From mboxrd@z Thu Jan 1 00:00:00 1970 From: Minchan Kim Subject: [PATCH] mm: pmd dirty emulation in page fault handler Date: Thu, 22 Dec 2016 08:48:21 +0900 Message-ID: <1482364101-16204-1-git-send-email-minchan@kernel.org> Return-path: Sender: owner-linux-mm@kvack.org To: Andrew Morton Cc: linux-mm@kvack.org, Minchan Kim , Jason Evans , "Kirill A . Shutemov" , Will Deacon , Catalin Marinas , linux-arch@vger.kernel.org, linux-arm-kernel@lists.infradead.org, "[4.5+]" , Andreas Schwab List-Id: linux-arch.vger.kernel.org Andreas reported [1] made a test in jemalloc hang in THP mode in arm64. http://lkml.kernel.org/r/mvmmvfy37g1.fsf@hawking.suse.de The problem is page fault handler supports only accessed flag emulation for THP page of SW-dirty/accessed architecture. This patch enables dirty-bit emulation for those architectures. Without it, MADV_FREE makes application hang by repeated fault forever. [1] mm/huge_memory.c: don't split THP page when MADV_FREE syscall is called Cc: Jason Evans Cc: Kirill A. Shutemov Cc: Will Deacon Cc: Catalin Marinas Cc: linux-arch@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: [4.5+] Fixes: b8d3c4c3009d ("mm/huge_memory.c: don't split THP page when MADV_FREE syscall is called") Reported-by: Andreas Schwab Signed-off-by: Minchan Kim --- mm/huge_memory.c | 6 ++++-- mm/memory.c | 18 ++++++++++-------- 2 files changed, 14 insertions(+), 10 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 10eedbf..29ec8a4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -883,15 +883,17 @@ void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd) { pmd_t entry; unsigned long haddr; + bool write = vmf->flags & FAULT_FLAG_WRITE; vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) goto unlock; entry = pmd_mkyoung(orig_pmd); + if (write) + entry = pmd_mkdirty(entry); haddr = vmf->address & HPAGE_PMD_MASK; - if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry, - vmf->flags & FAULT_FLAG_WRITE)) + if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry, write)) update_mmu_cache_pmd(vmf->vma, vmf->address, vmf->pmd); unlock: diff --git a/mm/memory.c b/mm/memory.c index 36c774f..7408ddc 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3637,18 +3637,20 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, if (pmd_protnone(orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&vmf, orig_pmd); - if ((vmf.flags & FAULT_FLAG_WRITE) && - !pmd_write(orig_pmd)) { - ret = wp_huge_pmd(&vmf, orig_pmd); - if (!(ret & VM_FAULT_FALLBACK)) + if (vmf.flags & FAULT_FLAG_WRITE) { + if (!pmd_write(orig_pmd)) { + ret = wp_huge_pmd(&vmf, orig_pmd); + if (ret == VM_FAULT_FALLBACK) + goto pte_fault; return ret; - } else { - huge_pmd_set_accessed(&vmf, orig_pmd); - return 0; + } } + + huge_pmd_set_accessed(&vmf, orig_pmd); + return 0; } } - +pte_fault: return handle_pte_fault(&vmf); } -- 2.7.4 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from LGEAMRELO12.lge.com ([156.147.23.52]:51965 "EHLO lgeamrelo12.lge.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1764294AbcLUXsa (ORCPT ); Wed, 21 Dec 2016 18:48:30 -0500 From: Minchan Kim Subject: [PATCH] mm: pmd dirty emulation in page fault handler Date: Thu, 22 Dec 2016 08:48:21 +0900 Message-ID: <1482364101-16204-1-git-send-email-minchan@kernel.org> Sender: linux-arch-owner@vger.kernel.org List-ID: To: Andrew Morton Cc: linux-mm@kvack.org, Minchan Kim , Jason Evans , "Kirill A . Shutemov" , Will Deacon , Catalin Marinas , linux-arch@vger.kernel.org, linux-arm-kernel@lists.infradead.org, "[4.5+]" , Andreas Schwab Message-ID: <20161221234821.0Gj-Lh1KdDJEdE8z-ucNnf5o1xqWJa_ZDVsPZa4Oqwc@z> Andreas reported [1] made a test in jemalloc hang in THP mode in arm64. http://lkml.kernel.org/r/mvmmvfy37g1.fsf@hawking.suse.de The problem is page fault handler supports only accessed flag emulation for THP page of SW-dirty/accessed architecture. This patch enables dirty-bit emulation for those architectures. Without it, MADV_FREE makes application hang by repeated fault forever. [1] mm/huge_memory.c: don't split THP page when MADV_FREE syscall is called Cc: Jason Evans Cc: Kirill A. Shutemov Cc: Will Deacon Cc: Catalin Marinas Cc: linux-arch@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: [4.5+] Fixes: b8d3c4c3009d ("mm/huge_memory.c: don't split THP page when MADV_FREE syscall is called") Reported-by: Andreas Schwab Signed-off-by: Minchan Kim --- mm/huge_memory.c | 6 ++++-- mm/memory.c | 18 ++++++++++-------- 2 files changed, 14 insertions(+), 10 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 10eedbf..29ec8a4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -883,15 +883,17 @@ void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd) { pmd_t entry; unsigned long haddr; + bool write = vmf->flags & FAULT_FLAG_WRITE; vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) goto unlock; entry = pmd_mkyoung(orig_pmd); + if (write) + entry = pmd_mkdirty(entry); haddr = vmf->address & HPAGE_PMD_MASK; - if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry, - vmf->flags & FAULT_FLAG_WRITE)) + if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry, write)) update_mmu_cache_pmd(vmf->vma, vmf->address, vmf->pmd); unlock: diff --git a/mm/memory.c b/mm/memory.c index 36c774f..7408ddc 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3637,18 +3637,20 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, if (pmd_protnone(orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&vmf, orig_pmd); - if ((vmf.flags & FAULT_FLAG_WRITE) && - !pmd_write(orig_pmd)) { - ret = wp_huge_pmd(&vmf, orig_pmd); - if (!(ret & VM_FAULT_FALLBACK)) + if (vmf.flags & FAULT_FLAG_WRITE) { + if (!pmd_write(orig_pmd)) { + ret = wp_huge_pmd(&vmf, orig_pmd); + if (ret == VM_FAULT_FALLBACK) + goto pte_fault; return ret; - } else { - huge_pmd_set_accessed(&vmf, orig_pmd); - return 0; + } } + + huge_pmd_set_accessed(&vmf, orig_pmd); + return 0; } } - +pte_fault: return handle_pte_fault(&vmf); } -- 2.7.4 From mboxrd@z Thu Jan 1 00:00:00 1970 From: minchan@kernel.org (Minchan Kim) Date: Thu, 22 Dec 2016 08:48:21 +0900 Subject: [PATCH] mm: pmd dirty emulation in page fault handler Message-ID: <1482364101-16204-1-git-send-email-minchan@kernel.org> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org Andreas reported [1] made a test in jemalloc hang in THP mode in arm64. http://lkml.kernel.org/r/mvmmvfy37g1.fsf at hawking.suse.de The problem is page fault handler supports only accessed flag emulation for THP page of SW-dirty/accessed architecture. This patch enables dirty-bit emulation for those architectures. Without it, MADV_FREE makes application hang by repeated fault forever. [1] mm/huge_memory.c: don't split THP page when MADV_FREE syscall is called Cc: Jason Evans Cc: Kirill A. Shutemov Cc: Will Deacon Cc: Catalin Marinas Cc: linux-arch at vger.kernel.org Cc: linux-arm-kernel at lists.infradead.org Cc: [4.5+] Fixes: b8d3c4c3009d ("mm/huge_memory.c: don't split THP page when MADV_FREE syscall is called") Reported-by: Andreas Schwab Signed-off-by: Minchan Kim --- mm/huge_memory.c | 6 ++++-- mm/memory.c | 18 ++++++++++-------- 2 files changed, 14 insertions(+), 10 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 10eedbf..29ec8a4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -883,15 +883,17 @@ void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd) { pmd_t entry; unsigned long haddr; + bool write = vmf->flags & FAULT_FLAG_WRITE; vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) goto unlock; entry = pmd_mkyoung(orig_pmd); + if (write) + entry = pmd_mkdirty(entry); haddr = vmf->address & HPAGE_PMD_MASK; - if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry, - vmf->flags & FAULT_FLAG_WRITE)) + if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry, write)) update_mmu_cache_pmd(vmf->vma, vmf->address, vmf->pmd); unlock: diff --git a/mm/memory.c b/mm/memory.c index 36c774f..7408ddc 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3637,18 +3637,20 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, if (pmd_protnone(orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&vmf, orig_pmd); - if ((vmf.flags & FAULT_FLAG_WRITE) && - !pmd_write(orig_pmd)) { - ret = wp_huge_pmd(&vmf, orig_pmd); - if (!(ret & VM_FAULT_FALLBACK)) + if (vmf.flags & FAULT_FLAG_WRITE) { + if (!pmd_write(orig_pmd)) { + ret = wp_huge_pmd(&vmf, orig_pmd); + if (ret == VM_FAULT_FALLBACK) + goto pte_fault; return ret; - } else { - huge_pmd_set_accessed(&vmf, orig_pmd); - return 0; + } } + + huge_pmd_set_accessed(&vmf, orig_pmd); + return 0; } } - +pte_fault: return handle_pte_fault(&vmf); } -- 2.7.4