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

[PATCH net-next v21 04/14] mm: page_frag: avoid caller accessing 'page_frag_cache' directly

by Yunsheng Lin

Use appropriate frag_page API instead of caller accessing 'page_frag_cache' directly. 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> Acked-by: Chuck Lever <chuck.lever(a)oracle.com> --- drivers/vhost/net.c | 2 +- include/linux/page_frag_cache.h | 10 ++++++++++ net/core/skbuff.c | 6 +++--- net/rxrpc/conn_object.c | 4 +--- net/rxrpc/local_object.c | 4 +--- net/sunrpc/svcsock.c | 6 ++---- tools/testing/selftests/mm/page_frag/page_frag_test.c | 2 +- 7 files changed, 19 insertions(+), 15 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index f16279351db5..9ad37c012189 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1325,7 +1325,7 @@ static int vhost_net_open(struct inode *inode, struct file *f) vqs[VHOST_NET_VQ_RX]); f->private_data = n; - n->pf_cache.va = NULL; + page_frag_cache_init(&n->pf_cache); return 0; } diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h index 67ac8626ed9b..0a52f7a179c8 100644 --- a/include/linux/page_frag_cache.h +++ b/include/linux/page_frag_cache.h @@ -7,6 +7,16 @@ #include <linux/mm_types_task.h> #include <linux/types.h> +static inline void page_frag_cache_init(struct page_frag_cache *nc) +{ + nc->va = NULL; +} + +static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc) +{ + return !!nc->pfmemalloc; +} + 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, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 00afeb90c23a..6841e61a6bd0 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -753,14 +753,14 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, if (in_hardirq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc(nc, len, gfp_mask); - pfmemalloc = nc->pfmemalloc; + pfmemalloc = page_frag_cache_is_pfmemalloc(nc); } else { local_bh_disable(); local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc = this_cpu_ptr(&napi_alloc_cache.page); data = page_frag_alloc(nc, len, gfp_mask); - pfmemalloc = nc->pfmemalloc; + pfmemalloc = page_frag_cache_is_pfmemalloc(nc); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); local_bh_enable(); @@ -850,7 +850,7 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) len = SKB_HEAD_ALIGN(len); data = page_frag_alloc(&nc->page, len, gfp_mask); - pfmemalloc = nc->page.pfmemalloc; + pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); } local_unlock_nested_bh(&napi_alloc_cache.bh_lock); diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 1539d315afe7..694c4df7a1a3 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -337,9 +337,7 @@ static void rxrpc_clean_up_connection(struct work_struct *work) */ rxrpc_purge_queue(&conn->rx_queue); - if (conn->tx_data_alloc.va) - __page_frag_cache_drain(virt_to_page(conn->tx_data_alloc.va), - conn->tx_data_alloc.pagecnt_bias); + page_frag_cache_drain(&conn->tx_data_alloc); call_rcu(&conn->rcu, rxrpc_rcu_free_connection); } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index f9623ace2201..2792d2304605 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -452,9 +452,7 @@ void rxrpc_destroy_local(struct rxrpc_local *local) #endif rxrpc_purge_queue(&local->rx_queue); rxrpc_purge_client_connections(local); - if (local->tx_alloc.va) - __page_frag_cache_drain(virt_to_page(local->tx_alloc.va), - local->tx_alloc.pagecnt_bias); + page_frag_cache_drain(&local->tx_alloc); } /* diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 825ec5357691..b785425c3315 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1608,7 +1608,6 @@ static void svc_tcp_sock_detach(struct svc_xprt *xprt) static void svc_sock_free(struct svc_xprt *xprt) { struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); - struct page_frag_cache *pfc = &svsk->sk_frag_cache; struct socket *sock = svsk->sk_sock; trace_svcsock_free(svsk, sock); @@ -1618,8 +1617,7 @@ static void svc_sock_free(struct svc_xprt *xprt) sockfd_put(sock); else sock_release(sock); - if (pfc->va) - __page_frag_cache_drain(virt_to_head_page(pfc->va), - pfc->pagecnt_bias); + + page_frag_cache_drain(&svsk->sk_frag_cache); kfree(svsk); } 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 13c44133e009..e806c1866e36 100644 --- a/tools/testing/selftests/mm/page_frag/page_frag_test.c +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -126,7 +126,7 @@ static int __init page_frag_test_init(void) u64 duration; int ret; - test_nc.va = NULL; + page_frag_cache_init(&test_nc); atomic_set(&nthreads, 2); init_completion(&wait); -- 2.33.0

