October 2024 - Linux-kselftest-mirror

[PATCH net-next v20 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 74149dc4ee31..ca01880c7ad0 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 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 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 fdf204550c9a..36543a129e40 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_nc.va = NULL; + page_frag_cache_init(&test_nc); atomic_set(&nthreads, 2); init_completion(&wait); -- 2.33.0

10 months, 3 weeks

1
0
0 0

[PATCH net-next v20 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 eeb2b6bc681a..fdf204550c9a 100644 --- a/tools/testing/selftests/mm/page_frag/page_frag_test.c +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -6,12 +6,12 @@ * Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> */ -#include <linux/mm.h> #include <linux/module.h> #include <linux/cpumask.h> #include <linux/completion.h> #include <linux/ptr_ring.h> #include <linux/kthread.h> +#include <linux/page_frag_cache.h> static struct ptr_ring ptr_ring; static int nr_objs = 512; -- 2.33.0

10 months, 3 weeks

1
0
0 0

[RESEND PATCH v4] list: test: Check the size of every lists for list_cut_position*()

by I Hsin Cheng

Check the total number of elements in both resultant lists are correct within list_cut_position*(). Previously, only the first list's size was checked. wo additional elements in the second list would not have been caught. Signed-off-by: I Hsin Cheng <richard120310(a)gmail.com> --- change in v4: Amend the description of commit message, make it less confusing and focus on the correct check which is performed now. lib/list-test.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/lib/list-test.c b/lib/list-test.c index 37cbc33e9fdb..b4b3810c71d0 100644 --- a/lib/list-test.c +++ b/lib/list-test.c @@ -408,6 +408,8 @@ static void list_test_list_cut_position(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); i++; } + + KUNIT_EXPECT_EQ(test, i, 3); } static void list_test_list_cut_before(struct kunit *test) @@ -436,6 +438,8 @@ static void list_test_list_cut_before(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); i++; } + + KUNIT_EXPECT_EQ(test, i, 3); } static void list_test_list_splice(struct kunit *test) -- 2.43.0

10 months, 3 weeks

2
1
0 0

[RESEND PATCH v4] list: test: Check the size of every lists for list_cut_position*()

by I Hsin Cheng

Check the total number of elements in both resultant lists are correct within list_cut_position*(). Previously, only the first list's size was checked. so additional elements in the second list would not have been caught. Signed-off-by: I Hsin Cheng <richard120310(a)gmail.com> --- change in v4: Amend the description of commit message, make it less confusing and focus on the correct check which is performed now. lib/list-test.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/lib/list-test.c b/lib/list-test.c index 37cbc33e9fdb..b4b3810c71d0 100644 --- a/lib/list-test.c +++ b/lib/list-test.c @@ -408,6 +408,8 @@ static void list_test_list_cut_position(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); i++; } + + KUNIT_EXPECT_EQ(test, i, 3); } static void list_test_list_cut_before(struct kunit *test) @@ -436,6 +438,8 @@ static void list_test_list_cut_before(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); i++; } + + KUNIT_EXPECT_EQ(test, i, 3); } static void list_test_list_splice(struct kunit *test) -- 2.43.0

