15 files changed, 414 insertions, 61 deletions

diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index d7ec9552229..f0e43559970 100644
--- a/arch/mips/mm/Makefile
+++ b/arch/mips/mm/Makefile
@@ -8,6 +8,7 @@ obj-y				+= cache.o dma-default.o extable.o fault.o \
 obj-$(CONFIG_32BIT)		+= ioremap.o pgtable-32.o
 obj-$(CONFIG_64BIT)		+= pgtable-64.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
+obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 
 obj-$(CONFIG_CPU_LOONGSON2)	+= c-r4k.o cex-gen.o tlb-r4k.o
 obj-$(CONFIG_CPU_MIPS32)	+= c-r4k.o cex-gen.o tlb-r4k.o
diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c
index 44d01a0a849..b165cdcb281 100644
--- a/arch/mips/mm/c-octeon.c
+++ b/arch/mips/mm/c-octeon.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/smp.h>
 #include <linux/mm.h>
 #include <linux/bitops.h>
 #include <linux/cpu.h>
diff --git a/arch/mips/mm/c-r3k.c b/arch/mips/mm/c-r3k.c
index 5500c20c79a..54e5f7b9f44 100644
--- a/arch/mips/mm/c-r3k.c
+++ b/arch/mips/mm/c-r3k.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/smp.h>
 #include <linux/mm.h>
 
 #include <asm/page.h>
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 171951d2305..6721ee2b1e8 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/linkage.h>
 #include <linux/sched.h>
+#include <linux/smp.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/bitops.h>
@@ -100,6 +101,12 @@ static inline void r4k_blast_dcache_page_dc32(unsigned long addr)
 	blast_dcache32_page(addr);
 }
 
+static inline void r4k_blast_dcache_page_dc64(unsigned long addr)
+{
+	R4600_HIT_CACHEOP_WAR_IMPL;
+	blast_dcache64_page(addr);
+}
+
 static void __cpuinit r4k_blast_dcache_page_setup(void)
 {
 	unsigned long  dc_lsize = cpu_dcache_line_size();
@@ -110,6 +117,8 @@ static void __cpuinit r4k_blast_dcache_page_setup(void)
 		r4k_blast_dcache_page = blast_dcache16_page;
 	else if (dc_lsize == 32)
 		r4k_blast_dcache_page = r4k_blast_dcache_page_dc32;
+	else if (dc_lsize == 64)
+		r4k_blast_dcache_page = r4k_blast_dcache_page_dc64;
 }
 
 static void (* r4k_blast_dcache_page_indexed)(unsigned long addr);
@@ -124,6 +133,8 @@ static void __cpuinit r4k_blast_dcache_page_indexed_setup(void)
 		r4k_blast_dcache_page_indexed = blast_dcache16_page_indexed;
 	else if (dc_lsize == 32)
 		r4k_blast_dcache_page_indexed = blast_dcache32_page_indexed;
+	else if (dc_lsize == 64)
+		r4k_blast_dcache_page_indexed = blast_dcache64_page_indexed;
 }
 
 static void (* r4k_blast_dcache)(void);
@@ -138,6 +149,8 @@ static void __cpuinit r4k_blast_dcache_setup(void)
 		r4k_blast_dcache = blast_dcache16;
 	else if (dc_lsize == 32)
 		r4k_blast_dcache = blast_dcache32;
+	else if (dc_lsize == 64)
+		r4k_blast_dcache = blast_dcache64;
 }
 
 /* force code alignment (used for TX49XX_ICACHE_INDEX_INV_WAR) */
diff --git a/arch/mips/mm/c-tx39.c b/arch/mips/mm/c-tx39.c
index f7c8f9ce39c..6515b441871 100644
--- a/arch/mips/mm/c-tx39.c
+++ b/arch/mips/mm/c-tx39.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/smp.h>
 #include <linux/mm.h>
 
 #include <asm/cacheops.h>
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index 4fdb7f5216b..7e48e76148a 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -20,9 +20,10 @@
 
 #include <dma-coherence.h>
 
-static inline unsigned long dma_addr_to_virt(dma_addr_t dma_addr)
+static inline unsigned long dma_addr_to_virt(struct device *dev,
+	dma_addr_t dma_addr)
 {
-	unsigned long addr = plat_dma_addr_to_phys(dma_addr);
+	unsigned long addr = plat_dma_addr_to_phys(dev, dma_addr);
 
 	return (unsigned long)phys_to_virt(addr);
 }
@@ -111,7 +112,7 @@ EXPORT_SYMBOL(dma_alloc_coherent);
 void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
 	dma_addr_t dma_handle)
 {
-	plat_unmap_dma_mem(dev, dma_handle);
+	plat_unmap_dma_mem(dev, dma_handle, size, DMA_BIDIRECTIONAL);
 	free_pages((unsigned long) vaddr, get_order(size));
 }
 
