Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932756AbdIHSJd (ORCPT ); Fri, 8 Sep 2017 14:09:33 -0400 Received: from mx0b-001b2d01.pphosted.com ([148.163.158.5]:49592 "EHLO mx0a-001b2d01.pphosted.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S932639AbdIHSIN (ORCPT ); Fri, 8 Sep 2017 14:08:13 -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 , Sergey Senozhatsky 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 v3 16/20] mm: Adding speculative page fault failure trace events Date: Fri, 8 Sep 2017 20:07:00 +0200 X-Mailer: git-send-email 2.7.4 In-Reply-To: <1504894024-2750-1-git-send-email-ldufour@linux.vnet.ibm.com> References: <1504894024-2750-1-git-send-email-ldufour@linux.vnet.ibm.com> X-TM-AS-GCONF: 00 x-cbid: 17090818-0040-0000-0000-000003D89EA1 X-IBM-AV-DETECTION: SAVI=unused REMOTE=unused XFE=unused x-cbparentid: 17090818-0041-0000-0000-000025D9A567 Message-Id: <1504894024-2750-17-git-send-email-ldufour@linux.vnet.ibm.com> X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:,, definitions=2017-09-08_12:,, signatures=0 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 spamscore=0 suspectscore=0 malwarescore=0 phishscore=0 adultscore=0 bulkscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1707230000 definitions=main-1709080270 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7970 Lines: 287 This patch a set of new trace events to collect the speculative page fault event failures. Signed-off-by: Laurent Dufour --- include/trace/events/pagefault.h | 87 ++++++++++++++++++++++++++++++++++++++++ mm/memory.c | 59 ++++++++++++++++++++++----- 2 files changed, 135 insertions(+), 11 deletions(-) create mode 100644 include/trace/events/pagefault.h diff --git a/include/trace/events/pagefault.h b/include/trace/events/pagefault.h new file mode 100644 index 000000000000..d7d56f8102d1 --- /dev/null +++ b/include/trace/events/pagefault.h @@ -0,0 +1,87 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM pagefault + +#if !defined(_TRACE_PAGEFAULT_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PAGEFAULT_H + +#include +#include + +DECLARE_EVENT_CLASS(spf, + + TP_PROTO(unsigned long caller, + struct vm_area_struct *vma, unsigned long address), + + TP_ARGS(caller, vma, address), + + TP_STRUCT__entry( + __field(unsigned long, caller) + __field(unsigned long, vm_start) + __field(unsigned long, vm_end) + __field(unsigned long, address) + ), + + TP_fast_assign( + __entry->caller = caller; + __entry->vm_start = vma->vm_start; + __entry->vm_end = vma->vm_end; + __entry->address = address; + ), + + TP_printk("ip:%lx vma:%lu-%lx address:%lx", + __entry->caller, __entry->vm_start, __entry->vm_end, + __entry->address) +); + +DEFINE_EVENT(spf, spf_pte_lock, + + TP_PROTO(unsigned long caller, + struct vm_area_struct *vma, unsigned long address), + + TP_ARGS(caller, vma, address) +); + +DEFINE_EVENT(spf, spf_vma_changed, + + TP_PROTO(unsigned long caller, + struct vm_area_struct *vma, unsigned long address), + + TP_ARGS(caller, vma, address) +); + +DEFINE_EVENT(spf, spf_vma_dead, + + TP_PROTO(unsigned long caller, + struct vm_area_struct *vma, unsigned long address), + + TP_ARGS(caller, vma, address) +); + +DEFINE_EVENT(spf, spf_vma_noanon, + + TP_PROTO(unsigned long caller, + struct vm_area_struct *vma, unsigned long address), + + TP_ARGS(caller, vma, address) +); + +DEFINE_EVENT(spf, spf_vma_notsup, + + TP_PROTO(unsigned long caller, + struct vm_area_struct *vma, unsigned long address), + + TP_ARGS(caller, vma, address) +); + +DEFINE_EVENT(spf, spf_vma_access, + + TP_PROTO(unsigned long caller, + struct vm_area_struct *vma, unsigned long address), + + TP_ARGS(caller, vma, address) +); + +#endif /* _TRACE_PAGEFAULT_H */ + +/* This part must be outside protection */ +#include diff --git a/mm/memory.c b/mm/memory.c index 18b39f930ce1..c2a52ddc850b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -81,6 +81,9 @@ #include "internal.h" +#define CREATE_TRACE_POINTS +#include + #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif @@ -2428,15 +2431,20 @@ static bool pte_spinlock(struct vm_fault *vmf) } local_irq_disable(); - if (vma_has_changed(vmf)) + if (vma_has_changed(vmf)) { + trace_spf_vma_changed(_RET_IP_, vmf->vma, vmf->address); goto out; + } vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); - if (unlikely(!spin_trylock(vmf->ptl))) + if (unlikely(!spin_trylock(vmf->ptl))) { + trace_spf_pte_lock(_RET_IP_, vmf->vma, vmf->address); goto out; + } if (vma_has_changed(vmf)) { spin_unlock(vmf->ptl); + trace_spf_vma_changed(_RET_IP_, vmf->vma, vmf->address); goto out; } @@ -2466,8 +2474,10 @@ static bool pte_map_lock(struct vm_fault *vmf) * block on the PTL and thus we're safe. */ local_irq_disable(); - if (vma_has_changed(vmf)) + if (vma_has_changed(vmf)) { + trace_spf_vma_changed(_RET_IP_, vmf->vma, vmf->address); goto out; + } /* * Same as pte_offset_map_lock() except that we call @@ -2480,11 +2490,13 @@ static bool pte_map_lock(struct vm_fault *vmf) pte = pte_offset_map(vmf->pmd, vmf->address); if (unlikely(!spin_trylock(ptl))) { pte_unmap(pte); + trace_spf_pte_lock(_RET_IP_, vmf->vma, vmf->address); goto out; } if (vma_has_changed(vmf)) { pte_unmap_unlock(pte, ptl); + trace_spf_vma_changed(_RET_IP_, vmf->vma, vmf->address); goto out; } @@ -4164,32 +4176,45 @@ int handle_speculative_fault(struct mm_struct *mm, unsigned long address, * Validate the VMA found by the lockless lookup. */ dead = RB_EMPTY_NODE(&vma->vm_rb); + if (dead) { + trace_spf_vma_dead(_RET_IP_, vma, address); + goto unlock; + } + seq = raw_read_seqcount(&vma->vm_sequence); /* rmb <-> seqlock,vma_rb_erase() */ - if ((seq & 1) || dead) + if (seq & 1) { + trace_spf_vma_changed(_RET_IP_, vma, address); goto unlock; + } /* * Can't call vm_ops service has we don't know what they would do * with the VMA. * This include huge page from hugetlbfs. */ - if (vma->vm_ops) + if (vma->vm_ops) { + trace_spf_vma_notsup(_RET_IP_, vma, address); goto unlock; + } /* * __anon_vma_prepare() requires the mmap_sem to be held * because vm_next and vm_prev must be safe. This can't be guaranteed * in the speculative path. */ - if (unlikely(!vma->anon_vma)) + if (unlikely(!vma->anon_vma)) { + trace_spf_vma_notsup(_RET_IP_, vma, address); goto unlock; + } vmf.vma_flags = READ_ONCE(vma->vm_flags); vmf.vma_page_prot = READ_ONCE(vma->vm_page_prot); /* Can't call userland page fault handler in the speculative path */ - if (unlikely(vmf.vma_flags & VM_UFFD_MISSING)) + if (unlikely(vmf.vma_flags & VM_UFFD_MISSING)) { + trace_spf_vma_notsup(_RET_IP_, vma, address); goto unlock; + } #ifdef CONFIG_NUMA /* @@ -4199,25 +4224,32 @@ int handle_speculative_fault(struct mm_struct *mm, unsigned long address, pol = __get_vma_policy(vma, address); if (!pol) pol = get_task_policy(current); - if (pol && pol->mode == MPOL_INTERLEAVE) + if (pol && pol->mode == MPOL_INTERLEAVE) { + trace_spf_vma_notsup(_RET_IP_, vma, address); goto unlock; + } #endif - if (vmf.vma_flags & VM_GROWSDOWN || vmf.vma_flags & VM_GROWSUP) + if (vmf.vma_flags & VM_GROWSDOWN || vmf.vma_flags & VM_GROWSUP) { /* * This could be detected by the check address against VMA's * boundaries but we want to trace it as not supported instead * of changed. */ + trace_spf_vma_notsup(_RET_IP_, vma, address); goto unlock; + } if (address < READ_ONCE(vma->vm_start) - || READ_ONCE(vma->vm_end) <= address) + || READ_ONCE(vma->vm_end) <= address) { + trace_spf_vma_changed(_RET_IP_, vma, address); goto unlock; + } if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, flags & FAULT_FLAG_INSTRUCTION, flags & FAULT_FLAG_REMOTE)) { + trace_spf_vma_access(_RET_IP_, vma, address); ret = VM_FAULT_SIGSEGV; goto unlock; } @@ -4225,10 +4257,12 @@ int handle_speculative_fault(struct mm_struct *mm, unsigned long address, /* This is one is required to check that the VMA has write access set */ if (flags & FAULT_FLAG_WRITE) { if (unlikely(!(vmf.vma_flags & VM_WRITE))) { + trace_spf_vma_access(_RET_IP_, vma, address); ret = VM_FAULT_SIGSEGV; goto unlock; } } else if (unlikely(!(vmf.vma_flags & (VM_READ|VM_EXEC|VM_WRITE)))) { + trace_spf_vma_access(_RET_IP_, vma, address); ret = VM_FAULT_SIGSEGV; goto unlock; } @@ -4282,8 +4316,10 @@ int handle_speculative_fault(struct mm_struct *mm, unsigned long address, * We need to re-validate the VMA after checking the bounds, otherwise * we might have a false positive on the bounds. */ - if (read_seqcount_retry(&vma->vm_sequence, seq)) + if (read_seqcount_retry(&vma->vm_sequence, seq)) { + trace_spf_vma_changed(_RET_IP_, vma, address); goto unlock; + } ret = handle_pte_fault(&vmf); @@ -4292,6 +4328,7 @@ int handle_speculative_fault(struct mm_struct *mm, unsigned long address, return ret; out_walk: + trace_spf_vma_notsup(_RET_IP_, vma, address); local_irq_enable(); goto unlock; } -- 2.7.4