10 months, 3 weeks

1
0
0 0

[PATCH 00/33] riscv control-flow integrity for usermode

by Deepak Gupta

v5 for cpu assisted riscv user mode control flow integrity. zicfiss and zicfilp [1] are ratified riscv CPU extensions. Changes in this version are - rebased on v6.12-rc1 - Fixed schema related issues in device tree file - Fixed some of the documentation related issues in zicfilp/ss.rst (style issues and added index) - added `SHADOW_STACK_SET_MARKER` so that implementation can define base of shadow stack. - Fixed warnings on definitions added in usercfi.h when CONFIG_RISCV_USER_CFI is not selected. - Adopted context header based signal handling as proposed by Andy Chiu - Added support for enabling kernel mode access to shadow stack using FWFT [4] v4 [3] and v3 [2] are earlier versions of patch series. To get more information on kernel interactions with respect to zicfilp and zicfiss, patch series adds documentation for `zicfilp` and `zicfiss` Documentation/arch/riscv/zicfiss.rst Documentation/arch/riscv/zicfilp.rst How to test this series ======================= Toolchain --------- $ git clone git@github.com:sifive/riscv-gnu-toolchain.git -b cfi-dev $ riscv-gnu-toolchain/configure --prefix=<path-to-where-to-build> --with-arch=rv64gc_zicfilp_zicfiss --enable-linux --disable-gdb --with-extra-multilib-test="rv64gc_zicfilp_zicfiss-lp64d:-static" $ make -j$(nproc) Qemu ---- $ git clone git@github.com:deepak0414/qemu.git -b zicfilp_zicfiss_ratified_master_july11 $ cd qemu $ mkdir build $ cd build $ ../configure --target-list=riscv64-softmmu $ make -j$(nproc) Opensbi ------- $ git clone git@github.com:deepak0414/opensbi.git -b v6_cfi_spec_split_opensbi $ make CROSS_COMPILE=<your riscv toolchain> -j$(nproc) PLATFORM=generic Linux ----- Running defconfig is fine. CFI is enabled by default if the toolchain supports it. $ make ARCH=riscv CROSS_COMPILE=<path-to-cfi-riscv-gnu-toolchain>/build/bin/riscv64-unknown-linux-gnu- -j$(nproc) defconfig $ make ARCH=riscv CROSS_COMPILE=<path-to-cfi-riscv-gnu-toolchain>/build/bin/riscv64-unknown-linux-gnu- -j$(nproc) Running ------- Modify your qemu command to have: -bios <path-to-cfi-opensbi>/build/platform/generic/firmware/fw_dynamic.bin -cpu rv64,zicfilp=true,zicfiss=true,zimop=true,zcmop=true vDSO related Opens (in the flux) ================================= I am listing these opens for laying out plan and what to expect in future patch sets. And of course for the sake of discussion. Shadow stack and landing pad enabling in vDSO ---------------------------------------------- vDSO must have shadow stack and landing pad support compiled in for task to have shadow stack and landing pad support. This patch series doesn't enable that (yet). Enabling shadow stack support in vDSO should be straight forward (intend to do that in next versions of patch set). Enabling landing pad support in vDSO requires some collaboration with toolchain folks to follow a single label scheme for all object binaries. This is necessary to ensure that all indirect call-sites are setting correct label and target landing pads are decorated with same label scheme. How many vDSOs --------------- Shadow stack instructions are carved out of zimop (may be operations) and if CPU doesn't implement zimop, they're illegal instructions. Kernel could be running on a CPU which may or may not implement zimop. And thus kernel will have to carry 2 different vDSOs and expose the appropriate one depending on whether CPU implements zimop or not. [1] - https://github.com/riscv/riscv-cfi [2] - https://lore.kernel.org/lkml/20240403234054.2020347-1-debug@rivosinc.com/ [3] - https://lore.kernel.org/all/20240912231650.3740732-1-debug@rivosinc.com/ [4] - https://github.com/riscv-non-isa/riscv-sbi-doc/blob/master/src/ext-firmware… --- changelog --------- v4 -- - rebased on 6.11-rc6 - envcfg: Converged with Samuel Holland's patches for envcfg management on per- thread basis. - vma_is_shadow_stack is renamed to is_vma_shadow_stack - picked up Mark Brown's `ARCH_HAS_USER_SHADOW_STACK` patch - signal context: using extended context management to maintain compatibility. - fixed `-Wmissing-prototypes` compiler warnings for prctl functions - Documentation fixes and amending typos. v3 -- envcfg: logic to pick up base envcfg had a bug where `ENVCFG_CBZE` could have been picked on per task basis, even though CPU didn't implement it. Fixed in this series. dt-bindings: As suggested, split into separate commit. fixed the messaging that spec is in public review arch_is_shadow_stack change: arch_is_shadow_stack changed to vma_is_shadow_stack hwprobe: zicfiss / zicfilp if present will get enumerated in hwprobe selftests: As suggested, added object and binary filenames to .gitignore Selftest binary anyways need to be compiled with cfi