Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc-next

Pull sparc updates from David Miller:

 1) Use register window state adjustment instructions when available,
    from Anthony Yznaga.

 2) Add VCC console concentrator driver, from Jag Raman.

 3) Add 16GB hugepage support, from Nitin Gupta.

 4) Support cpu 'poke' hypercall, from Vijay Kumar.

 5) Add M7/M8 optimized memcpy/memset/copy_{to,from}_user, from Babu
    Moger.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc-next: (33 commits)
  sparc64: Handle additional cases of no fault loads
  sparc64: speed up etrap/rtrap on NG2 and later processors
  sparc64: vcc: make ktermios const
  sparc: leon: grpci1: constify of_device_id
  sparc: leon: grpci2: constify of_device_id
  sparc64: vcc: Check for IS_ERR() instead of NULL
  sparc64: Cleanup hugepage table walk functions
  sparc64: Add 16GB hugepage support
  sparc64: Support huge PUD case in get_user_pages
  sparc64: vcc: Add install & cleanup TTY operations
  sparc64: vcc: Add break_ctl TTY operation
  sparc64: vcc: Add chars_in_buffer TTY operation
  sparc64: vcc: Add write & write_room TTY operations
  sparc64: vcc: Add hangup TTY operation
  sparc64: vcc: Add open & close TTY operations
  sparc64: vcc: Enable LDC event processing engine
  sparc64: vcc: Add RX & TX timer for delayed LDC operation
  sparc64: vcc: Create sysfs attribute group
  sparc64: vcc: Enable VCC port probe and removal
  sparc64: vcc: TTY driver initialization and cleanup
  ...

37 files changed, 2326 insertions, 297 deletions

diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig
index ca8609d7292f..4d4e1cc6402f 100644
--- a/arch/sparc/configs/sparc64_defconfig
+++ b/arch/sparc/configs/sparc64_defconfig
@@ -238,3 +238,4 @@ CONFIG_CRYPTO_TWOFISH=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRC16=m
 CONFIG_LIBCRC32C=m
+CONFIG_VCC=m
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index d1f837dc77a4..0ca7caab1b06 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -4,6 +4,13 @@
 #include <asm/page.h>
 #include <asm-generic/hugetlb.h>
 
+#ifdef CONFIG_HUGETLB_PAGE
+struct pud_huge_patch_entry {
+	unsigned int addr;
+	unsigned int insn;
+};
+extern struct pud_huge_patch_entry __pud_huge_patch, __pud_huge_patch_end;
+#endif
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h
index 73cb8978df58..3dc9215d0357 100644
--- a/arch/sparc/include/asm/hypervisor.h
+++ b/arch/sparc/include/asm/hypervisor.h
@@ -298,6 +298,24 @@ unsigned long sun4v_cpu_stop(unsigned long cpuid);
 unsigned long sun4v_cpu_yield(void);
 #endif
 
+/* cpu_poke()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_CPU_POKE
+ * RET0:	status
+ * ERRORS:	ENOCPU		cpuid refers to a CPU that does not exist
+ *		EINVAL		cpuid is current CPU
+ *
+ * Poke CPU cpuid. If the target CPU is currently suspended having
+ * invoked the cpu-yield service, that vCPU will be resumed.
+ * Poke interrupts may only be sent to valid, non-local CPUs.
+ * It is not legal to poke the current vCPU.
+ */
+#define HV_FAST_CPU_POKE                0x13
+
+#ifndef __ASSEMBLY__
+unsigned long sun4v_cpu_poke(unsigned long cpuid);
+#endif
+
 /* cpu_qconf()
  * TRAP:	HV_FAST_TRAP
  * FUNCTION:	HV_FAST_CPU_QCONF
diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h
index 5961b2d8398a..8ee1f97589a1 100644
--- a/arch/sparc/include/asm/page_64.h
+++ b/arch/sparc/include/asm/page_64.h
@@ -17,6 +17,7 @@
 
