20 files changed, 217 insertions, 117 deletions

diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index e9e837bc3158..80ddc01f57ac 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -18,5 +18,4 @@ generic-y += preempt.h
 generic-y += rwsem.h
 generic-y += serial.h
 generic-y += trace_clock.h
-generic-y += types.h
 generic-y += word-at-a-time.h
diff --git a/arch/sparc/include/asm/asm-prototypes.h b/arch/sparc/include/asm/asm-prototypes.h
new file mode 100644
index 000000000000..d381e11c5dbb
--- /dev/null
+++ b/arch/sparc/include/asm/asm-prototypes.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (c) 2017 Oracle and/or its affiliates. All rights reserved.
+ */
+
+#include <asm/xor.h>
+#include <asm/checksum.h>
+#include <asm/trap_block.h>
+#include <asm/uaccess.h>
+#include <asm/atomic.h>
+#include <asm/ftrace.h>
+#include <asm/cacheflush.h>
+#include <asm/oplib.h>
+#include <linux/atomic.h>
+
+void *__memscan_zero(void *, size_t);
+void *__memscan_generic(void *, int, size_t);
+void *__bzero(void *, size_t);
+void VISenter(void); /* Dummy prototype to supress warning */
+#undef memcpy
+#undef memset
+void *memcpy(void *dest, const void *src, size_t n);
+void *memset(void *s, int c, size_t n);
+typedef int TItype __attribute__((mode(TI)));
+TItype __multi3(TItype a, TItype b);
diff --git a/arch/sparc/include/asm/nmi.h b/arch/sparc/include/asm/nmi.h
index 26ad2b2607c6..284eac3ffaf2 100644
--- a/arch/sparc/include/asm/nmi.h
+++ b/arch/sparc/include/asm/nmi.h
@@ -7,6 +7,7 @@ void nmi_adjust_hz(unsigned int new_hz);
 
 extern atomic_t nmi_active;
 
+void arch_touch_nmi_watchdog(void);
 void start_nmi_watchdog(void *unused);
 void stop_nmi_watchdog(void *unused);
 
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index ec9c04de3664..ff05992dae7a 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -54,6 +54,7 @@ extern struct trap_per_cpu trap_block[NR_CPUS];
 void init_cur_cpu_trap(struct thread_info *);
 void setup_tba(void);
 extern int ncpus_probed;
+extern u64 cpu_mondo_counter[NR_CPUS];
 
 unsigned long real_hard_smp_processor_id(void);
 
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index 113d84eaa15e..6d4c997d1a9e 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -9,7 +9,6 @@
 #include <linux/string.h>
 #include <asm/asi.h>
 #include <asm/spitfire.h>
-#include <asm-generic/uaccess-unaligned.h>
 #include <asm/extable_64.h>
 
 #include <asm/processor.h>
diff --git a/arch/sparc/include/uapi/asm/Kbuild b/arch/sparc/include/uapi/asm/Kbuild
index b15bf6bc0e94..2178c78c7c1a 100644
--- a/arch/sparc/include/uapi/asm/Kbuild
+++ b/arch/sparc/include/uapi/asm/Kbuild
@@ -1,2 +1,4 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
+
+generic-y += types.h
diff --git a/arch/sparc/include/uapi/asm/ioctls.h b/arch/sparc/include/uapi/asm/ioctls.h
index 6d27398632ea..f5df72b93bb2 100644
--- a/arch/sparc/include/uapi/asm/ioctls.h
+++ b/arch/sparc/include/uapi/asm/ioctls.h
@@ -88,7 +88,7 @@
 #define TIOCGPTN	_IOR('t', 134, unsigned int) /* Get Pty Number */
 #define TIOCSPTLCK	_IOW('t', 135, int) /* Lock/unlock PTY */
 #define TIOCSIG		_IOW('t', 136, int) /* Generate signal on Pty slave */
-#define TIOCGPTPEER	_IOR('t', 137, int) /* Safely open the slave */
+#define TIOCGPTPEER	_IO('t', 137) /* Safely open the slave */
 
