Merge branch 'master' into for-next

Sync with Linus' tree to be able to apply patches against new
code I have in queue.

55 files changed, 748 insertions, 286 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index a3128ca0fe11..2729c6663d8a 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -91,14 +91,6 @@ config GENERIC_HWEIGHT
 	bool
 	default y
 
-config GENERIC_FIND_NEXT_BIT
-	bool
-	default y
-
-config GENERIC_FIND_BIT_LE
-	bool
-	default y
-
 config GENERIC_GPIO
 	bool
 	help
@@ -140,6 +132,8 @@ config PPC
 	select IRQ_PER_CPU
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
+	select HAVE_RCU_TABLE_FREE if SMP
+	select HAVE_SYSCALL_TRACEPOINTS
 
 config EARLY_PRINTK
 	bool
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index a597dd77b903..e72dcf6a421d 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -35,27 +35,6 @@ config DEBUG_STACKOVERFLOW
 	  This option will cause messages to be printed if free stack space
 	  drops below a certain limit.
 
-config DEBUG_STACK_USAGE
-	bool "Stack utilization instrumentation"
-	depends on DEBUG_KERNEL
-	help
-	  Enables the display of the minimum amount of free stack which each
-	  task has ever had available in the sysrq-T and sysrq-P debug output.
-
-	  This option will slow down process creation somewhat.
-
-config DEBUG_PER_CPU_MAPS
-	bool "Debug access to per_cpu maps"
-	depends on DEBUG_KERNEL
-	depends on SMP
-	default n
-	---help---
-	  Say Y to verify that the per_cpu map being accessed has
-	  been setup.  Adds a fair amount of code to kernel memory
-	  and decreases performance.
-
-	  Say N if unsure.
-
 config HCALL_STATS
 	bool "Hypervisor call instrumentation"
 	depends on PPC_PSERIES && DEBUG_FS && TRACEPOINTS
diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore
index 3d80c3e9cf60..12da77ec0228 100644
--- a/arch/powerpc/boot/.gitignore
+++ b/arch/powerpc/boot/.gitignore
@@ -1,5 +1,4 @@
 addnote
-dtc
 empty.c
 hack-coff
 infblock.c
diff --git a/arch/powerpc/boot/dtc-src/.gitignore b/arch/powerpc/boot/dtc-src/.gitignore
deleted file mode 100644
index a7c3f94e5e75..000000000000
--- a/arch/powerpc/boot/dtc-src/.gitignore
+++ /dev/null
@@ -1,3 +0,0 @@
-dtc-lexer.lex.c
-dtc-parser.tab.c
-dtc-parser.tab.h
diff --git a/arch/powerpc/boot/dts/canyonlands.dts b/arch/powerpc/boot/dts/canyonlands.dts
index 2779f08313a5..22dd6ae84da0 100644
--- a/arch/powerpc/boot/dts/canyonlands.dts
+++ b/arch/powerpc/boot/dts/canyonlands.dts
@@ -530,5 +530,23 @@
 				0x0 0x0 0x0 0x3 &UIC3 0x12 0x4 /* swizzled int C */
 				0x0 0x0 0x0 0x4 &UIC3 0x13 0x4 /* swizzled int D */>;
 		};
+
+		MSI: ppc4xx-msi@C10000000 {
+			compatible = "amcc,ppc4xx-msi", "ppc4xx-msi";
+			reg = < 0xC 0x10000000 0x100>;
+			sdr-base = <0x36C>;
+			msi-data = <0x00000000>;
+			msi-mask = <0x44440000>;
+			interrupt-count = <3>;
+			interrupts = <0 1 2 3>;
+			interrupt-parent = <&UIC3>;
+			#interrupt-cells = <1>;
+			#address-cells = <0>;
+			#size-cells = <0>;
+			interrupt-map = <0 &UIC3 0x18 1
+					1 &UIC3 0x19 1
+					2 &UIC3 0x1A 1
+					3 &UIC3 0x1B 1>;
+		};
 	};
 };
diff --git a/arch/powerpc/boot/dts/katmai.dts b/arch/powerpc/boot/dts/katmai.dts
index 7c3be5e45748..f913dbe25d35 100644
--- a/arch/powerpc/boot/dts/katmai.dts
+++ b/arch/powerpc/boot/dts/katmai.dts
@@ -442,6 +442,24 @@
 				0x0 0x0 0x0 0x4 &UIC3 0xb 0x4 /* swizzled int D */>;
 		};
 
+		MSI: ppc4xx-msi@400300000 {
+				compatible = "amcc,ppc4xx-msi", "ppc4xx-msi";
+				reg = < 0x4 0x00300000 0x100>;
+				sdr-base = <0x3B0>;
+				msi-data = <0x00000000>;
+				msi-mask = <0x44440000>;
+				interrupt-count = <3>;
+				interrupts =<0 1 2 3>;
+				interrupt-parent = <&UIC0>;
+				#interrupt-cells = <1>;
+				#address-cells = <0>;
+				#size-cells = <0>;
+				interrupt-map = <0 &UIC0 0xC 1
+					1 &UIC0 0x0D 1
+					2 &UIC0 0x0E 1
+					3 &UIC0 0x0F 1>;
+		};
+
 		I2O: i2o@400100000 {
 			compatible = "ibm,i2o-440spe";
 			reg = <0x00000004 0x00100000 0x100>;
diff --git a/arch/powerpc/boot/dts/kilauea.dts b/arch/powerpc/boot/dts/kilauea.dts
index 89edb16649c3..1613d6e4049e 100644
--- a/arch/powerpc/boot/dts/kilauea.dts
+++ b/arch/powerpc/boot/dts/kilauea.dts
@@ -403,5 +403,33 @@
 				0x0 0x0 0x0 0x3 &UIC2 0xd 0x4 /* swizzled int C */
 				0x0 0x0 0x0 0x4 &UIC2 0xe 0x4 /* swizzled int D */>;
 		};
+
+		MSI: ppc4xx-msi@C10000000 {
+			compatible = "amcc,ppc4xx-msi", "ppc4xx-msi";
+			reg = < 0x0 0xEF620000 0x100>;
+			sdr-base = <0x4B0>;
+			msi-data = <0x00000000>;
+			msi-mask = <0x44440000>;
+			interrupt-count = <12>;
+			interrupts = <0 1 2 3 4 5 6 7 8 9 0xA 0xB 0xC 0xD>;
+			interrupt-parent = <&UIC2>;
+			#interrupt-cells = <1>;
+			#address-cells = <0>;
+			#size-cells = <0>;
+			interrupt-map = <0 &UIC2 0x10 1
+					1 &UIC2 0x11 1
+					2 &UIC2 0x12 1
+					2 &UIC2 0x13 1
+					2 &UIC2 0x14 1
+					2 &UIC2 0x15 1
+					2 &UIC2 0x16 1
+					2 &UIC2 0x17 1
+					2 &UIC2 0x18 1
+					2 &UIC2 0x19 1
+					2 &UIC2 0x1A 1
+					2 &UIC2 0x1B 1
+					2 &UIC2 0x1C 1
+					3 &UIC2 0x1D 1>;
+		};
 	};
 };
diff --git a/arch/powerpc/boot/dts/mpc8313erdb.dts b/arch/powerpc/boot/dts/mpc8313erdb.dts
index 761faa7b6964..ac1eb320c7b4 100644
--- a/arch/powerpc/boot/dts/mpc8313erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8313erdb.dts
@@ -176,6 +176,19 @@
 			sleep = <&pmc 0x00300000>;
 		};
 
+		ptp_clock@24E00 {
+			compatible = "fsl,etsec-ptp";
+			reg = <0x24E00 0xB0>;
+			interrupts = <12 0x8 13 0x8>;
+			interrupt-parent = < &ipic >;
+			fsl,tclk-period = <10>;
+			fsl,tmr-prsc    = <100>;
+			fsl,tmr-add     = <0x999999A4>;
+			fsl,tmr-fiper1  = <0x3B9AC9F6>;
+			fsl,tmr-fiper2  = <0x00018696>;
+			fsl,max-adj     = <659999998>;
+		};
+
 		enet0: ethernet@24000 {
 			#address-cells = <1>;
 			#size-cells = <1>;
diff --git a/arch/powerpc/boot/dts/mpc8572ds.dts b/arch/powerpc/boot/dts/mpc8572ds.dts
index cafc1285c140..f6c04d25e916 100644
--- a/arch/powerpc/boot/dts/mpc8572ds.dts
+++ b/arch/powerpc/boot/dts/mpc8572ds.dts
@@ -324,6 +324,19 @@
 			};
 		};
 
