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

[PATCH net-next v15 04/13] 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 1748673e1fe0..9352fcf8cda3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -752,14 +752,14 @@ 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(); @@ -849,7 +849,7 @@ 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 504453c688d7..a8cffe47cf01 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 6b3f01beb294..dcfd84cf0694 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1609,7 +1609,6 @@ 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); @@ -1619,8 +1618,7 @@ 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 4a009122991e..c52598eaf7e7 100644 --- a/tools/testing/selftests/mm/page_frag/page_frag_test.c +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -117,7 +117,7 @@ static int __init page_frag_test_init(void) u64 duration; int ret; - test_frag.va = NULL; + page_frag_cache_init(&test_frag); atomic_set(&nthreads, 2); init_completion(&wait); -- 2.33.0

1 year, 2 months

1
0
0 0

[PATCH net-next v15 02/13] mm: move the page fragment allocator from page_alloc into its own file

by Yunsheng Lin

Inspired by [1], move the page fragment allocator from page_alloc into its own c file and header file, as we are about to make more change for it to replace another page_frag implementation in sock.c As this patchset is going to replace 'struct page_frag' with 'struct page_frag_cache' in sched.h, including page_frag_cache.h in sched.h has a compiler error caused by interdependence between mm_types.h and mm.h for asm-offsets.c, see [2]. So avoid the compiler error by moving 'struct page_frag_cache' to mm_types_task.h as suggested by Alexander, see [3]. 1. https://lore.kernel.org/all/20230411160902.4134381-3-dhowells@redhat.com/ 2. https://lore.kernel.org/all/15623dac-9358-4597-b3ee-3694a5956920@gmail.com/ 3. https://lore.kernel.org/all/CAKgT0UdH1yD=LSCXFJ=YM_aiA4OomD-2wXykO42bizaWMt… CC: David Howells <dhowells(a)redhat.com> CC: Alexander Duyck <alexander.duyck(a)gmail.com> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> Acked-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/gfp.h | 22 --- include/linux/mm_types.h | 18 --- include/linux/mm_types_task.h | 18 +++ include/linux/page_frag_cache.h | 31 ++++ include/linux/skbuff.h | 1 + mm/Makefile | 1 + mm/page_alloc.c | 136 ---------------- mm/page_frag_cache.c | 145 ++++++++++++++++++ .../selftests/mm/page_frag/page_frag_test.c | 2 +- 9 files changed, 197 insertions(+), 177 deletions(-) create mode 100644 include/linux/page_frag_cache.h create mode 100644 mm/page_frag_cache.c diff --git a/include/linux/gfp.h b/include/linux/gfp.h index f53f76e0b17e..01a49be7c98d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -371,28 +371,6 @@ __meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mas extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); -struct page_frag_cache; -void page_frag_cache_drain(struct page_frag_cache *nc); -extern void __page_frag_cache_drain(struct page *page, unsigned int count); -void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, - gfp_t gfp_mask, unsigned int align_mask); - -static inline void *page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align) -{ - WARN_ON_ONCE(!is_power_of_2(align)); - return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); -} - -static inline void *page_frag_alloc(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask) -{ - return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); -} - -extern void page_frag_free(void *addr); - #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 485424979254..843d75412105 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -521,9 +521,6 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); */ #define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page))) -#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) -#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) - /* * page_private can be used on tail pages. However, PagePrivate is only * checked by the VM on the head page. So page_private on the tail pages @@ -542,21 +539,6 @@ static inline void *folio_get_private(struct folio *folio) return folio->private; } -struct page_frag_cache { - void * va; -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - __u16 offset; - __u16 size; -#else - __u32 offset; -#endif - /* we maintain a pagecount bias, so that we dont dirty cache line - * containing page->_refcount every time we allocate a fragment. - */ - unsigned int pagecnt_bias; - bool pfmemalloc; -}; - typedef unsigned long vm_flags_t; /* diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index a2f6179b672b..cdc1e3696439 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -8,6 +8,7 @@ * (These are defined separately to decouple sched.h from mm_types.h as much as possible.) */ +#include <linux/align.h> #include <linux/types.h> #include <asm/page.h> @@ -46,6 +47,23 @@ struct page_frag { #endif }; +#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) +#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) +struct page_frag_cache { + void *va; +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + __u16 offset; + __u16 size; +#else + __u32 offset; +#endif + /* we maintain a pagecount bias, so that we dont dirty cache line + * containing page->_refcount every time we allocate a fragment. + */ + unsigned int pagecnt_bias; + bool pfmemalloc; +}; + /* Track pages that require TLB flushes */ struct tlbflush_unmap_batch { #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h new file mode 100644 index 000000000000..67ac8626ed9b --- /dev/null +++ b/include/linux/page_frag_cache.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_PAGE_FRAG_CACHE_H +#define _LINUX_PAGE_FRAG_CACHE_H + +#include <linux/log2.h> +#include <linux/mm_types_task.h> +#include <linux/types.h> + +void page_frag_cache_drain(struct page_frag_cache *nc); +void __page_frag_cache_drain(struct page *page, unsigned int count); +void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, + gfp_t gfp_mask, unsigned int align_mask); + +static inline void *page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align) +{ + WARN_ON_ONCE(!is_power_of_2(align)); + return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); +} + +static inline void *page_frag_alloc(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask) +{ + return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); +} + +void page_frag_free(void *addr); + +#endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cf8f6ce06742..7482997c719f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -31,6 +31,7 @@ #include <linux/in6.h> #include <linux/if_packet.h> #include <linux/llist.h> +#include <linux/page_frag_cache.h> #include <net/flow.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> diff --git a/mm/Makefile b/mm/Makefile index d2915f8c9dc0..e9d342fa8058 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -65,6 +65,7 @@ page-alloc-$(CONFIG_SHUFFLE_PAGE_ALLOCATOR) += shuffle.o memory-hotplug-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-y += page-alloc.o +obj-y += page_frag_cache.o obj-y += init-mm.o obj-y += memblock.o obj-y += $(memory-hotplug-y) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c565de8f48e9..d0e88aa6eb0d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4798,142 +4798,6 @@ void free_pages(unsigned long addr, unsigned int order) EXPORT_SYMBOL(free_pages); -/* - * Page Fragment: - * An arbitrary-length arbitrary-offset area of memory which resides - * within a 0 or higher order page. Multiple fragments within that page - * are individually refcounted, in the page's reference counter. - * - * The page_frag functions below provide a simple allocation framework for - * page fragments. This is used by the network stack and network device - * drivers to provide a backing region of memory for use as either an - * sk_buff->head, or to be used in the "frags" portion of skb_shared_info. - */ -static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, - gfp_t gfp_mask) -{ - struct page *page = NULL; - gfp_t gfp = gfp_mask; - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | - __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; - page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, - PAGE_FRAG_CACHE_MAX_ORDER); - nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; -#endif - if (unlikely(!page)) - page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); - - nc->va = page ? page_address(page) : NULL; - - return page; -} - -void page_frag_cache_drain(struct page_frag_cache *nc) -{ - if (!nc->va) - return; - - __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); - nc->va = NULL; -} -EXPORT_SYMBOL(page_frag_cache_drain); - -void __page_frag_cache_drain(struct page *page, unsigned int count) -{ - VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); - - if (page_ref_sub_and_test(page, count)) - free_unref_page(page, compound_order(page)); -} -EXPORT_SYMBOL(__page_frag_cache_drain); - -void *__page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align_mask) -{ - unsigned int size = PAGE_SIZE; - struct page *page; - int offset; - - if (unlikely(!nc->va)) { -refill: - page = __page_frag_cache_refill(nc, gfp_mask); - if (!page) - return NULL; - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - /* if size can vary use size else just use PAGE_SIZE */ - size = nc->size; -#endif - /* Even if we own the page, we do not use atomic_set(). - * This would break get_page_unless_zero() users. - */ - page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); - - /* reset page count bias and offset to start of new frag */ - nc->pfmemalloc = page_is_pfmemalloc(page); - nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; - nc->offset = size; - } - - offset = nc->offset - fragsz; - if (unlikely(offset < 0)) { - page = virt_to_page(nc->va); - - if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) - goto refill; - - if (unlikely(nc->pfmemalloc)) { - free_unref_page(page, compound_order(page)); - goto refill; - } - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - /* if size can vary use size else just use PAGE_SIZE */ - size = nc->size; -#endif - /* OK, page count is 0, we can safely set it */ - set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); - - /* reset page count bias and offset to start of new frag */ - nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; - offset = size - fragsz; - if (unlikely(offset < 0)) { - /* - * The caller is trying to allocate a fragment - * with fragsz > PAGE_SIZE but the cache isn't big - * enough to satisfy the request, this may - * happen in low memory conditions. - * We don't release the cache page because - * it could make memory pressure worse - * so we simply return NULL here. - */ - return NULL; - } - } - - nc->pagecnt_bias--; - offset &= align_mask; - nc->offset = offset; - - return nc->va + offset; -} -EXPORT_SYMBOL(__page_frag_alloc_align); - -/* - * Frees a page fragment allocated out of either a compound or order 0 page. - */ -void page_frag_free(void *addr) -{ - struct page *page = virt_to_head_page(addr); - - if (unlikely(put_page_testzero(page))) - free_unref_page(page, compound_order(page)); -} -EXPORT_SYMBOL(page_frag_free); - static void *make_alloc_exact(unsigned long addr, unsigned int order, size_t size) { diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c new file mode 100644 index 000000000000..609a485cd02a --- /dev/null +++ b/mm/page_frag_cache.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Page fragment allocator + * + * Page Fragment: + * An arbitrary-length arbitrary-offset area of memory which resides within a + * 0 or higher order page. Multiple fragments within that page are + * individually refcounted, in the page's reference counter. + * + * The page_frag functions provide a simple allocation framework for page + * fragments. This is used by the network stack and network device drivers to + * provide a backing region of memory for use as either an sk_buff->head, or to + * be used in the "frags" portion of skb_shared_info. + */ + +#include <linux/export.h> +#include <linux/gfp_types.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/page_frag_cache.h> +#include "internal.h" + +static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, + gfp_t gfp_mask) +{ + struct page *page = NULL; + gfp_t gfp = gfp_mask; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | + __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; + page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, + PAGE_FRAG_CACHE_MAX_ORDER); + nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; +#endif + if (unlikely(!page)) + page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); + + nc->va = page ? page_address(page) : NULL; + + return page; +} + +void page_frag_cache_drain(struct page_frag_cache *nc) +{ + if (!nc->va) + return; + + __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); + nc->va = NULL; +} +EXPORT_SYMBOL(page_frag_cache_drain); + +void __page_frag_cache_drain(struct page *page, unsigned int count) +{ + VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); + + if (page_ref_sub_and_test(page, count)) + free_unref_page(page, compound_order(page)); +} +EXPORT_SYMBOL(__page_frag_cache_drain); + +void *__page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align_mask) +{ + unsigned int size = PAGE_SIZE; + struct page *page; + int offset; + + if (unlikely(!nc->va)) { +refill: + page = __page_frag_cache_refill(nc, gfp_mask); + if (!page) + return NULL; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size = nc->size; +#endif + /* Even if we own the page, we do not use atomic_set(). + * This would break get_page_unless_zero() users. + */ + page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); + + /* reset page count bias and offset to start of new frag */ + nc->pfmemalloc = page_is_pfmemalloc(page); + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; + nc->offset = size; + } + + offset = nc->offset - fragsz; + if (unlikely(offset < 0)) { + page = virt_to_page(nc->va); + + if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) + goto refill; + + if (unlikely(nc->pfmemalloc)) { + free_unref_page(page, compound_order(page)); + goto refill; + } + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size = nc->size; +#endif + /* OK, page count is 0, we can safely set it */ + set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); + + /* reset page count bias and offset to start of new frag */ + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; + offset = size - fragsz; + if (unlikely(offset < 0)) { + /* + * The caller is trying to allocate a fragment + * with fragsz > PAGE_SIZE but the cache isn't big + * enough to satisfy the request, this may + * happen in low memory conditions. + * We don't release the cache page because + * it could make memory pressure worse + * so we simply return NULL here. + */ + return NULL; + } + } + + nc->pagecnt_bias--; + offset &= align_mask; + nc->offset = offset; + + return nc->va + offset; +} +EXPORT_SYMBOL(__page_frag_alloc_align); + +/* + * Frees a page fragment allocated out of either a compound or order 0 page. + */ +void page_frag_free(void *addr) +{ + struct page *page = virt_to_head_page(addr); + + if (unlikely(put_page_testzero(page))) + free_unref_page(page, compound_order(page)); +} +EXPORT_SYMBOL(page_frag_free); diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c index 0e803db1ad79..4a009122991e 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: linyunsheng(a)huawei.com */ -#include <linux/mm.h> #include <linux/module.h> #include <linux/cpumask.h> #include <linux/completion.h> #include <linux/ptr_ring.h> #include <linux/kthread.h> +#include <linux/page_frag_cache.h> static struct ptr_ring ptr_ring; static int nr_objs = 512; -- 2.33.0