@@ -122,7 +123,7 @@ void dma_free_coherent(struct device *dev, size_t size, void *vaddr,
 {
 	unsigned long addr = (unsigned long) vaddr;
 
-	plat_unmap_dma_mem(dev, dma_handle);
+	plat_unmap_dma_mem(dev, dma_handle, size, DMA_BIDIRECTIONAL);
 
 	if (!plat_device_is_coherent(dev))
 		addr = CAC_ADDR(addr);
@@ -170,10 +171,10 @@ void dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
 	enum dma_data_direction direction)
 {
 	if (cpu_is_noncoherent_r10000(dev))
-		__dma_sync(dma_addr_to_virt(dma_addr), size,
+		__dma_sync(dma_addr_to_virt(dev, dma_addr), size,
 		           direction);
 
-	plat_unmap_dma_mem(dev, dma_addr);
+	plat_unmap_dma_mem(dev, dma_addr, size, direction);
 }
 
 EXPORT_SYMBOL(dma_unmap_single);
@@ -232,7 +233,7 @@ void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
 			if (addr)
 				__dma_sync(addr, sg->length, direction);
 		}
-		plat_unmap_dma_mem(dev, sg->dma_address);
+		plat_unmap_dma_mem(dev, sg->dma_address, sg->length, direction);
 	}
 }
 
@@ -246,7 +247,7 @@ void dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
 	if (cpu_is_noncoherent_r10000(dev)) {
 		unsigned long addr;
 
-		addr = dma_addr_to_virt(dma_handle);
+		addr = dma_addr_to_virt(dev, dma_handle);
 		__dma_sync(addr, size, direction);
 	}
 }
@@ -262,7 +263,7 @@ void dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
 	if (!plat_device_is_coherent(dev)) {
 		unsigned long addr;
 
-		addr = dma_addr_to_virt(dma_handle);
+		addr = dma_addr_to_virt(dev, dma_handle);
 		__dma_sync(addr, size, direction);
 	}
 }
@@ -277,7 +278,7 @@ void dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
 	if (cpu_is_noncoherent_r10000(dev)) {
 		unsigned long addr;
 
-		addr = dma_addr_to_virt(dma_handle);
+		addr = dma_addr_to_virt(dev, dma_handle);
 		__dma_sync(addr + offset, size, direction);
 	}
 }
@@ -293,7 +294,7 @@ void dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
 	if (!plat_device_is_coherent(dev)) {
 		unsigned long addr;
 
-		addr = dma_addr_to_virt(dma_handle);
+		addr = dma_addr_to_virt(dev, dma_handle);
 		__dma_sync(addr + offset, size, direction);
 	}
 }
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 55767ad9f00..6751ce9ede9 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -102,7 +102,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, write);
+	fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/mips/mm/highmem.c b/arch/mips/mm/highmem.c
index 2b1309b2580..e274fda329f 100644
--- a/arch/mips/mm/highmem.c
+++ b/arch/mips/mm/highmem.c
@@ -1,5 +1,6 @@
 #include <linux/module.h>
 #include <linux/highmem.h>
+#include <linux/smp.h>
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
 
diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c
new file mode 100644
index 00000000000..471c09aa161
--- /dev/null
+++ b/arch/mips/mm/hugetlbpage.c
@@ -0,0 +1,101 @@
+/*
+ * MIPS Huge TLB Page Support for Kernel.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
+ * Copyright 2005, Embedded Alley Solutions, Inc.
+ * Matt Porter <mporter@embeddedalley.com>
+ * Copyright (C) 2008, 2009 Cavium Networks, Inc.
+ */
+
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/smp_lock.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/sysctl.h>
+#include <asm/mman.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+
+pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr,
+		      unsigned long sz)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pte_t *pte = NULL;
+
+	pgd = pgd_offset(mm, addr);
+	pud = pud_alloc(mm, pgd, addr);
+	if (pud)
+		pte = (pte_t *)pmd_alloc(mm, pud, addr);
+
+	return pte;
+}
+
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd = NULL;
+
+	pgd = pgd_offset(mm, addr);
+	if (pgd_present(*pgd)) {
+		pud = pud_offset(pgd, addr);
+		if (pud_present(*pud))
+			pmd = pmd_offset(pud, addr);
+	}
+	return (pte_t *) pmd;
+}
+
+int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+{
+	return 0;
+}
+
+/*
+ * This function checks for proper alignment of input addr and len parameters.
+ */
+int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
+{
+	if (len & ~HPAGE_MASK)
+		return -EINVAL;
+	if (addr & ~HPAGE_MASK)
+		return -EINVAL;
+	return 0;
+}
+
+struct page *
+follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+int pmd_huge(pmd_t pmd)
+{
+	return (pmd_val(pmd) & _PAGE_HUGE) != 0;
+}
+
+int pud_huge(pud_t pud)
+{
+	return (pud_val(pud) & _PAGE_HUGE) != 0;
+}
+
+struct page *
+follow_huge_pmd(struct mm_struct *mm, unsigned long address,
+		pmd_t *pmd, int write)
+{
+	struct page *page;
+
+	page = pte_page(*(pte_t *)pmd);
+	if (page)
+		page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT);
+	return page;
+}
+
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index c5511294a9e..0e820508ff2 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
+#include <linux/smp.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/string.h>
diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c
index 48060c635ac..f5c73754d66 100644
--- a/arch/mips/mm/page.c
+++ b/arch/mips/mm/page.c
@@ -10,6 +10,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/smp.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/proc_fs.h>
diff --git a/arch/mips/mm/tlb-r3k.c b/arch/mips/mm/tlb-r3k.c
index 1c0048a6f5c..0f5ab236ab6 100644
--- a/arch/mips/mm/tlb-r3k.c
+++ b/arch/mips/mm/tlb-r3k.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/smp.h>
 #include <linux/mm.h>
 
 #include <asm/page.h>
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index 892be426787..cee502caf39 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -10,7 +10,9 @@
  */
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/smp.h>
 #include <linux/mm.h>
+#include <linux/hugetlb.h>
 
 #include <asm/cpu.h>
 #include <asm/bootinfo.h>
@@ -295,21 +297,41 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte)
 	pudp = pud_offset(pgdp, address);
 	pmdp = pmd_offset(pudp, address);
 	idx = read_c0_index();
-	ptep = pte_offset_map(pmdp, address);
+#ifdef CONFIG_HUGETLB_PAGE
+	/* this could be a huge page  */
+	if (pmd_huge(*pmdp)) {
+		unsigned long lo;
+		write_c0_pagemask(PM_HUGE_MASK);
+		ptep = (pte_t *)pmdp;
+		lo = pte_val(*ptep) >> 6;
+		write_c0_entrylo0(lo);
+		write_c0_entrylo1(lo + (HPAGE_SIZE >> 7));
+
+		mtc0_tlbw_hazard();
+		if (idx < 0)
+			tlb_write_random();
+		else
+			tlb_write_indexed();
+		write_c0_pagemask(PM_DEFAULT_MASK);
+	} else
+#endif
+	{
+		ptep = pte_offset_map(pmdp, address);
 
 #if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32)
-	write_c0_entrylo0(ptep->pte_high);
-	ptep++;
-	write_c0_entrylo1(ptep->pte_high);
+		write_c0_entrylo0(ptep->pte_high);
+		ptep++;
+		write_c0_entrylo1(ptep->pte_high);
 #else
-	write_c0_entrylo0(pte_val(*ptep++) >> 6);
-	write_c0_entrylo1(pte_val(*ptep) >> 6);
+		write_c0_entrylo0(pte_val(*ptep++) >> 6);
+		write_c0_entrylo1(pte_val(*ptep) >> 6);
 #endif
-	mtc0_tlbw_hazard();
-	if (idx < 0)
-		tlb_write_random();
-	else
-		tlb_write_indexed();
+		mtc0_tlbw_hazard();
+		if (idx < 0)
+			tlb_write_random();
+		else
+			tlb_write_indexed();
+	}
 	tlbw_use_hazard();
 	FLUSH_ITLB_VM(vma);
 	EXIT_CRITICAL(flags);
diff --git a/arch/mips/mm/tlb-r8k.c b/arch/mips/mm/tlb-r8k.c
index 4ec95cc2df2..2b82f23df1a 100644
--- a/arch/mips/mm/tlb-r8k.c
+++ b/arch/mips/mm/tlb-r8k.c
@@ -10,6 +10,7 @@
  */
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/smp.h>
 #include <linux/mm.h>
 
 #include <asm/cpu.h>
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 0615b62efd6..9a17bf8395d 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -6,8 +6,9 @@
  * Synthesize TLB refill handlers at runtime.
  *
  * Copyright (C) 2004, 2005, 2006, 2008  Thiemo Seufer
- * Copyright (C) 2005, 2007  Maciej W. Rozycki
+ * Copyright (C) 2005, 2007, 2008, 2009  Maciej W. Rozycki
  * Copyright (C) 2006  Ralf Baechle (ralf@linux-mips.org)
+ * Copyright (C) 2008, 2009 Cavium Networks, Inc.
  *
  * ... and the days got worse and worse and now you see
  * I've gone completly out of my mind.
@@ -19,8 +20,10 @@
  * (Condolences to Napoleon XIV)
  */
 