6 months, 2 weeks

1
0
0 0

[PATCH net-next v21 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 39f1d16f3628..560e2b49f98b 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, 2 weeks

1
0
0 0

[PATCH net-next v21 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, 2 weeks

1
0
0 0

[PATCH v3] lib/crc16_kunit.c: add KUnit tests for crc16

by Vinicius Peixoto

Add Kunit tests for the kernel's implementation of the standard CRC-16 algorithm (<linux/crc16.h>). The test data consists of 100 randomly-generated test cases, validated against a naive CRC-16 implementation. This test follows roughly the same logic as lib/crc32test.c, but without the performance measurements. Signed-off-by: Vinicius Peixoto <vpeixoto(a)lkcamp.dev> Co-developed-by: Enzo Bertoloti <ebertoloti(a)lkcamp.dev> Signed-off-by: Enzo Bertoloti <ebertoloti(a)lkcamp.dev> Co-developed-by: Fabricio Gasperin <fgasperin(a)lkcamp.dev> Signed-off-by: Fabricio Gasperin <fgasperin(a)lkcamp.dev> Suggested-by: David Laight <David.Laight(a)ACULAB.COM> --- This patch was developed during a hackathon organized by LKCAMP [1], with the objective of writing KUnit tests, both to introduce people to the kernel development process and to learn about different subsystems (with the positive side effect of improving the kernel test coverage, of course). We noticed there were tests for CRC32 in lib/crc32test.c and thought it would be nice to have something similar for CRC16, since it seems to be widely used in network drivers (as well as in some ext4 code). We would really appreciate any feedback/suggestions on how to improve this. Thanks! :-) Changes in v2 (suggested by David Laight): - Use the PRNG from include/linux/prandom.h to generate pseudorandom data/test cases instead of having them hardcoded as large static arrays - Add a naive CRC16 implementation used to validate the kernel's implementation (instead of having the test case results be hard-coded) - Link to v1: https://lore.kernel.org/linux-kselftest/20240922232643.535329-1-vpeixoto@lk… Changes in v3: - Fix compilation warnings about function documentation - Link to v2: https://lore.kernel.org/r/20241003-crc16-kunit-v2-1-5fe74b113e1e@lkcamp.dev [1] https://lkcamp.dev/about --- lib/Kconfig.debug | 9 ++++ lib/Makefile | 1 + lib/crc16_kunit.c | 155 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 165 insertions(+) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 7315f643817ae1021f1e4b3dd27b424f49e3f761..f9617e3054948ce43090f524dc67650e9549cee8 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2850,6 +2850,15 @@ config USERCOPY_KUNIT_TEST on the copy_to/from_user infrastructure, making sure basic user/kernel boundary testing is working. +config CRC16_KUNIT_TEST + tristate "KUnit tests for CRC16" + depends on KUNIT + default KUNIT_ALL_TESTS + select CRC16 + help + Enable this option to run unit tests for the kernel's CRC16 + implementation (<linux/crc16.h>). + config TEST_UDELAY tristate "udelay test driver" help diff --git a/lib/Makefile b/lib/Makefile index 773adf88af41665b2419202e5427e0513c6becae..1faed6414a85fd366b4966a00e8ba231d7546e14 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -389,6 +389,7 @@ CFLAGS_fortify_kunit.o += $(DISABLE_STRUCTLEAK_PLUGIN) obj-$(CONFIG_FORTIFY_KUNIT_TEST) += fortify_kunit.o obj-$(CONFIG_SIPHASH_KUNIT_TEST) += siphash_kunit.o obj-$(CONFIG_USERCOPY_KUNIT_TEST) += usercopy_kunit.o +obj-$(CONFIG_CRC16_KUNIT_TEST) += crc16_kunit.o obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o diff --git a/lib/crc16_kunit.c b/lib/crc16_kunit.c new file mode 100644 index 0000000000000000000000000000000000000000..0918c98a96d26f4e795e3eb92923db7c549ac01f --- /dev/null +++ b/lib/crc16_kunit.c @@ -0,0 +1,155 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnits tests for CRC16. + * + * Copyright (C) 2024, LKCAMP + * Author: Vinicius