 /* Little f */
 #define FIOCLEX		_IO('f', 1)
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index e4b4e790bf89..fa466ce45bc9 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -205,7 +205,7 @@ static struct mdesc_handle *mdesc_kmalloc(unsigned int mdesc_size)
 	handle_size = (sizeof(struct mdesc_handle) -
 		       sizeof(struct mdesc_hdr) +
 		       mdesc_size);
-	base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_REPEAT);
+	base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!base)
 		return NULL;
 
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
index 95e73c63c99d..048ad783ea3f 100644
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@@ -51,7 +51,7 @@ static DEFINE_PER_CPU(unsigned int, last_irq_sum);
 static DEFINE_PER_CPU(long, alert_counter);
 static DEFINE_PER_CPU(int, nmi_touch);
 
-void touch_nmi_watchdog(void)
+void arch_touch_nmi_watchdog(void)
 {
 	if (atomic_read(&nmi_active)) {
 		int cpu;
@@ -61,10 +61,8 @@ void touch_nmi_watchdog(void)
 				per_cpu(nmi_touch, cpu) = 1;
 		}
 	}
-
-	touch_softlockup_watchdog();
 }
-EXPORT_SYMBOL(touch_nmi_watchdog);
+EXPORT_SYMBOL(arch_touch_nmi_watchdog);
 
 static void die_nmi(const char *str, struct pt_regs *regs, int do_panic)
 {
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 24f21c726dfa..f10e2f712394 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -673,12 +673,14 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
 static int dma_4v_supported(struct device *dev, u64 device_mask)
 {
 	struct iommu *iommu = dev->archdata.iommu;
-	u64 dma_addr_mask;
+	u64 dma_addr_mask = iommu->dma_addr_mask;
 
-	if (device_mask > DMA_BIT_MASK(32) && iommu->atu)
-		dma_addr_mask = iommu->atu->dma_addr_mask;
-	else
-		dma_addr_mask = iommu->dma_addr_mask;
+	if (device_mask > DMA_BIT_MASK(32)) {
+		if (iommu->atu)
+			dma_addr_mask = iommu->atu->dma_addr_mask;
+		else
+			return 0;
+	}
 
 	if ((device_mask & dma_addr_mask) == dma_addr_mask)
 		return 1;
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index fdf31040a7dc..3218bc43302e 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -622,22 +622,48 @@ retry:
 	}
 }
 
-/* Multi-cpu list version.  */
+#define	CPU_MONDO_COUNTER(cpuid)	(cpu_mondo_counter[cpuid])
+#define	MONDO_USEC_WAIT_MIN		2
+#define	MONDO_USEC_WAIT_MAX		100
+#define	MONDO_RETRY_LIMIT		500000
+
+/* Multi-cpu list version.
+ *
+ * Deliver xcalls to 'cnt' number of cpus in 'cpu_list'.
+ * Sometimes not all cpus receive the mondo, requiring us to re-send
+ * the mondo until all cpus have received, or cpus are truly stuck
+ * unable to receive mondo, and we timeout.
+ * Occasionally a target cpu strand is borrowed briefly by hypervisor to
+ * perform guest service, such as PCIe error handling. Consider the
+ * service time, 1 second overall wait is reasonable for 1 cpu.
+ * Here two in-between mondo check wait time are defined: 2 usec for
+ * single cpu quick turn around and up to 100usec for large cpu count.
+ * Deliver mondo to large number of cpus could take longer, we adjusts
+ * the retry count as long as target cpus are making forward progress.
+ */
 static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt)
 {
-	int retries, this_cpu, prev_sent, i, saw_cpu_error;
+	int this_cpu, tot_cpus, prev_sent, i, rem;
+	int usec_wait, retries, tot_retries;
+	u16 first_cpu = 0xffff;
+	unsigned long xc_rcvd = 0;
 	unsigned long status;
+	int ecpuerror_id = 0;
+	int enocpu_id = 0;
 	u16 *cpu_list;
+	u16 cpu;
 
 	this_cpu = smp_processor_id();
-
 	cpu_list = __va(tb->cpu_list_pa);
-
-	saw_cpu_error = 0;
-	retries = 0;
+	usec_wait = cnt * MONDO_USEC_WAIT_MIN;
+	if (usec_wait > MONDO_USEC_WAIT_MAX)
+		usec_wait = MONDO_USEC_WAIT_MAX;
+	retries = tot_retries = 0;
+	tot_cpus = cnt;
 	prev_sent = 0;
+
 	do {
-		int forward_progress, n_sent;
+		int n_sent, mondo_delivered, target_cpu_busy;
 
 		status = sun4v_cpu_mondo_send(cnt,
 					      tb->cpu_list_pa,
@@ -645,94 +671,113 @@ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt)
 
