/**
* efi_partition(struct parsed_partitions *state, struct block_device *bdev)
* @state
* @bdev
*
* Description: called from check.c, if the disk contains GPT
* partitions, sets up partition entries in the kernel.
*
* If the first block on the disk is a legacy MBR,
* it will get handled by msdos_partition().
* If it's a Protective MBR, we'll handle it here.
*
* We do not create a Linux partition for GPT, but
* only for the actual data partitions.
* Returns:
* -1 if unable to read the partition table
* 0 if this isn't our partition table
* 1 if successful
*
*/
int
efi_partition(struct parsed_partitions *state, struct block_device *bdev)
{
gpt_header *gpt = NULL;
gpt_entry *ptes = NULL;
u32 i;
unsigned ssz = bdev_logical_block_size(bdev) / 512;
if (!find_valid_gpt(bdev, &gpt, &ptes) || !gpt || !ptes) {
kfree(gpt);
kfree(ptes);
return 0;
}
pr_debug("GUID Partition Table is valid! Yea!\n");
for (i = 0; i < le32_to_cpu(gpt->num_partition_entries) && i < state->limit-1; i++) {
u64 start = le64_to_cpu(ptes[i].starting_lba);
u64 size = le64_to_cpu(ptes[i].ending_lba) -
le64_to_cpu(ptes[i].starting_lba) + 1ULL;
if (!is_pte_valid(&ptes[i], last_lba(bdev)))
continue;
put_partition(state, i+1, start * ssz, size * ssz);
/* If this is a RAID volume, tell md */
if (!efi_guidcmp(ptes[i].partition_type_guid,
PARTITION_LINUX_RAID_GUID))
state->parts[i+1].flags = 1;
}
kfree(ptes);
kfree(gpt);
printk("\n");
return 1;
}
/*
* Write the physical details regarding the block device to the store, and
* switch to Connected state.
*/
static void connect(struct backend_info *be)
{
struct xenbus_transaction xbt;
int err;
struct xenbus_device *dev = be->dev;
DPRINTK("%s", dev->otherend);
/* Supply the information about the device the frontend needs */
again:
err = xenbus_transaction_start(&xbt);
if (err) {
xenbus_dev_fatal(dev, err, "starting transaction");
return;
}
err = xen_blkbk_flush_diskcache(xbt, be, be->blkif->vbd.flush_support);
if (err)
goto abort;
err = xenbus_printf(xbt, dev->nodename, "sectors", "%llu",
(unsigned long long)vbd_sz(&be->blkif->vbd));
if (err) {
xenbus_dev_fatal(dev, err, "writing %s/sectors",
dev->nodename);
goto abort;
}
/* FIXME: use a typename instead */
err = xenbus_printf(xbt, dev->nodename, "info", "%u",
be->blkif->vbd.type |
(be->blkif->vbd.readonly ? VDISK_READONLY : 0));
if (err) {
xenbus_dev_fatal(dev, err, "writing %s/info",
dev->nodename);
goto abort;
}
err = xenbus_printf(xbt, dev->nodename, "sector-size", "%lu",
(unsigned long)
bdev_logical_block_size(be->blkif->vbd.bdev));
if (err) {
xenbus_dev_fatal(dev, err, "writing %s/sector-size",
dev->nodename);
goto abort;
}
err = xenbus_transaction_end(xbt, 0);
if (err == -EAGAIN)
goto again;
if (err)
xenbus_dev_fatal(dev, err, "ending transaction");
err = xenbus_switch_state(dev, XenbusStateConnected);
if (err)
xenbus_dev_fatal(dev, err, "switching to Connected state",
dev->nodename);
return;
abort:
xenbus_transaction_end(xbt, 1);
}
/**
* efi_partition(struct parsed_partitions *state)
* @state
*
* Description: called from check.c, if the disk contains GPT
* partitions, sets up partition entries in the kernel.
*
* If the first block on the disk is a legacy MBR,
* it will get handled by msdos_partition().
* If it's a Protective MBR, we'll handle it here.
*
* We do not create a Linux partition for GPT, but
* only for the actual data partitions.
* Returns:
* -1 if unable to read the partition table
* 0 if this isn't our partition table
* 1 if successful
*
*/
int efi_partition(struct parsed_partitions *state)
{
gpt_header *gpt = NULL;
gpt_entry *ptes = NULL;
u32 i;
unsigned ssz = bdev_logical_block_size(state->bdev) / 512;
u8 unparsed_guid[37];
if (!find_valid_gpt(state, &gpt, &ptes) || !gpt || !ptes) {
kfree(gpt);
kfree(ptes);
return 0;
}
pr_debug("GUID Partition Table is valid! Yea!\n");
for (i = 0; i < le32_to_cpu(gpt->num_partition_entries) && i < state->limit-1; i++) {
struct partition_meta_info *info;
unsigned label_count = 0;
unsigned label_max;
u64 start = le64_to_cpu(ptes[i].starting_lba);
u64 size = le64_to_cpu(ptes[i].ending_lba) -
le64_to_cpu(ptes[i].starting_lba) + 1ULL;
if (!is_pte_valid(&ptes[i], last_lba(state->bdev)))
continue;
put_partition(state, i+1, start * ssz, size * ssz);
/* If this is a RAID volume, tell md */
if (!efi_guidcmp(ptes[i].partition_type_guid,
PARTITION_LINUX_RAID_GUID))
state->parts[i + 1].flags = ADDPART_FLAG_RAID;
info = &state->parts[i + 1].info;
/* Instead of doing a manual swap to big endian, reuse the
* common ASCII hex format as the interim.
*/
efi_guid_unparse(&ptes[i].unique_partition_guid, unparsed_guid);
part_pack_uuid(unparsed_guid, info->uuid);
/* Naively convert UTF16-LE to 7 bits. */
label_max = min(sizeof(info->volname) - 1,
sizeof(ptes[i].partition_name));
info->volname[label_max] = 0;
while (label_count < label_max) {
u8 c = ptes[i].partition_name[label_count] & 0xff;
if (c && !isprint(c))
c = '!';
info->volname[label_count] = c;
label_count++;
}
state->parts[i + 1].has_info = true;
}
/* Add static partitions for SOS and LNX if specified in kernel config (Tegra platform) */
#ifdef CONFIG_TEGRA_BOOTBLOCK_EXPOSE
printk(KERN_NOTICE "Adding SOS as MMC partition %i: offset %i bytes, size: %i bytes\n", i+1, CONFIG_BOOTBLOCK_EXPOSE_SOS_OFFSET * 512, CONFIG_BOOTBLOCK_EXPOSE_SOS_SIZE * 512);
put_partition(state, i+1, CONFIG_BOOTBLOCK_EXPOSE_SOS_OFFSET * ssz, CONFIG_BOOTBLOCK_EXPOSE_SOS_SIZE * ssz);
printk(KERN_NOTICE "Adding LNX as MMC partition %i: offset %i bytes, size: %i bytes\n", i+2, CONFIG_BOOTBLOCK_EXPOSE_LNX_OFFSET * 512, CONFIG_BOOTBLOCK_EXPOSE_LNX_SIZE * 512);
put_partition(state, i+2, CONFIG_BOOTBLOCK_EXPOSE_LNX_OFFSET * ssz, CONFIG_BOOTBLOCK_EXPOSE_LNX_SIZE * ssz);
#endif
kfree(ptes);
kfree(gpt);
strlcat(state->pp_buf, "\n", PAGE_SIZE);
return 1;
}
int msdos_partition(struct parsed_partitions *state)
{
sector_t sector_size = bdev_logical_block_size(state->bdev) / 512;
Sector sect;
unsigned char *data;
struct partition *p;
struct fat_boot_sector *fb;
int slot;
data = read_part_sector(state, 0, §);
if (!data)
return -1;
if (!msdos_magic_present(data + 510)) {
put_dev_sector(sect);
return 0;
}
if (aix_magic_present(state, data)) {
put_dev_sector(sect);
printk( " [AIX]");
return 0;
}
/*
* Now that the 55aa signature is present, this is probably
* either the boot sector of a FAT filesystem or a DOS-type
* partition table. Reject this in case the boot indicator
* is not 0 or 0x80.
*/
p = (struct partition *) (data + 0x1be);
for (slot = 1; slot <= 4; slot++, p++) {
if (p->boot_ind != 0 && p->boot_ind != 0x80) {
/*
* Even without a valid boot inidicator value
* its still possible this is valid FAT filesystem
* without a partition table.
*/
fb = (struct fat_boot_sector *) data;
if (slot == 1 && fb->reserved && fb->fats
&& fat_valid_media(fb->media)) {
printk("\n");
put_dev_sector(sect);
return 1;
} else {
put_dev_sector(sect);
return 0;
}
}
}
#ifdef CONFIG_EFI_PARTITION
p = (struct partition *) (data + 0x1be);
for (slot = 1 ; slot <= 4 ; slot++, p++) {
/* If this is an EFI GPT disk, msdos should ignore it. */
if (SYS_IND(p) == EFI_PMBR_OSTYPE_EFI_GPT) {
put_dev_sector(sect);
return 0;
}
}
#endif
p = (struct partition *) (data + 0x1be);
/*
* Look for partitions in two passes:
* First find the primary and DOS-type extended partitions.
* On the second pass look inside *BSD, Unixware and Solaris partitions.
*/
state->next = 5;
for (slot = 1 ; slot <= 4 ; slot++, p++) {
sector_t start = start_sect(p)*sector_size;
sector_t size = nr_sects(p)*sector_size;
if (!size)
continue;
if (is_extended_partition(p)) {
/*
* prevent someone doing mkfs or mkswap on an
* extended partition, but leave room for LILO
* FIXME: this uses one logical sector for > 512b
* sector, although it may not be enough/proper.
*/
sector_t n = 2;
n = min(size, max(sector_size, n));
put_partition(state, slot, start, n);
printk(" <");
parse_extended(state, start, size);
printk(" >");
continue;
}
put_partition(state, slot, start, size);
if (SYS_IND(p) == LINUX_RAID_PARTITION)
state->parts[slot].flags = ADDPART_FLAG_RAID;
if (SYS_IND(p) == DM6_PARTITION)
printk("[DM]");
if (SYS_IND(p) == EZD_PARTITION)
printk("[EZD]");
}
printk("\n");
/* second pass - output for each on a separate line */
p = (struct partition *) (0x1be + data);
for (slot = 1 ; slot <= 4 ; slot++, p++) {
unsigned char id = SYS_IND(p);
int n;
if (!nr_sects(p))
continue;
for (n = 0; subtypes[n].parse && id != subtypes[n].id; n++)
;
if (!subtypes[n].parse)
continue;
subtypes[n].parse(state, start_sect(p) * sector_size,
nr_sects(p) * sector_size, slot);
}
put_dev_sector(sect);
return 1;
}
/**
* is_gpt_valid() - tests one GPT header and PTEs for validity
* @state
* @lba is the logical block address of the GPT header to test
* @gpt is a GPT header ptr, filled on return.
