22 files changed, 137 insertions, 117 deletions

diff --git a/fs/aio.c b/fs/aio.c
index da887604dfc5..67a6db3e1b6f 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -93,9 +93,8 @@ static void aio_free_ring(struct kioctx *ctx)
                 put_page(info->ring_pages[i]);
 
         if (info->mmap_size) {
-                down_write(&ctx->mm->mmap_sem);
-                do_munmap(ctx->mm, info->mmap_base, info->mmap_size);
-                up_write(&ctx->mm->mmap_sem);
+                BUG_ON(ctx->mm != current->mm);
+                vm_munmap(info->mmap_base, info->mmap_size);
         }
 
         if (info->ring_pages && info->ring_pages != info->internal_pages)
@@ -389,6 +388,17 @@ void exit_aio(struct mm_struct *mm)
                                 "exit_aio:ioctx still alive: %d %d %d\n",
                                 atomic_read(&ctx->users), ctx->dead,
                                 ctx->reqs_active);
+                /*
+                 * We don't need to bother with munmap() here -
+                 * exit_mmap(mm) is coming and it'll unmap everything.
+                 * Since aio_free_ring() uses non-zero ->mmap_size
+                 * as indicator that it needs to unmap the area,
+                 * just set it to 0; aio_free_ring() is the only
+                 * place that uses ->mmap_size, so it's safe.
+                 * That way we get all munmap done to current->mm -
+                 * all other callers have ctx->mm == current->mm.
+                 */
+                ctx->ring_info.mmap_size = 0;
                 put_ioctx(ctx);
         }
 }
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index 2eb12f13593d..d146e181d10d 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -50,9 +50,7 @@ static int set_brk(unsigned long start, unsigned long end)
         end = PAGE_ALIGN(end);
         if (end > start) {
                 unsigned long addr;
-                down_write(&current->mm->mmap_sem);
-                addr = do_brk(start, end - start);
-                up_write(&current->mm->mmap_sem);
+                addr = vm_brk(start, end - start);
                 if (BAD_ADDR(addr))
                         return addr;
         }
@@ -280,9 +278,7 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
                 pos = 32;
                 map_size = ex.a_text+ex.a_data;
 #endif
-                down_write(&current->mm->mmap_sem);
-                error = do_brk(text_addr & PAGE_MASK, map_size);
-                up_write(&current->mm->mmap_sem);
+                error = vm_brk(text_addr & PAGE_MASK, map_size);
                 if (error != (text_addr & PAGE_MASK)) {
                         send_sig(SIGKILL, current, 0);
                         return error;
@@ -313,9 +309,7 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 
                 if (!bprm->file->f_op->mmap||((fd_offset & ~PAGE_MASK) != 0)) {
                         loff_t pos = fd_offset;
-                        down_write(&current->mm->mmap_sem);
-                        do_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
-                        up_write(&current->mm->mmap_sem);
+                        vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
                         bprm->file->f_op->read(bprm->file,
                                         (char __user *)N_TXTADDR(ex),
                                         ex.a_text+ex.a_data, &pos);
@@ -325,24 +319,20 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
                         goto beyond_if;
                 }
 
-                down_write(&current->mm->mmap_sem);
-                error = do_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
+                error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
                         PROT_READ | PROT_EXEC,
                         MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE,
                         fd_offset);
-                up_write(&current->mm->mmap_sem);
 
                 if (error != N_TXTADDR(ex)) {
                         send_sig(SIGKILL, current, 0);
                         return error;
                 }
 
-                down_write(&current->mm->mmap_sem);
-                error = do_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
+                error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
                                 PROT_READ | PROT_WRITE | PROT_EXEC,
                                 MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE,
                                 fd_offset + ex.a_text);
-                up_write(&current->mm->mmap_sem);
                 if (error != N_DATADDR(ex)) {
                         send_sig(SIGKILL, current, 0);
                         return error;
@@ -412,9 +402,7 @@ static int load_aout_library(struct file *file)
                                "N_TXTOFF is not page aligned. Please convert library: %s\n",
                                file->f_path.dentry->d_name.name);
                 }
-                down_write(&current->mm->mmap_sem);
-                do_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
-                up_write(&current->mm->mmap_sem);
+                vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
                 
