diff options
Diffstat (limited to 'drivers/infiniband/hw')
19 files changed, 948 insertions, 479 deletions
diff --git a/drivers/infiniband/hw/mthca/mthca_av.c b/drivers/infiniband/hw/mthca/mthca_av.c index a19e0ed..f023d39 100644 --- a/drivers/infiniband/hw/mthca/mthca_av.c +++ b/drivers/infiniband/hw/mthca/mthca_av.c @@ -147,7 +147,7 @@ int mthca_destroy_ah(struct mthca_dev *dev, struct mthca_ah *ah) switch (ah->type) { case MTHCA_AH_ON_HCA: mthca_free(&dev->av_table.alloc, - (ah->avdma - dev->av_table.ddr_av_base) / + (ah->avdma - dev->av_table.ddr_av_base) / MTHCA_AV_SIZE); break; @@ -193,6 +193,37 @@ int mthca_read_ah(struct mthca_dev *dev, struct mthca_ah *ah, return 0; } +int mthca_ah_query(struct ib_ah *ibah, struct ib_ah_attr *attr) +{ + struct mthca_ah *ah = to_mah(ibah); + struct mthca_dev *dev = to_mdev(ibah->device); + + /* Only implement for MAD and memfree ah for now. */ + if (ah->type == MTHCA_AH_ON_HCA) + return -ENOSYS; + + memset(attr, 0, sizeof *attr); + attr->dlid = be16_to_cpu(ah->av->dlid); + attr->sl = be32_to_cpu(ah->av->sl_tclass_flowlabel) >> 28; + attr->static_rate = ah->av->msg_sr & 0x7; + attr->src_path_bits = ah->av->g_slid & 0x7F; + attr->port_num = be32_to_cpu(ah->av->port_pd) >> 24; + attr->ah_flags = mthca_ah_grh_present(ah) ? IB_AH_GRH : 0; + + if (attr->ah_flags) { + attr->grh.traffic_class = + be32_to_cpu(ah->av->sl_tclass_flowlabel) >> 20; + attr->grh.flow_label = + be32_to_cpu(ah->av->sl_tclass_flowlabel) & 0xfffff; + attr->grh.hop_limit = ah->av->hop_limit; + attr->grh.sgid_index = ah->av->gid_index & + (dev->limits.gid_table_len - 1); + memcpy(attr->grh.dgid.raw, ah->av->dgid, 16); + } + + return 0; +} + int __devinit mthca_init_av_table(struct mthca_dev *dev) { int err; diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c index 2825615..343eca5 100644 --- a/drivers/infiniband/hw/mthca/mthca_cmd.c +++ b/drivers/infiniband/hw/mthca/mthca_cmd.c @@ -1,7 +1,7 @@ /* * Copyright (c) 2004, 2005 Topspin Communications. All rights reserved. * Copyright (c) 2005 Mellanox Technologies. All rights reserved. - * Copyright (c) 2005 Cisco Systems. All rights reserved. + * Copyright (c) 2005, 2006 Cisco Systems. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -182,25 +182,58 @@ struct mthca_cmd_context { u8 status; }; +static int fw_cmd_doorbell = 1; +module_param(fw_cmd_doorbell, int, 0644); +MODULE_PARM_DESC(fw_cmd_doorbell, "post FW commands through doorbell page if nonzero " + "(and supported by FW)"); + static inline int go_bit(struct mthca_dev *dev) { return readl(dev->hcr + HCR_STATUS_OFFSET) & swab32(1 << HCR_GO_BIT); } -static int mthca_cmd_post(struct mthca_dev *dev, - u64 in_param, - u64 out_param, - u32 in_modifier, - u8 op_modifier, - u16 op, - u16 token, - int event) +static void mthca_cmd_post_dbell(struct mthca_dev *dev, + u64 in_param, + u64 out_param, + u32 in_modifier, + u8 op_modifier, + u16 op, + u16 token) { - int err = 0; + void __iomem *ptr = dev->cmd.dbell_map; + u16 *offs = dev->cmd.dbell_offsets; - mutex_lock(&dev->cmd.hcr_mutex); + __raw_writel((__force u32) cpu_to_be32(in_param >> 32), ptr + offs[0]); + wmb(); + __raw_writel((__force u32) cpu_to_be32(in_param & 0xfffffffful), ptr + offs[1]); + wmb(); + __raw_writel((__force u32) cpu_to_be32(in_modifier), ptr + offs[2]); + wmb(); + __raw_writel((__force u32) cpu_to_be32(out_param >> 32), ptr + offs[3]); + wmb(); + __raw_writel((__force u32) cpu_to_be32(out_param & 0xfffffffful), ptr + offs[4]); + wmb(); + __raw_writel((__force u32) cpu_to_be32(token << 16), ptr + offs[5]); + wmb(); + __raw_writel((__force u32) cpu_to_be32((1 << HCR_GO_BIT) | + (1 << HCA_E_BIT) | + (op_modifier << HCR_OPMOD_SHIFT) | + op), ptr + offs[6]); + wmb(); + __raw_writel((__force u32) 0, ptr + offs[7]); + wmb(); +} +static int mthca_cmd_post_hcr(struct mthca_dev *dev, + u64 in_param, + u64 out_param, + u32 in_modifier, + u8 op_modifier, + u16 op, + u16 token, + int event) +{ if (event) { unsigned long end = jiffies + GO_BIT_TIMEOUT; @@ -210,10 +243,8 @@ static int mthca_cmd_post(struct mthca_dev *dev, } } - if (go_bit(dev)) { - err = -EAGAIN; - goto out; - } + if (go_bit(dev)) + return -EAGAIN; /* * We use writel (instead of something like memcpy_toio) @@ -236,7 +267,29 @@ static int mthca_cmd_post(struct mthca_dev *dev, (op_modifier << HCR_OPMOD_SHIFT) | op), dev->hcr + 6 * 4); -out: + return 0; +} + +static int mthca_cmd_post(struct mthca_dev *dev, + u64 in_param, + u64 out_param, + u32 in_modifier, + u8 op_modifier, + u16 op, + u16 token, + int event) +{ + int err = 0; + + mutex_lock(&dev->cmd.hcr_mutex); + + if (event && dev->cmd.flags & MTHCA_CMD_POST_DOORBELLS && fw_cmd_doorbell) + mthca_cmd_post_dbell(dev, in_param, out_param, in_modifier, + op_modifier, op, token); + else + err = mthca_cmd_post_hcr(dev, in_param, out_param, in_modifier, + op_modifier, op, token, event); + mutex_unlock(&dev->cmd.hcr_mutex); return err; } @@ -275,7 +328,7 @@ static int mthca_cmd_poll(struct mthca_dev *dev, } if (out_is_imm) - *out_param = + *out_param = (u64) be32_to_cpu((__force __be32) __raw_readl(dev->hcr + HCR_OUT_PARAM_OFFSET)) << 32 | (u64) be32_to_cpu((__force __be32) @@ -386,7 +439,7 @@ static int mthca_cmd_box(struct mthca_dev *dev, unsigned long timeout, u8 *status) { - if (dev->cmd.use_events) + if (dev->cmd.flags & MTHCA_CMD_USE_EVENTS) return mthca_cmd_wait(dev, in_param, &out_param, 0, in_modifier, op_modifier, op, timeout, status); @@ -423,7 +476,7 @@ static int mthca_cmd_imm(struct mthca_dev *dev, unsigned long timeout, u8 *status) { - if (dev->cmd.use_events) + if (dev->cmd.flags & MTHCA_CMD_USE_EVENTS) return mthca_cmd_wait(dev, in_param, out_param, 1, in_modifier, op_modifier, op, timeout, status); @@ -437,7 +490,7 @@ int mthca_cmd_init(struct mthca_dev *dev) { mutex_init(&dev->cmd.hcr_mutex); sema_init(&dev->cmd.poll_sem, 1); - dev->cmd.use_events = 0; + dev->cmd.flags = 0; dev->hcr = ioremap(pci_resource_start(dev->pdev, 0) + MTHCA_HCR_BASE, MTHCA_HCR_SIZE); @@ -461,6 +514,8 @@ void mthca_cmd_cleanup(struct mthca_dev *dev) { pci_pool_destroy(dev->cmd.pool); iounmap(dev->hcr); + if (dev->cmd.flags & MTHCA_CMD_POST_DOORBELLS) + iounmap(dev->cmd.dbell_map); } /* @@ -498,7 +553,8 @@ int mthca_cmd_use_events(struct mthca_dev *dev) ; /* nothing */ --dev->cmd.token_mask; - dev->cmd.use_events = 1; + dev->cmd.flags |= MTHCA_CMD_USE_EVENTS; + down(&dev->cmd.poll_sem); return 0; @@ -511,7 +567,7 @@ void mthca_cmd_use_polling(struct mthca_dev *dev) { int i; - dev->cmd.use_events = 0; + dev->cmd.flags &= ~MTHCA_CMD_USE_EVENTS; for (i = 0; i < dev->cmd.max_cmds; ++i) down(&dev->cmd.event_sem); @@ -596,8 +652,9 @@ static int mthca_map_cmd(struct mthca_dev *dev, u16 op, struct mthca_icm *icm, * address or size and use that as our log2 size. */ lg = ffs(mthca_icm_addr(&iter) | mthca_icm_size(&iter)) - 1; - if (lg < 12) { - mthca_warn(dev, "Got FW area not aligned to 4K (%llx/%lx).\n", + if (lg < MTHCA_ICM_PAGE_SHIFT) { + mthca_warn(dev, "Got FW area not aligned to %d (%llx/%lx).\n", + MTHCA_ICM_PAGE_SIZE, (unsigned long long) mthca_icm_addr(&iter), mthca_icm_size(&iter)); err = -EINVAL; @@ -609,8 +666,9 @@ static int mthca_map_cmd(struct mthca_dev *dev, u16 op, struct mthca_icm *icm, virt += 1 << lg; } - pages[nent * 2 + 1] = cpu_to_be64((mthca_icm_addr(&iter) + - (i << lg)) | (lg - 12)); + pages[nent * 2 + 1] = + cpu_to_be64((mthca_icm_addr(&iter) + (i << lg)) | + (lg - MTHCA_ICM_PAGE_SHIFT)); ts += 1 << (lg - 10); ++tc; @@ -661,12 +719,41 @@ int mthca_RUN_FW(struct mthca_dev *dev, u8 *status) return mthca_cmd(dev, 0, 0, 0, CMD_RUN_FW, CMD_TIME_CLASS_A, status); } +static void mthca_setup_cmd_doorbells(struct mthca_dev *dev, u64 base) +{ + unsigned long addr; + u16 max_off = 0; + int i; + + for (i = 0; i < 8; ++i) + max_off = max(max_off, dev->cmd.dbell_offsets[i]); + + if ((base & PAGE_MASK) != ((base + max_off) & PAGE_MASK)) { + mthca_warn(dev, "Firmware doorbell region at 0x%016llx, " + "length 0x%x crosses a page boundary\n", + (unsigned long long) base, max_off); + return; + } + + addr = pci_resource_start(dev->pdev, 2) + + ((pci_resource_len(dev->pdev, 2) - 1) & base); + dev->cmd.dbell_map = ioremap(addr, max_off + sizeof(u32)); + if (!dev->cmd.dbell_map) + return; + + dev->cmd.flags |= MTHCA_CMD_POST_DOORBELLS; + mthca_dbg(dev, "Mapped doorbell page for posting FW commands\n"); +} + int mthca_QUERY_FW(struct mthca_dev *dev, u8 *status) { struct mthca_mailbox *mailbox; u32 *outbox; + u64 base; + u32 tmp; int err = 0; u8 lg; + int i; #define QUERY_FW_OUT_SIZE 0x100 #define QUERY_FW_VER_OFFSET 0x00 @@ -674,6 +761,10 @@ int mthca_QUERY_FW(struct mthca_dev *dev, u8 *status) #define QUERY_FW_ERR_START_OFFSET 0x30 #define QUERY_FW_ERR_SIZE_OFFSET 0x38 +#define QUERY_FW_CMD_DB_EN_OFFSET 0x10 +#define QUERY_FW_CMD_DB_OFFSET 0x50 +#define QUERY_FW_CMD_DB_BASE 0x60 + #define QUERY_FW_START_OFFSET 0x20 #define QUERY_FW_END_OFFSET 0x28 @@ -702,16 +793,29 @@ int mthca_QUERY_FW(struct mthca_dev *dev, u8 *status) ((dev->fw_ver & 0xffff0000ull) >> 16) | ((dev->fw_ver & 0x0000ffffull) << 16); + mthca_dbg(dev, "FW version %012llx, max commands %d\n", + (unsigned long long) dev->fw_ver, dev->cmd.max_cmds); + MTHCA_GET(lg, outbox, QUERY_FW_MAX_CMD_OFFSET); dev->cmd.max_cmds = 1 << lg; MTHCA_GET(dev->catas_err.addr, outbox, QUERY_FW_ERR_START_OFFSET); MTHCA_GET(dev->catas_err.size, outbox, QUERY_FW_ERR_SIZE_OFFSET); - mthca_dbg(dev, "FW version %012llx, max commands %d\n", - (unsigned long long) dev->fw_ver, dev->cmd.max_cmds); mthca_dbg(dev, "Catastrophic error buffer at 0x%llx, size 0x%x\n", (unsigned long long) dev->catas_err.addr, dev->catas_err.size); + MTHCA_GET(tmp, outbox, QUERY_FW_CMD_DB_EN_OFFSET); + if (tmp & 0x1) { + mthca_dbg(dev, "FW supports commands through doorbells\n"); + + MTHCA_GET(base, outbox, QUERY_FW_CMD_DB_BASE); + for (i = 0; i < MTHCA_CMD_NUM_DBELL_DWORDS; ++i) + MTHCA_GET(dev->cmd.dbell_offsets[i], outbox, + QUERY_FW_CMD_DB_OFFSET + (i << 1)); + + mthca_setup_cmd_doorbells(dev, base); + } + if (mthca_is_memfree(dev)) { MTHCA_GET(dev->fw.arbel.fw_pages, outbox, QUERY_FW_SIZE_OFFSET); MTHCA_GET(dev->fw.arbel.clr_int_base, outbox, QUERY_FW_CLR_INT_BASE_OFFSET); @@ -720,12 +824,12 @@ int mthca_QUERY_FW(struct mthca_dev *dev, u8 *status) mthca_dbg(dev, "FW size %d KB\n", dev->fw.arbel.fw_pages << 2); /* - * Arbel page size is always 4 KB; round up number of - * system pages needed. + * Round up number of system pages needed in case + * MTHCA_ICM_PAGE_SIZE < PAGE_SIZE. */ dev->fw.arbel.fw_pages = - ALIGN(dev->fw.arbel.fw_pages, PAGE_SIZE >> 12) >> - (PAGE_SHIFT - 12); + ALIGN(dev->fw.arbel.fw_pages, PAGE_SIZE / MTHCA_ICM_PAGE_SIZE) >> + (PAGE_SHIFT - MTHCA_ICM_PAGE_SHIFT); mthca_dbg(dev, "Clear int @ %llx, EQ arm @ %llx, EQ set CI @ %llx\n", (unsigned long long) dev->fw.arbel.clr_int_base, @@ -1173,7 +1277,8 @@ int mthca_INIT_HCA(struct mthca_dev *dev, int err; #define INIT_HCA_IN_SIZE 0x200 -#define INIT_HCA_FLAGS_OFFSET 0x014 +#define INIT_HCA_FLAGS1_OFFSET 0x00c +#define INIT_HCA_FLAGS2_OFFSET 0x014 #define INIT_HCA_QPC_OFFSET 0x020 #define INIT_HCA_QPC_BASE_OFFSET (INIT_HCA_QPC_OFFSET + 0x10) #define INIT_HCA_LOG_QP_OFFSET (INIT_HCA_QPC_OFFSET + 0x17) @@ -1216,15 +1321,18 @@ int mthca_INIT_HCA(struct mthca_dev *dev, memset(inbox, 0, INIT_HCA_IN_SIZE); + if (dev->mthca_flags & MTHCA_FLAG_SINAI_OPT) + MTHCA_PUT(inbox, 0x1, INIT_HCA_FLAGS1_OFFSET); + #if defined(__LITTLE_ENDIAN) - *(inbox + INIT_HCA_FLAGS_OFFSET / 4) &= ~cpu_to_be32(1 << 1); + *(inbox + INIT_HCA_FLAGS2_OFFSET / 4) &= ~cpu_to_be32(1 << 1); #elif defined(__BIG_ENDIAN) - *(inbox + INIT_HCA_FLAGS_OFFSET / 4) |= cpu_to_be32(1 << 1); + *(inbox + INIT_HCA_FLAGS2_OFFSET / 4) |= cpu_to_be32(1 << 1); #else #error Host endianness not defined #endif /* Check port for UD address vector: */ - *(inbox + INIT_HCA_FLAGS_OFFSET / 4) |= cpu_to_be32(1); + *(inbox + INIT_HCA_FLAGS2_OFFSET / 4) |= cpu_to_be32(1); /* We leave wqe_quota, responder_exu, etc as 0 (default) */ @@ -1438,11 +1546,11 @@ int mthca_SET_ICM_SIZE(struct mthca_dev *dev, u64 icm_size, u64 *aux_pages, return ret; /* - * Arbel page size is always 4 KB; round up number of system - * pages needed. + * Round up number of system pages needed in case + * MTHCA_ICM_PAGE_SIZE < PAGE_SIZE. */ - *aux_pages = (*aux_pages + (1 << (PAGE_SHIFT - 12)) - 1) >> (PAGE_SHIFT - 12); - *aux_pages = ALIGN(*aux_pages, PAGE_SIZE >> 12) >> (PAGE_SHIFT - 12); + *aux_pages = ALIGN(*aux_pages, PAGE_SIZE / MTHCA_ICM_PAGE_SIZE) >> + (PAGE_SHIFT - MTHCA_ICM_PAGE_SHIFT); return 0; } @@ -1514,6 +1622,37 @@ int mthca_HW2SW_CQ(struct mthca_dev *dev, struct mthca_mailbox *mailbox, CMD_TIME_CLASS_A, status); } +int mthca_RESIZE_CQ(struct mthca_dev *dev, int cq_num, u32 lkey, u8 log_size, + u8 *status) +{ + struct mthca_mailbox *mailbox; + __be32 *inbox; + int err; + +#define RESIZE_CQ_IN_SIZE 0x40 +#define RESIZE_CQ_LOG_SIZE_OFFSET 0x0c +#define RESIZE_CQ_LKEY_OFFSET 0x1c + + mailbox = mthca_alloc_mailbox(dev, GFP_KERNEL); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + inbox = mailbox->buf; + + memset(inbox, 0, RESIZE_CQ_IN_SIZE); + /* + * Leave start address fields zeroed out -- mthca assumes that + * MRs for CQs always start at virtual address 0. + */ + MTHCA_PUT(inbox, log_size, RESIZE_CQ_LOG_SIZE_OFFSET); + MTHCA_PUT(inbox, lkey, RESIZE_CQ_LKEY_OFFSET); + + err = mthca_cmd(dev, mailbox->dma, cq_num, 1, CMD_RESIZE_CQ, + CMD_TIME_CLASS_B, status); + + mthca_free_mailbox(dev, mailbox); + return err; +} + int mthca_SW2HW_SRQ(struct mthca_dev *dev, struct mthca_mailbox *mailbox, int srq_num, u8 *status) { @@ -1529,37 +1668,69 @@ int mthca_HW2SW_SRQ(struct mthca_dev *dev, struct mthca_mailbox *mailbox, CMD_TIME_CLASS_A, status); } +int mthca_QUERY_SRQ(struct mthca_dev *dev, u32 num, + struct mthca_mailbox *mailbox, u8 *status) +{ + return mthca_cmd_box(dev, 0, mailbox->dma, num, 0, + CMD_QUERY_SRQ, CMD_TIME_CLASS_A, status); +} + int mthca_ARM_SRQ(struct mthca_dev *dev, int srq_num, int limit, u8 *status) { return mthca_cmd(dev, limit, srq_num, 0, CMD_ARM_SRQ, CMD_TIME_CLASS_B, status); } -int mthca_MODIFY_QP(struct mthca_dev *dev, int trans, u32 num, - int is_ee, struct mthca_mailbox *mailbox, u32 optmask, +int mthca_MODIFY_QP(struct mthca_dev *dev, enum ib_qp_state cur, + enum ib_qp_state next, u32 num, int is_ee, + struct mthca_mailbox *mailbox, u32 optmask, u8 *status) { - static const u16 op[] = { - [MTHCA_TRANS_RST2INIT] = CMD_RST2INIT_QPEE, - [MTHCA_TRANS_INIT2INIT] = CMD_INIT2INIT_QPEE, - [MTHCA_TRANS_INIT2RTR] = CMD_INIT2RTR_QPEE, - [MTHCA_TRANS_RTR2RTS] = CMD_RTR2RTS_QPEE, - [MTHCA_TRANS_RTS2RTS] = CMD_RTS2RTS_QPEE, - [MTHCA_TRANS_SQERR2RTS] = CMD_SQERR2RTS_QPEE, - [MTHCA_TRANS_ANY2ERR] = CMD_2ERR_QPEE, - [MTHCA_TRANS_RTS2SQD] = CMD_RTS2SQD_QPEE, - [MTHCA_TRANS_SQD2SQD] = CMD_SQD2SQD_QPEE, - [MTHCA_TRANS_SQD2RTS] = CMD_SQD2RTS_QPEE, - [MTHCA_TRANS_ANY2RST] = CMD_ERR2RST_QPEE + static const u16 op[IB_QPS_ERR + 1][IB_QPS_ERR + 1] = { + [IB_QPS_RESET] = { + [IB_QPS_RESET] = CMD_ERR2RST_QPEE, + [IB_QPS_ERR] = CMD_2ERR_QPEE, + [IB_QPS_INIT] = CMD_RST2INIT_QPEE, + }, + [IB_QPS_INIT] = { + [IB_QPS_RESET] = CMD_ERR2RST_QPEE, + [IB_QPS_ERR] = CMD_2ERR_QPEE, + [IB_QPS_INIT] = CMD_INIT2INIT_QPEE, + [IB_QPS_RTR] = CMD_INIT2RTR_QPEE, + }, + [IB_QPS_RTR] = { + [IB_QPS_RESET] = CMD_ERR2RST_QPEE, + [IB_QPS_ERR] = CMD_2ERR_QPEE, + [IB_QPS_RTS] = CMD_RTR2RTS_QPEE, + }, + [IB_QPS_RTS] = { + [IB_QPS_RESET] = CMD_ERR2RST_QPEE, + [IB_QPS_ERR] = CMD_2ERR_QPEE, + [IB_QPS_RTS] = CMD_RTS2RTS_QPEE, + [IB_QPS_SQD] = CMD_RTS2SQD_QPEE, + }, + [IB_QPS_SQD] = { + [IB_QPS_RESET] = CMD_ERR2RST_QPEE, + [IB_QPS_ERR] = CMD_2ERR_QPEE, + [IB_QPS_RTS] = CMD_SQD2RTS_QPEE, + [IB_QPS_SQD] = CMD_SQD2SQD_QPEE, + }, + [IB_QPS_SQE] = { + [IB_QPS_RESET] = CMD_ERR2RST_QPEE, + [IB_QPS_ERR] = CMD_2ERR_QPEE, + [IB_QPS_RTS] = CMD_SQERR2RTS_QPEE, + }, + [IB_QPS_ERR] = { + [IB_QPS_RESET] = CMD_ERR2RST_QPEE, + [IB_QPS_ERR] = CMD_2ERR_QPEE, + } }; + u8 op_mod = 0; int my_mailbox = 0; int err; - if (trans < 0 || trans >= ARRAY_SIZE(op)) - return -EINVAL; - - if (trans == MTHCA_TRANS_ANY2RST) { + if (op[cur][next] == CMD_ERR2RST_QPEE) { op_mod = 3; /* don't write outbox, any->reset */ /* For debugging */ @@ -1571,34 +1742,35 @@ int mthca_MODIFY_QP(struct mthca_dev *dev, int trans, u32 num, } else mailbox = NULL; } - } else { - if (0) { + + err = mthca_cmd_box(dev, 0, mailbox ? mailbox->dma : 0, + (!!is_ee << 24) | num, op_mod, + op[cur][next], CMD_TIME_CLASS_C, status); + + if (0 && mailbox) { int i; mthca_dbg(dev, "Dumping QP context:\n"); - printk(" opt param mask: %08x\n", be32_to_cpup(mailbox->buf)); + printk(" %08x\n", be32_to_cpup(mailbox->buf)); for (i = 0; i < 0x100 / 4; ++i) { if (i % 8 == 0) - printk(" [%02x] ", i * 4); + printk("[%02x] ", i * 4); printk(" %08x", be32_to_cpu(((__be32 *) mailbox->buf)[i + 2])); if ((i + 1) % 8 == 0) printk("\n"); } } - } - - if (trans == MTHCA_TRANS_ANY2RST) { - err = mthca_cmd_box(dev, 0, mailbox ? mailbox->dma : 0, - (!!is_ee << 24) | num, op_mod, - op[trans], CMD_TIME_CLASS_C, status); - if (0 && mailbox) { + if (my_mailbox) + mthca_free_mailbox(dev, mailbox); + } else { + if (0) { int i; mthca_dbg(dev, "Dumping QP context:\n"); - printk(" %08x\n", be32_to_cpup(mailbox->buf)); + printk(" opt param mask: %08x\n", be32_to_cpup(mailbox->buf)); for (i = 0; i < 0x100 / 4; ++i) { if (i % 8 == 0) - printk("[%02x] ", i * 4); + printk(" [%02x] ", i * 4); printk(" %08x", be32_to_cpu(((__be32 *) mailbox->buf)[i + 2])); if ((i + 1) % 8 == 0) @@ -1606,12 +1778,9 @@ int mthca_MODIFY_QP(struct mthca_dev *dev, int trans, u32 num, } } - } else - err = mthca_cmd(dev, mailbox->dma, (!!is_ee << 24) | num, - op_mod, op[trans], CMD_TIME_CLASS_C, status); - - if (my_mailbox) - mthca_free_mailbox(dev, mailbox); + err = mthca_cmd(dev, mailbox->dma, optmask | (!!is_ee << 24) | num, + op_mod, op[cur][next], CMD_TIME_CLASS_C, status); + } return err; } diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.h b/drivers/infiniband/hw/mthca/mthca_cmd.h index 18175be..e4ec35c 100644 --- a/drivers/infiniband/hw/mthca/mthca_cmd.h +++ b/drivers/infiniband/hw/mthca/mthca_cmd.h @@ -1,6 +1,7 @@ /* * Copyright (c) 2004, 2005 Topspin Communications. All rights reserved. * Copyright (c) 2005 Mellanox Technologies. All rights reserved. + * Copyright (c) 2006 Cisco Systems. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -73,9 +74,9 @@ enum { MTHCA_CMD_STAT_REG_BOUND = 0x21, /* HCA local attached memory not present: */ MTHCA_CMD_STAT_LAM_NOT_PRE = 0x22, - /* Bad management packet (silently discarded): */ + /* Bad management packet (silently discarded): */ MTHCA_CMD_STAT_BAD_PKT = 0x30, - /* More outstanding CQEs in CQ than new CQ size: */ + /* More outstanding CQEs in CQ than new CQ size: */ MTHCA_CMD_STAT_BAD_SIZE = 0x40 }; @@ -298,13 +299,18 @@ int mthca_SW2HW_CQ(struct mthca_dev *dev, struct mthca_mailbox *mailbox, int cq_num, u8 *status); int mthca_HW2SW_CQ(struct mthca_dev *dev, struct mthca_mailbox *mailbox, int cq_num, u8 *status); +int mthca_RESIZE_CQ(struct mthca_dev *dev, int cq_num, u32 lkey, u8 log_size, + u8 *status); int mthca_SW2HW_SRQ(struct mthca_dev *dev, struct mthca_mailbox *mailbox, int srq_num, u8 *status); int mthca_HW2SW_SRQ(struct mthca_dev *dev, struct mthca_mailbox *mailbox, int srq_num, u8 *status); +int mthca_QUERY_SRQ(struct mthca_dev *dev, u32 num, + struct mthca_mailbox *mailbox, u8 *status); int mthca_ARM_SRQ(struct mthca_dev *dev, int srq_num, int limit, u8 *status); -int mthca_MODIFY_QP(struct mthca_dev *dev, int trans, u32 num, - int is_ee, struct mthca_mailbox *mailbox, u32 optmask, +int mthca_MODIFY_QP(struct mthca_dev *dev, enum ib_qp_state cur, + enum ib_qp_state next, u32 num, int is_ee, + struct mthca_mailbox *mailbox, u32 optmask, u8 *status); int mthca_QUERY_QP(struct mthca_dev *dev, u32 num, int is_ee, struct mthca_mailbox *mailbox, u8 *status); diff --git a/drivers/infiniband/hw/mthca/mthca_cq.c b/drivers/infiniband/hw/mthca/mthca_cq.c index 96f1a86..76aabc5 100644 --- a/drivers/infiniband/hw/mthca/mthca_cq.c +++ b/drivers/infiniband/hw/mthca/mthca_cq.c @@ -1,7 +1,7 @@ /* * Copyright (c) 2004, 2005 Topspin Communications. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. - * Copyright (c) 2005 Cisco Systems, Inc. All rights reserved. + * Copyright (c) 2005, 2006 Cisco Systems, Inc. All rights reserved. * Copyright (c) 2005 Mellanox Technologies. All rights reserved. * Copyright (c) 2004 Voltaire, Inc. All rights reserved. * @@ -150,24 +150,29 @@ struct mthca_err_cqe { #define MTHCA_ARBEL_CQ_DB_REQ_NOT (2 << 24) #define MTHCA_ARBEL_CQ_DB_REQ_NOT_MULT (3 << 24) -static inline struct mthca_cqe *get_cqe(struct mthca_cq *cq, int entry) +static inline struct mthca_cqe *get_cqe_from_buf(struct mthca_cq_buf *buf, + int entry) { - if (cq->is_direct) - return cq->queue.direct.buf + (entry * MTHCA_CQ_ENTRY_SIZE); + if (buf->is_direct) + return buf->queue.direct.buf + (entry * MTHCA_CQ_ENTRY_SIZE); else - return cq->queue.page_list[entry * MTHCA_CQ_ENTRY_SIZE / PAGE_SIZE].buf + return buf->queue.page_list[entry * MTHCA_CQ_ENTRY_SIZE / PAGE_SIZE].buf + (entry * MTHCA_CQ_ENTRY_SIZE) % PAGE_SIZE; } -static inline struct mthca_cqe *cqe_sw(struct mthca_cq *cq, int i) +static inline struct mthca_cqe *get_cqe(struct mthca_cq *cq, int entry) +{ + return get_cqe_from_buf(&cq->buf, entry); +} + +static inline struct mthca_cqe *cqe_sw(struct mthca_cqe *cqe) { - struct mthca_cqe *cqe = get_cqe(cq, i); return MTHCA_CQ_ENTRY_OWNER_HW & cqe->owner ? NULL : cqe; } static inline struct mthca_cqe *next_cqe_sw(struct mthca_cq *cq) { - return cqe_sw(cq, cq->cons_index & cq->ibcq.cqe); + return cqe_sw(get_cqe(cq, cq->cons_index & cq->ibcq.cqe)); } static inline void set_cqe_hw(struct mthca_cqe *cqe) @@ -289,7 +294,7 @@ void mthca_cq_clean(struct mthca_dev *dev, u32 cqn, u32 qpn, * from our QP and therefore don't need to be checked. */ for (prod_index = cq->cons_index; - cqe_sw(cq, prod_index & cq->ibcq.cqe); + cqe_sw(get_cqe(cq, prod_index & cq->ibcq.cqe)); ++prod_index) if (prod_index == cq->cons_index + cq->ibcq.cqe) break; @@ -324,12 +329,58 @@ void mthca_cq_clean(struct mthca_dev *dev, u32 cqn, u32 qpn, wake_up(&cq->wait); } -static int handle_error_cqe(struct mthca_dev *dev, struct mthca_cq *cq, - struct mthca_qp *qp, int wqe_index, int is_send, - struct mthca_err_cqe *cqe, - struct ib_wc *entry, int *free_cqe) +void mthca_cq_resize_copy_cqes(struct mthca_cq *cq) +{ + int i; + + /* + * In Tavor mode, the hardware keeps the consumer and producer + * indices mod the CQ size. Since we might be making the CQ + * bigger, we need to deal with the case where the producer + * index wrapped around before the CQ was resized. + */ + if (!mthca_is_memfree(to_mdev(cq->ibcq.device)) && + cq->ibcq.cqe < cq->resize_buf->cqe) { + cq->cons_index &= cq->ibcq.cqe; + if (cqe_sw(get_cqe(cq, cq->ibcq.cqe))) + cq->cons_index -= cq->ibcq.cqe + 1; + } + + for (i = cq->cons_index; cqe_sw(get_cqe(cq, i & cq->ibcq.cqe)); ++i) + memcpy(get_cqe_from_buf(&cq->resize_buf->buf, + i & cq->resize_buf->cqe), + get_cqe(cq, i & cq->ibcq.cqe), MTHCA_CQ_ENTRY_SIZE); +} + +int mthca_alloc_cq_buf(struct mthca_dev *dev, struct mthca_cq_buf *buf, int nent) +{ + int ret; + int i; + + ret = mthca_buf_alloc(dev, nent * MTHCA_CQ_ENTRY_SIZE, + MTHCA_MAX_DIRECT_CQ_SIZE, + &buf->queue, &buf->is_direct, + &dev->driver_pd, 1, &buf->mr); + if (ret) + return ret; + + for (i = 0; i < nent; ++i) + set_cqe_hw(get_cqe_from_buf(buf, i)); + + return 0; +} + +void mthca_free_cq_buf(struct mthca_dev *dev, struct mthca_cq_buf *buf, int cqe) +{ + mthca_buf_free(dev, (cqe + 1) * MTHCA_CQ_ENTRY_SIZE, &buf->queue, + buf->is_direct, &buf->mr); +} + +static void handle_error_cqe(struct mthca_dev *dev, struct mthca_cq *cq, + struct mthca_qp *qp, int wqe_index, int is_send, + struct mthca_err_cqe *cqe, + struct ib_wc *entry, int *free_cqe) { - int err; int dbd; __be32 new_wqe; @@ -412,11 +463,9 @@ static int handle_error_cqe(struct mthca_dev *dev, struct mthca_cq *cq, * error case, so we don't have to check the doorbell count, etc. */ if (mthca_is_memfree(dev)) - return 0; + return; - err = mthca_free_err_wqe(dev, qp, is_send, wqe_index, &dbd, &new_wqe); - if (err) - return err; + mthca_free_err_wqe(dev, qp, is_send, wqe_index, &dbd, &new_wqe); /* * If we're at the end of the WQE chain, or we've used up our @@ -424,15 +473,13 @@ static int handle_error_cqe(struct mthca_dev *dev, struct mthca_cq *cq, * the next poll operation. */ if (!(new_wqe & cpu_to_be32(0x3f)) || (!cqe->db_cnt && dbd)) - return 0; + return; cqe->db_cnt = cpu_to_be16(be16_to_cpu(cqe->db_cnt) - dbd); cqe->wqe = new_wqe; cqe->syndrome = SYNDROME_WR_FLUSH_ERR; *free_cqe = 0; - - return 0; } static inline int mthca_poll_one(struct mthca_dev *dev, @@ -518,9 +565,9 @@ static inline int mthca_poll_one(struct mthca_dev *dev, } if (is_error) { - err = handle_error_cqe(dev, cq, *cur_qp, wqe_index, is_send, - (struct mthca_err_cqe *) cqe, - entry, &free_cqe); + handle_error_cqe(dev, cq, *cur_qp, wqe_index, is_send, + (struct mthca_err_cqe *) cqe, + entry, &free_cqe); goto out; } @@ -614,11 +661,14 @@ int mthca_poll_cq(struct ib_cq *ibcq, int num_entries, spin_lock_irqsave(&cq->lock, flags); - for (npolled = 0; npolled < num_entries; ++npolled) { + npolled = 0; +repoll: + while (npolled < num_entries) { err = mthca_poll_one(dev, cq, &qp, &freed, entry + npolled); if (err) break; + ++npolled; } if (freed) { @@ -626,6 +676,42 @@ int mthca_poll_cq(struct ib_cq *ibcq, int num_entries, update_cons_index(dev, cq, freed); } + /* + * If a CQ resize is in progress and we discovered that the + * old buffer is empty, then peek in the new buffer, and if + * it's not empty, switch to the new buffer and continue + * polling there. + */ + if (unlikely(err == -EAGAIN && cq->resize_buf && + cq->resize_buf->state == CQ_RESIZE_READY)) { + /* + * In Tavor mode, the hardware keeps the producer + * index modulo the CQ size. Since we might be making + * the CQ bigger, we need to mask our consumer index + * using the size of the old CQ buffer before looking + * in the new CQ buffer. + */ + if (!mthca_is_memfree(dev)) + cq->cons_index &= cq->ibcq.cqe; + + if (cqe_sw(get_cqe_from_buf(&cq->resize_buf->buf, + cq->cons_index & cq->resize_buf->cqe))) { + struct mthca_cq_buf tbuf; + int tcqe; + + tbuf = cq->buf; + tcqe = cq->ibcq.cqe; + cq->buf = cq->resize_buf->buf; + cq->ibcq.cqe = cq->resize_buf->cqe; + + cq->resize_buf->buf = tbuf; + cq->resize_buf->cqe = tcqe; + cq->resize_buf->state = CQ_RESIZE_SWAPPED; + + goto repoll; + } + } + spin_unlock_irqrestore(&cq->lock, flags); return err == 0 || err == -EAGAIN ? npolled : err; @@ -684,24 +770,14 @@ int mthca_arbel_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify notify) return 0; } -static void mthca_free_cq_buf(struct mthca_dev *dev, struct mthca_cq *cq) -{ - mthca_buf_free(dev, (cq->ibcq.cqe + 1) * MTHCA_CQ_ENTRY_SIZE, - &cq->queue, cq->is_direct, &cq->mr); -} - int mthca_init_cq(struct mthca_dev *dev, int nent, struct mthca_ucontext *ctx, u32 pdn, struct mthca_cq *cq) { - int size = nent * MTHCA_CQ_ENTRY_SIZE; struct mthca_mailbox *mailbox; struct mthca_cq_context *cq_context; int err = -ENOMEM; u8 status; - int i; - - might_sleep(); cq->ibcq.cqe = nent - 1; cq->is_kernel = !ctx; @@ -739,14 +815,9 @@ int mthca_init_cq(struct mthca_dev *dev, int nent, cq_context = mailbox->buf; if (cq->is_kernel) { - err = mthca_buf_alloc(dev, size, MTHCA_MAX_DIRECT_CQ_SIZE, - &cq->queue, &cq->is_direct, - &dev->driver_pd, 1, &cq->mr); + err = mthca_alloc_cq_buf(dev, &cq->buf, nent); if (err) goto err_out_mailbox; - - for (i = 0; i < nent; ++i) - set_cqe_hw(get_cqe(cq, i)); } spin_lock_init(&cq->lock); @@ -765,7 +836,7 @@ int mthca_init_cq(struct mthca_dev *dev, int nent, cq_context->error_eqn = cpu_to_be32(dev->eq_table.eq[MTHCA_EQ_ASYNC].eqn); cq_context->comp_eqn = cpu_to_be32(dev->eq_table.eq[MTHCA_EQ_COMP].eqn); cq_context->pd = cpu_to_be32(pdn); - cq_context->lkey = cpu_to_be32(cq->mr.ibmr.lkey); + cq_context->lkey = cpu_to_be32(cq->buf.mr.ibmr.lkey); cq_context->cqn = cpu_to_be32(cq->cqn); if (mthca_is_memfree(dev)) { @@ -803,7 +874,7 @@ int mthca_init_cq(struct mthca_dev *dev, int nent, err_out_free_mr: if (cq->is_kernel) - mthca_free_cq_buf(dev, cq); + mthca_free_cq_buf(dev, &cq->buf, cq->ibcq.cqe); err_out_mailbox: mthca_free_mailbox(dev, mailbox); @@ -832,8 +903,6 @@ void mthca_free_cq(struct mthca_dev *dev, int err; u8 status; - might_sleep(); - mailbox = mthca_alloc_mailbox(dev, GFP_KERNEL); if (IS_ERR(mailbox)) { mthca_warn(dev, "No memory for mailbox to free CQ.\n"); @@ -871,7 +940,7 @@ void mthca_free_cq(struct mthca_dev *dev, wait_event(cq->wait, !atomic_read(&cq->refcount)); if (cq->is_kernel) { - mthca_free_cq_buf(dev, cq); + mthca_free_cq_buf(dev, &cq->buf, cq->ibcq.cqe); if (mthca_is_memfree(dev)) { mthca_free_db(dev, MTHCA_DB_TYPE_CQ_ARM, cq->arm_db_index); mthca_free_db(dev, MTHCA_DB_TYPE_CQ_SET_CI, cq->set_ci_db_index); diff --git a/drivers/infiniband/hw/mthca/mthca_dev.h b/drivers/infiniband/hw/mthca/mthca_dev.h index e4810372..ad52edb 100644 --- a/drivers/infiniband/hw/mthca/mthca_dev.h +++ b/drivers/infiniband/hw/mthca/mthca_dev.h @@ -1,7 +1,7 @@ /* * Copyright (c) 2004, 2005 Topspin Communications. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. - * Copyright (c) 2005 Cisco Systems. All rights reserved. + * Copyright (c) 2005, 2006 Cisco Systems. All rights reserved. * Copyright (c) 2005 Mellanox Technologies. All rights reserved. * Copyright (c) 2004 Voltaire, Inc. All rights reserved. * @@ -53,8 +53,8 @@ #define DRV_NAME "ib_mthca" #define PFX DRV_NAME ": " -#define DRV_VERSION "0.07" -#define DRV_RELDATE "February 13, 2006" +#define DRV_VERSION "0.08" +#define DRV_RELDATE "February 14, 2006" enum { MTHCA_FLAG_DDR_HIDDEN = 1 << 1, @@ -64,7 +64,8 @@ enum { MTHCA_FLAG_NO_LAM = 1 << 5, MTHCA_FLAG_FMR = 1 << 6, MTHCA_FLAG_MEMFREE = 1 << 7, - MTHCA_FLAG_PCIE = 1 << 8 + MTHCA_FLAG_PCIE = 1 << 8, + MTHCA_FLAG_SINAI_OPT = 1 << 9 }; enum { @@ -110,9 +111,17 @@ enum { MTHCA_OPCODE_INVALID = 0xff }; +enum { + MTHCA_CMD_USE_EVENTS = 1 << 0, + MTHCA_CMD_POST_DOORBELLS = 1 << 1 +}; + +enum { + MTHCA_CMD_NUM_DBELL_DWORDS = 8 +}; + struct mthca_cmd { struct pci_pool *pool; - int use_events; struct mutex hcr_mutex; struct semaphore poll_sem; struct semaphore event_sem; @@ -121,6 +130,9 @@ struct mthca_cmd { int free_head; struct mthca_cmd_context *context; u16 token_mask; + u32 flags; + void __iomem *dbell_map; + u16 dbell_offsets[MTHCA_CMD_NUM_DBELL_DWORDS]; }; struct mthca_limits { @@ -470,12 +482,16 @@ void mthca_cq_event(struct mthca_dev *dev, u32 cqn, enum ib_event_type event_type); void mthca_cq_clean(struct mthca_dev *dev, u32 cqn, u32 qpn, struct mthca_srq *srq); +void mthca_cq_resize_copy_cqes(struct mthca_cq *cq); +int mthca_alloc_cq_buf(struct mthca_dev *dev, struct mthca_cq_buf *buf, int nent); +void mthca_free_cq_buf(struct mthca_dev *dev, struct mthca_cq_buf *buf, int cqe); int mthca_alloc_srq(struct mthca_dev *dev, struct mthca_pd *pd, struct ib_srq_attr *attr, struct mthca_srq *srq); void mthca_free_srq(struct mthca_dev *dev, struct mthca_srq *srq); int mthca_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr, enum ib_srq_attr_mask attr_mask); +int mthca_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr); void mthca_srq_event(struct mthca_dev *dev, u32 srqn, enum ib_event_type event_type); void mthca_free_srq_wqe(struct mthca_srq *srq, u32 wqe_addr); @@ -486,6 +502,8 @@ int mthca_arbel_post_srq_recv(struct ib_srq *srq, struct ib_recv_wr *wr, void mthca_qp_event(struct mthca_dev *dev, u32 qpn, enum ib_event_type event_type); +int mthca_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr_mask, + struct ib_qp_init_attr *qp_init_attr); int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask); int mthca_tavor_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, struct ib_send_wr **bad_wr); @@ -495,8 +513,8 @@ int mthca_arbel_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, struct ib_send_wr **bad_wr); int mthca_arbel_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr, struct ib_recv_wr **bad_wr); -int mthca_free_err_wqe(struct mthca_dev *dev, struct mthca_qp *qp, int is_send, - int index, int *dbd, __be32 *new_wqe); +void mthca_free_err_wqe(struct mthca_dev *dev, struct mthca_qp *qp, int is_send, + int index, int *dbd, __be32 *new_wqe); int mthca_alloc_qp(struct mthca_dev *dev, struct mthca_pd *pd, struct mthca_cq *send_cq, @@ -522,6 +540,7 @@ int mthca_create_ah(struct mthca_dev *dev, int mthca_destroy_ah(struct mthca_dev *dev, struct mthca_ah *ah); int mthca_read_ah(struct mthca_dev *dev, struct mthca_ah *ah, struct ib_ud_header *header); +int mthca_ah_query(struct ib_ah *ibah, struct ib_ah_attr *attr); int mthca_ah_grh_present(struct mthca_ah *ah); int mthca_multicast_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid); diff --git a/drivers/infiniband/hw/mthca/mthca_eq.c b/drivers/infiniband/hw/mthca/mthca_eq.c index 2eabb27..cbdc348 100644 --- a/drivers/infiniband/hw/mthca/mthca_eq.c +++ b/drivers/infiniband/hw/mthca/mthca_eq.c @@ -497,7 +497,7 @@ static int __devinit mthca_create_eq(struct mthca_dev *dev, eq->dev = dev; eq->nent = roundup_pow_of_two(max(nent, 2)); - npages = ALIGN(eq->nent * MTHCA_EQ_ENTRY_SIZE, PAGE_SIZE) / PAGE_SIZE; + npages = ALIGN(eq->nent * MTHCA_EQ_ENTRY_SIZE, PAGE_SIZE) / PAGE_SIZE; eq->page_list = kmalloc(npages * sizeof *eq->page_list, GFP_KERNEL); @@ -825,7 +825,7 @@ void __devexit mthca_unmap_eq_icm(struct mthca_dev *dev) { u8 status; - mthca_UNMAP_ICM(dev, dev->eq_table.icm_virt, PAGE_SIZE / 4096, &status); + mthca_UNMAP_ICM(dev, dev->eq_table.icm_virt, 1, &status); pci_unmap_page(dev->pdev, dev->eq_table.icm_dma, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); __free_page(dev->eq_table.icm_page); @@ -928,7 +928,7 @@ int __devinit mthca_init_eq_table(struct mthca_dev *dev) mthca_warn(dev, "MAP_EQ for cmd EQ %d returned status 0x%02x\n", dev->eq_table.eq[MTHCA_EQ_CMD].eqn, status); - for (i = 0; i < MTHCA_EQ_CMD; ++i) + for (i = 0; i < MTHCA_NUM_EQ; ++i) if (mthca_is_memfree(dev)) arbel_eq_req_not(dev, dev->eq_table.eq[i].eqn_mask); else diff --git a/drivers/infiniband/hw/mthca/mthca_mad.c b/drivers/infiniband/hw/mthca/mthca_mad.c index 1229c60..4ace6a3 100644 --- a/drivers/infiniband/hw/mthca/mthca_mad.c +++ b/drivers/infiniband/hw/mthca/mthca_mad.c @@ -109,6 +109,19 @@ static void smp_snoop(struct ib_device *ibdev, } } +static void node_desc_override(struct ib_device *dev, + struct ib_mad *mad) +{ + if ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED || + mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) && + mad->mad_hdr.method == IB_MGMT_METHOD_GET_RESP && + mad->mad_hdr.attr_id == IB_SMP_ATTR_NODE_DESC) { + mutex_lock(&to_mdev(dev)->cap_mask_mutex); + memcpy(((struct ib_smp *) mad)->data, dev->node_desc, 64); + mutex_unlock(&to_mdev(dev)->cap_mask_mutex); + } +} + static void forward_trap(struct mthca_dev *dev, u8 port_num, struct ib_mad *mad) @@ -207,8 +220,10 @@ int mthca_process_mad(struct ib_device *ibdev, return IB_MAD_RESULT_FAILURE; } - if (!out_mad->mad_hdr.status) + if (!out_mad->mad_hdr.status) { smp_snoop(ibdev, port_num, in_mad); + node_desc_override(ibdev, out_mad); + } /* set return bit in status of directed route responses */ if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) diff --git a/drivers/infiniband/hw/mthca/mthca_main.c b/drivers/infiniband/hw/mthca/mthca_main.c index 9c849d2..266f347 100644 --- a/drivers/infiniband/hw/mthca/mthca_main.c +++ b/drivers/infiniband/hw/mthca/mthca_main.c @@ -935,13 +935,19 @@ enum { static struct { u64 latest_fw; - int is_memfree; - int is_pcie; + u32 flags; } mthca_hca_table[] = { - [TAVOR] = { .latest_fw = MTHCA_FW_VER(3, 3, 3), .is_memfree = 0, .is_pcie = 0 }, - [ARBEL_COMPAT] = { .latest_fw = MTHCA_FW_VER(4, 7, 0), .is_memfree = 0, .is_pcie = 1 }, - [ARBEL_NATIVE] = { .latest_fw = MTHCA_FW_VER(5, 1, 0), .is_memfree = 1, .is_pcie = 1 }, - [SINAI] = { .latest_fw = MTHCA_FW_VER(1, 0, 1), .is_memfree = 1, .is_pcie = 1 } + [TAVOR] = { .latest_fw = MTHCA_FW_VER(3, 4, 0), + .flags = 0 }, + [ARBEL_COMPAT] = { .latest_fw = MTHCA_FW_VER(4, 7, 400), + .flags = MTHCA_FLAG_PCIE }, + [ARBEL_NATIVE] = { .latest_fw = MTHCA_FW_VER(5, 1, 0), + .flags = MTHCA_FLAG_MEMFREE | + MTHCA_FLAG_PCIE }, + [SINAI] = { .latest_fw = MTHCA_FW_VER(1, 0, 800), + .flags = MTHCA_FLAG_MEMFREE | + MTHCA_FLAG_PCIE | + MTHCA_FLAG_SINAI_OPT } }; static int __devinit mthca_init_one(struct pci_dev *pdev, @@ -1031,12 +1037,9 @@ static int __devinit mthca_init_one(struct pci_dev *pdev, mdev->pdev = pdev; + mdev->mthca_flags = mthca_hca_table[id->driver_data].flags; if (ddr_hidden) mdev->mthca_flags |= MTHCA_FLAG_DDR_HIDDEN; - if (mthca_hca_table[id->driver_data].is_memfree) - mdev->mthca_flags |= MTHCA_FLAG_MEMFREE; - if (mthca_hca_table[id->driver_data].is_pcie) - mdev->mthca_flags |= MTHCA_FLAG_PCIE; /* * Now reset the HCA before we touch the PCI capabilities or diff --git a/drivers/infiniband/hw/mthca/mthca_mcg.c b/drivers/infiniband/hw/mthca/mthca_mcg.c index 321f11e..9965bda 100644 --- a/drivers/infiniband/hw/mthca/mthca_mcg.c +++ b/drivers/infiniband/hw/mthca/mthca_mcg.c @@ -187,7 +187,7 @@ int mthca_multicast_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) for (i = 0; i < MTHCA_QP_PER_MGM; ++i) if (mgm->qp[i] == cpu_to_be32(ibqp->qp_num | (1 << 31))) { - mthca_dbg(dev, "QP %06x already a member of MGM\n", + mthca_dbg(dev, "QP %06x already a member of MGM\n", ibqp->qp_num); err = 0; goto out; diff --git a/drivers/infiniband/hw/mthca/mthca_memfree.c b/drivers/infiniband/hw/mthca/mthca_memfree.c index d709cb1..15cc2f6 100644 --- a/drivers/infiniband/hw/mthca/mthca_memfree.c +++ b/drivers/infiniband/hw/mthca/mthca_memfree.c @@ -202,7 +202,8 @@ void mthca_table_put(struct mthca_dev *dev, struct mthca_icm_table *table, int o if (--table->icm[i]->refcount == 0) { mthca_UNMAP_ICM(dev, table->virt + i * MTHCA_TABLE_CHUNK_SIZE, - MTHCA_TABLE_CHUNK_SIZE >> 12, &status); + MTHCA_TABLE_CHUNK_SIZE / MTHCA_ICM_PAGE_SIZE, + &status); mthca_free_icm(dev, table->icm[i]); table->icm[i] = NULL; } @@ -336,7 +337,8 @@ err: for (i = 0; i < num_icm; ++i) if (table->icm[i]) { mthca_UNMAP_ICM(dev, virt + i * MTHCA_TABLE_CHUNK_SIZE, - MTHCA_TABLE_CHUNK_SIZE >> 12, &status); + MTHCA_TABLE_CHUNK_SIZE / MTHCA_ICM_PAGE_SIZE, + &status); mthca_free_icm(dev, table->icm[i]); } @@ -353,7 +355,8 @@ void mthca_free_icm_table(struct mthca_dev *dev, struct mthca_icm_table *table) for (i = 0; i < table->num_icm; ++i) if (table->icm[i]) { mthca_UNMAP_ICM(dev, table->virt + i * MTHCA_TABLE_CHUNK_SIZE, - MTHCA_TABLE_CHUNK_SIZE >> 12, &status); + MTHCA_TABLE_CHUNK_SIZE / MTHCA_ICM_PAGE_SIZE, + &status); mthca_free_icm(dev, table->icm[i]); } @@ -364,7 +367,7 @@ static u64 mthca_uarc_virt(struct mthca_dev *dev, struct mthca_uar *uar, int pag { return dev->uar_table.uarc_base + uar->index * dev->uar_table.uarc_size + - page * 4096; + page * MTHCA_ICM_PAGE_SIZE; } int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar, @@ -401,7 +404,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar, if (ret < 0) goto out; - db_tab->page[i].mem.length = 4096; + db_tab->page[i].mem.length = MTHCA_ICM_PAGE_SIZE; db_tab->page[i].mem.offset = uaddr & ~PAGE_MASK; ret = pci_map_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE); @@ -455,7 +458,7 @@ struct mthca_user_db_table *mthca_init_user_db_tab(struct mthca_dev *dev) if (!mthca_is_memfree(dev)) return NULL; - npages = dev->uar_table.uarc_size / 4096; + npages = dev->uar_table.uarc_size / MTHCA_ICM_PAGE_SIZE; db_tab = kmalloc(sizeof *db_tab + npages * sizeof *db_tab->page, GFP_KERNEL); if (!db_tab) return ERR_PTR(-ENOMEM); @@ -478,7 +481,7 @@ void mthca_cleanup_user_db_tab(struct mthca_dev *dev, struct mthca_uar *uar, if (!mthca_is_memfree(dev)) return; - for (i = 0; i < dev->uar_table.uarc_size / 4096; ++i) { + for (i = 0; i < dev->uar_table.uarc_size / MTHCA_ICM_PAGE_SIZE; ++i) { if (db_tab->page[i].uvirt) { mthca_UNMAP_ICM(dev, mthca_uarc_virt(dev, uar, i), 1, &status); pci_unmap_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE); @@ -551,20 +554,20 @@ int mthca_alloc_db(struct mthca_dev *dev, enum mthca_db_type type, page = dev->db_tab->page + end; alloc: - page->db_rec = dma_alloc_coherent(&dev->pdev->dev, 4096, + page->db_rec = dma_alloc_coherent(&dev->pdev->dev, MTHCA_ICM_PAGE_SIZE, &page->mapping, GFP_KERNEL); if (!page->db_rec) { ret = -ENOMEM; goto out; } - memset(page->db_rec, 0, 4096); + memset(page->db_rec, 0, MTHCA_ICM_PAGE_SIZE); ret = mthca_MAP_ICM_page(dev, page->mapping, mthca_uarc_virt(dev, &dev->driver_uar, i), &status); if (!ret && status) ret = -EINVAL; if (ret) { - dma_free_coherent(&dev->pdev->dev, 4096, + dma_free_coherent(&dev->pdev->dev, MTHCA_ICM_PAGE_SIZE, page->db_rec, page->mapping); goto out; } @@ -612,7 +615,7 @@ void mthca_free_db(struct mthca_dev *dev, int type, int db_index) i >= dev->db_tab->max_group1 - 1) { mthca_UNMAP_ICM(dev, mthca_uarc_virt(dev, &dev->driver_uar, i), 1, &status); - dma_free_coherent(&dev->pdev->dev, 4096, + dma_free_coherent(&dev->pdev->dev, MTHCA_ICM_PAGE_SIZE, page->db_rec, page->mapping); page->db_rec = NULL; @@ -640,7 +643,7 @@ int mthca_init_db_tab(struct mthca_dev *dev) mutex_init(&dev->db_tab->mutex); - dev->db_tab->npages = dev->uar_table.uarc_size / 4096; + dev->db_tab->npages = dev->uar_table.uarc_size / MTHCA_ICM_PAGE_SIZE; dev->db_tab->max_group1 = 0; dev->db_tab->min_group2 = dev->db_tab->npages - 1; @@ -681,7 +684,7 @@ void mthca_cleanup_db_tab(struct mthca_dev *dev) mthca_UNMAP_ICM(dev, mthca_uarc_virt(dev, &dev->driver_uar, i), 1, &status); - dma_free_coherent(&dev->pdev->dev, 4096, + dma_free_coherent(&dev->pdev->dev, MTHCA_ICM_PAGE_SIZE, dev->db_tab->page[i].db_rec, dev->db_tab->page[i].mapping); } diff --git a/drivers/infiniband/hw/mthca/mthca_memfree.h b/drivers/infiniband/hw/mthca/mthca_memfree.h index 36f1141..6d42947 100644 --- a/drivers/infiniband/hw/mthca/mthca_memfree.h +++ b/drivers/infiniband/hw/mthca/mthca_memfree.h @@ -45,6 +45,12 @@ ((256 - sizeof (struct list_head) - 2 * sizeof (int)) / \ (sizeof (struct scatterlist))) +enum { + MTHCA_ICM_PAGE_SHIFT = 12, + MTHCA_ICM_PAGE_SIZE = 1 << MTHCA_ICM_PAGE_SHIFT, + MTHCA_DB_REC_PER_PAGE = MTHCA_ICM_PAGE_SIZE / 8 +}; + struct mthca_icm_chunk { struct list_head list; int npages; @@ -131,10 +137,6 @@ static inline unsigned long mthca_icm_size(struct mthca_icm_iter *iter) return sg_dma_len(&iter->chunk->mem[iter->page_idx]); } -enum { - MTHCA_DB_REC_PER_PAGE = 4096 / 8 -}; - struct mthca_db_page { DECLARE_BITMAP(used, MTHCA_DB_REC_PER_PAGE); __be64 *db_rec; diff --git a/drivers/infiniband/hw/mthca/mthca_mr.c b/drivers/infiniband/hw/mthca/mthca_mr.c index e995e2a..698b621 100644 --- a/drivers/infiniband/hw/mthca/mthca_mr.c +++ b/drivers/infiniband/hw/mthca/mthca_mr.c @@ -76,6 +76,8 @@ struct mthca_mpt_entry { #define MTHCA_MPT_STATUS_SW 0xF0 #define MTHCA_MPT_STATUS_HW 0x00 +#define SINAI_FMR_KEY_INC 0x1000000 + /* * Buddy allocator for MTT segments (currently not very efficient * since it doesn't keep a free list and just searches linearly @@ -330,6 +332,14 @@ static inline u32 key_to_hw_index(struct mthca_dev *dev, u32 key) return tavor_key_to_hw_index(key); } +static inline u32 adjust_key(struct mthca_dev *dev, u32 key) +{ + if (dev->mthca_flags & MTHCA_FLAG_SINAI_OPT) + return ((key << 20) & 0x800000) | (key & 0x7fffff); + else + return key; +} + int mthca_mr_alloc(struct mthca_dev *dev, u32 pd, int buffer_size_shift, u64 iova, u64 total_size, u32 access, struct mthca_mr *mr) { @@ -340,13 +350,12 @@ int mthca_mr_alloc(struct mthca_dev *dev, u32 pd, int buffer_size_shift, int err; u8 status; - might_sleep(); - WARN_ON(buffer_size_shift >= 32); key = mthca_alloc(&dev->mr_table.mpt_alloc); if (key == -1) return -ENOMEM; + key = adjust_key(dev, key); mr->ibmr.rkey = mr->ibmr.lkey = hw_index_to_key(dev, key); if (mthca_is_memfree(dev)) { @@ -467,8 +476,6 @@ void mthca_free_mr(struct mthca_dev *dev, struct mthca_mr *mr) int err; u8 status; - might_sleep(); - err = mthca_HW2SW_MPT(dev, NULL, key_to_hw_index(dev, mr->ibmr.lkey) & (dev->limits.num_mpts - 1), @@ -495,9 +502,7 @@ int mthca_fmr_alloc(struct mthca_dev *dev, u32 pd, int err = -ENOMEM; int i; - might_sleep(); - - if (mr->attr.page_size < 12 || mr->attr.page_size >= 32) + if (mr->attr.page_shift < 12 || mr->attr.page_shift >= 32) return -EINVAL; /* For Arbel, all MTTs must fit in the same page. */ @@ -510,6 +515,7 @@ int mthca_fmr_alloc(struct mthca_dev *dev, u32 pd, key = mthca_alloc(&dev->mr_table.mpt_alloc); if (key == -1) return -ENOMEM; + key = adjust_key(dev, key); idx = key & (dev->limits.num_mpts - 1); mr->ibmr.rkey = mr->ibmr.lkey = hw_index_to_key(dev, key); @@ -523,7 +529,7 @@ int mthca_fmr_alloc(struct mthca_dev *dev, u32 pd, BUG_ON(!mr->mem.arbel.mpt); } else mr->mem.tavor.mpt = dev->mr_table.tavor_fmr.mpt_base + - sizeof *(mr->mem.tavor.mpt) * idx; + sizeof *(mr->mem.tavor.mpt) * idx; mr->mtt = __mthca_alloc_mtt(dev, list_len, dev->mr_table.fmr_mtt_buddy); if (IS_ERR(mr->mtt)) @@ -549,7 +555,7 @@ int mthca_fmr_alloc(struct mthca_dev *dev, u32 pd, MTHCA_MPT_FLAG_REGION | access); - mpt_entry->page_size = cpu_to_be32(mr->attr.page_size - 12); + mpt_entry->page_size = cpu_to_be32(mr->attr.page_shift - 12); mpt_entry->key = cpu_to_be32(key); mpt_entry->pd = cpu_to_be32(pd); memset(&mpt_entry->start, 0, @@ -617,7 +623,7 @@ static inline int mthca_check_fmr(struct mthca_fmr *fmr, u64 *page_list, if (list_len > fmr->attr.max_pages) return -EINVAL; - page_mask = (1 << fmr->attr.page_size) - 1; + page_mask = (1 << fmr->attr.page_shift) - 1; /* We are getting page lists, so va must be page aligned. */ if (iova & page_mask) @@ -665,7 +671,7 @@ int mthca_tavor_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list, } mpt_entry.lkey = cpu_to_be32(key); - mpt_entry.length = cpu_to_be64(list_len * (1ull << fmr->attr.page_size)); + mpt_entry.length = cpu_to_be64(list_len * (1ull << fmr->attr.page_shift)); mpt_entry.start = cpu_to_be64(iova); __raw_writel((__force u32) mpt_entry.lkey, &fmr->mem.tavor.mpt->key); @@ -693,7 +699,10 @@ int mthca_arbel_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list, ++fmr->maps; key = arbel_key_to_hw_index(fmr->ibmr.lkey); - key += dev->limits.num_mpts; + if (dev->mthca_flags & MTHCA_FLAG_SINAI_OPT) + key += SINAI_FMR_KEY_INC; + else + key += dev->limits.num_mpts; fmr->ibmr.lkey = fmr->ibmr.rkey = arbel_hw_index_to_key(key); *(u8 *) fmr->mem.arbel.mpt = MTHCA_MPT_STATUS_SW; @@ -706,7 +715,7 @@ int mthca_arbel_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list, fmr->mem.arbel.mpt->key = cpu_to_be32(key); fmr->mem.arbel.mpt->lkey = cpu_to_be32(key); - fmr->mem.arbel.mpt->length = cpu_to_be64(list_len * (1ull << fmr->attr.page_size)); + fmr->mem.arbel.mpt->length = cpu_to_be64(list_len * (1ull << fmr->attr.page_shift)); fmr->mem.arbel.mpt->start = cpu_to_be64(iova); wmb(); @@ -766,6 +775,9 @@ int __devinit mthca_init_mr_table(struct mthca_dev *dev) else dev->mthca_flags |= MTHCA_FLAG_FMR; + if (dev->mthca_flags & MTHCA_FLAG_SINAI_OPT) + mthca_dbg(dev, "Memory key throughput optimization activated.\n"); + err = mthca_buddy_init(&dev->mr_table.mtt_buddy, fls(dev->limits.num_mtt_segs - 1)); @@ -785,7 +797,7 @@ int __devinit mthca_init_mr_table(struct mthca_dev *dev) } dev->mr_table.tavor_fmr.mpt_base = - ioremap(dev->mr_table.mpt_base, + ioremap(dev->mr_table.mpt_base, (1 << i) * sizeof (struct mthca_mpt_entry)); if (!dev->mr_table.tavor_fmr.mpt_base) { @@ -813,7 +825,7 @@ int __devinit mthca_init_mr_table(struct mthca_dev *dev) goto err_reserve_fmr; dev->mr_table.fmr_mtt_buddy = - &dev->mr_table.tavor_fmr.mtt_buddy; + &dev->mr_table.tavor_fmr.mtt_buddy; } else dev->mr_table.fmr_mtt_buddy = &dev->mr_table.mtt_buddy; diff --git a/drivers/infiniband/hw/mthca/mthca_pd.c b/drivers/infiniband/hw/mthca/mthca_pd.c index 3dbf06a..105fc5f 100644 --- a/drivers/infiniband/hw/mthca/mthca_pd.c +++ b/drivers/infiniband/hw/mthca/mthca_pd.c @@ -43,8 +43,6 @@ int mthca_pd_alloc(struct mthca_dev *dev, int privileged, struct mthca_pd *pd) { int err = 0; - might_sleep(); - pd->privileged = privileged; atomic_set(&pd->sqp_count, 0); @@ -66,7 +64,6 @@ int mthca_pd_alloc(struct mthca_dev *dev, int privileged, struct mthca_pd *pd) void mthca_pd_free(struct mthca_dev *dev, struct mthca_pd *pd) { - might_sleep(); if (pd->privileged) mthca_free_mr(dev, &pd->ntmr); mthca_free(&dev->pd_table.alloc, pd->pd_num); diff --git a/drivers/infiniband/hw/mthca/mthca_profile.c b/drivers/infiniband/hw/mthca/mthca_profile.c index 08a9093..58d44aa 100644 --- a/drivers/infiniband/hw/mthca/mthca_profile.c +++ b/drivers/infiniband/hw/mthca/mthca_profile.c @@ -152,7 +152,7 @@ u64 mthca_make_profile(struct mthca_dev *dev, } if (total_size > mem_avail) { mthca_err(dev, "Profile requires 0x%llx bytes; " - "won't in 0x%llx bytes of context memory.\n", + "won't fit in 0x%llx bytes of context memory.\n", (unsigned long long) total_size, (unsigned long long) mem_avail); kfree(profile); @@ -262,6 +262,14 @@ u64 mthca_make_profile(struct mthca_dev *dev, */ dev->limits.num_pds = MTHCA_NUM_PDS; + if (dev->mthca_flags & MTHCA_FLAG_SINAI_OPT && + init_hca->log_mpt_sz > 23) { + mthca_warn(dev, "MPT table too large (requested size 2^%d >= 2^24)\n", + init_hca->log_mpt_sz); + mthca_warn(dev, "Disabling memory key throughput optimization.