Linux-libre 4.7.1-gnupck-4.7.1-gnu

9 files changed, 95 insertions, 15 deletions

diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 3d793b55f..636e0720f 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -16,6 +16,7 @@ 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
@@ -32,6 +33,7 @@ config MICROBLAZE
 	select OF_EARLY_FLATTREE
 	select TRACING_SUPPORT
 	select VIRT_TO_BUS
+	select CPU_NO_EFFICIENT_FFS
 
 config SWAP
 	def_bool n
diff --git a/arch/microblaze/include/asm/hash.h b/arch/microblaze/include/asm/hash.h
new file mode 100644
index 000000000..753513ae8
--- /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 61436d697..7c89390c0 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/include/asm/processor.h b/arch/microblaze/include/asm/processor.h
index 497a988d7..c38d0dd91 100644
--- a/arch/microblaze/include/asm/processor.h
+++ b/arch/microblaze/include/asm/processor.h
@@ -70,11 +70,6 @@ static inline void release_thread(struct task_struct *dead_task)
 {
 }
 
-/* Free all resources held by a thread. */
-static inline void exit_thread(void)
-{
-}
-
 extern unsigned long thread_saved_pc(struct task_struct *t);
 
 extern unsigned long get_wchan(struct task_struct *p);
@@ -127,11 +122,6 @@ static inline void release_thread(struct task_struct *dead_task)
 {
 }
 
-/* Free current thread data structures etc.  */
-static inline void exit_thread(void)
-{
-}
-
 /* Return saved (kernel) PC of a blocked thread.  */
 #  define thread_saved_pc(tsk)	\
 	((tsk)->thread.regs ? (tsk)->thread.regs->r15 : 0)
diff --git a/arch/microblaze/include/asm/unistd.h b/arch/microblaze/include/asm/unistd.h
index 76ed17b56..805ae5d71 100644
--- a/arch/microblaze/include/asm/unistd.h
+++ b/arch/microblaze/include/asm/unistd.h
@@ -38,6 +38,6 @@
 
 #endif /* __ASSEMBLY__ */
 
-#define __NR_syscalls         389
+#define __NR_syscalls         392
 
 #endif /* _ASM_MICROBLAZE_UNISTD_H */
diff --git a/arch/microblaze/include/uapi/asm/unistd.h b/arch/microblaze/include/uapi/asm/unistd.h
index 32850c73b..a8bd3fa28 100644
--- a/arch/microblaze/include/uapi/asm/unistd.h
+++ b/arch/microblaze/include/uapi/asm/unistd.h
@@ -404,5 +404,8 @@
 #define __NR_memfd_create	386
 #define __NR_bpf		387
 #define __NR_execveat		388
+#define __NR_userfaultfd	389
+#define __NR_membarrier		390
+#define __NR_mlock2		391
 
 #endif /* _UAPI_ASM_MICROBLAZE_UNISTD_H */
diff --git a/arch/microblaze/kernel/syscall_table.S b/arch/microblaze/kernel/syscall_table.S
index 29c8568ec..6b3dd9912 100644
--- a/arch/microblaze/kernel/syscall_table.S
+++ b/arch/microblaze/kernel/syscall_table.S
@@ -389,3 +389,6 @@ ENTRY(sys_call_table)
 	.long sys_memfd_create
 	.long sys_bpf
 	.long sys_execveat
+	.long sys_userfaultfd
+	.long sys_membarrier		/* 390 */
+	.long sys_mlock2
diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c
index 4f4520e77..eb99fcc76 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)
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index 35654be3f..14cba600d 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -48,6 +48,8 @@ static int global_phb_number;		/* Global phb counter */
 resource_size_t isa_mem_base;
 
 unsigned long isa_io_base;
+EXPORT_SYMBOL(isa_io_base);
+
 static int pci_bus_count;
 
 struct pci_controller *pcibios_alloc_controller(struct device_node *dev)