Merge http://ppc.bkbits.net/for-linus-ppc64

into home.osdl.org:/home/torvalds/v2.5/linux

arch/ppc64/Kconfig

@@ -72,6 +72,17 @@ config PPC64
 	bool
 	default y
 
+config HUGETLB_PAGE
+	bool "Huge TLB Page Support"
+	help
+	  This enables support for huge pages.  User space applications
+	  can make use of this support with the sys_alloc_hugepages and
+	  sys_free_hugepages system calls.  If your applications are
+	  huge page aware and your processor supports this (only POWER4,
+	  then say Y here.
+
+	  Otherwise, say N.
+
 config SMP
 	bool "Symmetric multi-processing support"
 	---help---

arch/ppc64/Makefile

@@ -18,7 +18,13 @@ KERNELLOAD	:= 0xc000000000000000
 LDFLAGS		:= -m elf64ppc
 LDFLAGS_vmlinux	:= -Bstatic -e $(KERNELLOAD) -Ttext $(KERNELLOAD)
 CFLAGS		+= -msoft-float -pipe -Wno-uninitialized -mminimal-toc \
-		-mtraceback=full -mcpu=power4
+		-mcpu=power4
+
+have_zero_bss := $(shell if $(CC) -fno-zero-initialized-in-bss -S -o /dev/null -xc /dev/null > /dev/null 2>&1; then echo y; else echo n; fi)
+
+ifeq ($(have_zero_bss),y)
+CFLAGS		+= -fno-zero-initialized-in-bss
+endif
 
 head-y := arch/ppc64/kernel/head.o
 
@@ -39,6 +45,12 @@ $(boottarget-y): vmlinux
 	rm -f .config arch/ppc64/defconfig
 	cp -f arch/ppc64/configs/$(@:config=defconfig) arch/ppc64/defconfig
 
+bootimage-$(CONFIG_PPC_PSERIES) := zImage
+bootimage-$(CONFIG_PPC_ISERIES) := vmlinux.sm
+BOOTIMAGE := $(bootimage-y)
+install: vmlinux
+	$(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) $@
+
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
 

arch/ppc64/boot/Makefile

@@ -122,5 +122,7 @@ $(obj)/imagesize.c: vmlinux
 	awk '{printf "unsigned long vmlinux_memsize = 0x%s;\n", substr($$1,8)}' \
 		>> $(obj)/imagesize.c
 
+install: $(CONFIGURE) $(obj)/$(BOOTIMAGE)
+	sh -x $(src)/install.sh "$(KERNELRELEASE)" "$(obj)/$(BOOTIMAGE)" "$(TOPDIR)/System.map" "$(INSTALL_PATH)"
 
 clean-files := $(patsubst $(obj)/%,%, $(obj-boot))

arch/ppc64/boot/install.sh

+#!/bin/sh
+#
+# arch/ppc64/boot/install.sh
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 1995 by Linus Torvalds
+#
+# Blatantly stolen from in arch/i386/boot/install.sh by Dave Hansen 
+#
+# "make install" script for ppc64 architecture
+#
+# Arguments:
+#   $1 - kernel version
+#   $2 - kernel image file
+#   $3 - kernel map file
+#   $4 - default install path (blank if root directory)
+#
+
+# User may have a custom install script
+
+if [ -x ~/bin/installkernel ]; then exec ~/bin/installkernel "$@"; fi
+if [ -x /sbin/installkernel ]; then exec /sbin/installkernel "$@"; fi
+
+# Default install
+
+# this should work for both the pSeries zImage and the iSeries vmlinux.sm
+image_name=`basename $2`
+
+if [ -f $4/$image_name ]; then
+	mv $4/$image_name $4/$image_name.old
+fi
+
+if [ -f $4/System.map ]; then
+	mv $4/System.map $4/System.old
+fi
+
+cat $2 > $4/$image_name
+cp $3 $4/System.map

arch/ppc64/defconfig

@@ -8,11 +8,13 @@ CONFIG_HAVE_DEC_LOCK=y
 CONFIG_EARLY_PRINTK=y
 CONFIG_COMPAT=y
 CONFIG_FRAME_POINTER=y
+CONFIG_FORCE_MAX_ZONEORDER=13
 
 #
 # Code maturity level options
 #
 CONFIG_EXPERIMENTAL=y
+# CONFIG_BROKEN is not set
 
 #
 # General setup
@@ -21,11 +23,14 @@ CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 CONFIG_SYSCTL=y
-CONFIG_LOG_BUF_SHIFT=15
+CONFIG_LOG_BUF_SHIFT=16
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
 # CONFIG_EMBEDDED is not set
 CONFIG_KALLSYMS=y
 CONFIG_FUTEX=y
 CONFIG_EPOLL=y
+CONFIG_IOSCHED_NOOP=y
 CONFIG_IOSCHED_AS=y
 CONFIG_IOSCHED_DEADLINE=y
 
@@ -72,7 +77,6 @@ CONFIG_PROC_DEVICETREE=y
 #
 # Generic Driver Options
 #
-# CONFIG_FW_LOADER is not set
 
 #
 # Memory Technology Devices (MTD)
@@ -99,7 +103,7 @@ CONFIG_BLK_DEV_FD=y
 # CONFIG_BLK_DEV_UMEM is not set
 CONFIG_BLK_DEV_LOOP=y
 # CONFIG_BLK_DEV_CRYPTOLOOP is not set
-CONFIG_BLK_DEV_NBD=y
+CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=4096
 CONFIG_BLK_DEV_INITRD=y
@@ -127,9 +131,9 @@ CONFIG_CHR_DEV_SG=y
 #
 # Some SCSI devices (e.g. CD jukebox) support multiple LUNs
 #
-# CONFIG_SCSI_MULTI_LUN is not set
-# CONFIG_SCSI_REPORT_LUNS is not set
-# CONFIG_SCSI_CONSTANTS is not set
+CONFIG_SCSI_MULTI_LUN=y
+CONFIG_SCSI_REPORT_LUNS=y
+CONFIG_SCSI_CONSTANTS=y
 # CONFIG_SCSI_LOGGING is not set
 
 #
@@ -178,7 +182,8 @@ CONFIG_MD_RAID0=y
 CONFIG_MD_RAID1=y
 CONFIG_MD_RAID5=y
 # CONFIG_MD_MULTIPATH is not set
-# CONFIG_BLK_DEV_DM is not set
+CONFIG_BLK_DEV_DM=y
+CONFIG_DM_IOCTL_V4=y
 
 #
 # Fusion MPT device support
@@ -206,9 +211,8 @@ CONFIG_NET=y
 CONFIG_PACKET=y
 # CONFIG_PACKET_MMAP is not set
 # CONFIG_NETLINK_DEV is not set
-# CONFIG_NETFILTER is not set
 CONFIG_UNIX=y
-# CONFIG_NET_KEY is not set
+CONFIG_NET_KEY=m
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 # CONFIG_IP_ADVANCED_ROUTER is not set
@@ -217,13 +221,17 @@ CONFIG_NET_IPIP=y
 # CONFIG_NET_IPGRE is not set
 # CONFIG_IP_MROUTE is not set
 # CONFIG_ARPD is not set
-# CONFIG_INET_ECN is not set
+CONFIG_INET_ECN=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_AH is not set
-# CONFIG_INET_ESP is not set
-# CONFIG_INET_IPCOMP is not set
+CONFIG_INET_AH=m
+CONFIG_INET_ESP=m
+CONFIG_INET_IPCOMP=m
 # CONFIG_IPV6 is not set
-# CONFIG_XFRM_USER is not set
+# CONFIG_DECNET is not set
+# CONFIG_BRIDGE is not set
+# CONFIG_NETFILTER is not set
+CONFIG_XFRM=y
+CONFIG_XFRM_USER=m
 
 #
 # SCTP Configuration (EXPERIMENTAL)
@@ -233,8 +241,6 @@ CONFIG_IPV6_SCTP__=y
 # CONFIG_ATM is not set
 # CONFIG_VLAN_8021Q is not set
 # CONFIG_LLC is not set
-# CONFIG_DECNET is not set
-# CONFIG_BRIDGE is not set
 # CONFIG_X25 is not set
 # CONFIG_LAPB is not set
 # CONFIG_NET_DIVERT is not set
@@ -258,10 +264,10 @@ CONFIG_NETDEVICES=y
 # ARCnet devices
 #
 # CONFIG_ARCNET is not set
-# CONFIG_DUMMY is not set
-# CONFIG_BONDING is not set
+CONFIG_DUMMY=m
+CONFIG_BONDING=m
 # CONFIG_EQUALIZER is not set
-# CONFIG_TUN is not set
+CONFIG_TUN=m
 # CONFIG_ETHERTAP is not set
 
 #
@@ -312,6 +318,7 @@ CONFIG_E1000=y
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
 # CONFIG_R8169 is not set
+# CONFIG_SIS190 is not set
 # CONFIG_SK98LIN is not set
 # CONFIG_TIGON3 is not set
 
@@ -321,7 +328,14 @@ CONFIG_E1000=y
 # CONFIG_IXGB is not set
 # CONFIG_FDDI is not set
 # CONFIG_HIPPI is not set
-# CONFIG_PPP is not set
+CONFIG_PPP=m
+# CONFIG_PPP_MULTILINK is not set
+# CONFIG_PPP_FILTER is not set
+CONFIG_PPP_ASYNC=m
+CONFIG_PPP_SYNC_TTY=m
+CONFIG_PPP_DEFLATE=m
+CONFIG_PPP_BSDCOMP=m
+CONFIG_PPPOE=m
 # CONFIG_SLIP is not set
 
 #
@@ -489,26 +503,32 @@ CONFIG_RAW_DRIVER=y
 # File systems
 #
 CONFIG_EXT2_FS=y
-# CONFIG_EXT2_FS_XATTR is not set
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_EXT2_FS_POSIX_ACL=y
+# CONFIG_EXT2_FS_SECURITY is not set
 CONFIG_EXT3_FS=y
-# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_EXT3_FS_XATTR=y
+CONFIG_EXT3_FS_POSIX_ACL=y
+# CONFIG_EXT3_FS_SECURITY is not set
 CONFIG_JBD=y
 # CONFIG_JBD_DEBUG is not set
+CONFIG_FS_MBCACHE=y
 CONFIG_REISERFS_FS=y
 # CONFIG_REISERFS_CHECK is not set
 # CONFIG_REISERFS_PROC_INFO is not set
 CONFIG_JFS_FS=y
-# CONFIG_JFS_POSIX_ACL is not set
+CONFIG_JFS_POSIX_ACL=y
 # CONFIG_JFS_DEBUG is not set
 # CONFIG_JFS_STATISTICS is not set
-CONFIG_XFS_FS=y
+CONFIG_FS_POSIX_ACL=y
+CONFIG_XFS_FS=m
 # CONFIG_XFS_RT is not set
 # CONFIG_XFS_QUOTA is not set
-# CONFIG_XFS_POSIX_ACL is not set
+CONFIG_XFS_POSIX_ACL=y
 # CONFIG_MINIX_FS is not set
 # CONFIG_ROMFS_FS is not set
 # CONFIG_QUOTA is not set
-CONFIG_AUTOFS_FS=y
+CONFIG_AUTOFS_FS=m
 # CONFIG_AUTOFS4_FS is not set
 
 #
@@ -517,7 +537,7 @@ CONFIG_AUTOFS_FS=y
 CONFIG_ISO9660_FS=y
 # CONFIG_JOLIET is not set
 # CONFIG_ZISOFS is not set
-# CONFIG_UDF_FS is not set
+CONFIG_UDF_FS=m
 
 #
 # DOS/FAT/NT Filesystems
@@ -533,8 +553,9 @@ CONFIG_VFAT_FS=y
 CONFIG_PROC_FS=y
 # CONFIG_DEVFS_FS is not set
 CONFIG_DEVPTS_FS=y
-# CONFIG_DEVPTS_FS_XATTR is not set
-# CONFIG_TMPFS is not set
+CONFIG_DEVPTS_FS_XATTR=y
+# CONFIG_DEVPTS_FS_SECURITY is not set
+CONFIG_TMPFS=y
 CONFIG_RAMFS=y
 
 #
@@ -546,7 +567,7 @@ CONFIG_RAMFS=y
 # CONFIG_BEFS_FS is not set
 # CONFIG_BFS_FS is not set
 # CONFIG_EFS_FS is not set
-# CONFIG_CRAMFS is not set
+CONFIG_CRAMFS=y
 # CONFIG_VXFS_FS is not set
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
@@ -561,15 +582,16 @@ CONFIG_NFS_V3=y
 CONFIG_NFS_V4=y
 CONFIG_NFSD=y
 CONFIG_NFSD_V3=y
-# CONFIG_NFSD_V4 is not set
+CONFIG_NFSD_V4=y
 CONFIG_NFSD_TCP=y
 CONFIG_LOCKD=y
 CONFIG_LOCKD_V4=y
 CONFIG_EXPORTFS=y
 CONFIG_SUNRPC=y
-# CONFIG_SUNRPC_GSS is not set
+CONFIG_SUNRPC_GSS=m
+CONFIG_RPCSEC_GSS_KRB5=m
 # CONFIG_SMB_FS is not set
-CONFIG_CIFS=y
+CONFIG_CIFS=m
 # CONFIG_NCP_FS is not set
 # CONFIG_CODA_FS is not set
 # CONFIG_INTERMEZZO_FS is not set
@@ -705,6 +727,7 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_XMON=y
 CONFIG_XMON_DEFAULT=y
 # CONFIG_PPCDBG is not set
+# CONFIG_DEBUG_INFO is not set
 
 #
 # Security options
@@ -714,9 +737,27 @@ CONFIG_XMON_DEFAULT=y
 #
 # Cryptographic options
 #
-# CONFIG_CRYPTO is not set
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_NULL=m
+CONFIG_CRYPTO_MD4=m
+CONFIG_CRYPTO_MD5=m
+CONFIG_CRYPTO_SHA1=m
+CONFIG_CRYPTO_SHA256=m
+CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_DES=m
+CONFIG_CRYPTO_BLOWFISH=m
+CONFIG_CRYPTO_TWOFISH=m
+CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_AES=m
+CONFIG_CRYPTO_CAST5=m
+CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DEFLATE=m
+CONFIG_CRYPTO_TEST=m
 
 #
 # Library routines
 #
 CONFIG_CRC32=y
+CONFIG_ZLIB_INFLATE=y
+CONFIG_ZLIB_DEFLATE=m

arch/ppc64/kernel/asm-offsets.c

@@ -83,9 +83,7 @@ int main(void)
         DEFINE(PACALPQUEUE, offsetof(struct paca_struct, lpQueuePtr));
 	DEFINE(PACATOC, offsetof(struct paca_struct, xTOC));
 	DEFINE(PACAEXCSP, offsetof(struct paca_struct, exception_sp));
-	DEFINE(PACAHRDWINTSTACK, offsetof(struct paca_struct, xHrdIntStack));
 	DEFINE(PACAPROCENABLED, offsetof(struct paca_struct, xProcEnabled));
-	DEFINE(PACAHRDWINTCOUNT, offsetof(struct paca_struct, xHrdIntCount));
 	DEFINE(PACADEFAULTDECR, offsetof(struct paca_struct, default_decr));
 	DEFINE(PACAPROFENABLED, offsetof(struct paca_struct, prof_enabled));
 	DEFINE(PACAPROFLEN, offsetof(struct paca_struct, prof_len));

arch/ppc64/kernel/chrp_setup.c

@@ -72,6 +72,7 @@ extern void openpic_init_IRQ(void);
 
 extern void find_and_init_phbs(void);
 
+extern void pSeries_get_boot_time(struct rtc_time *rtc_time);
 extern void pSeries_get_rtc_time(struct rtc_time *rtc_time);
 extern int  pSeries_set_rtc_time(struct rtc_time *rtc_time);
 void pSeries_calibrate_decr(void);
@@ -256,7 +257,7 @@ chrp_init(unsigned long r3, unsigned long r4, unsigned long r5,
 	ppc_md.power_off      = rtas_power_off;
 	ppc_md.halt           = rtas_halt;
 
