linux.git/arch/alpha/Kconfig, branch master

atomic64: no need for CONFIG_ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE

2016-10-08T01:46:30+00:00

This came to light when implementing native 64-bit atomics for ARCv2. The atomic64 self-test code uses CONFIG_ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE to check whether atomic64_dec_if_positive() is available. It seems it was needed when not every arch defined it. However as of current code the Kconfig option seems needless - for CONFIG_GENERIC_ATOMIC64 it is auto-enabled in lib/Kconfig and a generic definition of API is present lib/atomic64.c - arches with native 64-bit atomics select it in arch/*/Kconfig and define the API in their headers So I see no point in keeping the Kconfig option Compile tested for: - blackfin (CONFIG_GENERIC_ATOMIC64) - x86 (!CONFIG_GENERIC_ATOMIC64) - ia64 Link: http://lkml.kernel.org/r/1473703083-8625-3-git-send-email-vgupta@synopsys.com Signed-off-by: Vineet Gupta Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Russell King Cc: Catalin Marinas Cc: Will Deacon Cc: Ralf Baechle Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: "David S. Miller" Cc: Chris Metcalf Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Vineet Gupta Cc: Zhaoxiu Zeng Cc: Linus Walleij Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Herbert Xu Cc: Ming Lin Cc: Arnd Bergmann Cc: Geert Uytterhoeven Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Andi Kleen Cc: Boqun Feng Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

lib/GCD.c: use binary GCD algorithm instead of Euclidean

2016-05-21T00:58:30+00:00

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 #include #include #include #include #include #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 Signed-off-by: George Spelvin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

alpha: remove ARCH_WANT_OPTIONAL_GPIOLIB

2016-04-26T11:58:25+00:00

This symbols is not needed to get access to selecting the GPIOLIB anymore: any arch can select GPIOLIB. Cc: Michael Büsch Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: linux-alpha@vger.kernel.org Acked-by: Matt Turner Signed-off-by: Linus Walleij

dma-mapping: always provide the dma_map_ops based implementation

2016-01-21T01:09:18+00:00

Move the generic implementation to now that all architectures support it and remove the HAVE_DMA_ATTR Kconfig symbol now that everyone supports them. [valentinrothberg@gmail.com: remove leftovers in Kconfig] Signed-off-by: Christoph Hellwig Cc: "David S. Miller" Cc: Aurelien Jacquiot Cc: Chris Metcalf Cc: David Howells Cc: Geert Uytterhoeven Cc: Haavard Skinnemoen Cc: Hans-Christian Egtvedt Cc: Helge Deller Cc: James Hogan Cc: Jesper Nilsson Cc: Koichi Yasutake Cc: Ley Foon Tan Cc: Mark Salter Cc: Mikael Starvik Cc: Steven Miao Cc: Vineet Gupta Cc: Christian Borntraeger Cc: Joerg Roedel Cc: Sebastian Ott Signed-off-by: Valentin Rothberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

alpha: select CONFIG_ARCH_USE_CMPXCHG_LOCKREF.

2015-08-31T01:01:16+00:00

On Alpha we have spinlocks that are 32b in size and an efficient cmpxchg64 implementation, so we qualify to make use of cmpxchg backed lockrefs. Select the ARCH_USE_CMPXCHG_LOCKREF Kconfig symbol and provide a trivial implementation of arch_spin_value_unlocked to satisfy the lockref code. Using Linus' simple testcase from http://article.gmane.org/gmane.linux.file-systems/77466 on a dual CPU ES47 system I see around an 8% gain: N Min Max Median Avg Stddev x 30 6194580 6295654 6272504 6272514 17694.232 + 30 6731164 6786334 6767982 6764274 13738.863 Difference at 95.0% confidence 491760 +/- 8188.17 7.83992% +/- 0.130541% (Student's t, pooled s = 15840.5) Signed-off-by: Matt Turner

