21 files changed, 299 insertions, 75 deletions

diff --git a/arch/sparc/crypto/md5_glue.c b/arch/sparc/crypto/md5_glue.c
index b688731..c9d2b92 100644
--- a/arch/sparc/crypto/md5_glue.c
+++ b/arch/sparc/crypto/md5_glue.c
@@ -33,10 +33,10 @@ static int md5_sparc64_init(struct shash_desc *desc)
 {
 	struct md5_state *mctx = shash_desc_ctx(desc);
 
-	mctx->hash[0] = cpu_to_le32(0x67452301);
-	mctx->hash[1] = cpu_to_le32(0xefcdab89);
-	mctx->hash[2] = cpu_to_le32(0x98badcfe);
-	mctx->hash[3] = cpu_to_le32(0x10325476);
+	mctx->hash[0] = cpu_to_le32(MD5_H0);
+	mctx->hash[1] = cpu_to_le32(MD5_H1);
+	mctx->hash[2] = cpu_to_le32(MD5_H2);
+	mctx->hash[3] = cpu_to_le32(MD5_H3);
 	mctx->byte_count = 0;
 
 	return 0;
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
index 7664894..809941e 100644
--- a/arch/sparc/include/asm/barrier_64.h
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -40,8 +40,8 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 #define dma_rmb()	rmb()
 #define dma_wmb()	wmb()
 
-#define set_mb(__var, __value) \
-	do { __var = __value; membar_safe("#StoreLoad"); } while(0)
+#define smp_store_mb(__var, __value) \
+	do { WRITE_ONCE(__var, __value); membar_safe("#StoreLoad"); } while(0)
 
 #ifdef CONFIG_SMP
 #define smp_mb()	mb()
diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
index d38b52d..83ffb83 100644
--- a/arch/sparc/include/asm/cmpxchg_32.h
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -34,7 +34,6 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int
  *
  * Cribbed from <asm-parisc/atomic.h>
  */
-#define __HAVE_ARCH_CMPXCHG	1
 
 /* bug catcher for when unsupported size is used - won't link */
 void __cmpxchg_called_with_bad_pointer(void);
diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h
index 0e1ed6c..faa2f61 100644
--- a/arch/sparc/include/asm/cmpxchg_64.h
+++ b/arch/sparc/include/asm/cmpxchg_64.h
@@ -65,8 +65,6 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr,
 
 #include <asm-generic/cmpxchg-local.h>
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 static inline unsigned long
 __cmpxchg_u32(volatile int *m, int old, int new)
 {
diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h
index a6e424d..a6cfdab 100644
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@@ -24,7 +24,8 @@ typedef struct {
 	unsigned int	icache_line_size;
 	unsigned int	ecache_size;
 	unsigned int	ecache_line_size;
-	int		core_id;
+	unsigned short	sock_id;
+	unsigned short	core_id;
 	int		proc_id;
 } cpuinfo_sparc;
 
diff --git a/arch/sparc/include/asm/io_32.h b/arch/sparc/include/asm/io_32.h
index 407ac14..57f26c3 100644
--- a/arch/sparc/include/asm/io_32.h
+++ b/arch/sparc/include/asm/io_32.h
@@ -129,6 +129,7 @@ static inline void sbus_memcpy_toio(volatile void __iomem *dst,
 void __iomem *ioremap(unsigned long offset, unsigned long size);
 #define ioremap_nocache(X,Y)	ioremap((X),(Y))
 #define ioremap_wc(X,Y)		ioremap((X),(Y))
+#define ioremap_wt(X,Y)		ioremap((X),(Y))
 void iounmap(volatile void __iomem *addr);
 
