static int mthca_tune_pci(struct mthca_dev *mdev)
{
if (!tune_pci)
return 0;
/* First try to max out Read Byte Count */
if (pci_find_capability(mdev->pdev, PCI_CAP_ID_PCIX)) {
if (pcix_set_mmrbc(mdev->pdev, pcix_get_max_mmrbc(mdev->pdev))) {
mthca_err(mdev, "Couldn't set PCI-X max read count, "
"aborting.\n");
return -ENODEV;
}
} else if (!(mdev->mthca_flags & MTHCA_FLAG_PCIE))
mthca_info(mdev, "No PCI-X capability, not setting RBC.\n");
if (pci_find_capability(mdev->pdev, PCI_CAP_ID_EXP)) {
if (pcie_set_readrq(mdev->pdev, 4096)) {
mthca_err(mdev, "Couldn't write PCI Express read request, "
"aborting.\n");
return -ENODEV;
}
} else if (mdev->mthca_flags & MTHCA_FLAG_PCIE)
mthca_info(mdev, "No PCI Express capability, "
"not setting Max Read Request Size.\n");
return 0;
}
static void handle_catas(struct mthca_dev *dev)
{
struct ib_event event;
const char *type;
int i;
event.device = &dev->ib_dev;
event.event = IB_EVENT_DEVICE_FATAL;
event.element.port_num = 0;
ib_dispatch_event(&event);
switch (swab32(readl(dev->catas_err.map)) >> 24) {
case MTHCA_CATAS_TYPE_INTERNAL:
type = "internal error";
break;
case MTHCA_CATAS_TYPE_UPLINK:
type = "uplink bus error";
break;
case MTHCA_CATAS_TYPE_DDR:
type = "DDR data error";
break;
case MTHCA_CATAS_TYPE_PARITY:
type = "internal parity error";
break;
default:
type = "unknown error";
break;
}
mthca_err(dev, "Catastrophic error detected: %s\n", type);
for (i = 0; i < dev->catas_err.size; ++i)
mthca_err(dev, " buf[%02x]: %08x\n",
i, swab32(readl(dev->catas_err.map + i)));
}
static int mthca_load_fw(struct mthca_dev *mdev)
{
u8 status;
int err;
/* FIXME: use HCA-attached memory for FW if present */
mdev->fw.arbel.fw_icm =
mthca_alloc_icm(mdev, mdev->fw.arbel.fw_pages,
GFP_HIGHUSER | __GFP_NOWARN, 0);
if (!mdev->fw.arbel.fw_icm) {
mthca_err(mdev, "Couldn't allocate FW area, aborting.\n");
return -ENOMEM;
}
err = mthca_MAP_FA(mdev, mdev->fw.arbel.fw_icm, &status);
if (err) {
mthca_err(mdev, "MAP_FA command failed, aborting.\n");
goto err_free;
}
if (status) {
mthca_err(mdev, "MAP_FA returned status 0x%02x, aborting.\n", status);
err = -EINVAL;
goto err_free;
}
err = mthca_RUN_FW(mdev, &status);
if (err) {
mthca_err(mdev, "RUN_FW command failed, aborting.\n");
goto err_unmap_fa;
}
if (status) {
mthca_err(mdev, "RUN_FW returned status 0x%02x, aborting.\n", status);
err = -EINVAL;
goto err_unmap_fa;
}
return 0;
err_unmap_fa:
mthca_UNMAP_FA(mdev, &status);
err_free:
mthca_free_icm(mdev, mdev->fw.arbel.fw_icm, 0);
return err;
}
static int mthca_setup_hca(struct mthca_dev *dev)
{
int err;
u8 status;
MTHCA_INIT_DOORBELL_LOCK(&dev->doorbell_lock);
err = mthca_init_uar_table(dev);
if (err) {
mthca_err(dev, "Failed to initialize "
"user access region table, aborting.\n");
return err;
}
err = mthca_uar_alloc(dev, &dev->driver_uar);
if (err) {
mthca_err(dev, "Failed to allocate driver access region, "
"aborting.\n");
goto err_uar_table_free;
}
<<<<<<< HEAD
static int mthca_init_hca(struct mthca_dev *mdev)
{
u8 status;
int err;
struct mthca_adapter adapter;
if (mthca_is_memfree(mdev))
err = mthca_init_arbel(mdev);
else
err = mthca_init_tavor(mdev);
if (err)
return err;
err = mthca_QUERY_ADAPTER(mdev, &adapter, &status);
if (err) {
mthca_err(mdev, "QUERY_ADAPTER command failed, aborting.\n");
goto err_close;
}
if (status) {
mthca_err(mdev, "QUERY_ADAPTER returned status 0x%02x, "
"aborting.\n", status);
err = -EINVAL;
goto err_close;
}
mdev->eq_table.inta_pin = adapter.inta_pin;
if (!mthca_is_memfree(mdev))
mdev->rev_id = adapter.revision_id;
memcpy(mdev->board_id, adapter.board_id, sizeof mdev->board_id);
return 0;
err_close:
mthca_close_hca(mdev);
return err;
}
int mthca_create_agents(struct mthca_dev *dev)
{
struct ib_mad_agent *agent;
int p, q;
int ret;
spin_lock_init(&dev->sm_lock);
for (p = 0; p < dev->limits.num_ports; ++p)
for (q = 0; q <= 1; ++q) {
agent = ib_register_mad_agent(&dev->ib_dev, p + 1,
q ? IB_QPT_GSI : IB_QPT_SMI,
NULL, 0, send_handler,
NULL, NULL);
if (IS_ERR(agent)) {
ret = PTR_ERR(agent);
goto err;
}
dev->send_agent[p][q] = agent;
}
for (p = 1; p <= dev->limits.num_ports; ++p) {
ret = mthca_update_rate(dev, p);
if (ret) {
mthca_err(dev, "Failed to obtain port %d rate."