 #define HPAGE_SHIFT		23
 #define REAL_HPAGE_SHIFT	22
+#define HPAGE_16GB_SHIFT	34
 #define HPAGE_2GB_SHIFT		31
 #define HPAGE_256MB_SHIFT	28
 #define HPAGE_64K_SHIFT		16
@@ -28,7 +29,7 @@
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
 #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 #define REAL_HPAGE_PER_HPAGE	(_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT))
-#define HUGE_MAX_HSTATE		4
+#define HUGE_MAX_HSTATE		5
 #endif
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 6fbd931f0570..4fefe3762083 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -414,6 +414,11 @@ static inline bool is_hugetlb_pmd(pmd_t pmd)
 	return !!(pmd_val(pmd) & _PAGE_PMD_HUGE);
 }
 
+static inline bool is_hugetlb_pud(pud_t pud)
+{
+	return !!(pud_val(pud) & _PAGE_PUD_HUGE);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline pmd_t pmd_mkhuge(pmd_t pmd)
 {
@@ -687,6 +692,8 @@ static inline unsigned long pmd_write(pmd_t pmd)
 	return pte_write(pte);
 }
 
+#define pud_write(pud)	pte_write(__pte(pud_val(pud)))
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline unsigned long pmd_dirty(pmd_t pmd)
 {
@@ -823,9 +830,18 @@ static inline unsigned long __pmd_page(pmd_t pmd)
 
 	return ((unsigned long) __va(pfn << PAGE_SHIFT));
 }
+
+static inline unsigned long pud_page_vaddr(pud_t pud)
+{
+	pte_t pte = __pte(pud_val(pud));
+	unsigned long pfn;
+
+	pfn = pte_pfn(pte);
+
+	return ((unsigned long) __va(pfn << PAGE_SHIFT));
+}
+
 #define pmd_page(pmd) 			virt_to_page((void *)__pmd_page(pmd))
-#define pud_page_vaddr(pud)		\
-	((unsigned long) __va(pud_val(pud)))
 #define pud_page(pud) 			virt_to_page((void *)pud_page_vaddr(pud))
 #define pmd_clear(pmdp)			(pmd_val(*(pmdp)) = 0UL)
 #define pud_present(pud)		(pud_val(pud) != 0U)
diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h
index ce2233f7e662..a75089285db8 100644
--- a/arch/sparc/include/asm/smp_64.h
+++ b/arch/sparc/include/asm/smp_64.h
@@ -33,6 +33,9 @@
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 extern cpumask_t cpu_core_map[NR_CPUS];
 
+void smp_init_cpu_poke(void);
+void scheduler_poke(void);
+
 void arch_send_call_function_single_ipi(int cpu);
 void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
@@ -74,6 +77,8 @@ void __cpu_die(unsigned int cpu);
 #define smp_fetch_global_regs() do { } while (0)
 #define smp_fetch_global_pmu() do { } while (0)
 #define smp_fill_in_cpu_possible_map() do { } while (0)
+#define smp_init_cpu_poke() do { } while (0)
+#define scheduler_poke() do { } while (0)
 
 #endif /* !(CONFIG_SMP) */
 
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index ff05992dae7a..dfc538609eb2 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -73,6 +73,8 @@ struct sun4v_1insn_patch_entry {
 };
 extern struct sun4v_1insn_patch_entry __sun4v_1insn_patch,
 	__sun4v_1insn_patch_end;
+extern struct sun4v_1insn_patch_entry __fast_win_ctrl_1insn_patch,
+	__fast_win_ctrl_1insn_patch_end;
 
 struct sun4v_2insn_patch_entry {
 	unsigned int	addr;
diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h
index 32258e08da03..acf55063aa3d 100644
--- a/arch/sparc/include/asm/tsb.h
+++ b/arch/sparc/include/asm/tsb.h
@@ -195,6 +195,41 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 nop; \
 699:
 
