Merge git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc

* git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc: (139 commits)
  [POWERPC] re-enable OProfile for iSeries, using timer interrupt
  [POWERPC] support ibm,extended-*-frequency properties
  [POWERPC] Extra sanity check in EEH code
  [POWERPC] Dont look for class-code in pci children
  [POWERPC] Fix mdelay badness on shared processor partitions
  [POWERPC] disable floating point exceptions for init
  [POWERPC] Unify ppc syscall tables
  [POWERPC] mpic: add support for serial mode interrupts
  [POWERPC] pseries: Print PCI slot location code on failure
  [POWERPC] spufs: one more fix for 64k pages
  [POWERPC] spufs: fail spu_create with invalid flags
  [POWERPC] spufs: clear class2 interrupt status before wakeup
  [POWERPC] spufs: fix Makefile for "make clean"
  [POWERPC] spufs: remove stop_code from struct spu
  [POWERPC] spufs: fix spu irq affinity setting
  [POWERPC] spufs: further abstract priv1 register access
  [POWERPC] spufs: split the Cell BE support into generic and platform dependant parts
  [POWERPC] spufs: dont try to access SPE channel 1 count
  [POWERPC] spufs: use kzalloc in create_spu
  [POWERPC] spufs: fix initial state of wbox file
  ...

Manually resolved conflicts in:
	drivers/net/phy/Makefile
	include/asm-powerpc/spu.h

15 files changed, 185 insertions, 108 deletions

diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S
index ea469ee..94255be 100644
--- a/arch/powerpc/mm/hash_low_32.S
+++ b/arch/powerpc/mm/hash_low_32.S
@@ -74,12 +74,6 @@ _GLOBAL(hash_page_sync)
  */
 	.text
 _GLOBAL(hash_page)
-#ifdef CONFIG_PPC64BRIDGE
-	mfmsr	r0
-	clrldi	r0,r0,1		/* make sure it's in 32-bit mode */
-	MTMSRD(r0)
-	isync
-#endif
 	tophys(r7,0)			/* gets -KERNELBASE into r7 */
 #ifdef CONFIG_SMP
 	addis	r8,r7,mmu_hash_lock@h
@@ -285,7 +279,6 @@ Hash_base = 0xc0180000
 Hash_bits = 12				/* e.g. 256kB hash table */
 Hash_msk = (((1 << Hash_bits) - 1) * 64)
 
-#ifndef CONFIG_PPC64BRIDGE
 /* defines for the PTE format for 32-bit PPCs */
 #define PTE_SIZE	8
 #define PTEG_SIZE	64
@@ -299,21 +292,6 @@ Hash_msk = (((1 << Hash_bits) - 1) * 64)
 #define SET_V(r)	oris r,r,PTE_V@h
 #define CLR_V(r,t)	rlwinm r,r,0,1,31
 
-#else
-/* defines for the PTE format for 64-bit PPCs */
-#define PTE_SIZE	16
-#define PTEG_SIZE	128
-#define LG_PTEG_SIZE	7
-#define LDPTEu		ldu
-#define STPTE		std
-#define CMPPTE		cmpd
-#define PTE_H		2
-#define PTE_V		1
-#define TST_V(r)	andi. r,r,PTE_V
-#define SET_V(r)	ori r,r,PTE_V
-#define CLR_V(r,t)	li t,PTE_V; andc r,r,t
-#endif /* CONFIG_PPC64BRIDGE */
-
 #define HASH_LEFT	31-(LG_PTEG_SIZE+Hash_bits-1)
 #define HASH_RIGHT	31-LG_PTEG_SIZE
 
@@ -331,14 +309,8 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_NEED_COHERENT)
 
 	/* Construct the high word of the PPC-style PTE (r5) */
-#ifndef CONFIG_PPC64BRIDGE
 	rlwinm	r5,r3,7,1,24		/* put VSID in 0x7fffff80 bits */
 	rlwimi	r5,r4,10,26,31		/* put in API (abbrev page index) */
-#else /* CONFIG_PPC64BRIDGE */
-	clrlwi	r3,r3,8			/* reduce vsid to 24 bits */
-	sldi	r5,r3,12		/* shift vsid into position */
-	rlwimi	r5,r4,16,20,24		/* put in API (abbrev page index) */
-#endif /* CONFIG_PPC64BRIDGE */
 	SET_V(r5)			/* set V (valid) bit */
 
