Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (151 commits)
  powerpc: Fix usage of 64-bit instruction in 32-bit altivec code
  MAINTAINERS: Add PowerPC patterns
  powerpc/pseries: Track previous CPPR values to correctly EOI interrupts
  powerpc/pseries: Correct pseries/dlpar.c build break without CONFIG_SMP
  powerpc: Make "intspec" pointers in irq_host->xlate() const
  powerpc/8xx: DTLB Miss cleanup
  powerpc/8xx: Remove DIRTY pte handling in DTLB Error.
  powerpc/8xx: Start using dcbX instructions in various copy routines
  powerpc/8xx: Restore _PAGE_WRITETHRU
  powerpc/8xx: Add missing Guarded setting in DTLB Error.
  powerpc/8xx: Fixup DAR from buggy dcbX instructions.
  powerpc/8xx: Tag DAR with 0x00f0 to catch buggy instructions.
  powerpc/8xx: Update TLB asm so it behaves as linux mm expects.
  powerpc/8xx: Invalidate non present TLBs
  powerpc/pseries: Serialize cpu hotplug operations during deactivate Vs deallocate
  pseries/pseries: Add code to online/offline CPUs of a DLPAR node
  powerpc: stop_this_cpu: remove the cpu from the online map.
  powerpc/pseries: Add kernel based CPU DLPAR handling
  sysfs/cpu: Add probe/release files
  powerpc/pseries: Kernel DLPAR Infrastructure
  ...

arch/powerpc/include/asm/page_64.h

@@ -90,7 +90,7 @@ extern unsigned int HPAGE_SHIFT;
 #define HPAGE_SIZE		((1UL) << HPAGE_SHIFT)
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
-#define HUGE_MAX_HSTATE		3
+#define HUGE_MAX_HSTATE		(MMU_PAGE_COUNT-1)
 
 #endif /* __ASSEMBLY__ */
 

arch/powerpc/include/asm/pgalloc-32.h

@@ -3,7 +3,8 @@
 
 #include <linux/threads.h>
 
-#define PTE_NONCACHE_NUM	0  /* dummy for now to share code w/ppc64 */
+/* For 32-bit, all levels of page tables are just drawn from get_free_page() */
+#define MAX_PGTABLE_INDEX_SIZE	0
 
 extern void __bad_pte(pmd_t *pmd);
 
@@ -36,11 +37,10 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
 extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr);
 
-static inline void pgtable_free(pgtable_free_t pgf)
+static inline void pgtable_free(void *table, unsigned index_size)
 {
-	void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
-
-	free_page((unsigned long)p);
+	BUG_ON(index_size); /* 32-bit doesn't use this */
+	free_page((unsigned long)table);
 }
 
 #define check_pgt_cache()	do { } while (0)

arch/powerpc/include/asm/pgalloc-64.h

@@ -11,27 +11,34 @@
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
 
-#ifndef CONFIG_PPC_SUBPAGE_PROT
-static inline void subpage_prot_free(pgd_t *pgd) {}
-#endif
+/*
+ * Functions that deal with pagetables that could be at any level of
+ * the table need to be passed an "index_size" so they know how to
+ * handle allocation.  For PTE pages (which are linked to a struct
+ * page for now, and drawn from the main get_free_pages() pool), the
+ * allocation size will be (2^index_size * sizeof(pointer)) and
+ * allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
+ *
+ * The maximum index size needs to be big enough to allow any
+ * pagetable sizes we need, but small enough to fit in the low bits of
+ * any page table pointer.  In other words all pagetables, even tiny
+ * ones, must be aligned to allow at least enough low 0 bits to
+ * contain this value.  This value is also used as a mask, so it must
+ * be one less than a power of two.
+ */
+#define MAX_PGTABLE_INDEX_SIZE	0xf
 
 extern struct kmem_cache *pgtable_cache[];
-
-#define PGD_CACHE_NUM		0
-#define PUD_CACHE_NUM		1
-#define PMD_CACHE_NUM		1
-#define HUGEPTE_CACHE_NUM	2
-#define PTE_NONCACHE_NUM	7  /* from GFP rather than kmem_cache */
+#define PGT_CACHE(shift) (pgtable_cache[(shift)-1])
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return kmem_cache_alloc(pgtable_cache[PGD_CACHE_NUM], GFP_KERNEL);
+	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL);
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-	subpage_prot_free(pgd);
-	kmem_cache_free(pgtable_cache[PGD_CACHE_NUM], pgd);
+	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
 }
 
 #ifndef CONFIG_PPC_64K_PAGES
@@ -40,13 +47,13 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(pgtable_cache[PUD_CACHE_NUM],
+	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
 				GFP_KERNEL|__GFP_REPEAT);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 {
-	kmem_cache_free(pgtable_cache[PUD_CACHE_NUM], pud);
+	kmem_cache_free(PGT_CACHE(PUD_INDEX_SIZE), pud);
 }
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
@@ -78,13 +85,13 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(pgtable_cache[PMD_CACHE_NUM],
+	return kmem_cache_alloc(PGT_CACHE(PMD_INDEX_SIZE),
 				GFP_KERNEL|__GFP_REPEAT);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-	kmem_cache_free(pgtable_cache[PMD_CACHE_NUM], pmd);
+	kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
 }
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
@@ -107,24 +114,22 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 	return page;
 }
 
-static inline void pgtable_free(pgtable_free_t pgf)
+static inline void pgtable_free(void *table, unsigned index_size)
 {
-	void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
-	int cachenum = pgf.val & PGF_CACHENUM_MASK;
-
-	if (cachenum == PTE_NONCACHE_NUM)
-		free_page((unsigned long)p);
-	else
-		kmem_cache_free(pgtable_cache[cachenum], p);
+	if (!index_size)
+		free_page((unsigned long)table);
+	else {
+		BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
+		kmem_cache_free(PGT_CACHE(index_size), table);
+	}
 }
 
-#define __pmd_free_tlb(tlb, pmd,addr)		      \
-	pgtable_free_tlb(tlb, pgtable_free_cache(pmd, \
-		PMD_CACHE_NUM, PMD_TABLE_SIZE-1))
+#define __pmd_free_tlb(tlb, pmd, addr)		      \
+	pgtable_free_tlb(tlb, pmd, PMD_INDEX_SIZE)
 #ifndef CONFIG_PPC_64K_PAGES
 #define __pud_free_tlb(tlb, pud, addr)		      \
-	pgtable_free_tlb(tlb, pgtable_free_cache(pud, \
-		PUD_CACHE_NUM, PUD_TABLE_SIZE-1))
+	pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE)
+
 #endif /* CONFIG_PPC_64K_PAGES */
 
