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

* git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6:
  [IA64] update memory attribute aliasing documentation & test cases
  [IA64] fail mmaps that span areas with incompatible attributes
  [IA64] allow WB /sys/.../legacy_mem mmaps
  [IA64] make ioremap avoid unsupported attributes
  [IA64] rename ioremap variables to match i386
  [IA64] relax per-cpu TLB requirement to DTC
  [IA64] remove per-cpu ia64_phys_stacked_size_p8
  [IA64] Fix example error injection program
  [IA64] Itanium MC Error Injection Tool: pal_mc_error_inject() interface
  [IA64] Itanium MC Error Injection Tool: Makefile changes
  [IA64] Itanium MC Error Injection Tool: Driver sysfs interface
  [IA64] Itanium MC Error Injection Tool: Doc and sample application
  [IA64] Itanium MC Error Injection Tool: Kernel configuration

Documentation/ia64/aliasing-test.c

+/*
+ * Exercise /dev/mem mmap cases that have been troublesome in the past
+ *
+ * (c) Copyright 2007 Hewlett-Packard Development Company, L.P.
+ *	Bjorn Helgaas <bjorn.helgaas@hp.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <fcntl.h>
+#include <fnmatch.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+int sum;
+
+int map_mem(char *path, off_t offset, size_t length, int touch)
+{
+	int fd, rc;
+	void *addr;
+	int *c;
+
+	fd = open(path, O_RDWR);
+	if (fd == -1) {
+		perror(path);
+		return -1;
+	}
+
+	addr = mmap(NULL, length, PROT_READ|PROT_WRITE, MAP_SHARED, fd, offset);
+	if (addr == MAP_FAILED)
+		return 1;
+
+	if (touch) {
+		c = (int *) addr;
+		while (c < (int *) (offset + length))
+			sum += *c++;
+	}
+
+	rc = munmap(addr, length);
+	if (rc == -1) {
+		perror("munmap");
+		return -1;
+	}
+
+	close(fd);
+	return 0;
+}
+
+int scan_sysfs(char *path, char *file, off_t offset, size_t length, int touch)
+{
+	struct dirent **namelist;
+	char *name, *path2;
+	int i, n, r, rc, result = 0;
+	struct stat buf;
+
+	n = scandir(path, &namelist, 0, alphasort);
+	if (n < 0) {
+		perror("scandir");
+		return -1;
+	}
+
+	for (i = 0; i < n; i++) {
+		name = namelist[i]->d_name;
+
+		if (fnmatch(".", name, 0) == 0)
+			goto skip;
+		if (fnmatch("..", name, 0) == 0)
+			goto skip;
+
+		path2 = malloc(strlen(path) + strlen(name) + 3);
+		strcpy(path2, path);
+		strcat(path2, "/");
+		strcat(path2, name);
+
+		if (fnmatch(file, name, 0) == 0) {
+			rc = map_mem(path2, offset, length, touch);
+			if (rc == 0)
+				fprintf(stderr, "PASS: %s 0x%lx-0x%lx is %s\n", path2, offset, offset + length, touch ? "readable" : "mappable");
+			else if (rc > 0)
+				fprintf(stderr, "PASS: %s 0x%lx-0x%lx not mappable\n", path2, offset, offset + length);
+			else {
+				fprintf(stderr, "FAIL: %s 0x%lx-0x%lx not accessible\n", path2, offset, offset + length);
+				return rc;
+			}
+		} else {
+			r = lstat(path2, &buf);
+			if (r == 0 && S_ISDIR(buf.st_mode)) {
+				rc = scan_sysfs(path2, file, offset, length, touch);
+				if (rc < 0)
+					return rc;
+			}
+		}
+
+		result |= rc;
+		free(path2);
+
+skip:
+		free(namelist[i]);
+	}
+	free(namelist);
+	return rc;
+}
+
+char buf[1024];
+
+int read_rom(char *path)
+{
+	int fd, rc;
+	size_t size = 0;
+
+	fd = open(path, O_RDWR);
+	if (fd == -1) {
+		perror(path);
+		return -1;
+	}
+
+	rc = write(fd, "1", 2);
+	if (rc <= 0) {
+		perror("write");
+		return -1;
+	}
+
+	do {
+		rc = read(fd, buf, sizeof(buf));
+		if (rc > 0)
+			size += rc;
+	} while (rc > 0);
+
+	close(fd);
+	return size;
+}
+
+int scan_rom(char *path, char *file)
+{
+	struct dirent **namelist;
+	char *name, *path2;
+	int i, n, r, rc, result = 0;
+	struct stat buf;
+
+	n = scandir(path, &namelist, 0, alphasort);
+	if (n < 0) {
+		perror("scandir");
+		return -1;
+	}
+
+	for (i = 0; i < n; i++) {
+		name = namelist[i]->d_name;
+
+		if (fnmatch(".", name, 0) == 0)
+			goto skip;
+		if (fnmatch("..", name, 0) == 0)
+			goto skip;
+
+		path2 = malloc(strlen(path) + strlen(name) + 3);
+		strcpy(path2, path);
+		strcat(path2, "/");
+		strcat(path2, name);
+
+		if (fnmatch(file, name, 0) == 0) {
+			rc = read_rom(path2);
+
+			/*
+			 * It's OK if the ROM is unreadable.  Maybe there
+			 * is no ROM, or some other error ocurred.  The
+			 * important thing is that no MCA happened.
+			 */
+			if (rc > 0)
+				fprintf(stderr, "PASS: %s read %ld bytes\n", path2, rc);
+			else {
+				fprintf(stderr, "PASS: %s not readable\n", path2);
+				return rc;
+			}
+		} else {
+			r = lstat(path2, &buf);
+			if (r == 0 && S_ISDIR(buf.st_mode)) {
+				rc = scan_rom(path2, file);
+				if (rc < 0)
+					return rc;
+			}
+		}
+
+		result |= rc;
+		free(path2);
+
+skip:
+		free(namelist[i]);
+	}
+	free(namelist);
+	return rc;
+}
+
+main()
+{
+	int rc;
+
+	if (map_mem("/dev/mem", 0, 0xA0000, 1) == 0)
+		fprintf(stderr, "PASS: /dev/mem 0x0-0xa0000 is readable\n");
+	else
+		fprintf(stderr, "FAIL: /dev/mem 0x0-0xa0000 not accessible\n");
+
+	/*
+	 * It's not safe to blindly read the VGA frame buffer.  If you know
+	 * how to poke the card the right way, it should respond, but it's
+	 * not safe in general.  Many machines, e.g., Intel chipsets, cover
+	 * up a non-responding card by just returning -1, but others will
+	 * report the failure as a machine check.
+	 */
+	if (map_mem("/dev/mem", 0xA0000, 0x20000, 0) == 0)
+		fprintf(stderr, "PASS: /dev/mem 0xa0000-0xc0000 is mappable\n");
+	else
+		fprintf(stderr, "FAIL: /dev/mem 0xa0000-0xc0000 not accessible\n");
+
+	if (map_mem("/dev/mem", 0xC0000, 0x40000, 1) == 0)
+		fprintf(stderr, "PASS: /dev/mem 0xc0000-0x100000 is readable\n");
+	else
+		fprintf(stderr, "FAIL: /dev/mem 0xc0000-0x100000 not accessible\n");
+
+	/*
+	 * Often you can map all the individual pieces above (0-0xA0000,
+	 * 0xA0000-0xC0000, and 0xC0000-0x100000), but can't map the whole
+	 * thing at once.  This is because the individual pieces use different
+	 * attributes, and there's no single attribute supported over the
+	 * whole region.
+	 */
+	rc = map_mem("/dev/mem", 0, 1024*1024, 0);
+	if (rc == 0)
+		fprintf(stderr, "PASS: /dev/mem 0x0-0x100000 is mappable\n");
+	else if (rc > 0)
+		fprintf(stderr, "PASS: /dev/mem 0x0-0x100000 not mappable\n");
+	else
+		fprintf(stderr, "FAIL: /dev/mem 0x0-0x100000 not accessible\n");
+
+	scan_sysfs("/sys/class/pci_bus", "legacy_mem", 0, 0xA0000, 1);
+	scan_sysfs("/sys/class/pci_bus", "legacy_mem", 0xA0000, 0x20000, 0);
+	scan_sysfs("/sys/class/pci_bus", "legacy_mem", 0xC0000, 0x40000, 1);
+	scan_sysfs("/sys/class/pci_bus", "legacy_mem", 0, 1024*1024, 0);
+
+	scan_rom("/sys/devices", "rom");
+}

