Merge tiger.hpl.hp.com:/data1/bk/vanilla/linux-2.5

into tiger.hpl.hp.com:/data1/bk/lia64/to-linus-2.5

arch/ia64/Config.help

@@ -157,6 +157,11 @@ CONFIG_PCMCIA
   and ds.o.  If you want to compile it as a module, say M here and
   read <file:Documentation/modules.txt>.
 
+CONFIG_KALLSYMS
+  Say Y here to let the kernel print out symbolic crash information and
+  symbolic stack backtraces. This increases the size of the kernel
+  somewhat, as all symbols have to be loaded into the kernel image.
+
 CONFIG_KCORE_ELF
   If you enabled support for /proc file system then the file
   /proc/kcore will contain the kernel core image. This can be used

arch/ia64/Makefile

@@ -33,26 +33,25 @@ ifeq ($(CONFIG_ITANIUM_BSTEP_SPECIFIC),y)
 	CFLAGS += -mb-step
 endif
 
-HEAD := arch/$(ARCH)/kernel/head.o arch/ia64/kernel/init_task.o
+HEAD := arch/$(ARCH)/kernel/head.o arch/$(ARCH)/kernel/init_task.o
 
-core-$(CONFIG_IA64_GENERIC) 	+= arch/$(ARCH)/hp/	  arch/$(ARCH)/dig/
-core-$(CONFIG_IA64_HP_SIM)	+= arch/$(ARCH)/hp/
-core-$(CONFIG_IA64_HP_ZX1)	+= arch/$(ARCH)/hp/ 	  arch/$(ARCH)/dig/
-core-$(CONFIG_IA64_SGI_SN)	+= arch/$(ARCH)/sn/kernel arch/$(ARCH)/sn/io
+libs-y				+= arch/$(ARCH)/lib/
+core-y				+= arch/$(ARCH)/kernel/ arch/$(ARCH)/mm/
+core-$(CONFIG_IA32_SUPPORT)	+= arch/$(ARCH)/ia32/
 core-$(CONFIG_IA64_DIG) 	+= arch/$(ARCH)/dig/
+core-$(CONFIG_IA64_GENERIC) 	+= arch/$(ARCH)/hp/ arch/$(ARCH)/dig/
+core-$(CONFIG_IA64_HP_SIM)	+= arch/$(ARCH)/hp/
+core-$(CONFIG_IA64_HP_ZX1)	+= arch/$(ARCH)/hp/ arch/$(ARCH)/dig/
+core-$(CONFIG_IA64_SGI_SN)	+= arch/$(ARCH)/sn/kernel arch/$(ARCH)/sn/io \
+				   arch/$(ARCH)/sn/fakeprom
+drivers-$(CONFIG_PCI)		+= arch/$(ARCH)/pci/
+drivers-$(CONFIG_IA64_HP_ZX1)	+= arch/$(ARCH)/hp/common/ arch/$(ARCH)/hp/zx1/
 
 ifdef CONFIG_IA64_SGI_SN
 	CFLAGS			+= -DBRINGUP
         SUBDIRS         	+= arch/$(ARCH)/sn/fakeprom
 endif
 
-core-$(CONFIG_IA32_SUPPORT)	+= arch/$(ARCH)/ia32/
-
-libs-y				+= arch/$(ARCH)/lib/
-core-y				+= arch/$(ARCH)/kernel/ arch/$(ARCH)/mm/
-drivers-$(CONFIG_PCI)		+= arch/$(ARCH)/pci/
-drivers-$(CONFIG_IA64_HP_ZX1)	+= arch/$(ARCH)/hp/common/ arch/$(ARCH)/hp/zx1/
-
 MAKEBOOT = $(MAKE) -C arch/$(ARCH)/boot
 
 compressed: vmlinux

arch/ia64/config.in

@@ -267,6 +267,7 @@ choice 'Physical memory granularity'				\
 
 bool 'Kernel debugging' CONFIG_DEBUG_KERNEL
 if [ "$CONFIG_DEBUG_KERNEL" != "n" ]; then
+   bool '  Load all symbols for debugging/kksymoops' CONFIG_KALLSYMS
    bool '  Print possible IA64 hazards to console' CONFIG_IA64_PRINT_HAZARDS
    bool '  Disable VHPT' CONFIG_DISABLE_VHPT
    bool '  Magic SysRq key' CONFIG_MAGIC_SYSRQ

arch/ia64/ia32/ia32_ioctl.c

@@ -26,6 +26,12 @@
 #include <linux/if_ppp.h>
 #include <linux/ixjuser.h>
 #include <linux/i2o-dev.h>
+#include <scsi/scsi.h>
+/* Ugly hack. */
+#undef	__KERNEL__
+#include <scsi/scsi_ioctl.h>
+#define	__KERNEL__
+#include <scsi/sg.h>
 
 #include <asm/ia32.h>
 
@@ -60,6 +66,235 @@ put_dirent32 (struct dirent *d, struct linux32_dirent *d32)
 		|| put_user(d->d_reclen, &d32->d_reclen)
 		|| copy_to_user(d32->d_name, d->d_name, namelen + 1));
 }
+/*
+ *  The transform code for the SG_IO ioctl was brazenly lifted from
+ *  the Sparc64 port in the file `arch/sparc64/kernel/ioctl32.c'.
+ *  Thanks to Jakub Jelinek & Eddie C. Dost.
+ */
+typedef struct sg_io_hdr32 {
+	int interface_id;	/* [i] 'S' for SCSI generic (required) */
+	int dxfer_direction;	/* [i] data transfer direction  */
+	char  cmd_len;		/* [i] SCSI command length ( <= 16 bytes) */
+	char  mx_sb_len;		/* [i] max length to write to sbp */
+	short iovec_count;	/* [i] 0 implies no scatter gather */
+	int dxfer_len;		/* [i] byte count of data transfer */
+	int dxferp;		/* [i], [*io] points to data transfer memory
+					      or scatter gather list */
+	int cmdp;		/* [i], [*i] points to command to perform */
+	int sbp;		/* [i], [*o] points to sense_buffer memory */
+	int timeout;		/* [i] MAX_UINT->no timeout (unit: millisec) */
+	int flags;		/* [i] 0 -> default, see SG_FLAG... */
+	int pack_id;		/* [i->o] unused internally (normally) */
+	int usr_ptr;		/* [i->o] unused internally */
+	char  status;		/* [o] scsi status */
+	char  masked_status;	/* [o] shifted, masked scsi status */
+	char  msg_status;	/* [o] messaging level data (optional) */
+	char  sb_len_wr;	/* [o] byte count actually written to sbp */
+	short host_status;	/* [o] errors from host adapter */
+	short driver_status;	/* [o] errors from software driver */
+	int resid;		/* [o] dxfer_len - actual_transferred */
+	int duration;		/* [o] time taken by cmd (unit: millisec) */
+	int info;		/* [o] auxiliary information */
+} sg_io_hdr32_t;  /* 64 bytes long (on IA32) */
+
+struct iovec32 { unsigned int iov_base; int iov_len; };
+
+static int alloc_sg_iovec(sg_io_hdr_t *sgp, int uptr32)
+{
+	struct iovec32 *uiov = (struct iovec32 *) P(uptr32);
+	sg_iovec_t *kiov;
+	int i;
+
+	sgp->dxferp = kmalloc(sgp->iovec_count *
+			      sizeof(sg_iovec_t), GFP_KERNEL);
+	if (!sgp->dxferp)
+		return -ENOMEM;
+	memset(sgp->dxferp, 0,
+	       sgp->iovec_count * sizeof(sg_iovec_t));
+
+	kiov = (sg_iovec_t *) sgp->dxferp;
+	for (i = 0; i < sgp->iovec_count; i++) {
+		int iov_base32;
+		if (__get_user(iov_base32, &uiov->iov_base) ||
+		    __get_user(kiov->iov_len, &uiov->iov_len))
+			return -EFAULT;
+
+		kiov->iov_base = kmalloc(kiov->iov_len, GFP_KERNEL);
+		if (!kiov->iov_base)
+			return -ENOMEM;
+		if (copy_from_user(kiov->iov_base,
+				   (void *) P(iov_base32),
+				   kiov->iov_len))
+			return -EFAULT;
+
+		uiov++;
+		kiov++;
+	}
+
+	return 0;
+}
+
+static int copy_back_sg_iovec(sg_io_hdr_t *sgp, int uptr32)
+{
+	struct iovec32 *uiov = (struct iovec32 *) P(uptr32);
+	sg_iovec_t *kiov = (sg_iovec_t *) sgp->dxferp;
+	int i;
+
+	for (i = 0; i < sgp->iovec_count; i++) {
+		int iov_base32;
+
+		if (__get_user(iov_base32, &uiov->iov_base))
+			return -EFAULT;
+
+		if (copy_to_user((void *) P(iov_base32),
+				 kiov->iov_base,
+				 kiov->iov_len))
+			return -EFAULT;
+
+		uiov++;
+		kiov++;
+	}
+
+	return 0;
+}
+
+static void free_sg_iovec(sg_io_hdr_t *sgp)
+{
+	sg_iovec_t *kiov = (sg_iovec_t *) sgp->dxferp;
+	int i;
+
+	for (i = 0; i < sgp->iovec_count; i++) {
+		if (kiov->iov_base) {
+			kfree(kiov->iov_base);
+			kiov->iov_base = NULL;
+		}
+		kiov++;
+	}
+	kfree(sgp->dxferp);
+	sgp->dxferp = NULL;
+}
+
+static int sg_ioctl_trans(unsigned int fd, unsigned int cmd, unsigned long arg)
+{
+	sg_io_hdr32_t *sg_io32;
+	sg_io_hdr_t sg_io64;
+	int dxferp32, cmdp32, sbp32;
+	mm_segment_t old_fs;
+	int err = 0;
+
+	sg_io32 = (sg_io_hdr32_t *)arg;
+	err = __get_user(sg_io64.interface_id, &sg_io32->interface_id);
+	err |= __get_user(sg_io64.dxfer_direction, &sg_io32->dxfer_direction);
+	err |= __get_user(sg_io64.cmd_len, &sg_io32->cmd_len);
+	err |= __get_user(sg_io64.mx_sb_len, &sg_io32->mx_sb_len);
+	err |= __get_user(sg_io64.iovec_count, &sg_io32->iovec_count);
+	err |= __get_user(sg_io64.dxfer_len, &sg_io32->dxfer_len);
+	err |= __get_user(sg_io64.timeout, &sg_io32->timeout);
+	err |= __get_user(sg_io64.flags, &sg_io32->flags);
+	err |= __get_user(sg_io64.pack_id, &sg_io32->pack_id);
+
+	sg_io64.dxferp = NULL;
+	sg_io64.cmdp = NULL;
+	sg_io64.sbp = NULL;
+
+	err |= __get_user(cmdp32, &sg_io32->cmdp);
+	sg_io64.cmdp = kmalloc(sg_io64.cmd_len, GFP_KERNEL);
+	if (!sg_io64.cmdp) {
+		err = -ENOMEM;
+		goto out;
+	}
+	if (copy_from_user(sg_io64.cmdp,
+			   (void *) P(cmdp32),
+			   sg_io64.cmd_len)) {
+		err = -EFAULT;
+		goto out;
+	}
+
+	err |= __get_user(sbp32, &sg_io32->sbp);
+	sg_io64.sbp = kmalloc(sg_io64.mx_sb_len, GFP_KERNEL);
+	if (!sg_io64.sbp) {
+		err = -ENOMEM;
+		goto out;
+	}
+	if (copy_from_user(sg_io64.sbp,
+			   (void *) P(sbp32),
+			   sg_io64.mx_sb_len)) {
+		err = -EFAULT;
+		goto out;
+	}
+
+	err |= __get_user(dxferp32, &sg_io32->dxferp);
+	if (sg_io64.iovec_count) {
+		int ret;
+
+		if ((ret = alloc_sg_iovec(&sg_io64, dxferp32))) {
+			err = ret;
+			goto out;
+		}
+	} else {
+		sg_io64.dxferp = kmalloc(sg_io64.dxfer_len, GFP_KERNEL);
+		if (!sg_io64.dxferp) {
+			err = -ENOMEM;
+			goto out;
+		}
+		if (copy_from_user(sg_io64.dxferp,
+				   (void *) P(dxferp32),
+				   sg_io64.dxfer_len)) {
+			err = -EFAULT;
+			goto out;
+		}
+	}
+
+	/* Unused internally, do not even bother to copy it over. */
+	sg_io64.usr_ptr = NULL;
+
+	if (err)
+		return -EFAULT;
+
+	old_fs = get_fs();
+	set_fs (KERNEL_DS);
+	err = sys_ioctl (fd, cmd, (unsigned long) &sg_io64);
+	set_fs (old_fs);
+
+	if (err < 0)
+		goto out;
+
+	err = __put_user(sg_io64.pack_id, &sg_io32->pack_id);
+	err |= __put_user(sg_io64.status, &sg_io32->status);
+	err |= __put_user(sg_io64.masked_status, &sg_io32->masked_status);
+	err |= __put_user(sg_io64.msg_status, &sg_io32->msg_status);
+	err |= __put_user(sg_io64.sb_len_wr, &sg_io32->sb_len_wr);
+	err |= __put_user(sg_io64.host_status, &sg_io32->host_status);
+	err |= __put_user(sg_io64.driver_status, &sg_io32->driver_status);
+	err |= __put_user(sg_io64.resid, &sg_io32->resid);
+	err |= __put_user(sg_io64.duration, &sg_io32->duration);
+	err |= __put_user(sg_io64.info, &sg_io32->info);
+	err |= copy_to_user((void *)P(sbp32), sg_io64.sbp, sg_io64.mx_sb_len);
+	if (sg_io64.dxferp) {
+		if (sg_io64.iovec_count)
+			err |= copy_back_sg_iovec(&sg_io64, dxferp32);
+		else
+			err |= copy_to_user((void *)P(dxferp32),
+					    sg_io64.dxferp,
+					    sg_io64.dxfer_len);
+	}
+	if (err)
+		err = -EFAULT;
+
+out:
+	if (sg_io64.cmdp)
+		kfree(sg_io64.cmdp);
+	if (sg_io64.sbp)
+		kfree(sg_io64.sbp);
+	if (sg_io64.dxferp) {
+		if (sg_io64.iovec_count) {
+			free_sg_iovec(&sg_io64);
+		} else {
+			kfree(sg_io64.dxferp);
+		}
+	}
+	return err;
+}
 
 asmlinkage long
 sys32_ioctl (unsigned int fd, unsigned int cmd, unsigned int arg)
@@ -271,6 +506,9 @@ sys32_ioctl (unsigned int fd, unsigned int cmd, unsigned int arg)
 	      default:
 		return sys_ioctl(fd, cmd, (unsigned long)arg);
 
+		case IOCTL_NR(SG_IO):
+			return(sg_ioctl_trans(fd, cmd, arg));
+
 	}
 	printk("%x:unimplemented IA32 ioctl system call\n", cmd);
 	return -EINVAL;

arch/ia64/ia32/sys_ia32.c

@@ -2842,20 +2842,6 @@ putreg (struct task_struct *child, int regno, unsigned int value)
 	}
 }
 
-static inline void
-ia32f2ia64f (void *dst, void *src)
-{
-	asm volatile ("ldfe f6=[%1];; stf.spill [%0]=f6" :: "r"(dst), "r"(src) : "memory");
-	return;
-}
-
-static inline void
-ia64f2ia32f (void *dst, void *src)
-{
-	asm volatile ("ldf.fill f6=[%1];; stfe [%0]=f6" :: "r"(dst),  "r"(src) : "memory");
-	return;
-}
-
 static void
 put_fpreg (int regno, struct _fpreg_ia32 *reg, struct pt_regs *ptp, struct switch_stack *swp,
 	   int tos)

arch/ia64/kernel/acpi.c

@@ -8,6 +8,9 @@
  *  Copyright (C) 2000 Intel Corp.
  *  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) 2002 Erich Focht <efocht@ess.nec.de>
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
@@ -43,6 +46,7 @@
 #include <asm/machvec.h>
 #include <asm/page.h>
 #include <asm/system.h>
+#include <asm/numa.h>
 
 
 #define PREFIX			"ACPI: "
@@ -447,6 +451,158 @@ acpi_parse_madt (unsigned long phys_addr, unsigned long size)
 }
 
 
+#ifdef CONFIG_ACPI_NUMA
+
+#define SLIT_DEBUG
+
+#define PXM_FLAG_LEN ((MAX_PXM_DOMAINS + 1)/32)
+
+static int __initdata srat_num_cpus;			/* number of cpus */
+static u32 __initdata pxm_flag[PXM_FLAG_LEN];
+#define pxm_bit_set(bit)	(set_bit(bit,(void *)pxm_flag))
+#define pxm_bit_test(bit)	(test_bit(bit,(void *)pxm_flag))
+/* maps to convert between proximity domain and logical node ID */
+int __initdata pxm_to_nid_map[MAX_PXM_DOMAINS];
+int __initdata nid_to_pxm_map[NR_NODES];
+static struct acpi_table_slit __initdata *slit_table;
+
+/*
+ * ACPI 2.0 SLIT (System Locality Information Table)
+ * http://devresource.hp.com/devresource/Docs/TechPapers/IA64/slit.pdf
+ */
+void __init
+acpi_numa_slit_init (struct acpi_table_slit *slit)
+{
+	int i, j, node_from, node_to;
+	u32 len;
+
+	len = sizeof(struct acpi_table_header) + 8
+		+ slit->localities * slit->localities;
+	if (slit->header.length != len) {
+		printk("ACPI 2.0 SLIT: size mismatch: %d expected, %d actual\n",
+		      len, slit->header.length);
+		memset(numa_slit, 10, sizeof(numa_slit));
+		return;
+	}
+	slit_table = slit;
+}
+
+void __init
+acpi_numa_processor_affinity_init (struct acpi_table_processor_affinity *pa)
+{
+	/* record this node in proximity bitmap */
+	pxm_bit_set(pa->proximity_domain);
+
+	node_cpuid[srat_num_cpus].phys_id = (pa->apic_id << 8) | (pa->lsapic_eid);
+	/* nid should be overridden as logical node id later */
+	node_cpuid[srat_num_cpus].nid = pa->proximity_domain;
+	srat_num_cpus++;
+}
+
+void __init
+acpi_numa_memory_affinity_init (struct acpi_table_memory_affinity *ma)
+{
+	unsigned long paddr, size;
+	u8 pxm;
+	struct node_memblk_s *p, *q, *pend;
+
+	pxm = ma->proximity_domain;
+
+	/* record this node in proximity bitmap */
+	pxm_bit_set(pxm);
+
+	/* fill node memory chunk structure */
+	paddr = ma->base_addr_hi;
+	paddr = (paddr << 32) | ma->base_addr_lo;
+	size = ma->length_hi;
+	size = (size << 32) | ma->length_lo;
+
+	if (num_memblks >= NR_MEMBLKS) {
+		printk("Too many mem chunks in SRAT. Ignoring %ld MBytes at %lx\n",
+			size/(1024*1024), paddr);
+		return;
+	}
+
+	/* Insertion sort based on base address */
+	pend = &node_memblk[num_memblks];
+	for (p = &node_memblk[0]; p < pend; p++) {
+		if (paddr < p->start_paddr)
+			break;
+	}
+	if (p < pend) {
+		for (q = pend; q >= p; q--)
+			*(q + 1) = *q;
+	}
+	p->start_paddr = paddr;
+	p->size = size;
+	p->nid = pxm;
+	num_memblks++;
+}
+
+void __init
+acpi_numa_arch_fixup(void)
+{
+	int i, j;
+
+	/* calculate total number of nodes in system from PXM bitmap */
+	numnodes = 0;		/* init total nodes in system */
+
+	memset(pxm_to_nid_map, -1, sizeof(pxm_to_nid_map));
+	memset(nid_to_pxm_map, -1, sizeof(nid_to_pxm_map));
+	for (i = 0; i < MAX_PXM_DOMAINS; i++) {
+		if (pxm_bit_test(i)) {
+			pxm_to_nid_map[i] = numnodes;
+			nid_to_pxm_map[numnodes++] = i;
+		}
+	}
+
+	/* set logical node id in memory chunk structure */
+	for (i = 0; i < num_memblks; i++)
+		node_memblk[i].nid = pxm_to_nid_map[node_memblk[i].nid];
+
+	/* assign memory bank numbers for each chunk on each node */
+	for (i = 0; i < numnodes; i++) {
+		int bank;
+
+		bank = 0;
+		for (j = 0; j < num_memblks; j++)
+			if (node_memblk[j].nid == i)
+				node_memblk[j].bank = bank++;
+	}
+
+	/* set logical node id in cpu structure */
+	for (i = 0; i < srat_num_cpus; i++)
+		node_cpuid[i].nid = pxm_to_nid_map[node_cpuid[i].nid];
+
+	printk("Number of logical nodes in system = %d\n", numnodes);
+	printk("Number of memory chunks in system = %d\n", num_memblks);
+
+	if (!slit_table) return;
+	memset(numa_slit, -1, sizeof(numa_slit));
+	for (i=0; i<slit_table->localities; i++) {
+		if (!pxm_bit_test(i))
+			continue;
+		node_from = pxm_to_nid_map[i];
+		for (j=0; j<slit_table->localities; j++) {
+			if (!pxm_bit_test(j))
+				continue;
+			node_to = pxm_to_nid_map[j];
+			node_distance(node_from, node_to) = 
+				slit_table->entry[i*slit_table->localities + j];
+		}
+	}
+
+#ifdef SLIT_DEBUG
+	printk("ACPI 2.0 SLIT locality table:\n");
+	for (i = 0; i < numnodes; i++) {
+		for (j = 0; j < numnodes; j++)
+			printk("%03d ", node_distance(i,j));
+		printk("\n");
+	}
+#endif
+}
+#endif /* CONFIG_ACPI_NUMA */
+
 static int __init
 acpi_parse_fadt (unsigned long phys_addr, unsigned long size)
 {
@@ -556,12 +712,6 @@ acpi_parse_spcr (unsigned long phys_addr, unsigned long size)
 int __init
 acpi_boot_init (char *cmdline)
 {
-	int result;
-
-	/* Initialize the ACPI boot-time table parser */
-	result = acpi_table_init(cmdline);
-	if (result)
-		return result;
 
 	/*
 	 * MADT

arch/ia64/kernel/efi.c

@@ -60,67 +60,157 @@ struct proc_dir_entry *efi_dir = NULL;
 
 static unsigned long mem_limit = ~0UL;
 
-static efi_status_t
-phys_get_time (efi_time_t *tm, efi_time_cap_t *tc)
-{
-	return efi_call_phys(__va(runtime->get_time), __pa(tm), __pa(tc));
+#define efi_call_virt(f, args...)	(*(f))(args)
+
+#define STUB_GET_TIME(prefix, adjust_arg)							\
+static efi_status_t										\
+prefix##_get_time (efi_time_t *tm, efi_time_cap_t *tc)						\
+{												\
+	struct ia64_fpreg fr[6];								\
+	efi_status_t ret;									\
+												\
+	ia64_save_scratch_fpregs(fr);								\
+	ret = efi_call_##prefix((efi_get_time_t *) __va(runtime->get_time), adjust_arg(tm),	\
+				adjust_arg(tc));						\
+	ia64_load_scratch_fpregs(fr);								\
+	return ret;										\
 }
 
-static efi_status_t
-phys_set_time (efi_time_t *tm)
-{
-	return efi_call_phys(__va(runtime->set_time), __pa(tm));
+#define STUB_SET_TIME(prefix, adjust_arg)							\
+static efi_status_t										\
+prefix##_set_time (efi_time_t *tm)								\
+{												\
+	struct ia64_fpreg fr[6];								\
+	efi_status_t ret;									\
+												\
+	ia64_save_scratch_fpregs(fr);								\
+	ret = efi_call_##prefix((efi_set_time_t *) __va(runtime->set_time), adjust_arg(tm));	\
+	ia64_load_scratch_fpregs(fr);								\
+	return ret;										\
 }
 
-static efi_status_t
-phys_get_wakeup_time (efi_bool_t *enabled, efi_bool_t *pending, efi_time_t *tm)
-{
-	return efi_call_phys(__va(runtime->get_wakeup_time), __pa(enabled), __pa(pending),
-			     __pa(tm));
+#define STUB_GET_WAKEUP_TIME(prefix, adjust_arg)						\
+static efi_status_t										\
+prefix##_get_wakeup_time (efi_bool_t *enabled, efi_bool_t *pending, efi_time_t *tm)		\
+{												\
+	struct ia64_fpreg fr[6];								\
+	efi_status_t ret;									\
+												\
+	ia64_save_scratch_fpregs(fr);								\
+	ret = efi_call_##prefix((efi_get_wakeup_time_t *) __va(runtime->get_wakeup_time),	\
+				adjust_arg(enabled), adjust_arg(pending), adjust_arg(tm));	\
+	ia64_load_scratch_fpregs(fr);								\
+	return ret;										\
 }
 
-static efi_status_t
-phys_set_wakeup_time (efi_bool_t enabled, efi_time_t *tm)
-{
-	return efi_call_phys(__va(runtime->set_wakeup_time), enabled, __pa(tm));
+#define STUB_SET_WAKEUP_TIME(prefix, adjust_arg)						\
+static efi_status_t										\
+prefix##_set_wakeup_time (efi_bool_t enabled, efi_time_t *tm)					\
+{												\
+	struct ia64_fpreg fr[6];								\
+	efi_status_t ret;									\
+												\
+	ia64_save_scratch_fpregs(fr);								\
+	ret = efi_call_##prefix((efi_set_wakeup_time_t *) __va(runtime->set_wakeup_time),	\
+				enabled, adjust_arg(tm));					\
+	ia64_load_scratch_fpregs(fr);								\
+	return ret;										\
 }
 
-static efi_status_t
-phys_get_variable (efi_char16_t *name, efi_guid_t *vendor, u32 *attr,
-		   unsigned long *data_size, void *data)
-{
-	return efi_call_phys(__va(runtime->get_variable), __pa(name), __pa(vendor), __pa(attr),
-			     __pa(data_size), __pa(data));
+#define STUB_GET_VARIABLE(prefix, adjust_arg)						\
+static efi_status_t									\
+prefix##_get_variable (efi_char16_t *name, efi_guid_t *vendor, u32 *attr,		\
+		       unsigned long *data_size, void *data)				\
+{											\
+	struct ia64_fpreg fr[6];							\
+	efi_status_t ret;								\
+											\
+	ia64_save_scratch_fpregs(fr);							\
+	ret = efi_call_##prefix((efi_get_variable_t *) __va(runtime->get_variable),	\
+				adjust_arg(name), adjust_arg(vendor), adjust_arg(attr),	\
+				adjust_arg(data_size), adjust_arg(data));		\
+	ia64_load_scratch_fpregs(fr);							\
+	return ret;									\
 }
 
-static efi_status_t
-phys_get_next_variable (unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor)
-{
-	return efi_call_phys(__va(runtime->get_next_variable), __pa(name_size), __pa(name),
-			     __pa(vendor));
+#define STUB_GET_NEXT_VARIABLE(prefix, adjust_arg)						\
+static efi_status_t										\
+prefix##_get_next_variable (unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor)	\
+{												\
+	struct ia64_fpreg fr[6];								\
+	efi_status_t ret;									\
+												\
+	ia64_save_scratch_fpregs(fr);								\
+	ret = efi_call_##prefix((efi_get_next_variable_t *) __va(runtime->get_next_variable),	\
+				adjust_arg(name_size), adjust_arg(name), adjust_arg(vendor));	\
+	ia64_load_scratch_fpregs(fr);								\
+	return ret;										\
 }
 
-static efi_status_t
-phys_set_variable (efi_char16_t *name, efi_guid_t *vendor, u32 attr,
-		   unsigned long data_size, void *data)
-{
-	return efi_call_phys(__va(runtime->set_variable), __pa(name), __pa(vendor), attr,
-			     data_size, __pa(data));
+#define STUB_SET_VARIABLE(prefix, adjust_arg)						\
+static efi_status_t									\
+prefix##_set_variable (efi_char16_t *name, efi_guid_t *vendor, u32 attr,		\
+		       unsigned long data_size, void *data)				\
+{											\
+	struct ia64_fpreg fr[6];							\
+	efi_status_t ret;								\
+											\
+	ia64_save_scratch_fpregs(fr);							\
+	ret = efi_call_##prefix((efi_set_variable_t *) __va(runtime->set_variable),	\
+				adjust_arg(name), adjust_arg(vendor), attr, data_size,	\
+				adjust_arg(data));					\
+	ia64_load_scratch_fpregs(fr);							\
+	return ret;									\
 }
 
-static efi_status_t
-phys_get_next_high_mono_count (u64 *count)
-{
-	return efi_call_phys(__va(runtime->get_next_high_mono_count), __pa(count));
+#define STUB_GET_NEXT_HIGH_MONO_COUNT(prefix, adjust_arg)					\
+static efi_status_t										\
+prefix##_get_next_high_mono_count (u64 *count)							\
+{												\
+	struct ia64_fpreg fr[6];								\
+	efi_status_t ret;									\
+												\
+	ia64_save_scratch_fpregs(fr);								\
+	ret = efi_call_##prefix((efi_get_next_high_mono_count_t *)				\
+				__va(runtime->get_next_high_mono_count), adjust_arg(count));	\
+	ia64_load_scratch_fpregs(fr);								\
+	return ret;										\
 }
 
-static void
-phys_reset_system (int reset_type, efi_status_t status,
-		   unsigned long data_size, efi_char16_t *data)
-{
-	efi_call_phys(__va(runtime->reset_system), status, data_size, __pa(data));
+#define STUB_RESET_SYSTEM(prefix, adjust_arg)					\
+static void									\
+prefix##_reset_system (int reset_type, efi_status_t status,			\
+		       unsigned long data_size, efi_char16_t *data)		\
+{										\
+	struct ia64_fpreg fr[6];						\
+										\
+	ia64_save_scratch_fpregs(fr);						\
+	efi_call_##prefix((efi_reset_system_t *) __va(runtime->reset_system),	\
+			  reset_type, status, data_size, adjust_arg(data));	\
+	/* should not return, but just in case... */				\
+	ia64_load_scratch_fpregs(fr);						\
 }
 
+STUB_GET_TIME(phys, __pa)
+STUB_SET_TIME(phys, __pa)
+STUB_GET_WAKEUP_TIME(phys, __pa)
+STUB_SET_WAKEUP_TIME(phys, __pa)
+STUB_GET_VARIABLE(phys, __pa)
+STUB_GET_NEXT_VARIABLE(phys, __pa)
+STUB_SET_VARIABLE(phys, __pa)
+STUB_GET_NEXT_HIGH_MONO_COUNT(phys, __pa)
+STUB_RESET_SYSTEM(phys, __pa)
+
+STUB_GET_TIME(virt, )
+STUB_SET_TIME(virt, )
+STUB_GET_WAKEUP_TIME(virt, )
+STUB_SET_WAKEUP_TIME(virt, )
+STUB_GET_VARIABLE(virt, )
+STUB_GET_NEXT_VARIABLE(virt, )
+STUB_SET_VARIABLE(virt, )
+STUB_GET_NEXT_HIGH_MONO_COUNT(virt, )
+STUB_RESET_SYSTEM(virt, )
+
 void
 efi_gettimeofday (struct timeval *tv)
 {
@@ -574,18 +664,17 @@ efi_enter_virtual_mode (void)
 	}
 
 	/*
-	 * Now that EFI is in virtual mode, we arrange for EFI functions to be
-	 * called directly:
+	 * Now that EFI is in virtual mode, we call the EFI functions more efficiently:
 	 */
-	efi.get_time = __va(runtime->get_time);
-	efi.set_time = __va(runtime->set_time);
-	efi.get_wakeup_time = __va(runtime->get_wakeup_time);
-	efi.set_wakeup_time = __va(runtime->set_wakeup_time);
-	efi.get_variable = __va(runtime->get_variable);
-	efi.get_next_variable = __va(runtime->get_next_variable);
-	efi.set_variable = __va(runtime->set_variable);
-	efi.get_next_high_mono_count = __va(runtime->get_next_high_mono_count);
-	efi.reset_system = __va(runtime->reset_system);
+	efi.get_time = virt_get_time;
+	efi.set_time = virt_set_time;
+	efi.get_wakeup_time = virt_get_wakeup_time;
+	efi.set_wakeup_time = virt_set_wakeup_time;
+	efi.get_variable = virt_get_variable;
+	efi.get_next_variable = virt_get_next_variable;
+	efi.set_variable = virt_set_variable;
+	efi.get_next_high_mono_count = virt_get_next_high_mono_count;
+	efi.reset_system = virt_reset_system;
 }
 
 /*

arch/ia64/kernel/fw-emu.c

@@ -2,7 +2,7 @@
  * PAL & SAL emulation.
  *
  * Copyright (C) 1998-2001 Hewlett-Packard Co
- * Copyright (C) 1998-2001 David Mosberger-Tang <davidm@hpl.hp.com>
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
  *
  * For the HP simulator, this file gets include in boot/bootloader.c.
  * For SoftSDV, this file gets included in sys_softsdv.c.

arch/ia64/kernel/iosapic.c

@@ -133,12 +133,8 @@ find_iosapic (unsigned int gsi)
 	return -1;
 }
 
-/*
- * Translate GSI number to the corresponding IA-64 interrupt vector.  If no
- * entry exists, return -1.
- */
-int
-gsi_to_vector (unsigned int gsi)
+static inline int
+_gsi_to_vector (unsigned int gsi)
 {
 	struct iosapic_intr_info *info;
 
@@ -148,6 +144,26 @@ gsi_to_vector (unsigned int gsi)
 	return -1;
 }
 
+/*
+ * Translate GSI number to the corresponding IA-64 interrupt vector.  If no
+ * entry exists, return -1.
+ */
+inline int
+gsi_to_vector (unsigned int gsi)
+{
+	return _gsi_to_vector(gsi);
+}
+
+int
+gsi_to_irq (unsigned int gsi)
+{
+	/*
+	 * XXX fix me: this assumes an identity mapping vetween IA-64 vector and Linux irq
+	 * numbers...
+	 */
+	return _gsi_to_vector(gsi);
+}
+
 static void
 set_rte (unsigned int vector, unsigned int dest)
 {
@@ -157,7 +173,7 @@ set_rte (unsigned int vector, unsigned int dest)
 	int rte_index;
 	char redir;
 
-	DBG(KERN_DEBUG"IOSAPIC: routing vector %d to %x\n", vector, dest);
+	DBG(KERN_DEBUG"IOSAPIC: routing vector %d to 0x%x\n", vector, dest);
 
 	rte_index = iosapic_intr_info[vector].rte_index;
 	if (rte_index < 0)

arch/ia64/kernel/ivt.S

@@ -116,8 +116,8 @@ ENTRY(vhpt_miss)
 	;;
 (p8)	dep r25=r18,r25,2,6
 (p8)	shr r22=r22,HPAGE_SHIFT-PAGE_SHIFT
-	;;
 #endif
+	;;
 	cmp.eq p6,p7=5,r17			// is IFA pointing into to region 5?
 	shr.u r18=r22,PGDIR_SHIFT		// get bits 33-63 of the faulting address
 	;;

arch/ia64/kernel/mca.c

@@ -1012,28 +1012,13 @@ ia64_log_prt_oem_data (int header_len, int sect_len, u8 *p_data, prfunc_t prfunc
 void
 ia64_log_rec_header_print (sal_log_record_header_t *lh, prfunc_t prfunc)
 {
-	char str_buf[32];
-
-	sprintf(str_buf, "%2d.%02d",
-		(lh->revision.major >> 4) * 10 + (lh->revision.major & 0xf),
-		(lh->revision.minor >> 4) * 10 + (lh->revision.minor & 0xf));
-	prfunc("+Err Record ID: %d    SAL Rev: %s\n", lh->id, str_buf);
-	sprintf(str_buf, "%02d/%02d/%04d/ %02d:%02d:%02d",
-		(lh->timestamp.slh_month >> 4) * 10 +
-		(lh->timestamp.slh_month & 0xf),
-		(lh->timestamp.slh_day >> 4) * 10 +
-		(lh->timestamp.slh_day & 0xf),
-		(lh->timestamp.slh_century >> 4) * 1000 +
-		(lh->timestamp.slh_century & 0xf) * 100 +
-		(lh->timestamp.slh_year >> 4) * 10 +
-		(lh->timestamp.slh_year & 0xf),
-		(lh->timestamp.slh_hour >> 4) * 10 +
-		(lh->timestamp.slh_hour & 0xf),
-		(lh->timestamp.slh_minute >> 4) * 10 +
-		(lh->timestamp.slh_minute & 0xf),
-		(lh->timestamp.slh_second >> 4) * 10 +
-		(lh->timestamp.slh_second & 0xf));
-	prfunc("+Time: %s    Severity %d\n", str_buf, lh->severity);
+	prfunc("+Err Record ID: %d    SAL Rev: %2x.%02x\n", lh->id,
+			lh->revision.major, lh->revision.minor);
+	prfunc("+Time: %02x/%02x/%02x%02x %02x:%02x:%02x    Severity %d\n",
+			lh->timestamp.slh_month, lh->timestamp.slh_day,
+			lh->timestamp.slh_century, lh->timestamp.slh_year,
+			lh->timestamp.slh_hour, lh->timestamp.slh_minute,
+			lh->timestamp.slh_second, lh->severity);
 }
 
 /*

arch/ia64/kernel/perfmon.c

@@ -63,6 +63,26 @@
  * Misc macros and definitions
  */
 #define PMU_FIRST_COUNTER	4
+#define PMU_MAX_PMCS		256
+#define PMU_MAX_PMDS		256
+
+/*
+ * type of a PMU register (bitmask).
+ * bitmask structure:
+ * 	bit0   : register implemented
+ * 	bit1   : end marker 
+ * 	bit2-3 : reserved
+ * 	bit4-7 : register type
+ * 	bit8-31: reserved
+ */
+#define PFM_REG_IMPL		0x1 /* register implemented */
+#define PFM_REG_END		0x2 /* end marker */
+#define PFM_REG_MONITOR		(0x1<<4|PFM_REG_IMPL) /* a PMC with a pmc.pm field only */
+#define PFM_REG_COUNTING	(0x2<<4|PFM_REG_IMPL) /* a PMC with a pmc.pm AND pmc.oi, a PMD used as a counter */
+#define PFM_REG_CONTROL		(0x3<<4|PFM_REG_IMPL) /* PMU control register */
+#define	PFM_REG_CONFIG		(0x4<<4|PFM_REG_IMPL) /* refine configuration */
+#define PFM_REG_BUFFER	 	(0x5<<4|PFM_REG_IMPL) /* PMD used as buffer */
+
 
 #define PFM_IS_DISABLED() pmu_conf.pfm_is_disabled
 
@@ -70,13 +90,18 @@
 #define PFM_FL_INHERIT_MASK	(PFM_FL_INHERIT_NONE|PFM_FL_INHERIT_ONCE|PFM_FL_INHERIT_ALL)
 
 /* i assume unsigned */
-#define PMC_IS_IMPL(i)	  (i<pmu_conf.num_pmcs && pmu_conf.impl_regs[i>>6] & (1UL<< (i) %64))
-#define PMD_IS_IMPL(i)	  (i<pmu_conf.num_pmds &&  pmu_conf.impl_regs[4+(i>>6)] & (1UL<<(i) % 64))
+#define PMC_IS_IMPL(i)	  (i< PMU_MAX_PMCS && (pmu_conf.pmc_desc[i].type & PFM_REG_IMPL))
+#define PMD_IS_IMPL(i)	  (i< PMU_MAX_PMDS && (pmu_conf.pmd_desc[i].type & PFM_REG_IMPL))
 
 /* XXX: these three assume that register i is implemented */
 #define PMD_IS_COUNTING(i) (pmu_conf.pmd_desc[i].type == PFM_REG_COUNTING)
 #define PMC_IS_COUNTING(i) (pmu_conf.pmc_desc[i].type == PFM_REG_COUNTING)
 #define PMC_IS_MONITOR(i)  (pmu_conf.pmc_desc[i].type == PFM_REG_MONITOR)
+#define PMC_DFL_VAL(i)     pmu_conf.pmc_desc[i].default_value
+#define PMC_RSVD_MASK(i)   pmu_conf.pmc_desc[i].reserved_mask
+#define PMD_PMD_DEP(i)	   pmu_conf.pmd_desc[i].dep_pmd[0]
+#define PMC_PMD_DEP(i)	   pmu_conf.pmc_desc[i].dep_pmd[0]
+
 
 /* k assume unsigned */
 #define IBR_IS_IMPL(k)	  (k<pmu_conf.num_ibrs)
@@ -175,19 +200,6 @@ typedef struct _pfm_smpl_buffer_desc {
 #define LOCK_PSB(p)	spin_lock(&(p)->psb_lock)
 #define UNLOCK_PSB(p)	spin_unlock(&(p)->psb_lock)
 
-/*
- * The possible type of a PMU register
- */
-typedef enum { 
-	PFM_REG_NOTIMPL, /* not implemented */
-	PFM_REG_NONE, 	 /* end marker */
-	PFM_REG_MONITOR, /* a PMC with a pmc.pm field only */
-	PFM_REG_COUNTING,/* a PMC with a pmc.pm AND pmc.oi, a PMD used as a counter */
-	PFM_REG_CONTROL, /* PMU control register */
-	PFM_REG_CONFIG,  /* refine configuration */
-	PFM_REG_BUFFER	 /* PMD used as buffer */
-} pfm_pmu_reg_type_t;
-
 /*
  * 64-bit software counter structure
  */
@@ -283,13 +295,16 @@ typedef struct {
  * dep_pmc[]: a bitmask of dependent PMC registers
  */
 typedef struct {
-	pfm_pmu_reg_type_t	type;
+	unsigned int		type;
 	int			pm_pos;
+	unsigned long		default_value;	/* power-on default value */
+	unsigned long		reserved_mask;	/* bitmask of reserved bits */
 	int			(*read_check)(struct task_struct *task, unsigned int cnum, unsigned long *val, struct pt_regs *regs);
 	int			(*write_check)(struct task_struct *task, unsigned int cnum, unsigned long *val, struct pt_regs *regs);
 	unsigned long		dep_pmd[4];
 	unsigned long		dep_pmc[4];
 } pfm_reg_desc_t;
+
 /* assume cnum is a valid monitor */
 #define PMC_PM(cnum, val)	(((val) >> (pmu_conf.pmc_desc[cnum].pm_pos)) & 0x1)
 #define PMC_WR_FUNC(cnum)	(pmu_conf.pmc_desc[cnum].write_check)
@@ -401,8 +416,6 @@ static ctl_table pfm_sysctl_root[] = {
 };
 static struct ctl_table_header *pfm_sysctl_header;
 