 #define check_pgt_cache()	do { } while (0)

arch/powerpc/include/asm/pgalloc.h

@@ -24,25 +24,6 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 	__free_page(ptepage);
 }
 
-typedef struct pgtable_free {
-	unsigned long val;
-} pgtable_free_t;
-
-/* This needs to be big enough to allow for MMU_PAGE_COUNT + 2 to be stored
- * and small enough to fit in the low bits of any naturally aligned page
- * table cache entry. Arbitrarily set to 0x1f, that should give us some
- * room to grow
- */
-#define PGF_CACHENUM_MASK	0x1f
-
-static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
-						unsigned long mask)
-{
-	BUG_ON(cachenum > PGF_CACHENUM_MASK);
-
-	return (pgtable_free_t){.val = ((unsigned long) p & ~mask) | cachenum};
-}
-
 #ifdef CONFIG_PPC64
 #include <asm/pgalloc-64.h>
 #else
@@ -50,12 +31,12 @@ static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
 #endif
 
 #ifdef CONFIG_SMP
-extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
+extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift);
 extern void pte_free_finish(void);
 #else /* CONFIG_SMP */
-static inline void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf)
+static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
 {
-	pgtable_free(pgf);
+	pgtable_free(table, shift);
 }
 static inline void pte_free_finish(void) { }
 #endif /* !CONFIG_SMP */
@@ -63,12 +44,9 @@ static inline void pte_free_finish(void) { }
 static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage,
 				  unsigned long address)
 {
-	pgtable_free_t pgf = pgtable_free_cache(page_address(ptepage),
-						PTE_NONCACHE_NUM,
-						PTE_TABLE_SIZE-1);
 	tlb_flush_pgtable(tlb, address);
 	pgtable_page_dtor(ptepage);
-	pgtable_free_tlb(tlb, pgf);
+	pgtable_free_tlb(tlb, page_address(ptepage), 0);
 }
 
 #endif /* __KERNEL__ */

arch/powerpc/include/asm/pgtable-ppc64.h

@@ -354,6 +354,7 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 #define pgoff_to_pte(off)	((pte_t) {((off) << PTE_RPN_SHIFT)|_PAGE_FILE})
 #define PTE_FILE_MAX_BITS	(BITS_PER_LONG - PTE_RPN_SHIFT)
 
+void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
 void pgtable_cache_init(void);
 
 /*
@@ -378,7 +379,18 @@ void pgtable_cache_init(void);
 	return pt;
 }
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long address);
+#ifdef CONFIG_HUGETLB_PAGE
+pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
+				 unsigned *shift);
+#else
+static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
+					       unsigned *shift)
+{
+	if (shift)
+		*shift = 0;
+	return find_linux_pte(pgdir, ea);
+}
+#endif /* !CONFIG_HUGETLB_PAGE */
 
 #endif /* __ASSEMBLY__ */
 

arch/powerpc/include/asm/pgtable.h

@@ -211,6 +211,9 @@ extern void paging_init(void);
  */
 extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t);
 
+extern int gup_hugepd(hugepd_t *hugepd, unsigned pdshift, unsigned long addr,
+		      unsigned long end, int write, struct page **pages, int *nr);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */

arch/powerpc/include/asm/pte-8xx.h

@@ -33,21 +33,21 @@
 #define _PAGE_NO_CACHE	0x0002	/* I: cache inhibit */
 #define _PAGE_SHARED	0x0004	/* No ASID (context) compare */
 #define _PAGE_SPECIAL	0x0008	/* SW entry, forced to 0 by the TLB miss */
+#define _PAGE_DIRTY	0x0100	/* C: page changed */
 
-/* These five software bits must be masked out when the entry is loaded
- * into the TLB.
+/* These 4 software bits must be masked out when the entry is loaded
+ * into the TLB, 1 SW bit left(0x0080).
  */
 #define _PAGE_GUARDED	0x0010	/* software: guarded access */
-#define _PAGE_DIRTY	0x0020	/* software: page changed */
-#define _PAGE_RW	0x0040	/* software: user write access allowed */
-#define _PAGE_ACCESSED	0x0080	/* software: page referenced */
+#define _PAGE_ACCESSED	0x0020	/* software: page referenced */
+#define _PAGE_WRITETHRU	0x0040	/* software: caching is write through */
 
 /* Setting any bits in the nibble with the follow two controls will
  * require a TLB exception handler change.  It is assumed unused bits
  * are always zero.
  */
-#define _PAGE_HWWRITE	0x0100	/* h/w write enable: never set in Linux PTE */
-#define _PAGE_USER	0x0800	/* One of the PP bits, the other is USER&~RW */
+#define _PAGE_RW	0x0400	/* lsb PP bits, inverted in HW */
+#define _PAGE_USER	0x0800	/* msb PP bits */
 
 #define _PMD_PRESENT	0x0001
 #define _PMD_BAD	0x0ff0

arch/powerpc/include/asm/pte-hash64-64k.h

@@ -76,41 +76,4 @@
 	remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE,		\
 			__pgprot(pgprot_val((prot)) | _PAGE_4K_PFN))
 
-
-#ifdef CONFIG_PPC_SUBPAGE_PROT
-/*
- * For the sub-page protection option, we extend the PGD with one of
- * these.  Basically we have a 3-level tree, with the top level being
- * the protptrs array.  To optimize speed and memory consumption when
- * only addresses < 4GB are being protected, pointers to the first
- * four pages of sub-page protection words are stored in the low_prot
- * array.
- * Each page of sub-page protection words protects 1GB (4 bytes
- * protects 64k).  For the 3-level tree, each page of pointers then
- * protects 8TB.
- */
-struct subpage_prot_table {
-	unsigned long maxaddr;	/* only addresses < this are protected */
-	unsigned int **protptrs[2];
-	unsigned int *low_prot[4];
-};
-
-#undef PGD_TABLE_SIZE
-#define PGD_TABLE_SIZE		((sizeof(pgd_t) << PGD_INDEX_SIZE) + \
-				 sizeof(struct subpage_prot_table))
-
-#define SBP_L1_BITS		(PAGE_SHIFT - 2)
-#define SBP_L2_BITS		(PAGE_SHIFT - 3)
-#define SBP_L1_COUNT		(1 << SBP_L1_BITS)
-#define SBP_L2_COUNT		(1 << SBP_L2_BITS)
-#define SBP_L2_SHIFT		(PAGE_SHIFT + SBP_L1_BITS)
-#define SBP_L3_SHIFT		(SBP_L2_SHIFT + SBP_L2_BITS)
-
-extern void subpage_prot_free(pgd_t *pgd);
-
-static inline struct subpage_prot_table *pgd_subpage_prot(pgd_t *pgd)
-{
-	return (struct subpage_prot_table *)(pgd + PTRS_PER_PGD);
-}
-#endif /* CONFIG_PPC_SUBPAGE_PROT */
 #endif	/* __ASSEMBLY__ */

arch/powerpc/include/asm/qe.h

@@ -87,7 +87,7 @@ extern spinlock_t cmxgcr_lock;
 