 	/* Get the address of the primary PTE group in the hash table (r3) */
@@ -516,14 +488,8 @@ _GLOBAL(flush_hash_pages)
 	add	r3,r3,r0		/* note code below trims to 24 bits */
 
 	/* Construct the high word of the PPC-style PTE (r11) */
-#ifndef CONFIG_PPC64BRIDGE
 	rlwinm	r11,r3,7,1,24		/* put VSID in 0x7fffff80 bits */
 	rlwimi	r11,r4,10,26,31		/* put in API (abbrev page index) */
-#else /* CONFIG_PPC64BRIDGE */
-	clrlwi	r3,r3,8			/* reduce vsid to 24 bits */
-	sldi	r11,r3,12		/* shift vsid into position */
-	rlwimi	r11,r4,16,20,24		/* put in API (abbrev page index) */
-#endif /* CONFIG_PPC64BRIDGE */
 	SET_V(r11)			/* set V (valid) bit */
 
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index e0d02c4..52e9142 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -136,6 +136,7 @@ _GLOBAL(__hash_page_4K)
 	and	r0,r0,r4		/* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/
 	andc	r0,r30,r0		/* r0 = pte & ~r0 */
 	rlwimi	r3,r0,32-1,31,31	/* Insert result into PP lsb */
+	ori	r3,r3,HPTE_R_C		/* Always add "C" bit for perf. */
 
 	/* We eventually do the icache sync here (maybe inline that
 	 * code rather than call a C function...) 
@@ -368,6 +369,7 @@ _GLOBAL(__hash_page_4K)
 	rlwinm	r30,r4,32-9+7,31-7,31-7	/* _PAGE_RW -> _PAGE_DIRTY */
 	or	r30,r30,r31
 	ori	r30,r30,_PAGE_BUSY | _PAGE_ACCESSED | _PAGE_HASHPTE
+	oris	r30,r30,_PAGE_COMBO@h
 	/* Write the linux PTE atomically (setting busy) */
 	stdcx.	r30,0,r6
 	bne-	1b
@@ -400,6 +402,7 @@ _GLOBAL(__hash_page_4K)
 	and	r0,r0,r4		/* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/
 	andc	r0,r30,r0		/* r0 = pte & ~r0 */
 	rlwimi	r3,r0,32-1,31,31	/* Insert result into PP lsb */
+	ori	r3,r3,HPTE_R_C		/* Always add "C" bit for perf. */
 
 	/* We eventually do the icache sync here (maybe inline that
 	 * code rather than call a C function...)
@@ -426,6 +429,14 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 	andi.	r0,r31,_PAGE_HASHPTE
 	li	r26,0			/* Default hidx */
 	beq	htab_insert_pte
+
+	/*
+	 * Check if the pte was already inserted into the hash table
+	 * as a 64k HW page, and invalidate the 64k HPTE if so.
+	 */
+	andis.	r0,r31,_PAGE_COMBO@h
+	beq	htab_inval_old_hpte
+
 	ld	r6,STK_PARM(r6)(r1)
 	ori	r26,r6,0x8000		/* Load the hidx mask */
 	ld	r26,0(r26)
@@ -496,6 +507,19 @@ _GLOBAL(htab_call_hpte_remove)
 	/* Try all again */
 	b	htab_insert_pte
 
+	/*
+	 * Call out to C code to invalidate an 64k HW HPTE that is
+	 * useless now that the segment has been switched to 4k pages.
+	 */
+htab_inval_old_hpte:
+	mr	r3,r29			/* virtual addr */
+	mr	r4,r31			/* PTE.pte */
+	li	r5,0			/* PTE.hidx */
+	li	r6,MMU_PAGE_64K		/* psize */
+	ld	r7,STK_PARM(r8)(r1)	/* local */
+	bl	.flush_hash_page
+	b	htab_insert_pte
+	
 htab_bail_ok:
 	li	r3,0
 	b	htab_bail
@@ -636,6 +660,12 @@ _GLOBAL(__hash_page_64K)
 	 * is changing this PTE anyway and might hash it.
 	 */
 	bne-	ht64_bail_ok
+BEGIN_FTR_SECTION
+	/* Check if PTE has the cache-inhibit bit set */
+	andi.	r0,r31,_PAGE_NO_CACHE
+	/* If so, bail out and refault as a 4k page */
+	bne-	ht64_bail_ok
+END_FTR_SECTION_IFCLR(CPU_FTR_CI_LARGE_PAGE)
 	/* Prepare new PTE value (turn access RW into DIRTY, then
 	 * add BUSY,HASHPTE and ACCESSED)
 	 */
@@ -671,6 +701,7 @@ _GLOBAL(__hash_page_64K)
 	and	r0,r0,r4		/* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/
 	andc	r0,r30,r0		/* r0 = pte & ~r0 */
 	rlwimi	r3,r0,32-1,31,31	/* Insert result into PP lsb */
+	ori	r3,r3,HPTE_R_C		/* Always add "C" bit for perf. */
 
