Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
1 年多 前同步成功

通知 160
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 21 5月, 2016 1 次提交
    • Z
      lib/GCD.c: use binary GCD algorithm instead of Euclidean · fff7fb0b
      由 Zhaoxiu Zeng 提交于 
      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: NZhaoxiu Zeng <zhaoxiu.zeng@gmail.com>
Signed-off-by: NGeorge Spelvin <linux@horizon.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      fff7fb0b
  3. 09 3月, 2016 1 次提交
    • B
      PCI: Include pci/hotplug Kconfig directly from pci/Kconfig · e7e127e3
      由 Bjorn Helgaas 提交于 
      Include pci/hotplug/Kconfig directly from pci/Kconfig, so arches don't
have to source both pci/Kconfig and pci/hotplug/Kconfig.

Note that this effectively adds pci/hotplug/Kconfig to the following
arches, because they already sourced drivers/pci/Kconfig but they
previously did not source drivers/pci/hotplug/Kconfig:

  alpha
  arm
  avr32
  frv
  m68k
  microblaze
  mn10300
  sparc
  unicore32

Inspired-by-patch-from: Bogicevic Sasa <brutallesale@gmail.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>
      e7e127e3
  5. 06 2月, 2016 1 次提交
    • S
      m32r: fix build failure due to SMP and MMU · af1ddcb5
      由 Sudip Mukherjee 提交于 
      One of the randconfig build failed with the error:

  arch/m32r/kernel/smp.c: In function 'smp_flush_tlb_mm':
  arch/m32r/kernel/smp.c:283:20: error: subscripted value is neither array nor pointer nor vector
    mmc = &mm->context[cpu_id];
                      ^
  arch/m32r/kernel/smp.c: In function 'smp_flush_tlb_page':
  arch/m32r/kernel/smp.c:353:20: error: subscripted value is neither array nor pointer nor vector
    mmc = &mm->context[cpu_id];
                      ^
  arch/m32r/kernel/smp.c: In function 'smp_invalidate_interrupt':
  arch/m32r/kernel/smp.c:479:41: error: subscripted value is neither array nor pointer nor vector
    unsigned long *mmc = &flush_mm->context[cpu_id];

It turned out that CONFIG_SMP was defined but CONFIG_MMU was not
defined.  But arch/m32r/include/asm/mmu.h only defines mm_context_t as
an array when both CONFIG_SMP and CONFIG_MMU are defined.  And
arch/m32r/kernel/smp.c is always using context as an array.  So without
MMU SMP can not work.
Signed-off-by: NSudip Mukherjee <sudip@vectorindia.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      af1ddcb5
  7. 09 1月, 2016 1 次提交
  9. 08 4月, 2014 1 次提交
  11. 24 1月, 2014 1 次提交
  13. 15 11月, 2013 1 次提交
  15. 13 9月, 2013 1 次提交
  17. 05 7月, 2013 1 次提交
  19. 17 4月, 2013 1 次提交
  21. 08 4月, 2013 1 次提交
  23. 13 3月, 2013 1 次提交
  25. 28 2月, 2013 1 次提交
  27. 14 2月, 2013 1 次提交
    • A
      burying unused conditionals · d64008a8
      由 Al Viro 提交于 
      __ARCH_WANT_SYS_RT_SIGACTION,
__ARCH_WANT_SYS_RT_SIGSUSPEND,
__ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND,
__ARCH_WANT_COMPAT_SYS_SCHED_RR_GET_INTERVAL - not used anymore
CONFIG_GENERIC_{SIGALTSTACK,COMPAT_RT_SIG{ACTION,QUEUEINFO,PENDING,PROCMASK}} -
can be assumed always set.
      d64008a8
  29. 04 2月, 2013 1 次提交
  31. 20 12月, 2012 1 次提交
  33. 01 11月, 2012 1 次提交
  35. 09 10月, 2012 1 次提交
  37. 28 9月, 2012 1 次提交
    • D
      Make most arch asm/module.h files use asm-generic/module.h · 786d35d4
      由 David Howells 提交于 
      Use the mapping of Elf_[SPE]hdr, Elf_Addr, Elf_Sym, Elf_Dyn, Elf_Rel/Rela,
ELF_R_TYPE() and ELF_R_SYM() to either the 32-bit version or the 64-bit version
into asm-generic/module.h for all arches bar MIPS.

Also, use the generic definition mod_arch_specific where possible.

To this end, I've defined three new config bools:

 (*) HAVE_MOD_ARCH_SPECIFIC

     Arches define this if they don't want to use the empty generic
     mod_arch_specific struct.

 (*) MODULES_USE_ELF_RELA

     Arches define this if their modules can contain RELA records.  This causes
     the Elf_Rela mapping to be emitted and allows apply_relocate_add() to be
     defined by the arch rather than have the core emit an error message.

 (*) MODULES_USE_ELF_REL

     Arches define this if their modules can contain REL records.  This causes
     the Elf_Rel mapping to be emitted and allows apply_relocate() to be
     defined by the arch rather than have the core emit an error message.

Note that it is possible to allow both REL and RELA records: m68k and mips are
two arches that do this.

With this, some arch asm/module.h files can be deleted entirely and replaced
with a generic-y marker in the arch Kbuild file.