" aborting.\n", p);
goto err;
}
}
return 0;
err:
for (p = 0; p < dev->limits.num_ports; ++p)
for (q = 0; q <= 1; ++q)
if (dev->send_agent[p][q])
ib_unregister_mad_agent(dev->send_agent[p][q]);
return ret;
}
int mthca_reset(struct mthca_dev *mdev)
{
int i;
int err = 0;
u32 *hca_header = NULL;
u32 *bridge_header = NULL;
struct pci_dev *bridge = NULL;
int bridge_pcix_cap = 0;
int hca_pcie_cap = 0;
int hca_pcix_cap = 0;
u16 devctl;
u16 linkctl;
#define MTHCA_RESET_OFFSET 0xf0010
#define MTHCA_RESET_VALUE swab32(1)
/*
* Reset the chip. This is somewhat ugly because we have to
* save off the PCI header before reset and then restore it
* after the chip reboots. We skip config space offsets 22
* and 23 since those have a special meaning.
*
* To make matters worse, for Tavor (PCI-X HCA) we have to
* find the associated bridge device and save off its PCI
* header as well.
*/
if (!(mdev->mthca_flags & MTHCA_FLAG_PCIE)) {
/* Look for the bridge -- its device ID will be 2 more
than HCA's device ID. */
while ((bridge = pci_get_device(mdev->pdev->vendor,
mdev->pdev->device + 2,
bridge)) != NULL) {
if (bridge->hdr_type == PCI_HEADER_TYPE_BRIDGE &&
bridge->subordinate == mdev->pdev->bus) {
mthca_dbg(mdev, "Found bridge: %s\n",
pci_name(bridge));
break;
}
}
if (!bridge) {
/*
* Didn't find a bridge for a Tavor device --
* assume we're in no-bridge mode and hope for
* the best.
*/
mthca_warn(mdev, "No bridge found for %s\n",
pci_name(mdev->pdev));
}
}
/* For Arbel do we need to save off the full 4K PCI Express header?? */
hca_header = kmalloc(256, GFP_KERNEL);
if (!hca_header) {
err = -ENOMEM;
mthca_err(mdev, "Couldn't allocate memory to save HCA "
"PCI header, aborting.\n");
goto out;
}
for (i = 0; i < 64; ++i) {
if (i == 22 || i == 23)
continue;
if (pci_read_config_dword(mdev->pdev, i * 4, hca_header + i)) {
err = -ENODEV;
mthca_err(mdev, "Couldn't save HCA "
"PCI header, aborting.\n");
goto out;
}
}
hca_pcix_cap = pci_find_capability(mdev->pdev, PCI_CAP_ID_PCIX);
<<<<<<< HEAD
int mthca_reset(struct mthca_dev *mdev)
{
int i;
int err = 0;
u32 *hca_header = NULL;
u32 *bridge_header = NULL;
struct pci_dev *bridge = NULL;
int bridge_pcix_cap = 0;
int hca_pcie_cap = 0;
int hca_pcix_cap = 0;
u16 devctl;
u16 linkctl;
#define MTHCA_RESET_OFFSET 0xf0010
#define MTHCA_RESET_VALUE swab32(1)
/*
* Reset the chip. This is somewhat ugly because we have to
* save off the PCI header before reset and then restore it
* after the chip reboots. We skip config space offsets 22
* and 23 since those have a special meaning.
*
* To make matters worse, for Tavor (PCI-X HCA) we have to
* find the associated bridge device and save off its PCI
* header as well.
*/
if (!(mdev->mthca_flags & MTHCA_FLAG_PCIE)) {
/* Look for the bridge -- its device ID will be 2 more
than HCA's device ID. */
while ((bridge = pci_get_device(mdev->pdev->vendor,
mdev->pdev->device + 2,
bridge)) != NULL) {
if (bridge->hdr_type == PCI_HEADER_TYPE_BRIDGE &&
bridge->subordinate == mdev->pdev->bus) {
mthca_dbg(mdev, "Found bridge: %s\n",
pci_name(bridge));
break;
}
}
if (!bridge) {
/*
* Didn't find a bridge for a Tavor device --
* assume we're in no-bridge mode and hope for
* the best.