+#include <linux/bug.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <linux/smp.h>
 #include <linux/string.h>
 #include <linux/init.h>
 
@@ -82,6 +85,9 @@ enum label_id {
 	label_nopage_tlbm,
 	label_smp_pgtable_change,
 	label_r3000_write_probe_fail,
+#ifdef CONFIG_HUGETLB_PAGE
+	label_tlb_huge_update,
+#endif
 };
 
 UASM_L_LA(_second_part)
@@ -98,6 +104,9 @@ UASM_L_LA(_nopage_tlbs)
 UASM_L_LA(_nopage_tlbm)
 UASM_L_LA(_smp_pgtable_change)
 UASM_L_LA(_r3000_write_probe_fail)
+#ifdef CONFIG_HUGETLB_PAGE
+UASM_L_LA(_tlb_huge_update)
+#endif
 
 /*
  * For debug purposes.
@@ -125,6 +134,7 @@ static inline void dump_handler(const u32 *handler, int count)
 #define C0_TCBIND	2, 2
 #define C0_ENTRYLO1	3, 0
 #define C0_CONTEXT	4, 0
+#define C0_PAGEMASK	5, 0
 #define C0_BADVADDR	8, 0
 #define C0_ENTRYHI	10, 0
 #define C0_EPC		14, 0
@@ -258,7 +268,8 @@ static void __cpuinit build_tlb_write_entry(u32 **p, struct uasm_label **l,
 	}
 
 	if (cpu_has_mips_r2) {
-		uasm_i_ehb(p);
+		if (cpu_has_mips_r2_exec_hazard)
+			uasm_i_ehb(p);
 		tlbw(p);
 		return;
 	}
@@ -310,7 +321,6 @@ static void __cpuinit build_tlb_write_entry(u32 **p, struct uasm_label **l,
 	case CPU_BCM3302:
 	case CPU_BCM4710:
 	case CPU_LOONGSON2:
-	case CPU_CAVIUM_OCTEON:
 	case CPU_R5500:
 		if (m4kc_tlbp_war())
 			uasm_i_nop(p);
@@ -382,6 +392,98 @@ static void __cpuinit build_tlb_write_entry(u32 **p, struct uasm_label **l,
 	}
 }
 