+	/* PUD has been loaded into REG1, interpret the value, seeing
+	 * if it is a HUGE PUD or a normal one.  If it is not valid
+	 * then jump to FAIL_LABEL.  If it is a HUGE PUD, and it
+	 * translates to a valid PTE, branch to PTE_LABEL.
+	 *
+	 * We have to propagate bits [32:22] from the virtual address
+	 * to resolve at 4M granularity.
+	 */
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+#define USER_PGTABLE_CHECK_PUD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, PTE_LABEL) \
+700:	ba 700f;					\
+	 nop;						\
+	.section	.pud_huge_patch, "ax";		\
+	.word		700b;				\
+	nop;						\
+	.previous;					\
+	brz,pn		REG1, FAIL_LABEL;		\
+	 sethi		%uhi(_PAGE_PUD_HUGE), REG2;	\
+	sllx		REG2, 32, REG2;			\
+	andcc		REG1, REG2, %g0;		\
+	be,pt		%xcc, 700f;			\
+	 sethi		%hi(0x1ffc0000), REG2;		\
+	sllx		REG2, 1, REG2;			\
+	brgez,pn	REG1, FAIL_LABEL;		\
+	 andn		REG1, REG2, REG1;		\
+	and		VADDR, REG2, REG2;		\
+	brlz,pt		REG1, PTE_LABEL;		\
+	 or		REG1, REG2, REG1;		\
+700:
+#else
+#define USER_PGTABLE_CHECK_PUD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, PTE_LABEL) \
+	brz,pn		REG1, FAIL_LABEL; \
+	 nop;
+#endif
+
 	/* PMD has been loaded into REG1, interpret the value, seeing
 	 * if it is a HUGE PMD or a normal one.  If it is not valid
 	 * then jump to FAIL_LABEL.  If it is a HUGE PMD, and it
@@ -242,6 +277,7 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
 	andn		REG2, 0x7, REG2; \
 	ldxa		[REG1 + REG2] ASI_PHYS_USE_EC, REG1; \
+	USER_PGTABLE_CHECK_PUD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, 800f) \
 	brz,pn		REG1, FAIL_LABEL; \
 	 sllx		VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \
 	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index d1c47e9f0090..f3d4ac232690 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -52,6 +52,7 @@ struct vio_ver_info {
 #define VDEV_NETWORK_SWITCH	0x02
 #define VDEV_DISK		0x03
 #define VDEV_DISK_SERVER	0x04
+#define VDEV_CONSOLE_CON	0x05
 
 	u8			resv1[3];
 	u64			resv2[5];
@@ -282,6 +283,14 @@ struct vio_dring_state {
 	struct ldc_trans_cookie	cookies[VIO_MAX_RING_COOKIES];
 };
 
+#define VIO_TAG_SIZE		((int)sizeof(struct vio_msg_tag))
+#define VIO_VCC_MTU_SIZE	(LDC_PACKET_SIZE - VIO_TAG_SIZE)
+
+struct vio_vcc {
+	struct vio_msg_tag	tag;
+	char			data[VIO_VCC_MTU_SIZE];
+};
+
 static inline void *vio_dring_cur(struct vio_dring_state *dr)
 {
 	return dr->base + (dr->entry_size * dr->prod);
diff --git a/arch/sparc/kernel/etrap_64.S b/arch/sparc/kernel/etrap_64.S
index 1276ca2567ba..5c237467d156 100644
--- a/arch/sparc/kernel/etrap_64.S
+++ b/arch/sparc/kernel/etrap_64.S
@@ -38,7 +38,11 @@ etrap_syscall:	TRAP_LOAD_THREAD_REG(%g6, %g1)
 		or	%g1, %g3, %g1
 		bne,pn	%xcc, 1f
 		 sub	%sp, STACKFRAME_SZ+TRACEREG_SZ-STACK_BIAS, %g2
-		wrpr	%g0, 7, %cleanwin
+661:		wrpr	%g0, 7, %cleanwin
+		.section .fast_win_ctrl_1insn_patch, "ax"
+		.word	661b
+		.word	0x85880000	! allclean
+		.previous
 
 		sethi	%hi(TASK_REGOFF), %g2
 		sethi	%hi(TSTATE_PEF), %g3
@@ -88,16 +92,30 @@ etrap_save:	save	%g2, -STACK_BIAS, %sp
 
 		bne,pn	%xcc, 3f
 		 mov	PRIMARY_CONTEXT, %l4
-		rdpr	%canrestore, %g3
+661:		rdpr	%canrestore, %g3
+		.section .fast_win_ctrl_1insn_patch, "ax"
+		.word	661b
+		nop
+		.previous
+
 		rdpr	%wstate, %g2
-		wrpr	%g0, 0, %canrestore
+661:		wrpr	%g0, 0, %canrestore
+		.section .fast_win_ctrl_1insn_patch, "ax"
+		.word	661b
+		nop
+		.previous
 		sll	%g2, 3, %g2
 