 /* Create a virtual mapping cookie for an IO port range */
diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index 50d4840..c32fa3f 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -402,6 +402,7 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 
 #define ioremap_nocache(X,Y)		ioremap((X),(Y))
 #define ioremap_wc(X,Y)			ioremap((X),(Y))
+#define ioremap_wt(X,Y)			ioremap((X),(Y))
 
 static inline void iounmap(volatile void __iomem *addr)
 {
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index dc165eb..2a52c91 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -308,12 +308,26 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot)
 	"	sllx		%1, 32, %1\n"
 	"	or		%0, %1, %0\n"
 	"	.previous\n"
+	"	.section	.sun_m7_2insn_patch, \"ax\"\n"
+	"	.word		661b\n"
+	"	sethi		%%uhi(%4), %1\n"
+	"	sethi		%%hi(%4), %0\n"
+	"	.word		662b\n"
+	"	or		%1, %%ulo(%4), %1\n"
+	"	or		%0, %%lo(%4), %0\n"
+	"	.word		663b\n"
+	"	sllx		%1, 32, %1\n"
+	"	or		%0, %1, %0\n"
+	"	.previous\n"
 	: "=r" (mask), "=r" (tmp)
 	: "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U |
 	       _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U |
 	       _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4U),
 	  "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
 	       _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V |
+	       _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V),
+	  "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
+	       _PAGE_CP_4V | _PAGE_E_4V |
 	       _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V));
 
 	return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask));
@@ -342,9 +356,15 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot)
 	"	andn		%0, %4, %0\n"
 	"	or		%0, %5, %0\n"
 	"	.previous\n"
+	"	.section	.sun_m7_2insn_patch, \"ax\"\n"
+	"	.word		661b\n"
+	"	andn		%0, %6, %0\n"
+	"	or		%0, %5, %0\n"
+	"	.previous\n"
 	: "=r" (val)
 	: "0" (val), "i" (_PAGE_CP_4U | _PAGE_CV_4U), "i" (_PAGE_E_4U),
-	             "i" (_PAGE_CP_4V | _PAGE_CV_4V), "i" (_PAGE_E_4V));
+	             "i" (_PAGE_CP_4V | _PAGE_CV_4V), "i" (_PAGE_E_4V),
+	             "i" (_PAGE_CP_4V));
 
 	return __pgprot(val);
 }
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index ed8f071..01d1704 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -40,11 +40,12 @@ static inline int pcibus_to_node(struct pci_bus *pbus)
 #ifdef CONFIG_SMP
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).proc_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).core_id)
-#define topology_core_cpumask(cpu)		(&cpu_core_map[cpu])
-#define topology_thread_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
+#define topology_core_cpumask(cpu)		(&cpu_core_sib_map[cpu])
+#define topology_sibling_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
 #endif /* CONFIG_SMP */
 
 extern cpumask_t cpu_core_map[NR_CPUS];
+extern cpumask_t cpu_core_sib_map[NR_CPUS];
 static inline const struct cpumask *cpu_coregroup_mask(int cpu)
 {
         return &cpu_core_map[cpu];
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index 6fd4436..ec9c04d 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -79,6 +79,8 @@ struct sun4v_2insn_patch_entry {
 };
 extern struct sun4v_2insn_patch_entry __sun4v_2insn_patch,
 	__sun4v_2insn_patch_end;
+extern struct sun4v_2insn_patch_entry __sun_m7_2insn_patch,
+	__sun_m7_2insn_patch_end;
 
 
 #endif /* !(__ASSEMBLY__) */
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index 07cc49e5..0f67942 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -69,6 +69,8 @@ void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
 			     struct sun4v_1insn_patch_entry *);
 void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
 			     struct sun4v_2insn_patch_entry *);
+void sun_m7_patch_2insn_range(struct sun4v_2insn_patch_entry *,
+			     struct sun4v_2insn_patch_entry *);
 extern unsigned int dcache_parity_tl1_occurred;
 extern unsigned int icache_parity_tl1_occurred;
 
diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c
index 94e392b..814fb17 100644
--- a/arch/sparc/kernel/leon_pci_grpci2.c
+++ b/arch/sparc/kernel/leon_pci_grpci2.c
@@ -723,7 +723,6 @@ static int grpci2_of_probe(struct platform_device *ofdev)
 		err = -ENOMEM;
 		goto err1;
 	}
-	memset(grpci2priv, 0, sizeof(*grpci2priv));
 	priv->regs = regs;
 	priv->irq = ofdev->archdata.irqs[0]; /* BASE IRQ */
 	priv->irq_mode = (capability & STS_IRQMODE) >> STS_IRQMODE_BIT;
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index 26c80e1..6f80936 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -614,45 +614,68 @@ static void fill_in_one_cache(cpuinfo_sparc *c, struct mdesc_handle *hp, u64 mp)
 	}
 }
 
-static void mark_core_ids(struct mdesc_handle *hp, u64 mp, int core_id)
+static void find_back_node_value(struct mdesc_handle *hp, u64 node,
+				 char *srch_val,
+				 void (*func)(struct mdesc_handle *, u64, int),
+				 u64 val, int depth)
 {
-	u64 a;
-
-	mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_BACK) {
-		u64 t = mdesc_arc_target(hp, a);
-		const char *name;
-		const u64 *id;
+	u64 arc;
 
-		name = mdesc_node_name(hp, t);
-		if (!strcmp(name, "cpu")) {
-			id = mdesc_get_property(hp, t, "id", NULL);
-			if (*id < NR_CPUS)
-				cpu_data(*id).core_id = core_id;
-		} else {
-			u64 j;
+	/* Since we have an estimate of recursion depth, do a sanity check. */
+	if (depth == 0)
+		return;
 
-			mdesc_for_each_arc(j, hp, t, MDESC_ARC_TYPE_BACK) {
-				u64 n = mdesc_arc_target(hp, j);
-				const char *n_name;
+	mdesc_for_each_arc(arc, hp, node, MDESC_ARC_TYPE_BACK) {
+		u64 n = mdesc_arc_target(hp, arc);
+		const char *name = mdesc_node_name(hp, n);
 
-				n_name = mdesc_node_name(hp, n);
-				if (strcmp(n_name, "cpu"))
-					continue;
+		if (!strcmp(srch_val, name))
+			(*func)(hp, n, val);
 
-				id = mdesc_get_property(hp, n, "id", NULL);
-				if (*id < NR_CPUS)
-					cpu_data(*id).core_id = core_id;
-			}
-		}
+		find_back_node_value(hp, n, srch_val, func, val, depth-1);
 	}
 }
 
+static void __mark_core_id(struct mdesc_handle *hp, u64 node,
+			   int core_id)
+{
+	const u64 *id = mdesc_get_property(hp, node, "id", NULL);
+
+	if (*id < num_possible_cpus())
+		cpu_data(*id).core_id = core_id;
+}
+
+static void __mark_sock_id(struct mdesc_handle *hp, u64 node,
+			   int sock_id)
+{
+	const u64 *id = mdesc_get_property(hp, node, "id", NULL);
+
+	if (*id < num_possible_cpus())
+		cpu_data(*id).sock_id = sock_id;
+}
+
+static void mark_core_ids(struct mdesc_handle *hp, u64 mp,
+			  int core_id)
+{
+	find_back_node_value(hp, mp, "cpu", __mark_core_id, core_id, 10);
+}
+
+static void mark_sock_ids(struct mdesc_handle *hp, u64 mp,
+			  int sock_id)
+{
+	find_back_node_value(hp, mp, "cpu", __mark_sock_id, sock_id, 10);
+}
+
 static void set_core_ids(struct mdesc_handle *hp)
 {
 	int idx;
 	u64 mp;
 
 	idx = 1;
+
+	/* Identify unique cores by looking for cpus backpointed to by
+	 * level 1 instruction caches.
+	 */
 	mdesc_for_each_node_by_name(hp, mp, "cache") {
 		const u64 *level;
 		const char *type;
@@ -667,11 +690,72 @@ static void set_core_ids(struct mdesc_handle *hp)
 			continue;
 