 	/* We eventually do the icache sync here (maybe inline that
 	 * code rather than call a C function...)
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 994856e..a0f3cbd 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -238,7 +238,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 		DBG_LOW(" -> hit\n");
 		/* Update the HPTE */
 		hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
-			(newpp & (HPTE_R_PP | HPTE_R_N));
+			(newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C));
 		native_unlock_hpte(hptep);
 	}
 
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index c006d90..d03fd2b 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -92,10 +92,15 @@ unsigned long htab_size_bytes;
 unsigned long htab_hash_mask;
 int mmu_linear_psize = MMU_PAGE_4K;
 int mmu_virtual_psize = MMU_PAGE_4K;
+int mmu_vmalloc_psize = MMU_PAGE_4K;
+int mmu_io_psize = MMU_PAGE_4K;
 #ifdef CONFIG_HUGETLB_PAGE
 int mmu_huge_psize = MMU_PAGE_16M;
 unsigned int HPAGE_SHIFT;
 #endif
+#ifdef CONFIG_PPC_64K_PAGES
+int mmu_ci_restrictions;
+#endif
 
 /* There are definitions of page sizes arrays to be used when none
  * is provided by the firmware.
@@ -308,20 +313,31 @@ static void __init htab_init_page_sizes(void)
 	else if (mmu_psize_defs[MMU_PAGE_1M].shift)
 		mmu_linear_psize = MMU_PAGE_1M;
 
+#ifdef CONFIG_PPC_64K_PAGES
 	/*
 	 * Pick a size for the ordinary pages. Default is 4K, we support
-	 * 64K if cache inhibited large pages are supported by the
-	 * processor
+	 * 64K for user mappings and vmalloc if supported by the processor.
+	 * We only use 64k for ioremap if the processor
+	 * (and firmware) support cache-inhibited large pages.
+	 * If not, we use 4k and set mmu_ci_restrictions so that
+	 * hash_page knows to switch processes that use cache-inhibited
+	 * mappings to 4k pages.
 	 */
-#ifdef CONFIG_PPC_64K_PAGES
-	if (mmu_psize_defs[MMU_PAGE_64K].shift &&
-	    cpu_has_feature(CPU_FTR_CI_LARGE_PAGE))
+	if (mmu_psize_defs[MMU_PAGE_64K].shift) {
 		mmu_virtual_psize = MMU_PAGE_64K;
+		mmu_vmalloc_psize = MMU_PAGE_64K;
+		if (cpu_has_feature(CPU_FTR_CI_LARGE_PAGE))
+			mmu_io_psize = MMU_PAGE_64K;
+		else
+			mmu_ci_restrictions = 1;
+	}
 #endif
 
-	printk(KERN_INFO "Page orders: linear mapping = %d, others = %d\n",
+	printk(KERN_DEBUG "Page orders: linear mapping = %d, "
+	       "virtual = %d, io = %d\n",
 	       mmu_psize_defs[mmu_linear_psize].shift,
-	       mmu_psize_defs[mmu_virtual_psize].shift);
+	       mmu_psize_defs[mmu_virtual_psize].shift,
+	       mmu_psize_defs[mmu_io_psize].shift);
 
 #ifdef CONFIG_HUGETLB_PAGE
 	/* Init large page size. Currently, we pick 16M or 1M depending
@@ -556,6 +572,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 	pte_t *ptep;
 	cpumask_t tmp;
 	int rc, user_region = 0, local = 0;
+	int psize;
 