+		ptp_clock@24E00 {
+			compatible = "fsl,etsec-ptp";
+			reg = <0x24E00 0xB0>;
+			interrupts = <68 2 69 2 70 2 71 2>;
+			interrupt-parent = < &mpic >;
+			fsl,tclk-period = <5>;
+			fsl,tmr-prsc = <200>;
+			fsl,tmr-add = <0xAAAAAAAB>;
+			fsl,tmr-fiper1 = <0x3B9AC9FB>;
+			fsl,tmr-fiper2 = <0x3B9AC9FB>;
+			fsl,max-adj = <499999999>;
+		};
+
 		enet0: ethernet@24000 {
 			#address-cells = <1>;
 			#size-cells = <1>;
diff --git a/arch/powerpc/boot/dts/p2020ds.dts b/arch/powerpc/boot/dts/p2020ds.dts
index 2bcf3683d223..dae403100f2f 100644
--- a/arch/powerpc/boot/dts/p2020ds.dts
+++ b/arch/powerpc/boot/dts/p2020ds.dts
@@ -178,6 +178,19 @@
 
 		};
 
+		ptp_clock@24E00 {
+			compatible = "fsl,etsec-ptp";
+			reg = <0x24E00 0xB0>;
+			interrupts = <68 2 69 2 70 2>;
+			interrupt-parent = < &mpic >;
+			fsl,tclk-period = <5>;
+			fsl,tmr-prsc = <200>;
+			fsl,tmr-add = <0xCCCCCCCD>;
+			fsl,tmr-fiper1 = <0x3B9AC9FB>;
+			fsl,tmr-fiper2 = <0x0001869B>;
+			fsl,max-adj = <249999999>;
+		};
+
 		enet0: ethernet@24000 {
 			tbi-handle = <&tbi0>;
 			phy-handle = <&phy0>;
diff --git a/arch/powerpc/boot/dts/p2020rdb.dts b/arch/powerpc/boot/dts/p2020rdb.dts
index 3782a58f13be..1d7a05f3021e 100644
--- a/arch/powerpc/boot/dts/p2020rdb.dts
+++ b/arch/powerpc/boot/dts/p2020rdb.dts
@@ -224,6 +224,19 @@
 			status = "disabled";
 		};
 
+		ptp_clock@24E00 {
+			compatible = "fsl,etsec-ptp";
+			reg = <0x24E00 0xB0>;
+			interrupts = <68 2 69 2 70 2>;
+			interrupt-parent = < &mpic >;
+			fsl,tclk-period = <5>;
+			fsl,tmr-prsc = <200>;
+			fsl,tmr-add = <0xCCCCCCCD>;
+			fsl,tmr-fiper1 = <0x3B9AC9FB>;
+			fsl,tmr-fiper2 = <0x0001869B>;
+			fsl,max-adj = <249999999>;
+		};
+
 		enet0: ethernet@24000 {
 			fixed-link = <1 1 1000 0 0>;
 			phy-connection-type = "rgmii-id";
diff --git a/arch/powerpc/boot/dts/redwood.dts b/arch/powerpc/boot/dts/redwood.dts
index 81636c01d906..d86a3a498118 100644
--- a/arch/powerpc/boot/dts/redwood.dts
+++ b/arch/powerpc/boot/dts/redwood.dts
@@ -358,8 +358,28 @@
 				0x0 0x0 0x0 0x4 &UIC3 0xb 0x4 /* swizzled int D */>;
 		};
 
+		MSI: ppc4xx-msi@400300000 {
+				compatible = "amcc,ppc4xx-msi", "ppc4xx-msi";
+				reg = < 0x4 0x00300000 0x100
+					0x4 0x00300000 0x100>;
+				sdr-base = <0x3B0>;
+				msi-data = <0x00000000>;
+				msi-mask = <0x44440000>;
+				interrupt-count = <3>;
+				interrupts =<0 1 2 3>;
+				interrupt-parent = <&UIC0>;
+				#interrupt-cells = <1>;
+				#address-cells = <0>;
+				#size-cells = <0>;
+				interrupt-map = <0 &UIC0 0xC 1
+					1 &UIC0 0x0D 1
+					2 &UIC0 0x0E 1
+					3 &UIC0 0x0F 1>;
+		};
+
 	};
 
+
 	chosen {
 		linux,stdout-path = "/plb/opb/serial@ef600200";
 	};
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index 214208924a9c..04360f9b0109 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -10,7 +10,6 @@ CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_AUDIT=y
 CONFIG_CGROUPS=y
-CONFIG_CGROUP_NS=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index 7de13865508c..c9f212b5f3de 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -15,7 +15,6 @@ CONFIG_AUDITSYSCALL=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_CGROUPS=y
-CONFIG_CGROUP_NS=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
diff --git a/arch/powerpc/include/asm/fsl_lbc.h b/arch/powerpc/include/asm/fsl_lbc.h
index 5c1bf3466749..8a0b5ece8f76 100644
--- a/arch/powerpc/include/asm/fsl_lbc.h
+++ b/arch/powerpc/include/asm/fsl_lbc.h
@@ -157,6 +157,8 @@ struct fsl_lbc_regs {
 #define LBCR_EPAR_SHIFT    16
 #define LBCR_BMT   0x0000FF00
 #define LBCR_BMT_SHIFT      8
+#define LBCR_BMTPS 0x0000000F
+#define LBCR_BMTPS_SHIFT    0
 #define LBCR_INIT  0x00040000
 	__be32 lcrr;            /**< Clock Ratio Register */
 #define LCRR_DBYP    0x80000000
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index dde1296b8b41..169d039ed402 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -60,4 +60,18 @@ struct dyn_arch_ftrace {
 
 #endif
 
+#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64) && !defined(__ASSEMBLY__)
+#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
+{
+	/*
+	 * Compare the symbol name with the system call name. Skip the .sys or .SyS
+	 * prefix from the symbol name and the sys prefix from the system call name and
+	 * just match the rest. This is only needed on ppc64 since symbol names on
+	 * 32bit do not start with a period so the generic function will work.
+	 */
+	return !strcmp(sym + 4, name + 3);
+}
+#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 && !__ASSEMBLY__ */
+
 #endif /* _ASM_POWERPC_FTRACE */
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 852b8c1c09db..fd8201dddd4b 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -236,7 +236,7 @@
 #define H_HOME_NODE_ASSOCIATIVITY 0x2EC
 #define H_BEST_ENERGY		0x2F4
 #define H_GET_MPP_X		0x314
-#define MAX_HCALL_OPCODE	H_BEST_ENERGY
+#define MAX_HCALL_OPCODE	H_GET_MPP_X
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index abe8532bd14e..bf301ac62f35 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -31,14 +31,29 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 #endif
 
 #ifdef CONFIG_SMP
-extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift);
-extern void pte_free_finish(void);
+struct mmu_gather;
+extern void tlb_remove_table(struct mmu_gather *, void *);
+
+static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
+{
+	unsigned long pgf = (unsigned long)table;
+	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+	pgf |= shift;
+	tlb_remove_table(tlb, (void *)pgf);
+}
+
+static inline void __tlb_remove_table(void *_table)
+{
+	void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+	unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+	pgtable_free(table, shift);
+}
 #else /* CONFIG_SMP */
 static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
 {
 	pgtable_free(table, shift);
 }
-static inline void pte_free_finish(void) { }
 #endif /* !CONFIG_SMP */
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage,
diff --git a/arch/powerpc/include/asm/rio.h b/arch/powerpc/include/asm/rio.h
index 0018bf80cb25..b1d2deceeedb 100644
--- a/arch/powerpc/include/asm/rio.h
+++ b/arch/powerpc/include/asm/rio.h
@@ -14,5 +14,10 @@
 #define ASM_PPC_RIO_H
 
 extern void platform_rio_init(void);
+#ifdef CONFIG_FSL_RIO
+extern int fsl_rio_mcheck_exception(struct pt_regs *);
+#else
+static inline int fsl_rio_mcheck_exception(struct pt_regs *regs) {return 0; }
+#endif
 
 #endif				/* ASM_PPC_RIO_H */
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 880b8c1e6e53..11eb404b5606 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -191,8 +191,6 @@ extern unsigned long __secondary_hold_spinloop;
 extern unsigned long __secondary_hold_acknowledge;
 extern char __secondary_hold;
 
-extern irqreturn_t debug_ipi_action(int irq, void *data);
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/suspend.h b/arch/powerpc/include/asm/suspend.h
deleted file mode 100644
index c6efc3466aa6..000000000000
--- a/arch/powerpc/include/asm/suspend.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_POWERPC_SUSPEND_H
-#define __ASM_POWERPC_SUSPEND_H
-
-static inline int arch_prepare_suspend(void) { return 0; }
-
-#endif /* __ASM_POWERPC_SUSPEND_H */
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index 23913e902fc3..b54b2add07be 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -15,6 +15,11 @@
 
