From 1543e317f1da31b75942316931e8f491a8920811 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Thu, 04 Jan 2024 10:08:02 +0000
Subject: [PATCH] disable FB
---
kernel/drivers/nvme/target/rdma.c | 724 +++++++++++++++++++++++++++++++++++++++++++------------
1 files changed, 561 insertions(+), 163 deletions(-)
diff --git a/kernel/drivers/nvme/target/rdma.c b/kernel/drivers/nvme/target/rdma.c
index cfd2643..6d5552f 100644
--- a/kernel/drivers/nvme/target/rdma.c
+++ b/kernel/drivers/nvme/target/rdma.c
@@ -1,15 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* NVMe over Fabrics RDMA target.
* Copyright (c) 2015-2016 HGST, a Western Digital Company.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/atomic.h>
@@ -28,6 +20,7 @@
#include <rdma/ib_verbs.h>
#include <rdma/rdma_cm.h>
#include <rdma/rw.h>
+#include <rdma/ib_cm.h>
#include <linux/nvme-rdma.h>
#include "nvmet.h"
@@ -39,6 +32,12 @@
#define NVMET_RDMA_MAX_INLINE_SGE 4
#define NVMET_RDMA_MAX_INLINE_DATA_SIZE max_t(int, SZ_16K, PAGE_SIZE)
+/* Assume mpsmin == device_page_size == 4KB */
+#define NVMET_RDMA_MAX_MDTS 8
+#define NVMET_RDMA_MAX_METADATA_MDTS 5
+
+struct nvmet_rdma_srq;
+
struct nvmet_rdma_cmd {
struct ib_sge sge[NVMET_RDMA_MAX_INLINE_SGE + 1];
struct ib_cqe cqe;
@@ -46,6 +45,7 @@
struct scatterlist inline_sg[NVMET_RDMA_MAX_INLINE_SGE];
struct nvme_command *nvme_cmd;
struct nvmet_rdma_queue *queue;
+ struct nvmet_rdma_srq *nsrq;
};
enum {
@@ -62,6 +62,7 @@
struct nvmet_rdma_queue *queue;
struct ib_cqe read_cqe;
+ struct ib_cqe write_cqe;
struct rdma_rw_ctx rw;
struct nvmet_req req;
@@ -88,6 +89,7 @@
struct ib_cq *cq;
atomic_t sq_wr_avail;
struct nvmet_rdma_device *dev;
+ struct nvmet_rdma_srq *nsrq;
spinlock_t state_lock;
enum nvmet_rdma_queue_state state;
struct nvmet_cq nvme_cq;
@@ -105,17 +107,31 @@
int idx;
int host_qid;
+ int comp_vector;
int recv_queue_size;
int send_queue_size;
struct list_head queue_list;
};
+struct nvmet_rdma_port {
+ struct nvmet_port *nport;
+ struct sockaddr_storage addr;
+ struct rdma_cm_id *cm_id;
+ struct delayed_work repair_work;
+};
+
+struct nvmet_rdma_srq {
+ struct ib_srq *srq;
+ struct nvmet_rdma_cmd *cmds;
+ struct nvmet_rdma_device *ndev;
+};
+
struct nvmet_rdma_device {
struct ib_device *device;
struct ib_pd *pd;
- struct ib_srq *srq;
- struct nvmet_rdma_cmd *srq_cmds;
+ struct nvmet_rdma_srq **srqs;
+ int srq_count;
size_t srq_size;
struct kref ref;
struct list_head entry;
@@ -126,6 +142,16 @@
static bool nvmet_rdma_use_srq;
module_param_named(use_srq, nvmet_rdma_use_srq, bool, 0444);
MODULE_PARM_DESC(use_srq, "Use shared receive queue.");
+
+static int srq_size_set(const char *val, const struct kernel_param *kp);
+static const struct kernel_param_ops srq_size_ops = {
+ .set = srq_size_set,
+ .get = param_get_int,
+};
+
+static int nvmet_rdma_srq_size = 1024;
+module_param_cb(srq_size, &srq_size_ops, &nvmet_rdma_srq_size, 0644);
+MODULE_PARM_DESC(srq_size, "set Shared Receive Queue (SRQ) size, should >= 256 (default: 1024)");
static DEFINE_IDA(nvmet_rdma_queue_ida);
static LIST_HEAD(nvmet_rdma_queue_list);
@@ -138,6 +164,7 @@
static void nvmet_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc);
static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc);
static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc);
+static void nvmet_rdma_write_data_done(struct ib_cq *cq, struct ib_wc *wc);
static void nvmet_rdma_qp_event(struct ib_event *event, void *priv);
static void nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue);
static void nvmet_rdma_free_rsp(struct nvmet_rdma_device *ndev,
@@ -147,15 +174,20 @@
static const struct nvmet_fabrics_ops nvmet_rdma_ops;
+static int srq_size_set(const char *val, const struct kernel_param *kp)
+{
+ int n = 0, ret;
+
+ ret = kstrtoint(val, 10, &n);