 	DBG_LOW("hash_page(ea=%016lx, access=%lx, trap=%lx\n",
 		ea, access, trap);
@@ -575,10 +592,15 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 			return 1;
 		}
 		vsid = get_vsid(mm->context.id, ea);
+		psize = mm->context.user_psize;
 		break;
 	case VMALLOC_REGION_ID:
 		mm = &init_mm;
 		vsid = get_kernel_vsid(ea);
+		if (ea < VMALLOC_END)
+			psize = mmu_vmalloc_psize;
+		else
+			psize = mmu_io_psize;
 		break;
 	default:
 		/* Not a valid range
@@ -629,7 +651,40 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 #ifndef CONFIG_PPC_64K_PAGES
 	rc = __hash_page_4K(ea, access, vsid, ptep, trap, local);
 #else
-	if (mmu_virtual_psize == MMU_PAGE_64K)
+	if (mmu_ci_restrictions) {
+		/* If this PTE is non-cacheable, switch to 4k */
+		if (psize == MMU_PAGE_64K &&
+		    (pte_val(*ptep) & _PAGE_NO_CACHE)) {
+			if (user_region) {
+				psize = MMU_PAGE_4K;
+				mm->context.user_psize = MMU_PAGE_4K;
+				mm->context.sllp = SLB_VSID_USER |
+					mmu_psize_defs[MMU_PAGE_4K].sllp;
+			} else if (ea < VMALLOC_END) {
+				/*
+				 * some driver did a non-cacheable mapping
+				 * in vmalloc space, so switch vmalloc
+				 * to 4k pages
+				 */
+				printk(KERN_ALERT "Reducing vmalloc segment "
+				       "to 4kB pages because of "
+				       "non-cacheable mapping\n");
+				psize = mmu_vmalloc_psize = MMU_PAGE_4K;
+			}
+		}
+		if (user_region) {
+			if (psize != get_paca()->context.user_psize) {
+				get_paca()->context = mm->context;
+				slb_flush_and_rebolt();
+			}
+		} else if (get_paca()->vmalloc_sllp !=
+			   mmu_psize_defs[mmu_vmalloc_psize].sllp) {
+			get_paca()->vmalloc_sllp =
+				mmu_psize_defs[mmu_vmalloc_psize].sllp;
+			slb_flush_and_rebolt();
+		}
+	}
+	if (psize == MMU_PAGE_64K)
 		rc = __hash_page_64K(ea, access, vsid, ptep, trap, local);
 	else
 		rc = __hash_page_4K(ea, access, vsid, ptep, trap, local);
@@ -681,7 +736,18 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 #ifndef CONFIG_PPC_64K_PAGES
 	__hash_page_4K(ea, access, vsid, ptep, trap, local);
 #else
-	if (mmu_virtual_psize == MMU_PAGE_64K)
+	if (mmu_ci_restrictions) {
+		/* If this PTE is non-cacheable, switch to 4k */
+		if (mm->context.user_psize == MMU_PAGE_64K &&
+		    (pte_val(*ptep) & _PAGE_NO_CACHE)) {
+			mm->context.user_psize = MMU_PAGE_4K;
+			mm->context.sllp = SLB_VSID_USER |
+				mmu_psize_defs[MMU_PAGE_4K].sllp;
+			get_paca()->context = mm->context;
+			slb_flush_and_rebolt();
+		}
+	}
+	if (mm->context.user_psize == MMU_PAGE_64K)
 		__hash_page_64K(ea, access, vsid, ptep, trap, local);
 	else
 		__hash_page_4K(ea, access, vsid, ptep, trap, local);
diff --git a/arch/powerpc/mm/lmb.c b/arch/powerpc/mm/lmb.c
index 417d585..8b6f522 100644
--- a/arch/powerpc/mm/lmb.c
+++ b/arch/powerpc/mm/lmb.c
@@ -89,20 +89,25 @@ static long __init lmb_regions_adjacent(struct lmb_region *rgn,
 	return lmb_addrs_adjacent(base1, size1, base2, size2);
 }
 
-/* Assumption: base addr of region 1 < base addr of region 2 */
-static void __init lmb_coalesce_regions(struct lmb_region *rgn,
-		unsigned long r1, unsigned long r2)
+static void __init lmb_remove_region(struct lmb_region *rgn, unsigned long r)
 {
 	unsigned long i;
 
