From 863981e96738983919de841ec669e157e6bdaeb0 Mon Sep 17 00:00:00 2001 From: André Fabian Silva Delgado Date: Sun, 11 Sep 2016 04:34:46 -0300 Subject: Linux-libre 4.7.1-gnu --- arch/microblaze/include/asm/hash.h | 81 +++++++++++++++++++++++++++++++++ arch/microblaze/include/asm/pgalloc.h | 4 +- arch/microblaze/include/asm/processor.h | 10 ---- arch/microblaze/include/asm/unistd.h | 2 +- 4 files changed, 84 insertions(+), 13 deletions(-) create mode 100644 arch/microblaze/include/asm/hash.h (limited to 'arch/microblaze/include/asm') 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 */ -- cgit v1.2.3-54-g00ecf