Merge branch 'master' into queue

* master: (15791 commits)
  Linux 3.9-rc1
  btrfs/raid56: Add missing #include <linux/vmalloc.h>
  fix compat_sys_rt_sigprocmask()
  SUNRPC: One line comment fix
  ext4: enable quotas before orphan cleanup
  ext4: don't allow quota mount options when quota feature enabled
  ext4: fix a warning from sparse check for ext4_dir_llseek
  ext4: convert number of blocks to clusters properly
  ext4: fix possible memory leak in ext4_remount()
  jbd2: fix ERR_PTR dereference in jbd2__journal_start
  metag: Provide dma_get_sgtable()
  metag: prom.h: remove declaration of metag_dt_memblock_reserve()
  metag: copy devicetree to non-init memory
  metag: cleanup metag_ksyms.c includes
  metag: move mm/init.c exports out of metag_ksyms.c
  metag: move usercopy.c exports out of metag_ksyms.c
  metag: move setup.c exports out of metag_ksyms.c
  metag: move kick.c exports out of metag_ksyms.c
  metag: move traps.c exports out of metag_ksyms.c
  metag: move irq enable out of irqflags.h on SMP
  ...

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Conflicts:
	arch/x86/kernel/kvmclock.c

24 files changed, 293 insertions, 224 deletions

diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index 90ceb963aaf1..1dcec30ad1c4 100644
--- a/arch/mips/mm/Makefile
+++ b/arch/mips/mm/Makefile
@@ -16,9 +16,9 @@ obj-$(CONFIG_CPU_R3000)		+= c-r3k.o tlb-r3k.o
 obj-$(CONFIG_CPU_R8000)		+= c-r4k.o cex-gen.o tlb-r8k.o
 obj-$(CONFIG_CPU_SB1)		+= c-r4k.o cerr-sb1.o cex-sb1.o tlb-r4k.o
 obj-$(CONFIG_CPU_TX39XX)	+= c-tx39.o tlb-r3k.o
-obj-$(CONFIG_CPU_CAVIUM_OCTEON)	+= c-octeon.o cex-oct.o tlb-r4k.o
+obj-$(CONFIG_CPU_CAVIUM_OCTEON) += c-octeon.o cex-oct.o tlb-r4k.o
 
 obj-$(CONFIG_IP22_CPU_SCACHE)	+= sc-ip22.o
-obj-$(CONFIG_R5000_CPU_SCACHE)  += sc-r5k.o
-obj-$(CONFIG_RM7000_CPU_SCACHE)	+= sc-rm7k.o
+obj-$(CONFIG_R5000_CPU_SCACHE)	+= sc-r5k.o
+obj-$(CONFIG_RM7000_CPU_SCACHE) += sc-rm7k.o
 obj-$(CONFIG_MIPS_CPU_SCACHE)	+= sc-mips.o
diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c
index 44e69e7a4519..8557fb552863 100644
--- a/arch/mips/mm/c-octeon.c
+++ b/arch/mips/mm/c-octeon.c
@@ -5,6 +5,7 @@
  *
  * Copyright (C) 2005-2007 Cavium Networks
  */
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
@@ -28,6 +29,7 @@
 #include <asm/octeon/octeon.h>
 
 unsigned long long cache_err_dcache[NR_CPUS];
+EXPORT_SYMBOL_GPL(cache_err_dcache);
 
 /**
  * Octeon automatically flushes the dcache on tlb changes, so
@@ -104,7 +106,7 @@ static void octeon_flush_icache_all(void)
  * Called to flush all memory associated with a memory
  * context.
  *
- * @mm:     Memory context to flush
+ * @mm:	    Memory context to flush
  */
 static void octeon_flush_cache_mm(struct mm_struct *mm)
 {
@@ -284,39 +286,59 @@ void __cpuinit octeon_cache_init(void)
 	board_cache_error_setup = octeon_cache_error_setup;
 }
 
-/**
+/*
  * Handle a cache error exception
  */
+static RAW_NOTIFIER_HEAD(co_cache_error_chain);
 
-static void  cache_parity_error_octeon(int non_recoverable)
+int register_co_cache_error_notifier(struct notifier_block *nb)
 {
-	unsigned long coreid = cvmx_get_core_num();
-	uint64_t icache_err = read_octeon_c0_icacheerr();
-
-	pr_err("Cache error exception:\n");
-	pr_err("cp0_errorepc == %lx\n", read_c0_errorepc());
-	if (icache_err & 1) {
-		pr_err("CacheErr (Icache) == %llx\n",
-		       (unsigned long long)icache_err);
-		write_octeon_c0_icacheerr(0);
-	}
-	if (cache_err_dcache[coreid] & 1) {
-		pr_err("CacheErr (Dcache) == %llx\n",
-		       (unsigned long long)cache_err_dcache[coreid]);
-		cache_err_dcache[coreid] = 0;
-	}
+	return raw_notifier_chain_register(&co_cache_error_chain, nb);
+}
+EXPORT_SYMBOL_GPL(register_co_cache_error_notifier);
+
+int unregister_co_cache_error_notifier(struct notifier_block *nb)
+{
+	return raw_notifier_chain_unregister(&co_cache_error_chain, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_co_cache_error_notifier);
 
-	if (non_recoverable)
-		panic("Can't handle cache error: nested exception");
+static void co_cache_error_call_notifiers(unsigned long val)
+{
+	int rv = raw_notifier_call_chain(&co_cache_error_chain, val, NULL);
+	if ((rv & ~NOTIFY_STOP_MASK) != NOTIFY_OK) {
+		u64 dcache_err;
+		unsigned long coreid = cvmx_get_core_num();
+		u64 icache_err = read_octeon_c0_icacheerr();
+
+		if (val) {
+			dcache_err = cache_err_dcache[coreid];
+			cache_err_dcache[coreid] = 0;
+		} else {
+			dcache_err = read_octeon_c0_dcacheerr();
+		}
+
+		pr_err("Core%lu: Cache error exception:\n", coreid);
+		pr_err("cp0_errorepc == %lx\n", read_c0_errorepc());
+		if (icache_err & 1) {
+			pr_err("CacheErr (Icache) == %llx\n",
+			       (unsigned long long)icache_err);
+			write_octeon_c0_icacheerr(0);
+		}
+		if (dcache_err & 1) {
+			pr_err("CacheErr (Dcache) == %llx\n",
+			       (unsigned long long)dcache_err);
+		}
+	}
 }
 
-/**
+/*
  * Called when the the exception is recoverable
  */
 
 asmlinkage void cache_parity_error_octeon_recoverable(void)
 {
-	cache_parity_error_octeon(0);
+	co_cache_error_call_notifiers(0);
 }
 
 /**
@@ -325,5 +347,6 @@ asmlinkage void cache_parity_error_octeon_recoverable(void)
 
 asmlinkage void cache_parity_error_octeon_non_recoverable(void)
 {
-	cache_parity_error_octeon(1);
+	co_cache_error_call_notifiers(1);
+	panic("Can't handle cache error: nested exception");
 }
diff --git a/arch/mips/mm/c-r3k.c b/arch/mips/mm/c-r3k.c
index 031c4c2cdf2e..704dc735a59d 100644
--- a/arch/mips/mm/c-r3k.c
+++ b/arch/mips/mm/c-r3k.c
@@ -119,7 +119,7 @@ static void r3k_flush_icache_range(unsigned long start, unsigned long end)
 	write_c0_status((ST0_ISC|ST0_SWC|flags)&~ST0_IEC);
 
 	for (i = 0; i < size; i += 0x080) {
-		asm( 	"sb\t$0, 0x000(%0)\n\t"
+		asm(	"sb\t$0, 0x000(%0)\n\t"
 			"sb\t$0, 0x004(%0)\n\t"
 			"sb\t$0, 0x008(%0)\n\t"
 			"sb\t$0, 0x00c(%0)\n\t"
@@ -176,7 +176,7 @@ static void r3k_flush_dcache_range(unsigned long start, unsigned long end)
 	write_c0_status((ST0_ISC|flags)&~ST0_IEC);
 
 	for (i = 0; i < size; i += 0x080) {
-		asm( 	"sb\t$0, 0x000(%0)\n\t"
+		asm(	"sb\t$0, 0x000(%0)\n\t"
 			"sb\t$0, 0x004(%0)\n\t"
 			"sb\t$0, 0x008(%0)\n\t"
 			"sb\t$0, 0x00c(%0)\n\t"
@@ -285,13 +285,13 @@ static void r3k_flush_cache_sigtramp(unsigned long addr)
 	write_c0_status(flags&~ST0_IEC);
 