enabled compiler which will make sure that landing pad and shadow stack are enabled. Thus removed separate enable/disable tests. Cleaned up tests a bit. v2 -- - Using config `CONFIG_RISCV_USER_CFI`, kernel support for riscv control flow integrity for user mode programs can be compiled in the kernel. - Enabling of control flow integrity for user programs is left to user runtime - This patch series introduces arch agnostic `prctls` to enable shadow stack and indirect branch tracking. And implements them on riscv. Signed-off-by: Deepak Gupta <debug(a)rivosinc.com> --- Andy Chiu (1): riscv: signal: abstract header saving for setup_sigcontext Clément Léger (1): riscv: Add Firmware Feature SBI extensions definitions Deepak Gupta (26): mm: helper `is_shadow_stack_vma` to check shadow stack vma riscv/Kconfig: enable HAVE_EXIT_THREAD for riscv riscv: zicfilp / zicfiss in dt-bindings (extensions.yaml) riscv: zicfiss / zicfilp enumeration riscv: zicfiss / zicfilp extension csr and bit definitions riscv: usercfi state for task and save/restore of CSR_SSP on trap entry/exit riscv/mm : ensure PROT_WRITE leads to VM_READ | VM_WRITE riscv mm: manufacture shadow stack pte riscv mmu: teach pte_mkwrite to manufacture shadow stack PTEs riscv mmu: write protect and shadow stack riscv/mm: Implement map_shadow_stack() syscall riscv/shstk: If needed allocate a new shadow stack on clone prctl: arch-agnostic prctl for indirect branch tracking riscv: Implements arch agnostic shadow stack prctls riscv: Implements arch agnostic indirect branch tracking prctls riscv/traps: Introduce software check exception riscv signal: save and restore of shadow stack for signal riscv/kernel: update __show_regs to print shadow stack register riscv/ptrace: riscv cfi status and state via ptrace and in core files riscv/hwprobe: zicfilp / zicfiss enumeration in hwprobe riscv: enable kernel access to shadow stack memory via FWFT sbi call riscv: kernel command line option to opt out of user cfi riscv: create a config for shadow stack and landing pad instr support riscv: Documentation for landing pad / indirect branch tracking riscv: Documentation for shadow stack on riscv kselftest/riscv: kselftest for user mode cfi Mark Brown (2): mm: Introduce ARCH_HAS_USER_SHADOW_STACK prctl: arch-agnostic prctl for shadow stack Samuel Holland (3): riscv: Enable cbo.zero only when all harts support Zicboz riscv: Add support for per-thread envcfg CSR values riscv: Call riscv_user_isa_enable() only on the boot hart Documentation/arch/riscv/index.rst | 2 + Documentation/arch/riscv/zicfilp.rst | 115 +++++ Documentation/arch/riscv/zicfiss.rst | 176 +++++++ .../devicetree/bindings/riscv/extensions.yaml | 14 + arch/riscv/Kconfig | 20 + arch/riscv/include/asm/asm-prototypes.h | 1 + arch/riscv/include/asm/cpufeature.h | 15 +- arch/riscv/include/asm/csr.h | 16 + arch/riscv/include/asm/entry-common.h | 2 + arch/riscv/include/asm/hwcap.h | 2 + arch/riscv/include/asm/mman.h | 24 + arch/riscv/include/asm/pgtable.h | 30 +- arch/riscv/include/asm/processor.h | 2 + arch/riscv/include/asm/sbi.h | 27 ++ arch/riscv/include/asm/switch_to.h | 8 + arch/riscv/include/asm/thread_info.h | 4 + arch/riscv/include/asm/usercfi.h | 89 ++++ arch/riscv/include/uapi/asm/hwprobe.h | 2 + arch/riscv/include/uapi/asm/ptrace.h | 22 + arch/riscv/include/uapi/asm/sigcontext.h | 1 + arch/riscv/kernel/Makefile | 2 + arch/riscv/kernel/asm-offsets.c | 8 + arch/riscv/kernel/cpufeature.c | 13 +- arch/riscv/kernel/entry.S | 31 +- arch/riscv/kernel/head.S | 12 + arch/riscv/kernel/process.c | 31 +- arch/riscv/kernel/ptrace.c | 83 ++++ arch/riscv/kernel/signal.c | 140 +++++- arch/riscv/kernel/smpboot.c | 2 - arch/riscv/kernel/suspend.c | 4 +- arch/riscv/kernel/sys_hwprobe.c | 2 + arch/riscv/kernel/sys_riscv.c | 10 + arch/riscv/kernel/traps.c | 42 ++ arch/riscv/kernel/usercfi.c | 526 +++++++++++++++++++++ arch/riscv/mm/init.c | 2 +- arch/riscv/mm/pgtable.c | 17 + arch/x86/Kconfig | 1 + fs/proc/task_mmu.c | 2 +- include/linux/cpu.h | 4 + include/linux/mm.h | 5 +- include/uapi/asm-generic/mman.h | 4 + include/uapi/linux/elf.h | 1 + include/uapi/linux/prctl.h | 48 ++ kernel/sys.c | 60 +++ mm/Kconfig | 6 + mm/gup.c | 2 +- mm/mmap.c | 1 + mm/vma.h | 10 +- tools/testing/selftests/riscv/Makefile | 2 +- tools/testing/selftests/riscv/cfi/.gitignore | 3 + tools/testing/selftests/riscv/cfi/Makefile | 10 + tools/testing/selftests/riscv/cfi/cfi_rv_test.h | 83 ++++ tools/testing/selftests/riscv/cfi/riscv_cfi_test.c | 82 ++++ tools/testing/selftests/riscv/cfi/shadowstack.c | 362 ++++++++++++++ tools/testing/selftests/riscv/cfi/shadowstack.h | 37 ++ 55 files changed, 2178 insertions(+), 42 deletions(-) --- base-commit: 9852d85ec9d492ebef56dc5f229416c925758edc change-id: 20240930-v5_user_cfi_series-3dc332f8f5b2 -- - debug