 /* Export QE common operations */
 #ifdef CONFIG_QUICC_ENGINE
-extern void __init qe_reset(void);
+extern void qe_reset(void);
 #else
 static inline void qe_reset(void) {}
 #endif
@@ -145,8 +145,17 @@ static inline void qe_pin_set_gpio(struct qe_pin *qe_pin) {}
 static inline void qe_pin_set_dedicated(struct qe_pin *pin) {}
 #endif /* CONFIG_QE_GPIO */
 
-/* QE internal API */
+#ifdef CONFIG_QUICC_ENGINE
 int qe_issue_cmd(u32 cmd, u32 device, u8 mcn_protocol, u32 cmd_input);
+#else
+static inline int qe_issue_cmd(u32 cmd, u32 device, u8 mcn_protocol,
+			       u32 cmd_input)
+{
+	return -ENOSYS;
+}
+#endif /* CONFIG_QUICC_ENGINE */
+
+/* QE internal API */
 enum qe_clock qe_clock_source(const char *source);
 unsigned int qe_get_brg_clk(void);
 int qe_setbrg(enum qe_clock brg, unsigned int rate, unsigned int multiplier);
@@ -154,7 +163,28 @@ int qe_get_snum(void);
 void qe_put_snum(u8 snum);
 unsigned int qe_get_num_of_risc(void);
 unsigned int qe_get_num_of_snums(void);
-int qe_alive_during_sleep(void);
+
+static inline int qe_alive_during_sleep(void)
+{
+	/*
+	 * MPC8568E reference manual says:
+	 *
+	 * "...power down sequence waits for all I/O interfaces to become idle.
+	 *  In some applications this may happen eventually without actively
+	 *  shutting down interfaces, but most likely, software will have to
+	 *  take steps to shut down the eTSEC, QUICC Engine Block, and PCI
+	 *  interfaces before issuing the command (either the write to the core
+	 *  MSR[WE] as described above or writing to POWMGTCSR) to put the
+	 *  device into sleep state."
+	 *
+	 * MPC8569E reference manual has a similar paragraph.
+	 */
+#ifdef CONFIG_PPC_85xx
+	return 0;
+#else
+	return 1;
+#endif
+}
 
 /* we actually use cpm_muram implementation, define this for convenience */
 #define qe_muram_init cpm_muram_init
@@ -210,8 +240,15 @@ struct qe_firmware_info {
 	u64 extended_modes;	/* Extended modes */
 };
 
+#ifdef CONFIG_QUICC_ENGINE
 /* Upload a firmware to the QE */
 int qe_upload_firmware(const struct qe_firmware *firmware);
+#else
+static inline int qe_upload_firmware(const struct qe_firmware *firmware)
+{
+	return -ENOSYS;
+}
+#endif /* CONFIG_QUICC_ENGINE */
 
 /* Obtain information on the uploaded firmware */
 struct qe_firmware_info *qe_get_firmware_info(void);

arch/powerpc/include/asm/systbl.h

@@ -145,7 +145,7 @@ SYSCALL_SPU(setfsuid)
 SYSCALL_SPU(setfsgid)
 SYSCALL_SPU(llseek)
 COMPAT_SYS_SPU(getdents)
-SYSX_SPU(sys_select,ppc32_select,ppc_select)
+SYSX_SPU(sys_select,ppc32_select,sys_select)
 SYSCALL_SPU(flock)
 SYSCALL_SPU(msync)
 COMPAT_SYS_SPU(readv)

arch/powerpc/kernel/Makefile

@@ -42,10 +42,11 @@ obj-$(CONFIG_ALTIVEC)		+= vecemu.o
 obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
 obj-$(CONFIG_PPC_OF)		+= of_device.o of_platform.o prom_parse.o
 obj-$(CONFIG_PPC_CLOCK)		+= clock.o
-procfs-$(CONFIG_PPC64)		:= proc_ppc64.o
+procfs-y			:= proc_powerpc.o
 obj-$(CONFIG_PROC_FS)		+= $(procfs-y)
 rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI)	:= rtas_pci.o
 obj-$(CONFIG_PPC_RTAS)		+= rtas.o rtas-rtc.o $(rtaspci-y-y)
+obj-$(CONFIG_PPC_RTAS_DAEMON)	+= rtasd.o
 obj-$(CONFIG_RTAS_FLASH)	+= rtas_flash.o
 obj-$(CONFIG_RTAS_PROC)		+= rtas-proc.o
 obj-$(CONFIG_LPARCFG)		+= lparcfg.o

arch/powerpc/kernel/asm-offsets.c

@@ -190,6 +190,11 @@ int main(void)
 	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
 	DEFINE(PACA_DATA_OFFSET, offsetof(struct paca_struct, data_offset));
 	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+	DEFINE(PACA_KVM_IN_GUEST, offsetof(struct paca_struct, kvm_in_guest));
+	DEFINE(PACA_KVM_SLB, offsetof(struct paca_struct, kvm_slb));
+	DEFINE(PACA_KVM_SLB_MAX, offsetof(struct paca_struct, kvm_slb_max));
+#endif
 #endif /* CONFIG_PPC64 */
 
 	/* RTAS */
@@ -398,14 +403,24 @@ int main(void)
 	DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
 	DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
 	DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
+
+	/* book3s_64 */
+#ifdef CONFIG_PPC64
+	DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr));
+	DEFINE(VCPU_HOST_RETIP, offsetof(struct kvm_vcpu, arch.host_retip));
+	DEFINE(VCPU_HOST_R2, offsetof(struct kvm_vcpu, arch.host_r2));
+	DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr));
+	DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
+	DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem));
+	DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter));
+	DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler));
+	DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
+#endif
 #endif
 #ifdef CONFIG_44x
 	DEFINE(PGD_T_LOG2, PGD_T_LOG2);
 	DEFINE(PTE_T_LOG2, PTE_T_LOG2);
 #endif
-#ifdef CONFIG_FSL_BOOKE
-	DEFINE(TLBCAM_SIZE, sizeof(struct tlbcam));
-#endif
 