+#ifdef CONFIG_HUGETLB_PAGE
+static __cpuinit void build_huge_tlb_write_entry(u32 **p,
+						 struct uasm_label **l,
+						 struct uasm_reloc **r,
+						 unsigned int tmp,
+						 enum tlb_write_entry wmode)
+{
+	/* Set huge page tlb entry size */
+	uasm_i_lui(p, tmp, PM_HUGE_MASK >> 16);
+	uasm_i_ori(p, tmp, tmp, PM_HUGE_MASK & 0xffff);
+	uasm_i_mtc0(p, tmp, C0_PAGEMASK);
+
+	build_tlb_write_entry(p, l, r, wmode);
+
+	/* Reset default page size */
+	if (PM_DEFAULT_MASK >> 16) {
+		uasm_i_lui(p, tmp, PM_DEFAULT_MASK >> 16);
+		uasm_i_ori(p, tmp, tmp, PM_DEFAULT_MASK & 0xffff);
+		uasm_il_b(p, r, label_leave);
+		uasm_i_mtc0(p, tmp, C0_PAGEMASK);
+	} else if (PM_DEFAULT_MASK) {
+		uasm_i_ori(p, tmp, 0, PM_DEFAULT_MASK);
+		uasm_il_b(p, r, label_leave);
+		uasm_i_mtc0(p, tmp, C0_PAGEMASK);
+	} else {
+		uasm_il_b(p, r, label_leave);
+		uasm_i_mtc0(p, 0, C0_PAGEMASK);
+	}
+}
+
+/*
+ * Check if Huge PTE is present, if so then jump to LABEL.
+ */
+static void __cpuinit
+build_is_huge_pte(u32 **p, struct uasm_reloc **r, unsigned int tmp,
+		unsigned int pmd, int lid)
+{
+	UASM_i_LW(p, tmp, 0, pmd);
+	uasm_i_andi(p, tmp, tmp, _PAGE_HUGE);
+	uasm_il_bnez(p, r, tmp, lid);
+}
+
+static __cpuinit void build_huge_update_entries(u32 **p,
+						unsigned int pte,
+						unsigned int tmp)
+{
+	int small_sequence;
+
+	/*
+	 * A huge PTE describes an area the size of the
+	 * configured huge page size. This is twice the
+	 * of the large TLB entry size we intend to use.
+	 * A TLB entry half the size of the configured
+	 * huge page size is configured into entrylo0
+	 * and entrylo1 to cover the contiguous huge PTE
+	 * address space.
+	 */
+	small_sequence = (HPAGE_SIZE >> 7) < 0x10000;
+
+	/* We can clobber tmp.  It isn't used after this.*/
+	if (!small_sequence)
+		uasm_i_lui(p, tmp, HPAGE_SIZE >> (7 + 16));
+
+	UASM_i_SRL(p, pte, pte, 6); /* convert to entrylo */
+	uasm_i_mtc0(p, pte, C0_ENTRYLO0); /* load it */
+	/* convert to entrylo1 */
+	if (small_sequence)
+		UASM_i_ADDIU(p, pte, pte, HPAGE_SIZE >> 7);
+	else
+		UASM_i_ADDU(p, pte, pte, tmp);
+
+	uasm_i_mtc0(p, pte, C0_ENTRYLO1); /* load it */
+}
+
+static __cpuinit void build_huge_handler_tail(u32 **p,
+					      struct uasm_reloc **r,
+					      struct uasm_label **l,
+					      unsigned int pte,
+					      unsigned int ptr)
+{
+#ifdef CONFIG_SMP
+	UASM_i_SC(p, pte, 0, ptr);
+	uasm_il_beqz(p, r, pte, label_tlb_huge_update);
+	UASM_i_LW(p, pte, 0, ptr); /* Needed because SC killed our PTE */
+#else
+	UASM_i_SW(p, pte, 0, ptr);
+#endif
+	build_huge_update_entries(p, pte, ptr);
+	build_huge_tlb_write_entry(p, l, r, pte, tlb_indexed);
+}
+#endif /* CONFIG_HUGETLB_PAGE */
+
 #ifdef CONFIG_64BIT
 /*
  * TMP and PTR are scratch.
@@ -649,6 +751,14 @@ static void __cpuinit build_update_entries(u32 **p, unsigned int tmp,
 #endif
 }
 
+/*
+ * For a 64-bit kernel, we are using the 64-bit XTLB refill exception
+ * because EXL == 0.  If we wrap, we can also use the 32 instruction
+ * slots before the XTLB refill exception handler which belong to the
+ * unused TLB refill exception.
+ */
+#define MIPS64_REFILL_INSNS 32
+
 static void __cpuinit build_r4000_tlb_refill_handler(void)
 {
 	u32 *p = tlb_handler;
@@ -680,12 +790,23 @@ static void __cpuinit build_r4000_tlb_refill_handler(void)
 	build_get_pgde32(&p, K0, K1); /* get pgd in K1 */
 #endif
 
+#ifdef CONFIG_HUGETLB_PAGE
+	build_is_huge_pte(&p, &r, K0, K1, label_tlb_huge_update);
+#endif
+
 	build_get_ptep(&p, K0, K1);
 	build_update_entries(&p, K0, K1);
 	build_tlb_write_entry(&p, &l, &r, tlb_random);
 	uasm_l_leave(&l, p);
 	uasm_i_eret(&p); /* return from trap */
 
+#ifdef CONFIG_HUGETLB_PAGE
+	uasm_l_tlb_huge_update(&l, p);
+	UASM_i_LW(&p, K0, 0, K1);
+	build_huge_update_entries(&p, K0, K1);
+	build_huge_tlb_write_entry(&p, &l, &r, K0, tlb_random);
+#endif
+
 #ifdef CONFIG_64BIT
 	build_get_pgd_vmalloc64(&p, &l, &r, K0, K1);
 #endif
@@ -702,9 +823,10 @@ static void __cpuinit build_r4000_tlb_refill_handler(void)
 	if ((p - tlb_handler) > 64)
 		panic("TLB refill handler space exceeded");
 #else
-	if (((p - tlb_handler) > 63)
-	    || (((p - tlb_handler) > 61)
-		&& uasm_insn_has_bdelay(relocs, tlb_handler + 29)))
+	if (((p - tlb_handler) > (MIPS64_REFILL_INSNS * 2) - 1)
+	    || (((p - tlb_handler) > (MIPS64_REFILL_INSNS * 2) - 3)
+		&& uasm_insn_has_bdelay(relocs,
+					tlb_handler + MIPS64_REFILL_INSNS - 3)))
 		panic("TLB refill handler space exceeded");
 #endif
 