*/
mthca_warn(mdev, "No bridge found for %s\n",
pci_name(mdev->pdev));
}
}
/* For Arbel do we need to save off the full 4K PCI Express header?? */
hca_header = kmalloc(256, GFP_KERNEL);
if (!hca_header) {
err = -ENOMEM;
mthca_err(mdev, "Couldn't allocate memory to save HCA "
"PCI header, aborting.\n");
goto out;
}
for (i = 0; i < 64; ++i) {
if (i == 22 || i == 23)
continue;
if (pci_read_config_dword(mdev->pdev, i * 4, hca_header + i)) {
err = -ENODEV;
mthca_err(mdev, "Couldn't save HCA "
"PCI header, aborting.\n");
goto out;
}
}
hca_pcix_cap = pci_find_capability(mdev->pdev, PCI_CAP_ID_PCIX);
hca_pcie_cap = pci_find_capability(mdev->pdev, PCI_CAP_ID_EXP);
if (bridge) {
bridge_header = kmalloc(256, GFP_KERNEL);
if (!bridge_header) {
err = -ENOMEM;
mthca_err(mdev, "Couldn't allocate memory to save HCA "
"bridge PCI header, aborting.\n");
goto out;
}
for (i = 0; i < 64; ++i) {
if (i == 22 || i == 23)
continue;
if (pci_read_config_dword(bridge, i * 4, bridge_header + i)) {
err = -ENODEV;
mthca_err(mdev, "Couldn't save HCA bridge "
"PCI header, aborting.\n");
goto out;
}
}
bridge_pcix_cap = pci_find_capability(bridge, PCI_CAP_ID_PCIX);
if (!bridge_pcix_cap) {
err = -ENODEV;
mthca_err(mdev, "Couldn't locate HCA bridge "
"PCI-X capability, aborting.\n");
goto out;
}
}
/* actually hit reset */
{
void __iomem *reset = ioremap(pci_resource_start(mdev->pdev, 0) +
MTHCA_RESET_OFFSET, 4);
if (!reset) {
err = -ENOMEM;
mthca_err(mdev, "Couldn't map HCA reset register, "
"aborting.\n");
goto out;
}
writel(MTHCA_RESET_VALUE, reset);
iounmap(reset);
}
/* Docs say to wait one second before accessing device */
msleep(1000);
/* Now wait for PCI device to start responding again */
{
u32 v;
int c = 0;
for (c = 0; c < 100; ++c) {
if (pci_read_config_dword(bridge ? bridge : mdev->pdev, 0, &v)) {
err = -ENODEV;
mthca_err(mdev, "Couldn't access HCA after reset, "
"aborting.\n");
goto out;
}
if (v != 0xffffffff)
goto good;
msleep(100);
}
err = -ENODEV;
mthca_err(mdev, "PCI device did not come back after reset, "
"aborting.\n");
goto out;
}
good:
/* Now restore the PCI headers */
if (bridge) {
if (pci_write_config_dword(bridge, bridge_pcix_cap + 0x8,
bridge_header[(bridge_pcix_cap + 0x8) / 4])) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA bridge Upstream "
"split transaction control, aborting.\n");
goto out;
}
if (pci_write_config_dword(bridge, bridge_pcix_cap + 0xc,
bridge_header[(bridge_pcix_cap + 0xc) / 4])) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA bridge Downstream "
"split transaction control, aborting.\n");
goto out;
}
/*
* Bridge control register is at 0x3e, so we'll
* naturally restore it last in this loop.
*/
for (i = 0; i < 16; ++i) {
if (i * 4 == PCI_COMMAND)
continue;
if (pci_write_config_dword(bridge, i * 4, bridge_header[i])) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA bridge reg %x, "
"aborting.\n", i);
goto out;
}
}
if (pci_write_config_dword(bridge, PCI_COMMAND,
bridge_header[PCI_COMMAND / 4])) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA bridge COMMAND, "
"aborting.\n");
goto out;
}
}
if (hca_pcix_cap) {
if (pci_write_config_dword(mdev->pdev, hca_pcix_cap,
hca_header[hca_pcix_cap / 4])) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA PCI-X "
"command register, aborting.\n");
goto out;
}
}
if (hca_pcie_cap) {
devctl = hca_header[(hca_pcie_cap + PCI_EXP_DEVCTL) / 4];
if (pci_write_config_word(mdev->pdev, hca_pcie_cap + PCI_EXP_DEVCTL,
devctl)) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA PCI Express "
"Device Control register, aborting.\n");
goto out;
}
linkctl = hca_header[(hca_pcie_cap + PCI_EXP_LNKCTL) / 4];
if (pci_write_config_word(mdev->pdev, hca_pcie_cap + PCI_EXP_LNKCTL,
linkctl)) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA PCI Express "
"Link control register, aborting.\n");
goto out;
}
}
for (i = 0; i < 16; ++i) {
if (i * 4 == PCI_COMMAND)
continue;
if (pci_write_config_dword(mdev->pdev, i * 4, hca_header[i])) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA reg %x, "
"aborting.\n", i);
goto out;
}
}
if (pci_write_config_dword(mdev->pdev, PCI_COMMAND,
hca_header[PCI_COMMAND / 4])) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA COMMAND, "
"aborting.\n");
goto out;
}
out:
if (bridge)
pci_dev_put(bridge);
kfree(bridge_header);
kfree(hca_header);
return err;
}
int mthca_process_mad(struct ib_device *ibdev,
int mad_flags,
u8 port_num,
struct ib_wc *in_wc,
struct ib_grh *in_grh,
struct ib_mad *in_mad,
struct ib_mad *out_mad)
{
int err;
u8 status;
u16 slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
/* Forward locally generated traps to the SM */
if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP &&
slid == 0) {
forward_trap(to_mdev(ibdev), port_num, in_mad);
return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED;
}
/*
* Only handle SM gets, sets and trap represses for SM class
*
* Only handle PMA and Mellanox vendor-specific class gets and
* sets for other classes.
*/
if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) {
if (in_mad->mad_hdr.method != IB_MGMT_METHOD_GET &&
in_mad->mad_hdr.method != IB_MGMT_METHOD_SET &&
in_mad->mad_hdr.method != IB_MGMT_METHOD_TRAP_REPRESS)
return IB_MAD_RESULT_SUCCESS;
/*
* Don't process SMInfo queries or vendor-specific
* MADs -- the SMA can't handle them.