 #include <linux/sched.h>
 
+/* ftrace syscalls requires exporting the sys_call_table */
+#ifdef CONFIG_FTRACE_SYSCALLS
+extern const unsigned long *sys_call_table;
+#endif /* CONFIG_FTRACE_SYSCALLS */
+
 static inline long syscall_get_nr(struct task_struct *task,
 				  struct pt_regs *regs)
 {
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 8489d372077f..f6736b7da463 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -353,3 +353,4 @@ COMPAT_SYS_SPU(open_by_handle_at)
 COMPAT_SYS_SPU(clock_adjtime)
 SYSCALL_SPU(syncfs)
 COMPAT_SYS_SPU(sendmmsg)
+SYSCALL_SPU(setns)
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index d8529ef13b23..836f231ec1f0 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -110,7 +110,8 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_NOERROR		12	/* Force successful syscall return */
 #define TIF_NOTIFY_RESUME	13	/* callback before returning to user */
 #define TIF_FREEZE		14	/* Freezing for suspend */
-#define TIF_RUNLATCH		15	/* Is the runlatch enabled? */
+#define TIF_SYSCALL_TRACEPOINT	15	/* syscall tracepoint instrumentation */
+#define TIF_RUNLATCH		16	/* Is the runlatch enabled? */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
@@ -127,8 +128,10 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_NOERROR		(1<<TIF_NOERROR)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
 #define _TIF_FREEZE		(1<<TIF_FREEZE)
+#define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_RUNLATCH		(1<<TIF_RUNLATCH)
-#define _TIF_SYSCALL_T_OR_A	(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP)
+#define _TIF_SYSCALL_T_OR_A	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
+				 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT)
 
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
 				 _TIF_NOTIFY_RESUME)
@@ -139,10 +142,12 @@ static inline struct thread_info *current_thread_info(void)
 #define TLF_NAPPING		0	/* idle thread enabled NAP mode */
 #define TLF_SLEEPING		1	/* suspend code enabled SLEEP mode */
 #define TLF_RESTORE_SIGMASK	2	/* Restore signal mask in do_signal */
+#define TLF_LAZY_MMU		3	/* tlb_batch is active */
 
 #define _TLF_NAPPING		(1 << TLF_NAPPING)
 #define _TLF_SLEEPING		(1 << TLF_SLEEPING)
 #define _TLF_RESTORE_SIGMASK	(1 << TLF_RESTORE_SIGMASK)
+#define _TLF_LAZY_MMU		(1 << TLF_LAZY_MMU)
 
 #ifndef __ASSEMBLY__
 #define HAVE_SET_RESTORE_SIGMASK	1
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 6d23c8193caa..b8b3f599362b 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -372,10 +372,11 @@
 #define __NR_clock_adjtime	347
 #define __NR_syncfs		348
 #define __NR_sendmmsg		349
+#define __NR_setns		350
 
 #ifdef __KERNEL__
 
-#define __NR_syscalls		350
+#define __NR_syscalls		351
 
 #define __NR__exit __NR_exit
 #define NR_syscalls	__NR_syscalls
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 9aab36312572..e8b981897d44 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -109,6 +109,7 @@ obj-$(CONFIG_PPC_IO_WORKAROUNDS)	+= io-workarounds.o
 
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
+obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_callchain.o
 
 obj-$(CONFIG_PPC_PERF_CTRS)	+= perf_event.o
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 34d2722b9451..9fb933248ab6 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -1979,7 +1979,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.pvr_value		= 0x80240000,
 		.cpu_name		= "e5500",
 		.cpu_features		= CPU_FTRS_E5500,
-		.cpu_user_features	= COMMON_USER_BOOKE,
+		.cpu_user_features	= COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
 		.mmu_features		= MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS |
 			MMU_FTR_USE_TLBILX,
 		.icache_bsize		= 64,
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index ce1f3e44c24f..bf99cfa6bbfe 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -22,6 +22,7 @@
 #include <asm/cacheflush.h>
 #include <asm/code-patching.h>
 #include <asm/ftrace.h>
+#include <asm/syscall.h>
 
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -600,3 +601,10 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 	}
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64)
+unsigned long __init arch_syscall_addr(int nr)
+{
+	return sys_call_table[nr*2];
+}
+#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index a24d37d4cf51..5b428e308666 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -295,17 +295,20 @@ static inline void handle_one_irq(unsigned int irq)
 	unsigned long saved_sp_limit;
 	struct irq_desc *desc;
 
+	desc = irq_to_desc(irq);
+	if (!desc)
+		return;
+
 	/* Switch to the irq stack to handle this */
 	curtp = current_thread_info();
 	irqtp = hardirq_ctx[smp_processor_id()];
 
 	if (curtp == irqtp) {
 		/* We're already on the irq stack, just handle it */
-		generic_handle_irq(irq);
+		desc->handle_irq(irq, desc);
 		return;
 	}
 
-	desc = irq_to_desc(irq);
 	saved_sp_limit = current->thread.ksp_limit;
 
 	irqtp->task = curtp->task;
@@ -557,15 +560,8 @@ struct irq_host *irq_alloc_host(struct device_node *of_node,
 	if (revmap_type == IRQ_HOST_MAP_LEGACY) {
 		if (irq_map[0].host != NULL) {
 			raw_spin_unlock_irqrestore(&irq_big_lock, flags);
-			/* If we are early boot, we can't free the structure,
-			 * too bad...
-			 * this will be fixed once slab is made available early
-			 * instead of the current cruft
-			 */
-			if (mem_init_done) {
-				of_node_put(host->of_node);
-				kfree(host);
-			}
+			of_node_put(host->of_node);
+			kfree(host);
 			return NULL;
 		}
 		irq_map[0].host = host;
@@ -727,9 +723,7 @@ unsigned int irq_create_mapping(struct irq_host *host,
 	}
 	pr_debug("irq: -> using host @%p\n", host);
 
-	/* Check if mapping already exist, if it does, call
-	 * host->ops->map() to update the flags
-	 */
+	/* Check if mapping already exists */
 	virq = irq_find_mapping(host, hwirq);
 	if (virq != NO_IRQ) {
 		pr_debug("irq: -> existing mapping on virq %d\n", virq);
@@ -899,10 +893,13 @@ unsigned int irq_radix_revmap_lookup(struct irq_host *host,
 		return irq_find_mapping(host, hwirq);
 
 	/*
-	 * No rcu_read_lock(ing) needed, the ptr returned can't go under us
-	 * as it's referencing an entry in the static irq_map table.
+	 * The ptr returned references the static global irq_map.
+	 * but freeing an irq can delete nodes along the path to
+	 * do the lookup via call_rcu.
 	 */
+	rcu_read_lock();
 	ptr = radix_tree_lookup(&host->revmap_data.tree, hwirq);
+	rcu_read_unlock();
 
 	/*
 	 * If found in radix tree, then fine.
@@ -1010,14 +1007,23 @@ void irq_free_virt(unsigned int virq, unsigned int count)
 	WARN_ON (virq < NUM_ISA_INTERRUPTS);
 	WARN_ON (count == 0 || (virq + count) > irq_virq_count);
 
+	if (virq < NUM_ISA_INTERRUPTS) {
+		if (virq + count < NUM_ISA_INTERRUPTS)
+			return;
+		count  =- NUM_ISA_INTERRUPTS - virq;
+		virq = NUM_ISA_INTERRUPTS;
+	}
+
+	if (count > irq_virq_count || virq > irq_virq_count - count) {
+		if (virq > irq_virq_count)
+			return;
+		count = irq_virq_count - virq;
+	}
+
 	raw_spin_lock_irqsave(&irq_big_lock, flags);
 	for (i = virq; i < (virq + count); i++) {
 		struct irq_host *host;
 
-		if (i < NUM_ISA_INTERRUPTS ||
-		    (virq + count) > irq_virq_count)
-			continue;
-
 		host = irq_map[i].host;
 		irq_map[i].hwirq = host->inval_irq;
 		smp_wmb();
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 095043d79946..91e52df3d81d 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -395,6 +395,9 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	struct thread_struct *new_thread, *old_thread;
 	unsigned long flags;
 	struct task_struct *last;
+#ifdef CONFIG_PPC_BOOK3S_64
+	struct ppc64_tlb_batch *batch;
+#endif
 
 #ifdef CONFIG_SMP
 	/* avoid complexity of lazy save/restore of fpu
@@ -513,7 +516,17 @@ struct task_struct *__switch_to(struct task_struct *prev,
 		old_thread->accum_tb += (current_tb - start_tb);
 		new_thread->start_tb = current_tb;
 	}
-#endif
+#endif /* CONFIG_PPC64 */
+
+#ifdef CONFIG_PPC_BOOK3S_64
+	batch = &__get_cpu_var(ppc64_tlb_batch);
+	if (batch->active) {
+		current_thread_info()->local_flags |= _TLF_LAZY_MMU;
+		if (batch->index)
+			__flush_tlb_pending(batch);
+		batch->active = 0;
+	}
+#endif /* CONFIG_PPC_BOOK3S_64 */
 
 	local_irq_save(flags);
 
