September 2024 - Linux-kselftest-mirror

[PATCH net-next v17 02/14] mm: move the page fragment allocator from page_alloc into its own file

by Yunsheng Lin

Inspired by [1], move the page fragment allocator from page_alloc into its own c file and header file, as we are about to make more change for it to replace another page_frag implementation in sock.c As this patchset is going to replace 'struct page_frag' with 'struct page_frag_cache' in sched.h, including page_frag_cache.h in sched.h has a compiler error caused by interdependence between mm_types.h and mm.h for asm-offsets.c, see [2]. So avoid the compiler error by moving 'struct page_frag_cache' to mm_types_task.h as suggested by Alexander, see [3]. 1. https://lore.kernel.org/all/20230411160902.4134381-3-dhowells@redhat.com/ 2. https://lore.kernel.org/all/15623dac-9358-4597-b3ee-3694a5956920@gmail.com/ 3. https://lore.kernel.org/all/CAKgT0UdH1yD=LSCXFJ=YM_aiA4OomD-2wXykO42bizaWMt… CC: David Howells <dhowells(a)redhat.com> CC: Alexander Duyck <alexander.duyck(a)gmail.com> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> Acked-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/gfp.h | 22 --- include/linux/mm_types.h | 18 --- include/linux/mm_types_task.h | 18 +++ include/linux/page_frag_cache.h | 31 ++++ include/linux/skbuff.h | 1 + mm/Makefile | 1 + mm/page_alloc.c | 136 ---------------- mm/page_frag_cache.c | 145 ++++++++++++++++++ .../selftests/mm/page_frag/page_frag_test.c | 2 +- 9 files changed, 197 insertions(+), 177 deletions(-) create mode 100644 include/linux/page_frag_cache.h create mode 100644 mm/page_frag_cache.c diff --git a/include/linux/gfp.h b/include/linux/gfp.h index f53f76e0b17e..01a49be7c98d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -371,28 +371,6 @@ __meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mas extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); -struct page_frag_cache; -void page_frag_cache_drain(struct page_frag_cache *nc); -extern void __page_frag_cache_drain(struct page *page, unsigned int count); -void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, - gfp_t gfp_mask, unsigned int align_mask); - -static inline void *page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align) -{ - WARN_ON_ONCE(!is_power_of_2(align)); - return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); -} - -static inline void *page_frag_alloc(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask) -{ - return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); -} - -extern void page_frag_free(void *addr); - #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 485424979254..843d75412105 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -521,9 +521,6 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); */ #define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page))) -#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) -#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) - /* * page_private can be used on tail pages. However, PagePrivate is only * checked by the VM on the head page. So page_private on the tail pages @@ -542,21 +539,6 @@ static inline void *folio_get_private(struct folio *folio) return folio->private; } -struct page_frag_cache { - void * va; -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - __u16 offset; - __u16 size; -#else - __u32 offset; -#endif - /* we maintain a pagecount bias, so that we dont dirty cache line - * containing page->_refcount every time we allocate a fragment. - */ - unsigned int pagecnt_bias; - bool pfmemalloc; -}; - typedef unsigned long vm_flags_t; /* diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index a2f6179b672b..cdc1e3696439 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -8,6 +8,7 @@ * (These are defined separately to decouple sched.h from mm_types.h as much as possible.) */ +#include <linux/align.h> #include <linux/types.h> #include <asm/page.h> @@ -46,6 +47,23 @@ struct page_frag { #endif }; +#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) +#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) +struct page_frag_cache { + void *va; +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + __u16 offset; + __u16 size; +#else + __u32 offset; +#endif + /* we maintain a pagecount bias, so that we dont dirty cache line + * containing page->_refcount every time we allocate a fragment. + */ + unsigned int pagecnt_bias; + bool pfmemalloc; +}; + /* Track pages that require TLB flushes */ struct tlbflush_unmap_batch { #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h new file mode 100644 index 000000000000..67ac8626ed9b --- /dev/null +++ b/include/linux/page_frag_cache.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_PAGE_FRAG_CACHE_H +#define _LINUX_PAGE_FRAG_CACHE_H + +#include <linux/log2.h> +#include <linux/mm_types_task.h> +#include <linux/types.h> + +void page_frag_cache_drain(struct page_frag_cache *nc); +void __page_frag_cache_drain(struct page *page, unsigned int count); +void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, + gfp_t gfp_mask, unsigned int align_mask); + +static inline void *page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align) +{ + WARN_ON_ONCE(!is_power_of_2(align)); + return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); +} + +static inline void *page_frag_alloc(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask) +{ + return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); +} + +void page_frag_free(void *addr); + +#endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cf8f6ce06742..7482997c719f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -31,6 +31,7 @@ #include <linux/in6.h> #include <linux/if_packet.h> #include <linux/llist.h> +#include <linux/page_frag_cache.h> #include <net/flow.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> diff --git a/mm/Makefile b/mm/Makefile index d2915f8c9dc0..e9d342fa8058 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -65,6 +65,7 @@ page-alloc-$(CONFIG_SHUFFLE_PAGE_ALLOCATOR) += shuffle.o memory-hotplug-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-y += page-alloc.o +obj-y += page_frag_cache.o obj-y += init-mm.o obj-y += memblock.o obj-y += $(memory-hotplug-y) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c565de8f48e9..d0e88aa6eb0d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4798,142 +4798,6 @@ void free_pages(unsigned long addr, unsigned int order) EXPORT_SYMBOL(free_pages); -/* - * Page Fragment: - * An arbitrary-length arbitrary-offset area of memory which resides - * within a 0 or higher order page. Multiple fragments within that page - * are individually refcounted, in the page's reference counter. - * - * The page_frag functions below provide a simple allocation framework for - * page fragments. This is used by the network stack and network device - * drivers to provide a backing region of memory for use as either an - * sk_buff->head, or to be used in the "frags" portion of skb_shared_info. - */ -static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, - gfp_t gfp_mask) -{ - struct page *page = NULL; - gfp_t gfp = gfp_mask; - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | - __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; - page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, - PAGE_FRAG_CACHE_MAX_ORDER); - nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; -#endif - if (unlikely(!page)) - page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); - - nc->va = page ? page_address(page) : NULL; - - return page; -} - -void page_frag_cache_drain(struct page_frag_cache *nc) -{ - if (!nc->va) - return; - - __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); - nc->va = NULL; -} -EXPORT_SYMBOL(page_frag_cache_drain); - -void __page_frag_cache_drain(struct page *page, unsigned int count) -{ - VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); - - if (page_ref_sub_and_test(page, count)) - free_unref_page(page, compound_order(page)); -} -EXPORT_SYMBOL(__page_frag_cache_drain); - -void *__page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align_mask) -{ - unsigned int size = PAGE_SIZE; - struct page *page; - int offset; - - if (unlikely(!nc->va)) { -refill: - page = __page_frag_cache_refill(nc, gfp_mask); - if (!page) - return NULL; - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - /* if size can vary use size else just use PAGE_SIZE */ - size = nc->size; -#endif - /* Even if we own the page, we do not use atomic_set(). - * This would break get_page_unless_zero() users. - */ - page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); - - /* reset page count bias and offset to start of new frag */ - nc->pfmemalloc = page_is_pfmemalloc(page); - nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; - nc->offset = size; - } - - offset = nc->offset - fragsz; - if (unlikely(offset < 0)) { - page = virt_to_page(nc->va); - - if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) - goto refill; - - if (unlikely(nc->pfmemalloc)) { - free_unref_page(page, compound_order(page)); - goto refill; - } - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - /* if size can vary use size else just use PAGE_SIZE */ - size = nc->size; -#endif - /* OK, page count is 0, we can safely set it */ - set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); - - /* reset page count bias and offset to start of new frag */ - nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; - offset = size - fragsz; - if (unlikely(offset < 0)) { - /* - * The caller is trying to allocate a fragment - * with fragsz > PAGE_SIZE but the cache isn't big - * enough to satisfy the request, this may - * happen in low memory conditions. - * We don't release the cache page because - * it could make memory pressure worse - * so we simply return NULL here. - */ - return NULL; - } - } - - nc->pagecnt_bias--; - offset &= align_mask; - nc->offset = offset; - - return nc->va + offset; -} -EXPORT_SYMBOL(__page_frag_alloc_align); - -/* - * Frees a page fragment allocated out of either a compound or order 0 page. - */ -void page_frag_free(void *addr) -{ - struct page *page = virt_to_head_page(addr); - - if (unlikely(put_page_testzero(page))) - free_unref_page(page, compound_order(page)); -} -EXPORT_SYMBOL(page_frag_free); - static void *make_alloc_exact(unsigned long addr, unsigned int order, size_t size) { diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c new file mode 100644 index 000000000000..609a485cd02a --- /dev/null +++ b/mm/page_frag_cache.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Page fragment allocator + * + * Page Fragment: + * An arbitrary-length arbitrary-offset area of memory which resides within a + * 0 or higher order page. Multiple fragments within that page are + * individually refcounted, in the page's reference counter. + * + * The page_frag functions provide a simple allocation framework for page + * fragments. This is used by the network stack and network device drivers to + * provide a backing region of memory for use as either an sk_buff->head, or to + * be used in the "frags" portion of skb_shared_info. + */ + +#include <linux/export.h> +#include <linux/gfp_types.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/page_frag_cache.h> +#include "internal.h" + +static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, + gfp_t gfp_mask) +{ + struct page *page = NULL; + gfp_t gfp = gfp_mask; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | + __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; + page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, + PAGE_FRAG_CACHE_MAX_ORDER); + nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; +#endif + if (unlikely(!page)) + page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); + + nc->va = page ? page_address(page) : NULL; + + return page; +} + +void page_frag_cache_drain(struct page_frag_cache *nc) +{ + if (!nc->va) + return; + + __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); + nc->va = NULL; +} +EXPORT_SYMBOL(page_frag_cache_drain); + +void __page_frag_cache_drain(struct page *page, unsigned int count) +{ + VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); + + if (page_ref_sub_and_test(page, count)) + free_unref_page(page, compound_order(page)); +} +EXPORT_SYMBOL(__page_frag_cache_drain); + +void *__page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align_mask) +{ + unsigned int size = PAGE_SIZE; + struct page *page; + int offset; + + if (unlikely(!nc->va)) { +refill: + page = __page_frag_cache_refill(nc, gfp_mask); + if (!page) + return NULL; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size = nc->size; +#endif + /* Even if we own the page, we do not use atomic_set(). + * This would break get_page_unless_zero() users. + */ + page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); + + /* reset page count bias and offset to start of new frag */ + nc->pfmemalloc = page_is_pfmemalloc(page); + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; + nc->offset = size; + } + + offset = nc->offset - fragsz; + if (unlikely(offset < 0)) { + page = virt_to_page(nc->va); + + if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) + goto refill; + + if (unlikely(nc->pfmemalloc)) { + free_unref_page(page, compound_order(page)); + goto refill; + } + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size = nc->size; +#endif + /* OK, page count is 0, we can safely set it */ + set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); + + /* reset page count bias and offset to start of new frag */ + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; + offset = size - fragsz; + if (unlikely(offset < 0)) { + /* + * The caller is trying to allocate a fragment + * with fragsz > PAGE_SIZE but the cache isn't big + * enough to satisfy the request, this may + * happen in low memory conditions. + * We don't release the cache page because + * it could make memory pressure worse + * so we simply return NULL here. + */ + return NULL; + } + } + + nc->pagecnt_bias--; + offset &= align_mask; + nc->offset = offset; + + return nc->va + offset; +} +EXPORT_SYMBOL(__page_frag_alloc_align); + +/* + * Frees a page fragment allocated out of either a compound or order 0 page. + */ +void page_frag_free(void *addr) +{ + struct page *page = virt_to_head_page(addr); + + if (unlikely(put_page_testzero(page))) + free_unref_page(page, compound_order(page)); +} +EXPORT_SYMBOL(page_frag_free); diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c index 6d6f31936b10..5395a36e4030 100644 --- a/tools/testing/selftests/mm/page_frag/page_frag_test.c +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -6,12 +6,12 @@ * Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> */ -#include <linux/mm.h> #include <linux/module.h> #include <linux/cpumask.h> #include <linux/completion.h> #include <linux/ptr_ring.h> #include <linux/kthread.h> +#include <linux/page_frag_cache.h> static struct ptr_ring ptr_ring; static int nr_objs = 512; -- 2.33.0

