From: Miaohe Lin linmiaohe@huawei.com
stable inclusion from stable-5.10.50 commit b65597377b7b690efaaa1c9f4875ded8b4c46212 bugzilla: 174522 https://gitee.com/openeuler/kernel/issues/I4DNFY
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
[ Upstream commit e6be37b2e7bddfe0c76585ee7c7eee5acc8efeab ]
Since commit 99cb0dbd47a1 ("mm,thp: add read-only THP support for (non-shmem) FS"), read-only THP file mapping is supported. But it forgot to add checking for it in transparent_hugepage_enabled(). To fix it, we add checking for read-only THP file mapping and also introduce helper transhuge_vma_enabled() to check whether thp is enabled for specified vma to reduce duplicated code. We rename transparent_hugepage_enabled to transparent_hugepage_active to make the code easier to follow as suggested by David Hildenbrand.
[linmiaohe@huawei.com: define transhuge_vma_enabled next to transhuge_vma_suitable] Link: https://lkml.kernel.org/r/20210514093007.4117906-1-linmiaohe@huawei.com
Link: https://lkml.kernel.org/r/20210511134857.1581273-4-linmiaohe@huawei.com Fixes: 99cb0dbd47a1 ("mm,thp: add read-only THP support for (non-shmem) FS") Signed-off-by: Miaohe Lin linmiaohe@huawei.com Reviewed-by: Yang Shi shy828301@gmail.com Cc: Alexey Dobriyan adobriyan@gmail.com Cc: "Aneesh Kumar K . V" aneesh.kumar@linux.ibm.com Cc: Anshuman Khandual anshuman.khandual@arm.com Cc: David Hildenbrand david@redhat.com Cc: Hugh Dickins hughd@google.com Cc: Johannes Weiner hannes@cmpxchg.org Cc: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Matthew Wilcox willy@infradead.org Cc: Minchan Kim minchan@kernel.org Cc: Ralph Campbell rcampbell@nvidia.com Cc: Rik van Riel riel@surriel.com Cc: Song Liu songliubraving@fb.com Cc: William Kucharski william.kucharski@oracle.com Cc: Zi Yan ziy@nvidia.com Cc: Mike Kravetz mike.kravetz@oracle.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Chen Jun chenjun102@huawei.com Acked-by: Weilong Chen chenweilong@huawei.com Signed-off-by: Chen Jun chenjun102@huawei.com [hejingxian: fix build error in pin_mem_area() mm/pin_mem.c] Signed-off-by: Jingxian He hejingxian@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- fs/proc/task_mmu.c | 2 +- include/linux/huge_mm.h | 57 +++++++++++++++++++++++++---------------- mm/huge_memory.c | 11 +++++++- mm/khugepaged.c | 4 +-- mm/pin_mem.c | 2 +- mm/shmem.c | 3 +-- 6 files changed, 49 insertions(+), 30 deletions(-)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f46c7efd6147..464562ad470f 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -832,7 +832,7 @@ static int show_smap(struct seq_file *m, void *v) __show_smap(m, &mss, false);
seq_printf(m, "THPeligible: %d\n", - transparent_hugepage_enabled(vma)); + transparent_hugepage_active(vma));
if (arch_pkeys_enabled()) seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index bf37fbdaa59d..42dc994c8897 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -124,9 +124,34 @@ extern struct kobj_attribute shmem_enabled_attr;
extern unsigned long transparent_hugepage_flags;
+static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, + unsigned long haddr) +{ + /* Don't have to check pgoff for anonymous vma */ + if (!vma_is_anonymous(vma)) { + if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, + HPAGE_PMD_NR)) + return false; + } + + if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) + return false; + return true; +} + +static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + /* Explicitly disabled through madvise. */ + if ((vm_flags & VM_NOHUGEPAGE) || + test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + return false; + return true; +} + /* * to be used on vmas which are known to support THP. - * Use transparent_hugepage_enabled otherwise + * Use transparent_hugepage_active otherwise */ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { @@ -137,15 +162,12 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) return false;
- if (vma->vm_flags & VM_NOHUGEPAGE) + if (!transhuge_vma_enabled(vma, vma->vm_flags)) return false;
if (vma_is_temporary_stack(vma)) return false;
- if (test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) - return false; - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) return true;
@@ -159,22 +181,7 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) return false; }
-bool transparent_hugepage_enabled(struct vm_area_struct *vma); - -static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, - unsigned long haddr) -{ - /* Don't have to check pgoff for anonymous vma */ - if (!vma_is_anonymous(vma)) { - if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, - HPAGE_PMD_NR)) - return false; - } - - if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) - return false; - return true; -} +bool transparent_hugepage_active(struct vm_area_struct *vma);
#define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ @@ -366,7 +373,7 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) return false; }
-static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) +static inline bool transparent_hugepage_active(struct vm_area_struct *vma) { return false; } @@ -377,6 +384,12 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, return false; }
+static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + return false; +} + static inline void prep_transhuge_page(struct page *page) {}
static inline bool is_transparent_hugepage(struct page *page) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 41e9ff8c4ddc..89fe08f63afc 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -63,7 +63,14 @@ static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; unsigned long huge_zero_pfn __read_mostly = ~0UL;
-bool transparent_hugepage_enabled(struct vm_area_struct *vma) +static inline bool file_thp_enabled(struct vm_area_struct *vma) +{ + return transhuge_vma_enabled(vma, vma->vm_flags) && vma->vm_file && + !inode_is_open_for_write(vma->vm_file->f_inode) && + (vma->vm_flags & VM_EXEC); +} + +bool transparent_hugepage_active(struct vm_area_struct *vma) { /* The addr is used to check if the vma size fits */ unsigned long addr = (vma->vm_end & HPAGE_PMD_MASK) - HPAGE_PMD_SIZE; @@ -74,6 +81,8 @@ bool transparent_hugepage_enabled(struct vm_area_struct *vma) return __transparent_hugepage_enabled(vma); if (vma_is_shmem(vma)) return shmem_huge_enabled(vma); + if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) + return file_thp_enabled(vma);
return false; } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 5a806dbb568a..b56ce6be2cae 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -440,9 +440,7 @@ static inline int khugepaged_test_exit(struct mm_struct *mm) static bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags) { - /* Explicitly disabled through madvise. */ - if ((vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + if (!transhuge_vma_enabled(vma, vm_flags)) return false;
/* Enabled via shmem mount options or sysfs settings. */ diff --git a/mm/pin_mem.c b/mm/pin_mem.c index 3fd3638a89e3..ff6ddd3a47f9 100644 --- a/mm/pin_mem.c +++ b/mm/pin_mem.c @@ -701,7 +701,7 @@ int pin_mem_area(struct task_struct *task, struct mm_struct *mm, goto finish; } if (start_addr == (start_addr & HPAGE_PMD_MASK) && - transparent_hugepage_enabled(vma)) { + transparent_hugepage_active(vma)) { page_size = HPAGE_PMD_SIZE; is_huge_page = true; } else { diff --git a/mm/shmem.c b/mm/shmem.c index 223a0a88326d..d43f2806df18 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3999,8 +3999,7 @@ bool shmem_huge_enabled(struct vm_area_struct *vma) loff_t i_size; pgoff_t off;
- if ((vma->vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + if (!transhuge_vma_enabled(vma, vma->vm_flags)) return false; if (shmem_huge == SHMEM_HUGE_FORCE) return true;