@@ -528,6 +541,14 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	hard_irq_disable();
 	last = _switch(old_thread, new_thread);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (current_thread_info()->local_flags & _TLF_LAZY_MMU) {
+		current_thread_info()->local_flags &= ~_TLF_LAZY_MMU;
+		batch = &__get_cpu_var(ppc64_tlb_batch);
+		batch->active = 1;
+	}
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
 	local_irq_restore(flags);
 
 	return last;
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 48aeb55faae9..8c3112a57cf2 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -82,11 +82,29 @@ static int __init early_parse_mem(char *p)
 }
 early_param("mem", early_parse_mem);
 
+/*
+ * overlaps_initrd - check for overlap with page aligned extension of
+ * initrd.
+ */
+static inline int overlaps_initrd(unsigned long start, unsigned long size)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+	if (!initrd_start)
+		return 0;
+
+	return	(start + size) > _ALIGN_DOWN(initrd_start, PAGE_SIZE) &&
+			start <= _ALIGN_UP(initrd_end, PAGE_SIZE);
+#else
+	return 0;
+#endif
+}
+
 /**
  * move_device_tree - move tree to an unused area, if needed.
  *
  * The device tree may be allocated beyond our memory limit, or inside the
- * crash kernel region for kdump. If so, move it out of the way.
+ * crash kernel region for kdump, or within the page aligned range of initrd.
+ * If so, move it out of the way.
  */
 static void __init move_device_tree(void)
 {
@@ -99,7 +117,8 @@ static void __init move_device_tree(void)
 	size = be32_to_cpu(initial_boot_params->totalsize);
 
 	if ((memory_limit && (start + size) > PHYSICAL_START + memory_limit) ||
-			overlaps_crashkernel(start, size)) {
+			overlaps_crashkernel(start, size) ||
+			overlaps_initrd(start, size)) {
 		p = __va(memblock_alloc(size, PAGE_SIZE));
 		memcpy(p, initial_boot_params, size);
 		initial_boot_params = (struct boot_param_header *)p;
@@ -555,7 +574,9 @@ static void __init early_reserve_mem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* then reserve the initrd, if any */
 	if (initrd_start && (initrd_end > initrd_start))
-		memblock_reserve(__pa(initrd_start), initrd_end - initrd_start);
+		memblock_reserve(_ALIGN_DOWN(__pa(initrd_start), PAGE_SIZE),
+			_ALIGN_UP(initrd_end, PAGE_SIZE) -
+			_ALIGN_DOWN(initrd_start, PAGE_SIZE));
 #endif /* CONFIG_BLK_DEV_INITRD */
 
 #ifdef CONFIG_PPC32
@@ -694,7 +715,7 @@ void __init early_init_devtree(void *params)
 	 * device-tree, including the platform type, initrd location and
 	 * size, TCE reserve, and more ...
 	 */
-	of_scan_flat_dt(early_init_dt_scan_chosen_ppc, NULL);
+	of_scan_flat_dt(early_init_dt_scan_chosen_ppc, cmd_line);
 
 	/* Scan memory nodes and rebuild MEMBLOCKs */
 	memblock_init();
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index a6ae1cfad86c..cb22024f2b42 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -29,6 +29,7 @@
 #include <linux/signal.h>
 #include <linux/seccomp.h>
 #include <linux/audit.h>
+#include <trace/syscall.h>
 #ifdef CONFIG_PPC32
 #include <linux/module.h>
 #endif
@@ -40,6 +41,9 @@
 #include <asm/pgtable.h>
 #include <asm/system.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
 /*
  * The parameter save area on the stack is used to store arguments being passed
  * to callee function and is located at fixed offset from stack pointer.
@@ -1710,6 +1714,9 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 		 */
 		ret = -1L;
 
+	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+		trace_sys_enter(regs, regs->gpr[0]);
+
 	if (unlikely(current->audit_context)) {
 #ifdef CONFIG_PPC64
 		if (!is_32bit_task())
@@ -1738,6 +1745,9 @@ void do_syscall_trace_leave(struct pt_regs *regs)
 		audit_syscall_exit((regs->ccr&0x10000000)?AUDITSC_FAILURE:AUDITSC_SUCCESS,
 				   regs->result);
 
+	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+		trace_sys_exit(regs, regs->result);
+
 	step = test_thread_flag(TIF_SINGLESTEP);
 	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, step);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 4a6f2ec7e761..8ebc6700b98d 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -129,7 +129,7 @@ static irqreturn_t call_function_single_action(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-irqreturn_t debug_ipi_action(int irq, void *data)
+static irqreturn_t debug_ipi_action(int irq, void *data)
 {
 	if (crash_ipi_function_ptr) {
 		crash_ipi_function_ptr(get_irq_regs());
diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c
index 560c96119501..aa17b76dd427 100644
--- a/arch/powerpc/kernel/swsusp.c
+++ b/arch/powerpc/kernel/swsusp.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/sched.h>
-#include <asm/suspend.h>
 #include <asm/system.h>
 #include <asm/current.h>
 #include <asm/mmu_context.h>
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index b13306b0d925..0ff4ab98d50c 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -55,6 +55,7 @@
 #endif
 #include <asm/kexec.h>
 #include <asm/ppc-opcode.h>
+#include <asm/rio.h>
 
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
 int (*__debugger)(struct pt_regs *regs) __read_mostly;
@@ -424,6 +425,12 @@ int machine_check_e500mc(struct pt_regs *regs)
 	unsigned long reason = mcsr;
 	int recoverable = 1;
 
+	if (reason & MCSR_BUS_RBERR) {
+		recoverable = fsl_rio_mcheck_exception(regs);
+		if (recoverable == 1)
+			goto silent_out;
+	}
+
 	printk("Machine check in kernel mode.\n");
 	printk("Caused by (from MCSR=%lx): ", reason);
 
@@ -499,6 +506,7 @@ int machine_check_e500mc(struct pt_regs *regs)
 		       reason & MCSR_MEA ? "Effective" : "Physical", addr);
 	}
 
+silent_out:
 	mtspr(SPRN_MCSR, mcsr);
 	return mfspr(SPRN_MCSR) == 0 && recoverable;
 }
@@ -507,6 +515,11 @@ int machine_check_e500(struct pt_regs *regs)
 {
 	unsigned long reason = get_mc_reason(regs);
 
+	if (reason & MCSR_BUS_RBERR) {
+		if (fsl_rio_mcheck_exception(regs))
+			return 1;
+	}
+
 	printk("Machine check in kernel mode.\n");
 	printk("Caused by (from MCSR=%lx): ", reason);
 
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index b9150f07d266..920276c0f6a1 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -160,7 +160,7 @@ SECTIONS
 		INIT_RAM_FS
 	}
 
-	PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
+	PERCPU_SECTION(L1_CACHE_BYTES)
 
 	. = ALIGN(8);
 	.machine.desc : AT(ADDR(.machine.desc) - LOAD_OFFSET) {
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index d65b591e5556..5de0f254dbb5 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -223,21 +223,6 @@ void free_initmem(void)
 #undef FREESEC
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	if (start < end)
-		printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
-	for (; start < end; start += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(start));
-		init_page_count(virt_to_page(start));
-		free_page(start);
-		totalram_pages++;
-	}
-}
-#endif
-
-
 #ifdef CONFIG_8xx /* No 8xx specific .c file to put that in ... */
 void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 				phys_addr_t first_memblock_size)
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 6374b2196a17..f6dbb4c20e64 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -99,20 +99,6 @@ void free_initmem(void)
 		((unsigned long)__init_end - (unsigned long)__init_begin) >> 10);
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	if (start < end)
-		printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
-	for (; start < end; start += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(start));
-		init_page_count(virt_to_page(start));
-		free_page(start);
-		totalram_pages++;
-	}
-}
-#endif
-
 static void pgd_ctor(void *addr)
 {
 	memset(addr, 0, PGD_TABLE_SIZE);
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 57e545b84bf1..29d4dde65c45 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -382,6 +382,25 @@ void __init mem_init(void)
 	mem_init_done = 1;
 }
 
+#ifdef CONFIG_BLK_DEV_INITRD
+void __init free_initrd_mem(unsigned long start, unsigned long end)
+{
+	if (start >= end)
+		return;
+
+	start = _ALIGN_DOWN(start, PAGE_SIZE);
+	end = _ALIGN_UP(end, PAGE_SIZE);
+	pr_info("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
+
+	for (; start < end; start += PAGE_SIZE) {
+		ClearPageReserved(virt_to_page(start));
+		init_page_count(virt_to_page(start));
+		free_page(start);
+		totalram_pages++;
+	}
+}
+#endif
+
 /*
  * This is called when a page has been modified by the kernel.
  * It just marks the page as not i-cache clean.  We do the i-cache
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 6a3997f98dfb..af40c8768a78 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -33,110 +33,6 @@
 
 #include "mmu_decl.h"
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
-#ifdef CONFIG_SMP
-
-/*
- * Handle batching of page table freeing on SMP. Page tables are
- * queued up and send to be freed later by RCU in order to avoid
- * freeing a page table page that is being walked without locks
- */
-
-static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
-static unsigned long pte_freelist_forced_free;
-
-struct pte_freelist_batch
-{
-	struct rcu_head	rcu;
-	unsigned int	index;
-	unsigned long	tables[0];
-};
-
-#define PTE_FREELIST_SIZE \
-	((PAGE_SIZE - sizeof(struct pte_freelist_batch)) \
-	  / sizeof(unsigned long))
-
-static void pte_free_smp_sync(void *arg)
-{
-	/* Do nothing, just ensure we sync with all CPUs */
-}
-
-/* This is only called when we are critically out of memory
- * (and fail to get a page in pte_free_tlb).
- */
-static void pgtable_free_now(void *table, unsigned shift)
-{
-	pte_freelist_forced_free++;
-
-	smp_call_function(pte_free_smp_sync, NULL, 1);
-
-	pgtable_free(table, shift);
-}
-
-static void pte_free_rcu_callback(struct rcu_head *head)
-{
-	struct pte_freelist_batch *batch =
-		container_of(head, struct pte_freelist_batch, rcu);
-	unsigned int i;
-
-	for (i = 0; i < batch->index; i++) {
-		void *table = (void *)(batch->tables[i] & ~MAX_PGTABLE_INDEX_SIZE);
-		unsigned shift = batch->tables[i] & MAX_PGTABLE_INDEX_SIZE;
-
-		pgtable_free(table, shift);
-	}
-
-	free_page((unsigned long)batch);
-}
-
-static void pte_free_submit(struct pte_freelist_batch *batch)
-{
-	call_rcu_sched(&batch->rcu, pte_free_rcu_callback);
-}
-
-void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
-{
-	/* This is safe since tlb_gather_mmu has disabled preemption */
-	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
-	unsigned long pgf;
-
-	if (atomic_read(&tlb->mm->mm_users) < 2 ||
-	    cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))){
-		pgtable_free(table, shift);
-		return;
-	}
-
-	if (*batchp == NULL) {
-		*batchp = (struct pte_freelist_batch *)__get_free_page(GFP_ATOMIC);
-		if (*batchp == NULL) {
-			pgtable_free_now(table, shift);
-			return;
-		}
-		(*batchp)->index = 0;
-	}
-	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
-	pgf = (unsigned long)table | shift;
-	(*batchp)->tables[(*batchp)->index++] = pgf;
-	if ((*batchp)->index == PTE_FREELIST_SIZE) {
-		pte_free_submit(*batchp);
-		*batchp = NULL;
-	}
-}
-
-void pte_free_finish(void)
-{
-	/* This is safe since tlb_gather_mmu has disabled preemption */
-	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
-
-	if (*batchp == NULL)
-		return;
-	pte_free_submit(*batchp);
-	*batchp = NULL;
-}
-
-#endif /* CONFIG_SMP */
-
 static inline int is_exec_fault(void)
 {
 	return current->thread.regs && TRAP(current->thread.regs) == 0x400;
diff --git a/arch/powerpc/mm/tlb_hash32.c b/arch/powerpc/mm/tlb_hash32.c
index 690566b66e8e..27b863c14941 100644
--- a/arch/powerpc/mm/tlb_hash32.c
+++ b/arch/powerpc/mm/tlb_hash32.c
@@ -71,9 +71,6 @@ void tlb_flush(struct mmu_gather *tlb)
 		 */
 		_tlbia();
 	}
-
-	/* Push out batch of freed page tables */
-	pte_free_finish();
 }
 
 /*
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index c14d09f614f3..31f18207970b 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -155,7 +155,7 @@ void __flush_tlb_pending(struct ppc64_tlb_batch *batch)
 
 void tlb_flush(struct mmu_gather *tlb)
 {
-	struct ppc64_tlb_batch *tlbbatch = &__get_cpu_var(ppc64_tlb_batch);
+	struct ppc64_tlb_batch *tlbbatch = &get_cpu_var(ppc64_tlb_batch);
 
 	/* If there's a TLB batch pending, then we must flush it because the
 	 * pages are going to be freed and we really don't want to have a CPU
@@ -164,8 +164,7 @@ void tlb_flush(struct mmu_gather *tlb)
 	if (tlbbatch->index)
 		__flush_tlb_pending(tlbbatch);
 
-	/* Push out batch of freed page tables */
-	pte_free_finish();
+	put_cpu_var(ppc64_tlb_batch);
 }
 
 /**
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 2a030d89bbc6..0bdad3aecc67 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -299,9 +299,6 @@ EXPORT_SYMBOL(flush_tlb_range);
 void tlb_flush(struct mmu_gather *tlb)
 {
 	flush_tlb_mm(tlb->mm);
-
-	/* Push out batch of freed page tables */
-	pte_free_finish();
 }
 
 /*
diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c
index 8ee51a252cf1..e6bec74be131 100644
--- a/arch/powerpc/oprofile/op_model_power4.c
+++ b/arch/powerpc/oprofile/op_model_power4.c
@@ -261,6 +261,28 @@ static int get_kernel(unsigned long pc, unsigned long mmcra)
 	return is_kernel;
 }
 
+static bool pmc_overflow(unsigned long val)
+{
+	if ((int)val < 0)
+		return true;
+
+	/*
+	 * Events on POWER7 can roll back if a speculative event doesn't
+	 * eventually complete. Unfortunately in some rare cases they will
+	 * raise a performance monitor exception. We need to catch this to
+	 * ensure we reset the PMC. In all cases the PMC will be 256 or less
+	 * cycles from overflow.
+	 *
+	 * We only do this if the first pass fails to find any overflowing
+	 * PMCs because a user might set a period of less than 256 and we
+	 * don't want to mistakenly reset them.
+	 */
+	if (__is_processor(PV_POWER7) && ((0x80000000 - val) <= 256))
+		return true;
+
+	return false;
+}
+
 static void power4_handle_interrupt(struct pt_regs *regs,
 				    struct op_counter_config *ctr)
 {
@@ -281,7 +303,7 @@ static void power4_handle_interrupt(struct pt_regs *regs,
 
 	for (i = 0; i < cur_cpu_spec->num_pmcs; ++i) {
 		val = classic_ctr_read(i);
-		if (val < 0) {
+		if (pmc_overflow(val)) {
 			if (oprofile_running && ctr[i].enabled) {
 				oprofile_add_ext_sample(pc, regs, i, is_kernel);
 				classic_ctr_write(i, reset_value[i]);
diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig
index b72176434ebe..d733d7ca939c 100644
--- a/arch/powerpc/platforms/40x/Kconfig
+++ b/arch/powerpc/platforms/40x/Kconfig
@@ -57,6 +57,8 @@ config KILAUEA
 	select 405EX
 	select PPC40x_SIMPLE
 	select PPC4xx_PCI_EXPRESS
+	select PCI_MSI
+	select PPC4xx_MSI
 	help
 	  This option enables support for the AMCC PPC405EX evaluation board.
 
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index f485fc5f6d5e..e958b6f48ec2 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -74,6 +74,8 @@ config KATMAI
 	select 440SPe
 	select PCI
 	select PPC4xx_PCI_EXPRESS
+	select PCI_MSI
+	select PCC4xx_MSI
 	help
 	  This option enables support for the AMCC PPC440SPe evaluation board.
 
@@ -118,6 +120,8 @@ config CANYONLANDS
 	select 460EX
 	select PCI
 	select PPC4xx_PCI_EXPRESS
+	select PCI_MSI
+	select PPC4xx_MSI
 	select IBM_NEW_EMAC_RGMII
 	select IBM_NEW_EMAC_ZMII
 	help
@@ -144,6 +148,8 @@ config REDWOOD
 	select 460SX
 	select PCI
 	select PPC4xx_PCI_EXPRESS
+	select PCI_MSI
+	select PPC4xx_MSI
 	help
 	  This option enables support for the AMCC PPC460SX Redwood board.
 
