diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-12-15 12:03:32 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-12-15 12:03:32 -0800 |
commit | 4d5b57e05a67c3cfd8e2b2a64ca356245a15b1c6 (patch) | |
tree | d8f3ea3bc3ccfe289f414bbe9a4bdd1e935d9228 /drivers/infiniband/hw/hfi1 | |
parent | 6df8b74b1720db1133ace0861cb6721bfe57819a (diff) | |
parent | 6f94ba20799b98c8badf047b184fb4cd7bc45e44 (diff) | |
download | linux-4d5b57e05a67c3cfd8e2b2a64ca356245a15b1c6.tar.bz2 |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma
Pull rdma updates from Doug Ledford:
"This is the complete update for the rdma stack for this release cycle.
Most of it is typical driver and core updates, but there is the
entirely new VMWare pvrdma driver. You may have noticed that there
were changes in DaveM's pull request to the bnxt Ethernet driver to
support a RoCE RDMA driver. The bnxt_re driver was tentatively set to
be pulled in this release cycle, but it simply wasn't ready in time
and was dropped (a few review comments still to address, and some
multi-arch build issues like prefetch() not working across all
arches).
Summary:
- shared mlx5 updates with net stack (will drop out on merge if
Dave's tree has already been merged)
- driver updates: cxgb4, hfi1, hns-roce, i40iw, mlx4, mlx5, qedr, rxe
- debug cleanups
- new connection rejection helpers
- SRP updates
- various misc fixes
- new paravirt driver from vmware"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (210 commits)
IB: Add vmw_pvrdma driver
IB/mlx4: fix improper return value
IB/ocrdma: fix bad initialization
infiniband: nes: return value of skb_linearize should be handled
MAINTAINERS: Update Intel RDMA RNIC driver maintainers
MAINTAINERS: Remove Mitesh Ahuja from emulex maintainers
IB/core: fix unmap_sg argument
qede: fix general protection fault may occur on probe
IB/mthca: Replace pci_pool_alloc by pci_pool_zalloc
mlx5, calc_sq_size(): Make a debug message more informative
mlx5: Remove a set-but-not-used variable
mlx5: Use { } instead of { 0 } to init struct
IB/srp: Make writing the add_target sysfs attr interruptible
IB/srp: Make mapping failures easier to debug
IB/srp: Make login failures easier to debug
IB/srp: Introduce a local variable in srp_add_one()
IB/srp: Fix CONFIG_DYNAMIC_DEBUG=n build
IB/multicast: Check ib_find_pkey() return value
IPoIB: Avoid reading an uninitialized member variable
IB/mad: Fix an array index check
...
Diffstat (limited to 'drivers/infiniband/hw/hfi1')
29 files changed, 1181 insertions, 380 deletions
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index 67ea85a56945..7a3d906b3671 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -125,6 +125,7 @@ int node_affinity_init(void) cpumask_weight(topology_sibling_cpumask( cpumask_first(&node_affinity.proc.mask) )); + node_affinity.num_possible_nodes = num_possible_nodes(); node_affinity.num_online_nodes = num_online_nodes(); node_affinity.num_online_cpus = num_online_cpus(); @@ -135,7 +136,7 @@ int node_affinity_init(void) */ init_real_cpu_mask(); - hfi1_per_node_cntr = kcalloc(num_possible_nodes(), + hfi1_per_node_cntr = kcalloc(node_affinity.num_possible_nodes, sizeof(*hfi1_per_node_cntr), GFP_KERNEL); if (!hfi1_per_node_cntr) return -ENOMEM; diff --git a/drivers/infiniband/hw/hfi1/affinity.h b/drivers/infiniband/hw/hfi1/affinity.h index 42e63316afd1..e78c7aa094e0 100644 --- a/drivers/infiniband/hw/hfi1/affinity.h +++ b/drivers/infiniband/hw/hfi1/affinity.h @@ -70,14 +70,6 @@ struct cpu_mask_set { uint gen; }; -struct hfi1_affinity { - struct cpu_mask_set def_intr; - struct cpu_mask_set rcv_intr; - struct cpumask real_cpu_mask; - /* spin lock to protect affinity struct */ - spinlock_t lock; -}; - struct hfi1_msix_entry; /* Initialize non-HT cpu cores mask */ @@ -115,6 +107,7 @@ struct hfi1_affinity_node_list { struct cpumask real_cpu_mask; struct cpu_mask_set proc; int num_core_siblings; + int num_possible_nodes; int num_online_nodes; int num_online_cpus; struct mutex lock; /* protects affinity nodes */ diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 24d0820873cf..ef72bc2a9e1d 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -8477,7 +8477,10 @@ static int do_8051_command( */ if (type == HCMD_WRITE_LCB_CSR) { in_data |= ((*out_data) & 0xffffffffffull) << 8; - reg = ((((*out_data) >> 40) & 0xff) << + /* must preserve COMPLETED - it is tied to hardware */ + reg = read_csr(dd, DC_DC8051_CFG_EXT_DEV_0); + reg &= DC_DC8051_CFG_EXT_DEV_0_COMPLETED_SMASK; + reg |= ((((*out_data) >> 40) & 0xff) << DC_DC8051_CFG_EXT_DEV_0_RETURN_CODE_SHIFT) | ((((*out_data) >> 48) & 0xffff) << DC_DC8051_CFG_EXT_DEV_0_RSP_DATA_SHIFT); @@ -9556,11 +9559,11 @@ int bringup_serdes(struct hfi1_pportdata *ppd) if (HFI1_CAP_IS_KSET(EXTENDED_PSN)) add_rcvctrl(dd, RCV_CTRL_RCV_EXTENDED_PSN_ENABLE_SMASK); - guid = ppd->guid; + guid = ppd->guids[HFI1_PORT_GUID_INDEX]; if (!guid) { if (dd->base_guid) guid = dd->base_guid + ppd->port - 1; - ppd->guid = guid; + ppd->guids[HFI1_PORT_GUID_INDEX] = guid; } /* Set linkinit_reason on power up per OPA spec */ diff --git a/drivers/infiniband/hw/hfi1/chip_registers.h b/drivers/infiniband/hw/hfi1/chip_registers.h index 5b9993899789..5bfa839d1c48 100644 --- a/drivers/infiniband/hw/hfi1/chip_registers.h +++ b/drivers/infiniband/hw/hfi1/chip_registers.h @@ -415,6 +415,9 @@ #define ASIC_CFG_SBUS_REQUEST_DATA_IN_SHIFT 32 #define ASIC_CFG_SBUS_REQUEST_RECEIVER_ADDR_SHIFT 0 #define ASIC_CFG_SCRATCH (ASIC + 0x000000000020) +#define ASIC_CFG_SCRATCH_1 (ASIC_CFG_SCRATCH + 0x08) +#define ASIC_CFG_SCRATCH_2 (ASIC_CFG_SCRATCH + 0x10) +#define ASIC_CFG_SCRATCH_3 (ASIC_CFG_SCRATCH + 0x18) #define ASIC_CFG_THERM_POLL_EN (ASIC + 0x000000000050) #define ASIC_EEP_ADDR_CMD (ASIC + 0x000000000308) #define ASIC_EEP_ADDR_CMD_EP_ADDR_MASK 0xFFFFFFull diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c index 632ba21759ab..8725f4c086cf 100644 --- a/drivers/infiniband/hw/hfi1/debugfs.c +++ b/drivers/infiniband/hw/hfi1/debugfs.c @@ -541,6 +541,114 @@ static ssize_t asic_flags_write(struct file *file, const char __user *buf, return ret; } +/* read the dc8051 memory */ +static ssize_t dc8051_memory_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct hfi1_pportdata *ppd = private2ppd(file); + ssize_t rval; + void *tmp; + loff_t start, end; + + /* the checks below expect the position to be positive */ + if (*ppos < 0) + return -EINVAL; + + tmp = kzalloc(DC8051_DATA_MEM_SIZE, GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + /* + * Fill in the requested portion of the temporary buffer from the + * 8051 memory. The 8051 memory read is done in terms of 8 bytes. + * Adjust start and end to fit. Skip reading anything if out of + * range. + */ + start = *ppos & ~0x7; /* round down */ + if (start < DC8051_DATA_MEM_SIZE) { + end = (*ppos + count + 7) & ~0x7; /* round up */ + if (end > DC8051_DATA_MEM_SIZE) + end = DC8051_DATA_MEM_SIZE; + rval = read_8051_data(ppd->dd, start, end - start, + (u64 *)(tmp + start)); + if (rval) + goto done; + } + + rval = simple_read_from_buffer(buf, count, ppos, tmp, + DC8051_DATA_MEM_SIZE); +done: + kfree(tmp); + return rval; +} + +static ssize_t debugfs_lcb_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct hfi1_pportdata *ppd = private2ppd(file); + struct hfi1_devdata *dd = ppd->dd; + unsigned long total, csr_off; + u64 data; + + if (*ppos < 0) + return -EINVAL; + /* only read 8 byte quantities */ + if ((count % 8) != 0) + return -EINVAL; + /* offset must be 8-byte aligned */ + if ((*ppos % 8) != 0) + return -EINVAL; + /* do nothing if out of range or zero count */ + if (*ppos >= (LCB_END - LCB_START) || !count) + return 0; + /* reduce count if needed */ + if (*ppos + count > LCB_END - LCB_START) + count = (LCB_END - LCB_START) - *ppos; + + csr_off = LCB_START + *ppos; + for (total = 0; total < count; total += 8, csr_off += 8) { + if (read_lcb_csr(dd, csr_off, (u64 *)&data)) + break; /* failed */ + if (put_user(data, (unsigned long __user *)(buf + total))) + break; + } + *ppos += total; + return total; +} + +static ssize_t debugfs_lcb_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct hfi1_pportdata *ppd = private2ppd(file); + struct hfi1_devdata *dd = ppd->dd; + unsigned long total, csr_off, data; + + if (*ppos < 0) + return -EINVAL; + /* only write 8 byte quantities */ + if ((count % 8) != 0) + return -EINVAL; + /* offset must be 8-byte aligned */ + if ((*ppos % 8) != 0) + return -EINVAL; + /* do nothing if out of range or zero count */ + if (*ppos >= (LCB_END - LCB_START) || !count) + return 0; + /* reduce count if needed */ + if (*ppos + count > LCB_END - LCB_START) + count = (LCB_END - LCB_START) - *ppos; + + csr_off = LCB_START + *ppos; + for (total = 0; total < count; total += 8, csr_off += 8) { + if (get_user(data, (unsigned long __user *)(buf + total))) + break; + if (write_lcb_csr(dd, csr_off, data)) + break; /* failed */ + } + *ppos += total; + return total; +} + /* * read the per-port QSFP data for ppd */ @@ -931,6 +1039,8 @@ static const struct counter_info port_cntr_ops[] = { DEBUGFS_XOPS("qsfp2", qsfp2_debugfs_read, qsfp2_debugfs_write, qsfp2_debugfs_open, qsfp2_debugfs_release), DEBUGFS_OPS("asic_flags", asic_flags_read, asic_flags_write), + DEBUGFS_OPS("dc8051_memory", dc8051_memory_read, NULL), + DEBUGFS_OPS("lcb", debugfs_lcb_read, debugfs_lcb_write), }; static void *_sdma_cpu_list_seq_start(struct seq_file *s, loff_t *pos) diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c index c5efff29c147..4fbaee68012b 100644 --- a/drivers/infiniband/hw/hfi1/driver.c +++ b/drivers/infiniband/hw/hfi1/driver.c @@ -795,8 +795,7 @@ static inline void process_rcv_qp_work(struct hfi1_packet *packet) hfi1_schedule_send(qp); spin_unlock_irqrestore(&qp->s_lock, flags); } - if (atomic_dec_and_test(&qp->refcount)) - wake_up(&qp->wait); + rvt_put_qp(qp); } } diff --git a/drivers/infiniband/hw/hfi1/eprom.c b/drivers/infiniband/hw/hfi1/eprom.c index e70c223801b4..26da124c88e2 100644 --- a/drivers/infiniband/hw/hfi1/eprom.c +++ b/drivers/infiniband/hw/hfi1/eprom.c @@ -207,6 +207,40 @@ done_asic: /* magic character sequence that trails an image */ #define IMAGE_TRAIL_MAGIC "egamiAPO" +/* EPROM file types */ +#define HFI1_EFT_PLATFORM_CONFIG 2 + +/* segment size - 128 KiB */ +#define SEG_SIZE (128 * 1024) + +struct hfi1_eprom_footer { + u32 oprom_size; /* size of the oprom, in bytes */ + u16 num_table_entries; + u16 version; /* version of this footer */ + u32 magic; /* must be last */ +}; + +struct hfi1_eprom_table_entry { + u32 type; /* file type */ + u32 offset; /* file offset from start of EPROM */ + u32 size; /* file size, in bytes */ +}; + +/* + * Calculate the max number of table entries that will fit within a directory + * buffer of size 'dir_size'. + */ +#define MAX_TABLE_ENTRIES(dir_size) \ + (((dir_size) - sizeof(struct hfi1_eprom_footer)) / \ + sizeof(struct hfi1_eprom_table_entry)) + +#define DIRECTORY_SIZE(n) (sizeof(struct hfi1_eprom_footer) + \ + (sizeof(struct hfi1_eprom_table_entry) * (n))) + +#define MAGIC4(a, b, c, d) ((d) << 24 | (c) << 16 | (b) << 8 | (a)) +#define FOOTER_MAGIC MAGIC4('e', 'p', 'r', 'm') +#define FOOTER_VERSION 1 + /* * Read all of partition 1. The actual file is at the front. Adjust * the returned size if a trailing image magic is found. @@ -242,6 +276,167 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data, } /* + * The segment magic has been checked. There is a footer and table of + * contents present. + * + * directory is a u32 aligned buffer of size EP_PAGE_SIZE. + */ +static int read_segment_platform_config(struct