* @ptes is a PTEs ptr, filled on return.
*
* Description: returns 1 if valid, 0 on error.
* If valid, returns pointers to newly allocated GPT header and PTEs.
*/
static int is_gpt_valid(struct parsed_partitions *state, u64 lba,
gpt_header **gpt, gpt_entry **ptes)
{
u32 crc, origcrc;
u64 lastlba;
if (!ptes)
return 0;
if (!(*gpt = alloc_read_gpt_header(state, lba)))
return 0;
/* Check the GUID Partition Table signature */
if (le64_to_cpu((*gpt)->signature) != GPT_HEADER_SIGNATURE) {
pr_debug("GUID Partition Table Header signature is wrong:"
"%lld != %lld\n",
(unsigned long long)le64_to_cpu((*gpt)->signature),
(unsigned long long)GPT_HEADER_SIGNATURE);
goto fail;
}
/* Check the GUID Partition Table header size is too big */
if (le32_to_cpu((*gpt)->header_size) >
bdev_logical_block_size(state->bdev)) {
pr_debug("GUID Partition Table Header size is too large: %u > %u\n",
le32_to_cpu((*gpt)->header_size),
bdev_logical_block_size(state->bdev));
goto fail;
}
/* Check the GUID Partition Table header size is too small */
if (le32_to_cpu((*gpt)->header_size) < sizeof(gpt_header)) {
pr_debug("GUID Partition Table Header size is too small: %u < %zu\n",
le32_to_cpu((*gpt)->header_size),
sizeof(gpt_header));
goto fail;
}
/* Check the GUID Partition Table CRC */
origcrc = le32_to_cpu((*gpt)->header_crc32);
(*gpt)->header_crc32 = 0;
crc = efi_crc32((const unsigned char *) (*gpt), le32_to_cpu((*gpt)->header_size));
if (crc != origcrc) {
pr_debug("GUID Partition Table Header CRC is wrong: %x != %x\n",
crc, origcrc);
goto fail;
}
(*gpt)->header_crc32 = cpu_to_le32(origcrc);
/* Check that the my_lba entry points to the LBA that contains
* the GUID Partition Table */
if (le64_to_cpu((*gpt)->my_lba) != lba) {
pr_debug("GPT my_lba incorrect: %lld != %lld\n",
(unsigned long long)le64_to_cpu((*gpt)->my_lba),
(unsigned long long)lba);
goto fail;
}
/* Check the first_usable_lba and last_usable_lba are
* within the disk.
*/
lastlba = last_lba(state->bdev);
if (le64_to_cpu((*gpt)->first_usable_lba) > lastlba) {
pr_debug("GPT: first_usable_lba incorrect: %lld > %lld\n",
(unsigned long long)le64_to_cpu((*gpt)->first_usable_lba),
(unsigned long long)lastlba);
goto fail;
}
if (le64_to_cpu((*gpt)->last_usable_lba) > lastlba) {
pr_debug("GPT: last_usable_lba incorrect: %lld > %lld\n",
(unsigned long long)le64_to_cpu((*gpt)->last_usable_lba),
(unsigned long long)lastlba);
goto fail;
}
/* Check that sizeof_partition_entry has the correct value */
if (le32_to_cpu((*gpt)->sizeof_partition_entry) != sizeof(gpt_entry)) {
pr_debug("GUID Partitition Entry Size check failed.\n");
goto fail;
}
if (!(*ptes = alloc_read_gpt_entries(state, *gpt)))
goto fail;
/* Check the GUID Partition Entry Array CRC */
crc = efi_crc32((const unsigned char *) (*ptes),
le32_to_cpu((*gpt)->num_partition_entries) *
le32_to_cpu((*gpt)->sizeof_partition_entry));
if (crc != le32_to_cpu((*gpt)->partition_entry_array_crc32)) {
pr_debug("GUID Partitition Entry Array CRC check failed.\n");
goto fail_ptes;
}
/* We're done, all's well */
return 1;
fail_ptes:
kfree(*ptes);
*ptes = NULL;
fail:
kfree(*gpt);
*gpt = NULL;
if (!force_gpt)
BUG_ON(1);
return 0;
}
int atari_partition(struct parsed_partitions *state)
{
Sector sect;
struct rootsector *rs;
struct partition_info *pi;
u32 extensect;
u32 hd_size;
int slot;
#ifdef ICD_PARTS
int part_fmt = 0; /* 0:unknown, 1:AHDI, 2:ICD/Supra */
#endif
/*
* ATARI partition scheme supports 512 lba only. If this is not
* the case, bail early to avoid miscalculating hd_size.
*/
if (bdev_logical_block_size(state->bdev) != 512)
return 0;
rs = read_part_sector(state, 0, §);
if (!rs)
return -1;
/* Verify this is an Atari rootsector: */
hd_size = state->bdev->bd_inode->i_size >> 9;
if (!VALID_PARTITION(&rs->part[0], hd_size) &&
!VALID_PARTITION(&rs->part[1], hd_size) &&
!VALID_PARTITION(&rs->part[2], hd_size) &&
!VALID_PARTITION(&rs->part[3], hd_size)) {
/*
* if there's no valid primary partition, assume that no Atari
* format partition table (there's no reliable magic or the like
* :-()
*/
put_dev_sector(sect);
return 0;
}
pi = &rs->part[0];
strlcat(state->pp_buf, " AHDI", PAGE_SIZE);
for (slot = 1; pi < &rs->part[4] && slot < state->limit; slot++, pi++) {
struct rootsector *xrs;
Sector sect2;
ulong partsect;
if ( !(pi->flg & 1) )
continue;
/* active partition */
if (memcmp (pi->id, "XGM", 3) != 0) {
/* we don't care about other id's */
put_partition (state, slot, be32_to_cpu(pi->st),
be32_to_cpu(pi->siz));
continue;
}
/* extension partition */
#ifdef ICD_PARTS
part_fmt = 1;
#endif
strlcat(state->pp_buf, " XGM<", PAGE_SIZE);
partsect = extensect = be32_to_cpu(pi->st);
while (1) {
xrs = read_part_sector(state, partsect, §2);
if (!xrs) {
printk (" block %ld read failed\n", partsect);
put_dev_sector(sect);
return -1;
}
/* ++roman: sanity check: bit 0 of flg field must be set */
if (!(xrs->part[0].flg & 1)) {
printk( "\nFirst sub-partition in extended partition is not valid!\n" );
put_dev_sector(sect2);
break;
}
put_partition(state, slot,
partsect + be32_to_cpu(xrs->part[0].st),
be32_to_cpu(xrs->part[0].siz));
if (!(xrs->part[1].flg & 1)) {
/* end of linked partition list */
put_dev_sector(sect2);
break;
}
if (memcmp( xrs->part[1].id, "XGM", 3 ) != 0) {
printk("\nID of extended partition is not XGM!\n");
put_dev_sector(sect2);
break;
}
partsect = be32_to_cpu(xrs->part[1].st) + extensect;
put_dev_sector(sect2);
if (++slot == state->limit) {
printk( "\nMaximum number of partitions reached!\n" );
break;
}
}
strlcat(state->pp_buf, " >", PAGE_SIZE);
}
#ifdef ICD_PARTS
if ( part_fmt!=1 ) { /* no extended partitions -> test ICD-format */
pi = &rs->icdpart[0];
/* sanity check: no ICD format if first partition invalid */
if (OK_id(pi->id)) {
strlcat(state->pp_buf, " ICD<", PAGE_SIZE);
for (; pi < &rs->icdpart[8] && slot < state->limit; slot++, pi++) {
/* accept only GEM,BGM,RAW,LNX,SWP partitions */
if (!((pi->flg & 1) && OK_id(pi->id)))
continue;
part_fmt = 2;
put_partition (state, slot,
be32_to_cpu(pi->st),
be32_to_cpu(pi->siz));
}
strlcat(state->pp_buf, " >", PAGE_SIZE);
}
}
#endif
put_dev_sector(sect);
strlcat(state->pp_buf, "\n", PAGE_SIZE);
return 1;
}
int drbd_md_sync_page_io(struct drbd_conf *mdev, struct drbd_backing_dev *bdev,
sector_t sector, int rw)
{
int logical_block_size, mask, ok;
int offset = 0;
struct page *iop = mdev->md_io_page;
D_ASSERT(mutex_is_locked(&mdev->md_io_mutex));
if (!bdev->md_bdev) {
if (DRBD_ratelimit(5*HZ, 5)) {
dev_err(DEV, "bdev->md_bdev==NULL\n");
dump_stack();
}
return 0;
}
logical_block_size = bdev_logical_block_size(bdev->md_bdev);
if (logical_block_size == 0)
logical_block_size = MD_SECTOR_SIZE;
/* in case logical_block_size != 512 [ s390 only? ] */
if (logical_block_size != MD_SECTOR_SIZE) {
mask = (logical_block_size / MD_SECTOR_SIZE) - 1;
D_ASSERT(mask == 1 || mask == 3 || mask == 7);
D_ASSERT(logical_block_size == (mask+1) * MD_SECTOR_SIZE);
offset = sector & mask;
sector = sector & ~mask;
iop = mdev->md_io_tmpp;
if (rw & WRITE) {
/* these are GFP_KERNEL pages, pre-allocated
* on device initialization */
void *p = page_address(mdev->md_io_page);
void *hp = page_address(mdev->md_io_tmpp);
ok = _drbd_md_sync_page_io(mdev, bdev, iop, sector,
READ, logical_block_size);
if (unlikely(!ok)) {
dev_err(DEV, "drbd_md_sync_page_io(,%llus,"
"READ [logical_block_size!=512]) failed!\n",
(unsigned long long)sector);
return 0;
}
memcpy(hp + offset*MD_SECTOR_SIZE, p, MD_SECTOR_SIZE);
}
}
#if DUMP_MD >= 3
dev_info(DEV, "%s [%d]:%s(,%llus,%s)\n",
current->comm, current->pid, __func__,
(unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ");
#endif
if (sector < drbd_md_first_sector(bdev) ||
sector > drbd_md_last_sector(bdev))
dev_alert(DEV, "%s [%d]:%s(,%llus,%s) out of range md access!\n",
current->comm, current->pid, __func__,
(unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ");
ok = _drbd_md_sync_page_io(mdev, bdev, iop, sector, rw, logical_block_size);
if (unlikely(!ok)) {
dev_err(DEV, "drbd_md_sync_page_io(,%llus,%s) failed!\n",
(unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ");
return 0;
}
if (logical_block_size != MD_SECTOR_SIZE && !(rw & WRITE)) {
void *p = page_address(mdev->md_io_page);
void *hp = page_address(mdev->md_io_tmpp);
memcpy(p, hp + offset*MD_SECTOR_SIZE, MD_SECTOR_SIZE);
}
return ok;
}
int
parse_tegrapart(struct parsed_partitions *state)
{
char *ptr;
char *pstart;
int pstate;
char name[8];
u64 offset, size, blocksize, kblocksize;
int done;
int ret=0;
printk(KERN_INFO "parse_tegrapart: tegrapart=%s\n", partition_list);
kblocksize = bdev_logical_block_size(state->bdev);
ptr = partition_list;
pstart = ptr;
pstate = STATE_NAME;
name[0] = '\0';
offset = 0;
size = 0;
blocksize = 0;
done = 0;
do {
switch(pstate) {
case STATE_NAME:
if (*ptr==':') {
int len=ptr-pstart;
if (len>7)
len=7;
memcpy(name, pstart, len);
name[len] = '\0';
pstate++;
pstart = ptr+1;
}
break;
case STATE_OFFSET:
if (*ptr==':') {
offset=strtohex(pstart);
pstate++;
pstart = ptr+1;
}
break;
case STATE_SIZE:
if (*ptr==':') {
size=strtohex(pstart);
pstate++;
pstart = ptr+1;
}
break;
case STATE_BLOCKSIZE:
if (*ptr=='\0')
done = 1;
if ((*ptr==',') || (*ptr=='\0')) {
blocksize=strtohex(pstart);
pstate = STATE_NAME;
pstart = ptr+1;
offset = offset*blocksize;
size = size*blocksize;
do_div(offset, kblocksize);
do_div(size, kblocksize);
if (!strcasecmp(name, "mbr")) {
printk(KERN_INFO "parse_tegrapart: mbr start=%llu\n", offset);
return tegra_msdos_parse(state, state->bdev, offset);
}
printk(KERN_INFO "parse_tegrapart: part #%d [%s] start=%llu size=%llu\n",
state->next, name, offset, size);
put_partition(state, state->next++, offset, size);
ret = 1;
}
break;
}
ptr++;
}
while (!done);
printk(KERN_INFO "parse_tegrapart: done without mbr\n");
return ret;
}
/**
* efi_partition(struct parsed_partitions *state)
* @state
*
* Description: called from check.c, if the disk contains GPT
* partitions, sets up partition entries in the kernel.
