FEX-Emu/linux
1
0
Fork 0
mirror of https://github.com/FEX-Emu/linux.git synced 2024-12-27 20:07:09 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
9eeb226477
linux/arch/arm/mm/Kconfig
Zhaoxiu Zeng fff7fb0b2d lib/GCD.c: use binary GCD algorithm instead of Euclidean 
The binary GCD algorithm is based on the following facts:
	1. If a and b are all evens, then gcd(a,b) = 2 * gcd(a/2, b/2)
	2. If a is even and b is odd, then gcd(a,b) = gcd(a/2, b)
	3. If a and b are all odds, then gcd(a,b) = gcd((a-b)/2, b) = gcd((a+b)/2, b)

Even on x86 machines with reasonable division hardware, the binary
algorithm runs about 25% faster (80% the execution time) than the
division-based Euclidian algorithm.

On platforms like Alpha and ARMv6 where division is a function call to
emulation code, it's even more significant.

There are two variants of the code here, depending on whether a fast
__ffs (find least significant set bit) instruction is available.  This
allows the unpredictable branches in the bit-at-a-time shifting loop to
be eliminated.

If fast __ffs is not available, the "even/odd" GCD variant is used.

I use the following code to benchmark:

	#include <stdio.h>
	#include <stdlib.h>
	#include <stdint.h>
	#include <string.h>
	#include <time.h>
	#include <unistd.h>

	#define swap(a, b) \
		do { \
			a ^= b; \
			b ^= a; \
			a ^= b; \
		} while (0)

	unsigned long gcd0(unsigned long a, unsigned long b)
	{
		unsigned long r;

		if (a < b) {
			swap(a, b);
		}

		if (b == 0)
			return a;

		while ((r = a % b) != 0) {
			a = b;
			b = r;
		}

		return b;
	}

	unsigned long gcd1(unsigned long a, unsigned long b)
	{
		unsigned long r = a | b;

		if (!a || !b)
			return r;

		b >>= __builtin_ctzl(b);

		for (;;) {
			a >>= __builtin_ctzl(a);
			if (a == b)
				return a << __builtin_ctzl(r);

			if (a < b)
				swap(a, b);
			a -= b;
		}
	}

	unsigned long gcd2(unsigned long a, unsigned long b)
	{
		unsigned long r = a | b;

		if (!a || !b)
			return r;

		r &= -r;

		while (!(b & r))
			b >>= 1;

		for (;;) {
			while (!(a & r))
				a >>= 1;
			if (a == b)
				return a;

			if (a < b)
				swap(a, b);
			a -= b;
			a >>= 1;
			if (a & r)
				a += b;
			a >>= 1;
		}
	}

	unsigned long gcd3(unsigned long a, unsigned long b)
	{
		unsigned long r = a | b;

		if (!a || !b)
			return r;

		b >>= __builtin_ctzl(b);
		if (b == 1)
			return r & -r;

		for (;;) {
			a >>= __builtin_ctzl(a);
			if (a == 1)
				return r & -r;
			if (a == b)
				return a << __builtin_ctzl(r);

			if (a < b)
				swap(a, b);
			a -= b;
		}
	}

	unsigned long gcd4(unsigned long a, unsigned long b)
	{
		unsigned long r = a | b;

		if (!a || !b)
			return r;

		r &= -r;

		while (!(b & r))
			b >>= 1;
		if (b == r)
			return r;

		for (;;) {
			while (!(a & r))
				a >>= 1;
			if (a == r)
				return r;
			if (a == b)
				return a;

			if (a < b)
				swap(a, b);
			a -= b;
			a >>= 1;
			if (a & r)
				a += b;
			a >>= 1;
		}
	}

	static unsigned long (*gcd_func[])(unsigned long a, unsigned long b) = {
		gcd0, gcd1, gcd2, gcd3, gcd4,
	};

	#define TEST_ENTRIES (sizeof(gcd_func) / sizeof(gcd_func[0]))

	#if defined(__x86_64__)

	#define rdtscll(val) do { \
		unsigned long __a,__d; \
		__asm__ __volatile__("rdtsc" : "=a" (__a), "=d" (__d)); \
		(val) = ((unsigned long long)__a) | (((unsigned long long)__d)<<32); \
	} while(0)

	static unsigned long long benchmark_gcd_func(unsigned long (*gcd)(unsigned long, unsigned long),
								unsigned long a, unsigned long b, unsigned long *res)
	{
		unsigned long long start, end;
		unsigned long long ret;
		unsigned long gcd_res;

		rdtscll(start);
		gcd_res = gcd(a, b);
		rdtscll(end);

		if (end >= start)
			ret = end - start;
		else
			ret = ~0ULL - start + 1 + end;