Documentation/ia64/aliasing.txt

@@ -112,16 +112,6 @@ POTENTIAL ATTRIBUTE ALIASING CASES
 
 	The /dev/mem mmap constraints apply.
 
-	However, since this is for mapping legacy MMIO space, WB access
-	does not make sense.  This matters on machines without legacy
-	VGA support: these machines may have WB memory for the entire
-	first megabyte (or even the entire first granule).
-
-	On these machines, we could mmap legacy_mem as WB, which would
-	be safe in terms of attribute aliasing, but X has no way of
-	knowing that it is accessing regular memory, not a frame buffer,
-	so the kernel should fail the mmap rather than doing it with WB.
-
     read/write of /dev/mem
 
 	This uses copy_from_user(), which implicitly uses a kernel
@@ -138,14 +128,20 @@ POTENTIAL ATTRIBUTE ALIASING CASES
 
     ioremap()
 
-	This returns a kernel identity mapping for use inside the
-	kernel.
+	This returns a mapping for use inside the kernel.
 
 	If the region is in kern_memmap, we should use the attribute
-	specified there.  Otherwise, if the EFI memory map reports that
-	the entire granule supports WB, we should use that (granules
-	that are partially reserved or occupied by firmware do not appear
-	in kern_memmap).  Otherwise, we should use a UC mapping.
+	specified there.
+
+	If the EFI memory map reports that the entire granule supports
+	WB, we should use that (granules that are partially reserved
+	or occupied by firmware do not appear in kern_memmap).
+
+	If the granule contains non-WB memory, but we can cover the
+	region safely with kernel page table mappings, we can use
+	ioremap_page_range() as most other architectures do.
+
+	Failing all of the above, we have to fall back to a UC mapping.
 
 PAST PROBLEM CASES
 
@@ -158,7 +154,7 @@ PAST PROBLEM CASES
       succeed.  It may create either WB or UC user mappings, depending
       on whether the region is in kern_memmap or the EFI memory map.
 
-    mmap of 0x0-0xA0000 /dev/mem by "hwinfo" on HP sx1000 with VGA enabled
+    mmap of 0x0-0x9FFFF /dev/mem by "hwinfo" on HP sx1000 with VGA enabled
 
       See https://bugzilla.novell.com/show_bug.cgi?id=140858.
 
@@ -171,28 +167,25 @@ PAST PROBLEM CASES
       so it is safe to use WB mappings.
 
       The kernel VGA driver may ioremap the VGA frame buffer at 0xA0000,
-      which will use a granule-sized UC mapping covering 0-0xFFFFF.  This
-      granule covers some WB-only memory, but since UC is non-speculative,
-      the processor will never generate an uncacheable reference to the
-      WB-only areas unless the driver explicitly touches them.
+      which uses a granule-sized UC mapping.  This granule will cover some
+      WB-only memory, but since UC is non-speculative, the processor will
+      never generate an uncacheable reference to the WB-only areas unless
+      the driver explicitly touches them.
 
     mmap of 0x0-0xFFFFF legacy_mem by "X"
 
-      If the EFI memory map reports this entire range as WB, there
-      is no VGA MMIO hole, and the mmap should fail or be done with
-      a WB mapping.
+      If the EFI memory map reports that the entire range supports the
+      same attributes, we can allow the mmap (and we will prefer WB if
+      supported, as is the case with HP sx[12]000 machines with VGA
+      disabled).
 