hfi1_devdata *dd, + void *directory, void **data, u32 *size) +{ + struct hfi1_eprom_footer *footer; + struct hfi1_eprom_table_entry *table; + struct hfi1_eprom_table_entry *entry; + void *buffer = NULL; + void *table_buffer = NULL; + int ret, i; + u32 directory_size; + u32 seg_base, seg_offset; + u32 bytes_available, ncopied, to_copy; + + /* the footer is at the end of the directory */ + footer = (struct hfi1_eprom_footer *) + (directory + EP_PAGE_SIZE - sizeof(*footer)); + + /* make sure the structure version is supported */ + if (footer->version != FOOTER_VERSION) + return -EINVAL; + + /* oprom size cannot be larger than a segment */ + if (footer->oprom_size >= SEG_SIZE) + return -EINVAL; + + /* the file table must fit in a segment with the oprom */ + if (footer->num_table_entries > + MAX_TABLE_ENTRIES(SEG_SIZE - footer->oprom_size)) + return -EINVAL; + + /* find the file table start, which precedes the footer */ + directory_size = DIRECTORY_SIZE(footer->num_table_entries); + if (directory_size <= EP_PAGE_SIZE) { + /* the file table fits into the directory buffer handed in */ + table = (struct hfi1_eprom_table_entry *) + (directory + EP_PAGE_SIZE - directory_size); + } else { + /* need to allocate and read more */ + table_buffer = kmalloc(directory_size, GFP_KERNEL); + if (!table_buffer) + return -ENOMEM; + ret = read_length(dd, SEG_SIZE - directory_size, + directory_size, table_buffer); + if (ret) + goto done; + table = table_buffer; + } + + /* look for the platform configuration file in the table */ + for (entry = NULL, i = 0; i < footer->num_table_entries; i++) { + if (table[i].type == HFI1_EFT_PLATFORM_CONFIG) { + entry = &table[i]; + break; + } + } + if (!entry) { + ret = -ENOENT; + goto done; + } + + /* + * Sanity check on the configuration file size - it should never + * be larger than 4 KiB. + */ + if (entry->size > (4 * 1024)) { + dd_dev_err(dd, "Bad configuration file size 0x%x\n", + entry->size); + ret = -EINVAL; + goto done; + } + + /* check for bogus offset and size that wrap when added together */ + if (entry->offset + entry->size < entry->offset) { + dd_dev_err(dd, + "Bad configuration file start + size 0x%x+0x%x\n", + entry->offset, entry->size); + ret = -EINVAL; + goto done; + } + + /* allocate the buffer to return */ + buffer = kmalloc(entry->size, GFP_KERNEL); + if (!buffer) { + ret = -ENOMEM; + goto done; + } + + /* + * Extract the file by looping over segments until it is fully read. + */ + seg_offset = entry->offset % SEG_SIZE; + seg_base = entry->offset - seg_offset; + ncopied = 0; + while (ncopied < entry->size) { + /* calculate data bytes available in this segment */ + + /* start with the bytes from the current offset to the end */ + bytes_available = SEG_SIZE - seg_offset; + /* subtract off footer and table from segment 0 */ + if (seg_base == 0) { + /* + * Sanity check: should not have a starting point + * at or within the directory. + */ + if (bytes_available <= directory_size) { + dd_dev_err(dd, + "Bad configuration file - offset 0x%x within footer+table\n", + entry->offset); + ret = -EINVAL; + goto done; + } + bytes_available -= directory_size; + } + + /* calculate bytes wanted */ + to_copy = entry->size - ncopied; + + /* max out at the available bytes in this segment */ + if (to_copy > bytes_available) + to_copy = bytes_available; + + /* + * Read from the EPROM. + * + * The sanity check for entry->offset is done in read_length(). + * The EPROM offset is validated against what the hardware + * addressing supports. In addition, if the offset is larger + * than the actual EPROM, it silently wraps. It will work + * fine, though the reader may not get what they expected + * from the EPROM. + */ + ret = read_length(dd, seg_base + seg_offset, to_copy, + buffer + ncopied); + if (ret) + goto done; + + ncopied += to_copy; + + /* set up for next segment */ + seg_offset = footer->oprom_size; + seg_base += SEG_SIZE; + } + + /* success */ + ret = 0; + *data = buffer; + *size = entry->size; + +done: + kfree(table_buffer); + if (ret) + kfree(buffer); + return ret; +} + +/* * Read the platform configuration file from the EPROM. * * On success, an allocated buffer containing the data and its size are @@ -253,6 +448,7 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data, * -EBUSY - not able to acquire access to the EPROM * -ENOENT - no recognizable file written * -ENOMEM - buffer could not be allocated + * -EINVAL - invalid EPROM contentents found */ int eprom_read_platform_config(struct hfi1_devdata *dd, void **data, u32 *size) { @@ -266,21 +462,20 @@ int eprom_read_platform_config(struct hfi1_devdata *dd, void **data, u32 *size) if (ret) return -EBUSY; - /* read the last page of P0 for the EPROM format magic */ - ret = read_length(dd, P1_START - EP_PAGE_SIZE, EP_PAGE_SIZE, directory); + /* read the last page of the segment for the EPROM format magic */ + ret = read_length(dd, SEG_SIZE - EP_PAGE_SIZE, EP_PAGE_SIZE, directory); if (ret) goto done; - /* last dword of P0 contains a magic indicator */ - if (directory[EP_PAGE_DWORDS - 1] == 0) { + /* last dword of the segment contains a magic value */ + if (directory[EP_PAGE_DWORDS - 1] == FOOTER_MAGIC) { + /* segment format */ + ret = read_segment_platform_config(dd, directory, data, size); + } else { /* partition format */ ret = read_partition_platform_config(dd, data, size); - goto done; } - /* nothing recognized */ - ret = -ENOENT; - done: release_chip_resource(dd, CR_EPROM); return ret; diff --git a/drivers/infiniband/hw/hfi1/firmware.c b/drivers/infiniband/hw/hfi1/firmware.c index 13db8eb4f4ec..0dd50cdb039a 100644 --- a/drivers/infiniband/hw/hfi1/firmware.c +++ b/drivers/infiniband/hw/hfi1/firmware.c @@ -239,6 +239,16 @@ static const u8 all_fabric_serdes_broadcast = 0xe1; const u8 pcie_serdes_broadcast[2] = { 0xe2, 0xe3 }; static const u8 all_pcie_serdes_broadcast = 0xe0; +static const u32 platform_config_table_limits[PLATFORM_CONFIG_TABLE_MAX] = { + 0, + SYSTEM_TABLE_MAX, + PORT_TABLE_MAX, + RX_PRESET_TABLE_MAX, + TX_PRESET_TABLE_MAX, + QSFP_ATTEN_TABLE_MAX, + VARIABLE_SETTINGS_TABLE_MAX +}; + /* forwards */ static void dispose_one_firmware(struct firmware_details *fdet); static int load_fabric_serdes_firmware(struct hfi1_devdata *dd, @@ -263,11 +273,13 @@ static int __read_8051_data(struct hfi1_devdata *dd, u32 addr, u64 *result) u64 reg; int count; - /* start the read at the given address */ - reg = ((addr & DC_DC8051_CFG_RAM_ACCESS_CTRL_ADDRESS_MASK) - << DC_DC8051_CFG_RAM_ACCESS_CTRL_ADDRESS_SHIFT) - | DC_DC8051_CFG_RAM_ACCESS_CTRL_READ_ENA_SMASK; + /* step 1: set the address, clear enable */ + reg = (addr & DC_DC8051_CFG_RAM_ACCESS_CTRL_ADDRESS_MASK) + << DC_DC8051_CFG_RAM_ACCESS_CTRL_ADDRESS_SHIFT; write_csr(dd, DC_DC8051_CFG_RAM_ACCESS_CTRL, reg); + /* step 2: enable */ + write_csr(dd, DC_DC8051_CFG_RAM_ACCESS_CTRL, + reg | DC_DC8051_CFG_RAM_ACCESS_CTRL_READ_ENA_SMASK); /* wait until ACCESS_COMPLETED is set */ count = 0; @@ -707,6 +719,9 @@ static int obtain_firmware(struct hfi1_devdata *dd) &dd->pcidev->dev); if (err) { platform_config = NULL; + dd_dev_err(dd, + "%s: No default platform config file found\n", + __func__); goto done; } dd->platform_config.data = platform_config->data; @@ -1761,8 +1776,17 @@ int parse_platform_config(struct hfi1_devdata *dd) u32 record_idx = 0, table_type = 0, table_length_dwords = 0; int ret = -EINVAL; /* assume failure */ + /* + * For integrated devices that did not fall back to the default file, + * the SI tuning information for active channels is acquired from the + * scratch register bitmap, thus there is no platform config to parse. + * Skip parsing in these situations. + */ + if (is_integrated(dd) && !platform_config_load) + return 0; + if (!dd->platform_config.data) { - dd_dev_info(dd, "%s: Missing config file\n", __func__); + dd_dev_err(dd, "%s: Missing config file\n", __func__); goto bail; } ptr = (u32 *)dd->platform_config.data; @@ -1770,7 +1794,7 @@ int parse_platform_config(struct hfi1_devdata *dd) magic_num = *ptr; ptr++; if (magic_num != PLATFORM_CONFIG_MAGIC_NUM) { - dd_dev_info(dd, "%s: Bad config file\n", __func__); + dd_dev_err(dd, "%s: Bad config file\n", __func__); goto bail; } @@ -1797,9 +1821,9 @@ int parse_platform_config(struct hfi1_devdata *dd) header1 = *ptr; header2 = *(ptr + 1); if (header1 != ~header2) { - dd_dev_info(dd, "%s: Failed validation at offset %ld\n", - __func__, (ptr - (u32 *) - dd->platform_config.data)); + dd_dev_err(dd, "%s: Failed validation at offset %ld\n", + __func__, (ptr - (u32 *) + dd->platform_config.data)); goto bail; } @@ -1841,11 +1865,11 @@ int parse_platform_config(struct hfi1_devdata *dd) table_length_dwords; break; default: - dd_dev_info(dd, - "%s: Unknown data table %d, offset %ld\n", - __func__, table_type, - (ptr - (u32 *) - dd->platform_config.data)); + dd_dev_err(dd, + "%s: Unknown data table %d, offset %ld\n", + __func__, table_type, + (ptr - (u32 *) + dd->platform_config.data)); goto bail; /* We don't trust this file now */ } pcfgcache->config_tables[table_type].table = ptr; @@ -1865,11 +1889,11 @@ int parse_platform_config(struct hfi1_devdata *dd) case PLATFORM_CONFIG_VARIABLE_SETTINGS_TABLE: break; default: - dd_dev_info(dd, - "%s: Unknown meta table %d, offset %ld\n", - __func__, table_type, - (ptr - - (u32 *)dd->platform_config.data)); + dd_dev_err(dd, + "%s: Unknown meta table %d, offset %ld\n", + __func__, table_type, + (ptr - + (u32 *)dd->platform_config.data)); goto bail; /* We don't trust this file now */ } pcfgcache->config_tables[table_type].table_metadata = @@ -1884,10 +1908,9 @@ int parse_platform_config(struct hfi1_devdata *dd) /* Jump the table */ ptr += table_length_dwords; if (crc != *ptr) { - dd_dev_info(dd, "%s: Failed CRC check at offset %ld\n", - __func__, (ptr - - (u32 *) - dd->platform_config.data)); + dd_dev_err(dd, "%s: Failed CRC check at offset %ld\n", + __func__, (ptr - + (u32 *)dd->platform_config.data)); goto bail; } /* Jump the CRC DWORD */ @@ -1901,6 +1924,84 @@ bail: return ret; } +static void get_integrated_platform_config_field( + struct hfi1_devdata *dd, + enum platform_config_table_type_encoding table_type, + int field_index, u32 *data) +{ + struct hfi1_pportdata *ppd = dd->pport; + u8 *cache = ppd->qsfp_info.cache; + u32 tx_preset = 0; + + switch (table_type) { + case PLATFORM_CONFIG_SYSTEM_TABLE: + if (field_index == SYSTEM_TABLE_QSFP_POWER_CLASS_MAX) + *data = ppd->max_power_class; + else if (field_index == SYSTEM_TABLE_QSFP_ATTENUATION_DEFAULT_25G) + *data = ppd->default_atten; + break; + case PLATFORM_CONFIG_PORT_TABLE: + if (field_index == PORT_TABLE_PORT_TYPE) + *data = ppd->port_type; + else if (field_index == PORT_TABLE_LOCAL_ATTEN_25G) + *data = ppd->local_atten; + else if (field_index == PORT_TABLE_REMOTE_ATTEN_25G) + *data = ppd->remote_atten; + break; + case PLATFORM_CONFIG_RX_PRESET_TABLE: + if (field_index == RX_PRESET_TABLE_QSFP_RX_CDR_APPLY) + *data = (ppd->rx_preset & QSFP_RX_CDR_APPLY_SMASK) >> + QSFP_RX_CDR_APPLY_SHIFT; + else if (field_index == RX_PRESET_TABLE_QSFP_RX_EMP_APPLY) + *data = (ppd->rx_preset & QSFP_RX_EMP_APPLY_SMASK) >> + QSFP_RX_EMP_APPLY_SHIFT; + else if (field_index == RX_PRESET_TABLE_QSFP_RX_AMP_APPLY) + *data = (ppd->rx_preset & QSFP_RX_AMP_APPLY_SMASK) >> + QSFP_RX_AMP_APPLY_SHIFT; + else if (field_index == RX_PRESET_TABLE_QSFP_RX_CDR) + *data = (ppd->rx_preset & QSFP_RX_CDR_SMASK) >> + QSFP_RX_CDR_SHIFT; + else if (field_index == RX_PRESET_TABLE_QSFP_RX_EMP) + *data = (ppd->rx_preset & QSFP_RX_EMP_SMASK) >> + QSFP_RX_EMP_SHIFT; + else if (field_index == RX_PRESET_TABLE_QSFP_RX_AMP) + *data = (ppd->rx_preset & QSFP_RX_AMP_SMASK) >> + QSFP_RX_AMP_SHIFT; + break; + case PLATFORM_CONFIG_TX_PRESET_TABLE: + if (cache[QSFP_EQ_INFO_OFFS] & 0x4) + tx_preset = ppd->tx_preset_eq; + else + tx_preset = ppd->tx_preset_noeq; + if (field_index == TX_PRESET_TABLE_PRECUR) + *data = (tx_preset & TX_PRECUR_SMASK) >> + TX_PRECUR_SHIFT; + else if (field_index == TX_PRESET_TABLE_ATTN) + *data = (tx_preset & TX_ATTN_SMASK) >> + TX_ATTN_SHIFT; + else if (field_index == TX_PRESET_TABLE_POSTCUR) + *data = (tx_preset & TX_POSTCUR_SMASK) >> + TX_POSTCUR_SHIFT; + else if (field_index == TX_PRESET_TABLE_QSFP_TX_CDR_APPLY) + *data = (tx_preset & QSFP_TX_CDR_APPLY_SMASK) >> + QSFP_TX_CDR_APPLY_SHIFT; + else if (field_index == TX_PRESET_TABLE_QSFP_TX_EQ_APPLY) + *data = (tx_preset & QSFP_TX_EQ_APPLY_SMASK) >> + QSFP_TX_EQ_APPLY_SHIFT; + else if (field_index == TX_PRESET_TABLE_QSFP_TX_CDR) + *data = (tx_preset & QSFP_TX_CDR_SMASK) >> + QSFP_TX_CDR_SHIFT; + else if (field_index == TX_PRESET_TABLE_QSFP_TX_EQ) + *data = (tx_preset & QSFP_TX_EQ_SMASK) >> + QSFP_TX_EQ_SHIFT; + break; + case PLATFORM_CONFIG_QSFP_ATTEN_TABLE: + case PLATFORM_CONFIG_VARIABLE_SETTINGS_TABLE: + default: + break; + } +} + static int get_platform_fw_field_metadata(struct hfi1_devdata *dd, int table, int field, u32 *field_len_bits, u32 *field_start_bits) @@ -1976,6 +2077,15 @@ int get_platform_config_field(struct hfi1_devdata *dd, else return -EINVAL; + if (is_integrated(dd) && !platform_config_load) { + /* + * Use saved configuration from ppd for integrated platforms + */ + get_integrated_platform_config_field(dd, table_type, + field_index, data); + return 0; + } + ret = get_platform_fw_field_metadata(dd, table_type, field_index, &field_len_bits, &field_start_bits); diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index cc87fd4e534b..751a0fb29fa5 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -492,6 +492,9 @@ struct rvt_sge_state; #define HFI1_MIN_VLS_SUPPORTED 1 #define HFI1_MAX_VLS_SUPPORTED 8 +#define HFI1_GUIDS_PER_PORT 5 +#define HFI1_PORT_GUID_INDEX 0 + static inline void incr_cntr64(u64 *cntr) { if (*cntr < (u64)-1LL) @@ -559,11 +562,20 @@ struct hfi1_pportdata { struct kobject vl2mtu_kobj; /* PHY support */ - u32 port_type; struct qsfp_data qsfp_info; + /* Values for SI tuning of SerDes */ + u32 port_type; + u32 tx_preset_eq; + u32 tx_preset_noeq; + u32 rx_preset; + u8 local_atten; + u8 remote_atten; + u8 default_atten; + u8 max_power_class; + + /* GUIDs for this interface, in host order, guids[0] is a port guid */ + u64 guids[HFI1_GUIDS_PER_PORT]; - /* GUID for this interface, in host order */ - u64 guid; /* GUID for peer interface, in host order */ u64 neighbor_guid; @@ -826,32 +838,29 @@ struct hfi1_devdata { u8 __iomem *kregend; /* physical address of chip for io_remap, etc. */ resource_size_t physaddr; - /* receive context data */ - struct hfi1_ctxtdata **rcd; + /* Per VL data. Enough for all VLs but not all elements are set/used. */ + struct per_vl_data vld[PER_VL_SEND_CONTEXTS]; /* send context data */ struct send_context_info *send_contexts; /* map hardware send contexts to software index */ u8 *hw_to_sw; /* spinlock for allocating and releasing send context resources */ spinlock_t sc_lock; - /* Per VL data. Enough for all VLs but not all elements are set/used. */ - struct per_vl_data vld[PER_VL_SEND_CONTEXTS]; /* lock for pio_map */ spinlock_t pio_map_lock; + /* Send Context initialization lock. */ + spinlock_t sc_init_lock; + /* lock for sdma_map */ + spinlock_t sde_map_lock; /* array of kernel send contexts */ struct send_context **kernel_send_context; /* array of vl maps */ struct pio_vl_map __rcu *pio_map; - /* seqlock for sc2vl */ - seqlock_t sc2vl_lock; - u64 sc2vl[4]; - /* Send Context initialization lock. */ - spinlock_t sc_init_lock; + /* default flags to last descriptor */ + u64 default_desc1; /* fields common to all SDMA engines */ - /* default flags to last descriptor */ - u64 default_desc1; volatile __le64 *sdma_heads_dma; /* DMA'ed by chip */ dma_addr_t sdma_heads_phys; void *sdma_pad_dma; /* DMA'ed by chip */ @@ -862,8 +871,6 @@ struct hfi1_devdata { u32 chip_sdma_engines; /* num used */ u32 num_sdma; - /* lock for sdma_map */ - spinlock_t sde_map_lock; /* array of engines sized by num_sdma */ struct sdma_engine *per_sdma; /* array of vl maps */ @@ -872,14 +879,11 @@ struct hfi1_devdata { wait_queue_head_t sdma_unfreeze_wq; atomic_t sdma_unfreeze_count; + u32 lcb_access_count; /* count of LCB users */ + /* common data between shared ASIC HFIs in this OS */ struct hfi1_asic_data *asic_data; - /* hfi1_pportdata, points to array of (physical) port-specific - * data structs, indexed by pidx (0..n-1) - */ - struct hfi1_pportdata *pport; - /* mem-mapped pointer to base of PIO buffers */ void __iomem *piobase; /* @@ -896,20 +900,13 @@ struct hfi1_devdata { /* send context numbers and sizes for each type */ struct sc_config_sizes sc_sizes[SC_MAX]; - u32 lcb_access_count; /* count of LCB users */ - char *boardname; /* human readable board info */ - /* device (not port) flags, basically device capabilities */ - u32 flags; - /* reset value */ u64 z_int_counter; u64 z_rcv_limit; u64 z_send_schedule; - /* percpu int_counter */ - u64 __percpu *int_counter; - u64 __percpu *rcv_limit; + u64 __percpu *send_schedule; /* number of receive contexts in use by the driver */ u32 num_rcv_contexts; @@ -924,6 +921,7 @@ struct hfi1_devdata { /* base receive interrupt timeout, in CSR units */ u32 rcv_intr_timeout_csr; + u32 freezelen; /* max length of freezemsg */ u64 __iomem *egrtidbase; spinlock_t sendctrl_lock; /* protect changes to SendCtrl */ spinlock_t rcvctrl_lock; /* protect changes to RcvCtrl */ @@ -945,7 +943,6 @@ struct hfi1_devdata { * IB link status cheaply */ struct hfi1_status *status; - u32 freezelen; /* max length of freezemsg */ /* revision register shadow */ u64 revision; @@ -973,6 +970,8 @@ struct hfi1_devdata { u16 rcvegrbufsize_shift; /* both sides of the PCIe link are gen3 capable */ u8 link_gen3_capable; + /* default link down value (poll/sleep) */ + u8 link_default; /* localbus width (1, 2,4,8,16,32) from config space */ u32 lbus_width; /* localbus speed in MHz */ @@ -1008,8 +1007,6 @@ struct hfi1_devdata { u8 hfi1_id; /* implementation code */ u8 icode; - /* default link down value (poll/sleep) */ - u8 link_default; /* vAU of this device */ u8 vau; /* vCU of this device */ @@ -1020,27 +1017,17 @@ struct hfi1_devdata { u16 vl15_init; /* Misc small ints */ - /* Number of physical ports available */ - u8 num_pports; - /* Lowest context number which can be used by user processes */ - u8 first_user_ctxt; u8 n_krcv_queues; u8 qos_shift; - u8 qpn_mask; - u16 rhf_offset; /* offset of RHF within receive header entry */ u16 irev; /* implementation revision */ u16 dc8051_ver; /* 8051 firmware version */ + spinlock_t hfi1_diag_trans_lock; /* protect diag observer ops */ struct platform_config platform_config; struct platform_config_cache pcfg_cache; struct diag_client *diag_client; - spinlock_t hfi1_diag_trans_lock; /* protect diag observer ops */ - - u8 psxmitwait_supported; - /* cycle length of PS* counters in HW (in picoseconds) */ - u16 psxmitwait_check_rate; /* MSI-X information */ struct hfi1_msix_entry *msix_entries; @@ -1055,6 +1042,9 @@ struct hfi1_devdata { struct rcv_array_data rcv_entries; + /* cycle length of PS* counters in HW (in picoseconds) */ + u16 psxmitwait_check_rate; + /* * 64 bit synthetic counters */ @@ -1085,11 +1075,11 @@ struct hfi1_devdata { struct err_info_rcvport err_info_rcvport; struct err_info_constraint err_info_rcv_constraint; struct err_info_constraint err_info_xmit_constraint; - u8 err_info_uncorrectable; - u8 err_info_fmconfig; atomic_t drop_packet; u8 do_drop; + u8 err_info_uncorrectable; + u8 err_info_fmconfig; /* * Software counters for the status bits defined by the @@ -1112,40 +1102,60 @@ struct hfi1_devdata { u64 sw_cce_err_status_aggregate; /* Software counter that aggregates all bypass packet rcv errors */ u64 sw_rcv_bypass_packet_errors; - /* receive interrupt functions */ - rhf_rcv_function_ptr *rhf_rcv_function_map; + /* receive interrupt function */ rhf_rcv_function_ptr normal_rhf_rcv_functions[8]; + /* Save the enabled LCB error bits */ + u64 lcb_err_en; + /* * Capability to have different send engines simply by changing a * pointer value. */ - send_routine process_pio_send; + send_routine process_pio_send ____cacheline_aligned_in_smp; send_routine process_dma_send; void (*pio_inline_send)(struct hfi1_devdata *dd, struct pio_buf *pbuf, u64 pbc, const void *from, size_t count); + /* hfi1_pportdata, points to array of (physical) port-specific + * data structs, indexed by pidx (0..n-1) + */ + struct hfi1_pportdata *pport; + /* receive context data */ + struct hfi1_ctxtdata **rcd; + u64 __percpu *int_counter; + /* device (not port) flags, basically device capabilities */ + u16 flags; + /* Number of physical ports available */ + u8 num_pports; + /* Lowest context number which can be used by user processes */ + u8 first_user_ctxt; + /* adding a new field here would make it part of this cacheline */ + + /* seqlock for sc2vl */ + seqlock_t sc2vl_lock ____cacheline_aligned_in_smp; + u64 sc2vl[4]; + /* receive interrupt functions */ + rhf_rcv_function_ptr *rhf_rcv_function_map; + u64 __percpu *rcv_limit; + u16 rhf_offset; /* offset of RHF within receive header entry */ + /* adding a new field here would make it part of this cacheline */ /* OUI comes from the HW. Used everywhere as 3 separate bytes. */ u8 oui1; u8 oui2; u8 oui3; + u8 dc_shutdown; + /* Timer and counter used to detect RcvBufOvflCnt changes */ struct timer_list rcverr_timer; - u32 rcv_ovfl_cnt; wait_queue_head_t event_queue; - /* Save the enabled LCB error bits */ - u64 lcb_err_en; - u8 dc_shutdown; - /* receive context tail dummy address */ __le64 *rcvhdrtail_dummy_kvaddr; dma_addr_t rcvhdrtail_dummy_dma; - bool eprom_available; /* true if EPROM is available for this device */ - bool aspm_supported; /* Does HW support ASPM */ - bool aspm_enabled; /* ASPM state: enabled/disabled */ + u32 rcv_ovfl_cnt; /* Serialize ASPM enable/disable between multiple verbs contexts */ spinlock_t aspm_lock; /* Number of verbs contexts which have disabled ASPM */ @@ -1155,8 +1165,11 @@ struct hfi1_devdata { /* Used to wait for outstanding user space clients before dev removal */ struct completion user_comp; - struct hfi1_affinity *affinity; + bool eprom_available; /* true if EPROM is available for this device */ + bool aspm_supported; /* Does HW support ASPM */ + bool aspm_enabled; /* ASPM state: enabled/disabled */ struct rhashtable sdma_rht; + struct kobject kobj; }; @@ -1604,6 +1617,17 @@ static inline u16 hfi1_get_pkey(struct hfi1_ibport *ibp, unsigned index) } /* + * Return the indexed GUID from the port GUIDs table. + */ +static inline __be64 get_sguid(struct hfi1_ibport *ibp, unsigned int index) +{ + struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); + + WARN_ON(index >= HFI1_GUIDS_PER_PORT); + return cpu_to_be64(ppd->guids[index]); +} + +/* * Called by readers of cc_state only, must call under rcu_read_lock(). */ static inline struct cc_state *get_cc_state(struct hfi1_pportdata *ppd) @@ -1982,6 +2006,12 @@ static inline u32 qsfp_resource(struct hfi1_devdata *dd) return i2c_target(dd->hfi1_id); } +/* Is this device integrated or discrete? */ +static inline bool is_integrated(struct hfi1_devdata *dd) +{ + return dd->pcidev->device == PCI_DEVICE_ID_INTEL1; +} + int hfi1_tempsense_rd(struct