		*res = gcd_res;
		return ret;
	}

	#else

	static inline struct timespec read_time(void)
	{
		struct timespec time;
		clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &time);
		return time;
	}

	static inline unsigned long long diff_time(struct timespec start, struct timespec end)
	{
		struct timespec temp;

		if ((end.tv_nsec - start.tv_nsec) < 0) {
			temp.tv_sec = end.tv_sec - start.tv_sec - 1;
			temp.tv_nsec = 1000000000ULL + end.tv_nsec - start.tv_nsec;
		} else {
			temp.tv_sec = end.tv_sec - start.tv_sec;
			temp.tv_nsec = end.tv_nsec - start.tv_nsec;
		}

		return temp.tv_sec * 1000000000ULL + temp.tv_nsec;
	}

	static unsigned long long benchmark_gcd_func(unsigned long (*gcd)(unsigned long, unsigned long),
								unsigned long a, unsigned long b, unsigned long *res)
	{
		struct timespec start, end;
		unsigned long gcd_res;

		start = read_time();
		gcd_res = gcd(a, b);
		end = read_time();

		*res = gcd_res;
		return diff_time(start, end);
	}

	#endif

	static inline unsigned long get_rand()
	{
		if (sizeof(long) == 8)
			return (unsigned long)rand() << 32 | rand();
		else
			return rand();
	}

	int main(int argc, char **argv)
	{
		unsigned int seed = time(0);
		int loops = 100;
		int repeats = 1000;
		unsigned long (*res)[TEST_ENTRIES];
		unsigned long long elapsed[TEST_ENTRIES];
		int i, j, k;

		for (;;) {
			int opt = getopt(argc, argv, "n:r:s:");
			/* End condition always first */
			if (opt == -1)
				break;

			switch (opt) {
			case 'n':
				loops = atoi(optarg);
				break;
			case 'r':
				repeats = atoi(optarg);
				break;
			case 's':
				seed = strtoul(optarg, NULL, 10);
				break;
			default:
				/* You won't actually get here. */
				break;
			}
		}

		res = malloc(sizeof(unsigned long) * TEST_ENTRIES * loops);
		memset(elapsed, 0, sizeof(elapsed));

		srand(seed);
		for (j = 0; j < loops; j++) {
			unsigned long a = get_rand();
			/* Do we have args? */
			unsigned long b = argc > optind ? strtoul(argv[optind], NULL, 10) : get_rand();
			unsigned long long min_elapsed[TEST_ENTRIES];
			for (k = 0; k < repeats; k++) {
				for (i = 0; i < TEST_ENTRIES; i++) {
					unsigned long long tmp = benchmark_gcd_func(gcd_func[i], a, b, &res[j][i]);
					if (k == 0 || min_elapsed[i] > tmp)
						min_elapsed[i] = tmp;
				}
			}
			for (i = 0; i < TEST_ENTRIES; i++)
				elapsed[i] += min_elapsed[i];
		}

		for (i = 0; i < TEST_ENTRIES; i++)
			printf("gcd%d: elapsed %llu\n", i, elapsed[i]);

		k = 0;
		srand(seed);
		for (j = 0; j < loops; j++) {
			unsigned long a = get_rand();
			unsigned long b = argc > optind ? strtoul(argv[optind], NULL, 10) : get_rand();
			for (i = 1; i < TEST_ENTRIES; i++) {
				if (res[j][i] != res[j][0])
					break;
			}
			if (i < TEST_ENTRIES) {
				if (k == 0) {
					k = 1;
					fprintf(stderr, "Error:\n");
				}
				fprintf(stderr, "gcd(%lu, %lu): ", a, b);
				for (i = 0; i < TEST_ENTRIES; i++)
					fprintf(stderr, "%ld%s", res[j][i], i < TEST_ENTRIES - 1 ? ", " : "\n");
			}
		}

		if (k == 0)
			fprintf(stderr, "PASS\n");

		free(res);

		return 0;
	}

Compiled with "-O2", on "VirtualBox 4.4.0-22-generic #38-Ubuntu x86_64" got:

  zhaoxiuzeng@zhaoxiuzeng-VirtualBox:~/develop$ ./gcd -r 500000 -n 10
  gcd0: elapsed 10174
  gcd1: elapsed 2120
  gcd2: elapsed 2902
  gcd3: elapsed 2039
  gcd4: elapsed 2812
  PASS
  zhaoxiuzeng@zhaoxiuzeng-VirtualBox:~/develop$ ./gcd -r 500000 -n 10
  gcd0: elapsed 9309
  gcd1: elapsed 2280
  gcd2: elapsed 2822
  gcd3: elapsed 2217
  gcd4: elapsed 2710
  PASS
  zhaoxiuzeng@zhaoxiuzeng-VirtualBox:~/develop$ ./gcd -r 500000 -n 10
  gcd0: elapsed 9589
  gcd1: elapsed 2098
  gcd2: elapsed 2815
  gcd3: elapsed 2030
  gcd4: elapsed 2718
  PASS
  zhaoxiuzeng@zhaoxiuzeng-VirtualBox:~/develop$ ./gcd -r 500000 -n 10
  gcd0: elapsed 9914
  gcd1: elapsed 2309
  gcd2: elapsed 2779
  gcd3: elapsed 2228
  gcd4: elapsed 2709
  PASS

[akpm@linux-foundation.org: avoid #defining a CONFIG_ variable]
Signed-off-by: Zhaoxiu Zeng <zhaoxiu.zeng@gmail.com>
Signed-off-by: George Spelvin <linux@horizon.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-20 17:58:30 -07:00