 		/* HV_EOK means all cpus received the xcall, we're done.  */
 		if (likely(status == HV_EOK))
-			break;
+			goto xcall_done;
+
+		/* If not these non-fatal errors, panic */
+		if (unlikely((status != HV_EWOULDBLOCK) &&
+			(status != HV_ECPUERROR) &&
+			(status != HV_ENOCPU)))
+			goto fatal_errors;
 
 		/* First, see if we made any forward progress.
 		 *
+		 * Go through the cpu_list, count the target cpus that have
+		 * received our mondo (n_sent), and those that did not (rem).
+		 * Re-pack cpu_list with the cpus remain to be retried in the
+		 * front - this simplifies tracking the truly stalled cpus.
+		 *
 		 * The hypervisor indicates successful sends by setting
 		 * cpu list entries to the value 0xffff.
+		 *
+		 * EWOULDBLOCK means some target cpus did not receive the
+		 * mondo and retry usually helps.
+		 *
+		 * ECPUERROR means at least one target cpu is in error state,
+		 * it's usually safe to skip the faulty cpu and retry.
+		 *
+		 * ENOCPU means one of the target cpu doesn't belong to the
+		 * domain, perhaps offlined which is unexpected, but not
+		 * fatal and it's okay to skip the offlined cpu.
 		 */
+		rem = 0;
 		n_sent = 0;
 		for (i = 0; i < cnt; i++) {
-			if (likely(cpu_list[i] == 0xffff))
+			cpu = cpu_list[i];
+			if (likely(cpu == 0xffff)) {
 				n_sent++;
+			} else if ((status == HV_ECPUERROR) &&
+				(sun4v_cpu_state(cpu) == HV_CPU_STATE_ERROR)) {
+				ecpuerror_id = cpu + 1;
+			} else if (status == HV_ENOCPU && !cpu_online(cpu)) {
+				enocpu_id = cpu + 1;
+			} else {
+				cpu_list[rem++] = cpu;
+			}
 		}
 
-		forward_progress = 0;
-		if (n_sent > prev_sent)
-			forward_progress = 1;
+		/* No cpu remained, we're done. */
+		if (rem == 0)
+			break;
 
-		prev_sent = n_sent;
+		/* Otherwise, update the cpu count for retry. */
+		cnt = rem;
 
-		/* If we get a HV_ECPUERROR, then one or more of the cpus
-		 * in the list are in error state.  Use the cpu_state()
-		 * hypervisor call to find out which cpus are in error state.
+		/* Record the overall number of mondos received by the
+		 * first of the remaining cpus.
 		 */
-		if (unlikely(status == HV_ECPUERROR)) {
-			for (i = 0; i < cnt; i++) {
-				long err;
-				u16 cpu;
+		if (first_cpu != cpu_list[0]) {
+			first_cpu = cpu_list[0];
+			xc_rcvd = CPU_MONDO_COUNTER(first_cpu);
+		}
 
-				cpu = cpu_list[i];
-				if (cpu == 0xffff)
-					continue;
+		/* Was any mondo delivered successfully? */
+		mondo_delivered = (n_sent > prev_sent);
+		prev_sent = n_sent;
 
-				err = sun4v_cpu_state(cpu);
-				if (err == HV_CPU_STATE_ERROR) {
-					saw_cpu_error = (cpu + 1);
-					cpu_list[i] = 0xffff;
-				}
-			}
-		} else if (unlikely(status != HV_EWOULDBLOCK))
-			goto fatal_mondo_error;
+		/* or, was any target cpu busy processing other mondos? */
+		target_cpu_busy = (xc_rcvd < CPU_MONDO_COUNTER(first_cpu));
+		xc_rcvd = CPU_MONDO_COUNTER(first_cpu);
 