1 year, 2 months

1
0
0 0

[PATCH rc 0/2] Fix maps created without READ or WRITE

by Jason Gunthorpe

I noticed some bugs here while working on iommupt. Fix them up. Joerg, can you pick this both for your -rc branch? Thanks, Jason Jason Gunthorpe (2): iommufd: Do not allow creating areas without READ or WRITE iommu: Do not return 0 from map_pages if it doesn't do anything drivers/iommu/io-pgtable-arm-v7s.c | 3 +-- drivers/iommu/io-pgtable-arm.c | 3 +-- drivers/iommu/io-pgtable-dart.c | 3 +-- drivers/iommu/iommufd/ioas.c | 8 ++++++++ tools/testing/selftests/iommu/iommufd.c | 6 +++--- 5 files changed, 14 insertions(+), 9 deletions(-) base-commit: 4be8b00b2b0f669989486e9f2fb9b65edb4ef8c4 -- 2.46.0

1 year, 2 months

5
7
0 0

[PATCH v5 0/4] Allow userspace to change ID_AA64PFR1_EL1

by Shaoqin Huang

Hi guys, This is another try to allow userspace to change ID_AA64PFR1_EL1, and we want to give userspace the ability to control the visible feature set for a VM, which could be used by userspace in such a way to transparently migrate VMs. The patch series have four part: The first patch disable those fields which KVM doesn't know how to handle, so KVM will only expose value 0 of those fields to the guest. The second patch check the FEAT_SSBS in guest IDREG instead of the cpu capability. The third patch allow userspace to change ID_AA64PFR1_EL1, it only advertise the fields known to KVM and leave others unadvertise. The fourth patch adds the kselftest to test if userspace can change the ID_AA64PFR1_EL1. Besides, I also noticed there is another patch [1] which try to make the ID_AA64PFR1_EL1 writable. This patch [1] is try to enable GCS on baremental, and add GCS support for the guest. What I understand is if we have GCS support on baremental, it will be clear to how to handle them in KVM. And same for other fields like NMI, THE, DF2, MTEX.. At that time, they can be writable. [1] [PATCH v9 13/39] KVM: arm64: Manage GCS registers for guests https://lore.kernel.org/all/20240625-arm64-gcs-v9-13-0f634469b8f0@kernel.or… Changelog: ---------- v4 -> v5: * Only advertise fields which KVM know how to handle to userspace, leave others unadvertised. * Add a new patch to check FEAT_SSBS in IDREG instead of cpu capability. * Tweak the kselftest writable fields. * Improve the commit message. v3 -> v4: * Add a new patch to disable some feature which KVM doesn't know how to handle in the register accessor. * Handle all the fields in the register. * Fixes a small cnt issue in kselftest. v2 -> v3: * Give more description about why only part of the fields can be writable. * Updated the writable mask by referring the latest ARM spec. v1 -> v2: * Tackling the full register instead of single field. * Changing the patch title and commit message. RFCv1 -> v1: * Fix the compilation error. * Delete the machine specific information and make the description more generable. RFCv1: https://lore.kernel.org/all/20240612023553.127813-1-shahuang@redhat.com/ v1: https://lore.kernel.org/all/20240617075131.1006173-1-shahuang@redhat.com/ v2: https://lore.kernel.org/all/20240618063808.1040085-1-shahuang@redhat.com/ v3: https://lore.kernel.org/all/20240628060454.1936886-2-shahuang@redhat.com/ v4: https://lore.kernel.org/all/20240718035017.434996-1-shahuang@redhat.com/ Shaoqin Huang (4): KVM: arm64: Disable fields that KVM doesn't know how to handle in ID_AA64PFR1_EL1 KVM: arm64: Use kvm_has_feat() to check if FEAT_SSBS is advertised to the guest KVM: arm64: Allow userspace to change ID_AA64PFR1_EL1 KVM: selftests: aarch64: Add writable test for ID_AA64PFR1_EL1 arch/arm64/kvm/hypercalls.c | 12 +++++----- arch/arm64/kvm/sys_regs.c | 22 ++++++++++++++++++- .../selftests/kvm/aarch64/set_id_regs.c | 14 +++++++++--- 3 files changed, 38 insertions(+), 10 deletions(-) -- 2.40.1

1 year, 2 months

3
6
0 0

[PATCH bpf-next 0/2] selftests: bpf: avoid duplicated UAPI headers

by Matthieu Baerts (NGI0)