 		mark_core_ids(hp, mp, idx);
+		idx++;
+	}
+}
+
+static int set_sock_ids_by_cache(struct mdesc_handle *hp, int level)
+{
+	u64 mp;
+	int idx = 1;
+	int fnd = 0;
+
+	/* Identify unique sockets by looking for cpus backpointed to by
+	 * shared level n caches.
+	 */
+	mdesc_for_each_node_by_name(hp, mp, "cache") {
+		const u64 *cur_lvl;
+
+		cur_lvl = mdesc_get_property(hp, mp, "level", NULL);
+		if (*cur_lvl != level)
+			continue;
+
+		mark_sock_ids(hp, mp, idx);
+		idx++;
+		fnd = 1;
+	}
+	return fnd;
+}
+
+static void set_sock_ids_by_socket(struct mdesc_handle *hp, u64 mp)
+{
+	int idx = 1;
 
+	mdesc_for_each_node_by_name(hp, mp, "socket") {
+		u64 a;
+
+		mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_FWD) {
+			u64 t = mdesc_arc_target(hp, a);
+			const char *name;
+			const u64 *id;
+
+			name = mdesc_node_name(hp, t);
+			if (strcmp(name, "cpu"))
+				continue;
+
+			id = mdesc_get_property(hp, t, "id", NULL);
+			if (*id < num_possible_cpus())
+				cpu_data(*id).sock_id = idx;
+		}
 		idx++;
 	}
 }
 
+static void set_sock_ids(struct mdesc_handle *hp)
+{
+	u64 mp;
+
+	/* If machine description exposes sockets data use it.
+	 * Otherwise fallback to use shared L3 or L2 caches.
+	 */
+	mp = mdesc_node_by_name(hp, MDESC_NODE_NULL, "sockets");
+	if (mp != MDESC_NODE_NULL)
+		return set_sock_ids_by_socket(hp, mp);
+
+	if (!set_sock_ids_by_cache(hp, 3))
+		set_sock_ids_by_cache(hp, 2);
+}
+
 static void mark_proc_ids(struct mdesc_handle *hp, u64 mp, int proc_id)
 {
 	u64 a;
@@ -707,7 +791,6 @@ static void __set_proc_ids(struct mdesc_handle *hp, const char *exec_unit_name)
 			continue;
 
 		mark_proc_ids(hp, mp, idx);
-
 		idx++;
 	}
 }
@@ -900,6 +983,7 @@ void mdesc_fill_in_cpu_data(cpumask_t *mask)
 
 	set_core_ids(hp);
 	set_proc_ids(hp);
+	set_sock_ids(hp);
 
 	mdesc_release(hp);
 
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 6f7251f..c928bc6 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -1002,6 +1002,38 @@ static int __init pcibios_init(void)
 subsys_initcall(pcibios_init);
 
 #ifdef CONFIG_SYSFS
+
+#define SLOT_NAME_SIZE  11  /* Max decimal digits + null in u32 */
+
+static void pcie_bus_slot_names(struct pci_bus *pbus)
+{
+	struct pci_dev *pdev;
+	struct pci_bus *bus;
+
+	list_for_each_entry(pdev, &pbus->devices, bus_list) {
+		char name[SLOT_NAME_SIZE];
+		struct pci_slot *pci_slot;
+		const u32 *slot_num;
+		int len;
+
+		slot_num = of_get_property(pdev->dev.of_node,
+					   "physical-slot#", &len);
+
+		if (slot_num == NULL || len != 4)
+			continue;
+
+		snprintf(name, sizeof(name), "%u", slot_num[0]);
+		pci_slot = pci_create_slot(pbus, slot_num[0], name, NULL);
+
+		if (IS_ERR(pci_slot))
+			pr_err("PCI: pci_create_slot returned %ld.\n",
+			       PTR_ERR(pci_slot));
+	}
+
+	list_for_each_entry(bus, &pbus->children, node)
+		pcie_bus_slot_names(bus);
+}
+
 static void pci_bus_slot_names(struct device_node *node, struct pci_bus *bus)
 {
 	const struct pci_slot_names {
@@ -1053,18 +1085,29 @@ static int __init of_pci_slot_init(void)
 
 	while ((pbus = pci_find_next_bus(pbus)) != NULL) {
 		struct device_node *node;
+		struct pci_dev *pdev;
+
+		pdev = list_first_entry(&pbus->devices, struct pci_dev,
+					bus_list);
 