-		/* Don't bother rewriting the CPU list, just leave the
-		 * 0xffff and non-0xffff entries in there and the
-		 * hypervisor will do the right thing.
-		 *
-		 * Only advance timeout state if we didn't make any
-		 * forward progress.
+		/* Retry count is for no progress. If we're making progress,
+		 * reset the retry count.
 		 */
-		if (unlikely(!forward_progress)) {
-			if (unlikely(++retries > 10000))
-				goto fatal_mondo_timeout;
-
-			/* Delay a little bit to let other cpus catch up
-			 * on their cpu mondo queue work.
-			 */
-			udelay(2 * cnt);
+		if (likely(mondo_delivered || target_cpu_busy)) {
+			tot_retries += retries;
+			retries = 0;
+		} else if (unlikely(retries > MONDO_RETRY_LIMIT)) {
+			goto fatal_mondo_timeout;
 		}
-	} while (1);
 
-	if (unlikely(saw_cpu_error))
-		goto fatal_mondo_cpu_error;
+		/* Delay a little bit to let other cpus catch up on
+		 * their cpu mondo queue work.
+		 */
+		if (!mondo_delivered)
+			udelay(usec_wait);
 
-	return;
+		retries++;
+	} while (1);
 
-fatal_mondo_cpu_error:
-	printk(KERN_CRIT "CPU[%d]: SUN4V mondo cpu error, some target cpus "
-	       "(including %d) were in error state\n",
-	       this_cpu, saw_cpu_error - 1);
+xcall_done:
+	if (unlikely(ecpuerror_id > 0)) {
+		pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) was in error state\n",
+		       this_cpu, ecpuerror_id - 1);
+	} else if (unlikely(enocpu_id > 0)) {
+		pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) does not belong to the domain\n",
+		       this_cpu, enocpu_id - 1);
+	}
 	return;
 
+fatal_errors:
+	/* fatal errors include bad alignment, etc */
+	pr_crit("CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) mondo_block_pa(%lx)\n",
+	       this_cpu, tot_cpus, tb->cpu_list_pa, tb->cpu_mondo_block_pa);
+	panic("Unexpected SUN4V mondo error %lu\n", status);
+
 fatal_mondo_timeout:
-	printk(KERN_CRIT "CPU[%d]: SUN4V mondo timeout, no forward "
-	       " progress after %d retries.\n",
-	       this_cpu, retries);
-	goto dump_cpu_list_and_out;
-
-fatal_mondo_error:
-	printk(KERN_CRIT "CPU[%d]: Unexpected SUN4V mondo error %lu\n",
-	       this_cpu, status);
-	printk(KERN_CRIT "CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) "
-	       "mondo_block_pa(%lx)\n",
-	       this_cpu, cnt, tb->cpu_list_pa, tb->cpu_mondo_block_pa);
-
-dump_cpu_list_and_out:
-	printk(KERN_CRIT "CPU[%d]: CPU list [ ", this_cpu);
-	for (i = 0; i < cnt; i++)
-		printk("%u ", cpu_list[i]);
-	printk("]\n");
+	/* some cpus being non-responsive to the cpu mondo */
+	pr_crit("CPU[%d]: SUN4V mondo timeout, cpu(%d) made no forward progress after %d retries. Total target cpus(%d).\n",
+	       this_cpu, first_cpu, (tot_retries + retries), tot_cpus);
+	panic("SUN4V mondo timeout panic\n");
 }
 
 static void (*xcall_deliver_impl)(struct trap_per_cpu *, int);
diff --git a/arch/sparc/kernel/sun4v_ivec.S b/arch/sparc/kernel/sun4v_ivec.S
index 559bc5e9c199..34631995859a 100644
--- a/arch/sparc/kernel/sun4v_ivec.S
+++ b/arch/sparc/kernel/sun4v_ivec.S
@@ -26,6 +26,21 @@ sun4v_cpu_mondo:
 	ldxa	[%g0] ASI_SCRATCHPAD, %g4
 	sub	%g4, TRAP_PER_CPU_FAULT_INFO, %g4
 