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 449c08c15862..3e4eba603e6b 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -176,14 +176,14 @@ EXPORT_SYMBOL_GPL(iic_get_target_id);
 #ifdef CONFIG_SMP
 
 /* Use the highest interrupt priorities for IPI */
-static inline int iic_ipi_to_irq(int ipi)
+static inline int iic_msg_to_irq(int msg)
 {
-	return IIC_IRQ_TYPE_IPI + 0xf - ipi;
+	return IIC_IRQ_TYPE_IPI + 0xf - msg;
 }
 
-void iic_cause_IPI(int cpu, int mesg)
+void iic_message_pass(int cpu, int msg)
 {
-	out_be64(&per_cpu(cpu_iic, cpu).regs->generate, (0xf - mesg) << 4);
+	out_be64(&per_cpu(cpu_iic, cpu).regs->generate, (0xf - msg) << 4);
 }
 
 struct irq_host *iic_get_irq_host(int node)
@@ -192,50 +192,31 @@ struct irq_host *iic_get_irq_host(int node)
 }
 EXPORT_SYMBOL_GPL(iic_get_irq_host);
 
-static irqreturn_t iic_ipi_action(int irq, void *dev_id)
-{
-	int ipi = (int)(long)dev_id;
-
-	switch(ipi) {
-	case PPC_MSG_CALL_FUNCTION:
-		generic_smp_call_function_interrupt();
-		break;
-	case PPC_MSG_RESCHEDULE:
-		scheduler_ipi();
-		break;
-	case PPC_MSG_CALL_FUNC_SINGLE:
-		generic_smp_call_function_single_interrupt();
-		break;
-	case PPC_MSG_DEBUGGER_BREAK:
-		debug_ipi_action(0, NULL);
-		break;
-	}
-	return IRQ_HANDLED;
-}
-static void iic_request_ipi(int ipi, const char *name)
+static void iic_request_ipi(int msg)
 {
 	int virq;
 
-	virq = irq_create_mapping(iic_host, iic_ipi_to_irq(ipi));
+	virq = irq_create_mapping(iic_host, iic_msg_to_irq(msg));
 	if (virq == NO_IRQ) {
 		printk(KERN_ERR
-		       "iic: failed to map IPI %s\n", name);
+		       "iic: failed to map IPI %s\n", smp_ipi_name[msg]);
 		return;
 	}
-	if (request_irq(virq, iic_ipi_action, IRQF_DISABLED, name,
-			(void *)(long)ipi))
-		printk(KERN_ERR
-		       "iic: failed to request IPI %s\n", name);
+
+	/*
+	 * If smp_request_message_ipi encounters an error it will notify
+	 * the error.  If a message is not needed it will return non-zero.
+	 */
+	if (smp_request_message_ipi(virq, msg))
+		irq_dispose_mapping(virq);
 }
 
 void iic_request_IPIs(void)
 {
-	iic_request_ipi(PPC_MSG_CALL_FUNCTION, "IPI-call");
-	iic_request_ipi(PPC_MSG_RESCHEDULE, "IPI-resched");
-	iic_request_ipi(PPC_MSG_CALL_FUNC_SINGLE, "IPI-call-single");
-#ifdef CONFIG_DEBUGGER
-	iic_request_ipi(PPC_MSG_DEBUGGER_BREAK, "IPI-debug");
-#endif /* CONFIG_DEBUGGER */
+	iic_request_ipi(PPC_MSG_CALL_FUNCTION);
+	iic_request_ipi(PPC_MSG_RESCHEDULE);
+	iic_request_ipi(PPC_MSG_CALL_FUNC_SINGLE);
+	iic_request_ipi(PPC_MSG_DEBUGGER_BREAK);
 }
 
 #endif /* CONFIG_SMP */
diff --git a/arch/powerpc/platforms/cell/interrupt.h b/arch/powerpc/platforms/cell/interrupt.h
index 942dc39d6045..4f60ae6ca358 100644
--- a/arch/powerpc/platforms/cell/interrupt.h
+++ b/arch/powerpc/platforms/cell/interrupt.h
@@ -75,7 +75,7 @@ enum {
 };
 
 extern void iic_init_IRQ(void);
-extern void iic_cause_IPI(int cpu, int mesg);
+extern void iic_message_pass(int cpu, int msg);
 extern void iic_request_IPIs(void);
 extern void iic_setup_cpu(void);
 
diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c
index d176e6148e3f..dbb641ea90dd 100644
--- a/arch/powerpc/platforms/cell/smp.c
+++ b/arch/powerpc/platforms/cell/smp.c
@@ -152,7 +152,7 @@ static int smp_cell_cpu_bootable(unsigned int nr)
 	return 1;
 }
 static struct smp_ops_t bpa_iic_smp_ops = {
-	.message_pass	= iic_cause_IPI,
+	.message_pass	= iic_message_pass,
 	.probe		= smp_iic_probe,
 	.kick_cpu	= smp_cell_kick_cpu,
 	.setup_cpu	= smp_cell_setup_cpu,
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 9089b0421191..7667db448aa7 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -715,7 +715,8 @@ static struct syscore_ops pmacpic_syscore_ops = {
 
 static int __init init_pmacpic_syscore(void)
 {
-	register_syscore_ops(&pmacpic_syscore_ops);
+	if (pmac_irq_hw[0])
+		register_syscore_ops(&pmacpic_syscore_ops);
 	return 0;
 }
 
diff --git a/arch/powerpc/sysdev/Kconfig b/arch/powerpc/sysdev/Kconfig
index d775fd148d13..7b4df37ac381 100644
--- a/arch/powerpc/sysdev/Kconfig
+++ b/arch/powerpc/sysdev/Kconfig
@@ -7,11 +7,18 @@ config PPC4xx_PCI_EXPRESS
 	depends on PCI && 4xx
 	default n
 
+config PPC4xx_MSI
+	bool
+	depends on PCI_MSI
+	depends on PCI && 4xx
+	default n
+
 config PPC_MSI_BITMAP
 	bool
 	depends on PCI_MSI
 	default y if MPIC
 	default y if FSL_PCI
+	default y if PPC4xx_MSI
 
 source "arch/powerpc/sysdev/xics/Kconfig"
 
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index 6076e0074a87..0efa990e3344 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -41,6 +41,7 @@ obj-$(CONFIG_OF_RTC)		+= of_rtc.o
 ifeq ($(CONFIG_PCI),y)
 obj-$(CONFIG_4xx)		+= ppc4xx_pci.o
 endif
+obj-$(CONFIG_PPC4xx_MSI)	+= ppc4xx_msi.o
 obj-$(CONFIG_PPC4xx_CPM)	+= ppc4xx_cpm.o
 obj-$(CONFIG_PPC4xx_GPIO)	+= ppc4xx_gpio.o
 
diff --git a/arch/powerpc/sysdev/fsl_lbc.c b/arch/powerpc/sysdev/fsl_lbc.c
index 4fcb5a4e60dd..d917573cf1a8 100644
--- a/arch/powerpc/sysdev/fsl_lbc.c
+++ b/arch/powerpc/sysdev/fsl_lbc.c
@@ -184,7 +184,8 @@ int fsl_upm_run_pattern(struct fsl_upm *upm, void __iomem *io_base, u32 mar)
 }
 EXPORT_SYMBOL(fsl_upm_run_pattern);
 
-static int __devinit fsl_lbc_ctrl_init(struct fsl_lbc_ctrl *ctrl)
+static int __devinit fsl_lbc_ctrl_init(struct fsl_lbc_ctrl *ctrl,
+				       struct device_node *node)
 {
 	struct fsl_lbc_regs __iomem *lbc = ctrl->regs;
 
@@ -195,8 +196,9 @@ static int __devinit fsl_lbc_ctrl_init(struct fsl_lbc_ctrl *ctrl)
 	out_be32(&lbc->lteccr, LTECCR_CLEAR);
 	out_be32(&lbc->ltedr, LTEDR_ENABLE);
 
-	/* Enable interrupts for any detected events */
-	out_be32(&lbc->lteir, LTEIR_ENABLE);
+	/* Set the monitor timeout value to the maximum for erratum A001 */
+	if (of_device_is_compatible(node, "fsl,elbc"))
+		clrsetbits_be32(&lbc->lbcr, LBCR_BMT, LBCR_BMTPS);
 
 	return 0;
 }
@@ -304,7 +306,7 @@ static int __devinit fsl_lbc_ctrl_probe(struct platform_device *dev)
 
 	fsl_lbc_ctrl_dev->dev = &dev->dev;
 
-	ret = fsl_lbc_ctrl_init(fsl_lbc_ctrl_dev);
+	ret = fsl_lbc_ctrl_init(fsl_lbc_ctrl_dev, dev->dev.of_node);
 	if (ret < 0)
 		goto err;
 
@@ -317,6 +319,9 @@ static int __devinit fsl_lbc_ctrl_probe(struct platform_device *dev)
 		goto err;
 	}
 
+	/* Enable interrupts for any detected events */
+	out_be32(&fsl_lbc_ctrl_dev->regs->lteir, LTEIR_ENABLE);
+
 	return 0;
 
 err:
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index 49798532b477..5b206a2fe17c 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -10,7 +10,7 @@
  * - Added Port-Write message handling
  * - Added Machine Check exception handling
  *
- * Copyright (C) 2007, 2008 Freescale Semiconductor, Inc.
+ * Copyright (C) 2007, 2008, 2010 Freescale Semiconductor, Inc.
  * Zhang Wei <wei.zhang@freescale.com>
  *
  * Copyright 2005 MontaVista Software, Inc.
@@ -47,15 +47,33 @@
 #define IRQ_RIO_RX(m)		(((struct rio_priv *)(m->priv))->rxirq)
 #define IRQ_RIO_PW(m)		(((struct rio_priv *)(m->priv))->pwirq)
 