-      There's no easy way for X to determine whether the 0xA0000-0xBFFFF
-      region is a frame buffer or just memory, so I think it's best to
-      just fail this mmap request rather than using a WB mapping.  As
-      far as I know, there's no need to map legacy_mem with WB
-      mappings.
+      If EFI reports the range as partly WB and partly UC (as on sx[12]000
+      machines with VGA enabled), we must fail the mmap because there's no
+      safe attribute to use.
 
-      Otherwise, a UC mapping of the entire region is probably safe.
-      The VGA hole means the region will not be in kern_memmap.  The
-      HP sx1000 chipset doesn't support UC access to the memory surrounding
-      the VGA hole, but X doesn't need that area anyway and should not
-      reference it.
+      If EFI reports some of the range but not all (as on Intel firmware
+      that doesn't report the VGA frame buffer at all), we should fail the
+      mmap and force the user to map just the specific region of interest.
 
     mmap of 0xA0000-0xBFFFF legacy_mem by "X" on HP sx1000 with VGA disabled
 
@@ -202,6 +195,16 @@ PAST PROBLEM CASES
       This is a special case of the previous case, and the mmap should
       fail for the same reason as above.
 
+    read of /sys/devices/.../rom
+
+      For VGA devices, this may cause an ioremap() of 0xC0000.  This
+      used to be done with a UC mapping, because the VGA frame buffer
+      at 0xA0000 prevents use of a WB granule.  The UC mapping causes
+      an MCA on HP sx[12]000 chipsets.
+
+      We should use WB page table mappings to avoid covering the VGA
+      frame buffer.
+
 NOTES
 
     [1] SDM rev 2.2, vol 2, sec 4.4.1.

arch/ia64/Kconfig

@@ -439,6 +439,16 @@ config IA64_PALINFO
 	  To use this option, you have to ensure that the "/proc file system
 	  support" (CONFIG_PROC_FS) is enabled, too.
 
+config IA64_MC_ERR_INJECT
+	tristate "MC error injection support"
+	help
+	  Selets whether support for MC error injection. By enabling the
+	  support, kernel provide sysfs interface for user application to
+	  call MC error injection PAL procedure to inject various errors.
+	  This is a useful tool for MCA testing.
+
+	  If you're unsure, do not select this option.
+
 config SGI_SN
 	def_bool y if (IA64_SGI_SN2 || IA64_GENERIC)
 

arch/ia64/defconfig

@@ -164,6 +164,7 @@ CONFIG_COMPAT=y
 CONFIG_IA64_MCA_RECOVERY=y
 CONFIG_PERFMON=y
 CONFIG_IA64_PALINFO=y
+# CONFIG_MC_ERR_INJECT is not set
 CONFIG_SGI_SN=y
 # CONFIG_IA64_ESI is not set
 

arch/ia64/kernel/Makefile

@@ -34,6 +34,7 @@ obj-$(CONFIG_IA64_UNCACHED_ALLOCATOR)	+= uncached.o
 obj-$(CONFIG_AUDIT)		+= audit.o
 obj-$(CONFIG_PCI_MSI)		+= msi_ia64.o
 mca_recovery-y			+= mca_drv.o mca_drv_asm.o
+obj-$(CONFIG_IA64_MC_ERR_INJECT)+= err_inject.o
 
 obj-$(CONFIG_IA64_ESI)		+= esi.o
 ifneq ($(CONFIG_IA64_ESI),)

arch/ia64/kernel/efi.c

@@ -660,6 +660,29 @@ efi_memory_descriptor (unsigned long phys_addr)
 	return NULL;
 }
 
+static int
+efi_memmap_intersects (unsigned long phys_addr, unsigned long size)
+{
+	void *efi_map_start, *efi_map_end, *p;
+	efi_memory_desc_t *md;
+	u64 efi_desc_size;
+	unsigned long end;
+
+	efi_map_start = __va(ia64_boot_param->efi_memmap);
+	efi_map_end   = efi_map_start + ia64_boot_param->efi_memmap_size;
+	efi_desc_size = ia64_boot_param->efi_memdesc_size;
+
+	end = phys_addr + size;
+
+	for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
+		md = p;
+
+		if (md->phys_addr < end && efi_md_end(md) > phys_addr)
+			return 1;
+	}
+	return 0;
+}
+
 u32
 efi_mem_type (unsigned long phys_addr)
 {
@@ -766,11 +789,28 @@ valid_phys_addr_range (unsigned long phys_addr, unsigned long size)
 int
 valid_mmap_phys_addr_range (unsigned long pfn, unsigned long size)
 {
+	unsigned long phys_addr = pfn << PAGE_SHIFT;
+	u64 attr;
+
+	attr = efi_mem_attribute(phys_addr, size);
+
 	/*
-	 * MMIO regions are often missing from the EFI memory map.
-	 * We must allow mmap of them for programs like X, so we
-	 * currently can't do any useful validation.
+	 * /dev/mem mmap uses normal user pages, so we don't need the entire
+	 * granule, but the entire region we're mapping must support the same
+	 * attribute.
 	 */
+	if (attr & EFI_MEMORY_WB || attr & EFI_MEMORY_UC)
+		return 1;
+
+	/*
+	 * Intel firmware doesn't tell us about all the MMIO regions, so
+	 * in general we have to allow mmap requests.  But if EFI *does*
+	 * tell us about anything inside this region, we should deny it.
+	 * The user can always map a smaller region to avoid the overlap.
+	 */
+	if (efi_memmap_intersects(phys_addr, size))
+		return 0;
+
 	return 1;
 }
 

arch/ia64/kernel/entry.S

@@ -767,7 +767,7 @@ ENTRY(ia64_leave_syscall)
 	ld8.fill r15=[r3]			// M0|1 restore r15
 	mov b6=r18				// I0   restore b6
 
