- Linux-kselftest-mirror - lists.linaro.org

[PATCH net-next v22 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> Reviewed-by: Alexander Duyck <alexanderduyck(a)fb.com> --- 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 a951de920e20..a0a6d25f883f 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 6e3bdf8e38bc..92314ef2d978 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 bff5706b76e1..0ac6daebdd5c 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> @@ -43,6 +44,23 @@ 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 48f1e0fa2a13..7adca0fa2602 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 d5639b036166..dba52bb0da8a 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 8afab64814dc..6ca2abce857b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4836,142 +4836,6 @@ 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 912d97b99107..13c44133e009 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> #define TEST_FAILED_PREFIX "page_frag_test failed: " -- 2.33.0

6 months, 1 week

1
0
0 0

[PATCH net-next v22 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> Reviewed-by: Alexander Duyck <alexanderduyck(a)fb.com> --- tools/testing/selftests/mm/Makefile | 3 + tools/testing/selftests/mm/page_frag/Makefile | 18 ++ .../selftests/mm/page_frag/page_frag_test.c | 198 ++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 8 + tools/testing/selftests/mm/test_page_frag.sh | 175 ++++++++++++++++ 5 files changed, 402 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 02e1204971b0..acec529baaca 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 @@ -126,6 +128,7 @@ 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..912d97b99107 --- /dev/null +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -0,0 +1,198 @@ +// 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> + +#define TEST_FAILED_PREFIX "page_frag_test failed: " + +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 test_popped; +static int test_pushed; +static bool force_exit; + +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; + + pr_info("page_frag pop test thread begins on cpu %d\n", + smp_processor_id()); + + while (test_popped < nr_test) { + void *obj = __ptr_ring_consume(ring); + + if (obj) { + test_popped++; + page_frag_free(obj); + } else { + if (force_exit) + break; + + 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; + + pr_info("page_frag push test thread begins on cpu %d\n", + smp_processor_id()); + + while (test_pushed < nr_test && !force_exit) { + void *va; + int ret; + + if (test_align) { + va = page_frag_alloc_align(&test_nc, test_alloc_len, + GFP_KERNEL, SMP_CACHE_BYTES); + + if ((unsigned long)va & (SMP_CACHE_BYTES - 1)) { + force_exit = true; + WARN_ONCE(true, TEST_FAILED_PREFIX "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 { + test_pushed++; + } + } + + 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; + int last_pushed = 0, last_popped = 0; + 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"); + + while (!wait_for_completion_timeout(&wait, msecs_to_jiffies(10000))) { + /* exit if there is no progress for push or pop size */ + if (last_pushed == test_pushed || last_popped == test_popped) { + WARN_ONCE(true, TEST_FAILED_PREFIX "no progress\n"); + force_exit = true; + continue; + } + + last_pushed = test_pushed; + last_popped = test_popped; + pr_info("page_frag_test progress: pushed = %d, popped = %d\n", + test_pushed, test_popped); + } + + if (force_exit) { + pr_err(TEST_FAILED_PREFIX "exit with error\n"); + goto out; + } + + 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); + +out: + 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 c5797ad1d37b..2c5394584af4 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..f55b105084cf --- /dev/null +++ b/tools/testing/selftests/mm/test_page_frag.sh @@ -0,0 +1,175 @@ +#!/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 + +check_test_failed_prefix() { + if dmesg | grep -q 'page_frag_test failed:';then + echo "page_frag_test failed, please check dmesg" + exit $exitcode + fi +} + +# +# Static templates for testing of page_frag APIs. +# Also it is possible to pass any supported parameters manually. +# +SMOKE_PARAM="test_push_cpu=$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 +} + +run_aligned_check() +{ + echo "Run performance tests to evaluate how fast aligned alloc API is." + + insmod $DRIVER $ALIGNED_PARAM > /dev/null 2>&1 +} + +run_smoke_check() +{ + echo "Run smoke test." + + insmod $DRIVER $SMOKE_PARAM > /dev/null 2>&1 +} + +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 +} + +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_failed_prefix + + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +check_test_requirements +run_test $@ + +exit 0 -- 2.33.0