 #ifdef CONFIG_KVM_EXIT_TIMING
 	DEFINE(VCPU_TIMING_EXIT_TBU, offsetof(struct kvm_vcpu,

arch/powerpc/kernel/crash.c

@@ -373,7 +373,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	hard_irq_disable();
 
 	for_each_irq(i) {
-		struct irq_desc *desc = irq_desc + i;
+		struct irq_desc *desc = irq_to_desc(i);
 
 		if (desc->status & IRQ_INPROGRESS)
 			desc->chip->eoi(i);

arch/powerpc/kernel/dma-swiotlb.c

@@ -21,7 +21,6 @@
 #include <asm/dma.h>
 #include <asm/abs_addr.h>
 
-int swiotlb __read_mostly;
 unsigned int ppc_swiotlb_enable;
 
 /*

arch/powerpc/kernel/exceptions-64s.S

@@ -41,6 +41,7 @@ __start_interrupts:
 	. = 0x200
 _machine_check_pSeries:
 	HMT_MEDIUM
+	DO_KVM	0x200
 	mtspr	SPRN_SPRG_SCRATCH0,r13		/* save r13 */
 	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common)
 
@@ -48,6 +49,7 @@ _machine_check_pSeries:
 	.globl data_access_pSeries
 data_access_pSeries:
 	HMT_MEDIUM
+	DO_KVM	0x300
 	mtspr	SPRN_SPRG_SCRATCH0,r13
 BEGIN_FTR_SECTION
 	mfspr	r13,SPRN_SPRG_PACA
@@ -77,6 +79,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_SLB)
 	.globl data_access_slb_pSeries
 data_access_slb_pSeries:
 	HMT_MEDIUM
+	DO_KVM	0x380
 	mtspr	SPRN_SPRG_SCRATCH0,r13
 	mfspr	r13,SPRN_SPRG_PACA		/* get paca address into r13 */
 	std	r3,PACA_EXSLB+EX_R3(r13)
@@ -115,6 +118,7 @@ data_access_slb_pSeries:
 	.globl instruction_access_slb_pSeries
 instruction_access_slb_pSeries:
 	HMT_MEDIUM
+	DO_KVM	0x480
 	mtspr	SPRN_SPRG_SCRATCH0,r13
 	mfspr	r13,SPRN_SPRG_PACA		/* get paca address into r13 */
 	std	r3,PACA_EXSLB+EX_R3(r13)
@@ -154,6 +158,7 @@ instruction_access_slb_pSeries:
 	.globl	system_call_pSeries
 system_call_pSeries:
 	HMT_MEDIUM
+	DO_KVM	0xc00
 BEGIN_FTR_SECTION
 	cmpdi	r0,0x1ebe
 	beq-	1f
@@ -187,14 +192,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	 */
 performance_monitor_pSeries_1:
 	. = 0xf00
+	DO_KVM	0xf00
 	b	performance_monitor_pSeries
 
 altivec_unavailable_pSeries_1:
 	. = 0xf20
+	DO_KVM	0xf20
 	b	altivec_unavailable_pSeries
 
 vsx_unavailable_pSeries_1:
 	. = 0xf40
+	DO_KVM	0xf40
 	b	vsx_unavailable_pSeries
 
 #ifdef CONFIG_CBE_RAS

arch/powerpc/kernel/head_64.S

@@ -37,6 +37,7 @@
 #include <asm/firmware.h>
 #include <asm/page_64.h>
 #include <asm/irqflags.h>
+#include <asm/kvm_book3s_64_asm.h>
 
 /* The physical memory is layed out such that the secondary processor
  * spin code sits at 0x0000...0x00ff. On server, the vectors follow
@@ -165,6 +166,12 @@ exception_marker:
 #include "exceptions-64s.S"
 #endif
 
+/* KVM trampoline code needs to be close to the interrupt handlers */
+
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#include "../kvm/book3s_64_rmhandlers.S"
+#endif
+
 _GLOBAL(generic_secondary_thread_init)
 	mr	r24,r3
 

arch/powerpc/kernel/head_8xx.S

@@ -206,6 +206,8 @@ MachineCheck:
 	EXCEPTION_PROLOG
 	mfspr r4,SPRN_DAR
 	stw r4,_DAR(r11)
+	li r5,0x00f0
+	mtspr SPRN_DAR,r5	/* Tag DAR, to be used in DTLB Error */
 	mfspr r5,SPRN_DSISR
 	stw r5,_DSISR(r11)
 	addi r3,r1,STACK_FRAME_OVERHEAD
@@ -222,6 +224,8 @@ DataAccess:
 	stw	r10,_DSISR(r11)
 	mr	r5,r10
 	mfspr	r4,SPRN_DAR
+	li	r10,0x00f0
+	mtspr	SPRN_DAR,r10	/* Tag DAR, to be used in DTLB Error */
 	EXC_XFER_EE_LITE(0x300, handle_page_fault)
 
 /* Instruction access exception.
@@ -244,6 +248,8 @@ Alignment:
 	EXCEPTION_PROLOG
 	mfspr	r4,SPRN_DAR
 	stw	r4,_DAR(r11)
+	li	r5,0x00f0
+	mtspr	SPRN_DAR,r5	/* Tag DAR, to be used in DTLB Error */
 	mfspr	r5,SPRN_DSISR
 	stw	r5,_DSISR(r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
@@ -333,26 +339,20 @@ InstructionTLBMiss:
 	mfspr	r11, SPRN_MD_TWC	/* ....and get the pte address */
 	lwz	r10, 0(r11)	/* Get the pte */
 
-#ifdef CONFIG_SWAP
-	/* do not set the _PAGE_ACCESSED bit of a non-present page */
-	andi.	r11, r10, _PAGE_PRESENT
-	beq	4f
-	ori	r10, r10, _PAGE_ACCESSED
-	mfspr	r11, SPRN_MD_TWC	/* get the pte address again */
-	stw	r10, 0(r11)
-4:
-#else
-	ori	r10, r10, _PAGE_ACCESSED
-	stw	r10, 0(r11)
-#endif
+	andi.	r11, r10, _PAGE_ACCESSED | _PAGE_PRESENT
+	cmpwi	cr0, r11, _PAGE_ACCESSED | _PAGE_PRESENT
+	bne-	cr0, 2f
+
+	/* Clear PP lsb, 0x400 */
+	rlwinm 	r10, r10, 0, 22, 20
 
 	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 21, 22 and 28 must be clear.
+	 * Software indicator bits 22 and 28 must be clear.
 	 * Software indicator bits 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
-2:	li	r11, 0x00f0
+	li	r11, 0x00f0
 	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
 	DO_8xx_CPU6(0x2d80, r3)
 	mtspr	SPRN_MI_RPN, r10	/* Update TLB entry */
@@ -365,6 +365,22 @@ InstructionTLBMiss:
 	lwz	r3, 8(r0)
 #endif
 	rfi
+2:
+	mfspr	r11, SPRN_SRR1
+	/* clear all error bits as TLB Miss
+	 * sets a few unconditionally
+	*/
+	rlwinm	r11, r11, 0, 0xffff
+	mtspr	SPRN_SRR1, r11
+
+	mfspr	r10, SPRN_M_TW	/* Restore registers */
+	lwz	r11, 0(r0)
+	mtcr	r11
+	lwz	r11, 4(r0)
+#ifdef CONFIG_8xx_CPU6
+	lwz	r3, 8(r0)
+#endif
+	b	InstructionAccess
 
 	. = 0x1200
 DataStoreTLBMiss:
@@ -406,29 +422,45 @@ DataStoreTLBMiss:
 	 * above.
 	 */
 	rlwimi	r11, r10, 0, 27, 27
+	/* Insert the WriteThru flag into the TWC from the Linux PTE.
+	 * It is bit 25 in the Linux PTE and bit 30 in the TWC
+	 */
+	rlwimi	r11, r10, 32-5, 30, 30
 	DO_8xx_CPU6(0x3b80, r3)
 	mtspr	SPRN_MD_TWC, r11
 
-#ifdef CONFIG_SWAP
-	/* do not set the _PAGE_ACCESSED bit of a non-present page */
-	andi.	r11, r10, _PAGE_PRESENT
-	beq	4f
-	ori	r10, r10, _PAGE_ACCESSED
-4:
-	/* and update pte in table */
-#else
-	ori	r10, r10, _PAGE_ACCESSED
-#endif
-	mfspr	r11, SPRN_MD_TWC	/* get the pte address again */
-	stw	r10, 0(r11)
+	/* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set.
+	 * We also need to know if the insn is a load/store, so:
+	 * Clear _PAGE_PRESENT and load that which will
+	 * trap into DTLB Error with store bit set accordinly.
+	 */
+	/* PRESENT=0x1, ACCESSED=0x20
+	 * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5));
+	 * r10 = (r10 & ~PRESENT) | r11;
+	 */
+	rlwinm	r11, r10, 32-5, _PAGE_PRESENT
+	and	r11, r11, r10
+	rlwimi	r10, r11, 0, _PAGE_PRESENT
+
+	/* Honour kernel RO, User NA */
+	/* 0x200 == Extended encoding, bit 22 */
+	/* r11 =  (r10 & _PAGE_USER) >> 2 */
+	rlwinm	r11, r10, 32-2, 0x200
+	or	r10, r11, r10
+	/* r11 =  (r10 & _PAGE_RW) >> 1 */
+	rlwinm	r11, r10, 32-1, 0x200
+	or	r10, r11, r10
+	/* invert RW and 0x200 bits */
+	xori	r10, r10, _PAGE_RW | 0x200
 
 	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 21, 22 and 28 must be clear.
+	 * Software indicator bits 22 and 28 must be clear.
 	 * Software indicator bits 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
 2:	li	r11, 0x00f0
+	mtspr	SPRN_DAR,r11	/* Tag DAR */
 	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
 	DO_8xx_CPU6(0x3d80, r3)
 	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
@@ -469,97 +501,10 @@ DataTLBError:
 	stw	r10, 0(r0)
 	stw	r11, 4(r0)
 
-	/* First, make sure this was a store operation.
-	*/
-	mfspr	r10, SPRN_DSISR
-	andis.	r11, r10, 0x0200	/* If set, indicates store op */
-	beq	2f
-
-	/* The EA of a data TLB miss is automatically stored in the MD_EPN
-	 * register.  The EA of a data TLB error is automatically stored in
-	 * the DAR, but not the MD_EPN register.  We must copy the 20 most
-	 * significant bits of the EA from the DAR to MD_EPN before we
-	 * start walking the page tables.  We also need to copy the CASID
-	 * value from the M_CASID register.
-	 * Addendum:  The EA of a data TLB error is _supposed_ to be stored
-	 * in DAR, but it seems that this doesn't happen in some cases, such
-	 * as when the error is due to a dcbi instruction to a page with a
-	 * TLB that doesn't have the changed bit set.  In such cases, there
-	 * does not appear to be any way  to recover the EA of the error
-	 * since it is neither in DAR nor MD_EPN.  As a workaround, the
-	 * _PAGE_HWWRITE bit is set for all kernel data pages when the PTEs
-	 * are initialized in mapin_ram().  This will avoid the problem,
-	 * assuming we only use the dcbi instruction on kernel addresses.
-	 */
 	mfspr	r10, SPRN_DAR
-	rlwinm	r11, r10, 0, 0, 19
-	ori	r11, r11, MD_EVALID
-	mfspr	r10, SPRN_M_CASID
-	rlwimi	r11, r10, 0, 28, 31
-	DO_8xx_CPU6(0x3780, r3)
-	mtspr	SPRN_MD_EPN, r11
-
-	mfspr	r10, SPRN_M_TWB	/* Get level 1 table entry address */
-
-	/* If we are faulting a kernel address, we have to use the
-	 * kernel page tables.
-	 */
-	andi.	r11, r10, 0x0800
-	beq	3f
-	lis	r11, swapper_pg_dir@h
-	ori	r11, r11, swapper_pg_dir@l
-	rlwimi	r10, r11, 0, 2, 19
-3:
-	lwz	r11, 0(r10)	/* Get the level 1 entry */
-	rlwinm.	r10, r11,0,0,19	/* Extract page descriptor page address */
-	beq	2f		/* If zero, bail */
-
-	/* We have a pte table, so fetch the pte from the table.
-	 */
-	ori	r11, r11, 1		/* Set valid bit in physical L2 page */
-	DO_8xx_CPU6(0x3b80, r3)
-	mtspr	SPRN_MD_TWC, r11		/* Load pte table base address */
-	mfspr	r11, SPRN_MD_TWC		/* ....and get the pte address */
-	lwz	r10, 0(r11)		/* Get the pte */
-
-	andi.	r11, r10, _PAGE_RW	/* Is it writeable? */
-	beq	2f			/* Bail out if not */
-
-	/* Update 'changed', among others.
-	*/
-#ifdef CONFIG_SWAP
-	ori	r10, r10, _PAGE_DIRTY|_PAGE_HWWRITE
-	/* do not set the _PAGE_ACCESSED bit of a non-present page */
-	andi.	r11, r10, _PAGE_PRESENT
-	beq	4f
-	ori	r10, r10, _PAGE_ACCESSED
-4:
-#else
-	ori	r10, r10, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE
-#endif
-	mfspr	r11, SPRN_MD_TWC		/* Get pte address again */
-	stw	r10, 0(r11)		/* and update pte in table */
-
-	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 21, 22 and 28 must be clear.
-	 * Software indicator bits 24, 25, 26, and 27 must be
-	 * set.  All other Linux PTE bits control the behavior
-	 * of the MMU.
-	 */
-	li	r11, 0x00f0
-	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
-	DO_8xx_CPU6(0x3d80, r3)
-	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
-
-	mfspr	r10, SPRN_M_TW	/* Restore registers */
-	lwz	r11, 0(r0)
-	mtcr	r11
-	lwz	r11, 4(r0)
-#ifdef CONFIG_8xx_CPU6
-	lwz	r3, 8(r0)
-#endif
-	rfi
-2:
+	cmpwi	cr0, r10, 0x00f0
+	beq-	FixupDAR	/* must be a buggy dcbX, icbi insn. */
+DARFixed:/* Return from dcbx instruction bug workaround, r10 holds value of DAR */
 	mfspr	r10, SPRN_M_TW	/* Restore registers */
 	lwz	r11, 0(r0)
 	mtcr	r11
@@ -588,6 +533,140 @@ DataTLBError:
 