Peixoto <vpeixoto(a)lkcamp.dev> + * Author: Fabricio Gasperin <fgasperin(a)lkcamp.dev> + * Author: Enzo Bertoloti <ebertoloti(a)lkcamp.dev> + */ +#include <kunit/test.h> +#include <linux/crc16.h> +#include <linux/prandom.h> + +#define CRC16_KUNIT_DATA_SIZE 4096 +#define CRC16_KUNIT_TEST_SIZE 100 +#define CRC16_KUNIT_SEED 0x12345678 + +/** + * struct crc16_test - CRC16 test data + * @crc: initial input value to CRC16 + * @start: Start index within the data buffer + * @length: Length of the data + */ +static struct crc16_test { + u16 crc; + u16 start; + u16 length; +} tests[CRC16_KUNIT_TEST_SIZE]; + +u8 data[CRC16_KUNIT_DATA_SIZE]; + + +/* Naive implementation of CRC16 for validation purposes */ +static inline u16 _crc16_naive_byte(u16 crc, u8 data) +{ + u8 i = 0; + + crc ^= (u16) data; + for (i = 0; i < 8; i++) { + if (crc & 0x01) + crc = (crc >> 1) ^ 0xa001; + else + crc = crc >> 1; + } + + return crc; +} + + +static inline u16 _crc16_naive(u16 crc, u8 *buffer, size_t len) +{ + while (len--) + crc = _crc16_naive_byte(crc, *buffer++); + return crc; +} + + +/* Small helper for generating pseudorandom 16-bit data */ +static inline u16 _rand16(void) +{ + static u32 rand = CRC16_KUNIT_SEED; + + rand = next_pseudo_random32(rand); + return rand & 0xFFFF; +} + + +static int crc16_init_test_data(struct kunit_suite *suite) +{ + size_t i; + + /* Fill the data buffer with random bytes */ + for (i = 0; i < CRC16_KUNIT_DATA_SIZE; i++) + data[i] = _rand16() & 0xFF; + + /* Generate random test data while ensuring the random + * start + length values won't overflow the 4096-byte + * buffer (0x7FF * 2 = 0xFFE < 0x1000) + */ + for (size_t i = 0; i < CRC16_KUNIT_TEST_SIZE; i++) { + tests[i].crc = _rand16(); + tests[i].start = _rand16() & 0x7FF; + tests[i].length = _rand16() & 0x7FF; + } + + return 0; +} + +static void crc16_test_empty(struct kunit *test) +{ + u16 crc; + + /* The result for empty data should be the same as the + * initial crc + */ + crc = crc16(0x00, data, 0); + KUNIT_EXPECT_EQ(test, crc, 0); + crc = crc16(0xFF, data, 0); + KUNIT_EXPECT_EQ(test, crc, 0xFF); +} + +static void crc16_test_correctness(struct kunit *test) +{ + size_t i; + u16 crc, crc_naive; + + for (i = 0; i < CRC16_KUNIT_TEST_SIZE; i++) { + /* Compare results with the naive crc16 implementation */ + crc = crc16(tests[i].crc, data + tests[i].start, + tests[i].length); + crc_naive = _crc16_naive(tests[i].crc, data + tests[i].start, + tests[i].length); + KUNIT_EXPECT_EQ(test, crc, crc_naive); + } +} + + +static void crc16_test_combine(struct kunit *test) +{ + size_t i, j; + u16 crc, crc_naive; + + /* Make sure that combining two consecutive crc16 calculations + * yields the same result as calculating the crc16 for the whole thing + */ + for (i = 0; i < CRC16_KUNIT_TEST_SIZE; i++) { + crc_naive = crc16(tests[i].crc, data + tests[i].start, tests[i].length); + for (j = 0; j < tests[i].length; j++) { + crc = crc16(tests[i].crc, data + tests[i].start, j); + crc = crc16(crc, data + tests[i].start + j, tests[i].length - j); + KUNIT_EXPECT_EQ(test, crc, crc_naive); + } + } +} + + +static struct kunit_case crc16_test_cases[] = { + KUNIT_CASE(crc16_test_empty), + KUNIT_CASE(crc16_test_combine), + KUNIT_CASE(crc16_test_correctness), + {}, +}; + +static struct kunit_suite crc16_test_suite = { + .name = "crc16", + .test_cases = crc16_test_cases, + .suite_init = crc16_init_test_data, +}; +kunit_test_suite(crc16_test_suite); + +MODULE_AUTHOR("Fabricio Gasperin <fgasperin(a)lkcamp.dev>"); +MODULE_AUTHOR("Vinicius Peixoto <vpeixoto(a)lkcamp.dev>"); +MODULE_AUTHOR("Enzo Bertoloti <ebertoloti(a)lkcamp.dev>"); +MODULE_DESCRIPTION("Unit tests for crc16"); +MODULE_LICENSE("GPL"); --- base-commit: 9852d85ec9d492ebef56dc5f229416c925758edc change-id: 20241003-crc16-kunit-127a4dc2b72c Best regards, -- Vinicius Peixoto <vpeixoto(a)lkcamp.dev>