                 file->f_op->read(file, (char __user *)start_addr,
                         ex.a_text + ex.a_data, &pos);
@@ -425,12 +413,10 @@ static int load_aout_library(struct file *file)
                 goto out;
         }
         /* Now use mmap to map the library into memory. */
-        down_write(&current->mm->mmap_sem);
-        error = do_mmap(file, start_addr, ex.a_text + ex.a_data,
+        error = vm_mmap(file, start_addr, ex.a_text + ex.a_data,
                         PROT_READ | PROT_WRITE | PROT_EXEC,
                         MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE,
                         N_TXTOFF(ex));
-        up_write(&current->mm->mmap_sem);
         retval = error;
         if (error != start_addr)
                 goto out;
@@ -438,9 +424,7 @@ static int load_aout_library(struct file *file)
         len = PAGE_ALIGN(ex.a_text + ex.a_data);
         bss = ex.a_text + ex.a_data + ex.a_bss;
         if (bss > len) {
-                down_write(&current->mm->mmap_sem);
-                error = do_brk(start_addr + len, bss - len);
-                up_write(&current->mm->mmap_sem);
+                error = vm_brk(start_addr + len, bss - len);
                 retval = error;
                 if (error != start_addr + len)
                         goto out;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 48ffb3dc610a..16f735417072 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -82,9 +82,7 @@ static int set_brk(unsigned long start, unsigned long end)
         end = ELF_PAGEALIGN(end);
         if (end > start) {
                 unsigned long addr;
-                down_write(&current->mm->mmap_sem);
-                addr = do_brk(start, end - start);
-                up_write(&current->mm->mmap_sem);
+                addr = vm_brk(start, end - start);
                 if (BAD_ADDR(addr))
                         return addr;
         }
@@ -514,9 +512,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
                 elf_bss = ELF_PAGESTART(elf_bss + ELF_MIN_ALIGN - 1);
 
                 /* Map the last of the bss segment */
-                down_write(&current->mm->mmap_sem);
-                error = do_brk(elf_bss, last_bss - elf_bss);
-                up_write(&current->mm->mmap_sem);
+                error = vm_brk(elf_bss, last_bss - elf_bss);
                 if (BAD_ADDR(error))
                         goto out_close;
         }
@@ -962,10 +958,8 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
                    and some applications "depend" upon this behavior.
                    Since we do not have the power to recompile these, we
                    emulate the SVr4 behavior. Sigh. */
-                down_write(&current->mm->mmap_sem);
-                error = do_mmap(NULL, 0, PAGE_SIZE, PROT_READ | PROT_EXEC,
+                error = vm_mmap(NULL, 0, PAGE_SIZE, PROT_READ | PROT_EXEC,
                                 MAP_FIXED | MAP_PRIVATE, 0);
-                up_write(&current->mm->mmap_sem);
         }
 
 #ifdef ELF_PLAT_INIT
@@ -1050,8 +1044,7 @@ static int load_elf_library(struct file *file)
                 eppnt++;
 
         /* Now use mmap to map the library into memory. */
-        down_write(&current->mm->mmap_sem);
-        error = do_mmap(file,
+        error = vm_mmap(file,
                         ELF_PAGESTART(eppnt->p_vaddr),
                         (eppnt->p_filesz +
                          ELF_PAGEOFFSET(eppnt->p_vaddr)),
@@ -1059,7 +1052,6 @@ static int load_elf_library(struct file *file)
                         MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE,
                         (eppnt->p_offset -
                          ELF_PAGEOFFSET(eppnt->p_vaddr)));
-        up_write(&current->mm->mmap_sem);
         if (error != ELF_PAGESTART(eppnt->p_vaddr))
                 goto out_free_ph;
 
@@ -1072,11 +1064,8 @@ static int load_elf_library(struct file *file)
         len = ELF_PAGESTART(eppnt->p_filesz + eppnt->p_vaddr +
                             ELF_MIN_ALIGN - 1);
         bss = eppnt->p_memsz + eppnt->p_vaddr;
-        if (bss > len) {
-                down_write(&current->mm->mmap_sem);
-                do_brk(len, bss - len);
-                up_write(&current->mm->mmap_sem);
-        }
+        if (bss > len)
+                vm_brk(len, bss - len);
         error = 0;
 
 out_free_ph:
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 9bd5612a8224..d390a0fffc65 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -390,21 +390,17 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
             (executable_stack == EXSTACK_DEFAULT && VM_STACK_FLAGS & VM_EXEC))
                 stack_prot |= PROT_EXEC;
 