-	rgn->region[r1].size += rgn->region[r2].size;
-	for (i=r2; i < rgn->cnt-1; i++) {
-		rgn->region[i].base = rgn->region[i+1].base;
-		rgn->region[i].size = rgn->region[i+1].size;
+	for (i = r; i < rgn->cnt - 1; i++) {
+		rgn->region[i].base = rgn->region[i + 1].base;
+		rgn->region[i].size = rgn->region[i + 1].size;
 	}
 	rgn->cnt--;
 }
 
+/* Assumption: base addr of region 1 < base addr of region 2 */
+static void __init lmb_coalesce_regions(struct lmb_region *rgn,
+		unsigned long r1, unsigned long r2)
+{
+	rgn->region[r1].size += rgn->region[r2].size;
+	lmb_remove_region(rgn, r2);
+}
+
 /* This routine called with relocation disabled. */
 void __init lmb_init(void)
 {
@@ -294,17 +299,16 @@ unsigned long __init lmb_end_of_DRAM(void)
 	return (lmb.memory.region[idx].base + lmb.memory.region[idx].size);
 }
 
-/*
- * Truncate the lmb list to memory_limit if it's set
- * You must call lmb_analyze() after this.
- */
+/* You must call lmb_analyze() after this. */
 void __init lmb_enforce_memory_limit(unsigned long memory_limit)
 {
 	unsigned long i, limit;
+	struct lmb_property *p;
 
 	if (! memory_limit)
 		return;
 
+	/* Truncate the lmb regions to satisfy the memory limit. */
 	limit = memory_limit;
 	for (i = 0; i < lmb.memory.cnt; i++) {
 		if (limit > lmb.memory.region[i].size) {
@@ -316,4 +320,21 @@ void __init lmb_enforce_memory_limit(unsigned long memory_limit)
 		lmb.memory.cnt = i + 1;
 		break;
 	}
+
+	lmb.rmo_size = lmb.memory.region[0].size;
+
+	/* And truncate any reserves above the limit also. */
+	for (i = 0; i < lmb.reserved.cnt; i++) {
+		p = &lmb.reserved.region[i];
+
+		if (p->base > memory_limit)
+			p->size = 0;
+		else if ((p->base + p->size) > memory_limit)
+			p->size = memory_limit - p->base;
+
+		if (p->size == 0) {
+			lmb_remove_region(&lmb.reserved, i);
+			i--;
+		}
+	}
 }
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 741dd88..69f3b9a 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -299,9 +299,9 @@ void __init paging_init(void)
 	kmap_prot = PAGE_KERNEL;
 #endif /* CONFIG_HIGHMEM */
 
-	printk(KERN_INFO "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
+	printk(KERN_DEBUG "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
 	       top_of_ram, total_ram);
-	printk(KERN_INFO "Memory hole size: %ldMB\n",
+	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (top_of_ram - total_ram) >> 20);
 	/*
 	 * All pages are DMA-able so we put them all in the DMA zone.
@@ -380,7 +380,7 @@ void __init mem_init(void)
 			totalhigh_pages++;
 		}
 		totalram_pages += totalhigh_pages;
-		printk(KERN_INFO "High memory: %luk\n",
+		printk(KERN_DEBUG "High memory: %luk\n",
 		       totalhigh_pages << (PAGE_SHIFT-10));
 	}
 #endif /* CONFIG_HIGHMEM */
diff --git a/arch/powerpc/mm/mmu_context_32.c b/arch/powerpc/mm/mmu_context_32.c
index a8816e0..e326e42 100644
--- a/arch/powerpc/mm/mmu_context_32.c
+++ b/arch/powerpc/mm/mmu_context_32.c
@@ -30,7 +30,7 @@
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
 
-mm_context_t next_mmu_context;
+unsigned long next_mmu_context;
 unsigned long context_map[LAST_CONTEXT / BITS_PER_LONG + 1];
 #ifdef FEW_CONTEXTS
 atomic_t nr_free_contexts;
diff --git a/arch/powerpc/mm/mmu_context_64.c b/arch/powerpc/mm/mmu_context_64.c
index 714a84d..65d18dc 100644
--- a/arch/powerpc/mm/mmu_context_64.c
+++ b/arch/powerpc/mm/mmu_context_64.c
@@ -49,6 +49,9 @@ again:
 	}
 
 	mm->context.id = index;
+	mm->context.user_psize = mmu_virtual_psize;
+	mm->context.sllp = SLB_VSID_USER |
+		mmu_psize_defs[mmu_virtual_psize].sllp;
 
 	return 0;
 }
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 092355f..aa98cb3 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -487,9 +487,9 @@ static void __init setup_nonnuma(void)
 	unsigned long total_ram = lmb_phys_mem_size();
 	unsigned int i;
 