hfi1_devdata *dd, struct hfi1_temp *temp); #define DD_DEV_ENTRY(dd) __string(dev, dev_name(&(dd)->pcidev->dev)) diff --git a/drivers/infiniband/hw/hfi1/iowait.h b/drivers/infiniband/hw/hfi1/iowait.h index 2ec6ef38d389..d9740ddea6f1 100644 --- a/drivers/infiniband/hw/hfi1/iowait.h +++ b/drivers/infiniband/hw/hfi1/iowait.h @@ -64,6 +64,7 @@ struct sdma_engine; /** * struct iowait - linkage for delayed progress/waiting * @list: used to add/insert into QP/PQ wait lists + * @lock: uses to record the list head lock * @tx_head: overflow list of sdma_txreq's * @sleep: no space callback * @wakeup: space callback wakeup @@ -91,6 +92,11 @@ struct sdma_engine; * so sleeping is not allowed. * * The wait_dma member along with the iow + * + * The lock field is used by waiters to record + * the seqlock_t that guards the list head. + * Waiters explicity know that, but the destroy + * code that unwaits QPs does not. */ struct iowait { @@ -103,6 +109,7 @@ struct iowait { unsigned seq); void (*wakeup)(struct iowait *wait, int reason); void (*sdma_drained)(struct iowait *wait); + seqlock_t *lock; struct work_struct iowork; wait_queue_head_t wait_dma; wait_queue_head_t wait_pio; @@ -141,6 +148,7 @@ static inline void iowait_init( void (*sdma_drained)(struct iowait *wait)) { wait->count = 0; + wait->lock = NULL; INIT_LIST_HEAD(&wait->list); INIT_LIST_HEAD(&wait->tx_head); INIT_WORK(&wait->iowork, func); diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c index 9487c9bb8920..6e595afca24c 100644 --- a/drivers/infiniband/hw/hfi1/mad.c +++ b/drivers/infiniband/hw/hfi1/mad.c @@ -128,7 +128,7 @@ static void send_trap(struct hfi1_ibport *ibp, void *data, unsigned len) smp = send_buf->mad; smp->base_version = OPA_MGMT_BASE_VERSION; smp->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED; - smp->class_version = OPA_SMI_CLASS_VERSION; + smp->class_version = OPA_SM_CLASS_VERSION; smp->method = IB_MGMT_METHOD_TRAP; ibp->rvp.tid++; smp->tid = cpu_to_be64(ibp->rvp.tid); @@ -336,20 +336,20 @@ static int __subn_get_opa_nodeinfo(struct opa_smp *smp, u32 am, u8 *data, ni = (struct opa_node_info *)data; /* GUID 0 is illegal */ - if (am || pidx >= dd->num_pports || dd->pport[pidx].guid == 0) { + if (am || pidx >= dd->num_pports || ibdev->node_guid == 0 || + get_sguid(to_iport(ibdev, port), HFI1_PORT_GUID_INDEX) == 0) { smp->status |= IB_SMP_INVALID_FIELD; return reply((struct ib_mad_hdr *)smp); } - ni->port_guid = cpu_to_be64(dd->pport[pidx].guid); + ni->port_guid = get_sguid(to_iport(ibdev, port), HFI1_PORT_GUID_INDEX); ni->base_version = OPA_MGMT_BASE_VERSION; - ni->class_version = OPA_SMI_CLASS_VERSION; + ni->class_version = OPA_SM_CLASS_VERSION; ni->node_type = 1; /* channel adapter */ ni->num_ports = ibdev->phys_port_cnt; /* This is already in network order */ ni->system_image_guid = ib_hfi1_sys_image_guid; - /* Use first-port GUID as node */ - ni->node_guid = cpu_to_be64(dd->pport->guid); + ni->node_guid = ibdev->node_guid; ni->partition_cap = cpu_to_be16(hfi1_get_npkeys(dd)); ni->device_id = cpu_to_be16(dd->pcidev->device); ni->revision = cpu_to_be32(dd->minrev); @@ -373,19 +373,20 @@ static int subn_get_nodeinfo(struct ib_smp *smp, struct ib_device *ibdev, /* GUID 0 is illegal */ if (smp->attr_mod || pidx >= dd->num_pports || - dd->pport[pidx].guid == 0) + ibdev->node_guid == 0 || + get_sguid(to_iport(ibdev, port), HFI1_PORT_GUID_INDEX) == 0) { smp->status |= IB_SMP_INVALID_FIELD; - else - nip->port_guid = cpu_to_be64(dd->pport[pidx].guid); + return reply((struct ib_mad_hdr *)smp); + } + nip->port_guid = get_sguid(to_iport(ibdev, port), HFI1_PORT_GUID_INDEX); nip->base_version = OPA_MGMT_BASE_VERSION; - nip->class_version = OPA_SMI_CLASS_VERSION; + nip->class_version = OPA_SM_CLASS_VERSION; nip->node_type = 1; /* channel adapter */ nip->num_ports = ibdev->phys_port_cnt; /* This is already in network order */ nip->sys_guid = ib_hfi1_sys_image_guid; - /* Use first-port GUID as node */ - nip->node_guid = cpu_to_be64(dd->pport->guid); + nip->node_guid = ibdev->node_guid; nip->partition_cap = cpu_to_be16(hfi1_get_npkeys(dd)); nip->device_id = cpu_to_be16(dd->pcidev->device); nip->revision = cpu_to_be32(dd->minrev); @@ -2302,7 +2303,7 @@ static int pma_get_opa_classportinfo(struct opa_pma_mad *pmp, pmp->mad_hdr.status |= IB_SMP_INVALID_FIELD; p->base_version = OPA_MGMT_BASE_VERSION; - p->class_version = OPA_SMI_CLASS_VERSION; + p->class_version = OPA_SM_CLASS_VERSION; /* * Expected response time is 4.096 usec. * 2^18 == 1.073741824 sec. */ @@ -4022,7 +4023,7 @@ static int process_subn_opa(struct ib_device *ibdev, int mad_flags, am = be32_to_cpu(smp->attr_mod); attr_id = smp->attr_id; - if (smp->class_version != OPA_SMI_CLASS_VERSION) { + if (smp->class_version != OPA_SM_CLASS_VERSION) { smp->status |= IB_SMP_UNSUP_VERSION; ret = reply((struct ib_mad_hdr *)smp); return ret; @@ -4232,7 +4233,7 @@ static int process_perf_opa(struct ib_device *ibdev, u8 port, *out_mad = *in_mad; - if (pmp->mad_hdr.class_version != OPA_SMI_CLASS_VERSION) { + if (pmp->mad_hdr.class_version != OPA_SM_CLASS_VERSION) { pmp->mad_hdr.status |= IB_SMP_UNSUP_VERSION; return reply((struct ib_mad_hdr *)pmp); } diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index 7ad30898fc19..ccbf52c8ff6f 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -81,7 +81,7 @@ static void do_remove(struct mmu_rb_handler *handler, struct list_head *del_list); static void handle_remove(struct work_struct *work); -static struct mmu_notifier_ops mn_opts = { +static const struct mmu_notifier_ops mn_opts = { .invalidate_page = mmu_notifier_page, .invalidate_range_start = mmu_notifier_range_start, }; diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index d89b8745d4c1..615be68e40b3 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -758,6 +758,7 @@ struct send_context *sc_alloc(struct hfi1_devdata *dd, int type, sc->hw_context = hw_context; cr_group_addresses(sc, &dma); sc->credits = sci->credits; + sc->size = sc->credits * PIO_BLOCK_SIZE; /* PIO Send Memory Address details */ #define PIO_ADDR_CONTEXT_MASK 0xfful @@ -1242,6 +1243,7 @@ int sc_enable(struct send_context *sc) sc->free = 0; sc->alloc_free = 0; sc->fill = 0; + sc->fill_wrap = 0; sc->sr_head = 0; sc->sr_tail = 0; sc->flags = 0; @@ -1385,7 +1387,7 @@ struct pio_buf *sc_buffer_alloc(struct send_context *sc, u32 dw_len, unsigned long flags; unsigned long avail; unsigned long blocks = dwords_to_blocks(dw_len); - unsigned long start_fill; + u32 fill_wrap; int trycount = 0; u32 head, next; @@ -1410,9 +1412,7 @@ retry: (sc->fill - sc->alloc_free); if (blocks > avail) { /* still no room, actively update */ - spin_unlock_irqrestore(&sc->alloc_lock, flags); sc_release_update(sc); - spin_lock_irqsave(&sc->alloc_lock, flags); sc->alloc_free = ACCESS_ONCE(sc->free); trycount++; goto retry; @@ -1428,8 +1428,11 @@ retry: head = sc->sr_head; /* "allocate" the buffer */ - start_fill = sc->fill; sc->fill += blocks; + fill_wrap = sc->fill_wrap; + sc->fill_wrap += blocks; + if (sc->fill_wrap >= sc->credits) + sc->fill_wrap = sc->fill_wrap - sc->credits; /* * Fill the parts that the releaser looks at before moving the head. @@ -1458,11 +1461,8 @@ retry: spin_unlock_irqrestore(&sc->alloc_lock, flags); /* finish filling in the buffer outside the lock */ - pbuf->start = sc->base_addr + ((start_fill % sc->credits) - * PIO_BLOCK_SIZE); - pbuf->size = sc->credits * PIO_BLOCK_SIZE; - pbuf->end = sc->base_addr + pbuf->size; - pbuf->block_count = blocks; + pbuf->start = sc->base_addr + fill_wrap * PIO_BLOCK_SIZE; + pbuf->end = sc->base_addr + sc->size; pbuf->qw_written = 0; pbuf->carry_bytes = 0; pbuf->carry.val64 = 0; @@ -1573,6 +1573,7 @@ static void sc_piobufavail(struct send_context *sc) qp = iowait_to_qp(wait); priv = qp->priv; list_del_init(&priv->s_iowait.list); + priv->s_iowait.lock = NULL; /* refcount held until actual wake up */ qps[n++] = qp; } @@ -2028,29 +2029,17 @@ freesc15: int init_credit_return(struct hfi1_devdata *dd) { int ret; - int num_numa; int i; - num_numa = num_online_nodes(); - /* enforce the expectation that the numas are compact */ - for (i = 0; i < num_numa; i++) { - if (!node_online(i)) { - dd_dev_err(dd, "NUMA nodes are not compact\n"); - ret = -EINVAL; - goto done; - } - } - dd->cr_base = kcalloc( - num_numa, + node_affinity.num_possible_nodes, sizeof(struct credit_return_base), GFP_KERNEL); if (!dd->cr_base) { - dd_dev_err(dd, "Unable to allocate credit return base\n"); ret = -ENOMEM; goto done; } - for (i = 0; i < num_numa; i++) { + for_each_node_with_cpus(i) { int bytes = TXE_NUM_CONTEXTS * sizeof(struct credit_return); set_dev_node(&dd->pcidev->dev, i); @@ -2077,14 +2066,11 @@ done: void free_credit_return(struct hfi1_devdata *dd) { - int num_numa; int i; if (!dd->cr_base) return; - - num_numa = num_online_nodes(); - for (i = 0; i < num_numa; i++) { + for (i = 0; i < node_affinity.num_possible_nodes; i++) { if (dd->cr_base[i].va) { dma_free_coherent(&dd->pcidev->dev, TXE_NUM_CONTEXTS * diff --git a/drivers/infiniband/hw/hfi1/pio.h b/drivers/infiniband/hw/hfi1/pio.h index e709eaf743b5..867e5ffc3595 100644 --- a/drivers/infiniband/hw/hfi1/pio.h +++ b/drivers/infiniband/hw/hfi1/pio.h @@ -83,53 +83,55 @@ struct pio_buf { void *arg; /* argument for cb */ void __iomem *start; /* buffer start address */ void __iomem *end; /* context end address */ - unsigned long size; /* context size, in bytes */ unsigned long sent_at; /* buffer is sent when <= free */ - u32 block_count; /* size of buffer, in blocks */ - u32 qw_written; /* QW written so far */ - u32 carry_bytes; /* number of valid bytes in carry */ union mix carry; /* pending unwritten bytes */ + u16 qw_written; /* QW written so far */ + u8 carry_bytes; /* number of valid bytes in carry */ }; /* cache line aligned pio buffer array */ union pio_shadow_ring { struct pio_buf pbuf; - u64 unused[16]; /* cache line spacer */ } ____cacheline_aligned; /* per-NUMA send context */ struct send_context { /* read-only after init */ struct hfi1_devdata *dd; /* device */ - void __iomem *base_addr; /* start of PIO memory */ union pio_shadow_ring *sr; /* shadow ring */ + void __iomem *base_addr; /* start of PIO memory */ + u32 __percpu *buffers_allocated;/* count of buffers allocated */ + u32 size; /* context size, in bytes */ - volatile __le64 *hw_free; /* HW free counter */ - struct work_struct halt_work; /* halted context work queue entry */ - unsigned long flags; /* flags */ int node; /* context home node */ - int type; /* context type */ - u32 sw_index; /* software index number */ - u32 hw_context; /* hardware context number */ - u32 credits; /* number of blocks in context */ u32 sr_size; /* size of the shadow ring */ - u32 group; /* credit return group */ + u16 flags; /* flags */ + u8 type; /* context type */ + u8 sw_index; /* software index number */ + u8 hw_context; /* hardware context number */ + u8 group; /* credit return group */ + /* allocator fields */ spinlock_t alloc_lock ____cacheline_aligned_in_smp; + u32 sr_head; /* shadow ring head */ unsigned long fill; /* official alloc count */ unsigned long alloc_free; /* copy of free (less cache thrash) */ - u32 sr_head; /* shadow ring head */ + u32 fill_wrap; /* tracks fill within ring */ + u32 credits; /* number of blocks in context */ + /* adding a new field here would make it part of this cacheline */ + /* releaser fields */ spinlock_t release_lock ____cacheline_aligned_in_smp; - unsigned long free; /* official free count */ u32 sr_tail; /* shadow ring tail */ + unsigned long free; /* official free count */ + volatile __le64 *hw_free; /* HW