From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Date: Thu, 22 Dec 2016 23:52:03 +0900 From: Minchan Kim To: "Kirill A. Shutemov" Cc: Andrew Morton , linux-mm@kvack.org, Jason Evans , "Kirill A . Shutemov" , Will Deacon , Catalin Marinas , linux-arch@vger.kernel.org, linux-arm-kernel@lists.infradead.org, "[4.5+]" , Andreas Schwab Subject: Re: [PATCH] mm: pmd dirty emulation in page fault handler Message-ID: <20161222145203.GA18970@bbox> References: <1482364101-16204-1-git-send-email-minchan@kernel.org> <20161222081713.GA32480@node.shutemov.name> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20161222081713.GA32480@node.shutemov.name> Sender: owner-linux-mm@kvack.org List-ID: Hello, On Thu, Dec 22, 2016 at 11:17:13AM +0300, Kirill A. Shutemov wrote: < snip > > > 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) > > In theory, more than one flag can be set and it would lead to > false-negative. Bit check was the right thing. > > And I don't understand why do you need to change code in > __handle_mm_fault() at all. > From what I see change to huge_pmd_set_accessed() should be enough. Yeb. Thanks for the review. Here v2 goes. >>From b3ec95c0df91ad113525968a4a6b53030fd0b48d Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 22 Dec 2016 23:43:49 +0900 Subject: [PATCH v2] mm: pmd dirty emulation in page fault handler 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] b8d3c4c3009d, 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 --- * from v1 * Remove __handle_mm_fault part - Kirill mm/huge_memory.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 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: -- 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 From: Minchan Kim Subject: Re: [PATCH] mm: pmd dirty emulation in page fault handler Date: Thu, 22 Dec 2016 23:52:03 +0900 Message-ID: <20161222145203.GA18970@bbox> References: <1482364101-16204-1-git-send-email-minchan@kernel.org> <20161222081713.GA32480@node.shutemov.name> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20161222081713.GA32480@node.shutemov.name> Sender: stable-owner@vger.kernel.org To: "Kirill A. Shutemov" Cc: Andrew Morton , linux-mm@kvack.org, 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 Hello, On Thu, Dec 22, 2016 at 11:17:13AM +0300, Kirill A. Shutemov wrote: < snip > > > 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) > > In theory, more than one flag can be set and it would lead to > false-negative. Bit check was the right thing. > > And I don't understand why do you need to change code in > __handle_mm_fault() at all. > From what I see change to huge_pmd_set_accessed() should be enough. Yeb. Thanks for the review. Here v2 goes. >From b3ec95c0df91ad113525968a4a6b53030fd0b48d Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 22 Dec 2016 23:43:49 +0900 Subject: [PATCH v2] mm: pmd dirty emulation in page fault handler 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] b8d3c4c3009d, 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 --- * from v1 * Remove __handle_mm_fault part - Kirill mm/huge_memory.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 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: -- 2.7.4 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from LGEAMRELO11.lge.com ([156.147.23.51]:43923 "EHLO lgeamrelo11.lge.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752614AbcLVOwI (ORCPT ); Thu, 22 Dec 2016 09:52:08 -0500 Date: Thu, 22 Dec 2016 23:52:03 +0900 From: Minchan Kim Subject: Re: [PATCH] mm: pmd dirty emulation in page fault handler Message-ID: <20161222145203.GA18970@bbox> References: <1482364101-16204-1-git-send-email-minchan@kernel.org> <20161222081713.GA32480@node.shutemov.name> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20161222081713.GA32480@node.shutemov.name> Sender: linux-arch-owner@vger.kernel.org List-ID: To: "Kirill A. Shutemov" Cc: Andrew Morton , linux-mm@kvack.org, 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: <20161222145203.DLWbA7lWDT7kWb5msHDSgysswHn2VClv7-2FKdUm0d8@z> Hello, On Thu, Dec 22, 2016 at 11:17:13AM +0300, Kirill A. Shutemov wrote: < snip > > > 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) > > In theory, more than one flag can be set and it would lead to > false-negative. Bit check was the right thing. > > And I don't understand why do you need to change code in > __handle_mm_fault() at all. > From what I see change to huge_pmd_set_accessed() should be enough. Yeb. Thanks for the review. Here v2 goes. From mboxrd@z Thu Jan 1 00:00:00 1970 From: minchan@kernel.org (Minchan Kim) Date: Thu, 22 Dec 2016 23:52:03 +0900 Subject: [PATCH] mm: pmd dirty emulation in page fault handler In-Reply-To: <20161222081713.GA32480@node.shutemov.name> References: <1482364101-16204-1-git-send-email-minchan@kernel.org> <20161222081713.GA32480@node.shutemov.name> Message-ID: <20161222145203.GA18970@bbox> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org Hello, On Thu, Dec 22, 2016 at 11:17:13AM +0300, Kirill A. Shutemov wrote: < snip > > > 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) > > In theory, more than one flag can be set and it would lead to > false-negative. Bit check was the right thing. > > And I don't understand why do you need to change code in > __handle_mm_fault() at all. > From what I see change to huge_pmd_set_accessed() should be enough. Yeb. Thanks for the review. Here v2 goes. >>From b3ec95c0df91ad113525968a4a6b53030fd0b48d Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 22 Dec 2016 23:43:49 +0900 Subject: [PATCH v2] mm: pmd dirty emulation in page fault handler 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] b8d3c4c3009d, 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 --- * from v1 * Remove __handle_mm_fault part - Kirill mm/huge_memory.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 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: -- 2.7.4