+	/* Get smp_processor_id() into %g3 */
+	sethi	%hi(trap_block), %g5
+	or	%g5, %lo(trap_block), %g5
+	sub	%g4, %g5, %g3
+	srlx	%g3, TRAP_BLOCK_SZ_SHIFT, %g3
+
+	/* Increment cpu_mondo_counter[smp_processor_id()] */
+	sethi	%hi(cpu_mondo_counter), %g5
+	or	%g5, %lo(cpu_mondo_counter), %g5
+	sllx	%g3, 3, %g3
+	add	%g5, %g3, %g5
+	ldx	[%g5], %g3
+	add	%g3, 1, %g3
+	stx	%g3, [%g5]
+
 	/* Get CPU mondo queue base phys address into %g7.  */
 	ldx	[%g4 + TRAP_PER_CPU_CPU_MONDO_PA], %g7
 
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 196ee5eb4d48..ad31af1dd726 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2733,6 +2733,7 @@ void do_getpsr(struct pt_regs *regs)
 	}
 }
 
+u64 cpu_mondo_counter[NR_CPUS] = {0};
 struct trap_per_cpu trap_block[NR_CPUS];
 EXPORT_SYMBOL(trap_block);
 
diff --git a/arch/sparc/lib/atomic_64.S b/arch/sparc/lib/atomic_64.S
index 1c6a1bde5138..ce17c3094ba6 100644
--- a/arch/sparc/lib/atomic_64.S
+++ b/arch/sparc/lib/atomic_64.S
@@ -62,19 +62,23 @@ ENTRY(atomic_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */	\
 ENDPROC(atomic_fetch_##op);						\
 EXPORT_SYMBOL(atomic_fetch_##op);
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
+ATOMIC_OP(add)
+ATOMIC_OP_RETURN(add)
+ATOMIC_FETCH_OP(add)
 
-ATOMIC_OPS(add)
-ATOMIC_OPS(sub)
+ATOMIC_OP(sub)
+ATOMIC_OP_RETURN(sub)
+ATOMIC_FETCH_OP(sub)
 
-#undef ATOMIC_OPS
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+ATOMIC_OP(and)
+ATOMIC_FETCH_OP(and)
 
-ATOMIC_OPS(and)
-ATOMIC_OPS(or)
-ATOMIC_OPS(xor)
+ATOMIC_OP(or)
+ATOMIC_FETCH_OP(or)
+
+ATOMIC_OP(xor)
+ATOMIC_FETCH_OP(xor)
 
-#undef ATOMIC_OPS
 #undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -124,19 +128,23 @@ ENTRY(atomic64_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */	\
 ENDPROC(atomic64_fetch_##op);						\
 EXPORT_SYMBOL(atomic64_fetch_##op);
 
-#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) ATOMIC64_FETCH_OP(op)
+ATOMIC64_OP(add)
+ATOMIC64_OP_RETURN(add)
+ATOMIC64_FETCH_OP(add)
+
+ATOMIC64_OP(sub)
+ATOMIC64_OP_RETURN(sub)
+ATOMIC64_FETCH_OP(sub)
 
-ATOMIC64_OPS(add)
-ATOMIC64_OPS(sub)
+ATOMIC64_OP(and)
+ATOMIC64_FETCH_OP(and)
 
-#undef ATOMIC64_OPS
-#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_FETCH_OP(op)
+ATOMIC64_OP(or)
+ATOMIC64_FETCH_OP(or)
 
-ATOMIC64_OPS(and)
-ATOMIC64_OPS(or)
-ATOMIC64_OPS(xor)
+ATOMIC64_OP(xor)
+ATOMIC64_FETCH_OP(xor)
 
-#undef ATOMIC64_OPS
 #undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
diff --git a/arch/sparc/lib/checksum_64.S b/arch/sparc/lib/checksum_64.S
index f6732174fe6b..6cfa521f444d 100644
--- a/arch/sparc/lib/checksum_64.S
+++ b/arch/sparc/lib/checksum_64.S
@@ -38,6 +38,7 @@ csum_partial_fix_alignment:
 