@@ -717,39 +839,74 @@ static void __cpuinit build_r4000_tlb_refill_handler(void)
 	uasm_copy_handler(relocs, labels, tlb_handler, p, f);
 	final_len = p - tlb_handler;
 #else /* CONFIG_64BIT */
-	f = final_handler + 32;
-	if ((p - tlb_handler) <= 32) {
+	f = final_handler + MIPS64_REFILL_INSNS;
+	if ((p - tlb_handler) <= MIPS64_REFILL_INSNS) {
 		/* Just copy the handler. */
 		uasm_copy_handler(relocs, labels, tlb_handler, p, f);
 		final_len = p - tlb_handler;
 	} else {
-		u32 *split = tlb_handler + 30;
+#if defined(CONFIG_HUGETLB_PAGE)
+		const enum label_id ls = label_tlb_huge_update;
+#elif defined(MODULE_START)
+		const enum label_id ls = label_module_alloc;
+#else
+		const enum label_id ls = label_vmalloc;
+#endif
+		u32 *split;
+		int ov = 0;
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(labels) && labels[i].lab != ls; i++)
+			;
+		BUG_ON(i == ARRAY_SIZE(labels));
+		split = labels[i].addr;
 
 		/*
-		 * Find the split point.
+		 * See if we have overflown one way or the other.
 		 */
-		if (uasm_insn_has_bdelay(relocs, split - 1))
-			split--;
-
+		if (split > tlb_handler + MIPS64_REFILL_INSNS ||
+		    split < p - MIPS64_REFILL_INSNS)
+			ov = 1;
+
+		if (ov) {
+			/*
+			 * Split two instructions before the end.  One
+			 * for the branch and one for the instruction
+			 * in the delay slot.
+			 */
+			split = tlb_handler + MIPS64_REFILL_INSNS - 2;
+
+			/*
+			 * If the branch would fall in a delay slot,
+			 * we must back up an additional instruction
+			 * so that it is no longer in a delay slot.
+			 */
+			if (uasm_insn_has_bdelay(relocs, split - 1))
+				split--;
+		}
 		/* Copy first part of the handler. */
 		uasm_copy_handler(relocs, labels, tlb_handler, split, f);
 		f += split - tlb_handler;
 
-		/* Insert branch. */
-		uasm_l_split(&l, final_handler);
-		uasm_il_b(&f, &r, label_split);
-		if (uasm_insn_has_bdelay(relocs, split))
-			uasm_i_nop(&f);
-		else {
-			uasm_copy_handler(relocs, labels, split, split + 1, f);
-			uasm_move_labels(labels, f, f + 1, -1);
-			f++;
-			split++;
+		if (ov) {
+			/* Insert branch. */
+			uasm_l_split(&l, final_handler);
+			uasm_il_b(&f, &r, label_split);
+			if (uasm_insn_has_bdelay(relocs, split))
+				uasm_i_nop(&f);
+			else {
+				uasm_copy_handler(relocs, labels,
+						  split, split + 1, f);
+				uasm_move_labels(labels, f, f + 1, -1);
+				f++;
+				split++;
+			}
 		}
 
 		/* Copy the rest of the handler. */
 		uasm_copy_handler(relocs, labels, split, p, final_handler);
-		final_len = (f - (final_handler + 32)) + (p - split);
+		final_len = (f - (final_handler + MIPS64_REFILL_INSNS)) +
+			    (p - split);
 	}
 #endif /* CONFIG_64BIT */
 
@@ -782,7 +939,7 @@ u32 handle_tlbs[FASTPATH_SIZE] __cacheline_aligned;
 u32 handle_tlbm[FASTPATH_SIZE] __cacheline_aligned;
 
 static void __cpuinit
-iPTE_LW(u32 **p, struct uasm_label **l, unsigned int pte, unsigned int ptr)
+iPTE_LW(u32 **p, unsigned int pte, unsigned int ptr)
 {
 #ifdef CONFIG_SMP
 # ifdef CONFIG_64BIT_PHYS_ADDR
@@ -862,13 +1019,13 @@ iPTE_SW(u32 **p, struct uasm_reloc **r, unsigned int pte, unsigned int ptr,
  * with it's original value.
  */
 static void __cpuinit
-build_pte_present(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
+build_pte_present(u32 **p, struct uasm_reloc **r,
 		  unsigned int pte, unsigned int ptr, enum label_id lid)
 {
 	uasm_i_andi(p, pte, pte, _PAGE_PRESENT | _PAGE_READ);
 	uasm_i_xori(p, pte, pte, _PAGE_PRESENT | _PAGE_READ);
 	uasm_il_bnez(p, r, pte, lid);
-	iPTE_LW(p, l, pte, ptr);
+	iPTE_LW(p, pte, ptr);
 }
 