 	/* Fill the TLB to avoid an exception with caches isolated. */
-	asm( 	"lw\t$0, 0x000(%0)\n\t"
+	asm(	"lw\t$0, 0x000(%0)\n\t"
 		"lw\t$0, 0x004(%0)\n\t"
 		: : "r" (addr) );
 
 	write_c0_status((ST0_ISC|ST0_SWC|flags)&~ST0_IEC);
 
-	asm( 	"sb\t$0, 0x000(%0)\n\t"
+	asm(	"sb\t$0, 0x000(%0)\n\t"
 		"sb\t$0, 0x004(%0)\n\t"
 		: : "r" (addr) );
 
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 4c32ede464b5..ecca559b8d7b 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -160,7 +160,7 @@ static void __cpuinit r4k_blast_dcache_setup(void)
 		"1:\n\t" \
 		)
 #define CACHE32_UNROLL32_ALIGN	JUMP_TO_ALIGN(10) /* 32 * 32 = 1024 */
-#define CACHE32_UNROLL32_ALIGN2	JUMP_TO_ALIGN(11)
+#define CACHE32_UNROLL32_ALIGN2 JUMP_TO_ALIGN(11)
 
 static inline void blast_r4600_v1_icache32(void)
 {
@@ -177,7 +177,7 @@ static inline void tx49_blast_icache32(void)
 	unsigned long end = start + current_cpu_data.icache.waysize;
 	unsigned long ws_inc = 1UL << current_cpu_data.icache.waybit;
 	unsigned long ws_end = current_cpu_data.icache.ways <<
-	                       current_cpu_data.icache.waybit;
+			       current_cpu_data.icache.waybit;
 	unsigned long ws, addr;
 
 	CACHE32_UNROLL32_ALIGN2;
@@ -208,7 +208,7 @@ static inline void tx49_blast_icache32_page_indexed(unsigned long page)
 	unsigned long end = start + PAGE_SIZE;
 	unsigned long ws_inc = 1UL << current_cpu_data.icache.waybit;
 	unsigned long ws_end = current_cpu_data.icache.ways <<
-	                       current_cpu_data.icache.waybit;
+			       current_cpu_data.icache.waybit;
 	unsigned long ws, addr;
 
 	CACHE32_UNROLL32_ALIGN2;
@@ -632,20 +632,14 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 		if (size >= scache_size)
 			r4k_blast_scache();
 		else {
-			unsigned long lsize = cpu_scache_line_size();
-			unsigned long almask = ~(lsize - 1);
-
 			/*
 			 * There is no clearly documented alignment requirement
 			 * for the cache instruction on MIPS processors and
 			 * some processors, among them the RM5200 and RM7000
 			 * QED processors will throw an address error for cache
-			 * hit ops with insufficient alignment.  Solved by
+			 * hit ops with insufficient alignment.	 Solved by
 			 * aligning the address to cache line size.
 			 */
-			cache_op(Hit_Writeback_Inv_SD, addr & almask);
-			cache_op(Hit_Writeback_Inv_SD,
-				 (addr + size - 1) & almask);
 			blast_inv_scache_range(addr, addr + size);
 		}
 		__sync();
@@ -655,12 +649,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 	if (cpu_has_safe_index_cacheops && size >= dcache_size) {
 		r4k_blast_dcache();
 	} else {
-		unsigned long lsize = cpu_dcache_line_size();
-		unsigned long almask = ~(lsize - 1);
-
 		R4600_HIT_CACHEOP_WAR_IMPL;
-		cache_op(Hit_Writeback_Inv_D, addr & almask);
-		cache_op(Hit_Writeback_Inv_D, (addr + size - 1)  & almask);
 		blast_inv_dcache_range(addr, addr + size);
 	}
 
@@ -875,7 +864,7 @@ static void __cpuinit probe_pcache(void)
 		icache_size = 1 << (12 + ((config & CONF_IC) >> 9));
 		c->icache.linesz = 16 << ((config & CONF_IB) >> 5);
 		c->icache.ways = 1;
-		c->icache.waybit = 0; 	/* doesn't matter */
+		c->icache.waybit = 0;	/* doesn't matter */
 
 		dcache_size = 1 << (12 + ((config & CONF_DC) >> 6));
 		c->dcache.linesz = 16 << ((config & CONF_DB) >> 4);
@@ -934,7 +923,7 @@ static void __cpuinit probe_pcache(void)
 		icache_size = 1 << (10 + ((config & CONF_IC) >> 9));
 		c->icache.linesz = 16 << ((config & CONF_IB) >> 5);
 		c->icache.ways = 1;
-		c->icache.waybit = 0; 	/* doesn't matter */
+		c->icache.waybit = 0;	/* doesn't matter */
 
 		dcache_size = 1 << (10 + ((config & CONF_DC) >> 6));
 		c->dcache.linesz = 16 << ((config & CONF_DB) >> 4);
@@ -947,7 +936,6 @@ static void __cpuinit probe_pcache(void)
 	case CPU_RM7000:
 		rm7k_erratum31();
 
-	case CPU_RM9000:
 		icache_size = 1 << (12 + ((config & CONF_IC) >> 9));
 		c->icache.linesz = 16 << ((config & CONF_IB) >> 5);
 		c->icache.ways = 4;
@@ -958,9 +946,7 @@ static void __cpuinit probe_pcache(void)
 		c->dcache.ways = 4;
 		c->dcache.waybit = __ffs(dcache_size / c->dcache.ways);
 
-#if !defined(CONFIG_SMP) || !defined(RM9000_CDEX_SMP_WAR)
 		c->options |= MIPS_CPU_CACHE_CDEX_P;
-#endif
 		c->options |= MIPS_CPU_PREFETCH;
 		break;
 
@@ -1000,8 +986,8 @@ static void __cpuinit probe_pcache(void)
 		c->icache.ways = 1 + ((config1 >> 16) & 7);
 
 		icache_size = c->icache.sets *
-		              c->icache.ways *
-		              c->icache.linesz;
+			      c->icache.ways *
+			      c->icache.linesz;
 		c->icache.waybit = __ffs(icache_size/c->icache.ways);
 
 		if (config & 0x8)		/* VI bit */
@@ -1020,8 +1006,8 @@ static void __cpuinit probe_pcache(void)
 		c->dcache.ways = 1 + ((config1 >> 7) & 7);
 
 		dcache_size = c->dcache.sets *
-		              c->dcache.ways *
-		              c->dcache.linesz;
+			      c->dcache.ways *
+			      c->dcache.linesz;
 		c->dcache.waybit = __ffs(dcache_size/c->dcache.ways);
 
 		c->options |= MIPS_CPU_PREFETCH;
@@ -1030,7 +1016,7 @@ static void __cpuinit probe_pcache(void)
 
 	/*
 	 * Processor configuration sanity check for the R4000SC erratum
-	 * #5.  With page sizes larger than 32kB there is no possibility
+	 * #5.	With page sizes larger than 32kB there is no possibility
 	 * to get a VCE exception anymore so we don't care about this
 	 * misconfiguration.  The case is rather theoretical anyway;
 	 * presumably no vendor is shipping his hardware in the "bad"
@@ -1071,6 +1057,7 @@ static void __cpuinit probe_pcache(void)
 		break;
 
 	case CPU_M14KC:
+	case CPU_M14KEC:
 	case CPU_24K:
 	case CPU_34K:
 	case CPU_74K:
@@ -1102,7 +1089,7 @@ static void __cpuinit probe_pcache(void)
 		break;
 	}
 
-#ifdef  CONFIG_CPU_LOONGSON2
+#ifdef	CONFIG_CPU_LOONGSON2
 	/*
 	 * LOONGSON2 has 4 way icache, but when using indexed cache op,
 	 * one op will act on all 4 ways
@@ -1242,10 +1229,9 @@ static void __cpuinit setup_scache(void)
 #ifdef CONFIG_R5000_CPU_SCACHE
 		r5k_sc_init();
 #endif
-                return;
+		return;
 
 	case CPU_RM7000:
-	case CPU_RM9000:
 #ifdef CONFIG_RM7000_CPU_SCACHE
 		rm7k_sc_init();
 #endif
@@ -1348,10 +1334,10 @@ static int __init cca_setup(char *str)
 {
 	get_option(&str, &cca);
 
-	return 1;
+	return 0;
 }
 
-__setup("cca=", cca_setup);
+early_param("cca", cca_setup);
 
 static void __cpuinit coherency_setup(void)
 {
@@ -1401,10 +1387,10 @@ static int __init setcoherentio(char *str)
 {
 	coherentio = 1;
 