If a BPF selftest program requires (recent) UAPI headers [1], it is currently needed to duplicate these header files into tools/include/uapi. That's not a good solution, because it is a duplication that needs to be kept up-to-date, while the required files are only a few directories away. A solution to avoid these duplicated files is to use the KHDR_INCLUDES from the kselftest infrastructure. That is what is being done in the first patch. The second patch removes 'if_xdp.h', which is no longer needed, and was causing a warning when building the libbpf required by the BPF selftests. There could be more duplicated UAPI header files that could be removed, but I didn't spend too much time checking which ones are not used by anything else from the 'tools' directory. Hopefully, these modifications should not cause any issues on the different CIs, because it is using the recommended method for the kernel selftests. If this causes issues on the CIs side, it should be easy to fix by overriding the KHDR_INCLUDES variable, and it might be better to do that, because it likely means the CI is not following the recommended way to execute the kernel selftests. See patch 1/2 for more details about that. Link: https://lore.kernel.org/all/08f925cd-e267-4a6b-84b1-792515c4e199@kernel.org… [1] Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Matthieu Baerts (NGI0) (2): selftests: bpf: use KHDR_INCLUDES for the UAPI headers selftests: bpf: remove duplicated UAPI if_xdp headers tools/include/uapi/linux/if_xdp.h | 173 --------------------- tools/lib/bpf/Makefile | 3 - tools/testing/selftests/bpf/Makefile | 2 +- .../selftests/bpf/prog_tests/assign_reuse.c | 2 +- tools/testing/selftests/bpf/prog_tests/tc_links.c | 4 +- tools/testing/selftests/bpf/prog_tests/tc_netkit.c | 2 +- tools/testing/selftests/bpf/prog_tests/tc_opts.c | 2 +- .../selftests/bpf/prog_tests/user_ringbuf.c | 2 +- .../testing/selftests/bpf/prog_tests/xdp_bonding.c | 2 +- .../selftests/bpf/prog_tests/xdp_cpumap_attach.c | 2 +- .../selftests/bpf/prog_tests/xdp_devmap_attach.c | 2 +- .../selftests/bpf/prog_tests/xdp_do_redirect.c | 2 +- tools/testing/selftests/bpf/prog_tests/xdp_link.c | 2 +- tools/testing/selftests/bpf/xdp_features.c | 4 +- 14 files changed, 14 insertions(+), 190 deletions(-) --- base-commit: fdf1c728fac541891ef1aa773bfd42728626769c change-id: 20240816-ups-bpf-next-selftests-use-khdr-28f935c8848a Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

1 year, 2 months

3
7
0 0

[PATCH v2] selftests: fix relative rpath usage

by Eugene Syromiatnikov

The relative RPATH ("./") supplied to linker options in CFLAGS is resolved relative to current working directory and not the executable directory, which will lead in incorrect resolution when the test executables are run from elsewhere. Changing it to $ORIGIN makes it resolve relative to the directory in which the executables reside, which is supposedly the desired behaviour. This patch also moves these CFLAGS to lib.mk, so the RPATH is provided for all selftest binaries, which is arguably a useful default. Comparison of find -type f -perm /111 -print0 | sort -z | xargs -0 ldd 2>&1 | sed 's/([^)]*)//' output before and after the change shows that only the binaries that previously used RPATH of "," are affected and that the linker now able to find the used dynamic libraries when the executable invoked outside directory it resides in: $ diff -U 0 old_ldd new_ldd --- old_ldd 2024-08-12 08:00:16.093535910 -0400 +++ new_ldd 2024-08-09 09:58:22.657883491 -0400 @@ -10 +10 @@ - libatest.so => not found + libatest.so => /home/build/linux/tools/testing/selftests/./alsa/libatest.so @@ -17 +17 @@ - libatest.so => not found + libatest.so => /home/build/linux/tools/testing/selftests/./alsa/libatest.so @@ -24 +24 @@ - libatest.so => not found + libatest.so => /home/build/linux/tools/testing/selftests/./alsa/libatest.so @@ -119 +119 @@ - liburandom_read.so => not found + liburandom_read.so => /home/build/linux/tools/testing/selftests/./bpf/no_alu32/liburandom_read.so @@ -445 +445 @@ - liburandom_read.so => not found + liburandom_read.so => /home/build/linux/tools/testing/selftests/./bpf/liburandom_read.so @@ -3321 +3321 @@ - librseq.so => not found + librseq.so => /home/build/linux/tools/testing/selftests/./rseq/librseq.so @@ -3326 +3326 @@ - librseq.so => not found + librseq.so => /home/build/linux/tools/testing/selftests/./rseq/librseq.so @@ -3331 +3331 @@ - librseq.so => not found + librseq.so => /home/build/linux/tools/testing/selftests/./rseq/librseq.so @@ -3340 +3340 @@ - librseq.so => not found + librseq.so => /home/build/linux/tools/testing/selftests/./rseq/librseq.so @@ -3345 +3345 @@ - librseq.so => not found + librseq.so => /home/build/linux/tools/testing/selftests/./rseq/librseq.so @@ -3350 +3350 @@ - librseq.so => not found + librseq.so => /home/build/linux/tools/testing/selftests/./rseq/librseq.so @@ -3355 +3355 @@ - librseq.so => not found + librseq.so => /home/build/linux/tools/testing/selftests/./rseq/librseq.so @@ -3360 +3360 @@ - librseq.so => not found + librseq.so => /home/build/linux/tools/testing/selftests/./rseq/librseq.so @@ -3365 +3365 @@ - librseq.so => not found + librseq.so => /home/build/linux/tools/testing/selftests/./rseq/librseq.so Some minimal testing is done to verify that it does not affect the tests: alsa, rseq, and sched (which also had the RPATH tag but didn't actually link against any locally built libraries) selftests are run successfully before and after the change; for the rest of the selftests, there was no regression observed as well. Discovered by the check-rpaths script[1][2] that checks for insecure RPATH/RUNPATH[3], such as relative directories, during an attempt to package BPF selftests for later use in CI: ERROR 0004: file '/usr/libexec/kselftests/bpf/urandom_read' contains an insecure runpath '.' in [.] [1] https://github.com/rpm-software-management/rpm/blob/master/scripts/check-rp… [2] https://github.com/rpm-software-management/rpm/blob/master/scripts/check-rp… [3] https://cwe.mitre.org/data/definitions/426.html Signed-off-by: Eugene Syromiatnikov <esyr(a)redhat.com> --- v2: - Consolidated the updated -L/-Wl,-rpath setting into lib.mk - Described the testing done in the commit message v1: https://lore.kernel.org/lkml/20240808145639.GA20510@asgard.redhat.com/ https://lore.kernel.org/lkml/20240808151335.GA5495@asgard.redhat.com/ https://lore.kernel.org/lkml/20240808151621.GA10025@asgard.redhat.com/ https://lore.kernel.org/lkml/20240808151621.GA10025@asgard.redhat.com/ --- tools/testing/selftests/alsa/Makefile | 1 - tools/testing/selftests/bpf/Makefile | 5 ++--- tools/testing/selftests/lib.mk | 3 +++ tools/testing/selftests/rseq/Makefile | 2 +- tools/testing/selftests/sched/Makefile | 3 +-- 5 files changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile index c1ce39874e2b..68a1651360e5 100644 --- a/tools/testing/selftests/alsa/Makefile +++ b/tools/testing/selftests/alsa/Makefile @@ -6,7 +6,6 @@ LDLIBS += $(shell pkg-config --libs alsa) ifeq ($(LDLIBS),) LDLIBS += -lasound endif -CFLAGS += -L$(OUTPUT) -Wl,-rpath=./ LDLIBS+=-lpthread diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 81d4757ecd4c..a152c12b8a3b 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -239,9 +239,8 @@ $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_r $(call msg,BINARY,,$@) $(Q)$(CLANG) $(CLANG_TARGET_ARCH) \ $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $(filter %.c,$^) \ - -lurandom_read $(filter-out -static,$(LDLIBS)) -L$(OUTPUT) \ - -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \ - -Wl,-rpath=. -o $@ + -lurandom_read $(filter-out -static,$(LDLIBS)) \ + -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 -o $@ $(OUTPUT)/sign-file: ../../../../scripts/sign-file.c $(call msg,SIGN-FILE,,$@) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index d6edcfcb5be8..d75a20bb569c 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -199,6 +199,9 @@ clean: $(if $(TEST_GEN_MODS_DIR),clean_mods_dir) # Build with _GNU_SOURCE by default CFLAGS += -D_GNU_SOURCE= +# Simplify usage of libraries built alongside the test executables +CFLAGS += -L$(OUTPUT) -Wl,-rpath=\$$ORIGIN/ + # Enables to extend CFLAGS and LDFLAGS from command line, e.g. # make USERCFLAGS=-Werror USERLDFLAGS=-static CFLAGS += $(USERCFLAGS) diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 5a3432fceb58..887b45d4a675 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -6,7 +6,7 @@ endif top_srcdir = ../../../.. -CFLAGS += -O2 -Wall -g -I./ $(KHDR_INCLUDES) -L$(OUTPUT) -Wl,-rpath=./ \ +CFLAGS += -O2 -Wall -g -I./ $(KHDR_INCLUDES) \ $(CLANG_FLAGS) -I$(top_srcdir)/tools/include LDLIBS += -lpthread -ldl diff --git a/tools/testing/selftests/sched/Makefile b/tools/testing/selftests/sched/Makefile index 099ee9213557..0e4581ded9d6 100644 --- a/tools/testing/selftests/sched/Makefile +++ b/tools/testing/selftests/sched/Makefile @@ -4,8 +4,7 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) CLANG_FLAGS += -no-integrated-as endif -CFLAGS += -O2 -Wall -g -I./ $(KHDR_INCLUDES) -Wl,-rpath=./ \ - $(CLANG_FLAGS) +CFLAGS += -O2 -Wall -g -I./ $(KHDR_INCLUDES) $(CLANG_FLAGS) LDLIBS += -lpthread TEST_GEN_FILES := cs_prctl_test -- 2.28.0