-	ppc_md.get_boot_time  = pSeries_get_rtc_time;
+	ppc_md.get_boot_time  = pSeries_get_boot_time;
 	ppc_md.get_rtc_time   = pSeries_get_rtc_time;
 	ppc_md.set_rtc_time   = pSeries_set_rtc_time;
 	ppc_md.calibrate_decr = pSeries_calibrate_decr;

arch/ppc64/kernel/eeh.c

@@ -115,8 +115,17 @@ unsigned long eeh_check_failure(void *token, unsigned long val)
 		ret = rtas_call(ibm_read_slot_reset_state, 3, 3, rets,
 				dn->eeh_config_addr, BUID_HI(dn->phb->buid), BUID_LO(dn->phb->buid));
 		if (ret == 0 && rets[1] == 1 && rets[0] >= 2) {
-			panic("EEH:  MMIO failure (%ld) on device:\n  %s %s\n",
-			      rets[0], pci_name(dev), dev->dev.name);
+			/*
+			 * XXX We should create a separate sysctl for this.
+			 *
+			 * Since the panic_on_oops sysctl is used to halt
+			 * the system in light of potential corruption, we
+			 * can use it here.
+			 */
+			if (panic_on_oops)
+				panic("EEH: MMIO failure (%ld) on device:\n%s\n", rets[0], pci_name(dev));
+			else
+				printk("EEH: MMIO failure (%ld) on device:\n%s\n", rets[0], pci_name(dev));
 		}
 	}
 	eeh_false_positives++;

arch/ppc64/kernel/head.S

@@ -40,6 +40,15 @@
 #define DO_SOFT_DISABLE
 #endif
 
+/* copy saved SOFTE bit or EE bit from saved MSR depending
+ * if we are doing soft-disable or not
+ */
+#ifdef DO_SOFT_DISABLE
+#define DO_COPY_EE()	ld	r20,SOFTE(r1)
+#else
+#define DO_COPY_EE()	rldicl	r20,r23,49,63
+#endif
+
 /*
  * hcall interface to pSeries LPAR
  */
@@ -618,11 +627,7 @@ stab_bolted_user_return:
 	ld      r4,_DAR(r1)
 	ld      r5,_DSISR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-#ifdef DO_SOFT_DISABLE
-	ld	r20,SOFTE(r1)		/* Copy saved SOFTE bit */
-#else
-	rldicl	r20,r23,49,63   	/* copy EE bit from saved MSR */
-#endif
+	DO_COPY_EE()
 	li	r6,0x300
 	bl      .save_remaining_regs
 	bl      .do_page_fault
@@ -644,12 +649,9 @@ DataAccessSLB_common:
 	or.	r3,r3,r3		/* Check return code */
 	beq     fast_exception_return   /* Return if we succeeded */
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-#ifdef DO_SOFT_DISABLE
-	ld	r20,SOFTE(r1)
-#else
-	rldicl	r20,r23,49,63   	/* copy EE bit from saved MSR */
-#endif
+	DO_COPY_EE()
 	li	r6,0x380
+	li	r5,0
 	bl      .save_remaining_regs
 	bl      .do_page_fault
 	b       .ret_from_except
@@ -670,13 +672,9 @@ InstructionAccess_common:
 	bl	.do_hash_page_ISI	/* Try to handle as hpte fault */
 1:
 	mr	r4,r22
-	mr	r5,r23
+	rlwinm	r5,r23,0,4,4		/* We only care about PR in error_code */
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-#ifdef DO_SOFT_DISABLE
-	ld	r20,SOFTE(r1)
-#else
-	rldicl	r20,r23,49,63   	/* copy EE bit from saved MSR */
-#endif
+	DO_COPY_EE()
 	li	r6,0x400
 	bl      .save_remaining_regs
 	bl      .do_page_fault
@@ -692,12 +690,9 @@ InstructionAccessSLB_common:
 	beq+	fast_exception_return   /* Return if we succeeded */
 
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-#ifdef DO_SOFT_DISABLE
-	ld	r20,SOFTE(r1)
-#else
-	rldicl	r20,r23,49,63   	/* copy EE bit from saved MSR */
-#endif
+	DO_COPY_EE()
 	li	r6,0x480
+	li	r5,0
 	bl      .save_remaining_regs
 	bl      .do_page_fault
 	b       .ret_from_except
@@ -710,70 +705,14 @@ HardwareInterrupt_entry:
 	li	r20,0
 	li	r6,0x500
 	bl      .save_remaining_regs
-	/* Determine if need to run do_irq on a hardware interrupt stack  */
-	/*   The first invocation of do_irq will occur on the kernel      */
-	/*   stack in the current stack                                   */
-	/*   All other invocations of do_irq will run on the hardware     */
-	/*   interrupt stack associated with the PACA of the current      */
-	/*   processor.                                                   */
-	/*                                                                */
-	/*  The call to do_irq will preserve the value of r14 - r31       */
-	/*                                                                */
-/*
- * XXX turn off interrupt stacks until the thread_info stuff is fixed.
- * Otherwise we end up setting need_resched etc bits in the interrupt
- *  stack and they never get seen when we return to the process stack - Anton
- */
-#if 0
-	lbz     r21,PACAHRDWINTCOUNT(r13)    /* get hardware interrupt cnt */
-	cmpi    0,r21,1                     /*                            */
-	addi    r21,r21,1                   /* incr hardware interrupt cnt*/
-	stb     r21,PACAHRDWINTCOUNT(r13)   /*                            */
-	bne     2f                          /*                            */
-
-	mr      r14,r1                      /* preserve current r1        */
-	ld      r1,PACAHRDWINTSTACK(r13)    /*                            */
-	std     r14,0(r1)                   /* set the back chain         */
 	bl      .do_IRQ
-	lbz     r22,PACAHRDWINTCOUNT(r13)   /* get hardware interrupt cnt */
-	cmp     0,r22,r21                   /* debug test                 */
-	bne     3f
-	subi    r21,r21,1
-	stb     r21,PACAHRDWINTCOUNT(r13)   /*                            */
-	mr      r1,r14                      /*                            */
 	b       .ret_from_except
-#endif
-
-2:
-	bl      .do_IRQ
-
-#if 0
-	lbz     r22,PACAHRDWINTCOUNT(r13)   /* get hardware interrupt cnt */
-	cmp     0,r22,r21                   /* debug test                 */
-	bne     3f                          /*                            */
-	subi    r21,r21,1                   /* decr hardware interrupt cnt*/
-	stb     r21,PACAHRDWINTCOUNT(r13)   /*                            */
-#endif
-
-	b       .ret_from_except
-
-3:
-	/* error - counts out of sync                                      */
-#ifdef CONFIG_XMON
-	bl	.xmon
-#endif
-4:	b	4b
-
 
 	.globl Alignment_common
 Alignment_common:
 	EXCEPTION_PROLOG_COMMON
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-#ifdef DO_SOFT_DISABLE
-	ld	r20,SOFTE(r1)
-#else
-	rldicl	r20,r23,49,63   	/* copy EE bit from saved MSR */
-#endif
+	DO_COPY_EE()
 	li	r6,0x600
 	bl      .save_remaining_regs
 	bl      .AlignmentException
@@ -783,11 +722,7 @@ Alignment_common:
 ProgramCheck_common:
 	EXCEPTION_PROLOG_COMMON
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-#ifdef DO_SOFT_DISABLE
-	ld	r20,SOFTE(r1)
-#else
-	rldicl	r20,r23,49,63   	/* copy EE bit from saved MSR */
-#endif
+	DO_COPY_EE()
 	li	r6,0x700
 	bl      .save_remaining_regs
 	bl      .ProgramCheckException
@@ -798,11 +733,7 @@ FPUnavailable_common:
 	EXCEPTION_PROLOG_COMMON
 	bne	.load_up_fpu		/* if from user, just load it up */
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-#ifdef DO_SOFT_DISABLE
-	ld	r20,SOFTE(r1)
-#else
-	rldicl	r20,r23,49,63   	/* copy EE bit from saved MSR */
-#endif
+	DO_COPY_EE()
 	li	r6,0x800
 	bl      .save_remaining_regs
 	bl      .KernelFPUnavailableException
@@ -818,11 +749,7 @@ SystemCall_common:
 	beq+	HardwareInterrupt_entry
 1:
 #endif
-#ifdef DO_SOFT_DISABLE
-	ld	r20,SOFTE(r1)
-#else
-	rldicl	r20,r23,49,63   	/* copy EE bit from saved MSR */
-#endif
+	DO_COPY_EE()
 	li	r6,0xC00
 	bl      .save_remaining_regs
 	bl      .DoSyscall
@@ -1866,18 +1793,6 @@ _STATIC(start_here_common)
 	li	r5,0
 	std	r0,PACAKSAVE(r13)
 
-	/* ptr to hardware interrupt stack for boot processor */
-	LOADADDR(r3, hardware_int_paca0)
-	li      r5,PAGE_SIZE
-	sldi    r5,r5,3
-	subi    r5,r5,STACK_FRAME_OVERHEAD
-
-	add     r3,r3,r5
-	std     r3,PACAHRDWINTSTACK(r13)
-
-	li      r3,0
-	stb     r3,PACAHRDWINTCOUNT(r13)
-
 	/* Restore the parms passed in from the bootloader. */
 	mr	r3,r31
 	mr	r4,r30
@@ -1999,10 +1914,6 @@ swapper_pg_dir:
 ioremap_dir:
 	.space	4096
 
-	.globl  hardware_int_paca0
-hardware_int_paca0:
-	.space	8*PAGE_SIZE
-
 /* 1 page segment table per cpu (max 48, cpu0 allocated at STAB0_PHYS_ADDR) */
 	.globl	stab_array
 stab_array:

arch/ppc64/kernel/htab.c

@@ -197,7 +197,7 @@ pte_t *find_linux_pte(pgd_t *pgdir, unsigned long ea)
 	if (!pgd_none(*pg)) {
 
 		pm = pmd_offset(pg, ea);
-		if (!pmd_none(*pm)) { 
+		if (pmd_present(*pm)) { 
 			pt = pte_offset_kernel(pm, ea);
 			pte = *pt;
 			if (!pte_present(pte))
@@ -436,8 +436,12 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 	if (user_region && cpus_equal(mm->cpu_vm_mask, tmp))
 		local = 1;
 
-	ptep = find_linux_pte(pgdir, ea);
-	ret = __hash_page(ea, access, vsid, ptep, trap, local);
+	ret = hash_huge_page(mm, access, ea, vsid, local);
+	if (ret < 0) {
+		ptep = find_linux_pte(pgdir, ea);
+		ret = __hash_page(ea, access, vsid, ptep, trap, local);
+	}
+
 	spin_unlock(&mm->page_table_lock);
 
 	return ret;

arch/ppc64/kernel/irq.c

@@ -39,6 +39,7 @@
 #include <linux/irq.h>
 #include <linux/proc_fs.h>
 #include <linux/random.h>
+#include <linux/kallsyms.h>
 
 #include <asm/uaccess.h>
 #include <asm/bitops.h>
@@ -350,14 +351,11 @@ int show_interrupts(struct seq_file *p, void *v)
 	return 0;
 }
 
-extern char *ppc_find_proc_name(unsigned *p, char *buf, unsigned buflen);
-
-static inline void handle_irq_event(int irq, struct pt_regs *regs,
-				    struct irqaction *action)
+static inline int handle_irq_event(int irq, struct pt_regs *regs,
+				   struct irqaction *action)
 {
 	int status = 0;
 	int retval = 0;
-	struct irqaction *first_action = action;
 
 	if (!(action->flags & SA_INTERRUPT))
 		local_irq_enable();
@@ -370,30 +368,90 @@ static inline void handle_irq_event(int irq, struct pt_regs *regs,
 	if (status & SA_SAMPLE_RANDOM)
 		add_interrupt_randomness(irq);
 	local_irq_disable();
-	if (retval != 1) {
-		static int count = 100;
-		char name_buf[256];
-		if (count) {
-			count--;
-			if (retval) {
-				printk("irq event %d: bogus retval mask %x\n",
-					irq, retval);
-			} else {
-				printk("irq %d: nobody cared!\n", irq);
-			}
-			dump_stack();
-			printk("handlers:\n");
-			action = first_action;
-			do {
-				printk("[<%p>]", action->handler);
-				printk(" (%s)\n",
-				       ppc_find_proc_name((unsigned *)action->handler, name_buf, 256));
-				action = action->next;
-			} while (action);
-		}
+	return retval;
+}
+
+static void __report_bad_irq(int irq, irq_desc_t *desc, irqreturn_t action_ret)
+{
+	struct irqaction *action;
+
+	if (action_ret != IRQ_HANDLED && action_ret != IRQ_NONE) {
+		printk(KERN_ERR "irq event %d: bogus return value %x\n",
+				irq, action_ret);
+	} else {
+		printk(KERN_ERR "irq %d: nobody cared!\n", irq);
+	}
+	dump_stack();
+	printk(KERN_ERR "handlers:\n");
+	action = desc->action;
+	do {
+		printk(KERN_ERR "[<%p>]", action->handler);
+		print_symbol(" (%s)",
+			(unsigned long)action->handler);
+		printk("\n");
+		action = action->next;
+	} while (action);
+}
+
+static void report_bad_irq(int irq, irq_desc_t *desc, irqreturn_t action_ret)
+{
+	static int count = 100;
+
+	if (count) {
+		count--;
+		__report_bad_irq(irq, desc, action_ret);
 	}
 }
 
+static int noirqdebug;
+
+static int __init noirqdebug_setup(char *str)
+{
+	noirqdebug = 1;
+	printk("IRQ lockup detection disabled\n");
+	return 1;
+}
+
+__setup("noirqdebug", noirqdebug_setup);
+
+/*
+ * If 99,900 of the previous 100,000 interrupts have not been handled then
+ * assume that the IRQ is stuck in some manner.  Drop a diagnostic and try to
+ * turn the IRQ off.
+ *
+ * (The other 100-of-100,000 interrupts may have been a correctly-functioning
+ *  device sharing an IRQ with the failing one)
+ *
+ * Called under desc->lock
+ */
+static void note_interrupt(int irq, irq_desc_t *desc, irqreturn_t action_ret)
+{
+	if (action_ret != IRQ_HANDLED) {
+		desc->irqs_unhandled++;
+		if (action_ret != IRQ_NONE)
+			report_bad_irq(irq, desc, action_ret);
+	}
+
+	desc->irq_count++;
+	if (desc->irq_count < 100000)
+		return;
+
+	desc->irq_count = 0;
+	if (desc->irqs_unhandled > 99900) {
+		/*
+		 * The interrupt is stuck
+		 */
+		__report_bad_irq(irq, desc, action_ret);
+		/*
+		 * Now kill the IRQ
+		 */
+		printk(KERN_EMERG "Disabling IRQ #%d\n", irq);
+		desc->status |= IRQ_DISABLED;
+		desc->handler->disable(irq);
+	}
+	desc->irqs_unhandled = 0;
+}
+
 /*
  * Eventually, this should take an array of interrupts and an array size
  * so it can dispatch multiple interrupts.
@@ -462,10 +520,13 @@ void ppc_irq_dispatch_handler(struct pt_regs *regs, int irq)
 	 * SMP environment.
 	 */
 	for (;;) {
+		irqreturn_t action_ret;
+
 		spin_unlock(&desc->lock);
-		handle_irq_event(irq, regs, action);
+		action_ret = handle_irq_event(irq, regs, action);
 		spin_lock(&desc->lock);
-		
+		if (!noirqdebug)
+			note_interrupt(irq, desc, action_ret);
 		if (likely(!(desc->status & IRQ_PENDING)))
 			break;
 		desc->status &= ~IRQ_PENDING;

arch/ppc64/kernel/pSeries_lpar.c

@@ -36,18 +36,6 @@
 #include <asm/tlb.h>
 #include <asm/hvcall.h>
 
-
-long plpar_pte_enter(unsigned long flags,
-		     unsigned long ptex,
-		     unsigned long new_pteh, unsigned long new_ptel,
-		     unsigned long *old_pteh_ret, unsigned long *old_ptel_ret)
-{
-	unsigned long dummy, ret;
-	ret = plpar_hcall(H_ENTER, flags, ptex, new_pteh, new_ptel,
-			   old_pteh_ret, old_ptel_ret, &dummy);
-	return(ret);
-}
-
 long plpar_pte_remove(unsigned long flags,
 		      unsigned long ptex,
 		      unsigned long avpn,
@@ -83,7 +71,6 @@ long plpar_tce_get(unsigned long liobn,
 			   tce_ret, &dummy, &dummy);
 }
 
-
 long plpar_tce_put(unsigned long liobn,
 		   unsigned long ioba,
 		   unsigned long tceval)
@@ -104,10 +91,9 @@ long plpar_put_term_char(unsigned long termno,
 			 unsigned long len,
 			 const char *buffer)
 {
-	unsigned long dummy;
 	unsigned long *lbuf = (unsigned long *)buffer;  /* ToDo: alignment? */
-	return plpar_hcall(H_PUT_TERM_CHAR, termno, len,
-			   lbuf[0], lbuf[1], &dummy, &dummy, &dummy);
+	return plpar_hcall_norets(H_PUT_TERM_CHAR, termno, len, lbuf[0],
+				  lbuf[1]);
 }
 
 static void tce_build_pSeriesLP(struct TceTable *tbl, long tcenum, 
@@ -287,12 +273,11 @@ int hvc_get_chars(int index, char *buf, int count)
 
 int hvc_put_chars(int index, const char *buf, int count)
 {
-	unsigned long dummy;
 	unsigned long *lbuf = (unsigned long *) buf;
 	long ret;
 
-	ret = plpar_hcall(H_PUT_TERM_CHAR, index, count, lbuf[0], lbuf[1],
-			  &dummy, &dummy, &dummy);
+	ret = plpar_hcall_norets(H_PUT_TERM_CHAR, index, count, lbuf[0],
+				 lbuf[1]);
 	if (ret == H_Success)
 		return count;
 	if (ret == H_Busy)
@@ -318,7 +303,6 @@ int hvc_count(int *start_termno)
 
 
 
-
 long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 			      unsigned long va, unsigned long prpn,
 			      int secondary, unsigned long hpteflags,
@@ -329,6 +313,7 @@ long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 	unsigned long flags;
 	unsigned long slot;
 	HPTE lhpte;
+	unsigned long dummy0, dummy1;
 
 	/* Fill in the local HPTE with absolute rpn, avpn and flags */
 	lhpte.dw1.dword1      = 0;
@@ -348,7 +333,6 @@ long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 
 	/* Now fill in the actual HPTE */
 	/* Set CEC cookie to 0         */
-	/* Large page = 0              */
 	/* Zero page = 0               */
 	/* I-cache Invalidate = 0      */
 	/* I-cache synchronize = 0     */
@@ -359,19 +343,8 @@ long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 	if (hpteflags & (_PAGE_GUARDED|_PAGE_NO_CACHE))
 		lhpte.dw1.flags.flags &= ~_PAGE_COHERENT;
 
