Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754060AbdHQWNR (ORCPT ); Thu, 17 Aug 2017 18:13:17 -0400 Received: from mx0a-001b2d01.pphosted.com ([148.163.156.1]:56787 "EHLO mx0a-001b2d01.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753693AbdHQWFn (ORCPT ); Thu, 17 Aug 2017 18:05:43 -0400 From: Laurent Dufour To: paulmck@linux.vnet.ibm.com, peterz@infradead.org, akpm@linux-foundation.org, kirill@shutemov.name, ak@linux.intel.com, mhocko@kernel.org, dave@stgolabs.net, jack@suse.cz, Matthew Wilcox , benh@kernel.crashing.org, mpe@ellerman.id.au, paulus@samba.org, Thomas Gleixner , Ingo Molnar , hpa@zytor.com, Will Deacon Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org, haren@linux.vnet.ibm.com, khandual@linux.vnet.ibm.com, npiggin@gmail.com, bsingharora@gmail.com, Tim Chen , linuxppc-dev@lists.ozlabs.org, x86@kernel.org Subject: [PATCH v2 02/20] mm: Prepare for FAULT_FLAG_SPECULATIVE Date: Fri, 18 Aug 2017 00:05:01 +0200 X-Mailer: git-send-email 2.7.4 In-Reply-To: <1503007519-26777-1-git-send-email-ldufour@linux.vnet.ibm.com> References: <1503007519-26777-1-git-send-email-ldufour@linux.vnet.ibm.com> X-TM-AS-GCONF: 00 x-cbid: 17081722-0012-0000-0000-0000057087B9 X-IBM-AV-DETECTION: SAVI=unused REMOTE=unused XFE=unused x-cbparentid: 17081722-0013-0000-0000-000018E8530B Message-Id: <1503007519-26777-3-git-send-email-ldufour@linux.vnet.ibm.com> X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:,, definitions=2017-08-17_12:,, signatures=0 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 spamscore=0 suspectscore=2 malwarescore=0 phishscore=0 adultscore=0 bulkscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1707230000 definitions=main-1708170357 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5755 Lines: 171 From: Peter Zijlstra When speculating faults (without holding mmap_sem) we need to validate that the vma against which we loaded pages is still valid when we're ready to install the new PTE. Therefore, replace the pte_offset_map_lock() calls that (re)take the PTL with pte_map_lock() which can fail in case we find the VMA changed since we started the fault. Signed-off-by: Peter Zijlstra (Intel) [Port to 4.12 kernel] [Remove the comment about the fault_env structure which has been implemented as the vm_fault structure in the kernel] Signed-off-by: Laurent Dufour --- include/linux/mm.h | 1 + mm/memory.c | 55 ++++++++++++++++++++++++++++++++++++++---------------- 2 files changed, 40 insertions(+), 16 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 46b9ac5e8569..8763ec96dc78 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -286,6 +286,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_USER 0x40 /* The fault originated in userspace */ #define FAULT_FLAG_REMOTE 0x80 /* faulting for non current tsk/mm */ #define FAULT_FLAG_INSTRUCTION 0x100 /* The fault was during an instruction fetch */ +#define FAULT_FLAG_SPECULATIVE 0x200 /* Speculative fault, not holding mmap_sem */ #define FAULT_FLAG_TRACE \ { FAULT_FLAG_WRITE, "WRITE" }, \ diff --git a/mm/memory.c b/mm/memory.c index 36609c082256..3ed1b00ca841 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2269,6 +2269,12 @@ static inline void wp_page_reuse(struct vm_fault *vmf) pte_unmap_unlock(vmf->pte, vmf->ptl); } +static bool pte_map_lock(struct vm_fault *vmf) +{ + vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); + return true; +} + /* * Handle the case of a page which we actually need to copy to a new page. * @@ -2296,6 +2302,7 @@ static int wp_page_copy(struct vm_fault *vmf) const unsigned long mmun_start = vmf->address & PAGE_MASK; const unsigned long mmun_end = mmun_start + PAGE_SIZE; struct mem_cgroup *memcg; + int ret = VM_FAULT_OOM; if (unlikely(anon_vma_prepare(vma))) goto oom; @@ -2323,7 +2330,11 @@ static int wp_page_copy(struct vm_fault *vmf) /* * Re-check the pte - we dropped the lock */ - vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl); + if (!pte_map_lock(vmf)) { + mem_cgroup_cancel_charge(new_page, memcg, false); + ret = VM_FAULT_RETRY; + goto oom_free_new; + } if (likely(pte_same(*vmf->pte, vmf->orig_pte))) { if (old_page) { if (!PageAnon(old_page)) { @@ -2411,7 +2422,7 @@ static int wp_page_copy(struct vm_fault *vmf) oom: if (old_page) put_page(old_page); - return VM_FAULT_OOM; + return ret; } /** @@ -2432,8 +2443,8 @@ static int wp_page_copy(struct vm_fault *vmf) int finish_mkwrite_fault(struct vm_fault *vmf) { WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED)); - vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, - &vmf->ptl); + if (!pte_map_lock(vmf)) + return VM_FAULT_RETRY; /* * We might have raced with another page fault while we released the * pte_offset_map_lock. @@ -2551,8 +2562,11 @@ static int do_wp_page(struct vm_fault *vmf) get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); lock_page(vmf->page); - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); + if (!pte_map_lock(vmf)) { + unlock_page(vmf->page); + put_page(vmf->page); + return VM_FAULT_RETRY; + } if (!pte_same(*vmf->pte, vmf->orig_pte)) { unlock_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); @@ -2710,8 +2724,10 @@ int do_swap_page(struct vm_fault *vmf) * Back out if somebody else faulted in this pte * while we released the pte lock. */ - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); + if (!pte_map_lock(vmf)) { + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + return VM_FAULT_RETRY; + } if (likely(pte_same(*vmf->pte, vmf->orig_pte))) ret = VM_FAULT_OOM; delayacct_clear_flag(DELAYACCT_PF_SWAPIN); @@ -2767,8 +2783,11 @@ int do_swap_page(struct vm_fault *vmf) /* * Back out if somebody else already faulted in this pte. */ - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, - &vmf->ptl); + if (!pte_map_lock(vmf)) { + ret = VM_FAULT_RETRY; + mem_cgroup_cancel_charge(page, memcg, false); + goto out_page; + } if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) goto out_nomap; @@ -2894,8 +2913,8 @@ static int do_anonymous_page(struct vm_fault *vmf) !mm_forbids_zeropage(vma->vm_mm)) { entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address), vma->vm_page_prot)); - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); + if (!pte_map_lock(vmf)) + return VM_FAULT_RETRY; if (!pte_none(*vmf->pte)) goto unlock; /* Deliver the page fault to userland, check inside PT lock */ @@ -2927,8 +2946,11 @@ static int do_anonymous_page(struct vm_fault *vmf) if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, - &vmf->ptl); + if (!pte_map_lock(vmf)) { + mem_cgroup_cancel_charge(page, memcg, false); + put_page(page); + return VM_FAULT_RETRY; + } if (!pte_none(*vmf->pte)) goto release; @@ -3048,8 +3070,9 @@ static int pte_alloc_one_map(struct vm_fault *vmf) * pte_none() under vmf->ptl protection when we return to * alloc_set_pte(). */ - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, - &vmf->ptl); + if (!pte_map_lock(vmf)) + return VM_FAULT_RETRY; + return 0; } -- 2.7.4