Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:

 - a few misc things

 - kexec updates

 - DMA-mapping updates to better support networking DMA operations

 - IPC updates

 - various MM changes to improve DAX fault handling

 - lots of radix-tree changes, mainly to the test suite. All leading up
   to reimplementing the IDA/IDR code to be a wrapper layer over the
   radix-tree. However the final trigger-pulling patch is held off for
   4.11.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (114 commits)
  radix tree test suite: delete unused rcupdate.c
  radix tree test suite: add new tag check
  radix-tree: ensure counts are initialised
  radix tree test suite: cache recently freed objects
  radix tree test suite: add some more functionality
  idr: reduce the number of bits per level from 8 to 6
  rxrpc: abstract away knowledge of IDR internals
  tpm: use idr_find(), not idr_find_slowpath()
  idr: add ida_is_empty
  radix tree test suite: check multiorder iteration
  radix-tree: fix replacement for multiorder entries
  radix-tree: add radix_tree_split_preload()
  radix-tree: add radix_tree_split
  radix-tree: add radix_tree_join
  radix-tree: delete radix_tree_range_tag_if_tagged()
  radix-tree: delete radix_tree_locate_item()
  radix-tree: improve multiorder iterators
  btrfs: fix race in btrfs_free_dummy_fs_info()
  radix-tree: improve dump output
  radix-tree: make radix_tree_find_next_bit more useful
  ...

1 files changed, 17 insertions, 29 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0b5b2e4df14e..4424784ac374 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -292,36 +292,23 @@ extern pgprot_t protection_map[16];
  * pgoff should be used in favour of virtual_address, if possible.
  */
 struct vm_fault {
+        struct vm_area_struct *vma;     /* Target VMA */
         unsigned int flags;             /* FAULT_FLAG_xxx flags */
         gfp_t gfp_mask;                 /* gfp mask to be used for allocations */
         pgoff_t pgoff;                  /* Logical page offset based on vma */
-        void __user *virtual_address;   /* Faulting virtual address */
+        unsigned long address;          /* Faulting virtual address */
+        pmd_t *pmd;                     /* Pointer to pmd entry matching
+                                         * the 'address' */
+        pte_t orig_pte;                 /* Value of PTE at the time of fault */
 
-        struct page *cow_page;          /* Handler may choose to COW */
+        struct page *cow_page;          /* Page handler may use for COW fault */
+        struct mem_cgroup *memcg;       /* Cgroup cow_page belongs to */
         struct page *page;              /* ->fault handlers should return a
                                          * page here, unless VM_FAULT_NOPAGE
                                          * is set (which is also implied by
                                          * VM_FAULT_ERROR).
                                          */
-        void *entry;                    /* ->fault handler can alternatively
-                                         * return locked DAX entry. In that
-                                         * case handler should return
-                                         * VM_FAULT_DAX_LOCKED and fill in
-                                         * entry here.
-                                         */
-};
-
-/*
- * Page fault context: passes though page fault handler instead of endless list
- * of function arguments.
- */
-struct fault_env {
-        struct vm_area_struct *vma;     /* Target VMA */
-        unsigned long address;          /* Faulting virtual address */
-        unsigned int flags;             /* FAULT_FLAG_xxx flags */
-        pmd_t *pmd;                     /* Pointer to pmd entry matching
-                                         * the 'address'
-                                         */
+        /* These three entries are valid only while holding ptl lock */
         pte_t *pte;                     /* Pointer to pte entry matching
                                          * the 'address'. NULL if the page
                                          * table hasn't been allocated.
@@ -351,7 +338,7 @@ struct vm_operations_struct {
         int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
         int (*pmd_fault)(struct vm_area_struct *, unsigned long address,
                                                 pmd_t *, unsigned int flags);
-        void (*map_pages)(struct fault_env *fe,
+        void (*map_pages)(struct vm_fault *vmf,
                         pgoff_t start_pgoff, pgoff_t end_pgoff);
 
         /* notification that a previously read-only page is about to become
@@ -625,8 +612,10 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
         return pte;
 }
 
-int alloc_set_pte(struct fault_env *fe, struct mem_cgroup *memcg,
+int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
                 struct page *page);
+int finish_fault(struct vm_fault *vmf);
+int finish_mkwrite_fault(struct vm_fault *vmf);
 #endif
 
 /*
@@ -1110,7 +1099,7 @@ static inline void clear_page_pfmemalloc(struct page *page)
 #define VM_FAULT_LOCKED 0x0200  /* ->fault locked the returned page */
 #define VM_FAULT_RETRY  0x0400  /* ->fault blocked, must retry */
 #define VM_FAULT_FALLBACK 0x0800        /* huge page fault failed, fall back to small */
-#define VM_FAULT_DAX_LOCKED 0x1000      /* ->fault has locked DAX entry */
+#define VM_FAULT_DONE_COW   0x1000      /* ->fault has fully handled COW */
 
 #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
 
@@ -1221,6 +1210,8 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
                         struct vm_area_struct *vma);
 void unmap_mapping_range(struct address_space *mapping,
                 loff_t const holebegin, loff_t const holelen, int even_cows);
+int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp,
+               spinlock_t **ptlp);
 int follow_pfn(struct vm_area_struct *vma, unsigned long address,
         unsigned long *pfn);
 int follow_phys(struct vm_area_struct *vma, unsigned long address,
@@ -1276,15 +1267,12 @@ extern int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
                             unsigned long start, unsigned long nr_pages,
                             unsigned int gup_flags, struct page **pages,
-                            struct vm_area_struct **vmas);
+                            struct vm_area_struct **vmas, int *locked);
 long get_user_pages(unsigned long start, unsigned long nr_pages,
                             unsigned int gup_flags, struct page **pages,
                             struct vm_area_struct **vmas);
 long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
                     unsigned int gup_flags, struct page **pages, int *locked);
-long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
-                               unsigned long start, unsigned long nr_pages,
-                               struct page **pages, unsigned int gup_flags);
 long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
                     struct page **pages, unsigned int gup_flags);
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
@@ -2099,7 +2087,7 @@ extern void truncate_inode_pages_final(struct address_space *);
 
 /* generic vm_area_ops exported for stackable file systems */
 extern int filemap_fault(struct vm_area_struct *, struct vm_fault *);
-extern void filemap_map_pages(struct fault_env *fe,
+extern void filemap_map_pages(struct vm_fault *vmf,
                 pgoff_t start_pgoff, pgoff_t end_pgoff);
 extern int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);