-	printk(KERN_INFO "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
+	printk(KERN_DEBUG "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
 	       top_of_ram, total_ram);
-	printk(KERN_INFO "Memory hole size: %ldMB\n",
+	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (top_of_ram - total_ram) >> 20);
 
 	for (i = 0; i < lmb.memory.cnt; ++i)
@@ -507,7 +507,7 @@ void __init dump_numa_cpu_topology(void)
 		return;
 
 	for_each_online_node(node) {
-		printk(KERN_INFO "Node %d CPUs:", node);
+		printk(KERN_DEBUG "Node %d CPUs:", node);
 
 		count = 0;
 		/*
@@ -543,7 +543,7 @@ static void __init dump_numa_memory_topology(void)
 	for_each_online_node(node) {
 		unsigned long i;
 
-		printk(KERN_INFO "Node %d Memory:", node);
+		printk(KERN_DEBUG "Node %d Memory:", node);
 
 		count = 0;
 
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index ed7fcfe..2ed43a4 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -42,18 +42,14 @@ unsigned long _SDR1;
 
 union ubat {			/* BAT register values to be loaded */
 	BAT	bat;
-#ifdef CONFIG_PPC64BRIDGE
-	u64	word[2];
-#else
 	u32	word[2];
-#endif
-} BATS[4][2];			/* 4 pairs of IBAT, DBAT */
+} BATS[8][2];			/* 8 pairs of IBAT, DBAT */
 
 struct batrange {		/* stores address ranges mapped by BATs */
 	unsigned long start;
 	unsigned long limit;
 	unsigned long phys;
-} bat_addrs[4];
+} bat_addrs[8];
 
 /*
  * Return PA for this VA if it is mapped by a BAT, or 0
@@ -190,7 +186,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 		return;
 	pmd = pmd_offset(pgd_offset(mm, ea), ea);
 	if (!pmd_none(*pmd))
-		add_hash_page(mm->context, ea, pmd_val(*pmd));
+		add_hash_page(mm->context.id, ea, pmd_val(*pmd));
 }
 
 /*
@@ -220,15 +216,9 @@ void __init MMU_init_hw(void)
 
 	if ( ppc_md.progress ) ppc_md.progress("hash:enter", 0x105);
 
-#ifdef CONFIG_PPC64BRIDGE
-#define LG_HPTEG_SIZE	7		/* 128 bytes per HPTEG */
-#define SDR1_LOW_BITS	(lg_n_hpteg - 11)
-#define MIN_N_HPTEG	2048		/* min 256kB hash table */
-#else
 #define LG_HPTEG_SIZE	6		/* 64 bytes per HPTEG */
 #define SDR1_LOW_BITS	((n_hpteg - 1) >> 10)
 #define MIN_N_HPTEG	1024		/* min 64kB hash table */
-#endif
 
 	/*
 	 * Allow 1 HPTE (1/8 HPTEG) for each page of memory.
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index ffc8ed4..6a8bf6c 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -60,19 +60,19 @@ static inline void create_slbe(unsigned long ea, unsigned long flags,
 		     : "memory" );
 }
 
-static void slb_flush_and_rebolt(void)
+void slb_flush_and_rebolt(void)
 {
 	/* If you change this make sure you change SLB_NUM_BOLTED
 	 * appropriately too. */
-	unsigned long linear_llp, virtual_llp, lflags, vflags;
+	unsigned long linear_llp, vmalloc_llp, lflags, vflags;
 	unsigned long ksp_esid_data;
 