-	addl r17=THIS_CPU(ia64_phys_stacked_size_p8),r0 // A
+	LOAD_PHYS_STACK_REG_SIZE(r17)
 	mov f9=f0					// F    clear f9
 (pKStk) br.cond.dpnt.many skip_rbs_switch		// B
 
@@ -775,7 +775,6 @@ ENTRY(ia64_leave_syscall)
 	shr.u r18=r19,16		// I0|1 get byte size of existing "dirty" partition
 	cover				// B    add current frame into dirty partition & set cr.ifs
 	;;
-(pUStk) ld4 r17=[r17]			// M0|1 r17 = cpu_data->phys_stacked_size_p8
 	mov r19=ar.bsp			// M2   get new backing store pointer
 	mov f10=f0			// F    clear f10
 
@@ -953,9 +952,7 @@ GLOBAL_ENTRY(ia64_leave_kernel)
 	shr.u r18=r19,16	// get byte size of existing "dirty" partition
 	;;
 	mov r16=ar.bsp		// get existing backing store pointer
-	addl r17=THIS_CPU(ia64_phys_stacked_size_p8),r0
-	;;
-	ld4 r17=[r17]		// r17 = cpu_data->phys_stacked_size_p8
+	LOAD_PHYS_STACK_REG_SIZE(r17)
 (pKStk)	br.cond.dpnt skip_rbs_switch
 