\n"); + dev->mthca_flags &= ~MTHCA_FLAG_SINAI_OPT; + } + /* * For Tavor, FMRs use ioremapped PCI memory. For 32 bit * systems it may use too much vmalloc space to map all MTT diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c index e88e39a..2c250bc 100644 --- a/drivers/infiniband/hw/mthca/mthca_provider.c +++ b/drivers/infiniband/hw/mthca/mthca_provider.c @@ -1,7 +1,7 @@ /* * Copyright (c) 2004, 2005 Topspin Communications. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. - * Copyright (c) 2005 Cisco Systems. All rights reserved. + * Copyright (c) 2005, 2006 Cisco Systems. All rights reserved. * Copyright (c) 2005 Mellanox Technologies. All rights reserved. * Copyright (c) 2004 Voltaire, Inc. All rights reserved. * @@ -108,12 +108,12 @@ static int mthca_query_device(struct ib_device *ibdev, props->max_srq_wr = mdev->limits.max_srq_wqes; props->max_srq_sge = mdev->limits.max_sg; props->local_ca_ack_delay = mdev->limits.local_ca_ack_delay; - props->atomic_cap = mdev->limits.flags & DEV_LIM_FLAG_ATOMIC ? + props->atomic_cap = mdev->limits.flags & DEV_LIM_FLAG_ATOMIC ? IB_ATOMIC_HCA : IB_ATOMIC_NONE; props->max_pkeys = mdev->limits.pkey_table_len; props->max_mcast_grp = mdev->limits.num_mgms + mdev->limits.num_amgms; props->max_mcast_qp_attach = MTHCA_QP_PER_MGM; - props->max_total_mcast_qp_attach = props->max_mcast_qp_attach * + props->max_total_mcast_qp_attach = props->max_mcast_qp_attach * props->max_mcast_grp; err = 0; @@ -176,6 +176,23 @@ static int mthca_query_port(struct ib_device *ibdev, return err; } +static int mthca_modify_device(struct ib_device *ibdev, + int mask, + struct ib_device_modify *props) +{ + if (mask & ~IB_DEVICE_MODIFY_NODE_DESC) + return -EOPNOTSUPP; + + if (mask & IB_DEVICE_MODIFY_NODE_DESC) { + if (mutex_lock_interruptible(&to_mdev(ibdev)->cap_mask_mutex)) + return -ERESTARTSYS; + memcpy(ibdev->node_desc, props->node_desc, 64); + mutex_unlock(&to_mdev(ibdev)->cap_mask_mutex); + } + + return 0; +} + static int mthca_modify_port(struct ib_device *ibdev, u8 port, int port_modify_mask, struct ib_port_modify *props) @@ -669,9 +686,9 @@ static struct ib_cq *mthca_create_cq(struct ib_device *ibdev, int entries, } if (context) { - cq->mr.ibmr.lkey = ucmd.lkey; - cq->set_ci_db_index = ucmd.set_db_index; - cq->arm_db_index = ucmd.arm_db_index; + cq->buf.mr.ibmr.lkey = ucmd.lkey; + cq->set_ci_db_index = ucmd.set_db_index; + cq->arm_db_index = ucmd.arm_db_index; } for (nent = 1; nent <= entries; nent <<= 1) @@ -689,6 +706,8 @@ static struct ib_cq *mthca_create_cq(struct ib_device *ibdev, int entries, goto err_free; } + cq->resize_buf = NULL; + return &cq->ibcq; err_free: @@ -707,6 +726,121 @@ err_unmap_set: return ERR_PTR(err); } +static int mthca_alloc_resize_buf(struct mthca_dev *dev, struct mthca_cq *cq, + int entries) +{ + int ret; + + spin_lock_irq(&cq->lock); + if (cq->resize_buf) { + ret = -EBUSY; + goto unlock; + } + + cq->resize_buf = kmalloc(sizeof *cq->resize_buf, GFP_ATOMIC); + if (!cq->resize_buf) { + ret = -ENOMEM; + goto unlock; + } + + cq->resize_buf->state = CQ_RESIZE_ALLOC; + + ret = 0; + +unlock: + spin_unlock_irq(&cq->lock); + + if (ret) + return ret; + + ret = mthca_alloc_cq_buf(dev, &cq->resize_buf->buf, entries); + if (ret) { + spin_lock_irq(&cq->lock); + kfree(cq->resize_buf); + cq->resize_buf = NULL; + spin_unlock_irq(&cq->lock); + return ret; + } + + cq->resize_buf->cqe = entries - 1; + + spin_lock_irq(&cq->lock); + cq->resize_buf->state = CQ_RESIZE_READY; + spin_unlock_irq(&cq->lock); + + return 0; +} + +static int mthca_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata) +{ + struct mthca_dev *dev = to_mdev(ibcq->device); + struct mthca_cq *cq = to_mcq(ibcq); + struct mthca_resize_cq ucmd; + u32 lkey; + u8 status; + int ret; + + if (entries < 1 || entries > dev->limits.max_cqes) + return -EINVAL; + + entries = roundup_pow_of_two(entries + 1); + if (entries == ibcq->cqe + 1) + return 0; + + if (cq->is_kernel) { + ret = mthca_alloc_resize_buf(dev, cq, entries); + if (ret) + return ret; + lkey = cq->resize_buf->buf.mr.ibmr.lkey; + } else { + if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd)) + return -EFAULT; + lkey = ucmd.lkey; + } + + ret = mthca_RESIZE_CQ(dev, cq->cqn, lkey, long_log2(entries), &status); + if (status) + ret = -EINVAL; + + if (ret) { + if (cq->resize_buf) { + mthca_free_cq_buf(dev, &cq->resize_buf->buf, + cq->resize_buf->cqe); + kfree(cq->resize_buf); + spin_lock_irq(&cq->lock); + cq->resize_buf = NULL; + spin_unlock_irq(&cq->lock); + } + return ret; + } + + if (cq->is_kernel) { + struct mthca_cq_buf tbuf; + int tcqe; + + spin_lock_irq(&cq->lock); + if (cq->resize_buf->state == CQ_RESIZE_READY) { + mthca_cq_resize_copy_cqes(cq); + tbuf = cq->buf; + tcqe = cq->ibcq.cqe; + cq->buf = cq->resize_buf->buf; + cq->ibcq.cqe = cq->resize_buf->cqe; + } else { + tbuf = cq->resize_buf->buf; + tcqe = cq->resize_buf->cqe; + } + + kfree(cq->resize_buf); + cq->resize_buf = NULL; + spin_unlock_irq(&cq->lock); + + mthca_free_cq_buf(dev, &tbuf, tcqe); + } else + ibcq->cqe = entries - 1; + + return 0; +} + static int mthca_destroy_cq(struct ib_cq *cq) { if (cq->uobject) { @@ -1070,6 +1204,20 @@ static int mthca_init_node_data(struct mthca_dev *dev) goto out; init_query_mad(in_mad); + in_mad->attr_id = IB_SMP_ATTR_NODE_DESC; + + err = mthca_MAD_IFC(dev, 1, 1, + 1, NULL, NULL, in_mad, out_mad, + &status); + if (err) + goto out; + if (status) { + err = -EINVAL; + goto out; + } + + memcpy(dev->ib_dev.node_desc, out_mad->data, 64); + in_mad->attr_id = IB_SMP_ATTR_NODE_INFO; err = mthca_MAD_IFC(dev, 1, 1, @@ -1113,14 +1261,17 @@ int mthca_register_device(struct mthca_dev *dev) (1ull << IB_USER_VERBS_CMD_DEREG_MR) | (1ull << IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL) | (1ull << IB_USER_VERBS_CMD_CREATE_CQ) | + (1ull << IB_USER_VERBS_CMD_RESIZE_CQ) | (1ull << IB_USER_VERBS_CMD_DESTROY_CQ) | (1ull << IB_USER_VERBS_CMD_CREATE_QP) | + (1ull << IB_USER_VERBS_CMD_QUERY_QP) | (1ull << IB_USER_VERBS_CMD_MODIFY_QP) | (1ull << IB_USER_VERBS_CMD_DESTROY_QP) | (1ull << IB_USER_VERBS_CMD_ATTACH_MCAST) | (1ull << IB_USER_VERBS_CMD_DETACH_MCAST) | (1ull << IB_USER_VERBS_CMD_CREATE_SRQ) | (1ull << IB_USER_VERBS_CMD_MODIFY_SRQ) | + (1ull << IB_USER_VERBS_CMD_QUERY_SRQ) | (1ull << IB_USER_VERBS_CMD_DESTROY_SRQ); dev->ib_dev.node_type = IB_NODE_CA; dev->ib_dev.phys_port_cnt = dev->limits.num_ports; @@ -1128,6 +1279,7 @@ int mthca_register_device(struct mthca_dev *dev) dev->ib_dev.class_dev.dev = &dev->pdev->dev; dev->ib_dev.query_device = mthca_query_device; dev->ib_dev.query_port = mthca_query_port; + dev->ib_dev.modify_device = mthca_modify_device; dev->ib_dev.modify_port = mthca_modify_port; dev->ib_dev.query_pkey = mthca_query_pkey; dev->ib_dev.query_gid = mthca_query_gid; @@ -1137,11 +1289,13 @@ int mthca_register_device(struct mthca_dev *dev) dev->ib_dev.alloc_pd = mthca_alloc_pd; dev->ib_dev.dealloc_pd = mthca_dealloc_pd; dev->ib_dev.create_ah = mthca_ah_create; + dev->ib_dev.query_ah = mthca_ah_query; dev->ib_dev.destroy_ah = mthca_ah_destroy; if (dev->mthca_flags & MTHCA_FLAG_SRQ) { dev->ib_dev.create_srq = mthca_create_srq; - dev->ib_dev.modify_srq = mthca_modify_srq; + dev->ib_dev.modify_srq = mthca_modify_srq; + dev->ib_dev.query_srq = mthca_query_srq; dev->ib_dev.destroy_srq = mthca_destroy_srq; if (mthca_is_memfree(dev)) @@ -1152,8 +1306,10 @@ int mthca_register_device(struct mthca_dev *dev) dev->ib_dev.create_qp = mthca_create_qp; dev->ib_dev.modify_qp = mthca_modify_qp; + dev->ib_dev.query_qp = mthca_query_qp; dev->ib_dev.destroy_qp = mthca_destroy_qp; dev->ib_dev.create_cq = mthca_create_cq; + dev->ib_dev.resize_cq = mthca_resize_cq; dev->ib_dev.destroy_cq = mthca_destroy_cq; dev->ib_dev.poll_cq = mthca_poll_cq; dev->ib_dev.get_dma_mr = mthca_get_dma_mr; diff --git a/drivers/infiniband/hw/mthca/mthca_provider.h b/drivers/infiniband/hw/mthca/mthca_provider.h index 1e73947..2e7f521 100644 --- a/drivers/infiniband/hw/mthca/mthca_provider.h +++ b/drivers/infiniband/hw/mthca/mthca_provider.h @@ -1,6 +1,6 @@ /* * Copyright (c) 2004 Topspin Communications. All rights reserved. - * Copyright (c) 2005 Cisco Systems. All rights reserved. + * Copyright (c) 2005, 2006 Cisco Systems. All rights reserved. * Copyright (c) 2005 Mellanox Technologies. All rights reserved. * * This software is available to you under a choice of one of two @@ -164,9 +164,11 @@ struct mthca_ah { * - wait_event until ref count is zero * * It is the consumer's responsibilty to make sure that no QP - * operations (WQE posting or state modification) are pending when the + * operations (WQE posting or state modification) are pending when a * QP is destroyed. Also, the consumer must make sure that calls to - * qp_modify are serialized. + * qp_modify are serialized. Similarly, the consumer is responsible + * for ensuring that no CQ resize operations are pending when a CQ + * is destroyed. * * Possible optimizations (wait for profile data to see if/where we * have locks bouncing between CPUs): @@ -176,25 +178,40 @@ struct mthca_ah { * send queue and one for the receive queue) */ +struct mthca_cq_buf { + union mthca_buf queue; + struct mthca_mr mr; + int is_direct; +}; + +struct mthca_cq_resize { + struct mthca_cq_buf buf; + int cqe; + enum { + CQ_RESIZE_ALLOC, + CQ_RESIZE_READY, + CQ_RESIZE_SWAPPED + } state; +}; + struct mthca_cq { - struct ib_cq ibcq; - spinlock_t lock; - atomic_t refcount; - int cqn; - u32 cons_index; - int is_direct; - int is_kernel; + struct ib_cq ibcq; + spinlock_t lock; + atomic_t refcount; + int cqn; + u32 cons_index; + struct mthca_cq_buf buf; + struct mthca_cq_resize *resize_buf; + int is_kernel; /* Next fields are Arbel only */ - int set_ci_db_index; - __be32 *set_ci_db; - int arm_db_index; - __be32 *arm_db; - int arm_sn; + int set_ci_db_index; + __be32 *set_ci_db; + int arm_db_index; + __be32 *arm_db; + int arm_sn; - union mthca_buf queue; - struct mthca_mr mr; - wait_queue_head_t wait; + wait_queue_head_t wait; }; struct mthca_srq { diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c index