-	return 1;
+	return 0;
 }
 
-__setup("coherentio", setcoherentio);
+early_param("coherentio", setcoherentio);
 #endif
 
 static void __cpuinit r4k_cache_error_setup(void)
diff --git a/arch/mips/mm/c-tx39.c b/arch/mips/mm/c-tx39.c
index 87d23cada6d6..ba9da270289f 100644
--- a/arch/mips/mm/c-tx39.c
+++ b/arch/mips/mm/c-tx39.c
@@ -33,9 +33,9 @@ extern int r3k_have_wired_reg;	/* in r3k-tlb.c */
 /* This sequence is required to ensure icache is disabled immediately */
 #define TX39_STOP_STREAMING() \
 __asm__ __volatile__( \
-	".set    push\n\t" \
-	".set    noreorder\n\t" \
-	"b       1f\n\t" \
+	".set	 push\n\t" \
+	".set	 noreorder\n\t" \
+	"b	 1f\n\t" \
 	"nop\n\t" \
 	"1:\n\t" \
 	".set pop" \
@@ -361,7 +361,7 @@ void __cpuinit tx39_cache_init(void)
 		/* TX39/H core (writethru direct-map cache) */
 		__flush_cache_vmap	= tx39__flush_cache_vmap;
 		__flush_cache_vunmap	= tx39__flush_cache_vunmap;
-		flush_cache_all	= tx39h_flush_icache_all;
+		flush_cache_all = tx39h_flush_icache_all;
 		__flush_cache_all	= tx39h_flush_icache_all;
 		flush_cache_mm		= (void *) tx39h_flush_icache_all;
 		flush_cache_range	= (void *) tx39h_flush_icache_all;
@@ -409,8 +409,8 @@ void __cpuinit tx39_cache_init(void)
 		_dma_cache_inv = tx39_dma_cache_inv;
 
 		shm_align_mask = max_t(unsigned long,
-		                       (dcache_size / current_cpu_data.dcache.ways) - 1,
-		                       PAGE_SIZE - 1);
+				       (dcache_size / current_cpu_data.dcache.ways) - 1,
+				       PAGE_SIZE - 1);
 
 		break;
 	}
diff --git a/arch/mips/mm/cerr-sb1.c b/arch/mips/mm/cerr-sb1.c
index 3571090ba178..576add33bf5b 100644
--- a/arch/mips/mm/cerr-sb1.c
+++ b/arch/mips/mm/cerr-sb1.c
@@ -27,7 +27,7 @@
 
 /*
  * We'd like to dump the L2_ECC_TAG register on errors, but errata make
- * that unsafe... So for now we don't.  (BCM1250/BCM112x erratum SOC-48.)
+ * that unsafe... So for now we don't.	(BCM1250/BCM112x erratum SOC-48.)
  */
 #undef DUMP_L2_ECC_TAG_ON_ERROR
 
@@ -48,7 +48,7 @@
 #define CP0_CERRI_EXTERNAL     (1 << 26)
 
 #define CP0_CERRI_IDX_VALID(c) (!((c) & CP0_CERRI_EXTERNAL))
-#define CP0_CERRI_DATA         (CP0_CERRI_DATA_PARITY)
+#define CP0_CERRI_DATA	       (CP0_CERRI_DATA_PARITY)
 
 #define CP0_CERRD_MULTIPLE     (1 << 31)
 #define CP0_CERRD_TAG_STATE    (1 << 30)
@@ -56,8 +56,8 @@
 #define CP0_CERRD_DATA_SBE     (1 << 28)
 #define CP0_CERRD_DATA_DBE     (1 << 27)
 #define CP0_CERRD_EXTERNAL     (1 << 26)
-#define CP0_CERRD_LOAD         (1 << 25)
-#define CP0_CERRD_STORE        (1 << 24)
+#define CP0_CERRD_LOAD	       (1 << 25)
+#define CP0_CERRD_STORE	       (1 << 24)
 #define CP0_CERRD_FILLWB       (1 << 23)
 #define CP0_CERRD_COHERENCY    (1 << 22)
 #define CP0_CERRD_DUPTAG       (1 << 21)
@@ -69,10 +69,10 @@
    (CP0_CERRD_LOAD | CP0_CERRD_STORE | CP0_CERRD_FILLWB | CP0_CERRD_COHERENCY | CP0_CERRD_DUPTAG)
 #define CP0_CERRD_TYPES \
    (CP0_CERRD_TAG_STATE | CP0_CERRD_TAG_ADDRESS | CP0_CERRD_DATA_SBE | CP0_CERRD_DATA_DBE | CP0_CERRD_EXTERNAL)
-#define CP0_CERRD_DATA         (CP0_CERRD_DATA_SBE | CP0_CERRD_DATA_DBE)
+#define CP0_CERRD_DATA	       (CP0_CERRD_DATA_SBE | CP0_CERRD_DATA_DBE)
 
-static uint32_t	extract_ic(unsigned short addr, int data);
-static uint32_t	extract_dc(unsigned short addr, int data);
+static uint32_t extract_ic(unsigned short addr, int data);
+static uint32_t extract_dc(unsigned short addr, int data);
 
 static inline void breakout_errctl(unsigned int val)
 {
@@ -209,11 +209,11 @@ asmlinkage void sb1_cache_error(void)
 	  "=r" (dpahi), "=r" (dpalo), "=r" (eepc));
 
 	cerr_dpa = (((uint64_t)dpahi) << 32) | dpalo;
-	printk(" c0_errorepc ==   %08x\n", eepc);
-	printk(" c0_errctl   ==   %08x", errctl);
+	printk(" c0_errorepc ==	  %08x\n", eepc);
+	printk(" c0_errctl   ==	  %08x", errctl);
 	breakout_errctl(errctl);
 	if (errctl & CP0_ERRCTL_ICACHE) {
-		printk(" c0_cerr_i   ==   %08x", cerr_i);
+		printk(" c0_cerr_i   ==	  %08x", cerr_i);
 		breakout_cerri(cerr_i);
 		if (CP0_CERRI_IDX_VALID(cerr_i)) {
 			/* Check index of EPC, allowing for delay slot */
@@ -229,7 +229,7 @@ asmlinkage void sb1_cache_error(void)
 		}
 	}
 	if (errctl & CP0_ERRCTL_DCACHE) {
-		printk(" c0_cerr_d   ==   %08x", cerr_d);
+		printk(" c0_cerr_d   ==	  %08x", cerr_d);
 		breakout_cerrd(cerr_d);
 		if (CP0_CERRD_DPA_VALID(cerr_d)) {
 			printk(" c0_cerr_dpa == %010llx\n", cerr_dpa);
@@ -256,7 +256,7 @@ asmlinkage void sb1_cache_error(void)
 	/*
 	 * Calling panic() when a fatal cache error occurs scrambles the
 	 * state of the system (and the cache), making it difficult to
-	 * investigate after the fact.  However, if you just stall the CPU,
+	 * investigate after the fact.	However, if you just stall the CPU,
 	 * the other CPU may keep on running, which is typically very
 	 * undesirable.
 	 */
@@ -411,7 +411,7 @@ static uint32_t extract_ic(unsigned short addr, int data)
 				"	dmfc0  $1, $28, 1\n\t"
 				"	dsrl32 %1, $1, 0 \n\t"
 				"	sll    %2, $1, 0 \n\t"
-				"	.set	pop         \n"
+				"	.set	pop	    \n"
 				: "=r" (datahi), "=r" (insta), "=r" (instb)
 				: "r" ((way << 13) | addr | (offset << 3)));
 				predecode = (datahi >> 8) & 0xff;
@@ -441,8 +441,8 @@ static uint8_t dc_ecc(uint64_t dword)
 {
 	uint64_t t;
 	uint32_t w;
-	uint8_t  p;
-	int      i;
+	uint8_t	 p;
+	int	 i;
 
 	p = 0;
 	for (i = 7; i >= 0; i--)
diff --git a/arch/mips/mm/cex-gen.S b/arch/mips/mm/cex-gen.S
index e743622fd24d..45dff5cd4b8e 100644
--- a/arch/mips/mm/cex-gen.S
+++ b/arch/mips/mm/cex-gen.S
@@ -14,17 +14,17 @@
 #include <asm/stackframe.h>
 
 /*
- * Game over.  Go to the button.  Press gently.  Swear where allowed by
+ * Game over.  Go to the button.  Press gently.	 Swear where allowed by
  * legislation.
  */
 	LEAF(except_vec2_generic)
 	.set	noreorder
 	.set	noat
-	.set    mips0
+	.set	mips0
 	/*
 	 * This is a very bad place to be.  Our cache error
 	 * detection has triggered.  If we have write-back data
-	 * in the cache, we may not be able to recover.  As a
+	 * in the cache, we may not be able to recover.	 As a
 	 * first-order desperate measure, turn off KSEG0 cacheing.
 	 */
 	mfc0	k0,CP0_CONFIG
diff --git a/arch/mips/mm/cex-oct.S b/arch/mips/mm/cex-oct.S
index 3db8553fcd34..9029092aa740 100644
--- a/arch/mips/mm/cex-oct.S
+++ b/arch/mips/mm/cex-oct.S
@@ -18,7 +18,7 @@
  */
 	LEAF(except_vec2_octeon)
 
-	.set    push
+	.set	push
 	.set	mips64r2
 	.set	noreorder
 	.set	noat
@@ -27,19 +27,19 @@
 	/* due to an errata we need to read the COP0 CacheErr (Dcache)
 	 * before any cache/DRAM access	 */
 
-	rdhwr   k0, $0        /* get core_id */
-	PTR_LA  k1, cache_err_dcache
-	sll     k0, k0, 3
+	rdhwr	k0, $0	      /* get core_id */
+	PTR_LA	k1, cache_err_dcache
+	sll	k0, k0, 3
 	PTR_ADDU k1, k0, k1    /* k1 = &cache_err_dcache[core_id] */
 
-	dmfc0   k0, CP0_CACHEERR, 1
-	sd      k0, (k1)
-	dmtc0   $0, CP0_CACHEERR, 1
+	dmfc0	k0, CP0_CACHEERR, 1
+	sd	k0, (k1)
+	dmtc0	$0, CP0_CACHEERR, 1
 
-        /* check whether this is a nested exception */
-	mfc0    k1, CP0_STATUS
-	andi    k1, k1, ST0_EXL
-	beqz    k1, 1f
+	/* check whether this is a nested exception */
+	mfc0	k1, CP0_STATUS
+	andi	k1, k1, ST0_EXL
+	beqz	k1, 1f
 	 nop
 	j	cache_parity_error_octeon_non_recoverable
 	 nop
@@ -48,22 +48,22 @@
 1:	j	handle_cache_err
 	 nop
 
-	.set    pop
+	.set	pop
 	END(except_vec2_octeon)
 
  /* We need to jump to handle_cache_err so that the previous handler
   * can fit within 0x80 bytes. We also move from 0xFFFFFFFFAXXXXXXX
-  * space (uncached) to the 0xFFFFFFFF8XXXXXXX space (cached).  */
+  * space (uncached) to the 0xFFFFFFFF8XXXXXXX space (cached).	*/
 	LEAF(handle_cache_err)
-	.set    push
-        .set    noreorder
-        .set    noat
+	.set	push
+	.set	noreorder
+	.set	noat
 
 	SAVE_ALL
 	KMODE
-	jal     cache_parity_error_octeon_recoverable
+	jal	cache_parity_error_octeon_recoverable
 	nop
-	j       ret_from_exception
+	j	ret_from_exception
 	nop
 
 	.set pop
diff --git a/arch/mips/mm/cex-sb1.S b/arch/mips/mm/cex-sb1.S
index 89c412bc4b64..fe1d887e8d70 100644
--- a/arch/mips/mm/cex-sb1.S
+++ b/arch/mips/mm/cex-sb1.S
@@ -24,9 +24,9 @@
 #include <asm/cacheops.h>
 #include <asm/sibyte/board.h>
 
-#define C0_ERRCTL     $26             /* CP0: Error info */
-#define C0_CERR_I     $27             /* CP0: Icache error */
-#define C0_CERR_D     $27,1           /* CP0: Dcache error */
+#define C0_ERRCTL     $26	      /* CP0: Error info */
+#define C0_CERR_I     $27	      /* CP0: Icache error */
+#define C0_CERR_D     $27,1	      /* CP0: Dcache error */
 
 	/*
 	 * Based on SiByte sample software cache-err/cerr.S
@@ -88,7 +88,7 @@ attempt_recovery:
 	/*
 	 * k0 has C0_ERRCTL << 1, which puts 'DC' at bit 31.  Any
 	 * Dcache errors we can recover from will take more extensive
-	 * processing.  For now, they are considered "unrecoverable".
+	 * processing.	For now, they are considered "unrecoverable".
 	 * Note that 'DC' becoming set (outside of ERL mode) will
 	 * cause 'IC' to clear; so if there's an Icache error, we'll
 	 * only find out about it if we recover from this error and
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index 3fab2046c8a4..f9ef83829a52 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -4,7 +4,7 @@
  * for more details.
  *
  * Copyright (C) 2000  Ani Joshi <ajoshi@unixbox.com>
- * Copyright (C) 2000, 2001, 06  Ralf Baechle <ralf@linux-mips.org>
+ * Copyright (C) 2000, 2001, 06	 Ralf Baechle <ralf@linux-mips.org>
  * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
  */
 
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index ddcec1e1a0cd..0fead53d1c26 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -52,7 +52,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, unsigned long writ
 
 #ifdef CONFIG_KPROBES
 	/*
-	 * This is to notify the fault handler of the kprobes.  The
+	 * This is to notify the fault handler of the kprobes.	The
 	 * exception code is redundant as it is also carried in REGS,
 	 * but we pass it anyhow.
 	 */
@@ -216,7 +216,7 @@ bad_area_nosemaphore:
 	}
 
 no_context:
-	/* Are we prepared to handle this kernel fault?  */
+	/* Are we prepared to handle this kernel fault?	 */
 	if (fixup_exception(regs)) {
 		current->thread.cp0_baduaddr = address;
 		return;
diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c
index dcfd573871c1..d4ea5c9c4a93 100644
--- a/arch/mips/mm/gup.c
+++ b/arch/mips/mm/gup.c
@@ -249,7 +249,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
  * @nr_pages:	number of pages from start to pin
  * @write:	whether pages will be written to
  * @pages:	array that receives pointers to the pages pinned.
- * 		Should be at least nr_pages long.
+ *		Should be at least nr_pages long.
  *
  * Attempt to pin user pages in memory without taking mm->mmap_sem.
  * If not successful, it will fall back to taking the lock and
diff --git a/arch/mips/mm/highmem.c b/arch/mips/mm/highmem.c
index aff57057a949..da815d295239 100644
--- a/arch/mips/mm/highmem.c
+++ b/arch/mips/mm/highmem.c
@@ -1,3 +1,4 @@
+#include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/highmem.h>
 #include <linux/sched.h>
@@ -67,7 +68,7 @@ EXPORT_SYMBOL(kmap_atomic);
 void __kunmap_atomic(void *kvaddr)
 {
 	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
-	int type;
+	int type __maybe_unused;
 
 	if (vaddr < FIXADDR_START) { // FIXME
 		pagefault_enable();
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index be9acb2b959d..67929251286c 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -66,7 +66,7 @@
 
 /*
  * We have up to 8 empty zeroed pages so we can map one of the right colour
- * when needed.  This is necessary only on R4000 / R4400 SC and MC versions
+ * when needed.	 This is necessary only on R4000 / R4400 SC and MC versions
  * where we have to avoid VCED / VECI exceptions for good performance at
  * any price.  Since page is never written to after the initialization we
  * don't have to care about aliases on other CPUs.
@@ -380,7 +380,7 @@ void __init mem_init(void)
 	high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
 
 	totalram_pages += free_all_bootmem();
-	totalram_pages -= setup_zero_pages();	/* Setup zeroed pages.  */
+	totalram_pages -= setup_zero_pages();	/* Setup zeroed pages.	*/
 
 	reservedpages = ram = 0;
 	for (tmp = 0; tmp < max_low_pfn; tmp++)
diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c
index cacfd31e8ec9..7f840bc08abf 100644
--- a/arch/mips/mm/ioremap.c
+++ b/arch/mips/mm/ioremap.c
@@ -22,7 +22,7 @@ static inline void remap_area_pte(pte_t * pte, unsigned long address,
 	phys_t end;
 	unsigned long pfn;
 	pgprot_t pgprot = __pgprot(_PAGE_GLOBAL | _PAGE_PRESENT | __READABLE
-	                           | __WRITEABLE | flags);
+				   | __WRITEABLE | flags);
 
 	address &= ~PMD_MASK;
 	end = address + size;
@@ -185,7 +185,7 @@ void __iounmap(const volatile void __iomem *addr)
 	if (!p)
 		printk(KERN_ERR "iounmap: bad address %p\n", addr);
 
-        kfree(p);
+	kfree(p);
 }
 
 EXPORT_SYMBOL(__ioremap);
diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c
index d9be7540a6be..7e5fe2790d8a 100644
--- a/arch/mips/mm/mmap.c
+++ b/arch/mips/mm/mmap.c
@@ -192,3 +192,9 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
 
 	return ret;
 }
+
+int __virt_addr_valid(const volatile void *kaddr)
+{
+	return pfn_valid(PFN_DOWN(virt_to_phys(kaddr)));
+}
+EXPORT_SYMBOL_GPL(__virt_addr_valid);
diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c
index 98f530e18216..a29fba55b53e 100644
--- a/arch/mips/mm/page.c
+++ b/arch/mips/mm/page.c
@@ -140,15 +140,6 @@ static void __cpuinit set_prefetch_parameters(void)
 			pref_bias_copy_load = 256;
 			break;
 
-		case CPU_RM9000:
-			/*
-			 * As a workaround for erratum G105 which make the
-			 * PrepareForStore hint unusable we fall back to
-			 * StoreRetained on the RM9000.  Once it is known which
-			 * versions of the RM9000 we'll be able to condition-
-			 * alize this.
-			 */
-
 		case CPU_R10000:
 		case CPU_R12000:
 		case CPU_R14000:
@@ -280,7 +271,7 @@ void __cpuinit build_clear_page(void)
 		uasm_i_lui(&buf, AT, 0xa000);
 
 	off = cache_line_size ? min(8, pref_bias_clear_store / cache_line_size)
-	                        * cache_line_size : 0;
+				* cache_line_size : 0;
 	while (off) {
 		build_clear_pref(&buf, -off);
 		off -= cache_line_size;
@@ -426,13 +417,13 @@ void __cpuinit build_copy_page(void)
 		uasm_i_lui(&buf, AT, 0xa000);
 
 	off = cache_line_size ? min(8, pref_bias_copy_load / cache_line_size) *
-	                        cache_line_size : 0;
+				cache_line_size : 0;
 	while (off) {
 		build_copy_load_pref(&buf, -off);
 		off -= cache_line_size;
 	}
 	off = cache_line_size ? min(8, pref_bias_copy_store / cache_line_size) *
-	                        cache_line_size : 0;
+				cache_line_size : 0;
 	while (off) {
 		build_copy_store_pref(&buf, -off);
 		off -= cache_line_size;
diff --git a/arch/mips/mm/pgtable-64.c b/arch/mips/mm/pgtable-64.c
index 25407794edb4..e8adc0069d66 100644
--- a/arch/mips/mm/pgtable-64.c
+++ b/arch/mips/mm/pgtable-64.c
@@ -11,6 +11,7 @@
 #include <asm/fixmap.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
 
 void pgd_init(unsigned long page)
 {
@@ -23,7 +24,7 @@ void pgd_init(unsigned long page)
 	entry = (unsigned long)invalid_pmd_table;
 #endif
 
- 	p = (unsigned long *) page;
+	p = (unsigned long *) page;
 	end = p + PTRS_PER_PGD;
 
 	do {
@@ -44,7 +45,7 @@ void pmd_init(unsigned long addr, unsigned long pagetable)
 {
 	unsigned long *p, *end;
 
- 	p = (unsigned long *) addr;
+	p = (unsigned long *) addr;
 	end = p + PTRS_PER_PMD;
 
 	do {
@@ -61,6 +62,36 @@ void pmd_init(unsigned long addr, unsigned long pagetable)
 }
 #endif
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+void pmdp_splitting_flush(struct vm_area_struct *vma,
+			 unsigned long address,
+			 pmd_t *pmdp)
+{
+	if (!pmd_trans_splitting(*pmdp)) {
+		pmd_t pmd = pmd_mksplitting(*pmdp);
+		set_pmd_at(vma->vm_mm, address, pmdp, pmd);
+	}
+}
+
+#endif
+
+pmd_t mk_pmd(struct page *page, pgprot_t prot)
+{
+	pmd_t pmd;
+
+	pmd_val(pmd) = (page_to_pfn(page) << _PFN_SHIFT) | pgprot_val(prot);
+
+	return pmd;
+}
+
+void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+		pmd_t *pmdp, pmd_t pmd)
+{
+	*pmdp = pmd;
+	flush_tlb_all();
+}
+
 void __init pagetable_init(void)
 {
 	unsigned long vaddr;
diff --git a/arch/mips/mm/sc-ip22.c b/arch/mips/mm/sc-ip22.c
index 1eb708ef75ff..c6aaed934d53 100644
--- a/arch/mips/mm/sc-ip22.c
+++ b/arch/mips/mm/sc-ip22.c
@@ -159,7 +159,7 @@ static inline int __init indy_sc_probe(void)
 }
 
 /* XXX Check with wje if the Indy caches can differenciate between
-   writeback + invalidate and just invalidate.  */
+   writeback + invalidate and just invalidate.	*/
 static struct bcache_ops indy_sc_ops = {
 	.bc_enable = indy_sc_enable,
 	.bc_disable = indy_sc_disable,
diff --git a/arch/mips/mm/sc-r5k.c b/arch/mips/mm/sc-r5k.c
index 8d90ff25b123..8bc67720e145 100644
--- a/arch/mips/mm/sc-r5k.c
+++ b/arch/mips/mm/sc-r5k.c
@@ -58,7 +58,7 @@ static void r5k_dma_cache_inv_sc(unsigned long addr, unsigned long size)
 
 static void r5k_sc_enable(void)
 {
-        unsigned long flags;
+	unsigned long flags;
 
 	local_irq_save(flags);
 	set_c0_config(R5K_CONF_SE);
@@ -68,7 +68,7 @@ static void r5k_sc_enable(void)
 
 static void r5k_sc_disable(void)
 {
-        unsigned long flags;
+	unsigned long flags;
 
 	local_irq_save(flags);
 	blast_r5000_scache();
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index 88e79ad6f811..493131c81a29 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -295,7 +295,7 @@ 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();
-#ifdef CONFIG_HUGETLB_PAGE
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 	/* this could be a huge page  */
 	if (pmd_huge(*pmdp)) {
 		unsigned long lo;
@@ -367,6 +367,26 @@ void add_wired_entry(unsigned long entrylo0, unsigned long entrylo1,
 	EXIT_CRITICAL(flags);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+int __init has_transparent_hugepage(void)
+{
+	unsigned int mask;
+	unsigned long flags;
+
+	ENTER_CRITICAL(flags);
+	write_c0_pagemask(PM_HUGE_MASK);
+	back_to_back_c0_hazard();
+	mask = read_c0_pagemask();
+	write_c0_pagemask(PM_DEFAULT_MASK);
+
+	EXIT_CRITICAL(flags);
+
+	return mask == PM_HUGE_MASK;
+}
+
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE  */
+
 static int __cpuinitdata ntlb;
 static int __init set_ntlb(char *str)
 {
@@ -404,7 +424,7 @@ void __cpuinit tlb_init(void)
 		write_c0_pagegrain(pg);
 	}
 
-        /* From this point on the ARC firmware is dead.  */
+	/* From this point on the ARC firmware is dead.	 */
 	local_flush_tlb_all();
 
 	/* Did I tell you that ARC SUCKS?  */
diff --git a/arch/mips/mm/tlbex-fault.S b/arch/mips/mm/tlbex-fault.S
index e99eaa1fbedc..318855eb5f80 100644
--- a/arch/mips/mm/tlbex-fault.S
+++ b/arch/mips/mm/tlbex-fault.S
@@ -7,7 +7,6 @@
  * Copyright (C) 1999 Silicon Graphics, Inc.
  */
 #include <asm/mipsregs.h>
-#include <asm/page.h>
 #include <asm/regdef.h>
 #include <asm/stackframe.h>
 
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 2833dcb67b5a..820e6612d744 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -5,8 +5,8 @@
  *
  * Synthesize TLB refill handlers at runtime.
  *
- * Copyright (C) 2004, 2005, 2006, 2008  Thiemo Seufer
- * Copyright (C) 2005, 2007, 2008, 2009  Maciej W. Rozycki
+ * Copyright (C) 2004, 2005, 2006, 2008	 Thiemo Seufer
+ * 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.
  * Copyright (C) 2011  MIPS Technologies, Inc.
@@ -158,7 +158,7 @@ enum label_id {
 	label_smp_pgtable_change,
 	label_r3000_write_probe_fail,
 	label_large_segbits_fault,
-#ifdef CONFIG_HUGETLB_PAGE
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 	label_tlb_huge_update,
 #endif
 };
@@ -177,13 +177,15 @@ UASM_L_LA(_nopage_tlbm)
 UASM_L_LA(_smp_pgtable_change)
 UASM_L_LA(_r3000_write_probe_fail)
 UASM_L_LA(_large_segbits_fault)
-#ifdef CONFIG_HUGETLB_PAGE
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 UASM_L_LA(_tlb_huge_update)
 #endif
 
 static int __cpuinitdata hazard_instance;
 
-static void uasm_bgezl_hazard(u32 **p, struct uasm_reloc **r, int instance)
+static void __cpuinit uasm_bgezl_hazard(u32 **p,
+					struct uasm_reloc **r,
+					int instance)
 {
 	switch (instance) {
 	case 0 ... 7:
@@ -194,7 +196,9 @@ static void uasm_bgezl_hazard(u32 **p, struct uasm_reloc **r, int instance)
 	}
 }
 
-static void uasm_bgezl_label(struct uasm_label **l, u32 **p, int instance)
+static void __cpuinit uasm_bgezl_label(struct uasm_label **l,
+				       u32 **p,
+				       int instance)
 {
 	switch (instance) {
 	case 0 ... 7:
@@ -206,19 +210,59 @@ static void uasm_bgezl_label(struct uasm_label **l, u32 **p, int instance)
 }
 
 /*
- * For debug purposes.
+ * pgtable bits are assigned dynamically depending on processor feature
+ * and statically based on kernel configuration.  This spits out the actual
+ * values the kernel is using.	Required to make sense from disassembled
+ * TLB exception handlers.
  */
-static inline void dump_handler(const u32 *handler, int count)
+static void output_pgtable_bits_defines(void)
+{
+#define pr_define(fmt, ...)					\
+	pr_debug("#define " fmt, ##__VA_ARGS__)
+
+	pr_debug("#include <asm/asm.h>\n");
+	pr_debug("#include <asm/regdef.h>\n");
+	pr_debug("\n");
+
+	pr_define("_PAGE_PRESENT_SHIFT %d\n", _PAGE_PRESENT_SHIFT);
+	pr_define("_PAGE_READ_SHIFT %d\n", _PAGE_READ_SHIFT);
+	pr_define("_PAGE_WRITE_SHIFT %d\n", _PAGE_WRITE_SHIFT);
+	pr_define("_PAGE_ACCESSED_SHIFT %d\n", _PAGE_ACCESSED_SHIFT);
+	pr_define("_PAGE_MODIFIED_SHIFT %d\n", _PAGE_MODIFIED_SHIFT);
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
+	pr_define("_PAGE_HUGE_SHIFT %d\n", _PAGE_HUGE_SHIFT);
+	pr_define("_PAGE_SPLITTING_SHIFT %d\n", _PAGE_SPLITTING_SHIFT);
+#endif
+	if (cpu_has_rixi) {
+#ifdef _PAGE_NO_EXEC_SHIFT
+		pr_define("_PAGE_NO_EXEC_SHIFT %d\n", _PAGE_NO_EXEC_SHIFT);
+#endif
+#ifdef _PAGE_NO_READ_SHIFT
+		pr_define("_PAGE_NO_READ_SHIFT %d\n", _PAGE_NO_READ_SHIFT);
+#endif
+	}
+	pr_define("_PAGE_GLOBAL_SHIFT %d\n", _PAGE_GLOBAL_SHIFT);
+	pr_define("_PAGE_VALID_SHIFT %d\n", _PAGE_VALID_SHIFT);
+	pr_define("_PAGE_DIRTY_SHIFT %d\n", _PAGE_DIRTY_SHIFT);
+	pr_define("_PFN_SHIFT %d\n", _PFN_SHIFT);
+	pr_debug("\n");
+}
+
+static inline void dump_handler(const char *symbol, const u32 *handler, int count)
 {
 	int i;
 
+	pr_debug("LEAF(%s)\n", symbol);
+
 	pr_debug("\t.set push\n");
 	pr_debug("\t.set noreorder\n");
 
 	for (i = 0; i < count; i++)
-		pr_debug("\t%p\t.word 0x%08x\n", &handler[i], handler[i]);
+		pr_debug("\t.word\t0x%08x\t\t# %p\n", handler[i], &handler[i]);
 
-	pr_debug("\t.set pop\n");
+	pr_debug("\t.set\tpop\n");
+
+	pr_debug("\tEND(%s)\n", symbol);
 }
 
 /* The only general purpose registers allowed in TLB handlers. */
@@ -401,7 +445,7 @@ static void __cpuinit build_r3000_tlb_refill_handler(void)
 
 	memcpy((void *)ebase, tlb_handler, 0x80);
 
-	dump_handler((u32 *)ebase, 32);
+	dump_handler("r3000_tlb_refill", (u32 *)ebase, 32);
 }
 #endif /* CONFIG_MIPS_PGD_C0_CONTEXT */
 
@@ -420,8 +464,8 @@ static u32 final_handler[64] __cpuinitdata;
  * From the IDT errata for the QED RM5230 (Nevada), processor revision 1.0:
  * 2. A timing hazard exists for the TLBP instruction.
  *
- *      stalling_instruction
- *      TLBP
+ *	stalling_instruction
+ *	TLBP
  *
  * The JTLB is being read for the TLBP throughout the stall generated by the
  * previous instruction. This is not really correct as the stalling instruction
@@ -432,7 +476,7 @@ static u32 final_handler[64] __cpuinitdata;
  * The software work-around is to not allow the instruction preceding the TLBP
  * to stall - make it an NOP or some other instruction guaranteed not to stall.
  *
- * Errata 2 will not be fixed.  This errata is also on the R5000.
+ * Errata 2 will not be fixed.	This errata is also on the R5000.
  *
  * As if we MIPS hackers wouldn't know how to nop pipelines happy ...
  */
@@ -443,7 +487,6 @@ static void __cpuinit __maybe_unused build_tlb_probe_entry(u32 **p)
 	case CPU_R4600:
 	case CPU_R4700:
 	case CPU_R5000:
-	case CPU_R5000A:
 	case CPU_NEVADA:
 		uasm_i_nop(p);
 		uasm_i_tlbp(p);
@@ -517,7 +560,6 @@ static void __cpuinit build_tlb_write_entry(u32 **p, struct uasm_label **l,
 		break;
 
 	case CPU_R5000:
-	case CPU_R5000A:
 	case CPU_NEVADA:
 		uasm_i_nop(p); /* QED specifies 2 nops hazard */
 		uasm_i_nop(p); /* QED specifies 2 nops hazard */
@@ -539,6 +581,7 @@ static void __cpuinit build_tlb_write_entry(u32 **p, struct uasm_label **l,
 	case CPU_4KC:
 	case CPU_4KEC:
 	case CPU_M14KC:
+	case CPU_M14KEC:
 	case CPU_SB1:
 	case CPU_SB1A:
 	case CPU_4KSC:
@@ -565,24 +608,6 @@ static void __cpuinit build_tlb_write_entry(u32 **p, struct uasm_label **l,
 		tlbw(p);
 		break;
 
-	case CPU_RM9000:
-		/*
-		 * When the JTLB is updated by tlbwi or tlbwr, a subsequent
-		 * use of the JTLB for instructions should not occur for 4
-		 * cpu cycles and use for data translations should not occur
-		 * for 3 cpu cycles.
-		 */
-		uasm_i_ssnop(p);
-		uasm_i_ssnop(p);
-		uasm_i_ssnop(p);
-		uasm_i_ssnop(p);
-		tlbw(p);
-		uasm_i_ssnop(p);
-		uasm_i_ssnop(p);
-		uasm_i_ssnop(p);
-		uasm_i_ssnop(p);
-		break;
-
 	case CPU_VR4111:
 	case CPU_VR4121:
 	case CPU_VR4122:
@@ -629,7 +654,7 @@ static __cpuinit __maybe_unused void build_convert_pte_to_entrylo(u32 **p,
 	}
 }
 
-#ifdef CONFIG_HUGETLB_PAGE
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 
 static __cpuinit void build_restore_pagemask(u32 **p,
 					     struct uasm_reloc **r,
@@ -724,7 +749,7 @@ static __cpuinit void build_huge_update_entries(u32 **p,
 	 */
 	small_sequence = (HPAGE_SIZE >> 7) < 0x10000;
 
-	/* We can clobber tmp.  It isn't used after this.*/
+	/* We can clobber tmp.	It isn't used after this.*/
 	if (!small_sequence)
 		uasm_i_lui(p, tmp, HPAGE_SIZE >> (7 + 16));
 
@@ -755,7 +780,7 @@ static __cpuinit void build_huge_handler_tail(u32 **p,
 	build_huge_update_entries(p, pte, ptr);
 	build_huge_tlb_write_entry(p, l, r, pte, tlb_indexed, 0);
 }
-#endif /* CONFIG_HUGETLB_PAGE */
+#endif /* CONFIG_MIPS_HUGE_TLB_SUPPORT */
 
