/* Send an option request.
*
* The request is for option @opt, with @data containing @len bytes of
* additional payload for the request (@len may be -1 to treat @data as
* a C string; and @data may be NULL if @len is 0).
* Return 0 if successful, -1 with errp set if it is impossible to
* continue. */
static int nbd_send_option_request(QIOChannel *ioc, uint32_t opt,
uint32_t len, const char *data,
Error **errp)
{
nbd_option req;
QEMU_BUILD_BUG_ON(sizeof(req) != 16);
if (len == -1) {
req.length = len = strlen(data);
}
trace_nbd_send_option_request(opt, nbd_opt_lookup(opt), len);
stq_be_p(&req.magic, NBD_OPTS_MAGIC);
stl_be_p(&req.option, opt);
stl_be_p(&req.length, len);
if (nbd_write(ioc, &req, sizeof(req), errp) < 0) {
error_prepend(errp, "Failed to send option request header");
return -1;
}
if (len && nbd_write(ioc, (char *) data, len, errp) < 0) {
error_prepend(errp, "Failed to send option request data");
return -1;
}
return 0;
}
static int multipath_pr_in(int fd, const uint8_t *cdb, uint8_t *sense,
uint8_t *data, int sz)
{
int rq_servact = cdb[1];
struct prin_resp resp;
size_t written;
int r;
switch (rq_servact) {
case MPATH_PRIN_RKEY_SA:
case MPATH_PRIN_RRES_SA:
case MPATH_PRIN_RCAP_SA:
break;
case MPATH_PRIN_RFSTAT_SA:
/* Nobody implements it anyway, so bail out. */
default:
/* Cannot parse any other output. */
scsi_build_sense(sense, SENSE_CODE(INVALID_FIELD));
return CHECK_CONDITION;
}
r = mpath_persistent_reserve_in(fd, rq_servact, &resp, noisy, verbose);
if (r == MPATH_PR_SUCCESS) {
switch (rq_servact) {
case MPATH_PRIN_RKEY_SA:
case MPATH_PRIN_RRES_SA: {
struct prin_readdescr *out = &resp.prin_descriptor.prin_readkeys;
assert(sz >= 8);
written = MIN(out->additional_length + 8, sz);
stl_be_p(&data[0], out->prgeneration);
stl_be_p(&data[4], out->additional_length);
memcpy(&data[8], out->key_list, written - 8);
break;
}
case MPATH_PRIN_RCAP_SA: {
struct prin_capdescr *out = &resp.prin_descriptor.prin_readcap;
assert(sz >= 6);
written = 6;
stw_be_p(&data[0], out->length);
data[2] = out->flags[0];
data[3] = out->flags[1];
stw_be_p(&data[4], out->pr_type_mask);
break;
}
default:
scsi_build_sense(sense, SENSE_CODE(INVALID_OPCODE));
return CHECK_CONDITION;
}
assert(written <= sz);
memset(data + written, 0, sz - written);
}
return mpath_reconstruct_sense(fd, r, sense);
}
int nbd_send_request(QIOChannel *ioc, NBDRequest *request)
{
uint8_t buf[NBD_REQUEST_SIZE];
trace_nbd_send_request(request->from, request->len, request->handle,
request->flags, request->type,
nbd_cmd_lookup(request->type));
stl_be_p(buf, NBD_REQUEST_MAGIC);
stw_be_p(buf + 4, request->flags);
stw_be_p(buf + 6, request->type);
stq_be_p(buf + 8, request->handle);
stq_be_p(buf + 16, request->from);
stl_be_p(buf + 24, request->len);
return nbd_write(ioc, buf, sizeof(buf), NULL);
}
static void pcie_aer_update_log(PCIDevice *dev, const PCIEAERErr *err)
{
uint8_t *aer_cap = dev->config + dev->exp.aer_cap;
uint8_t first_bit = ctz32(err->status);
uint32_t errcap = pci_get_long(aer_cap + PCI_ERR_CAP);
int i;
assert(err->status);
assert(!(err->status & (err->status - 1)));
