Merge tag 'xfs-for-linus-v3.12-rc1' of git://oss.sgi.com/xfs/xfs

Pull xfs updates from Ben Myers:
 "For 3.12-rc1 there are a number of bugfixes in addition to work to
  ease usage of shared code between libxfs and the kernel, the rest of
  the work to enable project and group quotas to be used simultaneously,
  performance optimisations in the log and the CIL, directory entry file
  type support, fixes for log space reservations, some spelling/grammar
  cleanups, and the addition of user namespace support.

   - introduce readahead to log recovery
   - add directory entry file type support
   - fix a number of spelling errors in comments
   - introduce new Q_XGETQSTATV quotactl for project quotas
   - add USER_NS support
   - log space reservation rework
   - CIL optimisations
  - kernel/userspace libxfs rework"

* tag 'xfs-for-linus-v3.12-rc1' of git://oss.sgi.com/xfs/xfs: (112 commits)
  xfs: XFS_MOUNT_QUOTA_ALL needed by userspace
  xfs: dtype changed xfs_dir2_sfe_put_ino to xfs_dir3_sfe_put_ino
  Fix wrong flag ASSERT in xfs_attr_shortform_getvalue
  xfs: finish removing IOP_* macros.
  xfs: inode log reservations are too small
  xfs: check correct status variable for xfs_inobt_get_rec() call
  xfs: inode buffers may not be valid during recovery readahead
  xfs: check LSN ordering for v5 superblocks during recovery
  xfs: btree block LSN escaping to disk uninitialised
  XFS: Assertion failed: first <= last && last < BBTOB(bp->b_length), file: fs/xfs/xfs_trans_buf.c, line: 568
  xfs: fix bad dquot buffer size in log recovery readahead
  xfs: don't account buffer cancellation during log recovery readahead
  xfs: check for underflow in xfs_iformat_fork()
  xfs: xfs_dir3_sfe_put_ino can be static
  xfs: introduce object readahead to log recovery
  xfs: Simplify xfs_ail_min() with list_first_entry_or_null()
  xfs: Register hotcpu notifier after initialization
  xfs: add xfs sb v4 support for dirent filetype field
  xfs: Add write support for dirent filetype field
  xfs: Add read-only support for dirent filetype field
  ...

Author: torvalds

arch/powerpc/platforms/cell/spufs/inode.c

@@ -620,12 +620,16 @@ spufs_parse_options(struct super_block *sb, char *options, struct inode *root)
 		case Opt_uid:
 			if (match_int(&args[0], &option))
 				return 0;
-			root->i_uid = option;
+			root->i_uid = make_kuid(current_user_ns(), option);
+			if (!uid_valid(root->i_uid))
+				return 0;
 			break;
 		case Opt_gid:
 			if (match_int(&args[0], &option))
 				return 0;
-			root->i_gid = option;
+			root->i_gid = make_kgid(current_user_ns(), option);
+			if (!gid_valid(root->i_gid))
+				return 0;
 			break;
 		case Opt_mode:
 			if (match_octal(&args[0], &option))

fs/quota/quota.c

@@ -27,6 +27,7 @@ static int check_quotactl_permission(struct super_block *sb, int type, int cmd,
 	case Q_SYNC:
 	case Q_GETINFO:
 	case Q_XGETQSTAT:
+	case Q_XGETQSTATV:
 	case Q_XQUOTASYNC:
 		break;
 	/* allow to query information for dquots we "own" */
@@ -217,6 +218,31 @@ static int quota_getxstate(struct super_block *sb, void __user *addr)
 	return ret;
 }
 
+static int quota_getxstatev(struct super_block *sb, void __user *addr)
+{
+	struct fs_quota_statv fqs;
+	int ret;
+
+	if (!sb->s_qcop->get_xstatev)
+		return -ENOSYS;
+
+	memset(&fqs, 0, sizeof(fqs));
+	if (copy_from_user(&fqs, addr, 1)) /* Just read qs_version */
+		return -EFAULT;
+
+	/* If this kernel doesn't support user specified version, fail */
+	switch (fqs.qs_version) {
+	case FS_QSTATV_VERSION1:
+		break;
+	default:
+		return -EINVAL;
+	}
+	ret = sb->s_qcop->get_xstatev(sb, &fqs);
+	if (!ret && copy_to_user(addr, &fqs, sizeof(fqs)))
+		return -EFAULT;
+	return ret;
+}
+
 static int quota_setxquota(struct super_block *sb, int type, qid_t id,
 			   void __user *addr)
 {
@@ -293,6 +319,8 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 		return quota_setxstate(sb, cmd, addr);
 	case Q_XGETQSTAT:
 		return quota_getxstate(sb, addr);
+	case Q_XGETQSTATV:
+		return quota_getxstatev(sb, addr);
 	case Q_XSETQLIM:
 		return quota_setxquota(sb, type, id, addr);
 	case Q_XGETQUOTA:
@@ -317,6 +345,7 @@ static int quotactl_cmd_write(int cmd)
 	case Q_GETINFO:
 	case Q_SYNC:
 	case Q_XGETQSTAT:
+	case Q_XGETQSTATV:
 	case Q_XGETQUOTA:
 	case Q_XQUOTASYNC:
 		return 0;

fs/xfs/Makefile

@@ -27,9 +27,12 @@ xfs-y				+= xfs_trace.o
 
 # highlevel code
 xfs-y				+= xfs_aops.o \
+				   xfs_attr_inactive.o \
+				   xfs_attr_list.o \
 				   xfs_bit.o \
+				   xfs_bmap_util.o \
 				   xfs_buf.o \
-				   xfs_dfrag.o \
+				   xfs_dir2_readdir.o \
 				   xfs_discard.o \
 				   xfs_error.o \
 				   xfs_export.o \
@@ -44,11 +47,11 @@ xfs-y				+= xfs_aops.o \
 				   xfs_iops.o \
 				   xfs_itable.o \
 				   xfs_message.o \
+				   xfs_mount.o \
 				   xfs_mru_cache.o \
-				   xfs_rename.o \
 				   xfs_super.o \
-				   xfs_utils.o \
-				   xfs_vnodeops.o \
+				   xfs_symlink.o \
+				   xfs_trans.o \
 				   xfs_xattr.o \
 				   kmem.o \
 				   uuid.o
@@ -73,10 +76,13 @@ xfs-y				+= xfs_alloc.o \
 				   xfs_ialloc_btree.o \
 				   xfs_icreate_item.o \
 				   xfs_inode.o \
+				   xfs_inode_fork.o \
+				   xfs_inode_buf.o \
 				   xfs_log_recover.o \
-				   xfs_mount.o \
-				   xfs_symlink.o \
-				   xfs_trans.o
+				   xfs_log_rlimit.o \
+				   xfs_sb.o \
+				   xfs_symlink_remote.o \
+				   xfs_trans_resv.o
 
 # low-level transaction/log code
 xfs-y				+= xfs_log.o \

fs/xfs/xfs_acl.c

@@ -16,11 +16,13 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include "xfs.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_acl.h"
 #include "xfs_attr.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_inode.h"
-#include "xfs_vnodeops.h"
+#include "xfs_ag.h"
 #include "xfs_sb.h"
 #include "xfs_mount.h"
 #include "xfs_trace.h"
@@ -68,14 +70,15 @@ xfs_acl_from_disk(
 
 		switch (acl_e->e_tag) {
 		case ACL_USER:
+			acl_e->e_uid = xfs_uid_to_kuid(be32_to_cpu(ace->ae_id));
+			break;
 		case ACL_GROUP:
-			acl_e->e_id = be32_to_cpu(ace->ae_id);
+			acl_e->e_gid = xfs_gid_to_kgid(be32_to_cpu(ace->ae_id));
 			break;
 		case ACL_USER_OBJ:
 		case ACL_GROUP_OBJ:
 		case ACL_MASK:
 		case ACL_OTHER:
-			acl_e->e_id = ACL_UNDEFINED_ID;
 			break;
 		default:
 			goto fail;
@@ -101,7 +104,18 @@ xfs_acl_to_disk(struct xfs_acl *aclp, const struct posix_acl *acl)
 		acl_e = &acl->a_entries[i];
 
 		ace->ae_tag = cpu_to_be32(acl_e->e_tag);
-		ace->ae_id = cpu_to_be32(acl_e->e_id);
+		switch (acl_e->e_tag) {
+		case ACL_USER:
+			ace->ae_id = cpu_to_be32(xfs_kuid_to_uid(acl_e->e_uid));
+			break;
+		case ACL_GROUP:
+			ace->ae_id = cpu_to_be32(xfs_kgid_to_gid(acl_e->e_gid));
+			break;
+		default:
+			ace->ae_id = cpu_to_be32(ACL_UNDEFINED_ID);
+			break;
+		}
+
 		ace->ae_perm = cpu_to_be16(acl_e->e_perm);
 	}
 }
@@ -360,7 +374,7 @@ xfs_xattr_acl_set(struct dentry *dentry, const char *name,
 		return -EINVAL;
 	if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
 		return value ? -EACCES : 0;
-	if ((current_fsuid() != inode->i_uid) && !capable(CAP_FOWNER))
+	if (!inode_owner_or_capable(inode))
 		return -EPERM;
 
 	if (!value)

fs/xfs/xfs_ag.h

@@ -226,59 +226,6 @@ typedef struct xfs_agfl {
 	__be32		agfl_bno[];	/* actually XFS_AGFL_SIZE(mp) */
 } xfs_agfl_t;
 
-/*
- * Per-ag incore structure, copies of information in agf and agi,
- * to improve the performance of allocation group selection.
- */
-#define XFS_PAGB_NUM_SLOTS	128
-
-typedef struct xfs_perag {
-	struct xfs_mount *pag_mount;	/* owner filesystem */
-	xfs_agnumber_t	pag_agno;	/* AG this structure belongs to */
-	atomic_t	pag_ref;	/* perag reference count */
-	char		pagf_init;	/* this agf's entry is initialized */
-	char		pagi_init;	/* this agi's entry is initialized */
-	char		pagf_metadata;	/* the agf is preferred to be metadata */
-	char		pagi_inodeok;	/* The agi is ok for inodes */
-	__uint8_t	pagf_levels[XFS_BTNUM_AGF];
-					/* # of levels in bno & cnt btree */
-	__uint32_t	pagf_flcount;	/* count of blocks in freelist */
-	xfs_extlen_t	pagf_freeblks;	/* total free blocks */
-	xfs_extlen_t	pagf_longest;	/* longest free space */
-	__uint32_t	pagf_btreeblks;	/* # of blocks held in AGF btrees */
-	xfs_agino_t	pagi_freecount;	/* number of free inodes */
-	xfs_agino_t	pagi_count;	/* number of allocated inodes */
-
-	/*
-	 * Inode allocation search lookup optimisation.
-	 * If the pagino matches, the search for new inodes
-	 * doesn't need to search the near ones again straight away
-	 */
-	xfs_agino_t	pagl_pagino;
-	xfs_agino_t	pagl_leftrec;
-	xfs_agino_t	pagl_rightrec;
-#ifdef __KERNEL__
-	spinlock_t	pagb_lock;	/* lock for pagb_tree */
-	struct rb_root	pagb_tree;	/* ordered tree of busy extents */
-
-	atomic_t        pagf_fstrms;    /* # of filestreams active in this AG */
-
-	spinlock_t	pag_ici_lock;	/* incore inode cache lock */
-	struct radix_tree_root pag_ici_root;	/* incore inode cache root */
-	int		pag_ici_reclaimable;	/* reclaimable inodes */
-	struct mutex	pag_ici_reclaim_lock;	/* serialisation point */
-	unsigned long	pag_ici_reclaim_cursor;	/* reclaim restart point */
-
-	/* buffer cache index */
-	spinlock_t	pag_buf_lock;	/* lock for pag_buf_tree */
-	struct rb_root	pag_buf_tree;	/* ordered tree of active buffers */
-
-	/* for rcu-safe freeing */
-	struct rcu_head	rcu_head;
-#endif
-	int		pagb_count;	/* pagb slots in use */
-} xfs_perag_t;
-
 /*
  * tags for inode radix tree
  */

fs/xfs/xfs_alloc.c

@@ -878,7 +878,7 @@ xfs_alloc_ag_vextent_near(
 	xfs_agblock_t	ltnew;		/* useful start bno of left side */
 	xfs_extlen_t	rlen;		/* length of returned extent */
 	int		forced = 0;
-#if defined(DEBUG) && defined(__KERNEL__)
+#ifdef DEBUG
 	/*
 	 * Randomly don't execute the first algorithm.
 	 */
@@ -938,8 +938,8 @@ xfs_alloc_ag_vextent_near(
 		xfs_extlen_t	blen=0;
 		xfs_agblock_t	bnew=0;
 
-#if defined(DEBUG) && defined(__KERNEL__)
-		if (!dofirst)
+#ifdef DEBUG
+		if (dofirst)
 			break;
 #endif
 		/*

fs/xfs/xfs_aops.c

@@ -28,9 +28,9 @@
 #include "xfs_alloc.h"
 #include "xfs_error.h"
 #include "xfs_iomap.h"
-#include "xfs_vnodeops.h"
 #include "xfs_trace.h"
 #include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
 #include <linux/aio.h>
 #include <linux/gfp.h>
 #include <linux/mpage.h>
@@ -108,7 +108,7 @@ xfs_setfilesize_trans_alloc(
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
 
-	error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
+	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0);
 	if (error) {
 		xfs_trans_cancel(tp, 0);
 		return error;
@@ -440,7 +440,7 @@ xfs_start_page_writeback(
 		end_page_writeback(page);
 }
 
-static inline int bio_add_buffer(struct bio *bio, struct buffer_head *bh)
+static inline int xfs_bio_add_buffer(struct bio *bio, struct buffer_head *bh)
 {
 	return bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
 }
@@ -514,7 +514,7 @@ xfs_submit_ioend(
 				goto retry;
 			}
 
-			if (bio_add_buffer(bio, bh) != bh->b_size) {
+			if (xfs_bio_add_buffer(bio, bh) != bh->b_size) {
 				xfs_submit_ioend_bio(wbc, ioend, bio);
 				goto retry;
 			}
@@ -1498,13 +1498,26 @@ xfs_vm_write_failed(
 	loff_t			pos,
 	unsigned		len)
 {
-	loff_t			block_offset = pos & PAGE_MASK;
+	loff_t			block_offset;
 	loff_t			block_start;
 	loff_t			block_end;
 	loff_t			from = pos & (PAGE_CACHE_SIZE - 1);
 	loff_t			to = from + len;
 	struct buffer_head	*bh, *head;
 
+	/*
+	 * The request pos offset might be 32 or 64 bit, this is all fine
+	 * on 64-bit platform.  However, for 64-bit pos request on 32-bit
+	 * platform, the high 32-bit will be masked off if we evaluate the
+	 * block_offset via (pos & PAGE_MASK) because the PAGE_MASK is
+	 * 0xfffff000 as an unsigned long, hence the result is incorrect
+	 * which could cause the following ASSERT failed in most cases.
+	 * In order to avoid this, we can evaluate the block_offset of the
+	 * start of the page by using shifts rather than masks the mismatch
+	 * problem.
+	 */
+	block_offset = (pos >> PAGE_CACHE_SHIFT) << PAGE_CACHE_SHIFT;
+
 	ASSERT(block_offset + from == pos);
 
 	head = page_buffers(page);