6 months, 2 weeks

1
0
0 0

[PATCH v4 00/10] iommufd support pasid attach/replace

by Yi Liu

PASID (Process Address Space ID) is a PCIe extension to tag the DMA transactions out of a physical device, and most modern IOMMU hardware have supported PASID granular address translation. So a PASID-capable device can be attached to multiple hwpts (a.k.a. domains), and each attachment is tagged with a pasid. This series is based on the preparation series [1] [2], it first adds a missing iommu API to replace the domain for a pasid. Based on the iommu pasid attach/ replace/detach APIs, this series adds iommufd APIs for device drivers to attach/replace/detach pasid to/from hwpt per userspace's request, and adds selftest to validate the iommufd APIs. While this series has a missing part which is to enforce the domain allocation with special flag if it will be used by PASID [3]. This is due to special requirements by AMD. Since it is still in mailing discussion [4], so let's mark it here. Once it's finalized, this series needs to enforce the domain flag check to ensure the AMD pasid support is not broken from day-1. The completed code can be found in the below link [5]. Heads up! The existing iommufd selftest was broken, there was a fix [6] to it, but not been upstreamed yet. If want to run the iommufd selftest, please apply that fix. Sorry for the inconvenience. [1] https://lore.kernel.org/linux-iommu/20240912130427.10119-1-yi.l.liu@intel.c… [2] https://lore.kernel.org/linux-iommu/20240912130653.11028-1-yi.l.liu@intel.c… [3] https://lore.kernel.org/linux-iommu/20240822124433.GD3468552@ziepe.ca/ [4] https://lore.kernel.org/linux-iommu/20240911101911.6269-3-vasant.hegde@amd.… [5] https://github.com/yiliu1765/iommufd/tree/iommufd_pasid [6] https://lore.kernel.org/linux-iommu/20240111073213.180020-1-baolu.lu@linux.… Change log: v4: - Replace remove_dev_pasid() by supporting set_dev_pasid() for blocking domain (Kevin) - This is done by the preparation series "Support attaching PASID to the blocked_domain" - Misc tweaks to foil the merging of the iommufd iopf series. Three new patches are added: - iommufd: Always pass iommu_attach_handle to iommu core - iommufd: Move the iommufd_handle helpers to iommufd_private.h - iommufd: Refactor __fault_domain_replace_dev() to be a wrapper of iommu_replace_group_handle() - Renmae patch 03 of v3 to be "iommufd: Support pasid attach/replace" - Add test case for attaching/replacing iopf-capable hwpt to pasid v3: https://lore.kernel.org/kvm/20240628090557.50898-1-yi.l.liu@intel.com/ - Split the set_dev_pasid op enhancements for domain replacement to be a separate series "Make set_dev_pasid op supportting domain replacement" [1]. The below changes are made in the separate series. *) set_dev_pasid() callback should keep the old config if failed to attach to a domain. This simplifies the caller a lot as caller