-        down_write(&current->mm->mmap_sem);
-        current->mm->start_brk = do_mmap(NULL, 0, stack_size, stack_prot,
+        current->mm->start_brk = vm_mmap(NULL, 0, stack_size, stack_prot,
                                          MAP_PRIVATE | MAP_ANONYMOUS |
                                          MAP_UNINITIALIZED | MAP_GROWSDOWN,
                                          0);
 
         if (IS_ERR_VALUE(current->mm->start_brk)) {
-                up_write(&current->mm->mmap_sem);
                 retval = current->mm->start_brk;
                 current->mm->start_brk = 0;
                 goto error_kill;
         }
 
-        up_write(&current->mm->mmap_sem);
-
         current->mm->brk = current->mm->start_brk;
         current->mm->context.end_brk = current->mm->start_brk;
         current->mm->context.end_brk +=
@@ -955,10 +951,8 @@ static int elf_fdpic_map_file_constdisp_on_uclinux(
         if (params->flags & ELF_FDPIC_FLAG_EXECUTABLE)
                 mflags |= MAP_EXECUTABLE;
 
-        down_write(&mm->mmap_sem);
-        maddr = do_mmap(NULL, load_addr, top - base,
+        maddr = vm_mmap(NULL, load_addr, top - base,
                         PROT_READ | PROT_WRITE | PROT_EXEC, mflags, 0);
-        up_write(&mm->mmap_sem);
         if (IS_ERR_VALUE(maddr))
                 return (int) maddr;
 
@@ -1096,10 +1090,8 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params,
 
                 /* create the mapping */
                 disp = phdr->p_vaddr & ~PAGE_MASK;
-                down_write(&mm->mmap_sem);
-                maddr = do_mmap(file, maddr, phdr->p_memsz + disp, prot, flags,
+                maddr = vm_mmap(file, maddr, phdr->p_memsz + disp, prot, flags,
                                 phdr->p_offset - disp);
-                up_write(&mm->mmap_sem);
 
                 kdebug("mmap[%d] <file> sz=%lx pr=%x fl=%x of=%lx --> %08lx",
                        loop, phdr->p_memsz + disp, prot, flags,
@@ -1143,10 +1135,8 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params,
                         unsigned long xmaddr;
 
                         flags |= MAP_FIXED | MAP_ANONYMOUS;
-                        down_write(&mm->mmap_sem);
-                        xmaddr = do_mmap(NULL, xaddr, excess - excess1,
+                        xmaddr = vm_mmap(NULL, xaddr, excess - excess1,
                                          prot, flags, 0);
-                        up_write(&mm->mmap_sem);
 
                         kdebug("mmap[%d] <anon>"
                                " ad=%lx sz=%lx pr=%x fl=%x of=0 --> %08lx",
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 024d20ee3ca3..6b2daf99fab8 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -542,10 +542,8 @@ static int load_flat_file(struct linux_binprm * bprm,
                  */
                 DBG_FLT("BINFMT_FLAT: ROM mapping of file (we hope)\n");
 
-                down_write(&current->mm->mmap_sem);
-                textpos = do_mmap(bprm->file, 0, text_len, PROT_READ|PROT_EXEC,
+                textpos = vm_mmap(bprm->file, 0, text_len, PROT_READ|PROT_EXEC,
                                   MAP_PRIVATE|MAP_EXECUTABLE, 0);
-                up_write(&current->mm->mmap_sem);
                 if (!textpos || IS_ERR_VALUE(textpos)) {
                         if (!textpos)
                                 textpos = (unsigned long) -ENOMEM;
@@ -556,10 +554,8 @@ static int load_flat_file(struct linux_binprm * bprm,
 
                 len = data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long);
                 len = PAGE_ALIGN(len);
-                down_write(&current->mm->mmap_sem);
-                realdatastart = do_mmap(0, 0, len,
+                realdatastart = vm_mmap(0, 0, len,
                         PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, 0);
-                up_write(&current->mm->mmap_sem);
 
                 if (realdatastart == 0 || IS_ERR_VALUE(realdatastart)) {
                         if (!realdatastart)
@@ -603,10 +599,8 @@ static int load_flat_file(struct linux_binprm * bprm,
 
                 len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long);
                 len = PAGE_ALIGN(len);
-                down_write(&current->mm->mmap_sem);
-                textpos = do_mmap(0, 0, len,
+                textpos = vm_mmap(0, 0, len,
                         PROT_READ | PROT_EXEC | PROT_WRITE, MAP_PRIVATE, 0);
-                up_write(&current->mm->mmap_sem);
 
                 if (!textpos || IS_ERR_VALUE(textpos)) {
                         if (!textpos)
diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c
index e4fc746629a7..4517aaff61b4 100644
--- a/fs/binfmt_som.c
+++ b/fs/binfmt_som.c
@@ -147,10 +147,8 @@ static int map_som_binary(struct file *file,
         code_size = SOM_PAGEALIGN(hpuxhdr->exec_tsize);
         current->mm->start_code = code_start;
         current->mm->end_code = code_start + code_size;
-        down_write(&current->mm->mmap_sem);
-        retval = do_mmap(file, code_start, code_size, prot,
+        retval = vm_mmap(file, code_start, code_size, prot,
                         flags, SOM_PAGESTART(hpuxhdr->exec_tfile));
-        up_write(&current->mm->mmap_sem);
         if (retval < 0 && retval > -1024)
                 goto out;
 
@@ -158,20 +156,16 @@ static int map_som_binary(struct file *file,
         data_size = SOM_PAGEALIGN(hpuxhdr->exec_dsize);
         current->mm->start_data = data_start;
         current->mm->end_data = bss_start = data_start + data_size;
-        down_write(&current->mm->mmap_sem);
-        retval = do_mmap(file, data_start, data_size,
+        retval = vm_mmap(file, data_start, data_size,
                         prot | PROT_WRITE, flags,
                         SOM_PAGESTART(hpuxhdr->exec_dfile));
-        up_write(&current->mm->mmap_sem);
         if (retval < 0 && retval > -1024)
                 goto out;
 
         som_brk = bss_start + SOM_PAGEALIGN(hpuxhdr->exec_bsize);
         current->mm->start_brk = current->mm->brk = som_brk;
-        down_write(&current->mm->mmap_sem);
-        retval = do_mmap(NULL, bss_start, som_brk - bss_start,
+        retval = vm_mmap(NULL, bss_start, som_brk - bss_start,
                         prot | PROT_WRITE, MAP_FIXED | MAP_PRIVATE, 0);
-        up_write(&current->mm->mmap_sem);
         if (retval > 0 || retval < -1024)
                 retval = 0;
 out:
diff --git a/fs/buffer.c b/fs/buffer.c
index 36d66653b931..351e18ea2e53 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -985,7 +985,6 @@ grow_dev_page(struct block_device *bdev, sector_t block,
         return page;
 
 failed:
-        BUG();
         unlock_page(page);
         page_cache_release(page);
         return NULL;
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index fa5c07d51dcc..4c58d4a3adc4 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -1737,6 +1737,18 @@ static int _can_be_granted(struct dlm_rsb *r, struct dlm_lkb *lkb, int now)
                 return 1;
 
         /*
+         * Even if the convert is compat with all granted locks,
+         * QUECVT forces it behind other locks on the convert queue.
+         */
+
+        if (now && conv && (lkb->lkb_exflags & DLM_LKF_QUECVT)) {
+                if (list_empty(&r->res_convertqueue))
+                        return 1;
+                else
+                        goto out;
+        }
+
+        /*
          * The NOORDER flag is set to avoid the standard vms rules on grant
          * order.
          */
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 739b0985b398..c0b3c70ee87a 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1663,8 +1663,10 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
         if (op == EPOLL_CTL_ADD) {
                 if (is_file_epoll(tfile)) {
                         error = -ELOOP;
-                        if (ep_loop_check(ep, tfile) != 0)
+                        if (ep_loop_check(ep, tfile) != 0) {
+                                clear_tfile_check_list();
                                 goto error_tgt_fput;
+                        }
                 } else
                         list_add(&tfile->f_tfile_llink, &tfile_check_list);
         }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6da193564e43..e1fb1d5de58e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1597,7 +1597,9 @@ static int parse_options(char *options, struct super_block *sb,
                          unsigned int *journal_ioprio,
                          int is_remount)
 {
+#ifdef CONFIG_QUOTA
         struct ext4_sb_info *sbi = EXT4_SB(sb);
+#endif
         char *p;
         substring_t args[MAX_OPT_ARGS];
         int token;
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index f8411bd1b805..5f5e70e047dc 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -200,10 +200,11 @@ static int make_mode(const unsigned int lmstate)
         return -1;
 }
 
-static u32 make_flags(const u32 lkid, const unsigned int gfs_flags,
+static u32 make_flags(struct gfs2_glock *gl, const unsigned int gfs_flags,
                       const int req)
 {
         u32 lkf = DLM_LKF_VALBLK;
+        u32 lkid = gl->gl_lksb.sb_lkid;
 
         if (gfs_flags & LM_FLAG_TRY)
                 lkf |= DLM_LKF_NOQUEUE;
@@ -227,8 +228,11 @@ static u32 make_flags(const u32 lkid, const unsigned int gfs_flags,
                         BUG();
         }
 
-        if (lkid != 0) 
+        if (lkid != 0) {
                 lkf |= DLM_LKF_CONVERT;
+                if (test_bit(GLF_BLOCKING, &gl->gl_flags))
+                        lkf |= DLM_LKF_QUECVT;
+        }
 
         return lkf;
 }
@@ -250,7 +254,7 @@ static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state,
         char strname[GDLM_STRNAME_BYTES] = "";
 
         req = make_mode(req_state);
-        lkf = make_flags(gl->gl_lksb.sb_lkid, flags, req);
+        lkf = make_flags(gl, flags, req);
         gfs2_glstats_inc(gl, GFS2_LKS_DCOUNT);
         gfs2_sbstats_inc(gl, GFS2_LKS_DCOUNT);
         if (gl->gl_lksb.sb_lkid) {
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 28cf06e4ec84..001ef01d2fe2 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -485,6 +485,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
                 inode->i_fop = &simple_dir_operations;
                 /* directory inodes start off with i_nlink == 2 (for "." entry) */
                 inc_nlink(inode);
+                lockdep_annotate_inode_mutex_key(inode);
         }
         return inode;
 }
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 806525a7269c..840f70f50792 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -723,7 +723,7 @@ start_journal_io:
         if (commit_transaction->t_need_data_flush &&
             (journal->j_fs_dev != journal->j_dev) &&
             (journal->j_flags & JBD2_BARRIER))
-                blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
+                blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS, NULL);
 
         /* Done it all: now write the commit record asynchronously. */
         if (JBD2_HAS_INCOMPAT_FEATURE(journal,
@@ -859,7 +859,7 @@ wait_for_iobuf:
         if (JBD2_HAS_INCOMPAT_FEATURE(journal,
                                       JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) &&
             journal->j_flags & JBD2_BARRIER) {
-                blkdev_issue_flush(journal->j_dev, GFP_KERNEL, NULL);
+                blkdev_issue_flush(journal->j_dev, GFP_NOFS, NULL);
         }
 
         if (err)
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 4aaf0316d76a..8789210c6905 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1429,7 +1429,7 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
         }
 
         open_flags = nd->intent.open.flags;
-        attr.ia_valid = 0;
+        attr.ia_valid = ATTR_OPEN;
 
         ctx = create_nfs_open_context(dentry, open_flags);
         res = ERR_CAST(ctx);
@@ -1536,7 +1536,7 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
         if (IS_ERR(ctx))
                 goto out;
 
-        attr.ia_valid = 0;
+        attr.ia_valid = ATTR_OPEN;
         if (openflags & O_TRUNC) {
                 attr.ia_valid |= ATTR_SIZE;
                 attr.ia_size = 0;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 97ecc863dd76..b6db9e33fb7b 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -59,6 +59,7 @@ struct nfs_unique_id {
 
 #define NFS_SEQID_CONFIRMED 1
 struct nfs_seqid_counter {
+        ktime_t create_time;
         int owner_id;
         int flags;
         u32 counter;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f82bde005a82..60d5f4c26dda 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -838,7 +838,8 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
         p->o_arg.open_flags = flags;
         p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE);
         p->o_arg.clientid = server->nfs_client->cl_clientid;
-        p->o_arg.id = sp->so_seqid.owner_id;
+        p->o_arg.id.create_time = ktime_to_ns(sp->so_seqid.create_time);
+        p->o_arg.id.uniquifier = sp->so_seqid.owner_id;
         p->o_arg.name = &dentry->d_name;
         p->o_arg.server = server;
         p->o_arg.bitmask = server->attr_bitmask;
@@ -1466,8 +1467,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
                         goto unlock_no_action;
                 rcu_read_unlock();
         }
-        /* Update sequence id. */
-        data->o_arg.id = sp->so_seqid.owner_id;
+        /* Update client id. */
         data->o_arg.clientid = sp->so_server->nfs_client->cl_clientid;
         if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS) {
                 task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR];
@@ -1954,10 +1954,19 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
         };
         int err;
         do {
-                err = nfs4_handle_exception(server,
-                                _nfs4_do_setattr(inode, cred, fattr, sattr, state),
-                                &exception);
+                err = _nfs4_do_setattr(inode, cred, fattr, sattr, state);
+                switch (err) {
+                case -NFS4ERR_OPENMODE:
+                        if (state && !(state->state & FMODE_WRITE)) {
+                                err = -EBADF;
+                                if (sattr->ia_valid & ATTR_OPEN)
+                                        err = -EACCES;
+                                goto out;
+                        }
+                }
+                err = nfs4_handle_exception(server, err, &exception);
         } while (exception.retry);
+out:
         return err;
 }
 
@@ -4558,7 +4567,9 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request)
 {
         struct nfs_server *server = NFS_SERVER(state->inode);
-        struct nfs4_exception exception = { };
+        struct nfs4_exception exception = {
+                .inode = state->inode,
+        };
         int err;
 
         do {
@@ -4576,7 +4587,9 @@ static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request
 static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request)
 {
         struct nfs_server *server = NFS_SERVER(state->inode);
-        struct nfs4_exception exception = { };
+        struct nfs4_exception exception = {
+                .inode = state->inode,
+        };
         int err;
 
         err = nfs4_set_lock_state(state, request);
@@ -4676,6 +4689,7 @@ static int nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *
 {
         struct nfs4_exception exception = {
                 .state = state,
+                .inode = state->inode,
         };
         int err;
 
@@ -4721,6 +4735,20 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
 
         if (state == NULL)
                 return -ENOLCK;
+        /*
+         * Don't rely on the VFS having checked the file open mode,
+         * since it won't do this for flock() locks.
+         */
+        switch (request->fl_type & (F_RDLCK|F_WRLCK|F_UNLCK)) {
+        case F_RDLCK:
+                if (!(filp->f_mode & FMODE_READ))
+                        return -EBADF;
+                break;
+        case F_WRLCK:
+                if (!(filp->f_mode & FMODE_WRITE))
+                        return -EBADF;
+        }
+
         do {
                 status = nfs4_proc_setlk(state, cmd, request);
                 if ((status != -EAGAIN) || IS_SETLK(cmd))
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 0f43414eb25a..7f0fcfc1fe9d 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -393,6 +393,7 @@ nfs4_remove_state_owner_locked(struct nfs4_state_owner *sp)
 static void
 nfs4_init_seqid_counter(struct nfs_seqid_counter *sc)
 {
+        sc->create_time = ktime_get();
         sc->flags = 0;
         sc->counter = 0;
         spin_lock_init(&sc->lock);
@@ -434,13 +435,17 @@ nfs4_alloc_state_owner(struct nfs_server *server,
 static void
 nfs4_drop_state_owner(struct nfs4_state_owner *sp)
 {
-        if (!RB_EMPTY_NODE(&sp->so_server_node)) {
+        struct rb_node *rb_node = &sp->so_server_node;
+
+        if (!RB_EMPTY_NODE(rb_node)) {
                 struct nfs_server *server = sp->so_server;
                 struct nfs_client *clp = server->nfs_client;
 
                 spin_lock(&clp->cl_lock);
-                rb_erase(&sp->so_server_node, &server->state_owners);
-                RB_CLEAR_NODE(&sp->so_server_node);
+                if (!RB_EMPTY_NODE(rb_node)) {
+                        rb_erase(rb_node, &server->state_owners);
+                        RB_CLEAR_NODE(rb_node);
+                }
                 spin_unlock(&clp->cl_lock);
         }
 }
@@ -516,6 +521,14 @@ out:
 /**
  * nfs4_put_state_owner - Release a nfs4_state_owner
  * @sp: state owner data to release
+ *
+ * Note that we keep released state owners on an LRU
+ * list.
+ * This caches valid state owners so that they can be
+ * reused, to avoid the OPEN_CONFIRM on minor version 0.
+ * It also pins the uniquifier of dropped state owners for
+ * a while, to ensure that those state owner names are
+ * never reused.
  */
 void nfs4_put_state_owner(struct nfs4_state_owner *sp)
 {
@@ -525,15 +538,9 @@ void nfs4_put_state_owner(struct nfs4_state_owner *sp)
         if (!atomic_dec_and_lock(&sp->so_count, &clp->cl_lock))
                 return;
 
-        if (!RB_EMPTY_NODE(&sp->so_server_node)) {
-                sp->so_expires = jiffies;
-                list_add_tail(&sp->so_lru, &server->state_owners_lru);
-                spin_unlock(&clp->cl_lock);
-        } else {
-                nfs4_remove_state_owner_locked(sp);
-                spin_unlock(&clp->cl_lock);
-                nfs4_free_state_owner(sp);
-        }
+        sp->so_expires = jiffies;
+        list_add_tail(&sp->so_lru, &server->state_owners_lru);
+        spin_unlock(&clp->cl_lock);
 }
 
 /**
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index c74fdb114b48..77fc5f959c4e 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -74,7 +74,7 @@ static int nfs4_stat_to_errno(int);
 /* lock,open owner id:
  * we currently use size 2 (u64) out of (NFS4_OPAQUE_LIMIT  >> 2)
  */
-#define open_owner_id_maxsz     (1 + 1 + 4)
+#define open_owner_id_maxsz     (1 + 2 + 1 + 1 + 2)
 #define lock_owner_id_maxsz     (1 + 1 + 4)
 #define decode_lockowner_maxsz  (1 + XDR_QUADLEN(IDMAP_NAMESZ))
 #define compound_encode_hdr_maxsz       (3 + (NFS4_MAXTAGLEN >> 2))
@@ -1340,12 +1340,13 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena
  */
         encode_nfs4_seqid(xdr, arg->seqid);
         encode_share_access(xdr, arg->fmode);
-        p = reserve_space(xdr, 32);
+        p = reserve_space(xdr, 36);
         p = xdr_encode_hyper(p, arg->clientid);
-        *p++ = cpu_to_be32(20);
+        *p++ = cpu_to_be32(24);
         p = xdr_encode_opaque_fixed(p, "open id:", 8);
         *p++ = cpu_to_be32(arg->server->s_dev);
-        xdr_encode_hyper(p, arg->id);
+        *p++ = cpu_to_be32(arg->id.uniquifier);
+        xdr_encode_hyper(p, arg->id.create_time);
 }
 
 static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_openargs *arg)
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 9a0e8ef4a409..0a4be28c2ea3 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -322,7 +322,7 @@ out_bad:
         while (!list_empty(res)) {
                 data = list_entry(res->next, struct nfs_read_data, list);
                 list_del(&data->list);
-                nfs_readdata_free(data);
+                nfs_readdata_release(data);
         }
         nfs_readpage_release(req);
         return -ENOMEM;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 37412f706b32..1e6715f0616c 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2767,11 +2767,15 @@ static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type,
         char *root_devname;
         size_t len;
 
-        len = strlen(hostname) + 3;
+        len = strlen(hostname) + 5;
         root_devname = kmalloc(len, GFP_KERNEL);
         if (root_devname == NULL)
                 return ERR_PTR(-ENOMEM);
-        snprintf(root_devname, len, "%s:/", hostname);
+        /* Does hostname needs to be enclosed in brackets? */
+        if (strchr(hostname, ':'))
+                snprintf(root_devname, len, "[%s]:/", hostname);
+        else
+                snprintf(root_devname, len, "%s:/", hostname);
         root_mnt = vfs_kern_mount(fs_type, flags, root_devname, data);
         kfree(root_devname);
         return root_mnt;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 2c68818f68ac..c07462320f6b 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -682,7 +682,8 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
                 req->wb_bytes = rqend - req->wb_offset;
 out_unlock:
         spin_unlock(&inode->i_lock);
-        nfs_clear_request_commit(req);
+        if (req)
+                nfs_clear_request_commit(req);
         return req;
 out_flushme:
         spin_unlock(&inode->i_lock);
@@ -1018,7 +1019,7 @@ out_bad:
         while (!list_empty(res)) {
                 data = list_entry(res->next, struct nfs_write_data, list);
                 list_del(&data->list);
-                nfs_writedata_free(data);
+                nfs_writedata_release(data);
         }
         nfs_redirty_request(req);
         return -ENOMEM;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 2b9a7607cbd5..2d60492d6df8 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -597,9 +597,6 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
                 if (!page)
                         continue;
 
-                if (PageReserved(page))
-                        continue;
-
                 /* Clear accessed and referenced bits. */
                 ptep_test_and_clear_young(vma, addr, pte);
                 ClearPageReferenced(page);