Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Laurent Dufour <ldufour@linux.ibm.com>
To:     akpm@linux-foundation.org, mhocko@kernel.org, peterz@infradead.org,
        kirill@shutemov.name, ak@linux.intel.com, dave@stgolabs.net,
        jack@suse.cz, Matthew Wilcox <willy@infradead.org>,
        aneesh.kumar@linux.ibm.com, benh@kernel.crashing.org,
        mpe@ellerman.id.au, paulus@samba.org,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, hpa@zytor.com,
        Will Deacon <will.deacon@arm.com>,
        Sergey Senozhatsky <sergey.senozhatsky@gmail.com>,
        sergey.senozhatsky.work@gmail.com,
        Andrea Arcangeli <aarcange@redhat.com>,
        Alexei Starovoitov <alexei.starovoitov@gmail.com>,
        kemi.wang@intel.com, Daniel Jordan <daniel.m.jordan@oracle.com>,
        David Rientjes <rientjes@google.com>,
        Jerome Glisse <jglisse@redhat.com>,
        Ganesh Mahendran <opensource.ganesh@gmail.com>,
        Minchan Kim <minchan@kernel.org>,
        Punit Agrawal <punitagrawal@gmail.com>,
        vinayak menon <vinayakm.list@gmail.com>,
        Yang Shi <yang.shi@linux.alibaba.com>,
        zhong jiang <zhongjiang@huawei.com>,
        Haiyan Song <haiyanx.song@intel.com>,
        Balbir Singh <bsingharora@gmail.com>, sj38.park@gmail.com,
        Michel Lespinasse <walken@google.com>,
        Mike Rapoport <rppt@linux.ibm.com>
Cc:     linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        haren@linux.vnet.ibm.com, npiggin@gmail.com,
        paulmck@linux.vnet.ibm.com, Tim Chen <tim.c.chen@linux.intel.com>,
        linuxppc-dev@lists.ozlabs.org, x86@kernel.org
Subject: [PATCH v12 13/31] mm: cache some VMA fields in the vm_fault structure
Date:   Tue, 16 Apr 2019 15:45:04 +0200
In-Reply-To: <20190416134522.17540-1-ldufour@linux.ibm.com>
References: <20190416134522.17540-1-ldufour@linux.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Message-Id: <20190416134522.17540-14-ldufour@linux.ibm.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

When handling speculative page fault, the vma->vm_flags and
vma->vm_page_prot fields are read once the page table lock is released. So
there is no more guarantee that these fields would not change in our back.
They will be saved in the vm_fault structure before the VMA is checked for
changes.

In the detail, when we deal with a speculative page fault, the mmap_sem is
not taken, so parallel VMA's changes can occurred. When a VMA change is
done which will impact the page fault processing, we assumed that the VMA
sequence counter will be changed.  In the page fault processing, at the
time the PTE is locked, we checked the VMA sequence counter to detect
changes done in our back. If no change is detected we can continue further.
But this doesn't prevent the VMA to not be changed in our back while the
PTE is locked. So VMA's fields which are used while the PTE is locked must
be saved to ensure that we are using *static* values.  This is important
since the PTE changes will be made on regards to these VMA fields and they
need to be consistent. This concerns the vma->vm_flags and
vma->vm_page_prot VMA fields.

This patch also set the fields in hugetlb_no_page() and
__collapse_huge_page_swapin even if it is not need for the callee.

Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
---
 include/linux/mm.h | 10 +++++++--
 mm/huge_memory.c   |  6 +++---
 mm/hugetlb.c       |  2 ++
 mm/khugepaged.c    |  2 ++
 mm/memory.c        | 53 ++++++++++++++++++++++++----------------------
 mm/migrate.c       |  2 +-
 6 files changed, 44 insertions(+), 31 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5d45b7d8718d..f465bb2b049e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -439,6 +439,12 @@ struct vm_fault {
 					 * page table to avoid allocation from
 					 * atomic context.
 					 */
+	/*
+	 * These entries are required when handling speculative page fault.
+	 * This way the page handling is done using consistent field values.
+	 */
+	unsigned long vma_flags;
+	pgprot_t vma_page_prot;
 };
 
 /* page entry size for vm->huge_fault() */
@@ -781,9 +787,9 @@ void free_compound_page(struct page *page);
  * pte_mkwrite.  But get_user_pages can cause write faults for mappings
  * that do not have writing enabled, when used by access_process_vm.
  */
-static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
+static inline pte_t maybe_mkwrite(pte_t pte, unsigned long vma_flags)
 {
-	if (likely(vma->vm_flags & VM_WRITE))
+	if (likely(vma_flags & VM_WRITE))
 		pte = pte_mkwrite(pte);
 	return pte;
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 823688414d27..865886a689ee 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1244,8 +1244,8 @@ static vm_fault_t do_huge_pmd_wp_page_fallback(struct vm_fault *vmf,
 
 	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
 		pte_t entry;
-		entry = mk_pte(pages[i], vma->vm_page_prot);
-		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		entry = mk_pte(pages[i], vmf->vma_page_prot);
+		entry = maybe_mkwrite(pte_mkdirty(entry), vmf->vma_flags);
 		memcg = (void *)page_private(pages[i]);
 		set_page_private(pages[i], 0);
 		page_add_new_anon_rmap(pages[i], vmf->vma, haddr, false);
@@ -2228,7 +2228,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 				entry = pte_swp_mksoft_dirty(entry);
 		} else {
 			entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot));
-			entry = maybe_mkwrite(entry, vma);
+			entry = maybe_mkwrite(entry, vma->vm_flags);
 			if (!write)
 				entry = pte_wrprotect(entry);
 			if (!young)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 109f5de82910..13246da4bc50 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3812,6 +3812,8 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 				.vma = vma,
 				.address = haddr,
 				.flags = flags,
+				.vma_flags = vma->vm_flags,
+				.vma_page_prot = vma->vm_page_prot,
 				/*
 				 * Hard to debug if it ends up being
 				 * used by a callee that assumes
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 6a0cbca3885e..42469037240a 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -888,6 +888,8 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 		.flags = FAULT_FLAG_ALLOW_RETRY,
 		.pmd = pmd,
 		.pgoff = linear_page_index(vma, address),
+		.vma_flags = vma->vm_flags,
+		.vma_page_prot = vma->vm_page_prot,
 	};
 
 	/* we only decide to swapin, if there is enough young ptes */
diff --git a/mm/memory.c b/mm/memory.c
index 2cf7b6185daa..d0de58464479 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1560,7 +1560,8 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 				goto out_unlock;
 			}
 			entry = pte_mkyoung(*pte);
-			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+			entry = maybe_mkwrite(pte_mkdirty(entry),
+					      vma->vm_flags);
 			if (ptep_set_access_flags(vma, addr, pte, entry, 1))
 				update_mmu_cache(vma, addr, pte);
 		}
@@ -1575,7 +1576,7 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 
 	if (mkwrite) {
 		entry = pte_mkyoung(entry);
-		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		entry = maybe_mkwrite(pte_mkdirty(entry), vma->vm_flags);
 	}
 
 	set_pte_at(mm, addr, pte, entry);
@@ -2257,7 +2258,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
 
 	flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
 	entry = pte_mkyoung(vmf->orig_pte);
-	entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+	entry = maybe_mkwrite(pte_mkdirty(entry), vmf->vma_flags);
 	if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1))
 		update_mmu_cache(vma, vmf->address, vmf->pte);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -2335,8 +2336,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 			inc_mm_counter_fast(mm, MM_ANONPAGES);
 		}
 		flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
-		entry = mk_pte(new_page, vma->vm_page_prot);
-		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		entry = mk_pte(new_page, vmf->vma_page_prot);
+		entry = maybe_mkwrite(pte_mkdirty(entry), vmf->vma_flags);
 		/*
 		 * Clear the pte entry and flush it first, before updating the
 		 * pte with the new entry. This will avoid a race condition
@@ -2401,7 +2402,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		 * Don't let another task, with possibly unlocked vma,
 		 * keep the mlocked page.
 		 */
-		if (page_copied && (vma->vm_flags & VM_LOCKED)) {
+		if (page_copied && (vmf->vma_flags & VM_LOCKED)) {
 			lock_page(old_page);	/* LRU manipulation */
 			if (PageMlocked(old_page))
 				munlock_vma_page(old_page);
@@ -2438,7 +2439,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
  */
 vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf)
 {
-	WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED));
+	WARN_ON_ONCE(!(vmf->vma_flags & VM_SHARED));
 	if (!pte_map_lock(vmf))
 		return VM_FAULT_RETRY;
 	/*
@@ -2540,7 +2541,7 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 		 * We should not cow pages in a shared writeable mapping.
 		 * Just mark the pages writable and/or call ops->pfn_mkwrite.
 		 */
-		if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
+		if ((vmf->vma_flags & (VM_WRITE|VM_SHARED)) ==
 				     (VM_WRITE|VM_SHARED))
 			return wp_pfn_shared(vmf);
 
@@ -2599,7 +2600,7 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 			return VM_FAULT_WRITE;
 		}
 		unlock_page(vmf->page);
-	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
+	} else if (unlikely((vmf->vma_flags & (VM_WRITE|VM_SHARED)) ==
 					(VM_WRITE|VM_SHARED))) {
 		return wp_page_shared(vmf);
 	}
@@ -2878,9 +2879,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 
 	inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
 	dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS);
-	pte = mk_pte(page, vma->vm_page_prot);
+	pte = mk_pte(page, vmf->vma_page_prot);
 	if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) {
-		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
+		pte = maybe_mkwrite(pte_mkdirty(pte), vmf->vma_flags);
 		vmf->flags &= ~FAULT_FLAG_WRITE;
 		ret |= VM_FAULT_WRITE;
 		exclusive = RMAP_EXCLUSIVE;
@@ -2905,7 +2906,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 
 	swap_free(entry);
 	if (mem_cgroup_swap_full(page) ||
-	    (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
+	    (vmf->vma_flags & VM_LOCKED) || PageMlocked(page))
 		try_to_free_swap(page);
 	unlock_page(page);
 	if (page != swapcache && swapcache) {
@@ -2963,7 +2964,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	pte_t entry;
 
 	/* File mapping without ->vm_ops ? */
-	if (vma->vm_flags & VM_SHARED)
+	if (vmf->vma_flags & VM_SHARED)
 		return VM_FAULT_SIGBUS;
 
 	/*
@@ -2987,7 +2988,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	if (!(vmf->flags & FAULT_FLAG_WRITE) &&
 			!mm_forbids_zeropage(vma->vm_mm)) {
 		entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address),
-						vma->vm_page_prot));
+						vmf->vma_page_prot));
 		if (!pte_map_lock(vmf))
 			return VM_FAULT_RETRY;
 		if (!pte_none(*vmf->pte))
@@ -3021,8 +3022,8 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	 */
 	__SetPageUptodate(page);
 
-	entry = mk_pte(page, vma->vm_page_prot);
-	if (vma->vm_flags & VM_WRITE)
+	entry = mk_pte(page, vmf->vma_page_prot);
+	if (vmf->vma_flags & VM_WRITE)
 		entry = pte_mkwrite(pte_mkdirty(entry));
 
 	if (!pte_map_lock(vmf)) {
@@ -3242,7 +3243,7 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 	for (i = 0; i < HPAGE_PMD_NR; i++)
 		flush_icache_page(vma, page + i);
 
-	entry = mk_huge_pmd(page, vma->vm_page_prot);
+	entry = mk_huge_pmd(page, vmf->vma_page_prot);
 	if (write)
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 
@@ -3318,11 +3319,11 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
 		return VM_FAULT_NOPAGE;
 
 	flush_icache_page(vma, page);
-	entry = mk_pte(page, vma->vm_page_prot);
+	entry = mk_pte(page, vmf->vma_page_prot);
 	if (write)
-		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		entry = maybe_mkwrite(pte_mkdirty(entry), vmf->vma_flags);
 	/* copy-on-write page */
-	if (write && !(vma->vm_flags & VM_SHARED)) {
+	if (write && !(vmf->vma_flags & VM_SHARED)) {
 		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
 		page_add_new_anon_rmap(page, vma, vmf->address, false);
 		mem_cgroup_commit_charge(page, memcg, false, false);
@@ -3362,7 +3363,7 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 
 	/* Did we COW the page? */
 	if ((vmf->flags & FAULT_FLAG_WRITE) &&
-	    !(vmf->vma->vm_flags & VM_SHARED))
+	    !(vmf->vma_flags & VM_SHARED))
 		page = vmf->cow_page;
 	else
 		page = vmf->page;
@@ -3641,7 +3642,7 @@ static vm_fault_t do_fault(struct vm_fault *vmf)
 		}
 	} else if (!(vmf->flags & FAULT_FLAG_WRITE))
 		ret = do_read_fault(vmf);
-	else if (!(vma->vm_flags & VM_SHARED))
+	else if (!(vmf->vma_flags & VM_SHARED))
 		ret = do_cow_fault(vmf);
 	else
 		ret = do_shared_fault(vmf);
@@ -3698,7 +3699,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 	 * accessible ptes, some can allow access by kernel mode.
 	 */
 	old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte);
-	pte = pte_modify(old_pte, vma->vm_page_prot);
+	pte = pte_modify(old_pte, vmf->vma_page_prot);
 	pte = pte_mkyoung(pte);
 	if (was_writable)
 		pte = pte_mkwrite(pte);
@@ -3732,7 +3733,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 	 * Flag if the page is shared between multiple address spaces. This
 	 * is later used when determining whether to group tasks together
 	 */
-	if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED))
+	if (page_mapcount(page) > 1 && (vmf->vma_flags & VM_SHARED))
 		flags |= TNF_SHARED;
 
 	last_cpupid = page_cpupid_last(page);
@@ -3777,7 +3778,7 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
 		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
 
 	/* COW handled on pte level: split pmd */
-	VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma);
+	VM_BUG_ON_VMA(vmf->vma_flags & VM_SHARED, vmf->vma);
 	__split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL);
 
 	return VM_FAULT_FALLBACK;
@@ -3924,6 +3925,8 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 		.flags = flags,
 		.pgoff = linear_page_index(vma, address),
 		.gfp_mask = __get_fault_gfp_mask(vma),
+		.vma_flags = vma->vm_flags,
+		.vma_page_prot = vma->vm_page_prot,
 	};
 	unsigned int dirty = flags & FAULT_FLAG_WRITE;
 	struct mm_struct *mm = vma->vm_mm;
diff --git a/mm/migrate.c b/mm/migrate.c
index f2ecc2855a12..a9138093a8e2 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -240,7 +240,7 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 		 */
 		entry = pte_to_swp_entry(*pvmw.pte);
 		if (is_write_migration_entry(entry))
-			pte = maybe_mkwrite(pte, vma);
+			pte = maybe_mkwrite(pte, vma->vm_flags);
 
 		if (unlikely(is_zone_device_page(new))) {
 			if (is_device_private_page(new)) {
-- 
2.21.0