This patch a set of new trace events to collect the speculative page fault event failures.
Signed-off-by: Laurent Dufour <lduf...@linux.vnet.ibm.com> --- include/trace/events/pagefault.h | 87 ++++++++++++++++++++++++++++++++++++++++ mm/memory.c | 68 ++++++++++++++++++++++++------- 2 files changed, 141 insertions(+), 14 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 <linux/tracepoint.h> +#include <linux/mm.h> + +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 <trace/define_trace.h> diff --git a/mm/memory.c b/mm/memory.c index 8c701e4f59d3..549d23583f53 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -79,6 +79,9 @@ #include "internal.h" +#define CREATE_TRACE_POINTS +#include <trace/events/pagefault.h> + #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif @@ -2296,15 +2299,20 @@ 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; } @@ -2334,8 +2342,10 @@ 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 @@ -2348,11 +2358,13 @@ 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; } @@ -3989,27 +4001,40 @@ 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; + } - 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; + } /* * MPOL_INTERLEAVE implies additional check in mpol_misplaced() which @@ -4018,20 +4043,26 @@ 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; + } - 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; + } /* * The three following checks are copied from access_error from @@ -4039,16 +4070,22 @@ int handle_speculative_fault(struct mm_struct *mm, unsigned long address, */ if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, flags & FAULT_FLAG_INSTRUCTION, - flags & FAULT_FLAG_REMOTE)) + flags & FAULT_FLAG_REMOTE)) { + trace_spf_vma_access(_RET_IP_, vma, address); goto unlock; + } /* 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))) + if (unlikely(!(vmf.vma_flags & VM_WRITE))) { + trace_spf_vma_access(_RET_IP_, vma, address); goto unlock; + } } else { - if (unlikely(!(vmf.vma_flags & (VM_READ | VM_EXEC | VM_WRITE)))) + if (unlikely(!(vmf.vma_flags & (VM_READ | VM_EXEC | VM_WRITE)))) { + trace_spf_vma_access(_RET_IP_, vma, address); goto unlock; + } } /* @@ -4097,8 +4134,10 @@ 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); @@ -4107,6 +4146,7 @@ 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