alpha: expose number of page table levels on Kconfig level

2015-04-14T23:49:01+00:00

I've implemented accounting for pmd page tables as we have for pte (see mm->nr_ptes). It's requires a new counter in mm_struct: mm->nr_pmds. But the feature doesn't make any sense if an architecture has PMD level folded and it would be nice get rid of the counter in this case. The problem is that we cannot use __PAGETABLE_PMD_FOLDED in due to circular dependencies: -> -> In most cases wants to get definition of struct page and struct vm_area_struct. I've tried to split mm_struct into separate header file to be able to user there. But it doesn't fly on some architectures, like ARM: it wants mm_struct to implement tlb flushing. I don't see how to fix it without massive de-inlining or coverting a lot for inline functions to macros. This is other approach: expose number of page tables in use via Kconfig and use it in instead of __PAGETABLE_PMD_FOLDED from . This patch (of 19): We would want to use number of page table level to define mm_struct. Let's expose it as CONFIG_PGTABLE_LEVELS. Signed-off-by: Kirill A. Shutemov Acked-by: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Tested-by: Guenter Roeck Cc: "David S. Miller" Cc: "H. Peter Anvin" Cc: "James E.J. Bottomley" Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Chris Metcalf Cc: David Howells Cc: Fenghua Yu Cc: Geert Uytterhoeven Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Jeff Dike Cc: Kirill A. Shutemov Cc: Koichi Yasutake Cc: Martin Schwidefsky Cc: Michael Ellerman Cc: Paul Mackerras Cc: Ralf Baechle Cc: Richard Weinberger Cc: Russell King Cc: Thomas Gleixner Cc: Tony Luck Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

Merge git://git.infradead.org/users/eparis/audit

2014-04-12T19:38:53+00:00

Pull audit updates from Eric Paris. * git://git.infradead.org/users/eparis/audit: (28 commits) AUDIT: make audit_is_compat depend on CONFIG_AUDIT_COMPAT_GENERIC audit: renumber AUDIT_FEATURE_CHANGE into the 1300 range audit: do not cast audit_rule_data pointers pointlesly AUDIT: Allow login in non-init namespaces audit: define audit_is_compat in kernel internal header kernel: Use RCU_INIT_POINTER(x, NULL) in audit.c sched: declare pid_alive as inline audit: use uapi/linux/audit.h for AUDIT_ARCH declarations syscall_get_arch: remove useless function arguments audit: remove stray newline from audit_log_execve_info() audit_panic() call audit: remove stray newlines from audit_log_lost messages audit: include subject in login records audit: remove superfluous new- prefix in AUDIT_LOGIN messages audit: allow user processes to log from another PID namespace audit: anchor all pid references in the initial pid namespace audit: convert PPIDs to the inital PID namespace. pid: get pid_t ppid of task in init_pid_ns audit: rename the misleading audit_get_context() to audit_take_context() audit: Add generic compat syscall support audit: Add CONFIG_HAVE_ARCH_AUDITSYSCALL ...

audit: Add CONFIG_HAVE_ARCH_AUDITSYSCALL

2014-03-20T14:11:10+00:00

Currently AUDITSYSCALL has a long list of architecture depencency: depends on AUDIT && (X86 || PARISC || PPC || S390 || IA64 || UML || SPARC64 || SUPERH || (ARM && AEABI && !OABI_COMPAT) || ALPHA) The purpose of this patch is to replace it with HAVE_ARCH_AUDITSYSCALL for simplicity. Signed-off-by: AKASHI Takahiro Acked-by: Will Deacon (arm) Acked-by: Richard Guy Briggs (audit) Acked-by: Matt Turner (alpha) Acked-by: Michael Ellerman (powerpc) Signed-off-by: Eric Paris

alpha: Enable system-call auditing support.

2014-03-20T14:11:09+00:00

Signed-off-by: Zhenglong.cai Signed-off-by: Matt Turner

alpha: Enable system-call auditing support.

2014-01-31T17:21:55+00:00

Signed-off-by: Zhenglong.cai Signed-off-by: Matt Turner