 	/*

arch/ia64/kernel/err_inject.c

+/*
+ * err_inject.c -
+ *	1.) Inject errors to a processor.
+ *	2.) Query error injection capabilities.
+ * This driver along with user space code can be acting as an error
+ * injection tool.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Written by: Fenghua Yu <fenghua.yu@intel.com>, Intel Corporation
+ * Copyright (C) 2006, Intel Corp.  All rights reserved.
+ *
+ */
+#include <linux/sysdev.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/cpu.h>
+#include <linux/module.h>
+
+#define ERR_INJ_DEBUG
+
+#define ERR_DATA_BUFFER_SIZE 3 		// Three 8-byte;
+
+#define define_one_ro(name) 						\
+static SYSDEV_ATTR(name, 0444, show_##name, NULL)
+
+#define define_one_rw(name) 						\
+static SYSDEV_ATTR(name, 0644, show_##name, store_##name)
+
+static u64 call_start[NR_CPUS];
+static u64 phys_addr[NR_CPUS];
+static u64 err_type_info[NR_CPUS];
+static u64 err_struct_info[NR_CPUS];
+static struct {
+	u64 data1;
+	u64 data2;
+	u64 data3;
+} __attribute__((__aligned__(16))) err_data_buffer[NR_CPUS];
+static s64 status[NR_CPUS];
+static u64 capabilities[NR_CPUS];
+static u64 resources[NR_CPUS];
+
+#define show(name) 							\
+static ssize_t 								\
+show_##name(struct sys_device *dev, char *buf)				\
+{									\
+	u32 cpu=dev->id;						\
+	return sprintf(buf, "%lx\n", name[cpu]);			\
+}
+
+#define store(name)							\
+static ssize_t 								\
+store_##name(struct sys_device *dev, const char *buf, size_t size)	\
+{									\
+	unsigned int cpu=dev->id;					\
+	name[cpu] = simple_strtoull(buf, NULL, 16);			\
+	return size;							\
+}
+
+show(call_start)
+
+/* It's user's responsibility to call the PAL procedure on a specific
+ * processor. The cpu number in driver is only used for storing data.
+ */
+static ssize_t
+store_call_start(struct sys_device *dev, const char *buf, size_t size)
+{
+	unsigned int cpu=dev->id;
+	unsigned long call_start = simple_strtoull(buf, NULL, 16);
+
+#ifdef ERR_INJ_DEBUG
+	printk(KERN_DEBUG "pal_mc_err_inject for cpu%d:\n", cpu);
+	printk(KERN_DEBUG "err_type_info=%lx,\n", err_type_info[cpu]);
+	printk(KERN_DEBUG "err_struct_info=%lx,\n", err_struct_info[cpu]);
+	printk(KERN_DEBUG "err_data_buffer=%lx, %lx, %lx.\n",
+			  err_data_buffer[cpu].data1,
+			  err_data_buffer[cpu].data2,
+			  err_data_buffer[cpu].data3);
+#endif
+	switch (call_start) {
+	    case 0: /* Do nothing. */
+		break;
+	    case 1: /* Call pal_mc_error_inject in physical mode. */
+		status[cpu]=ia64_pal_mc_error_inject_phys(err_type_info[cpu],
+					err_struct_info[cpu],
+					ia64_tpa(&err_data_buffer[cpu]),
+					&capabilities[cpu],
+			 		&resources[cpu]);
+		break;
+	    case 2: /* Call pal_mc_error_inject in virtual mode. */
+		status[cpu]=ia64_pal_mc_error_inject_virt(err_type_info[cpu],
+					err_struct_info[cpu],
+					ia64_tpa(&err_data_buffer[cpu]),
+					&capabilities[cpu],
+			 		&resources[cpu]);
+		break;
+	    default:
+		status[cpu] = -EINVAL;
+		break;
+	}
+
+#ifdef ERR_INJ_DEBUG
+	printk(KERN_DEBUG "Returns: status=%d,\n", (int)status[cpu]);
+	printk(KERN_DEBUG "capapbilities=%lx,\n", capabilities[cpu]);
+	printk(KERN_DEBUG "resources=%lx\n", resources[cpu]);
+#endif
+	return size;
+}
+
+show(err_type_info)
+store(err_type_info)
+
+static ssize_t
+show_virtual_to_phys(struct sys_device *dev, char *buf)
+{
+	unsigned int cpu=dev->id;
+	return sprintf(buf, "%lx\n", phys_addr[cpu]);
+}
+
+static ssize_t
+store_virtual_to_phys(struct sys_device *dev, const char *buf, size_t size)
+{
+	unsigned int cpu=dev->id;
+	u64 virt_addr=simple_strtoull(buf, NULL, 16);
+	int ret;
+
+        ret = get_user_pages(current, current->mm, virt_addr,
+                        1, VM_READ, 0, NULL, NULL);
+	if (ret<=0) {
+#ifdef ERR_INJ_DEBUG
+		printk("Virtual address %lx is not existing.\n",virt_addr);
+#endif
+		return -EINVAL;
+	}
+
+	phys_addr[cpu] = ia64_tpa(virt_addr);
+	return size;
+}
+
+show(err_struct_info)
+store(err_struct_info)
+
+static ssize_t
+show_err_data_buffer(struct sys_device *dev, char *buf)
+{
+	unsigned int cpu=dev->id;
+
+	return sprintf(buf, "%lx, %lx, %lx\n",
+			err_data_buffer[cpu].data1,
+			err_data_buffer[cpu].data2,
+			err_data_buffer[cpu].data3);
+}
+
+static ssize_t
+store_err_data_buffer(struct sys_device *dev, const char *buf, size_t size)
+{
+	unsigned int cpu=dev->id;
+	int ret;
+
+#ifdef ERR_INJ_DEBUG
+	printk("write err_data_buffer=[%lx,%lx,%lx] on cpu%d\n",
+		 err_data_buffer[cpu].data1,
+		 err_data_buffer[cpu].data2,
+		 err_data_buffer[cpu].data3,
+		 cpu);
+#endif
+	ret=sscanf(buf, "%lx, %lx, %lx",
+			&err_data_buffer[cpu].data1,
+			&err_data_buffer[cpu].data2,
+			&err_data_buffer[cpu].data3);
+	if (ret!=ERR_DATA_BUFFER_SIZE)
+		return -EINVAL;
+
+	return size;
+}
+
+show(status)
+show(capabilities)
+show(resources)
+
+define_one_rw(call_start);
+define_one_rw(err_type_info);
+define_one_rw(err_struct_info);
+define_one_rw(err_data_buffer);
+define_one_rw(virtual_to_phys);
+define_one_ro(status);
+define_one_ro(capabilities);
+define_one_ro(resources);
+
+static struct attribute *default_attrs[] = {
+	&attr_call_start.attr,
+	&attr_virtual_to_phys.attr,
+	&attr_err_type_info.attr,
+	&attr_err_struct_info.attr,
+	&attr_err_data_buffer.attr,
+	&attr_status.attr,
+	&attr_capabilities.attr,
+	&attr_resources.attr,
+	NULL
+};
+
+static struct attribute_group err_inject_attr_group = {
+	.attrs = default_attrs,
+	.name = "err_inject"
+};
+/* Add/Remove err_inject interface for CPU device */
+static int __cpuinit err_inject_add_dev(struct sys_device * sys_dev)
+{
+	return sysfs_create_group(&sys_dev->kobj, &err_inject_attr_group);
+}
+
+static int __cpuinit err_inject_remove_dev(struct sys_device * sys_dev)
+{
+	sysfs_remove_group(&sys_dev->kobj, &err_inject_attr_group);
+	return 0;
+}
+static int __cpuinit err_inject_cpu_callback(struct notifier_block *nfb,
+		unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (unsigned long)hcpu;
+	struct sys_device *sys_dev;
+
+	sys_dev = get_cpu_sysdev(cpu);
+	switch (action) {
+	case CPU_ONLINE:
+		err_inject_add_dev(sys_dev);
+		break;
+	case CPU_DEAD:
+		err_inject_remove_dev(sys_dev);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata err_inject_cpu_notifier =
+{
+	.notifier_call = err_inject_cpu_callback,
+};
+
+static int __init
+err_inject_init(void)
+{
+	int i;
+
+#ifdef ERR_INJ_DEBUG
+	printk(KERN_INFO "Enter error injection driver.\n");
+#endif
+	for_each_online_cpu(i) {
+		err_inject_cpu_callback(&err_inject_cpu_notifier, CPU_ONLINE,
+				(void *)(long)i);
+	}
+
+	register_hotcpu_notifier(&err_inject_cpu_notifier);
+
+	return 0;
+}
+
+static void __exit
+err_inject_exit(void)
+{
+	int i;
+	struct sys_device *sys_dev;
+
+#ifdef ERR_INJ_DEBUG
+	printk(KERN_INFO "Exit error injection driver.\n");
+#endif
+	for_each_online_cpu(i) {
+		sys_dev = get_cpu_sysdev(i);
+		sysfs_remove_group(&sys_dev->kobj, &err_inject_attr_group);
+	}
+	unregister_hotcpu_notifier(&err_inject_cpu_notifier);
+}
+
+module_init(err_inject_init);
+module_exit(err_inject_exit);
+
+MODULE_AUTHOR("Fenghua Yu <fenghua.yu@intel.com>");
+MODULE_DESCRIPTION("MC error injection kenrel sysfs interface");
+MODULE_LICENSE("GPL");