-static unsigned long reset_pmcs[IA64_NUM_PMC_REGS];	/* contains PAL reset values for PMCS */
-
 static void pfm_vm_close(struct vm_area_struct * area);
 
 static struct vm_operations_struct pfm_vm_ops={
@@ -422,7 +435,7 @@ static struct {
 /*
  * forward declarations
  */
-static void ia64_reset_pmu(struct task_struct *);
+static void pfm_reset_pmu(struct task_struct *);
 #ifdef CONFIG_SMP
 static void pfm_fetch_regs(int cpu, struct task_struct *task, pfm_context_t *ctx);
 #endif
@@ -2244,7 +2257,7 @@ pfm_enable(struct task_struct *task, pfm_context_t *ctx, void *arg, int count,
 		pfm_lazy_save_regs(PMU_OWNER());
 
 	/* reset all registers to stable quiet state */
-	ia64_reset_pmu(task);
+	pfm_reset_pmu(task);
 
 	/* make sure nothing starts */
 	if (ctx->ctx_fl_system) {
@@ -2307,7 +2320,7 @@ pfm_get_pmc_reset(struct task_struct *task, pfm_context_t *ctx, void *arg, int c
 
 		if (!PMC_IS_IMPL(cnum)) goto abort_mission;
 
-		tmp.reg_value = reset_pmcs[cnum];
+		tmp.reg_value = PMC_DFL_VAL(cnum);
 
 		PFM_REG_RETFLAG_SET(tmp.reg_flags, 0);
 
@@ -2998,6 +3011,8 @@ perfmon_proc_info(char *page)
 		p += sprintf(p, "CPU%-2d recorded samples : %lu\n", i, pfm_stats[i].pfm_recorded_samples_count);
 		p += sprintf(p, "CPU%-2d smpl buffer full : %lu\n", i, pfm_stats[i].pfm_full_smpl_buffer_count);
 		p += sprintf(p, "CPU%-2d owner            : %d\n", i, pmu_owners[i].owner ? pmu_owners[i].owner->pid: -1);
+		p += sprintf(p, "CPU%-2d syst_wide        : %d\n", i, per_cpu(pfm_syst_wide, i));
+		p += sprintf(p, "CPU%-2d dcr_pp           : %d\n", i, per_cpu(pfm_dcr_pp, i));
 	}
 
 	LOCK_PFS();
@@ -3398,11 +3413,10 @@ pfm_load_regs (struct task_struct *task)
  * XXX: make this routine able to work with non current context
  */
 static void
-ia64_reset_pmu(struct task_struct *task)
+pfm_reset_pmu(struct task_struct *task)
 {
 	struct thread_struct *t = &task->thread;
 	pfm_context_t *ctx = t->pfm_context;
-	unsigned long mask;
 	int i;
 
 	if (task != current) {
@@ -3415,30 +3429,27 @@ ia64_reset_pmu(struct task_struct *task)
 
 	/*
 	 * install reset values for PMC. We skip PMC0 (done above)
-	 * XX: good up to 64 PMCS
 	 */
-	mask = pmu_conf.impl_regs[0] >> 1;
-	for(i=1; mask; mask>>=1, i++) {
-		if (mask & 0x1) {
-			ia64_set_pmc(i, reset_pmcs[i]);
-			/*
-			 * When restoring context, we must restore ALL pmcs, even the ones 
-			 * that the task does not use to avoid leaks and possibly corruption
-			 * of the sesion because of configuration conflicts. So here, we 
-			 * initialize the entire set used in the context switch restore routine.
-	 		 */
-			t->pmc[i] = reset_pmcs[i];
-			DBprintk((" pmc[%d]=0x%lx\n", i, reset_pmcs[i]));
-						 
-		}
+	for (i=1; (pmu_conf.pmc_desc[i].type & PFM_REG_END) == 0; i++) {
+		if ((pmu_conf.pmc_desc[i].type & PFM_REG_IMPL) == 0) continue;
+		ia64_set_pmc(i, PMC_DFL_VAL(i));
+		/*
+		 * When restoring context, we must restore ALL pmcs, even the ones 
+		 * that the task does not use to avoid leaks and possibly corruption
+		 * of the sesion because of configuration conflicts. So here, we 
+		 * initialize the entire set used in the context switch restore routine.
+	 	 */
+		t->pmc[i] = PMC_DFL_VAL(i);
+		DBprintk(("pmc[%d]=0x%lx\n", i, t->pmc[i]));
 	}
+
 	/*
 	 * clear reset values for PMD. 
 	 * XXX: good up to 64 PMDS. Suppose that zero is a valid value.
 	 */
-	mask = pmu_conf.impl_regs[4];
-	for(i=0; mask; mask>>=1, i++) {
-		if (mask & 0x1) ia64_set_pmd(i, 0UL);
+	for (i=0; (pmu_conf.pmd_desc[i].type & PFM_REG_END) == 0; i++) {
+		if ((pmu_conf.pmd_desc[i].type & PFM_REG_IMPL) == 0) continue;
+		ia64_set_pmd(i, 0UL);
 		t->pmd[i] = 0UL;
 	}
 
@@ -4119,23 +4130,6 @@ static struct irqaction perfmon_irqaction = {
 };
 
 
-static void
-pfm_pmu_snapshot(void)
-{
-	int i;
-
-	for (i=0; i < IA64_NUM_PMC_REGS; i++) {
-		if (i >= pmu_conf.num_pmcs) break;
-		if (PMC_IS_IMPL(i)) reset_pmcs[i] = ia64_get_pmc(i);
-	}
-#ifdef CONFIG_MCKINLEY
-	/*
-	 * set the 'stupid' enable bit to power the PMU!
-	 */
-	reset_pmcs[4] |= 1UL << 23;
-#endif
-}
-
 /*
  * perfmon initialization routine, called from the initcall() table
  */
@@ -4160,6 +4154,9 @@ perfmon_init (void)
 	}
 
 	pmu_conf.perf_ovfl_val = (1UL << pm_info.pal_perf_mon_info_s.width) - 1;
+	/*
+	 * XXX: use the pfm_*_desc tables instead and simply verify with PAL
+	 */
 	pmu_conf.max_counters  = pm_info.pal_perf_mon_info_s.generic;
 	pmu_conf.num_pmcs      = find_num_pm_regs(pmu_conf.impl_regs);
 	pmu_conf.num_pmds      = find_num_pm_regs(&pmu_conf.impl_regs[4]);
@@ -4183,24 +4180,11 @@ perfmon_init (void)
 	pmu_conf.num_ibrs <<=1;
 	pmu_conf.num_dbrs <<=1;
 
-	/*
-	 * take a snapshot of all PMU registers. PAL is supposed
-	 * to configure them with stable/safe values, i.e., not
-	 * capturing anything.
-	 * We take a snapshot now, before we make any modifications. This
-	 * will become our master copy. Then we will reuse the snapshot
-	 * to reset the PMU in pfm_enable(). Using this technique, perfmon
-	 * does NOT have to know about the specific values to program for
-	 * the PMC/PMD. The safe values may be different from one CPU model to
-	 * the other.
-	 */
-	pfm_pmu_snapshot();
-
 	/*
 	 * setup the register configuration descriptions for the CPU
 	 */
-	pmu_conf.pmc_desc = pmc_desc;
-	pmu_conf.pmd_desc = pmd_desc;
+	pmu_conf.pmc_desc = pfm_pmc_desc;
+	pmu_conf.pmd_desc = pfm_pmd_desc;
 
 	/* we are all set */
 	pmu_conf.pfm_is_disabled = 0;
@@ -4222,11 +4206,34 @@ __initcall(perfmon_init);
 void
 perfmon_init_percpu (void)
 {
+	int i;
+
 	if (smp_processor_id() == 0)
 		register_percpu_irq(IA64_PERFMON_VECTOR, &perfmon_irqaction);
 
 	ia64_set_pmv(IA64_PERFMON_VECTOR);
 	ia64_srlz_d();
+
+	/*
+	 * we first initialize the PMU to a stable state.
+	 * the values may have been changed from their power-up
+	 * values by software executed before the kernel took over.
+	 *
+	 * At this point, pmu_conf has not yet been initialized
+	 *
+	 * On McKinley, this code is ineffective until PMC4 is initialized.
+	 */
+	for (i=1; (pfm_pmc_desc[i].type & PFM_REG_END) == 0;  i++) {
+		if ((pfm_pmc_desc[i].type & PFM_REG_IMPL) == 0) continue;
+		ia64_set_pmc(i, pfm_pmc_desc[i].default_value);
+	}
+	for (i=0; (pfm_pmd_desc[i].type & PFM_REG_END) == 0; i++) {
+		if ((pfm_pmd_desc[i].type & PFM_REG_IMPL) == 0) continue;
+		ia64_set_pmd(i, 0UL);
+	}
+	ia64_set_pmc(0,1UL);
+	ia64_srlz_d();
+
 }
 
 #else /* !CONFIG_PERFMON */

arch/ia64/kernel/perfmon_generic.h

+#define RDEP(x)	(1UL<<(x))
+
+#if defined(CONFIG_ITANIUM) || defined(CONFIG_MCKINLEY)
+#error "This file should only be used when CONFIG_ITANIUM and CONFIG_MCKINLEY are not defined"
+#endif
+
+static pfm_reg_desc_t pmc_desc[PMU_MAX_PMCS]={
+/* pmc0  */ { PFM_REG_CONTROL , 0, 0x1UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc1  */ { PFM_REG_CONTROL , 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc2  */ { PFM_REG_CONTROL , 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc3  */ { PFM_REG_CONTROL , 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc4  */ { PFM_REG_COUNTING, 0, 0x0UL, -1UL, NULL, NULL, {RDEP(4),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc5  */ { PFM_REG_COUNTING, 0, 0x0UL, -1UL, NULL, NULL, {RDEP(5),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc6  */ { PFM_REG_COUNTING, 0, 0x0UL, -1UL, NULL, NULL, {RDEP(6),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc7  */ { PFM_REG_COUNTING, 0, 0x0UL, -1UL, NULL, NULL, {RDEP(7),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+	     { PFM_REG_END     , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}}, /* end marker */
+};
+
+static pfm_reg_desc_t pmd_desc[PMU_MAX_PMDS]={
+/* pmd0  */ { PFM_REG_NOTIMPL , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}},
+/* pmd1  */ { PFM_REG_NOTIMPL , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}},
+/* pmd2  */ { PFM_REG_NOTIMPL , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}},
+/* pmd3  */ { PFM_REG_NOTIMPL , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}},
+/* pmd4  */ { PFM_REG_COUNTING, 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {RDEP(4),0UL, 0UL, 0UL}},
+/* pmd5  */ { PFM_REG_COUNTING, 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {RDEP(5),0UL, 0UL, 0UL}},
+/* pmd6  */ { PFM_REG_COUNTING, 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {RDEP(6),0UL, 0UL, 0UL}},
+/* pmd7  */ { PFM_REG_COUNTING, 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {RDEP(7),0UL, 0UL, 0UL}},
+	     { PFM_REG_END     , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}}, /* end marker */
+};

arch/ia64/kernel/perfmon_itanium.h

@@ -15,44 +15,44 @@
 static int pfm_ita_pmc_check(struct task_struct *task, unsigned int cnum, unsigned long *val, struct pt_regs *regs);
 static int pfm_write_ibr_dbr(int mode, struct task_struct *task, void *arg, int count, struct pt_regs *regs);
 