-	__asm__ __volatile__ (
-		H_ENTER_r3
-		"mr    4, %2\n"
-                "mr    5, %3\n"
-                "mr    6, %4\n"
-                "mr    7, %5\n"
-                HSC    
-                "mr    %0, 3\n"
-                "mr    %1, 4\n"
-		: "=r" (lpar_rc), "=r" (slot)
-		: "r" (flags), "r" (hpte_group), "r" (lhpte.dw0.dword0),
-		"r" (lhpte.dw1.dword1)
-		: "r3", "r4", "r5", "r6", "r7", "cc");
+	lpar_rc = plpar_hcall(H_ENTER, flags, hpte_group, lhpte.dw0.dword0,
+			      lhpte.dw1.dword1, &slot, &dummy0, &dummy1);
 
 	if (lpar_rc == H_PTEG_Full)
 		return -1;

arch/ppc64/kernel/pSeries_pci.c

@@ -427,6 +427,7 @@ unsigned long __init find_and_init_phbs(void)
 
 void pcibios_name_device(struct pci_dev *dev)
 {
+#if 0
 	struct device_node *dn;
 
 	/*
@@ -446,6 +447,7 @@ void pcibios_name_device(struct pci_dev *dev)
 			}
 		}
 	}
+#endif
 }   
 
 void __init pcibios_fixup_device_resources(struct pci_dev *dev,

arch/ppc64/kernel/ppc_ksyms.c

@@ -49,8 +49,6 @@
 
 extern int sys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg);
 extern int do_signal(sigset_t *, struct pt_regs *);
-extern int register_ioctl32_conversion(unsigned int cmd, int (*handler)(unsigned int, unsigned int, unsigned long, struct file *));
-extern int unregister_ioctl32_conversion(unsigned int cmd);
 
 int abs(int);
 
@@ -66,9 +64,6 @@ EXPORT_SYMBOL(disable_irq_nosync);
 EXPORT_SYMBOL(synchronize_irq);
 #endif /* CONFIG_SMP */
 
-EXPORT_SYMBOL(register_ioctl32_conversion);
-EXPORT_SYMBOL(unregister_ioctl32_conversion);
-
 EXPORT_SYMBOL(isa_io_base);
 EXPORT_SYMBOL(pci_io_base);
 

arch/ppc64/kernel/process.c

@@ -32,6 +32,7 @@
 #include <linux/init_task.h>
 #include <linux/prctl.h>
 #include <linux/ptrace.h>
+#include <linux/kallsyms.h>
 
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
@@ -130,12 +131,9 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	return last;
 }
 
-char *ppc_find_proc_name(unsigned *p, char *buf, unsigned buflen);
-
 void show_regs(struct pt_regs * regs)
 {
 	int i;
-	char name_buf[256];
 
 	printk("NIP: %016lX XER: %016lX LR: %016lX\n",
 	       regs->nip, regs->xer, regs->link);
@@ -170,8 +168,7 @@ void show_regs(struct pt_regs * regs)
 	 * above info out without failing
 	 */
 	printk("NIP [%016lx] ", regs->nip);
-	printk("%s\n", ppc_find_proc_name((unsigned *)regs->nip,
-	       name_buf, 256));
+	print_symbol("%s\n", regs->nip);
 	show_stack(current, (unsigned long *)regs->gpr[1]);
 }
 
@@ -385,102 +382,6 @@ int sys_execve(unsigned long a0, unsigned long a1, unsigned long a2,
 	return error;
 }
 
-void initialize_paca_hardware_interrupt_stack(void)
-{
-	int i;
-	unsigned long stack;
-	unsigned long end_of_stack =0;
-
-	for (i=1; i < NR_CPUS; i++) {
-		if (!cpu_possible(i))
-			continue;
-		/* Carve out storage for the hardware interrupt stack */
-		stack = __get_free_pages(GFP_ATOMIC, get_order(8*PAGE_SIZE));
-
-		if ( !stack ) {     
-			printk("ERROR, cannot find space for hardware stack.\n");
-			panic(" no hardware stack ");
-		}
-
-
-		/* Store the stack value in the PACA for the processor */
-		paca[i].xHrdIntStack = stack + (8*PAGE_SIZE) - STACK_FRAME_OVERHEAD;
-		paca[i].xHrdIntCount = 0;
-
-	}
-
-	/*
-	 * __get_free_pages() might give us a page > KERNBASE+256M which
-	 * is mapped with large ptes so we can't set up the guard page.
-	 */
-	if (cur_cpu_spec->cpu_features & CPU_FTR_16M_PAGE)
-		return;
-
-	for (i=0; i < NR_CPUS; i++) {
-		if (!cpu_possible(i))
-			continue;
-		/* set page at the top of stack to be protected - prevent overflow */
-		end_of_stack = paca[i].xHrdIntStack - (8*PAGE_SIZE - STACK_FRAME_OVERHEAD);
-		ppc_md.hpte_updateboltedpp(PP_RXRX,end_of_stack);
-	}
-}
-
-char *ppc_find_proc_name(unsigned *p, char *buf, unsigned buflen)
-{
-	unsigned long tb_flags;
-	unsigned short name_len;
-	unsigned long tb_start, code_start, code_ptr, code_offset;
-	unsigned int code_len;
-	unsigned long end;
-
-	strcpy(buf, "Unknown");
-	code_ptr = (unsigned long)p;
-	code_offset = 0;
-
-	/* handle functions in text and init sections */
-	if (((unsigned long)p >= (unsigned long)_stext) && 
-	    ((unsigned long)p < (unsigned long)_etext))
-		end = (unsigned long)_etext;
-	else if (((unsigned long)p >= (unsigned long)__init_begin) && 
-		 ((unsigned long)p < (unsigned long)__init_end))
-		end = (unsigned long)__init_end;
-	else
-		return buf;
-
-	while ((unsigned long)p < end) {
-		if (*p == 0) {
-			tb_start = (unsigned long)p;
-			++p;	/* Point to traceback flags */
-			tb_flags = *((unsigned long *)p);
-			p += 2;	/* Skip over traceback flags */
-			if (tb_flags & TB_NAME_PRESENT) {
-				if (tb_flags & TB_PARMINFO)
-					++p;	/* skip over parminfo data */
-				if (tb_flags & TB_HAS_TBOFF) {
-					code_len = *p;	/* get code length */
-					code_start = tb_start - code_len;
-					code_offset = code_ptr - code_start + 1;
-					if (code_offset > 0x100000)
-						break;
-					++p;	/* skip over code size */
-				}
-				name_len = *((unsigned short *)p);
-				if (name_len > (buflen-20))
-					name_len = buflen-20;
-				memcpy(buf, ((char *)p)+2, name_len);
-				buf[name_len] = 0;
-				if (code_offset)
-					sprintf(buf+name_len, "+0x%lx",
-						code_offset-1); 
-			}
-			break;
-		}
-		++p;
-	}
-
-	return buf;
-}
-
 /*
  * These bracket the sleeping functions..
  */
@@ -520,7 +421,6 @@ void show_stack(struct task_struct *p, unsigned long *_sp)
 	unsigned long ip;
 	unsigned long stack_page = (unsigned long)p->thread_info;
 	int count = 0;
-	char name_buf[256];
 	unsigned long sp = (unsigned long)_sp;
 
 	if (!p)
@@ -539,8 +439,7 @@ void show_stack(struct task_struct *p, unsigned long *_sp)
 		if (__get_user(ip, (unsigned long *)(sp + 16)))
 			break;
 		printk("[%016lx] ", ip);
-		printk("%s\n", ppc_find_proc_name((unsigned *)ip,
-		       name_buf, 256));
+		print_symbol("%s\n", ip);
 	} while (count++ < 32);
 }
 

arch/ppc64/kernel/rtas.c

@@ -24,6 +24,7 @@
 #include <asm/machdep.h>
 #include <asm/paca.h>
 #include <asm/page.h>
+#include <asm/param.h>
 #include <asm/system.h>
 #include <asm/abs_addr.h>
 #include <asm/udbg.h>
@@ -178,6 +179,26 @@ rtas_call(int token, int nargs, int nret,
 	return (ulong)((nret > 0) ? rtas_args->rets[0] : 0);
 }
 
+/* Given an RTAS status code of 990n compute the hinted delay of 10^n
+ * (last digit) milliseconds.  For now we bound at n=3 (1 sec).
+ */
+unsigned int
+rtas_extended_busy_delay_time(int status)
+{
+	int order = status - 9900;
+	unsigned int ms;
+
+	if (order < 0)
+		order = 0;	/* RTC depends on this for -2 clock busy */
+	else if (order > 3)
+		order = 3;	/* bound */
+
+	/* Use microseconds for reasonable accuracy */
+	for (ms = 1000; order > 0; order--)
+		ms = ms * 10;
+	return ms / (1000000/HZ); /* round down is fine */
+}
+
 #define FLASH_BLOCK_LIST_VERSION (1UL)
 static void
 rtas_flash_firmware(void)

arch/ppc64/kernel/rtc.c

@@ -35,6 +35,7 @@
 #include <linux/spinlock.h>
 #include <linux/bcd.h>
 
+#include <asm/hardirq.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -340,20 +341,63 @@ void iSeries_get_boot_time(struct rtc_time *tm)
 #endif
 
 #ifdef CONFIG_PPC_PSERIES
+#define MAX_RTC_WAIT 5000	/* 5 sec */
+#define RTAS_CLOCK_BUSY (-2)
+void pSeries_get_boot_time(struct rtc_time *rtc_tm)
+{
+	unsigned long ret[8];
+	int error, wait_time;
+	unsigned long max_wait_tb;
+
+	max_wait_tb = __get_tb() + tb_ticks_per_usec * 1000 * MAX_RTC_WAIT;
+	do {
+		error = rtas_call(rtas_token("get-time-of-day"), 0, 8, (void *)&ret);
+		if (error == RTAS_CLOCK_BUSY || rtas_is_extended_busy(error)) {
+			wait_time = rtas_extended_busy_delay_time(error);
+			/* This is boot time so we spin. */
+			udelay(wait_time*1000);
+			error = RTAS_CLOCK_BUSY;
+		}
+	} while (error == RTAS_CLOCK_BUSY && (__get_tb() < max_wait_tb));
+
+	if (error != 0) {
+		printk(KERN_WARNING "error: reading the clock failed (%d)\n",
+			error);
+		return;
+	}
+
+	rtc_tm->tm_sec = ret[5];
+	rtc_tm->tm_min = ret[4];
+	rtc_tm->tm_hour = ret[3];
+	rtc_tm->tm_mday = ret[2];
+	rtc_tm->tm_mon = ret[1] - 1;
+	rtc_tm->tm_year = ret[0] - 1900;
+}
+
+/* NOTE: get_rtc_time will get an error if executed in interrupt context
+ * and if a delay is needed to read the clock.  In this case we just
+ * silently return without updating rtc_tm.
+ */
 void pSeries_get_rtc_time(struct rtc_time *rtc_tm)
 {
         unsigned long ret[8];
-        int error;
-	int count;
+	int error, wait_time;
+	unsigned long max_wait_tb;
 
-	/*
-	 * error -2 is clock busy, we keep retrying a few times to see
-	 * if it will come good  -- paulus
-	 */
-	count = 0;
+	max_wait_tb = __get_tb() + tb_ticks_per_usec * 1000 * MAX_RTC_WAIT;
 	do {
 		error = rtas_call(rtas_token("get-time-of-day"), 0, 8, (void *)&ret);
-	} while (error == -2 && ++count < 1000);
+		if (error == RTAS_CLOCK_BUSY || rtas_is_extended_busy(error)) {
+			if (in_interrupt()) {
+				printk(KERN_WARNING "error: reading clock would delay interrupt\n");
+				return;	/* delay not allowed */
+			}
+			wait_time = rtas_extended_busy_delay_time(error);
+			set_current_state(TASK_INTERRUPTIBLE);
+			schedule_timeout(wait_time);
+			error = RTAS_CLOCK_BUSY;
+		}
+	} while (error == RTAS_CLOCK_BUSY && (__get_tb() < max_wait_tb));
 
         if (error != 0) {
                 printk(KERN_WARNING "error: reading the clock failed (%d)\n",
@@ -371,20 +415,24 @@ void pSeries_get_rtc_time(struct rtc_time *rtc_tm)
 
 int pSeries_set_rtc_time(struct rtc_time *tm)
 {
-        int error;
-	int count;
+	int error, wait_time;
+	unsigned long max_wait_tb;
 
-	/*
-	 * error -2 is clock busy, we keep retrying a few times to see
-	 * if it will come good  -- paulus
-	 */
-	count = 0;
+	max_wait_tb = __get_tb() + tb_ticks_per_usec * 1000 * MAX_RTC_WAIT;
 	do {
 	        error = rtas_call(rtas_token("set-time-of-day"), 7, 1, NULL,
 				  tm->tm_year + 1900, tm->tm_mon + 1, 
 				  tm->tm_mday, tm->tm_hour, tm->tm_min, 
 				  tm->tm_sec, 0);
-	} while (error == -2 && ++count < 1000);
+		if (error == RTAS_CLOCK_BUSY || rtas_is_extended_busy(error)) {
+			if (in_interrupt())
+				return 1;	/* probably decrementer */
+			wait_time = rtas_extended_busy_delay_time(error);
+			set_current_state(TASK_INTERRUPTIBLE);
+			schedule_timeout(wait_time);
+			error = RTAS_CLOCK_BUSY;
+		}
+	} while (error == RTAS_CLOCK_BUSY && (__get_tb() < max_wait_tb));
 
         if (error != 0)
                 printk(KERN_WARNING "error: setting the clock failed (%d)\n",

arch/ppc64/kernel/semaphore.c

@@ -75,9 +75,8 @@ void __down(struct semaphore *sem)
 	struct task_struct *tsk = current;
 	DECLARE_WAITQUEUE(wait, tsk);
 
-	tsk->state = TASK_UNINTERRUPTIBLE;
+	__set_task_state(tsk, TASK_UNINTERRUPTIBLE);
 	add_wait_queue_exclusive(&sem->wait, &wait);
-	smp_wmb();
 
 	/*
 	 * Try to get the semaphore.  If the count is > 0, then we've
@@ -87,10 +86,10 @@ void __down(struct semaphore *sem)
 	 */
 	while (__sem_update_count(sem, -1) <= 0) {
 		schedule();
-		tsk->state = TASK_UNINTERRUPTIBLE;
+		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
 	}
 	remove_wait_queue(&sem->wait, &wait);
-	tsk->state = TASK_RUNNING;
+	__set_task_state(tsk, TASK_RUNNING);
 
 	/*
 	 * If there are any more sleepers, wake one of them up so
@@ -106,9 +105,8 @@ int __down_interruptible(struct semaphore * sem)
 	struct task_struct *tsk = current;
 	DECLARE_WAITQUEUE(wait, tsk);
 
-	tsk->state = TASK_INTERRUPTIBLE;
+	__set_task_state(tsk, TASK_INTERRUPTIBLE);
 	add_wait_queue_exclusive(&sem->wait, &wait);
-	smp_wmb();
 
 	while (__sem_update_count(sem, -1) <= 0) {
 		if (signal_pending(current)) {
@@ -122,10 +120,11 @@ int __down_interruptible(struct semaphore * sem)
 			break;
 		}
 		schedule();
-		tsk->state = TASK_INTERRUPTIBLE;
+		set_task_state(tsk, TASK_INTERRUPTIBLE);
 	}
-	tsk->state = TASK_RUNNING;
 	remove_wait_queue(&sem->wait, &wait);
+	__set_task_state(tsk, TASK_RUNNING);
+
 	wake_up(&sem->wait);
 	return retval;
 }

arch/ppc64/kernel/stab.c

@@ -221,15 +221,18 @@ void make_slbe(unsigned long esid, unsigned long vsid, int large,
 }
 
 static inline void __ste_allocate(unsigned long esid, unsigned long vsid,
-				  int kernel_segment)
+				  int kernel_segment, mm_context_t context)
 {
 	if (cur_cpu_spec->cpu_features & CPU_FTR_SLB) {
+		int large = 0;
+
 #ifndef CONFIG_PPC_ISERIES
 		if (REGION_ID(esid << SID_SHIFT) == KERNEL_REGION_ID)
-			make_slbe(esid, vsid, 1, kernel_segment); 
-		else
+			large = 1;
+		else if (REGION_ID(esid << SID_SHIFT) == USER_REGION_ID)
+			large = in_hugepage_area(context, esid << SID_SHIFT);
 #endif
-			make_slbe(esid, vsid, 0, kernel_segment);
+		make_slbe(esid, vsid, large, kernel_segment);
 	} else {
 		unsigned char top_entry, stab_entry, *segments; 
 
@@ -255,6 +258,7 @@ int ste_allocate(unsigned long ea)
 {
 	unsigned long vsid, esid;
 	int kernel_segment = 0;
+	mm_context_t context;
 
 	PMC_SW_PROCESSOR(stab_faults); 
 