 		/* Set TI_SYS_FPDEPTH to 1 and clear TI_SYS_NOERROR.  */
 		mov	1, %l5
 		sth	%l5, [%l6 + TI_SYS_NOERROR]
 
-		wrpr	%g3, 0, %otherwin
+661:		wrpr	%g3, 0, %otherwin
+		.section .fast_win_ctrl_1insn_patch, "ax"
+		.word	661b
+		.word	0x87880000	! otherw
+		.previous
+
 		wrpr	%g2, 0, %wstate
 		sethi	%hi(sparc64_kern_pri_context), %g2
 		ldx	[%g2 + %lo(sparc64_kern_pri_context)], %g3
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 78e0211753d2..4de9fbd1a177 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -603,10 +603,10 @@ niagara_tlb_fixup:
 	be,pt	%xcc, niagara4_patch
 	 nop
 	cmp	%g1, SUN4V_CHIP_SPARC_M7
-	be,pt	%xcc, niagara4_patch
+	be,pt	%xcc, sparc_m7_patch
 	 nop
 	cmp	%g1, SUN4V_CHIP_SPARC_M8
-	be,pt	%xcc, niagara4_patch
+	be,pt	%xcc, sparc_m7_patch
 	 nop
 	cmp	%g1, SUN4V_CHIP_SPARC_SN
 	be,pt	%xcc, niagara4_patch
@@ -621,6 +621,18 @@ niagara_tlb_fixup:
 
 	ba,a,pt	%xcc, 80f
 	 nop
+
+sparc_m7_patch:
+	call	m7_patch_copyops
+	 nop
+	call	m7_patch_bzero
+	 nop
+	call	m7_patch_pageops
+	 nop
+
+	ba,a,pt	%xcc, 80f
+	 nop
+
 niagara4_patch:
 	call	niagara4_patch_copyops
 	 nop
@@ -881,7 +893,6 @@ sparc64_boot_end:
 #include "misctrap.S"
 #include "syscalls.S"
 #include "helpers.S"
-#include "hvcalls.S"
 #include "sun4v_tlb_miss.S"
 #include "sun4v_ivec.S"
 #include "ktlb.S"
@@ -926,6 +937,7 @@ swapper_4m_tsb:
 
 ! 0x0000000000428000
 
+#include "hvcalls.S"
 #include "systbls_64.S"
 
 	.data
diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c
index 267731234ce8..d41ce33d87d6 100644
--- a/arch/sparc/kernel/hvapi.c
+++ b/arch/sparc/kernel/hvapi.c
@@ -189,7 +189,7 @@ void __init sun4v_hvapi_init(void)
 
 	group = HV_GRP_CORE;
 	major = 1;
-	minor = 1;
+	minor = 6;
 	if (sun4v_hvapi_register(group, major, &minor))
 		goto bad;
 
diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S
index 4116ee5c7791..e57007ff7f8f 100644
--- a/arch/sparc/kernel/hvcalls.S
+++ b/arch/sparc/kernel/hvcalls.S
@@ -106,6 +106,17 @@ ENTRY(sun4v_cpu_yield)
 	 nop
 ENDPROC(sun4v_cpu_yield)
 
+	/* %o0: cpuid
+	 *
+	 * returns %o0:	status
+	 */
+ENTRY(sun4v_cpu_poke)
+	mov     HV_FAST_CPU_POKE, %o5
+	ta      HV_FAST_TRAP
+	retl
+	 nop
+ENDPROC(sun4v_cpu_poke)
+
 	/* %o0:	type
 	 * %o1:	queue paddr
 	 * %o2:	num queue entries
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 840e0b21bfe3..acffbc894ab0 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -1480,6 +1480,7 @@ int ldc_rx_reset(struct ldc_channel *lp)
 {
 	return __set_rx_head(lp, lp->rx_tail);
 }
+EXPORT_SYMBOL(ldc_rx_reset);
 
 void __ldc_print(struct ldc_channel *lp, const char *caller)
 {
@@ -1493,6 +1494,7 @@ void __ldc_print(struct ldc_channel *lp, const char *caller)
 		lp->tx_head, lp->tx_tail, lp->tx_num_entries,
 		lp->rcv_nxt, lp->snd_nxt);
 }
+EXPORT_SYMBOL(__ldc_print);
 
 static int write_raw(struct ldc_channel *lp, const void *buf, unsigned int size)
 {
diff --git a/arch/sparc/kernel/leon_pci_grpci1.c b/arch/sparc/kernel/leon_pci_grpci1.c
index 1e77128a8f88..83ba5005d44c 100644
--- a/arch/sparc/kernel/leon_pci_grpci1.c
+++ b/arch/sparc/kernel/leon_pci_grpci1.c
@@ -695,7 +695,7 @@ err1:
 	return err;
 }
 