-static pfm_reg_desc_t pmc_desc[256]={
-/* pmc0  */ { PFM_REG_CONTROL, 0, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
-/* pmc1  */ { PFM_REG_CONTROL, 0, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
-/* pmc2  */ { PFM_REG_CONTROL, 0, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
-/* pmc3  */ { PFM_REG_CONTROL, 0, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
-/* pmc4  */ { PFM_REG_COUNTING, 6, NULL, NULL, {RDEP(4),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
-/* pmc5  */ { PFM_REG_COUNTING, 6, NULL, NULL, {RDEP(5),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
-/* pmc6  */ { PFM_REG_COUNTING, 6, NULL, NULL, {RDEP(6),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
-/* pmc7  */ { PFM_REG_COUNTING, 6, NULL, NULL, {RDEP(7),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
-/* pmc8  */ { PFM_REG_CONFIG, 0, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
-/* pmc9  */ { PFM_REG_CONFIG, 0, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
-/* pmc10 */ { PFM_REG_MONITOR, 6, NULL, NULL, {RDEP(0)|RDEP(1),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
-/* pmc11 */ { PFM_REG_MONITOR, 6, NULL, pfm_ita_pmc_check, {RDEP(2)|RDEP(3)|RDEP(17),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
-/* pmc12 */ { PFM_REG_MONITOR, 6, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(10)|RDEP(11)|RDEP(12)|RDEP(13)|RDEP(14)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
-/* pmc13 */ { PFM_REG_CONFIG, 0, NULL, pfm_ita_pmc_check, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
-	    { PFM_REG_NONE, 0, NULL, NULL, {0,}, {0,}}, /* end marker */
+static pfm_reg_desc_t pfm_pmc_desc[PMU_MAX_PMCS]={
+/* pmc0  */ { PFM_REG_CONTROL , 0, 0x1UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc1  */ { PFM_REG_CONTROL , 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc2  */ { PFM_REG_CONTROL , 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc3  */ { PFM_REG_CONTROL , 0, 0x0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc4  */ { PFM_REG_COUNTING, 6, 0x0UL, -1UL, NULL, NULL, {RDEP(4),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc5  */ { PFM_REG_COUNTING, 6, 0x0UL, -1UL, NULL, NULL, {RDEP(5),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc6  */ { PFM_REG_COUNTING, 6, 0x0UL, -1UL, NULL, NULL, {RDEP(6),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc7  */ { PFM_REG_COUNTING, 6, 0x0UL, -1UL, NULL, NULL, {RDEP(7),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc8  */ { PFM_REG_CONFIG  , 0, 0xf00000003ffffff8UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc9  */ { PFM_REG_CONFIG  , 0, 0xf00000003ffffff8UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc10 */ { PFM_REG_MONITOR , 6, 0x0UL, -1UL, NULL, NULL, {RDEP(0)|RDEP(1),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc11 */ { PFM_REG_MONITOR , 6, 0x0000000010000000UL, -1UL, NULL, pfm_ita_pmc_check, {RDEP(2)|RDEP(3)|RDEP(17),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc12 */ { PFM_REG_MONITOR , 6, 0x0UL, -1UL, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(10)|RDEP(11)|RDEP(12)|RDEP(13)|RDEP(14)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+/* pmc13 */ { PFM_REG_CONFIG  , 0, 0x0003ffff00000001UL, -1UL, NULL, pfm_ita_pmc_check, {0UL,0UL, 0UL, 0UL}, {0UL,0UL, 0UL, 0UL}},
+	    { PFM_REG_END     , 0, 0x0UL, -1UL, NULL, NULL, {0,}, {0,}}, /* end marker */
 };
 
-static pfm_reg_desc_t pmd_desc[256]={
-/* pmd0  */ { PFM_REG_BUFFER, 0, NULL, NULL, {RDEP(1),0UL, 0UL, 0UL}, {RDEP(10),0UL, 0UL, 0UL}},
-/* pmd1  */ { PFM_REG_BUFFER, 0, NULL, NULL, {RDEP(0),0UL, 0UL, 0UL}, {RDEP(10),0UL, 0UL, 0UL}},
-/* pmd2  */ { PFM_REG_BUFFER, 0, NULL, NULL, {RDEP(3)|RDEP(17),0UL, 0UL, 0UL}, {RDEP(11),0UL, 0UL, 0UL}},
-/* pmd3  */ { PFM_REG_BUFFER, 0, NULL, NULL, {RDEP(2)|RDEP(17),0UL, 0UL, 0UL}, {RDEP(11),0UL, 0UL, 0UL}},
-/* pmd4  */ { PFM_REG_COUNTING, 0, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {RDEP(4),0UL, 0UL, 0UL}},
-/* pmd5  */ { PFM_REG_COUNTING, 0, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {RDEP(5),0UL, 0UL, 0UL}},
-/* pmd6  */ { PFM_REG_COUNTING, 0, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {RDEP(6),0UL, 0UL, 0UL}},
-/* pmd7  */ { PFM_REG_COUNTING, 0, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {RDEP(7),0UL, 0UL, 0UL}},
-/* pmd8  */ { PFM_REG_BUFFER, 0, NULL, NULL, {RDEP(9)|RDEP(10)|RDEP(11)|RDEP(12)|RDEP(13)|RDEP(14)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
-/* pmd9  */ { PFM_REG_BUFFER, 0, NULL, NULL, {RDEP(8)|RDEP(10)|RDEP(11)|RDEP(12)|RDEP(13)|RDEP(14)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
-/* pmd10 */ { PFM_REG_BUFFER, 0, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(11)|RDEP(12)|RDEP(13)|RDEP(14)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
-/* pmd11 */ { PFM_REG_BUFFER, 0, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(10)|RDEP(12)|RDEP(13)|RDEP(14)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
-/* pmd12 */ { PFM_REG_BUFFER, 0, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(10)|RDEP(11)|RDEP(13)|RDEP(14)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
-/* pmd13 */ { PFM_REG_BUFFER, 0, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(10)|RDEP(11)|RDEP(12)|RDEP(14)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
-/* pmd14 */ { PFM_REG_BUFFER, 0, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(10)|RDEP(11)|RDEP(12)|RDEP(13)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
-/* pmd15 */ { PFM_REG_BUFFER, 0, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(10)|RDEP(11)|RDEP(12)|RDEP(13)|RDEP(14)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
-/* pmd16 */ { PFM_REG_BUFFER, 0, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(10)|RDEP(11)|RDEP(12)|RDEP(13)|RDEP(14)|RDEP(15),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
-/* pmd17 */ { PFM_REG_BUFFER, 0, NULL, NULL, {RDEP(2)|RDEP(3),0UL, 0UL, 0UL}, {RDEP(11),0UL, 0UL, 0UL}},
-	    { PFM_REG_NONE, 0, NULL, NULL, {0,}, {0,}}, /* end marker */
+static pfm_reg_desc_t pfm_pmd_desc[PMU_MAX_PMDS]={
+/* pmd0  */ { PFM_REG_BUFFER  , 0, 0UL, -1UL, NULL, NULL, {RDEP(1),0UL, 0UL, 0UL}, {RDEP(10),0UL, 0UL, 0UL}},
+/* pmd1  */ { PFM_REG_BUFFER  , 0, 0UL, -1UL, NULL, NULL, {RDEP(0),0UL, 0UL, 0UL}, {RDEP(10),0UL, 0UL, 0UL}},
+/* pmd2  */ { PFM_REG_BUFFER  , 0, 0UL, -1UL, NULL, NULL, {RDEP(3)|RDEP(17),0UL, 0UL, 0UL}, {RDEP(11),0UL, 0UL, 0UL}},
+/* pmd3  */ { PFM_REG_BUFFER  , 0, 0UL, -1UL, NULL, NULL, {RDEP(2)|RDEP(17),0UL, 0UL, 0UL}, {RDEP(11),0UL, 0UL, 0UL}},
+/* pmd4  */ { PFM_REG_COUNTING, 0, 0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {RDEP(4),0UL, 0UL, 0UL}},
+/* pmd5  */ { PFM_REG_COUNTING, 0, 0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {RDEP(5),0UL, 0UL, 0UL}},
+/* pmd6  */ { PFM_REG_COUNTING, 0, 0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {RDEP(6),0UL, 0UL, 0UL}},
+/* pmd7  */ { PFM_REG_COUNTING, 0, 0UL, -1UL, NULL, NULL, {0UL,0UL, 0UL, 0UL}, {RDEP(7),0UL, 0UL, 0UL}},
+/* pmd8  */ { PFM_REG_BUFFER  , 0, 0UL, -1UL, NULL, NULL, {RDEP(9)|RDEP(10)|RDEP(11)|RDEP(12)|RDEP(13)|RDEP(14)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
+/* pmd9  */ { PFM_REG_BUFFER  , 0, 0UL, -1UL, NULL, NULL, {RDEP(8)|RDEP(10)|RDEP(11)|RDEP(12)|RDEP(13)|RDEP(14)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
+/* pmd10 */ { PFM_REG_BUFFER  , 0, 0UL, -1UL, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(11)|RDEP(12)|RDEP(13)|RDEP(14)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
+/* pmd11 */ { PFM_REG_BUFFER  , 0, 0UL, -1UL, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(10)|RDEP(12)|RDEP(13)|RDEP(14)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
+/* pmd12 */ { PFM_REG_BUFFER  , 0, 0UL, -1UL, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(10)|RDEP(11)|RDEP(13)|RDEP(14)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
+/* pmd13 */ { PFM_REG_BUFFER  , 0, 0UL, -1UL, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(10)|RDEP(11)|RDEP(12)|RDEP(14)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
+/* pmd14 */ { PFM_REG_BUFFER  , 0, 0UL, -1UL, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(10)|RDEP(11)|RDEP(12)|RDEP(13)|RDEP(15)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
+/* pmd15 */ { PFM_REG_BUFFER  , 0, 0UL, -1UL, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(10)|RDEP(11)|RDEP(12)|RDEP(13)|RDEP(14)|RDEP(16),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
+/* pmd16 */ { PFM_REG_BUFFER  , 0, 0UL, -1UL, NULL, NULL, {RDEP(8)|RDEP(9)|RDEP(10)|RDEP(11)|RDEP(12)|RDEP(13)|RDEP(14)|RDEP(15),0UL, 0UL, 0UL}, {RDEP(12),0UL, 0UL, 0UL}},
+/* pmd17 */ { PFM_REG_BUFFER  , 0, 0UL, -1UL, NULL, NULL, {RDEP(2)|RDEP(3),0UL, 0UL, 0UL}, {RDEP(11),0UL, 0UL, 0UL}},
+	    { PFM_REG_END     , 0, 0UL, -1UL, NULL, NULL, {0,}, {0,}}, /* end marker */
 };
 
 static int

arch/ia64/kernel/process.c

@@ -12,6 +12,7 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/module.h>
 #include <linux/personality.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -45,8 +46,9 @@ static void
 do_show_stack (struct unw_frame_info *info, void *arg)
 {
 	unsigned long ip, sp, bsp;
+	char buf[80];			/* don't make it so big that it overflows the stack! */
 