 	. = 0x2000
 
+/* This is the procedure to calculate the data EA for buggy dcbx,dcbi instructions
+ * by decoding the registers used by the dcbx instruction and adding them.
+ * DAR is set to the calculated address and r10 also holds the EA on exit.
+ */
+ /* define if you don't want to use self modifying code */
+#define NO_SELF_MODIFYING_CODE
+FixupDAR:/* Entry point for dcbx workaround. */
+	/* fetch instruction from memory. */
+	mfspr	r10, SPRN_SRR0
+	DO_8xx_CPU6(0x3780, r3)
+	mtspr	SPRN_MD_EPN, r10
+	mfspr	r11, SPRN_M_TWB	/* Get level 1 table entry address */
+	cmplwi	cr0, r11, 0x0800
+	blt-	3f		/* Branch if user space */
+	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@h
+	ori	r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l
+	rlwimi	r11, r10, 32-20, 0xffc /* r11 = r11&~0xffc|(r10>>20)&0xffc */
+3:	lwz	r11, 0(r11)	/* Get the level 1 entry */
+	DO_8xx_CPU6(0x3b80, r3)
+	mtspr	SPRN_MD_TWC, r11	/* Load pte table base address */
+	mfspr	r11, SPRN_MD_TWC	/* ....and get the pte address */
+	lwz	r11, 0(r11)	/* Get the pte */
+	/* concat physical page address(r11) and page offset(r10) */
+	rlwimi	r11, r10, 0, 20, 31
+	lwz	r11,0(r11)
+/* Check if it really is a dcbx instruction. */
+/* dcbt and dcbtst does not generate DTLB Misses/Errors,
+ * no need to include them here */
+	srwi	r10, r11, 26	/* check if major OP code is 31 */
+	cmpwi	cr0, r10, 31
+	bne-	141f
+	rlwinm	r10, r11, 0, 21, 30
+	cmpwi	cr0, r10, 2028	/* Is dcbz? */
+	beq+	142f
+	cmpwi	cr0, r10, 940	/* Is dcbi? */
+	beq+	142f
+	cmpwi	cr0, r10, 108	/* Is dcbst? */
+	beq+	144f		/* Fix up store bit! */
+	cmpwi	cr0, r10, 172	/* Is dcbf? */
+	beq+	142f
+	cmpwi	cr0, r10, 1964	/* Is icbi? */
+	beq+	142f
+141:	mfspr	r10, SPRN_DAR	/* r10 must hold DAR at exit */
+	b	DARFixed	/* Nope, go back to normal TLB processing */
+
+144:	mfspr	r10, SPRN_DSISR
+	rlwinm	r10, r10,0,7,5	/* Clear store bit for buggy dcbst insn */
+	mtspr	SPRN_DSISR, r10
+142:	/* continue, it was a dcbx, dcbi instruction. */
+#ifdef CONFIG_8xx_CPU6
+	lwz	r3, 8(r0)	/* restore r3 from memory */
+#endif
+#ifndef NO_SELF_MODIFYING_CODE
+	andis.	r10,r11,0x1f	/* test if reg RA is r0 */
+	li	r10,modified_instr@l
+	dcbtst	r0,r10		/* touch for store */
+	rlwinm	r11,r11,0,0,20	/* Zero lower 10 bits */
+	oris	r11,r11,640	/* Transform instr. to a "add r10,RA,RB" */
+	ori	r11,r11,532
+	stw	r11,0(r10)	/* store add/and instruction */
+	dcbf	0,r10		/* flush new instr. to memory. */
+	icbi	0,r10		/* invalidate instr. cache line */
+	lwz	r11, 4(r0)	/* restore r11 from memory */
+	mfspr	r10, SPRN_M_TW	/* restore r10 from M_TW */
+	isync			/* Wait until new instr is loaded from memory */
+modified_instr:
+	.space	4		/* this is where the add instr. is stored */
+	bne+	143f
+	subf	r10,r0,r10	/* r10=r10-r0, only if reg RA is r0 */
+143:	mtdar	r10		/* store faulting EA in DAR */
+	b	DARFixed	/* Go back to normal TLB handling */
+#else
+	mfctr	r10
+	mtdar	r10			/* save ctr reg in DAR */
+	rlwinm	r10, r11, 24, 24, 28	/* offset into jump table for reg RB */
+	addi	r10, r10, 150f@l	/* add start of table */
+	mtctr	r10			/* load ctr with jump address */
+	xor	r10, r10, r10		/* sum starts at zero */
+	bctr				/* jump into table */
+150:
+	add	r10, r10, r0	;b	151f
+	add	r10, r10, r1	;b	151f
+	add	r10, r10, r2	;b	151f
+	add	r10, r10, r3	;b	151f
+	add	r10, r10, r4	;b	151f
+	add	r10, r10, r5	;b	151f
+	add	r10, r10, r6	;b	151f
+	add	r10, r10, r7	;b	151f
+	add	r10, r10, r8	;b	151f
+	add	r10, r10, r9	;b	151f
+	mtctr	r11	;b	154f	/* r10 needs special handling */
+	mtctr	r11	;b	153f	/* r11 needs special handling */
+	add	r10, r10, r12	;b	151f
+	add	r10, r10, r13	;b	151f
+	add	r10, r10, r14	;b	151f
+	add	r10, r10, r15	;b	151f
+	add	r10, r10, r16	;b	151f
+	add	r10, r10, r17	;b	151f
+	add	r10, r10, r18	;b	151f
+	add	r10, r10, r19	;b	151f
+	add	r10, r10, r20	;b	151f
+	add	r10, r10, r21	;b	151f
+	add	r10, r10, r22	;b	151f
+	add	r10, r10, r23	;b	151f
+	add	r10, r10, r24	;b	151f
+	add	r10, r10, r25	;b	151f
+	add	r10, r10, r26	;b	151f
+	add	r10, r10, r27	;b	151f
+	add	r10, r10, r28	;b	151f
+	add	r10, r10, r29	;b	151f
+	add	r10, r10, r30	;b	151f
+	add	r10, r10, r31
+151:
+	rlwinm. r11,r11,19,24,28	/* offset into jump table for reg RA */
+	beq	152f			/* if reg RA is zero, don't add it */
+	addi	r11, r11, 150b@l	/* add start of table */
+	mtctr	r11			/* load ctr with jump address */
+	rlwinm	r11,r11,0,16,10		/* make sure we don't execute this more than once */
+	bctr				/* jump into table */
+152:
+	mfdar	r11
+	mtctr	r11			/* restore ctr reg from DAR */
+	mtdar	r10			/* save fault EA to DAR */
+	b	DARFixed		/* Go back to normal TLB handling */
+
+	/* special handling for r10,r11 since these are modified already */
+153:	lwz	r11, 4(r0)	/* load r11 from memory */
+	b	155f
+154:	mfspr	r11, SPRN_M_TW	/* load r10 from M_TW */
+155:	add	r10, r10, r11	/* add it */
+	mfctr	r11		/* restore r11 */
+	b	151b
+#endif
+
 	.globl	giveup_fpu
 giveup_fpu:
 	blr