 /* Make PTE valid, store result in PTR. */
@@ -886,13 +1043,13 @@ build_make_valid(u32 **p, struct uasm_reloc **r, unsigned int pte,
  * restore PTE with value from PTR when done.
  */
 static void __cpuinit
-build_pte_writable(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
+build_pte_writable(u32 **p, struct uasm_reloc **r,
 		   unsigned int pte, unsigned int ptr, enum label_id lid)
 {
 	uasm_i_andi(p, pte, pte, _PAGE_PRESENT | _PAGE_WRITE);
 	uasm_i_xori(p, pte, pte, _PAGE_PRESENT | _PAGE_WRITE);
 	uasm_il_bnez(p, r, pte, lid);
-	iPTE_LW(p, l, pte, ptr);
+	iPTE_LW(p, pte, ptr);
 }
 
 /* Make PTE writable, update software status bits as well, then store
@@ -913,12 +1070,12 @@ build_make_write(u32 **p, struct uasm_reloc **r, unsigned int pte,
  * restore PTE with value from PTR when done.
  */
 static void __cpuinit
-build_pte_modifiable(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
+build_pte_modifiable(u32 **p, struct uasm_reloc **r,
 		     unsigned int pte, unsigned int ptr, enum label_id lid)
 {
 	uasm_i_andi(p, pte, pte, _PAGE_WRITE);
 	uasm_il_beqz(p, r, pte, lid);
-	iPTE_LW(p, l, pte, ptr);
+	iPTE_LW(p, pte, ptr);
 }
 
 /*
@@ -994,7 +1151,7 @@ static void __cpuinit build_r3000_tlb_load_handler(void)
 	memset(relocs, 0, sizeof(relocs));
 
 	build_r3000_tlbchange_handler_head(&p, K0, K1);
-	build_pte_present(&p, &l, &r, K0, K1, label_nopage_tlbl);
+	build_pte_present(&p, &r, K0, K1, label_nopage_tlbl);
 	uasm_i_nop(&p); /* load delay */
 	build_make_valid(&p, &r, K0, K1);
 	build_r3000_tlb_reload_write(&p, &l, &r, K0, K1);
@@ -1024,7 +1181,7 @@ static void __cpuinit build_r3000_tlb_store_handler(void)
 	memset(relocs, 0, sizeof(relocs));
 
 	build_r3000_tlbchange_handler_head(&p, K0, K1);
-	build_pte_writable(&p, &l, &r, K0, K1, label_nopage_tlbs);
+	build_pte_writable(&p, &r, K0, K1, label_nopage_tlbs);
 	uasm_i_nop(&p); /* load delay */
 	build_make_write(&p, &r, K0, K1);
 	build_r3000_tlb_reload_write(&p, &l, &r, K0, K1);
@@ -1054,7 +1211,7 @@ static void __cpuinit build_r3000_tlb_modify_handler(void)
 	memset(relocs, 0, sizeof(relocs));
 
 	build_r3000_tlbchange_handler_head(&p, K0, K1);
-	build_pte_modifiable(&p, &l, &r, K0, K1, label_nopage_tlbm);
+	build_pte_modifiable(&p, &r, K0, K1, label_nopage_tlbm);
 	uasm_i_nop(&p); /* load delay */
 	build_make_write(&p, &r, K0, K1);
 	build_r3000_pte_reload_tlbwi(&p, K0, K1);
@@ -1087,6 +1244,15 @@ build_r4000_tlbchange_handler_head(u32 **p, struct uasm_label **l,
 	build_get_pgde32(p, pte, ptr); /* get pgd in ptr */
 #endif
 
+#ifdef CONFIG_HUGETLB_PAGE
+	/*
+	 * For huge tlb entries, pmd doesn't contain an address but
+	 * instead contains the tlb pte. Check the PAGE_HUGE bit and
+	 * see if we need to jump to huge tlb processing.
+	 */
+	build_is_huge_pte(p, r, pte, ptr, label_tlb_huge_update);
+#endif
+
 	UASM_i_MFC0(p, pte, C0_BADVADDR);
 	UASM_i_LW(p, ptr, 0, ptr);
 	UASM_i_SRL(p, pte, pte, PAGE_SHIFT + PTE_ORDER - PTE_T_LOG2);
@@ -1096,7 +1262,7 @@ build_r4000_tlbchange_handler_head(u32 **p, struct uasm_label **l,
 #ifdef CONFIG_SMP
 	uasm_l_smp_pgtable_change(l, *p);
 #endif
-	iPTE_LW(p, l, pte, ptr); /* get even pte */
+	iPTE_LW(p, pte, ptr); /* get even pte */
 	if (!m4kc_tlbp_war())
 		build_tlb_probe_entry(p);
 }
@@ -1138,12 +1304,25 @@ static void __cpuinit build_r4000_tlb_load_handler(void)
 	}
 