-static struct of_device_id grpci1_of_match[] = {
+static const struct of_device_id grpci1_of_match[] __initconst = {
 	{
 	 .name = "GAISLER_PCIFBRG",
 	 },
diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c
index f727c4de1316..ff0e5c90310f 100644
--- a/arch/sparc/kernel/leon_pci_grpci2.c
+++ b/arch/sparc/kernel/leon_pci_grpci2.c
@@ -886,7 +886,7 @@ err1:
 	return err;
 }
 
-static struct of_device_id grpci2_of_match[] = {
+static const struct of_device_id grpci2_of_match[] __initconst = {
 	{
 	 .name = "GAISLER_GRPCI2",
 	 },
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index b96104da5bd6..44e5da405f96 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -77,8 +77,13 @@ void arch_cpu_idle(void)
 			: "=&r" (pstate)
 			: "i" (PSTATE_IE));
 
-		if (!need_resched() && !cpu_is_offline(smp_processor_id()))
+		if (!need_resched() && !cpu_is_offline(smp_processor_id())) {
 			sun4v_cpu_yield();
+			/* If resumed by cpu_poke then we need to explicitly
+			 * call scheduler_ipi().
+			 */
+			scheduler_poke();
+		}
 
 		/* Re-enable interrupts. */
 		__asm__ __volatile__(
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index 709a82ebd294..dff86fad0a1f 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -224,10 +224,19 @@ rt_continue:	ldx			[%sp + PTREGS_OFF + PT_V9_G1], %g1
 		rdpr			%otherwin, %l2
 		srl			%l1, 3, %l1
 
-		wrpr			%l2, %g0, %canrestore
+661:		wrpr			%l2, %g0, %canrestore
+		.section		.fast_win_ctrl_1insn_patch, "ax"
+		.word			661b
+		.word			0x89880000	! normalw
+		.previous
+
 		wrpr			%l1, %g0, %wstate
 		brnz,pt			%l2, user_rtt_restore
-		 wrpr			%g0, %g0, %otherwin
+661:		 wrpr			%g0, %g0, %otherwin
+		.section		.fast_win_ctrl_1insn_patch, "ax"
+		.word			661b
+		 nop
+		.previous
 
 		ldx			[%g6 + TI_FLAGS], %g3
 		wr			%g0, ASI_AIUP, %asi
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 150ee7d4b059..db4c4d7e28a0 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -300,6 +300,11 @@ static void __init sun4v_patch(void)
 		break;
 	}
 
+	if (sun4v_chip_type != SUN4V_CHIP_NIAGARA1) {
+		sun4v_patch_1insn_range(&__fast_win_ctrl_1insn_patch,
+					&__fast_win_ctrl_1insn_patch_end);
+	}
+
 	sun4v_hvapi_init();
 }
 
@@ -363,6 +368,7 @@ void __init start_early_boot(void)
 	check_if_starfire();
 	per_cpu_patch();
 	sun4v_patch();
+	smp_init_cpu_poke();
 
 	cpu = hard_smp_processor_id();
 	if (cpu >= NR_CPUS) {
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 3218bc43302e..4898329970c5 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -74,6 +74,9 @@ EXPORT_SYMBOL(cpu_core_sib_cache_map);
 
 static cpumask_t smp_commenced_mask;
 
+static DEFINE_PER_CPU(bool, poke);
+static bool cpu_poke;
+
 void smp_info(struct seq_file *m)
 {
 	int i;
@@ -1439,15 +1442,86 @@ void __init smp_cpus_done(unsigned int max_cpus)
 {
 }
 
