From: Christoph Hellwig Date: Fri, 27 Mar 2026 06:16:37 +0000 (+0100) Subject: xor: move to lib/raid/ X-Git-Tag: ceph-for-7.1-rc4~216^2~52 X-Git-Url: http://git-server-git.apps.pok.os.sepia.ceph.com/?a=commitdiff_plain;h=9e229025e2474115c151f08bdbdd3d8d5f159af3;p=ceph-client.git xor: move to lib/raid/ Move the RAID XOR code to lib/raid/ as it has nothing to do with the crypto API. Link: https://lkml.kernel.org/r/20260327061704.3707577-6-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Eric Biggers Tested-by: Eric Biggers Cc: Albert Ou Cc: Alexander Gordeev Cc: Alexandre Ghiti Cc: Andreas Larsson Cc: Anton Ivanov Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: "Borislav Petkov (AMD)" Cc: Catalin Marinas Cc: Chris Mason Cc: Christian Borntraeger Cc: Dan Williams Cc: David S. Miller Cc: David Sterba Cc: Heiko Carstens Cc: Herbert Xu Cc: "H. Peter Anvin" Cc: Huacai Chen Cc: Ingo Molnar Cc: Jason A. Donenfeld Cc: Johannes Berg Cc: Li Nan Cc: Madhavan Srinivasan Cc: Magnus Lindholm Cc: Matt Turner Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Palmer Dabbelt Cc: Richard Henderson Cc: Richard Weinberger Cc: Russell King Cc: Song Liu Cc: Sven Schnelle Cc: Ted Ts'o Cc: Vasily Gorbik Cc: WANG Xuerui Cc: Will Deacon Signed-off-by: Andrew Morton --- diff --git a/crypto/Kconfig b/crypto/Kconfig index b4bb85e8e226..97d73136a0b4 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -2,8 +2,6 @@ # # Generic algorithms support # -config XOR_BLOCKS - tristate # # async_tx api: hardware offloaded memory transfer/transform support diff --git a/crypto/Makefile b/crypto/Makefile index 04e269117589..795c2eea51fe 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -196,7 +196,6 @@ obj-$(CONFIG_CRYPTO_ECRDSA) += ecrdsa_generic.o # # generic algorithms and the async_tx api # -obj-$(CONFIG_XOR_BLOCKS) += xor.o obj-$(CONFIG_ASYNC_CORE) += async_tx/ obj-$(CONFIG_ASYMMETRIC_KEY_TYPE) += asymmetric_keys/ crypto_simd-y := simd.o diff --git a/crypto/xor.c b/crypto/xor.c deleted file mode 100644 index df530ddc9f06..000000000000 --- a/crypto/xor.c +++ /dev/null @@ -1,176 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * xor.c : Multiple Devices driver for Linux - * - * Copyright (C) 1996, 1997, 1998, 1999, 2000, - * Ingo Molnar, Matti Aarnio, Jakub Jelinek, Richard Henderson. - * - * Dispatch optimized RAID-5 checksumming functions. - */ - -#define BH_TRACE 0 -#include -#include -#include -#include -#include -#include - -#ifndef XOR_SELECT_TEMPLATE -#define XOR_SELECT_TEMPLATE(x) (x) -#endif - -/* The xor routines to use. */ -static struct xor_block_template *active_template; - -void -xor_blocks(unsigned int src_count, unsigned int bytes, void *dest, void **srcs) -{ - unsigned long *p1, *p2, *p3, *p4; - - WARN_ON_ONCE(!in_task() || irqs_disabled() || softirq_count()); - - p1 = (unsigned long *) srcs[0]; - if (src_count == 1) { - active_template->do_2(bytes, dest, p1); - return; - } - - p2 = (unsigned long *) srcs[1]; - if (src_count == 2) { - active_template->do_3(bytes, dest, p1, p2); - return; - } - - p3 = (unsigned long *) srcs[2]; - if (src_count == 3) { - active_template->do_4(bytes, dest, p1, p2, p3); - return; - } - - p4 = (unsigned long *) srcs[3]; - active_template->do_5(bytes, dest, p1, p2, p3, p4); -} -EXPORT_SYMBOL(xor_blocks); - -/* Set of all registered templates. */ -static struct xor_block_template *__initdata template_list; - -#ifndef MODULE -static void __init do_xor_register(struct xor_block_template *tmpl) -{ - tmpl->next = template_list; - template_list = tmpl; -} - -static int __init register_xor_blocks(void) -{ - active_template = XOR_SELECT_TEMPLATE(NULL); - - if (!active_template) { -#define xor_speed do_xor_register - // register all the templates and pick the first as the default - XOR_TRY_TEMPLATES; -#undef xor_speed - active_template = template_list; - } - return 0; -} -#endif - -#define BENCH_SIZE 4096 -#define REPS 800U - -static void __init -do_xor_speed(struct xor_block_template *tmpl, void *b1, void *b2) -{ - int speed; - unsigned long reps; - ktime_t min, start, t0; - - tmpl->next = template_list; - template_list = tmpl; - - preempt_disable(); - - reps = 0; - t0 = ktime_get(); - /* delay start until time has advanced */ - while ((start = ktime_get()) == t0) - cpu_relax(); - do { - mb(); /* prevent loop optimization */ - tmpl->do_2(BENCH_SIZE, b1, b2); - mb(); - } while (reps++ < REPS || (t0 = ktime_get()) == start); - min = ktime_sub(t0, start); - - preempt_enable(); - - // bytes/ns == GB/s, multiply by 1000 to get MB/s [not MiB/s] - speed = (1000 * reps * BENCH_SIZE) / (unsigned int)ktime_to_ns(min); - tmpl->speed = speed; - - pr_info(" %-16s: %5d MB/sec\n", tmpl->name, speed); -} - -static int __init -calibrate_xor_blocks(void) -{ - void *b1, *b2; - struct xor_block_template *f, *fastest; - - fastest = XOR_SELECT_TEMPLATE(NULL); - - if (fastest) { - printk(KERN_INFO "xor: automatically using best " - "checksumming function %-10s\n", - fastest->name); - goto out; - } - - b1 = (void *) __get_free_pages(GFP_KERNEL, 2); - if (!b1) { - printk(KERN_WARNING "xor: Yikes! No memory available.\n"); - return -ENOMEM; - } - b2 = b1 + 2*PAGE_SIZE + BENCH_SIZE; - - /* - * If this arch/cpu has a short-circuited selection, don't loop through - * all the possible functions, just test the best one - */ - -#define xor_speed(templ) do_xor_speed((templ), b1, b2) - - printk(KERN_INFO "xor: measuring software checksum speed\n"); - template_list = NULL; - XOR_TRY_TEMPLATES; - fastest = template_list; - for (f = fastest; f; f = f->next) - if (f->speed > fastest->speed) - fastest = f; - - pr_info("xor: using function: %s (%d MB/sec)\n", - fastest->name, fastest->speed); - -#undef xor_speed - - free_pages((unsigned long)b1, 2); -out: - active_template = fastest; - return 0; -} - -static __exit void xor_exit(void) { } - -MODULE_DESCRIPTION("RAID-5 checksumming functions"); -MODULE_LICENSE("GPL"); - -#ifndef MODULE -/* when built-in xor.o must initialize before drivers/md/md.o */ -core_initcall(register_xor_blocks); -#endif - -module_init(calibrate_xor_blocks); -module_exit(xor_exit); diff --git a/lib/Kconfig b/lib/Kconfig index 2b0c56a53a2a..00a9509636c1 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -138,6 +138,7 @@ config TRACE_MMIO_ACCESS source "lib/crc/Kconfig" source "lib/crypto/Kconfig" +source "lib/raid/Kconfig" config XXHASH tristate diff --git a/lib/Makefile b/lib/Makefile index 60c9c9e79375..9ea149e618d2 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -120,7 +120,7 @@ endif obj-$(CONFIG_DEBUG_INFO_REDUCED) += debug_info.o CFLAGS_debug_info.o += $(call cc-option, -femit-struct-debug-detailed=any) -obj-y += math/ crc/ crypto/ tests/ vdso/ +obj-y += math/ crc/ crypto/ tests/ vdso/ raid/ obj-$(CONFIG_GENERIC_IOMAP) += iomap.o obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o diff --git a/lib/raid/Kconfig b/lib/raid/Kconfig new file mode 100644 index 000000000000..01b73a1c303f --- /dev/null +++ b/lib/raid/Kconfig @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 + +config XOR_BLOCKS + tristate diff --git a/lib/raid/Makefile b/lib/raid/Makefile new file mode 100644 index 000000000000..3540fe846dc4 --- /dev/null +++ b/lib/raid/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y += xor/ diff --git a/lib/raid/xor/Makefile b/lib/raid/xor/Makefile new file mode 100644 index 000000000000..7bca0ce8e90a --- /dev/null +++ b/lib/raid/xor/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_XOR_BLOCKS) += xor.o + +xor-y += xor-core.o diff --git a/lib/raid/xor/xor-core.c b/lib/raid/xor/xor-core.c new file mode 100644 index 000000000000..df530ddc9f06 --- /dev/null +++ b/lib/raid/xor/xor-core.c @@ -0,0 +1,176 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * xor.c : Multiple Devices driver for Linux + * + * Copyright (C) 1996, 1997, 1998, 1999, 2000, + * Ingo Molnar, Matti Aarnio, Jakub Jelinek, Richard Henderson. + * + * Dispatch optimized RAID-5 checksumming functions. + */ + +#define BH_TRACE 0 +#include +#include +#include +#include +#include +#include + +#ifndef XOR_SELECT_TEMPLATE +#define XOR_SELECT_TEMPLATE(x) (x) +#endif + +/* The xor routines to use. */ +static struct xor_block_template *active_template; + +void +xor_blocks(unsigned int src_count, unsigned int bytes, void *dest, void **srcs) +{ + unsigned long *p1, *p2, *p3, *p4; + + WARN_ON_ONCE(!in_task() || irqs_disabled() || softirq_count()); + + p1 = (unsigned long *) srcs[0]; + if (src_count == 1) { + active_template->do_2(bytes, dest, p1); + return; + } + + p2 = (unsigned long *) srcs[1]; + if (src_count == 2) { + active_template->do_3(bytes, dest, p1, p2); + return; + } + + p3 = (unsigned long *) srcs[2]; + if (src_count == 3) { + active_template->do_4(bytes, dest, p1, p2, p3); + return; + } + + p4 = (unsigned long *) srcs[3]; + active_template->do_5(bytes, dest, p1, p2, p3, p4); +} +EXPORT_SYMBOL(xor_blocks); + +/* Set of all registered templates. */ +static struct xor_block_template *__initdata template_list; + +#ifndef MODULE +static void __init do_xor_register(struct xor_block_template *tmpl) +{ + tmpl->next = template_list; + template_list = tmpl; +} + +static int __init register_xor_blocks(void) +{ + active_template = XOR_SELECT_TEMPLATE(NULL); + + if (!active_template) { +#define xor_speed do_xor_register + // register all the templates and pick the first as the default + XOR_TRY_TEMPLATES; +#undef xor_speed + active_template = template_list; + } + return 0; +} +#endif + +#define BENCH_SIZE 4096 +#define REPS 800U + +static void __init +do_xor_speed(struct xor_block_template *tmpl, void *b1, void *b2) +{ + int speed; + unsigned long reps; + ktime_t min, start, t0; + + tmpl->next = template_list; + template_list = tmpl; + + preempt_disable(); + + reps = 0; + t0 = ktime_get(); + /* delay start until time has advanced */ + while ((start = ktime_get()) == t0) + cpu_relax(); + do { + mb(); /* prevent loop optimization */ + tmpl->do_2(BENCH_SIZE, b1, b2); + mb(); + } while (reps++ < REPS || (t0 = ktime_get()) == start); + min = ktime_sub(t0, start); + + preempt_enable(); + + // bytes/ns == GB/s, multiply by 1000 to get MB/s [not MiB/s] + speed = (1000 * reps * BENCH_SIZE) / (unsigned int)ktime_to_ns(min); + tmpl->speed = speed; + + pr_info(" %-16s: %5d MB/sec\n", tmpl->name, speed); +} + +static int __init +calibrate_xor_blocks(void) +{ + void *b1, *b2; + struct xor_block_template *f, *fastest; + + fastest = XOR_SELECT_TEMPLATE(NULL); + + if (fastest) { + printk(KERN_INFO "xor: automatically using best " + "checksumming function %-10s\n", + fastest->name); + goto out; + } + + b1 = (void *) __get_free_pages(GFP_KERNEL, 2); + if (!b1) { + printk(KERN_WARNING "xor: Yikes! No memory available.\n"); + return -ENOMEM; + } + b2 = b1 + 2*PAGE_SIZE + BENCH_SIZE; + + /* + * If this arch/cpu has a short-circuited selection, don't loop through + * all the possible functions, just test the best one + */ + +#define xor_speed(templ) do_xor_speed((templ), b1, b2) + + printk(KERN_INFO "xor: measuring software checksum speed\n"); + template_list = NULL; + XOR_TRY_TEMPLATES; + fastest = template_list; + for (f = fastest; f; f = f->next) + if (f->speed > fastest->speed) + fastest = f; + + pr_info("xor: using function: %s (%d MB/sec)\n", + fastest->name, fastest->speed); + +#undef xor_speed + + free_pages((unsigned long)b1, 2); +out: + active_template = fastest; + return 0; +} + +static __exit void xor_exit(void) { } + +MODULE_DESCRIPTION("RAID-5 checksumming functions"); +MODULE_LICENSE("GPL"); + +#ifndef MODULE +/* when built-in xor.o must initialize before drivers/md/md.o */ +core_initcall(register_xor_blocks); +#endif + +module_init(calibrate_xor_blocks); +module_exit(xor_exit);