*
* If the first block on the disk is a legacy MBR,
* it will get handled by msdos_partition().
* If it's a Protective MBR, we'll handle it here.
*
* We do not create a Linux partition for GPT, but
* only for the actual data partitions.
* Returns:
* -1 if unable to read the partition table
* 0 if this isn't our partition table
* 1 if successful
*
*/
int efi_partition(struct parsed_partitions *state)
{
char* partition_name = NULL;
gpt_header *gpt = NULL;
gpt_entry *ptes = NULL;
u32 i;
unsigned ssz = bdev_logical_block_size(state->bdev) / 512;
u8 unparsed_guid[37];
partition_name = kzalloc(sizeof(ptes->partition_name), GFP_KERNEL);
if (!partition_name)
return 0;
if (!find_valid_gpt(state, &gpt, &ptes) || !gpt || !ptes) {
kfree(gpt);
kfree(ptes);
kfree(partition_name);
return 0;
}
pr_debug("GUID Partition Table is valid! Yea!\n");
for (i = 0; i < le32_to_cpu(gpt->num_partition_entries) && i < state->limit-1; i++) {
int partition_name_len;
struct partition_meta_info *info;
unsigned label_count = 0;
unsigned label_max;
u64 start = le64_to_cpu(ptes[i].starting_lba);
u64 size = le64_to_cpu(ptes[i].ending_lba) -
le64_to_cpu(ptes[i].starting_lba) + 1ULL;
if (!is_pte_valid(&ptes[i], last_lba(state->bdev)))
continue;
partition_name_len = utf16s_to_utf8s(ptes[i].partition_name,
sizeof(ptes[i].partition_name),
UTF16_LITTLE_ENDIAN,
partition_name,
sizeof(ptes[i].partition_name));
#ifdef CONFIG_APANIC_ON_MMC
if(strncmp(partition_name,CONFIG_APANIC_PLABEL,partition_name_len) == 0) {
apanic_partition_start = start * ssz;
apanic_partition_size = size * ssz;
pr_debug("apanic partition found starts at %lu \r\n",
apanic_partition_start);
pr_debug("apanic partition size = %lu\n",
apanic_partition_size);
}
#endif
put_partition(state, i+1, start * ssz, size * ssz);
/* If this is a RAID volume, tell md */
if (!efi_guidcmp(ptes[i].partition_type_guid,
PARTITION_LINUX_RAID_GUID))
state->parts[i + 1].flags = ADDPART_FLAG_RAID;
info = &state->parts[i + 1].info;
/* Instead of doing a manual swap to big endian, reuse the
* common ASCII hex format as the interim.
*/
efi_guid_unparse(&ptes[i].unique_partition_guid, unparsed_guid);
part_pack_uuid(unparsed_guid, info->uuid);
/* Naively convert UTF16-LE to 7 bits. */
label_max = min(sizeof(info->volname) - 1,
sizeof(ptes[i].partition_name));
info->volname[label_max] = 0;
while (label_count < label_max) {
u8 c = ptes[i].partition_name[label_count] & 0xff;
if (c && !isprint(c))
c = '!';
info->volname[label_count] = c;
label_count++;
}
state->parts[i + 1].has_info = true;
#ifdef CONFIG_APANIC_ON_MMC
if(strncmp(info->volname,CONFIG_APANIC_PLABEL,label_count) == 0) {
apanic_partition_start = start * ssz;
pr_debug("apanic partition found starts at %lu \r\n", apanic_partition_start);
}
#endif
}
kfree(ptes);
kfree(gpt);
kfree(partition_name);
strlcat(state->pp_buf, "\n", PAGE_SIZE);
return 1;
}
/* fd_create_virtdevice(): (Part of se_subsystem_api_t template)
*
*
*/
static struct se_device *fd_create_virtdevice(
struct se_hba *hba,
struct se_subsystem_dev *se_dev,
void *p)
{
char *dev_p = NULL;
struct se_device *dev;
struct se_dev_limits dev_limits;
struct queue_limits *limits;
struct fd_dev *fd_dev = p;
struct fd_host *fd_host = hba->hba_ptr;
mm_segment_t old_fs;
struct file *file;
struct inode *inode = NULL;
int dev_flags = 0, flags, ret = -EINVAL;
memset(&dev_limits, 0, sizeof(struct se_dev_limits));
old_fs = get_fs();
set_fs(get_ds());
dev_p = getname(fd_dev->fd_dev_name);
set_fs(old_fs);
if (IS_ERR(dev_p)) {
pr_err("getname(%s) failed: %lu\n",
fd_dev->fd_dev_name, IS_ERR(dev_p));
ret = PTR_ERR(dev_p);
goto fail;
}
/*
* Use O_DSYNC by default instead of O_SYNC to forgo syncing
* of pure timestamp updates.
*/
flags = O_RDWR | O_CREAT | O_LARGEFILE | O_DSYNC;
file = filp_open(dev_p, flags, 0600);
if (IS_ERR(file)) {
pr_err("filp_open(%s) failed\n", dev_p);
ret = PTR_ERR(file);
goto fail;
}
if (!file || !file->f_dentry) {
pr_err("filp_open(%s) failed\n", dev_p);
goto fail;
}
fd_dev->fd_file = file;
/*
* If using a block backend with this struct file, we extract
* fd_dev->fd_[block,dev]_size from struct block_device.
*
* Otherwise, we use the passed fd_size= from configfs
*/
inode = file->f_mapping->host;
if (S_ISBLK(inode->i_mode)) {
struct request_queue *q;
unsigned long long dev_size;
/*
* Setup the local scope queue_limits from struct request_queue->limits
* to pass into transport_add_device_to_core_hba() as struct se_dev_limits.
*/
q = bdev_get_queue(inode->i_bdev);
limits = &dev_limits.limits;
limits->logical_block_size = bdev_logical_block_size(inode->i_bdev);
limits->max_hw_sectors = queue_max_hw_sectors(q);
limits->max_sectors = queue_max_sectors(q);
/*
* Determine the number of bytes from i_size_read() minus
* one (1) logical sector from underlying struct block_device
*/
fd_dev->fd_block_size = bdev_logical_block_size(inode->i_bdev);
dev_size = (i_size_read(file->f_mapping->host) -
fd_dev->fd_block_size);
pr_debug("FILEIO: Using size: %llu bytes from struct"
" block_device blocks: %llu logical_block_size: %d\n",
dev_size, div_u64(dev_size, fd_dev->fd_block_size),
fd_dev->fd_block_size);
} else {
if (!(fd_dev->fbd_flags & FBDF_HAS_SIZE)) {
pr_err("FILEIO: Missing fd_dev_size="
" parameter, and no backing struct"
" block_device\n");
goto fail;
}
limits = &dev_limits.limits;
limits->logical_block_size = FD_BLOCKSIZE;
limits->max_hw_sectors = FD_MAX_SECTORS;
limits->max_sectors = FD_MAX_SECTORS;
fd_dev->fd_block_size = FD_BLOCKSIZE;
}
dev_limits.hw_queue_depth = FD_MAX_DEVICE_QUEUE_DEPTH;
dev_limits.queue_depth = FD_DEVICE_QUEUE_DEPTH;
dev = transport_add_device_to_core_hba(hba, &fileio_template,
se_dev, dev_flags, fd_dev,
&dev_limits, "FILEIO", FD_VERSION);
if (!dev)
goto fail;
fd_dev->fd_dev_id = fd_host->fd_host_dev_id_count++;
fd_dev->fd_queue_depth = dev->queue_depth;
pr_debug("CORE_FILE[%u] - Added TCM FILEIO Device ID: %u at %s,"
" %llu total bytes\n", fd_host->fd_host_id, fd_dev->fd_dev_id,
fd_dev->fd_dev_name, fd_dev->fd_dev_size);
putname(dev_p);
return dev;
fail:
if (fd_dev->fd_file) {
filp_close(fd_dev->fd_file, NULL);
fd_dev->fd_file = NULL;
}
putname(dev_p);
return ERR_PTR(ret);
}
/**
* efi_partition(struct parsed_partitions *state)
* @state
*
* Description: called from check.c, if the disk contains GPT
* partitions, sets up partition entries in the kernel.
*
* If the first block on the disk is a legacy MBR,
* it will get handled by msdos_partition().
* If it's a Protective MBR, we'll handle it here.
*
* We do not create a Linux partition for GPT, but
* only for the actual data partitions.
