) addr;
+	ptr->x = val;
 }
 
 static inline void
-__ustw (unsigned long r5, unsigned short * r11)
+__ust2 (unsigned long val, unsigned short * addr)
 {
-	struct __una_u16 *ptr = (struct __una_u16 *) r11;
-	ptr->x = r5;
+	struct __una_u16 *ptr = (struct __una_u16 *) addr;
+	ptr->x = val;
 }
 
 
 /*
- * This function doesn't actually exist.  The idea is that when
- * someone uses the macros below with an unsupported size (datatype),
- * the linker will alert us to the problem via an unresolved reference
- * error.
+ * This function doesn't actually exist.  The idea is that when someone uses the macros
+ * below with an unsupported size (datatype), the linker will alert us to the problem via
+ * an unresolved reference error.
  */
 extern unsigned long ia64_bad_unaligned_access_length (void);
 
 #define ia64_get_unaligned(_ptr,size)						\
 ({										\
-	const void *ptr = (_ptr);				\
-	unsigned long val;					\
+	const void *__ia64_ptr = (_ptr);					\
+	unsigned long __ia64_val;						\
 										\
 	switch (size) {								\
 	      case 1:								\
-		val = *(const unsigned char *) ptr;		\
+		__ia64_val = *(const unsigned char *) __ia64_ptr;		\
 		break;								\
 	      case 2:								\
-		val = __uldw((const unsigned short *)ptr);	\
+		__ia64_val = __uld2((const unsigned short *)__ia64_ptr);	\
 		break;								\
 	      case 4:								\
-		val = __uldl((const unsigned int *)ptr);	\
+		__ia64_val = __uld4((const unsigned int *)__ia64_ptr);		\
 		break;								\
 	      case 8:								\
-		val = __uldq((const unsigned long *)ptr);	\
+		__ia64_val = __uld8((const unsigned long *)__ia64_ptr);		\
 		break;								\
 	      default:								\
-		val = ia64_bad_unaligned_access_length();	\
+		__ia64_val = ia64_bad_unaligned_access_length();		\
 	}									\
-	val;							\
+	__ia64_val;								\
 })
 
 #define ia64_put_unaligned(_val,_ptr,size)				\
 do {									\
-	const void *ptr = (_ptr);			\
-	unsigned long val = (_val);			\
+	const void *__ia64_ptr = (_ptr);				\
+	unsigned long __ia64_val = (_val);				\
 									\
 	switch (size) {							\
 	      case 1:							\
-		*(unsigned char *)ptr = (val);		\
+		*(unsigned char *)__ia64_ptr = (__ia64_val);		\
 	        break;							\
 	      case 2:							\
-		__ustw(val, (unsigned short *)ptr);	\
+		__ust2(__ia64_val, (unsigned short *)__ia64_ptr);	\
 		break;							\
 	      case 4:							\
-		__ustl(val, (unsigned int *)ptr);	\
+		__ust4(__ia64_val, (unsigned int *)__ia64_ptr);		\
 		break;							\
 	      case 8:							\
-		__ustq(val, (unsigned long *)ptr);	\
+		__ust8(__ia64_val, (unsigned long *)__ia64_ptr);	\
 		break;							\
 	      default:							\
 	    	ia64_bad_unaligned_access_length();			\