From 4fc701ead77ede96df3e8b3de13fdf2b1326ee5b Mon Sep 17 00:00:00 2001 From: Haggai Eran Date: Tue, 6 Jan 2015 13:56:02 +0200 Subject: IB/core: Properly handle registration of on-demand paging MRs after dereg When the last on-demand paging MR is released the notifier count is left non-zero so that concurrent page faults will have to abort. If a new MR is then registered, the counter is reset. However, the decision is made to put the new MR in the list waiting for the notifier count to reach zero, before the counter is reset. An invalidation or another MR registration can release the MR to handle page faults, but without such an event the MR can wait forever. The patch fixes this issue by adding a check whether the MR is the first on-demand paging MR when deciding whether it is ready to handle page faults. If it is the first MR, we know that there are no mmu notifiers running in parallel to the registration. Fixes: 882214e2b128 ("IB/core: Implement support for MMU notifiers regarding on demand paging regions") Signed-off-by: Haggai Eran Signed-off-by: Shachar Raindel Signed-off-by: Roland Dreier --- drivers/infiniband/core/umem_odp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/infiniband/core') diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index 6095872549e7..8b8cc6fa0ab0 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -294,7 +294,8 @@ int ib_umem_odp_get(struct ib_ucontext *context, struct ib_umem *umem) if (likely(ib_umem_start(umem) != ib_umem_end(umem))) rbt_ib_umem_insert(&umem->odp_data->interval_tree, &context->umem_tree); - if (likely(!atomic_read(&context->notifier_count))) + if (likely(!atomic_read(&context->notifier_count)) || + context->odp_mrs_count == 1) umem->odp_data->mn_counters_active = true; else list_add(&umem->odp_data->no_private_counters, -- cgit v1.2.3 From 02d1aa7af17ef0e0655745ce32cab369ed040a67 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Sun, 8 Feb 2015 13:28:50 +0200 Subject: IB/core: Add support for extended query device caps Add extensible query device capabilities verb to allow adding new features. ib_uverbs_ex_query_device is added and copy_query_dev_fields is used to copy capability fields to be used by both ib_uverbs_query_device and ib_uverbs_ex_query_device. Following the discussion about this patch [1], the code now validates the command's comp_mask is zero, returning -EINVAL for unknown values, in order to allow extending the verb in the future. The verb also checks the user-space provided response buffer size and only fills in capabilities that will fit in the buffer. In attempt to follow the spirit of presentation [2] by Tzahi Oved that was presented during OpenFabrics Alliance International Developer Workshop 2013, the comp_mask bits will only describe which fields are valid. Furthermore, fields that can simply be cleared when they are not supported, do not require a comp_mask bit at all. The verb returns a response_length field containing the actual number of bytes written by the kernel, so that a newer version running on an older kernel can tell which fields were actually returned. [1] [PATCH v1 0/5] IB/core: extended query device caps cleanup for v3.19 http://thread.gmane.org/gmane.linux.kernel.api/7889/ [2] https://www.openfabrics.org/images/docs/2013_Dev_Workshop/Tues_0423/2013_Workshop_Tues_0830_Tzahi_Oved-verbs_extensions_ofa_2013-tzahio.pdf Signed-off-by: Eli Cohen Signed-off-by: Haggai Eran Reviewed-by: Yann Droneaud Signed-off-by: Roland Dreier --- drivers/infiniband/core/uverbs.h | 1 + drivers/infiniband/core/uverbs_cmd.c | 131 +++++++++++++++++++++++----------- drivers/infiniband/core/uverbs_main.c | 1 + 3 files changed, 92 insertions(+), 41 deletions(-) (limited to 'drivers/infiniband/core') diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h index 643c08a025a5..b716b0815644 100644 --- a/drivers/infiniband/core/uverbs.h +++ b/drivers/infiniband/core/uverbs.h @@ -258,5 +258,6 @@ IB_UVERBS_DECLARE_CMD(close_xrcd); IB_UVERBS_DECLARE_EX_CMD(create_flow); IB_UVERBS_DECLARE_EX_CMD(destroy_flow); +IB_UVERBS_DECLARE_EX_CMD(query_device); #endif /* UVERBS_H */ diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index b7943ff16ed3..8f507538c42b 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -400,6 +400,52 @@ err: return ret; } +static void copy_query_dev_fields(struct ib_uverbs_file *file, + struct ib_uverbs_query_device_resp *resp, + struct ib_device_attr *attr) +{ + resp->fw_ver = attr->fw_ver; + resp->node_guid = file->device->ib_dev->node_guid; + resp->sys_image_guid = attr->sys_image_guid; + resp->max_mr_size = attr->max_mr_size; + resp->page_size_cap = attr->page_size_cap; + resp->vendor_id = attr->vendor_id; + resp->vendor_part_id = attr->vendor_part_id; + resp->hw_ver = attr->hw_ver; + resp->max_qp = attr->max_qp; + resp->max_qp_wr = attr->max_qp_wr; + resp->device_cap_flags = attr->device_cap_flags; + resp->max_sge = attr->max_sge; + resp->max_sge_rd = attr->max_sge_rd; + resp->max_cq = attr->max_cq; + resp->max_cqe = attr->max_cqe; + resp->max_mr = attr->max_mr; + resp->max_pd = attr->max_pd; + resp->max_qp_rd_atom = attr->max_qp_rd_atom; + resp->max_ee_rd_atom = attr->max_ee_rd_atom; + resp->max_res_rd_atom = attr->max_res_rd_atom; + resp->max_qp_init_rd_atom = attr->max_qp_init_rd_atom; + resp->max_ee_init_rd_atom = attr->max_ee_init_rd_atom; + resp->atomic_cap = attr->atomic_cap; + resp->max_ee = attr->max_ee; + resp->max_rdd = attr->max_rdd; + resp->max_mw = attr->max_mw; + resp->max_raw_ipv6_qp = attr->max_raw_ipv6_qp; + resp->max_raw_ethy_qp = attr->max_raw_ethy_qp; + resp->max_mcast_grp = attr->max_mcast_grp; + resp->max_mcast_qp_attach = attr->max_mcast_qp_attach; + resp->max_total_mcast_qp_attach = attr->max_total_mcast_qp_attach; + resp->max_ah = attr->max_ah; + resp->max_fmr = attr->max_fmr; + resp->max_map_per_fmr = attr->max_map_per_fmr; + resp->max_srq = attr->max_srq; + resp->max_srq_wr = attr->max_srq_wr; + resp->max_srq_sge = attr->max_srq_sge; + resp->max_pkeys = attr->max_pkeys; + resp->local_ca_ack_delay = attr->local_ca_ack_delay; + resp->phys_port_cnt = file->device->ib_dev->phys_port_cnt; +} + ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file, const char __user *buf, int in_len, int out_len) @@ -420,47 +466,7 @@ ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file, return ret; memset(&resp, 0, sizeof resp); - - resp.fw_ver = attr.fw_ver; - resp.node_guid = file->device->ib_dev->node_guid; - resp.sys_image_guid = attr.sys_image_guid; - resp.max_mr_size = attr.max_mr_size; - resp.page_size_cap = attr.page_size_cap; - resp.vendor_id = attr.vendor_id; - resp.vendor_part_id = attr.vendor_part_id; - resp.hw_ver = attr.hw_ver; - resp.max_qp = attr.max_qp; - resp.max_qp_wr = attr.max_qp_wr; - resp.device_cap_flags = attr.device_cap_flags; - resp.max_sge = attr.max_sge; - resp.max_sge_rd = attr.max_sge_rd; - resp.max_cq = attr.max_cq; - resp.max_cqe = attr.max_cqe; - resp.max_mr = attr.max_mr; - resp.max_pd = attr.max_pd; - resp.max_qp_rd_atom = attr.max_qp_rd_atom; - resp.max_ee_rd_atom = attr.max_ee_rd_atom; - resp.max_res_rd_atom = attr.max_res_rd_atom; - resp.max_qp_init_rd_atom = attr.max_qp_init_rd_atom; - resp.max_ee_init_rd_atom = attr.max_ee_init_rd_atom; - resp.atomic_cap = attr.atomic_cap; - resp.max_ee = attr.max_ee; - resp.max_rdd = attr.max_rdd; - resp.max_mw = attr.max_mw; - resp.max_raw_ipv6_qp = attr.max_raw_ipv6_qp; - resp.max_raw_ethy_qp = attr.max_raw_ethy_qp; - resp.max_mcast_grp = attr.max_mcast_grp; - resp.max_mcast_qp_attach = attr.max_mcast_qp_attach; - resp.max_total_mcast_qp_attach = attr.max_total_mcast_qp_attach; - resp.max_ah = attr.max_ah; - resp.max_fmr = attr.max_fmr; - resp.max_map_per_fmr = attr.max_map_per_fmr; - resp.max_srq = attr.max_srq; - resp.max_srq_wr = attr.max_srq_wr; - resp.max_srq_sge = attr.max_srq_sge; - resp.max_pkeys = attr.max_pkeys; - resp.local_ca_ack_delay = attr.local_ca_ack_delay; - resp.phys_port_cnt = file->device->ib_dev->phys_port_cnt; + copy_query_dev_fields(file, &resp, &attr); if (copy_to_user((void __user *) (unsigned long) cmd.response, &resp, sizeof resp)) @@ -3287,3 +3293,46 @@ ssize_t ib_uverbs_destroy_srq(struct ib_uverbs_file *file, return ret ? ret : in_len; } + +int ib_uverbs_ex_query_device(struct ib_uverbs_file *file, + struct ib_udata *ucore, + struct ib_udata *uhw) +{ + struct ib_uverbs_ex_query_device_resp resp; + struct ib_uverbs_ex_query_device cmd; + struct ib_device_attr attr; + struct ib_device *device; + int err; + + device = file->device->ib_dev; + if (ucore->inlen < sizeof(cmd)) + return -EINVAL; + + err = ib_copy_from_udata(&cmd, ucore, sizeof(cmd)); + if (err) + return err; + + if (cmd.comp_mask) + return -EINVAL; + + if (cmd.reserved) + return -EINVAL; + + resp.response_length = sizeof(resp); + + if (ucore->outlen < resp.response_length) + return -ENOSPC; + + err = device->query_device(device, &attr); + if (err) + return err; + + copy_query_dev_fields(file, &resp.base, &attr); + resp.comp_mask = 0; + + err = ib_copy_to_udata(ucore, &resp, resp.response_length); + if (err) + return err; + + return 0; +} diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 5db1a8cc388d..259dcc7779f5 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -123,6 +123,7 @@ static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file, struct ib_udata *uhw) = { [IB_USER_VERBS_EX_CMD_CREATE_FLOW] = ib_uverbs_ex_create_flow, [IB_USER_VERBS_EX_CMD_DESTROY_FLOW] = ib_uverbs_ex_destroy_flow, + [IB_USER_VERBS_EX_CMD_QUERY_DEVICE] = ib_uverbs_ex_query_device, }; static void ib_uverbs_add_one(struct ib_device *device); -- cgit v1.2.3 From f4056bfd8ccff4475417078d6e5456dfa1962dd3 Mon Sep 17 00:00:00 2001 From: Haggai Eran Date: Sun, 8 Feb 2015 13:28:51 +0200 Subject: IB/core: Add on demand paging caps to ib_uverbs_ex_query_device Add on-demand paging capabilities reporting to the extended query device verb. Yann Droneaud writes: Note: as offsetof() is used to retrieve the size of the lower chunk of the response, beware that it only works if the upper chunk is right after, without any implicit padding. And, as the size of the latter chunk is added to the base size, implicit padding at the end of the structure is not taken in account. Both point must be taken in account when extending the uverbs functionalities. Signed-off-by: Haggai Eran Reviewed-by: Yann Droneaud Signed-off-by: Roland Dreier --- drivers/infiniband/core/uverbs_cmd.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'drivers/infiniband/core') diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 8f507538c42b..04ca04559ce5 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -3318,7 +3318,7 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file, if (cmd.reserved) return -EINVAL; - resp.response_length = sizeof(resp); + resp.response_length = offsetof(typeof(resp), odp_caps); if (ucore->outlen < resp.response_length) return -ENOSPC; @@ -3330,6 +3330,24 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file, copy_query_dev_fields(file, &resp.base, &attr); resp.comp_mask = 0; + if (ucore->outlen < resp.response_length + sizeof(resp.odp_caps)) + goto end; + +#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING + resp.odp_caps.general_caps = attr.odp_caps.general_caps; + resp.odp_caps.per_transport_caps.rc_odp_caps = + attr.odp_caps.per_transport_caps.rc_odp_caps; + resp.odp_caps.per_transport_caps.uc_odp_caps = + attr.odp_caps.per_transport_caps.uc_odp_caps; + resp.odp_caps.per_transport_caps.ud_odp_caps = + attr.odp_caps.per_transport_caps.ud_odp_caps; + resp.odp_caps.reserved = 0; +#else + memset(&resp.odp_caps, 0, sizeof(resp.odp_caps)); +#endif + resp.response_length += sizeof(resp.odp_caps); + +end: err = ib_copy_to_udata(ucore, &resp, resp.response_length); if (err) return err; -- cgit v1.2.3