arch/powerpc/kernel/head_fsl_booke.S

@@ -943,28 +943,6 @@ _GLOBAL(__setup_e500mc_ivors)
 	sync
 	blr
 
-/*
- * extern void loadcam_entry(unsigned int index)
- *
- * Load TLBCAM[index] entry in to the L2 CAM MMU
- */
-_GLOBAL(loadcam_entry)
-	lis	r4,TLBCAM@ha
-	addi	r4,r4,TLBCAM@l
-	mulli	r5,r3,TLBCAM_SIZE
-	add	r3,r5,r4
-	lwz	r4,0(r3)
-	mtspr	SPRN_MAS0,r4
-	lwz	r4,4(r3)
-	mtspr	SPRN_MAS1,r4
-	lwz	r4,8(r3)
-	mtspr	SPRN_MAS2,r4
-	lwz	r4,12(r3)
-	mtspr	SPRN_MAS3,r4
-	tlbwe
-	isync
-	blr
-
 /*
  * extern void giveup_altivec(struct task_struct *prev)
  *

arch/powerpc/kernel/io.c

@@ -161,7 +161,7 @@ void _memcpy_fromio(void *dest, const volatile void __iomem *src,
 		dest++;
 		n--;
 	}
-	while(n > 4) {
+	while(n >= 4) {
 		*((u32 *)dest) = *((volatile u32 *)vsrc);
 		eieio();
 		vsrc += 4;
@@ -190,7 +190,7 @@ void _memcpy_toio(volatile void __iomem *dest, const void *src, unsigned long n)
 		vdest++;
 		n--;
 	}
-	while(n > 4) {
+	while(n >= 4) {
 		*((volatile u32 *)vdest) = *((volatile u32 *)src);
 		src += 4;
 		vdest += 4;

arch/powerpc/kernel/irq.c

@@ -87,7 +87,10 @@ extern int tau_interrupts(int);
 #endif /* CONFIG_PPC32 */
 
 #ifdef CONFIG_PPC64
+
+#ifndef CONFIG_SPARSE_IRQ
 EXPORT_SYMBOL(irq_desc);
+#endif
 
 int distribute_irqs = 1;
 
@@ -189,33 +192,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "CPU%d       ", j);
 		seq_putc(p, '\n');
-	}
-
-	if (i < NR_IRQS) {
-		desc = get_irq_desc(i);
-		spin_lock_irqsave(&desc->lock, flags);
-		action = desc->action;
-		if (!action || !action->handler)
-			goto skip;
-		seq_printf(p, "%3d: ", i);
-#ifdef CONFIG_SMP
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
-#else
-		seq_printf(p, "%10u ", kstat_irqs(i));
-#endif /* CONFIG_SMP */
-		if (desc->chip)
-			seq_printf(p, " %s ", desc->chip->typename);
-		else
-			seq_puts(p, "  None      ");
-		seq_printf(p, "%s", (desc->status & IRQ_LEVEL) ? "Level " : "Edge  ");
-		seq_printf(p, "    %s", action->name);
-		for (action = action->next; action; action = action->next)
-			seq_printf(p, ", %s", action->name);
-		seq_putc(p, '\n');
-skip:
-		spin_unlock_irqrestore(&desc->lock, flags);
-	} else if (i == NR_IRQS) {
+	} else if (i == nr_irqs) {
 #if defined(CONFIG_PPC32) && defined(CONFIG_TAU_INT)
 		if (tau_initialized){
 			seq_puts(p, "TAU: ");
@@ -225,30 +202,68 @@ int show_interrupts(struct seq_file *p, void *v)
 		}
 #endif /* CONFIG_PPC32 && CONFIG_TAU_INT*/
 		seq_printf(p, "BAD: %10u\n", ppc_spurious_interrupts);
+
+		return 0;
 	}
+
+	desc = irq_to_desc(i);
+	if (!desc)
+		return 0;
+
+	spin_lock_irqsave(&desc->lock, flags);
+
+	action = desc->action;
+	if (!action || !action->handler)
+		goto skip;
+
+	seq_printf(p, "%3d: ", i);
+#ifdef CONFIG_SMP
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
+#else
+	seq_printf(p, "%10u ", kstat_irqs(i));
+#endif /* CONFIG_SMP */
+
+	if (desc->chip)
+		seq_printf(p, " %s ", desc->chip->name);
+	else
+		seq_puts(p, "  None      ");
+
+	seq_printf(p, "%s", (desc->status & IRQ_LEVEL) ? "Level " : "Edge  ");
+	seq_printf(p, "    %s", action->name);
+
+	for (action = action->next; action; action = action->next)
+		seq_printf(p, ", %s", action->name);
+	seq_putc(p, '\n');
+
+skip:
+	spin_unlock_irqrestore(&desc->lock, flags);
+
 	return 0;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
 void fixup_irqs(cpumask_t map)
 {
+	struct irq_desc *desc;
 	unsigned int irq;
 	static int warned;
 
 	for_each_irq(irq) {
 		cpumask_t mask;
 
