Merge branch 'akpm' (patches from Andrew)

Mergr misc fixes from Andrew Morton: "28 fixes" * emailed patches from Andrew Morton <[email protected]>: (28 commits) fs/hugetlbfs/inode.c: change put_page/unlock_page order in hugetlbfs_fallocate() mm/hugetlb: fix NULL-pointer dereference on 5-level paging machine autofs: revert "autofs: fix AT_NO_AUTOMOUNT not being honored" autofs: revert "autofs: take more care to not update last_used on path walk" fs/fat/inode.c: fix sb_rdonly() change mm, memcg: fix mem_cgroup_swapout() for THPs mm: migrate: fix an incorrect call of prep_transhuge_page() kmemleak: add scheduling point to kmemleak_scan() scripts/bloat-o-meter: don't fail with division by 0 fs/mbcache.c: make count_objects() more robust Revert "mm/page-writeback.c: print a warning if the vm dirtiness settings are illogical" mm/madvise.c: fix madvise() infinite loop under special circumstances exec: avoid RLIMIT_STACK races with prlimit() IB/core: disable memory registration of filesystem-dax vmas v4l2: disable filesystem-dax mapping support mm: fail get_vaddr_frames() for filesystem-dax mappings mm: introduce get_user_pages_longterm device-dax: implement ->split() to catch invalid munmap attempts mm, hugetlbfs: introduce ->split() to vm_operations_struct scripts/faddr2line: extend usage on generic arch ...
berg · Nov 30, 2017 · a0908a1 · a0908a1
2 parents b915176 + 72639e6
commit a0908a1
Show file tree

Hide file tree

Showing 40 changed files with 238 additions and 101 deletions.
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
@@ -158,10 +158,6 @@ Note: the minimum value allowed for dirty_bytes is two pages (in bytes); any
 value lower than this limit will be ignored and the old configuration will be
 retained.
 
-Note: the value of dirty_bytes also must be set greater than
-dirty_background_bytes or the amount of memory corresponding to
-dirty_background_ratio.
-
 ==============================================================
 
 dirty_expire_centisecs
@@ -181,9 +177,6 @@ generating disk writes will itself start writing out dirty data.
 
 The total available memory is not equal to total system memory.
 
-Note: dirty_ratio must be set greater than dirty_background_ratio or
-ratio corresponding to dirty_background_bytes.
-
 ==============================================================
 
 dirty_writeback_centisecs

diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
@@ -221,7 +221,6 @@ static inline pte_t pte_mkspecial(pte_t pte)
 }
 #define	__HAVE_ARCH_PTE_SPECIAL
 
-#define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		(pmd_isclear((pmd), L_PMD_SECT_RDONLY))
 #define pmd_dirty(pmd)		(pmd_isset((pmd), L_PMD_SECT_DIRTY))
 #define pud_page(pud)		pmd_page(__pmd(pud_val(pud)))

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
@@ -345,7 +345,6 @@ static inline int pmd_protnone(pmd_t pmd)
 
 #define pmd_thp_or_huge(pmd)	(pmd_huge(pmd) || pmd_trans_huge(pmd))
 
-#define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))

diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
@@ -552,7 +552,7 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
 extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		       pmd_t *pmdp, pmd_t pmd);
 
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
 static inline int pmd_write(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & _PAGE_WRITE);

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1005,7 +1005,6 @@ static inline int pmd_protnone(pmd_t pmd)
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
-#define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
 #define __pmd_write(pmd)	__pte_write(pmd_pte(pmd))
 #define pmd_savedwrite(pmd)	pte_savedwrite(pmd_pte(pmd))

diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
@@ -709,7 +709,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
 	return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT;
 }
 
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
 static inline int pmd_write(pmd_t pmd)
 {
 	return (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) != 0;
@@ -1264,6 +1264,12 @@ static inline pud_t pud_mkwrite(pud_t pud)
 	return pud;
 }
 
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+	return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0;
+}
+
 static inline pud_t pud_mkclean(pud_t pud)
 {
 	if (pud_large(pud)) {

diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
@@ -715,7 +715,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
 	return pte_pfn(pte);
 }
 
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
 static inline unsigned long pmd_write(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));

diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
@@ -75,7 +75,7 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 	if (!(pmd_val(pmd) & _PAGE_VALID))
 		return 0;
 
-	if (write && !pmd_write(pmd))
+	if (!pmd_access_permitted(pmd, write))
 		return 0;
 
 	refs = 0;
@@ -114,7 +114,7 @@ static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr,
 	if (!(pud_val(pud) & _PAGE_VALID))
 		return 0;
 
-	if (write && !pud_write(pud))
+	if (!pud_access_permitted(pud, write))
 		return 0;
 
 	refs = 0;

diff --git a/arch/tile/include/asm/pgtable.h b/arch/tile/include/asm/pgtable.h
@@ -475,7 +475,6 @@ static inline void pmd_clear(pmd_t *pmdp)
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_huge_page(pmd)	pte_huge(pmd_pte(pmd))
 #define pmd_mkhuge(pmd)		pte_pmd(pte_mkhuge(pmd_pte(pmd)))
-#define __HAVE_ARCH_PMD_WRITE
 
 #define pfn_pmd(pfn, pgprot)	pte_pmd(pfn_pte((pfn), (pgprot)))
 #define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
@@ -1061,7 +1061,7 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
 				  unsigned long address, pmd_t *pmdp);
 
 
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
 static inline int pmd_write(pmd_t pmd)
 {
 	return pmd_flags(pmd) & _PAGE_RW;
@@ -1088,6 +1088,12 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 	clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
 }
 
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+	return pud_flags(pud) & _PAGE_RW;
+}
+
 /*
  * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
  *

diff --git a/drivers/dax/device.c b/drivers/dax/device.c
@@ -428,9 +428,21 @@ static int dev_dax_fault(struct vm_fault *vmf)
 	return dev_dax_huge_fault(vmf, PE_SIZE_PTE);
 }
 
+static int dev_dax_split(struct vm_area_struct *vma, unsigned long addr)
+{
+	struct file *filp = vma->vm_file;
+	struct dev_dax *dev_dax = filp->private_data;
+	struct dax_region *dax_region = dev_dax->region;
+
+	if (!IS_ALIGNED(addr, dax_region->align))
+		return -EINVAL;
+	return 0;
+}
+
 static const struct vm_operations_struct dax_vm_ops = {
 	.fault = dev_dax_fault,
 	.huge_fault = dev_dax_huge_fault,
+	.split = dev_dax_split,
 };
 
 static int dax_mmap(struct file *filp, struct vm_area_struct *vma)

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
@@ -191,7 +191,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	sg_list_start = umem->sg_head.sgl;
 
 	while (npages) {
-		ret = get_user_pages(cur_base,
+		ret = get_user_pages_longterm(cur_base,
 				     min_t(unsigned long, npages,
 					   PAGE_SIZE / sizeof (struct page *)),
 				     gup_flags, page_list, vma_list);

diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -185,12 +185,13 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
 	dprintk(1, "init user [0x%lx+0x%lx => %d pages]\n",
 		data, size, dma->nr_pages);
 
-	err = get_user_pages(data & PAGE_MASK, dma->nr_pages,
+	err = get_user_pages_longterm(data & PAGE_MASK, dma->nr_pages,
 			     flags, dma->pages, NULL);
 
 	if (err != dma->nr_pages) {
 		dma->nr_pages = (err >= 0) ? err : 0;
-		dprintk(1, "get_user_pages: err=%d [%d]\n", err, dma->nr_pages);
+		dprintk(1, "get_user_pages_longterm: err=%d [%d]\n", err,
+			dma->nr_pages);
 		return err < 0 ? err : -EINVAL;
 	}
 	return 0;

diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
@@ -281,8 +281,8 @@ static int autofs4_mount_wait(const struct path *path, bool rcu_walk)
 		pr_debug("waiting for mount name=%pd\n", path->dentry);
 		status = autofs4_wait(sbi, path, NFY_MOUNT);
 		pr_debug("mount wait done status=%d\n", status);
-		ino->last_used = jiffies;
 	}
+	ino->last_used = jiffies;
 	return status;
 }
 
@@ -321,21 +321,16 @@ static struct dentry *autofs4_mountpoint_changed(struct path *path)
 	 */
 	if (autofs_type_indirect(sbi->type) && d_unhashed(dentry)) {
 		struct dentry *parent = dentry->d_parent;
+		struct autofs_info *ino;
 		struct dentry *new;
 
 		new = d_lookup(parent, &dentry->d_name);
 		if (!new)
 			return NULL;
-		if (new == dentry)
-			dput(new);
-		else {
-			struct autofs_info *ino;
-
-			ino = autofs4_dentry_ino(new);
-			ino->last_used = jiffies;
-			dput(path->dentry);
-			path->dentry = new;
-		}
+		ino = autofs4_dentry_ino(new);
+		ino->last_used = jiffies;
+		dput(path->dentry);
+		path->dentry = new;
 	}
 	return path->dentry;
 }

diff --git a/fs/dax.c b/fs/dax.c
@@ -627,7 +627,8 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
 
 			if (pfn != pmd_pfn(*pmdp))
 				goto unlock_pmd;
-			if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp))
+			if (!pmd_dirty(*pmdp)
+					&& !pmd_access_permitted(*pmdp, WRITE))
 				goto unlock_pmd;
 
 			flush_cache_page(vma, address, pfn);

diff --git a/fs/exec.c b/fs/exec.c
@@ -1340,10 +1340,15 @@ void setup_new_exec(struct linux_binprm * bprm)
 		 * avoid bad behavior from the prior rlimits. This has to
 		 * happen before arch_pick_mmap_layout(), which examines
 		 * RLIMIT_STACK, but after the point of no return to avoid
-		 * needing to clean up the change on failure.
+		 * races from other threads changing the limits. This also
+		 * must be protected from races with prlimit() calls.
 		 */
+		task_lock(current->group_leader);
 		if (current->signal->rlim[RLIMIT_STACK].rlim_cur > _STK_LIM)
 			current->signal->rlim[RLIMIT_STACK].rlim_cur = _STK_LIM;
+		if (current->signal->rlim[RLIMIT_STACK].rlim_max > _STK_LIM)
+			current->signal->rlim[RLIMIT_STACK].rlim_max = _STK_LIM;
+		task_unlock(current->group_leader);
 	}
 
 	arch_pick_mmap_layout(current->mm);

diff --git a/fs/fat/inode.c b/fs/fat/inode.c
@@ -779,7 +779,7 @@ static void __exit fat_destroy_inodecache(void)
 
 static int fat_remount(struct super_block *sb, int *flags, char *data)
 {
-	int new_rdonly;
+	bool new_rdonly;
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
 	*flags |= SB_NODIRATIME | (sbi->options.isvfat ? 0 : SB_NOATIME);
 

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
@@ -639,11 +639,11 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 
 		/*
-		 * page_put due to reference from alloc_huge_page()
 		 * unlock_page because locked by add_to_page_cache()
+		 * page_put due to reference from alloc_huge_page()
 		 */
-		put_page(page);
 		unlock_page(page);
+		put_page(page);
 	}
 
 	if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)

diff --git a/fs/mbcache.c b/fs/mbcache.c
@@ -269,6 +269,9 @@ static unsigned long mb_cache_count(struct shrinker *shrink,
 	struct mb_cache *cache = container_of(shrink, struct mb_cache,
 					      c_shrink);
 
+	/* Unlikely, but not impossible */
+	if (unlikely(cache->c_entry_count < 0))
+		return 0;
 	return cache->c_entry_count;
 }
 

diff --git a/fs/namei.c b/fs/namei.c
@@ -1129,18 +1129,9 @@ static int follow_automount(struct path *path, struct nameidata *nd,
 	 * of the daemon to instantiate them before they can be used.
 	 */
 	if (!(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
-			   LOOKUP_OPEN | LOOKUP_CREATE |
-			   LOOKUP_AUTOMOUNT))) {
-		/* Positive dentry that isn't meant to trigger an
-		 * automount, EISDIR will allow it to be used,
-		 * otherwise there's no mount here "now" so return
-		 * ENOENT.
-		 */
-		if (path->dentry->d_inode)
-			return -EISDIR;
-		else
-			return -ENOENT;
-	}
+			   LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
+	    path->dentry->d_inode)
+		return -EISDIR;
 
 	if (path->dentry->d_sb->s_user_ns != &init_user_ns)
 		return -EACCES;

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
@@ -805,15 +805,23 @@ static inline int pmd_trans_huge(pmd_t pmd)
 {
 	return 0;
 }
-#ifndef __HAVE_ARCH_PMD_WRITE
+#ifndef pmd_write
 static inline int pmd_write(pmd_t pmd)
 {
 	BUG();
 	return 0;
 }
-#endif /* __HAVE_ARCH_PMD_WRITE */
+#endif /* pmd_write */
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+#ifndef pud_write
+static inline int pud_write(pud_t pud)
+{
+	BUG();
+	return 0;
+}
+#endif /* pud_write */
+
 #if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \
 	(defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
 	 !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD))

diff --git a/include/linux/fs.h b/include/linux/fs.h
@@ -3088,7 +3088,8 @@ static inline int vfs_lstat(const char __user *name, struct kstat *stat)
 static inline int vfs_fstatat(int dfd, const char __user *filename,
 			      struct kstat *stat, int flags)
 {
-	return vfs_statx(dfd, filename, flags, stat, STATX_BASIC_STATS);
+	return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT,
+			 stat, STATX_BASIC_STATS);
 }
 static inline int vfs_fstat(int fd, struct kstat *stat)
 {
@@ -3194,6 +3195,20 @@ static inline bool vma_is_dax(struct vm_area_struct *vma)
 	return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
 }
 
+static inline bool vma_is_fsdax(struct vm_area_struct *vma)
+{
+	struct inode *inode;
+
+	if (!vma->vm_file)
+		return false;
+	if (!vma_is_dax(vma))
+		return false;
+	inode = file_inode(vma->vm_file);
+	if (inode->i_mode == S_IFCHR)
+		return false; /* device-dax */
+	return true;
+}
+
 static inline int iocb_flags(struct file *file)
 {
 	int res = 0;

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
@@ -239,14 +239,6 @@ static inline int pgd_write(pgd_t pgd)
 }
 #endif
 
-#ifndef pud_write
-static inline int pud_write(pud_t pud)
-{
-	BUG();
-	return 0;
-}
-#endif
-
 #define HUGETLB_ANON_FILE "anon_hugepage"
 
 enum {

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
@@ -54,7 +54,7 @@ static inline struct page *new_page_nodemask(struct page *page,
 	new_page = __alloc_pages_nodemask(gfp_mask, order,
 				preferred_nid, nodemask);
 
-	if (new_page && PageTransHuge(page))
+	if (new_page && PageTransHuge(new_page))
 		prep_transhuge_page(new_page);
 
 	return new_page;