* Returns:
* -1 if unable to read the partition table
* 0 if this isn't our partition table
* 1 if successful
*
*/
int efi_partition(struct parsed_partitions *state)
{
gpt_header *gpt = NULL;
gpt_entry *ptes = NULL;
u32 i;
unsigned ssz = bdev_logical_block_size(state->bdev) / 512;
if (!find_valid_gpt(state, &gpt, &ptes) || !gpt || !ptes) {
kfree(gpt);
kfree(ptes);
return 0;
}
pr_debug("GUID Partition Table is valid! Yea!\n");
for (i = 0; i < le32_to_cpu(gpt->num_partition_entries) && i < state->limit-1; i++) {
u64 start = le64_to_cpu(ptes[i].starting_lba);
u64 size = le64_to_cpu(ptes[i].ending_lba) -
le64_to_cpu(ptes[i].starting_lba) + 1ULL;
u8 name[sizeof(ptes->partition_name) / sizeof(efi_char16_t)];
int len;
if (!is_pte_valid(&ptes[i], last_lba(state->bdev)))
continue;
len = utf16s_to_utf8s(ptes[i].partition_name,
sizeof(ptes[i].partition_name) /
sizeof(efi_char16_t),
UTF16_LITTLE_ENDIAN, name,
sizeof(name));
put_named_partition(state, i+1, start * ssz, size * ssz,
name, len);
{
#define ADDPART_FLAG_QISDA_READONLY 32
u64 *attributes = (u64 *) &ptes[i].attributes;
if (*attributes & 0xD000000000000000ULL) {
pr_debug("guid partition attributes! set attributes by Qisda backdoor!\n");
if (*attributes & 0x1000000000000000ULL)
state->parts[i+1].flags |= ADDPART_FLAG_QISDA_READONLY;
}
}
/* If this is a RAID volume, tell md */
if (!efi_guidcmp(ptes[i].partition_type_guid,
PARTITION_LINUX_RAID_GUID))
state->parts[i + 1].flags = ADDPART_FLAG_RAID;
}
kfree(ptes);
kfree(gpt);
strlcat(state->pp_buf, "\n", PAGE_SIZE);
return 1;
}
unsigned long vbd_secsize(struct vbd *vbd)
{
return bdev_logical_block_size(vbd->bdev);
}
/**
* efi_partition(struct parsed_partitions *state, struct block_device *bdev)
* @state
* @bdev
*
* Description: called from check.c, if the disk contains GPT
* partitions, sets up partition entries in the kernel.
*
* If the first block on the disk is a legacy MBR,
* it will get handled by msdos_partition().
* If it's a Protective MBR, we'll handle it here.
*
* We do not create a Linux partition for GPT, but
* only for the actual data partitions.
* Returns:
* -1 if unable to read the partition table
* 0 if this isn't our partition table
* 1 if successful
*
*/
int
efi_partition(struct parsed_partitions *state, struct block_device *bdev)
{
gpt_header *gpt = NULL;
gpt_entry *ptes = NULL;
u32 i;
unsigned ssz = bdev_logical_block_size(bdev) / 512;
u8 unparsed_guid[37];
if (!find_valid_gpt(bdev, &gpt, &ptes) || !gpt || !ptes) {
kfree(gpt);
kfree(ptes);
return 0;
}
pr_debug("GUID Partition Table is valid! Yea!\n");
for (i = 0; i < le32_to_cpu(gpt->num_partition_entries) && i < state->limit-1; i++) {
struct partition_meta_info *info;
unsigned label_count = 0;
unsigned label_max;
u64 start = le64_to_cpu(ptes[i].starting_lba);
u64 size = le64_to_cpu(ptes[i].ending_lba) -
le64_to_cpu(ptes[i].starting_lba) + 1ULL;
if (!is_pte_valid(&ptes[i], last_lba(bdev)))
continue;
put_partition(state, i+1, start * ssz, size * ssz);
/* If this is a RAID volume, tell md */
if (!efi_guidcmp(ptes[i].partition_type_guid,
PARTITION_LINUX_RAID_GUID))
state->parts[i+1].flags = 1;
info = &state->parts[i + 1].info;
/* The EFI specification diverges from RFC 4122 with respect to
* the packed storage of its UUIDs. efi_guid_unparse unpacks to
* a common ASCII representation, which allows part_pack_uuid to
* pack it in the standard big endian layout for use by the rest
* of the kernel.
*/
efi_guid_unparse(&ptes[i].unique_partition_guid, unparsed_guid);
part_pack_uuid(unparsed_guid, info->uuid);
/* Naively convert UTF16-LE to 7 bits. */
label_max = min(sizeof(info->volname) - 1,
sizeof(ptes[i].partition_name));
info->volname[label_max] = 0;
while (label_count < label_max) {
u8 c = ptes[i].partition_name[label_count] & 0xff;
if (c && !isprint(c))
c = '!';
info->volname[label_count] = c;
label_count++;
}
state->parts[i + 1].has_info = true;
}
kfree(ptes);
kfree(gpt);
printk("\n");
return 1;
}
static int iblock_configure_device(struct se_device *dev)
{
struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
struct request_queue *q;
struct block_device *bd = NULL;
fmode_t mode;
int ret = -ENOMEM;
if (!(ib_dev->ibd_flags & IBDF_HAS_UDEV_PATH)) {
pr_err("Missing udev_path= parameters for IBLOCK\n");
return -EINVAL;
}
ib_dev->ibd_bio_set = bioset_create(IBLOCK_BIO_POOL_SIZE, 0);
if (!ib_dev->ibd_bio_set) {
pr_err("IBLOCK: Unable to create bioset\n");
goto out;
}
pr_debug( "IBLOCK: Claiming struct block_device: %s\n",
ib_dev->ibd_udev_path);
mode = FMODE_READ|FMODE_EXCL;
if (!ib_dev->ibd_readonly)
mode |= FMODE_WRITE;
bd = blkdev_get_by_path(ib_dev->ibd_udev_path, mode, ib_dev);
if (IS_ERR(bd)) {
ret = PTR_ERR(bd);
goto out_free_bioset;
}
ib_dev->ibd_bd = bd;
q = bdev_get_queue(bd);
dev->dev_attrib.hw_block_size = bdev_logical_block_size(bd);
dev->dev_attrib.hw_max_sectors = queue_max_hw_sectors(q);
dev->dev_attrib.hw_queue_depth = q->nr_requests;
/*
* Check if the underlying struct block_device request_queue supports
* the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM
* in ATA and we need to set TPE=1
*/
if (blk_queue_discard(q)) {
dev->dev_attrib.max_unmap_lba_count =
q->limits.max_discard_sectors;
/*
* Currently hardcoded to 1 in Linux/SCSI code..
*/
dev->dev_attrib.max_unmap_block_desc_count = 1;
dev->dev_attrib.unmap_granularity =
q->limits.discard_granularity >> 9;
dev->dev_attrib.unmap_granularity_alignment =
q->limits.discard_alignment;
pr_debug("IBLOCK: BLOCK Discard support available,"
" disabled by default\n");
}
/*
* Enable write same emulation for IBLOCK and use 0xFFFF as
* the smaller WRITE_SAME(10) only has a two-byte block count.
*/
dev->dev_attrib.max_write_same_len = 0xFFFF;
if (blk_queue_nonrot(q))
dev->dev_attrib.is_nonrot = 1;
return 0;
out_free_bioset:
bioset_free(ib_dev->ibd_bio_set);
ib_dev->ibd_bio_set = NULL;
out:
return ret;
}
/**
* find_valid_gpt() - Search disk for valid GPT headers and PTEs
* @state
* @gpt is a GPT header ptr, filled on return.
* @ptes is a PTEs ptr, filled on return.
* Description: Returns 1 if valid, 0 on error.
* If valid, returns pointers to newly allocated GPT header and PTEs.
* Validity depends on PMBR being valid (or being overridden by the
* 'gpt' kernel command line option) and finding either the Primary
* GPT header and PTEs valid, or the Alternate GPT header and PTEs
* valid. If the Primary GPT header is not valid, the Alternate GPT header
* is not checked unless the 'gpt' kernel command line option is passed.
* This protects against devices which misreport their size, and forces
* the user to decide to use the Alternate GPT.
*/
static int find_valid_gpt(struct parsed_partitions *state, gpt_header **gpt,
gpt_entry **ptes)
{
int good_pgpt = 0, good_agpt = 0, good_pmbr = 0;
gpt_header *pgpt = NULL, *agpt = NULL;
gpt_entry *pptes = NULL, *aptes = NULL;
legacy_mbr *legacymbr;
u64 lastlba;
if (!ptes)
return 0;
lastlba = last_lba(state->bdev);
#if 0 // merged from msm8960-gb by ZTE_BOOT_JIA_20120105 jia.jia
if (!force_gpt) {
#else
if (force_gpt) {
#endif
/* This will be added to the EFI Spec. per Intel after v1.02. */
legacymbr = kzalloc(sizeof (*legacymbr), GFP_KERNEL);
if (legacymbr) {
read_lba(state, 0, (u8 *) legacymbr,
sizeof (*legacymbr));
good_pmbr = is_pmbr_valid(legacymbr);
kfree(legacymbr);
}
if (!good_pmbr)
goto fail;
}
good_pgpt = is_gpt_valid(state, GPT_PRIMARY_PARTITION_TABLE_LBA,
&pgpt, &pptes);
if (good_pgpt)
good_agpt = is_gpt_valid(state,
le64_to_cpu(pgpt->alternate_lba),
&agpt, &aptes);
if (!good_agpt && force_gpt)
good_agpt = is_gpt_valid(state, lastlba, &agpt, &aptes);
/* The obviously unsuccessful case */
if (!good_pgpt && !good_agpt)
goto fail;
compare_gpts(pgpt, agpt, lastlba);
/* The good cases */
if (good_pgpt) {
*gpt = pgpt;
*ptes = pptes;
kfree(agpt);
kfree(aptes);
if (!good_agpt) {
printk(KERN_WARNING
"Alternate GPT is invalid, "
"using primary GPT.\n");
}
return 1;
}
else if (good_agpt) {
*gpt = agpt;
*ptes = aptes;
kfree(pgpt);
kfree(pptes);
printk(KERN_WARNING
"Primary GPT is invalid, using alternate GPT.\n");
return 1;
}
fail:
kfree(pgpt);
kfree(agpt);
kfree(pptes);
kfree(aptes);
*gpt = NULL;
*ptes = NULL;
return 0;
}
/**
* efi_partition(struct parsed_partitions *state)
* @state
*
* Description: called from check.c, if the disk contains GPT
* partitions, sets up partition entries in the kernel.
*
* If the first block on the disk is a legacy MBR,
* it will get handled by msdos_partition().
* If it's a Protective MBR, we'll handle it here.
*
* We do not create a Linux partition for GPT, but
* only for the actual data partitions.