-		if (irq_desc[irq].status & IRQ_PER_CPU)
+		desc = irq_to_desc(irq);
+		if (desc && desc->status & IRQ_PER_CPU)
 			continue;
 
-		cpumask_and(&mask, irq_desc[irq].affinity, &map);
+		cpumask_and(&mask, desc->affinity, &map);
 		if (any_online_cpu(mask) == NR_CPUS) {
 			printk("Breaking affinity for irq %i\n", irq);
 			mask = map;
 		}
-		if (irq_desc[irq].chip->set_affinity)
-			irq_desc[irq].chip->set_affinity(irq, &mask);
-		else if (irq_desc[irq].action && !(warned++))
+		if (desc->chip->set_affinity)
+			desc->chip->set_affinity(irq, &mask);
+		else if (desc->action && !(warned++))
 			printk("Cannot set affinity for irq %i\n", irq);
 	}
 
@@ -275,7 +290,7 @@ static inline void handle_one_irq(unsigned int irq)
 		return;
 	}
 
-	desc = irq_desc + irq;
+	desc = irq_to_desc(irq);
 	saved_sp_limit = current->thread.ksp_limit;
 
 	irqtp->task = curtp->task;
@@ -541,7 +556,7 @@ struct irq_host *irq_alloc_host(struct device_node *of_node,
 			smp_wmb();
 
 			/* Clear norequest flags */
-			get_irq_desc(i)->status &= ~IRQ_NOREQUEST;
+			irq_to_desc(i)->status &= ~IRQ_NOREQUEST;
 
 			/* Legacy flags are left to default at this point,
 			 * one can then use irq_create_mapping() to
@@ -607,8 +622,16 @@ void irq_set_virq_count(unsigned int count)
 static int irq_setup_virq(struct irq_host *host, unsigned int virq,
 			    irq_hw_number_t hwirq)
 {
+	struct irq_desc *desc;
+
+	desc = irq_to_desc_alloc_node(virq, 0);
+	if (!desc) {
+		pr_debug("irq: -> allocating desc failed\n");
+		goto error;
+	}
+
 	/* Clear IRQ_NOREQUEST flag */
-	get_irq_desc(virq)->status &= ~IRQ_NOREQUEST;
+	desc->status &= ~IRQ_NOREQUEST;
 
 	/* map it */
 	smp_wmb();
@@ -617,11 +640,14 @@ static int irq_setup_virq(struct irq_host *host, unsigned int virq,
 
 	if (host->ops->map(host, virq, hwirq)) {
 		pr_debug("irq: -> mapping failed, freeing\n");
-		irq_free_virt(virq, 1);
-		return -1;
+		goto error;
 	}
 
 	return 0;
+
+error:
+	irq_free_virt(virq, 1);
+	return -1;
 }
 
 unsigned int irq_create_direct_mapping(struct irq_host *host)
@@ -705,7 +731,7 @@ unsigned int irq_create_mapping(struct irq_host *host,
 EXPORT_SYMBOL_GPL(irq_create_mapping);
 
 unsigned int irq_create_of_mapping(struct device_node *controller,
-				   u32 *intspec, unsigned int intsize)
+				   const u32 *intspec, unsigned int intsize)
 {
 	struct irq_host *host;
 	irq_hw_number_t hwirq;
@@ -738,7 +764,7 @@ unsigned int irq_create_of_mapping(struct device_node *controller,
 
 	/* Set type if specified and different than the current one */
 	if (type != IRQ_TYPE_NONE &&
-	    type != (get_irq_desc(virq)->status & IRQF_TRIGGER_MASK))
+	    type != (irq_to_desc(virq)->status & IRQF_TRIGGER_MASK))
 		set_irq_type(virq, type);
 	return virq;
 }
@@ -810,7 +836,7 @@ void irq_dispose_mapping(unsigned int virq)
 	irq_map[virq].hwirq = host->inval_irq;
 
 	/* Set some flags */
-	get_irq_desc(virq)->status |= IRQ_NOREQUEST;
+	irq_to_desc(virq)->status |= IRQ_NOREQUEST;
 
 	/* Free it */
 	irq_free_virt(virq, 1);
@@ -1002,12 +1028,24 @@ void irq_free_virt(unsigned int virq, unsigned int count)
 	spin_unlock_irqrestore(&irq_big_lock, flags);
 }
 
-void irq_early_init(void)
+int arch_early_irq_init(void)
 {
-	unsigned int i;
+	struct irq_desc *desc;
+	int i;
+
+	for (i = 0; i < NR_IRQS; i++) {
+		desc = irq_to_desc(i);
+		if (desc)
+			desc->status |= IRQ_NOREQUEST;
+	}
 
-	for (i = 0; i < NR_IRQS; i++)
-		get_irq_desc(i)->status |= IRQ_NOREQUEST;
+	return 0;
+}
+
+int arch_init_chip_data(struct irq_desc *desc, int node)
+{
+	desc->status |= IRQ_NOREQUEST;
+	return 0;
 }
 
 /* We need to create the radix trees late */
@@ -1069,16 +1107,19 @@ static int virq_debug_show(struct seq_file *m, void *private)
 	seq_printf(m, "%-5s  %-7s  %-15s  %s\n", "virq", "hwirq",
 		      "chip name", "host name");
 
-	for (i = 1; i < NR_IRQS; i++) {
-		desc = get_irq_desc(i);
+	for (i = 1; i < nr_irqs; i++) {
+		desc = irq_to_desc(i);
+		if (!desc)
+			continue;
+
 		spin_lock_irqsave(&desc->lock, flags);
 
 		if (desc->action && desc->action->handler) {
 			seq_printf(m, "%5d  ", i);
 			seq_printf(m, "0x%05lx  ", virq_to_hw(i));
 
-			if (desc->chip && desc->chip->typename)
-				p = desc->chip->typename;
+			if (desc->chip && desc->chip->name)
+				p = desc->chip->name;
 			else
 				p = none;
 			seq_printf(m, "%-15s  ", p);