*/
if (in_mad->mad_hdr.attr_id == IB_SMP_ATTR_SM_INFO ||
((in_mad->mad_hdr.attr_id & IB_SMP_ATTR_VENDOR_MASK) ==
IB_SMP_ATTR_VENDOR_MASK))
return IB_MAD_RESULT_SUCCESS;
} else if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT ||
in_mad->mad_hdr.mgmt_class == MTHCA_VENDOR_CLASS1 ||
in_mad->mad_hdr.mgmt_class == MTHCA_VENDOR_CLASS2) {
if (in_mad->mad_hdr.method != IB_MGMT_METHOD_GET &&
in_mad->mad_hdr.method != IB_MGMT_METHOD_SET)
return IB_MAD_RESULT_SUCCESS;
} else
return IB_MAD_RESULT_SUCCESS;
err = mthca_MAD_IFC(to_mdev(ibdev),
mad_flags & IB_MAD_IGNORE_MKEY,
mad_flags & IB_MAD_IGNORE_BKEY,
port_num, in_wc, in_grh, in_mad, out_mad,
&status);
if (err) {
mthca_err(to_mdev(ibdev), "MAD_IFC failed\n");
return IB_MAD_RESULT_FAILURE;
}
if (status == MTHCA_CMD_STAT_BAD_PKT)
return IB_MAD_RESULT_SUCCESS;
if (status) {
mthca_err(to_mdev(ibdev), "MAD_IFC returned status %02x\n",
status);
return IB_MAD_RESULT_FAILURE;
}
if (!out_mad->mad_hdr.status) {
smp_snoop(ibdev, port_num, in_mad);
node_desc_override(ibdev, out_mad);
}
/* set return bit in status of directed route responses */
if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
out_mad->mad_hdr.status |= cpu_to_be16(1 << 15);
if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP_REPRESS)
/* no response for trap repress */
return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED;
return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
}
static int mthca_init_arbel(struct mthca_dev *mdev)
{
struct mthca_dev_lim dev_lim;
struct mthca_profile profile;
struct mthca_init_hca_param init_hca;
s64 icm_size;
u8 status;
int err;
err = mthca_QUERY_FW(mdev, &status);
if (err) {
mthca_err(mdev, "QUERY_FW command failed, aborting.\n");
return err;
}
if (status) {
mthca_err(mdev, "QUERY_FW returned status 0x%02x, "
"aborting.\n", status);
return -EINVAL;
}
err = mthca_ENABLE_LAM(mdev, &status);
if (err) {
mthca_err(mdev, "ENABLE_LAM command failed, aborting.\n");
return err;
}
if (status == MTHCA_CMD_STAT_LAM_NOT_PRE) {
mthca_dbg(mdev, "No HCA-attached memory (running in MemFree mode)\n");
mdev->mthca_flags |= MTHCA_FLAG_NO_LAM;
} else if (status) {
mthca_err(mdev, "ENABLE_LAM returned status 0x%02x, "
"aborting.\n", status);
return -EINVAL;
}
err = mthca_load_fw(mdev);
if (err) {
mthca_err(mdev, "Failed to start FW, aborting.\n");
goto err_disable;
}
err = mthca_dev_lim(mdev, &dev_lim);
if (err) {
mthca_err(mdev, "QUERY_DEV_LIM command failed, aborting.\n");
goto err_stop_fw;
}
profile = hca_profile;
profile.num_uar = dev_lim.uar_size / PAGE_SIZE;
profile.num_udav = 0;
if (mdev->mthca_flags & MTHCA_FLAG_SRQ)
profile.num_srq = dev_lim.max_srqs;
icm_size = mthca_make_profile(mdev, &profile, &dev_lim, &init_hca);
if (icm_size < 0) {
err = icm_size;
goto err_stop_fw;
}
err = mthca_init_icm(mdev, &dev_lim, &init_hca, icm_size);
if (err)
goto err_stop_fw;
err = mthca_INIT_HCA(mdev, &init_hca, &status);
if (err) {
mthca_err(mdev, "INIT_HCA command failed, aborting.\n");
goto err_free_icm;
}
if (status) {
mthca_err(mdev, "INIT_HCA returned status 0x%02x, "
"aborting.\n", status);
err = -EINVAL;
goto err_free_icm;
}
return 0;
err_free_icm:
mthca_free_icms(mdev);
err_stop_fw:
mthca_UNMAP_FA(mdev, &status);
mthca_free_icm(mdev, mdev->fw.arbel.fw_icm, 0);
err_disable:
if (!(mdev->mthca_flags & MTHCA_FLAG_NO_LAM))
mthca_DISABLE_LAM(mdev, &status);
return err;
}
static int mthca_init_icm(struct mthca_dev *mdev,
struct mthca_dev_lim *dev_lim,
struct mthca_init_hca_param *init_hca,
u64 icm_size)
{
u64 aux_pages;
u8 status;
int err;
err = mthca_SET_ICM_SIZE(mdev, icm_size, &aux_pages, &status);
if (err) {
mthca_err(mdev, "SET_ICM_SIZE command failed, aborting.\n");
return err;
}
if (status) {
mthca_err(mdev, "SET_ICM_SIZE returned status 0x%02x, "
"aborting.\n", status);
return -EINVAL;
}
mthca_dbg(mdev, "%lld KB of HCA context requires %lld KB aux memory.\n",
(unsigned long long) icm_size >> 10,
(unsigned long long) aux_pages << 2);
mdev->fw.arbel.aux_icm = mthca_alloc_icm(mdev, aux_pages,
GFP_HIGHUSER | __GFP_NOWARN, 0);
if (!mdev->fw.arbel.aux_icm) {
mthca_err(mdev, "Couldn't allocate aux memory, aborting.\n");
return -ENOMEM;
}
err = mthca_MAP_ICM_AUX(mdev, mdev->fw.arbel.aux_icm, &status);
if (err) {