fba608e..f673c46 100644 --- a/drivers/infiniband/hw/mthca/mthca_qp.c +++ b/drivers/infiniband/hw/mthca/mthca_qp.c @@ -2,7 +2,7 @@ * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Cisco Systems. All rights reserved. * Copyright (c) 2005 Mellanox Technologies. All rights reserved. - * Copyright (c) 2004 Voltaire, Inc. All rights reserved. + * Copyright (c) 2004 Voltaire, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -286,207 +286,6 @@ static int to_mthca_st(int transport) } } -static const struct { - int trans; - u32 req_param[NUM_TRANS]; - u32 opt_param[NUM_TRANS]; -} state_table[IB_QPS_ERR + 1][IB_QPS_ERR + 1] = { - [IB_QPS_RESET] = { - [IB_QPS_RESET] = { .trans = MTHCA_TRANS_ANY2RST }, - [IB_QPS_ERR] = { .trans = MTHCA_TRANS_ANY2ERR }, - [IB_QPS_INIT] = { - .trans = MTHCA_TRANS_RST2INIT, - .req_param = { - [UD] = (IB_QP_PKEY_INDEX | - IB_QP_PORT | - IB_QP_QKEY), - [UC] = (IB_QP_PKEY_INDEX | - IB_QP_PORT | - IB_QP_ACCESS_FLAGS), - [RC] = (IB_QP_PKEY_INDEX | - IB_QP_PORT | - IB_QP_ACCESS_FLAGS), - [MLX] = (IB_QP_PKEY_INDEX | - IB_QP_QKEY), - }, - /* bug-for-bug compatibility with VAPI: */ - .opt_param = { - [MLX] = IB_QP_PORT - } - }, - }, - [IB_QPS_INIT] = { - [IB_QPS_RESET] = { .trans = MTHCA_TRANS_ANY2RST }, - [IB_QPS_ERR] = { .trans = MTHCA_TRANS_ANY2ERR }, - [IB_QPS_INIT] = { - .trans = MTHCA_TRANS_INIT2INIT, - .opt_param = { - [UD] = (IB_QP_PKEY_INDEX | - IB_QP_PORT | - IB_QP_QKEY), - [UC] = (IB_QP_PKEY_INDEX | - IB_QP_PORT | - IB_QP_ACCESS_FLAGS), - [RC] = (IB_QP_PKEY_INDEX | - IB_QP_PORT | - IB_QP_ACCESS_FLAGS), - [MLX] = (IB_QP_PKEY_INDEX | - IB_QP_QKEY), - } - }, - [IB_QPS_RTR] = { - .trans = MTHCA_TRANS_INIT2RTR, - .req_param = { - [UC] = (IB_QP_AV | - IB_QP_PATH_MTU | - IB_QP_DEST_QPN | - IB_QP_RQ_PSN), - [RC] = (IB_QP_AV | - IB_QP_PATH_MTU | - IB_QP_DEST_QPN | - IB_QP_RQ_PSN | - IB_QP_MAX_DEST_RD_ATOMIC | - IB_QP_MIN_RNR_TIMER), - }, - .opt_param = { - [UD] = (IB_QP_PKEY_INDEX | - IB_QP_QKEY), - [UC] = (IB_QP_ALT_PATH | - IB_QP_ACCESS_FLAGS | - IB_QP_PKEY_INDEX), - [RC] = (IB_QP_ALT_PATH | - IB_QP_ACCESS_FLAGS | - IB_QP_PKEY_INDEX), - [MLX] = (IB_QP_PKEY_INDEX | - IB_QP_QKEY), - } - } - }, - [IB_QPS_RTR] = { - [IB_QPS_RESET] = { .trans = MTHCA_TRANS_ANY2RST }, - [IB_QPS_ERR] = { .trans = MTHCA_TRANS_ANY2ERR }, - [IB_QPS_RTS] = { - .trans = MTHCA_TRANS_RTR2RTS, - .req_param = { - [UD] = IB_QP_SQ_PSN, - [UC] = IB_QP_SQ_PSN, - [RC] = (IB_QP_TIMEOUT | - IB_QP_RETRY_CNT | - IB_QP_RNR_RETRY | - IB_QP_SQ_PSN | - IB_QP_MAX_QP_RD_ATOMIC), - [MLX] = IB_QP_SQ_PSN, - }, - .opt_param = { - [UD] = (IB_QP_CUR_STATE | - IB_QP_QKEY), - [UC] = (IB_QP_CUR_STATE | - IB_QP_ALT_PATH | - IB_QP_ACCESS_FLAGS | - IB_QP_PATH_MIG_STATE), - [RC] = (IB_QP_CUR_STATE | - IB_QP_ALT_PATH | - IB_QP_ACCESS_FLAGS | - IB_QP_MIN_RNR_TIMER | - IB_QP_PATH_MIG_STATE), - [MLX] = (IB_QP_CUR_STATE | - IB_QP_QKEY), - } - } - }, - [IB_QPS_RTS] = { - [IB_QPS_RESET] = { .trans = MTHCA_TRANS_ANY2RST }, - [IB_QPS_ERR] = { .trans = MTHCA_TRANS_ANY2ERR }, - [IB_QPS_RTS] = { - .trans = MTHCA_TRANS_RTS2RTS, - .opt_param = { - [UD] = (IB_QP_CUR_STATE | - IB_QP_QKEY), - [UC] = (IB_QP_ACCESS_FLAGS | - IB_QP_ALT_PATH | - IB_QP_PATH_MIG_STATE), - [RC] = (IB_QP_ACCESS_FLAGS | - IB_QP_ALT_PATH | - IB_QP_PATH_MIG_STATE | - IB_QP_MIN_RNR_TIMER), - [MLX] = (IB_QP_CUR_STATE | - IB_QP_QKEY), - } - }, - [IB_QPS_SQD] = { - .trans = MTHCA_TRANS_RTS2SQD, - }, - }, - [IB_QPS_SQD] = { - [IB_QPS_RESET] = { .trans = MTHCA_TRANS_ANY2RST }, - [IB_QPS_ERR] = { .trans = MTHCA_TRANS_ANY2ERR }, - [IB_QPS_RTS] = { - .trans = MTHCA_TRANS_SQD2RTS, - .opt_param = { - [UD] = (IB_QP_CUR_STATE | - IB_QP_QKEY), - [UC] = (IB_QP_CUR_STATE | - IB_QP_ALT_PATH | - IB_QP_ACCESS_FLAGS | - IB_QP_PATH_MIG_STATE), - [RC] = (IB_QP_CUR_STATE | - IB_QP_ALT_PATH | - IB_QP_ACCESS_FLAGS | - IB_QP_MIN_RNR_TIMER | - IB_QP_PATH_MIG_STATE), - [MLX] = (IB_QP_CUR_STATE | - IB_QP_QKEY), - } - }, - [IB_QPS_SQD] = { - .trans = MTHCA_TRANS_SQD2SQD, - .opt_param = { - [UD] = (IB_QP_PKEY_INDEX | - IB_QP_QKEY), - [UC] = (IB_QP_AV | - IB_QP_CUR_STATE | - IB_QP_ALT_PATH | - IB_QP_ACCESS_FLAGS | - IB_QP_PKEY_INDEX | - IB_QP_PATH_MIG_STATE), - [RC] = (IB_QP_AV | - IB_QP_TIMEOUT | - IB_QP_RETRY_CNT | - IB_QP_RNR_RETRY | - IB_QP_MAX_QP_RD_ATOMIC | - IB_QP_MAX_DEST_RD_ATOMIC | - IB_QP_CUR_STATE | - IB_QP_ALT_PATH | - IB_QP_ACCESS_FLAGS | - IB_QP_PKEY_INDEX | - IB_QP_MIN_RNR_TIMER | - IB_QP_PATH_MIG_STATE), - [MLX] = (IB_QP_PKEY_INDEX | - IB_QP_QKEY), - } - } - }, - [IB_QPS_SQE] = { - [IB_QPS_RESET] = { .trans = MTHCA_TRANS_ANY2RST }, - [IB_QPS_ERR] = { .trans = MTHCA_TRANS_ANY2ERR }, - [IB_QPS_RTS] = { - .trans = MTHCA_TRANS_SQERR2RTS, - .opt_param = { - [UD] = (IB_QP_CUR_STATE | - IB_QP_QKEY), - [UC] = (IB_QP_CUR_STATE | - IB_QP_ACCESS_FLAGS), - [MLX] = (IB_QP_CUR_STATE | - IB_QP_QKEY), - } - } - }, - [IB_QPS_ERR] = { - [IB_QPS_RESET] = { .trans = MTHCA_TRANS_ANY2RST }, - [IB_QPS_ERR] = { .trans = MTHCA_TRANS_ANY2ERR } - } -}; - static void store_attrs(struct mthca_sqp *sqp, struct ib_qp_attr *attr, int attr_mask) { @@ -549,6 +348,141 @@ static __be32 get_hw_access_flags(struct mthca_qp *qp, struct ib_qp_attr *attr, return cpu_to_be32(hw_access_flags); } +static inline enum ib_qp_state to_ib_qp_state(int mthca_state) +{ + switch (mthca_state) { + case MTHCA_QP_STATE_RST: return IB_QPS_RESET; + case MTHCA_QP_STATE_INIT: return IB_QPS_INIT; + case MTHCA_QP_STATE_RTR: return IB_QPS_RTR; + case MTHCA_QP_STATE_RTS: return IB_QPS_RTS; + case MTHCA_QP_STATE_DRAINING: + case MTHCA_QP_STATE_SQD: return IB_QPS_SQD; + case MTHCA_QP_STATE_SQE: return IB_QPS_SQE; + case MTHCA_QP_STATE_ERR: return IB_QPS_ERR; + default: return -1; + } +} + +static inline enum ib_mig_state to_ib_mig_state(int mthca_mig_state) +{ + switch (mthca_mig_state) { + case 0: return IB_MIG_ARMED; + case 1: return IB_MIG_REARM; + case 3: return IB_MIG_MIGRATED; + default: return -1; + } +} + +static int to_ib_qp_access_flags(int mthca_flags) +{ + int ib_flags = 0; + + if (mthca_flags & MTHCA_QP_BIT_RRE) + ib_flags |= IB_ACCESS_REMOTE_READ; + if (mthca_flags & MTHCA_QP_BIT_RWE) + ib_flags |= IB_ACCESS_REMOTE_WRITE; + if (mthca_flags & MTHCA_QP_BIT_RAE) + ib_flags |= IB_ACCESS_REMOTE_ATOMIC; + + return ib_flags; +} + +static void to_ib_ah_attr(struct mthca_dev *dev, struct ib_ah_attr *ib_ah_attr, + struct mthca_qp_path *path) +{ + memset(ib_ah_attr, 0, sizeof *path); + ib_ah_attr->port_num = (be32_to_cpu(path->port_pkey) >> 24) & 0x3; + ib_ah_attr->dlid = be16_to_cpu(path->rlid); + ib_ah_attr->sl = be32_to_cpu(path->sl_tclass_flowlabel) >> 28; + ib_ah_attr->src_path_bits = path->g_mylmc & 0x7f; + ib_ah_attr->static_rate = path->static_rate & 0x7; + ib_ah_attr->ah_flags = (path->g_mylmc & (1 << 7)) ? IB_AH_GRH : 0; + if (ib_ah_attr->ah_flags) { + ib_ah_attr->grh.sgid_index = path->mgid_index & (dev->limits.gid_table_len - 1); + ib_ah_attr->grh.hop_limit = path->hop_limit; + ib_ah_attr->grh.traffic_class = + (be32_to_cpu(path->sl_tclass_flowlabel) >> 20) & 0xff; + ib_ah_attr->grh.flow_label = + be32_to_cpu(path->sl_tclass_flowlabel) & 0xfffff; + memcpy(ib_ah_attr->grh.dgid.raw, + path->rgid, sizeof ib_ah_attr->grh.dgid.raw); + } +} + +int mthca_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr_mask, + struct ib_qp_init_attr *qp_init_attr) +{ + struct mthca_dev *dev = to_mdev(ibqp->device); + struct mthca_qp *qp = to_mqp(ibqp); + int err; + struct mthca_mailbox *mailbox; + struct mthca_qp_param *qp_param; + struct mthca_qp_context *context; + int mthca_state; + u8 status; + + mailbox = mthca_alloc_mailbox(dev, GFP_KERNEL); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + + err = mthca_QUERY_QP(dev, qp->qpn, 0, mailbox, &status); + if (err) + goto out; + if (status) { + mthca_warn(dev, "QUERY_QP returned status %02x\n", status); + err = -EINVAL; + goto out; + } + + qp_param = mailbox->buf; + context = &qp_param->context; + mthca_state = be32_to_cpu(context->flags) >> 28; + + qp_attr->qp_state = to_ib_qp_state(mthca_state); + qp_attr->cur_qp_state = qp_attr->qp_state; + qp_attr->path_mtu = context->mtu_msgmax >> 5; + qp_attr->path_mig_state = + to_ib_mig_state((be32_to_cpu(context->flags) >> 11) & 0x3); + qp_attr->qkey = be32_to_cpu(context->qkey); + qp_attr->rq_psn = be32_to_cpu(context->rnr_nextrecvpsn) & 0xffffff; + qp_attr->sq_psn = be32_to_cpu(context->next_send_psn) & 0xffffff; + qp_attr->dest_qp_num = be32_to_cpu(context->remote_qpn) & 0xffffff; + qp_attr->qp_access_flags = + to_ib_qp_access_flags(be32_to_cpu(context->params2)); + qp_attr->cap.max_send_wr = qp->sq.max; + qp_attr->cap.max_recv_wr = qp->rq.max; + qp_attr->cap.max_send_sge = qp->sq.max_gs; + qp_attr->cap.max_recv_sge = qp->rq.max_gs; + qp_attr->cap.max_inline_data = qp->max_inline_data; + + to_ib_ah_attr(dev, &qp_attr->ah_attr, &context->pri_path); + to_ib_ah_attr(dev, &qp_attr->alt_ah_attr, &context->alt_path); + + qp_attr->pkey_index = be32_to_cpu(context->pri_path.port_pkey) & 0x7f; + qp_attr->alt_pkey_index = be32_to_cpu(context->alt_path.port_pkey) & 0x7f; + + /* qp_attr->en_sqd_async_notify is only applicable in modify qp */ + qp_attr->sq_draining = mthca_state == MTHCA_QP_STATE_DRAINING; + + qp_attr->max_rd_atomic = 1 << ((be32_to_cpu(context->params1) >> 21) & 0x7); + + qp_attr->max_dest_rd_atomic = + 1 << ((be32_to_cpu(context->params2) >> 21) & 0x7); + qp_attr->min_rnr_timer = + (be32_to_cpu(context->rnr_nextrecvpsn) >> 24) & 0x1f; + qp_attr->port_num = qp_attr->ah_attr.port_num; + qp_attr->timeout = context->pri_path.ackto >> 3; + qp_attr->retry_cnt = (be32_to_cpu(context->params1) >> 16) & 0x7; + qp_attr->rnr_retry = context->pri_path.rnr_retry >> 5; + qp_attr->alt_port_num = qp_attr->alt_ah_attr.port_num; + qp_attr->alt_timeout = context->alt_path.ackto >> 3; + qp_init_attr->cap = qp_attr->cap; + +out: + mthca_free_mailbox(dev, mailbox); + return err; +} + static void mthca_path_set(struct ib_ah_attr *ah, struct mthca_qp_path *path) { path->g_mylmc = ah->src_path_bits & 0x7f; @@ -559,9 +493,9 @@ static void mthca_path_set(struct ib_ah_attr *ah, struct mthca_qp_path *path) path->g_mylmc |= 1 << 7; path->mgid_index = ah->grh.sgid_index; path->hop_limit = ah->grh.hop_limit; - path->sl_tclass_flowlabel = + path->sl_tclass_flowlabel = cpu_to_be32((ah->sl << 28) | - (ah->grh.traffic_class << 20) | + (ah->grh.traffic_class << 20) | (ah->grh.flow_label)); memcpy(path->rgid, ah->grh.dgid.raw, 16); } else @@ -576,18 +510,12 @@ int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask) struct mthca_mailbox *mailbox; struct mthca_qp_param *qp_param; struct mthca_qp_context *qp_context; - u32 req_param, opt_param; + u32 sqd_event = 0; u8 status; int err; if (attr_mask & IB_QP_CUR_STATE) { - if (attr->cur_qp_state != IB_QPS_RTR && - attr->cur_qp_state != IB_QPS_RTS && - attr->cur_qp_state != IB_QPS_SQD && - attr->cur_qp_state != IB_QPS_SQE) - return -EINVAL; - else - cur_state = attr->cur_qp_state; + cur_state = attr->cur_qp_state; } else { spin_lock_irq(&qp->sq.lock); spin_lock(&qp->rq.lock); @@ -596,44 +524,20 @@ int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask) spin_unlock_irq(&qp->sq.lock); } - if (attr_mask & IB_QP_STATE) { - if (attr->qp_state < 0 || attr->qp_state > IB_QPS_ERR) - return -EINVAL; - new_state = attr->qp_state; - } else - new_state = cur_state; - - if (state_table[cur_state][new_state].trans == MTHCA_TRANS_INVALID) { - mthca_dbg(dev, "Illegal QP transition " - "%d->%d\n", cur_state, new_state); - return -EINVAL; - } - - req_param = state_table[cur_state][new_state].req_param[qp->transport]; - opt_param = state_table[cur_state][new_state].opt_param[qp->transport]; + new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state; - if ((req_param & attr_mask) != req_param) { - mthca_dbg(dev, "QP transition " - "%d->%d missing req attr 0x%08x\n", - cur_state, new_state, - req_param & ~attr_mask); + if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask)) { + mthca_dbg(dev, "Bad QP transition (transport %d) " + "%d->%d with attr 0x%08x\n", + qp->transport, cur_state, new_state, + attr_mask); return -EINVAL; } - if (attr_mask & ~(req_param | opt_param | IB_QP_STATE)) { - mthca_dbg(dev, "QP transition (transport %d) " - "%d->%d has extra attr 0x%08x\n", - qp->transport, - cur_state, new_state, - attr_mask & ~(req_param | opt_param | - IB_QP_STATE)); - return -EINVAL; - } - - if ((attr_mask & IB_QP_PKEY_INDEX) && + if ((attr_mask & IB_QP_PKEY_INDEX) && attr->pkey_index >= dev->limits.pkey_table_len) { - mthca_dbg(dev, "PKey index (%u) too large. max is %d\n", - attr->pkey_index,dev->limits.pkey_table_len-1); + mthca_dbg(dev, "P_Key index (%u) too large. max is %d\n", + attr->pkey_index, dev->limits.pkey_table_len-1); return -EINVAL; } @@ -733,7 +637,7 @@ int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask) if (attr_mask & IB_QP_RNR_RETRY) { qp_context->alt_path.rnr_retry = qp_context->pri_path.rnr_retry = attr->rnr_retry << 5; - qp_param->opt_param_mask |= cpu_to_be32(MTHCA_QP_OPTPAR_RNR_RETRY | + qp_param->opt_param_mask |= cpu_to_be32(MTHCA_QP_OPTPAR_RNR_RETRY | MTHCA_QP_OPTPAR_ALT_RNR_RETRY); } @@ -748,14 +652,20 @@ int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask) } if (attr_mask & IB_QP_ALT_PATH) { + if (attr->alt_pkey_index >= dev->limits.pkey_table_len) { + mthca_dbg(dev, "Alternate P_Key index (%u) too large. max is %d\n", + attr->alt_pkey_index, dev->limits.pkey_table_len-1); + return -EINVAL; + } + if (attr->alt_port_num == 0 || attr->alt_port_num > dev->limits.num_ports) { - mthca_dbg(dev, "Alternate port number (%u) is invalid\n", + mthca_dbg(dev, "Alternate port number (%u) is invalid\n", attr->alt_port_num); return -EINVAL; } mthca_path_set(&attr->alt_ah_attr, &qp_context->alt_path); - qp_context->alt_path.port_pkey |= cpu_to_be32(attr->alt_pkey_index | + qp_context->alt_path.port_pkey |= cpu_to_be32(attr->alt_pkey_index | attr->alt_port_num << 24); qp_context->alt_path.ackto = attr->alt_timeout << 3; qp_param->opt_param_mask |= cpu_to_be32(MTHCA_QP_OPTPAR_ALT_ADDR_PATH); @@ -841,11 +751,16 @@ int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask) qp_context->srqn = cpu_to_be32(1 << 24 | to_msrq(ibqp->srq)->srqn); - err = mthca_MODIFY_QP(dev, state_table[cur_state][new_state].trans, - qp->qpn, 0, mailbox, 0, &status); + if (cur_state == IB_QPS_RTS && new_state == IB_QPS_SQD && + attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY && + attr->en_sqd_async_notify) + sqd_event = 1 << 31; + + err = mthca_MODIFY_QP(dev, cur_state, new_state, qp->qpn, 0, + mailbox, sqd_event, &status); if (status) { - mthca_warn(dev, "modify QP %d returned status %02x.\n", - state_table[cur_state][new_state].trans, status); + mthca_warn(dev, "modify QP %d->%d returned status %02x.\n", + cur_state, new_state, status); err = -EINVAL; } @@ -1078,10 +993,10 @@ static int mthca_map_memfree(struct mthca_dev *dev, if (ret) goto err_qpc; - ret = mthca_table_get(dev, dev->qp_table.rdb_table, - qp->qpn << dev->qp_table.rdb_shift); - if (ret) - goto err_eqpc; + ret = mthca_table_get(dev, dev->qp_table.rdb_table, + qp->qpn << dev->qp_table.rdb_shift); + if (ret) + goto err_eqpc; } @@ -1393,7 +1308,8 @@ void mthca_free_qp(struct mthca_dev *dev, wait_event(qp->wait, !atomic_read(&qp->refcount)); if (qp->state != IB_QPS_RESET) - mthca_MODIFY_QP(dev, MTHCA_TRANS_ANY2RST, qp->qpn, 0, NULL, 0, &status); + mthca_MODIFY_QP(dev, qp->state, IB_QPS_RESET, qp->qpn, 0, + NULL, 0, &status); /* * If this is a userspace QP, the buffers, MR, CQs and so on @@ -1699,7 +1615,9 @@ int mthca_tavor_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, mthca_opcode[wr->opcode]); wmb(); ((struct mthca_next_seg *) prev_wqe)->ee_nds = - cpu_to_be32((size0 ? 0 : MTHCA_NEXT_DBD) | size); + cpu_to_be32((size0 ? 0 : MTHCA_NEXT_DBD) | size | + ((wr->send_flags & IB_SEND_FENCE) ? + MTHCA_NEXT_FENCE : 0)); if (!size0) { size0 = size; @@ -2061,7 +1979,9 @@ int mthca_arbel_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, mthca_opcode[wr->opcode]); wmb(); ((struct mthca_next_seg *) prev_wqe)->ee_nds = - cpu_to_be32(MTHCA_NEXT_DBD | size); + cpu_to_be32(MTHCA_NEXT_DBD | size | + ((wr->send_flags & IB_SEND_FENCE) ? + MTHCA_NEXT_FENCE : 0)); if (!size0) { size0 = size; @@ -2115,7 +2035,7 @@ int mthca_arbel_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr, int i; void *wqe; - spin_lock_irqsave(&qp->rq.lock, flags); + spin_lock_irqsave(&qp->rq.lock, flags); /* XXX check that state is OK to post receive */ @@ -2182,8 +2102,8 @@ out: return err; } -int mthca_free_err_wqe(struct mthca_dev *dev, struct mthca_qp *qp, int is_send, - int index, int *dbd, __be32 *new_wqe) +void mthca_free_err_wqe(struct mthca_dev *dev, struct mthca_qp *qp, int is_send, + int index, int *dbd, __be32 *new_wqe) { struct mthca_next_seg *next; @@ -2193,7 +2113,7 @@ int mthca_free_err_wqe(struct mthca_dev *dev, struct mthca_qp *qp, int is_send, */ if (qp->ibqp.srq) { *new_wqe = 0; - return 0; + return; } if (is_send) @@ -2207,8 +2127,6 @@ int mthca_free_err_wqe(struct mthca_dev *dev, struct mthca_qp *qp, int is_send, (next->ee_nds & cpu_to_be32(0x3f)); else *new_wqe = 0; - - return 0; } int __devinit mthca_init_qp_table(struct mthca_dev *dev) diff --git a/drivers/infiniband/hw/mthca/mthca_srq.c b/drivers/infiniband/hw/mthca/mthca_srq.c index e7e153d..47a6a75 100644 --- a/drivers/infiniband/hw/mthca/mthca_srq.c +++ b/drivers/infiniband/hw/mthca/mthca_srq.c @@ -49,7 +49,8 @@ struct mthca_tavor_srq_context { __be32 state_pd; __be32 lkey; __be32 uar; - __be32 wqe_cnt; + __be16 limit_watermark; + __be16 wqe_cnt; u32 reserved[2]; }; @@ -271,6 +272,9 @@ int mthca_alloc_srq(struct mthca_dev *dev, struct mthca_pd *pd, srq->first_free = 0; srq->last_free = srq->max - 1; + attr->max_wr = (mthca_is_memfree(dev)) ? srq->max - 1 : srq->max; + attr->max_sge = srq->max_gs; + return 0; err_out_free_srq: @@ -339,7 +343,7 @@ void mthca_free_srq(struct mthca_dev *dev, struct mthca_srq *srq) int mthca_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr, enum ib_srq_attr_mask attr_mask) -{ +{ struct mthca_dev *dev = to_mdev(ibsrq->device); struct mthca_srq *srq = to_msrq(ibsrq); int ret; @@ -360,6 +364,41 @@ int mthca_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr, return 0; } +int mthca_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *srq_attr) +{ + struct mthca_dev *dev = to_mdev(ibsrq->device); + struct mthca_srq *srq = to_msrq(ibsrq); + struct mthca_mailbox *mailbox; + struct mthca_arbel_srq_context *arbel_ctx; + struct mthca_tavor_srq_context *tavor_ctx; + u8 status; + int err; + + mailbox = mthca_alloc_mailbox(dev, GFP_KERNEL); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + + err = mthca_QUERY_SRQ(dev, srq->srqn, mailbox, &status); + if (err) + goto out; + + if (mthca_is_memfree(dev)) { + arbel_ctx = mailbox->buf; + srq_attr->srq_limit = be16_to_cpu(arbel_ctx->limit_watermark); + } else { + tavor_ctx = mailbox->buf; + srq_attr->srq_limit = be16_to_cpu(tavor_ctx->limit_watermark); + } + + srq_attr->max_wr = (mthca_is_memfree(dev)) ? srq->max - 1 : srq->max; + srq_attr->max_sge = srq->max_gs; + +out: + mthca_free_mailbox(dev, mailbox); + + return err; +} + void mthca_srq_event(struct mthca_dev *dev, u32 srqn, enum ib_event_type event_type) { diff --git a/drivers/infiniband/hw/mthca/mthca_user.h b/drivers/infiniband/hw/mthca/mthca_user.h index bb015c6..02cc0a7 100644 --- a/drivers/infiniband/hw/mthca/mthca_user.h +++ b/drivers/infiniband/hw/mthca/mthca_user.h @@ -1,6 +1,6 @@ /* * Copyright (c) 2005 Topspin Communications. All rights reserved. - * Copyright (c) 2005 Cisco Systems. All rights reserved. + * Copyright (c) 2005, 2006 Cisco Systems. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -75,6 +75,11 @@ struct mthca_create_cq_resp { __u32 reserved; }; +struct mthca_resize_cq { + __u32 lkey; + __u32 reserved; +}; + struct mthca_create_srq { __u32 lkey; __u32 db_index; |