10 months, 3 weeks

7
48
0 0

[PATCH] selftests: vDSO: fix compile error for vdso_test_getrandom

by Yu Liao

When building selftests/vDSO: $ make -C tools/testing/selftests TARGETS=vDSO I hit the following compilation error: vdso_test_getrandom.c:260:17: error: 'CLONE_NEWTIME' undeclared (first use in this function); did you mean 'CLONE_NEWIPC'? 260 | assert(unshare(CLONE_NEWTIME) == 0); | ^~~~~~~~~~~~~ CLONE_NEWTIME is defined in linux/sched.h, so fix this by including <linux/sched.h>. Fixes: 2aec90036dcd ("selftests: vDSO: ensure vgetrandom works in a time namespace") Signed-off-by: Yu Liao <liaoyu15(a)huawei.com> --- tools/testing/selftests/vDSO/vdso_test_getrandom.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/vDSO/vdso_test_getrandom.c b/tools/testing/selftests/vDSO/vdso_test_getrandom.c index 72a1d9b43a84..84f2bbb2d5e0 100644 --- a/tools/testing/selftests/vDSO/vdso_test_getrandom.c +++ b/tools/testing/selftests/vDSO/vdso_test_getrandom.c @@ -19,6 +19,7 @@ #include <sys/ptrace.h> #include <sys/wait.h> #include <sys/types.h> +#include <linux/sched.h> #include <linux/random.h> #include <linux/compiler.h> #include <linux/ptrace.h> -- 2.33.0

10 months, 3 weeks

4
8
0 0

[PATCH] selftests/bpf: Add __init and __exit to the functions bpf_test_no_cfi_init()/bpf_test_no_cfi_exit()

by Yaxiong Tian

From: Yaxiong Tian <iambestgod(a)outlook.com> To save some running memory,Add __init and __exit to the module load/unload functions. Signed-off-by: Yaxiong Tian <tianyaxiong(a)kylinos.cn> --- tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c b/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c index 948eb3962732..aa571ab3c6c6 100644 --- a/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c +++ b/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c @@ -56,7 +56,7 @@ static struct bpf_struct_ops test_no_cif_ops = { .owner = THIS_MODULE, }; -static int bpf_test_no_cfi_init(void) +static int __init bpf_test_no_cfi_init(void) { int ret; @@ -71,7 +71,7 @@ static int bpf_test_no_cfi_init(void) return ret; } -static void bpf_test_no_cfi_exit(void) +static void __exit bpf_test_no_cfi_exit(void) { } -- 2.34.1