arch/ia64/kernel/ivt.S

@@ -374,6 +374,7 @@ ENTRY(alt_dtlb_miss)
 	movl r19=(((1 << IA64_MAX_PHYS_BITS) - 1) & ~0xfff)
 	mov r21=cr.ipsr
 	mov r31=pr
+	mov r24=PERCPU_ADDR
 	;;
 #ifdef CONFIG_DISABLE_VHPT
 	shr.u r22=r16,61			// get the region number into r21
@@ -386,22 +387,30 @@ ENTRY(alt_dtlb_miss)
 (p8)	mov r29=b0				// save b0
 (p8)	br.cond.dptk dtlb_fault
 #endif
+	cmp.ge p10,p11=r16,r24			// access to per_cpu_data?
+	tbit.z p12,p0=r16,61			// access to region 6?
+	mov r25=PERCPU_PAGE_SHIFT << 2
+	mov r26=PERCPU_PAGE_SIZE
+	nop.m 0
+	nop.b 0
+	;;
+(p10)	mov r19=IA64_KR(PER_CPU_DATA)
+(p11)	and r19=r19,r16				// clear non-ppn fields
 	extr.u r23=r21,IA64_PSR_CPL0_BIT,2	// extract psr.cpl
 	and r22=IA64_ISR_CODE_MASK,r20		// get the isr.code field
 	tbit.nz p6,p7=r20,IA64_ISR_SP_BIT	// is speculation bit on?
-	shr.u r18=r16,57			// move address bit 61 to bit 4
-	and r19=r19,r16				// clear ed, reserved bits, and PTE control bits
 	tbit.nz p9,p0=r20,IA64_ISR_NA_BIT	// is non-access bit on?
 	;;
-	andcm r18=0x10,r18	// bit 4=~address-bit(61)
+(p10)	sub r19=r19,r26
+(p10)	mov cr.itir=r25
 	cmp.ne p8,p0=r0,r23
 (p9)	cmp.eq.or.andcm p6,p7=IA64_ISR_CODE_LFETCH,r22	// check isr.code field
+(p12)	dep r17=-1,r17,4,1			// set ma=UC for region 6 addr
 (p8)	br.cond.spnt page_fault
 
 	dep r21=-1,r21,IA64_PSR_ED_BIT,1
-	or r19=r19,r17		// insert PTE control bits into r19
 	;;
-	or r19=r19,r18		// set bit 4 (uncached) if the access was to region 6
+	or r19=r19,r17		// insert PTE control bits into r19
 (p6)	mov cr.ipsr=r21
 	;;
 (p7)	itc.d r19		// insert the TLB entry

arch/ia64/kernel/mca_asm.S

@@ -101,14 +101,6 @@ ia64_do_tlb_purge:
 	;;
 	srlz.d
 	;;
-	// 2. Purge DTR for PERCPU data.
-	movl r16=PERCPU_ADDR
-	mov r18=PERCPU_PAGE_SHIFT<<2
-	;;
-	ptr.d r16,r18
-	;;
-	srlz.d
-	;;
 	// 3. Purge ITR for PAL code.
 	GET_THIS_PADDR(r2, ia64_mca_pal_base)
 	;;
@@ -196,22 +188,6 @@ ia64_reload_tr:
 	srlz.i
 	srlz.d
 	;;
-	// 2. Reload DTR register for PERCPU data.
-	GET_THIS_PADDR(r2, ia64_mca_per_cpu_pte)
-	;;
-	movl r16=PERCPU_ADDR		// vaddr
-	movl r18=PERCPU_PAGE_SHIFT<<2
-	;;
-	mov cr.itir=r18
-	mov cr.ifa=r16
-	;;
-	ld8 r18=[r2]			// load per-CPU PTE
-	mov r16=IA64_TR_PERCPU_DATA;
-	;;
-	itr.d dtr[r16]=r18
-	;;
-	srlz.d
-	;;
 	// 3. Reload ITR for PAL code.
 	GET_THIS_PADDR(r2, ia64_mca_pal_pte)
 	;;

arch/ia64/kernel/patch.c

@@ -195,3 +195,23 @@ ia64_patch_gate (void)
 	ia64_patch_vtop(START(vtop), END(vtop));
 	ia64_patch_mckinley_e9(START(mckinley_e9), END(mckinley_e9));
 }
+
+void ia64_patch_phys_stack_reg(unsigned long val)
+{
+	s32 * offp = (s32 *) __start___phys_stack_reg_patchlist;
+	s32 * end = (s32 *) __end___phys_stack_reg_patchlist;
+	u64 ip, mask, imm;
+
+	/* see instruction format A4: adds r1 = imm13, r3 */
+	mask = (0x3fUL << 27) | (0x7f << 13);
+	imm = (((val >> 7) & 0x3f) << 27) | (val & 0x7f) << 13;
+
+	while (offp < end) {
+		ip = (u64) offp + *offp;
+		ia64_patch(ip, mask, imm);
+		ia64_fc(ip);
+		++offp;
+	}
+	ia64_sync_i();
+	ia64_srlz_i();
+}

arch/ia64/kernel/setup.c

@@ -75,7 +75,6 @@ extern void ia64_setup_printk_clock(void);
 
 DEFINE_PER_CPU(struct cpuinfo_ia64, cpu_info);
 DEFINE_PER_CPU(unsigned long, local_per_cpu_offset);
-DEFINE_PER_CPU(unsigned long, ia64_phys_stacked_size_p8);
 unsigned long ia64_cycles_per_usec;
 struct ia64_boot_param *ia64_boot_param;
 struct screen_info screen_info;
@@ -869,6 +868,7 @@ void __cpuinit
 cpu_init (void)
 {
 	extern void __cpuinit ia64_mmu_init (void *);
+	static unsigned long max_num_phys_stacked = IA64_NUM_PHYS_STACK_REG;
 	unsigned long num_phys_stacked;
 	pal_vm_info_2_u_t vmi;
 	unsigned int max_ctx;
@@ -982,7 +982,10 @@ cpu_init (void)
 		num_phys_stacked = 96;
 	}
 	/* size of physical stacked register partition plus 8 bytes: */
-	__get_cpu_var(ia64_phys_stacked_size_p8) = num_phys_stacked*8 + 8;
+	if (num_phys_stacked > max_num_phys_stacked) {
+		ia64_patch_phys_stack_reg(num_phys_stacked*8 + 8);
+		max_num_phys_stacked = num_phys_stacked;
+	}
 	platform_cpu_init();
 	pm_idle = default_idle;
 }

arch/ia64/kernel/vmlinux.lds.S

@@ -78,6 +78,13 @@ SECTIONS
 	  __stop___mca_table = .;
 	}
 
+  .data.patch.phys_stack_reg : AT(ADDR(.data.patch.phys_stack_reg) - LOAD_OFFSET)
+	{
+	  __start___phys_stack_reg_patchlist = .;
+	  *(.data.patch.phys_stack_reg)
+	  __end___phys_stack_reg_patchlist = .;
+	}
+
   /* Global data */
   _data = .;
 

arch/ia64/mm/init.c

@@ -355,7 +355,7 @@ setup_gate (void)
 void __devinit
 ia64_mmu_init (void *my_cpu_data)
 {
-	unsigned long psr, pta, impl_va_bits;
+	unsigned long pta, impl_va_bits;
 	extern void __devinit tlb_init (void);
 
