1 files changed, 125 insertions, 83 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index fbcb3c96a186..07a1d22807be 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -34,6 +34,7 @@
 #include <linux/swap.h>
 #include <linux/uio.h>
 #include <linux/khugepaged.h>
+#include <linux/hugetlb.h>
 
 #include <asm/tlbflush.h> /* for arch/microblaze update_mmu_cache() */
 
@@ -188,6 +189,38 @@ static inline void shmem_unacct_blocks(unsigned long flags, long pages)
 		vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE));
 }
 
+static inline bool shmem_inode_acct_block(struct inode *inode, long pages)
+{
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+
+	if (shmem_acct_block(info->flags, pages))
+		return false;
+
+	if (sbinfo->max_blocks) {
+		if (percpu_counter_compare(&sbinfo->used_blocks,
+					   sbinfo->max_blocks - pages) > 0)
+			goto unacct;
+		percpu_counter_add(&sbinfo->used_blocks, pages);
+	}
+
+	return true;
+
+unacct:
+	shmem_unacct_blocks(info->flags, pages);
+	return false;
+}
+
+static inline void shmem_inode_unacct_blocks(struct inode *inode, long pages)
+{
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+
+	if (sbinfo->max_blocks)
+		percpu_counter_sub(&sbinfo->used_blocks, pages);
+	shmem_unacct_blocks(info->flags, pages);
+}
+
 static const struct super_operations shmem_ops;
 static const struct address_space_operations shmem_aops;
 static const struct file_operations shmem_file_operations;
@@ -249,23 +282,20 @@ static void shmem_recalc_inode(struct inode *inode)
 
 	freed = info->alloced - info->swapped - inode->i_mapping->nrpages;
 	if (freed > 0) {
-		struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
-		if (sbinfo->max_blocks)
-			percpu_counter_add(&sbinfo->used_blocks, -freed);
 		info->alloced -= freed;
 		inode->i_blocks -= freed * BLOCKS_PER_PAGE;
-		shmem_unacct_blocks(info->flags, freed);
+		shmem_inode_unacct_blocks(inode, freed);
 	}
 }
 
 bool shmem_charge(struct inode *inode, long pages)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
-	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
 	unsigned long flags;
 
-	if (shmem_acct_block(info->flags, pages))
+	if (!shmem_inode_acct_block(inode, pages))
 		return false;
+
 	spin_lock_irqsave(&info->lock, flags);
 	info->alloced += pages;
 	inode->i_blocks += pages * BLOCKS_PER_PAGE;
@@ -273,26 +303,12 @@ bool shmem_charge(struct inode *inode, long pages)
 	spin_unlock_irqrestore(&info->lock, flags);
 	inode->i_mapping->nrpages += pages;
 
-	if (!sbinfo->max_blocks)
-		return true;
-	if (percpu_counter_compare(&sbinfo->used_blocks,
-				sbinfo->max_blocks - pages) > 0) {
-		inode->i_mapping->nrpages -= pages;
-		spin_lock_irqsave(&info->lock, flags);
-		info->alloced -= pages;
-		shmem_recalc_inode(inode);
-		spin_unlock_irqrestore(&info->lock, flags);
-		shmem_unacct_blocks(info->flags, pages);
-		return false;
-	}
-	percpu_counter_add(&sbinfo->used_blocks, pages);
 	return true;
 }
 
 void shmem_uncharge(struct inode *inode, long pages)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
-	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
 	unsigned long flags;
 
 	spin_lock_irqsave(&info->lock, flags);
@@ -301,9 +317,7 @@ void shmem_uncharge(struct inode *inode, long pages)
 	shmem_recalc_inode(inode);
 	spin_unlock_irqrestore(&info->lock, flags);
 
-	if (sbinfo->max_blocks)
-		percpu_counter_sub(&sbinfo->used_blocks, pages);
-	shmem_unacct_blocks(info->flags, pages);
+	shmem_inode_unacct_blocks(inode, pages);
 }
 
 /*
@@ -1452,9 +1466,10 @@ static struct page *shmem_alloc_page(gfp_t gfp,
 }
 
 static struct page *shmem_alloc_and_acct_page(gfp_t gfp,
-		struct shmem_inode_info *info, struct shmem_sb_info *sbinfo,
+		struct inode *inode,
 		pgoff_t index, bool huge)
 {
+	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct page *page;
 	int nr;
 	int err = -ENOSPC;
@@ -1463,14 +1478,8 @@ static struct page *shmem_alloc_and_acct_page(gfp_t gfp,
 		huge = false;
 	nr = huge ? HPAGE_PMD_NR : 1;
 
-	if (shmem_acct_block(info->flags, nr))
+	if (!shmem_inode_acct_block(inode, nr))
 		goto failed;
-	if (sbinfo->max_blocks) {
-		if (percpu_counter_compare(&sbinfo->used_blocks,
-					sbinfo->max_blocks - nr) > 0)
-			goto unacct;
-		percpu_counter_add(&sbinfo->used_blocks, nr);
-	}
 
 	if (huge)
 		page = shmem_alloc_hugepage(gfp, info, index);
@@ -1483,10 +1492,7 @@ static struct page *shmem_alloc_and_acct_page(gfp_t gfp,
 	}
 
 	err = -ENOMEM;
-	if (sbinfo->max_blocks)
-		percpu_counter_add(&sbinfo->used_blocks, -nr);
-unacct:
-	shmem_unacct_blocks(info->flags, nr);
+	shmem_inode_unacct_blocks(inode, nr);
 failed:
 	return ERR_PTR(err);
 }
@@ -1644,7 +1650,7 @@ repeat:
 
 	if (swap.val) {
 		/* Look it up and read it in.. */
-		page = lookup_swap_cache(swap);
+		page = lookup_swap_cache(swap, NULL, 0);
 		if (!page) {
 			/* Or update major stats only when swapin succeeds?? */
 			if (fault_type) {
@@ -1751,10 +1757,9 @@ repeat:
 		}
 
 alloc_huge:
-		page = shmem_alloc_and_acct_page(gfp, info, sbinfo,
-				index, true);
+		page = shmem_alloc_and_acct_page(gfp, inode, index, true);
 		if (IS_ERR(page)) {
-alloc_nohuge:		page = shmem_alloc_and_acct_page(gfp, info, sbinfo,
+alloc_nohuge:		page = shmem_alloc_and_acct_page(gfp, inode,
 					index, false);
 		}
 		if (IS_ERR(page)) {
@@ -1876,10 +1881,7 @@ clear:
 	 * Error recovery.
 	 */
 unacct:
-	if (sbinfo->max_blocks)
-		percpu_counter_sub(&sbinfo->used_blocks,
-				1 << compound_order(page));
-	shmem_unacct_blocks(info->flags, 1 << compound_order(page));
+	shmem_inode_unacct_blocks(inode, 1 << compound_order(page));
 
 	if (PageTransHuge(page)) {
 		unlock_page(page);
@@ -2206,16 +2208,16 @@ bool shmem_mapping(struct address_space *mapping)
 	return mapping->a_ops == &shmem_aops;
 }
 
-int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm,
-			   pmd_t *dst_pmd,
-			   struct vm_area_struct *dst_vma,
-			   unsigned long dst_addr,
-			   unsigned long src_addr,
-			   struct page **pagep)
+static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
+				  pmd_t *dst_pmd,
+				  struct vm_area_struct *dst_vma,
+				  unsigned long dst_addr,
+				  unsigned long src_addr,
+				  bool zeropage,
+				  struct page **pagep)
 {
 	struct inode *inode = file_inode(dst_vma->vm_file);
 	struct shmem_inode_info *info = SHMEM_I(inode);
-	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
 	struct address_space *mapping = inode->i_mapping;
 	gfp_t gfp = mapping_gfp_mask(mapping);
 	pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
@@ -2227,33 +2229,30 @@ int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	int ret;
 
 	ret = -ENOMEM;
-	if (shmem_acct_block(info->flags, 1))
+	if (!shmem_inode_acct_block(inode, 1))
 		goto out;
-	if (sbinfo->max_blocks) {
-		if (percpu_counter_compare(&sbinfo->used_blocks,
-					   sbinfo->max_blocks) >= 0)
-			goto out_unacct_blocks;
-		percpu_counter_inc(&sbinfo->used_blocks);
-	}
 
 	if (!*pagep) {
 		page = shmem_alloc_page(gfp, info, pgoff);
 		if (!page)
-			goto out_dec_used_blocks;
-
-		page_kaddr = kmap_atomic(page);
-		ret = copy_from_user(page_kaddr, (const void __user *)src_addr,
-				     PAGE_SIZE);
-		kunmap_atomic(page_kaddr);
-
-		/* fallback to copy_from_user outside mmap_sem */
-		if (unlikely(ret)) {
-			*pagep = page;
-			if (sbinfo->max_blocks)
-				percpu_counter_add(&sbinfo->used_blocks, -1);
-			shmem_unacct_blocks(info->flags, 1);
-			/* don't free the page */
-			return -EFAULT;
+			goto out_unacct_blocks;
+
+		if (!zeropage) {	/* mcopy_atomic */
+			page_kaddr = kmap_atomic(page);
+			ret = copy_from_user(page_kaddr,
+					     (const void __user *)src_addr,
+					     PAGE_SIZE);
+			kunmap_atomic(page_kaddr);
+
+			/* fallback to copy_from_user outside mmap_sem */
+			if (unlikely(ret)) {
+				*pagep = page;
+				shmem_inode_unacct_blocks(inode, 1);
+				/* don't free the page */
+				return -EFAULT;
+			}
+		} else {		/* mfill_zeropage_atomic */
+			clear_highpage(page);
 		}
 	} else {
 		page = *pagep;
@@ -2314,14 +2313,33 @@ out_release_uncharge:
 out_release:
 	unlock_page(page);
 	put_page(page);
-out_dec_used_blocks:
-	if (sbinfo->max_blocks)
-		percpu_counter_add(&sbinfo->used_blocks, -1);
 out_unacct_blocks:
-	shmem_unacct_blocks(info->flags, 1);
+	shmem_inode_unacct_blocks(inode, 1);
 	goto out;
 }
 
+int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm,
+			   pmd_t *dst_pmd,
+			   struct vm_area_struct *dst_vma,
+			   unsigned long dst_addr,
+			   unsigned long src_addr,
+			   struct page **pagep)
+{
+	return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma,
+				      dst_addr, src_addr, false, pagep);
+}
+
+int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm,
+			     pmd_t *dst_pmd,
+			     struct vm_area_struct *dst_vma,
+			     unsigned long dst_addr)
+{
+	struct page *page = NULL;
+
+	return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma,
+				      dst_addr, 0, true, &page);
+}
+
 #ifdef CONFIG_TMPFS
 static const struct inode_operations shmem_symlink_inode_operations;
 static const struct inode_operations shmem_short_symlink_operations;
@@ -3635,7 +3653,7 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root)
 #define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1)
 #define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN)
 
-#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING)
+#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB)
 
 SYSCALL_DEFINE2(memfd_create,
 		const char __user *, uname,
@@ -3647,8 +3665,18 @@ SYSCALL_DEFINE2(memfd_create,
 	char *name;
 	long len;
 
-	if (flags & ~(unsigned int)MFD_ALL_FLAGS)
-		return -EINVAL;
+	if (!(flags & MFD_HUGETLB)) {
+		if (flags & ~(unsigned int)MFD_ALL_FLAGS)
+			return -EINVAL;
+	} else {
+		/* Sealing not supported in hugetlbfs (MFD_HUGETLB) */
+		if (flags & MFD_ALLOW_SEALING)
+			return -EINVAL;
+		/* Allow huge page size encoding in flags. */
+		if (flags & ~(unsigned int)(MFD_ALL_FLAGS |
+				(MFD_HUGE_MASK << MFD_HUGE_SHIFT)))
+			return -EINVAL;
+	}
 
 	/* length includes terminating zero */
 	len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1);
@@ -3657,7 +3685,7 @@ SYSCALL_DEFINE2(memfd_create,
 	if (len > MFD_NAME_MAX_LEN + 1)
 		return -EINVAL;
 
-	name = kmalloc(len + MFD_NAME_PREFIX_LEN, GFP_TEMPORARY);
+	name = kmalloc(len + MFD_NAME_PREFIX_LEN, GFP_KERNEL);
 	if (!name)
 		return -ENOMEM;
 
@@ -3679,16 +3707,30 @@ SYSCALL_DEFINE2(memfd_create,
 		goto err_name;
 	}
 
-	file = shmem_file_setup(name, 0, VM_NORESERVE);
+	if (flags & MFD_HUGETLB) {
+		struct user_struct *user = NULL;
+
+		file = hugetlb_file_setup(name, 0, VM_NORESERVE, &user,
+					HUGETLB_ANONHUGE_INODE,
+					(flags >> MFD_HUGE_SHIFT) &
+					MFD_HUGE_MASK);
+	} else
+		file = shmem_file_setup(name, 0, VM_NORESERVE);
 	if (IS_ERR(file)) {
 		error = PTR_ERR(file);
 		goto err_fd;
 	}
-	info = SHMEM_I(file_inode(file));
 	file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
 	file->f_flags |= O_RDWR | O_LARGEFILE;
-	if (flags & MFD_ALLOW_SEALING)
+
+	if (flags & MFD_ALLOW_SEALING) {
+		/*
+		 * flags check at beginning of function ensures
+		 * this is not a hugetlbfs (MFD_HUGETLB) file.
+		 */
+		info = SHMEM_I(file_inode(file));
 		info->seals &= ~F_SEAL_SEAL;
+	}
 
 	fd_install(fd, file);
 	kfree(name);