+#define IPWSR_CLEAR		0x98
+#define OMSR_CLEAR		0x1cb3
+#define IMSR_CLEAR		0x491
+#define IDSR_CLEAR		0x91
+#define ODSR_CLEAR		0x1c00
+#define LTLEECSR_ENABLE_ALL	0xFFC000FC
+#define ESCSR_CLEAR		0x07120204
+
+#define RIO_PORT1_EDCSR		0x0640
+#define RIO_PORT2_EDCSR		0x0680
+#define RIO_PORT1_IECSR		0x10130
+#define RIO_PORT2_IECSR		0x101B0
+#define RIO_IM0SR		0x13064
+#define RIO_IM1SR		0x13164
+#define RIO_OM0SR		0x13004
+#define RIO_OM1SR		0x13104
+
 #define RIO_ATMU_REGS_OFFSET	0x10c00
 #define RIO_P_MSG_REGS_OFFSET	0x11000
 #define RIO_S_MSG_REGS_OFFSET	0x13000
 #define RIO_GCCSR		0x13c
 #define RIO_ESCSR		0x158
+#define RIO_PORT2_ESCSR		0x178
 #define RIO_CCSR		0x15c
 #define RIO_LTLEDCSR		0x0608
-#define  RIO_LTLEDCSR_IER	0x80000000
-#define  RIO_LTLEDCSR_PRT	0x01000000
+#define RIO_LTLEDCSR_IER	0x80000000
+#define RIO_LTLEDCSR_PRT	0x01000000
 #define RIO_LTLEECSR		0x060c
 #define RIO_EPWISR		0x10010
 #define RIO_ISR_AACR		0x10120
@@ -88,7 +106,10 @@
 #define RIO_IPWSR_PWD		0x00000008
 #define RIO_IPWSR_PWB		0x00000004
 
-#define RIO_EPWISR_PINT		0x80000000
+/* EPWISR Error match value */
+#define RIO_EPWISR_PINT1	0x80000000
+#define RIO_EPWISR_PINT2	0x40000000
+#define RIO_EPWISR_MU		0x00000002
 #define RIO_EPWISR_PW		0x00000001
 
 #define RIO_MSG_DESC_SIZE	32
@@ -260,9 +281,7 @@ struct rio_priv {
 static void __iomem *rio_regs_win;
 
 #ifdef CONFIG_E500
-static int (*saved_mcheck_exception)(struct pt_regs *regs);
-
-static int fsl_rio_mcheck_exception(struct pt_regs *regs)
+int fsl_rio_mcheck_exception(struct pt_regs *regs)
 {
 	const struct exception_table_entry *entry = NULL;
 	unsigned long reason = mfspr(SPRN_MCSR);
@@ -284,11 +303,9 @@ static int fsl_rio_mcheck_exception(struct pt_regs *regs)
 		}
 	}
 
-	if (saved_mcheck_exception)
-		return saved_mcheck_exception(regs);
-	else
-		return cur_cpu_spec->machine_check(regs);
+	return 0;
 }
+EXPORT_SYMBOL_GPL(fsl_rio_mcheck_exception);
 #endif
 
 /**
@@ -1064,6 +1081,40 @@ static int fsl_rio_doorbell_init(struct rio_mport *mport)
 	return rc;
 }
 
+static void port_error_handler(struct rio_mport *port, int offset)
+{
+	/*XXX: Error recovery is not implemented, we just clear errors */
+	out_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR), 0);
+
+	if (offset == 0) {
+		out_be32((u32 *)(rio_regs_win + RIO_PORT1_EDCSR), 0);
+		out_be32((u32 *)(rio_regs_win + RIO_PORT1_IECSR), 0);
+		out_be32((u32 *)(rio_regs_win + RIO_ESCSR), ESCSR_CLEAR);
+	} else {
+		out_be32((u32 *)(rio_regs_win + RIO_PORT2_EDCSR), 0);
+		out_be32((u32 *)(rio_regs_win + RIO_PORT2_IECSR), 0);
+		out_be32((u32 *)(rio_regs_win + RIO_PORT2_ESCSR), ESCSR_CLEAR);
+	}
+}
+
+static void msg_unit_error_handler(struct rio_mport *port)
+{
+	struct rio_priv *priv = port->priv;
+
+	/*XXX: Error recovery is not implemented, we just clear errors */
+	out_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR), 0);
+
+	out_be32((u32 *)(rio_regs_win + RIO_IM0SR), IMSR_CLEAR);
+	out_be32((u32 *)(rio_regs_win + RIO_IM1SR), IMSR_CLEAR);
+	out_be32((u32 *)(rio_regs_win + RIO_OM0SR), OMSR_CLEAR);
+	out_be32((u32 *)(rio_regs_win + RIO_OM1SR), OMSR_CLEAR);
+
+	out_be32(&priv->msg_regs->odsr, ODSR_CLEAR);
+	out_be32(&priv->msg_regs->dsr, IDSR_CLEAR);
+
+	out_be32(&priv->msg_regs->pwsr, IPWSR_CLEAR);
+}
+
 /**
  * fsl_rio_port_write_handler - MPC85xx port write interrupt handler
  * @irq: Linux interrupt number
@@ -1144,10 +1195,22 @@ fsl_rio_port_write_handler(int irq, void *dev_instance)
 	}
 
 pw_done:
-	if (epwisr & RIO_EPWISR_PINT) {
+	if (epwisr & RIO_EPWISR_PINT1) {
+		tmp = in_be32(priv->regs_win + RIO_LTLEDCSR);
+		pr_debug("RIO_LTLEDCSR = 0x%x\n", tmp);
+		port_error_handler(port, 0);
+	}
+
+	if (epwisr & RIO_EPWISR_PINT2) {
 		tmp = in_be32(priv->regs_win + RIO_LTLEDCSR);
 		pr_debug("RIO_LTLEDCSR = 0x%x\n", tmp);
-		out_be32(priv->regs_win + RIO_LTLEDCSR, 0);
+		port_error_handler(port, 1);
+	}
+
+	if (epwisr & RIO_EPWISR_MU) {
+		tmp = in_be32(priv->regs_win + RIO_LTLEDCSR);
+		pr_debug("RIO_LTLEDCSR = 0x%x\n", tmp);
+		msg_unit_error_handler(port);
 	}
 
 	return IRQ_HANDLED;
@@ -1258,12 +1321,14 @@ static int fsl_rio_port_write_init(struct rio_mport *mport)
 
 
 	/* Hook up port-write handler */
-	rc = request_irq(IRQ_RIO_PW(mport), fsl_rio_port_write_handler, 0,
-			 "port-write", (void *)mport);
+	rc = request_irq(IRQ_RIO_PW(mport), fsl_rio_port_write_handler,
+			IRQF_SHARED, "port-write", (void *)mport);
 	if (rc < 0) {
 		pr_err("MPC85xx RIO: unable to request inbound doorbell irq");
 		goto err_out;
 	}
+	/* Enable Error Interrupt */
+	out_be32((u32 *)(rio_regs_win + RIO_LTLEECSR), LTLEECSR_ENABLE_ALL);
 
 	INIT_WORK(&priv->pw_work, fsl_pw_dpc);
 	spin_lock_init(&priv->pw_fifo_lock);
@@ -1538,11 +1603,6 @@ int fsl_rio_setup(struct platform_device *dev)
 	fsl_rio_doorbell_init(port);
 	fsl_rio_port_write_init(port);
 
