From 8f3ce3d996bf1e2f8474ec3ddabdb8765c19e6ea Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 7 Oct 2024 16:30:49 +0200 Subject: mm: percpu: increase PERCPU_DYNAMIC_SIZE_SHIFT on certain builds. Arnd reported a build failure due to the BUILD_BUG_ON() statement in alloc_kmem_cache_cpus(). The test PERCPU_DYNAMIC_EARLY_SIZE < NR_KMALLOC_TYPES * KMALLOC_SHIFT_HIGH * sizeof(struct kmem_cache_cpu) The factors that increase the right side of the equation: - PAGE_SIZE > 4KiB increases KMALLOC_SHIFT_HIGH - For the local_lock_t in kmem_cache_cpu: - PREEMPT_RT adds an actual lock. - LOCKDEP increases the size of the lock. - LOCK_STAT adds additional bytes plus padding to the lockdep structure. The net difference with and without PREEMPT_RT is 88 bytes for the lock_lock_t, 96 bytes for kmem_cache_cpu due to additional padding. This is enough to exceed the 80KiB limit with 16KiB page size - the 8KiB page size is fine. Increase PERCPU_DYNAMIC_SIZE_SHIFT to 13 on configs with PAGE_SIZE larger than 4KiB and LOCKDEP enabled. Link: https://lkml.kernel.org/r/20241007143049.gyMpEu89@linutronix.de Fixes: d8fccd9ca5f9 ("arm64: Allow to enable PREEMPT_RT.") Signed-off-by: Sebastian Andrzej Siewior Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202410020326.iaZIteIx-lkp@intel.com/ Reported-by: Arnd Bergmann Closes: https://lore.kernel.org/20241004095702.637528-1-arnd@kernel.org Acked-by: Arnd Bergmann Acked-by: Vlastimil Babka Acked-by: David Rientjes Cc: Christoph Lameter Cc: Dennis Zhou Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Joonsoo Kim Cc: Pekka Enberg Cc: Roman Gushchin Cc: Tejun Heo Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- include/linux/percpu.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index b6321fc49159..52b5ea663b9f 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -41,7 +41,11 @@ PCPU_MIN_ALLOC_SHIFT) #ifdef CONFIG_RANDOM_KMALLOC_CACHES -#define PERCPU_DYNAMIC_SIZE_SHIFT 12 +# if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PAGE_SIZE_4KB) +# define PERCPU_DYNAMIC_SIZE_SHIFT 13 +# else +# define PERCPU_DYNAMIC_SIZE_SHIFT 12 +#endif /* LOCKDEP and PAGE_SIZE > 4KiB */ #else #define PERCPU_DYNAMIC_SIZE_SHIFT 10 #endif -- cgit v1.2.3 From 963756aac1f011d904ddd9548ae82286d3a91f96 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 11 Oct 2024 12:24:44 +0200 Subject: mm: huge_memory: add vma_thp_disabled() and thp_disabled_by_hw() Patch series "mm: don't install PMD mappings when THPs are disabled by the hw/process/vma". During testing, it was found that we can get PMD mappings in processes where THP (and more precisely, PMD mappings) are supposed to be disabled. While it works as expected for anon+shmem, the pagecache is the problematic bit. For s390 KVM this currently means that a VM backed by a file located on filesystem with large folio support can crash when KVM tries accessing the problematic page, because the readahead logic might decide to use a PMD-sized THP and faulting it into the page tables will install a PMD mapping, something that s390 KVM cannot tolerate. This might also be a problem with HW that does not support PMD mappings, but I did not try reproducing it. Fix it by respecting the ways to disable THPs when deciding whether we can install a PMD mapping. khugepaged should already be taking care of not collapsing if THPs are effectively disabled for the hw/process/vma. This patch (of 2): Add vma_thp_disabled() and thp_disabled_by_hw() helpers to be shared by shmem_allowable_huge_orders() and __thp_vma_allowable_orders(). [david@redhat.com: rename to vma_thp_disabled(), split out thp_disabled_by_hw() ] Link: https://lkml.kernel.org/r/20241011102445.934409-2-david@redhat.com Fixes: 793917d997df ("mm/readahead: Add large folio readahead") Signed-off-by: Kefeng Wang Signed-off-by: David Hildenbrand Reported-by: Leo Fu Tested-by: Thomas Huth Reviewed-by: Ryan Roberts Cc: Boqiao Fu Cc: Christian Borntraeger Cc: Claudio Imbrenda Cc: Hugh Dickins Cc: Janosch Frank Cc: Matthew Wilcox Cc: Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 18 ++++++++++++++++++ mm/huge_memory.c | 13 +------------ mm/shmem.c | 7 +------ 3 files changed, 20 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 67d0ab3c3bba..ef5b80e48599 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -322,6 +322,24 @@ struct thpsize { (transparent_hugepage_flags & \ (1<vm_mm->flags); +} + +static inline bool thp_disabled_by_hw(void) +{ + /* If the hardware/firmware marked hugepage support disabled. */ + return transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED); +} + unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 87b49ecc7b1e..2fb328880b50 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -109,18 +109,7 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, if (!vma->vm_mm) /* vdso */ return 0; - /* - * Explicitly disabled through madvise or prctl, or some - * architectures may disable THP for some mappings, for - * example, s390 kvm. - * */ - if ((vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) - return 0; - /* - * If the hardware/firmware marked hugepage support disabled. - */ - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED)) + if (thp_disabled_by_hw() || vma_thp_disabled(vma, vm_flags)) return 0; /* khugepaged doesn't collapse DAX vma, but page fault is fine. */ diff --git a/mm/shmem.c b/mm/shmem.c index 4f11b5506363..c5adb987b23c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1664,12 +1664,7 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, loff_t i_size; int order; - if (vma && ((vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))) - return 0; - - /* If the hardware/firmware marked hugepage support disabled. */ - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED)) + if (thp_disabled_by_hw() || (vma && vma_thp_disabled(vma, vm_flags))) return 0; global_huge = shmem_huge_global_enabled(inode, index, write_end, -- cgit v1.2.3