free counter */ /* list for PIO waiters */ struct list_head piowait ____cacheline_aligned_in_smp; spinlock_t credit_ctrl_lock ____cacheline_aligned_in_smp; - u64 credit_ctrl; /* cache for credit control */ u32 credit_intr_count; /* count of credit intr users */ - u32 __percpu *buffers_allocated;/* count of buffers allocated */ + u64 credit_ctrl; /* cache for credit control */ wait_queue_head_t halt_wait; /* wait until kernel sees interrupt */ + struct work_struct halt_work; /* halted context work queue entry */ }; /* send context flags */ diff --git a/drivers/infiniband/hw/hfi1/pio_copy.c b/drivers/infiniband/hw/hfi1/pio_copy.c index aa7773643107..03024cec78dd 100644 --- a/drivers/infiniband/hw/hfi1/pio_copy.c +++ b/drivers/infiniband/hw/hfi1/pio_copy.c @@ -129,8 +129,8 @@ void pio_copy(struct hfi1_devdata *dd, struct pio_buf *pbuf, u64 pbc, dest += sizeof(u64); } - dest -= pbuf->size; - dend -= pbuf->size; + dest -= pbuf->sc->size; + dend -= pbuf->sc->size; } /* write 8-byte non-SOP, non-wrap chunk data */ @@ -361,8 +361,8 @@ void seg_pio_copy_start(struct pio_buf *pbuf, u64 pbc, dest += sizeof(u64); } - dest -= pbuf->size; - dend -= pbuf->size; + dest -= pbuf->sc->size; + dend -= pbuf->sc->size; } /* write 8-byte non-SOP, non-wrap chunk data */ @@ -458,8 +458,8 @@ static void mid_copy_mix(struct pio_buf *pbuf, const void *from, size_t nbytes) dest += sizeof(u64); } - dest -= pbuf->size; - dend -= pbuf->size; + dest -= pbuf->sc->size; + dend -= pbuf->sc->size; } /* write 8-byte non-SOP, non-wrap chunk data */ @@ -492,7 +492,7 @@ static void mid_copy_mix(struct pio_buf *pbuf, const void *from, size_t nbytes) */ /* adjust if we have wrapped */ if (dest >= pbuf->end) - dest -= pbuf->size; + dest -= pbuf->sc->size; /* jump to the SOP range if within the first block */ else if (pbuf->qw_written < PIO_BLOCK_QWS) dest += SOP_DISTANCE; @@ -584,8 +584,8 @@ static void mid_copy_straight(struct pio_buf *pbuf, dest += sizeof(u64); } - dest -= pbuf->size; - dend -= pbuf->size; + dest -= pbuf->sc->size; + dend -= pbuf->sc->size; } /* write 8-byte non-SOP, non-wrap chunk data */ @@ -666,7 +666,7 @@ void seg_pio_copy_mid(struct pio_buf *pbuf, const void *from, size_t nbytes) */ /* adjust if we've wrapped */ if (dest >= pbuf->end) - dest -= pbuf->size; + dest -= pbuf->sc->size; /* jump to SOP range if within the first block */ else if (pbuf->qw_written < PIO_BLOCK_QWS) dest += SOP_DISTANCE; @@ -719,7 +719,7 @@ void seg_pio_copy_end(struct pio_buf *pbuf) */ /* adjust if we have wrapped */ if (dest >= pbuf->end) - dest -= pbuf->size; + dest -= pbuf->sc->size; /* jump to the SOP range if within the first block */ else if (pbuf->qw_written < PIO_BLOCK_QWS) dest += SOP_DISTANCE; diff --git a/drivers/infiniband/hw/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c index 202433178864..838fe84e285a 100644 --- a/drivers/infiniband/hw/hfi1/platform.c +++ b/drivers/infiniband/hw/hfi1/platform.c @@ -49,6 +49,90 @@ #include "efivar.h" #include "eprom.h" +static int validate_scratch_checksum(struct hfi1_devdata *dd) +{ + u64 checksum = 0, temp_scratch = 0; + int i, j, version; + + temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH); + version = (temp_scratch & BITMAP_VERSION_SMASK) >> BITMAP_VERSION_SHIFT; + + /* Prevent power on default of all zeroes from passing checksum */ + if (!version) + return 0; + + /* + * ASIC scratch 0 only contains the checksum and bitmap version as + * fields of interest, both of which are handled separately from the + * loop below, so skip it + */ + checksum += version; + for (i = 1; i < ASIC_NUM_SCRATCH; i++) { + temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH + (8 * i)); + for (j = sizeof(u64); j != 0; j -= 2) { + checksum += (temp_scratch & 0xFFFF); + temp_scratch >>= 16; + } + } + + while (checksum >> 16) + checksum = (checksum & CHECKSUM_MASK) + (checksum >> 16); + + temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH); + temp_scratch &= CHECKSUM_SMASK; + temp_scratch >>= CHECKSUM_SHIFT; + + if (checksum + temp_scratch == 0xFFFF) + return 1; + return 0; +} + +static void save_platform_config_fields(struct hfi1_devdata *dd) +{ + struct hfi1_pportdata *ppd = dd->pport; + u64 temp_scratch = 0, temp_dest = 0; + + temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH_1); + + temp_dest = temp_scratch & + (dd->hfi1_id ? PORT1_PORT_TYPE_SMASK : + PORT0_PORT_TYPE_SMASK); + ppd->port_type = temp_dest >> + (dd->hfi1_id ? PORT1_PORT_TYPE_SHIFT : + PORT0_PORT_TYPE_SHIFT); + + temp_dest = temp_scratch & + (dd->hfi1_id ? PORT1_LOCAL_ATTEN_SMASK : + PORT0_LOCAL_ATTEN_SMASK); + ppd->local_atten = temp_dest >> + (dd->hfi1_id ? PORT1_LOCAL_ATTEN_SHIFT : + PORT0_LOCAL_ATTEN_SHIFT); + + temp_dest = temp_scratch & + (dd->hfi1_id ? PORT1_REMOTE_ATTEN_SMASK : + PORT0_REMOTE_ATTEN_SMASK); + ppd->remote_atten = temp_dest >> + (dd->hfi1_id ? PORT1_REMOTE_ATTEN_SHIFT : + PORT0_REMOTE_ATTEN_SHIFT); + + temp_dest = temp_scratch & + (dd->hfi1_id ? PORT1_DEFAULT_ATTEN_SMASK : + PORT0_DEFAULT_ATTEN_SMASK); + ppd->default_atten = temp_dest >> + (dd->hfi1_id ? PORT1_DEFAULT_ATTEN_SHIFT : + PORT0_DEFAULT_ATTEN_SHIFT); + + temp_scratch = read_csr(dd, dd->hfi1_id ? ASIC_CFG_SCRATCH_3 : + ASIC_CFG_SCRATCH_2); + + ppd->tx_preset_eq = (temp_scratch & TX_EQ_SMASK) >> TX_EQ_SHIFT; + ppd->tx_preset_noeq = (temp_scratch & TX_NO_EQ_SMASK) >> TX_NO_EQ_SHIFT; + ppd->rx_preset = (temp_scratch & RX_SMASK) >> RX_SHIFT; + + ppd->max_power_class = (temp_scratch & QSFP_MAX_POWER_SMASK) >> + QSFP_MAX_POWER_SHIFT; +} + void get_platform_config(struct hfi1_devdata *dd) { int ret = 0; @@ -56,38 +140,49 @@ void get_platform_config(struct hfi1_devdata *dd) u8 *temp_platform_config = NULL; u32 esize; - ret = eprom_read_platform_config(dd, (void **)&temp_platform_config, - &esize); - if (!ret) { - /* success */ - size = esize; - goto success; + if (is_integrated(dd)) { + if (validate_scratch_checksum(dd)) { + save_platform_config_fields(dd); + return; + } + dd_dev_err(dd, "%s: Config bitmap corrupted/uninitialized\n", + __func__); + dd_dev_err(dd, + "%s: Please update your BIOS to support active channels\n", + __func__); + } else { + ret = eprom_read_platform_config(dd, + (void **)&temp_platform_config, + &esize); + if (!ret) { + /* success */ + dd->platform_config.data = temp_platform_config; + dd->platform_config.size = esize; + return; + } + /* fail, try EFI variable */ + + ret = read_hfi1_efi_var(dd, "configuration", &size, + (void **)&temp_platform_config); + if (!ret) { + dd->platform_config.data = temp_platform_config; + dd->platform_config.size = size; + return; + } } - /* fail, try EFI variable */ - - ret = read_hfi1_efi_var(dd, "configuration", &size, - (void **)&temp_platform_config); - if (!ret) - goto success; - - dd_dev_info(dd, - "%s: Failed to get platform config from UEFI, falling back to request firmware\n", - __func__); + dd_dev_err(dd, + "%s: Failed to get platform config, falling back to sub-optimal default file\n", + __func__); /* fall back to request firmware */ platform_config_load = 1; - return; - -success: - dd->platform_config.data = temp_platform_config; - dd->platform_config.size = size; } void free_platform_config(struct hfi1_devdata *dd) { if (!platform_config_load) { /* - * was loaded from EFI, release memory - * allocated by read_efi_var + * was loaded from EFI or the EPROM, release memory + * allocated by read_efi_var/eprom_read_platform_config */ kfree(dd->platform_config.data); } @@ -100,12 +195,16 @@ void free_platform_config(struct hfi1_devdata *dd) void get_port_type(struct hfi1_pportdata *ppd) { int ret; + u32 temp; ret = get_platform_config_field(ppd->dd, PLATFORM_CONFIG_PORT_TABLE, 0, - PORT_TABLE_PORT_TYPE, &ppd->port_type, + PORT_TABLE_PORT_TYPE, &temp, 4); - if (ret) + if (ret) { ppd->port_type = PORT_TYPE_UNKNOWN; + return; + } + ppd->port_type = temp; } int set_qsfp_tx(struct hfi1_pportdata *ppd, int on) @@ -538,6 +637,38 @@ static void apply_tx_lanes(struct hfi1_pportdata *ppd, u8 field_id, } } +/* + * Return a special SerDes setting for low power AOC cables. The power class + * threshold and setting being used were all found by empirical testing. + * + * Summary of the logic: + * + * if (QSFP and QSFP_TYPE == AOC and QSFP_POWER_CLASS < 4) + * return 0xe + * return 0; // leave at default + */ +static u8 aoc_low_power_setting(struct hfi1_pportdata *ppd) +{ + u8 *cache = ppd->qsfp_info.cache; + int power_class; + + /* QSFP only */ + if (ppd->port_type != PORT_TYPE_QSFP) + return 0; /* leave at default */ + + /* active optical cables only */ + switch ((cache[QSFP_MOD_TECH_OFFS] & 0xF0) >> 4) { + case 0x0 ... 0x9: /* fallthrough */ + case 0xC: /* fallthrough */ + case 0xE: + /* active AOC */ + power_class = get_qsfp_power_class(cache[QSFP_MOD_PWR_OFFS]); + if (power_class < QSFP_POWER_CLASS_4) + return 0xe; + } + return 0; /* leave at default */ +} + static void apply_tunings( struct hfi1_pportdata *ppd, u32 tx_preset_index, u8 tuning_method, u32 total_atten, u8 limiting_active) @@ -606,7 +737,17 @@ static void apply_tunings( tx_preset_index, TX_PRESET_TABLE_POSTCUR, &tx_preset, 4); postcur = tx_preset; - config_data = precur | (attn << 8) | (postcur << 16); + /* + * NOTES: + * o The aoc_low_power_setting is applied to all lanes even + * though only lane 0's value is examined by the firmware. + * o A lingering low power setting after a cable swap does + * not occur. On cable unplug the 8051 is reset and + * restarted on cable insert. This resets all settings to + * their default, erasing any previous low power setting. + */ + config_data = precur | (attn << 8) | (postcur << 16) | + (aoc_low_power_setting(ppd) << 24); apply_tx_lanes(ppd, TX_EQ_SETTINGS, config_data, "Applying TX settings"); diff --git a/drivers/infiniband/hw/hfi1/platform.h b/drivers/infiniband/hw/hfi1/platform.h index e2c21613c326..eed0aa9124fa 100644 --- a/drivers/infiniband/hw/hfi1/platform.h +++ b/drivers/infiniband/hw/hfi1/platform.h @@ -168,16 +168,6 @@ struct platform_config_cache { struct platform_config_data config_tables[PLATFORM_CONFIG_TABLE_MAX]; }; -static const u32 platform_config_table_limits[PLATFORM_CONFIG_TABLE_MAX] = { - 0, - SYSTEM_TABLE_MAX, - PORT_TABLE_MAX, - RX_PRESET_TABLE_MAX, - TX_PRESET_TABLE_MAX, - QSFP_ATTEN_TABLE_MAX, - VARIABLE_SETTINGS_TABLE_MAX -}; - /* This section defines default values and encodings for the * fields defined for each table above */ @@ -295,6 +285,123 @@ enum link_tuning_encoding { OPA_UNKNOWN_TUNING }; +/* + * Shifts and masks for the link SI tuning values stuffed into the ASIC scratch + * registers for integrated platforms + */ +#define PORT0_PORT_TYPE_SHIFT 0 +#define PORT0_LOCAL_ATTEN_SHIFT 4 +#define PORT0_REMOTE_ATTEN_SHIFT 10 +#define PORT0_DEFAULT_ATTEN_SHIFT 32 + +#define PORT1_PORT_TYPE_SHIFT 16 +#define PORT1_LOCAL_ATTEN_SHIFT 20 +#define PORT1_REMOTE_ATTEN_SHIFT 26 +#define PORT1_DEFAULT_ATTEN_SHIFT 40 + +#define PORT0_PORT_TYPE_MASK 0xFUL +#define PORT0_LOCAL_ATTEN_MASK 0x3FUL +#define PORT0_REMOTE_ATTEN_MASK 0x3FUL +#define PORT0_DEFAULT_ATTEN_MASK 0xFFUL + +#define PORT1_PORT_TYPE_MASK 0xFUL +#define PORT1_LOCAL_ATTEN_MASK 0x3FUL +#define PORT1_REMOTE_ATTEN_MASK 0x3FUL +#define PORT1_DEFAULT_ATTEN_MASK 0xFFUL + +#define PORT0_PORT_TYPE_SMASK (PORT0_PORT_TYPE_MASK << \ + PORT0_PORT_TYPE_SHIFT) +#define PORT0_LOCAL_ATTEN_SMASK (PORT0_LOCAL_ATTEN_MASK << \ + PORT0_LOCAL_ATTEN_SHIFT) +#define PORT0_REMOTE_ATTEN_SMASK (PORT0_REMOTE_ATTEN_MASK << \ + PORT0_REMOTE_ATTEN_SHIFT) +#define PORT0_DEFAULT_ATTEN_SMASK (PORT0_DEFAULT_ATTEN_MASK << \ + PORT0_DEFAULT_ATTEN_SHIFT) + +#define PORT1_PORT_TYPE_SMASK (PORT1_PORT_TYPE_MASK << \ + PORT1_PORT_TYPE_SHIFT) +#define PORT1_LOCAL_ATTEN_SMASK (PORT1_LOCAL_ATTEN_MASK << \ + PORT1_LOCAL_ATTEN_SHIFT) +#define PORT1_REMOTE_ATTEN_SMASK (PORT1_REMOTE_ATTEN_MASK << \ + PORT1_REMOTE_ATTEN_SHIFT) +#define PORT1_DEFAULT_ATTEN_SMASK (PORT1_DEFAULT_ATTEN_MASK << \ + PORT1_DEFAULT_ATTEN_SHIFT) + +#define QSFP_MAX_POWER_SHIFT 0 +#define TX_NO_EQ_SHIFT 4 +#define TX_EQ_SHIFT 25 +#define RX_SHIFT 46 + +#define QSFP_MAX_POWER_MASK 0xFUL +#define TX_NO_EQ_MASK 0x1FFFFFUL +#define TX_EQ_MASK 0x1FFFFFUL +#define RX_MASK 0xFFFFUL + +#define QSFP_MAX_POWER_SMASK (QSFP_MAX_POWER_MASK << \ + QSFP_MAX_POWER_SHIFT) +#define TX_NO_EQ_SMASK (TX_NO_EQ_MASK << TX_NO_EQ_SHIFT) +#define TX_EQ_SMASK (TX_EQ_MASK << TX_EQ_SHIFT) +#define RX_SMASK (RX_MASK << RX_SHIFT) + +#define TX_PRECUR_SHIFT 0 +#define TX_ATTN_SHIFT 4 +#define QSFP_TX_CDR_APPLY_SHIFT 9 +#define QSFP_TX_EQ_APPLY_SHIFT 10 +#define QSFP_TX_CDR_SHIFT 11 +#define QSFP_TX_EQ_SHIFT 12 +#define TX_POSTCUR_SHIFT 16 + +#define TX_PRECUR_MASK 0xFUL +#define TX_ATTN_MASK 0x1FUL +#define QSFP_TX_CDR_APPLY_MASK 0x1UL +#define QSFP_TX_EQ_APPLY_MASK 0x1UL +#define QSFP_TX_CDR_MASK 0x1UL +#define QSFP_TX_EQ_MASK 0xFUL +#define TX_POSTCUR_MASK 0x1FUL + +#define TX_PRECUR_SMASK (TX_PRECUR_MASK << TX_PRECUR_SHIFT) +#define TX_ATTN_SMASK (TX_ATTN_MASK << TX_ATTN_SHIFT) +#define QSFP_TX_CDR_APPLY_SMASK (QSFP_TX_CDR_APPLY_MASK << \ + QSFP_TX_CDR_APPLY_SHIFT) +#define QSFP_TX_EQ_APPLY_SMASK (QSFP_TX_EQ_APPLY_MASK << \ + QSFP_TX_EQ_APPLY_SHIFT) +#define QSFP_TX_CDR_SMASK (QSFP_TX_CDR_MASK << QSFP_TX_CDR_SHIFT) +#define QSFP_TX_EQ_SMASK (QSFP_TX_EQ_MASK << QSFP_TX_EQ_SHIFT) +#define TX_POSTCUR_SMASK (TX_POSTCUR_MASK << TX_POSTCUR_SHIFT) + +#define QSFP_RX_CDR_APPLY_SHIFT 0 +#define QSFP_RX_EMP_APPLY_SHIFT 1 +#define QSFP_RX_AMP_APPLY_SHIFT 2 +#define QSFP_RX_CDR_SHIFT 3 +#define QSFP_RX_EMP_SHIFT 4 +#define QSFP_RX_AMP_SHIFT 8 + +#define QSFP_RX_CDR_APPLY_MASK 0x1UL +#define QSFP_RX_EMP_APPLY_MASK 0x1UL +#define QSFP_RX_AMP_APPLY_MASK 0x1UL +#define QSFP_RX_CDR_MASK 0x1UL +#define QSFP_RX_EMP_MASK 0xFUL +#define QSFP_RX_AMP_MASK 0x3UL + +#define QSFP_RX_CDR_APPLY_SMASK (QSFP_RX_CDR_APPLY_MASK << \ + QSFP_RX_CDR_APPLY_SHIFT) +#define QSFP_RX_EMP_APPLY_SMASK (QSFP_RX_EMP_APPLY_MASK << \ + QSFP_RX_EMP_APPLY_SHIFT) +#define QSFP_RX_AMP_APPLY_SMASK (QSFP_RX_AMP_APPLY_MASK << \ + QSFP_RX_AMP_APPLY_SHIFT) +#define QSFP_RX_CDR_SMASK (QSFP_RX_CDR_MASK << QSFP_RX_CDR_SHIFT) +#define QSFP_RX_EMP_SMASK (QSFP_RX_EMP_MASK << QSFP_RX_EMP_SHIFT) +#define QSFP_RX_AMP_SMASK (QSFP_RX_AMP_MASK << QSFP_RX_AMP_SHIFT) + +#define BITMAP_VERSION 1 +#define BITMAP_VERSION_SHIFT 44 +#define BITMAP_VERSION_MASK 0xFUL +#define BITMAP_VERSION_SMASK (BITMAP_VERSION_MASK << \ + BITMAP_VERSION_SHIFT) +#define CHECKSUM_SHIFT 48 +#define CHECKSUM_MASK 0xFFFFUL +#define CHECKSUM_SMASK (CHECKSUM_MASK << CHECKSUM_SHIFT) + /* platform.c */ void get_platform_config(struct hfi1_devdata *dd); void free_platform_config(struct hfi1_devdata *dd); diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c index 9fc75e7e8781..d752d6768a49 100644 --- a/drivers/infiniband/hw/hfi1/qp.c +++ b/drivers/infiniband/hw/hfi1/qp.c @@ -196,15 +196,18 @@ static void flush_tx_list(struct rvt_qp *qp) static void flush_iowait(struct rvt_qp *qp) { struct hfi1_qp_priv *priv = qp->priv; - struct hfi1_ibdev *dev = to_idev(qp->ibqp.device); unsigned long flags; + seqlock_t *lock = priv->s_iowait.lock; - write_seqlock_irqsave(&dev->iowait_lock, flags); + if (!lock) + return; + write_seqlock_irqsave(lock, flags); if (!list_empty(&priv->s_iowait.list)) { list_del_init(&priv->s_iowait.list); + priv->s_iowait.lock = NULL; rvt_put_qp(qp); } - write_sequnlock_irqrestore(&dev->iowait_lock, flags); + write_sequnlock_irqrestore(lock, flags); } static inline int opa_mtu_enum_to_int(int mtu) @@ -543,6 +546,7 @@ static int iowait_sleep( ibp->rvp.n_dmawait++; qp->s_flags |= RVT_S_WAIT_DMA_DESC; list_add_tail(&priv->s_iowait.list, &sde->dmawait); + priv->s_iowait.lock = &dev->iowait_lock; trace_hfi1_qpsleep(qp, RVT_S_WAIT_DMA_DESC); rvt_get_qp(qp); } @@ -964,6 +968,7 @@ void notify_error_qp(struct rvt_qp *qp) if (!list_empty(&priv->s_iowait.list) && !(qp->s_flags & RVT_S_BUSY)) { qp->s_flags &= ~RVT_S_ANY_WAIT_IO; list_del_init(&priv->s_iowait.list); + priv->s_iowait.lock = NULL; rvt_put_qp(qp); } write_sequnlock(&dev->iowait_lock); diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c index 83198a8a8797..809b26eb6d3c 100644 --- a/drivers/infiniband/hw/hfi1/rc.c +++ b/drivers/infiniband/hw/hfi1/rc.c @@ -276,7 +276,7 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp, rvt_get_mr(ps->s_txreq->mr); qp->s_ack_rdma_sge.sge = e->rdma_sge; qp->s_ack_rdma_sge.num_sge = 1; - qp->s_cur_sge = &qp->s_ack_rdma_sge; + ps->s_txreq->ss = &qp->s_ack_rdma_sge; if (len > pmtu) { len = pmtu; qp->s_ack_state = OP(RDMA_READ_RESPONSE_FIRST); @@ -290,7 +290,7 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp, bth2 = mask_psn(qp->s_ack_rdma_psn++); } else { /* COMPARE_SWAP or FETCH_ADD */ - qp->s_cur_sge = NULL; + ps->s_txreq->ss = NULL; len = 0; qp->s_ack_state = OP(ATOMIC_ACKNOWLEDGE); ohdr->u.at.aeth = hfi1_compute_aeth(qp); @@ -306,7 +306,7 @@ static int make_rc_ack(struct hfi1_ibdev *dev, struct rvt_qp *qp, qp->s_ack_state = OP(RDMA_READ_RESPONSE_MIDDLE); /* FALLTHROUGH */ case OP(RDMA_READ_RESPONSE_MIDDLE): - qp->s_cur_sge = &qp->s_ack_rdma_sge; + ps->s_txreq->ss = &qp->s_ack_rdma_sge; ps->s_txreq->mr = qp->s_ack_rdma_sge.sge.mr; if (ps->s_txreq->mr) rvt_get_mr(ps->s_txreq->mr); @@ -335,7 +335,7 @@ normal: */ qp->s_ack_state = OP(SEND_ONLY); qp->s_flags &= ~RVT_S_ACK_PENDING; - qp->s_cur_sge = NULL; + ps->s_txreq->ss = NULL; if (qp->s_nak_state) ohdr->u.aeth = cpu_to_be32((qp->r_msn & HFI1_MSN_MASK) | @@ -351,7 +351,7 @@ normal: qp->s_rdma_ack_cnt++; qp->s_hdrwords = hwords; ps->s_txreq->sde = priv->s_sde; - qp->s_cur_size = len; + ps->s_txreq->s_cur_size = len; hfi1_make_ruc_header(qp, ohdr, bth0, bth2, middle, ps); /* pbc */ ps->s_txreq->hdr_dwords = qp->s_hdrwords + 2; @@ -801,8 +801,8 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) qp->s_len -= len; qp->s_hdrwords = hwords; ps->s_txreq->sde = priv->s_sde; - qp->s_cur_sge = ss; - qp->s_cur_size = len; + ps->s_txreq->ss = ss; + ps->s_txreq->s_cur_size = len; hfi1_make_ruc_header( qp, ohdr, @@ -1146,8 +1146,6 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr) { struct ib_other_headers *ohdr; struct rvt_swqe *wqe; - struct ib_wc wc; - unsigned i; u32 opcode; u32 psn; @@ -1195,22 +1193,8 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr) qp->s_last = s_last; /* see post_send() */ barrier(); - for (i = 0; i < wqe->wr.num_sge; i++) { - struct rvt_sge *sge = &wqe->sg_list[i]; - - rvt_put_mr(sge->mr); - } - /* Post a send completion queue entry if requested. */ - if (!(qp->s_flags & RVT_S_SIGNAL_REQ_WR) || - (wqe->wr.send_flags & IB_SEND_SIGNALED)) { - memset(&wc, 0, sizeof(wc)); - wc.wr_id = wqe->wr.wr_id; - wc.status = IB_WC_SUCCESS; - wc.opcode = ib_hfi1_wc_opcode[wqe->wr.opcode]; - wc.byte_len = wqe->length; - wc.qp = &qp->ibqp; - rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.send_cq), &wc, 0); - } + rvt_put_swqe(wqe); + rvt_qp_swqe_complete(qp, wqe, IB_WC_SUCCESS); } /* * If we were waiting for sends to complete before re-sending, @@ -1240,9 +1224,6 @@ static struct rvt_swqe *do_rc_completion(struct rvt_qp *qp, struct rvt_swqe *wqe, struct hfi1_ibport *ibp) { - struct ib_wc wc; - unsigned i; - lockdep_assert_held(&qp->s_lock); /* * Don't decrement refcount and don't generate a @@ -1253,28 +1234,14 @@ static struct rvt_swqe *do_rc_completion(struct rvt_qp *qp, cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) > 0) { u32 s_last; - for (i = 0; i < wqe->wr.num_sge; i++) { - struct rvt_sge *sge = &wqe->sg_list[i]; - - rvt_put_mr(sge->mr); - } + rvt_put_swqe(wqe); s_last = qp->s_last; if (++s_last >= qp->s_size) s_last = 0; qp->s_last = s_last; /* see post_send() */ barrier(); - /* Post a send completion queue entry if requested. */ - if (!(qp->s_flags & RVT_S_SIGNAL_REQ_WR) || - (wqe->wr.send_flags & IB_SEND_SIGNALED)) { - memset(&wc, 0, sizeof(wc)); - wc.wr_id = wqe->wr.wr_id; - wc.status = IB_WC_SUCCESS; - wc.opcode = ib_hfi1_wc_opcode[wqe->wr.opcode]; - wc.byte_len = wqe->length; - wc.qp = &qp->ibqp; - rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.send_cq), &wc, 0); - } + rvt_qp_swqe_complete(qp, wqe, IB_WC_SUCCESS); } else { struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); @@ -2295,7 +2262,7 @@ send_last: hfi1_copy_sge(&qp->r_sge, data, tlen, 1, copy_last); rvt_put_ss(&qp->r_sge); qp->r_msn++; - if (!test_and_clear_bit(RVT_R_WRID_VALID, &qp->r_aflags)) + if (!__test_and_clear_bit(RVT_R_WRID_VALID, &qp->r_aflags)) break; wc.wr_id = qp->r_wr_id; wc.status = IB_WC_SUCCESS; @@ -2410,8 +2377,7 @@ send_last: * Update the next expected PSN. We add 1 later * below, so only add the remainder here. */ - if (len > pmtu) - qp->r_psn += (len - 1) / pmtu; + qp->r_psn += rvt_div_mtu(qp, len - 1); } else { e->rdma_sge.mr = NULL; e->rdma_sge.vaddr = NULL; diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c index a1576aea4756..717ed4b159d3 100644 --- a/drivers/infiniband/hw/hfi1/ruc.c +++ b/drivers/infiniband/hw/hfi1/ruc.c @@ -239,16 +239,6 @@ bail: return ret; } -static __be64 get_sguid(struct hfi1_ibport *ibp, unsigned index) -{ - if (!index) { - struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); - - return cpu_to_be64(ppd->guid); - } - return ibp->guids[index - 1]; -} - static int gid_ok(union ib_gid *gid, __be64 gid_prefix, __be64 id) { return (gid->global.interface_id == id && @@ -699,9 +689,9 @@ u32 hfi1_make_grh(struct hfi1_ibport *ibp, struct ib_grh *hdr, /* The SGID is 32-bit aligned. */ hdr->sgid.global.subnet_prefix = ibp->rvp.gid_prefix; hdr->sgid.global.interface_id = - grh->sgid_index && grh->sgid_index < ARRAY_SIZE(ibp->guids) ? - ibp->guids[grh->sgid_index - 1] : - cpu_to_be64(ppd_from_ibp(ibp)->guid); + grh->sgid_index < HFI1_GUIDS_PER_PORT ? + get_sguid(ibp, grh->sgid_index) : + get_sguid(ibp, HFI1_PORT_GUID_INDEX); hdr->dgid = grh->dgid; /* GRH header size in 32-bit words. */ @@ -777,8 +767,8 @@ void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr, u32 bth1; /* Construct the header. */ - extra_bytes = -qp->s_cur_size & 3; - nwords = (qp->s_cur_size + extra_bytes) >> 2; + extra_bytes = -ps->s_txreq->s_cur_size & 3; + nwords = (ps->s_txreq->s_cur_size + extra_bytes) >> 2; lrh0 = HFI1_LRH_BTH; if (unlikely(qp->remote_ah_attr.ah_flags & IB_AH_GRH)) { qp->s_hdrwords += hfi1_make_grh(ibp, @@ -952,7 +942,6 @@ void hfi1_send_complete(struct rvt_qp *qp, struct rvt_swqe *wqe, enum ib_wc_status status) { u32 old_last, last; - unsigned i; if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_OR_FLUSH_SEND)) return; @@ -964,32 +953,13 @@ void hfi1_send_complete(struct rvt_qp *qp, struct rvt_swqe *wqe, qp->s_last = last; /* See post_send() */ barrier(); - for (i = 0; i < wqe->wr.num_sge; i++) { - struct rvt_sge *sge = &wqe->sg_list[i]; - - rvt_put_mr(sge->mr); - } + rvt_put_swqe(wqe); if (qp->ibqp.qp_type == IB_QPT_UD || qp->ibqp.qp_type == IB_QPT_SMI || qp->ibqp.qp_type == IB_QPT_GSI) atomic_dec(&ibah_to_rvtah(wqe->ud_wr.ah)->refcount); - /* See ch. 11.2.4.1 and 10.7.3.1 */ - if (!