 	build_r4000_tlbchange_handler_head(&p, &l, &r, K0, K1);
-	build_pte_present(&p, &l, &r, K0, K1, label_nopage_tlbl);
+	build_pte_present(&p, &r, K0, K1, label_nopage_tlbl);
 	if (m4kc_tlbp_war())
 		build_tlb_probe_entry(&p);
 	build_make_valid(&p, &r, K0, K1);
 	build_r4000_tlbchange_handler_tail(&p, &l, &r, K0, K1);
 
+#ifdef CONFIG_HUGETLB_PAGE
+	/*
+	 * This is the entry point when build_r4000_tlbchange_handler_head
+	 * spots a huge page.
+	 */
+	uasm_l_tlb_huge_update(&l, p);
+	iPTE_LW(&p, K0, K1);
+	build_pte_present(&p, &r, K0, K1, label_nopage_tlbl);
+	build_tlb_probe_entry(&p);
+	uasm_i_ori(&p, K0, K0, (_PAGE_ACCESSED | _PAGE_VALID));
+	build_huge_handler_tail(&p, &r, &l, K0, K1);
+#endif
+
 	uasm_l_nopage_tlbl(&l, p);
 	uasm_i_j(&p, (unsigned long)tlb_do_page_fault_0 & 0x0fffffff);
 	uasm_i_nop(&p);
@@ -1169,12 +1348,26 @@ static void __cpuinit build_r4000_tlb_store_handler(void)
 	memset(relocs, 0, sizeof(relocs));
 
 	build_r4000_tlbchange_handler_head(&p, &l, &r, K0, K1);
-	build_pte_writable(&p, &l, &r, K0, K1, label_nopage_tlbs);
+	build_pte_writable(&p, &r, K0, K1, label_nopage_tlbs);
 	if (m4kc_tlbp_war())
 		build_tlb_probe_entry(&p);
 	build_make_write(&p, &r, K0, K1);
 	build_r4000_tlbchange_handler_tail(&p, &l, &r, K0, K1);
 
+#ifdef CONFIG_HUGETLB_PAGE
+	/*
+	 * This is the entry point when
+	 * build_r4000_tlbchange_handler_head spots a huge page.
+	 */
+	uasm_l_tlb_huge_update(&l, p);
+	iPTE_LW(&p, K0, K1);
+	build_pte_writable(&p, &r, K0, K1, label_nopage_tlbs);
+	build_tlb_probe_entry(&p);
+	uasm_i_ori(&p, K0, K0,
+		   _PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
+	build_huge_handler_tail(&p, &r, &l, K0, K1);
+#endif
+
 	uasm_l_nopage_tlbs(&l, p);
 	uasm_i_j(&p, (unsigned long)tlb_do_page_fault_1 & 0x0fffffff);
 	uasm_i_nop(&p);
@@ -1200,13 +1393,27 @@ static void __cpuinit build_r4000_tlb_modify_handler(void)
 	memset(relocs, 0, sizeof(relocs));
 
 	build_r4000_tlbchange_handler_head(&p, &l, &r, K0, K1);
-	build_pte_modifiable(&p, &l, &r, K0, K1, label_nopage_tlbm);
+	build_pte_modifiable(&p, &r, K0, K1, label_nopage_tlbm);
 	if (m4kc_tlbp_war())
 		build_tlb_probe_entry(&p);
 	/* Present and writable bits set, set accessed and dirty bits. */
 	build_make_write(&p, &r, K0, K1);
 	build_r4000_tlbchange_handler_tail(&p, &l, &r, K0, K1);
 
+#ifdef CONFIG_HUGETLB_PAGE
+	/*
+	 * This is the entry point when
+	 * build_r4000_tlbchange_handler_head spots a huge page.
+	 */
+	uasm_l_tlb_huge_update(&l, p);
+	iPTE_LW(&p, K0, K1);
+	build_pte_modifiable(&p, &r, K0, K1, label_nopage_tlbm);
+	build_tlb_probe_entry(&p);
+	uasm_i_ori(&p, K0, K0,
+		   _PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
+	build_huge_handler_tail(&p, &r, &l, K0, K1);
+#endif
+
 	uasm_l_nopage_tlbm(&l, p);
 	uasm_i_j(&p, (unsigned long)tlb_do_page_fault_1 & 0x0fffffff);
 	uasm_i_nop(&p);