mthca_err(mdev, "MAP_ICM_AUX command failed, aborting.\n");
goto err_free_aux;
}
if (status) {
mthca_err(mdev, "MAP_ICM_AUX returned status 0x%02x, aborting.\n", status);
err = -EINVAL;
goto err_free_aux;
}
err = mthca_map_eq_icm(mdev, init_hca->eqc_base);
if (err) {
mthca_err(mdev, "Failed to map EQ context memory, aborting.\n");
goto err_unmap_aux;
}
/* CPU writes to non-reserved MTTs, while HCA might DMA to reserved mtts */
mdev->limits.reserved_mtts = ALIGN(mdev->limits.reserved_mtts * mdev->limits.mtt_seg_size,
dma_get_cache_alignment()) / mdev->limits.mtt_seg_size;
mdev->mr_table.mtt_table = mthca_alloc_icm_table(mdev, init_hca->mtt_base,
mdev->limits.mtt_seg_size,
mdev->limits.num_mtt_segs,
mdev->limits.reserved_mtts,
1, 0);
if (!mdev->mr_table.mtt_table) {
mthca_err(mdev, "Failed to map MTT context memory, aborting.\n");
err = -ENOMEM;
goto err_unmap_eq;
}
mdev->mr_table.mpt_table = mthca_alloc_icm_table(mdev, init_hca->mpt_base,
dev_lim->mpt_entry_sz,
mdev->limits.num_mpts,
mdev->limits.reserved_mrws,
1, 1);
if (!mdev->mr_table.mpt_table) {
mthca_err(mdev, "Failed to map MPT context memory, aborting.\n");
err = -ENOMEM;
goto err_unmap_mtt;
}
mdev->qp_table.qp_table = mthca_alloc_icm_table(mdev, init_hca->qpc_base,
dev_lim->qpc_entry_sz,
mdev->limits.num_qps,
mdev->limits.reserved_qps,
0, 0);
if (!mdev->qp_table.qp_table) {
mthca_err(mdev, "Failed to map QP context memory, aborting.\n");
err = -ENOMEM;
goto err_unmap_mpt;
}
mdev->qp_table.eqp_table = mthca_alloc_icm_table(mdev, init_hca->eqpc_base,
dev_lim->eqpc_entry_sz,
mdev->limits.num_qps,
mdev->limits.reserved_qps,
0, 0);
if (!mdev->qp_table.eqp_table) {
mthca_err(mdev, "Failed to map EQP context memory, aborting.\n");
err = -ENOMEM;
goto err_unmap_qp;
}
mdev->qp_table.rdb_table = mthca_alloc_icm_table(mdev, init_hca->rdb_base,
MTHCA_RDB_ENTRY_SIZE,
mdev->limits.num_qps <<
mdev->qp_table.rdb_shift, 0,
0, 0);
if (!mdev->qp_table.rdb_table) {
mthca_err(mdev, "Failed to map RDB context memory, aborting\n");
err = -ENOMEM;
goto err_unmap_eqp;
}
mdev->cq_table.table = mthca_alloc_icm_table(mdev, init_hca->cqc_base,
dev_lim->cqc_entry_sz,
mdev->limits.num_cqs,
mdev->limits.reserved_cqs,
0, 0);
if (!mdev->cq_table.table) {
mthca_err(mdev, "Failed to map CQ context memory, aborting.\n");
err = -ENOMEM;
goto err_unmap_rdb;
}
if (mdev->mthca_flags & MTHCA_FLAG_SRQ) {
mdev->srq_table.table =
mthca_alloc_icm_table(mdev, init_hca->srqc_base,
dev_lim->srq_entry_sz,
mdev->limits.num_srqs,
mdev->limits.reserved_srqs,
0, 0);
if (!mdev->srq_table.table) {
mthca_err(mdev, "Failed to map SRQ context memory, "
"aborting.\n");
err = -ENOMEM;
goto err_unmap_cq;
}
}
/*
* It's not strictly required, but for simplicity just map the
* whole multicast group table now. The table isn't very big
* and it's a lot easier than trying to track ref counts.
*/
mdev->mcg_table.table = mthca_alloc_icm_table(mdev, init_hca->mc_base,
MTHCA_MGM_ENTRY_SIZE,
mdev->limits.num_mgms +
mdev->limits.num_amgms,
mdev->limits.num_mgms +
mdev->limits.num_amgms,
0, 0);
if (!mdev->mcg_table.table) {
mthca_err(mdev, "Failed to map MCG context memory, aborting.\n");
err = -ENOMEM;
goto err_unmap_srq;
}
return 0;
err_unmap_srq:
if (mdev->mthca_flags & MTHCA_FLAG_SRQ)
mthca_free_icm_table(mdev, mdev->srq_table.table);
err_unmap_cq:
mthca_free_icm_table(mdev, mdev->cq_table.table);
err_unmap_rdb:
mthca_free_icm_table(mdev, mdev->qp_table.rdb_table);
err_unmap_eqp:
mthca_free_icm_table(mdev, mdev->qp_table.eqp_table);
err_unmap_qp:
mthca_free_icm_table(mdev, mdev->qp_table.qp_table);
err_unmap_mpt:
mthca_free_icm_table(mdev, mdev->mr_table.mpt_table);
err_unmap_mtt:
mthca_free_icm_table(mdev, mdev->mr_table.mtt_table);
err_unmap_eq:
mthca_unmap_eq_icm(mdev);
err_unmap_aux:
mthca_UNMAP_ICM_AUX(mdev, &status);
err_free_aux:
mthca_free_icm(mdev, mdev->fw.arbel.aux_icm, 0);
return err;
}
static int mthca_init_tavor(struct mthca_dev *mdev)
{
s64 size;
u8 status;
int err;
struct mthca_dev_lim dev_lim;
struct mthca_profile profile;
struct mthca_init_hca_param init_hca;
err = mthca_SYS_EN(mdev, &status);
if (err) {
mthca_err(mdev, "SYS_EN command failed, aborting.\n");
return err;
}
if (status) {
mthca_err(mdev, "SYS_EN returned status 0x%02x, "
"aborting.\n", status);
return -EINVAL;
}
err = mthca_QUERY_FW(mdev, &status);
if (err) {
mthca_err(mdev, "QUERY_FW command failed, aborting.\n");
goto err_disable;
}
if (status) {
mthca_err(mdev, "QUERY_FW returned status 0x%02x, "
"aborting.\n", status);
err = -EINVAL;
goto err_disable;
}
err = mthca_QUERY_DDR(mdev, &status);
if (err) {
mthca_err(mdev, "QUERY_DDR command failed, aborting.\n");
goto err_disable;
}
if (status) {
mthca_err(mdev, "QUERY_DDR returned status 0x%02x, "
"aborting.\n", status);
err = -EINVAL;
goto err_disable;
}
err = mthca_dev_lim(mdev, &dev_lim);
if (err) {
mthca_err(mdev, "QUERY_DEV_LIM command failed, aborting.\n");
goto err_disable;
}
profile = hca_profile;
profile.num_uar = dev_lim.uar_size / PAGE_SIZE;
profile.uarc_size = 0;
if (mdev->mthca_flags & MTHCA_FLAG_SRQ)
profile.num_srq = dev_lim.max_srqs;
size = mthca_make_profile(mdev, &profile, &dev_lim, &init_hca);
if (size < 0) {
err = size;
goto err_disable;
}
err = mthca_INIT_HCA(mdev, &init_hca, &status);
if (err) {
mthca_err(mdev, "INIT_HCA command failed, aborting.\n");
goto err_disable;
}
if (status) {
mthca_err(mdev, "INIT_HCA returned status 0x%02x, "
"aborting.\n", status);
err = -EINVAL;
goto err_disable;
}
return 0;
err_disable:
mthca_SYS_DIS(mdev, &status);
return err;
}
static int mthca_dev_lim(struct mthca_dev *mdev, struct mthca_dev_lim *dev_lim)
{
int err;
u8 status;
mdev->limits.mtt_seg_size = (1 << log_mtts_per_seg) * 8;
err = mthca_QUERY_DEV_LIM(mdev, dev_lim, &status);
if (err) {
mthca_err(mdev, "QUERY_DEV_LIM command failed, aborting.\n");
return err;
}
if (status) {
mthca_err(mdev, "QUERY_DEV_LIM returned status 0x%02x, "
"aborting.\n", status);
return -EINVAL;
}
if (dev_lim->min_page_sz > PAGE_SIZE) {
mthca_err(mdev, "HCA minimum page size of %d bigger than "
"kernel PAGE_SIZE of %ld, aborting.\n",
dev_lim->min_page_sz, PAGE_SIZE);
return -ENODEV;
}
if (dev_lim->num_ports > MTHCA_MAX_PORTS) {
mthca_err(mdev, "HCA has %d ports, but we only support %d, "
"aborting.\n",
dev_lim->num_ports, MTHCA_MAX_PORTS);
return -ENODEV;
}
if (dev_lim->uar_size > pci_resource_len(mdev->pdev, 2)) {
mthca_err(mdev, "HCA reported UAR size of 0x%x bigger than "
"PCI resource 2 size of 0x%llx, aborting.\n",
dev_lim->uar_size,
(unsigned long long)pci_resource_len(mdev->pdev, 2));
return -ENODEV;
}
mdev->limits.num_ports = dev_lim->num_ports;
mdev->limits.vl_cap = dev_lim->max_vl;
mdev->limits.mtu_cap = dev_lim->max_mtu;
mdev->limits.gid_table_len = dev_lim->max_gids;
mdev->limits.pkey_table_len = dev_lim->max_pkeys;
mdev->limits.local_ca_ack_delay = dev_lim->local_ca_ack_delay;
/*
* Need to allow for worst case send WQE overhead and check
* whether max_desc_sz imposes a lower limit than max_sg; UD
* send has the biggest overhead.
*/
mdev->limits.max_sg = min_t(int, dev_lim->max_sg,
(dev_lim->max_desc_sz -
sizeof (struct mthca_next_seg) -
(mthca_is_memfree(mdev) ?
sizeof (struct mthca_arbel_ud_seg) :
sizeof (struct mthca_tavor_ud_seg))) /
sizeof (struct mthca_data_seg));
mdev->limits.max_wqes = dev_lim->max_qp_sz;
mdev->limits.max_qp_init_rdma = dev_lim->max_requester_per_qp;
mdev->limits.reserved_qps = dev_lim->reserved_qps;
mdev->limits.max_srq_wqes = dev_lim->max_srq_sz;
mdev->limits.reserved_srqs = dev_lim->reserved_srqs;
mdev->limits.reserved_eecs = dev_lim->reserved_eecs;
mdev->limits.max_desc_sz = dev_lim->max_desc_sz;
mdev->limits.max_srq_sge = mthca_max_srq_sge(mdev);
/*
* Subtract 1 from the limit because we need to allocate a
* spare CQE so the HCA HW can tell the difference between an
* empty CQ and a full CQ.
*/
mdev->limits.max_cqes = dev_lim->max_cq_sz - 1;
mdev->limits.reserved_cqs = dev_lim->reserved_cqs;
mdev->limits.reserved_eqs = dev_lim->reserved_eqs;
mdev->limits.reserved_mtts = dev_lim->reserved_mtts;
mdev->limits.reserved_mrws = dev_lim->reserved_mrws;
mdev->limits.reserved_uars = dev_lim->reserved_uars;
mdev->limits.reserved_pds = dev_lim->reserved_pds;
mdev->limits.port_width_cap = dev_lim->max_port_width;
mdev->limits.page_size_cap = ~(u32) (dev_lim->min_page_sz - 1);
mdev->limits.flags = dev_lim->flags;
/*
* For old FW that doesn't return static rate support, use a
* value of 0x3 (only static rate values of 0 or 1 are handled),
* except on Sinai, where even old FW can handle static rate
* values of 2 and 3.