-		if (pbus->self) {
-			/* PCI->PCI bridge */
-			node = pbus->self->dev.of_node;
+		if (pdev && pci_is_pcie(pdev)) {
+			pcie_bus_slot_names(pbus);
 		} else {
-			struct pci_pbm_info *pbm = pbus->sysdata;
 
-			/* Host PCI controller */
-			node = pbm->op->dev.of_node;
-		}
+			if (pbus->self) {
+
+				/* PCI->PCI bridge */
+				node = pbus->self->dev.of_node;
+
+			} else {
+				struct pci_pbm_info *pbm = pbus->sysdata;
 
-		pci_bus_slot_names(node, pbus);
+				/* Host PCI controller */
+				node = pbm->op->dev.of_node;
+			}
+
+			pci_bus_slot_names(node, pbus);
+		}
 	}
 
 	return 0;
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index c38d19f..f7b2617 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -255,6 +255,24 @@ void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
 	}
 }
 
+void sun_m7_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
+			     struct sun4v_2insn_patch_entry *end)
+{
+	while (start < end) {
+		unsigned long addr = start->addr;
+
+		*(unsigned int *) (addr +  0) = start->insns[0];
+		wmb();
+		__asm__ __volatile__("flush	%0" : : "r" (addr +  0));
+
+		*(unsigned int *) (addr +  4) = start->insns[1];
+		wmb();
+		__asm__ __volatile__("flush	%0" : : "r" (addr +  4));
+
+		start++;
+	}
+}
+
 static void __init sun4v_patch(void)
 {
 	extern void sun4v_hvapi_init(void);
@@ -267,6 +285,9 @@ static void __init sun4v_patch(void)
 
 	sun4v_patch_2insn_range(&__sun4v_2insn_patch,
 				&__sun4v_2insn_patch_end);
+	if (sun4v_chip_type == SUN4V_CHIP_SPARC_M7)
+		sun_m7_patch_2insn_range(&__sun_m7_2insn_patch,
+					 &__sun_m7_2insn_patch_end);
 
 	sun4v_hvapi_init();
 }
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 61139d9..19cd08d 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -60,8 +60,12 @@ DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
 	{ [0 ... NR_CPUS-1] = CPU_MASK_NONE };
 
+cpumask_t cpu_core_sib_map[NR_CPUS] __read_mostly = {
+	[0 ... NR_CPUS-1] = CPU_MASK_NONE };
+
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 EXPORT_SYMBOL(cpu_core_map);
+EXPORT_SYMBOL(cpu_core_sib_map);
 
 static cpumask_t smp_commenced_mask;
 
@@ -1243,6 +1247,15 @@ void smp_fill_in_sib_core_maps(void)
 		}
 	}
 
+	for_each_present_cpu(i)  {
+		unsigned int j;
+
+		for_each_present_cpu(j)  {
+			if (cpu_data(i).sock_id == cpu_data(j).sock_id)
+				cpumask_set_cpu(j, &cpu_core_sib_map[i]);
+		}
+	}
+
 	for_each_present_cpu(i) {
 		unsigned int j;
 
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 0924305..f1a2f68 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -138,6 +138,11 @@ SECTIONS
 		*(.pause_3insn_patch)
 		__pause_3insn_patch_end = .;
 	}
+	.sun_m7_2insn_patch : {
+		__sun_m7_2insn_patch = .;
+		*(.sun_m7_2insn_patch)
+		__sun_m7_2insn_patch_end = .;
+	}
 	PERCPU_SECTION(SMP_CACHE_BYTES)
 