+static void send_cpu_ipi(int cpu)
+{
+	xcall_deliver((u64) &xcall_receive_signal,
+			0, 0, cpumask_of(cpu));
+}
+
+void scheduler_poke(void)
+{
+	if (!cpu_poke)
+		return;
+
+	if (!__this_cpu_read(poke))
+		return;
+
+	__this_cpu_write(poke, false);
+	set_softint(1 << PIL_SMP_RECEIVE_SIGNAL);
+}
+
+static unsigned long send_cpu_poke(int cpu)
+{
+	unsigned long hv_err;
+
+	per_cpu(poke, cpu) = true;
+	hv_err = sun4v_cpu_poke(cpu);
+	if (hv_err != HV_EOK) {
+		per_cpu(poke, cpu) = false;
+		pr_err_ratelimited("%s: sun4v_cpu_poke() fails err=%lu\n",
+				    __func__, hv_err);
+	}
+
+	return hv_err;
+}
+
 void smp_send_reschedule(int cpu)
 {
 	if (cpu == smp_processor_id()) {
 		WARN_ON_ONCE(preemptible());
 		set_softint(1 << PIL_SMP_RECEIVE_SIGNAL);
-	} else {
-		xcall_deliver((u64) &xcall_receive_signal,
-			      0, 0, cpumask_of(cpu));
+		return;
+	}
+
+	/* Use cpu poke to resume idle cpu if supported. */
+	if (cpu_poke && idle_cpu(cpu)) {
+		unsigned long ret;
+
+		ret = send_cpu_poke(cpu);
+		if (ret == HV_EOK)
+			return;
 	}
+
+	/* Use IPI in following cases:
+	 * - cpu poke not supported
+	 * - cpu not idle
+	 * - send_cpu_poke() returns with error
+	 */
+	send_cpu_ipi(cpu);
+}
+
+void smp_init_cpu_poke(void)
+{
+	unsigned long major;
+	unsigned long minor;
+	int ret;
+
+	if (tlb_type != hypervisor)
+		return;
+
+	ret = sun4v_hvapi_get(HV_GRP_CORE, &major, &minor);
+	if (ret) {
+		pr_debug("HV_GRP_CORE is not registered\n");
+		return;
+	}
+
+	if (major == 1 && minor >= 6) {
+		/* CPU POKE is registered. */
+		cpu_poke = true;
+		return;
+	}
+
+	pr_debug("CPU_POKE not supported\n");
 }
 
 void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs)
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index ad31af1dd726..c74f2dffcc13 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -265,6 +265,45 @@ void sun4v_insn_access_exception_tl1(struct pt_regs *regs, unsigned long addr, u
 	sun4v_insn_access_exception(regs, addr, type_ctx);
 }
 
+bool is_no_fault_exception(struct pt_regs *regs)
+{
+	unsigned char asi;
+	u32 insn;
+
+	if (get_user(insn, (u32 __user *)regs->tpc) == -EFAULT)
+		return false;
+
+	/*
+	 * Must do a little instruction decoding here in order to
+	 * decide on a course of action. The bits of interest are:
+	 *  insn[31:30] = op, where 3 indicates the load/store group
+	 *  insn[24:19] = op3, which identifies individual opcodes
+	 *  insn[13] indicates an immediate offset
+	 *  op3[4]=1 identifies alternate space instructions
+	 *  op3[5:4]=3 identifies floating point instructions
+	 *  op3[2]=1 identifies stores
+	 * See "Opcode Maps" in the appendix of any Sparc V9
+	 * architecture spec for full details.
+	 */
+	if ((insn & 0xc0800000) == 0xc0800000) {    /* op=3, op3[4]=1   */
+		if (insn & 0x2000)		    /* immediate offset */
+			asi = (regs->tstate >> 24); /* saved %asi       */
+		else
+			asi = (insn >> 5);	    /* immediate asi    */
+		if ((asi & 0xf2) == ASI_PNF) {
+			if (insn & 0x1000000) {     /* op3[5:4]=3       */
+				handle_ldf_stq(insn, regs);
+				return true;
+			} else if (insn & 0x200000) { /* op3[2], stores */
+				return false;
+			}
+			handle_ld_nf(insn, regs);
+			return true;
+		}
+	}
+	return false;
+}
+
 void spitfire_data_access_exception(struct pt_regs *regs, unsigned long sfsr, unsigned long sfar)
 {
 	enum ctx_state prev_state = exception_enter();
@@ -296,6 +335,9 @@ void spitfire_data_access_exception(struct pt_regs *regs, unsigned long sfsr, un
 		die_if_kernel("Dax", regs);
 	}
 