does not need to attach it back to old domain explicitly. This also avoids some corner cases in which the core may do duplicated domain attachment as described in below link (Jason) https://lore.kernel.org/linux-iommu/BN9PR11MB52768C98314A95AFCD2FA6478C0F2@… *) Drop patch 10 of v2 as it's a bug fix and can be submitted separately (Kevin) *) Rebase on top of Baolu's domain_alloc_paging refactor series (Jason) - Drop the attach_data which includes attach_fn and pasid, insteadly passing the pasid through the device attach path. (Jason) - Add a pasid-num-bits property to mock dev to make pasid selftest work (Kevin) v2: https://lore.kernel.org/linux-iommu/20240412081516.31168-1-yi.l.liu@intel.c… - Domain replace for pasid should be handled in set_dev_pasid() callbacks instead of remove_dev_pasid and call set_dev_pasid afteward in iommu layer (Jason) - Make xarray operations more self-contained in iommufd pasid attach/replace/detach (Jason) - Tweak the dev_iommu_get_max_pasids() to allow iommu driver to populate the max_pasids. This makes the iommufd selftest simpler to meet the max_pasids check in iommu_attach_device_pasid() (Jason) v1: https://lore.kernel.org/kvm/20231127063428.127436-1-yi.l.liu@intel.com/#r - Implemnet iommu_replace_device_pasid() to fall back to the original domain if this replacement failed (Kevin) - Add check in do_attach() to check corressponding attach_fn per the pasid value. rfc: https://lore.kernel.org/linux-iommu/20230926092651.17041-1-yi.l.liu@intel.c… Regards, Yi Liu Yi Liu (10): iommu: Introduce a replace API for device pasid iommufd: Refactor __fault_domain_replace_dev() to be a wrapper of iommu_replace_group_handle() iommufd: Move the iommufd_handle helpers to iommufd_private.h iommufd: Always pass iommu_attach_handle to iommu core iommufd: Pass pasid through the device attach/replace path iommufd: Support pasid attach/replace iommufd/selftest: Add set_dev_pasid and remove_dev_pasid in mock iommu iommufd/selftest: Add a helper to get test device iommufd/selftest: Add test ops to test pasid attach/detach iommufd/selftest: Add coverage for iommufd pasid attach/detach drivers/iommu/iommu-priv.h | 4 + drivers/iommu/iommu.c | 90 +++++- drivers/iommu/iommufd/Makefile | 1 + drivers/iommu/iommufd/device.c | 46 ++-- drivers/iommu/iommufd/fault.c | 90 ++---- drivers/iommu/iommufd/hw_pagetable.c | 5 +- drivers/iommu/iommufd/iommufd_private.h | 129 ++++++++- drivers/iommu/iommufd/iommufd_test.h | 30 ++ drivers/iommu/iommufd/pasid.c | 157 +++++++++++ drivers/iommu/iommufd/selftest.c | 208 +++++++++++++- include/linux/iommufd.h | 7 + tools/testing/selftests/iommu/iommufd.c | 256 ++++++++++++++++++ .../selftests/iommu/iommufd_fail_nth.c | 29 +- tools/testing/selftests/iommu/iommufd_utils.h | 78 ++++++ 14 files changed, 1005 insertions(+), 125 deletions(-) create mode 100644 drivers/iommu/iommufd/pasid.c -- 2.34.1

