6 files changed, 123 insertions, 18 deletions
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index f17c3a4fb697..86f65721e629 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -3,7 +3,6 @@ config MICROBLAZE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_WANT_IPC_PARSE_VERSION
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select BUILDTIME_EXTABLE_SORT
 	select CLKSRC_OF
 	select CLONE_BACKWARDS3
@@ -16,6 +15,7 @@ config MICROBLAZE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
+	select HAVE_ARCH_HASH
 	select HAVE_ARCH_KGDB
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
diff --git a/arch/microblaze/include/asm/hash.h b/arch/microblaze/include/asm/hash.h
new file mode 100644
index 000000000000..753513ae8cb0
--- /dev/null
+++ b/arch/microblaze/include/asm/hash.h
@@ -0,0 +1,81 @@
+#ifndef _ASM_HASH_H
+#define _ASM_HASH_H
+
+/*
+ * Fortunately, most people who want to run Linux on Microblaze enable
+ * both multiplier and barrel shifter, but omitting them is technically
+ * a supported configuration.
+ *
+ * With just a barrel shifter, we can implement an efficient constant
+ * multiply using shifts and adds.  GCC can find a 9-step solution, but
+ * this 6-step solution was found by Yevgen Voronenko's implementation
+ * of the Hcub algorithm at http://spiral.ece.cmu.edu/mcm/gen.html.
+ *
+ * That software is really not designed for a single multiplier this large,
+ * but if you run it enough times with different seeds, it'll find several
+ * 6-shift, 6-add sequences for computing x * 0x61C88647.  They are all
+ *	c = (x << 19) + x;
+ *	a = (x <<  9) + c;
+ *	b = (x << 23) + a;
+ *	return (a<<11) + (b<<6) + (c<<3) - b;
+ * with variations on the order of the final add.
+ *
+ * Without even a shifter, it's hopless; any hash function will suck.
+ */
+
+#if CONFIG_XILINX_MICROBLAZE0_USE_HW_MUL == 0
+
+#define HAVE_ARCH__HASH_32 1
+
+/* Multiply by GOLDEN_RATIO_32 = 0x61C88647 */
+static inline u32 __attribute_const__ __hash_32(u32 a)
+{
+#if CONFIG_XILINX_MICROBLAZE0_USE_BARREL
+	unsigned int b, c;
+
+	/* Phase 1: Compute three intermediate values */
+	b =  a << 23;
+	c = (a << 19) + a;
+	a = (a <<  9) + c;
+	b += a;
+
+	/* Phase 2: Compute (a << 11) + (b << 6) + (c << 3) - b */
+	a <<= 5;
+	a += b;		/* (a << 5) + b */
+	a <<= 3;
+	a += c;		/* (a << 8) + (b << 3) + c */
+	a <<= 3;
+	return a - b;	/* (a << 11) + (b << 6) + (c << 3) - b */
+#else
+	/*
+	 * "This is really going to hurt."
+	 *
+	 * Without a barrel shifter, left shifts are implemented as
+	 * repeated additions, and the best we can do is an optimal
+	 * addition-subtraction chain.  This one is not known to be
+	 * optimal, but at 37 steps, it's decent for a 31-bit multiplier.
+	 *
+	 * Question: given its size (37*4 = 148 bytes per instance),
+	 * and slowness, is this worth having inline?
+	 */
+	unsigned int b, c, d;
+
+	b = a << 4;	/* 4    */
+	c = b << 1;	/* 1  5 */
+	b += a;		/* 1  6 */
+	c += b;		/* 1  7 */
+	c <<= 3;	/* 3 10 */
+	c -= a;		/* 1 11 */
+	d = c << 7;	/* 7 18 */
+	d += b;		/* 1 19 */
+	d <<= 8;	/* 8 27 */
+	d += a;		/* 1 28 */
+	d <<= 1;	/* 1 29 */
+	d += b;		/* 1 30 */
+	d <<= 6;	/* 6 36 */
+	return d + c;	/* 1 37 total instructions*/
+#endif
+}
+
+#endif /* !CONFIG_XILINX_MICROBLAZE0_USE_HW_MUL */
+#endif /* _ASM_HASH_H */
diff --git a/arch/microblaze/include/asm/pgalloc.h b/arch/microblaze/include/asm/pgalloc.h
index 61436d69775c..7c89390c0c13 100644
--- a/arch/microblaze/include/asm/pgalloc.h
+++ b/arch/microblaze/include/asm/pgalloc.h
@@ -116,9 +116,9 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 	struct page *ptepage;
 
 #ifdef CONFIG_HIGHPTE
-	int flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_REPEAT;
+	int flags = GFP_KERNEL | __GFP_HIGHMEM;
 #else
-	int flags = GFP_KERNEL | __GFP_REPEAT;
+	int flags = GFP_KERNEL;
 #endif
 
 	ptepage = alloc_pages(flags, 0);
diff --git a/arch/microblaze/kernel/timer.c b/arch/microblaze/kernel/timer.c
index 67e2ef48d2d0..5bbf38b916ef 100644
--- a/arch/microblaze/kernel/timer.c
+++ b/arch/microblaze/kernel/timer.c
@@ -170,7 +170,7 @@ static struct irqaction timer_irqaction = {
 	.dev_id = &clockevent_xilinx_timer,
 };
 
-static __init void xilinx_clockevent_init(void)
+static __init int xilinx_clockevent_init(void)
 {
 	clockevent_xilinx_timer.mult =
 		div_sc(timer_clock_freq, NSEC_PER_SEC,
@@ -181,6 +181,8 @@ static __init void xilinx_clockevent_init(void)
 		clockevent_delta2ns(1, &clockevent_xilinx_timer);
 	clockevent_xilinx_timer.cpumask = cpumask_of(0);
 	clockevents_register_device(&clockevent_xilinx_timer);
+
+	return 0;
 }
 
 static u64 xilinx_clock_read(void)
@@ -229,8 +231,14 @@ static struct clocksource clocksource_microblaze = {
 
 static int __init xilinx_clocksource_init(void)
 {
-	if (clocksource_register_hz(&clocksource_microblaze, timer_clock_freq))
-		panic("failed to register clocksource");
+	int ret;
+
+	ret = clocksource_register_hz(&clocksource_microblaze,
+				      timer_clock_freq);
+	if (ret) {
+		pr_err("failed to register clocksource");
+		return ret;
+	}
 
 	/* stop timer1 */
 	write_fn(read_fn(timer_baseaddr + TCSR1) & ~TCSR_ENT,
@@ -239,16 +247,16 @@ static int __init xilinx_clocksource_init(void)
 	write_fn(TCSR_TINT|TCSR_ENT|TCSR_ARHT, timer_baseaddr + TCSR1);
 
 	/* register timecounter - for ftrace support */
-	init_xilinx_timecounter();
-	return 0;
+	return init_xilinx_timecounter();
 }
 
-static void __init xilinx_timer_init(struct device_node *timer)
+static int __init xilinx_timer_init(struct device_node *timer)
 {
 	struct clk *clk;
 	static int initialized;
 	u32 irq;
 	u32 timer_num = 1;
+	int ret;
 
 	if (initialized)
 		return;
@@ -258,7 +266,7 @@ static void __init xilinx_timer_init(struct device_node *timer)
 	timer_baseaddr = of_iomap(timer, 0);
 	if (!timer_baseaddr) {
 		pr_err("ERROR: invalid timer base address\n");
-		BUG();
+		return -ENXIO;
 	}
 
 	write_fn = timer_write32;
@@ -271,11 +279,15 @@ static void __init xilinx_timer_init(struct device_node *timer)
 	}
 
 	irq = irq_of_parse_and_map(timer, 0);
+	if (irq <= 0) {
+		pr_err("Failed to parse and map irq");
+		return -EINVAL;
+	}
 
 	of_property_read_u32(timer, "xlnx,one-timer-only", &timer_num);
 	if (timer_num) {
-		pr_emerg("Please enable two timers in HW\n");
-		BUG();
+		pr_err("Please enable two timers in HW\n");
+		return -EINVAL;
 	}
 
 	pr_info("%s: irq=%d\n", timer->full_name, irq);
@@ -297,14 +309,27 @@ static void __init xilinx_timer_init(struct device_node *timer)
 
 	freq_div_hz = timer_clock_freq / HZ;
 
-	setup_irq(irq, &timer_irqaction);
+	ret = setup_irq(irq, &timer_irqaction);
+	if (ret) {
+		pr_err("Failed to setup IRQ");
+		return ret;
+	}
+
 #ifdef CONFIG_HEART_BEAT
 	microblaze_setup_heartbeat();
 #endif
-	xilinx_clocksource_init();
-	xilinx_clockevent_init();
+
+	ret = xilinx_clocksource_init();
+	if (ret)
+		return ret;
+
+	ret = xilinx_clockevent_init();
+	if (ret)
+		return ret;
 
 	sched_clock_register(xilinx_clock_read, 32, timer_clock_freq);
+
+	return 0;
 }
 
 CLOCKSOURCE_OF_DECLARE(xilinx_timer, "xlnx,xps-timer-1.00.a",
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index 177dfc003643..abb678ccde6f 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -216,7 +216,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags);
 
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
 		return;
diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c
index 4f4520e779a5..eb99fcc76088 100644
--- a/arch/microblaze/mm/pgtable.c
+++ b/arch/microblaze/mm/pgtable.c
@@ -239,8 +239,7 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 {
 	pte_t *pte;
 	if (mem_init_done) {
-		pte = (pte_t *)__get_free_page(GFP_KERNEL |
-					__GFP_REPEAT | __GFP_ZERO);
+		pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 	} else {
 		pte = (pte_t *)early_get_page();
 		if (pte)