+	if (is_no_fault_exception(regs))
+		return;
+
 	info.si_signo = SIGSEGV;
 	info.si_errno = 0;
 	info.si_code = SEGV_MAPERR;
@@ -352,6 +394,9 @@ void sun4v_data_access_exception(struct pt_regs *regs, unsigned long addr, unsig
 		regs->tpc &= 0xffffffff;
 		regs->tnpc &= 0xffffffff;
 	}
+	if (is_no_fault_exception(regs))
+		return;
+
 	info.si_signo = SIGSEGV;
 	info.si_errno = 0;
 	info.si_code = SEGV_MAPERR;
@@ -2575,6 +2620,9 @@ void mem_address_unaligned(struct pt_regs *regs, unsigned long sfar, unsigned lo
 		kernel_unaligned_trap(regs, *((unsigned int *)regs->tpc));
 		goto out;
 	}
+	if (is_no_fault_exception(regs))
+		return;
+
 	info.si_signo = SIGBUS;
 	info.si_errno = 0;
 	info.si_code = BUS_ADRALN;
@@ -2597,6 +2645,9 @@ void sun4v_do_mna(struct pt_regs *regs, unsigned long addr, unsigned long type_c
 		kernel_unaligned_trap(regs, *((unsigned int *)regs->tpc));
 		return;
 	}
+	if (is_no_fault_exception(regs))
+		return;
+
 	info.si_signo = SIGBUS;
 	info.si_errno = 0;
 	info.si_code = BUS_ADRALN;
diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S
index db872dbfafe9..f74115364b1e 100644
--- a/arch/sparc/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -117,7 +117,7 @@ tsb_miss_page_table_walk_sun4v_fastpath:
 	/* Valid PTE is now in %g5.  */
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	sethi		%uhi(_PAGE_PMD_HUGE), %g7
+	sethi		%uhi(_PAGE_PMD_HUGE | _PAGE_PUD_HUGE), %g7
 	sllx		%g7, 32, %g7
 
 	andcc		%g5, %g7, %g0
diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c
index 1c8763c9c52b..da1ac3f22b24 100644
--- a/arch/sparc/kernel/vio.c
+++ b/arch/sparc/kernel/vio.c
@@ -246,6 +246,7 @@ u64 vio_vdev_node(struct mdesc_handle *hp, struct vio_dev *vdev)
 
 	return node;
 }
+EXPORT_SYMBOL(vio_vdev_node);
 
 static void vio_fill_channel_info(struct mdesc_handle *hp, u64 mp,
 				  struct vio_dev *vdev)
diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c
index d4f13c037a40..dcd278f29573 100644
--- a/arch/sparc/kernel/viohs.c
+++ b/arch/sparc/kernel/viohs.c
@@ -814,15 +814,21 @@ int vio_driver_init(struct vio_driver_state *vio, struct vio_dev *vdev,
 	case VDEV_NETWORK_SWITCH:
 	case VDEV_DISK:
 	case VDEV_DISK_SERVER:
+	case VDEV_CONSOLE_CON:
 		break;
 
 	default:
 		return -EINVAL;
 	}
 
-	if (!ops || !ops->send_attr || !ops->handle_attr ||
-	    !ops->handshake_complete)
-		return -EINVAL;
+	if (dev_class == VDEV_NETWORK ||
+	    dev_class == VDEV_NETWORK_SWITCH ||
+	    dev_class == VDEV_DISK ||
+	    dev_class == VDEV_DISK_SERVER) {
+		if (!ops || !ops->send_attr || !ops->handle_attr ||
+		    !ops->handshake_complete)
+			return -EINVAL;
+	}
 
 	if (!ver_table || ver_table_size < 0)
 		return -EINVAL;
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 03b3d65d1266..d78847d56a4b 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -154,6 +154,16 @@ SECTIONS
 		*(.get_tick_patch)
 		__get_tick_patch_end = .;
 	}
+	.pud_huge_patch : {
+		__pud_huge_patch = .;
+		*(.pud_huge_patch)
+		__pud_huge_patch_end = .;
+	}
+	.fast_win_ctrl_1insn_patch : {
+		__fast_win_ctrl_1insn_patch = .;
+		*(.f