6 months, 2 weeks

3
20
0 0

[GIT PULL] Kselftest fixes update for Linux 6.12-rc3

by Shuah Khan

Hi Linus, Please pull this kselftest fixes update for Linux 6.12-rc3. This kselftest update for Linux 6.12-rc3 consists of several fixes for build, run-time errors, and reporting errors: -- ftrace: regression test for a kernel crash when running function graph tracing and then enabling function profiler. -- rseq: fix for mm_cid test failure. -- vDSO: - fixes to reporting skip and other error conditions. - changes to unconditionally build chacha and getrandom tests on all architectures to make it easier for them to run in CIs. - build error when sched.h to bring in CLONE_NEWTIME define. diff is attached. Note: Had to fix a commit message last minute on rseq patch right before generating the pull request. The last 2 patches have been in my tree longer than just a few hours. :) thanks, -- Shuah ---------------------------------------------------------------- The following changes since commit c66be905cda24fb782b91053b196bd2e966f95b7: selftests: breakpoints: use remaining time to check if suspend succeed (2024-10-02 14:37:30 -0600) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest tags/linux_kselftest-fixes-6.12-rc3 for you to fetch changes up to 4ee5ca9a29384fcf3f18232fdf8474166dea8dca: ftrace/selftest: Test combination of function_graph tracer and function profiler (2024-10-11 15:05:16 -0600) ---------------------------------------------------------------- linux_kselftest-fixes-6.12-rc3 This kselftest update for Linux 6.12-rc3 consists of several fixes for build, run-time errors, and reporting errors: -- ftrace: regression test for a kernel crash when running function graph tracing and then enabling function profiler. -- rseq: fix for mm_cid test failure. -- vDSO: - fixes to reporting skip and other error conditions. - changes unconditionally build chacha and getrandom tests on all architectures to make it easier for them to run in CIs. - build error when sched.h to bring in CLONE_NEWTIME define. ---------------------------------------------------------------- Jason A. Donenfeld (3): selftests: vDSO: unconditionally build chacha test selftests: vDSO: unconditionally build getrandom test selftests: vDSO: improve getrandom and chacha error messages Mathieu Desnoyers (1): selftests/rseq: Fix mm_cid test failure Steven Rostedt (1): ftrace/selftest: Test combination of function_graph tracer and function profiler Yu Liao (1): selftests: vDSO: Explicitly include sched.h tools/arch/arm64/vdso | 1 - tools/arch/loongarch/vdso | 1 - tools/arch/powerpc/vdso | 1 - tools/arch/s390/vdso | 1 - tools/arch/x86/vdso | 1 - .../ftrace/test.d/ftrace/fgraph-profiler.tc | 31 ++++++ tools/testing/selftests/rseq/rseq.c | 110 ++++++++++++++------- tools/testing/selftests/rseq/rseq.h | 10 +- tools/testing/selftests/vDSO/Makefile | 6 +- tools/testing/selftests/vDSO/vdso_test_chacha.c | 36 ++++--- tools/testing/selftests/vDSO/vdso_test_getrandom.c | 76 +++++++------- tools/testing/selftests/vDSO/vgetrandom-chacha.S | 18 ++++ 12 files changed, 183 insertions(+), 109 deletions(-) delete mode 120000 tools/arch/arm64/vdso delete mode 120000 tools/arch/loongarch/vdso delete mode 120000 tools/arch/powerpc/vdso delete mode 120000 tools/arch/s390/vdso delete mode 120000 tools/arch/x86/vdso create mode 100644 tools/testing/selftests/ftrace/test.d/ftrace/fgraph-profiler.tc create mode 100644 tools/testing/selftests/vDSO/vgetrandom-chacha.S ----------------------------------------------------------------

6 months, 2 weeks

2
1
0 0

[PATCH v2] selftests: net/rds: add module not found

by Alessandro Zanni

This fix solves this error, when calling kselftest with targets "net/rds": The error was found by running tests manually with the command: make kselftest TARGETS="net/rds" The patch also specifies to import ip() function from the utils module. Signed-off-by: Alessandro Zanni <alessandro.zanni87(a)gmail.com> --- Notes: v2: modified the way the parent path is added added test to reproduce the error tools/testing/selftests/net/rds/test.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/rds/test.py b/tools/testing/selftests/net/rds/test.py index e6bb109bcead..4a7178d11193 100755 --- a/tools/testing/selftests/net/rds/test.py +++ b/tools/testing/selftests/net/rds/test.py @@ -14,8 +14,11 @@ import sys import atexit from pwd import getpwuid from os import stat -from lib.py import ip +# Allow utils module to be imported from different directory +this_dir = os.path.dirname(os.path.realpath(__file__)) +sys.path.append(os.path.join(this_dir, "../")) +from lib.py.utils import ip libc = ctypes.cdll.LoadLibrary('libc.so.6') setns = libc.setns -- 2.43.0