1 year, 2 months

4
7
0 0

[PATCH v2] selftests/ftrace: Skip test for optimized probes on PowerPC if Secure Boot is enabled

by Akanksha J N

Currently while accessing debugfs with Secure Boot enabled on PowerPC, it is causing the kprobe_opt_types.tc test to fail. Below is the snippet of the error: +++ grep kernel_clone /sys/kernel/debug/kprobes/list grep: /sys/kernel/debug/kprobes/list: Operation not permitted ++ PROBE= + '[' 2 -ne 0 ']' + kill -s 37 7595 ++ SIG_RESULT=1 + eval_result 1 + case $1 in + prlog ' [\033[31mFAIL\033[0m]' + newline='\n' + '[' ' [\033[31mFAIL\033[0m]' = -n ']' + printf ' [\033[31mFAIL\033[0m]\n' [FAIL] This is happening when secure boot is enabled, as it enables lockdown by default. With lockdown, access to certain debug features and filesystems like debugfs may be restricted or completely disabled. To fix this, modify the test to check for Secure Boot status using lsprop /proc/device-tree/ibm,secure-boot. And, skip execution of the test on PowerPC if Secure Boot is enabled (00000002). With this patch, test skips as unsupported: === Ftrace unit tests === [1] Register/unregister optimized probe [UNSUPPORTED] Signed-off-by: Akanksha J N <akanksha(a)linux.ibm.com> --- .../selftests/ftrace/test.d/kprobe/kprobe_opt_types.tc | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_opt_types.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_opt_types.tc index 9f5d99328086..925e74d6acc7 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_opt_types.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_opt_types.tc @@ -10,6 +10,11 @@ x86_64) arm*) ;; ppc*) + lsprop_output=$(lsprop /proc/device-tree/ibm,secure-boot) + if echo "$lsprop_output" | grep -q "00000002"; then + echo "Secure Boot is enabled on PowerPC." + exit_unsupported + fi ;; *) echo "Please implement other architecture here" -- 2.45.2

1 year, 2 months

2
1
0 0

[PATCH RESEND v5] rust: str: Use `core::CStr`, remove the custom `CStr` implementation