 #ifdef CONFIG_DISABLE_VHPT
@@ -364,15 +364,6 @@ ia64_mmu_init (void *my_cpu_data)
 #	define VHPT_ENABLE_BIT	1
 #endif
 
-	/* Pin mapping for percpu area into TLB */
-	psr = ia64_clear_ic();
-	ia64_itr(0x2, IA64_TR_PERCPU_DATA, PERCPU_ADDR,
-		 pte_val(pfn_pte(__pa(my_cpu_data) >> PAGE_SHIFT, PAGE_KERNEL)),
-		 PERCPU_PAGE_SHIFT);
-
-	ia64_set_psr(psr);
-	ia64_srlz_i();
-
 	/*
 	 * Check if the virtually mapped linear page table (VMLPT) overlaps with a mapped
 	 * address space.  The IA-64 architecture guarantees that at least 50 bits of

arch/ia64/mm/ioremap.c

 /*
- * (c) Copyright 2006 Hewlett-Packard Development Company, L.P.
+ * (c) Copyright 2006, 2007 Hewlett-Packard Development Company, L.P.
  *	Bjorn Helgaas <bjorn.helgaas@hp.com>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -10,51 +10,101 @@
 #include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/efi.h>
+#include <linux/io.h>
+#include <linux/vmalloc.h>
 #include <asm/io.h>
 #include <asm/meminit.h>
 
 static inline void __iomem *
-__ioremap (unsigned long offset, unsigned long size)
+__ioremap (unsigned long phys_addr)
 {
-	return (void __iomem *) (__IA64_UNCACHED_OFFSET | offset);
+	return (void __iomem *) (__IA64_UNCACHED_OFFSET | phys_addr);
 }
 
 void __iomem *
-ioremap (unsigned long offset, unsigned long size)
+ioremap (unsigned long phys_addr, unsigned long size)
 {
+	void __iomem *addr;
+	struct vm_struct *area;
+	unsigned long offset;
+	pgprot_t prot;
 	u64 attr;
 	unsigned long gran_base, gran_size;
+	unsigned long page_base;
 
 	/*
 	 * For things in kern_memmap, we must use the same attribute
 	 * as the rest of the kernel.  For more details, see
 	 * Documentation/ia64/aliasing.txt.
 	 */
-	attr = kern_mem_attribute(offset, size);
+	attr = kern_mem_attribute(phys_addr, size);
 	if (attr & EFI_MEMORY_WB)
-		return (void __iomem *) phys_to_virt(offset);
+		return (void __iomem *) phys_to_virt(phys_addr);
 	else if (attr & EFI_MEMORY_UC)
-		return __ioremap(offset, size);
+		return __ioremap(phys_addr);
 
 	/*
 	 * Some chipsets don't support UC access to memory.  If
 	 * WB is supported for the whole granule, we prefer that.
 	 */
-	gran_base = GRANULEROUNDDOWN(offset);
-	gran_size = GRANULEROUNDUP(offset + size) - gran_base;
+	gran_base = GRANULEROUNDDOWN(phys_addr);
+	gran_size = GRANULEROUNDUP(phys_addr + size) - gran_base;
 	if (efi_mem_attribute(gran_base, gran_size) & EFI_MEMORY_WB)
-		return (void __iomem *) phys_to_virt(offset);
+		return (void __iomem *) phys_to_virt(phys_addr);
 
-	return __ioremap(offset, size);
+	/*
+	 * WB is not supported for the whole granule, so we can't use
+	 * the region 7 identity mapping.  If we can safely cover the
+	 * area with kernel page table mappings, we can use those
+	 * instead.
+	 */
+	page_base = phys_addr & PAGE_MASK;
+	size = PAGE_ALIGN(phys_addr + size) - page_base;
+	if (efi_mem_attribute(page_base, size) & EFI_MEMORY_WB) {
+		prot = PAGE_KERNEL;
+
+		/*
+		 * Mappings have to be page-aligned
+		 */
+		offset = phys_addr & ~PAGE_MASK;
+		phys_addr &= PAGE_MASK;
+
+		/*
+		 * Ok, go for it..
+		 */
+		area = get_vm_area(size, VM_IOREMAP);
+		if (!area)
+			return NULL;
+
+		area->phys_addr = phys_addr;
+		addr = (void __iomem *) area->addr;
+		if (ioremap_page_range((unsigned long) addr,
+				(unsigned long) addr + size, phys_addr, prot)) {
+			vunmap((void __force *) addr);
+			return NULL;
+		}
+
+		return (void __iomem *) (offset + (char __iomem *)addr);
+	}
+
+	return __ioremap(phys_addr);
 }
 EXPORT_SYMBOL(ioremap);
 
 void __iomem *
-ioremap_nocache (unsigned long offset, unsigned long size)
+ioremap_nocache (unsigned long phys_addr, unsigned long size)
 {
-	if (kern_mem_attribute(offset, size) & EFI_MEMORY_WB)
+	if (kern_mem_attribute(phys_addr, size) & EFI_MEMORY_WB)
 		return NULL;
 
-	return __ioremap(offset, size);
+	return __ioremap(phys_addr);
 }
 EXPORT_SYMBOL(ioremap_nocache);
+
+void
+iounmap (volatile void __iomem *addr)
+{
+	if (REGION_NUMBER(addr) == RGN_GATE)
+		vunmap((void *) ((unsigned long) addr & PAGE_MASK));
+}
+EXPORT_SYMBOL(iounmap);

arch/ia64/pci/pci.c

@@ -659,8 +659,6 @@ pci_mmap_legacy_page_range(struct pci_bus *bus, struct vm_area_struct *vma)
 		return -EINVAL;
 	prot = phys_mem_access_prot(NULL, vma->vm_pgoff, size,
 				    vma->vm_page_prot);
-	if (pgprot_val(prot) != pgprot_val(pgprot_noncached(vma->vm_page_prot)))
-		return -EINVAL;
 
 	addr = pci_get_legacy_mem(bus);
 	if (IS_ERR(addr))

include/asm-ia64/asmmacro.h

@@ -103,6 +103,16 @@
 # define FSYS_RETURN	br.ret.sptk.many b6
 #endif
 
+/*
+ * If physical stack register size is different from DEF_NUM_STACK_REG,
+ * dynamically patch the kernel for correct size.
+ */
+	.section ".data.patch.phys_stack_reg", "a"
+	.previous
+#define LOAD_PHYS_STACK_REG_SIZE(reg)			\
+[1:]	adds reg=IA64_NUM_PHYS_STACK_REG*8+8,r0;	\
+	.xdata4 ".data.patch.phys_stack_reg", 1b-.
+
 /*
  * Up until early 2004, use of .align within a function caused bad unwind info.
  * TEXT_ALIGN(n) expands into ".align n" if a fixed GAS is available or into nothing

include/asm-ia64/io.h

@@ -421,11 +421,7 @@ __writeq (unsigned long val, volatile void __iomem *addr)
 
 extern void __iomem * ioremap(unsigned long offset, unsigned long size);
 extern void __iomem * ioremap_nocache (unsigned long offset, unsigned long size);
-
-static inline void
-iounmap (volatile void __iomem *addr)
-{
-}
+extern void iounmap (volatile void __iomem *addr);
 
 /* Use normal IO mappings for DMI */
 #define dmi_ioremap ioremap

include/asm-ia64/kregs.h

@@ -29,8 +29,7 @@
  */
 #define IA64_TR_KERNEL		0	/* itr0, dtr0: maps kernel image (code & data) */
 #define IA64_TR_PALCODE		1	/* itr1: maps PALcode as required by EFI */
-#define IA64_TR_PERCPU_DATA	1	/* dtr1: percpu data */
-#define IA64_TR_CURRENT_STACK	2	/* dtr2: maps kernel's memory- & register-stacks */
+#define IA64_TR_CURRENT_STACK	1	/* dtr1: maps kernel's memory- & register-stacks */
 
 /* Processor status register bits: */
 #define IA64_PSR_BE_BIT		1

include/asm-ia64/pal.h

@@ -89,6 +89,8 @@
 #define PAL_GET_PSTATE_TYPE_AVGNORESET	2
 #define PAL_GET_PSTATE_TYPE_INSTANT	3
 
+#define PAL_MC_ERROR_INJECT	276	/* Injects processor error or returns injection capabilities */
+
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
@@ -1235,6 +1237,37 @@ ia64_pal_mc_error_info (u64 info_index, u64 type_index, u64 *size, u64 *error_in
 	return iprv.status;
 }
 
+/* Injects the requested processor error or returns info on
+ * supported injection capabilities for current processor implementation
+ */
+static inline s64
+ia64_pal_mc_error_inject_phys (u64 err_type_info, u64 err_struct_info,
+			u64 err_data_buffer, u64 *capabilities, u64 *resources)
+{
+	struct ia64_pal_retval iprv;
+	PAL_CALL_PHYS_STK(iprv, PAL_MC_ERROR_INJECT, err_type_info,
+			  err_struct_info, err_data_buffer);
+	if (capabilities)
+		*capabilities= iprv.v0;
+	if (resources)
+		*resources= iprv.v1;
+	return iprv.status;
+}
+
+static inline s64
+ia64_pal_mc_error_inject_virt (u64 err_type_info, u64 err_struct_info,
+			u64 err_data_buffer, u64 *capabilities, u64 *resources)
+{
+	struct ia64_pal_retval iprv;
+	PAL_CALL_STK(iprv, PAL_MC_ERROR_INJECT, err_type_info,
+			  err_struct_info, err_data_buffer);
+	if (capabilities)
+		*capabilities= iprv.v0;
+	if (resources)
+		*resources= iprv.v1;
+	return iprv.status;
+}
+
 /* Inform PALE_CHECK whether a machine check is expected so that PALE_CHECK willnot
  * attempt to correct any expected machine checks.
  */

include/asm-ia64/patch.h

@@ -20,6 +20,7 @@ extern void ia64_patch_imm60 (u64 insn_addr, u64 val);		/* patch "brl" w/ip-rel
 
 extern void ia64_patch_mckinley_e9 (unsigned long start, unsigned long end);
 extern void ia64_patch_vtop (unsigned long start, unsigned long end);
+extern void ia64_patch_phys_stack_reg(unsigned long val);
 extern void ia64_patch_gate (void);
 
 #endif /* _ASM_IA64_PATCH_H */

include/asm-ia64/processor.h

@@ -19,6 +19,7 @@
 #include <asm/ptrace.h>
 #include <asm/ustack.h>
 
+#define IA64_NUM_PHYS_STACK_REG	96
 #define IA64_NUM_DBG_REGS	8
 
 #define DEFAULT_MAP_BASE	__IA64_UL_CONST(0x2000000000000000)

include/asm-ia64/sections.h

@@ -11,6 +11,7 @@
 extern char __per_cpu_start[], __per_cpu_end[], __phys_per_cpu_start[];
 extern char __start___vtop_patchlist[], __end___vtop_patchlist[];
 extern char __start___mckinley_e9_bundles[], __end___mckinley_e9_bundles[];
+extern char __start___phys_stack_reg_patchlist[], __end___phys_stack_reg_patchlist[];
 extern char __start_gate_section[];
 extern char __start_gate_mckinley_e9_patchlist[], __end_gate_mckinley_e9_patchlist[];
 extern char __start_gate_vtop_patchlist[], __end_gate_vtop_patchlist[];