From 2ede647a6fde3e54a6bfda7cf01c716649655900 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Ricardo=20Ca=C3=B1uelo=20Navarro?= Date: Mon, 3 Feb 2025 08:52:06 +0100 Subject: [PATCH 01/16] mm,madvise,hugetlb: check for 0-length range after end address adjustment MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Add a sanity check to madvise_dontneed_free() to address a corner case in madvise where a race condition causes the current vma being processed to be backed by a different page size. During a madvise(MADV_DONTNEED) call on a memory region registered with a userfaultfd, there's a period of time where the process mm lock is temporarily released in order to send a UFFD_EVENT_REMOVE and let userspace handle the event. During this time, the vma covering the current address range may change due to an explicit mmap done concurrently by another thread. If, after that change, the memory region, which was originally backed by 4KB pages, is now backed by hugepages, the end address is rounded down to a hugepage boundary to avoid data loss (see "Fixes" below). This rounding may cause the end address to be truncated to the same address as the start. Make this corner case follow the same semantics as in other similar cases where the requested region has zero length (ie. return 0). This will make madvise_walk_vmas() continue to the next vma in the range (this time holding the process mm lock) which, due to the prev pointer becoming stale because of the vma change, will be the same hugepage-backed vma that was just checked before. The next time madvise_dontneed_free() runs for this vma, if the start address isn't aligned to a hugepage boundary, it'll return -EINVAL, which is also in line with the madvise api. From userspace perspective, madvise() will return EINVAL because the start address isn't aligned according to the new vma alignment requirements (hugepage), even though it was correctly page-aligned when the call was issued. Link: https://lkml.kernel.org/r/20250203075206.1452208-1-rcn@igalia.com Fixes: 8ebe0a5eaaeb ("mm,madvise,hugetlb: fix unexpected data loss with MADV_DONTNEED on hugetlbfs") Signed-off-by: Ricardo Cañuelo Navarro Reviewed-by: Oscar Salvador Cc: Florent Revest Cc: Rik van Riel Cc: Signed-off-by: Andrew Morton --- mm/madvise.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/mm/madvise.c b/mm/madvise.c index 49f3a75046f6..08b207f8e61e 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -933,7 +933,16 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, */ end = vma->vm_end; } - VM_WARN_ON(start >= end); + /* + * If the memory region between start and end was + * originally backed by 4kB pages and then remapped to + * be backed by hugepages while mmap_lock was dropped, + * the adjustment for hugetlb vma above may have rounded + * end down to the start address. + */ + if (start == end) + return 0; + VM_WARN_ON(start > end); } if (behavior == MADV_DONTNEED || behavior == MADV_DONTNEED_LOCKED) -- 2.51.0 From 639375b0aa4323fe59b5fe2a6ebc68b022c36f50 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Wed, 5 Feb 2025 12:01:00 -0800 Subject: [PATCH 02/16] .mailmap: add entries for Jeff Johnson Map past iterations of my e-mail addresses to the current one. Link: https://lkml.kernel.org/r/20250205-jjohnson-mailmap-v1-1-269cb7b1710d@oss.qualcomm.com Signed-off-by: Jeff Johnson Signed-off-by: Andrew Morton --- .mailmap | 2 ++ 1 file changed, 2 insertions(+) diff --git a/.mailmap b/.mailmap index fedebf86640a..c96dbe259c22 100644 --- a/.mailmap +++ b/.mailmap @@ -317,6 +317,8 @@ Jayachandran C Jean Tourrilhes Jeevan Shriram Jeff Garzik +Jeff Johnson +Jeff Johnson Jeff Layton Jeff Layton Jeff Layton -- 2.51.0 From 3219585e894c12cbffd4ac93d3e6783d236f146e Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Wed, 5 Feb 2025 14:04:57 +0800 Subject: [PATCH 03/16] mailmap: add entry for Feng Tang Map my old business email to personal email. Link: https://lkml.kernel.org/r/20250205060457.53667-1-feng.tang@linux.alibaba.com Signed-off-by: Feng Tang Signed-off-by: Andrew Morton --- .mailmap | 1 + 1 file changed, 1 insertion(+) diff --git a/.mailmap b/.mailmap index c96dbe259c22..f34af946180f 100644 --- a/.mailmap +++ b/.mailmap @@ -226,6 +226,7 @@ Fangrui Song Felipe W Damasio Felix Kuhling Felix Moeller +Feng Tang Fenglin Wu Filipe Lautert Finn Thain -- 2.51.0 From 035d3c778709680288b3954ee896043132bc3f8d Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 10 Feb 2025 12:05:18 -0800 Subject: [PATCH 04/16] tools/mm: fix build warnings with musl-libc musl-libc warns about the following: /home/florian/dev/buildroot/output/arm64/rpi4-b/host/aarch64-buildroot-linux-musl/sysroot/usr/include/sys/errno.h:1:2: attention: #warning redirecting incorrect #include to [-Wcpp] 1 | #warning redirecting incorrect #include to | ^~~~~~~ /home/florian/dev/buildroot/output/arm64/rpi4-b/host/aarch64-buildroot-linux-musl/sysroot/usr/include/sys/fcntl.h:1:2: attention: #warning redirecting incorrect #include to [-Wcpp] 1 | #warning redirecting incorrect #include to | ^~~~~~~ include errno.h and fcntl.h directly. Link: https://lkml.kernel.org/r/20250210200518.1137295-1-florian.fainelli@broadcom.com Signed-off-by: Florian Fainelli Signed-off-by: Andrew Morton --- tools/mm/page-types.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/mm/page-types.c b/tools/mm/page-types.c index bcac7ebfb51f..d7e5e8902af8 100644 --- a/tools/mm/page-types.c +++ b/tools/mm/page-types.c @@ -24,8 +24,8 @@ #include #include #include -#include -#include +#include +#include #include #include #include -- 2.51.0 From 41cddf83d8b00f29fd105e7a0777366edc69a5cf Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 10 Feb 2025 17:13:17 +0100 Subject: [PATCH 05/16] mm/migrate_device: don't add folio to be freed to LRU in migrate_device_finalize() MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit If migration succeeded, we called folio_migrate_flags()->mem_cgroup_migrate() to migrate the memcg from the old to the new folio. This will set memcg_data of the old folio to 0. Similarly, if migration failed, memcg_data of the dst folio is left unset. If we call folio_putback_lru() on such folios (memcg_data == 0), we will add the folio to be freed to the LRU, making memcg code unhappy. Running the hmm selftests: # ./hmm-tests ... # RUN hmm.hmm_device_private.migrate ... [ 102.078007][T14893] page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x7ff27d200 pfn:0x13cc00 [ 102.079974][T14893] anon flags: 0x17ff00000020018(uptodate|dirty|swapbacked|node=0|zone=2|lastcpupid=0x7ff) [ 102.082037][T14893] raw: 017ff00000020018 dead000000000100 dead000000000122 ffff8881353896c9 [ 102.083687][T14893] raw: 00000007ff27d200 0000000000000000 00000001ffffffff 0000000000000000 [ 102.085331][T14893] page dumped because: VM_WARN_ON_ONCE_FOLIO(!memcg && !mem_cgroup_disabled()) [ 102.087230][T14893] ------------[ cut here ]------------ [ 102.088279][T14893] WARNING: CPU: 0 PID: 14893 at ./include/linux/memcontrol.h:726 folio_lruvec_lock_irqsave+0x10e/0x170 [ 102.090478][T14893] Modules linked in: [ 102.091244][T14893] CPU: 0 UID: 0 PID: 14893 Comm: hmm-tests Not tainted 6.13.0-09623-g6c216bc522fd #151 [ 102.093089][T14893] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-2.fc40 04/01/2014 [ 102.094848][T14893] RIP: 0010:folio_lruvec_lock_irqsave+0x10e/0x170 [ 102.096104][T14893] Code: ... [ 102.099908][T14893] RSP: 0018:ffffc900236c37b0 EFLAGS: 00010293 [ 102.101152][T14893] RAX: 0000000000000000 RBX: ffffea0004f30000 RCX: ffffffff8183f426 [ 102.102684][T14893] RDX: ffff8881063cb880 RSI: ffffffff81b8117f RDI: ffff8881063cb880 [ 102.104227][T14893] RBP: 0000000000000000 R08: 0000000000000005 R09: 0000000000000000 [ 102.105757][T14893] R10: 0000000000000001 R11: 0000000000000002 R12: ffffc900236c37d8 [ 102.107296][T14893] R13: ffff888277a2bcb0 R14: 000000000000001f R15: 0000000000000000 [ 102.108830][T14893] FS: 00007ff27dbdd740(0000) GS:ffff888277a00000(0000) knlGS:0000000000000000 [ 102.110643][T14893] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 102.111924][T14893] CR2: 00007ff27d400000 CR3: 000000010866e000 CR4: 0000000000750ef0 [ 102.113478][T14893] PKRU: 55555554 [ 102.114172][T14893] Call Trace: [ 102.114805][T14893] [ 102.115397][T14893] ? folio_lruvec_lock_irqsave+0x10e/0x170 [ 102.116547][T14893] ? __warn.cold+0x110/0x210 [ 102.117461][T14893] ? folio_lruvec_lock_irqsave+0x10e/0x170 [ 102.118667][T14893] ? report_bug+0x1b9/0x320 [ 102.119571][T14893] ? handle_bug+0x54/0x90 [ 102.120494][T14893] ? exc_invalid_op+0x17/0x50 [ 102.121433][T14893] ? asm_exc_invalid_op+0x1a/0x20 [ 102.122435][T14893] ? __wake_up_klogd.part.0+0x76/0xd0 [ 102.123506][T14893] ? dump_page+0x4f/0x60 [ 102.124352][T14893] ? folio_lruvec_lock_irqsave+0x10e/0x170 [ 102.125500][T14893] folio_batch_move_lru+0xd4/0x200 [ 102.126577][T14893] ? __pfx_lru_add+0x10/0x10 [ 102.127505][T14893] __folio_batch_add_and_move+0x391/0x720 [ 102.128633][T14893] ? __pfx_lru_add+0x10/0x10 [ 102.129550][T14893] folio_putback_lru+0x16/0x80 [ 102.130564][T14893] migrate_device_finalize+0x9b/0x530 [ 102.131640][T14893] dmirror_migrate_to_device.constprop.0+0x7c5/0xad0 [ 102.133047][T14893] dmirror_fops_unlocked_ioctl+0x89b/0xc80 Likely, nothing else goes wrong: putting the last folio reference will remove the folio from the LRU again. So besides memcg complaining, adding the folio to be freed to the LRU is just an unnecessary step. The new flow resembles what we have in migrate_folio_move(): add the dst to the lru, remove migration ptes, unlock and unref dst. Link: https://lkml.kernel.org/r/20250210161317.717936-1-david@redhat.com Fixes: 8763cb45ab96 ("mm/migrate: new memory migration helper for use with device memory") Signed-off-by: David Hildenbrand Cc: Jérôme Glisse Cc: John Hubbard Cc: Alistair Popple Cc: Signed-off-by: Andrew Morton --- mm/migrate_device.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 9cf26592ac93..5bd888223cc8 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -840,20 +840,15 @@ void migrate_device_finalize(unsigned long *src_pfns, dst = src; } + if (!folio_is_zone_device(dst)) + folio_add_lru(dst); remove_migration_ptes(src, dst, 0); folio_unlock(src); - - if (folio_is_zone_device(src)) - folio_put(src); - else - folio_putback_lru(src); + folio_put(src); if (dst != src) { folio_unlock(dst); - if (folio_is_zone_device(dst)) - folio_put(dst); - else - folio_putback_lru(dst); + folio_put(dst); } } } -- 2.51.0 From 2272dbc471037b78f308b44351ab1b9f88d32628 Mon Sep 17 00:00:00 2001 From: Wang Yaxin Date: Sat, 8 Feb 2025 14:44:00 +0800 Subject: [PATCH 06/16] getdelays: fix error format characters getdelays had a compilation issue because the format string was not updated when the "delay min" was added. For example, after adding the "delay min" in printf, there were 7 strings but only 6 "%s" format specifiers. Similarly, after adding the 't->cpu_delay_total', there were 7 variables but only 6 format characters specifiers, causing compilation issues as follows. This commit fixes these issues to ensure that getdelays compiles correctly. root@xx:~/linux-next/tools/accounting$ make getdelays.c:199:9: warning: format `%llu' expects argument of type `long long unsigned int', but argument 8 has type `char *' [-Wformat=] 199 | printf("\n\nCPU %15s%15s%15s%15s%15s%15s\n" | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ..... 216 | "delay total", "delay average", "delay max", "delay min", | ~~~~~~~~~~~ | | | char * getdelays.c:200:21: note: format string is defined here 200 | " %15llu%15llu%15llu%15llu%15.3fms%13.6fms\n" | ~~~~~^ | | | long long unsigned int | %15s getdelays.c:199:9: warning: format `%f' expects argument of type `double', but argument 12 has type `long long unsigned int' [-Wformat=] 199 | printf("\n\nCPU %15s%15s%15s%15s%15s%15s\n" | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ..... 220 | (unsigned long long)t->cpu_delay_total, | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | | | long long unsigned int ..... Link: https://lkml.kernel.org/r/20250208144400544RduNRhwIpT3m2JyRBqskZ@zte.com.cn Fixes: f65c64f311ee ("delayacct: add delay min to record delay peak") Reviewed-by: xu xin Signed-off-by: Wang Yaxin Signed-off-by: Kun Jiang Cc: Balbir Singh Cc: David Hildenbrand Cc: Fan Yu Cc: Peilin He Cc: Qiang Tu Cc: wangyong Cc: ye xingchen Cc: Yunkai Zhang Signed-off-by: Andrew Morton --- tools/accounting/getdelays.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 100ad3dc091a..3feac0482fe9 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -196,22 +196,22 @@ static int get_family_id(int sd) static void print_delayacct(struct taskstats *t) { - printf("\n\nCPU %15s%15s%15s%15s%15s%15s\n" - " %15llu%15llu%15llu%15llu%15.3fms%13.6fms\n" - "IO %15s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "SWAP %15s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "RECLAIM %12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "THRASHING%12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "COMPACT %12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "WPCOPY %12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "IRQ %15s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n", + printf("\n\nCPU %15s%15s%15s%15s%15s%15s%15s\n" + " %15llu%15llu%15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "IO %15s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "SWAP %15s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "RECLAIM %12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "THRASHING%12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "COMPACT %12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "WPCOPY %12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "IRQ %15s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n", "count", "real total", "virtual total", "delay total", "delay average", "delay max", "delay min", (unsigned long long)t->cpu_count, -- 2.51.0 From b016d0873777462e55af4c615104cc684fce086d Mon Sep 17 00:00:00 2001 From: Wang Yaxin Date: Sat, 8 Feb 2025 14:49:01 +0800 Subject: [PATCH 07/16] taskstats: modify taskstats version After adding "delay max" and "delay min" to the taskstats structure, the taskstats version needs to be updated. Link: https://lkml.kernel.org/r/20250208144901218Q5ptVpqsQkb2MOEmW4Ujn@zte.com.cn Fixes: f65c64f311ee ("delayacct: add delay min to record delay peak") Signed-off-by: Wang Yaxin Signed-off-by: Kun Jiang Reviewed-by: xu xin Signed-off-by: Andrew Morton --- include/uapi/linux/taskstats.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 934e20ef7f79..95762232e018 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 14 +#define TASKSTATS_VERSION 15 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ -- 2.51.0 From f39edcf6349abb2ca2df96acc8645f4d2631d0a7 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Tue, 11 Feb 2025 15:26:25 +0800 Subject: [PATCH 08/16] mm: pgtable: fix incorrect reclaim of non-empty PTE pages In zap_pte_range(), if the pte lock was released midway, the pte entries may be refilled with physical pages by another thread, which may cause a non-empty PTE page to be reclaimed and eventually cause the system to crash. To fix it, fall back to the slow path in this case to recheck if all pte entries are still none. Link: https://lkml.kernel.org/r/20250211072625.89188-1-zhengqi.arch@bytedance.com Fixes: 6375e95f381e ("mm: pgtable: reclaim empty PTE page in madvise(MADV_DONTNEED)") Signed-off-by: Qi Zheng Reported-by: Christian Brauner Closes: https://lore.kernel.org/all/20250207-anbot-bankfilialen-acce9d79a2c7@brauner/ Reported-by: Qu Wenruo Closes: https://lore.kernel.org/all/152296f3-5c81-4a94-97f3-004108fba7be@gmx.com/ Tested-by: Zi Yan Cc: Cc: "Darrick J. Wong" Cc: Dave Chinner Cc: David Hildenbrand Cc: Jann Horn Cc: Matthew Wilcox Cc: Muchun Song Cc: Zi Yan Signed-off-by: Andrew Morton --- mm/memory.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index 539c0f7c6d54..b4d3d4893267 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1719,7 +1719,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, pmd_t pmdval; unsigned long start = addr; bool can_reclaim_pt = reclaim_pt_is_enabled(start, end, details); - bool direct_reclaim = false; + bool direct_reclaim = true; int nr; retry: @@ -1734,8 +1734,10 @@ retry: do { bool any_skipped = false; - if (need_resched()) + if (need_resched()) { + direct_reclaim = false; break; + } nr = do_zap_pte_range(tlb, vma, pte, addr, end, details, rss, &force_flush, &force_break, &any_skipped); @@ -1743,11 +1745,20 @@ retry: can_reclaim_pt = false; if (unlikely(force_break)) { addr += nr * PAGE_SIZE; + direct_reclaim = false; break; } } while (pte += nr, addr += PAGE_SIZE * nr, addr != end); - if (can_reclaim_pt && addr == end) + /* + * Fast path: try to hold the pmd lock and unmap the PTE page. + * + * If the pte lock was released midway (retry case), or if the attempt + * to hold the pmd lock failed, then we need to recheck all pte entries + * to ensure they are still none, thereby preventing the pte entries + * from being repopulated by another thread. + */ + if (can_reclaim_pt && direct_reclaim && addr == end) direct_reclaim = try_get_and_clear_pmd(mm, pmd, &pmdval); add_mm_rss_vec(mm, rss); -- 2.51.0 From 8648ee2622aefa5b567ebea71609822373995f37 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Tue, 11 Feb 2025 13:21:17 -0800 Subject: [PATCH 09/16] mailmap: update Nick's entry Link: https://lkml.kernel.org/r/20250211212117.3195265-1-ndesaulniers@google.com Signed-off-by: Nick Desaulniers Signed-off-by: Andrew Morton --- .mailmap | 1 + 1 file changed, 1 insertion(+) diff --git a/.mailmap b/.mailmap index f34af946180f..a897c16d3bae 100644 --- a/.mailmap +++ b/.mailmap @@ -534,6 +534,7 @@ Nicholas Piggin Nicholas Piggin Nicholas Piggin Nicholas Piggin +Nick Desaulniers Nicolas Ferre Nicolas Pitre Nicolas Pitre -- 2.51.0 From 99333229dee41b992f3b0493f6aa2e3528138384 Mon Sep 17 00:00:00 2001 From: Chen Ridong Date: Tue, 11 Feb 2025 08:18:19 +0000 Subject: [PATCH 10/16] memcg: avoid dead loop when setting memory.max A softlockup issue was found with stress test: watchdog: BUG: soft lockup - CPU#27 stuck for 26s! [migration/27:181] CPU: 27 UID: 0 PID: 181 Comm: migration/27 6.14.0-rc2-next-20250210 #1 Stopper: multi_cpu_stop <- stop_machine_from_inactive_cpu RIP: 0010:stop_machine_yield+0x2/0x10 RSP: 0000:ff4a0dcecd19be48 EFLAGS: 00000246 RAX: ffffffff89c0108f RBX: ff4a0dcec03afe44 RCX: 0000000000000000 RDX: ff1cdaaf6eba5808 RSI: 0000000000000282 RDI: ff1cda80c1775a40 RBP: 0000000000000001 R08: 00000011620096c6 R09: 7fffffffffffffff R10: 0000000000000001 R11: 0000000000000100 R12: ff1cda80c1775a40 R13: 0000000000000000 R14: 0000000000000001 R15: ff4a0dcec03afe20 FS: 0000000000000000(0000) GS:ff1cdaaf6eb80000(0000) CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000025e2c2a001 CR4: 0000000000773ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: multi_cpu_stop+0x8f/0x100 cpu_stopper_thread+0x90/0x140 smpboot_thread_fn+0xad/0x150 kthread+0xc2/0x100 ret_from_fork+0x2d/0x50 The stress test involves CPU hotplug operations and memory control group (memcg) operations. The scenario can be described as follows: echo xx > memory.max cache_ap_online oom_reaper (CPU23) (CPU50) xx < usage stop_machine_from_inactive_cpu for(;;) // all active cpus trigger OOM queue_stop_cpus_work // waiting oom_reaper multi_cpu_stop(migration/xx) // sync all active cpus ack // waiting cpu23 ack // CPU50 loops in multi_cpu_stop waiting cpu50 Detailed explanation: 1. When the usage is larger than xx, an OOM may be triggered. If the process does not handle with ths kill signal immediately, it will loop in the memory_max_write. 2. When cache_ap_online is triggered, the multi_cpu_stop is queued to the active cpus. Within the multi_cpu_stop function, it attempts to synchronize the CPU states. However, the CPU23 didn't acknowledge because it is stuck in a loop within the for(;;). 3. The oom_reaper process is blocked because CPU50 is in a loop, waiting for CPU23 to acknowledge the synchronization request. 4. Finally, it formed cyclic dependency and lead to softlockup and dead loop. To fix this issue, add cond_resched() in the memory_max_write, so that it will not block migration task. Link: https://lkml.kernel.org/r/20250211081819.33307-1-chenridong@huaweicloud.com Fixes: b6e6edcfa405 ("mm: memcontrol: reclaim and OOM kill when shrinking memory.max below usage") Signed-off-by: Chen Ridong Acked-by: Michal Hocko Cc: Roman Gushchin Cc: Johannes Weiner Cc: Shakeel Butt Cc: Muchun Song Cc: Wang Weiyang Signed-off-by: Andrew Morton --- mm/memcontrol.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 46f8b372d212..4de6acb9b8ec 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4166,6 +4166,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, memcg_memory_event(memcg, MEMCG_OOM); if (!mem_cgroup_out_of_memory(memcg, GFP_KERNEL, 0)) break; + cond_resched(); } memcg_wb_domain_size_changed(memcg); -- 2.51.0 From 6d7bc938adca9024a6b51cf55d9b0542b653b69c Mon Sep 17 00:00:00 2001 From: Luiz Capitulino Date: Mon, 10 Feb 2025 22:48:56 -0500 Subject: [PATCH 11/16] mm: hugetlb: avoid fallback for specific node allocation of 1G pages When using the HugeTLB kernel command-line to allocate 1G pages from a specific node, such as: default_hugepagesz=1G hugepages=1:1 If node 1 happens to not have enough memory for the requested number of 1G pages, the allocation falls back to other nodes. A quick way to reproduce this is by creating a KVM guest with a memory-less node and trying to allocate 1 1G page from it. Instead of failing, the allocation will fallback to other nodes. This defeats the purpose of node specific allocation. Also, specific node allocation for 2M pages don't have this behavior: the allocation will just fail for the pages it can't satisfy. This issue happens because HugeTLB calls memblock_alloc_try_nid_raw() for 1G boot-time allocation as this function falls back to other nodes if the allocation can't be satisfied. Use memblock_alloc_exact_nid_raw() instead, which ensures that the allocation will only be satisfied from the specified node. Link: https://lkml.kernel.org/r/20250211034856.629371-1-luizcap@redhat.com Fixes: b5389086ad7b ("hugetlbfs: extend the definition of hugepages parameter to support node allocation") Signed-off-by: Luiz Capitulino Acked-by: Oscar Salvador Acked-by: David Hildenbrand Cc: "Mike Rapoport (IBM)" Cc: Muchun Song Cc: Zhenguo Yao Cc: Frank van der Linden Signed-off-by: Andrew Morton --- mm/hugetlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 65068671e460..163190e89ea1 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3145,7 +3145,7 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid) /* do node specific alloc */ if (nid != NUMA_NO_NODE) { - m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), + m = memblock_alloc_exact_nid_raw(huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); if (!m) return 0; -- 2.51.0 From 5dcf52e2ce0fe3c4516b1e494c1af6d3a69e30e7 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 12 Feb 2025 17:44:25 +0000 Subject: [PATCH 12/16] selftests/mm: fix check for running THP tests When testing if we should try to compact memory or drop caches before we run the THP or HugeTLB tests we use | as an or operator. This doesn't work since run_vmtests.sh is written in shell where this is used to pipe the output of the first argument into the second. Instead use the shell's -o operator. Link: https://lkml.kernel.org/r/20250212-kselftest-mm-no-hugepages-v1-1-44702f538522@kernel.org Fixes: b433ffa8dbac ("selftests: mm: perform some system cleanup before using hugepages") Signed-off-by: Mark Brown Reviewed-by: Nico Pache Cc: Mariano Pache Cc: Shuah Khan Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/run_vmtests.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 333c468c2699..da7e26668103 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -220,7 +220,7 @@ run_test() { if test_selected ${CATEGORY}; then # On memory constrainted systems some tests can fail to allocate hugepages. # perform some cleanup before the test for a higher success rate. - if [ ${CATEGORY} == "thp" ] | [ ${CATEGORY} == "hugetlb" ]; then + if [ ${CATEGORY} == "thp" -o ${CATEGORY} == "hugetlb" ]; then echo 3 > /proc/sys/vm/drop_caches sleep 2 echo 1 > /proc/sys/vm/compact_memory -- 2.51.0 From 4998a6fa2a31176d0882bdfa27d5d03b665ba19b Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Wed, 12 Feb 2025 09:35:20 -0800 Subject: [PATCH 13/16] MAINTAINERS: update Nick's contact info Updated .mailmap, but forgot these other places. Link: https://lkml.kernel.org/r/20250212173523.3979840-1-ndesaulniers@google.com Signed-off-by: Nick Desaulniers Signed-off-by: Andrew Morton --- Documentation/process/embargoed-hardware-issues.rst | 2 +- .../translations/sp_SP/process/embargoed-hardware-issues.rst | 2 +- MAINTAINERS | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/process/embargoed-hardware-issues.rst b/Documentation/process/embargoed-hardware-issues.rst index daebce49cfdf..0e19d2f0d6bb 100644 --- a/Documentation/process/embargoed-hardware-issues.rst +++ b/Documentation/process/embargoed-hardware-issues.rst @@ -308,7 +308,7 @@ an involved disclosed