by Michal Rostecki

From: Michal Rostecki <vadorovsky(a)gmail.com> `CStr` became a part of `core` library in Rust 1.75. This change replaces the custom `CStr` implementation with the one from `core`. `core::CStr` behaves generally the same as the removed implementation, with the following differences: - It does not implement `Display`. - It does not provide `from_bytes_with_nul_unchecked_mut` method. - It has `as_ptr()` method instead of `as_char_ptr()`, which also returns `*const c_char`. The first two differences are handled by providing the `CStrExt` trait, with `display()` and `from_bytes_with_nul_unchecked_mut()` methods. `display()` returns a `CStrDisplay` wrapper, with a custom `Display` implementation. `DerefMut` implementation for `CString` is removed here, as it's not being used anywhere. Signed-off-by: Michal Rostecki <vadorovsky(a)gmail.com> --- rust/kernel/error.rs | 7 +- rust/kernel/kunit.rs | 18 +- rust/kernel/net/phy.rs | 2 +- rust/kernel/prelude.rs | 4 +- rust/kernel/str.rs | 465 ++++++------------------------------ rust/kernel/sync/condvar.rs | 5 +- rust/kernel/sync/lock.rs | 6 +- rust/kernel/workqueue.rs | 2 +- scripts/rustdoc_test_gen.rs | 4 +- 9 files changed, 93 insertions(+), 420 deletions(-) diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs index 6f1587a2524e..6a2bb11ac09c 100644 --- a/rust/kernel/error.rs +++ b/rust/kernel/error.rs @@ -4,10 +4,11 @@ //! //! C header: [`include/uapi/asm-generic/errno-base.h`](srctree/include/uapi/asm-generic/errno-base.h) -use crate::{alloc::AllocError, str::CStr}; +use crate::alloc::AllocError; use alloc::alloc::LayoutError; +use core::ffi::CStr; use core::fmt; use core::num::TryFromIntError; use core::str::Utf8Error; @@ -151,7 +152,7 @@ pub fn name(&self) -> Option<&'static CStr> { None } else { // SAFETY: The string returned by `errname` is static and `NUL`-terminated. - Some(unsafe { CStr::from_char_ptr(ptr) }) + Some(unsafe { CStr::from_ptr(ptr) }) } } @@ -173,7 +174,7 @@ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { None => f.debug_tuple("Error").field(&-self.0).finish(), // SAFETY: These strings are ASCII-only. Some(name) => f - .debug_tuple(unsafe { core::str::from_utf8_unchecked(name) }) + .debug_tuple(unsafe { core::str::from_utf8_unchecked(name.to_bytes()) }) .finish(), } } diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs index 0ba77276ae7e..79a50ab59af0 100644 --- a/rust/kernel/kunit.rs +++ b/rust/kernel/kunit.rs @@ -56,13 +56,15 @@ macro_rules! kunit_assert { break 'out; } - static FILE: &'static $crate::str::CStr = $crate::c_str!($file); + static FILE: &'static core::ffi::CStr = $file; static LINE: i32 = core::line!() as i32 - $diff; - static CONDITION: &'static $crate::str::CStr = $crate::c_str!(stringify!($condition)); + static CONDITION: &'static core::ffi::CStr = $crate::c_str!(stringify!($condition)); // SAFETY: FFI call without safety requirements. let kunit_test = unsafe { $crate::bindings::kunit_get_current_test() }; if kunit_test.is_null() { + use kernel::str::CStrExt; + // The assertion failed but this task is not running a KUnit test, so we cannot call // KUnit, but at least print an error to the kernel log. This may happen if this // macro is called from an spawned thread in a test (see @@ -71,11 +73,13 @@ macro_rules! kunit_assert { // // This mimics KUnit's failed assertion format. $crate::kunit::err(format_args!( - " # {}: ASSERTION FAILED at {FILE}:{LINE}\n", - $name + " # {}: ASSERTION FAILED at {}:{LINE}\n", + $name.display(), + FILE.display(), )); $crate::kunit::err(format_args!( - " Expected {CONDITION} to be true, but is false\n" + " Expected {} to be true, but is false\n", + CONDITION.display(), )); $crate::kunit::err(format_args!( " Failure not reported to KUnit since this is a non-KUnit task\n" @@ -98,12 +102,12 @@ unsafe impl Sync for Location {} unsafe impl Sync for UnaryAssert {} static LOCATION: Location = Location($crate::bindings::kunit_loc { - file: FILE.as_char_ptr(), + file: FILE.as_ptr(), line: LINE, }); static ASSERTION: UnaryAssert = UnaryAssert($crate::bindings::kunit_unary_assert { assert: $crate::bindings::kunit_assert {}, - condition: CONDITION.as_char_ptr(), + condition: CONDITION.as_ptr(), expected_true: true, }); diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs index fd40b703d224..19f45922ec42 100644 --- a/rust/kernel/net/phy.rs +++ b/rust/kernel/net/phy.rs @@ -502,7 +502,7 @@ unsafe impl Sync for DriverVTable {} pub const fn create_phy_driver<T: Driver>() -> DriverVTable { // INVARIANT: All the fields of `struct phy_driver` are initialized properly. DriverVTable(Opaque::new(bindings::phy_driver { - name: T::NAME.as_char_ptr().cast_mut(), + name: T::NAME.as_ptr().cast_mut(), flags: T::FLAGS, phy_id: T::PHY_DEVICE_ID.id, phy_id_mask: T::PHY_DEVICE_ID.mask_as_int(), diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs index b37a0b3180fb..b0969ca78f10 100644 --- a/rust/kernel/prelude.rs +++ b/rust/kernel/prelude.rs @@ -12,7 +12,7 @@ //! ``` #[doc(no_inline)] -pub use core::pin::Pin; +pub use core::{ffi::CStr, pin::Pin}; pub use crate::alloc::{box_ext::BoxExt, flags::*, vec_ext::VecExt}; @@ -35,7 +35,7 @@ pub use super::error::{code::*, Error, Result}; -pub use super::{str::CStr, ThisModule}; +pub use super::ThisModule; pub use super::init::{InPlaceInit, Init, PinInit}; diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs index bb8d4f41475b..97a298a44b96 100644 --- a/rust/kernel/str.rs +++ b/rust/kernel/str.rs @@ -4,8 +4,9 @@ use crate::alloc::{flags::*, vec_ext::VecExt, AllocError}; use alloc::vec::Vec; +use core::ffi::CStr; use core::fmt::{self, Write}; -use core::ops::{self, Deref, DerefMut, Index}; +use core::ops::Deref; use crate::error::{code::*, Error}; @@ -41,11 +42,11 @@ impl fmt::Display for BStr { /// # use kernel::{fmt, b_str, str::{BStr, CString}}; /// let ascii = b_str!("Hello, BStr!"); /// let s = CString::try_from_fmt(fmt!("{}", ascii)).unwrap(); - /// assert_eq!(s.as_bytes(), "Hello, BStr!".as_bytes()); + /// assert_eq!(s.to_bytes(), "Hello, BStr!".as_bytes()); /// /// let non_ascii = b_str!("🦀"); /// let s = CString::try_from_fmt(fmt!("{}", non_ascii)).unwrap(); - /// assert_eq!(s.as_bytes(), "\\xf0\\x9f\\xa6\\x80".as_bytes()); + /// assert_eq!(s.to_bytes(), "\\xf0\\x9f\\xa6\\x80".as_bytes()); /// ``` fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { for &b in &self.0 { @@ -72,11 +73,11 @@ impl fmt::Debug for BStr { /// // Embedded double quotes are escaped. /// let ascii = b_str!("Hello, \"BStr\"!"); /// let s = CString::try_from_fmt(fmt!("{:?}", ascii)).unwrap(); - /// assert_eq!(s.as_bytes(), "\"Hello, \\\"BStr\\\"!\"".as_bytes()); + /// assert_eq!(s.to_bytes(), "\"Hello, \\\"BStr\\\"!\"".as_bytes()); /// /// let non_ascii = b_str!("😺"); /// let s = CString::try_from_fmt(fmt!("{:?}", non_ascii)).unwrap(); - /// assert_eq!(s.as_bytes(), "\"\\xf0\\x9f\\x98\\xba\"".as_bytes()); + /// assert_eq!(s.to_bytes(), "\"\\xf0\\x9f\\x98\\xba\"".as_bytes()); /// ``` fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { f.write_char('"')?; @@ -128,271 +129,29 @@ macro_rules! b_str { }}; } -/// Possible errors when using conversion functions in [`CStr`]. -#[derive(Debug, Clone, Copy)] -pub enum CStrConvertError { - /// Supplied bytes contain an interior `NUL`. - InteriorNul, +/// Wrapper around [`CStr`] which implements [`Display`](core::fmt::Display). +pub struct CStrDisplay<'a>(&'a CStr); - /// Supplied bytes are not terminated by `NUL`. - NotNulTerminated, -} - -impl From<CStrConvertError> for Error { - #[inline] - fn from(_: CStrConvertError) -> Error { - EINVAL - } -} - -/// A string that is guaranteed to have exactly one `NUL` byte, which is at the -/// end. -/// -/// Used for interoperability with kernel APIs that take C strings. -#[repr(transparent)] -pub struct CStr([u8]); - -impl CStr { - /// Returns the length of this string excluding `NUL`. - #[inline] - pub const fn len(&self) -> usize { - self.len_with_nul() - 1 - } - - /// Returns the length of this string with `NUL`. - #[inline] - pub const fn len_with_nul(&self) -> usize { - // SAFETY: This is one of the invariant of `CStr`. - // We add a `unreachable_unchecked` here to hint the optimizer that - // the value returned from this function is non-zero. - if self.0.is_empty() { - unsafe { core::hint::unreachable_unchecked() }; - } - self.0.len() - } - - /// Returns `true` if the string only includes `NUL`. - #[inline] - pub const fn is_empty(&self) -> bool { - self.len() == 0 - } - - /// Wraps a raw C string pointer. - /// - /// # Safety - /// - /// `ptr` must be a valid pointer to a `NUL`-terminated C string, and it must - /// last at least `'a`. When `CStr` is alive, the memory pointed by `ptr` - /// must not be mutated. - #[inline] - pub unsafe fn from_char_ptr<'a>(ptr: *const core::ffi::c_char) -> &'a Self { - // SAFETY: The safety precondition guarantees `ptr` is a valid pointer - // to a `NUL`-terminated C string. - let len = unsafe { bindings::strlen(ptr) } + 1; - // SAFETY: Lifetime guaranteed by the safety precondition. - let bytes = unsafe { core::slice::from_raw_parts(ptr as _, len as _) }; - // SAFETY: As `len` is returned by `strlen`, `bytes` does not contain interior `NUL`. - // As we have added 1 to `len`, the last byte is known to be `NUL`. - unsafe { Self::from_bytes_with_nul_unchecked(bytes) } - } - - /// Creates a [`CStr`] from a `[u8]`. - /// - /// The