*/
if (dev_lim->stat_rate_support)
mdev->limits.stat_rate_support = dev_lim->stat_rate_support;
else if (mdev->mthca_flags & MTHCA_FLAG_SINAI_OPT)
mdev->limits.stat_rate_support = 0xf;
else
mdev->limits.stat_rate_support = 0x3;
/* IB_DEVICE_RESIZE_MAX_WR not supported by driver.
May be doable since hardware supports it for SRQ.
IB_DEVICE_N_NOTIFY_CQ is supported by hardware but not by driver.
IB_DEVICE_SRQ_RESIZE is supported by hardware but SRQ is not
supported by driver. */
mdev->device_cap_flags = IB_DEVICE_CHANGE_PHY_PORT |
IB_DEVICE_PORT_ACTIVE_EVENT |
IB_DEVICE_SYS_IMAGE_GUID |
IB_DEVICE_RC_RNR_NAK_GEN;
if (dev_lim->flags & DEV_LIM_FLAG_BAD_PKEY_CNTR)
mdev->device_cap_flags |= IB_DEVICE_BAD_PKEY_CNTR;
if (dev_lim->flags & DEV_LIM_FLAG_BAD_QKEY_CNTR)
mdev->device_cap_flags |= IB_DEVICE_BAD_QKEY_CNTR;
if (dev_lim->flags & DEV_LIM_FLAG_RAW_MULTI)
mdev->device_cap_flags |= IB_DEVICE_RAW_MULTI;
if (dev_lim->flags & DEV_LIM_FLAG_AUTO_PATH_MIG)
mdev->device_cap_flags |= IB_DEVICE_AUTO_PATH_MIG;
if (dev_lim->flags & DEV_LIM_FLAG_UD_AV_PORT_ENFORCE)
mdev->device_cap_flags |= IB_DEVICE_UD_AV_PORT_ENFORCE;
if (dev_lim->flags & DEV_LIM_FLAG_SRQ)
mdev->mthca_flags |= MTHCA_FLAG_SRQ;
if (mthca_is_memfree(mdev))
if (dev_lim->flags & DEV_LIM_FLAG_IPOIB_CSUM)
mdev->device_cap_flags |= IB_DEVICE_UD_IP_CSUM;
return 0;
}
int mthca_reset(struct mthca_dev *mdev)
{
int i;
int err = 0;
u32 *hca_header = NULL;
u32 *bridge_header = NULL;
struct pci_dev *bridge = NULL;
int bridge_pcix_cap = 0;
int hca_pcie_cap = 0;
int hca_pcix_cap = 0;
u16 devctl;
u16 linkctl;
#define MTHCA_RESET_OFFSET 0xf0010
#define MTHCA_RESET_VALUE swab32(1)
if (!(mdev->mthca_flags & MTHCA_FLAG_PCIE)) {
while ((bridge = pci_get_device(mdev->pdev->vendor,
mdev->pdev->device + 2,
bridge)) != NULL) {
if (bridge->hdr_type == PCI_HEADER_TYPE_BRIDGE &&
bridge->subordinate == mdev->pdev->bus) {
mthca_dbg(mdev, "Found bridge: %s\n",
pci_name(bridge));
break;
}
}
if (!bridge) {
mthca_warn(mdev, "No bridge found for %s\n",
pci_name(mdev->pdev));
}
}
hca_header = kmalloc(256, GFP_KERNEL);
if (!hca_header) {
err = -ENOMEM;
mthca_err(mdev, "Couldn't allocate memory to save HCA "
"PCI header, aborting.\n");
goto out;
}
for (i = 0; i < 64; ++i) {
if (i == 22 || i == 23)
continue;
if (pci_read_config_dword(mdev->pdev, i * 4, hca_header + i)) {
err = -ENODEV;
mthca_err(mdev, "Couldn't save HCA "
"PCI header, aborting.\n");
goto out;
}
}
hca_pcix_cap = pci_find_capability(mdev->pdev, PCI_CAP_ID_PCIX);
hca_pcie_cap = pci_pcie_cap(mdev->pdev);
if (bridge) {
bridge_header = kmalloc(256, GFP_KERNEL);
if (!bridge_header) {
err = -ENOMEM;
mthca_err(mdev, "Couldn't allocate memory to save HCA "
"bridge PCI header, aborting.\n");
goto out;
}
for (i = 0; i < 64; ++i) {
if (i == 22 || i == 23)
continue;
if (pci_read_config_dword(bridge, i * 4, bridge_header + i)) {
err = -ENODEV;
mthca_err(mdev, "Couldn't save HCA bridge "
"PCI header, aborting.\n");
goto out;
}
}
bridge_pcix_cap = pci_find_capability(bridge, PCI_CAP_ID_PCIX);
if (!bridge_pcix_cap) {
err = -ENODEV;
mthca_err(mdev, "Couldn't locate HCA bridge "
"PCI-X capability, aborting.\n");
goto out;
}
}
{
void __iomem *reset = ioremap(pci_resource_start(mdev->pdev, 0) +
MTHCA_RESET_OFFSET, 4);
if (!reset) {
err = -ENOMEM;
mthca_err(mdev, "Couldn't map HCA reset register, "
"aborting.\n");
goto out;
}
writel(MTHCA_RESET_VALUE, reset);
iounmap(reset);
}
msleep(1000);
{
u32 v;
int c = 0;
for (c = 0; c < 100; ++c) {
if (pci_read_config_dword(bridge ? bridge : mdev->pdev, 0, &v)) {
err = -ENODEV;
mthca_err(mdev, "Couldn't access HCA after reset, "
"aborting.\n");
goto out;
}
if (v != 0xffffffff)
goto good;
msleep(100);
}
err = -ENODEV;
mthca_err(mdev, "PCI device did not come back after reset, "
"aborting.\n");
goto out;
}
good:
if (bridge) {
if (pci_write_config_dword(bridge, bridge_pcix_cap + 0x8,
bridge_header[(bridge_pcix_cap + 0x8) / 4])) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA bridge Upstream "
"split transaction control, aborting.\n");
goto out;
}
if (pci_write_config_dword(bridge, bridge_pcix_cap + 0xc,
bridge_header[(bridge_pcix_cap + 0xc) / 4])) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA bridge Downstream "
"split transaction control, aborting.\n");
goto out;
}
for (i = 0; i < 16; ++i) {
if (i * 4 == PCI_COMMAND)
continue;
if (pci_write_config_dword(bridge, i * 4, bridge_header[i])) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA bridge reg %x, "
"aborting.\n", i);
goto out;
}
}
if (pci_write_config_dword(bridge, PCI_COMMAND,
bridge_header[PCI_COMMAND / 4])) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA bridge COMMAND, "
"aborting.\n");
goto out;
}
}
if (hca_pcix_cap) {
if (pci_write_config_dword(mdev->pdev, hca_pcix_cap,
hca_header[hca_pcix_cap / 4])) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA PCI-X "
"command register, aborting.\n");
goto out;
}
}
if (hca_pcie_cap) {
devctl = hca_header[(hca_pcie_cap + PCI_EXP_DEVCTL) / 4];
if (pci_write_config_word(mdev->pdev, hca_pcie_cap + PCI_EXP_DEVCTL,
devctl)) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA PCI Express "
"Device Control register, aborting.\n");
goto out;
}
linkctl = hca_header[(hca_pcie_cap + PCI_EXP_LNKCTL) / 4];
if (pci_write_config_word(mdev->pdev, hca_pcie_cap + PCI_EXP_LNKCTL,
linkctl)) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA PCI Express "
"Link control register, aborting.\n");
goto out;
}
}
for (i = 0; i < 16; ++i) {
if (i * 4 == PCI_COMMAND)
continue;
if (pci_write_config_dword(mdev->pdev, i * 4, hca_header[i])) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA reg %x, "
"aborting.\n", i);
goto out;
}
}
if (pci_write_config_dword(mdev->pdev, PCI_COMMAND,
hca_header[PCI_COMMAND / 4])) {
err = -ENODEV;
mthca_err(mdev, "Couldn't restore HCA COMMAND, "
"aborting.\n");
goto out;
}
out:
if (bridge)
pci_dev_put(bridge);
kfree(bridge_header);
kfree(hca_header);
return err;
}
int mthca_process_mad(struct ib_device *ibdev,
int mad_flags,
u8 port_num,
const struct ib_wc *in_wc,
const struct ib_grh *in_grh,
const struct ib_mad_hdr *in, size_t in_mad_size,
struct ib_mad_hdr *out, size_t *out_mad_size,
u16 *out_mad_pkey_index)
{
int err;
u16 slid = in_wc ? ib_lid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
u16 prev_lid = 0;
struct ib_port_attr pattr;
const struct ib_mad *in_mad = (const struct ib_mad *)in;
struct ib_mad *out_mad = (struct ib_mad *)out;
if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
*out_mad_size != sizeof(*out_mad)))
return IB_MAD_RESULT_FAILURE;
/* Forward locally generated traps to the SM */
if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP &&
slid == 0) {
forward_trap(to_mdev(ibdev), port_num, in_mad);
return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED;
}
/*
* Only handle SM gets, sets and trap represses for SM class
*
* Only handle PMA and Mellanox vendor-specific class gets and
* sets for other classes.
*/
if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) {
if (in_mad->mad_hdr.method != IB_MGMT_METHOD_GET &&
in_mad->mad_hdr.method != IB_MGMT_METHOD_SET &&
in_mad->mad_hdr.method != IB_MGMT_METHOD_TRAP_REPRESS)
return IB_MAD_RESULT_SUCCESS;
/*
* Don't process SMInfo queries or vendor-specific
* MADs -- the SMA can't handle them.
*/
if (in_mad->mad_hdr.attr_id == IB_SMP_ATTR_SM_INFO ||
((in_mad->mad_hdr.attr_id & IB_SMP_ATTR_VENDOR_MASK) ==
IB_SMP_ATTR_VENDOR_MASK))
return IB_MAD_RESULT_SUCCESS;
} else if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT ||
in_mad->mad_hdr.mgmt_class == MTHCA_VENDOR_CLASS1 ||
in_mad->mad_hdr.mgmt_class == MTHCA_VENDOR_CLASS2) {
if (in_mad->mad_hdr.method != IB_MGMT_METHOD_GET &&
in_mad->mad_hdr.method != IB_MGMT_METHOD_SET)
return IB_MAD_RESULT_SUCCESS;
} else
return IB_MAD_RESULT_SUCCESS;
if ((in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) &&
in_mad->mad_hdr.method == IB_MGMT_METHOD_SET &&
in_mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO &&
!ib_query_port(ibdev, port_num, &pattr))
prev_lid = ib_lid_cpu16(pattr.lid);
err = mthca_MAD_IFC(to_mdev(ibdev),
mad_flags & IB_MAD_IGNORE_MKEY,
mad_flags & IB_MAD_IGNORE_BKEY,
port_num, in_wc, in_grh, in_mad, out_mad);
if (err == -EBADMSG)
return IB_MAD_RESULT_SUCCESS;
else if (err) {
mthca_err(to_mdev(ibdev), "MAD_IFC returned %d\n", err);
return IB_MAD_RESULT_FAILURE;
}
if (!out_mad->mad_hdr.status) {
smp_snoop(ibdev, port_num, in_mad, prev_lid);
node_desc_override(ibdev, out_mad);
}
/* set return bit in status of directed route responses */
if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
out_mad->mad_hdr.status |= cpu_to_be16(1 << 15);
if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP_REPRESS)
/* no response for trap repress */
return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED;
return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
}