10 months, 3 weeks

2
2
0 0

[PATCH v2] selftests: sched_ext: Add sched_ext as proper selftest target

by Björn Töpel

From: Björn Töpel <bjorn(a)rivosinc.com> The sched_ext selftests is missing proper cross-compilation support, a proper target entry, and out-of-tree build support. When building the kselftest suite, e.g.: make ARCH=riscv CROSS_COMPILE=riscv64-linux-gnu- \ SKIP_TARGETS="" O=/output/foo -C tools/testing/selftests install The expectation is that the sched_ext is included, cross-built, and placed into /output/foo. Add CROSS_COMPILE, OUTPUT, and TARGETS support to the sched_ext selftest. Also, remove some variables that were unused by the Makefile. Signed-off-by: Björn Töpel <bjorn(a)rivosinc.com> --- v2: * Removed the duplicated LLVM prefix parsing (David) * Made sure make clean didn't do a complete mess (David) * Added sched_ext to default skip (Shuah) --- tools/testing/selftests/Makefile | 9 +-- tools/testing/selftests/sched_ext/Makefile | 80 +++++++++++----------- 2 files changed, 45 insertions(+), 44 deletions(-) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index b38199965f99..363d031a16f7 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -88,6 +88,7 @@ TARGETS += rlimits TARGETS += rseq TARGETS += rtc TARGETS += rust +TARGETS += sched_ext TARGETS += seccomp TARGETS += sgx TARGETS += sigaltstack @@ -129,10 +130,10 @@ ifeq ($(filter net/lib,$(TARGETS)),) endif endif -# User can optionally provide a TARGETS skiplist. By default we skip -# BPF since it has cutting edge build time dependencies which require -# more effort to install. -SKIP_TARGETS ?= bpf +# User can optionally provide a TARGETS skiplist. By default we skip +# targets using BPF since it has cutting edge build time dependencies +# which require more effort to install. +SKIP_TARGETS ?= bpf sched_ext ifneq ($(SKIP_TARGETS),) TMP := $(filter-out $(SKIP_TARGETS), $(TARGETS)) override TARGETS := $(TMP) diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 0754a2c110a1..acab9732b23e 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -3,24 +3,13 @@ include ../../../build/Build.include include ../../../scripts/Makefile.arch include ../../../scripts/Makefile.include + +TEST_GEN_PROGS := runner + +# override lib.mk's default rules +OVERRIDE_TARGETS := 1 include ../lib.mk -ifneq ($(LLVM),) -ifneq ($(filter %/,$(LLVM)),) -LLVM_PREFIX := $(LLVM) -else ifneq ($(filter -%,$(LLVM)),) -LLVM_SUFFIX := $(LLVM) -endif - -CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX) $(CLANG_FLAGS) -fintegrated-as -else -CC := gcc -endif # LLVM - -ifneq ($(CROSS_COMPILE),) -$(error CROSS_COMPILE not supported for scx selftests) -endif # CROSS_COMPILE - CURDIR := $(abspath .) REPOROOT := $(abspath ../../../..) TOOLSDIR := $(REPOROOT)/tools @@ -34,18 +23,31 @@ GENHDR := $(GENDIR)/autoconf.h SCXTOOLSDIR := $(TOOLSDIR)/sched_ext SCXTOOLSINCDIR := $(TOOLSDIR)/sched_ext/include -OUTPUT_DIR := $(CURDIR)/build +OUTPUT_DIR := $(OUTPUT)/build OBJ_DIR := $(OUTPUT_DIR)/obj INCLUDE_DIR := $(OUTPUT_DIR)/include BPFOBJ_DIR := $(OBJ_DIR)/libbpf SCXOBJ_DIR := $(OBJ_DIR)/sched_ext BPFOBJ := $(BPFOBJ_DIR)/libbpf.a LIBBPF_OUTPUT := $(OBJ_DIR)/libbpf/libbpf.a -DEFAULT_BPFTOOL := $(OUTPUT_DIR)/sbin/bpftool -HOST_BUILD_DIR := $(OBJ_DIR) -HOST_OUTPUT_DIR := $(OUTPUT_DIR) -VMLINUX_BTF_PATHS ?= ../../../../vmlinux \ +ifneq ($(CROSS_COMPILE),) +DEFAULT_BPFTOOL := $(OUTPUT_DIR)/host/sbin/bpftool +HOST_OBJ_DIR := $(OBJ_DIR)/host/bpftool +HOST_LIBBPF_OUTPUT := $(OBJ_DIR)/host/libbpf/ +HOST_LIBBPF_DESTDIR := $(OUTPUT_DIR)/host/ +HOST_DESTDIR := $(OUTPUT_DIR)/host/ +else +DEFAULT_BPFTOOL := $(OUTPUT_DIR)/sbin/bpftool +HOST_OBJ_DIR := $(OBJ_DIR)/bpftool +HOST_LIBBPF_OUTPUT := $(OBJ_DIR)/libbpf/ +HOST_LIBBPF_DESTDIR := $(OUTPUT_DIR)/ +HOST_DESTDIR := $(OUTPUT_DIR)/ +endif + +VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ + $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ + ../../../../vmlinux \ /sys/kernel/btf/vmlinux \ /boot/vmlinux-$(shell uname -r) VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) @@ -80,17 +82,23 @@ IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \ # Use '-idirafter': Don't interfere with include mechanics except where the # build would have failed anyways. define get_sys_includes -$(shell $(1) -v -E - </dev/null 2>&1 \ +$(shell $(1) $(2) -v -E - </dev/null 2>&1 \ | sed -n '/<...> search starts here:/,/End of search list./{ s| $/.*$|-idirafter \1|p }') \ -$(shell $(1) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') +$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') endef +ifneq ($(CROSS_COMPILE),) +CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) +endif + +CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) + BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) \ $(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) \ -I$(CURDIR)/include -I$(CURDIR)/include/bpf-compat \ -I$(INCLUDE_DIR) -I$(APIDIR) -I$(SCXTOOLSINCDIR) \ -I$(REPOROOT)/include \ - $(call get_sys_includes,$(CLANG)) \ + $(CLANG_SYS_INCLUDES) \ -Wall -Wno-compare-distinct-pointer-types \ -Wno-incompatible-function-pointer-types \ -O2 -mcpu=v3 @@ -98,7 +106,7 @@ BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) \ # sort removes libbpf duplicates when not cross-building MAKE_DIRS := $(sort $(OBJ_DIR)/libbpf $(OBJ_DIR)/libbpf \ $(OBJ_DIR)/bpftool $(OBJ_DIR)/resolve_btfids \ - $(INCLUDE_DIR) $(SCXOBJ_DIR)) + $(HOST_OBJ_DIR) $(INCLUDE_DIR) $(SCXOBJ_DIR)) $(MAKE_DIRS): $(call msg,MKDIR,,$@) @@ -112,14 +120,14 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ DESTDIR=$(OUTPUT_DIR) prefix= all install_headers $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ - $(LIBBPF_OUTPUT) | $(OBJ_DIR)/bpftool + $(LIBBPF_OUTPUT) | $(HOST_OBJ_DIR) $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \ ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) \ EXTRA_CFLAGS='-g -O0' \ - OUTPUT=$(OBJ_DIR)/bpftool/ \ - LIBBPF_OUTPUT=$(OBJ_DIR)/libbpf/ \ - LIBBPF_DESTDIR=$(OUTPUT_DIR)/ \ - prefix= DESTDIR=$(OUTPUT_DIR)/ install-bin + OUTPUT=$(HOST_OBJ_DIR)/ \ + LIBBPF_OUTPUT=$(HOST_LIBBPF_OUTPUT) \ + LIBBPF_DESTDIR=$(HOST_LIBBPF_DESTDIR) \ + prefix= DESTDIR=$(HOST_DESTDIR) install-bin $(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR) ifeq ($(VMLINUX_H),) @@ -150,9 +158,7 @@ $(INCLUDE_DIR)/%.bpf.skel.h: $(SCXOBJ_DIR)/%.bpf.o $(INCLUDE_DIR)/vmlinux.h $(BP override define CLEAN rm -rf $(OUTPUT_DIR) - rm -f *.o *.bpf.o *.bpf.skel.h *.bpf.subskel.h rm -f $(TEST_GEN_PROGS) - rm -f runner endef # Every testcase takes all of the BPF progs are dependencies by default. This @@ -196,21 +202,15 @@ $(SCXOBJ_DIR)/runner.o: runner.c | $(SCXOBJ_DIR) # function doesn't support using implicit rules otherwise. $(testcase-targets): $(SCXOBJ_DIR)/%.o: %.c $(SCXOBJ_DIR)/runner.o $(all_test_bpfprogs) | $(SCXOBJ_DIR) $(eval test=$(patsubst %.o,%.c,$(notdir $@))) - $(CC) $(CFLAGS) -c $< -o $@ $(SCXOBJ_DIR)/runner.o + $(CC) $(CFLAGS) -c $< -o $@ $(SCXOBJ_DIR)/util.o: util.c | $(SCXOBJ_DIR) $(CC) $(CFLAGS) -c $< -o $@ -runner: $(SCXOBJ_DIR)/runner.o $(SCXOBJ_DIR)/util.o $(BPFOBJ) $(testcase-targets) +$(OUTPUT)/runner: $(SCXOBJ_DIR)/runner.o $(SCXOBJ_DIR)/util.o $(BPFOBJ) $(testcase-targets) @echo "$(testcase-targets)" $(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS) -TEST_GEN_PROGS := runner - -all: runner - -.PHONY: all clean help - .DEFAULT_GOAL := all .DELETE_ON_ERROR: base-commit: 8cf0b93919e13d1e8d4466eb4080a4c4d9d66d7b -- 2.43.0