6 months, 1 week

1
0
0 0

[PATCH v2] kselftests: Add test to detect boot event slowdowns

by Laura Nao

Introduce a new kselftest to identify slowdowns in key boot events. This test uses ftrace to monitor the start and end times, as well as the durations of all initcalls, and compares these timings to reference values to identify significant slowdowns. The script functions in two modes: the 'generate' mode allows to create a JSON file containing initial reference timings for all initcalls from a known stable kernel. The 'test' mode can be used during subsequent boots to assess current timings against the reference values and determine if there are any significant differences. The test ships with a bootconfig file for setting up ftrace and a configuration fragment for the necessary kernel configs. Signed-off-by: Laura Nao <laura.nao(a)collabora.com> --- Hello, This v2 is a follow-up to RFCv1[1] and includes changes based on feedback from the LPC 2024 session [2], along with some other fixes. [1] https://lore.kernel.org/all/20240725110622.96301-1-laura.nao@collabora.com/ [2] https://www.youtube.com/watch?v=rWhW2-Vzi40 After reviewing other available tests and considering the feedback from discussions at Plumbers, I decided to stick with the bootconfig file approach but extend it to track all initcalls instead of a fixed set of functions or events. The bootconfig file can be expanded and adapted to track additional functions if needed for specific use cases. I also defined a synthetic event to calculate initcall durations, while still tracking their start and end times. Users are then allowed to choose whether to compare start times, end times, or durations. Support for specifying different rules for different initcalls has also been added. In RFCv1, there was some discussion about using existing tools like bootgraph.py. However, the output from these tools is mainly for manual inspection (e.g., HTML visual output), whereas this test is designed to run in automated CI environments too. The kselftest proposed here combines the process of generating reference data and running tests into a single script with two modes, making it easy to integrate into automated workflows. Many of the features in this v2 (e.g., generating a JSON reference file, comparing timings, and reporting results in KTAP format) could potentially be integrated into bootgraph.py with some effort. However, since this test is intended for automated execution rather than manual use, I've decided to keep it separate for now and explore the options suggested at LPC, such as using ftrace histograms for initcall latencies. I'm open to revisiting this decision and working toward integrating the changes into bootgraph.py if there's a strong preference for unifying the tools. Let me know your thoughts. A comprehensive changelog is reported below. Thanks, Laura --- Changes in v2: - Updated ftrace configuration to track all initcall start times, end times, and durations, and generate a histogram. - Modified test logic to compare initcall durations by default, with the option to compare start or end times if needed. - Added warnings if the initcalls in the reference file differ from those detected in the running system. - Combined the scripts into a single script with two modes: one for generating the reference file and one for running the test. - Added support for specifying different rules for individual initcalls. - Switched the reference format from YAML to JSON. - Added metadata to the reference file, including kernel version, kernel configuration, and cmdline. - Link to v1: https://lore.kernel.org/all/20240725110622.96301-1-laura.nao@collabora.com/ --- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/boot-time/Makefile | 16 ++ tools/testing/selftests/boot-time/bootconfig | 15 + tools/testing/selftests/boot-time/config | 6 + .../selftests/boot-time/test_boot_time.py | 265 ++++++++++++++++++ 5 files changed, 303 insertions(+) create mode 100644 tools/testing/selftests/boot-time/Makefile create mode 100644 tools/testing/selftests/boot-time/bootconfig create mode 100644 tools/testing/selftests/boot-time/config create mode 100755 tools/testing/selftests/boot-time/test_boot_time.py diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index b38199965f99..1bb20d1e3854 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -3,6 +3,7 @@ TARGETS += acct TARGETS += alsa TARGETS += amd-pstate TARGETS += arm64 +TARGETS += boot-time TARGETS += bpf TARGETS += breakpoints TARGETS += cachestat diff --git a/tools/testing/selftests/boot-time/Makefile b/tools/testing/selftests/boot-time/Makefile new file mode 100644 index 000000000000..cdcdc1bbe779 --- /dev/null +++ b/tools/testing/selftests/boot-time/Makefile @@ -0,0 +1,16 @@ +PY3 = $(shell which python3 2>/dev/null) + +ifneq ($(PY3),) + +TEST_PROGS := test_boot_time.py + +include ../lib.mk + +else + +all: no_py3_warning + +no_py3_warning: + @echo "Missing python3. This test will be skipped." + +endif \ No newline at end of file diff --git a/tools/testing/selftests/boot-time/bootconfig b/tools/testing/selftests/boot-time/bootconfig new file mode 100644 index 000000000000..e4b89a33b7a3 --- /dev/null +++ b/tools/testing/selftests/boot-time/bootconfig @@ -0,0 +1,15 @@ +ftrace.event { + synthetic.initcall_latency { + # Synthetic event to record initcall latency, start, and end times + fields = "unsigned long func", "u64 lat", "u64 start", "u64 end" + actions = "hist:keys=func.sym,start,end:vals=lat:sort=lat" + } + initcall.initcall_start { + # Capture the start time (ts0) when initcall starts + actions = "hist:keys=func:ts0=common_timestamp.usecs" + } + initcall.initcall_finish { + # Capture the end time, calculate latency, and trigger synthetic event + actions = "hist:keys=func:lat=common_timestamp.usecs-$ts0:start=$ts0:end=common_timestamp.usecs:onmatch(initcall.initcall_start).initcall_latency(func,$lat,$start,$end)" + } +} \ No newline at end of file diff --git a/tools/testing/selftests/boot-time/config b/tools/testing/selftests/boot-time/config new file mode 100644 index 000000000000..bcb646ec3cd8 --- /dev/null +++ b/tools/testing/selftests/boot-time/config @@ -0,0 +1,6 @@ +CONFIG_TRACING=y +CONFIG_BOOTTIME_TRACING=y +CONFIG_BOOT_CONFIG_EMBED=y +CONFIG_BOOT_CONFIG_EMBED_FILE="tools/testing/selftests/boot-time/bootconfig" +CONFIG_SYNTH_EVENTS=y +CONFIG_HIST_TRIGGERS=y \ No newline at end of file diff --git a/tools/testing/selftests/boot-time/test_boot_time.py b/tools/testing/selftests/boot-time/test_boot_time.py new file mode 100755 index 000000000000..556dacf04b6d --- /dev/null +++ b/tools/testing/selftests/boot-time/test_boot_time.py @@ -0,0 +1,265 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2024 Collabora Ltd +# +# This script reads the +# /sys/kernel/debug/tracing/events/synthetic/initcall_latency/hist file, +# extracts function names and timings, and compares them against reference +# timings provided in an input JSON file to identify significant boot +# slowdowns. +# The script operates in two modes: +# - Generate Mode: parses initcall timings from the current kernel's ftrace +# event histogram and generates a JSON reference file with function +# names, start times, end times, and latencies. +# - Test Mode: compares current initcall timings against the reference +# file, allowing users to define a maximum allowed difference between the +# values (delta). Users can also apply custom delta thresholds for +# specific initcalls using regex-based overrides. The comparison can be +# done on latency, start, or