provided slice must be `NUL`-terminated, does not contain any - /// interior `NUL` bytes. - pub const fn from_bytes_with_nul(bytes: &[u8]) -> Result<&Self, CStrConvertError> { - if bytes.is_empty() { - return Err(CStrConvertError::NotNulTerminated); - } - if bytes[bytes.len() - 1] != 0 { - return Err(CStrConvertError::NotNulTerminated); - } - let mut i = 0; - // `i + 1 < bytes.len()` allows LLVM to optimize away bounds checking, - // while it couldn't optimize away bounds checks for `i < bytes.len() - 1`. - while i + 1 < bytes.len() { - if bytes[i] == 0 { - return Err(CStrConvertError::InteriorNul); - } - i += 1; - } - // SAFETY: We just checked that all properties hold. - Ok(unsafe { Self::from_bytes_with_nul_unchecked(bytes) }) - } - - /// Creates a [`CStr`] from a `[u8]` without performing any additional - /// checks. - /// - /// # Safety - /// - /// `bytes` *must* end with a `NUL` byte, and should only have a single - /// `NUL` byte (or the string will be truncated). - #[inline] - pub const unsafe fn from_bytes_with_nul_unchecked(bytes: &[u8]) -> &CStr { - // SAFETY: Properties of `bytes` guaranteed by the safety precondition. - unsafe { core::mem::transmute(bytes) } - } - - /// Creates a mutable [`CStr`] from a `[u8]` without performing any - /// additional checks. - /// - /// # Safety - /// - /// `bytes` *must* end with a `NUL` byte, and should only have a single - /// `NUL` byte (or the string will be truncated). - #[inline] - pub unsafe fn from_bytes_with_nul_unchecked_mut(bytes: &mut [u8]) -> &mut CStr { - // SAFETY: Properties of `bytes` guaranteed by the safety precondition. - unsafe { &mut *(bytes as *mut [u8] as *mut CStr) } - } - - /// Returns a C pointer to the string. - #[inline] - pub const fn as_char_ptr(&self) -> *const core::ffi::c_char { - self.0.as_ptr() as _ - } - - /// Convert the string to a byte slice without the trailing `NUL` byte. - #[inline] - pub fn as_bytes(&self) -> &[u8] { - &self.0[..self.len()] - } - - /// Convert the string to a byte slice containing the trailing `NUL` byte. - #[inline] - pub const fn as_bytes_with_nul(&self) -> &[u8] { - &self.0 - } - - /// Yields a [`&str`] slice if the [`CStr`] contains valid UTF-8. - /// - /// If the contents of the [`CStr`] are valid UTF-8 data, this - /// function will return the corresponding [`&str`] slice. Otherwise, - /// it will return an error with details of where UTF-8 validation failed. - /// - /// # Examples - /// - /// ``` - /// # use kernel::str::CStr; - /// let cstr = CStr::from_bytes_with_nul(b"foo\0").unwrap(); - /// assert_eq!(cstr.to_str(), Ok("foo")); - /// ``` - #[inline] - pub fn to_str(&self) -> Result<&str, core::str::Utf8Error> { - core::str::from_utf8(self.as_bytes()) - } - - /// Unsafely convert this [`CStr`] into a [`&str`], without checking for - /// valid UTF-8. - /// - /// # Safety - /// - /// The contents must be valid UTF-8. +impl fmt::Display for CStrDisplay<'_> { + /// Formats printable ASCII characters, escaping the rest. /// /// # Examples /// /// ``` - /// # use kernel::c_str; - /// # use kernel::str::CStr; - /// let bar = c_str!("ツ"); - /// // SAFETY: String literals are guaranteed to be valid UTF-8 - /// // by the Rust compiler. - /// assert_eq!(unsafe { bar.as_str_unchecked() }, "ツ"); - /// ``` - #[inline] - pub unsafe fn as_str_unchecked(&self) -> &str { - unsafe { core::str::from_utf8_unchecked(self.as_bytes()) } - } - - /// Convert this [`CStr`] into a [`CString`] by allocating memory and - /// copying over the string data. - pub fn to_cstring(&self) -> Result<CString, AllocError> { - CString::try_from(self) - } - - /// Converts this [`CStr`] to its ASCII lower case equivalent in-place. - /// - /// ASCII letters 'A' to 'Z' are mapped to 'a' to 'z', - /// but non-ASCII letters are unchanged. - /// - /// To return a new lowercased value without modifying the existing one, use - /// [`to_ascii_lowercase()`]. - /// - /// [`to_ascii_lowercase()`]: #method.to_ascii_lowercase - pub fn make_ascii_lowercase(&mut self) { - // INVARIANT: This doesn't introduce or remove NUL bytes in the C - // string. - self.0.make_ascii_lowercase(); - } - - /// Converts this [`CStr`] to its ASCII upper case equivalent in-place. - /// - /// ASCII letters 'a' to 'z' are mapped to 'A' to 'Z', - /// but non-ASCII letters are unchanged. - /// - /// To return a new uppercased value without modifying the existing one, use - /// [`to_ascii_uppercase()`]. - /// - /// [`to_ascii_uppercase()`]: #method.to_ascii_uppercase - pub fn make_ascii_uppercase(&mut self) { - // INVARIANT: This doesn't introduce or remove NUL bytes in the C - // string. - self.0.make_ascii_uppercase(); - } - - /// Returns a copy of this [`CString`] where each character is mapped to its - /// ASCII lower case equivalent. - /// - /// ASCII letters 'A' to 'Z' are mapped to 'a' to 'z', - /// but non-ASCII letters are unchanged. - /// - /// To lowercase the value in-place, use [`make_ascii_lowercase`]. - /// - /// [`make_ascii_lowercase`]: str::make_ascii_lowercase - pub fn to_ascii_lowercase(&self) -> Result<CString, AllocError> { - let mut s = self.to_cstring()?; - - s.make_ascii_lowercase(); - - Ok(s) - } - - /// Returns a copy of this [`CString`] where each character is mapped to its - /// ASCII upper case equivalent. - /// - /// ASCII letters 'a' to 'z' are mapped to 'A' to 'Z', - /// but non-ASCII letters are unchanged. - /// - /// To uppercase the value in-place, use [`make_ascii_uppercase`]. - /// - /// [`make_ascii_uppercase`]: str::make_ascii_uppercase - pub fn to_ascii_uppercase(&self) -> Result<CString, AllocError> { - let mut s = self.to_cstring()?; - - s.make_ascii_uppercase(); - - Ok(s) - } -} - -impl fmt::Display for CStr { - /// Formats printable ASCII characters, escaping the rest. - /// - /// ``` + /// # use core::ffi::CStr; /// # use kernel::c_str; /// # use kernel::fmt; - /// # use kernel::str::CStr; - /// # use kernel::str::CString; - /// let penguin = c_str!("🐧"); - /// let s = CString::try_from_fmt(fmt!("{}", penguin)).unwrap(); - /// assert_eq!(s.as_bytes_with_nul(), "\\xf0\\x9f\\x90\\xa7\0".as_bytes()); - /// - /// let ascii = c_str!("so \"cool\""); - /// let s = CString::try_from_fmt(fmt!("{}", ascii)).unwrap(); - /// assert_eq!(s.as_bytes_with_nul(), "so \"cool\"\0".as_bytes()); + /// # use kernel::str::{CStrExt, CString}; + /// let penguin = c"🐧"; + /// let s = CString::try_from_fmt(fmt!("{}", penguin.display())).unwrap(); + /// assert_eq!(s.to_bytes_with_nul(), "\\xf0\\x9f\\x90\\xa7\0".as_bytes()); + /// + /// let ascii = c"so \"cool\""; + /// let s = CString::try_from_fmt(fmt!("{}", ascii.display())).unwrap(); + /// assert_eq!(s.to_bytes_with_nul(), "so \"cool\"\0".as_bytes()); /// ``` fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { - for &c in self.as_bytes() { + for &c in self.0.to_bytes() { if (0x20..0x7f).contains(&c) { // Printable character. f.write_char(c as char)?; @@ -404,116 +163,70 @@ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { } } -impl fmt::Debug for CStr { - /// Formats printable ASCII characters with a double quote on either end, escaping the rest. +/// Extensions to [`CStr`]. +pub trait CStrExt { + /// Returns an object that implements [`Display`](core::fmt::Display) for + /// safely printing a [`CStr`] that may contain non-ASCII data, which are + /// escaped. + /// + /// # Examples /// /// ``` + /// # use core::ffi::CStr; /// # use kernel::c_str; /// # use kernel::fmt; - /// # use kernel::str::CStr; - /// # use kernel::str::CString; - /// let penguin = c_str!("🐧"); - /// let s = CString::try_from_fmt(fmt!("{:?}", penguin)).unwrap(); - /// assert_eq!(s.as_bytes_with_nul(), "\"\\xf0\\x9f\\x90\\xa7\"\0".as_bytes()); - /// - /// // Embedded double quotes are escaped. - /// let ascii = c_str!("so \"cool\""); - /// let s = CString::try_from_fmt(fmt!("{:?}", ascii)).unwrap(); - /// assert_eq!(s.as_bytes_with_nul(), "\"so \\\"cool\\\"\"\0".as_bytes()); + /// # use kernel::str::{CStrExt, CString}; + /// let penguin = c"🐧"; + /// let s = CString::try_from_fmt(fmt!("{}", penguin.display())).unwrap(); + /// assert_eq!(s.to_bytes_with_nul(), "\\xf0\\x9f\\x90\\xa7\0".as_bytes()); + /// + /// let ascii = c"so \"cool\""; + /// let s = CString::try_from_fmt(fmt!("{}", ascii.display())).unwrap(); + /// assert_eq!(s.to_bytes_with_nul(), "so \"cool\"\0".as_bytes()); /// ``` - fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { - f.write_str("\"")?; - for &c in self.as_bytes() { - match c { - // Printable characters. - b'\"' => f.write_str("\\\"")?, - 0x20..=0x7e => f.write_char(c as char)?, - _ => write!