 	.align		32
 	.globl		csum_partial
+	.type		csum_partial,#function
 	EXPORT_SYMBOL(csum_partial)
 csum_partial:		/* %o0=buff, %o1=len, %o2=sum */
 	prefetch	[%o0 + 0x000], #n_reads
diff --git a/arch/sparc/lib/csum_copy.S b/arch/sparc/lib/csum_copy.S
index 0ecbafc30fd0..b1051e77c49a 100644
--- a/arch/sparc/lib/csum_copy.S
+++ b/arch/sparc/lib/csum_copy.S
@@ -65,6 +65,7 @@
 	 add		%o5, %o4, %o4
 
 	.globl		FUNC_NAME
+	.type		FUNC_NAME,#function
 	EXPORT_SYMBOL(FUNC_NAME)
 FUNC_NAME:		/* %o0=src, %o1=dst, %o2=len, %o3=sum */
 	LOAD(prefetch, %o0 + 0x000, #n_reads)
diff --git a/arch/sparc/lib/memscan_64.S b/arch/sparc/lib/memscan_64.S
index daa96f4b03e6..5efee1f4be36 100644
--- a/arch/sparc/lib/memscan_64.S
+++ b/arch/sparc/lib/memscan_64.S
@@ -14,6 +14,8 @@
 	.text
 	.align	32
 	.globl		__memscan_zero, __memscan_generic
+	.type		__memscan_zero,#function
+	.type		__memscan_generic,#function
 	.globl		memscan
 	EXPORT_SYMBOL(__memscan_zero)
 	EXPORT_SYMBOL(__memscan_generic)
diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S
index bb539b42b088..e23338dbfc43 100644
--- a/arch/sparc/lib/memset.S
+++ b/arch/sparc/lib/memset.S
@@ -63,6 +63,7 @@
 __bzero_begin:
 
 	.globl	__bzero
+	.type	__bzero,#function
 	.globl	memset
 	EXPORT_SYMBOL(__bzero)
 	EXPORT_SYMBOL(memset)
diff --git a/arch/sparc/mm/extable.c b/arch/sparc/mm/extable.c
index db214e9931d9..2422511dc8c5 100644
--- a/arch/sparc/mm/extable.c
+++ b/arch/sparc/mm/extable.c
@@ -13,11 +13,11 @@ void sort_extable(struct exception_table_entry *start,
 
 /* Caller knows they are in a range if ret->fixup == 0 */
 const struct exception_table_entry *
-search_extable(const struct exception_table_entry *start,
-	       const struct exception_table_entry *last,
+search_extable(const struct exception_table_entry *base,
+	       const size_t num,
 	       unsigned long value)
 {
-	const struct exception_table_entry *walk;
+	int i;
 
 	/* Single insn entries are encoded as:
 	 *	word 1:	insn address
@@ -37,30 +37,30 @@ search_extable(const struct exception_table_entry *start,
 	 */
 
 	/* 1. Try to find an exact match. */
-	for (walk = start; walk <= last; walk++) {
-		if (walk->fixup == 0) {
+	for (i = 0; i < num; i++) {
+		if (base[i].fixup == 0) {
 			/* A range entry, skip both parts. */
-			walk++;
+			i++;
 			continue;
 		}
 
 		/* A deleted entry; see trim_init_extable */
-		if (walk->fixup == -1)
+		if (base[i].fixup == -1)
 			continue;
 
-		if (walk->insn == value)
-			return walk;
+		if (base[i].insn == value)
+			return &base[i];
 	}
 
 	/* 2. Try to find a range match. */
-	for (walk = start; walk <= (last - 1); walk++) {
-		if (walk->fixup)
+	for (i = 0; i < (num - 1); i++) {
+		if (base[i].fixup)
 			continue;
 
-		if (walk[0].insn <= value && walk[1].insn > value)
-			return walk;
+		if (base[i].insn <= value && base[i + 1].insn > value)
+			return &base[i];
 
-		walk++;
+		i++;
 	}
 
         return NULL;
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
index cd0e32bbcb1d..f80cfc64c55b 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -78,8 +78,8 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 		return 0;
 
 	refs = 0;
-	head = pmd_page(pmd);
-	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+	page = pmd_page(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+	head = compound_head(page);
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;