1 year, 3 months

2
1
0 0

[PATCH net-next v17 01/14] mm: page_frag: add a test module for page_frag

by Yunsheng Lin

The testing is done by ensuring that the fragment allocated from a frag_frag_cache instance is pushed into a ptr_ring instance in a kthread binded to a specified cpu, and a kthread binded to a specified cpu will pop the fragment from the ptr_ring and free the fragment. CC: Alexander Duyck <alexander.duyck(a)gmail.com> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> --- tools/testing/selftests/mm/Makefile | 3 + tools/testing/selftests/mm/page_frag/Makefile | 18 ++ .../selftests/mm/page_frag/page_frag_test.c | 170 +++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 8 + tools/testing/selftests/mm/test_page_frag.sh | 171 ++++++++++++++++++ 5 files changed, 370 insertions(+) create mode 100644 tools/testing/selftests/mm/page_frag/Makefile create mode 100644 tools/testing/selftests/mm/page_frag/page_frag_test.c create mode 100755 tools/testing/selftests/mm/test_page_frag.sh diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index cfad627e8d94..e98ec779b2aa 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -36,6 +36,8 @@ MAKEFLAGS += --no-builtin-rules CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm +TEST_GEN_MODS_DIR := page_frag + TEST_GEN_FILES = cow TEST_GEN_FILES += compaction_test TEST_GEN_FILES += gup_longterm @@ -125,6 +127,7 @@ TEST_FILES += test_hmm.sh TEST_FILES += va_high_addr_switch.sh TEST_FILES += charge_reserved_hugetlb.sh TEST_FILES += hugetlb_reparenting_test.sh +TEST_FILES += test_page_frag.sh # required by charge_reserved_hugetlb.sh TEST_FILES += write_hugetlb_memory.sh diff --git a/tools/testing/selftests/mm/page_frag/Makefile b/tools/testing/selftests/mm/page_frag/Makefile new file mode 100644 index 000000000000..58dda74d50a3 --- /dev/null +++ b/tools/testing/selftests/mm/page_frag/Makefile @@ -0,0 +1,18 @@ +PAGE_FRAG_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= $(abspath $(PAGE_FRAG_TEST_DIR)/../../../../..) + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +MODULES = page_frag_test.ko + +obj-m += page_frag_test.o + +all: + +$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) clean diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c new file mode 100644 index 000000000000..6d6f31936b10 --- /dev/null +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -0,0 +1,170 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Test module for page_frag cache + * + * Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> + */ + +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/cpumask.h> +#include <linux/completion.h> +#include <linux/ptr_ring.h> +#include <linux/kthread.h> + +static struct ptr_ring ptr_ring; +static int nr_objs = 512; +static atomic_t nthreads; +static struct completion wait; +static struct page_frag_cache test_nc; + +static int nr_test = 2000000; +module_param(nr_test, int, 0); +MODULE_PARM_DESC(nr_test, "number of iterations to test"); + +static bool test_align; +module_param(test_align, bool, 0); +MODULE_PARM_DESC(test_align, "use align API for testing"); + +static int test_alloc_len = 2048; +module_param(test_alloc_len, int, 0); +MODULE_PARM_DESC(test_alloc_len, "alloc len for testing"); + +static int test_push_cpu; +module_param(test_push_cpu, int, 0); +MODULE_PARM_DESC(test_push_cpu, "test cpu for pushing fragment"); + +static int test_pop_cpu; +module_param(test_pop_cpu, int, 0); +MODULE_PARM_DESC(test_pop_cpu, "test cpu for popping fragment"); + +static int page_frag_pop_thread(void *arg) +{ + struct ptr_ring *ring = arg; + int nr = nr_test; + + pr_info("page_frag pop test thread begins on cpu %d\n", + smp_processor_id()); + + while (nr > 0) { + void *obj = __ptr_ring_consume(ring); + + if (obj) { + nr--; + page_frag_free(obj); + } else { + cond_resched(); + } + } + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + pr_info("page_frag pop test thread exits on cpu %d\n", + smp_processor_id()); + + return 0; +} + +static int page_frag_push_thread(void *arg) +{ + struct ptr_ring *ring = arg; + int nr = nr_test; + + pr_info("page_frag push test thread begins on cpu %d\n", + smp_processor_id()); + + while (nr > 0) { + void *va; + int ret; + + if (test_align) { + va = page_frag_alloc_align(&test_nc, test_alloc_len, + GFP_KERNEL, SMP_CACHE_BYTES); + + WARN_ONCE((unsigned long)va & (SMP_CACHE_BYTES - 1), + "unaligned va returned\n"); + } else { + va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL); + } + + if (!va) + continue; + + ret = __ptr_ring_produce(ring, va); + if (ret) { + page_frag_free(va); + cond_resched(); + } else { + nr--; + } + } + + pr_info("page_frag push test thread exits on cpu %d\n", + smp_processor_id()); + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + return 0; +} + +static int __init page_frag_test_init(void) +{ + struct task_struct *tsk_push, *tsk_pop; + ktime_t start; + u64 duration; + int ret; + + test_nc.va = NULL; + atomic_set(&nthreads, 2); + init_completion(&wait); + + if (test_alloc_len > PAGE_SIZE || test_alloc_len <= 0 || + !cpu_active(test_push_cpu) || !cpu_active(test_pop_cpu)) + return -EINVAL; + + ret = ptr_ring_init(&ptr_ring, nr_objs, GFP_KERNEL); + if (ret) + return ret; + + tsk_push = kthread_create_on_cpu(page_frag_push_thread, &ptr_ring, + test_push_cpu, "page_frag_push"); + if (IS_ERR(tsk_push)) + return PTR_ERR(tsk_push); + + tsk_pop = kthread_create_on_cpu(page_frag_pop_thread, &ptr_ring, + test_pop_cpu, "page_frag_pop"); + if (IS_ERR(tsk_pop)) { + kthread_stop(tsk_push); + return PTR_ERR(tsk_pop); + } + + start = ktime_get(); + wake_up_process(tsk_push); + wake_up_process(tsk_pop); + + pr_info("waiting for test to complete\n"); + wait_for_completion(&wait); + + duration = (u64)ktime_us_delta(ktime_get(), start); + pr_info("%d of iterations for %s testing took: %lluus\n", nr_test, + test_align ? "aligned" : "non-aligned", duration); + + ptr_ring_cleanup(&ptr_ring, NULL); + page_frag_cache_drain(&test_nc); + + return -EAGAIN; +} + +static void __exit page_frag_test_exit(void) +{ +} + +module_init(page_frag_test_init); +module_exit(page_frag_test_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Yunsheng Lin <linyunsheng(a)huawei.com>"); +MODULE_DESCRIPTION("Test module for page_frag"); diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 36045edb10de..96fd470b9f51 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -75,6 +75,8 @@ separated by spaces: read-only VMAs - mdwe test prctl(PR_SET_MDWE, ...) +- page_frag + test handling of page fragment allocation and freeing example: ./run_vmtests.sh -t "hmm mmap ksm" EOF @@ -456,6 +458,12 @@ CATEGORY="mkdirty" run_test ./mkdirty CATEGORY="mdwe" run_test ./mdwe_test +CATEGORY="page_frag" run_test ./test_page_frag.sh smoke + +CATEGORY="page_frag" run_test ./test_page_frag.sh aligned + +CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned + echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix echo "1..${count_total}" | tap_output diff --git a/tools/testing/selftests/mm/test_page_frag.sh b/tools/testing/selftests/mm/test_page_frag.sh new file mode 100755 index 000000000000..d2b0734a90b5 --- /dev/null +++ b/tools/testing/selftests/mm/test_page_frag.sh @@ -0,0 +1,171 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> +# Copyright (C) 2018 Uladzislau Rezki (Sony) <urezki(a)gmail.com> +# +# This is a test script for the kernel test driver to test the +# correctness and performance of page_frag's implementation. +# Therefore it is just a kernel module loader. You can specify +# and pass different parameters in order to: +# a) analyse performance of page fragment allocations; +# b) stressing and stability check of page_frag subsystem. + +DRIVER="./page_frag/page_frag_test.ko" +CPU_LIST=$(grep -m 2 processor /proc/cpuinfo | cut -d ' ' -f 2) +TEST_CPU_0=$(echo $CPU_LIST | awk '{print $1}') + +if [ $(echo $CPU_LIST | wc -w) -gt 1 ]; then + TEST_CPU_1=$(echo $CPU_LIST | awk '{print $2}') + NR_TEST=100000000 +else + TEST_CPU_1=$TEST_CPU_0 + NR_TEST=1000000 +fi + +# 1 if fails +exitcode=1 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +# +# Static templates for testing of page_frag APIs. +# Also it is possible to pass any supported parameters manually. +# +SMOKE_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_1" +NONALIGNED_PARAM="$SMOKE_PARAM test_alloc_len=75 nr_test=$NR_TEST" +ALIGNED_PARAM="$NONALIGNED_PARAM test_align=1" + +check_test_requirements() +{ + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo "$0: Must be run as root" + exit $ksft_skip + fi + + if ! which insmod > /dev/null 2>&1; then + echo "$0: You need insmod installed" + exit $ksft_skip + fi + + if [ ! -f $DRIVER ]; then + echo "$0: You need to compile page_frag_test module" + exit $ksft_skip + fi +} + +run_nonaligned_check() +{ + echo "Run performance tests to evaluate how fast nonaligned alloc API is." + + insmod $DRIVER $NONALIGNED_PARAM > /dev/null 2>&1 + echo "Done." + echo "Ccheck the kernel ring buffer to see the summary." +} + +run_aligned_check() +{ + echo "Run performance tests to evaluate how fast aligned alloc API is." + + insmod $DRIVER $ALIGNED_PARAM > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +run_smoke_check() +{ + echo "Run smoke test." + + insmod $DRIVER $SMOKE_PARAM > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +usage() +{ + echo -n "Usage: $0 [ aligned ] | [ nonaligned ] | | [ smoke ] | " + echo "manual parameters" + echo + echo "Valid tests and parameters:" + echo + modinfo $DRIVER + echo + echo "Example usage:" + echo + echo "# Shows help message" + echo "$0" + echo + echo "# Smoke testing" + echo "$0 smoke" + echo + echo "# Performance testing for nonaligned alloc API" + echo "$0 nonaligned" + echo + echo "# Performance testing for aligned alloc API" + echo "$0 aligned" + echo + exit 0 +} + +function validate_passed_args() +{ + VALID_ARGS=`modinfo $DRIVER | awk '/parm:/ {print $2}' | sed 's/:.*//'` + + # + # Something has been passed, check it. + # + for passed_arg in $@; do + key=${passed_arg//=*/} + valid=0 + + for valid_arg in $VALID_ARGS; do + if [[ $key = $valid_arg ]]; then + valid=1 + break + fi + done + + if [[ $valid -ne 1 ]]; then + echo "Error: key is not correct: ${key}" + exit $exitcode + fi + done +} + +function run_manual_check() +{ + # + # Validate passed parameters. If there is wrong one, + # the script exists and does not execute further. + # + validate_passed_args $@ + + echo "Run the test with following parameters: $@" + insmod $DRIVER $@ > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +function run_test() +{ + if [ $# -eq 0 ]; then + usage + else + if [[ "$1" = "smoke" ]]; then + run_smoke_check + elif [[ "$1" = "nonaligned" ]]; then + run_nonaligned_check + elif [[ "$1" = "aligned" ]]; then + run_aligned_check + else + run_manual_check $@ + fi + fi +} + +check_test_requirements +run_test $@ + +exit 0 -- 2.33.0