Additionally, I have removed the bits from m32r and score that handle the
unsupported type of relocation record as that's now handled centrally.
Signed-off-by: NDavid Howells <dhowells@redhat.com>
Acked-by: NSam Ravnborg <sam@ravnborg.org>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
      786d35d4
  39. 31 7月, 2012 1 次提交
  41. 21 5月, 2012 1 次提交
  43. 05 5月, 2012 2 次提交
  45. 01 11月, 2011 1 次提交
  47. 18 10月, 2011 1 次提交
  49. 06 7月, 2011 1 次提交
    • F
      m32r: Use generic PREEMPT config · dab16ae1
      由 Frederic Weisbecker 提交于 
      Use the generic preempt config definition in m32r instead of
using a custom one.

This also makes it handle the new CONFIG_PREEMPT_COUNT that
need to be selected by CONFIG_PREEMPT.

Without that it breaks

  kernel/sched.c: In function 'preempt_schedule':
  kernel/sched.c:4364: error: implicit declaration of function 'add_preempt_count_notrace'
  kernel/sched.c:4366: error: implicit declaration of function 'sub_preempt_count_notrace'
Reported-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Hirokazu Takata <takata@linux-m32r.org>
      dab16ae1
  51. 27 5月, 2011 1 次提交
  53. 30 3月, 2011 1 次提交
  55. 25 3月, 2011 1 次提交
  57. 24 3月, 2011 1 次提交
  59. 21 1月, 2011 1 次提交
  61. 18 10月, 2010 1 次提交
  63. 20 9月, 2010 1 次提交
  65. 27 7月, 2010 1 次提交
  67. 04 11月, 2009 1 次提交
  69. 22 9月, 2009 1 次提交
  71. 13 12月, 2008 1 次提交
    • R
      cpumask: centralize cpu_online_map and cpu_possible_map · 98a79d6a
      由 Rusty Russell 提交于 
      Impact: cleanup

Each SMP arch defines these themselves.  Move them to a central
location.

Twists:
1) Some archs (m32, parisc, s390) set possible_map to all 1, so we add a
   CONFIG_INIT_ALL_POSSIBLE for this rather than break them.

2) mips and sparc32 '#define cpu_possible_map phys_cpu_present_map'.
   Those archs simply have phys_cpu_present_map replaced everywhere.

3) Alpha defined cpu_possible_map to cpu_present_map; this is tricky
   so I just manipulate them both in sync.

4) IA64, cris and m32r have gratuitous 'extern cpumask_t cpu_possible_map'
   declarations.
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Reviewed-by: NGrant Grundler <grundler@parisc-linux.org>
Tested-by: NTony Luck <tony.luck@intel.com>
Acked-by: NIngo Molnar <mingo@elte.hu>
Cc: Mike Travis <travis@sgi.com>
Cc: ink@jurassic.park.msu.ru
Cc: rmk@arm.linux.org.uk
Cc: starvik@axis.com
Cc: tony.luck@intel.com
Cc: takata@linux-m32r.org
Cc: ralf@linux-mips.org
Cc: grundler@parisc-linux.org
Cc: paulus@samba.org
Cc: schwidefsky@de.ibm.com
Cc: lethal@linux-sh.org
Cc: wli@holomorphy.com
Cc: davem@davemloft.net
Cc: jdike@addtoit.com
Cc: mingo@redhat.com
      98a79d6a
  73. 11 11月, 2008 1 次提交
  75. 20 10月, 2008 1 次提交
    • M
      container freezer: implement freezer cgroup subsystem · dc52ddc0
      由 Matt Helsley 提交于 
      This patch implements a new freezer subsystem in the control groups
framework.  It provides a way to stop and resume execution of all tasks in
a cgroup by writing in the cgroup filesystem.

The freezer subsystem in the container filesystem defines a file named
freezer.state.  Writing "FROZEN" to the state file will freeze all tasks
in the cgroup.  Subsequently writing "RUNNING" will unfreeze the tasks in
the cgroup.  Reading will return the current state.

* Examples of usage :

   # mkdir /containers/freezer
   # mount -t cgroup -ofreezer freezer  /containers
   # mkdir /containers/0
   # echo $some_pid > /containers/0/tasks

to get status of the freezer subsystem :

   # cat /containers/0/freezer.state
   RUNNING

to freeze all tasks in the container :

   # echo FROZEN > /containers/0/freezer.state
   # cat /containers/0/freezer.state
   FREEZING
   # cat /containers/0/freezer.state
   FROZEN

to unfreeze all tasks in the container :

   # echo RUNNING > /containers/0/freezer.state
   # cat /containers/0/freezer.state
   RUNNING

This is the basic mechanism which should do the right thing for user space
task in a simple scenario.

It's important to note that freezing can be incomplete.  In that case we
return EBUSY.  This means that some tasks in the cgroup are busy doing
something that prevents us from completely freezing the cgroup at this
time.  After EBUSY, the cgroup will remain partially frozen -- reflected
by freezer.state reporting "FREEZING" when read.  The state will remain
"FREEZING" until one of these things happens:

	1) Userspace cancels the freezing operation by writing "RUNNING" to
		the freezer.state file
	2) Userspace retries the freezing operation by writing "FROZEN" to
		the freezer.state file (writing "FREEZING" is not legal
		and returns EIO)
	3) The tasks that blocked the cgroup from entering the "FROZEN"
		state disappear from the cgroup's set of tasks.

[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: export thaw_process]
Signed-off-by: NCedric Le Goater <clg@fr.ibm.com>
Signed-off-by: NMatt Helsley <matthltc@us.ibm.com>
Acked-by: NSerge E. Hallyn <serue@us.ibm.com>
Tested-by: NMatt Helsley <matthltc@us.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      dc52ddc0
  77. 27 9月, 2008 1 次提交