On Tue, Apr 16, 2019 at 03:44:58PM +0200, Laurent Dufour wrote:
> pte_unmap_same() is making the assumption that the page table are still
> around because the mmap_sem is held.
> This is no more the case when running a speculative page fault and
> additional check must be made to ensure that the final page table are still
> there.
>
> This is now done by calling pte_spinlock() to check for the VMA's
> consistency while locking for the page tables.
>
> This is requiring passing a vm_fault structure to pte_unmap_same() which is
> containing all the needed parameters.
>
> As pte_spinlock() may fail in the case of a speculative page fault, if the
> VMA has been touched in our back, pte_unmap_same() should now return 3
> cases :
> 1. pte are the same (0)
> 2. pte are different (VM_FAULT_PTNOTSAME)
> 3. a VMA's changes has been detected (VM_FAULT_RETRY)
>
> The case 2 is handled by the introduction of a new VM_FAULT flag named
> VM_FAULT_PTNOTSAME which is then trapped in cow_user_page().
> If VM_FAULT_RETRY is returned, it is passed up to the callers to retry the
> page fault while holding the mmap_sem.
>
> Acked-by: David Rientjes <rient...@google.com>
> Signed-off-by: Laurent Dufour <lduf...@linux.ibm.com>
Reviewed-by: Jérôme Glisse <jgli...@redhat.com>
> ---
> include/linux/mm_types.h | 6 +++++-
> mm/memory.c | 37 +++++++++++++++++++++++++++----------
> 2 files changed, 32 insertions(+), 11 deletions(-)
>
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index 8ec38b11b361..fd7d38ee2e33 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -652,6 +652,8 @@ typedef __bitwise unsigned int vm_fault_t;
> * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and
> needs
> * fsync() to complete (for synchronous page faults
> * in DAX)
> + * @VM_FAULT_PTNOTSAME Page table entries have changed during a
> + * speculative page fault handling.
> * @VM_FAULT_HINDEX_MASK: mask HINDEX value
> *
> */
> @@ -669,6 +671,7 @@ enum vm_fault_reason {
> VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800,
> VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000,
> VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000,
> + VM_FAULT_PTNOTSAME = (__force vm_fault_t)0x004000,
> VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000,
> };
>
> @@ -693,7 +696,8 @@ enum vm_fault_reason {
> { VM_FAULT_RETRY, "RETRY" }, \
> { VM_FAULT_FALLBACK, "FALLBACK" }, \
> { VM_FAULT_DONE_COW, "DONE_COW" }, \
> - { VM_FAULT_NEEDDSYNC, "NEEDDSYNC" }
> + { VM_FAULT_NEEDDSYNC, "NEEDDSYNC" }, \
> + { VM_FAULT_PTNOTSAME, "PTNOTSAME" }
>
> struct vm_special_mapping {
> const char *name; /* The name, e.g. "[vdso]". */
> diff --git a/mm/memory.c b/mm/memory.c
> index 221ccdf34991..d5bebca47d98 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -2094,21 +2094,29 @@ static inline bool pte_map_lock(struct vm_fault *vmf)
> * parts, do_swap_page must check under lock before unmapping the pte and
> * proceeding (but do_wp_page is only called after already making such a
> check;
> * and do_anonymous_page can safely check later on).
> + *
> + * pte_unmap_same() returns:
> + * 0 if the PTE are the same
> + * VM_FAULT_PTNOTSAME if the PTE are different
> + * VM_FAULT_RETRY if the VMA has changed in our back during
> + * a speculative page fault handling.
> */
> -static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
> - pte_t *page_table, pte_t orig_pte)
> +static inline vm_fault_t pte_unmap_same(struct vm_fault *vmf)
> {
> - int same = 1;
> + int ret = 0;
> +
> #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
> if (sizeof(pte_t) > sizeof(unsigned long)) {
> - spinlock_t *ptl = pte_lockptr(mm, pmd);
> - spin_lock(ptl);
> - same = pte_same(*page_table, orig_pte);
> - spin_unlock(ptl);
> + if (pte_spinlock(vmf)) {
> + if (!pte_same(*vmf->pte, vmf->orig_pte))
> + ret = VM_FAULT_PTNOTSAME;
> + spin_unlock(vmf->ptl);
> + } else
> + ret = VM_FAULT_RETRY;
> }
> #endif
> - pte_unmap(page_table);
> - return same;
> + pte_unmap(vmf->pte);
> + return ret;
> }
>
> static inline void cow_user_page(struct page *dst, struct page *src,
> unsigned long va, struct vm_area_struct *vma)
> @@ -2714,8 +2722,17 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> int exclusive = 0;
> vm_fault_t ret = 0;
>
> - if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte))
> + ret = pte_unmap_same(vmf);
> + if (ret) {
> + /*
> + * If pte != orig_pte, this means another thread did the
> + * swap operation in our back.
> + * So nothing else to do.
> + */
> + if (ret == VM_FAULT_PTNOTSAME)
> + ret = 0;
> goto out;
> + }
>
> entry = pte_to_swp_entry(vmf->orig_pte);
> if (unlikely(non_swap_entry(entry))) {
> --
> 2.21.0
>