1066 lines
28 KiB
Plaintext
Raw Blame History

comment "Processor Type"
# Select CPU types depending on the architecture selected. This selects
# which CPUs we support in the kernel image, and the compiler instruction
# optimiser behaviour.
# ARM7TDMI
config CPU_ARM7TDMI
bool
depends on !MMU
select CPU_32v4T
select CPU_ABRT_LV4T
select CPU_CACHE_V4
select CPU_PABRT_LEGACY
help
A 32-bit RISC microprocessor based on the ARM7 processor core
which has no memory control unit and cache.
Say Y if you want support for the ARM7TDMI processor.
Otherwise, say N.
# ARM720T
config CPU_ARM720T
bool
select CPU_32v4T
select CPU_ABRT_LV4T
select CPU_CACHE_V4
select CPU_CACHE_VIVT
select CPU_COPY_V4WT if MMU
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_V4WT if MMU
help
A 32-bit RISC processor with 8kByte Cache, Write Buffer and
MMU built around an ARM7TDMI core.
Say Y if you want support for the ARM720T processor.
Otherwise, say N.
# ARM740T
config CPU_ARM740T
bool
depends on !MMU
select CPU_32v4T
select CPU_ABRT_LV4T
select CPU_CACHE_V4
select CPU_CP15_MPU
select CPU_PABRT_LEGACY
help
A 32-bit RISC processor with 8KB cache or 4KB variants,
write buffer and MPU(Protection Unit) built around
an ARM7TDMI core.
Say Y if you want support for the ARM740T processor.
Otherwise, say N.
# ARM9TDMI
config CPU_ARM9TDMI
bool
depends on !MMU
select CPU_32v4T
select CPU_ABRT_NOMMU
select CPU_CACHE_V4
select CPU_PABRT_LEGACY
help
A 32-bit RISC microprocessor based on the ARM9 processor core
which has no memory control unit and cache.
Say Y if you want support for the ARM9TDMI processor.
Otherwise, say N.
# ARM920T
config CPU_ARM920T
bool
select CPU_32v4T
select CPU_ABRT_EV4T
select CPU_CACHE_V4WT
select CPU_CACHE_VIVT
select CPU_COPY_V4WB if MMU
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_V4WBI if MMU
help
The ARM920T is licensed to be produced by numerous vendors,
and is used in the Cirrus EP93xx and the Samsung S3C2410.
Say Y if you want support for the ARM920T processor.
Otherwise, say N.
# ARM922T
config CPU_ARM922T
bool
select CPU_32v4T
select CPU_ABRT_EV4T
select CPU_CACHE_V4WT
select CPU_CACHE_VIVT
select CPU_COPY_V4WB if MMU
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_V4WBI if MMU
help
The ARM922T is a version of the ARM920T, but with smaller
instruction and data caches. It is used in Altera's
Excalibur XA device family and Micrel's KS8695 Centaur.
Say Y if you want support for the ARM922T processor.
Otherwise, say N.
# ARM925T
config CPU_ARM925T
bool
select CPU_32v4T
select CPU_ABRT_EV4T
select CPU_CACHE_V4WT
select CPU_CACHE_VIVT
select CPU_COPY_V4WB if MMU
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_V4WBI if MMU
help
The ARM925T is a mix between the ARM920T and ARM926T, but with
different instruction and data caches. It is used in TI's OMAP
device family.
Say Y if you want support for the ARM925T processor.
Otherwise, say N.
# ARM926T
config CPU_ARM926T
bool
select CPU_32v5
select CPU_ABRT_EV5TJ
select CPU_CACHE_VIVT
select CPU_COPY_V4WB if MMU
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_V4WBI if MMU
help
This is a variant of the ARM920. It has slightly different
instruction sequences for cache and TLB operations. Curiously,
there is no documentation on it at the ARM corporate website.
Say Y if you want support for the ARM926T processor.
Otherwise, say N.
# FA526
config CPU_FA526
bool
select CPU_32v4
select CPU_ABRT_EV4
select CPU_CACHE_FA
select CPU_CACHE_VIVT
select CPU_COPY_FA if MMU
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_FA if MMU
help
The FA526 is a version of the ARMv4 compatible processor with
Branch Target Buffer, Unified TLB and cache line size 16.
Say Y if you want support for the FA526 processor.
Otherwise, say N.
# ARM940T
config CPU_ARM940T
bool
depends on !MMU
select CPU_32v4T
select CPU_ABRT_NOMMU
select CPU_CACHE_VIVT
select CPU_CP15_MPU
select CPU_PABRT_LEGACY
help
ARM940T is a member of the ARM9TDMI family of general-
purpose microprocessors with MPU and separate 4KB
instruction and 4KB data cases, each with a 4-word line
length.
Say Y if you want support for the ARM940T processor.
Otherwise, say N.
# ARM946E-S
config CPU_ARM946E
bool
depends on !MMU
select CPU_32v5
select CPU_ABRT_NOMMU
select CPU_CACHE_VIVT
select CPU_CP15_MPU
select CPU_PABRT_LEGACY
help
ARM946E-S is a member of the ARM9E-S family of high-
performance, 32-bit system-on-chip processor solutions.
The TCM and ARMv5TE 32-bit instruction set is supported.
Say Y if you want support for the ARM946E-S processor.
Otherwise, say N.
# ARM1020 - needs validating
config CPU_ARM1020
bool
select CPU_32v5
select CPU_ABRT_EV4T
select CPU_CACHE_V4WT
select CPU_CACHE_VIVT
select CPU_COPY_V4WB if MMU
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_V4WBI if MMU
help
The ARM1020 is the 32K cached version of the ARM10 processor,
with an addition of a floating-point unit.
Say Y if you want support for the ARM1020 processor.
Otherwise, say N.
# ARM1020E - needs validating
config CPU_ARM1020E
bool
depends on n
select CPU_32v5
select CPU_ABRT_EV4T
select CPU_CACHE_V4WT
select CPU_CACHE_VIVT
select CPU_COPY_V4WB if MMU
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_V4WBI if MMU
# ARM1022E
config CPU_ARM1022
bool
select CPU_32v5
select CPU_ABRT_EV4T
select CPU_CACHE_VIVT
select CPU_COPY_V4WB if MMU # can probably do better
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_V4WBI if MMU
help
The ARM1022E is an implementation of the ARMv5TE architecture
based upon the ARM10 integer core with a 16KiB L1 Harvard cache,
embedded trace macrocell, and a floating-point unit.
Say Y if you want support for the ARM1022E processor.
Otherwise, say N.
# ARM1026EJ-S
config CPU_ARM1026
bool
select CPU_32v5
select CPU_ABRT_EV5T # But need Jazelle, but EV5TJ ignores bit 10
select CPU_CACHE_VIVT
select CPU_COPY_V4WB if MMU # can probably do better
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_V4WBI if MMU
help
The ARM1026EJ-S is an implementation of the ARMv5TEJ architecture
based upon the ARM10 integer core.
Say Y if you want support for the ARM1026EJ-S processor.
Otherwise, say N.
# SA110
config CPU_SA110
bool
select CPU_32v3 if ARCH_RPC
select CPU_32v4 if !ARCH_RPC
select CPU_ABRT_EV4
select CPU_CACHE_V4WB
select CPU_CACHE_VIVT
select CPU_COPY_V4WB if MMU
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_V4WB if MMU
help
The Intel StrongARM(R) SA-110 is a 32-bit microprocessor and
is available at five speeds ranging from 100 MHz to 233 MHz.
More information is available at
<http://developer.intel.com/design/strong/sa110.htm>.
Say Y if you want support for the SA-110 processor.
Otherwise, say N.
# SA1100
config CPU_SA1100
bool
select CPU_32v4
select CPU_ABRT_EV4
select CPU_CACHE_V4WB
select CPU_CACHE_VIVT
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_V4WB if MMU
# XScale
config CPU_XSCALE
bool
select CPU_32v5
select CPU_ABRT_EV5T
select CPU_CACHE_VIVT
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_V4WBI if MMU
# XScale Core Version 3
config CPU_XSC3
bool
select CPU_32v5
select CPU_ABRT_EV5T
select CPU_CACHE_VIVT
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_V4WBI if MMU
select IO_36
# Marvell PJ1 (Mohawk)
config CPU_MOHAWK
bool
select CPU_32v5
select CPU_ABRT_EV5T
select CPU_CACHE_VIVT
select CPU_COPY_V4WB if MMU
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_V4WBI if MMU
# Feroceon
config CPU_FEROCEON
bool
select CPU_32v5
select CPU_ABRT_EV5T
select CPU_CACHE_VIVT
select CPU_COPY_FEROCEON if MMU
select CPU_CP15_MMU
select CPU_PABRT_LEGACY
select CPU_TLB_FEROCEON if MMU
config CPU_FEROCEON_OLD_ID
bool "Accept early Feroceon cores with an ARM926 ID"
depends on CPU_FEROCEON && !CPU_ARM926T
default y
help
This enables the usage of some old Feroceon cores
for which the CPU ID is equal to the ARM926 ID.
Relevant for Feroceon-1850 and early Feroceon-2850.
# Marvell PJ4
config CPU_PJ4
bool
select ARM_THUMBEE
select CPU_V7
config CPU_PJ4B
bool
select CPU_V7
# ARMv6
config CPU_V6
bool
select CPU_32v6
select CPU_ABRT_EV6
select CPU_CACHE_V6
select CPU_CACHE_VIPT
select CPU_COPY_V6 if MMU
select CPU_CP15_MMU
select CPU_HAS_ASID if MMU
select CPU_PABRT_V6
select CPU_TLB_V6 if MMU
# ARMv6k
config CPU_V6K
bool
select CPU_32v6
select CPU_32v6K
select CPU_ABRT_EV6
select CPU_CACHE_V6
select CPU_CACHE_VIPT
select CPU_COPY_V6 if MMU
select CPU_CP15_MMU
select CPU_HAS_ASID if MMU
select CPU_PABRT_V6
select CPU_TLB_V6 if MMU
# ARMv7
config CPU_V7
bool
select CPU_32v6K
select CPU_32v7
select CPU_ABRT_EV7
select CPU_CACHE_V7
select CPU_CACHE_VIPT
select CPU_COPY_V6 if MMU
select CPU_CP15_MMU if MMU
select CPU_CP15_MPU if !MMU
select CPU_HAS_ASID if MMU
select CPU_PABRT_V7
select CPU_TLB_V7 if MMU
# ARMv7M
config CPU_V7M
bool
select CPU_32v7M
select CPU_ABRT_NOMMU
select CPU_CACHE_NOP
select CPU_PABRT_LEGACY
select CPU_THUMBONLY
config CPU_THUMBONLY
bool
# There are no CPUs available with MMU that don't implement an ARM ISA:
depends on !MMU
help
Select this if your CPU doesn't support the 32 bit ARM instructions.
# Figure out what processor architecture version we should be using.
# This defines the compiler instruction set which depends on the machine type.
config CPU_32v3
bool
select CPU_USE_DOMAINS if MMU
select NEED_KUSER_HELPERS
select TLS_REG_EMUL if SMP || !MMU
select CPU_NO_EFFICIENT_FFS
config CPU_32v4
bool
select CPU_USE_DOMAINS if MMU
select NEED_KUSER_HELPERS
select TLS_REG_EMUL if SMP || !MMU
select CPU_NO_EFFICIENT_FFS
config CPU_32v4T
bool
select CPU_USE_DOMAINS if MMU
select NEED_KUSER_HELPERS
select TLS_REG_EMUL if SMP || !MMU
select CPU_NO_EFFICIENT_FFS
config CPU_32v5
bool
select CPU_USE_DOMAINS if MMU
select NEED_KUSER_HELPERS
select TLS_REG_EMUL if SMP || !MMU
config CPU_32v6
bool
select TLS_REG_EMUL if !CPU_32v6K && !MMU
config CPU_32v6K
bool
config CPU_32v7
bool
config CPU_32v7M
bool
# The abort model
config CPU_ABRT_NOMMU
bool
config CPU_ABRT_EV4
bool
config CPU_ABRT_EV4T
bool
config CPU_ABRT_LV4T
bool
config CPU_ABRT_EV5T
bool
config CPU_ABRT_EV5TJ
bool
config CPU_ABRT_EV6
bool
config CPU_ABRT_EV7
bool
config CPU_PABRT_LEGACY
bool
config CPU_PABRT_V6
bool
config CPU_PABRT_V7
bool
# The cache model
config CPU_CACHE_V4
bool
config CPU_CACHE_V4WT
bool
config CPU_CACHE_V4WB
bool
config CPU_CACHE_V6
bool
config CPU_CACHE_V7
bool
config CPU_CACHE_NOP
bool
config CPU_CACHE_VIVT
bool
config CPU_CACHE_VIPT
bool
config CPU_CACHE_FA
bool
if MMU
# The copy-page model
config CPU_COPY_V4WT
bool
config CPU_COPY_V4WB
bool
config CPU_COPY_FEROCEON
bool
config CPU_COPY_FA
bool
config CPU_COPY_V6
bool
# This selects the TLB model
config CPU_TLB_V4WT
bool
help
ARM Architecture Version 4 TLB with writethrough cache.
config CPU_TLB_V4WB
bool
help
ARM Architecture Version 4 TLB with writeback cache.
config CPU_TLB_V4WBI
bool
help
ARM Architecture Version 4 TLB with writeback cache and invalidate
instruction cache entry.
config CPU_TLB_FEROCEON
bool
help
Feroceon TLB (v4wbi with non-outer-cachable page table walks).
config CPU_TLB_FA
bool
help
Faraday ARM FA526 architecture, unified TLB with writeback cache
and invalidate instruction cache entry. Branch target buffer is
also supported.
config CPU_TLB_V6
bool
config CPU_TLB_V7
bool
config VERIFY_PERMISSION_FAULT
bool
endif
config CPU_HAS_ASID
bool
help
This indicates whether the CPU has the ASID register; used to
tag TLB and possibly cache entries.
config CPU_CP15
bool
help
Processor has the CP15 register.
config CPU_CP15_MMU
bool
select CPU_CP15
help
Processor has the CP15 register, which has MMU related registers.
config CPU_CP15_MPU
bool
select CPU_CP15
help
Processor has the CP15 register, which has MPU related registers.
config CPU_USE_DOMAINS
bool
help
This option enables or disables the use of domain switching
via the set_fs() function.
config CPU_V7M_NUM_IRQ
int "Number of external interrupts connected to the NVIC"
depends on CPU_V7M
default 90 if ARCH_STM32
default 38 if ARCH_EFM32
default 112 if SOC_VF610
default 240
help
This option indicates the number of interrupts connected to the NVIC.
The value can be larger than the real number of interrupts supported
by the system, but must not be lower.
The default value is 240, corresponding to the maximum number of
interrupts supported by the NVIC on Cortex-M family.
If unsure, keep default value.
#
# CPU supports 36-bit I/O
#
config IO_36
bool
comment "Processor Features"
config ARM_LPAE
bool "Support for the Large Physical Address Extension"
depends on MMU && CPU_32v7 && !CPU_32v6 && !CPU_32v5 && \
!CPU_32v4 && !CPU_32v3
help
Say Y if you have an ARMv7 processor supporting the LPAE page
table format and you would like to access memory beyond the
4GB limit. The resulting kernel image will not run on
processors without the LPA extension.
If unsure, say N.
config ARM_PV_FIXUP
def_bool y
depends on ARM_LPAE && ARM_PATCH_PHYS_VIRT && ARCH_KEYSTONE
config ARCH_PHYS_ADDR_T_64BIT
def_bool ARM_LPAE
config ARCH_DMA_ADDR_T_64BIT
bool
config ARM_THUMB
bool "Support Thumb user binaries" if !CPU_THUMBONLY
depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || \
CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || \
CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || \
CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || \
CPU_V7 || CPU_FEROCEON || CPU_V7M
default y
help
Say Y if you want to include kernel support for running user space
Thumb binaries.
The Thumb instruction set is a compressed form of the standard ARM
instruction set resulting in smaller binaries at the expense of
slightly less efficient code.
If you don't know what this all is, saying Y is a safe choice.