1 year, 3 months

2
1
0 0

next: rcu_preempt self-detected stall on CPU - queued_spin_lock_slowpath

by Naresh Kamboju

The following kernel rcu info generated while running the test case selftests: memfd: run_fuse_test.sh on qemu-arm64 running Linux next-20240902. The qemu-arm64 did not recover. This build was created with kselftest merge configs. Anders bisected this to, # first bad commit: [5fb9c98e9d8ddf2abc645e2dcd9eb6703f77fdab] fuse: add support for no forget requests Crash log: ---------- [ 0.000000] Booting Linux on physical CPU 0x0000000000 [0x000f0510] [ 0.000000] Linux version 6.11.0-rc6-next-20240902 (tuxmake@tuxmake) (aarch64-linux-gnu-gcc (Debian 13.3.0-5) 13.3.0, GNU ld (GNU Binutils for Debian) 2.43) #1 SMP PREEMPT @1725295942 [ 0.000000] KASLR enabled [ 0.000000] random: crng init done [ 0.000000] Machine model: linux,dummy-virt .. # selftests: memfd: run_fuse_test.sh <3>[ 107.408167] rcu: INFO: rcu_preempt self-detected stall on CPU <3>[ 107.409195] rcu: 1-....: (5249 ticks this GP) idle=4d34/1/0x4000000000000000 softirq=10271/10271 fqs=2623 <3>[ 107.410438] rcu: (t=5250 jiffies g=20109 q=58 ncpus=2) <4>[ 107.411776] CPU: 1 UID: 0 PID: 386 Comm: fuse_mnt Not tainted 6.11.0-rc6-next-20240902 #1 <4>[ 107.412663] Hardware name: linux,dummy-virt (DT) <4>[ 107.413680] pstate: 03400009 (nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) <4>[ 107.414341] pc : queued_spin_lock_slowpath+0x5c/0x440 <4>[ 107.415481] lr : _raw_spin_lock+0x74/0x90 <4>[ 107.415974] sp : ffff800080993ad0 <4>[ 107.419229] x29: ffff800080993ad0 x28: 0000000000000008 x27: fff000000635b800 <4>[ 107.421148] x26: 0000000000000000 x25: 0000000000000000 x24: ffff800080993ba0 <4>[ 107.422099] x23: ffffa8c953aa02c8 x22: ffffa8c953aa02a0 x21: 0000000000000000 <4>[ 107.423060] x20: fff0000005088330 x19: fff0000005088330 x18: 0000000000000000 <4>[ 107.424145] x17: fff057375aeca000 x16: ffffa8c9a382f930 x15: 0000000000000000 <4>[ 107.425097] x14: 0000000000000000 x13: 00000000000000d0 x12: 0000000000000000 <4>[ 107.425990] x11: 0000000000000000 x10: fff00000ff7fb7b0 x9 : ffffa8c9a382f9a4 <4>[ 107.426955] x8 : ffff800080993a38 x7 : 0000000000000000 x6 : 0000000000000001 <4>[ 107.427836] x5 : ffffa8c9a490a000 x4 : ffffa8c9a490a5c0 x3 : 0000000000000000 <4>[ 107.428777] x2 : 0000000000000002 x1 : 0000000000000000 x0 : 0000000000000001 <4>[ 107.430091] Call trace: <4>[ 107.430421] queued_spin_lock_slowpath+0x5c/0x440 <4>[ 107.431226] _raw_spin_lock+0x74/0x90 <4>[ 107.431841] fuse_iget+0x1a0/0x2b8 [fuse] <4>[ 107.433439] fuse_fill_super_common+0x344/0x468 [fuse] <4>[ 107.434320] fuse_fill_super+0x6c/0xc8 [fuse] <4>[ 107.435044] get_tree_nodev+0x78/0xc8 <4>[ 107.435656] fuse_get_tree+0xc8/0x1a0 [fuse] <4>[ 107.436133] vfs_get_tree+0x30/0x100 <4>[ 107.436927] path_mount+0x3f4/0xa70 <4>[ 107.437515] __arm64_sys_mount+0x1e0/0x2a8 <4>[ 107.438148] invoke_syscall+0x50/0x120 <4>[ 107.438760] el0_svc_common.constprop.0+0x48/0xf0 <4>[ 107.439484] do_el0_svc+0x24/0x38 <4>[ 107.440251] el0_svc+0x3c/0x108 <4>[ 107.440574] el0t_64_sync_handler+0x120/0x130 <4>[ 107.440978] el0t_64_sync+0x190/0x198 <3>[ 170.451886] rcu: INFO: rcu_preempt self-detected stall on CPU <3>[ 170.452546] rcu: 1-....: (21001 ticks this GP) idle=4d34/1/0x4000000000000000 softirq=10271/10271 fqs=10494 <3>[ 170.453323] rcu: (t=21011 jiffies g=20109 q=83 ncpus=2) <4>[ 170.454283] CPU: 1 UID: 0 PID: 386 Comm: fuse_mnt Not tainted 6.11.0-rc6-next-20240902 #1 <4>[ 170.454966] Hardware name: linux,dummy-virt (DT) <4>[ 170.455736] pstate: 03400009 (nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) <4>[ 170.456697] pc : queued_spin_lock_slowpath+0x5c/0x440 <4>[ 170.457179] lr : _raw_spin_lock+0x74/0x90 boot Log links, -------- - https://storage.tuxsuite.com/public/linaro/lkft/tests/2lWV52ERJsLvYqFnGkWoP… - https://storage.tuxsuite.com/public/linaro/lkft/tests/2lWV52ERJsLvYqFnGkWoP… metadata: ---- git describe: next-20240902 git repo: https://gitlab.com/Linaro/lkft/mirrors/next/linux-next git sha: ecc768a84f0b8e631986f9ade3118fa37852fef0 kernel config: https://storage.tuxsuite.com/public/linaro/lkft/builds/2lWV3S20oiROqoJeQxul… build url: https://storage.tuxsuite.com/public/linaro/lkft/builds/2lWV3S20oiROqoJeQxul… toolchain: gcc-13 Steps to reproduce: --------- - https://storage.tuxsuite.com/public/linaro/lkft/tests/2lWV52ERJsLvYqFnGkWoP… - https://storage.tuxsuite.com/public/linaro/lkft/tests/2lWV52ERJsLvYqFnGkWoP… -- Linaro LKFT https://lkft.linaro.org

