--- v5
+++ v2
@@ -1,109 +1,96 @@
-The speculative page fault handler which is run without holding the
-mmap_sem is calling lru_cache_add_active_or_unevictable() but the vm_flags
-is not guaranteed to remain constant.
-Introducing __lru_cache_add_active_or_unevictable() which has the vma flags
-value parameter instead of the vma pointer.
+When dealing with the speculative fault path we should use the VMA's field
+cached value stored in the vm_fault structure.
+
+Currently vm_normal_page() is using the pointer to the VMA to fetch the
+vm_flags value. This patch provides a new __vm_normal_page() which is
+receiving the vm_flags flags value as parameter.
+
+Note: The speculative path is turned on for architecture providing support
+for special PTE flag. So only the first block of vm_normal_page is used
+during the speculative path.
Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
---
- include/linux/swap.h | 11 +++++++++--
- mm/memory.c | 8 ++++----
- mm/swap.c | 12 ++++++------
- 3 files changed, 19 insertions(+), 12 deletions(-)
+ mm/memory.c | 25 +++++++++++++++++--------
+ 1 file changed, 17 insertions(+), 8 deletions(-)
-diff --git a/include/linux/swap.h b/include/linux/swap.h
-index cd2f66fdfc2d..a50d64f06bcf 100644
---- a/include/linux/swap.h
-+++ b/include/linux/swap.h
-@@ -324,8 +324,15 @@ extern void swap_setup(void);
+diff --git a/mm/memory.c b/mm/memory.c
+index ad7b6372d302..9f9e5bb7a556 100644
+--- a/mm/memory.c
++++ b/mm/memory.c
+@@ -820,8 +820,9 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
+ #else
+ # define HAVE_PTE_SPECIAL 0
+ #endif
+-struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+- pte_t pte)
++static struct page *__vm_normal_page(struct vm_area_struct *vma,
++ unsigned long addr,
++ pte_t pte, unsigned long vma_flags)
+ {
+ unsigned long pfn = pte_pfn(pte);
- extern void add_page_to_unevictable_list(struct page *page);
+@@ -830,7 +831,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+ goto check_pfn;
+ if (vma->vm_ops && vma->vm_ops->find_special_page)
+ return vma->vm_ops->find_special_page(vma, addr);
+- if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
++ if (vma_flags & (VM_PFNMAP | VM_MIXEDMAP))
+ return NULL;
+ if (!is_zero_pfn(pfn))
+ print_bad_pte(vma, addr, pte, NULL);
+@@ -839,8 +840,8 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
--extern void lru_cache_add_active_or_unevictable(struct page *page,
-- struct vm_area_struct *vma);
-+extern void __lru_cache_add_active_or_unevictable(struct page *page,
-+ unsigned long vma_flags);
-+
-+static inline void lru_cache_add_active_or_unevictable(struct page *page,
-+ struct vm_area_struct *vma)
+ /* !HAVE_PTE_SPECIAL case follows: */
+
+- if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
+- if (vma->vm_flags & VM_MIXEDMAP) {
++ if (unlikely(vma_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
++ if (vma_flags & VM_MIXEDMAP) {
+ if (!pfn_valid(pfn))
+ return NULL;
+ goto out;
+@@ -849,7 +850,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+ off = (addr - vma->vm_start) >> PAGE_SHIFT;
+ if (pfn == vma->vm_pgoff + off)
+ return NULL;
+- if (!is_cow_mapping(vma->vm_flags))
++ if (!is_cow_mapping(vma_flags))
+ return NULL;
+ }
+ }
+@@ -870,6 +871,13 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+ return pfn_to_page(pfn);
+ }
+
++struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
++ pte_t pte)
+{
-+ return __lru_cache_add_active_or_unevictable(page, vma->vm_flags);
++ return __vm_normal_page(vma, addr, pte, vma->vm_flags);
+}
+
++
+ #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
+ pmd_t pmd)
+@@ -2548,7 +2556,8 @@ static int do_wp_page(struct vm_fault *vmf)
+ {
+ struct vm_area_struct *vma = vmf->vma;
- /* linux/mm/vmscan.c */
- extern unsigned long zone_reclaimable_pages(struct zone *zone);
-diff --git a/mm/memory.c b/mm/memory.c
-index 94de8e976c01..5e5b8e3189f2 100644
---- a/mm/memory.c
-+++ b/mm/memory.c
-@@ -2552,7 +2552,7 @@ static int wp_page_copy(struct vm_fault *vmf)
- ptep_clear_flush_notify(vma, vmf->address, vmf->pte);
- page_add_new_anon_rmap(new_page, vma, vmf->address, false);
- mem_cgroup_commit_charge(new_page, memcg, false, false);
-- lru_cache_add_active_or_unevictable(new_page, vma);
-+ __lru_cache_add_active_or_unevictable(new_page, vmf->vma_flags);
+- vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte);
++ vmf->page = __vm_normal_page(vma, vmf->address, vmf->orig_pte,
++ vmf->vma_flags);
+ if (!vmf->page) {
/*
- * We call the notify macro here because, when using secondary
- * mmu page tables (such as kvm shadow page tables), we want the
-@@ -3065,7 +3065,7 @@ int do_swap_page(struct vm_fault *vmf)
- if (unlikely(page != swapcache && swapcache)) {
- page_add_new_anon_rmap(page, vma, vmf->address, false);
- mem_cgroup_commit_charge(page, memcg, false, false);
-- lru_cache_add_active_or_unevictable(page, vma);
-+ __lru_cache_add_active_or_unevictable(page, vmf->vma_flags);
- } else {
- do_page_add_anon_rmap(page, vma, vmf->address, exclusive);
- mem_cgroup_commit_charge(page, memcg, true, false);
-@@ -3215,7 +3215,7 @@ static int do_anonymous_page(struct vm_fault *vmf)
- 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);
-- lru_cache_add_active_or_unevictable(page, vma);
-+ __lru_cache_add_active_or_unevictable(page, vmf->vma_flags);
- setpte:
- set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
+ * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a
+@@ -3575,7 +3584,7 @@ static int do_numa_page(struct vm_fault *vmf)
+ ptep_modify_prot_commit(vma->vm_mm, vmf->address, vmf->pte, pte);
+ update_mmu_cache(vma, vmf->address, vmf->pte);
-@@ -3467,7 +3467,7 @@ int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
- 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);
-- lru_cache_add_active_or_unevictable(page, vma);
-+ __lru_cache_add_active_or_unevictable(page, vmf->vma_flags);
- } else {
- inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
- page_add_file_rmap(page, false);
-diff --git a/mm/swap.c b/mm/swap.c
-index a77d68f2c1b6..30e1b038f9b0 100644
---- a/mm/swap.c
-+++ b/mm/swap.c
-@@ -470,21 +470,21 @@ void add_page_to_unevictable_list(struct page *page)
- }
-
- /**
-- * lru_cache_add_active_or_unevictable
-- * @page: the page to be added to LRU
-- * @vma: vma in which page is mapped for determining reclaimability
-+ * __lru_cache_add_active_or_unevictable
-+ * @page: the page to be added to LRU
-+ * @vma_flags: vma in which page is mapped for determining reclaimability
- *
- * Place @page on the active or unevictable LRU list, depending on its
- * evictability. Note that if the page is not evictable, it goes
- * directly back onto it's zone's unevictable list, it does NOT use a
- * per cpu pagevec.
- */
--void lru_cache_add_active_or_unevictable(struct page *page,
-- struct vm_area_struct *vma)
-+void __lru_cache_add_active_or_unevictable(struct page *page,
-+ unsigned long vma_flags)
- {
- VM_BUG_ON_PAGE(PageLRU(page), page);
-
-- if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) {
-+ if (likely((vma_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) {
- SetPageActive(page);
- lru_cache_add(page);
- return;
+- page = vm_normal_page(vma, vmf->address, pte);
++ page = __vm_normal_page(vma, vmf->address, pte, vmf->vma_flags);
+ if (!page) {
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
+ return 0;
--
2.7.4