6 months, 2 weeks

3
2
0 0

[PATCH v2] selftests: drivers: net: fix name not defined

by Alessandro Zanni

This fix solves this error, when calling kselftest with targets "drivers/net": File "tools/testing/selftests/net/lib/py/nsim.py", line 64, in __init__ if e.errno == errno.ENOSPC: NameError: name 'errno' is not defined The error was found by running tests manually with the command: make kselftest TARGETS="drivers/net" The module errno makes available standard error system symbols. Reviewed-by: Petr Machata <petrm(a)nvidia.com> Signed-off-by: Alessandro Zanni <alessandro.zanni87(a)gmail.com> --- Notes: v2: added how to run the test tools/testing/selftests/net/lib/py/nsim.py | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/net/lib/py/nsim.py b/tools/testing/selftests/net/lib/py/nsim.py index f571a8b3139b..1a8cbe9acc48 100644 --- a/tools/testing/selftests/net/lib/py/nsim.py +++ b/tools/testing/selftests/net/lib/py/nsim.py @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 +import errno import json import os import random -- 2.43.0

6 months, 2 weeks

2
1
0 0

[PATCH v3 0/2] selftests/futex: Create test for robust list

by André Almeida

This patchset creates a selftest for the robust list interface, to track regressions and assure that the interface keeps working as expected. In this version I removed the kselftest_harness include, but I expanded the current futex selftest API a little bit with basic ASSERT_ macros to make the test easier to write and read. In the future, hopefully we can move all futex selftests to the kselftest_harness API anyway. Changes from v2: - Create ASSERT_ macros for futex selftests - Dropped kselftest_harness include, using just futex test API - This is the expected output: TAP version 13 1..6 ok 1 test_robustness ok 2 test_set_robust_list_invalid_size ok 3 test_get_robust_list_self ok 4 test_get_robust_list_child ok 5 test_set_list_op_pending ok 6 test_robust_list_multiple_elements # Totals: pass:6 fail:0 xfail:0 xpass:0 skip:0 error:0 https://lore.kernel.org/lkml/20240903134033.816500-1-andrealmeid@igalia.com André Almeida (2): selftests/futex: Add ASSERT_ macros selftests/futex: Create test for robust list .../selftests/futex/functional/.gitignore | 1 + .../selftests/futex/functional/Makefile | 3 +- .../selftests/futex/functional/robust_list.c | 512 ++++++++++++++++++ .../testing/selftests/futex/include/logging.h | 28 + 4 files changed, 543 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/futex/functional/robust_list.c -- 2.46.0

6 months, 2 weeks

2
3
0 0

[PATCH] selftests/ftrace: Fix check of return value in fgraph-retval.tc test

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> The addition of recording both the function name and return address to the function graph tracer updated the selftest to check for "=-5" from "= -5". But this causes the test to fail on certain configs, as "= -5" is still a value that can be returned if function addresses are not enabled (older kernels). Check for both "=-5" and " -5" as a success value. Fixes: 21e92806d39c6 ("function_graph: Support recording and printing the function return address") Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- Shuah, this update is only for changes in my tree, so you do not need to add it. tools/testing/selftests/ftrace/test.d/ftrace/fgraph-retval.tc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-retval.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-retval.tc index e8e46378b88d..4307d4eef417 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-retval.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-retval.tc @@ -29,7 +29,7 @@ set -e : "Test printing the error code in signed decimal format" echo 0 > options/funcgraph-retval-hex -count=`cat trace | grep 'proc_reg_write' | grep '=-5' | wc -l` +count=`cat trace | grep 'proc_reg_write' | grep -e '=-5 ' -e '= -5 ' | wc -l` if [ $count -eq 0 ]; then fail "Return value can not be printed in signed decimal format" fi -- 2.45.2

6 months, 2 weeks

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror