[PATCH 0.9/9] xfs: introduce the XFS_IOC_GETFSMAP ioctl

["Darrick J. Wong" <darrick.wong@oracle.com>]

From: Darrick J. Wong <darrick.wong@oracle.com>

Introduce a new ioctl that uses the reverse mapping btree to return
information about the physical layout of the filesystem.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 configure.ac          |    1 
 include/builddefs.in  |    7 +++
 include/linux.h       |  109 +++++++++++++++++++++++++++++++++++++++++++++++++
 libxfs/xfs_fs.h       |   13 ++++++
 libxfs/xfs_rmap.c     |   28 +++++++++++++
 libxfs/xfs_rmap.h     |    2 +
 m4/package_libcdev.m4 |   19 +++++++++
 7 files changed, 178 insertions(+), 1 deletion(-)

diff --git a/configure.ac b/configure.ac
index aa102e4..794a804 100644
--- a/configure.ac
+++ b/configure.ac
@@ -142,6 +142,7 @@ AC_HAVE_READDIR
 AC_HAVE_FSETXATTR
 AC_HAVE_MREMAP
 AC_NEED_INTERNAL_FSXATTR
+AC_HAVE_SYS_GETFSMAP
 
 if test "$enable_blkid" = yes; then
 AC_HAVE_BLKID_TOPO
diff --git a/include/builddefs.in b/include/builddefs.in
index 4d6bb2d..e285731 100644
--- a/include/builddefs.in
+++ b/include/builddefs.in
@@ -112,16 +112,18 @@ HAVE_FLS = @have_fls@
 HAVE_FSETXATTR = @have_fsetxattr@
 HAVE_MREMAP = @have_mremap@
 NEED_INTERNAL_FSXATTR = @need_internal_fsxattr@
+HAVE_SYS_GETFSMAP = @have_sys_getfsmap@
 
 GCCFLAGS = -funsigned-char -fno-strict-aliasing -Wall
 #	   -Wbitwise -Wno-transparent-union -Wno-old-initializer -Wno-decl
 
 ifeq ($(PKG_PLATFORM),linux)
-PCFLAGS = -D_GNU_SOURCE $(GCCFLAGS)
+PCFLAGS = -D_GNU_SOURCE $(GCCFLAGS) -DHAVE_GETFSMAP
 ifeq ($(HAVE_UMODE_T),yes)
 PCFLAGS += -DHAVE_UMODE_T
 endif
 DEPENDFLAGS = -D__linux__
+HAVE_GETFSMAP = yes
 endif
 ifeq ($(PKG_PLATFORM),gnukfreebsd)
 PCFLAGS = -D_GNU_SOURCE $(GCCFLAGS)
@@ -150,6 +152,9 @@ endif
 ifeq ($(NEED_INTERNAL_FSXATTR),yes)
 PCFLAGS+= -DOVERRIDE_SYSTEM_FSXATTR
 endif
+ifeq ($(PKG_PLATFORM)_$(HAVE_SYS_GETFSMAP),linux_)
+PCFLAGS+= -DOVERRIDE_GETFSMAP
+endif
 
 
 GCFLAGS = $(DEBUG) \
diff --git a/include/linux.h b/include/linux.h
index 6a676ca..181d25c 100644
--- a/include/linux.h
+++ b/include/linux.h
@@ -35,7 +35,15 @@
 #ifdef OVERRIDE_SYSTEM_FSXATTR
 # define fsxattr sys_fsxattr
 #endif
+#ifdef OVERRIDE_GETFSMAP
+# define fsmap sys_fsmap
+# define fsmap_head sys_fsmap_head
+#endif
 #include <linux/fs.h> /* fsxattr defintion for new kernels */
+#ifdef OVERRIDE_GETFSMAP
+# undef fsmap
+# undef fsmap_head
+#endif
 #ifdef OVERRIDE_SYSTEM_FSXATTR
 # undef fsxattr
 #endif
@@ -222,4 +230,105 @@ struct fsxattr {
 #define FS_XFLAG_COWEXTSIZE	0x00010000	/* CoW extent size allocator hint */
 #endif
 
+#ifdef OVERRIDE_GETFSMAP
+/*
+ *	Structure for FS_IOC_GETFSMAP.
+ *
+ *	The memory layout for this call are the scalar values defined in
+ *	struct fsmap_head, followed by two struct fsmap that describe
+ *	the lower and upper bound of mappings to return, followed by an
+ *	array of struct fsmap mappings.
+ *
+ *	fmh_iflags control the output of the call, whereas fmh_oflags report
+ *	on the overall record output.  fmh_count should be set to the
+ *	length of the fmh_recs array, and fmh_entries will be set to the
+ *	number of entries filled out during each call.  If fmh_count is
+ *	zero, the number of reverse mappings will be returned in
+ *	fmh_entries, though no mappings will be returned.  fmh_reserved
+ *	must be set to zero.
+ *
+ *	The two elements in the fmh_keys array are used to constrain the
+ *	output.  The first element in the array should represent the
+ *	lowest disk mapping ("low key") that the user wants to learn
+ *	about.  If this value is all zeroes, the filesystem will return
+ *	the first entry it knows about.  For a subsequent call, the
+ *	contents of fsmap_head.fmh_recs[fsmap_head.fmh_count - 1] should be
+ *	copied into fmh_keys[0] to have the kernel start where it left off.
+ *
+ *	The second element in the fmh_keys array should represent the
+ *	highest disk mapping ("high key") that the user wants to learn
+ *	about.  If this value is all ones, the filesystem will not stop
+ *	until it runs out of mapping to return or runs out of space in
+ *	fmh_recs.
+ *
+ *	fmr_device can be either a 32-bit cookie representing a device, or
+ *	a 32-bit dev_t if the FMH_OF_DEV_T flag is set.  fmr_physical,
+ *	fmr_offset, and fmr_length are expressed in units of bytes.
+ *	fmr_owner is either an inode number, or a special value if
+ *	FMR_OF_SPECIAL_OWNER is set in fmr_flags.
+ */
+struct fsmap {
+	__u32		fmr_device;	/* device id */
+	__u32		fmr_flags;	/* mapping flags */
+	__u64		fmr_physical;	/* device offset of segment */
+	__u64		fmr_owner;	/* owner id */
+	__u64		fmr_offset;	/* file offset of segment */
+	__u64		fmr_length;	/* length of segment */
+	__u64		fmr_reserved[3];	/* must be zero */
+};
+
+struct fsmap_head {
+	__u32		fmh_iflags;	/* control flags */
+	__u32		fmh_oflags;	/* output flags */
+	__u32		fmh_count;	/* # of entries in array incl. input */
+	__u32		fmh_entries;	/* # of entries filled in (output). */
+	__u64		fmh_reserved[6];	/* must be zero */
+
+	struct fsmap	fmh_keys[2];	/* low and high keys for the mapping search */
+	struct fsmap	fmh_recs[];	/* returned records */
+};
+
+/* Size of an fsmap_head with room for nr records. */
+static inline size_t
+fsmap_sizeof(
+	unsigned int	nr)
+{
+	return sizeof(struct fsmap_head) + nr * sizeof(struct fsmap);
+}
+
+/* Start the next fsmap query at the end of the current query results. */
+static inline void
+fsmap_advance(
+	struct fsmap_head	*head)
+{
+	head->fmh_keys[0] = head->fmh_recs[head->fmh_entries - 1];
+}
+
+/*	fmh_iflags values - set by XFS_IOC_GETFSMAP caller in the header. */
+/* no flags defined yet */
+#define FMH_IF_VALID		0
+
+/*	fmh_oflags values - returned in the header segment only. */
+#define FMH_OF_DEV_T		0x1	/* fmr_device values will be dev_t */
+
+/*	fmr_flags values - returned for each non-header segment */
+#define FMR_OF_PREALLOC		0x1	/* segment = unwritten pre-allocation */
+#define FMR_OF_ATTR_FORK	0x2	/* segment = attribute fork */
+#define FMR_OF_EXTENT_MAP	0x4	/* segment = extent map */
+#define FMR_OF_SHARED		0x8	/* segment = shared with another file */
+#define FMR_OF_SPECIAL_OWNER	0x10	/* owner is a special value */
+#define FMR_OF_LAST		0x20	/* segment is the last in the FS */
+
+/* Each FS gets to define its own special owner codes. */
+#define FMR_OWNER(type, code)	(((__u64)type << 32) | \
+				 ((__u64)code & 0xFFFFFFFFULL))
+#define FMR_OWNER_TYPE(owner)	((__u32)((__u64)owner >> 32))
+#define FMR_OWNER_CODE(owner)	((__u32)(((__u64)owner & 0xFFFFFFFFULL)))
+#define FMR_OWN_FREE		FMR_OWNER(0, 1) /* free space */
+#define FMR_OWN_UNKNOWN		FMR_OWNER(0, 2) /* unknown owner */
+#define FMR_OWN_METADATA	FMR_OWNER(0, 3) /* metadata */
+
+#define FS_IOC_GETFSMAP		_IOWR('X', 59, struct fsmap_head)
+#endif /* OVERRIDE_GETFSMAP */
+
 #endif	/* __XFS_LINUX_H__ */
diff --git a/libxfs/xfs_fs.h b/libxfs/xfs_fs.h
index 11fe42a..1831cff 100644
--- a/libxfs/xfs_fs.h
+++ b/libxfs/xfs_fs.h
@@ -113,6 +113,18 @@ struct getbmapx {
 #define BMV_OF_LAST		0x4	/* segment is the last in the file */
 #define BMV_OF_SHARED		0x8	/* segment shared with another file */
 
+/*	fmr_owner special values for FS_IOC_GETFSMAP */
+#define XFS_FMR_OWN_FREE	FMR_OWN_FREE      /* free space */
+#define XFS_FMR_OWN_UNKNOWN	FMR_OWN_UNKNOWN   /* unknown owner */
+#define XFS_FMR_OWN_FS		FMR_OWNER('X', 1) /* static fs metadata */
+#define XFS_FMR_OWN_LOG		FMR_OWNER('X', 2) /* journalling log */
+#define XFS_FMR_OWN_AG		FMR_OWNER('X', 3) /* per-AG metadata */
+#define XFS_FMR_OWN_INOBT	FMR_OWNER('X', 4) /* inode btree blocks */
+#define XFS_FMR_OWN_INODES	FMR_OWNER('X', 5) /* inodes */
+#define XFS_FMR_OWN_REFC	FMR_OWNER('X', 6) /* refcount tree */
+#define XFS_FMR_OWN_COW		FMR_OWNER('X', 7) /* cow staging */
+#define XFS_FMR_OWN_DEFECTIVE	FMR_OWNER('X', 8) /* bad blocks */
+
 /*
  * Structure for XFS_IOC_FSSETDM.
  * For use by backup and restore programs to set the XFS on-disk inode
@@ -522,6 +534,7 @@ typedef struct xfs_swapext
 #define XFS_IOC_GETBMAPX	_IOWR('X', 56, struct getbmap)
 #define XFS_IOC_ZERO_RANGE	_IOW ('X', 57, struct xfs_flock64)
 #define XFS_IOC_FREE_EOFBLOCKS	_IOR ('X', 58, struct xfs_fs_eofblocks)
+/*	XFS_IOC_GETFSMAP ------ hoisted 59         */
 
 /*
  * ioctl commands that replace IRIX syssgi()'s
diff --git a/libxfs/xfs_rmap.c b/libxfs/xfs_rmap.c
index 7738f50..f78771d 100644
--- a/libxfs/xfs_rmap.c
+++ b/libxfs/xfs_rmap.c
@@ -2303,3 +2303,31 @@ xfs_rmap_free_extent(
 	return __xfs_rmap_add(mp, dfops, XFS_RMAP_FREE, owner,
 			XFS_DATA_FORK, &bmap);
 }
+
+/* Compare rmap records.  Returns -1 if a < b, 1 if a > b, and 0 if equal. */
+int
+xfs_rmap_compare(
+	const struct xfs_rmap_irec	*a,
+	const struct xfs_rmap_irec	*b)
+{
+	__u64				oa;
+	__u64				ob;
+
+	oa = xfs_rmap_irec_offset_pack(a);
+	ob = xfs_rmap_irec_offset_pack(b);
+
+	if (a->rm_startblock < b->rm_startblock)
+		return -1;
+	else if (a->rm_startblock > b->rm_startblock)
+		return 1;
+	else if (a->rm_owner < b->rm_owner)
+		return -1;
+	else if (a->rm_owner > b->rm_owner)
+		return 1;
+	else if (oa < ob)
+		return -1;
+	else if (oa > ob)
+		return 1;
+	else
+		return 0;
+}
diff --git a/libxfs/xfs_rmap.h b/libxfs/xfs_rmap.h
index faf2c1a..98f908f 100644
--- a/libxfs/xfs_rmap.h
+++ b/libxfs/xfs_rmap.h
@@ -214,5 +214,7 @@ int xfs_rmap_find_left_neighbor(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 int xfs_rmap_lookup_le_range(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 		uint64_t owner, uint64_t offset, unsigned int flags,
 		struct xfs_rmap_irec *irec, int	*stat);
+int xfs_rmap_compare(const struct xfs_rmap_irec *a,
+		const struct xfs_rmap_irec *b);
 
 #endif	/* __XFS_RMAP_H__ */
diff --git a/m4/package_libcdev.m4 b/m4/package_libcdev.m4
index bc3b4ce..f9b0945 100644
--- a/m4/package_libcdev.m4
+++ b/m4/package_libcdev.m4
@@ -277,3 +277,22 @@ AC_DEFUN([AC_NEED_INTERNAL_FSXATTR],
     )
     AC_SUBST(need_internal_fsxattr)
   ])
+
+#
+# Check if we have a FS_IOC_GETFSMAP ioctl (Linux)
+#
+AC_DEFUN([AC_HAVE_SYS_GETFSMAP],
+  [ AC_MSG_CHECKING([for GETFSMAP])
+    AC_TRY_LINK([
+#define _GNU_SOURCE
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <linux/fsmap.h>
+    ], [
+         unsigned long x = FS_IOC_GETFSMAP;
+         struct fsmap_head fh;
+    ], have_sys_getfsmap=yes
+       AC_MSG_RESULT(yes),
+       AC_MSG_RESULT(no))
+    AC_SUBST(have_sys_getfsmap)
+  ])