@@ -266,16 +270,18 @@ int ste_allocate(unsigned long ea)
 	if (REGION_ID(ea) >= KERNEL_REGION_ID) {
 		kernel_segment = 1;
 		vsid = get_kernel_vsid(ea);
+		context = REGION_ID(ea);
 	} else {
-		struct mm_struct *mm = current->mm;
-		if (mm)
-			vsid = get_vsid(mm->context, ea);
-		else
+		if (! current->mm)
 			return 1;
+
+		context = current->mm->context;
+		
+		vsid = get_vsid(context, ea);
 	}
 
 	esid = GET_ESID(ea);
-	__ste_allocate(esid, vsid, kernel_segment);
+	__ste_allocate(esid, vsid, kernel_segment, context);
 	if (!(cur_cpu_spec->cpu_features & CPU_FTR_SLB)) {
 		/* Order update */
 		asm volatile("sync":::"memory"); 
@@ -302,7 +308,7 @@ static void preload_stab(struct task_struct *tsk, struct mm_struct *mm)
 		for (esid = 0; esid < 16; esid++) {
 			unsigned long ea = esid << SID_SHIFT;
 			vsid = get_vsid(mm->context, ea);
-			__ste_allocate(esid, vsid, 0);
+			__ste_allocate(esid, vsid, 0, mm->context);
 		}
 	} else {
 		unsigned long pc = KSTK_EIP(tsk);
@@ -316,7 +322,7 @@ static void preload_stab(struct task_struct *tsk, struct mm_struct *mm)
 			    (REGION_ID(pc) >= KERNEL_REGION_ID))
 				return;
 			vsid = get_vsid(mm->context, pc);
-			__ste_allocate(GET_ESID(pc), vsid, 0);
+			__ste_allocate(GET_ESID(pc), vsid, 0, mm->context);
 		}
 
 		if (stack && (pc_segment != stack_segment)) {
@@ -324,7 +330,7 @@ static void preload_stab(struct task_struct *tsk, struct mm_struct *mm)
 			    (REGION_ID(stack) >= KERNEL_REGION_ID))
 				return;
 			vsid = get_vsid(mm->context, stack);
-			__ste_allocate(GET_ESID(stack), vsid, 0);
+			__ste_allocate(GET_ESID(stack), vsid, 0, mm->context);
 		}
 	}
 

arch/ppc64/kernel/sys_ppc32.c

@@ -1243,16 +1243,19 @@ asmlinkage long sys32_settimeofday(struct compat_timeval *tv, struct timezone *t
 }
 
 
-struct msgbuf32 { s32 mtype; char mtext[1]; };
+struct msgbuf32 {
+	compat_long_t mtype; 
+	char mtext[1];
+};
 
 struct semid_ds32 {
 	struct ipc_perm sem_perm;
 	compat_time_t sem_otime;
 	compat_time_t sem_ctime;
-	u32 sem_base;
-	u32 sem_pending;
-	u32 sem_pending_last;
-	u32 undo;
+	compat_uptr_t sem_base;
+	compat_uptr_t sem_pending;
+	compat_uptr_t sem_pending_last;
+	compat_uptr_t undo;
 	unsigned short sem_nsems;
 };
 
@@ -1262,21 +1265,20 @@ struct semid64_ds32 {
 	compat_time_t sem_otime;
 	unsigned int __unused2;
 	compat_time_t sem_ctime;
-	u32 sem_nsems;
-	u32 __unused3;
-	u32 __unused4;
+	compat_ulong_t sem_nsems;
+	compat_ulong_t __unused3;
+	compat_ulong_t __unused4;
 };
 
-struct msqid_ds32
-{
+struct msqid_ds32 {
 	struct ipc_perm msg_perm;
-	u32 msg_first;
-	u32 msg_last;
+	compat_uptr_t msg_first;
+	compat_uptr_t msg_last;
 	compat_time_t msg_stime;
 	compat_time_t msg_rtime;
 	compat_time_t msg_ctime;
-	u32 msg_lcbytes;
-	u32 msg_lqbytes;
+	compat_ulong_t msg_lcbytes;
+	compat_ulong_t msg_lqbytes;
 	unsigned short msg_cbytes;
 	unsigned short msg_qnum;
 	unsigned short msg_qbytes;
@@ -1292,13 +1294,13 @@ struct msqid64_ds32 {
 	compat_time_t msg_rtime;
 	unsigned int __unused3;
 	compat_time_t msg_ctime;
-	unsigned int msg_cbytes;
-	unsigned int msg_qnum;
-	unsigned int msg_qbytes;
+	compat_ulong_t msg_cbytes;
+	compat_ulong_t msg_qnum;
+	compat_ulong_t msg_qbytes;
 	compat_pid_t msg_lspid;
 	compat_pid_t msg_lrpid;
-	unsigned int __unused4;
-	unsigned int __unused5;
+	compat_ulong_t __unused4;
+	compat_ulong_t __unused5;
 };
 
 struct shmid_ds32 {
@@ -1311,8 +1313,8 @@ struct shmid_ds32 {
 	compat_ipc_pid_t shm_lpid;
 	unsigned short shm_nattch;
 	unsigned short __unused;
-	unsigned int __unused2;
-	unsigned int __unused3;
+	compat_uptr_t __unused2;
+	compat_uptr_t __unused3;
 };
 
 struct shmid64_ds32 {
@@ -1327,9 +1329,9 @@ struct shmid64_ds32 {
 	compat_size_t shm_segsz;
 	compat_pid_t shm_cpid;
 	compat_pid_t shm_lpid;
-	unsigned int shm_nattch;
-	unsigned int __unused5;
-	unsigned int __unused6;
+	compat_ulong_t shm_nattch;
+	compat_ulong_t __unused5;
+	compat_ulong_t __unused6;
 };
 
 /*
@@ -1350,7 +1352,7 @@ static long do_sys32_semctl(int first, int second, int third, void *uptr)
 	err = -EFAULT;
 	if (get_user(pad, (u32 *)uptr))
 		return err;
-	if (third == SETVAL)
+	if ((third & ~IPC_64) == SETVAL)
 		fourth.val = (int)pad;
 	else
 		fourth.__pad = (void *)A(pad);

arch/ppc64/kernel/syscalls.c

 /*
- * linux/arch/ppc/kernel/sys_ppc.c
+ * linux/arch/ppc64/kernel/sys_ppc.c
  *
  *  PowerPC version 
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -40,7 +40,6 @@
 #include <asm/uaccess.h>
 #include <asm/ipc.h>
 #include <asm/semaphore.h>
-#include <asm/ppcdebug.h>
 #include <asm/time.h>
 
 extern unsigned long wall_jiffies;
@@ -79,6 +78,7 @@ sys_ipc (uint call, int first, int second, long third, void *ptr, long fifth)
 	case SEMCTL: {
 		union semun fourth;
 
+		ret = -EINVAL;
 		if (!ptr)
 			break;
 		if ((ret = get_user(fourth.__pad, (void **)ptr)))
@@ -94,6 +94,7 @@ sys_ipc (uint call, int first, int second, long third, void *ptr, long fifth)
 		case 0: {
 			struct ipc_kludge tmp;
 
+			ret = -EINVAL;
 			if (!ptr)
 				break;
 			if ((ret = copy_from_user(&tmp,
@@ -127,6 +128,7 @@ sys_ipc (uint call, int first, int second, long third, void *ptr, long fifth)
 			break;
 		}
 		case 1:	/* iBCS2 emulator entry point */
+			ret = -EINVAL;
 			if (!segment_eq(get_fs(), get_ds()))
 				break;
 			ret = sys_shmat (first, (char *) ptr, second,

arch/ppc64/kernel/vmlinux.lds.S

@@ -137,4 +137,9 @@ SECTIONS
   . = ALIGN(4096);
   _end = . ;
   PROVIDE (end = .);
+
+  /* Sections to be discarded. */
+  /DISCARD/ : {
+    *(.exitcall.exit)
+  }
 }

arch/ppc64/kernel/xics.c

@@ -267,6 +267,15 @@ void xics_disable_irq(u_int virq)
 		       irq, call_status);
 		return;
 	}
+
+	/* Have to set XIVE to 0xff to be able to remove a slot */
+	call_status = rtas_call(ibm_set_xive, 3, 1, NULL, irq, default_server,
+				0xff);
+	if (call_status != 0) {
+	printk("xics_disable_irq: irq=%x: ibm_set_xive(0xff) returned %lx\n",
+	       irq, call_status);
+		return;
+	}
 }
 
 void xics_end_irq(u_int	irq)
@@ -375,12 +384,12 @@ void xics_init_IRQ(void)
 	int i;
 	unsigned long intr_size = 0;
 	struct device_node *np;
-	uint *ireg, ilen, indx=0;
+	uint *ireg, ilen, indx = 0;
 	unsigned long intr_base = 0;
 	struct xics_interrupt_node {
-		unsigned long long addr;
-		unsigned long long size;
-	} inodes[NR_CPUS*2]; 
+		unsigned long addr;
+		unsigned long size;
+	} inodes[NR_CPUS]; 
 
 	ppc64_boot_msg(0x20, "XICS Init");
 

arch/ppc64/mm/Makefile

@@ -6,3 +6,4 @@ EXTRA_CFLAGS += -mno-minimal-toc
 
 obj-y := fault.o init.o extable.o imalloc.o
 obj-$(CONFIG_DISCONTIGMEM) += numa.o
+obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o

arch/ppc64/mm/fault.c

@@ -46,8 +46,10 @@ int debugger_kernel_faults = 1;
 void bad_page_fault(struct pt_regs *, unsigned long, int);
 
 /*
- * For 600- and 800-family processors, the error_code parameter is DSISR
- * for a data fault, SRR1 for an instruction fault.
+ * The error_code parameter is
+ *  - DSISR for a non-SLB data access fault,
+ *  - SRR1 & 0x08000000 for a non-SLB instruction access fault
+ *  - 0 any SLB fault.
  */
 void do_page_fault(struct pt_regs *regs, unsigned long address,
 		   unsigned long error_code)
@@ -58,17 +60,6 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	unsigned long code = SEGV_MAPERR;
 	unsigned long is_write = error_code & 0x02000000;
 
-	/*
-	 * Fortunately the bit assignments in SRR1 for an instruction
-	 * fault and DSISR for a data fault are mostly the same for the
-	 * bits we are interested in.  But there are some bits which
-	 * indicate errors in DSISR but can validly be set in SRR1.
-	 */
-	if (regs->trap == 0x400)
-		error_code &= 0x48200000;
-	else if (regs->trap != 0x300) /* ensure error_code is 0 on SLB miss */
-		error_code = 0;
-
 #ifdef CONFIG_DEBUG_KERNEL
 	if (debugger_fault_handler && (regs->trap == 0x300 ||
 				       regs->trap == 0x380)) {