(f, "\\x{:02x}", c)?, - } - } - f.write_str("\"") - } -} - -impl AsRef<BStr> for CStr { - #[inline] - fn as_ref(&self) -> &BStr { - BStr::from_bytes(self.as_bytes()) - } -} - -impl Deref for CStr { - type Target = BStr; - - #[inline] - fn deref(&self) -> &Self::Target { - self.as_ref() - } -} - -impl Index<ops::RangeFrom<usize>> for CStr { - type Output = CStr; + fn display(&self) -> CStrDisplay<'_>; - #[inline] - fn index(&self, index: ops::RangeFrom<usize>) -> &Self::Output { - // Delegate bounds checking to slice. - // Assign to _ to mute clippy's unnecessary operation warning. - let _ = &self.as_bytes()[index.start..]; - // SAFETY: We just checked the bounds. - unsafe { Self::from_bytes_with_nul_unchecked(&self.0[index.start..]) } - } + /// Creates a mutable [`CStr`] from a `[u8]` without performing any + /// additional checks. + /// + /// # Safety + /// + /// `bytes` *must* end with a `NUL` byte, and should only have a single + /// `NUL` byte (or the string will be truncated). + unsafe fn from_bytes_with_nul_unchecked_mut(bytes: &mut [u8]) -> &mut Self; } -impl Index<ops::RangeFull> for CStr { - type Output = CStr; - - #[inline] - fn index(&self, _index: ops::RangeFull) -> &Self::Output { - self +impl CStrExt for CStr { + fn display(&self) -> CStrDisplay<'_> { + CStrDisplay(self) } -} -mod private { - use core::ops; - - // Marker trait for index types that can be forward to `BStr`. - pub trait CStrIndex {} - - impl CStrIndex for usize {} - impl CStrIndex for ops::Range<usize> {} - impl CStrIndex for ops::RangeInclusive<usize> {} - impl CStrIndex for ops::RangeToInclusive<usize> {} -} - -impl<Idx> Index<Idx> for CStr -where - Idx: private::CStrIndex, - BStr: Index<Idx>, -{ - type Output = <BStr as Index<Idx>>::Output; - - #[inline] - fn index(&self, index: Idx) -> &Self::Output { - &self.as_ref()[index] + unsafe fn from_bytes_with_nul_unchecked_mut(bytes: &mut [u8]) -> &mut Self { + // SAFETY: Properties of `bytes` guaranteed by the safety precondition. + unsafe { &mut *(bytes as *mut [u8] as *mut CStr) } } } /// Creates a new [`CStr`] from a string literal. /// -/// The string literal should not contain any `NUL` bytes. +/// This macro is not needed when C-string literals (`c"hello"` syntax) can be +/// used directly, but can be used when a C-string version of a standard string +/// literal is required (often when working with macros). +/// +/// The string should not contain any `NUL` bytes. /// /// # Examples /// /// ``` +/// # use core::ffi::CStr; /// # use kernel::c_str; -/// # use kernel::str::CStr; -/// const MY_CSTR: &CStr = c_str!("My awesome CStr!"); +/// const MY_CSTR: &CStr = c_str!(stringify!(5)); /// ``` #[macro_export] macro_rules! c_str { ($str:expr) => {{ const S: &str = concat!($str, "\0"); - const C: &$crate::str::CStr = match $crate::str::CStr::from_bytes_with_nul(S.as_bytes()) { + const C: &core::ffi::CStr = match core::ffi::CStr::from_bytes_with_nul(S.as_bytes()) { Ok(v) => v, Err(_) => panic!("string contains interior NUL"), }; @@ -540,40 +253,16 @@ mod tests { \\xe0\\xe1\\xe2\\xe3\\xe4\\xe5\\xe6\\xe7\\xe8\\xe9\\xea\\xeb\\xec\\xed\\xee\\xef\ \\xf0\\xf1\\xf2\\xf3\\xf4\\xf5\\xf6\\xf7\\xf8\\xf9\\xfa\\xfb\\xfc\\xfd\\xfe\\xff"; - #[test] - fn test_cstr_to_str() { - let good_bytes = b"\xf0\x9f\xa6\x80\0"; - let checked_cstr = CStr::from_bytes_with_nul(good_bytes).unwrap(); - let checked_str = checked_cstr.to_str().unwrap(); - assert_eq!(checked_str, "🦀"); - } - - #[test] - #[should_panic] - fn test_cstr_to_str_panic() { - let bad_bytes = b"\xc3\x28\0"; - let checked_cstr = CStr::from_bytes_with_nul(bad_bytes).unwrap(); - checked_cstr.to_str().unwrap(); - } - - #[test] - fn test_cstr_as_str_unchecked() { - let good_bytes = b"\xf0\x9f\x90\xA7\0"; - let checked_cstr = CStr::from_bytes_with_nul(good_bytes).unwrap(); - let unchecked_str = unsafe { checked_cstr.as_str_unchecked() }; - assert_eq!(unchecked_str, "🐧"); - } - #[test] fn test_cstr_display() { let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap(); - assert_eq!(format!("{}", hello_world), "hello, world!"); + assert_eq!(format!("{}", hello_world.display()), "hello, world!"); let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap(); - assert_eq!(format!("{}", non_printables), "\\x01\\x09\\x0a"); + assert_eq!(format!("{}", non_printables.display()), "\\x01\\x09\\x0a"); let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap(); - assert_eq!(format!("{}", non_ascii), "d\\xe9j\\xe0 vu"); + assert_eq!(format!("{}", non_ascii.display()), "d\\xe9j\\xe0 vu"); let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap(); - assert_eq!(format!("{}", good_bytes), "\\xf0\\x9f\\xa6\\x80"); + assert_eq!(format!("{}", good_bytes.display()), "\\xf0\\x9f\\xa6\\x80"); } #[test] @@ -584,19 +273,7 @@ fn test_cstr_display_all_bytes() { bytes[i as usize] = i.wrapping_add(1); } let cstr = CStr::from_bytes_with_nul(&bytes).unwrap(); - assert_eq!(format!("{}", cstr), ALL_ASCII_CHARS); - } - - #[test] - fn test_cstr_debug() { - let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap(); - assert_eq!(format!("{:?}", hello_world), "\"hello, world!\""); - let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap(); - assert_eq!(format!("{:?}", non_printables), "\"\\x01\\x09\\x0a\""); - let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap(); - assert_eq!(format!("{:?}", non_ascii), "\"d\\xe9j\\xe0 vu\""); - let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap(); - assert_eq!(format!("{:?}", good_bytes), "\"\\xf0\\x9f\\xa6\\x80\""); + assert_eq!(format!("{}", cstr.display()), ALL_ASCII_CHARS); } #[test] @@ -779,11 +456,11 @@ fn write_str(&mut self, s: &str) -> fmt::Result { /// use kernel::{str::CString, fmt}; /// /// let s = CString::try_from_fmt(fmt!("{}{}{}", "abc", 10, 20)).unwrap(); -/// assert_eq!(s.as_bytes_with_nul(), "abc1020\0".as_bytes()); +/// assert_eq!(s.to_bytes_with_nul(), "abc1020\0".as_bytes()); /// /// let tmp = "testing"; /// let s = CString::try_from_fmt(fmt!("{tmp}{}", 123)).unwrap(); -/// assert_eq!(s.as_bytes_with_nul(), "testing123\0".as_bytes()); +/// assert_eq!(s.to_bytes_with_nul(), "testing123\0".as_bytes()); /// /// // This fails because it has an embedded `NUL` byte. /// let s = CString::try_from_fmt(fmt!("a\0b{}", 123)); @@ -838,21 +515,13 @@ fn deref(&self) -> &Self::Target { } } -impl DerefMut for CString { - fn deref_mut(&mut self) -> &mut Self::Target { - // SAFETY: A `CString` is always NUL-terminated and contains no other - // NUL bytes. - unsafe { CStr::from_bytes_with_nul_unchecked_mut(self.buf.as_mut_slice()) } - } -} - impl<'a> TryFrom<&'a CStr> for CString { type Error = AllocError; fn try_from(cstr: &'a CStr) -> Result<CString, AllocError> { let mut buf = Vec::new(); - <Vec<_> as VecExt<_>>::extend_from_slice(&mut buf, cstr.as_bytes_with_nul(), GFP_KERNEL) + <Vec<_> as VecExt<_>>::extend_from_slice(&mut buf, cstr.to_bytes_with_nul(), GFP_KERNEL) .map_err(|_| AllocError)?; // INVARIANT: The `CStr` and `CString` types have the same invariants for diff --git a/rust/kernel/sync/condvar.rs b/rust/kernel/sync/condvar.rs index 2b306afbe56d..16d1a1cb8d00 100644 --- a/rust/kernel/sync/condvar.rs +++ b/rust/kernel/sync/condvar.rs @@ -9,12 +9,11 @@ use crate::{ init::PinInit, pin_init, - str::CStr, task::{MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE, TASK_NORMAL, TASK_UNINTERRUPTIBLE}, time::Jiffies, types::Opaque, }; -use core::ffi::{c_int, c_long}; +use core::ffi::{c_int, c_long, CStr}; use core::marker::PhantomPinned; use core::ptr; use macros::pin_data; @@ -108,7 +107,7 @@ pub fn new(name: &'static CStr, key: &'static LockClassKey) -> impl PinInit<Self // SAFETY: `slot` is valid while the closure is called and both `name` and `key` have // static lifetimes so they live indefinitely. wait_queue_head <- Opaque::ffi_init(|slot| unsafe { - bindings::__init_waitqueue_head(slot, name.as_char_ptr(), key.as_ptr()) + bindings::__init_waitqueue_head(slot, name.as_ptr(), key.as_ptr()) }), }) } diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs index f6c34ca4d819..318ecb5a5916 100644 --- a/rust/kernel/sync/lock.rs +++ b/rust/kernel/sync/lock.rs @@ -6,8 +6,8 @@ //! spinlocks, raw spinlocks) to be provided with minimal effort. use super::LockClassKey; -use crate::{init::PinInit, pin_init, str::CStr, types::Opaque, types::ScopeGuard}; -use core::{cell::UnsafeCell, marker::PhantomData, marker::PhantomPinned}; +use crate::{init::PinInit, pin_init, types::Opaque, types::ScopeGuard}; +use core::{cell::UnsafeCell, ffi::CStr, marker::PhantomData, marker::PhantomPinned}; use macros::pin_data; pub mod mutex; @@ -113,7 +113,7 @@ pub fn new(t: T, name: &'static CStr, key: &'static LockClassKey) -> impl PinIni // SAFETY: `slot` is valid while the closure is called and both `name` and `key` have // static lifetimes so they live indefinitely. state <- Opaque::ffi_init(|slot| unsafe { - B::init(slot, name.as_char_ptr(), key.as_ptr()) + B::init(slot, name.as_ptr(), key.as_ptr()) }), }) } diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs index 553a5cba2adc..a6418873e82e 100644 --- a/rust/kernel/workqueue.rs +++ b/rust/kernel/workqueue.rs @@ -380,7 +380,7 @@ pub fn new(name: &'static CStr, key: &'static LockClassKey) -> impl PinInit<Self slot, Some(T::Pointer::run), false, - name.as_char_ptr(), + name.as_ptr(), key.as_ptr(), ) } diff --git a/scripts/rustdoc_test_gen.rs b/scripts/rustdoc_test_gen.rs index 5ebd42ae4a3f..339991ee6885 100644 --- a/scripts/rustdoc_test_gen.rs +++ b/scripts/rustdoc_test_gen.rs @@ -172,7 +172,7 @@ pub extern "C" fn {kunit_name}(__kunit_test: *mut kernel::bindings::kunit) {{ #[allow(unused)] macro_rules! assert {{ ($cond:expr $(,)?) => {{{{ - kernel::kunit_assert!("{kunit_name}", "{real_path}", __DOCTEST_ANCHOR - {line}, $cond); + kernel::kunit_assert!(c"{kunit_name}", c"{real_path}", __DOCTEST_ANCHOR - {line}, $cond); }}}} }} @@ -180,7 +180,7 @@ macro_rules! assert {{ #[allow(unused)] macro_rules! assert_eq {{ ($left:expr, $right:expr $(,)?) => {{{{ - kernel::kunit_assert_eq!("{kunit_name}", "{real_path}", __DOCTEST_ANCHOR - {line}, $left, $right); + kernel::kunit_assert_eq!(c"{kunit_name}", c"{real_path}", __DOCTEST_ANCHOR - {line}, $left, $right); }}}} }} -- 2.44.2