errcap &= ~(PCI_ERR_CAP_FEP_MASK | PCI_ERR_CAP_TLP);
errcap |= PCI_ERR_CAP_FEP(first_bit);
if (err->flags & PCIE_AER_ERR_HEADER_VALID) {
for (i = 0; i < ARRAY_SIZE(err->header); ++i) {
/* 7.10.8 Header Log Register */
uint8_t *header_log =
aer_cap + PCI_ERR_HEADER_LOG + i * sizeof err->header[0];
stl_be_p(header_log, err->header[i]);
}
} else {
assert(!(err->flags & PCIE_AER_ERR_TLP_PREFIX_PRESENT));
memset(aer_cap + PCI_ERR_HEADER_LOG, 0, PCI_ERR_HEADER_LOG_SIZE);
}
if ((err->flags & PCIE_AER_ERR_TLP_PREFIX_PRESENT) &&
(pci_get_long(dev->config + dev->exp.exp_cap + PCI_EXP_DEVCAP2) &
PCI_EXP_DEVCAP2_EETLPP)) {
for (i = 0; i < ARRAY_SIZE(err->prefix); ++i) {
/* 7.10.12 tlp prefix log register */
uint8_t *prefix_log =
aer_cap + PCI_ERR_TLP_PREFIX_LOG + i * sizeof err->prefix[0];
stl_be_p(prefix_log, err->prefix[i]);
}
errcap |= PCI_ERR_CAP_TLP;
} else {
memset(aer_cap + PCI_ERR_TLP_PREFIX_LOG, 0,
PCI_ERR_TLP_PREFIX_LOG_SIZE);
}
pci_set_long(aer_cap + PCI_ERR_CAP, errcap);
}
/* warning: addr must be aligned */
static inline void glue(address_space_stl_internal, SUFFIX)(ARG1_DECL,
hwaddr addr, uint32_t val, MemTxAttrs attrs,
MemTxResult *result, enum device_endian endian)
{
uint8_t *ptr;
MemoryRegion *mr;
hwaddr l = 4;
hwaddr addr1;
MemTxResult r;
bool release_lock = false;
RCU_READ_LOCK();
mr = TRANSLATE(addr, &addr1, &l, true);
if (l < 4 || !IS_DIRECT(mr, true)) {
release_lock |= prepare_mmio_access(mr);
#if defined(TARGET_WORDS_BIGENDIAN)
if (endian == DEVICE_LITTLE_ENDIAN) {
val = bswap32(val);
}
#else
if (endian == DEVICE_BIG_ENDIAN) {
val = bswap32(val);
}
#endif
r = memory_region_dispatch_write(mr, addr1, val, 4, attrs);
} else {
/* RAM case */
ptr = MAP_RAM(mr, addr1);
switch (endian) {
case DEVICE_LITTLE_ENDIAN:
stl_le_p(ptr, val);
break;
case DEVICE_BIG_ENDIAN:
stl_be_p(ptr, val);
break;
default:
stl_p(ptr, val);
break;
}
INVALIDATE(mr, addr1, 4);
r = MEMTX_OK;
}
if (result) {
*result = r;
}
if (release_lock) {
qemu_mutex_unlock_iothread();
}
RCU_READ_UNLOCK();
}
static void scsi_read_complete(void * opaque, int ret)
{
SCSIGenericReq *r = (SCSIGenericReq *)opaque;
SCSIDevice *s = r->req.dev;
int len;
assert(r->req.aiocb != NULL);
r->req.aiocb = NULL;
aio_context_acquire(blk_get_aio_context(s->conf.blk));
if (ret || r->req.io_canceled) {
scsi_command_complete_noio(r, ret);
goto done;
}
len = r->io_header.dxfer_len - r->io_header.resid;
DPRINTF("Data ready tag=0x%x len=%d\n", r->req.tag, len);
r->len = -1;
if (len == 0) {
scsi_command_complete_noio(r, 0);
goto done;
}
/* Snoop READ CAPACITY output to set the blocksize. */
if (r->req.cmd.buf[0] == READ_CAPACITY_10 &&
(ldl_be_p(&r->buf[0]) != 0xffffffffU || s->max_lba == 0)) {
s->blocksize = ldl_be_p(&r->buf[4]);
s->max_lba = ldl_be_p(&r->buf[0]) & 0xffffffffULL;
} else if (r->req.cmd.buf[0] == SERVICE_ACTION_IN_16 &&
(r->req.cmd.buf[1] & 31) == SAI_READ_CAPACITY_16) {
s->blocksize = ldl_be_p(&r->buf[8]);
s->max_lba = ldq_be_p(&r->buf[0]);
}
blk_set_guest_block_size(s->conf.blk, s->blocksize);
/* Patch MODE SENSE device specific parameters if the BDS is opened
* readonly.