(qp->s_flags & RVT_S_SIGNAL_REQ_WR) || - (wqe->wr.send_flags & IB_SEND_SIGNALED) || - status != IB_WC_SUCCESS) { - struct ib_wc wc; - - memset(&wc, 0, sizeof(wc)); - wc.wr_id = wqe->wr.wr_id; - wc.status = status; - wc.opcode = ib_hfi1_wc_opcode[wqe->wr.opcode]; - wc.qp = &qp->ibqp; - if (status == IB_WC_SUCCESS) - wc.byte_len = wqe->length; - rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.send_cq), &wc, - status != IB_WC_SUCCESS); - } + rvt_qp_swqe_complete(qp, wqe, status); if (qp->s_acked == old_last) qp->s_acked = last; diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 9cbe52d21077..1d81cac1fa6c 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -375,7 +375,7 @@ static inline void complete_tx(struct sdma_engine *sde, sde->head_sn, tx->sn); sde->head_sn++; #endif - sdma_txclean(sde->dd, tx); + __sdma_txclean(sde->dd, tx); if (complete) (*complete)(tx, res); if (wait && iowait_sdma_dec(wait)) @@ -1643,7 +1643,7 @@ static inline u8 ahg_mode(struct sdma_txreq *tx) } /** - * sdma_txclean() - clean tx of mappings, descp *kmalloc's + * __sdma_txclean() - clean tx of mappings, descp *kmalloc's * @dd: hfi1_devdata for unmapping * @tx: tx request to clean * @@ -1653,7 +1653,7 @@ static inline u8 ahg_mode(struct sdma_txreq *tx) * The code can be called multiple times without issue. * */ -void sdma_txclean( +void __sdma_txclean( struct hfi1_devdata *dd, struct sdma_txreq *tx) { @@ -3065,7 +3065,7 @@ static int _extend_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx) tx->descp[i] = tx->descs[i]; return 0; enomem: - sdma_txclean(dd, tx); + __sdma_txclean(dd, tx); return -ENOMEM; } @@ -3094,14 +3094,14 @@ int ext_coal_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx, rval = _extend_sdma_tx_descs(dd, tx); if (rval) { - sdma_txclean(dd, tx); + __sdma_txclean(dd, tx); return rval; } /* If coalesce buffer is allocated, copy data into it */ if (tx->coalesce_buf) { if (type == SDMA_MAP_NONE) { - sdma_txclean(dd, tx); + __sdma_txclean(dd, tx); return -EINVAL; } @@ -3109,7 +3109,7 @@ int ext_coal_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx, kvaddr = kmap(page); kvaddr += offset; } else if (WARN_ON(!kvaddr)) { - sdma_txclean(dd, tx); + __sdma_txclean(dd, tx); return -EINVAL; } @@ -3139,7 +3139,7 @@ int ext_coal_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(&dd->pcidev->dev, addr))) { - sdma_txclean(dd, tx); + __sdma_txclean(dd, tx); return -ENOSPC; } @@ -3181,7 +3181,7 @@ int _pad_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx) if ((unlikely(tx->num_desc == tx->desc_limit))) { rval = _extend_sdma_tx_descs(dd, tx); if (rval) { - sdma_txclean(dd, tx); + __sdma_txclean(dd, tx); return rval; } } diff --git a/drivers/infiniband/hw/hfi1/sdma.h b/drivers/infiniband/hw/hfi1/sdma.h index 56257ea3598f..21f1e2834f37 100644 --- a/drivers/infiniband/hw/hfi1/sdma.h +++ b/drivers/infiniband/hw/hfi1/sdma.h @@ -667,7 +667,13 @@ int ext_coal_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx, int type, void *kvaddr, struct page *page, unsigned long offset, u16 len); int _pad_sdma_tx_descs(struct hfi1_devdata *, struct sdma_txreq *); -void sdma_txclean(struct hfi1_devdata *, struct sdma_txreq *); +void __sdma_txclean(struct hfi1_devdata *, struct sdma_txreq *); + +static inline void sdma_txclean(struct hfi1_devdata *dd, struct sdma_txreq *tx) +{ + if (tx->num_desc) + __sdma_txclean(dd, tx); +} /* helpers used by public routines */ static inline void _sdma_close_tx(struct hfi1_devdata *dd, @@ -753,7 +759,7 @@ static inline int sdma_txadd_page( DMA_TO_DEVICE); if (unlikely(dma_mapping_error(&dd->pcidev->dev, addr))) { - sdma_txclean(dd, tx); + __sdma_txclean(dd, tx); return -ENOSPC; } @@ -834,7 +840,7 @@ static inline int sdma_txadd_kvaddr( DMA_TO_DEVICE); if (unlikely(dma_mapping_error(&dd->pcidev->dev, addr))) { - sdma_txclean(dd, tx); + __sdma_txclean(dd, tx); return -ENOSPC; } diff --git a/drivers/infiniband/hw/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c index 5e6d1bac4914..b141a78ae38b 100644 --- a/drivers/infiniband/hw/hfi1/uc.c +++ b/drivers/infiniband/hw/hfi1/uc.c @@ -258,8 +258,8 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) qp->s_len -= len; qp->s_hdrwords = hwords; ps->s_txreq->sde = priv->s_sde; - qp->s_cur_sge = &qp->s_sge; - qp->s_cur_size = len; + ps->s_txreq->ss = &qp->s_sge; + ps->s_txreq->s_cur_size = len; hfi1_make_ruc_header(qp, ohdr, bth0 | (qp->s_state << 24), mask_psn(qp->s_psn++), middle, ps); /* pbc */ diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c index 97ae24b6314c..c071955c0272 100644 --- a/drivers/infiniband/hw/hfi1/ud.c +++ b/drivers/infiniband/hw/hfi1/ud.c @@ -354,8 +354,8 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) /* header size in 32-bit words LRH+BTH+DETH = (8+12+8)/4. */ qp->s_hdrwords = 7; - qp->s_cur_size = wqe->length; - qp->s_cur_sge = &qp->s_sge; + ps->s_txreq->s_cur_size = wqe->length; + ps->s_txreq->ss = &qp->s_sge; qp->s_srate = ah_attr->static_rate; qp->srate_mbps = ib_rate_to_mbps(qp->s_srate); qp->s_wqe = wqe; diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index 77697d690f3e..7d22f8ee98ef 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -115,6 +115,7 @@ MODULE_PARM_DESC(sdma_comp_size, "Size of User SDMA completion ring. Default: 12 #define KDETH_HCRC_LOWER_MASK 0xff #define AHG_KDETH_INTR_SHIFT 12 +#define AHG_KDETH_SH_SHIFT 13 #define PBC2LRH(x) ((((x) & 0xfff) << 2) - 4) #define LRH2PBC(x) ((((x) >> 2) + 1) & 0xfff) @@ -144,8 +145,9 @@ MODULE_PARM_DESC(sdma_comp_size, "Size of User SDMA completion ring. Default: 12 #define KDETH_OM_LARGE 64 #define KDETH_OM_MAX_SIZE (1 << ((KDETH_OM_LARGE / KDETH_OM_SMALL) + 1)) -/* Last packet in the request */ -#define TXREQ_FLAGS_REQ_LAST_PKT BIT(0) +/* Tx request flag bits */ +#define TXREQ_FLAGS_REQ_ACK BIT(0) /* Set the ACK bit in the header */ +#define TXREQ_FLAGS_REQ_DISABLE_SH BIT(1) /* Disable header suppression */ /* SDMA request flag bits */ #define SDMA_REQ_FOR_THREAD 1 @@ -943,8 +945,13 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts) tx->busycount = 0; INIT_LIST_HEAD(&tx->list); + /* + * For the last packet set the ACK request + * and disable header suppression. + */ if (req->seqnum == req->info.npkts - 1) - tx->flags |= TXREQ_FLAGS_REQ_LAST_PKT; + tx->flags |= (TXREQ_FLAGS_REQ_ACK | + TXREQ_FLAGS_REQ_DISABLE_SH); /* * Calculate the payload size - this is min of the fragment @@ -963,11 +970,22 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts) } datalen = compute_data_length(req, tx); + + /* + * Disable header suppression for the payload <= 8DWS. + * If there is an uncorrectable error in the receive + * data FIFO when the received payload size is less than + * or equal to 8DWS then the RxDmaDataFifoRdUncErr is + * not reported.There is set RHF.EccErr if the header + * is not suppressed. + */ if (!datalen) { SDMA_DBG(req, "Request has data but pkt len is 0"); ret = -EFAULT; goto free_tx; + } else if (datalen <= 32) { + tx->flags |= TXREQ_FLAGS_REQ_DISABLE_SH; } } @@ -990,6 +1008,10 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts) LRH2PBC(lrhlen); tx->hdr.pbc[0] = cpu_to_le16(pbclen); } + ret = check_header_template(req, &tx->hdr, + lrhlen, datalen); + if (ret) + goto free_tx; ret = sdma_txinit_ahg(&tx->txreq, SDMA_TXREQ_F_AHG_COPY, sizeof(tx->hdr) + datalen, @@ -1351,7 +1373,7 @@ static int set_txreq_header(struct user_sdma_request *req, req->seqnum)); /* Set ACK request on last packet */ - if (unlikely(tx->flags & TXREQ_FLAGS_REQ_LAST_PKT)) + if (unlikely(tx->flags & TXREQ_FLAGS_REQ_ACK)) hdr->bth[2] |= cpu_to_be32(1UL << 31); /* Set the new offset */ @@ -1384,8 +1406,8 @@ static int set_txreq_header(struct user_sdma_request *req, /* Set KDETH.TID based on value for this TID */ KDETH_SET(hdr->kdeth.ver_tid_offset, TID, EXP_TID_GET(tidval, IDX)); - /* Clear KDETH.SH only on the last packet */ - if (unlikely(tx->flags & TXREQ_FLAGS_REQ_LAST_PKT)) + /* Clear KDETH.SH when DISABLE_SH flag is set */ + if (unlikely(tx->flags & TXREQ_FLAGS_REQ_DISABLE_SH)) KDETH_SET(hdr->kdeth.ver_tid_offset, SH, 0); /* * Set the KDETH.OFFSET and KDETH.OM based on size of @@ -1429,7 +1451,7 @@ static int set_txreq_header_ahg(struct user_sdma_request *req, /* BTH.PSN and BTH.A */ val32 = (be32_to_cpu(hdr->bth[2]) + req->seqnum) & (HFI1_CAP_IS_KSET(EXTENDED_PSN) ? 0x7fffffff : 0xffffff); - if (unlikely(tx->flags & TXREQ_FLAGS_REQ_LAST_PKT)) + if (unlikely(tx->flags & TXREQ_FLAGS_REQ_ACK)) val32 |= 1UL << 31; AHG_HEADER_SET(req->ahg, diff, 6, 0, 16, cpu_to_be16(val32 >> 16)); AHG_HEADER_SET(req->ahg, diff, 6, 16, 16, cpu_to_be16(val32 & 0xffff)); @@ -1468,19 +1490,23 @@ static int set_txreq_header_ahg(struct user_sdma_request *req, AHG_HEADER_SET(req->ahg, diff, 7, 0, 16, ((!!(req->omfactor - KDETH_OM_SMALL)) << 15 | ((req->tidoffset / req->omfactor) & 0x7fff))); - /* KDETH.TIDCtrl, KDETH.TID */ + /* KDETH.TIDCtrl, KDETH.TID, KDETH.Intr, KDETH.SH */ val = cpu_to_le16(((EXP_TID_GET(tidval, CTRL) & 0x3) << 10) | - (EXP_TID_GET(tidval, IDX) & 0x3ff)); - /* Clear KDETH.SH on last packet */ - if (unlikely(tx->flags & TXREQ_FLAGS_REQ_LAST_PKT)) { - val |= cpu_to_le16(KDETH_GET(hdr->kdeth.ver_tid_offset, - INTR) << - AHG_KDETH_INTR_SHIFT); - val &= cpu_to_le16(~(1U << 13)); - AHG_HEADER_SET(req->ahg, diff, 7, 16, 14, val); + (EXP_TID_GET(tidval, IDX) & 0x3ff)); + + if (unlikely(tx->flags & TXREQ_FLAGS_REQ_DISABLE_SH)) { + val |= cpu_to_le16((KDETH_GET(hdr->kdeth.ver_tid_offset, + INTR) << + AHG_KDETH_INTR_SHIFT)); } else { - AHG_HEADER_SET(req->ahg, diff, 7, 16, 12, val); + val |= KDETH_GET(hdr->kdeth.ver_tid_offset, SH) ? + cpu_to_le16(0x1 << AHG_KDETH_SH_SHIFT) : + cpu_to_le16((KDETH_GET(hdr->kdeth.ver_tid_offset, + INTR) << + AHG_KDETH_INTR_SHIFT)); } + + AHG_HEADER_SET(req->ahg, diff, 7, 16, 14, val); } trace_hfi1_sdma_user_header_ahg(pq->dd, pq->ctxt, pq->subctxt, diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index 4b7a16ceb362..95ed4d6da510 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -297,22 +297,6 @@ static inline int wss_exceeds_threshold(void) } /* - * Translate ib_wr_opcode into ib_wc_opcode. - */ -const enum ib_wc_opcode ib_hfi1_wc_opcode[] = { - [IB_WR_RDMA_WRITE] = IB_WC_RDMA_WRITE, - [IB_WR_RDMA_WRITE_WITH_IMM] = IB_WC_RDMA_WRITE, - [IB_WR_SEND] = IB_WC_SEND, - [IB_WR_SEND_WITH_IMM] = IB_WC_SEND, - [IB_WR_RDMA_READ] = IB_WC_RDMA_READ, - [IB_WR_ATOMIC_CMP_AND_SWP] = IB_WC_COMP_SWAP, - [IB_WR_ATOMIC_FETCH_AND_ADD] = IB_WC_FETCH_ADD, - [IB_WR_SEND_WITH_INV] = IB_WC_SEND, - [IB_WR_LOCAL_INV] = IB_WC_LOCAL_INV, - [IB_WR_REG_MR] = IB_WC_REG_MR -}; - -/* * Length of header by opcode, 0 --> not supported */ const u8 hdr_len_by_opcode[256] = { @@ -694,6 +678,7 @@ static void mem_timer(unsigned long data) qp = iowait_to_qp(wait); priv = qp->priv; list_del_init(&priv->s_iowait.list); + priv->s_iowait.lock = NULL; /* refcount held until actual wake up */ if (!list_empty(list)) mod_timer(&dev->mem_timer, jiffies + 1); @@ -769,6 +754,7 @@ static int wait_kmem(struct hfi1_ibdev *dev, mod_timer(&dev->mem_timer, jiffies + 1); qp->s_flags |= RVT_S_WAIT_KMEM; list_add_tail(&priv->s_iowait.list, &dev->memwait); + priv->s_iowait.lock = &dev->iowait_lock; trace_hfi1_qpsleep(qp, RVT_S_WAIT_KMEM); rvt_get_qp(qp); } @@ -788,10 +774,10 @@ static int wait_kmem(struct hfi1_ibdev *dev, */ static noinline int build_verbs_ulp_payload( struct sdma_engine *sde, - struct rvt_sge_state *ss, u32 length, struct verbs_txreq *tx) { + struct rvt_sge_state *ss = tx->ss; struct rvt_sge *sg_list = ss->sg_list; struct rvt_sge sge = ss->sge; u8 num_sge = ss->num_sge; @@ -835,7 +821,6 @@ bail_txadd: /* New API */ static int build_verbs_tx_desc( struct sdma_engine *sde, - struct rvt_sge_state *ss, u32 length, struct verbs_txreq *tx, struct hfi1_ahg_info *ahg_info, @@ -879,9 +864,9 @@ static