-#ifdef CONFIG_E500
-	saved_mcheck_exception = ppc_md.machine_check_exception;
-	ppc_md.machine_check_exception = fsl_rio_mcheck_exception;
-#endif
-
 	return 0;
 err:
 	iounmap(priv->regs_win);
diff --git a/arch/powerpc/sysdev/ppc4xx_msi.c b/arch/powerpc/sysdev/ppc4xx_msi.c
new file mode 100644
index 000000000000..367af0241851
--- /dev/null
+++ b/arch/powerpc/sysdev/ppc4xx_msi.c
@@ -0,0 +1,276 @@
+/*
+ * Adding PCI-E MSI support for PPC4XX SoCs.
+ *
+ * Copyright (c) 2010, Applied Micro Circuits Corporation
+ * Authors:	Tirumala R Marri <tmarri@apm.com>
+ *		Feng Kan <fkan@apm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+ * MA 02111-1307 USA
+ */
+
+#include <linux/irq.h>
+#include <linux/bootmem.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <linux/of_platform.h>
+#include <linux/interrupt.h>
+#include <asm/prom.h>
+#include <asm/hw_irq.h>
+#include <asm/ppc-pci.h>
+#include <boot/dcr.h>
+#include <asm/dcr-regs.h>
+#include <asm/msi_bitmap.h>
+
+#define PEIH_TERMADH	0x00
+#define PEIH_TERMADL	0x08
+#define PEIH_MSIED	0x10
+#define PEIH_MSIMK	0x18
+#define PEIH_MSIASS	0x20
+#define PEIH_FLUSH0	0x30
+#define PEIH_FLUSH1	0x38
+#define PEIH_CNTRST	0x48
+#define NR_MSI_IRQS	4
+
+struct ppc4xx_msi {
+	u32 msi_addr_lo;
+	u32 msi_addr_hi;
+	void __iomem *msi_regs;
+	int msi_virqs[NR_MSI_IRQS];
+	struct msi_bitmap bitmap;
+	struct device_node *msi_dev;
+};
+
+static struct ppc4xx_msi ppc4xx_msi;
+
+static int ppc4xx_msi_init_allocator(struct platform_device *dev,
+		struct ppc4xx_msi *msi_data)
+{
+	int err;
+
+	err = msi_bitmap_alloc(&msi_data->bitmap, NR_MSI_IRQS,
+			      dev->dev.of_node);
+	if (err)
+		return err;
+
+	err = msi_bitmap_reserve_dt_hwirqs(&msi_data->bitmap);
+	if (err < 0) {
+		msi_bitmap_free(&msi_data->bitmap);
+		return err;
+	}
+
+	return 0;
+}
+
+static int ppc4xx_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	int int_no = -ENOMEM;
+	unsigned int virq;
+	struct msi_msg msg;
+	struct msi_desc *entry;
+	struct ppc4xx_msi *msi_data = &ppc4xx_msi;
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		int_no = msi_bitmap_alloc_hwirqs(&msi_data->bitmap, 1);
+		if (int_no >= 0)
+			break;
+		if (int_no < 0) {
+			pr_debug("%s: fail allocating msi interrupt\n",
+					__func__);
+		}
+		virq = irq_of_parse_and_map(msi_data->msi_dev, int_no);
+		if (virq == NO_IRQ) {
+			dev_err(&dev->dev, "%s: fail mapping irq\n", __func__);
+			msi_bitmap_free_hwirqs(&msi_data->bitmap, int_no, 1);
+			return -ENOSPC;
+		}
+		dev_dbg(&dev->dev, "%s: virq = %d\n", __func__, virq);
+
+		/* Setup msi address space */
+		msg.address_hi = msi_data->msi_addr_hi;
+		msg.address_lo = msi_data->msi_addr_lo;
+
+		irq_set_msi_desc(virq, entry);
+		msg.data = int_no;
+		write_msi_msg(virq, &msg);
+	}
+	return 0;
+}
+
+void ppc4xx_teardown_msi_irqs(struct pci_dev *dev)
+{
+	struct msi_desc *entry;
+	struct ppc4xx_msi *msi_data = &ppc4xx_msi;
+
+	dev_dbg(&dev->dev, "PCIE-MSI: tearing down msi irqs\n");
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		if (entry->irq == NO_IRQ)
+			continue;
+		irq_set_msi_desc(entry->irq, NULL);
+		msi_bitmap_free_hwirqs(&msi_data->bitmap,
+				virq_to_hw(entry->irq), 1);
+		irq_dispose_mapping(entry->irq);
+	}
+}
+
+static int ppc4xx_msi_check_device(struct pci_dev *pdev, int nvec, int type)
+{
+	dev_dbg(&pdev->dev, "PCIE-MSI:%s called. vec %x type %d\n",
+		__func__, nvec, type);
+	if (type == PCI_CAP_ID_MSIX)
+		pr_debug("ppc4xx msi: MSI-X untested, trying anyway.\n");
+
+	return 0;
+}
+
+static int ppc4xx_setup_pcieh_hw(struct platform_device *dev,
+				 struct resource res, struct ppc4xx_msi *msi)
+{
+	const u32 *msi_data;
+	const u32 *msi_mask;
+	const u32 *sdr_addr;
+	dma_addr_t msi_phys;
+	void *msi_virt;
+
+	sdr_addr = of_get_property(dev->dev.of_node, "sdr-base", NULL);
+	if (!sdr_addr)
+		return -1;
+
+	SDR0_WRITE(sdr_addr, (u64)res.start >> 32);	 /*HIGH addr */
+	SDR0_WRITE(sdr_addr + 1, res.start & 0xFFFFFFFF); /* Low addr */
+
+
+	msi->msi_dev = of_find_node_by_name(NULL, "ppc4xx-msi");
+	if (msi->msi_dev)
+		return -ENODEV;
+
+	msi->msi_regs = of_iomap(msi->msi_dev, 0);
+	if (!msi->msi_regs) {
+		dev_err(&dev->dev, "of_iomap problem failed\n");
+		return -ENOMEM;
+	}
+	dev_dbg(&dev->dev, "PCIE-MSI: msi register mapped 0x%x 0x%x\n",
+		(u32) (msi->msi_regs + PEIH_TERMADH), (u32) (msi->msi_regs));
+
+	msi_virt = dma_alloc_coherent(&dev->dev, 64, &msi_phys, GFP_KERNEL);
+	msi->msi_addr_hi = 0x0;
+	msi->msi_addr_lo = (u32) msi_phys;
+	dev_dbg(&dev->dev, "PCIE-MSI: msi address 0x%x\n", msi->msi_addr_lo);
+
+	/* Progam the Interrupt handler Termination addr registers */
+	out_be32(msi->msi_regs + PEIH_TERMADH, msi->msi_addr_hi);
+	out_be32(msi->msi_regs + PEIH_TERMADL, msi->msi_addr_lo);
+
+	msi_data = of_get_property(dev->dev.of_node, "msi-data", NULL);
+	if (!msi_data)
+		return -1;
+	msi_mask = of_get_property(dev->dev.of_node, "msi-mask", NULL);
+	if (!msi_mask)
+		return -1;
+	/* Program MSI Expected data and Mask bits */
+	out_be32(msi->msi_regs + PEIH_MSIED, *msi_data);
+	out_be32(msi->msi_regs + PEIH_MSIMK, *msi_mask);
+
+	return 0;
+}
+
+static int ppc4xx_of_msi_remove(struct platform_device *dev)
+{
+	struct ppc4xx_msi *msi = dev->dev.platform_data;
+	int i;
+	int virq;
+
+	for (i = 0; i < NR_MSI_IRQS; i++) {
+		virq = msi->msi_virqs[i];
+		if (virq != NO_IRQ)
+			irq_dispose_mapping(virq);
+	}
+
+	if (msi->bitmap.bitmap)
+		msi_bitmap_free(&msi->bitmap);
+	iounmap(msi->msi_regs);
+	of_node_put(msi->msi_dev);
+	kfree(msi);
+
+	return 0;
+}
+
+static int __devinit ppc4xx_msi_probe(struct platform_device *dev)
+{
+	struct ppc4xx_msi *msi;
+	struct resource res;
+	int err = 0;
+
+	msi = &ppc4xx_msi;/*keep the msi data for further use*/
+
+	dev_dbg(&dev->dev, "PCIE-MSI: Setting up MSI support...\n");
+
+	msi = kzalloc(sizeof(struct ppc4xx_msi), GFP_KERNEL);
+	if (!msi) {
+		dev_err(&dev->dev, "No memory for MSI structure\n");
+		return -ENOMEM;
+	}
+	dev->dev.platform_data = msi;
+
+	/* Get MSI ranges */
+	err = of_address_to_resource(dev->dev.of_node, 0, &res);
+	if (err) {
+		dev_err(&dev->dev, "%s resource error!\n",
+			dev->dev.of_node->full_name);
+		goto error_out;
+	}
+
+	if (ppc4xx_setup_pcieh_hw(dev, res, msi))
+		goto error_out;
+
+	err = ppc4xx_msi_init_allocator(dev, msi);
+	if (err) {
+		dev_err(&dev->dev, "Error allocating MSI bitmap\n");
+		goto error_out;
+	}
+
+	ppc_md.setup_msi_irqs = ppc4xx_setup_msi_irqs;
+	ppc_md.teardown_msi_irqs = ppc4xx_teardown_msi_irqs;
+	ppc_md.msi_check_device = ppc4xx_msi_check_device;
+	return err;
+
+error_out:
+	ppc4xx_of_msi_remove(dev);
+	return err;
+}
+static const struct of_device_id ppc4xx_msi_ids[] = {
+	{
+		.compatible = "amcc,ppc4xx-msi",
+	},
+	{}
+};
+static struct platform_driver ppc4xx_msi_driver = {
+	.probe = ppc4xx_msi_probe,
+	.remove = ppc4xx_of_msi_remove,
+	.driver = {
+		   .name = "ppc4xx-msi",
+		   .owner = THIS_MODULE,
+		   .of_match_table = ppc4xx_msi_ids,
+		   },
+
+};
+
+static __init int ppc4xx_msi_init(void)
+{
+	return platform_driver_register(&ppc4xx_msi_driver);
+}
+
+subsys_initcall(ppc4xx_msi_init);