10 months, 3 weeks

2
7
0 0

[PATCH v4] Kunit to check the longest symbol length

by Sergio González Collado

The longest length of a symbol (KSYM_NAME_LEN) was increased to 512 in the reference [1]. This patch adds a kunit test to check the longest symbol length. This test can also help other efforts for longer symbol lenght, like [2]. [1] https://lore.kernel.org/lkml/20220802015052.10452-6-ojeda@kernel.org/ [2] https://lore.kernel.org/lkml/20240605032120.3179157-1-song@kernel.org/ Tested-by: Martin Rodriguez Reboredo <yakoyoku(a)gmail.com> Signed-off-by: Sergio González Collado <sergio.collado(a)gmail.com> --- V1 -> V2: corrected CI tests. Added fix proposed at [3] [3] https://lore.kernel.org/lkml/Y9ES4UKl%2F+DtvAVS@gmail.com/T/#m3ef0e12bb834d… --- V2 -> V3: updated base and added MODULE_DESCRIPTION() and MODULE_AUTHOR() --- V3 -> V4: add x86 mantainers, add new reference. --- arch/x86/tools/insn_decoder_test.c | 3 +- lib/Kconfig.debug | 9 +++ lib/Makefile | 2 + lib/longest_symbol_kunit.c | 124 +++++++++++++++++++++++++++++ 4 files changed, 137 insertions(+), 1 deletion(-) create mode 100644 lib/longest_symbol_kunit.c diff --git a/arch/x86/tools/insn_decoder_test.c b/arch/x86/tools/insn_decoder_test.c index 472540aeabc2..3bde35ea4188 100644 --- a/arch/x86/tools/insn_decoder_test.c +++ b/arch/x86/tools/insn_decoder_test.c @@ -10,6 +10,7 @@ #include <assert.h> #include <unistd.h> #include <stdarg.h> +#include <linux/kallsysms.h> #define unlikely(cond) (cond) @@ -106,7 +107,7 @@ static void parse_args(int argc, char **argv) } } -#define BUFSIZE 256 +#define BUFSIZE (256 + KSYM_NAME_LEN) int main(int argc, char **argv) { diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index bc8faa4509e1..09015e7e07f3 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2805,6 +2805,15 @@ config FORTIFY_KUNIT_TEST by the str*() and mem*() family of functions. For testing runtime traps of FORTIFY_SOURCE, see LKDTM's "FORTIFY_*" tests. +config LONGEST_SYM_KUNIT_TEST + tristate "Test the longest symbol possible" if !KUNIT_ALL_TESTS + depends on KUNIT && KPROBES + default KUNIT_ALL_TESTS + help + Tests the longest symbol possible + + If unsure, say N. + config HW_BREAKPOINT_KUNIT_TEST bool "Test hw_breakpoint constraints accounting" if !KUNIT_ALL_TESTS depends on HAVE_HW_BREAKPOINT diff --git a/lib/Makefile b/lib/Makefile index 773adf88af41..fc878e716825 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -389,6 +389,8 @@ 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_LONGEST_SYM_KUNIT_TEST) += longest_symbol_kunit.o +CFLAGS_longest_symbol_kunit.o += $(call cc-disable-warning, missing-prototypes) obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o diff --git a/lib/longest_symbol_kunit.c b/lib/longest_symbol_kunit.c new file mode 100644 index 000000000000..557ad6eae56c --- /dev/null +++ b/lib/longest_symbol_kunit.c @@ -0,0 +1,124 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test the longest symbol length. Execute with: + * ./tools/testing/kunit/kunit.py run longest-symbol + * --arch=x86_64 --kconfig_add CONFIG_KPROBES=y --kconfig_add CONFIG_MODULES=y + * --kconfig_add CONFIG_RETPOLINE=n + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <kunit/test.h> +#include <linux/stringify.h> +#include <linux/kprobes.h> +#include <linux/kallsyms.h> + +#define DI(name) s##name##name +#define DDI(name) DI(n##name##name) +#define DDDI(name) DDI(n##name##name) +#define DDDDI(name) DDDI(n##name##name) +#define DDDDDI(name) DDDDI(n##name##name) + +#define PLUS1(name) __PASTE(name, e) + +/*Generate a symbol whose name length is 511 */ +#define LONGEST_SYM_NAME DDDDDI(g1h2i3j4k5l6m7n) + +/*Generate a symbol whose name length is 512 */ +#define LONGEST_SYM_NAME_PLUS1 PLUS1(LONGEST_SYM_NAME) + +#define RETURN_LONGEST_SYM 0xAAAAA +#define RETURN_LONGEST_SYM_PLUS1 0x55555 + +noinline int LONGEST_SYM_NAME(void); +noinline int