 #ifdef CONFIG_64BIT
 /*
@@ -806,12 +831,12 @@ build_get_pmde64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
 		/* Clear lower 23 bits of context. */
 		uasm_i_dins(p, ptr, 0, 0, 23);
 
-		/* 1 0  1 0 1  << 6  xkphys cached */
+		/* 1 0	1 0 1  << 6  xkphys cached */
 		uasm_i_ori(p, ptr, ptr, 0x540);
 		uasm_i_drotr(p, ptr, ptr, 11);
 	}
 #elif defined(CONFIG_SMP)
-# ifdef  CONFIG_MIPS_MT_SMTC
+# ifdef	 CONFIG_MIPS_MT_SMTC
 	/*
 	 * SMTC uses TCBind value as "CPU" index
 	 */
@@ -931,7 +956,7 @@ build_get_pgde32(u32 **p, unsigned int tmp, unsigned int ptr)
 
 	/* 32 bit SMP has smp_processor_id() stored in CONTEXT. */
 #ifdef CONFIG_SMP
-#ifdef  CONFIG_MIPS_MT_SMTC
+#ifdef	CONFIG_MIPS_MT_SMTC
 	/*
 	 * SMTC uses TCBind value as "CPU" index
 	 */
@@ -941,7 +966,7 @@ build_get_pgde32(u32 **p, unsigned int tmp, unsigned int ptr)
 #else
 	/*
 	 * smp_processor_id() << 3 is stored in CONTEXT.
-         */
+	 */
 	uasm_i_mfc0(p, ptr, C0_CONTEXT);
 	UASM_i_LA_mostly(p, tmp, pgdc);
 	uasm_i_srl(p, ptr, ptr, 23);
@@ -952,13 +977,6 @@ build_get_pgde32(u32 **p, unsigned int tmp, unsigned int ptr)
 #endif
 	uasm_i_mfc0(p, tmp, C0_BADVADDR); /* get faulting address */
 	uasm_i_lw(p, ptr, uasm_rel_lo(pgdc), ptr);
-
-	if (cpu_has_mips_r2) {
-		uasm_i_ext(p, tmp, tmp, PGDIR_SHIFT, (32 - PGDIR_SHIFT));
-		uasm_i_ins(p, ptr, tmp, PGD_T_LOG2, (32 - PGDIR_SHIFT));
-		return;
-	}
-
 	uasm_i_srl(p, tmp, tmp, PGDIR_SHIFT); /* get pgd only bits */
 	uasm_i_sll(p, tmp, tmp, PGD_T_LOG2);
 	uasm_i_addu(p, ptr, ptr, tmp); /* add in pgd offset */
@@ -994,15 +1012,6 @@ static void __cpuinit build_adjust_context(u32 **p, unsigned int ctx)
 
 static void __cpuinit build_get_ptep(u32 **p, unsigned int tmp, unsigned int ptr)
 {
-	if (cpu_has_mips_r2) {
-		/* PTE ptr offset is obtained from BadVAddr */
-		UASM_i_MFC0(p, tmp, C0_BADVADDR);
-		UASM_i_LW(p, ptr, 0, ptr);
-		uasm_i_ext(p, tmp, tmp, PAGE_SHIFT+1, PGDIR_SHIFT-PAGE_SHIFT-1);
-		uasm_i_ins(p, ptr, tmp, PTE_T_LOG2+1, PGDIR_SHIFT-PAGE_SHIFT-1);
-		return;
-	}
-
 	/*
 	 * Bug workaround for the Nevada. It seems as if under certain
 	 * circumstances the move from cp0_context might produce a
@@ -1145,7 +1154,7 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l,
 
 	if (pgd_reg == -1) {
 		vmalloc_branch_delay_filled = 1;
-		/* 1 0  1 0 1  << 6  xkphys cached */
+		/* 1 0	1 0 1  << 6  xkphys cached */
 		uasm_i_ori(p, ptr, ptr, 0x540);
 		uasm_i_drotr(p, ptr, ptr, 11);
 	}
@@ -1163,9 +1172,9 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l,
 	uasm_l_vmalloc_done(l, *p);
 
 	/*
-	 *                         tmp          ptr
-	 * fall-through case =   badvaddr  *pgd_current
-	 * vmalloc case      =   badvaddr  swapper_pg_dir
+	 *			   tmp		ptr
+	 * fall-through case =	 badvaddr  *pgd_current
+	 * vmalloc case	     =	 badvaddr  swapper_pg_dir
 	 */
 
 	if (vmalloc_branch_delay_filled)
@@ -1200,16 +1209,16 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l,
 	/* Adjust the context during the load latency. */
 	build_adjust_context(p, tmp);
 
-#ifdef CONFIG_HUGETLB_PAGE
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 	uasm_il_bbit1(p, r, scratch, ilog2(_PAGE_HUGE), label_tlb_huge_update);
 	/*
 	 * The in the LWX case we don't want to do the load in the
-	 * delay slot.  It cannot issue in the same cycle and may be
+	 * delay slot.	It cannot issue in the same cycle and may be
 	 * speculative and unneeded.
 	 */
 	if (use_lwx_insns())
 		uasm_i_nop(p);
-#endif /* CONFIG_HUGETLB_PAGE */
+#endif /* CONFIG_MIPS_HUGE_TLB_SUPPORT */
 
 
 	/* build_update_entries */
@@ -1312,7 +1321,7 @@ static void __cpuinit build_r4000_tlb_refill_handler(void)
 		build_get_pgde32(&p, K0, K1); /* get pgd in K1 */
 #endif
 
-#ifdef CONFIG_HUGETLB_PAGE
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 		build_is_huge_pte(&p, &r, K0, K1, label_tlb_huge_update);
 #endif
 
@@ -1322,7 +1331,7 @@ static void __cpuinit build_r4000_tlb_refill_handler(void)
 		uasm_l_leave(&l, p);
 		uasm_i_eret(&p); /* return from trap */
 	}
-#ifdef CONFIG_HUGETLB_PAGE
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 	uasm_l_tlb_huge_update(&l, p);
 	build_huge_update_entries(&p, htlb_info.huge_pte, K1);
 	build_huge_tlb_write_entry(&p, &l, &r, K0, tlb_random,
@@ -1367,7 +1376,7 @@ static void __cpuinit build_r4000_tlb_refill_handler(void)
 		uasm_copy_handler(relocs, labels, tlb_handler, p, f);
 		final_len = p - tlb_handler;
 	} else {
-#if defined(CONFIG_HUGETLB_PAGE)
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 		const enum label_id ls = label_tlb_huge_update;
 #else
 		const enum label_id ls = label_vmalloc;
@@ -1436,7 +1445,7 @@ static void __cpuinit build_r4000_tlb_refill_handler(void)
 
 	memcpy((void *)ebase, final_handler, 0x100);
 
-	dump_handler((u32 *)ebase, 64);
+	dump_handler("r4000_tlb_refill", (u32 *)ebase, 64);
 }
 
 /*
@@ -1493,7 +1502,8 @@ static void __cpuinit build_r4000_setup_pgd(void)
 	pr_debug("Wrote tlbmiss_handler_setup_pgd (%u instructions).\n",
 		 (unsigned int)(p - tlbmiss_handler_setup_pgd));
 
-	dump_handler(tlbmiss_handler_setup_pgd,
+	dump_handler("tlbmiss_handler",
+		     tlbmiss_handler_setup_pgd,
 		     ARRAY_SIZE(tlbmiss_handler_setup_pgd));
 }
 #endif
@@ -1763,7 +1773,7 @@ static void __cpuinit build_r3000_tlb_load_handler(void)
 	pr_debug("Wrote TLB load handler fastpath (%u instructions).\n",
 		 (unsigned int)(p - handle_tlbl));
 
-	dump_handler(handle_tlbl, ARRAY_SIZE(handle_tlbl));
+	dump_handler("r3000_tlb_load", handle_tlbl, ARRAY_SIZE(handle_tlbl));
 }
 
 static void __cpuinit build_r3000_tlb_store_handler(void)
@@ -1793,7 +1803,7 @@ static void __cpuinit build_r3000_tlb_store_handler(void)
 	pr_debug("Wrote TLB store handler fastpath (%u instructions).\n",
 		 (unsigned int)(p - handle_tlbs));
 
-	dump_handler(handle_tlbs, ARRAY_SIZE(handle_tlbs));
+	dump_handler("r3000_tlb_store", handle_tlbs, ARRAY_SIZE(handle_tlbs));
 }
 
 static void __cpuinit build_r3000_tlb_modify_handler(void)
@@ -1823,7 +1833,7 @@ static void __cpuinit build_r3000_tlb_modify_handler(void)
 	pr_debug("Wrote TLB modify handler fastpath (%u instructions).\n",
 		 (unsigned int)(p - handle_tlbm));
 
-	dump_handler(handle_tlbm, ARRAY_SIZE(handle_tlbm));
+	dump_handler("r3000_tlb_modify", handle_tlbm, ARRAY_SIZE(handle_tlbm));
 }
 #endif /* CONFIG_MIPS_PGD_C0_CONTEXT */
 
@@ -1842,7 +1852,7 @@ build_r4000_tlbchange_handler_head(u32 **p, struct uasm_label **l,
 	build_get_pgde32(p, wr.r1, wr.r2); /* get pgd in ptr */
 #endif
 
-#ifdef CONFIG_HUGETLB_PAGE
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 	/*
 	 * For huge tlb entries, pmd doesn't contain an address but
 	 * instead contains the tlb pte. Check the PAGE_HUGE bit and
@@ -1958,7 +1968,7 @@ static void __cpuinit build_r4000_tlb_load_handler(void)
 	build_make_valid(&p, &r, wr.r1, wr.r2);
 	build_r4000_tlbchange_handler_tail(&p, &l, &r, wr.r1, wr.r2);
 
-#ifdef CONFIG_HUGETLB_PAGE
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 	/*
 	 * This is the entry point when build_r4000_tlbchange_handler_head
 	 * spots a huge page.
@@ -2030,7 +2040,7 @@ static void __cpuinit build_r4000_tlb_load_handler(void)
 	pr_debug("Wrote TLB load handler fastpath (%u instructions).\n",
 		 (unsigned int)(p - handle_tlbl));
 
-	dump_handler(handle_tlbl, ARRAY_SIZE(handle_tlbl));
+	dump_handler("r4000_tlb_load", handle_tlbl, ARRAY_SIZE(handle_tlbl));
 }
 
 static void __cpuinit build_r4000_tlb_store_handler(void)
@@ -2051,7 +2061,7 @@ static void __cpuinit build_r4000_tlb_store_handler(void)
 	build_make_write(&p, &r, wr.r1, wr.r2);
 	build_r4000_tlbchange_handler_tail(&p, &l, &r, wr.r1, wr.r2);
 
-#ifdef CONFIG_HUGETLB_PAGE
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 	/*
 	 * This is the entry point when
 	 * build_r4000_tlbchange_handler_head spots a huge page.
@@ -2077,7 +2087,7 @@ static void __cpuinit build_r4000_tlb_store_handler(void)
 	pr_debug("Wrote TLB store handler fastpath (%u instructions).\n",
 		 (unsigned int)(p - handle_tlbs));
 
-	dump_handler(handle_tlbs, ARRAY_SIZE(handle_tlbs));
+	dump_handler("r4000_tlb_store", handle_tlbs, ARRAY_SIZE(handle_tlbs));
 }
 
 static void __cpuinit build_r4000_tlb_modify_handler(void)
@@ -2099,7 +2109,7 @@ static void __cpuinit build_r4000_tlb_modify_handler(void)
 	build_make_write(&p, &r, wr.r1, wr.r2);
 	build_r4000_tlbchange_handler_tail(&p, &l, &r, wr.r1, wr.r2);
 
-#ifdef CONFIG_HUGETLB_PAGE
+#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 	/*
 	 * This is the entry point when
 	 * build_r4000_tlbchange_handler_head spots a huge page.
@@ -2125,7 +2135,7 @@ static void __cpuinit build_r4000_tlb_modify_handler(void)
 	pr_debug("Wrote TLB modify handler fastpath (%u instructions).\n",
 		 (unsigned int)(p - handle_tlbm));
 
-	dump_handler(handle_tlbm, ARRAY_SIZE(handle_tlbm));
+	dump_handler("r4000_tlb_modify", handle_tlbm, ARRAY_SIZE(handle_tlbm));
 }
 
 void __cpuinit build_tlb_refill_handler(void)
@@ -2137,6 +2147,8 @@ void __cpuinit build_tlb_refill_handler(void)
 	 */
 	static int run_once = 0;
 
+	output_pgtable_bits_defines();
+
 #ifdef CONFIG_64BIT
 	check_for_high_segbits = current_cpu_data.vmbits > (PGDIR_SHIFT + PGD_ORDER + PAGE_SHIFT - 3);
 #endif
diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c
index 39b891056227..942ff6c2eba2 100644
--- a/arch/mips/mm/uasm.c
+++ b/arch/mips/mm/uasm.c
@@ -7,7 +7,7 @@
  * support a subset of instructions, and does not try to hide pipeline
  * effects like branch delay slots.
  *
- * Copyright (C) 2004, 2005, 2006, 2008  Thiemo Seufer
+ * Copyright (C) 2004, 2005, 2006, 2008	 Thiemo Seufer
  * Copyright (C) 2005, 2007  Maciej W. Rozycki
  * Copyright (C) 2006  Ralf Baechle (ralf@linux-mips.org)
  */
@@ -119,30 +119,30 @@ static struct insn insn_table[] __uasminitdata = {
 	{ insn_ext, M(spec3_op, 0, 0, 0, 0, ext_op), RS | RT | RD | RE },
 	{ insn_ins, M(spec3_op, 0, 0, 0, 0, ins_op), RS | RT | RD | RE },
 	{ insn_j,  M(j_op, 0, 0, 0, 0, 0),  JIMM },
-	{ insn_jal,  M(jal_op, 0, 0, 0, 0, 0),  JIMM },
+	{ insn_jal,  M(jal_op, 0, 0, 0, 0, 0),	JIMM },
 	{ insn_j,  M(j_op, 0, 0, 0, 0, 0),  JIMM },
 	{ insn_jr,  M(spec_op, 0, 0, 0, 0, jr_op),  RS },
 	{ insn_ld,  M(ld_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_ldx, M(spec3_op, 0, 0, 0, ldx_op, lx_op), RS | RT | RD },
-	{ insn_lld,  M(lld_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
+	{ insn_lld,  M(lld_op, 0, 0, 0, 0, 0),	RS | RT | SIMM },
 	{ insn_ll,  M(ll_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
-	{ insn_lui,  M(lui_op, 0, 0, 0, 0, 0),  RT | SIMM },
+	{ insn_lui,  M(lui_op, 0, 0, 0, 0, 0),	RT | SIMM },
 	{ insn_lw,  M(lw_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_lwx, M(spec3_op, 0, 0, 0, lwx_op, lx_op), RS | RT | RD },
 	{ insn_mfc0,  M(cop0_op, mfc_op, 0, 0, 0, 0),  RT | RD | SET},
 	{ insn_mtc0,  M(cop0_op, mtc_op, 0, 0, 0, 0),  RT | RD | SET},
-	{ insn_ori,  M(ori_op, 0, 0, 0, 0, 0),  RS | RT | UIMM },
+	{ insn_ori,  M(ori_op, 0, 0, 0, 0, 0),	RS | RT | UIMM },
 	{ insn_or,  M(spec_op, 0, 0, 0, 0, or_op),  RS | RT | RD },
 	{ insn_pref,  M(pref_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_rfe,  M(cop0_op, cop_op, 0, 0, 0, rfe_op),  0 },
 	{ insn_rotr,  M(spec_op, 1, 0, 0, 0, srl_op),  RT | RD | RE },
-	{ insn_scd,  M(scd_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
+	{ insn_scd,  M(scd_op, 0, 0, 0, 0, 0),	RS | RT | SIMM },
 	{ insn_sc,  M(sc_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_sd,  M(sd_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_sll,  M(spec_op, 0, 0, 0, 0, sll_op),  RT | RD | RE },
 	{ insn_sra,  M(spec_op, 0, 0, 0, 0, sra_op),  RT | RD | RE },
 	{ insn_srl,  M(spec_op, 0, 0, 0, 0, srl_op),  RT | RD | RE },
-	{ insn_subu,  M(spec_op, 0, 0, 0, 0, subu_op),  RS | RT | RD },
+	{ insn_subu,  M(spec_op, 0, 0, 0, 0, subu_op),	RS | RT | RD },
 	{ insn_sw,  M(sw_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_syscall, M(spec_op, 0, 0, 0, 0, syscall_op), SCIMM},
 	{ insn_tlbp,  M(cop0_op, cop_op, 0, 0, 0, tlbp_op),  0 },
@@ -345,7 +345,7 @@ Ip_u2u1msbu3(op)					\
 }							\
 UASM_EXPORT_SYMBOL(uasm_i##op);
 
-#define I_u2u1msbdu3(op) 				\
+#define I_u2u1msbdu3(op)				\
 Ip_u2u1msbu3(op)					\
 {							\
 	build_insn(buf, insn##op, b, a, d-1, c);	\