end times. +# + +import os +import sys +import argparse +import gzip +import json +import re +import subprocess + +this_dir = os.path.dirname(os.path.realpath(__file__)) +sys.path.append(os.path.join(this_dir, "../kselftest/")) + +import ksft + +def load_reference_from_json(file_path): + """ + Load reference data from a JSON file and returns the parsed data. + @file_path: path to the JSON file. + """ + + try: + with open(file_path, 'r', encoding="utf-8") as file: + return json.load(file) + except FileNotFoundError: + ksft.print_msg(f"Error: File {file_path} not found.") + ksft.exit_fail() + except json.JSONDecodeError: + ksft.print_msg(f"Error: Failed to decode JSON from {file_path}.") + ksft.exit_fail() + + +def mount_debugfs(path): + """ + Mount debugfs at the specified path if it is not already mounted. + @path: path where debugfs should be mounted + """ + # Check if debugfs is already mounted + with open('/proc/mounts', 'r', encoding="utf-8") as mounts: + for line in mounts: + if 'debugfs' in line and path in line: + print(f"debugfs is already mounted at {path}") + return True + + # Mount debugfs + try: + subprocess.run(['mount', '-t', 'debugfs', 'none', path], check=True) + return True + except subprocess.CalledProcessError as e: + print(f"Failed to mount debugfs: {e.stderr}") + return False + + +def ensure_unique_function_name(func, initcall_entries): + """ + Ensure the function name is unique by appending a suffix if necessary. + @func: the original function name. + @initcall_entries: a dictionary containing parsed initcall entries. + """ + i = 2 + base_func = func + while func in initcall_entries: + func = f'{base_func}[{i}]' + i += 1 + return func + + +def parse_initcall_latency_hist(): + """ + Parse the ftrace histogram for the initcall_latency event, extracting + function names, start times, end times, and latencies. Return a + dictionary where each entry is structured as follows: + { + <function symbolic name>: { + "start": <start time>, + "end": <end time>, + "latency": <latency> + } + } + """ + + pattern = re.compile(r'\{ func: \[\w+\] ([\w_]+)\s*, start: *(\d+), end: *(\d+) \} hitcount: *\d+ lat: *(\d+)') + initcall_entries = {} + + try: + with open('/sys/kernel/debug/tracing/events/synthetic/initcall_latency/hist', 'r', encoding="utf-8") as hist_file: + for line in hist_file: + match = pattern.search(line) + if match: + func = match.group(1).strip() + start = int(match.group(2)) + end = int(match.group(3)) + latency = int(match.group(4)) + + # filter out unresolved names + if not func.startswith("0x"): + func = ensure_unique_function_name(func, initcall_entries) + + initcall_entries[func] = { + "start": start, + "end": end, + "latency": latency + } + except FileNotFoundError: + print("Error: Histogram file not found.") + + return initcall_entries + + +def compare_initcall_list(ref_initcall_entries, cur_initcall_entries): + """ + Compare the current list of initcall functions against the reference + file. Print warnings if there are unique entries in either. + @ref_initcall_entries: reference initcall entries. + @cur_initcall_entries: current initcall entries. + """ + ref_entries = set(ref_initcall_entries.keys()) + cur_entries = set(cur_initcall_entries.keys()) + + unique_to_ref = ref_entries - cur_entries + unique_to_cur = cur_entries - ref_entries + + if (unique_to_ref): + ksft.print_msg( + f"Warning: {list(unique_to_ref)} not found in current data. Consider updating reference file.") + if unique_to_cur: + ksft.print_msg( + f"Warning: {list(unique_to_cur)} not found in reference data. Consider updating reference file.") + + +def run_test(ref_file_path, delta, overrides, mode): + """ + Run the test comparing the current timings with the reference values. + @ref_file_path: path to the JSON file containing reference values. + @delta: default allowed difference between reference and current + values. + @overrides: override rules in the form of regex:threshold. + @mode: the comparison mode (either 'start', 'end', or 'latency'). + """ + + ref_data = load_reference_from_json(ref_file_path) + + ref_initcall_entries = ref_data['data'] + cur_initcall_entries = parse_initcall_latency_hist() + + compare_initcall_list(ref_initcall_entries, cur_initcall_entries) + + ksft.set_plan(len(ref_initcall_entries)) + + for func_name in ref_initcall_entries: + effective_delta = delta + for regex, override_delta in overrides.items(): + if re.match(regex, func_name): + effective_delta = override_delta + break + if (func_name in cur_initcall_entries): + ref_metric = ref_initcall_entries[func_name].get(mode) + cur_metric = cur_initcall_entries[func_name].get(mode) + if (cur_metric > ref_metric and (cur_metric - ref_metric) >= effective_delta): + ksft.test_result_fail(func_name) + ksft.print_msg(f"'{func_name}' {mode} differs by " + f"{(cur_metric - ref_metric)} usecs.") + else: + ksft.test_result_pass(func_name) + else: + ksft.test_result_skip(func_name) + + +def generate_reference_file(file_path): + """ + Generate a reference file in JSON format, containing kernel metadata + and initcall timing data. + @file_path: output file path. + """ + metadata = {} + + config_file = "/proc/config.gz" + if os.path.isfile(config_file): + with gzip.open(config_file, "rt", encoding="utf-8") as f: + config = f.read() + metadata["config"] = config + + metadata["version"] = os.uname().release + + cmdline_file = "/proc/cmdline" + if os.path.isfile(cmdline_file): + with open(cmdline_file, "r", encoding="utf-8") as f: + cmdline = f.read().strip() + metadata["cmdline"] = cmdline + + ref_data = { + "metadata": metadata, + "data": parse_initcall_latency_hist(), + } + + with open(file_path, "w", encoding='utf-8') as f: + json.dump(ref_data, f, indent=4) + print(f"Generated {file_path}") + + +if __name__ == "__main__": + parser = argparse.ArgumentParser( + description="") + + subparsers = parser.add_subparsers(dest='mode', required=True, help='Choose between generate or test modes') + + generate_parser = subparsers.add_parser('generate', help="Generate a reference file") + generate_parser.add_argument('out_ref_file', nargs='?', default='reference_initcall_timings.json', + help='Path to output JSON reference file (default: reference_initcall_timings.json)') + + compare_parser = subparsers.add_parser('test', help='Test against a reference file') + compare_parser.add_argument('in_ref_file', help='Path to JSON reference file') + compare_parser.add_argument( + 'delta', type=int, help='Maximum allowed delta between the current and the reference timings (usecs)') + compare_parser.add_argument('--override', '-o', action='append', type=str, + help="Specify regex-based rules as regex:delta (e.g., '^acpi_.*:50')") + compare_parser.add_argument('--mode', '-m', default='latency', choices=[ + 'start', 'end', 'latency'], + help="Comparison mode: 'latency' (default) for latency, 'start' for start times, or 'end' for end times.") + + args = parser.parse_args() + + if args.mode == 'generate': + generate_reference_file(args.out_ref_file) + sys.exit(0) + + # Process overrides + overrides = {} + if args.override: + for override in args.override: + try: + pattern, delta = override.split(":") + overrides[pattern] = int(delta) + except ValueError: + print(f"Invalid override format: {override}. Expected format is 'regex:delta'.") + sys.exit(1) + + # Ensure debugfs is mounted + if not mount_debugfs("/sys/kernel/debug"): + ksft.exit_fail() + + ksft.print_header() + + run_test(args.in_ref_file, args.delta, overrides, args.mode) + + ksft.finished() -- 2.30.2

6 months, 1 week

1
0
0 0

[PATCH v2] selftest/tcp-ao: Add filter tests

by Leo Stone

Add tests that check if getsockopt(TCP_AO_GET_KEYS) returns the right keys when using different filters. Sample output: > # ok 114 filter keys: by sndid, rcvid, address > # ok 115 filter keys: by is_current > # ok 116 filter keys: by is_rnext > # ok 117 filter keys: by sndid, rcvid > # ok 118 filter keys: correct nkeys when in.nkeys < matched_keys Signed-off-by: Leo Stone <leocstone(a)gmail.com> --- Changes in v2: - Changed 2 unnecessary test_error calls to test_fail - Added another test to make sure getsockopt returns the right nkeys value when the input nkeys is smaller than the number of matching keys - Removed the TODO that this patch addresses Thank you for your feedback. --- .../selftests/net/tcp_ao/setsockopt-closed.c | 180 +++++++++++++++++- 1 file changed, 175 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c index 084db4ecdff6..4bfa76c28e4e 100644 --- a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c +++ b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c @@ -6,6 +6,8 @@ static union tcp_addr tcp_md5_client; +#define FILTER_TEST_NKEYS 16 + static int test_port = 7788; static void make_listen(int sk) { @@ -813,23 +815,191 @@ static void duplicate_tests(void) setsockopt_checked(sk, TCP_AO_ADD_KEY, &ao, EEXIST, "duplicate: SendID differs"); } + +static void fetch_all_keys(int sk, struct tcp_ao_getsockopt *keys) +{ + socklen_t optlen = sizeof(struct tcp_ao_getsockopt); + + memset(keys, 0, sizeof(struct tcp_ao_getsockopt) * FILTER_TEST_NKEYS); + keys[0].get_all = 1; + keys[0].nkeys = FILTER_TEST_NKEYS; + if (getsockopt(sk, IPPROTO_TCP, TCP_AO_GET_KEYS, &keys[0], &optlen)) + test_error("getsockopt"); +} + +static int prepare_test_keys(struct tcp_ao_getsockopt *keys) +{ + struct tcp_ao_add test_ao[FILTER_TEST_NKEYS]; + u8 rcvid = 100, sndid = 100; + const char *test_password = "Test password number "; + char test_password_scratch[64] = {}; + int sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP); + + if (sk < 0) + test_error("socket()"); + + for (int i = 0; i < FILTER_TEST_NKEYS; i++) { + snprintf(test_password_scratch, 64, "%s %d", test_password, i); + test_prepare_key(&test_ao[i], DEFAULT_TEST_ALGO, this_ip_dest, false, false, + DEFAULT_TEST_PREFIX, 0, sndid++, rcvid++, 0, 0, + strlen(test_password_scratch), test_password_scratch); + } + test_ao[0].set_current = 1; + test_ao[1].set_rnext = 1; + /* One key with a different addr and overlapping sndid, rcvid */ + tcp_addr_to_sockaddr_in(&test_ao[2].addr, &this_ip_addr, 0); + test_ao[2].sndid = 100; + test_ao[2].rcvid = 100; + + /* Add keys in a random order */ + for (int i = 0; i < FILTER_TEST_NKEYS; i++) { + int randidx = rand() % (FILTER_TEST_NKEYS - i); + + if (setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &test_ao[randidx], + sizeof(struct tcp_ao_add))) + test_error("setsockopt()"); + memcpy(&test_ao[randidx], &test_ao[FILTER_TEST_NKEYS - 1 - i], + sizeof(struct tcp_ao_add)); + } + + fetch_all_keys(sk, keys); + + return sk; +} + +/* Assumes passwords are unique */ +static int compare_mkts(struct tcp_ao_getsockopt *expected, int nexpected, + struct tcp_ao_getsockopt *actual, int nactual) +{ + int matches = 0; + + for (int i = 0; i < nexpected; i++) { + for (int j = 0; j < nactual; j++) { + if (memcmp(expected[i].key, actual[j].key, TCP_AO_MAXKEYLEN) == 0) + matches++; + } + } + return nexpected - matches; +} + +static void filter_keys_checked(int sk, struct tcp_ao_getsockopt *filter, + struct tcp_ao_getsockopt *expected, + unsigned int nexpected, const char *tst) +{ + struct tcp_ao_getsockopt all_keys[FILTER_TEST_NKEYS] = {}; + struct tcp_ao_getsockopt filtered_keys[FILTER_TEST_NKEYS] = {}; + socklen_t len = sizeof(struct tcp_ao_getsockopt); + + fetch_all_keys(sk, all_keys); + memcpy(&filtered_keys[0], filter, sizeof(struct tcp_ao_getsockopt)); + filtered_keys[0].nkeys = FILTER_TEST_NKEYS; + if (getsockopt(sk, IPPROTO_TCP, TCP_AO_GET_KEYS, filtered_keys, &len)) + test_error("getsockopt"); + if (filtered_keys[0].nkeys != nexpected) { + test_fail("wrong nr of keys, expected %u got %u", nexpected, + filtered_keys[0].nkeys); + goto out_close; + } + if (compare_mkts(expected, nexpected, filtered_keys, filtered_keys[0].nkeys)) { + test_fail("got wrong keys back"); + goto out_close; + } + test_ok("filter keys: %s", tst); + +out_close: + close(sk); + memset(filter, 0, sizeof(struct tcp_ao_getsockopt)); +} + +static void filter_tests(void) +{ + struct tcp_ao_getsockopt original_keys[FILTER_TEST_NKEYS]; + struct tcp_ao_getsockopt expected_keys[FILTER_TEST_NKEYS]; + struct tcp_ao_getsockopt filter = {}; + int sk, f, nmatches; + socklen_t len; + + f = 2; + sk = prepare_test_keys(original_keys); + filter.rcvid = original_keys[f].rcvid; + filter.sndid = original_keys[f].sndid; + memcpy(&filter.addr, &original_keys[f].addr, sizeof(original_keys[f].addr)); + filter.prefix = original_keys[f].prefix; + filter_keys_checked(sk, &filter, &original_keys[f], 1, "by sndid, rcvid, address"); + + f = -1; + sk = prepare_test_keys(original_keys); + for (int i = 0; i < original_keys[0].nkeys; i++) { + if (original_keys[i].is_current) { + f = i; + break; + } + } + if (f < 0) + test_error("No current key after adding one"); + filter.is_current = 1; + filter_keys_checked(sk, &filter, &original_keys[f], 1, "by is_current"); + + f = -1; + sk = prepare_test_keys(original_keys); + for (int i = 0; i < original_keys[0].nkeys; i++) { + if (original_keys[i].is_rnext) { + f = i; + break; + } + } + if (f < 0) + test_error("No rnext key after adding one"); + filter.is_rnext = 1; + filter_keys_checked(sk, &filter, &original_keys[f], 1, "by is_rnext"); + + f = -1; + nmatches = 0; + sk = prepare_test_keys(original_keys); + for (int i = 0; i < original_keys[0].nkeys; i++) { + if (original_keys[i].sndid == 100) { + f = i; + memcpy(&expected_keys[nmatches], &original_keys[i], + sizeof(struct tcp_ao_getsockopt)); + nmatches++; + } + } + if (f < 0) + test_error("No key for sndid 100"); + if (nmatches != 2) + test_error("Should have 2 keys with sndid 100"); + filter.rcvid = original_keys[f].rcvid; + filter.sndid = original_keys[f].sndid; + filter.addr.ss_family = test_family; + filter_keys_checked(sk, &filter, expected_keys, nmatches, "by sndid, rcvid"); + + sk = prepare_test_keys(original_keys); + filter.get_all = 1; + filter.nkeys = FILTER_TEST_NKEYS / 2; + len = sizeof(struct tcp_ao_getsockopt); + if (getsockopt(sk, IPPROTO_TCP, TCP_AO_GET_KEYS, &filter, &len)) + test_error("getsockopt"); + if (filter.nkeys == FILTER_TEST_NKEYS) + test_ok("filter keys: correct nkeys when in.nkeys < matched_keys"); + else + test_fail("filter keys: wrong nkeys, expected %u got %u", + FILTER_TEST_NKEYS, filter.nkeys); +} + static void *client_fn(void *arg) { if (inet_pton(TEST_FAMILY, __TEST_CLIENT_IP(2), &tcp_md5_client) != 1) test_error("Can't convert ip address"); extend_tests(); einval_tests(); + filter_tests(); duplicate_tests(); - /* - * TODO: check getsockopt(TCP_AO_GET_KEYS) with different filters - * returning proper nr & keys; - */ return NULL; } int main(int argc, char *argv[]) { - test_init(121, client_fn, NULL); + test_init(126, client_fn, NULL); return 0; } -- 2.43.0

6 months, 1 week

3
2
0 0

[PATCH v6 0/5] selftests: kvm: s390: Add ucontrol memory selftests

by Christoph Schlameuss

This patch series adds a some not yet picked selftests to the kvm s390x selftest suite. The additional test cases are covering: * Assert KVM_EXIT_S390_UCONTROL exit on not mapped memory access * Assert functionality of storage keys in ucontrol VM * Assert that memory region operations are rejected for ucontrol VMs Running the test cases requires sys_admin capabilities to start the ucontrol VM. This can be achieved by running as root or with a command like: sudo setpriv --reuid nobody --inh-caps -all,+sys_admin \ --ambient-caps -all,+sys_admin --bounding-set -all,+sys_admin \ ./ucontrol_test --- The patches in this series have been part of the previous patch series. The test cases added here do depend on the fixture added in the earlier patches. From v5 PATCH 7-9 the segment and page table generation has been removed and DAT has been disabled. Since DAT is not necessary to validate the KVM code. https://lore.kernel.org/kvm/20240807154512.316936-1-schlameuss@linux.ibm.co… v6: - add instruction intercept handling for skey specific instructions (iske, sske, rrbe) in addition to kss intercept to work properly on all machines - reorder local variables - fixup some method comments - add a patch correcting the IP.b value length a debug message v5: - rebased to current upstream master - corrected assertion on 0x00 to 0 - reworded fixup commit so that it can be merged on top of current upstream v4: - fix whitespaces in pointer function arguments (thanks Claudio) - fix whitespaces in comments (thanks Janosch) v3: - fix skey assertion (thanks Claudio) - introduce a wrapper around UCAS map and unmap ioctls to improve readability (Claudio) - add an displacement to accessed memory to assert translation intercepts actually point to segments to the uc_map_unmap test - add an misaligned failing mapping try to the uc_map_unmap test v2: - Reenable KSS intercept and handle it within skey test. - Modify the checked register between storing (sske) and reading (iske) it within the test program to make sure the. - Add an additional state assertion in the end of uc_skey - Fix some typos and white spaces. v1: - Remove segment and page table generation and disable DAT. This is not necessary to validate the KVM code. Christoph Schlameuss (5): selftests: kvm: s390: Add uc_map_unmap VM test case selftests: kvm: s390: Add uc_skey VM test case selftests: kvm: s390: Verify reject memory region operations for ucontrol VMs selftests: kvm: s390: Fix whitespace confusion in ucontrol test selftests: kvm: s390: correct IP.b length in uc_handle_sieic debug output .../selftests/kvm/include/s390x/processor.h | 6 + .../selftests/kvm/s390x/ucontrol_test.c | 307 +++++++++++++++++- 2 files changed, 305 insertions(+), 8 deletions(-) base-commit: eca631b8fe808748d7585059c4307005ca5c5820 -- 2.47.0

6 months, 1 week

2
11
0 0

[PATCH RFC v5 00/10] tun: Introduce virtio-net hashing feature

by Akihiko Odaki

virtio-net have two usage of hashes: one is RSS and another is hash reporting. Conventionally the hash calculation was done by the VMM. However, computing the hash after the queue was chosen defeats the purpose of RSS. Another approach is to use eBPF steering program. This approach has another downside: it cannot report the calculated hash due to the restrictive nature of eBPF. Introduce the code to compute hashes to the kernel in order to overcome thse challenges. An alternative solution is to extend the eBPF steering program so that it will be able to report to the userspace, but it is based on context rewrites, which is in feature freeze. We can adopt kfuncs, but they will not be UAPIs. We opt to ioctl to align with other relevant UAPIs (KVM and vhost_net). The patches for QEMU to use this new feature was submitted as RFC and is available at: https://patchew.org/QEMU/20240915-hash-v3-0-79cb08d28647@daynix.com/ This work was presented at LPC 2024: https://lpc.events/event/18/contributions/1963/ V1 -> V2: Changed to introduce a new BPF program type. Signed-off-by: Akihiko Odaki <akihiko.odaki(a)daynix.com> --- Changes in v5: - Fixed a compilation error with CONFIG_TUN_VNET_CROSS_LE. - Optimized the calculation of the hash value according to: https://git.dpdk.org/dpdk/commit/?id=3fb1ea032bd6ff8317af5dac9af901f1f324ca… - Added patch "tun: Unify vnet implementation". - Dropped patch "tap: Pad virtio header with zero". - Added patch "selftest: tun: Test vnet ioctls without device". - Reworked selftests to skip for older kernels. - Documented the case when the underlying device is deleted and packets have queue_mapping set by TC. - Reordered test harness arguments. - Added code to handle fragmented packets. - Link to v4: https://lore.kernel.org/r/20240924-rss-v4-0-84e932ec0e6c@daynix.com Changes in v4: - Moved tun_vnet_hash_ext to if_tun.h. - Renamed virtio_net_toeplitz() to virtio_net_toeplitz_calc(). - Replaced htons() with cpu_to_be16(). - Changed virtio_net_hash_rss() to return void. - Reordered variable declarations in virtio_net_hash_rss(). - Removed virtio_net_hdr_v1_hash_from_skb(). - Updated messages of "tap: Pad virtio header with zero" and "tun: Pad virtio header with zero". - Fixed vnet_hash allocation size. - Ensured to free vnet_hash when destructing tun_struct. - Link to v3: https://lore.kernel.org/r/20240915-rss-v3-0-c630015db082@daynix.com Changes in v3: - Reverted back to add ioctl. - Split patch "tun: Introduce virtio-net hashing feature" into "tun: Introduce virtio-net hash reporting feature" and "tun: Introduce virtio-net RSS". - Changed to reuse hash values computed for automq instead of performing RSS hashing when hash reporting is requested but RSS is not. - Extracted relevant data from struct tun_struct to keep it minimal. - Added kernel-doc. - Changed to allow calling TUNGETVNETHASHCAP before TUNSETIFF. - Initialized num_buffers with 1. - Added a test case for unclassified packets. - Fixed error handling in tests. - Changed tests to verify that the queue index will not overflow. - Rebased. - Link to v2: https://lore.kernel.org/r/20231015141644.260646-1-akihiko.odaki@daynix.com --- Akihiko Odaki (10): virtio_net: Add functions for hashing skbuff: Introduce SKB_EXT_TUN_VNET_HASH net: flow_dissector: Export flow_keys_dissector_symmetric tun: Unify vnet implementation tun: Pad virtio header with zero tun: Introduce virtio-net hash reporting feature tun: Introduce virtio-net RSS selftest: tun: Test vnet ioctls without device selftest: tun: Add tests for virtio-net hashing vhost/net: Support VIRTIO_NET_F_HASH_REPORT Documentation/networking/tuntap.rst | 7 + MAINTAINERS | 1 + drivers/net/Kconfig | 1 + drivers/net/tap.c | 218 ++++-------- drivers/net/tun.c | 293 ++++++---------- drivers/net/tun_vnet.h | 342 +++++++++++++++++++ drivers/vhost/net.c | 16 +- include/linux/if_tap.h | 2 + include/linux/skbuff.h | 3 + include/linux/virtio_net.h | 188 +++++++++++ include/net/flow_dissector.h | 1 + include/uapi/linux/if_tun.h | 75 +++++ net/core/flow_dissector.c | 3 +- net/core/skbuff.c | 4 + tools/testing/selftests/net/Makefile | 2 +- tools/testing/selftests/net/tun.c | 630 ++++++++++++++++++++++++++++++++++- 16 files changed, 1430 insertions(+), 356 deletions(-) --- base-commit: 752ebcbe87aceeb6334e846a466116197711a982 change-id: 20240403-rss-e737d89efa77 Best regards, -- Akihiko Odaki <akihiko.odaki(a)daynix.com>

6 months, 1 week

3
23
0 0

[PATCH 0/4] kunit: Add support for LoongArch

by Thomas Weißschuh

Enable LoongArch support in kunit. Example: $ ./tools/testing/kunit/kunit.py run --arch=loongarch --cross_compile=$CROSS_COMPILE [13:32:45] Configuring KUnit Kernel ... [13:32:45] Building KUnit Kernel ... Populating config with: $ make ARCH=loongarch olddefconfig CROSS_COMPILE=$CROSS_COMPILE Building with: $ make all compile_commands.json ARCH=loongarch --jobs=8 CROSS_COMPILE=$CROSS_COMPILE [13:32:48] Starting KUnit Kernel (1/1)... [13:32:48] ============================================================ Running tests with: $ qemu-system-loongarch64 -nodefaults -m 1024 -kernel .kunit/arch/loongarch/boot/vmlinux.elf -append 'kunit.enable=1 console=ttyS0 kunit_shutdown=poweroff' -no-reboot -nographic -serial stdio -machine virt -device pvpanic-pci -cpu max ... [13:33:14] ============================================================ [13:33:14] Testing complete. Ran 493 tests: passed: 453, skipped: 40 [13:33:14] Elapsed time: 28.862s total, 0.002s configuring, 2.526s building, 26.302s running Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- Thomas Weißschuh (4): LoongArch: Don't crash in stack_top() for tasks without vDSO kunit: qemu_configs: add LoongArch config kunit: tool: Allow overriding the shutdown mode from qemu config kunit: qemu_configs: loongarch: Enable shutdown arch/loongarch/kernel/process.c | 16 +++++++++------- tools/testing/kunit/kunit_kernel.py | 4 +++- tools/testing/kunit/qemu_configs/loongarch.py | 19 +++++++++++++++++++ 3 files changed, 31 insertions(+), 8 deletions(-) --- base-commit: 6485cf5ea253d40d507cd71253c9568c5470cd27 change-id: 20241014-kunit-loongarch-98a5b756e818 Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

6 months, 1 week

5
16
0 0

[PATCH 1/3] selftests: Add a few missing gitignore files

by Li Zhijian

Binary files should be added to .gitignore 'git status' complains: Untracked files: (use "git add <file>..." to include in what will be committed) alsa/global-timer alsa/utimer-test filesystems/statmount/statmount_test_ns mm/hugetlb_dio mm/pkey_sighandler_tests_32 mm/pkey_sighandler_tests_64 net/netfilter/conntrack_reverse_clash Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> --- tools/testing/selftests/alsa/.gitignore | 2 ++ tools/testing/selftests/filesystems/statmount/.gitignore | 1 + tools/testing/selftests/mm/.gitignore | 2 ++ tools/testing/selftests/net/netfilter/.gitignore | 1 + 4 files changed, 6 insertions(+) diff --git a/tools/testing/selftests/alsa/.gitignore b/tools/testing/selftests/alsa/.gitignore index 12dc3fcd3456..1407fd24a97b 100644 --- a/tools/testing/selftests/alsa/.gitignore +++ b/tools/testing/selftests/alsa/.gitignore @@ -1,3 +1,5 @@ mixer-test pcm-test test-pcmtest-driver +global-timer +utimer-test diff --git a/tools/testing/selftests/filesystems/statmount/.gitignore b/tools/testing/selftests/filesystems/statmount/.gitignore index 82a4846cbc4b..66a21f289453 100644 --- a/tools/testing/selftests/filesystems/statmount/.gitignore +++ b/tools/testing/selftests/filesystems/statmount/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only /*_test +statmount_test_ns diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index da030b43e43b..2ac11b7fcb26 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -51,3 +51,5 @@ hugetlb_madv_vs_map mseal_test seal_elf droppable +hugetlb_dio +pkey_sighandler_tests* diff --git a/tools/testing/selftests/net/netfilter/.gitignore b/tools/testing/selftests/net/netfilter/.gitignore index 0a64d6d0e29a..eef8d5784e94 100644 --- a/tools/testing/selftests/net/netfilter/.gitignore +++ b/tools/testing/selftests/net/netfilter/.gitignore @@ -4,3 +4,4 @@ connect_close conntrack_dump_flush sctp_collision nf_queue +conntrack_reverse_clash -- 2.44.0

6 months, 1 week

5
7
0 0

[PATCH] munmap sealed memory cause memory to split (bug)

by jeffxu＠chromium.org

From: Jeff Xu <jeffxu(a)google.com> It appears there is a regression on the latest mm, when munmap sealed memory, it can cause unexpected VMA split. E.g. repro use this test. --- tools/testing/selftests/mm/mseal_test.c | 76 +++++++++++++++++++++++++ 1 file changed, 76 insertions(+) diff --git a/tools/testing/selftests/mm/mseal_test.c b/tools/testing/selftests/mm/mseal_test.c index fa74dbe4a684..0af33e13b606 100644 --- a/tools/testing/selftests/mm/mseal_test.c +++ b/tools/testing/selftests/mm/mseal_test.c @@ -1969,6 +1969,79 @@ static void test_madvise_filebacked_was_writable(bool seal) REPORT_TEST_PASS(); } +static void test_munmap_free_multiple_ranges_with_split(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 12 * page_size; + int ret; + int prot; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* seal the middle 4 page */ + if (seal) { + ret = sys_mseal(ptr + 4 * page_size, 4 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + size = get_vma_size(ptr, &prot); + FAIL_TEST_IF_FALSE(size == 4 * page_size); + FAIL_TEST_IF_FALSE(prot == 4); + + size = get_vma_size(ptr + 4 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 4 * page_size); + FAIL_TEST_IF_FALSE(prot == 4); + + size = get_vma_size(ptr + 8 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 4 * page_size); + FAIL_TEST_IF_FALSE(prot == 4); + } + + /* munmap 4 pages from the third page */ + ret = sys_munmap(ptr + 2 * page_size, 4 * page_size); + if (seal) { + FAIL_TEST_IF_FALSE(ret); + FAIL_TEST_IF_FALSE(errno == EPERM); + + size = get_vma_size(ptr, &prot); + FAIL_TEST_IF_FALSE(size == 4 * page_size); + FAIL_TEST_IF_FALSE(prot == 4); + + size = get_vma_size(ptr + 4 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 4 * page_size); + FAIL_TEST_IF_FALSE(prot == 4); + + size = get_vma_size(ptr + 8 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 4 * page_size); + FAIL_TEST_IF_FALSE(prot == 4); + } else + FAIL_TEST_IF_FALSE(!ret); + + /* munmap 4 pages from the sealed page */ + ret = sys_munmap(ptr + 6 * page_size, 4 * page_size); + if (seal) { + FAIL_TEST_IF_FALSE(ret); + FAIL_TEST_IF_FALSE(errno == EPERM); + + size = get_vma_size(ptr + 4 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 4 * page_size); + FAIL_TEST_IF_FALSE(prot == 4); + + size = get_vma_size(ptr + 4 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 4 * page_size); + FAIL_TEST_IF_FALSE(prot == 4); + + size = get_vma_size(ptr + 8 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 4 * page_size); + FAIL_TEST_IF_FALSE(prot == 4); + } else + FAIL_TEST_IF_FALSE(!ret); + + REPORT_TEST_PASS(); +} + + int main(int argc, char **argv) { bool test_seal = seal_support(); @@ -2099,5 +2172,8 @@ int main(int argc, char **argv) test_madvise_filebacked_was_writable(false); test_madvise_filebacked_was_writable(true); + test_munmap_free_multiple_ranges_with_split(false); + test_munmap_free_multiple_ranges_with_split(true); + ksft_finished(); } -- 2.47.0.rc1.288.g06298d1525-goog

6 months, 1 week

6
11
0 0

[PATCH v3 0/3] introduce PIDFD_SELF* sentinels

by Lorenzo Stoakes

If you wish to utilise a pidfd interface to refer to the current process or thread it is rather cumbersome, requiring something like: int pidfd = pidfd_open(getpid(), 0 or PIDFD_THREAD); ... close(pidfd); Or the equivalent call opening /proc/self. It is more convenient to use a sentinel value to indicate to an interface that accepts a pidfd that we simply wish to refer to the current process thread. This series introduces sentinels for this purposes which can be passed as the pidfd in this instance rather than having to establish a dummy fd for this purpose. It is useful to refer to both the current thread from the userland's perspective for which we use PIDFD_SELF, and the current process from the userland's perspective, for which we use PIDFD_SELF_PROCESS. There is unfortunately some confusion between the kernel and userland as to what constitutes a process - a thread from the userland perspective is a process in userland, and a userland process is a thread group (more specifically the thread group leader from the kernel perspective). We therefore alias things thusly: * PIDFD_SELF_THREAD aliased by PIDFD_SELF - use PIDTYPE_PID. * PIDFD_SELF_THREAD_GROUP alised by PIDFD_SELF_PROCESS - use PIDTYPE_TGID. In all of the kernel code we refer to PIDFD_SELF_THREAD and PIDFD_SELF_THREAD_GROUP. However we expect users to use PIDFD_SELF and PIDFD_SELF_PROCESS. This matters for cases where, for instance, a user unshare()'s FDs or does thread-specific signal handling and where the user would be hugely confused if the FDs referenced or signal processed referred to the thread group leader rather than the individual thread. We ensure that pidfd_send_signal() and pidfd_getfd() work correctly, and assert as much in selftests. All other interfaces except setns() will work implicitly with this new interface, however it doesn't make sense to test waitid(P_PIDFD, ...) as waiting on ourselves is a blocking operation. In the case of setns() we explicitly disallow use of PIDFD_SELF* as it doesn't make sense to obtain the namespaces of our own process, and it would require work to implement this functionality there that would be of no use. We also do not provide the ability to utilise PIDFD_SELF* in ordinary fd operations such as open() or poll(), as this would require extensive work and be of no real use. v3: * Do not fput() an invalid fd as reported by kernel test bot. * Fix unintended churn from moving variable declaration. v2: * Fix tests as reported by Shuah. * Correct RFC version lore link. https://lore.kernel.org/linux-mm/cover.1728643714.git.lorenzo.stoakes@oracl… Non-RFC v1: * Removed RFC tag - there seems to be general consensus that this change is a good idea, but perhaps some debate to be had on implementation. It seems sensible then to move forward with the RFC flag removed. * Introduced PIDFD_SELF_THREAD, PIDFD_SELF_THREAD_GROUP and their aliases PIDFD_SELF and PIDFD_SELF_PROCESS respectively. * Updated testing accordingly. https://lore.kernel.org/linux-mm/cover.1728578231.git.lorenzo.stoakes@oracl… RFC version: https://lore.kernel.org/linux-mm/cover.1727644404.git.lorenzo.stoakes@oracl… Lorenzo Stoakes (3): pidfd: extend pidfd_get_pid() and de-duplicate pid lookup pidfd: add PIDFD_SELF_* sentinels to refer to own thread/process selftests: pidfd: add tests for PIDFD_SELF_* include/linux/pid.h | 43 +++++- include/uapi/linux/pidfd.h | 15 ++ kernel/exit.c | 3 +- kernel/nsproxy.c | 1 + kernel/pid.c | 73 ++++++--- kernel/signal.c | 26 +--- tools/testing/selftests/pidfd/pidfd.h | 8 + .../selftests/pidfd/pidfd_getfd_test.c | 141 ++++++++++++++++++ .../selftests/pidfd/pidfd_setns_test.c | 11 ++ tools/testing/selftests/pidfd/pidfd_test.c | 76 ++++++++-- 10 files changed, 342 insertions(+), 55 deletions(-) -- 2.46.2

6 months, 1 week

3
20
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror