From 67bab13307c83fb742c2556b06cdc39dbad27f07 Mon Sep 17 00:00:00 2001 From: Ge Yang Date: Wed, 19 Feb 2025 11:46:44 +0800 Subject: mm/hugetlb: wait for hugetlb folios to be freed Since the introduction of commit c77c0a8ac4c52 ("mm/hugetlb: defer freeing of huge pages if in non-task context"), which supports deferring the freeing of hugetlb pages, the allocation of contiguous memory through cma_alloc() may fail probabilistically. In the CMA allocation process, if it is found that the CMA area is occupied by in-use hugetlb folios, these in-use hugetlb folios need to be migrated to another location. When there are no available hugetlb folios in the free hugetlb pool during the migration of in-use hugetlb folios, new folios are allocated from the buddy system. A temporary state is set on the newly allocated folio. Upon completion of the hugetlb folio migration, the temporary state is transferred from the new folios to the old folios. Normally, when the old folios with the temporary state are freed, it is directly released back to the buddy system. However, due to the deferred freeing of hugetlb pages, the PageBuddy() check fails, ultimately leading to the failure of cma_alloc(). Here is a simplified call trace illustrating the process: cma_alloc() ->__alloc_contig_migrate_range() // Migrate in-use hugetlb folios ->unmap_and_move_huge_page() ->folio_putback_hugetlb() // Free old folios ->test_pages_isolated() ->__test_page_isolated_in_pageblock() ->PageBuddy(page) // Check if the page is in buddy To resolve this issue, we have implemented a function named wait_for_freed_hugetlb_folios(). This function ensures that the hugetlb folios are properly released back to the buddy system after their migration is completed. By invoking wait_for_freed_hugetlb_folios() before calling PageBuddy(), we ensure that PageBuddy() will succeed. Link: https://lkml.kernel.org/r/1739936804-18199-1-git-send-email-yangge1116@126.com Fixes: c77c0a8ac4c5 ("mm/hugetlb: defer freeing of huge pages if in non-task context") Signed-off-by: Ge Yang Reviewed-by: Muchun Song Acked-by: David Hildenbrand Cc: Baolin Wang Cc: Barry Song <21cnbao@gmail.com> Cc: Oscar Salvador Cc: Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ec8c0ccc8f95..dbe76d4f1bfc 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -682,6 +682,7 @@ struct huge_bootmem_page { int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn); +void wait_for_freed_hugetlb_folios(void); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, @@ -1066,6 +1067,10 @@ static inline int replace_free_hugepage_folios(unsigned long start_pfn, return 0; } +static inline void wait_for_freed_hugetlb_folios(void) +{ +} + static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner) -- cgit v1.2.3 From ce6d9c1c2b5cc785016faa11b48b6cd317eb367e Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Mon, 24 Feb 2025 21:20:02 -0500 Subject: NFS: fix nfs_release_folio() to not deadlock via kcompactd writeback Add PF_KCOMPACTD flag and current_is_kcompactd() helper to check for it so nfs_release_folio() can skip calling nfs_wb_folio() from kcompactd. Otherwise NFS can deadlock waiting for kcompactd enduced writeback which recurses back to NFS (which triggers writeback to NFSD via NFS loopback mount on the same host, NFSD blocks waiting for XFS's call to __filemap_get_folio): 6070.550357] INFO: task kcompactd0:58 blocked for more than 4435 seconds. {--- [58] "kcompactd0" [<0>] folio_wait_bit+0xe8/0x200 [<0>] folio_wait_writeback+0x2b/0x80 [<0>] nfs_wb_folio+0x80/0x1b0 [nfs] [<0>] nfs_release_folio+0x68/0x130 [nfs] [<0>] split_huge_page_to_list_to_order+0x362/0x840 [<0>] migrate_pages_batch+0x43d/0xb90 [<0>] migrate_pages_sync+0x9a/0x240 [<0>] migrate_pages+0x93c/0x9f0 [<0>] compact_zone+0x8e2/0x1030 [<0>] compact_node+0xdb/0x120 [<0>] kcompactd+0x121/0x2e0 [<0>] kthread+0xcf/0x100 [<0>] ret_from_fork+0x31/0x40 [<0>] ret_from_fork_asm+0x1a/0x30 ---} [akpm@linux-foundation.org: fix build] Link: https://lkml.kernel.org/r/20250225022002.26141-1-snitzer@kernel.org Fixes: 96780ca55e3c ("NFS: fix up nfs_release_folio() to try to release the page") Signed-off-by: Mike Snitzer Cc: Anna Schumaker Cc: Trond Myklebust Cc: Signed-off-by: Andrew Morton --- include/linux/compaction.h | 5 +++++ include/linux/sched.h | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index e94776496049..7bf0c521db63 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -80,6 +80,11 @@ static inline unsigned long compact_gap(unsigned int order) return 2UL << order; } +static inline int current_is_kcompactd(void) +{ + return current->flags & PF_KCOMPACTD; +} + #ifdef CONFIG_COMPACTION extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order); diff --git a/include/linux/sched.h b/include/linux/sched.h index 9632e3318e0d..9c15365a30c0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1701,7 +1701,7 @@ extern struct pid *cad_pid; #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ #define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ -#define PF__HOLE__00010000 0x00010000 +#define PF_KCOMPACTD 0x00010000 /* I am kcompactd */ #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */ -- cgit v1.2.3 From c29564d8b46f64f5e6e6f1c9c02f7761b7b90963 Mon Sep 17 00:00:00 2001 From: Su Hui Date: Fri, 21 Feb 2025 15:16:25 +0800 Subject: include/linux/log2.h: mark is_power_of_2() with __always_inline When building kernel with randconfig, there is an error: In function `kvm_is_cr4_bit_set',inlined from `kvm_update_cpuid_runtime' at arch/x86/kvm/cpuid.c:310:9: include/linux/compiler_types.h:542:38: error: call to `__compiletime_assert_380' declared with attribute error: BUILD_BUG_ON failed: !is_power_of_2(cr4_bit). '!is_power_of_2(X86_CR4_OSXSAVE)' is False, but gcc treats is_power_of_2() as non-inline function and a compilation error happens. Fix this by marking is_power_of_2() with __always_inline. Link: https://lkml.kernel.org/r/20250221071624.1356899-1-suhui@nfschina.com Signed-off-by: Su Hui Cc: Binbin Wu Cc: Paolo Bonzini Cc: Sean Christopherson Signed-off-by: Andrew Morton --- include/linux/log2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/log2.h b/include/linux/log2.h index 9f30d087a128..1366cb688a6d 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -41,7 +41,7 @@ int __ilog2_u64(u64 n) * *not* considered a power of two. * Return: true if @n is a power of 2, otherwise false. */ -static inline __attribute__((const)) +static __always_inline __attribute__((const)) bool is_power_of_2(unsigned long n) { return (n != 0 && ((n & (n - 1)) == 0)); -- cgit v1.2.3