LONGEST_SYM_NAME(void) +{ + return RETURN_LONGEST_SYM; +} + +noinline int LONGEST_SYM_NAME_PLUS1(void); +noinline int LONGEST_SYM_NAME_PLUS1(void) +{ + return RETURN_LONGEST_SYM_PLUS1; +} + +_Static_assert(sizeof(__stringify(LONGEST_SYM_NAME)) == KSYM_NAME_LEN, +"Incorrect symbol length found. Expected KSYM_NAME_LEN: " +__stringify(KSYM_NAME) ", but found: " +__stringify(sizeof(LONGEST_SYM_NAME))); + +static void test_longest_symbol(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, RETURN_LONGEST_SYM, LONGEST_SYM_NAME()); +}; + +static void test_longest_symbol_kallsyms(struct kunit *test) +{ + unsigned long (*kallsyms_lookup_name)(const char *name); + static int (*longest_sym)(void); + + struct kprobe kp = { + .symbol_name = "kallsyms_lookup_name", + }; + + if (register_kprobe(&kp) < 0) { + pr_info("%s: kprobe not registered\n", __func__); + KUNIT_FAIL(test, "test_longest_symbol kallsysms: kprobe not registered\n"); + return; + } + + kunit_warn(test, "test_longest_symbol kallsyms: kprobe registered\n"); + kallsyms_lookup_name = (unsigned long (*)(const char *name))kp.addr; + unregister_kprobe(&kp); + + longest_sym = + (void *) kallsyms_lookup_name(__stringify(LONGEST_SYM_NAME)); + KUNIT_EXPECT_EQ(test, RETURN_LONGEST_SYM, longest_sym()); +}; + +static void test_longest_symbol_plus1(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, RETURN_LONGEST_SYM_PLUS1, LONGEST_SYM_NAME_PLUS1()); +}; + +static void test_longest_symbol_plus1_kallsyms(struct kunit *test) +{ + unsigned long (*kallsyms_lookup_name)(const char *name); + static int (*longest_sym_plus1)(void); + + struct kprobe kp = { + .symbol_name = "kallsyms_lookup_name", + }; + + if (register_kprobe(&kp) < 0) { + pr_info("%s: kprobe not registered\n", __func__); + KUNIT_FAIL(test, "test_longest_symbol kallsysms: kprobe not registered\n"); + return; + } + + kunit_warn(test, "test_longest_symbol_plus1 kallsyms: kprobe registered\n"); + kallsyms_lookup_name = (unsigned long (*)(const char *name))kp.addr; + unregister_kprobe(&kp); + + longest_sym_plus1 = + (void *) kallsyms_lookup_name(__stringify(LONGEST_SYM_NAME_PLUS1)); + KUNIT_EXPECT_NULL(test, longest_sym_plus1); +}; + +static struct kunit_case longest_symbol_test_cases[] = { + KUNIT_CASE(test_longest_symbol), + KUNIT_CASE(test_longest_symbol_kallsyms), + KUNIT_CASE(test_longest_symbol_plus1), + KUNIT_CASE(test_longest_symbol_plus1_kallsyms), + {} +}; + +static struct kunit_suite longest_symbol_test_suite = { + .name = "longest-symbol", + .test_cases = longest_symbol_test_cases, +}; +kunit_test_suite(longest_symbol_test_suite); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Test the longest symbol length"); +MODULE_AUTHOR("Sergio González Collado"); base-commit: abf2050f51fdca0fd146388f83cddd95a57a008d -- 2.39.2

10 months, 3 weeks

2
1
0 0

[RESEND PATCH v3] list: test: Mending tests for list_cut_position()

by I Hsin Cheng

Mending test for list_cut_position*() for the missing check of integer "i" after the second loop. The variable should be checked for second time to make sure both lists after the cut operation are formed as expected. Signed-off-by: I Hsin Cheng <richard120310(a)gmail.com> --- lib/list-test.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/lib/list-test.c b/lib/list-test.c index 37cbc33e9fdb..b4b3810c71d0 100644 --- a/lib/list-test.c +++ b/lib/list-test.c @@ -408,6 +408,8 @@ static void list_test_list_cut_position(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); i++; } + + KUNIT_EXPECT_EQ(test, i, 3); } static void list_test_list_cut_before(struct kunit *test) @@ -436,6 +438,8 @@ static void list_test_list_cut_before(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); i++; } + + KUNIT_EXPECT_EQ(test, i, 3); } static void list_test_list_splice(struct kunit *test) -- 2.43.0

10 months, 3 weeks

3
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror October 2024