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 70d8171..c399e7b 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -21,6 +21,7 @@
 #include <linux/perf_event.h>
 #include <linux/interrupt.h>
 #include <linux/kdebug.h>
+#include <linux/uaccess.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -29,7 +30,6 @@
 #include <asm/setup.h>
 #include <asm/smp.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
 
 #include "mm_32.h"
 
@@ -196,7 +196,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (pagefault_disabled() || !mm)
 		goto no_context;
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 4798232..e9268ea 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -22,12 +22,12 @@
 #include <linux/kdebug.h>
 #include <linux/percpu.h>
 #include <linux/context_tracking.h>
+#include <linux/uaccess.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/openprom.h>
 #include <asm/oplib.h>
-#include <asm/uaccess.h>
 #include <asm/asi.h>
 #include <asm/lsu.h>
 #include <asm/sections.h>
@@ -330,7 +330,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto intr_or_no_mm;
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
diff --git a/arch/sparc/mm/highmem.c b/arch/sparc/mm/highmem.c
index 449f864..a454ec5 100644
--- a/arch/sparc/mm/highmem.c
+++ b/arch/sparc/mm/highmem.c
@@ -53,7 +53,7 @@ void *kmap_atomic(struct page *page)
 	unsigned long vaddr;
 	long idx, type;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -91,6 +91,7 @@ void __kunmap_atomic(void *kvaddr)
 
 	if (vaddr < FIXADDR_START) { // FIXME
 		pagefault_enable();
+		preempt_enable();
 		return;
 	}
 
@@ -126,5 +127,6 @@ void __kunmap_atomic(void *kvaddr)
 
 	kmap_atomic_idx_pop();
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 4ca0d6b..c5d08b8 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -54,6 +54,7 @@
 #include "init_64.h"
 
 unsigned long kern_linear_pte_xor[4] __read_mostly;
+static unsigned long page_cache4v_flag;
 
 /* A bitmap, two bits for every 256MB of physical memory.  These two
  * bits determine what page size we use for kernel linear
@@ -1909,11 +1910,24 @@ static void __init sun4u_linear_pte_xor_finalize(void)
 
 static void __init sun4v_linear_pte_xor_finalize(void)
 {
+	unsigned long pagecv_flag;
+
+	/* Bit 9 of TTE is no longer CV bit on M7 processor and it instead
+	 * enables MCD error. Do not set bit 9 on M7 processor.
+	 */
+	switch (sun4v_chip_type) {
+	case SUN4V_CHIP_SPARC_M7:
+		pagecv_flag = 0x00;
+		break;
+	default:
+		pagecv_flag = _PAGE_CV_4V;
+		break;
+	}
 #ifndef CONFIG_DEBUG_PAGEALLOC
 	if (cpu_pgsz_mask & HV_PGSZ_MASK_256MB) {
 		kern_linear_pte_xor[1] = (_PAGE_VALID | _PAGE_SZ256MB_4V) ^
 			PAGE_OFFSET;
-		kern_linear_pte_xor[1] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+		kern_linear_pte_xor[1] |= (_PAGE_CP_4V | pagecv_flag |
 					   _PAGE_P_4V | _PAGE_W_4V);
 	} else {
 		kern_linear_pte_xor[1] = kern_linear_pte_xor[0];
@@ -1922,7 +1936,7 @@ static void __init sun4v_linear_pte_xor_finalize(void)
 	if (cpu_pgsz_mask & HV_PGSZ_MASK_2GB) {
 		kern_linear_pte_xor[2] = (_PAGE_VALID | _PAGE_SZ2GB_4V) ^
 			PAGE_OFFSET;
-		kern_linear_pte_xor[2] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+		kern_linear_pte_xor[2] |= (_PAGE_CP_4V | pagecv_flag |
 					   _PAGE_P_4V | _PAGE_W_4V);
 	} else {
 		kern_linear_pte_xor[2] = kern_linear_pte_xor[1];
@@ -1931,7 +1945,7 @@ static void __init sun4v_linear_pte_xor_finalize(void)
 	if (cpu_pgsz_mask & HV_PGSZ_MASK_16GB) {
 		kern_linear_pte_xor[3] = (_PAGE_VALID | _PAGE_SZ16GB_4V) ^
 			PAGE_OFFSET;
-		kern_linear_pte_xor[3] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+		kern_linear_pte_xor[3] |= (_PAGE_CP_4V | pagecv_flag |
 					   _PAGE_P_4V | _PAGE_W_4V);
 	} else {
 		kern_linear_pte_xor[3] = kern_linear_pte_xor[2];
@@ -1958,6 +1972,13 @@ static phys_addr_t __init available_memory(void)
 	return available;
 }
 