party. The current ambassadors list: Google Kees Cook - LLVM Nick Desaulniers + LLVM Nick Desaulniers ============= ======================================================== If you want your organization to be added to the ambassadors list, please diff --git a/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst b/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst index 7d4d694967c7..9d444b9c46d3 100644 --- a/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst +++ b/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst @@ -287,7 +287,7 @@ revelada involucrada. La lista de embajadores actuales: Google Kees Cook - LLVM Nick Desaulniers + LLVM Nick Desaulniers ============= ======================================================== Si quiere que su organización se añada a la lista de embajadores, por diff --git a/MAINTAINERS b/MAINTAINERS index efee40ea589f..4e17764cb6ed 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5655,7 +5655,7 @@ F: .clang-format CLANG/LLVM BUILD SUPPORT M: Nathan Chancellor -R: Nick Desaulniers +R: Nick Desaulniers R: Bill Wendling R: Justin Stitt L: llvm@lists.linux.dev -- 2.51.0 From ac7af1f57acd1e1d112b36e036584ca4bc4c284a Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Mon, 17 Feb 2025 15:44:02 -0500 Subject: [PATCH 14/16] kasan: don't call find_vm_area() in a PREEMPT_RT kernel The following bug report was found when running a PREEMPT_RT debug kernel. BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48 in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 140605, name: kunit_try_catch preempt_count: 1, expected: 0 Call trace: rt_spin_lock+0x70/0x140 find_vmap_area+0x84/0x168 find_vm_area+0x1c/0x50 print_address_description.constprop.0+0x2a0/0x320 print_report+0x108/0x1f8 kasan_report+0x90/0xc8 Since commit e30a0361b851 ("kasan: make report_lock a raw spinlock"), report_lock was changed to raw_spinlock_t to fix another similar PREEMPT_RT problem. That alone isn't enough to cover other corner cases. print_address_description() is always invoked under the report_lock. The context under this lock is always atomic even on PREEMPT_RT. find_vm_area() acquires vmap_node::busy.lock which is a spinlock_t, becoming a sleeping lock on PREEMPT_RT and must not be acquired in atomic context. Don't invoke find_vm_area() on PREEMPT_RT and just print the address. Non-PREEMPT_RT builds remain unchanged. Add a DEFINE_WAIT_OVERRIDE_MAP() macro to tell lockdep that this lock nesting is allowed because the PREEMPT_RT part (which is invalid) has been taken care of. This macro was first introduced in commit 0cce06ba859a ("debugobjects,locking: Annotate debug_object_fill_pool() wait type violation"). Link: https://lkml.kernel.org/r/20250217204402.60533-1-longman@redhat.com Fixes: e30a0361b851 ("kasan: make report_lock a raw spinlock") Signed-off-by: Waiman Long Suggested-by: Andrey Konovalov Reviewed-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitriy Vyukov Cc: Steven Rostedt Cc: Mariano Pache Cc: Sebastian Andrzej Siewior Cc: Vincenzo Frascino Signed-off-by: Andrew Morton --- mm/kasan/report.c | 34 +++++++++++++++++++++++++++++++++- 1 file changed, 33 insertions(+), 1 deletion(-) diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 3fe77a360f1c..8357e1a33699 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -370,6 +370,36 @@ static inline bool init_task_stack_addr(const void *addr) sizeof(init_thread_union.stack)); } +/* + * This function is invoked with report_lock (a raw_spinlock) held. A + * PREEMPT_RT kernel cannot call find_vm_area() as it will acquire a sleeping + * rt_spinlock. + * + * For !RT kernel, the PROVE_RAW_LOCK_NESTING config option will print a + * lockdep warning for this raw_spinlock -> spinlock dependency. This config + * option is enabled by default to ensure better test coverage to expose this + * kind of RT kernel problem. This lockdep splat, however, can be suppressed + * by using DEFINE_WAIT_OVERRIDE_MAP() if it serves a useful purpose and the + * invalid PREEMPT_RT case has been taken care of. + */ +static inline struct vm_struct *kasan_find_vm_area(void *addr) +{ + static DEFINE_WAIT_OVERRIDE_MAP(vmalloc_map, LD_WAIT_SLEEP); + struct vm_struct *va; + + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + return NULL; + + /* + * Suppress lockdep warning and fetch vmalloc area of the + * offending address. + */ + lock_map_acquire_try(&vmalloc_map); + va = find_vm_area(addr); + lock_map_release(&vmalloc_map); + return va; +} + static void print_address_description(void *addr, u8 tag, struct kasan_report_info *info) { @@ -399,7 +429,7 @@ static void print_address_description(void *addr, u8 tag, } if (is_vmalloc_addr(addr)) { - struct vm_struct *va = find_vm_area(addr); + struct vm_struct *va = kasan_find_vm_area(addr); if (va) { pr_err("The buggy address belongs to the virtual mapping at\n" @@ -409,6 +439,8 @@ static void print_address_description(void *addr, u8 tag, pr_err("\n"); page = vmalloc_to_page(addr); + } else { + pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr); } } -- 2.51.0 From 8344017aaf32a7532cff293eb3df7fd2265ebafd Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Fri, 14 Feb 2025 00:36:59 +0800 Subject: [PATCH 15/16] test_xarray: fix failure in check_pause when CONFIG_XARRAY_MULTI is not defined In case CONFIG_XARRAY_MULTI is not defined, xa_store_order can store a multi-index entry but xas_for_each can't tell sbiling entry from valid entry. So the check_pause failed when we store a multi-index entry and wish xas_for_each can handle it normally. Avoid to store multi-index entry when CONFIG_XARRAY_MULTI is disabled to fix the failure. Link: https://lkml.kernel.org/r/20250213163659.414309-1-shikemeng@huaweicloud.com Fixes: c9ba5249ef8b ("Xarray: move forward index correctly in xas_pause()") Signed-off-by: Kemeng Shi Reported-by: Geert Uytterhoeven Closes: https://lore.kernel.org/r/CAMuHMdU_bfadUO=0OZ=AoQ9EAmQPA4wsLCBqohXR+QCeCKRn4A@mail.gmail.com Tested-by: Geert Uytterhoeven Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- lib/test_xarray.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 6932a26f4927..0e865bab4a10 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -1418,7 +1418,7 @@ static noinline void check_pause(struct xarray *xa) { XA_STATE(xas, xa, 0); void *entry; - unsigned int order; + int order; unsigned long index = 1; unsigned int count = 0; @@ -1450,7 +1450,7 @@ static noinline void check_pause(struct xarray *xa) xa_destroy(xa); index = 0; - for (order = XA_CHUNK_SHIFT; order > 0; order--) { + for (order = order_limit - 1; order >= 0; order--) { XA_BUG_ON(xa, xa_store_order(xa, index, order, xa_mk_index(index), GFP_KERNEL)); index += 1UL << order; @@ -1462,24 +1462,25 @@ static noinline void check_pause(struct xarray *xa) rcu_read_lock(); xas_for_each(&xas, entry, ULONG_MAX) { XA_BUG_ON(xa, entry != xa_mk_index(index)); - index += 1UL << (XA_CHUNK_SHIFT - count); + index += 1UL << (order_limit - count - 1); count++; } rcu_read_unlock(); - XA_BUG_ON(xa, count != XA_CHUNK_SHIFT); + XA_BUG_ON(xa, count != order_limit); index = 0; count = 0; - xas_set(&xas, XA_CHUNK_SIZE / 2 + 1); + /* test unaligned index */ + xas_set(&xas, 1 % (1UL << (order_limit - 1))); rcu_read_lock(); xas_for_each(&xas, entry, ULONG_MAX) { XA_BUG_ON(xa, entry != xa_mk_index(index)); - index += 1UL << (XA_CHUNK_SHIFT - count); + index += 1UL << (order_limit - count - 1); count++; xas_pause(&xas); } rcu_read_unlock(); - XA_BUG_ON(xa, count != XA_CHUNK_SHIFT); + XA_BUG_ON(xa, count != order_limit); xa_destroy(xa); -- 2.51.0 From 0a7565ee6ec31eb16c0476adbfc1af3f2271cb6b Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Thu, 13 Feb 2025 19:38:50 -0800 Subject: [PATCH 16/16] Revert "selftests/mm: remove local __NR_* definitions" This reverts commit a5c6bc590094a1a73cf6fa3f505e1945d2bf2461. The general approach described in commit e076eaca5906 ("selftests: break the dependency upon local header files") was taken one step too far here: it should not have been extended to include the syscall numbers. This is because doing so would require per-arch support in tools/include/uapi, and no such support exists. This revert fixes two separate reports of test failures, from Dave Hansen[1], and Li Wang[2]. An excerpt of Dave's report: Before this commit (a5c6bc590094a1a73cf6fa3f505e1945d2bf2461) things are fine. But after, I get: running PKEY tests for unsupported CPU/OS An excerpt of Li's report: I just found that mlock2_() return a wrong value in mlock2-test [1] https://lore.kernel.org/dc585017-6740-4cab-a536-b12b37a7582d@intel.com [2] https://lore.kernel.org/CAEemH2eW=UMu9+turT2jRie7+6ewUazXmA6kL+VBo3cGDGU6RA@mail.gmail.com Link: https://lkml.kernel.org/r/20250214033850.235171-1-jhubbard@nvidia.com Fixes: a5c6bc590094 ("selftests/mm: remove local __NR_* definitions") Signed-off-by: John Hubbard Cc: Dave Hansen Cc: Li Wang Cc: David Hildenbrand Cc: Jeff Xu Cc: Andrei Vagin Cc: Axel Rasmussen Cc: Christian Brauner Cc: Kees Cook Cc: Kent Overstreet Cc: Liam R. Howlett Cc: Muhammad Usama Anjum Cc: Peter Xu Cc: Rich Felker Cc: Shuah Khan Cc: Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/hugepage-mremap.c | 2 +- tools/testing/selftests/mm/ksm_functional_tests.c | 8 +++++++- tools/testing/selftests/mm/memfd_secret.c | 14 +++++++++++++- tools/testing/selftests/mm/mkdirty.c | 8 +++++++- tools/testing/selftests/mm/mlock2.h | 1 - tools/testing/selftests/mm/protection_keys.c | 2 +- tools/testing/selftests/mm/uffd-common.c | 4 ++++ tools/testing/selftests/mm/uffd-stress.c | 15 ++++++++++++++- tools/testing/selftests/mm/uffd-unit-tests.c | 14 +++++++++++++- 9 files changed, 60 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/mm/hugepage-mremap.c b/tools/testing/selftests/mm/hugepage-mremap.c index ada9156cc497..c463d1c09c9b 100644 --- a/tools/testing/selftests/mm/hugepage-mremap.c +++ b/tools/testing/selftests/mm/hugepage-mremap.c @@ -15,7 +15,7 @@ #define _GNU_SOURCE #include #include -#include +#include #include #include #include /* Definition of O_* constants */ diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index 66b4e111b5a2..b61803e36d1c 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include #include @@ -369,6 +369,7 @@ unmap: munmap(map, size); } +#ifdef __NR_userfaultfd static void test_unmerge_uffd_wp(void) { struct uffdio_writeprotect uffd_writeprotect; @@ -429,6 +430,7 @@ close_uffd: unmap: munmap(map, size); } +#endif /* Verify that KSM can be enabled / queried with prctl. */ static void test_prctl(void) @@ -684,7 +686,9 @@ int main(int argc, char **argv) exit(test_child_ksm()); } +#ifdef __NR_userfaultfd tests++; +#endif ksft_print_header(); ksft_set_plan(tests); @@ -696,7 +700,9 @@ int main(int argc, char **argv) test_unmerge(); test_unmerge_zero_pages(); test_unmerge_discarded(); +#ifdef __NR_userfaultfd test_unmerge_uffd_wp(); +#endif test_prot_none(); diff --git a/tools/testing/selftests/mm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c index 74c911aa3aea..9a0597310a76 100644 --- a/tools/testing/selftests/mm/memfd_secret.c +++ b/tools/testing/selftests/mm/memfd_secret.c @@ -17,7 +17,7 @@ #include #include -#include +#include #include #include #include @@ -28,6 +28,8 @@ #define pass(fmt, ...) ksft_test_result_pass(fmt, ##__VA_ARGS__) #define skip(fmt, ...) ksft_test_result_skip(fmt, ##__VA_ARGS__) +#ifdef __NR_memfd_secret + #define PATTERN 0x55 static const int prot = PROT_READ | PROT_WRITE; @@ -332,3 +334,13 @@ int main(int argc, char *argv[]) ksft_finished(); } + +#else /* __NR_memfd_secret */ + +int main(int argc, char *argv[]) +{ + printf("skip: skipping memfd_secret test (missing __NR_memfd_secret)\n"); + return KSFT_SKIP; +} + +#endif /* __NR_memfd_secret */ diff --git a/tools/testing/selftests/mm/mkdirty.c b/tools/testing/selftests/mm/mkdirty.c index af2fce496912..09feeb453646 100644 --- a/tools/testing/selftests/mm/mkdirty.c +++ b/tools/testing/selftests/mm/mkdirty.c @@ -9,7 +9,7 @@ */ #include #include -#include +#include #include #include #include @@ -265,6 +265,7 @@ munmap: munmap(mmap_mem, mmap_size); } +#ifdef __NR_userfaultfd static void test_uffdio_copy(void) { struct uffdio_register uffdio_register; @@ -322,6 +323,7 @@ munmap: munmap(dst, pagesize); free(src); } +#endif /* __NR_userfaultfd */ int main(void) { @@ -334,7 +336,9 @@ int main(void) thpsize / 1024); tests += 3; } +#ifdef __NR_userfaultfd tests += 1; +#endif /* __NR_userfaultfd */ ksft_print_header(); ksft_set_plan(tests); @@ -364,7 +368,9 @@ int main(void) if (thpsize) test_pte_mapped_thp(); /* Placing a fresh page via userfaultfd may set the PTE dirty. */ +#ifdef __NR_userfaultfd test_uffdio_copy(); +#endif /* __NR_userfaultfd */ err = ksft_get_fail_cnt(); if (err) diff --git a/tools/testing/selftests/mm/mlock2.h b/tools/testing/selftests/mm/mlock2.h index 1e5731bab499..4417eaa5cfb7 100644 --- a/tools/testing/selftests/mm/mlock2.h +++ b/tools/testing/selftests/mm/mlock2.h @@ -3,7 +3,6 @@ #include #include #include -#include static int mlock2_(void *start, size_t len, int flags) { diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index a4683f2476f2..35565af308af 100644 --- a/tools/testing/selftests/mm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c @@ -42,7 +42,7 @@ #include #include #include -#include +#include #include #include diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index 717539eddf98..7ad6ba660c7d 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -673,7 +673,11 @@ int uffd_open_dev(unsigned int flags) int uffd_open_sys(unsigned int flags) { +#ifdef __NR_userfaultfd return syscall(__NR_userfaultfd, flags); +#else + return -1; +#endif } int uffd_open(unsigned int flags) diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index a4b83280998a..944d559ade21 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -33,10 +33,11 @@ * pthread_mutex_lock will also verify the atomicity of the memory * transfer (UFFDIO_COPY). */ -#include + #include "uffd-common.h" uint64_t features; +#ifdef __NR_userfaultfd #define BOUNCE_RANDOM (1<<0) #define BOUNCE_RACINGFAULTS (1<<1) @@ -471,3 +472,15 @@ int main(int argc, char **argv) nr_pages, nr_pages_per_cpu); return userfaultfd_stress(); } + +#else /* __NR_userfaultfd */ + +#warning "missing __NR_userfaultfd definition" + +int main(void) +{ + printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n"); + return KSFT_SKIP; +} + +#endif /* __NR_userfaultfd */ diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 9ff71fa1f9bf..74c8bc02b506 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -5,11 +5,12 @@ * Copyright (C) 2015-2023 Red Hat, Inc. */ -#include #include "uffd-common.h" #include "../../../../mm/gup_test.h" +#ifdef __NR_userfaultfd + /* The unit test doesn't need a large or random size, make it 32MB for now */ #define UFFD_TEST_MEM_SIZE (32UL << 20) @@ -1558,3 +1559,14 @@ int main(int argc, char *argv[]) return ksft_get_fail_cnt() ? KSFT_FAIL : KSFT_PASS; } +#else /* __NR_userfaultfd */ + +#warning "missing __NR_userfaultfd definition" + +int main(void) +{ + printf("Skipping %s (missing __NR_userfaultfd)\n", __file__); + return KSFT_SKIP; +} + +#endif /* __NR_userfaultfd */ -- 2.51.0