int build_verbs_tx_desc( goto bail_txadd; } - /* add the ulp payload - if any. ss can be NULL for acks */ - if (ss) - ret = build_verbs_ulp_payload(sde, ss, length, tx); + /* add the ulp payload - if any. tx->ss can be NULL for acks */ + if (tx->ss) + ret = build_verbs_ulp_payload(sde, length, tx); bail_txadd: return ret; } @@ -892,8 +877,7 @@ int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps, struct hfi1_qp_priv *priv = qp->priv; struct hfi1_ahg_info *ahg_info = priv->s_ahg; u32 hdrwords = qp->s_hdrwords; - struct rvt_sge_state *ss = qp->s_cur_sge; - u32 len = qp->s_cur_size; + u32 len = ps->s_txreq->s_cur_size; u32 plen = hdrwords + ((len + 3) >> 2) + 2; /* includes pbc */ struct hfi1_ibdev *dev = ps->dev; struct hfi1_pportdata *ppd = ps->ppd; @@ -918,7 +902,7 @@ int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps, plen); } tx->wqe = qp->s_wqe; - ret = build_verbs_tx_desc(tx->sde, ss, len, tx, ahg_info, pbc); + ret = build_verbs_tx_desc(tx->sde, len, tx, ahg_info, pbc); if (unlikely(ret)) goto bail_build; } @@ -980,6 +964,7 @@ static int pio_wait(struct rvt_qp *qp, qp->s_flags |= flag; was_empty = list_empty(&sc->piowait); list_add_tail(&priv->s_iowait.list, &sc->piowait); + priv->s_iowait.lock = &dev->iowait_lock; trace_hfi1_qpsleep(qp, RVT_S_WAIT_PIO); rvt_get_qp(qp); /* counting: only call wantpiobuf_intr if first user */ @@ -1008,8 +993,8 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps, { struct hfi1_qp_priv *priv = qp->priv; u32 hdrwords = qp->s_hdrwords; - struct rvt_sge_state *ss = qp->s_cur_sge; - u32 len = qp->s_cur_size; + struct rvt_sge_state *ss = ps->s_txreq->ss; + u32 len = ps->s_txreq->s_cur_size; u32 dwords = (len + 3) >> 2; u32 plen = hdrwords + dwords + 2; /* includes pbc */ struct hfi1_pportdata *ppd = ps->ppd; @@ -1237,7 +1222,7 @@ static inline send_routine get_send_routine(struct rvt_qp *qp, u8 op = get_opcode(h); if (piothreshold && - qp->s_cur_size <= min(piothreshold, qp->pmtu) && + tx->s_cur_size <= min(piothreshold, qp->pmtu) && (BIT(op & OPMASK) & pio_opmask[op >> 5]) && iowait_sdma_pending(&priv->s_iowait) == 0 && !sdma_txreq_built(&tx->txreq)) @@ -1483,15 +1468,11 @@ static int hfi1_get_guid_be(struct rvt_dev_info *rdi, struct rvt_ibport *rvp, int guid_index, __be64 *guid) { struct hfi1_ibport *ibp = container_of(rvp, struct hfi1_ibport, rvp); - struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); - if (guid_index == 0) - *guid = cpu_to_be64(ppd->guid); - else if (guid_index < HFI1_GUIDS_PER_PORT) - *guid = ibp->guids[guid_index - 1]; - else + if (guid_index >= HFI1_GUIDS_PER_PORT) return -EINVAL; + *guid = get_sguid(ibp, guid_index); return 0; } @@ -1610,6 +1591,154 @@ static void hfi1_get_dev_fw_str(struct ib_device *ibdev, char *str, dc8051_ver_min(ver)); } +static const char * const driver_cntr_names[] = { + /* must be element 0*/ + "DRIVER_KernIntr", + "DRIVER_ErrorIntr", + "DRIVER_Tx_Errs", + "DRIVER_Rcv_Errs", + "DRIVER_HW_Errs", + "DRIVER_NoPIOBufs", + "DRIVER_CtxtsOpen", + "DRIVER_RcvLen_Errs", + "DRIVER_EgrBufFull", + "DRIVER_EgrHdrFull" +}; + +static const char **dev_cntr_names; +static const char **port_cntr_names; +static int num_driver_cntrs = ARRAY_SIZE(driver_cntr_names); +static int num_dev_cntrs; +static int num_port_cntrs; +static int cntr_names_initialized; + +/* + * Convert a list of names separated by '\n' into an array of NULL terminated + * strings. Optionally some entries can be reserved in the array to hold extra + * external strings. + */ +static int init_cntr_names(const char *names_in, + const int names_len, + int num_extra_names, + int *num_cntrs, + const char ***cntr_names) +{ + char *names_out, *p, **q; + int i, n; + + n = 0; + for (i = 0; i < names_len; i++) + if (names_in[i] == '\n') + n++; + + names_out = kmalloc((n + num_extra_names) * sizeof(char *) + names_len, + GFP_KERNEL); + if (!names_out) { + *num_cntrs = 0; + *cntr_names = NULL; + return -ENOMEM; + } + + p = names_out + (n + num_extra_names) * sizeof(char *); + memcpy(p, names_in, names_len); + + q = (char **)names_out; + for (i = 0; i < n; i++) { + q[i] = p; + p = strchr(p, '\n'); + *p++ = '\0'; + } + + *num_cntrs = n; + *cntr_names = (const char **)names_out; + return 0; +} + +static struct rdma_hw_stats *alloc_hw_stats(struct ib_device *ibdev, + u8 port_num) +{ + int i, err; + + if (!cntr_names_initialized) { + struct hfi1_devdata *dd = dd_from_ibdev(ibdev); + + err = init_cntr_names(dd->cntrnames, + dd->cntrnameslen, + num_driver_cntrs, + &num_dev_cntrs, + &dev_cntr_names); + if (err) + return NULL; + + for (i = 0; i < num_driver_cntrs; i++) + dev_cntr_names[num_dev_cntrs + i] = + driver_cntr_names[i]; + + err = init_cntr_names(dd->portcntrnames, + dd->portcntrnameslen, + 0, + &num_port_cntrs, + &port_cntr_names); + if (err) { + kfree(dev_cntr_names); + dev_cntr_names = NULL; + return NULL; + } + cntr_names_initialized = 1; + } + + if (!port_num) + return rdma_alloc_hw_stats_struct( + dev_cntr_names, + num_dev_cntrs + num_driver_cntrs, + RDMA_HW_STATS_DEFAULT_LIFESPAN); + else + return rdma_alloc_hw_stats_struct( + port_cntr_names, + num_port_cntrs, + RDMA_HW_STATS_DEFAULT_LIFESPAN); +} + +static u64 hfi1_sps_ints(void) +{ + unsigned long flags; + struct hfi1_devdata *dd; + u64 sps_ints = 0; + + spin_lock_irqsave(&hfi1_devs_lock, flags); + list_for_each_entry(dd, &hfi1_dev_list, list) { + sps_ints += get_all_cpu_total(dd->int_counter); + } + spin_unlock_irqrestore(&hfi1_devs_lock, flags); + return sps_ints; +} + +static int get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats, + u8 port, int index) +{ + u64 *values; + int count; + + if (!port) { + u64 *stats = (u64 *)&hfi1_stats; + int i; + + hfi1_read_cntrs(dd_from_ibdev(ibdev), NULL, &values); + values[num_dev_cntrs] = hfi1_sps_ints(); + for (i = 1; i < num_driver_cntrs; i++) + values[num_dev_cntrs + i] = stats[i]; + count = num_dev_cntrs + num_driver_cntrs; + } else { + struct hfi1_ibport *ibp = to_iport(ibdev, port); + + hfi1_read_portcntrs(ppd_from_ibp(ibp), NULL, &values); + count = num_port_cntrs; + } + + memcpy(stats->value, values, count * sizeof(u64)); + return count; +} + /** * hfi1_register_ib_device - register our device with the infiniband core * @dd: the device data structure @@ -1620,6 +1749,7 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd) struct hfi1_ibdev *dev = &dd->verbs_dev; struct ib_device *ibdev = &dev->rdi.ibdev; struct hfi1_pportdata *ppd = dd->pport; + struct hfi1_ibport *ibp = &ppd->ibport_data; unsigned i; int ret; size_t lcpysz = IB_DEVICE_NAME_MAX; @@ -1632,6 +1762,7 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd) setup_timer(&dev->mem_timer, mem_timer, (unsigned long)dev); seqlock_init(&dev->iowait_lock); + seqlock_init(&dev->txwait_lock); INIT_LIST_HEAD(&dev->txwait); INIT_LIST_HEAD(&dev->memwait); @@ -1639,20 +1770,24 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd) if (ret) goto err_verbs_txreq; + /* Use first-port GUID as node guid */ + ibdev->node_guid = get_sguid(ibp, HFI1_PORT_GUID_INDEX); + /* * The system image GUID is supposed to be the same for all * HFIs in a single system but since there can be other * device types in the system, we can't be sure this is unique. */ if (!ib_hfi1_sys_image_guid) - ib_hfi1_sys_image_guid = cpu_to_be64(ppd->guid); + ib_hfi1_sys_image_guid = ibdev->node_guid; lcpysz = strlcpy(ibdev->name, class_name(), lcpysz); strlcpy(ibdev->name + lcpysz, "_%d", IB_DEVICE_NAME_MAX - lcpysz); ibdev->owner = THIS_MODULE; - ibdev->node_guid = cpu_to_be64(ppd->guid); ibdev->phys_port_cnt = dd->num_pports; ibdev->dma_device = &dd->pcidev->dev; ibdev->modify_device = modify_device; + ibdev->alloc_hw_stats = alloc_hw_stats; + ibdev->get_hw_stats = get_hw_stats; /* keep process mad in the driver */ ibdev->process_mad = hfi1_process_mad; @@ -1767,6 +1902,10 @@ void hfi1_unregister_ib_device(struct hfi1_devdata *dd) del_timer_sync(&dev->mem_timer); verbs_txreq_exit(dev); + + kfree(dev_cntr_names); + kfree(port_cntr_names); + cntr_names_initialized = 0; } void hfi1_cnp_rcv(struct hfi1_packet *packet) diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h index 1c3815d89eb7..e6b893010e6d 100644 --- a/drivers/infiniband/hw/hfi1/verbs.h +++ b/drivers/infiniband/hw/hfi1/verbs.h @@ -73,7 +73,6 @@ struct hfi1_packet; #include "iowait.h" #define HFI1_MAX_RDMA_ATOMIC 16 -#define HFI1_GUIDS_PER_PORT 5 /* * Increment this value if any changes that break userspace ABI @@ -169,8 +168,6 @@ struct hfi1_ibport { struct rvt_qp __rcu *qp[2]; struct rvt_ibport rvp; - __be64 guids[HFI1_GUIDS_PER_PORT - 1]; /* writable GUIDs */ - /* the first 16 entries are sl_to_vl for !OPA */ u8 sl_to_sc[32]; u8 sc_to_sl[32]; @@ -180,18 +177,19 @@ struct hfi1_ibdev { struct rvt_dev_info rdi; /* Must be first */ /* QP numbers are shared by all IB ports */ - /* protect wait lists */ - seqlock_t iowait_lock; + /* protect txwait list */ + seqlock_t txwait_lock ____cacheline_aligned_in_smp; struct list_head txwait; /* list for wait verbs_txreq */ struct list_head memwait; /* list for wait kernel memory */ - struct list_head txreq_free; struct kmem_cache *verbs_txreq_cache; - struct timer_list mem_timer; + u64 n_txwait; + u64 n_kmem_wait; + /* protect iowait lists */ + seqlock_t iowait_lock ____cacheline_aligned_in_smp; u64 n_piowait; u64 n_piodrain; - u64 n_txwait; - u64 n_kmem_wait; + struct timer_list mem_timer; #ifdef CONFIG_DEBUG_FS /* per HFI debugfs */ diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.c b/drivers/infiniband/hw/hfi1/verbs_txreq.c index 094ab829ec42..5d23172c470f 100644 --- a/drivers/infiniband/hw/hfi1/verbs_txreq.c +++ b/drivers/infiniband/hw/hfi1/verbs_txreq.c @@ -72,22 +72,22 @@ void hfi1_put_txreq(struct verbs_txreq *tx) kmem_cache_free(dev->verbs_txreq_cache, tx); do { - seq = read_seqbegin(&dev->iowait_lock); + seq = read_seqbegin(&dev->txwait_lock); if (!list_empty(&dev->txwait)) { struct iowait *wait; - write_seqlock_irqsave(&dev->iowait_lock, flags); + write_seqlock_irqsave(&dev->txwait_lock, flags); wait = list_first_entry(&dev->txwait, struct iowait, list); qp = iowait_to_qp(wait); priv = qp->priv; list_del_init(&priv->s_iowait.list); /* refcount held until actual wake up */ - write_sequnlock_irqrestore(&dev->iowait_lock, flags); + write_sequnlock_irqrestore(&dev->txwait_lock, flags); hfi1_qp_wakeup(qp, RVT_S_WAIT_TX); break; } - } while (read_seqretry(&dev->iowait_lock, seq)); + } while (read_seqretry(&dev->txwait_lock, seq)); } struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev, @@ -96,7 +96,7 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev, { struct verbs_txreq *tx = ERR_PTR(-EBUSY); - write_seqlock(&dev->iowait_lock); + write_seqlock(&dev->txwait_lock); if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) { struct hfi1_qp_priv *priv; @@ -108,13 +108,14 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev, dev->n_txwait++; qp->s_flags |= RVT_S_WAIT_TX; list_add_tail(&priv->s_iowait.list, &dev->txwait); + priv->s_iowait.lock = &dev->txwait_lock; trace_hfi1_qpsleep(qp, RVT_S_WAIT_TX); rvt_get_qp(qp); } qp->s_flags &= ~RVT_S_BUSY; } out: - write_sequnlock(&dev->iowait_lock); + write_sequnlock(&dev->txwait_lock); return tx; } diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.h b/drivers/infiniband/hw/hfi1/verbs_txreq.h index 5660897593ba..76216f2ef35a 100644 --- a/drivers/infiniband/hw/hfi1/verbs_txreq.h +++ b/drivers/infiniband/hw/hfi1/verbs_txreq.h @@ -65,6 +65,7 @@ struct verbs_txreq { struct sdma_engine *sde; struct send_context *psc; u16 hdr_dwords; + u16 s_cur_size; }; struct hfi1_ibdev; |