* Returns:
* -1 if unable to read the partition table
* 0 if this isn't our partition table
* 1 if successful
*
*/
int efi_partition(struct parsed_partitions *state)
{
gpt_header *gpt = NULL;
gpt_entry *ptes = NULL;
u32 i;
unsigned ssz = bdev_logical_block_size(state->bdev) / 512;
u8 unparsed_guid[37];
if (!find_valid_gpt(state, &gpt, &ptes) || !gpt || !ptes) {
kfree(gpt);
kfree(ptes);
return 0;
}
pr_debug("GUID Partition Table is valid! Yea!\n");
for (i = 0; i < le32_to_cpu(gpt->num_partition_entries) && i < state->limit-1; i++) {
struct partition_meta_info *info;
unsigned label_count = 0;
unsigned label_max;
u64 start = le64_to_cpu(ptes[i].starting_lba);
u64 size = le64_to_cpu(ptes[i].ending_lba) -
le64_to_cpu(ptes[i].starting_lba) + 1ULL;
if (!is_pte_valid(&ptes[i], last_lba(state->bdev)))
continue;
put_partition(state, i+1, start * ssz, size * ssz);
/* If this is a RAID volume, tell md */
if (!efi_guidcmp(ptes[i].partition_type_guid,
PARTITION_LINUX_RAID_GUID))
state->parts[i + 1].flags = ADDPART_FLAG_RAID;
info = &state->parts[i + 1].info;
/* Instead of doing a manual swap to big endian, reuse the
* common ASCII hex format as the interim.
*/
efi_guid_unparse(&ptes[i].unique_partition_guid, unparsed_guid);
part_pack_uuid(unparsed_guid, info->uuid);
/* Naively convert UTF16-LE to 7 bits. */
label_max = min(sizeof(info->volname) - 1,
sizeof(ptes[i].partition_name));
info->volname[label_max] = 0;
while (label_count < label_max) {
u8 c = ptes[i].partition_name[label_count] & 0xff;
if (c && !isprint(c))
c = '!';
info->volname[label_count] = c;
label_count++;
}
state->parts[i + 1].has_info = true;
}
kfree(ptes);
kfree(gpt);
strlcat(state->pp_buf, "\n", PAGE_SIZE);
return 1;
}
/**
* nilfs_sufile_trim_fs() - trim ioctl handle function
* @sufile: inode of segment usage file
* @range: fstrim_range structure
*
* start: First Byte to trim
* len: number of Bytes to trim from start
* minlen: minimum extent length in Bytes
*
* Decription: nilfs_sufile_trim_fs goes through all segments containing bytes
* from start to start+len. start is rounded up to the next block boundary
* and start+len is rounded down. For each clean segment blkdev_issue_discard
* function is invoked.
*
* Return Value: On success, 0 is returned or negative error code, otherwise.
*/
int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
{
struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
struct buffer_head *su_bh;
struct nilfs_segment_usage *su;
void *kaddr;
size_t n, i, susz = NILFS_MDT(sufile)->mi_entry_size;
sector_t seg_start, seg_end, start_block, end_block;
sector_t start = 0, nblocks = 0;
u64 segnum, segnum_end, minlen, len, max_blocks, ndiscarded = 0;
int ret = 0;
unsigned int sects_per_block;
sects_per_block = (1 << nilfs->ns_blocksize_bits) /
bdev_logical_block_size(nilfs->ns_bdev);
len = range->len >> nilfs->ns_blocksize_bits;
minlen = range->minlen >> nilfs->ns_blocksize_bits;
max_blocks = ((u64)nilfs->ns_nsegments * nilfs->ns_blocks_per_segment);
if (!len || range->start >= max_blocks << nilfs->ns_blocksize_bits)
return -EINVAL;
start_block = (range->start + nilfs->ns_blocksize - 1) >>
nilfs->ns_blocksize_bits;
/*
* range->len can be very large (actually, it is set to
* ULLONG_MAX by default) - truncate upper end of the range
* carefully so as not to overflow.
*/
if (max_blocks - start_block < len)
end_block = max_blocks - 1;
else
end_block = start_block + len - 1;
segnum = nilfs_get_segnum_of_block(nilfs, start_block);
segnum_end = nilfs_get_segnum_of_block(nilfs, end_block);
down_read(&NILFS_MDT(sufile)->mi_sem);
while (segnum <= segnum_end) {
n = nilfs_sufile_segment_usages_in_block(sufile, segnum,
segnum_end);
ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0,
&su_bh);
if (ret < 0) {
if (ret != -ENOENT)
goto out_sem;
/* hole */
segnum += n;
continue;
}
kaddr = kmap_atomic(su_bh->b_page, KM_USER0);
su = nilfs_sufile_block_get_segment_usage(sufile, segnum,
su_bh, kaddr);
for (i = 0; i < n; ++i, ++segnum, su = (void *)su + susz) {
if (!nilfs_segment_usage_clean(su))
continue;
nilfs_get_segment_range(nilfs, segnum, &seg_start,
&seg_end);
if (!nblocks) {
/* start new extent */
start = seg_start;
nblocks = seg_end - seg_start + 1;
continue;
}
if (start + nblocks == seg_start) {
/* add to previous extent */
nblocks += seg_end - seg_start + 1;
continue;
}
/* discard previous extent */
if (start < start_block) {
nblocks -= start_block - start;
start = start_block;
}
if (nblocks >= minlen) {
kunmap_atomic(kaddr, KM_USER0);
ret = compat_blkdev_issue_discard(
nilfs->ns_bdev, start * sects_per_block,
nblocks * sects_per_block, GFP_NOFS, 0);
if (ret < 0) {
put_bh(su_bh);
goto out_sem;
}
ndiscarded += nblocks;
kaddr = kmap_atomic(su_bh->b_page, KM_USER0);
su = nilfs_sufile_block_get_segment_usage(
sufile, segnum, su_bh, kaddr);
}
/* start new extent */
start = seg_start;
nblocks = seg_end - seg_start + 1;
}
kunmap_atomic(kaddr, KM_USER0);
put_bh(su_bh);
}
if (nblocks) {
/* discard last extent */
if (start < start_block) {
nblocks -= start_block - start;
start = start_block;
}
if (start + nblocks > end_block + 1)
nblocks = end_block - start + 1;
if (nblocks >= minlen) {
ret = compat_blkdev_issue_discard(
nilfs->ns_bdev, start * sects_per_block,
nblocks * sects_per_block, GFP_NOFS, 0);
if (!ret)
ndiscarded += nblocks;
}
}
out_sem:
up_read(&NILFS_MDT(sufile)->mi_sem);
range->len = ndiscarded << nilfs->ns_blocksize_bits;
return ret;
}
/**
* efi_partition(struct parsed_partitions *state)
* @state
*
* Description: called from check.c, if the disk contains GPT
* partitions, sets up partition entries in the kernel.
*
* If the first block on the disk is a legacy MBR,
* it will get handled by msdos_partition().
* If it's a Protective MBR, we'll handle it here.
*
* We do not create a Linux partition for GPT, but
* only for the actual data partitions.
* Returns:
* -1 if unable to read the partition table
* 0 if this isn't our partition table
* 1 if successful
*
*/
int efi_partition(struct parsed_partitions *state)
{
char* partition_name = NULL;
gpt_header *gpt = NULL;
gpt_entry *ptes = NULL;
u32 i;
unsigned ssz = bdev_logical_block_size(state->bdev) / 512;
partition_name = kzalloc(sizeof(ptes->partition_name), GFP_KERNEL);
if (!partition_name)
return 0;
if (!find_valid_gpt(state, &gpt, &ptes) || !gpt || !ptes) {
kfree(gpt);
kfree(ptes);
kfree(partition_name);
return 0;
}
pr_debug("GUID Partition Table is valid! Yea!\n");
proc_create("emmc", 0666, NULL, &emmc_partition_fops);
gpt_info.num_of_partitions = le32_to_cpu(gpt->num_partition_entries);
gpt_info.erase_size = bdev_erase_size(state->bdev) * ssz;
/*
* Not certain if there is a chance this function is called again with
* a different GPT. In case there is, free previously allocated memory
*/
kfree(gpt_info.partitions);
gpt_info.partitions = kzalloc(gpt_info.num_of_partitions
* sizeof(*gpt_info.partitions), GFP_KERNEL);
for (i = 0; i < le32_to_cpu(gpt->num_partition_entries) && i < state->limit-1; i++) {
int partition_name_len;
struct partition_meta_info *info;
unsigned label_count = 0;
unsigned label_max;
u64 start = le64_to_cpu(ptes[i].starting_lba);
u64 size = le64_to_cpu(ptes[i].ending_lba) -
le64_to_cpu(ptes[i].starting_lba) + 1ULL;
gpt_info.partitions[i].size = size * ssz;
if (!is_pte_valid(&ptes[i], last_lba(state->bdev)))
continue;
partition_name_len = utf16s_to_utf8s(ptes[i].partition_name,
sizeof(ptes[i].partition_name),
UTF16_LITTLE_ENDIAN,
partition_name,
sizeof(ptes[i].partition_name));
#ifdef CONFIG_APANIC_ON_MMC
if(strncmp(partition_name,CONFIG_APANIC_PLABEL,partition_name_len) == 0) {
apanic_partition_start = start * ssz;
apanic_partition_size = size * ssz;
pr_debug("apanic partition found starts at %lu \r\n",
apanic_partition_start);
pr_debug("apanic partition size = %lu\n",
apanic_partition_size);
}
#endif
put_partition(state, i+1, start * ssz, size * ssz);
/* If this is a RAID volume, tell md */
if (!efi_guidcmp(ptes[i].partition_type_guid,
PARTITION_LINUX_RAID_GUID))
state->parts[i + 1].flags = ADDPART_FLAG_RAID;
info = &state->parts[i + 1].info;
efi_guid_unparse(&ptes[i].unique_partition_guid, info->uuid);
/* Naively convert UTF16-LE to 7 bits. */
label_max = min(sizeof(info->volname) - 1,
sizeof(ptes[i].partition_name));
info->volname[label_max] = 0;
while (label_count < label_max) {
u8 c = ptes[i].partition_name[label_count] & 0xff;
if (c && !isprint(c))
c = '!';
info->volname[label_count] = c;
if (label_count <= partition_name_len)
gpt_info.partitions[i].volname[label_count] = c;
label_count++;
}
state->parts[i + 1].has_info = true;
#ifdef CONFIG_APANIC_ON_MMC
if(strncmp(info->volname,CONFIG_APANIC_PLABEL,label_count) == 0) {
apanic_partition_start = start * ssz;
pr_debug("apanic partition found starts at %lu \r\n", apanic_partition_start);
}
#endif
}
kfree(ptes);
kfree(gpt);
kfree(partition_name);
strlcat(state->pp_buf, "\n", PAGE_SIZE);
return 1;
}
static void
tegra_msdos_parse_extended(struct parsed_partitions *state, struct block_device *bdev,
u64 mbr_offset, u64 first_sector, u64 first_size)
{
struct partition *p;
Sector sect;
unsigned char *data;
u64 this_sector, this_size;
int sector_size = bdev_logical_block_size(bdev) / 512;
int loopct = 0; /* number of links followed
without finding a data partition */
int i;
this_sector = first_sector;
this_size = first_size;
while (1) {
if (++loopct > 2) {
printk(KERN_INFO "tegra_msdos_parse_extended: loopcnt>2. exit\n");
return;
}
printk(KERN_INFO "tegra_msdos_parse_extended: read part sector, start=%llu+%llu size=%llu\n",
mbr_offset, this_sector, this_size);
data = read_dev_sector(bdev, mbr_offset+this_sector, §);
if (!data) {
printk(KERN_INFO "tegra_msdos_parse_extended: read error. exit\n");
return;
}
if (!msdos_magic_present(data + 510)) {
printk(KERN_INFO "tegra_msdos_parse_extended: no msdos magic. exit\n");
goto done;
}
p = (struct partition *) (data + 0x1be);
/*
* First process the data partition(s)
*/
for (i=0; i<4; i++, p++) {
u64 offs, size, next;
if (!NR_SECTS(p) || is_extended_partition(p))
continue;
offs = START_SECT(p)*sector_size;
size = NR_SECTS(p)*sector_size;
next = this_sector + offs;
if (i >= 2) {
if (offs + size > this_size)
continue;
if (next < first_sector)
continue;
if (next + size > first_sector + first_size)
continue;
}
printk(KERN_INFO "tegra_msdos_parse_extended: put_partition %d start=%llu+%llu size=%llu\n",
state->next, mbr_offset, next, size);
put_partition(state, state->next++, mbr_offset+next, size);
loopct = 0;
}
printk(KERN_INFO "tegra_msdos_parse_extended: done with this sector\n");
p -= 4;
for (i=0; i<4; i++, p++)
if (NR_SECTS(p) && is_extended_partition(p)) {
printk(KERN_INFO "tegra_msdos_parse_extended: extended part slot %d\n", i+1);
break;
}
if (i == 4)
goto done; /* nothing left to do */
this_sector = first_sector + START_SECT(p) * sector_size;
this_size = NR_SECTS(p) * sector_size;
put_dev_sector(sect);
}
done:
printk(KERN_INFO "tegra_msdos_parse_extended: done\n");
put_dev_sector(sect);
}
static int fsg_lun_open(struct fsg_lun *curlun, const char *filename)
{
int ro;
struct file *filp = NULL;
int rc = -EINVAL;
struct inode *inode = NULL;
struct backing_dev_info *bdi;
loff_t size;
loff_t num_sectors;
loff_t min_sectors;
unsigned int blkbits;
unsigned int blksize;
/* R/W if we can, R/O if we must */
ro = curlun->initially_ro;
if (!ro) {
filp = filp_open(filename, O_RDWR | O_LARGEFILE, 0);
if (PTR_ERR(filp) == -EROFS || PTR_ERR(filp) == -EACCES)
ro = 1;
}
if (ro)
filp = filp_open(filename, O_RDONLY | O_LARGEFILE, 0);
if (IS_ERR(filp)) {
LINFO(curlun, "unable to open backing file: %s\n", filename);
return PTR_ERR(filp);
}
if (!(filp->f_mode & FMODE_WRITE))
ro = 1;
inode = file_inode(filp);
if ((!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))) {
LINFO(curlun, "invalid file type: %s\n", filename);
goto out;
}
/*
* If we can't read the file, it's no good.