*/
if ((s->type == TYPE_DISK || s->type == TYPE_TAPE) &&
blk_is_read_only(s->conf.blk) &&
(r->req.cmd.buf[0] == MODE_SENSE ||
r->req.cmd.buf[0] == MODE_SENSE_10) &&
(r->req.cmd.buf[1] & 0x8) == 0) {
if (r->req.cmd.buf[0] == MODE_SENSE) {
r->buf[2] |= 0x80;
} else {
r->buf[3] |= 0x80;
}
}
if (s->type == TYPE_DISK &&
r->req.cmd.buf[0] == INQUIRY &&
r->req.cmd.buf[2] == 0xb0) {
uint32_t max_transfer =
blk_get_max_transfer(s->conf.blk) / s->blocksize;
assert(max_transfer);
stl_be_p(&r->buf[8], max_transfer);
/* Also take care of the opt xfer len. */
stl_be_p(&r->buf[12],
MIN_NON_ZERO(max_transfer, ldl_be_p(&r->buf[12])));
}
scsi_req_data(&r->req, len);
scsi_req_unref(&r->req);
done:
aio_context_release(blk_get_aio_context(s->conf.blk));
}
/* Returns -1 if NBD_OPT_GO proves the export @wantname cannot be
* used, 0 if NBD_OPT_GO is unsupported (fall back to NBD_OPT_LIST and
* NBD_OPT_EXPORT_NAME in that case), and > 0 if the export is good to
* go (with @info populated). */
static int nbd_opt_go(QIOChannel *ioc, const char *wantname,
NBDExportInfo *info, Error **errp)
{
nbd_opt_reply reply;
uint32_t len = strlen(wantname);
uint16_t type;
int error;
char *buf;
/* The protocol requires that the server send NBD_INFO_EXPORT with
* a non-zero flags (at least NBD_FLAG_HAS_FLAGS must be set); so
* flags still 0 is a witness of a broken server. */
info->flags = 0;
trace_nbd_opt_go_start(wantname);
buf = g_malloc(4 + len + 2 + 2 * info->request_sizes + 1);
stl_be_p(buf, len);
memcpy(buf + 4, wantname, len);
/* At most one request, everything else up to server */
stw_be_p(buf + 4 + len, info->request_sizes);
if (info->request_sizes) {
stw_be_p(buf + 4 + len + 2, NBD_INFO_BLOCK_SIZE);
}
error = nbd_send_option_request(ioc, NBD_OPT_GO,
4 + len + 2 + 2 * info->request_sizes,
buf, errp);
g_free(buf);
if (error < 0) {
return -1;
}
while (1) {
if (nbd_receive_option_reply(ioc, NBD_OPT_GO, &reply, errp) < 0) {
return -1;
}
error = nbd_handle_reply_err(ioc, &reply, errp);
if (error <= 0) {
return error;
}
len = reply.length;
if (reply.type == NBD_REP_ACK) {
/* Server is done sending info and moved into transmission
phase, but make sure it sent flags */
if (len) {
error_setg(errp, "server sent invalid NBD_REP_ACK");
return -1;
}
if (!info->flags) {
error_setg(errp, "broken server omitted NBD_INFO_EXPORT");
return -1;
}
trace_nbd_opt_go_success();
return 1;
}
if (reply.type != NBD_REP_INFO) {
error_setg(errp, "unexpected reply type %" PRIx32
" (%s), expected %x",
reply.type, nbd_rep_lookup(reply.type), NBD_REP_INFO);