arch/ppc64/mm/hugetlbpage.c

+/*
+ * PPC64 (POWER4) Huge TLB Page Support for Kernel.
+ *
+ * Copyright (C) 2003 David Gibson, IBM Corporation.
+ *
+ * Based on the IA-32 version:
+ * Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
+ */
+
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/smp_lock.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/sysctl.h>
+#include <asm/mman.h>
+#include <asm/pgalloc.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
+#include <asm/machdep.h>
+#include <asm/cputable.h>
+#include <asm/tlb.h>
+#include <asm/rmap.h>
+
+#include <linux/sysctl.h>
+
+int htlbpage_max;
+
+/* This lock protects the two counters and list below */
+static spinlock_t htlbpage_lock = SPIN_LOCK_UNLOCKED;
+
+static int htlbpage_free; /* = 0 */
+static int htlbpage_total; /* = 0 */
+static struct list_head hugepage_freelists[MAX_NUMNODES];
+
+static void enqueue_huge_page(struct page *page)
+{
+	list_add(&page->list,
+		&hugepage_freelists[page_zone(page)->zone_pgdat->node_id]);
+}
+
+/* XXX make this a sysctl */
+unsigned long largepage_roundrobin = 1;
+
+static struct page *dequeue_huge_page(void)
+{
+	static int nid = 0;
+	struct page *page = NULL;
+	int i;
+
+	if (!largepage_roundrobin)
+		nid = numa_node_id();
+
+	for (i = 0; i < numnodes; i++) {
+		if (!list_empty(&hugepage_freelists[nid]))
+			break;
+		nid = (nid + 1) % numnodes;
+	}
+
+	if (!list_empty(&hugepage_freelists[nid])) {
+		page = list_entry(hugepage_freelists[nid].next, struct page, list);
+		list_del(&page->list);
+	}
+
+	if (largepage_roundrobin)
+		nid = (nid + 1) % numnodes;
+
+	return page;
+}
+
+static struct page *alloc_fresh_huge_page(void)
+{
+	static int nid = 0;
+	struct page *page;
+
+	page = alloc_pages_node(nid, GFP_HIGHUSER, HUGETLB_PAGE_ORDER);
+	if (!page)
+		return NULL;
+
+	nid = page_zone(page)->zone_pgdat->node_id;
+	nid = (nid + 1) % numnodes;
+	return page;
+}
+
+/* HugePTE layout:
+ *
+ * 31 30 ... 15 14 13 12 10 9  8  7   6    5    4    3    2    1    0
+ * PFN>>12..... -  -  -  -  -  -  HASH_IX....   2ND  HASH RW   -    HG=1
+ */
+
+#define HUGEPTE_SHIFT	15
+#define _HUGEPAGE_PFN		0xffff8000
+#define _HUGEPAGE_BAD		0x00007f00
+#define _HUGEPAGE_HASHPTE	0x00000008
+#define _HUGEPAGE_SECONDARY	0x00000010
+#define _HUGEPAGE_GROUP_IX	0x000000e0
+#define _HUGEPAGE_HPTEFLAGS	(_HUGEPAGE_HASHPTE | _HUGEPAGE_SECONDARY | \
+				 _HUGEPAGE_GROUP_IX)
+#define _HUGEPAGE_RW		0x00000004
+
+typedef struct {unsigned int val;} hugepte_t;
+#define hugepte_val(hugepte)	((hugepte).val)
+#define __hugepte(x)		((hugepte_t) { (x) } )
+#define hugepte_pfn(x)		\
+	((unsigned long)(hugepte_val(x)>>HUGEPTE_SHIFT) << HUGETLB_PAGE_ORDER)
+#define mk_hugepte(page,wr)	__hugepte( \
+	((page_to_pfn(page)>>HUGETLB_PAGE_ORDER) << HUGEPTE_SHIFT ) \
+	| (!!(wr) * _HUGEPAGE_RW) | _PMD_HUGEPAGE )
+
+#define hugepte_bad(x)	( !(hugepte_val(x) & _PMD_HUGEPAGE) || \
+			  (hugepte_val(x) & _HUGEPAGE_BAD) )
+#define hugepte_page(x)	pfn_to_page(hugepte_pfn(x))
+#define hugepte_none(x)	(!(hugepte_val(x) & _HUGEPAGE_PFN))
+
+
+static void free_huge_page(struct page *page);
+static void flush_hash_hugepage(mm_context_t context, unsigned long ea,
+				hugepte_t pte, int local);
+
+static inline unsigned int hugepte_update(hugepte_t *p, unsigned int clr,
+					  unsigned int set)
+{
+	unsigned int old, tmp;
+
+	__asm__ __volatile__(
+	"1:	lwarx	%0,0,%3		# pte_update\n\
+	andc	%1,%0,%4 \n\
+	or	%1,%1,%5 \n\
+	stwcx.	%1,0,%3 \n\
+	bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*p)
+	: "r" (p), "r" (clr), "r" (set), "m" (*p)
+	: "cc" );
+	return old;
+}
+
+static inline void set_hugepte(hugepte_t *ptep, hugepte_t pte)
+{
+	hugepte_update(ptep, ~_HUGEPAGE_HPTEFLAGS,
+		       hugepte_val(pte) & ~_HUGEPAGE_HPTEFLAGS);
+}
+
+static struct page *alloc_hugetlb_page(void)
+{
+	int i;
+	struct page *page;
+
+	spin_lock(&htlbpage_lock);
+	page = dequeue_huge_page();
+	if (!page) {
+		spin_unlock(&htlbpage_lock);
+		return NULL;
+	}
+
+	htlbpage_free--;
+	spin_unlock(&htlbpage_lock);
+	set_page_count(page, 1);
+	page->lru.prev = (void *)free_huge_page;
+	for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); ++i)
+		clear_highpage(&page[i]);
+	return page;
+}
+
+static hugepte_t *hugepte_alloc(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	pmd_t *pmd = NULL;
+
+	BUG_ON(!in_hugepage_area(mm->context, addr));
+
+	pgd = pgd_offset(mm, addr);
+	pmd = pmd_alloc(mm, pgd, addr);
+
+	/* We shouldn't find a (normal) PTE page pointer here */
+	BUG_ON(!pmd_none(*pmd) && !pmd_hugepage(*pmd));
+	
+	return (hugepte_t *)pmd;
+}
+
+static hugepte_t *hugepte_offset(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	pmd_t *pmd = NULL;
+
+	BUG_ON(!in_hugepage_area(mm->context, addr));
+
+	pgd = pgd_offset(mm, addr);
+	pmd = pmd_offset(pgd, addr);
+
+	/* We shouldn't find a (normal) PTE page pointer here */
+	BUG_ON(!pmd_none(*pmd) && !pmd_hugepage(*pmd));
+
+	return (hugepte_t *)pmd;
+}
+
+static void setup_huge_pte(struct mm_struct *mm, struct page *page,
+			   hugepte_t *ptep, int write_access)
+{
+	hugepte_t entry;
+	int i;
+
+	mm->rss += (HPAGE_SIZE / PAGE_SIZE);
+	entry = mk_hugepte(page, write_access);
+	for (i = 0; i < HUGEPTE_BATCH_SIZE; i++)
+		set_hugepte(ptep+i, entry);
+}
+
+static void teardown_huge_pte(hugepte_t *ptep)
+{
+	int i;
+
+	for (i = 0; i < HUGEPTE_BATCH_SIZE; i++)
+		pmd_clear((pmd_t *)(ptep+i));
+}
+
+/*
+ * This function checks for proper alignment of input addr and len parameters.
+ */
+int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
+{
+	if (len & ~HPAGE_MASK)
+		return -EINVAL;
+	if (addr & ~HPAGE_MASK)
+		return -EINVAL;
+	if (! is_hugepage_only_range(addr, len))
+		return -EINVAL;
+	return 0;
+}
+
+static void do_slbia(void *unused)
+{
+	asm volatile ("isync; slbia; isync":::"memory");
+}
+
+/* Activate the low hpage region for 32bit processes.  mmap_sem must
+ * be held*/
+static int open_32bit_htlbpage_range(struct mm_struct *mm)
+{
+	struct vm_area_struct *vma;
+	unsigned long addr;
+
+	if (mm->context & CONTEXT_LOW_HPAGES)
+		return 0; /* The window is already open */
+	
+	/* Check no VMAs are in the region */
+	vma = find_vma(mm, TASK_HPAGE_BASE_32);
+
+	if (vma && (vma->vm_start < TASK_HPAGE_END_32))
+		return -EBUSY;
+
+	/* Clean up any leftover PTE pages in the region */
+	spin_lock(&mm->page_table_lock);
+	for (addr = TASK_HPAGE_BASE_32; addr < TASK_HPAGE_END_32;
+	     addr += PMD_SIZE) {
+		pgd_t *pgd = pgd_offset(mm, addr);
+		pmd_t *pmd = pmd_offset(pgd, addr);
+
+		if (! pmd_none(*pmd)) {
+			struct page *page = pmd_page(*pmd);
+			pte_t *pte = (pte_t *)pmd_page_kernel(*pmd);
+			int i;
+
+			/* No VMAs, so there should be no PTEs, check
+			 * just in case. */
+			for (i = 0; i < PTRS_PER_PTE; i++) {
+				BUG_ON(! pte_none(*pte));
+				pte++;
+			}
+
+			pmd_clear(pmd);
+			pgtable_remove_rmap(page);
+			pte_free(page);
+		}
+	}
+	spin_unlock(&mm->page_table_lock);
+
+	/* FIXME: do we need to scan for PTEs too? */
+
+	mm->context |= CONTEXT_LOW_HPAGES;
+
+	/* the context change must make it to memory before the slbia,
+	 * so that further SLB misses do the right thing. */
+	mb();
+
+	on_each_cpu(do_slbia, NULL, 0, 1);
+
+	return 0;
+}
+
+int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
+			struct vm_area_struct *vma)
+{
+	hugepte_t *src_pte, *dst_pte, entry;
+	struct page *ptepage;
+	unsigned long addr = vma->vm_start;
+	unsigned long end = vma->vm_end;
+
+	while (addr < end) {
+		BUG_ON(! in_hugepage_area(src->context, addr));
+		BUG_ON(! in_hugepage_area(dst->context, addr));
+
+		dst_pte = hugepte_alloc(dst, addr);
+		if (!dst_pte)
+			return -ENOMEM;
+
+		src_pte = hugepte_offset(src, addr);
+		entry = *src_pte;
+		
+		if ((addr % HPAGE_SIZE) == 0) {
+			/* This is the first hugepte in a batch */
+			ptepage = hugepte_page(entry);
+			get_page(ptepage);
+			dst->rss += (HPAGE_SIZE / PAGE_SIZE);
+		}
+		set_hugepte(dst_pte, entry);
+
+
+		addr += PMD_SIZE;
+	}
+	return 0;
+}
+
+int
+follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
+		    struct page **pages, struct vm_area_struct **vmas,
+		    unsigned long *position, int *length, int i)
+{
+	unsigned long vpfn, vaddr = *position;
+	int remainder = *length;
+
+	WARN_ON(!is_vm_hugetlb_page(vma));
+
+	vpfn = vaddr/PAGE_SIZE;
+	while (vaddr < vma->vm_end && remainder) {
+		BUG_ON(!in_hugepage_area(mm->context, vaddr));
+
+		if (pages) {
+			hugepte_t *pte;
+			struct page *page;
+
+			pte = hugepte_offset(mm, vaddr);
+
+			/* hugetlb should be locked, and hence, prefaulted */
+			WARN_ON(!pte || hugepte_none(*pte));
+
+			page = &hugepte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];
+
+			WARN_ON(!PageCompound(page));
+
+			get_page(page);
+			pages[i] = page;
+		}
+
+		if (vmas)
+			vmas[i] = vma;
+
+		vaddr += PAGE_SIZE;
+		++vpfn;
+		--remainder;
+		++i;
+	}
+
+	*length = remainder;
+	*position = vaddr;
+
+	return i;
+}
+
+struct page *
+follow_huge_addr(struct mm_struct *mm,
+	struct vm_area_struct *vma, unsigned long address, int write)
+{
+	return NULL;
+}
+
+struct vm_area_struct *hugepage_vma(struct mm_struct *mm, unsigned long addr)
+{
+	return NULL;
+}
+
+int pmd_huge(pmd_t pmd)
+{
+	return pmd_hugepage(pmd);
+}
+
+struct page *
+follow_huge_pmd(struct mm_struct *mm, unsigned long address,
+		pmd_t *pmd, int write)
+{
+	struct page *page;
+
+	BUG_ON(! pmd_hugepage(*pmd));
+
+	page = hugepte_page(*(hugepte_t *)pmd);
+	if (page) {
+		page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT);
+		get_page(page);
+	}
+	return page;
+}
+
+static void free_huge_page(struct page *page)
+{
+	BUG_ON(page_count(page));
+	BUG_ON(page->mapping);
+
+	INIT_LIST_HEAD(&page->list);
+
+	spin_lock(&htlbpage_lock);
+	enqueue_huge_page(page);
+	htlbpage_free++;
+	spin_unlock(&htlbpage_lock);
+}
+
+void huge_page_release(struct page *page)
+{
+	if (!put_page_testzero(page))
+		return;
+
+	free_huge_page(page);
+}
+
+void unmap_hugepage_range(struct vm_area_struct *vma,
+			  unsigned long start, unsigned long end)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long addr;
+	hugepte_t *ptep;
+	struct page *page;
+	int local = 0;
+	cpumask_t tmp;
+
+	WARN_ON(!is_vm_hugetlb_page(vma));
+	BUG_ON((start % HPAGE_SIZE) != 0);
+	BUG_ON((end % HPAGE_SIZE) != 0);
+
+	/* XXX are there races with checking cpu_vm_mask? - Anton */
+	tmp = cpumask_of_cpu(smp_processor_id());
+	if (cpus_equal(vma->vm_mm->cpu_vm_mask, tmp))
+		local = 1;
+
+	for (addr = start; addr < end; addr += HPAGE_SIZE) {
+		hugepte_t pte;
+
+		BUG_ON(!in_hugepage_area(mm->context, addr));
+
+		ptep = hugepte_offset(mm, addr);
+		if (!ptep || hugepte_none(*ptep))
+			continue;
+
+		pte = *ptep;
+		page = hugepte_page(pte);
+		teardown_huge_pte(ptep);
+		
+		if (hugepte_val(pte) & _HUGEPAGE_HASHPTE)
+			flush_hash_hugepage(mm->context, addr,
+					    pte, local);
+
+		huge_page_release(page);
+	}
+
+	mm->rss -= (end - start) >> PAGE_SHIFT;
+}
+
+void zap_hugepage_range(struct vm_area_struct *vma,
+			unsigned long start, unsigned long length)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	spin_lock(&mm->page_table_lock);
+	unmap_hugepage_range(vma, start, start + length);
+	spin_unlock(&mm->page_table_lock);
+}
+
+int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long addr;
+	int ret = 0;
+
+	WARN_ON(!is_vm_hugetlb_page(vma));
+	BUG_ON((vma->vm_start % HPAGE_SIZE) != 0);
+	BUG_ON((vma->vm_end % HPAGE_SIZE) != 0);
+
+	spin_lock(&mm->page_table_lock);
+	for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
+		unsigned long idx;
+		hugepte_t *pte = hugepte_alloc(mm, addr);
+		struct page *page;
+
+		BUG_ON(!in_hugepage_area(mm->context, addr));
+
+		if (!pte) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		if (!hugepte_none(*pte))
+			continue;
+
+		idx = ((addr - vma->vm_start) >> HPAGE_SHIFT)
+			+ (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
+		page = find_get_page(mapping, idx);
+		if (!page) {
+			page = alloc_hugetlb_page();
+			if (!page) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			ret = add_to_page_cache(page, mapping, idx, GFP_ATOMIC);
+			unlock_page(page);
+			if (ret) {
+				free_huge_page(page);
+				goto out;
+			}
+		}
+		setup_huge_pte(mm, page, pte, vma->vm_flags & VM_WRITE);
+	}
+out:
+	spin_unlock(&mm->page_table_lock);
+	return ret;
+}
+
+/* Because we have an exclusive hugepage region which lies within the
+ * normal user address space, we have to take special measures to make
+ * non-huge mmap()s evade the hugepage reserved region. */
+unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
+				     unsigned long len, unsigned long pgoff,
+				     unsigned long flags)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long start_addr;
+
+	if (len > TASK_SIZE)
+		return -ENOMEM;
+
+	if (addr) {
+		addr = PAGE_ALIGN(addr);
+		vma = find_vma(mm, addr);
+		if (TASK_SIZE - len >= addr &&
+		    (!vma || addr + len <= vma->vm_start) &&
+		    !is_hugepage_only_range(addr,len))
+			return addr;
+	}
+	start_addr = addr = mm->free_area_cache;
+
+full_search:
+	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
+		/* At this point:  (!vma || addr < vma->vm_end). */
+		if (TASK_SIZE - len < addr) {
+			/*
+			 * Start a new search - just in case we missed
+			 * some holes.
+			 */
+			if (start_addr != TASK_UNMAPPED_BASE) {
+				start_addr = addr = TASK_UNMAPPED_BASE;
+				goto full_search;
+			}
+			return -ENOMEM;
+		}
+		if (!vma || addr + len <= vma->vm_start) {
+			if (is_hugepage_only_range(addr, len)) {
+				if (addr < TASK_HPAGE_END_32)
+					addr = TASK_HPAGE_END_32;
+				else
+					addr = TASK_HPAGE_END;
+
+				continue;
+			}
+			/*
+			 * Remember the place where we stopped the search:
+			 */
+			mm->free_area_cache = addr + len;
+			return addr;
+		}
+		addr = vma->vm_end;
+	}
+}
+
+
+unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+					unsigned long len, unsigned long pgoff,
+					unsigned long flags)
+{
+	struct vm_area_struct *vma;
+	unsigned long base, end;
+
+	if (len & ~HPAGE_MASK)
+		return -EINVAL;
+
+	if (!(cur_cpu_spec->cpu_features & CPU_FTR_16M_PAGE))
+		return -EINVAL;
+
+	if (test_thread_flag(TIF_32BIT)) {
+		int err;
+
+		err = open_32bit_htlbpage_range(current->mm);
+		if (err)
+			return err; /* Should this just be EINVAL? */
+
+		base = TASK_HPAGE_BASE_32;
+		end = TASK_HPAGE_END_32;
+	} else {
+		base = TASK_HPAGE_BASE;
+		end = TASK_HPAGE_END;
+	}
+	
+	if (!in_hugepage_area(current->mm->context, addr) 
+	    || (addr & (HPAGE_SIZE - 1)))
+		addr = base;
+
+	for (vma = find_vma(current->mm, addr); ; vma = vma->vm_next) {
+		/* At this point:  (!vma || addr < vma->vm_end). */
+		if (addr + len > end)
+			return -ENOMEM;
+		if (!vma || (addr + len) <= vma->vm_start)
+			return addr;
+		addr = ALIGN(vma->vm_end, HPAGE_SIZE);
+
+		/* Because we're in an exclusively hugepage region,
+		 * this alignment shouldn't have skipped over any
+		 * other vmas */
+	}
+}
+
+static inline unsigned long computeHugeHptePP(unsigned int hugepte)
+{
+	unsigned long flags = 0x2;
+
+	if (! (hugepte & _HUGEPAGE_RW))
+		flags |= 0x1;
+	return flags;
+}
+
+int hash_huge_page(struct mm_struct *mm, unsigned long access,
+		   unsigned long ea, unsigned long vsid, int local)
+{
+	hugepte_t *ptep;
+	unsigned long va, vpn;
+	int is_write;
+	hugepte_t old_pte, new_pte;
+	unsigned long hpteflags, prpn;
+	long slot;
+
+	/* Is this for us? */
+	if (!in_hugepage_area(mm->context, ea))
+		return -1;
+
+	ea &= ~(HPAGE_SIZE-1);
+
+	/* We have to find the first hugepte in the batch, since
+	 * that's the one that will store the HPTE flags */
+	ptep = hugepte_offset(mm, ea);
+
+	/* Search the Linux page table for a match with va */
+	va = (vsid << 28) | (ea & 0x0fffffff);
+	vpn = va >> HPAGE_SHIFT;
+
+	/*
+	 * If no pte found or not present, send the problem up to
+	 * do_page_fault
+	 */
+	if (unlikely(!ptep || hugepte_none(*ptep)))
+		return 1;
+
+	BUG_ON(hugepte_bad(*ptep));
+
+	/* 
+	 * Check the user's access rights to the page.  If access should be
+	 * prevented then send the problem up to do_page_fault.
+	 */
+	is_write = access & _PAGE_RW;
+	if (unlikely(is_write && !(hugepte_val(*ptep) & _HUGEPAGE_RW)))
+		return 1;
+
+	/*
+	 * At this point, we have a pte (old_pte) which can be used to build
+	 * or update an HPTE. There are 2 cases:
+	 *
+	 * 1. There is a valid (present) pte with no associated HPTE (this is 
+	 *	the most common case)
+	 * 2. There is a valid (present) pte with an associated HPTE. The
+	 *	current values of the pp bits in the HPTE prevent access
+	 *	because we are doing software DIRTY bit management and the
+	 *	page is currently not DIRTY. 
+	 */
+
+	old_pte = *ptep;
+	new_pte = old_pte;
+
+	hpteflags = computeHugeHptePP(hugepte_val(new_pte));
+
+	/* Check if pte already has an hpte (case 2) */
+	if (unlikely(hugepte_val(old_pte) & _HUGEPAGE_HASHPTE)) {
+		/* There MIGHT be an HPTE for this pte */
+		unsigned long hash, slot;
+
+		hash = hpt_hash(vpn, 1);
+		if (hugepte_val(old_pte) & _HUGEPAGE_SECONDARY)
+			hash = ~hash;
+		slot = (hash & htab_data.htab_hash_mask) * HPTES_PER_GROUP;
+		slot += (hugepte_val(old_pte) & _HUGEPAGE_GROUP_IX) >> 5;
+
+		if (ppc_md.hpte_updatepp(slot, hpteflags, va, 1, local) == -1)
+			hugepte_val(old_pte) &= ~_HUGEPAGE_HPTEFLAGS;
+	}
+
+	if (likely(!(hugepte_val(old_pte) & _HUGEPAGE_HASHPTE))) {
+		unsigned long hash = hpt_hash(vpn, 1);
+		unsigned long hpte_group;
+
+		prpn = hugepte_pfn(old_pte);
+
+repeat:
+		hpte_group = ((hash & htab_data.htab_hash_mask) *
+			      HPTES_PER_GROUP) & ~0x7UL;
+
+		/* Update the linux pte with the HPTE slot */
+		hugepte_val(new_pte) &= ~_HUGEPAGE_HPTEFLAGS;
+		hugepte_val(new_pte) |= _HUGEPAGE_HASHPTE;
+
+		/* Add in WIMG bits */
+		/* XXX We should store these in the pte */
+		hpteflags |= _PAGE_COHERENT;
+
+		slot = ppc_md.hpte_insert(hpte_group, va, prpn, 0,
+					  hpteflags, 0, 1);
+
+		/* Primary is full, try the secondary */
+		if (unlikely(slot == -1)) {
+			hugepte_val(new_pte) |= _HUGEPAGE_SECONDARY;
+			hpte_group = ((~hash & htab_data.htab_hash_mask) *
+				      HPTES_PER_GROUP) & ~0x7UL; 
+			slot = ppc_md.hpte_insert(hpte_group, va, prpn,
+						  1, hpteflags, 0, 1);
+			if (slot == -1) {
+				if (mftb() & 0x1)
+					hpte_group = ((hash & htab_data.htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
+
+				ppc_md.hpte_remove(hpte_group);
+				goto repeat;
+                        }
+		}
+
+		if (unlikely(slot == -2))
+			panic("hash_huge_page: pte_insert failed\n");
+
+		hugepte_val(new_pte) |= (slot<<5) & _HUGEPAGE_GROUP_IX;
+
+		/* 
+		 * No need to use ldarx/stdcx here because all who
+		 * might be updating the pte will hold the
+		 * page_table_lock or the hash_table_lock
+		 * (we hold both)
+		 */
+		*ptep = new_pte;
+	}
+
+	return 0;
+}
+
+static void flush_hash_hugepage(mm_context_t context, unsigned long ea,
+				hugepte_t pte, int local)
+{
+	unsigned long vsid, vpn, va, hash, secondary, slot;
+
+	BUG_ON(hugepte_bad(pte));
+	BUG_ON(!in_hugepage_area(context, ea));
+
+	vsid = get_vsid(context, ea);
+
+	va = (vsid << 28) | (ea & 0x0fffffff);
+	vpn = va >> LARGE_PAGE_SHIFT;
+	hash = hpt_hash(vpn, 1);
+	secondary = !!(hugepte_val(pte) & _HUGEPAGE_SECONDARY);
+	if (secondary)
+		hash = ~hash;
+	slot = (hash & htab_data.htab_hash_mask) * HPTES_PER_GROUP;
+	slot += (hugepte_val(pte) & _HUGEPAGE_GROUP_IX) >> 5;
+
+	ppc_md.hpte_invalidate(slot, va, 1, local);
+}
+
+static void split_and_free_hugepage(struct page *page)
+{
+	int j;
+	struct page *map;
+
+	map = page;
+	htlbpage_total--;
+	for (j = 0; j < (HPAGE_SIZE / PAGE_SIZE); j++) {
+		map->flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced |
+				1 << PG_dirty | 1 << PG_active | 1 << PG_reserved |
+				1 << PG_private | 1<< PG_writeback);
+		set_page_count(map, 0);
+		map++;
+	}
+	set_page_count(page, 1);
+	__free_pages(page, HUGETLB_PAGE_ORDER);
+}
+
+int set_hugetlb_mem_size(int count)
+{
+	int lcount;
+	struct page *page;
+
+	if (!(cur_cpu_spec->cpu_features & CPU_FTR_16M_PAGE))
+		return 0;
+	
+	if (count < 0)
+		lcount = count;
+	else
+		lcount = count - htlbpage_total;
+
+	if (lcount == 0)
+		return htlbpage_total;
+	if (lcount > 0) {	/* Increase the mem size. */
+		while (lcount--) {
+			page = alloc_fresh_huge_page();
+			if (page == NULL)
+				break;
+			spin_lock(&htlbpage_lock);
+			enqueue_huge_page(page);
+			htlbpage_free++;
+			htlbpage_total++;
+			spin_unlock(&htlbpage_lock);
+		}
+		return htlbpage_total;
+	}
+	/* Shrink the memory size. */
+	while (lcount++) {
+		page = alloc_hugetlb_page();
+		if (page == NULL)
+			break;
+		spin_lock(&htlbpage_lock);
+		split_and_free_hugepage(page);
+		spin_unlock(&htlbpage_lock);
+	}
+	return htlbpage_total;
+}
+
+int hugetlb_sysctl_handler(ctl_table *table, int write,
+		struct file *file, void *buffer, size_t *length)
+{
+	proc_dointvec(table, write, file, buffer, length);
+	htlbpage_max = set_hugetlb_mem_size(htlbpage_max);
+	return 0;
+}
+
+static int __init hugetlb_setup(char *s)
+{
+	if (sscanf(s, "%d", &htlbpage_max) <= 0)
+		htlbpage_max = 0;
+	return 1;
+}
+__setup("hugepages=", hugetlb_setup);
+
+static int __init hugetlb_init(void)
+{
+	int i;
+	struct page *page;
+
+	if (cur_cpu_spec->cpu_features & CPU_FTR_16M_PAGE) {
+		for (i = 0; i < MAX_NUMNODES; ++i)
+			INIT_LIST_HEAD(&hugepage_freelists[i]);
+
+		for (i = 0; i < htlbpage_max; ++i) {
+			page = alloc_fresh_huge_page();
+			if (!page)
+				break;
+			spin_lock(&htlbpage_lock);
+			enqueue_huge_page(page);
+			spin_unlock(&htlbpage_lock);
+		}
+		htlbpage_max = htlbpage_free = htlbpage_total = i;
+		printk("Total HugeTLB memory allocated, %d\n", htlbpage_free);
+	} else {
+		htlbpage_max = 0;
+		printk("CPU does not support HugeTLB\n");
+	}
+
+	return 0;
+}
+module_init(hugetlb_init);
+
+int hugetlb_report_meminfo(char *buf)
+{
+	return sprintf(buf,
+			"HugePages_Total: %5d\n"
+			"HugePages_Free:  %5d\n"
+			"Hugepagesize:    %5lu kB\n",
+			htlbpage_total,
+			htlbpage_free,
+			HPAGE_SIZE/1024);
+}
+
+/* This is advisory only, so we can get away with accesing
+ * htlbpage_free without taking the lock. */
+int is_hugepage_mem_enough(size_t size)
+{
+	return (size + ~HPAGE_MASK)/HPAGE_SIZE <= htlbpage_free;
+}
+
+/*
+ * We cannot handle pagefaults against hugetlb pages at all.  They cause
+ * handle_mm_fault() to try to instantiate regular-sized pages in the
+ * hugegpage VMA.  do_page_fault() is supposed to trap this, so BUG is we get
+ * this far.
+ */
+static struct page *hugetlb_nopage(struct vm_area_struct *vma,
+				unsigned long address, int unused)
+{
+	BUG();
+	return NULL;
+}
+
+struct vm_operations_struct hugetlb_vm_ops = {
+	.nopage = hugetlb_nopage,
+};

arch/ppc64/mm/init.c

@@ -290,7 +290,7 @@ flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 
 	if (!pgd_none(*pgd)) {
 		pmd = pmd_offset(pgd, vmaddr);
-		if (!pmd_none(*pmd)) {
+		if (pmd_present(*pmd)) {
 			ptep = pte_offset_kernel(pmd, vmaddr);
 			/* Check if HPTE might exist and flush it if so */
 			pte = __pte(pte_update(ptep, _PAGE_HPTEFLAGS, 0));
@@ -298,6 +298,7 @@ flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 				flush_hash_page(context, vmaddr, pte, local);
 			}
 		}
+		WARN_ON(pmd_hugepage(*pmd));
 	}
 }
 
@@ -348,7 +349,7 @@ __flush_tlb_range(struct mm_struct *mm, unsigned long start, unsigned long end)
 				pmd_end = (start + PMD_SIZE) & PMD_MASK;
 				if (pmd_end > end)
 					pmd_end = end;
-				if (!pmd_none(*pmd)) {
+				if (pmd_present(*pmd)) {
 					ptep = pte_offset_kernel(pmd, start);
 					do {
 						if (pte_val(*ptep) & _PAGE_HASHPTE) {
@@ -367,6 +368,7 @@ __flush_tlb_range(struct mm_struct *mm, unsigned long start, unsigned long end)
 						++ptep;
 					} while (start < pmd_end);
 				} else {
+					WARN_ON(pmd_hugepage(*pmd));
 					start = pmd_end;
 				}
 				++pmd;
@@ -540,8 +542,6 @@ static int __init setup_kcore(void)
 }
 module_init(setup_kcore);
 
-void initialize_paca_hardware_interrupt_stack(void);
-
 void __init mem_init(void)
 {
 #ifndef CONFIG_DISCONTIGMEM
@@ -608,9 +608,6 @@ void __init mem_init(void)
 #endif
 	mem_init_done = 1;
 
-	/* set the last page of each hardware interrupt stack to be protected */
-	initialize_paca_hardware_interrupt_stack();
-
 #ifdef CONFIG_PPC_ISERIES
 	create_virtual_bus_tce_table();
 #endif

arch/ppc64/mm/numa.c

@@ -24,18 +24,21 @@
 int numa_cpu_lookup_table[NR_CPUS] = { [ 0 ... (NR_CPUS - 1)] = -1};
 int numa_memory_lookup_table[MAX_MEMORY >> MEMORY_INCREMENT_SHIFT] =
 	{ [ 0 ... ((MAX_MEMORY >> MEMORY_INCREMENT_SHIFT) - 1)] = -1};
-unsigned long numa_cpumask_lookup_table[MAX_NUMNODES];
+cpumask_t numa_cpumask_lookup_table[MAX_NUMNODES];
 int nr_cpus_in_node[MAX_NUMNODES] = { [0 ... (MAX_NUMNODES -1)] = 0};
 
 struct pglist_data node_data[MAX_NUMNODES];
 bootmem_data_t plat_node_bdata[MAX_NUMNODES];
 
+EXPORT_SYMBOL(node_data);
+EXPORT_SYMBOL(numa_memory_lookup_table);
+
 static inline void map_cpu_to_node(int cpu, int node)
 {
 	dbg("cpu %d maps to domain %d\n", cpu, node);
 	numa_cpu_lookup_table[cpu] = node;
-	if (!(numa_cpumask_lookup_table[node] & 1UL << cpu)) {
-		numa_cpumask_lookup_table[node] |= 1UL << cpu;
+	if (!(cpu_isset(cpu, numa_cpumask_lookup_table[node]))) {
+		cpu_set(cpu, numa_cpumask_lookup_table[node]);
 		nr_cpus_in_node[node]++;
 	}
 }

arch/ppc64/xmon/xmon.c

@@ -15,6 +15,8 @@
 #include <linux/mm.h>
 #include <linux/reboot.h>
 #include <linux/delay.h>
+#include <linux/kallsyms.h>
+
 #include <asm/ptrace.h>
 #include <asm/string.h>
 #include <asm/prom.h>
@@ -27,6 +29,7 @@
 #include <asm/paca.h>
 #include <asm/ppcdebug.h>
 #include <asm/cputable.h>
+
 #include "nonstdio.h"
 #include "privinst.h"
 
@@ -59,7 +62,6 @@ struct bpt {
 	unsigned instr;
 	unsigned long count;
 	unsigned char enabled;
-	char funcname[64];	/* function name for humans */
 };
 
 #define NBPTS	16
@@ -79,14 +81,9 @@ static void memex(void);
 static int bsesc(void);
 static void dump(void);
 static void prdump(unsigned long, long);
-#ifdef __MWERKS__
-static void prndump(unsigned, int);
-static int nvreadb(unsigned);
-#endif
 static int ppc_inst_dump(unsigned long, long);
 void print_address(unsigned long);
 static int getsp(void);
-static void dump_hash_table(void);
 static void backtrace(struct pt_regs *);
 static void excprint(struct pt_regs *);
 static void prregs(struct pt_regs *);
@@ -106,7 +103,6 @@ static void take_input(char *);
 static unsigned long read_spr(int);
 static void write_spr(int, unsigned long);
 static void super_regs(void);
-static void print_sysmap(void);
 static void remove_bpts(void);
 static void insert_bpts(void);
 static struct bpt *at_breakpoint(unsigned long pc);
@@ -158,7 +154,6 @@ Commands:\n\
   dd	dump double values\n\
   e	print exception information\n\
   f	flush cache\n\
-  h	dump hash table\n\
   m	examine/change memory\n\
   mm	move a block of memory\n\
   ms	set a block of memory\n\
@@ -183,6 +178,13 @@ static int xmon_trace[NR_CPUS];
 
 static struct pt_regs *xmon_regs[NR_CPUS];
 
+void __xmon_print_symbol(const char *fmt, unsigned long address);
+#define xmon_print_symbol(fmt, addr)		\
+do {						\
+	__check_printsym_format(fmt, "");	\
+	__xmon_print_symbol(fmt, addr);		\
+} while(0)
+
 /*
  * Stuff for reading and writing memory safely
  */
@@ -211,42 +213,6 @@ extern inline void sync(void)
  no functions have been called from the current function.
  */
 
-/*
- A traceback table typically follows each function.
- The find_tb_table() func will fill in this struct.  Note that the struct
- is not an exact match with the encoded table defined by the ABI.  It is
- defined here more for programming convenience.
- */
-struct tbtable {
-	unsigned long	flags;		/* flags: */
-#define TBTAB_FLAGSGLOBALLINK	(1L<<47)
-#define TBTAB_FLAGSISEPROL	(1L<<46)
-#define TBTAB_FLAGSHASTBOFF	(1L<<45)
-#define TBTAB_FLAGSINTPROC	(1L<<44)
-#define TBTAB_FLAGSHASCTL	(1L<<43)
-#define TBTAB_FLAGSTOCLESS	(1L<<42)
-#define TBTAB_FLAGSFPPRESENT	(1L<<41)
-#define TBTAB_FLAGSNAMEPRESENT	(1L<<38)
-#define TBTAB_FLAGSUSESALLOCA	(1L<<37)
-#define TBTAB_FLAGSSAVESCR	(1L<<33)
-#define TBTAB_FLAGSSAVESLR	(1L<<32)
-#define TBTAB_FLAGSSTORESBC	(1L<<31)
-#define TBTAB_FLAGSFIXUP	(1L<<30)
-#define TBTAB_FLAGSPARMSONSTK	(1L<<0)
-	unsigned char	fp_saved;	/* num fp regs saved f(32-n)..f31 */
-	unsigned char	gpr_saved;	/* num gpr's saved */
-	unsigned char	fixedparms;	/* num fixed point parms */
-	unsigned char	floatparms;	/* num float parms */
-	unsigned char	parminfo[32];	/* types of args.  null terminated */
-#define TBTAB_PARMFIXED 1
-#define TBTAB_PARMSFLOAT 2
-#define TBTAB_PARMDFLOAT 3
-	unsigned int	tb_offset;	/* offset from start of func */
-	unsigned long	funcstart;	/* addr of start of function */
-	char		name[64];	/* name of function (null terminated)*/
-};
-static int find_tb_table(unsigned long codeaddr, struct tbtable *tab);
-
 #define SURVEILLANCE_TOKEN	9000
 
 static inline void disable_surveillance(void)
@@ -304,8 +270,7 @@ xmon(struct pt_regs *excp)
 			std	29,232(%0)\n\
 			std	30,240(%0)\n\
 			std	31,248(%0)" : : "b" (&regs));
-		/* Fetch the link reg for this stack frame.
-		 NOTE: the prev printf fills in the lr. */
+
 		regs.nip = regs.link = ((unsigned long *)(regs.gpr[1]))[2];
 		regs.msr = get_msr();
 		regs.ctr = get_ctr();
@@ -380,7 +345,9 @@ xmon_bpt(struct pt_regs *regs)
 		xmon_trace[smp_processor_id()] = BRSTEP;
 		regs->msr |= MSR_SE;
 	} else {
-		printf("Stopped at breakpoint %x (%lx %s)\n", (bp - bpts)+1, bp->address, bp->funcname);
+		printf("Stopped at breakpoint %x (%lx ", (bp - bpts) + 1,
+			bp->address);
+		xmon_print_symbol("%s)\n", bp->address);
 		xmon(regs);
 	}
 	return 1;
@@ -578,9 +545,6 @@ cmds(struct pt_regs *excp)
 			else
 				excprint(excp);
 			break;
-		case 'M':
-			print_sysmap();
-			break;
 		case 'S':
 			super_regs();
 			break;
@@ -590,9 +554,6 @@ cmds(struct pt_regs *excp)
 		case 'f':
 			cacheflush();
 			break;
-		case 'h':
-			dump_hash_table();
-			break;
 		case 's':
 		case 'x':
 		case EOF:
@@ -773,7 +734,6 @@ bpt_cmds(void)
 	unsigned long a;
 	int mode, i;
 	struct bpt *bp;
-	struct tbtable tab;
 
 	cmd = inchar();
 	switch (cmd) {
@@ -829,7 +789,9 @@ bpt_cmds(void)
 			if (bp == 0) {
 				printf("No breakpoint at %x\n", a);
 			} else {
-				printf("Cleared breakpoint %x (%lx %s)\n", (bp - bpts)+1, bp->address, bp->funcname);
+				printf("Cleared breakpoint %x (%lx ", 
+					(bp - bpts) + 1, bp->address);
+				xmon_print_symbol("%s)\n", bp->address);
 				bp->enabled = 0;
 			}
 		}
@@ -863,8 +825,11 @@ bpt_cmds(void)
 				printf("   inst   %.16lx %8x\n", iabr.address & ~3,
 				       iabr.count);
 			for (bp = bpts, bpnum = 1; bp < &bpts[NBPTS]; ++bp, ++bpnum)
-				if (bp->enabled)
-					printf("%2x trap   %.16lx %8x  %s\n", bpnum, bp->address, bp->count, bp->funcname);
+				if (bp->enabled) {
+					printf("%2x trap   %.16lx %8x  ",
+						bpnum, bp->address, bp->count);
+					xmon_print_symbol("%s\n", bp->address);
+				}
 			break;
 		}
 		bp = at_breakpoint(a);
@@ -881,14 +846,9 @@ bpt_cmds(void)
 		bp->address = a;
 		bp->count = 0;
 		scanhex(&bp->count);
-		/* Find the function name just once. */
-		bp->funcname[0] = '\0';
-		if (find_tb_table(bp->address, &tab) && tab.name[0]) {
-			/* Got a nice name for it. */
-			int delta = bp->address - tab.funcstart;
-			sprintf(bp->funcname, "%s+0x%x", tab.name, delta);
-		}
-		printf("Set breakpoint %2x trap   %.16lx %8x  %s\n", (bp-bpts)+1, bp->address, bp->count, bp->funcname);
+		printf("Set breakpoint %2x trap   %.16lx %8x  ", (bp-bpts) + 1, 
+			bp->address, bp->count);
+		xmon_print_symbol("%s\n", bp->address);
 		break;
 	}
 }
@@ -925,7 +885,6 @@ backtrace(struct pt_regs *excp)
 	unsigned long lr;
 	unsigned long stack[3];
 	struct pt_regs regs;
-	struct tbtable tab;
 	int framecount;
 	char *funcname;
 	/* declare these as raw ptrs so we don't get func descriptors */
@@ -971,17 +930,11 @@ backtrace(struct pt_regs *excp)
 				break;
 			printf("exception: %lx %s regs %lx\n", regs.trap, getvecname(regs.trap), sp+112);
 			printf("                  %.16lx", regs.nip);
-			if ((regs.nip & 0xffffffff00000000UL) &&
-			    find_tb_table(regs.nip, &tab)) {
-				int delta = regs.nip-tab.funcstart;
-				if (delta < 0)
-					printf("  <unknown code>");
-				else
-					printf("  %s+0x%x", tab.name, delta);
-			}
+			if (regs.nip & 0xffffffff00000000UL)
+				xmon_print_symbol("  %s", regs.nip);
 			printf("\n");
                         if (regs.gpr[1] < sp) {
-                            printf("<Stack drops into 32-bit userspace %.16lx>\n", regs.gpr[1]);
+                            printf("<Stack drops into userspace %.16lx>\n", regs.gpr[1]);
                             break;
 			}
 
@@ -989,13 +942,8 @@ backtrace(struct pt_regs *excp)
 			if (mread(sp, stack, sizeof(stack)) != sizeof(stack))
 				break;
 		} else {
-			if (stack[2] && find_tb_table(stack[2], &tab)) {
-				int delta = stack[2]-tab.funcstart;
-				if (delta < 0)
-					printf("  <unknown code>");
-				else
-					printf("  %s+0x%x", tab.name, delta);
-			}
+			if (stack[2])
+				xmon_print_symbol("  %s", stack[2]);
 			printf("\n");
 		}
 		if (stack[0] && stack[0] <= sp) {
@@ -1024,8 +972,6 @@ spinlock_t exception_print_lock = SPIN_LOCK_UNLOCKED;
 void
 excprint(struct pt_regs *fp)
 {
-	struct task_struct *c;
-	struct tbtable tab;
 	unsigned long flags;
 
 	spin_lock_irqsave(&exception_print_lock, flags);
@@ -1034,21 +980,13 @@ excprint(struct pt_regs *fp)
 	printf("cpu %d: ", smp_processor_id());
 #endif /* CONFIG_SMP */
 
-	printf("Vector: %lx %s at  [%lx]\n", fp->trap, getvecname(fp->trap), fp);
+	printf("Vector: %lx %s at [%lx]\n", fp->trap, getvecname(fp->trap), fp);
 	printf("    pc: %lx", fp->nip);
-	if (find_tb_table(fp->nip, &tab) && tab.name[0]) {
-		/* Got a nice name for it */
-		int delta = fp->nip - tab.funcstart;
-		printf(" (%s+0x%x)", tab.name, delta);
-	}
-	printf("\n");
+	xmon_print_symbol(" (%s)\n", fp->nip);
+
 	printf("    lr: %lx", fp->link);
-	if (find_tb_table(fp->link, &tab) && tab.name[0]) {
-		/* Got a nice name for it */
-		int delta = fp->link - tab.funcstart;
-		printf(" (%s+0x%x)", tab.name, delta);
-	}
-	printf("\n");
+	xmon_print_symbol(" (%s)\n", fp->link);
+
 	printf("    sp: %lx\n", fp->gpr[1]);
 	printf("   msr: %lx\n", fp->msr);
 
@@ -1057,13 +995,11 @@ excprint(struct pt_regs *fp)
 		printf(" dsisr: %lx\n", fp->dsisr);
 	}
 
-	/* XXX: need to copy current or we die.  Why? */
-	c = current;
-	printf("  current = 0x%lx\n", c);
+	printf("  current = 0x%lx\n", current);
 	printf("  paca    = 0x%lx\n", get_paca());
-	if (c) {
-		printf("  current = %lx, pid = %ld, comm = %s\n",
-		       c, c->pid, c->comm);
+	if (current) {
+		printf("    pid   = %ld, comm = %s\n",
+		       current->pid, current->comm);
 	}
 
 	spin_unlock_irqrestore(&exception_print_lock, flags);
@@ -1152,14 +1088,6 @@ static unsigned long regno;
 extern char exc_prolog;
 extern char dec_exc;
 
-void
-print_sysmap(void)
-{
-	extern char *sysmap;
-	if ( sysmap )
-		printf("System.map: \n%s", sysmap);
-}
-
 void
 super_regs()
 {
@@ -1228,152 +1156,6 @@ super_regs()
 	scannl();
 }
 
-#ifndef CONFIG_PPC64BRIDGE
-static void
-dump_hash_table_seg(unsigned seg, unsigned start, unsigned end)
-{
-	extern void *Hash;
-	extern unsigned long Hash_size;
-	unsigned *htab = Hash;
-	unsigned hsize = Hash_size;
-	unsigned v, hmask, va, last_va;
-	int found, last_found, i;
-	unsigned *hg, w1, last_w2, last_va0;
-
-	last_found = 0;
-	hmask = hsize / 64 - 1;
-	va = start;
-	start = (start >> 12) & 0xffff;
-	end = (end >> 12) & 0xffff;
-	for (v = start; v < end; ++v) {
-		found = 0;
-		hg = htab + (((v ^ seg) & hmask) * 16);
-		w1 = 0x80000000 | (seg << 7) | (v >> 10);
-		for (i = 0; i < 8; ++i, hg += 2) {
-			if (*hg == w1) {
-				found = 1;
-				break;
-			}
-		}
-		if (!found) {
-			w1 ^= 0x40;
-			hg = htab + ((~(v ^ seg) & hmask) * 16);
-			for (i = 0; i < 8; ++i, hg += 2) {
-				if (*hg == w1) {
-					found = 1;
-					break;
-				}
-			}
-		}
-		if (!(last_found && found && (hg[1] & ~0x180) == last_w2 + 4096)) {
-			if (last_found) {
-				if (last_va != last_va0)
-					printf(" ... %x", last_va);
-				printf("\n");
-			}
-			if (found) {
-				printf("%x to %x", va, hg[1]);
-				last_va0 = va;
-			}
-			last_found = found;
-		}
-		if (found) {
-			last_w2 = hg[1] & ~0x180;
-			last_va = va;
-		}
-		va += 4096;
-	}
-	if (last_found)
-		printf(" ... %x\n", last_va);
-}
-
-#else /* CONFIG_PPC64BRIDGE */
-static void
-dump_hash_table_seg(unsigned seg, unsigned start, unsigned end)
-{
-	extern void *Hash;
-	extern unsigned long Hash_size;
-	unsigned *htab = Hash;
-	unsigned hsize = Hash_size;
-	unsigned v, hmask, va, last_va;
-	int found, last_found, i;
-	unsigned *hg, w1, last_w2, last_va0;
-
-	last_found = 0;
-	hmask = hsize / 128 - 1;
-	va = start;
-	start = (start >> 12) & 0xffff;
-	end = (end >> 12) & 0xffff;
-	for (v = start; v < end; ++v) {
-		found = 0;
-		hg = htab + (((v ^ seg) & hmask) * 32);
-		w1 = 1 | (seg << 12) | ((v & 0xf800) >> 4);
-		for (i = 0; i < 8; ++i, hg += 4) {
-			if (hg[1] == w1) {
-				found = 1;
-				break;
-			}
-		}
-		if (!found) {
-			w1 ^= 2;
-			hg = htab + ((~(v ^ seg) & hmask) * 32);
-			for (i = 0; i < 8; ++i, hg += 4) {
-				if (hg[1] == w1) {
-					found = 1;
-					break;
-				}
-			}
-		}
-		if (!(last_found && found && (hg[3] & ~0x180) == last_w2 + 4096)) {
-			if (last_found) {
-				if (last_va != last_va0)
-					printf(" ... %x", last_va);
-				printf("\n");
-			}
-			if (found) {
-				printf("%x to %x", va, hg[3]);
-				last_va0 = va;
-			}
-			last_found = found;
-		}
-		if (found) {
-			last_w2 = hg[3] & ~0x180;
-			last_va = va;
-		}
-		va += 4096;
-	}
-	if (last_found)
-		printf(" ... %x\n", last_va);
-}
-#endif /* CONFIG_PPC64BRIDGE */
-
-static unsigned long hash_ctx;
-static unsigned long hash_start;
-static unsigned long hash_end;
-
-static void
-dump_hash_table()
-{
-	int seg;
-	unsigned seg_start, seg_end;
-
-	hash_ctx = 0;
-	hash_start = 0;
-	hash_end = 0xfffff000;
-	scanhex(&hash_ctx);
-	scanhex(&hash_start);
-	scanhex(&hash_end);
-	printf("Mappings for context %x\n", hash_ctx);
-	seg_start = hash_start;
-	for (seg = hash_start >> 28; seg <= hash_end >> 28; ++seg) {
-		seg_end = (seg << 28) | 0x0ffff000;
-		if (seg_end > hash_end)
-			seg_end = hash_end;
-		dump_hash_table_seg((hash_ctx << 4) + seg, seg_start, seg_end);
-		seg_start = seg_end + 0x1000;
-	}
-}
-
 int
 mread(unsigned long adrs, void *buf, int size)
 {
@@ -2073,111 +1855,52 @@ char *str;
 	lineptr = str;
 }
 
-
-/* Starting at codeaddr scan forward for a tbtable and fill in the
- given table.  Return non-zero if successful at doing something.
- */
-static int
-find_tb_table(unsigned long codeaddr, struct tbtable *tab)
+/* xmon version of __print_symbol */
+void __xmon_print_symbol(const char *fmt, unsigned long address)
 {
-	unsigned long codeaddr_max;
-	unsigned long tbtab_start;
-	int nr;
-	int instr;
-	int num_parms;
-
-	/* don't look for traceback table in userspace */
-	if (codeaddr < PAGE_OFFSET)
-		return 0;
+	char *modname;
+	const char *name;
+	unsigned long offset, size;
+	char namebuf[128];
 
-	if (tab == NULL)
-		return 0;
-	memset(tab, 0, sizeof(tab));
-
-	/* Scan instructions starting at codeaddr for 128k max */
-	for (codeaddr_max = codeaddr + 128*1024*4;
-	     codeaddr < codeaddr_max;
-	     codeaddr += 4) {
-		nr = mread(codeaddr, &instr, 4);
-		if (nr != 4)
-			return 0;	/* Bad read.  Give up promptly. */
-		if (instr == 0) {
-			/* table should follow. */
-			int version;
-			unsigned long flags;
-			tbtab_start = codeaddr;	/* save it to compute func start addr */
-			codeaddr += 4;
-			nr = mread(codeaddr, &flags, 8);
-			if (nr != 8)
-				return 0;	/* Bad read or no tb table. */
-			tab->flags = flags;
-			version = (flags >> 56) & 0xff;
-			if (version != 0)
-				continue;	/* No tb table here. */
-			/* Now, like the version, some of the flags are values
-			 that are more conveniently extracted... */
-			tab->fp_saved = (flags >> 24) & 0x3f;
-			tab->gpr_saved = (flags >> 16) & 0x3f;
-			tab->fixedparms = (flags >> 8) & 0xff;
-			tab->floatparms = (flags >> 1) & 0x7f;
-			codeaddr += 8;
-			num_parms = tab->fixedparms + tab->floatparms;
-			if (num_parms) {
-				unsigned int parminfo;
-				int parm;
-				if (num_parms > 32)
-					return 1;	/* incomplete */
-				nr = mread(codeaddr, &parminfo, 4);
-				if (nr != 4)
-					return 1;	/* incomplete */
-				/* decode parminfo...32 bits.
-				 A zero means fixed.  A one means float and the
-				 following bit determines single (0) or double (1).
-				 */
-				for (parm = 0; parm < num_parms; parm++) {
-					if (parminfo & 0x80000000) {
-						parminfo <<= 1;
-						if (parminfo & 0x80000000)
-							tab->parminfo[parm] = TBTAB_PARMDFLOAT;
-						else
-							tab->parminfo[parm] = TBTAB_PARMSFLOAT;
-					} else {
-						tab->parminfo[parm] = TBTAB_PARMFIXED;
-					}
-					parminfo <<= 1;
-				}
-				codeaddr += 4;
-			}
-			if (flags & TBTAB_FLAGSHASTBOFF) {
-				nr = mread(codeaddr, &tab->tb_offset, 4);
-				if (nr != 4)
-					return 1;	/* incomplete */
-				if (tab->tb_offset > 0) {
-					tab->funcstart = tbtab_start - tab->tb_offset;
-				}
-				codeaddr += 4;
-			}
-			/* hand_mask appears to be always be omitted. */
-			if (flags & TBTAB_FLAGSHASCTL) {
-				/* Assume this will never happen for C or asm */
-				return 1;	/* incomplete */
-			}
-			if (flags & TBTAB_FLAGSNAMEPRESENT) {
-				short namlen;
-				nr = mread(codeaddr, &namlen, 2);
-				if (nr != 2)
-					return 1;	/* incomplete */
-				if (namlen >= sizeof(tab->name))
-					namlen = sizeof(tab->name)-1;
-				codeaddr += 2;
-				nr = mread(codeaddr, tab->name, namlen);
-				tab->name[namlen] = '\0';
-				codeaddr += namlen;
-			}
-			return 1;
-		}
+	if (setjmp(bus_error_jmp) == 0) {
+		debugger_fault_handler = handle_fault;
+		sync();
+		name = kallsyms_lookup(address, &size, &offset, &modname,
+				       namebuf);
+		sync();
+		/* wait a little while to see if we get a machine check */
+		__delay(200);
+	} else {
+		name = "symbol lookup failed";
+	}
+
+	debugger_fault_handler = 0;
+
+	if (!name) {
+		char addrstr[sizeof("0x%lx") + (BITS_PER_LONG*3/10)];
+
+		sprintf(addrstr, "0x%lx", address);
+		printf(fmt, addrstr);
+		return;
+	}
+
+	if (modname) {
+		/* This is pretty small. */
+		char buffer[sizeof("%s+%#lx/%#lx [%s]")
+			   + strlen(name) + 2*(BITS_PER_LONG*3/10)
+			   + strlen(modname)];
+
+		sprintf(buffer, "%s+%#lx/%#lx [%s]",
+			name, offset, size, modname);
+		printf(fmt, buffer);
+	} else {
+		char buffer[sizeof("%s+%#lx/%#lx")
+			   + strlen(name) + 2*(BITS_PER_LONG*3/10)];
+
+		sprintf(buffer, "%s+%#lx/%#lx", name, offset, size);
+		printf(fmt, buffer);
 	}
-	return 0;	/* hit max...sorry. */
 }
 
 void

include/asm-ppc64/hvcall.h

@@ -59,9 +59,6 @@
 #define H_XIRR			0x74
 #define H_PERFMON		0x7c
 
-#define HSC			".long 0x44000022\n"
-#define H_ENTER_r3		"li	3, 0x08\n"
-
 /* plpar_hcall() -- Generic call interface using above opcodes
  *
  * The actual call interface is a hypervisor call instruction with

include/asm-ppc64/ioctl.h

@@ -42,11 +42,21 @@
 	 ((nr)   << _IOC_NRSHIFT) | \
 	 ((size) << _IOC_SIZESHIFT))
 
+/* provoke compile error for invalid uses of size argument */
+extern int __invalid_size_argument_for_IOC;
+#define _IOC_TYPECHECK(t) \
+       ((sizeof(t) == sizeof(t[1]) && \
+         sizeof(t) < (1 << _IOC_SIZEBITS)) ? \
+         sizeof(t) : __invalid_size_argument_for_IOC)
+
 /* used to create numbers */
 #define _IO(type,nr)		_IOC(_IOC_NONE,(type),(nr),0)
-#define _IOR(type,nr,size)	_IOC(_IOC_READ,(type),(nr),sizeof(size))
-#define _IOW(type,nr,size)	_IOC(_IOC_WRITE,(type),(nr),sizeof(size))
-#define _IOWR(type,nr,size)	_IOC(_IOC_READ|_IOC_WRITE,(type),(nr),sizeof(size))
+#define _IOR(type,nr,size)	_IOC(_IOC_READ,(type),(nr),(_IOC_TYPECHECK(size)))
+#define _IOW(type,nr,size)	_IOC(_IOC_WRITE,(type),(nr),(_IOC_TYPECHECK(size)))
+#define _IOWR(type,nr,size)	_IOC(_IOC_READ|_IOC_WRITE,(type),(nr),(_IOC_TYPECHECK(size)))
+#define _IOR_BAD(type,nr,size)	_IOC(_IOC_READ,(type),(nr),sizeof(size))
+#define _IOW_BAD(type,nr,size)	_IOC(_IOC_WRITE,(type),(nr),sizeof(size))
+#define _IOWR_BAD(type,nr,size)	_IOC(_IOC_READ|_IOC_WRITE,(type),(nr),sizeof(size))
 
 /* used to decode them.. */
 #define _IOC_DIR(nr)		(((nr) >> _IOC_DIRSHIFT) & _IOC_DIRMASK)

include/asm-ppc64/local.h

+#include <asm-generic/local.h>

include/asm-ppc64/mmu.h

@@ -18,6 +18,12 @@
 /* Default "unsigned long" context */
 typedef unsigned long mm_context_t;
 
+#ifdef CONFIG_HUGETLB_PAGE
+#define CONTEXT_LOW_HPAGES	(1UL<<63)
+#else
+#define CONTEXT_LOW_HPAGES	0
+#endif
+
 /*
  * Define the size of the cache used for segment table entries.  The first
  * entry is used as a cache pointer, therefore the actual number of entries

include/asm-ppc64/mmu_context.h

@@ -127,7 +127,8 @@ destroy_context(struct mm_struct *mm)
 #endif
 
 	mmu_context_queue.size++;
-	mmu_context_queue.elements[index] = mm->context;
+	mmu_context_queue.elements[index] =
+		mm->context & ~CONTEXT_LOW_HPAGES;
 
 	spin_unlock_irqrestore(&mmu_context_queue.lock, flags);
 }
@@ -189,6 +190,8 @@ get_vsid( unsigned long context, unsigned long ea )
 {
 	unsigned long ordinal, vsid;
 
+	context &= ~CONTEXT_LOW_HPAGES;
+
 	ordinal = (((ea >> 28) & 0x1fffff) * LAST_USER_CONTEXT) | context;
 	vsid = (ordinal * VSID_RANDOMIZER) & VSID_MASK;
 

include/asm-ppc64/mmzone.h

@@ -20,7 +20,7 @@ extern struct pglist_data node_data[];
 
 extern int numa_cpu_lookup_table[];
 extern int numa_memory_lookup_table[];
-extern unsigned long numa_cpumask_lookup_table[];
+extern cpumask_t numa_cpumask_lookup_table[];
 extern int nr_cpus_in_node[];
 
 #define MAX_MEMORY (1UL << 41)

include/asm-ppc64/paca.h

@@ -63,7 +63,7 @@ struct paca_struct {
 	u16 xPacaIndex;			/* Logical processor number		0x18 */
 	u16 active;			/* Is this cpu active?			0x1a */
 	u32 default_decr;		/* Default decrementer value		0x1c */	
-	u64 xHrdIntStack;		/* Stack for hardware interrupts	0x20 */
+	u64 unused1;
 	u64 xKsave;			/* Saved Kernel stack addr or zero	0x28 */
 	u64 pvr;			/* Processor version register		0x30 */
 	u8 *exception_sp;		/*					0x38 */
@@ -73,7 +73,7 @@ struct paca_struct {
 	STAB xStab_data;		/* Segment table information		0x50,0x58,0x60 */
 	u8 xSegments[STAB_CACHE_SIZE];	/* Cache of used stab entries		0x68,0x70 */
 	u8 xProcEnabled;		/* 1=soft enabled			0x78 */
-	u8 xHrdIntCount;		/* Count of active hardware interrupts  0x79  */
+	u8 unused2;
 	u8 prof_enabled;		/* 1=iSeries profiling enabled          0x7A */
 	u8 stab_cache_pointer;	
 	u8 resv1[4];			/*					0x7B-0x7F */

include/asm-ppc64/page.h

@@ -22,6 +22,39 @@
 #define PAGE_MASK	(~(PAGE_SIZE-1))
 #define PAGE_OFFSET_MASK (PAGE_SIZE-1)
 
+#ifdef CONFIG_HUGETLB_PAGE
+
+#define HPAGE_SHIFT	24
+#define HPAGE_SIZE	((1UL) << HPAGE_SHIFT)
+#define HPAGE_MASK	(~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
+
+/* For 64-bit processes the hugepage range is 1T-1.5T */
+#define TASK_HPAGE_BASE 	(0x0000010000000000UL)
+#define TASK_HPAGE_END 	(0x0000018000000000UL)
+/* For 32-bit processes the hugepage range is 2-3G */
+#define TASK_HPAGE_BASE_32	(0x80000000UL)
+#define TASK_HPAGE_END_32	(0xc0000000UL)
+
+#define ARCH_HAS_HUGEPAGE_ONLY_RANGE
+#define is_hugepage_only_range(addr, len) \
+	( ((addr > (TASK_HPAGE_BASE-len)) && (addr < TASK_HPAGE_END)) || \
+	  ((current->mm->context & CONTEXT_LOW_HPAGES) && \
+	   (addr > (TASK_HPAGE_BASE_32-len)) && (addr < TASK_HPAGE_END_32)) )
+#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+
+#define in_hugepage_area(context, addr) \
+	((cur_cpu_spec->cpu_features & CPU_FTR_16M_PAGE) && \
+	 ((((addr) >= TASK_HPAGE_BASE) && ((addr) < TASK_HPAGE_END)) || \
+	  (((context) & CONTEXT_LOW_HPAGES) && \
+	   (((addr) >= TASK_HPAGE_BASE_32) && ((addr) < TASK_HPAGE_END_32)))))
+
+#else /* !CONFIG_HUGETLB_PAGE */
+
+#define in_hugepage_area(mm, addr)	0
+
+#endif /* !CONFIG_HUGETLB_PAGE */
+
 #define SID_SHIFT       28
 #define SID_MASK        0xfffffffff
 #define GET_ESID(x)     (((x) >> SID_SHIFT) & SID_MASK)

include/asm-ppc64/pgtable.h

@@ -149,6 +149,25 @@ extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)];
 /* shift to put page number into pte */
 #define PTE_SHIFT (16)
 
+/* We allow 2^41 bytes of real memory, so we need 29 bits in the PMD
+ * to give the PTE page number.  The bottom two bits are for flags. */
+#define PMD_TO_PTEPAGE_SHIFT (2)
+
+#ifdef CONFIG_HUGETLB_PAGE
+#define _PMD_HUGEPAGE	0x00000001U
+#define HUGEPTE_BATCH_SIZE (1<<(HPAGE_SHIFT-PMD_SHIFT))
+
+int hash_huge_page(struct mm_struct *mm, unsigned long access,
+		   unsigned long ea, unsigned long vsid, int local);
+
+#define HAVE_ARCH_UNMAPPED_AREA
+#else
+
+#define hash_huge_page(mm,a,ea,vsid,local)	-1
+#define _PMD_HUGEPAGE	0
+
+#endif
+
 #ifndef __ASSEMBLY__
 
 /*
@@ -178,12 +197,16 @@ extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)];
 #define pte_pfn(x)		((unsigned long)((pte_val(x) >> PTE_SHIFT)))
 #define pte_page(x)		pfn_to_page(pte_pfn(x))
 
-#define pmd_set(pmdp, ptep) 	(pmd_val(*(pmdp)) = (__ba_to_bpn(ptep)))
+#define pmd_set(pmdp, ptep) 	\
+	(pmd_val(*(pmdp)) = (__ba_to_bpn(ptep) << PMD_TO_PTEPAGE_SHIFT))
 #define pmd_none(pmd)		(!pmd_val(pmd))
-#define	pmd_bad(pmd)		((pmd_val(pmd)) == 0)
-#define	pmd_present(pmd)	((pmd_val(pmd)) != 0)
+#define	pmd_hugepage(pmd)	(!!(pmd_val(pmd) & _PMD_HUGEPAGE))
+#define	pmd_bad(pmd)		(((pmd_val(pmd)) == 0) || pmd_hugepage(pmd))
+#define	pmd_present(pmd)	((!pmd_hugepage(pmd)) \
+				 && (pmd_val(pmd) & ~_PMD_HUGEPAGE) != 0)
 #define	pmd_clear(pmdp)		(pmd_val(*(pmdp)) = 0)
-#define pmd_page_kernel(pmd)	(__bpn_to_ba(pmd_val(pmd)))
+#define pmd_page_kernel(pmd)	\
+	(__bpn_to_ba(pmd_val(pmd) >> PMD_TO_PTEPAGE_SHIFT))
 #define pmd_page(pmd)		virt_to_page(pmd_page_kernel(pmd))
 #define pgd_set(pgdp, pmdp)	(pgd_val(*(pgdp)) = (__ba_to_bpn(pmdp)))
 #define pgd_none(pgd)		(!pgd_val(pgd))

include/asm-ppc64/prom.h

@@ -183,8 +183,6 @@ extern struct device_node *find_type_devices(const char *type);
 extern struct device_node *find_path_device(const char *path);
 extern struct device_node *find_compatible_devices(const char *type,
 						   const char *compat);
-extern struct device_node *find_pci_device_OFnode(unsigned char bus,
-	unsigned char dev_fn);
 extern struct device_node *find_all_nodes(void);
 extern int device_is_compatible(struct device_node *device, const char *);
 extern int machine_is_compatible(const char *compat);

include/asm-ppc64/rtas.h

@@ -166,6 +166,13 @@ extern void rtas_restart(char *cmd);
 extern void rtas_power_off(void);
 extern void rtas_halt(void);
 
+/* Given an RTAS status code of 9900..9905 compute the hinted delay */
+unsigned int rtas_extended_busy_delay_time(int status);
+static inline int rtas_is_extended_busy(int status)
+{
+	return status >= 9900 && status <= 9909;
+}
+
 /* Some RTAS ops require a data buffer and that buffer must be < 4G.
  * Rather than having a memory allocator, just use this buffer
  * (get the lock first), make the RTAS call.  Copy the data instead

include/asm-ppc64/rwsem.h

 /*
- * include/asm-ppc/rwsem.h: R/W semaphores for PPC using the stuff
+ * include/asm-ppc64/rwsem.h: R/W semaphores for PPC using the stuff
  * in lib/rwsem.c.  Adapted largely from include/asm-i386/rwsem.h
  * by Paul Mackerras <paulus@samba.org>.
  *
@@ -74,9 +74,7 @@ static inline void init_rwsem(struct rw_semaphore *sem)
  */
 static inline void __down_read(struct rw_semaphore *sem)
 {
-	if (atomic_inc_return((atomic_t *)(&sem->count)) > 0)
-		smp_wmb();
-	else
+	if (unlikely(atomic_inc_return((atomic_t *)(&sem->count)) <= 0))
 		rwsem_down_read_failed(sem);
 }
 
@@ -87,7 +85,6 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 	while ((tmp = sem->count) >= 0) {
 		if (tmp == cmpxchg(&sem->count, tmp,
 				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
-			smp_wmb();
 			return 1;
 		}
 	}
@@ -103,9 +100,7 @@ static inline void __down_write(struct rw_semaphore *sem)
 
 	tmp = atomic_add_return(RWSEM_ACTIVE_WRITE_BIAS,
 				(atomic_t *)(&sem->count));
-	if (tmp == RWSEM_ACTIVE_WRITE_BIAS)
-		smp_wmb();
-	else
+	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
 		rwsem_down_write_failed(sem);
 }
 
@@ -115,7 +110,6 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
 
 	tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
 		      RWSEM_ACTIVE_WRITE_BIAS);
-	smp_wmb();
 	return tmp == RWSEM_UNLOCKED_VALUE;
 }
 
@@ -126,9 +120,8 @@ static inline void __up_read(struct rw_semaphore *sem)
 {
 	int tmp;
 
-	smp_wmb();
 	tmp = atomic_dec_return((atomic_t *)(&sem->count));
-	if (tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0)
+	if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
 		rwsem_wake(sem);
 }
 
@@ -137,9 +130,8 @@ static inline void __up_read(struct rw_semaphore *sem)
  */
 static inline void __up_write(struct rw_semaphore *sem)
 {
-	smp_wmb();
-	if (atomic_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
-			      (atomic_t *)(&sem->count)) < 0)
+	if (unlikely(atomic_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
+			      (atomic_t *)(&sem->count)) < 0))
 		rwsem_wake(sem);
 }
 
@@ -158,7 +150,6 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 {
 	int tmp;
 
-	smp_wmb();
 	tmp = atomic_add_return(-RWSEM_WAITING_BIAS, (atomic_t *)(&sem->count));
 	if (tmp < 0)
 		rwsem_downgrade_wake(sem);
@@ -169,7 +160,6 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
  */
 static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
 {
-	smp_mb();
 	return atomic_add_return(delta, (atomic_t *)(&sem->count));
 }
 

include/asm-ppc64/semaphore.h

@@ -82,9 +82,8 @@ static inline void down(struct semaphore * sem)
 	/*
 	 * Try to get the semaphore, take the slow path if we fail.
 	 */
-	if (atomic_dec_return(&sem->count) < 0)
+	if (unlikely(atomic_dec_return(&sem->count) < 0))
 		__down(sem);
-	smp_wmb();
 }
 
 static inline int down_interruptible(struct semaphore * sem)
@@ -96,23 +95,18 @@ static inline int down_interruptible(struct semaphore * sem)
 #endif
 	might_sleep();
 
-	if (atomic_dec_return(&sem->count) < 0)
+	if (unlikely(atomic_dec_return(&sem->count) < 0))
 		ret = __down_interruptible(sem);
-	smp_wmb();
 	return ret;
 }
 
 static inline int down_trylock(struct semaphore * sem)
 {
-	int ret;
-
 #ifdef WAITQUEUE_DEBUG
 	CHECK_MAGIC(sem->__magic);
 #endif
 
-	ret = atomic_dec_if_positive(&sem->count) < 0;
-	smp_wmb();
-	return ret;
+	return atomic_dec_if_positive(&sem->count) < 0;
 }
 
 static inline void up(struct semaphore * sem)
@@ -121,8 +115,7 @@ static inline void up(struct semaphore * sem)
 	CHECK_MAGIC(sem->__magic);
 #endif
 
-	smp_wmb();
-	if (atomic_inc_return(&sem->count) <= 0)
+	if (unlikely(atomic_inc_return(&sem->count) <= 0))
 		__up(sem);
 }
 

include/asm-ppc64/serial.h

@@ -26,11 +26,9 @@
 
 /* Standard COM flags (except for COM4, because of the 8514 problem) */
 #ifdef CONFIG_SERIAL_DETECT_IRQ
-#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ)
-#define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ)
+#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ)
 #else
-#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST)
-#define STD_COM4_FLAGS ASYNC_BOOT_AUTOCONF
+#define STD_COM_FLAGS ASYNC_BOOT_AUTOCONF
 #endif
 
 #ifdef CONFIG_SERIAL_MANY_PORTS
@@ -60,8 +58,8 @@
 	/* UART CLK   PORT IRQ     FLAGS        */			\
 	{ 0, BASE_BAUD, 0x3F8, 4, STD_COM_FLAGS },	/* ttyS0 */	\
 	{ 0, BASE_BAUD, 0x2F8, 3, STD_COM_FLAGS },	/* ttyS1 */	\
-	{ 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS },	/* ttyS2 */	\
-	{ 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS },	/* ttyS3 */
+	{ 0, BASE_BAUD, 0x890, 0xf, STD_COM_FLAGS },	/* ttyS2 */	\
+	{ 0, BASE_BAUD, 0x898, 0xe, STD_COM_FLAGS },	/* ttyS3 */
 
 
 #ifdef CONFIG_SERIAL_MANY_PORTS

include/asm-ppc64/topology.h

@@ -24,14 +24,16 @@ static inline int cpu_to_node(int cpu)
 
 #define parent_node(node)	(node)
 
-static inline unsigned long node_to_cpumask(int node)
+static inline cpumask_t node_to_cpumask(int node)
 {
 	return numa_cpumask_lookup_table[node];
 }
 
 static inline int node_to_first_cpu(int node)
 {
-	return __ffs(node_to_cpumask(node));
+	cpumask_t tmp;
+	tmp = node_to_cpumask(node);
+	return first_cpu(tmp);
 }
 
 #define node_to_memblk(node)	(node)

include/asm-ppc64/uaccess.h

@@ -132,6 +132,7 @@ extern long __put_user_bad(void);
 
 #define __put_user_size(x,ptr,size,retval,errret)			\
 do {									\
+	might_sleep();							\
 	retval = 0;							\
 	switch (size) {							\
 	  case 1: __put_user_asm(x,ptr,retval,"stb",errret); break;	\
@@ -185,6 +186,7 @@ extern long __get_user_bad(void);
 
 #define __get_user_size(x,ptr,size,retval,errret)			\
 do {									\
+	might_sleep();							\
 	retval = 0;							\
 	switch (size) {							\
 	  case 1: __get_user_asm(x,ptr,retval,"lbz",errret); break;	\
@@ -220,6 +222,7 @@ extern unsigned long __copy_tofrom_user(void *to, const void *from,
 static inline unsigned long
 __copy_from_user(void *to, const void __user *from, unsigned long n)
 {
+	might_sleep();
 	if (__builtin_constant_p(n)) {
 		unsigned long ret;
 
@@ -244,6 +247,7 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
 static inline unsigned long
 __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
+	might_sleep();
 	if (__builtin_constant_p(n)) {
 		unsigned long ret;
 
@@ -289,6 +293,7 @@ copy_to_user(void *to, const void *from, unsigned long n)
 static inline unsigned long
 copy_in_user(void *to, const void *from, unsigned long n)
 {
+	might_sleep();
 	if (likely(access_ok(VERIFY_READ, from, n) &&
 	    access_ok(VERIFY_WRITE, to, n)))
 		n =__copy_tofrom_user(to, from, n);
@@ -300,6 +305,7 @@ extern unsigned long __clear_user(void *addr, unsigned long size);
 static inline unsigned long
 clear_user(void *addr, unsigned long size)
 {
+	might_sleep();
 	if (likely(access_ok(VERIFY_WRITE, addr, size)))
 		size = __clear_user(addr, size);
 	return size;
@@ -310,6 +316,7 @@ extern int __strncpy_from_user(char *dst, const char *src, long count);
 static inline long
 strncpy_from_user(char *dst, const char *src, long count)
 {
+	might_sleep();
 	if (likely(access_ok(VERIFY_READ, src, 1)))
 		return __strncpy_from_user(dst, src, count);
 	return -EFAULT;
@@ -329,6 +336,7 @@ extern int __strnlen_user(const char *str, long len);
  */
 static inline int strnlen_user(const char *str, long len)
 {
+	might_sleep();
 	if (likely(access_ok(VERIFY_READ, str, 1)))
 		return __strnlen_user(str, len);
 	return 0;