config ARM_THUMBEE
bool "Enable ThumbEE CPU extension"
depends on CPU_V7
help
Say Y here if you have a CPU with the ThumbEE extension and code to
make use of it. Say N for code that can run on CPUs without ThumbEE.
config ARM_VIRT_EXT
bool
depends on MMU
default y if CPU_V7
help
Enable the kernel to make use of the ARM Virtualization
Extensions to install hypervisors without run-time firmware
assistance.
A compliant bootloader is required in order to make maximum
use of this feature. Refer to Documentation/arm/Booting for
details.
config SWP_EMULATE
bool "Emulate SWP/SWPB instructions" if !SMP
depends on CPU_V7
default y if SMP
select HAVE_PROC_CPU if PROC_FS
help
ARMv6 architecture deprecates use of the SWP/SWPB instructions.
ARMv7 multiprocessing extensions introduce the ability to disable
these instructions, triggering an undefined instruction exception
when executed. Say Y here to enable software emulation of these
instructions for userspace (not kernel) using LDREX/STREX.
Also creates /proc/cpu/swp_emulation for statistics.
In some older versions of glibc [<=2.8] SWP is used during futex
trylock() operations with the assumption that the code will not
be preempted. This invalid assumption may be more likely to fail
with SWP emulation enabled, leading to deadlock of the user
application.
NOTE: when accessing uncached shared regions, LDREX/STREX rely
on an external transaction monitoring block called a global
monitor to maintain update atomicity. If your system does not
implement a global monitor, this option can cause programs that
perform SWP operations to uncached memory to deadlock.
If unsure, say Y.
config CPU_BIG_ENDIAN
bool "Build big-endian kernel"
depends on ARCH_SUPPORTS_BIG_ENDIAN
help
Say Y if you plan on running a kernel in big-endian mode.
Note that your board must be properly built and your board
port must properly enable any big-endian related features
of your chipset/board/processor.
config CPU_ENDIAN_BE8
bool
depends on CPU_BIG_ENDIAN
default CPU_V6 || CPU_V6K || CPU_V7
help
Support for the BE-8 (big-endian) mode on ARMv6 and ARMv7 processors.
config CPU_ENDIAN_BE32
bool
depends on CPU_BIG_ENDIAN
default !CPU_ENDIAN_BE8
help
Support for the BE-32 (big-endian) mode on pre-ARMv6 processors.
config CPU_HIGH_VECTOR
depends on !MMU && CPU_CP15 && !CPU_ARM740T
bool "Select the High exception vector"
help
Say Y here to select high exception vector(0xFFFF0000~).
The exception vector can vary depending on the platform
design in nommu mode. If your platform needs to select
high exception vector, say Y.
Otherwise or if you are unsure, say N, and the low exception
vector (0x00000000~) will be used.
config CPU_ICACHE_DISABLE
bool "Disable I-Cache (I-bit)"
depends on CPU_CP15 && !(CPU_ARM720T || CPU_ARM740T || CPU_XSCALE || CPU_XSC3)
help
Say Y here to disable the processor instruction cache. Unless
you have a reason not to or are unsure, say N.
config CPU_DCACHE_DISABLE
bool "Disable D-Cache (C-bit)"
depends on CPU_CP15 && !SMP
help
Say Y here to disable the processor data cache. Unless
you have a reason not to or are unsure, say N.
config CPU_DCACHE_SIZE
hex
depends on CPU_ARM740T || CPU_ARM946E
default 0x00001000 if CPU_ARM740T
default 0x00002000 # default size for ARM946E-S
help
Some cores are synthesizable to have various sized cache. For
ARM946E-S case, it can vary from 0KB to 1MB.
To support such cache operations, it is efficient to know the size
before compile time.
If your SoC is configured to have a different size, define the value
here with proper conditions.
config CPU_DCACHE_WRITETHROUGH
bool "Force write through D-cache"
depends on (CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_FA526) && !CPU_DCACHE_DISABLE
default y if CPU_ARM925T
help
Say Y here to use the data cache in writethrough mode. Unless you
specifically require this or are unsure, say N.
config CPU_CACHE_ROUND_ROBIN
bool "Round robin I and D cache replacement algorithm"
depends on (CPU_ARM926T || CPU_ARM946E || CPU_ARM1020) && (!CPU_ICACHE_DISABLE || !CPU_DCACHE_DISABLE)
help
Say Y here to use the predictable round-robin cache replacement
policy. Unless you specifically require this or are unsure, say N.
config CPU_BPREDICT_DISABLE
bool "Disable branch prediction"
depends on CPU_ARM1020 || CPU_V6 || CPU_V6K || CPU_MOHAWK || CPU_XSC3 || CPU_V7 || CPU_FA526
help
Say Y here to disable branch prediction. If unsure, say N.
config TLS_REG_EMUL
bool
select NEED_KUSER_HELPERS
help
An SMP system using a pre-ARMv6 processor (there are apparently