 	WARN_ON(!irqs_disabled());
 
 	linear_llp = mmu_psize_defs[mmu_linear_psize].sllp;
-	virtual_llp = mmu_psize_defs[mmu_virtual_psize].sllp;
+	vmalloc_llp = mmu_psize_defs[mmu_vmalloc_psize].sllp;
 	lflags = SLB_VSID_KERNEL | linear_llp;
-	vflags = SLB_VSID_KERNEL | virtual_llp;
+	vflags = SLB_VSID_KERNEL | vmalloc_llp;
 
 	ksp_esid_data = mk_esid_data(get_paca()->kstack, 2);
 	if ((ksp_esid_data & ESID_MASK) == PAGE_OFFSET)
@@ -122,9 +122,6 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
 
 	get_paca()->slb_cache_ptr = 0;
 	get_paca()->context = mm->context;
-#ifdef CONFIG_PPC_64K_PAGES
-	get_paca()->pgdir = mm->pgd;
-#endif /* CONFIG_PPC_64K_PAGES */
 
 	/*
 	 * preload some userspace segments into the SLB.
@@ -167,11 +164,10 @@ static inline void patch_slb_encoding(unsigned int *insn_addr,
 
 void slb_initialize(void)
 {
-	unsigned long linear_llp, virtual_llp;
+	unsigned long linear_llp, vmalloc_llp, io_llp;
 	static int slb_encoding_inited;
 	extern unsigned int *slb_miss_kernel_load_linear;
-	extern unsigned int *slb_miss_kernel_load_virtual;
-	extern unsigned int *slb_miss_user_load_normal;
+	extern unsigned int *slb_miss_kernel_load_io;
 #ifdef CONFIG_HUGETLB_PAGE
 	extern unsigned int *slb_miss_user_load_huge;
 	unsigned long huge_llp;
@@ -181,18 +177,19 @@ void slb_initialize(void)
 
 	/* Prepare our SLB miss handler based on our page size */
 	linear_llp = mmu_psize_defs[mmu_linear_psize].sllp;
-	virtual_llp = mmu_psize_defs[mmu_virtual_psize].sllp;
+	io_llp = mmu_psize_defs[mmu_io_psize].sllp;
+	vmalloc_llp = mmu_psize_defs[mmu_vmalloc_psize].sllp;
+	get_paca()->vmalloc_sllp = SLB_VSID_KERNEL | vmalloc_llp;
+
 	if (!slb_encoding_inited) {
 		slb_encoding_inited = 1;
 		patch_slb_encoding(slb_miss_kernel_load_linear,
 				   SLB_VSID_KERNEL | linear_llp);
-		patch_slb_encoding(slb_miss_kernel_load_virtual,
-				   SLB_VSID_KERNEL | virtual_llp);
-		patch_slb_encoding(slb_miss_user_load_normal,
-				   SLB_VSID_USER | virtual_llp);
+		patch_slb_encoding(slb_miss_kernel_load_io,
+				   SLB_VSID_KERNEL | io_llp);
 
 		DBG("SLB: linear  LLP = %04x\n", linear_llp);
-		DBG("SLB: virtual LLP = %04x\n", virtual_llp);
+		DBG("SLB: io      LLP = %04x\n", io_llp);
 #ifdef CONFIG_HUGETLB_PAGE
 		patch_slb_encoding(slb_miss_user_load_huge,
 				   SLB_VSID_USER | huge_llp);
@@ -207,7 +204,7 @@ void slb_initialize(void)
 	unsigned long lflags, vflags;
 
 	lflags = SLB_VSID_KERNEL | linear_llp;
-	vflags = SLB_VSID_KERNEL | virtual_llp;
+	vflags = SLB_VSID_KERNEL | vmalloc_llp;
 
 	/* Invalidate the entire SLB (even slot 0) & all the ERATS */
 	asm volatile("isync":::"memory");
@@ -215,7 +212,6 @@ void slb_initialize(void)
 	asm volatile("isync; slbia; isync":::"memory");
 	create_slbe(PAGE_OFFSET, lflags, 0);
 
-	/* VMALLOC space has 4K pages always for now */
 	create_slbe(VMALLOC_START, vflags, 1);
 
 	/* We don't bolt the stack for the time being - we're in boot,
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index abfaabf..8548dcf 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -59,10 +59,19 @@ _GLOBAL(slb_miss_kernel_load_linear)
 	li	r11,0
 	b	slb_finish_load
 