+#define _PAGE_CACHE_4U	(_PAGE_CP_4U | _PAGE_CV_4U)
+#define _PAGE_CACHE_4V	(_PAGE_CP_4V | _PAGE_CV_4V)
+#define __DIRTY_BITS_4U	 (_PAGE_MODIFIED_4U | _PAGE_WRITE_4U | _PAGE_W_4U)
+#define __DIRTY_BITS_4V	 (_PAGE_MODIFIED_4V | _PAGE_WRITE_4V | _PAGE_W_4V)
+#define __ACCESS_BITS_4U (_PAGE_ACCESSED_4U | _PAGE_READ_4U | _PAGE_R)
+#define __ACCESS_BITS_4V (_PAGE_ACCESSED_4V | _PAGE_READ_4V | _PAGE_R)
+
 /* We need to exclude reserved regions. This exclusion will include
  * vmlinux and initrd. To be more precise the initrd size could be used to
  * compute a new lower limit because it is freed later during initialization.
@@ -2034,6 +2055,25 @@ void __init paging_init(void)
 	memset(swapper_4m_tsb, 0x40, sizeof(swapper_4m_tsb));
 #endif
 
+	/* TTE.cv bit on sparc v9 occupies the same position as TTE.mcde
+	 * bit on M7 processor. This is a conflicting usage of the same
+	 * bit. Enabling TTE.cv on M7 would turn on Memory Corruption
+	 * Detection error on all pages and this will lead to problems
+	 * later. Kernel does not run with MCD enabled and hence rest
+	 * of the required steps to fully configure memory corruption
+	 * detection are not taken. We need to ensure TTE.mcde is not
+	 * set on M7 processor. Compute the value of cacheability
+	 * flag for use later taking this into consideration.
+	 */
+	switch (sun4v_chip_type) {
+	case SUN4V_CHIP_SPARC_M7:
+		page_cache4v_flag = _PAGE_CP_4V;
+		break;
+	default:
+		page_cache4v_flag = _PAGE_CACHE_4V;
+		break;
+	}
+
 	if (tlb_type == hypervisor)
 		sun4v_pgprot_init();
 	else
@@ -2274,13 +2314,6 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
-#define _PAGE_CACHE_4U	(_PAGE_CP_4U | _PAGE_CV_4U)
-#define _PAGE_CACHE_4V	(_PAGE_CP_4V | _PAGE_CV_4V)
-#define __DIRTY_BITS_4U	 (_PAGE_MODIFIED_4U | _PAGE_WRITE_4U | _PAGE_W_4U)
-#define __DIRTY_BITS_4V	 (_PAGE_MODIFIED_4V | _PAGE_WRITE_4V | _PAGE_W_4V)
-#define __ACCESS_BITS_4U (_PAGE_ACCESSED_4U | _PAGE_READ_4U | _PAGE_R)
-#define __ACCESS_BITS_4V (_PAGE_ACCESSED_4V | _PAGE_READ_4V | _PAGE_R)
-
 pgprot_t PAGE_KERNEL __read_mostly;
 EXPORT_SYMBOL(PAGE_KERNEL);
 
@@ -2312,8 +2345,7 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
 		    _PAGE_P_4U | _PAGE_W_4U);
 	if (tlb_type == hypervisor)
 		pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4V |
-			    _PAGE_CP_4V | _PAGE_CV_4V |
-			    _PAGE_P_4V | _PAGE_W_4V);
+			    page_cache4v_flag | _PAGE_P_4V | _PAGE_W_4V);
 
 	pte_base |= _PAGE_PMD_HUGE;
 
@@ -2450,14 +2482,14 @@ static void __init sun4v_pgprot_init(void)
 	int i;
 
 	PAGE_KERNEL = __pgprot (_PAGE_PRESENT_4V | _PAGE_VALID |
-				_PAGE_CACHE_4V | _PAGE_P_4V |
+				page_cache4v_flag | _PAGE_P_4V |
 				__ACCESS_BITS_4V | __DIRTY_BITS_4V |
 				_PAGE_EXEC_4V);
 	PAGE_KERNEL_LOCKED = PAGE_KERNEL;
 
 	_PAGE_IE = _PAGE_IE_4V;
 	_PAGE_E = _PAGE_E_4V;
-	_PAGE_CACHE = _PAGE_CACHE_4V;
+	_PAGE_CACHE = page_cache4v_flag;
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	kern_linear_pte_xor[0] = _PAGE_VALID ^ PAGE_OFFSET;
@@ -2465,8 +2497,8 @@ static void __init sun4v_pgprot_init(void)
 	kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZ4MB_4V) ^
 		PAGE_OFFSET;
 #endif
-	kern_linear_pte_xor[0] |= (_PAGE_CP_4V | _PAGE_CV_4V |
-				   _PAGE_P_4V | _PAGE_W_4V);
+	kern_linear_pte_xor[0] |= (page_cache4v_flag | _PAGE_P_4V |
+				   _PAGE_W_4V);
 
 	for (i = 1; i < 4; i++)
 		kern_linear_pte_xor[i] = kern_linear_pte_xor[0];
@@ -2479,12 +2511,12 @@ static void __init sun4v_pgprot_init(void)
 			     _PAGE_SZ4MB_4V | _PAGE_SZ512K_4V |
 			     _PAGE_SZ64K_4V | _PAGE_SZ8K_4V);
 
-	page_none = _PAGE_PRESENT_4V | _PAGE_ACCESSED_4V | _PAGE_CACHE_4V;
-	page_shared = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+	page_none = _PAGE_PRESENT_4V | _PAGE_ACCESSED_4V | page_cache4v_flag;
+	page_shared = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
 		       __ACCESS_BITS_4V | _PAGE_WRITE_4V | _PAGE_EXEC_4V);
-	page_copy   = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+	page_copy   = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
 		       __ACCESS_BITS_4V | _PAGE_EXEC_4V);
-	page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+	page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
 			 __ACCESS_BITS_4V | _PAGE_EXEC_4V);
 
 	page_exec_bit = _PAGE_EXEC_4V;
@@ -2542,7 +2574,7 @@ static unsigned long kern_large_tte(unsigned long paddr)
 	       _PAGE_EXEC_4U | _PAGE_L_4U | _PAGE_W_4U);
 	if (tlb_type == hypervisor)
 		val = (_PAGE_VALID | _PAGE_SZ4MB_4V |
-		       _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_P_4V |
+		       page_cache4v_flag | _PAGE_P_4V |
 		       _PAGE_EXEC_4V | _PAGE_W_4V);
 
 	return val | paddr;
@@ -2706,7 +2738,7 @@ void hugetlb_setup(struct pt_regs *regs)
 	struct mm_struct *mm = current->mm;
 	struct tsb_config *tp;
 
-	if (in_atomic() || !mm) {
+	if (faulthandler_disabled() || !mm) {
 		const struct exception_table_entry *entry;
 
 		entry = search_exception_tables(regs->tpc);