1 year, 3 months

3
2
0 0

[PATCH RESEND] selftests/futex: Order calls in futex_requeue

by Edward Liaw

Similar to fbf4dec70277 ("selftests/futex: Order calls to futex_lock_pi"), which fixed a flake in futex_lock_pi due to racing between the parent and child threads. The same issue can occur in the futex_requeue test, because it expects waiterfn to make progress to futex_wait before the parent starts to requeue. This is mitigated by the parent sleeping for WAKE_WAIT_US, but it still fails occasionally. This can be reproduced by adding a sleep in the waiterfn before futex_wait: TAP version 13 1..2 not ok 1 futex_requeue simple returned: 0 not ok 2 futex_requeue simple returned: 0 not ok 3 futex_requeue many returned: 0 not ok 4 futex_requeue many returned: 0 Instead, replace the sleep with barriers to make the sequencing explicit. Fixes: 7cb5dd8e2c8c ("selftests: futex: Add futex compare requeue test") Reviewed-by: Muhammad Usama Anjum <usama.anjum(a)collabora.com> Signed-off-by: Edward Liaw <edliaw(a)google.com> --- .../selftests/futex/functional/futex_requeue.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/futex/functional/futex_requeue.c b/tools/testing/selftests/futex/functional/futex_requeue.c index 51485be6eb2f..8f7d3e8bf32a 100644 --- a/tools/testing/selftests/futex/functional/futex_requeue.c +++ b/tools/testing/selftests/futex/functional/futex_requeue.c @@ -12,9 +12,9 @@ #define TEST_NAME "futex-requeue" #define timeout_ns 30000000 -#define WAKE_WAIT_US 10000 volatile futex_t *f1; +static pthread_barrier_t barrier; void usage(char *prog) { @@ -32,6 +32,8 @@ void *waiterfn(void *arg) to.tv_sec = 0; to.tv_nsec = timeout_ns; + pthread_barrier_wait(&barrier); + if (futex_wait(f1, *f1, &to, 0)) printf("waiter failed errno %d\n", errno); @@ -70,13 +72,15 @@ int main(int argc, char *argv[]) ksft_print_msg("%s: Test futex_requeue\n", basename(argv[0])); + pthread_barrier_init(&barrier, NULL, 2); /* * Requeue a waiter from f1 to f2, and wake f2. */ if (pthread_create(&waiter[0], NULL, waiterfn, NULL)) error("pthread_create failed\n", errno); - usleep(WAKE_WAIT_US); + pthread_barrier_wait(&barrier); + pthread_barrier_destroy(&barrier); info("Requeuing 1 futex from f1 to f2\n"); res = futex_cmp_requeue(f1, 0, &f2, 0, 1, 0); @@ -99,6 +103,7 @@ int main(int argc, char *argv[]) ksft_test_result_pass("futex_requeue simple succeeds\n"); } + pthread_barrier_init(&barrier, NULL, 11); /* * Create 10 waiters at f1. At futex_requeue, wake 3 and requeue 7. @@ -109,7 +114,8 @@ int main(int argc, char *argv[]) error("pthread_create failed\n", errno); } - usleep(WAKE_WAIT_US); + pthread_barrier_wait(&barrier); + pthread_barrier_destroy(&barrier); info("Waking 3 futexes at f1 and requeuing 7 futexes from f1 to f2\n"); res = futex_cmp_requeue(f1, 0, &f2, 3, 7, 0); -- 2.46.0.469.g59c65b2a67-goog

1 year, 3 months

2
1
0 0

[PATCH net-next v2] selftests: add selftest for UDP SO_PEEK_OFF support

by Jason Xing

From: Jason Xing <kernelxing(a)tencent.com> Add the SO_PEEK_OFF selftest for UDP. In this patch, I mainly do three things: 1. rename tcp_so_peek_off.c 2. adjust for UDP protocol 3. add selftests into it Suggested-by: Jon Maloy <jmaloy(a)redhat.com> Reviewed-by: Willem de Bruijn <willemb(a)google.com> Signed-off-by: Jason Xing <kernelxing(a)tencent.com> --- v2 Link: https://lore.kernel.org/all/20240901051821.94956-1-kerneljasonxing@gmail.co… 1. update .gitignore (Stanislav) 2. use connect() < 0 as the test statement (Willem) v1 Link: https://lore.kernel.org/all/9f4dd14d-fbe3-4c61-b04c-f0e6b8096d7b@redhat.com/ --- tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 2 +- .../{tcp_so_peek_off.c => sk_so_peek_off.c} | 91 +++++++++++-------- 3 files changed, 57 insertions(+), 37 deletions(-) rename tools/testing/selftests/net/{tcp_so_peek_off.c => sk_so_peek_off.c} (58%) diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 666ab7d9390b..923bf098e2eb 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -34,6 +34,7 @@ scm_pidfd scm_rights sk_bind_sendto_listen sk_connect_zero_addr +sk_so_peek_off socket so_incoming_cpu so_netns_cookie diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 1179e3261bef..d5029f978aa9 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -80,7 +80,7 @@ TEST_PROGS += io_uring_zerocopy_tx.sh TEST_GEN_FILES += bind_bhash TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr -TEST_GEN_PROGS += tcp_so_peek_off +TEST_GEN_PROGS += sk_so_peek_off TEST_PROGS += test_ingress_egress_chaining.sh TEST_GEN_PROGS += so_incoming_cpu TEST_PROGS += sctp_vrf.sh diff --git a/tools/testing/selftests/net/tcp_so_peek_off.c b/tools/testing/selftests/net/sk_so_peek_off.c similarity index 58% rename from tools/testing/selftests/net/tcp_so_peek_off.c rename to tools/testing/selftests/net/sk_so_peek_off.c index df8a39d9d3c3..d87dd8d8d491 100644 --- a/tools/testing/selftests/net/tcp_so_peek_off.c +++ b/tools/testing/selftests/net/sk_so_peek_off.c @@ -10,37 +10,41 @@ #include <arpa/inet.h> #include "../kselftest.h" -static char *afstr(int af) +static char *afstr(int af, int proto) { - return af == AF_INET ? "TCP/IPv4" : "TCP/IPv6"; + if (proto == IPPROTO_TCP) + return af == AF_INET ? "TCP/IPv4" : "TCP/IPv6"; + else + return af == AF_INET ? "UDP/IPv4" : "UDP/IPv6"; } -int tcp_peek_offset_probe(sa_family_t af) +int sk_peek_offset_probe(sa_family_t af, int proto) { + int type = (proto == IPPROTO_TCP ? SOCK_STREAM : SOCK_DGRAM); int optv = 0; int ret = 0; int s; - s = socket(af, SOCK_STREAM | SOCK_CLOEXEC, IPPROTO_TCP); + s = socket(af, type, proto); if (s < 0) { ksft_perror("Temporary TCP socket creation failed"); } else { if (!setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &optv, sizeof(int))) ret = 1; else - printf("%s does not support SO_PEEK_OFF\n", afstr(af)); + printf("%s does not support SO_PEEK_OFF\n", afstr(af, proto)); close(s); } return ret; } -static void tcp_peek_offset_set(int s, int offset) +static void sk_peek_offset_set(int s, int offset) { if (setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &offset, sizeof(offset))) ksft_perror("Failed to set SO_PEEK_OFF value\n"); } -static int tcp_peek_offset_get(int s) +static int sk_peek_offset_get(int s) { int offset; socklen_t len = sizeof(offset); @@ -50,8 +54,9 @@ static int tcp_peek_offset_get(int s) return offset; } -static int tcp_peek_offset_test(sa_family_t af) +static int sk_peek_offset_test(sa_family_t af, int proto) { + int type = (proto == IPPROTO_TCP ? SOCK_STREAM : SOCK_DGRAM); union { struct sockaddr sa; struct sockaddr_in a4; @@ -62,13 +67,13 @@ static int tcp_peek_offset_test(sa_family_t af) int recv_sock = 0; int offset = 0; ssize_t len; - char buf; + char buf[2]; memset(&a, 0, sizeof(a)); a.sa.sa_family = af; - s[0] = socket(af, SOCK_STREAM, IPPROTO_TCP); - s[1] = socket(af, SOCK_STREAM | SOCK_NONBLOCK, IPPROTO_TCP); + s[0] = recv_sock = socket(af, type, proto); + s[1] = socket(af, type, proto); if (s[0] < 0 || s[1] < 0) { ksft_perror("Temporary socket creation failed\n"); @@ -82,76 +87,78 @@ static int tcp_peek_offset_test(sa_family_t af) ksft_perror("Temporary socket getsockname() failed\n"); goto out; } - if (listen(s[0], 0) < 0) { + if (proto == IPPROTO_TCP && listen(s[0], 0) < 0) { ksft_perror("Temporary socket listen() failed\n"); goto out; } - if (connect(s[1], &a.sa, sizeof(a)) >= 0 || errno != EINPROGRESS) { + if (connect(s[1], &a.sa, sizeof(a)) < 0) { ksft_perror("Temporary socket connect() failed\n"); goto out; } - recv_sock = accept(s[0], NULL, NULL); - if (recv_sock <= 0) { - ksft_perror("Temporary socket accept() failed\n"); - goto out; + if (proto == IPPROTO_TCP) { + recv_sock = accept(s[0], NULL, NULL); + if (recv_sock <= 0) { + ksft_perror("Temporary socket accept() failed\n"); + goto out; + } } /* Some basic tests of getting/setting offset */ - offset = tcp_peek_offset_get(recv_sock); + offset = sk_peek_offset_get(recv_sock); if (offset != -1) { ksft_perror("Initial value of socket offset not -1\n"); goto out; } - tcp_peek_offset_set(recv_sock, 0); - offset = tcp_peek_offset_get(recv_sock); + sk_peek_offset_set(recv_sock, 0); + offset = sk_peek_offset_get(recv_sock); if (offset != 0) { ksft_perror("Failed to set socket offset to 0\n"); goto out; } /* Transfer a message */ - if (send(s[1], (char *)("ab"), 2, 0) <= 0 || errno != EINPROGRESS) { + if (send(s[1], (char *)("ab"), 2, 0) != 2) { ksft_perror("Temporary probe socket send() failed\n"); goto out; } /* Read first byte */ - len = recv(recv_sock, &buf, 1, MSG_PEEK); - if (len != 1 || buf != 'a') { + len = recv(recv_sock, buf, 1, MSG_PEEK); + if (len != 1 || buf[0] != 'a') { ksft_perror("Failed to read first byte of message\n"); goto out; } - offset = tcp_peek_offset_get(recv_sock); + offset = sk_peek_offset_get(recv_sock); if (offset != 1) { ksft_perror("Offset not forwarded correctly at first byte\n"); goto out; } /* Try to read beyond last byte */ - len = recv(recv_sock, &buf, 2, MSG_PEEK); - if (len != 1 || buf != 'b') { + len = recv(recv_sock, buf, 2, MSG_PEEK); + if (len != 1 || buf[0] != 'b') { ksft_perror("Failed to read last byte of message\n"); goto out; } - offset = tcp_peek_offset_get(recv_sock); + offset = sk_peek_offset_get(recv_sock); if (offset != 2) { ksft_perror("Offset not forwarded correctly at last byte\n"); goto out; } /* Flush message */ - len = recv(recv_sock, NULL, 2, MSG_TRUNC); + len = recv(recv_sock, buf, 2, MSG_TRUNC); if (len != 2) { ksft_perror("Failed to flush message\n"); goto out; } - offset = tcp_peek_offset_get(recv_sock); + offset = sk_peek_offset_get(recv_sock); if (offset != 0) { ksft_perror("Offset not reverted correctly after flush\n"); goto out; } - printf("%s with MSG_PEEK_OFF works correctly\n", afstr(af)); + printf("%s with MSG_PEEK_OFF works correctly\n", afstr(af, proto)); res = 1; out: - if (recv_sock >= 0) + if (proto == IPPROTO_TCP && recv_sock >= 0) close(recv_sock); if (s[1] >= 0) close(s[1]); @@ -160,24 +167,36 @@ static int tcp_peek_offset_test(sa_family_t af) return res; } -int main(void) +static int do_test(int proto) { int res4, res6; - res4 = tcp_peek_offset_probe(AF_INET); - res6 = tcp_peek_offset_probe(AF_INET6); + res4 = sk_peek_offset_probe(AF_INET, proto); + res6 = sk_peek_offset_probe(AF_INET6, proto); if (!res4 && !res6) return KSFT_SKIP; if (res4) - res4 = tcp_peek_offset_test(AF_INET); + res4 = sk_peek_offset_test(AF_INET, proto); if (res6) - res6 = tcp_peek_offset_test(AF_INET6); + res6 = sk_peek_offset_test(AF_INET6, proto); if (!res4 || !res6) return KSFT_FAIL; return KSFT_PASS; } + +int main(void) +{ + int restcp, resudp; + + restcp = do_test(IPPROTO_TCP); + resudp = do_test(IPPROTO_UDP); + if (restcp == KSFT_FAIL || resudp == KSFT_FAIL) + return KSFT_FAIL; + + return KSFT_PASS; +} -- 2.37.3

1 year, 3 months

2
1
0 0

[PATCH] selftests: vDSO: enable partial vdso_test_getrandom bench

by Christophe Leroy

In order to use vdso_test_getrandom with analysis tools like 'perf' it can be useful to perform only one kind of test, for instead only vdso. Add an optional argument that allows telling which of the three API you want to benchmark. Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> --- .../selftests/vDSO/vdso_test_getrandom.c | 122 +++++++++++------- 1 file changed, 73 insertions(+), 49 deletions(-) diff --git a/tools/testing/selftests/vDSO/vdso_test_getrandom.c b/tools/testing/selftests/vDSO/vdso_test_getrandom.c index 8866b65a4605..c38210ac8dc5 100644 --- a/tools/testing/selftests/vDSO/vdso_test_getrandom.c +++ b/tools/testing/selftests/vDSO/vdso_test_getrandom.c @@ -46,6 +46,10 @@ static struct { .lock = PTHREAD_MUTEX_INITIALIZER }; +#define VDSO_TEST_VDSO 0x1 +#define VDSO_TEST_LIBC 0x2 +#define VDSO_TEST_SYSCALL 0x4 + static void *vgetrandom_get_state(void) { void *state = NULL; @@ -173,60 +177,72 @@ static void *test_syscall_getrandom(void *ctx) return NULL; } -static void bench_single(void) +static void bench_single(int tests) { struct timespec start, end, diff; - clock_gettime(CLOCK_MONOTONIC, &start); - test_vdso_getrandom(NULL); - clock_gettime(CLOCK_MONOTONIC, &end); - timespecsub(&end, &start, &diff); - printf(" vdso: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec); - - clock_gettime(CLOCK_MONOTONIC, &start); - test_libc_getrandom(NULL); - clock_gettime(CLOCK_MONOTONIC, &end); - timespecsub(&end, &start, &diff); - printf(" libc: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec); - - clock_gettime(CLOCK_MONOTONIC, &start); - test_syscall_getrandom(NULL); - clock_gettime(CLOCK_MONOTONIC, &end); - timespecsub(&end, &start, &diff); - printf("syscall: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec); + if (tests & VDSO_TEST_VDSO) { + clock_gettime(CLOCK_MONOTONIC, &start); + test_vdso_getrandom(NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" vdso: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec); + } + + if (tests & VDSO_TEST_LIBC) { + clock_gettime(CLOCK_MONOTONIC, &start); + test_libc_getrandom(NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" libc: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec); + } + + if (tests & VDSO_TEST_SYSCALL) { + clock_gettime(CLOCK_MONOTONIC, &start); + test_syscall_getrandom(NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf("syscall: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec); + } } -static void bench_multi(void) +static void bench_multi(int tests) { struct timespec start, end, diff; pthread_t threads[THREADS]; - clock_gettime(CLOCK_MONOTONIC, &start); - for (size_t i = 0; i < THREADS; ++i) - assert(pthread_create(&threads[i], NULL, test_vdso_getrandom, NULL) == 0); - for (size_t i = 0; i < THREADS; ++i) - pthread_join(threads[i], NULL); - clock_gettime(CLOCK_MONOTONIC, &end); - timespecsub(&end, &start, &diff); - printf(" vdso: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec); - - clock_gettime(CLOCK_MONOTONIC, &start); - for (size_t i = 0; i < THREADS; ++i) - assert(pthread_create(&threads[i], NULL, test_libc_getrandom, NULL) == 0); - for (size_t i = 0; i < THREADS; ++i) - pthread_join(threads[i], NULL); - clock_gettime(CLOCK_MONOTONIC, &end); - timespecsub(&end, &start, &diff); - printf(" libc: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec); - - clock_gettime(CLOCK_MONOTONIC, &start); - for (size_t i = 0; i < THREADS; ++i) - assert(pthread_create(&threads[i], NULL, test_syscall_getrandom, NULL) == 0); - for (size_t i = 0; i < THREADS; ++i) - pthread_join(threads[i], NULL); - clock_gettime(CLOCK_MONOTONIC, &end); - timespecsub(&end, &start, &diff); - printf(" syscall: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec); + if (tests & VDSO_TEST_VDSO) { + clock_gettime(CLOCK_MONOTONIC, &start); + for (size_t i = 0; i < THREADS; ++i) + assert(pthread_create(&threads[i], NULL, test_vdso_getrandom, NULL) == 0); + for (size_t i = 0; i < THREADS; ++i) + pthread_join(threads[i], NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" vdso: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec); + } + + if (tests & VDSO_TEST_LIBC) { + clock_gettime(CLOCK_MONOTONIC, &start); + for (size_t i = 0; i < THREADS; ++i) + assert(pthread_create(&threads[i], NULL, test_libc_getrandom, NULL) == 0); + for (size_t i = 0; i < THREADS; ++i) + pthread_join(threads[i], NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" libc: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec); + } + + if (tests & VDSO_TEST_SYSCALL) { + clock_gettime(CLOCK_MONOTONIC, &start); + for (size_t i = 0; i < THREADS; ++i) + assert(pthread_create(&threads[i], NULL, test_syscall_getrandom, NULL) == 0); + for (size_t i = 0; i < THREADS; ++i) + pthread_join(threads[i], NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" syscall: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec); + } } static void fill(void) @@ -255,11 +271,13 @@ static void kselftest(void) static void usage(const char *argv0) { - fprintf(stderr, "Usage: %s [bench-single|bench-multi|fill]\n", argv0); + fprintf(stderr, "Usage: %s [bench-single|bench-multi|fill [vdso|libc|syscall]]\n", argv0); } int main(int argc, char *argv[]) { + int tests = VDSO_TEST_VDSO | VDSO_TEST_LIBC | VDSO_TEST_SYSCALL; + vgetrandom_init(); if (argc == 1) { @@ -267,14 +285,20 @@ int main(int argc, char *argv[]) return 0; } - if (argc != 2) { + if (argc == 3 && !strcmp(argv[2], "vdso")) { + tests = VDSO_TEST_VDSO; + } else if (argc == 3 && !strcmp(argv[2], "libc")) { + tests = VDSO_TEST_LIBC; + } else if (argc == 3 && !strcmp(argv[2], "syscall")) { + tests = VDSO_TEST_SYSCALL; + } else if (argc != 2) { usage(argv[0]); return 1; } if (!strcmp(argv[1], "bench-single")) - bench_single(); + bench_single(tests); else if (!strcmp(argv[1], "bench-multi")) - bench_multi(); + bench_multi(tests); else if (!strcmp(argv[1], "fill")) fill(); else { -- 2.44.0

1 year, 3 months

1
0
0 0

[PATCH HID 0/7] HID: bpf: add a new hook to control hid-generic

by Benjamin Tissoires

This is a slight change from the fundamentals of HID-BPF. In theory, HID-BPF is abstract to the kernel itself, and makes only changes at the HID level (through report descriptors or events emitted to/from the device). However, we have seen a few use cases where HID-BPF might interact with the running kernel when the target device is already handled by a specific device. For example, the XP-Pen/Huion/UC-Logic tablets are handled by hid-uclogic but this driver is also doing a report descriptor fixup without checking if the device has already been fixed by HID-BPF. In the same way, another recent example[0] was when a cheap foot pedal is used and tricks iPhones and Windows machines by presenting itself as a known Apple wireless keyboard. The problem is that this fake keyboard is not presenting a compatible report descriptor and hid-core merges all device nodes together making libinput ignore the keyboard part for historical reasons. Last, there has been a long standing request to allow to disable the input part of a given gamepad while SDL or Steam opens the device through hidraw. This series aims at tackling both of these problems: - first we had a new hook `hid_bpf_driver_probe` which allows the BPF program to decide if the curently probed driver should be used or not - then this same hook can also change the ->driver_data of the struct hid_device_id argument, and we teach hid-generic to use that field as the connect mask. Basically, it means that when we insert a BPF program to fix a device, we can force hid-generic to handle the device, and thus preventing any other kernel driver to tamper with our device. We can also selectively decide to export the hidraw or input nodes when using hid-generic. In the SDL/Steam use case, this would means that the gaming application will load one BPF program per input device it wants to open through hidraw, that BPF program reassigns the input device to hid-generic and disables hid-input, then it can open the new hidraw node. Once that program terminates, the BPF program is removed (either automatically because no-one has the fd of the links open, or manually by SDL/Steam), and the normal driver rebinds to the HID device, restoring full input functionality. This branch is on top of the for-6.12/hidraw branch of hid.git, mainly because that branch saw some selftests/hid changes. [0] https://gitlab.freedesktop.org/libinput/libinput/-/issues/1014 Signed-off-by: Benjamin Tissoires <bentiss(a)kernel.org> --- Benjamin Tissoires (7): selftests/hid: add dependency on hid_common.h selftests/hid: cleanup C tests by adding a common struct uhid_device selftests/hid: allow to parametrize bus/vid/pid/rdesc on the test device HID: bpf: allow BPF programs to force using hid-generic selftests/hid: add test for assigning a given device to hid-generic HID: bpf: Allow to control the connect mask of hid-generic from BPF selftests/hid: add test to disable hid-input Documentation/hid/hid-bpf.rst | 2 +- drivers/hid/bpf/hid_bpf_dispatch.c | 31 ++++ drivers/hid/bpf/hid_bpf_struct_ops.c | 4 + drivers/hid/hid-core.c | 18 +- drivers/hid/hid-generic.c | 5 +- include/linux/hid_bpf.h | 40 ++++ tools/testing/selftests/hid/Makefile | 2 +- tools/testing/selftests/hid/hid_bpf.c | 205 ++++++++++++++++----- tools/testing/selftests/hid/hid_common.h | 112 +++++++---- tools/testing/selftests/hid/hidraw.c | 36 +--- tools/testing/selftests/hid/progs/hid.c | 31 ++++ .../testing/selftests/hid/progs/hid_bpf_helpers.h | 4 + 12 files changed, 372 insertions(+), 118 deletions(-) --- base-commit: 321f7798cfb8d834ae0ed0d467c8bf46804243f9 change-id: 20240829-hid-bpf-hid-generic-61579f5b5945 Best regards, -- Benjamin Tissoires <bentiss(a)kernel.org>

1 year, 3 months

2
12
0 0

kselftest/next kselftest-seccomp: 2 runs, 1 regressions (v6.11-rc1-17-gb4bcdff7e839)

by kernelci.org bot

kselftest/next kselftest-seccomp: 2 runs, 1 regressions (v6.11-rc1-17-gb4bcdff7e839) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.11-rc1-17-gb4… Test: kselftest-seccomp Tree: kselftest Branch: next Describe: v6.11-rc1-17-gb4bcdff7e839 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: b4bcdff7e839237d89a2aa15b6042b96b0240ac4 Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/66d7b13e6922285319c8685f Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-17-gb4bcdff7e839/arm… HTML log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-17-gb4bcdff7e839/arm… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-seccomp.login: https://kernelci.org/test/case/id/66d7b13e6922285319c86860 failing since 35 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

1 year, 3 months

1
0
0 0

kselftest/next kselftest-lkdtm: 1 runs, 1 regressions (v6.11-rc1-17-gb4bcdff7e839)

by kernelci.org bot

kselftest/next kselftest-lkdtm: 1 runs, 1 regressions (v6.11-rc1-17-gb4bcdff7e839) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.11-rc1-17-gb4… Test: kselftest-lkdtm Tree: kselftest Branch: next Describe: v6.11-rc1-17-gb4bcdff7e839 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: b4bcdff7e839237d89a2aa15b6042b96b0240ac4 Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/66d7b2a624bc264505c8685f Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-17-gb4bcdff7e839/arm… HTML log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-17-gb4bcdff7e839/arm… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-lkdtm.login: https://kernelci.org/test/case/id/66d7b2a624bc264505c86860 failing since 35 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

1 year, 3 months

1
0
0 0

kselftest/next build: 7 builds: 2 failed, 5 passed, 1 warning (v6.11-rc1-17-gb4bcdff7e839)

by kernelci.org bot

kselftest/next build: 7 builds: 2 failed, 5 passed, 1 warning (v6.11-rc1-17-gb4bcdff7e839) Full Build Summary: https://kernelci.org/build/kselftest/branch/next/kernel/v6.11-rc1-17-gb4bcd… Tree: kselftest Branch: next Git Describe: v6.11-rc1-17-gb4bcdff7e839 Git Commit: b4bcdff7e839237d89a2aa15b6042b96b0240ac4 Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git Built: 4 unique architectures Build Failures Detected: arm64: defconfig+kselftest+arm64-chromebook: (clang-16) FAIL defconfig+kselftest+arm64-chromebook: (gcc-12) FAIL Warnings Detected: arm64: arm: i386: x86_64: x86_64_defconfig+kselftest (clang-16): 1 warning Warnings summary: 1 vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x39: relocation to !ENDBR: .text+0x14ef94 ================================================================================ Detailed per-defconfig build reports: -------------------------------------------------------------------------------- defconfig+kselftest (arm64, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, gcc-12) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, clang-16) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- i386_defconfig+kselftest (i386, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- multi_v7_defconfig+kselftest (arm, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, clang-16) — PASS, 0 errors, 1 warning, 0 section mismatches Warnings: vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x39: relocation to !ENDBR: .text+0x14ef94 --- For more info write to <info(a)kernelci.org>

1 year, 3 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror September 2024