-1:	/* vmalloc/ioremap mapping encoding bits, the "li" instruction below
+1:	/* vmalloc/ioremap mapping encoding bits, the "li" instructions below
 	 * will be patched by the kernel at boot
 	 */
-_GLOBAL(slb_miss_kernel_load_virtual)
+BEGIN_FTR_SECTION
+	/* check whether this is in vmalloc or ioremap space */
+	clrldi	r11,r10,48
+	cmpldi	r11,(VMALLOC_SIZE >> 28) - 1
+	bgt	5f
+	lhz	r11,PACAVMALLOCSLLP(r13)
+	b	slb_finish_load
+5:
+END_FTR_SECTION_IFCLR(CPU_FTR_CI_LARGE_PAGE)
+_GLOBAL(slb_miss_kernel_load_io)
 	li	r11,0
 	b	slb_finish_load
 
@@ -96,9 +105,7 @@ _GLOBAL(slb_miss_user_load_huge)
 1:
 #endif /* CONFIG_HUGETLB_PAGE */
 
-_GLOBAL(slb_miss_user_load_normal)
-	li	r11,0
-
+	lhz	r11,PACACONTEXTSLLP(r13)
 2:
 	ld	r9,PACACONTEXTID(r13)
 	rldimi	r10,r9,USER_ESID_BITS,0
diff --git a/arch/powerpc/mm/stab.c b/arch/powerpc/mm/stab.c
index 4a9291d9..691320c 100644
--- a/arch/powerpc/mm/stab.c
+++ b/arch/powerpc/mm/stab.c
@@ -200,10 +200,6 @@ void switch_stab(struct task_struct *tsk, struct mm_struct *mm)
 
 	__get_cpu_var(stab_cache_ptr) = 0;
 
-#ifdef CONFIG_PPC_64K_PAGES
-	get_paca()->pgdir = mm->pgd;
-#endif /* CONFIG_PPC_64K_PAGES */
-
 	/* Now preload some entries for the new task */
 	if (test_tsk_thread_flag(tsk, TIF_32BIT))
 		unmapped_base = TASK_UNMAPPED_BASE_USER32;
diff --git a/arch/powerpc/mm/tlb_32.c b/arch/powerpc/mm/tlb_32.c
index ad580f3..02eb23e 100644
--- a/arch/powerpc/mm/tlb_32.c
+++ b/arch/powerpc/mm/tlb_32.c
@@ -42,7 +42,7 @@ void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, unsigned long addr)
 
 	if (Hash != 0) {
 		ptephys = __pa(ptep) & PAGE_MASK;
-		flush_hash_pages(mm->context, addr, ptephys, 1);
+		flush_hash_pages(mm->context.id, addr, ptephys, 1);
 	}
 }
 
@@ -102,7 +102,7 @@ static void flush_range(struct mm_struct *mm, unsigned long start,
 	pmd_t *pmd;
 	unsigned long pmd_end;
 	int count;
-	unsigned int ctx = mm->context;
+	unsigned int ctx = mm->context.id;
 
 	if (Hash == 0) {
 		_tlbia();
@@ -172,7 +172,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 	mm = (vmaddr < TASK_SIZE)? vma->vm_mm: &init_mm;
 	pmd = pmd_offset(pgd_offset(mm, vmaddr), vmaddr);
 	if (!pmd_none(*pmd))
-		flush_hash_pages(mm->context, vmaddr, pmd_val(*pmd), 1);
+		flush_hash_pages(mm->context.id, vmaddr, pmd_val(*pmd), 1);
 	FINISH_FLUSH;
 }
 
diff --git a/arch/powerpc/mm/tlb_64.c b/arch/powerpc/mm/tlb_64.c
index f734b11..e7449b0 100644
--- a/arch/powerpc/mm/tlb_64.c
+++ b/arch/powerpc/mm/tlb_64.c
@@ -131,7 +131,7 @@ void hpte_update(struct mm_struct *mm, unsigned long addr,
 {
 	struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
 	unsigned long vsid;
-	unsigned int psize = mmu_virtual_psize;
+	unsigned int psize;
 	int i;
 
 	i = batch->index;
@@ -148,7 +148,8 @@ void hpte_update(struct mm_struct *mm, unsigned long addr,
 #else
 		BUG();
 #endif
-	}
+	} else
+		psize = pte_pagesize_index(pte);
 
 	/*
 	 * This can happen when we are in the middle of a TLB batch and