From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932695AbcELPmB (ORCPT ); Thu, 12 May 2016 11:42:01 -0400 Received: from mga04.intel.com ([192.55.52.120]:19478 "EHLO mga04.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932669AbcELPl5 (ORCPT ); Thu, 12 May 2016 11:41:57 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.24,610,1455004800"; d="scan'208";a="804823436" From: "Kirill A. Shutemov" To: Hugh Dickins , Andrea Arcangeli , Andrew Morton Cc: Dave Hansen , Vlastimil Babka , Christoph Lameter , Naoya Horiguchi , Jerome Marchand , Yang Shi , Sasha Levin , Andres Lagar-Cavilla , Ning Qu , linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-fsdevel@vger.kernel.org, "Kirill A. Shutemov" Subject: [PATCHv8 25/32] shmem, thp: respect MADV_{NO,}HUGEPAGE for file mappings Date: Thu, 12 May 2016 18:41:05 +0300 Message-Id: <1463067672-134698-26-git-send-email-kirill.shutemov@linux.intel.com> X-Mailer: git-send-email 2.8.1 In-Reply-To: <1463067672-134698-1-git-send-email-kirill.shutemov@linux.intel.com> References: <1463067672-134698-1-git-send-email-kirill.shutemov@linux.intel.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Let's wire up existing madvise() hugepage hints for file mappings. MADV_HUGEPAGE advise shmem to allocate huge page on page fault in the VMA. It only has effect if the filesystem is mounted with huge=advise or huge=within_size. MADV_NOHUGEPAGE prevents hugepage from being allocated on page fault in the VMA. It doesn't prevent a huge page from being allocated by other means, i.e. page fault into different mapping or write(2) into file. Signed-off-by: Kirill A. Shutemov --- mm/huge_memory.c | 19 +++++-------------- mm/shmem.c | 20 +++++++++++++++++--- 2 files changed, 22 insertions(+), 17 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 648f60d55759..3658b7d2c424 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1837,7 +1837,7 @@ spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) return NULL; } -#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE) +#define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE) int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) @@ -1853,11 +1853,6 @@ int hugepage_madvise(struct vm_area_struct *vma, if (mm_has_pgste(vma->vm_mm)) return 0; #endif - /* - * Be somewhat over-protective like KSM for now! - */ - if (*vm_flags & VM_NO_THP) - return -EINVAL; *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; /* @@ -1865,15 +1860,11 @@ int hugepage_madvise(struct vm_area_struct *vma, * register it here without waiting a page fault that * may not happen any time soon. */ - if (unlikely(khugepaged_enter_vma_merge(vma, *vm_flags))) + if (!(*vm_flags & VM_NO_KHUGEPAGED) && + khugepaged_enter_vma_merge(vma, *vm_flags)) return -ENOMEM; break; case MADV_NOHUGEPAGE: - /* - * Be somewhat over-protective like KSM for now! - */ - if (*vm_flags & VM_NO_THP) - return -EINVAL; *vm_flags &= ~VM_HUGEPAGE; *vm_flags |= VM_NOHUGEPAGE; /* @@ -1984,7 +1975,7 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma, if (vma->vm_ops) /* khugepaged not yet working on file or special mappings */ return 0; - VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma); + VM_BUG_ON_VMA(vm_flags & VM_NO_KHUGEPAGED, vma); hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; if (hstart < hend) @@ -2373,7 +2364,7 @@ static bool hugepage_vma_check(struct vm_area_struct *vma) return false; if (is_vma_temporary_stack(vma)) return false; - VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma); + VM_BUG_ON_VMA(vma->vm_flags & VM_NO_KHUGEPAGED, vma); return true; } diff --git a/mm/shmem.c b/mm/shmem.c index ec899b5ea9e6..872d658d37c0 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -101,6 +101,8 @@ struct shmem_falloc { enum sgp_type { SGP_READ, /* don't exceed i_size, don't allocate page */ SGP_CACHE, /* don't exceed i_size, may allocate page */ + SGP_NOHUGE, /* like SGP_CACHE, but no huge pages */ + SGP_HUGE, /* like SGP_CACHE, huge pages preferred */ SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */ SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ }; @@ -1409,6 +1411,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct mem_cgroup *memcg; struct page *page; swp_entry_t swap; + enum sgp_type sgp_huge = sgp; pgoff_t hindex = index; int error; int once = 0; @@ -1416,6 +1419,8 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT)) return -EFBIG; + if (sgp == SGP_NOHUGE || sgp == SGP_HUGE) + sgp = SGP_CACHE; repeat: swap.val = 0; page = find_lock_entry(mapping, index); @@ -1534,7 +1539,7 @@ repeat: /* shmem_symlink() */ if (mapping->a_ops != &shmem_aops) goto alloc_nohuge; - if (shmem_huge == SHMEM_HUGE_DENY) + if (shmem_huge == SHMEM_HUGE_DENY || sgp_huge == SGP_NOHUGE) goto alloc_nohuge; if (shmem_huge == SHMEM_HUGE_FORCE) goto alloc_huge; @@ -1551,7 +1556,9 @@ repeat: goto alloc_huge; /* fallthrough */ case SHMEM_HUGE_ADVISE: - /* TODO: wire up fadvise()/madvise() */ + if (sgp_huge == SGP_HUGE) + goto alloc_huge; + /* TODO: implement fadvise() hints */ goto alloc_nohuge; } @@ -1680,6 +1687,7 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct inode *inode = file_inode(vma->vm_file); gfp_t gfp = mapping_gfp_mask(inode->i_mapping); + enum sgp_type sgp; int error; int ret = VM_FAULT_LOCKED; @@ -1741,7 +1749,13 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) spin_unlock(&inode->i_lock); } - error = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, SGP_CACHE, + sgp = SGP_CACHE; + if (vma->vm_flags & VM_HUGEPAGE) + sgp = SGP_HUGE; + else if (vma->vm_flags & VM_NOHUGEPAGE) + sgp = SGP_NOHUGE; + + error = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp, gfp, vma->vm_mm, &ret); if (error) return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS); -- 2.8.1