1 year, 2 months

4
6
0 0

[RFC PATCH v1 6/6] selftests/rseq: Implement NUMA node id vs mm_cid invariant test

by Mathieu Desnoyers

This test validates that the mapping between a mm_cid and a NUMA node id remains invariant for the process lifetime for a process with a number of threads >= number of allowed CPUs. In other words, it validates that if any thread within the process running on behalf of a mm_cid N observes a NUMA node id M, all threads within this process will always observe the same NUMA node id value when running on behalf of that same mm_cid. This characteristic is important for NUMA locality. On all architectures except Power, the NUMA topology is never reconfigured after a CPU has been associated with a NUMA node in the system lifetime. Even on Power, we can assume that NUMA topology reconfiguration happens rarely, and therefore we do not expect it to happen while the NUMA test is running. As a result the NUMA node id associated with a mm_cid should be invariant as long as: - A process has a number of threads >= number of allowed CPUs, - The allowed CPUs mask is unchanged, and - The NUMA configuration is unchanged. This test is skipped on architectures that do not implement rseq_load_u32_u32. Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Shuah Khan <skhan(a)linuxfoundation.org> Cc: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/rseq/.gitignore | 1 + tools/testing/selftests/rseq/Makefile | 2 +- .../testing/selftests/rseq/basic_numa_test.c | 144 ++++++++++++++++++ 3 files changed, 146 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/rseq/basic_numa_test.c diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore index 16496de5f6ce..8a8d163cbb9f 100644 --- a/tools/testing/selftests/rseq/.gitignore +++ b/tools/testing/selftests/rseq/.gitignore @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only +basic_numa_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test basic_test diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 5a3432fceb58..9ef1c949114a 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -14,7 +14,7 @@ LDLIBS += -lpthread -ldl # still track changes to header files and depend on shared object. OVERRIDE_TARGETS = 1 -TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ +TEST_GEN_PROGS = basic_test basic_numa_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ param_test_benchmark param_test_compare_twice param_test_mm_cid \ param_test_mm_cid_benchmark param_test_mm_cid_compare_twice diff --git a/tools/testing/selftests/rseq/basic_numa_test.c b/tools/testing/selftests/rseq/basic_numa_test.c new file mode 100644 index 000000000000..8e51c662057d --- /dev/null +++ b/tools/testing/selftests/rseq/basic_numa_test.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Basic rseq NUMA test. Validate that (mm_cid, numa_node_id) pairs are + * invariant when the number of threads >= number of allowed CPUs, as + * long as those preconditions are respected: + * + * - A process has a number of threads >= number of allowed CPUs, + * - The allowed CPUs mask is unchanged, and + * - The NUMA configuration is unchanged. + */ +#define _GNU_SOURCE +#include <assert.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <string.h> +#include <poll.h> +#include <sys/time.h> + +#include "rseq.h" + +#define NR_LOOPS 100 + +static int nr_threads, nr_active_threads, test_go, test_stop; + +#ifdef RSEQ_ARCH_HAS_LOAD_U32_U32 + +static int cpu_numa_id[CPU_SETSIZE]; + +static int get_affinity_weight(void) +{ + cpu_set_t allowed_cpus; + + if (sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus)) { + perror("sched_getaffinity"); + abort(); + } + return CPU_COUNT(&allowed_cpus); +} + +static void numa_id_init(void) +{ + int i; + + for (i = 0; i < CPU_SETSIZE; i++) + cpu_numa_id[i] = -1; +} + +static void *test_thread(void *arg) +{ + int i; + + if (rseq_register_current_thread()) { + fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n", + errno, strerror(errno)); + abort(); + } + /* + * Rendez-vous across all threads to make sure the number of + * threads >= number of possible CPUs for the entire test duration. + */ + if (__atomic_add_fetch(&nr_active_threads, 1, __ATOMIC_RELAXED) == nr_threads) + __atomic_store_n(&test_go, 1, __ATOMIC_RELAXED); + while (!__atomic_load_n(&test_go, __ATOMIC_RELAXED)) + rseq_barrier(); + + for (i = 0; i < NR_LOOPS; i++) { + uint32_t mm_cid, node; + int cached_node_id; + + while (rseq_load_u32_u32(RSEQ_MO_RELAXED, &mm_cid, + &rseq_get_abi()->mm_cid, + &node, &rseq_get_abi()->node_id) != 0) { + /* Retry. */ + } + cached_node_id = RSEQ_READ_ONCE(cpu_numa_id[mm_cid]); + if (cached_node_id == -1) { + RSEQ_WRITE_ONCE(cpu_numa_id[mm_cid], node); + } else { + if (node != cached_node_id) { + fprintf(stderr, "Error: NUMA node id discrepancy: mm_cid %u cached node id %d node id %u.\n", + mm_cid, cached_node_id, node); + fprintf(stderr, "This is likely a kernel bug, or caused by a concurrent NUMA topology reconfiguration.\n"); + abort(); + } + } + (void) poll(NULL, 0, 10); /* wait 10ms */ + } + /* + * Rendez-vous before exiting all threads to make sure the + * number of threads >= number of possible CPUs for the entire + * test duration. + */ + if (__atomic_sub_fetch(&nr_active_threads, 1, __ATOMIC_RELAXED) == 0) + __atomic_store_n(&test_stop, 1, __ATOMIC_RELAXED); + while (!__atomic_load_n(&test_stop, __ATOMIC_RELAXED)) + rseq_barrier(); + + if (rseq_unregister_current_thread()) { + fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n", + errno, strerror(errno)); + abort(); + } + return NULL; +} + +static int test_numa(void) +{ + pthread_t tid[nr_threads]; + int err, i; + void *tret; + + numa_id_init(); + + printf("testing rseq (mm_cid, numa_node_id) invariant, multi-threaded (%d threads)\n", + nr_threads); + + for (i = 0; i < nr_threads; i++) { + err = pthread_create(&tid[i], NULL, test_thread, NULL); + if (err != 0) + abort(); + } + + for (i = 0; i < nr_threads; i++) { + err = pthread_join(tid[i], &tret); + if (err != 0) + abort(); + } + + return 0; +} +#else +static int test_numa(void) +{ + fprintf(stderr, "rseq_load_u32_u32 is not implemented on this architecture. Skipping numa test.\n"); + return 0; +} +#endif + +int main(int argc, char **argv) +{ + nr_threads = get_affinity_weight(); + return test_numa(); +} -- 2.39.2

1 year, 2 months

1
0
0 0

[RFC PATCH v1 5/6] selftests/rseq: x86: Implement rseq_load_u32_u32

by Mathieu Desnoyers

Allow loading a pair of u32 within a rseq critical section. It can be used in situations where both rseq_abi()->mm_cid and rseq_abi()->node_id need to be sampled atomically with respect to preemption, signal delivery and migration. Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Shuah Khan <skhan(a)linuxfoundation.org> Cc: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/rseq/rseq-x86-bits.h | 43 ++++++++++++++++++++ tools/testing/selftests/rseq/rseq.h | 14 +++++++ 2 files changed, 57 insertions(+) diff --git a/tools/testing/selftests/rseq/rseq-x86-bits.h b/tools/testing/selftests/rseq/rseq-x86-bits.h index 8a9431eec467..fdf5ef398393 100644 --- a/tools/testing/selftests/rseq/rseq-x86-bits.h +++ b/tools/testing/selftests/rseq/rseq-x86-bits.h @@ -990,4 +990,47 @@ int RSEQ_TEMPLATE_IDENTIFIER(rseq_cmpeqv_trymemcpy_storev)(intptr_t *v, intptr_t #endif +#if defined(RSEQ_TEMPLATE_CPU_ID_NONE) && defined(RSEQ_TEMPLATE_MO_RELAXED) + +#define RSEQ_ARCH_HAS_LOAD_U32_U32 + +static inline __attribute__((always_inline)) +int RSEQ_TEMPLATE_IDENTIFIER(rseq_load_u32_u32)(uint32_t *dst1, uint32_t *src1, + uint32_t *dst2, uint32_t *src2) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_INJECT_ASM(3) + "movl %[src1], %%eax\n\t" + "movl %%eax, %[dst1]\n\t" + "movl %[src2], %%eax\n\t" + "movl %%eax, %[dst2]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(4) + RSEQ_ASM_DEFINE_ABORT(4, "", abort) + : /* gcc asm goto does not allow outputs */ + : [rseq_offset] "r" (rseq_offset), + /* final store input */ + [dst1] "m" (*dst1), + [src1] "m" (*src1), + [dst2] "m" (*dst2), + [src2] "m" (*src2) + : "memory", "cc", "rax" + RSEQ_INJECT_CLOBBER + : abort + ); + rseq_after_asm_goto(); + return 0; +abort: + rseq_after_asm_goto(); + RSEQ_INJECT_FAILED + return -1; +} + +#endif /* defined(RSEQ_TEMPLATE_CPU_ID_NONE) && defined(RSEQ_TEMPLATE_MO_RELAXED) */ + #include "rseq-bits-reset.h" diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index d7364ea4d201..b6095c2a5da6 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -381,4 +381,18 @@ int rseq_cmpeqv_trymemcpy_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode per } } +#ifdef RSEQ_ARCH_HAS_LOAD_U32_U32 + +static inline __attribute__((always_inline)) +int rseq_load_u32_u32(enum rseq_mo rseq_mo, + uint32_t *dst1, uint32_t *src1, + uint32_t *dst2, uint32_t *src2) +{ + if (rseq_mo != RSEQ_MO_RELAXED) + return -1; + return rseq_load_u32_u32_relaxed(dst1, src1, dst2, src2); +} + +#endif + #endif /* RSEQ_H_ */ -- 2.39.2

1 year, 2 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror