metadata: prevent writing beyond metadata area

lvm uses a bcache block size of 128K.  A bcache block
at the end of the metadata area will overlap the PEs
from which LVs are allocated.  How much depends on
alignments.  When lvm reads and writes one of these
bcache blocks to update VG metadata, it can also be
reading and writing PEs that belong to an LV.

If these overlapping PEs are being written to by the
LV user (e.g. filesystem) at the same time that lvm
is modifying VG metadata in the overlapping bcache
block, then the user's updates to the PEs can be lost.

This patch is a quick hack to prevent lvm from writing
past the end of the metadata area.

6 files changed, 130 insertions, 3 deletions

diff --git a/lib/device/bcache.c b/lib/device/bcache.c
index 531d83b10..62352563a 100644
--- a/lib/device/bcache.c
+++ b/lib/device/bcache.c
@@ -156,6 +156,10 @@ static void _async_destroy(struct io_engine *ioe)
 	dm_free(e);
 }
 
+static int _last_byte_fd;
+static uint64_t _last_byte_offset;
+static int _last_byte_sector_size;
+
 static bool _async_issue(struct io_engine *ioe, enum dir d, int fd,
 			 sector_t sb, sector_t se, void *data, void *context)
 {
@@ -163,12 +167,53 @@ static bool _async_issue(struct io_engine *ioe, enum dir d, int fd,
 	struct iocb *cb_array[1];
 	struct control_block *cb;
 	struct async_engine *e = _to_async(ioe);
+	sector_t offset;
+	sector_t nbytes;
+	sector_t limit_nbytes;
+	sector_t extra_nbytes = 0;
 
 	if (((uintptr_t) data) & e->page_mask) {
 		log_warn("misaligned data buffer");
 		return false;
 	}
 
+	offset = sb << SECTOR_SHIFT;
+	nbytes = (se - sb) << SECTOR_SHIFT;
+
+	/*
+	 * If bcache block goes past where lvm wants to write, then clamp it.
+	 */
+	if ((d == DIR_WRITE) && _last_byte_offset && (fd == _last_byte_fd)) {
+		if (offset > _last_byte_offset) {
+			log_error("Limit write at %llu len %llu beyond last byte %llu",
+				  (unsigned long long)offset,
+				  (unsigned long long)nbytes,
+				  (unsigned long long)_last_byte_offset);
+			return false;
+		}
+
+		if (offset + nbytes > _last_byte_offset) {
+			limit_nbytes = _last_byte_offset - offset;
+			if (limit_nbytes % _last_byte_sector_size)
+				extra_nbytes = _last_byte_sector_size - (limit_nbytes % _last_byte_sector_size);
+
+			if (extra_nbytes) {
+				log_debug("Limit write at %llu len %llu to len %llu rounded to %llu",
+					  (unsigned long long)offset,
+					  (unsigned long long)nbytes,
+					  (unsigned long long)limit_nbytes,
+					  (unsigned long long)(limit_nbytes + extra_nbytes));
+				nbytes = limit_nbytes + extra_nbytes;
+			} else {
+				log_debug("Limit write at %llu len %llu to len %llu",
+					  (unsigned long long)offset,
+					  (unsigned long long)nbytes,
+					  (unsigned long long)limit_nbytes);
+				nbytes = limit_nbytes;
+			}
+		}
+	}
+
 	cb = _cb_alloc(e->cbs, context);
 	if (!cb) {
 		log_warn("couldn't allocate control block");
@@ -179,10 +224,22 @@ static bool _async_issue(struct io_engine *ioe, enum dir d, int fd,
 
 	cb->cb.aio_fildes = (int) fd;
 	cb->cb.u.c.buf = data;
-	cb->cb.u.c.offset = sb << SECTOR_SHIFT;
-	cb->cb.u.c.nbytes = (se - sb) << SECTOR_SHIFT;
+	cb->cb.u.c.offset = offset;
+	cb->cb.u.c.nbytes = nbytes;
 	cb->cb.aio_lio_opcode = (d == DIR_READ) ? IO_CMD_PREAD : IO_CMD_PWRITE;
 
+#if 0
+	if (d == DIR_READ) {
+		log_debug("io R off %llu bytes %llu",
+			  (unsigned long long)cb->cb.u.c.offset,
+			  (unsigned long long)cb->cb.u.c.nbytes);
+	} else {
+		log_debug("io W off %llu bytes %llu",
+			  (unsigned long long)cb->cb.u.c.offset,
+			  (unsigned long long)cb->cb.u.c.nbytes);
+	}
+#endif
+
 	cb_array[0] = &cb->cb;
 	do {
 		r = io_submit(e->aio_context, 1, cb_array);
@@ -1153,3 +1210,21 @@ bool bcache_invalidate_fd(struct bcache *cache, int fd)
 
 //----------------------------------------------------------------
 
+void bcache_set_last_byte(struct bcache *cache, int fd, uint64_t offset, int sector_size)
+{
+	_last_byte_fd = fd;
+	_last_byte_offset = offset;
+	_last_byte_sector_size = sector_size;
+	if (!sector_size)
+		_last_byte_sector_size = 512;
+}
+
+void bcache_unset_last_byte(struct bcache *cache, int fd)
+{
+	if (_last_byte_fd == fd) {
+		_last_byte_fd = 0;
+		_last_byte_offset = 0;
+		_last_byte_sector_size = 0;
+	}
+}
+
diff --git a/lib/device/bcache.h b/lib/device/bcache.h
index b0aebb49d..cb902ef36 100644
--- a/lib/device/bcache.h
+++ b/lib/device/bcache.h
@@ -158,6 +158,9 @@ bool bcache_write_bytes(struct bcache *cache, int fd, uint64_t start, size_t len
 bool bcache_zero_bytes(struct bcache *cache, int fd, uint64_t start, size_t len);
 bool bcache_set_bytes(struct bcache *cache, int fd, uint64_t start, size_t len, uint8_t val);
 
+void bcache_set_last_byte(struct bcache *cache, int fd, uint64_t offset, int sector_size);
+void bcache_unset_last_byte(struct bcache *cache, int fd);
+
 //----------------------------------------------------------------
 
 #endif
diff --git a/lib/format_text/format-text.c b/lib/format_text/format-text.c
index 5c7b72f8e..4160ba810 100644
--- a/lib/format_text/format-text.c
+++ b/lib/format_text/format-text.c
@@ -400,10 +400,14 @@ static int _raw_write_mda_header(const struct format_type *fmt,
 					     MDA_HEADER_SIZE -
 					     sizeof(mdah->checksum_xl)));
 
+	dev_set_last_byte(dev, start_byte + MDA_HEADER_SIZE);
+
 	if (!dev_write_bytes(dev, start_byte, MDA_HEADER_SIZE, mdah)) {
+		dev_unset_last_byte(dev);
 		log_error("Failed to write mda header to %s fd %d", dev_name(dev), dev->bcache_fd);
 		return 0;
 	}
+	dev_unset_last_byte(dev);
 
 	return 1;
 }
@@ -677,10 +681,13 @@ static int _vg_write_raw(struct format_instance *fid, struct volume_group *vg,
 			    (unsigned long long)(mdac->rlocn.size - new_wrap),
 			    (unsigned long long)new_wrap);
 
+	dev_set_last_byte(mdac->area.dev, mdac->area.start + mdah->size);
+
 	if (!dev_write_bytes(mdac->area.dev, mdac->area.start + mdac->rlocn.offset,
 		                (size_t) (mdac->rlocn.size - new_wrap),
 		                fidtc->raw_metadata_buf)) {
 		log_error("Failed to write metadata to %s fd %d", dev_name(mdac->area.dev), mdac->area.dev->bcache_fd);
+		dev_unset_last_byte(mdac->area.dev);
 		goto out;
 	}
 
@@ -694,10 +701,13 @@ static int _vg_write_raw(struct format_instance *fid, struct volume_group *vg,
 			                (size_t) new_wrap,
 			                fidtc->raw_metadata_buf + mdac->rlocn.size - new_wrap)) {
 			log_error("Failed to write metadata wrap to %s fd %d", dev_name(mdac->area.dev), mdac->area.dev->bcache_fd);
+			dev_unset_last_byte(mdac->area.dev);
 			goto out;
 		}
 	}
 
+	dev_unset_last_byte(mdac->area.dev);
+
 	mdac->rlocn.checksum = calc_crc(INITIAL_CRC, (uint8_t *)fidtc->raw_metadata_buf,
 					(uint32_t) (mdac->rlocn.size -
 						    new_wrap));
diff --git a/lib/label/label.c b/lib/label/label.c
index e5aa2c129..5377847b3 100644
--- a/lib/label/label.c
+++ b/lib/label/label.c
@@ -173,6 +173,7 @@ int label_write(struct device *dev, struct label *label)
 {
 	char buf[LABEL_SIZE] __attribute__((aligned(8)));
 	struct label_header *lh = (struct label_header *) buf;
+	uint64_t offset;
 	int r = 1;
 
 	if (!label->labeller->ops->write) {
@@ -207,11 +208,17 @@ int label_write(struct device *dev, struct label *label)
 		return 0;
 	}
 
-	if (!dev_write_bytes(dev, label->sector << SECTOR_SHIFT, LABEL_SIZE, buf)) {
+	offset = label->sector << SECTOR_SHIFT;
+
+	dev_set_last_byte(dev, offset + LABEL_SIZE);
+
+	if (!dev_write_bytes(dev, offset, LABEL_SIZE, buf)) {
 		log_debug_devs("Failed to write label to %s", dev_name(dev));
 		r = 0;
 	}
 
+	dev_unset_last_byte(dev);
+
 	return r;
 }
 
@@ -1354,9 +1361,12 @@ bool dev_write_zeros(struct device *dev, uint64_t start, size_t len)
 		}
 	}
 
+	dev_set_last_byte(dev, start + len);
+
 	if (!bcache_zero_bytes(scan_bcache, dev->bcache_fd, start, len)) {
 		log_error("Error writing device %s at %llu length %u.",
 			  dev_name(dev), (unsigned long long)start, (uint32_t)len);
+		dev_unset_last_byte(dev);
 		label_scan_invalidate(dev);
 		return false;
 	}
@@ -1364,9 +1374,11 @@ bool dev_write_zeros(struct device *dev, uint64_t start, size_t len)
 	if (!bcache_flush(scan_bcache)) {
 		log_error("Error writing device %s at %llu length %u.",
 			  dev_name(dev), (unsigned long long)start, (uint32_t)len);
+		dev_unset_last_byte(dev);
 		label_scan_invalidate(dev);
 		return false;
 	}
+	dev_unset_last_byte(dev);
 	return true;
 }
 
@@ -1400,9 +1412,12 @@ bool dev_set_bytes(struct device *dev, uint64_t start, size_t len, uint8_t val)
 		}
 	}
 
+	dev_set_last_byte(dev, start + len);
+
 	if (!bcache_set_bytes(scan_bcache, dev->bcache_fd, start, len, val)) {
 		log_error("Error writing device %s at %llu length %u.",
 			  dev_name(dev), (unsigned long long)start, (uint32_t)len);
+		dev_unset_last_byte(dev);
 		label_scan_invalidate(dev);
 		return false;
 	}
@@ -1410,9 +1425,27 @@ bool dev_set_bytes(struct device *dev, uint64_t start, size_t len, uint8_t val)
 	if (!bcache_flush(scan_bcache)) {
 		log_error("Error writing device %s at %llu length %u.",
 			  dev_name(dev), (unsigned long long)start, (uint32_t)len);
+		dev_unset_last_byte(dev);
 		label_scan_invalidate(dev);
 		return false;
 	}
+
+	dev_unset_last_byte(dev);
 	return true;
 }
 
+void dev_set_last_byte(struct device *dev, uint64_t offset)
+{
+	unsigned int phys_block_size = 0;
+	unsigned int block_size = 0;
+
+	dev_get_block_size(dev, &phys_block_size, &block_size);
+
+	bcache_set_last_byte(scan_bcache, dev->bcache_fd, offset, phys_block_size);
+}
+
+void dev_unset_last_byte(struct device *dev)
+{
+	bcache_unset_last_byte(scan_bcache, dev->bcache_fd);
+}
+
diff --git a/lib/label/label.h b/lib/label/label.h
index 5b83bc734..ae6a4f5f4 100644
--- a/lib/label/label.h
+++ b/lib/label/label.h
@@ -126,5 +126,7 @@ bool dev_read_bytes(struct device *dev, uint64_t start, size_t len, void *data);
 bool dev_write_bytes(struct device *dev, uint64_t start, size_t len, void *data);
 bool dev_write_zeros(struct device *dev, uint64_t start, size_t len);
 bool dev_set_bytes(struct device *dev, uint64_t start, size_t len, uint8_t val);
+void dev_set_last_byte(struct device *dev, uint64_t offset);
+void dev_unset_last_byte(struct device *dev);
 
 #endif
diff --git a/lib/metadata/mirror.c b/lib/metadata/mirror.c
index c7d8a9e94..b1dcaa0e2 100644
--- a/lib/metadata/mirror.c
+++ b/lib/metadata/mirror.c
@@ -302,10 +302,14 @@ static int _write_log_header(struct cmd_context *cmd, struct logical_volume *lv)
 		return 0;
 	}
 
+	dev_set_last_byte(dev, sizeof(log_header));
+
 	if (!dev_write_bytes(dev, UINT64_C(0), sizeof(log_header), &log_header)) {
+		dev_unset_last_byte(dev);
 		log_error("Failed to write log header to %s.", name);
 		return 0;
 	}
+	dev_unset_last_byte(dev);
 
 	label_scan_invalidate(dev);