* If we can't write the file, use it read-only.
*/
if (!(filp->f_op->read || filp->f_op->aio_read)) {
LINFO(curlun, "file not readable: %s\n", filename);
goto out;
}
if (!(filp->f_op->write || filp->f_op->aio_write))
ro = 1;
size = i_size_read(inode->i_mapping->host);
if (size < 0) {
LINFO(curlun, "unable to find file size: %s\n", filename);
rc = (int) size;
goto out;
}
if (curlun->cdrom) {
blksize = 2048;
blkbits = 11;
} else if (inode->i_bdev) {
blksize = bdev_logical_block_size(inode->i_bdev);
blkbits = blksize_bits(blksize);
bdi = &inode->i_bdev->bd_queue->backing_dev_info;
if (bdi->capabilities & BDI_CAP_STRICTLIMIT) {
curlun->max_ratio = bdi->max_ratio;
curlun->nofua = 1;
if (bdi_set_max_ratio(bdi, uicc_ums_max_ratio))
pr_debug("%s, error in setting max_ratio\n",
__func__);
}
} else {
blksize = 512;
blkbits = 9;
}
num_sectors = size >> blkbits; /* File size in logic-block-size blocks */
min_sectors = 1;
if (curlun->cdrom) {
min_sectors = 300; /* Smallest track is 300 frames */
if (num_sectors >= 256*60*75) {
num_sectors = 256*60*75 - 1;
LINFO(curlun, "file too big: %s\n", filename);
LINFO(curlun, "using only first %d blocks\n",
(int) num_sectors);
}
}
if (num_sectors < min_sectors) {
LINFO(curlun, "file too small: %s\n", filename);
rc = -ETOOSMALL;
goto out;
}
if (fsg_lun_is_open(curlun))
fsg_lun_close(curlun);
curlun->blksize = blksize;
curlun->blkbits = blkbits;
curlun->ro = ro;
curlun->filp = filp;
curlun->file_length = size;
curlun->num_sectors = num_sectors;
LDBG(curlun, "open backing file: %s\n", filename);
return 0;
out:
fput(filp);
return rc;
}
static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
unsigned int argc, char **argv,
struct dm_dev *dev)
{
enum sync sync = DEFAULTSYNC;
struct log_c *lc;
uint32_t region_size;
unsigned int region_count;
size_t bitset_size, buf_size;
int r;
char dummy;
if (argc < 1 || argc > 2) {
DMWARN("wrong number of arguments to dirty region log");
return -EINVAL;
}
if (argc > 1) {
if (!strcmp(argv[1], "sync"))
sync = FORCESYNC;
else if (!strcmp(argv[1], "nosync"))
sync = NOSYNC;
else {
DMWARN("unrecognised sync argument to "
"dirty region log: %s", argv[1]);
return -EINVAL;
}
}
if (sscanf(argv[0], "%u%c", ®ion_size, &dummy) != 1 ||
!_check_region_size(ti, region_size)) {
DMWARN("invalid region size %s", argv[0]);
return -EINVAL;
}
region_count = dm_sector_div_up(ti->len, region_size);
lc = kmalloc(sizeof(*lc), GFP_KERNEL);
if (!lc) {
DMWARN("couldn't allocate core log");
return -ENOMEM;
}
lc->ti = ti;
lc->touched_dirtied = 0;
lc->touched_cleaned = 0;
lc->flush_failed = 0;
lc->region_size = region_size;
lc->region_count = region_count;
lc->sync = sync;
/*
* Work out how many "unsigned long"s we need to hold the bitset.
*/
bitset_size = dm_round_up(region_count,
sizeof(*lc->clean_bits) << BYTE_SHIFT);
bitset_size >>= BYTE_SHIFT;
lc->bitset_uint32_count = bitset_size / sizeof(*lc->clean_bits);
/*
* Disk log?
*/
if (!dev) {
lc->clean_bits = vmalloc(bitset_size);
if (!lc->clean_bits) {
DMWARN("couldn't allocate clean bitset");
kfree(lc);
return -ENOMEM;
}
lc->disk_header = NULL;
} else {
lc->log_dev = dev;
lc->log_dev_failed = 0;
lc->log_dev_flush_failed = 0;
lc->header_location.bdev = lc->log_dev->bdev;
lc->header_location.sector = 0;
/*
* Buffer holds both header and bitset.
*/
buf_size =
dm_round_up((LOG_OFFSET << SECTOR_SHIFT) + bitset_size,
bdev_logical_block_size(lc->header_location.
bdev));
if (buf_size > i_size_read(dev->bdev->bd_inode)) {
DMWARN("log device %s too small: need %llu bytes",
dev->name, (unsigned long long)buf_size);
kfree(lc);
return -EINVAL;
}
lc->header_location.count = buf_size >> SECTOR_SHIFT;
lc->io_req.mem.type = DM_IO_VMA;
lc->io_req.notify.fn = NULL;
lc->io_req.client = dm_io_client_create();
if (IS_ERR(lc->io_req.client)) {
r = PTR_ERR(lc->io_req.client);
DMWARN("couldn't allocate disk io client");
kfree(lc);
return r;
}
lc->disk_header = vmalloc(buf_size);
if (!lc->disk_header) {
DMWARN("couldn't allocate disk log buffer");
dm_io_client_destroy(lc->io_req.client);
kfree(lc);
return -ENOMEM;
}
lc->io_req.mem.ptr.vma = lc->disk_header;
lc->clean_bits = (void *)lc->disk_header +
(LOG_OFFSET << SECTOR_SHIFT);
}
memset(lc->clean_bits, -1, bitset_size);
lc->sync_bits = vmalloc(bitset_size);
if (!lc->sync_bits) {
DMWARN("couldn't allocate sync bitset");
if (!dev)
vfree(lc->clean_bits);
else
dm_io_client_destroy(lc->io_req.client);
vfree(lc->disk_header);
kfree(lc);
return -ENOMEM;
}
memset(lc->sync_bits, (sync == NOSYNC) ? -1 : 0, bitset_size);
lc->sync_count = (sync == NOSYNC) ? region_count : 0;
lc->recovering_bits = vzalloc(bitset_size);
if (!lc->recovering_bits) {
DMWARN("couldn't allocate sync bitset");
vfree(lc->sync_bits);
if (!dev)
vfree(lc->clean_bits);
else
dm_io_client_destroy(lc->io_req.client);
vfree(lc->disk_header);
kfree(lc);
return -ENOMEM;
}
lc->sync_search = 0;
log->context = lc;
return 0;
}
/* fd_create_virtdevice(): (Part of se_subsystem_api_t template)
*
*
*/
static struct se_device *fd_create_virtdevice(
struct se_hba *hba,
struct se_subsystem_dev *se_dev,
void *p)
{
char *dev_p = NULL;
struct se_device *dev;
struct se_dev_limits dev_limits;
struct queue_limits *limits;
struct fd_dev *fd_dev = p;
struct fd_host *fd_host = hba->hba_ptr;
mm_segment_t old_fs;
struct file *file;
struct inode *inode = NULL;
int dev_flags = 0, flags, ret = -EINVAL;
memset(&dev_limits, 0, sizeof(struct se_dev_limits));
old_fs = get_fs();
set_fs(get_ds());
dev_p = getname(fd_dev->fd_dev_name);
set_fs(old_fs);
if (IS_ERR(dev_p)) {
pr_err("getname(%s) failed: %lu\n",
fd_dev->fd_dev_name, IS_ERR(dev_p));
ret = PTR_ERR(dev_p);
goto fail;
}
/*
* Use O_DSYNC by default instead of O_SYNC to forgo syncing
* of pure timestamp updates.
*/
flags = O_RDWR | O_CREAT | O_LARGEFILE | O_DSYNC;
/*
* Optionally allow fd_buffered_io=1 to be enabled for people
* who want use the fs buffer cache as an WriteCache mechanism.
*
* This means that in event of a hard failure, there is a risk
* of silent data-loss if the SCSI client has *not* performed a
* forced unit access (FUA) write, or issued SYNCHRONIZE_CACHE
* to write-out the entire device cache.
*/
if (fd_dev->fbd_flags & FDBD_HAS_BUFFERED_IO_WCE) {
pr_debug("FILEIO: Disabling O_DSYNC, using buffered FILEIO\n");
flags &= ~O_DSYNC;
}
file = filp_open(dev_p, flags, 0600);
if (IS_ERR(file)) {
pr_err("filp_open(%s) failed\n", dev_p);
ret = PTR_ERR(file);
goto fail;
}
if (!file || !file->f_dentry) {
pr_err("filp_open(%s) failed\n", dev_p);
goto fail;
}
fd_dev->fd_file = file;
/*
* If using a block backend with this struct file, we extract
* fd_dev->fd_[block,dev]_size from struct block_device.
*
* Otherwise, we use the passed fd_size= from configfs
*/
inode = file->f_mapping->host;
if (S_ISBLK(inode->i_mode)) {
struct request_queue *q;
unsigned long long dev_size;
/*
* Setup the local scope queue_limits from struct request_queue->limits
* to pass into transport_add_device_to_core_hba() as struct se_dev_limits.
*/
q = bdev_get_queue(inode->i_bdev);
limits = &dev_limits.limits;
limits->logical_block_size = bdev_logical_block_size(inode->i_bdev);
limits->max_hw_sectors = queue_max_hw_sectors(q);
limits->max_sectors = queue_max_sectors(q);
/*
* Determine the number of bytes from i_size_read() minus
* one (1) logical sector from underlying struct block_device
*/
fd_dev->fd_block_size = bdev_logical_block_size(inode->i_bdev);
dev_size = (i_size_read(file->f_mapping->host) -
fd_dev->fd_block_size);
pr_debug("FILEIO: Using size: %llu bytes from struct"
" block_device blocks: %llu logical_block_size: %d\n",
dev_size, div_u64(dev_size, fd_dev->fd_block_size),
fd_dev->fd_block_size);
} else {
if (!(fd_dev->fbd_flags & FBDF_HAS_SIZE)) {
pr_err("FILEIO: Missing fd_dev_size="
" parameter, and no backing struct"
" block_device\n");
goto fail;
}
limits = &dev_limits.limits;
limits->logical_block_size = FD_BLOCKSIZE;
limits->max_hw_sectors = FD_MAX_SECTORS;
limits->max_sectors = FD_MAX_SECTORS;
fd_dev->fd_block_size = FD_BLOCKSIZE;
}
dev_limits.hw_queue_depth = FD_MAX_DEVICE_QUEUE_DEPTH;
dev_limits.queue_depth = FD_DEVICE_QUEUE_DEPTH;
dev = transport_add_device_to_core_hba(hba, &fileio_template,
se_dev, dev_flags, fd_dev,
&dev_limits, "FILEIO", FD_VERSION);
if (!dev)
goto fail;
if (fd_dev->fbd_flags & FDBD_HAS_BUFFERED_IO_WCE) {
pr_debug("FILEIO: Forcing setting of emulate_write_cache=1"
" with FDBD_HAS_BUFFERED_IO_WCE\n");
dev->se_sub_dev->se_dev_attrib.emulate_write_cache = 1;
}
fd_dev->fd_dev_id = fd_host->fd_host_dev_id_count++;
fd_dev->fd_queue_depth = dev->queue_depth;
pr_debug("CORE_FILE[%u] - Added TCM FILEIO Device ID: %u at %s,"
" %llu total bytes\n", fd_host->fd_host_id, fd_dev->fd_dev_id,
fd_dev->fd_dev_name, fd_dev->fd_dev_size);
putname(dev_p);
return dev;
fail:
if (fd_dev->fd_file) {
filp_close(fd_dev->fd_file, NULL);
fd_dev->fd_file = NULL;
}
putname(dev_p);
return ERR_PTR(ret);
}
static int fd_configure_device(struct se_device *dev)
{
struct fd_dev *fd_dev = FD_DEV(dev);
struct fd_host *fd_host = dev->se_hba->hba_ptr;
struct file *file;
struct inode *inode = NULL;
int flags, ret = -EINVAL;
if (!(fd_dev->fbd_flags & FBDF_HAS_PATH)) {
pr_err("Missing fd_dev_name=\n");
return -EINVAL;
}
/*
* Use O_DSYNC by default instead of O_SYNC to forgo syncing
* of pure timestamp updates.
*/
flags = O_RDWR | O_CREAT | O_LARGEFILE | O_DSYNC;
/*
* Optionally allow fd_buffered_io=1 to be enabled for people
* who want use the fs buffer cache as an WriteCache mechanism.
*
* This means that in event of a hard failure, there is a risk
* of silent data-loss if the SCSI client has *not* performed a
* forced unit access (FUA) write, or issued SYNCHRONIZE_CACHE
* to write-out the entire device cache.
*/
if (fd_dev->fbd_flags & FDBD_HAS_BUFFERED_IO_WCE) {
pr_debug("FILEIO: Disabling O_DSYNC, using buffered FILEIO\n");
flags &= ~O_DSYNC;
}
file = filp_open(fd_dev->fd_dev_name, flags, 0600);
if (IS_ERR(file)) {
pr_err("filp_open(%s) failed\n", fd_dev->fd_dev_name);
ret = PTR_ERR(file);
goto fail;
}
fd_dev->fd_file = file;
/*
* If using a block backend with this struct file, we extract
* fd_dev->fd_[block,dev]_size from struct block_device.
*
* Otherwise, we use the passed fd_size= from configfs
*/
inode = file->f_mapping->host;
if (S_ISBLK(inode->i_mode)) {
struct request_queue *q = bdev_get_queue(inode->i_bdev);
unsigned long long dev_size;
fd_dev->fd_block_size = bdev_logical_block_size(inode->i_bdev);
/*
* Determine the number of bytes from i_size_read() minus
* one (1) logical sector from underlying struct block_device
*/
dev_size = (i_size_read(file->f_mapping->host) -
fd_dev->fd_block_size);
pr_debug("FILEIO: Using size: %llu bytes from struct"
" block_device blocks: %llu logical_block_size: %d\n",
dev_size, div_u64(dev_size, fd_dev->fd_block_size),
fd_dev->fd_block_size);
/*
* Check if the underlying struct block_device request_queue supports
* the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM
* in ATA and we need to set TPE=1
*/
if (blk_queue_discard(q)) {
dev->dev_attrib.max_unmap_lba_count =
q->limits.max_discard_sectors;
/*
* Currently hardcoded to 1 in Linux/SCSI code..
*/
dev->dev_attrib.max_unmap_block_desc_count = 1;
dev->dev_attrib.unmap_granularity =
q->limits.discard_granularity >> 9;
dev->dev_attrib.unmap_granularity_alignment =
q->limits.discard_alignment;
pr_debug("IFILE: BLOCK Discard support available,"
" disabled by default\n");
}
/*
* Enable write same emulation for IBLOCK and use 0xFFFF as
* the smaller WRITE_SAME(10) only has a two-byte block count.
*/
dev->dev_attrib.max_write_same_len = 0xFFFF;
if (blk_queue_nonrot(q))
dev->dev_attrib.is_nonrot = 1;
} else {
if (!(fd_dev->fbd_flags & FBDF_HAS_SIZE)) {
static unsigned long long iblock_emulate_read_cap_with_block_size(
struct se_device *dev,
struct block_device *bd,
struct request_queue *q)
{
unsigned long long blocks_long = (div_u64(i_size_read(bd->bd_inode),
bdev_logical_block_size(bd)) - 1);
u32 block_size = bdev_logical_block_size(bd);
if (block_size == dev->se_sub_dev->se_dev_attrib.block_size)
return blocks_long;
switch (block_size) {
case 4096:
switch (dev->se_sub_dev->se_dev_attrib.block_size) {
case 2048:
blocks_long <<= 1;
break;
case 1024:
blocks_long <<= 2;
break;
case 512:
blocks_long <<= 3;
default:
break;
}
break;
case 2048:
switch (dev->se_sub_dev->se_dev_attrib.block_size) {
case 4096:
blocks_long >>= 1;
break;
case 1024:
blocks_long <<= 1;
break;
case 512:
blocks_long <<= 2;
break;
default:
break;
}
break;
case 1024:
switch (dev->se_sub_dev->se_dev_attrib.block_size) {
case 4096:
blocks_long >>= 2;
break;
case 2048:
blocks_long >>= 1;
break;
case 512:
blocks_long <<= 1;
break;
default:
break;
}
break;
case 512:
switch (dev->se_sub_dev->se_dev_attrib.block_size) {
case 4096:
blocks_long >>= 3;
break;
case 2048:
blocks_long >>= 2;
break;
case 1024:
blocks_long >>= 1;
break;
default:
break;
}
break;
default:
break;
}
return blocks_long;
}
static int fsg_lun_open(struct fsg_lun *curlun, const char *filename)
{
int ro;
struct file *filp = NULL;
int rc = -EINVAL;
struct inode *inode = NULL;
loff_t size;
loff_t num_sectors;
loff_t min_sectors;
unsigned int blkbits;
unsigned int blksize;
/* R/W if we can, R/O if we must */
ro = curlun->initially_ro;
if (!ro) {
filp = filp_open(filename, O_RDWR | O_LARGEFILE, 0);
if (PTR_ERR(filp) == -EROFS || PTR_ERR(filp) == -EACCES)
ro = 1;
}
if (ro)
filp = filp_open(filename, O_RDONLY | O_LARGEFILE, 0);
if (IS_ERR(filp)) {
LINFO(curlun, "unable to open backing file: %s\n", filename);
return PTR_ERR(filp);
}
if (!(filp->f_mode & FMODE_WRITE))
ro = 1;
inode = file_inode(filp);
if ((!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))) {
LINFO(curlun, "invalid file type: %s\n", filename);
goto out;
}
/*
* If we can't read the file, it's no good.
* If we can't write the file, use it read-only.