a few prototypes like that in existence) and therefore access to
that required register must be emulated.
config NEED_KUSER_HELPERS
bool
config KUSER_HELPERS
bool "Enable kuser helpers in vector page" if !NEED_KUSER_HELPERS
depends on MMU
default y
help
Warning: disabling this option may break user programs.
Provide kuser helpers in the vector page. The kernel provides
helper code to userspace in read only form at a fixed location
in the high vector page to allow userspace to be independent of
the CPU type fitted to the system. This permits binaries to be
run on ARMv4 through to ARMv7 without modification.
See Documentation/arm/kernel_user_helpers.txt for details.
However, the fixed address nature of these helpers can be used
by ROP (return orientated programming) authors when creating
exploits.
If all of the binaries and libraries which run on your platform
are built specifically for your platform, and make no use of
these helpers, then you can turn this option off to hinder
such exploits. However, in that case, if a binary or library
relying on those helpers is run, it will receive a SIGILL signal,
which will terminate the program.
Say N here only if you are absolutely certain that you do not
need these helpers; otherwise, the safe option is to say Y.
config VDSO
bool "Enable VDSO for acceleration of some system calls"
depends on AEABI && MMU && CPU_V7
default y if ARM_ARCH_TIMER
select GENERIC_TIME_VSYSCALL
help
Place in the process address space an ELF shared object
providing fast implementations of gettimeofday and
clock_gettime. Systems that implement the ARM architected
timer will receive maximum benefit.
You must have glibc 2.22 or later for programs to seamlessly
take advantage of this.
config DMA_CACHE_RWFO
bool "Enable read/write for ownership DMA cache maintenance"
depends on CPU_V6K && SMP
default y
help
The Snoop Control Unit on ARM11MPCore does not detect the
cache maintenance operations and the dma_{map,unmap}_area()
functions may leave stale cache entries on other CPUs. By
enabling this option, Read or Write For Ownership in the ARMv6
DMA cache maintenance functions is performed. These LDR/STR
instructions change the cache line state to shared or modified
so that the cache operation has the desired effect.
Note that the workaround is only valid on processors that do
not perform speculative loads into the D-cache. For such
processors, if cache maintenance operations are not broadcast
in hardware, other workarounds are needed (e.g. cache
maintenance broadcasting in software via FIQ).
config OUTER_CACHE
bool
config OUTER_CACHE_SYNC
bool
select ARM_HEAVY_MB
help
The outer cache has a outer_cache_fns.sync function pointer
that can be used to drain the write buffer of the outer cache.
config CACHE_FEROCEON_L2
bool "Enable the Feroceon L2 cache controller"
depends on ARCH_MV78XX0 || ARCH_MVEBU
default y
select OUTER_CACHE
help
This option enables the Feroceon L2 cache controller.
config CACHE_FEROCEON_L2_WRITETHROUGH
bool "Force Feroceon L2 cache write through"
depends on CACHE_FEROCEON_L2
help
Say Y here to use the Feroceon L2 cache in writethrough mode.
Unless you specifically require this, say N for writeback mode.
config MIGHT_HAVE_CACHE_L2X0
bool
help
This option should be selected by machines which have a L2x0
or PL310 cache controller, but where its use is optional.
The only effect of this option is to make CACHE_L2X0 and
related options available to the user for configuration.
Boards or SoCs which always require the cache controller
support to be present should select CACHE_L2X0 directly
instead of this option, thus preventing the user from
inadvertently configuring a broken kernel.
config CACHE_L2X0
bool "Enable the L2x0 outer cache controller" if MIGHT_HAVE_CACHE_L2X0
default MIGHT_HAVE_CACHE_L2X0
select OUTER_CACHE
select OUTER_CACHE_SYNC
help
This option enables the L2x0 PrimeCell.
if CACHE_L2X0
config PL310_ERRATA_588369
bool "PL310 errata: Clean & Invalidate maintenance operations do not invalidate clean lines"
help
The PL310 L2 cache controller implements three types of Clean &
Invalidate maintenance operations: by Physical Address
(offset 0x7F0), by Index/Way (0x7F8) and by Way (0x7FC).
They are architecturally defined to behave as the execution of a
clean operation followed immediately by an invalidate operation,
both performing to the same memory location. This functionality
is not correctly implemented in PL310 prior to r2p0 (fixed in r2p0)
as clean lines are not invalidated as a result of these operations.