-	printk("\nCall Trace: ");
+	printk("\nCall Trace:\n");
 	do {
 		unw_get_ip(info, &ip);
 		if (ip == 0)
@@ -54,7 +56,9 @@ do_show_stack (struct unw_frame_info *info, void *arg)
 
 		unw_get_sp(info, &sp);
 		unw_get_bsp(info, &bsp);
-		printk("[<%016lx>] sp=0x%016lx bsp=0x%016lx\n", ip, sp, bsp);
+		snprintf(buf, sizeof(buf), " [<%016lx>] %%s sp=0x%016lx bsp=0x%016lx\n",
+			 ip, sp, bsp);
+		print_symbol(buf, ip);
 	} while (unw_unwind(info) >= 0);
 }
 
@@ -94,6 +98,7 @@ show_regs (struct pt_regs *regs)
 	printk("\nPid: %d, comm: %20s\n", current->pid, current->comm);
 	printk("psr : %016lx ifs : %016lx ip  : [<%016lx>]    %s\n",
 	       regs->cr_ipsr, regs->cr_ifs, ip, print_tainted());
+	print_symbol("ip is at %s\n", ip);
 	printk("unat: %016lx pfs : %016lx rsc : %016lx\n",
 	       regs->ar_unat, regs->ar_pfs, regs->ar_rsc);
 	printk("rnat: %016lx bsps: %016lx pr  : %016lx\n",
@@ -199,10 +204,8 @@ ia64_save_extra (struct task_struct *task)
 	if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0)
 		pfm_save_regs(task);
 
-# ifdef CONFIG_SMP
 	if (__get_cpu_var(pfm_syst_wide))
 		pfm_syst_wide_update_task(task, 0);
-# endif
 #endif
 
 #ifdef CONFIG_IA32_SUPPORT
@@ -221,9 +224,8 @@ ia64_load_extra (struct task_struct *task)
 	if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0)
 		pfm_load_regs(task);
 
-# ifdef CONFIG_SMP
-	if (__get_cpu_var(pfm_syst_wide)) pfm_syst_wide_update_task(task, 1);
-# endif
+	if (__get_cpu_var(pfm_syst_wide)) 
+		pfm_syst_wide_update_task(task, 1);
 #endif
 
 #ifdef CONFIG_IA32_SUPPORT

arch/ia64/kernel/setup.c

@@ -296,6 +296,16 @@ setup_arch (char **cmdline_p)
 
 	efi_init();
 
+#ifdef CONFIG_ACPI_BOOT
+	/* Initialize the ACPI boot-time table parser */
+	acpi_table_init(*cmdline_p);
+
+#ifdef CONFIG_ACPI_NUMA
+	acpi_numa_init();
+#endif
+
+#endif /* CONFIG_APCI_BOOT */
+
 	find_memory();
 
 #if 0

arch/ia64/kernel/signal.c

@@ -41,6 +41,16 @@
 # define GET_SIGSET(k,u)	__get_user((k)->sig[0], &(u)->sig[0])
 #endif
 
+register double f16 asm ("f16"); register double f17 asm ("f17");
+register double f18 asm ("f18"); register double f19 asm ("f19");
+register double f20 asm ("f20"); register double f21 asm ("f21");
+register double f22 asm ("f22"); register double f23 asm ("f23");
+
+register double f24 asm ("f24"); register double f25 asm ("f25");
+register double f26 asm ("f26"); register double f27 asm ("f27");
+register double f28 asm ("f28"); register double f29 asm ("f29");
+register double f30 asm ("f30"); register double f31 asm ("f31");
+
 long
 ia64_rt_sigsuspend (sigset_t *uset, size_t sigsetsize, struct sigscratch *scr)
 {

arch/ia64/kernel/sys_ia64.c

@@ -282,18 +282,20 @@ sys_free_hugepages (unsigned long  addr)
 	extern int free_hugepages(struct vm_area_struct *);
 	int retval;
 
-	vma = find_vma(mm, addr);
-	if (!vma || !is_vm_hugetlb_page(vma) || (vma->vm_start != addr))
-		return -EINVAL;
-
 	down_write(&mm->mmap_sem);
 	{
+		vma = find_vma(mm, addr);
+		if (!vma || !is_vm_hugetlb_page(vma) || (vma->vm_start != addr))
+			retval = -EINVAL;
+			goto out;
+
 		spin_lock(&mm->page_table_lock);
 		{
 			retval = free_hugepages(vma);
 		}
 		spin_unlock(&mm->page_table_lock);
 	}
+out:
 	up_write(&mm->mmap_sem);
 	return retval;
 }

arch/ia64/kernel/traps.c

@@ -54,8 +54,8 @@ trap_init (void)
 	if (ia64_boot_param->fpswa) {
 		/* FPSWA fixup: make the interface pointer a kernel virtual address: */
 		fpswa_interface = __va(ia64_boot_param->fpswa);
-		major = fpswa_interface->revision & 0xffff;
-		minor = fpswa_interface->revision >> 16;
+		major = fpswa_interface->revision >> 16;
+		minor = fpswa_interface->revision & 0xffff;
 	}
 	printk("fpswa interface at %lx (rev %d.%d)\n", ia64_boot_param->fpswa, major, minor);
 }

arch/ia64/mm/Makefile

@@ -9,5 +9,6 @@
 
 obj-y	 := init.o fault.o tlb.o extable.o
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+obj-$(CONFIG_NUMA) += numa.o
 
 include $(TOPDIR)/Rules.make

arch/ia64/mm/init.c

@@ -78,7 +78,7 @@ ia64_init_addr_space (void)
 		vma->vm_mm = current->mm;
 		vma->vm_start = IA64_RBS_BOT;
 		vma->vm_end = vma->vm_start + PAGE_SIZE;
-		vma->vm_page_prot = protection_map[VM_READ | VM_WRITE];
+		vma->vm_page_prot = protection_map[VM_DATA_DEFAULT_FLAGS & 0x7];
 		vma->vm_flags = VM_READ|VM_WRITE|VM_MAYREAD|VM_MAYWRITE|VM_GROWSUP;
 		vma->vm_ops = NULL;
 		vma->vm_pgoff = 0;

arch/ia64/mm/numa.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.
+ *
+ * This file contains NUMA specific variables and functions which can
+ * be split away from DISCONTIGMEM and are used on NUMA machines with
+ * contiguous memory.
+ * 
+ *                         2002/08/07 Erich Focht <efocht@ess.nec.de>
+ */
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/mmzone.h>
+#include <asm/numa.h>
+
+/*
+ * The following structures are usually initialized by ACPI or
+ * similar mechanisms and describe the NUMA characteristics of the machine.
+ */
+int num_memblks = 0;
+struct node_memblk_s node_memblk[NR_MEMBLKS];
+struct node_cpuid_s node_cpuid[NR_CPUS];
+/*
+ * This is a matrix with "distances" between nodes, they should be
+ * proportional to the memory access latency ratios.
+ */
+u8 numa_slit[NR_NODES * NR_NODES];
+
+/* Identify which cnode a physical address resides on */
+int
+paddr_to_nid(unsigned long paddr)
+{
+	int	i;
+
+	for (i = 0; i < num_memblks; i++)
+		if (paddr >= node_memblk[i].start_paddr &&
+		    paddr < node_memblk[i].start_paddr + node_memblk[i].size)
+			break;
+
+	return (i < num_memblks) ? node_memblk[i].nid : -1;
+}

arch/ia64/pci/pci.c

@@ -141,13 +141,13 @@ pcibios_scan_root (int bus)
 /*
  *  Called after each bus is probed, but before its children are examined.
  */
-void __init
+void __devinit
 pcibios_fixup_bus (struct pci_bus *b)
 {
 	return;
 }
 
-void __init
+void __devinit
 pcibios_update_resource (struct pci_dev *dev, struct resource *root,
 			 struct resource *res, int resource)
 {
@@ -163,7 +163,7 @@ pcibios_update_resource (struct pci_dev *dev, struct resource *root,
 	/* ??? FIXME -- record old value for shutdown.  */
 }
 
-void __init
+void __devinit
 pcibios_update_irq (struct pci_dev *dev, int irq)
 {
 	pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq);
@@ -171,7 +171,7 @@ pcibios_update_irq (struct pci_dev *dev, int irq)
 	/* ??? FIXME -- record old value for shutdown.  */
 }
 
-void __init
+void __devinit
 pcibios_fixup_pbus_ranges (struct pci_bus * bus, struct pbus_set_ranges_data * ranges)
 {
 }

arch/ia64/vmlinux.lds.S

@@ -160,6 +160,14 @@ SECTIONS
   .bss : AT(ADDR(.bss) - PAGE_OFFSET)
 	{ *(.bss) *(COMMON) }
 
+  /* XXX Must this come last to avoid shifting other symbols?  --davidm */
+  __kallsyms : AT(ADDR(__kallsyms) - PAGE_OFFSET)
+	{
+	  __start___kallsyms = .;	/* All kernel symbols */
+	  *(__kallsyms)
+	  __stop___kallsyms = .;
+	}
+
   _end = .;
 
   /* Stabs debugging sections.  */

include/asm-ia64/acpi.h

@@ -97,17 +97,18 @@
 	} while (0)
 
 const char *acpi_get_sysname (void);
-int acpi_boot_init (char *cdline);
 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_irq_to_vector (u32 irq);
 
-#ifdef CONFIG_DISCONTIGMEM
-#define NODE_ARRAY_INDEX(x)	((x) / 8)	/* 8 bits/char */
-#define NODE_ARRAY_OFFSET(x)	((x) % 8)	/* 8 bits/char */
-#define MAX_PXM_DOMAINS		(256)
-#endif /* CONFIG_DISCONTIGMEM */
+#ifdef CONFIG_ACPI_NUMA
+#include <asm/numa.h>
+/* Proximity bitmap length; _PXM is at most 255 (8 bit)*/
+#define MAX_PXM_DOMAINS (256)
+extern int __initdata pxm_to_nid_map[MAX_PXM_DOMAINS];
+extern int __initdata nid_to_pxm_map[NR_NODES];
+#endif
 
 #endif /*__KERNEL__*/
 

include/asm-ia64/ia32.h

@@ -73,6 +73,17 @@ struct _fpreg_ia32 {
        unsigned short exponent;
 };
 