nbd_send_opt_abort(ioc);
return -1;
}
if (len < sizeof(type)) {
error_setg(errp, "NBD_REP_INFO length %" PRIu32 " is too short",
len);
nbd_send_opt_abort(ioc);
return -1;
}
if (nbd_read(ioc, &type, sizeof(type), errp) < 0) {
error_prepend(errp, "failed to read info type");
nbd_send_opt_abort(ioc);
return -1;
}
len -= sizeof(type);
be16_to_cpus(&type);
switch (type) {
case NBD_INFO_EXPORT:
if (len != sizeof(info->size) + sizeof(info->flags)) {
error_setg(errp, "remaining export info len %" PRIu32
" is unexpected size", len);
nbd_send_opt_abort(ioc);
return -1;
}
if (nbd_read(ioc, &info->size, sizeof(info->size), errp) < 0) {
error_prepend(errp, "failed to read info size");
nbd_send_opt_abort(ioc);
return -1;
}
be64_to_cpus(&info->size);
if (nbd_read(ioc, &info->flags, sizeof(info->flags), errp) < 0) {
error_prepend(errp, "failed to read info flags");
nbd_send_opt_abort(ioc);
return -1;
}
be16_to_cpus(&info->flags);
trace_nbd_receive_negotiate_size_flags(info->size, info->flags);
break;
case NBD_INFO_BLOCK_SIZE:
if (len != sizeof(info->min_block) * 3) {
error_setg(errp, "remaining export info len %" PRIu32
" is unexpected size", len);
nbd_send_opt_abort(ioc);
return -1;
}
if (nbd_read(ioc, &info->min_block, sizeof(info->min_block),
errp) < 0) {
error_prepend(errp, "failed to read info minimum block size");
nbd_send_opt_abort(ioc);
return -1;
}
be32_to_cpus(&info->min_block);
if (!is_power_of_2(info->min_block)) {
error_setg(errp, "server minimum block size %" PRId32
"is not a power of two", info->min_block);
nbd_send_opt_abort(ioc);
return -1;
}
if (nbd_read(ioc, &info->opt_block, sizeof(info->opt_block),
errp) < 0) {
error_prepend(errp, "failed to read info preferred block size");
nbd_send_opt_abort(ioc);
return -1;
}
be32_to_cpus(&info->opt_block);
if (!is_power_of_2(info->opt_block) ||
info->opt_block < info->min_block) {
error_setg(errp, "server preferred block size %" PRId32
"is not valid", info->opt_block);
nbd_send_opt_abort(ioc);
return -1;
}
if (nbd_read(ioc, &info->max_block, sizeof(info->max_block),
errp) < 0) {
error_prepend(errp, "failed to read info maximum block size");
nbd_send_opt_abort(ioc);
return -1;
}
be32_to_cpus(&info->max_block);
trace_nbd_opt_go_info_block_size(info->min_block, info->opt_block,
info->max_block);
break;
default:
trace_nbd_opt_go_info_unknown(type, nbd_info_lookup(type));
if (nbd_drop(ioc, len, errp) < 0) {
error_prepend(errp, "Failed to read info payload");
nbd_send_opt_abort(ioc);
return -1;
}
break;
}
}
}