*/
if (!(filp->f_op->read || filp->f_op->aio_read)) {
LINFO(curlun, "file not readable: %s\n", filename);
goto out;
}
if (!(filp->f_op->write || filp->f_op->aio_write))
ro = 1;
size = i_size_read(inode->i_mapping->host);
if (size < 0) {
LINFO(curlun, "unable to find file size: %s\n", filename);
rc = (int) size;
goto out;
}
/*
* curlun->blksize remains the old value when switch from cdrom to udisk
* so use the same blksie in cdrom and udisk
*/
#ifdef CONFIG_HUAWEI_USB
if (inode->i_bdev) {
blksize = bdev_logical_block_size(inode->i_bdev);
blkbits = blksize_bits(blksize);
} else {
blksize = 512;
blkbits = 9;
}
#else
if (curlun->cdrom) {
blksize = 2048;
blkbits = 11;
} else if (inode->i_bdev) {
blksize = bdev_logical_block_size(inode->i_bdev);
blkbits = blksize_bits(blksize);
} else {
blksize = 512;
blkbits = 9;
}
#endif
num_sectors = size >> blkbits; /* File size in logic-block-size blocks */
min_sectors = 1;
#ifndef CONFIG_HUAWEI_USB
if (curlun->cdrom) {
min_sectors = 300; /* Smallest track is 300 frames */
if (num_sectors >= 256*60*75) {
num_sectors = 256*60*75 - 1;
LINFO(curlun, "file too big: %s\n", filename);
LINFO(curlun, "using only first %d blocks\n",
(int) num_sectors);
}
}
#endif
if (num_sectors < min_sectors) {
LINFO(curlun, "file too small: %s\n", filename);
rc = -ETOOSMALL;
goto out;
}
if (fsg_lun_is_open(curlun))
fsg_lun_close(curlun);
curlun->blksize = blksize;
curlun->blkbits = blkbits;
curlun->ro = ro;
curlun->filp = filp;
curlun->file_length = size;
curlun->num_sectors = num_sectors;
LDBG(curlun, "open backing file: %s\n", filename);
return 0;
out:
fput(filp);
return rc;
}
static struct se_device *iblock_create_virtdevice(
struct se_hba *hba,
struct se_subsystem_dev *se_dev,
void *p)
{
struct iblock_dev *ib_dev = p;
struct se_device *dev;
struct se_dev_limits dev_limits;
struct block_device *bd = NULL;
struct request_queue *q;
struct queue_limits *limits;
u32 dev_flags = 0;
fmode_t mode;
int ret = -EINVAL;
if (!ib_dev) {
pr_err("Unable to locate struct iblock_dev parameter\n");
return ERR_PTR(ret);
}
memset(&dev_limits, 0, sizeof(struct se_dev_limits));
ib_dev->ibd_bio_set = bioset_create(IBLOCK_BIO_POOL_SIZE, 0);
if (!ib_dev->ibd_bio_set) {
pr_err("IBLOCK: Unable to create bioset()\n");
return ERR_PTR(-ENOMEM);
}
pr_debug("IBLOCK: Created bio_set()\n");
/*
* iblock_check_configfs_dev_params() ensures that ib_dev->ibd_udev_path
* must already have been set in order for echo 1 > $HBA/$DEV/enable to run.
*/
pr_debug( "IBLOCK: Claiming struct block_device: %s\n",
ib_dev->ibd_udev_path);
mode = FMODE_READ|FMODE_EXCL;
if (!ib_dev->ibd_readonly)
mode |= FMODE_WRITE;
bd = blkdev_get_by_path(ib_dev->ibd_udev_path, mode, ib_dev);
if (IS_ERR(bd)) {
ret = PTR_ERR(bd);
goto failed;
}
/*
* Setup the local scope queue_limits from struct request_queue->limits
* to pass into transport_add_device_to_core_hba() as struct se_dev_limits.
*/
q = bdev_get_queue(bd);
limits = &dev_limits.limits;
limits->logical_block_size = bdev_logical_block_size(bd);
limits->max_hw_sectors = UINT_MAX;
limits->max_sectors = UINT_MAX;
dev_limits.hw_queue_depth = q->nr_requests;
dev_limits.queue_depth = q->nr_requests;
ib_dev->ibd_bd = bd;
dev = transport_add_device_to_core_hba(hba,
&iblock_template, se_dev, dev_flags, ib_dev,
&dev_limits, "IBLOCK", IBLOCK_VERSION);
if (!dev)
goto failed;
/*
* Check if the underlying struct block_device request_queue supports
* the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM
* in ATA and we need to set TPE=1
*/
if (blk_queue_discard(q)) {
dev->se_sub_dev->se_dev_attrib.max_unmap_lba_count =
q->limits.max_discard_sectors;
/*
* Currently hardcoded to 1 in Linux/SCSI code..
*/
dev->se_sub_dev->se_dev_attrib.max_unmap_block_desc_count = 1;
dev->se_sub_dev->se_dev_attrib.unmap_granularity =
q->limits.discard_granularity >> 9;
dev->se_sub_dev->se_dev_attrib.unmap_granularity_alignment =
q->limits.discard_alignment;
pr_debug("IBLOCK: BLOCK Discard support available,"
" disabled by default\n");
}
if (blk_queue_nonrot(q))
dev->se_sub_dev->se_dev_attrib.is_nonrot = 1;
return dev;
failed:
if (ib_dev->ibd_bio_set) {
bioset_free(ib_dev->ibd_bio_set);
ib_dev->ibd_bio_set = NULL;
}
ib_dev->ibd_bd = NULL;
return ERR_PTR(ret);
}
static void parse_extended(struct parsed_partitions *state,
sector_t first_sector, sector_t first_size)
{
struct partition *p;
Sector sect;
unsigned char *data;
sector_t this_sector, this_size;
sector_t sector_size = bdev_logical_block_size(state->bdev) / 512;
int loopct = 0; /* number of links followed
without finding a data partition */
int i;
this_sector = first_sector;
this_size = first_size;
while (1) {
if (++loopct > 100)
return;
if (state->next == state->limit)
return;
data = read_part_sector(state, this_sector, §);
if (!data)
return;
if (!msdos_magic_present(data + 510))
goto done;
p = (struct partition *) (data + 0x1be);
/*
* Usually, the first entry is the real data partition,
* the 2nd entry is the next extended partition, or empty,
* and the 3rd and 4th entries are unused.
* However, DRDOS sometimes has the extended partition as
* the first entry (when the data partition is empty),
* and OS/2 seems to use all four entries.
*/
/*
* First process the data partition(s)
*/
for (i=0; i<4; i++, p++) {
sector_t offs, size, next;
if (!nr_sects(p) || is_extended_partition(p))
continue;
/* Check the 3rd and 4th entries -
these sometimes contain random garbage */
offs = start_sect(p)*sector_size;
size = nr_sects(p)*sector_size;
next = this_sector + offs;
if (i >= 2) {
if (offs + size > this_size)
continue;
if (next < first_sector)
continue;
if (next + size > first_sector + first_size)
continue;
}
put_partition(state, state->next, next, size);
if (SYS_IND(p) == LINUX_RAID_PARTITION)
state->parts[state->next].flags = ADDPART_FLAG_RAID;
loopct = 0;
if (++state->next == state->limit)
goto done;
}
/*
* Next, process the (first) extended partition, if present.
* (So far, there seems to be no reason to make
* parse_extended() recursive and allow a tree
* of extended partitions.)
* It should be a link to the next logical partition.
*/
p -= 4;
for (i=0; i<4; i++, p++)
if (nr_sects(p) && is_extended_partition(p))
break;
if (i == 4)
goto done; /* nothing left to do */
this_sector = first_sector + start_sect(p) * sector_size;
this_size = nr_sects(p) * sector_size;
put_dev_sector(sect);
}
done:
put_dev_sector(sect);
}
static int fd_configure_device(struct se_device *dev)
{
struct fd_dev *fd_dev = FD_DEV(dev);
struct fd_host *fd_host = dev->se_hba->hba_ptr;
struct file *file;
struct inode *inode = NULL;
int flags, ret = -EINVAL;
if (!(fd_dev->fbd_flags & FBDF_HAS_PATH)) {
pr_err("Missing fd_dev_name=\n");
return -EINVAL;
}
/*
* Use O_DSYNC by default instead of O_SYNC to forgo syncing
* of pure timestamp updates.
*/
flags = O_RDWR | O_CREAT | O_LARGEFILE | O_DSYNC;
/*
* Optionally allow fd_buffered_io=1 to be enabled for people
* who want use the fs buffer cache as an WriteCache mechanism.
*
* This means that in event of a hard failure, there is a risk
* of silent data-loss if the SCSI client has *not* performed a
* forced unit access (FUA) write, or issued SYNCHRONIZE_CACHE
* to write-out the entire device cache.
*/
if (fd_dev->fbd_flags & FDBD_HAS_BUFFERED_IO_WCE) {
pr_debug("FILEIO: Disabling O_DSYNC, using buffered FILEIO\n");
flags &= ~O_DSYNC;
}
file = filp_open(fd_dev->fd_dev_name, flags, 0600);
if (IS_ERR(file)) {
pr_err("filp_open(%s) failed\n", fd_dev->fd_dev_name);
ret = PTR_ERR(file);
goto fail;
}
fd_dev->fd_file = file;
/*
* If using a block backend with this struct file, we extract
* fd_dev->fd_[block,dev]_size from struct block_device.
*
* Otherwise, we use the passed fd_size= from configfs
*/
inode = file->f_mapping->host;
if (S_ISBLK(inode->i_mode)) {
unsigned long long dev_size;
fd_dev->fd_block_size = bdev_logical_block_size(inode->i_bdev);
/*
* Determine the number of bytes from i_size_read() minus
* one (1) logical sector from underlying struct block_device
*/
dev_size = (i_size_read(file->f_mapping->host) -
fd_dev->fd_block_size);
pr_debug("FILEIO: Using size: %llu bytes from struct"
" block_device blocks: %llu logical_block_size: %d\n",
dev_size, div_u64(dev_size, fd_dev->fd_block_size),
fd_dev->fd_block_size);
} else {
if (!(fd_dev->fbd_flags & FBDF_HAS_SIZE)) {
pr_err("FILEIO: Missing fd_dev_size="
" parameter, and no backing struct"
" block_device\n");
goto fail;
}
fd_dev->fd_block_size = FD_BLOCKSIZE;
}
dev->dev_attrib.hw_block_size = fd_dev->fd_block_size;
dev->dev_attrib.hw_max_sectors = FD_MAX_SECTORS;
dev->dev_attrib.hw_queue_depth = FD_MAX_DEVICE_QUEUE_DEPTH;
if (fd_dev->fbd_flags & FDBD_HAS_BUFFERED_IO_WCE) {
pr_debug("FILEIO: Forcing setting of emulate_write_cache=1"
" with FDBD_HAS_BUFFERED_IO_WCE\n");
dev->dev_attrib.emulate_write_cache = 1;
}
fd_dev->fd_dev_id = fd_host->fd_host_dev_id_count++;
fd_dev->fd_queue_depth = dev->queue_depth;
/*
* Limit WRITE_SAME w/ UNMAP=0 emulation to 8k Number of LBAs (NoLB)
* based upon struct iovec limit for vfs_writev()
*/
dev->dev_attrib.max_write_same_len = 0x1000;
pr_debug("CORE_FILE[%u] - Added TCM FILEIO Device ID: %u at %s,"
" %llu total bytes\n", fd_host->fd_host_id, fd_dev->fd_dev_id,
fd_dev->fd_dev_name, fd_dev->fd_dev_size);
return 0;
fail:
if (fd_dev->fd_file) {
filp_close(fd_dev->fd_file, NULL);
fd_dev->fd_file = NULL;
}
return ret;
}