+struct _fpxreg_ia32 {
+        unsigned short significand[4];
+        unsigned short exponent;
+        unsigned short padding[3];
+};
+
+struct _xmmreg_ia32 {
+        unsigned int element[4];
+};
+
+
 struct _fpstate_ia32 {
        unsigned int    cw,
 		       sw,
@@ -82,7 +93,16 @@ struct _fpstate_ia32 {
 		       dataoff,
 		       datasel;
        struct _fpreg_ia32      _st[8];
-       unsigned int    status;
+       unsigned short  status;
+       unsigned short  magic;          /* 0xffff = regular FPU data only */
+
+       /* FXSR FPU environment */
+       unsigned int         _fxsr_env[6];   /* FXSR FPU env is ignored */
+       unsigned int         mxcsr;
+       unsigned int         reserved;
+       struct _fpxreg_ia32  _fxsr_st[8];    /* FXSR FPU reg data is ignored */
+       struct _xmmreg_ia32  _xmm[8];
+       unsigned int         padding[56];
 };
 
 struct sigcontext_ia32 {
@@ -486,6 +506,18 @@ extern int ia32_intercept (struct pt_regs *regs, unsigned long isr);
 extern unsigned long ia32_do_mmap (struct file *, unsigned long, unsigned long, int, int, loff_t);
 extern void ia32_load_segment_descriptors (struct task_struct *task);
 
+#define ia32f2ia64f(dst,src) \
+	do { \
+	register double f6 asm ("f6"); \
+	asm volatile ("ldfe f6=[%2];; stf.spill [%1]=f6" : "=f"(f6): "r"(dst), "r"(src) : "memory"); \
+	} while(0)
+
+#define ia64f2ia32f(dst,src) \
+	do { \
+	register double f6 asm ("f6"); \
+	asm volatile ("ldf.fill f6=[%2];; stfe [%1]=f6" : "=f"(f6): "r"(dst),  "r"(src) : "memory"); \
+	} while(0)
+
 #endif /* !CONFIG_IA32_SUPPORT */
 
 #endif /* _ASM_IA64_IA32_H */

include/asm-ia64/iosapic.h

@@ -55,6 +55,8 @@ extern void __devinit iosapic_init (unsigned long address,
 				    unsigned int gsi_base,
 				    int pcat_compat);
 extern int gsi_to_vector (unsigned int gsi);
+extern int gsi_to_irq (unsigned int gsi);
+extern void iosapic_parse_prt (void);
 extern int iosapic_register_intr (unsigned int gsi, unsigned long polarity,
 				  unsigned long edge_triggered,
 				  u32 gsi_base, char *iosapic_address);

include/asm-ia64/numa.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.
+ *
+ * This file contains NUMA specific prototypes and definitions.
+ * 
+ * 2002/08/05 Erich Focht <efocht@ess.nec.de>
+ *
+ */
+#ifndef _ASM_IA64_NUMA_H
+#define _ASM_IA64_NUMA_H
+
+#ifdef CONFIG_NUMA
+
+#ifdef CONFIG_DISCONTIGMEM
+# include <asm/mmzone.h>
+# define NR_NODES     (PLAT_MAX_COMPACT_NODES)
+# define NR_MEMBLKS   (PLAT_MAXCLUMPS)
+#else
+# define NR_NODES     (8)
+# define NR_MEMBLKS   (NR_NODES * 8)
+#endif
+
+/* Stuff below this line could be architecture independent */
+
+extern int num_memblks;		/* total number of memory chunks */
+
+/*
+ * List of node memory chunks. Filled when parsing SRAT table to
+ * obtain information about memory nodes.
+*/
+
+struct node_memblk_s {
+	unsigned long start_paddr;
+	unsigned long size;
+	int nid;		/* which logical node contains this chunk? */
+	int bank;		/* which mem bank on this node */
+};
+
+struct node_cpuid_s {
+	u16	phys_id;	/* id << 8 | eid */
+	int	nid;		/* logical node containing this CPU */
+};
+
+extern struct node_memblk_s node_memblk[NR_MEMBLKS];
+extern struct node_cpuid_s node_cpuid[NR_CPUS];
+
+/*
+ * ACPI 2.0 SLIT (System Locality Information Table)
+ * http://devresource.hp.com/devresource/Docs/TechPapers/IA64/slit.pdf
+ *
+ * This is a matrix with "distances" between nodes, they should be
+ * proportional to the memory access latency ratios.
+ */
+
+extern u8 numa_slit[NR_NODES * NR_NODES];
+#define node_distance(from,to) (numa_slit[from * numnodes + to])
+
+extern int paddr_to_nid(unsigned long paddr);
+
+#endif /* CONFIG_NUMA */
+
+#endif /* _ASM_IA64_NUMA_H */

include/asm-ia64/perfmon.h

@@ -123,7 +123,7 @@ typedef struct {
  * Define the version numbers for both perfmon as a whole and the sampling buffer format.
  */
 #define PFM_VERSION_MAJ		1U
-#define PFM_VERSION_MIN		0U
+#define PFM_VERSION_MIN		1U
 #define PFM_VERSION		(((PFM_VERSION_MAJ&0xffff)<<16)|(PFM_VERSION_MIN & 0xffff))
 
 #define PFM_SMPL_VERSION_MAJ	1U

include/asm-ia64/siginfo.h

@@ -148,8 +148,8 @@ copy_siginfo (siginfo_t *to, siginfo_t *from)
 	if (from->si_code < 0)
 		memcpy(to, from, sizeof(siginfo_t));
 	else
-		/* _sigchld is currently the largest know union member */
-		memcpy(to, from, 4*sizeof(int) + sizeof(from->_sifields._sigchld));
+		/* _sigprof is currently the largest know union member */
+		memcpy(to, from, 4*sizeof(int) + sizeof(from->_sifields._sigprof));
 }
 
 extern int copy_siginfo_from_user(siginfo_t *to, siginfo_t *from);

include/asm-ia64/sn/bte_copy.h

@@ -250,7 +250,7 @@ bte_copy(u64 src, u64 dest, u64 len, u64 mode, void *notification)
 			 * status register into the notification area.
 			 * This fakes the shub performing the copy.
 			 */
-			if (jiffies > bte->idealTransferTimeout) {
+			if (time_after(jiffies, bte->idealTransferTimeout)) {
 				bte->notify = HUB_L(bte->bte_base_addr);
 				bte->idealTransferTimeoutReached++;
 				bte->idealTransferTimeout = jiffies +

include/asm-ia64/thread_info.h

@@ -37,11 +37,11 @@ struct thread_info {
 
 #define INIT_THREAD_INFO(ti)			\
 {						\
-	exec_domain:	&default_exec_domain,	\
-	flags:		0,			\
-	cpu:		0,			\
-	addr_limit:	KERNEL_DS,		\
-	preempt_count:	0,			\
+	.exec_domain	= &default_exec_domain,	\
+	.flags		= 0,			\
+	.cpu		= 0,			\
+	.addr_limit	= KERNEL_DS,		\
+	.preempt_count	= 0,			\
 }
 
 /* how to get the thread information struct from C */

include/asm-ia64/tlb.h

@@ -53,9 +53,10 @@
 
 typedef struct {
 	struct mm_struct	*mm;
-	unsigned int		nr;	/* == ~0U => fast mode */
-	unsigned int		fullmm;	/* non-zero means full mm flush */
-	unsigned long		freed;	/* number of pages freed */
+	unsigned int		nr;		/* == ~0U => fast mode */
+	unsigned char		fullmm;		/* non-zero means full mm flush */
+	unsigned char		need_flush;	/* really unmapped some PTEs? */
+	unsigned long		freed;		/* number of pages freed */
 	unsigned long		start_addr;
 	unsigned long		end_addr;
 	struct page 		*pages[FREE_PTE_NR];
@@ -73,6 +74,10 @@ ia64_tlb_flush_mmu (mmu_gather_t *tlb, unsigned long start, unsigned long end)
 {
 	unsigned int nr;
 
+	if (!tlb->need_flush)
+		return;
+	tlb->need_flush = 0;
+
 	if (tlb->fullmm) {
 		/*
 		 * Tearing down the entire address space.  This happens both as a result
@@ -167,18 +172,6 @@ tlb_finish_mmu (mmu_gather_t *tlb, unsigned long start, unsigned long end)
 	check_pgt_cache();
 }
 
-/*
- * Remove TLB entry for PTE mapped at virtual address ADDRESS.  This is called for any
- * PTE, not just those pointing to (normal) physical memory.
- */
-static inline void
-__tlb_remove_tlb_entry (mmu_gather_t *tlb, pte_t *ptep, unsigned long address)
-{
-	if (tlb->start_addr == ~0UL)
-		tlb->start_addr = address;
-	tlb->end_addr = address + PAGE_SIZE;
-}
-
 /*
  * Logically, this routine frees PAGE.  On MP machines, the actual freeing of the page
  * must be delayed until after the TLB has been flushed (see comments at the beginning of
@@ -187,6 +180,8 @@ __tlb_remove_tlb_entry (mmu_gather_t *tlb, pte_t *ptep, unsigned long address)
 static inline void
 tlb_remove_page (mmu_gather_t *tlb, struct page *page)
 {
+	tlb->need_flush = 1;
+
 	if (tlb_fast_mode(tlb)) {
 		free_page_and_swap_cache(page);
 		return;
@@ -196,11 +191,37 @@ tlb_remove_page (mmu_gather_t *tlb, struct page *page)
 		ia64_tlb_flush_mmu(tlb, tlb->start_addr, tlb->end_addr);
 }
 
+/*
+ * Remove TLB entry for PTE mapped at virtual address ADDRESS.  This is called for any
+ * PTE, not just those pointing to (normal) physical memory.
+ */
+static inline void
+__tlb_remove_tlb_entry (mmu_gather_t *tlb, pte_t *ptep, unsigned long address)
+{
+	if (tlb->start_addr == ~0UL)
+		tlb->start_addr = address;
+	tlb->end_addr = address + PAGE_SIZE;
+}
+
 #define tlb_start_vma(tlb, vma)			do { } while (0)
 #define tlb_end_vma(tlb, vma)			do { } while (0)
 
-#define tlb_remove_tlb_entry(tlb, ptep, addr)	__tlb_remove_tlb_entry(tlb, ptep, addr)
-#define pte_free_tlb(tlb, ptep)			__pte_free_tlb(tlb, ptep)
-#define pmd_free_tlb(tlb, ptep)			__pmd_free_tlb(tlb, ptep)
+#define tlb_remove_tlb_entry(tlb, ptep, addr)		\
+do {							\
+	tlb->need_flush = 1;				\
+	__tlb_remove_tlb_entry(tlb, ptep, addr);	\
+} while (0)
+
+#define pte_free_tlb(tlb, ptep)				\
+do {							\
+	tlb->need_flush = 1;				\
+	__pte_free_tlb(tlb, ptep);			\
+} while (0)
+
+#define pmd_free_tlb(tlb, ptep)				\
+do {							\
+	tlb->need_flush = 1;				\
+	__pmd_free_tlb(tlb, ptep);			\
+} while (0)
 
 #endif /* _ASM_IA64_TLB_H */