config PL310_ERRATA_727915
bool "PL310 errata: Background Clean & Invalidate by Way operation can cause data corruption"
help
PL310 implements the Clean & Invalidate by Way L2 cache maintenance
operation (offset 0x7FC). This operation runs in background so that
PL310 can handle normal accesses while it is in progress. Under very
rare circumstances, due to this erratum, write data can be lost when
PL310 treats a cacheable write transaction during a Clean &
Invalidate by Way operation. Revisions prior to r3p1 are affected by
this errata (fixed in r3p1).
config PL310_ERRATA_753970
bool "PL310 errata: cache sync operation may be faulty"
help
This option enables the workaround for the 753970 PL310 (r3p0) erratum.
Under some condition the effect of cache sync operation on
the store buffer still remains when the operation completes.
This means that the store buffer is always asked to drain and
this prevents it from merging any further writes. The workaround
is to replace the normal offset of cache sync operation (0x730)
by another offset targeting an unmapped PL310 register 0x740.
This has the same effect as the cache sync operation: store buffer
drain and waiting for all buffers empty.
config PL310_ERRATA_769419
bool "PL310 errata: no automatic Store Buffer drain"
help
On revisions of the PL310 prior to r3p2, the Store Buffer does
not automatically drain. This can cause normal, non-cacheable
writes to be retained when the memory system is idle, leading
to suboptimal I/O performance for drivers using coherent DMA.
This option adds a write barrier to the cpu_idle loop so that,
on systems with an outer cache, the store buffer is drained
explicitly.
endif
config CACHE_TAUROS2
bool "Enable the Tauros2 L2 cache controller"
depends on (ARCH_DOVE || ARCH_MMP || CPU_PJ4)
default y
select OUTER_CACHE
help
This option enables the Tauros2 L2 cache controller (as
found on PJ1/PJ4).
config CACHE_UNIPHIER
bool "Enable the UniPhier outer cache controller"
depends on ARCH_UNIPHIER
default y
select OUTER_CACHE
select OUTER_CACHE_SYNC
help
This option enables the UniPhier outer cache (system cache)
controller.
config CACHE_XSC3L2
bool "Enable the L2 cache on XScale3"
depends on CPU_XSC3
default y
select OUTER_CACHE
help
This option enables the L2 cache on XScale3.
config ARM_L1_CACHE_SHIFT_6
bool
default y if CPU_V7
help
Setting ARM L1 cache line size to 64 Bytes.
config ARM_L1_CACHE_SHIFT
int
default 6 if ARM_L1_CACHE_SHIFT_6
default 5
config ARM_DMA_MEM_BUFFERABLE
bool "Use non-cacheable memory for DMA" if (CPU_V6 || CPU_V6K) && !CPU_V7
default y if CPU_V6 || CPU_V6K || CPU_V7
help
Historically, the kernel has used strongly ordered mappings to
provide DMA coherent memory. With the advent of ARMv7, mapping
memory with differing types results in unpredictable behaviour,
so on these CPUs, this option is forced on.
Multiple mappings with differing attributes is also unpredictable
on ARMv6 CPUs, but since they do not have aggressive speculative
prefetch, no harm appears to occur.
However, drivers may be missing the necessary barriers for ARMv6,
and therefore turning this on may result in unpredictable driver
behaviour. Therefore, we offer this as an option.
You are recommended say 'Y' here and debug any affected drivers.
config ARCH_HAS_BARRIERS
bool
help
This option allows the use of custom mandatory barriers
included via the mach/barriers.h file.
config ARM_HEAVY_MB
bool
config ARCH_SUPPORTS_BIG_ENDIAN
bool
help
This option specifies the architecture can support big endian
operation.
config DEBUG_RODATA
bool "Make kernel text and rodata read-only"
depends on MMU && !XIP_KERNEL
default y if CPU_V7
help
If this is set, kernel text and rodata memory will be made
read-only, and non-text kernel memory will be made non-executable.
The tradeoff is that each region is padded to section-size (1MiB)
boundaries (because their permissions are different and splitting
the 1M pages into 4K ones causes TLB performance problems), which
can waste memory.
config DEBUG_ALIGN_RODATA
bool "Make rodata strictly non-executable"
depends on DEBUG_RODATA
default y
help
If this is set, rodata will be made explicitly non-executable. This
provides protection on the rare chance that attackers might find and
use ROP gadgets that exist in the rodata section. This adds an
additional section-aligned split of rodata from kernel text so it
can be made explicitly non-executable. This padding may waste memory
space to gain the additional protection.
Reference in New Issue View Git Blame Copy Permalink