+ if (ret != 0 || n < 256)
+ return -EINVAL;
+
+ return param_set_int(val, kp);
+}
+
static int num_pages(int len)
{
return 1 + (((len - 1) & PAGE_MASK) >> PAGE_SHIFT);
-}
-
-/* XXX: really should move to a generic header sooner or later.. */
-static inline u32 get_unaligned_le24(const u8 *p)
-{
- return (u32)p[0] | (u32)p[1] << 8 | (u32)p[2] << 16;
}
static inline bool nvmet_rdma_need_data_in(struct nvmet_rdma_rsp *rsp)
@@ -169,7 +201,7 @@
{
return !nvme_is_write(rsp->req.cmd) &&
rsp->req.transfer_len &&
- !rsp->req.rsp->status &&
+ !rsp->req.cqe->status &&
!(rsp->flags & NVMET_RDMA_REQ_INLINE_DATA);
}
@@ -373,16 +405,18 @@
struct nvmet_rdma_rsp *r)
{
/* NVMe CQE / RDMA SEND */
- r->req.rsp = kmalloc(sizeof(*r->req.rsp), GFP_KERNEL);
- if (!r->req.rsp)
+ r->req.cqe = kmalloc(sizeof(*r->req.cqe), GFP_KERNEL);
+ if (!r->req.cqe)
goto out;
- r->send_sge.addr = ib_dma_map_single(ndev->device, r->req.rsp,
- sizeof(*r->req.rsp), DMA_TO_DEVICE);
+ r->send_sge.addr = ib_dma_map_single(ndev->device, r->req.cqe,
+ sizeof(*r->req.cqe), DMA_TO_DEVICE);
if (ib_dma_mapping_error(ndev->device, r->send_sge.addr))
goto out_free_rsp;
- r->send_sge.length = sizeof(*r->req.rsp);
+ if (!ib_uses_virt_dma(ndev->device))
+ r->req.p2p_client = &ndev->device->dev;
+ r->send_sge.length = sizeof(*r->req.cqe);
r->send_sge.lkey = ndev->pd->local_dma_lkey;
r->send_cqe.done = nvmet_rdma_send_done;
@@ -394,10 +428,13 @@
/* Data In / RDMA READ */
r->read_cqe.done = nvmet_rdma_read_data_done;
+ /* Data Out / RDMA WRITE */
+ r->write_cqe.done = nvmet_rdma_write_data_done;
+
return 0;
out_free_rsp:
- kfree(r->req.rsp);
+ kfree(r->req.cqe);
out:
return -ENOMEM;
}
@@ -406,8 +443,8 @@
struct nvmet_rdma_rsp *r)
{
ib_dma_unmap_single(ndev->device, r->send_sge.addr,
- sizeof(*r->req.rsp), DMA_TO_DEVICE);
- kfree(r->req.rsp);
+ sizeof(*r->req.cqe), DMA_TO_DEVICE);
+ kfree(r->req.cqe);
}
static int
@@ -469,8 +506,8 @@
cmd->sge[0].addr, cmd->sge[0].length,
DMA_FROM_DEVICE);
- if (ndev->srq)
- ret = ib_post_srq_recv(ndev->srq, &cmd->wr, NULL);
+ if (cmd->nsrq)
+ ret = ib_post_srq_recv(cmd->nsrq->srq, &cmd->wr, NULL);
else
ret = ib_post_recv(cmd->queue->qp, &cmd->wr, NULL);
@@ -503,6 +540,129 @@
spin_unlock(&queue->rsp_wr_wait_lock);
}
+static u16 nvmet_rdma_check_pi_status(struct ib_mr *sig_mr)
+{
+ struct ib_mr_status mr_status;
+ int ret;
+ u16 status = 0;
+
+ ret = ib_check_mr_status(sig_mr, IB_MR_CHECK_SIG_STATUS, &mr_status);
+ if (ret) {
+ pr_err("ib_check_mr_status failed, ret %d\n", ret);
+ return NVME_SC_INVALID_PI;
+ }
+
+ if (mr_status.fail_status & IB_MR_CHECK_SIG_STATUS) {
+ switch (mr_status.sig_err.err_type) {
+ case IB_SIG_BAD_GUARD:
+ status = NVME_SC_GUARD_CHECK;
+ break;
+ case IB_SIG_BAD_REFTAG:
+ status = NVME_SC_REFTAG_CHECK;
+ break;
+ case IB_SIG_BAD_APPTAG:
+ status = NVME_SC_APPTAG_CHECK;
+ break;
+ }
+ pr_err("PI error found type %d expected 0x%x vs actual 0x%x\n",
+ mr_status.sig_err.err_type,
+ mr_status.sig_err.expected,
+ mr_status.sig_err.actual);
+ }
+
+ return status;
+}
+
+static void nvmet_rdma_set_sig_domain(struct blk_integrity *bi,
+ struct nvme_command *cmd, struct ib_sig_domain *domain,
+ u16 control, u8 pi_type)
+{
+ domain->sig_type = IB_SIG_TYPE_T10_DIF;
+ domain->sig.dif.bg_type = IB_T10DIF_CRC;
+ domain->sig.dif.pi_interval = 1 << bi->interval_exp;
+ domain->sig.dif.ref_tag = le32_to_cpu(cmd->rw.reftag);
+ if (control & NVME_RW_PRINFO_PRCHK_REF)
+ domain->sig.dif.ref_remap = true;
+
+ domain->sig.dif.app_tag = le16_to_cpu(cmd->rw.apptag);
+ domain->sig.dif.apptag_check_mask = le16_to_cpu(cmd->rw.appmask);
+ domain->sig.dif.app_escape = true;
+ if (pi_type == NVME_NS_DPS_PI_TYPE3)
+ domain->sig.dif.ref_escape = true;
+}
+
+static void nvmet_rdma_set_sig_attrs(struct nvmet_req *req,
+ struct ib_sig_attrs *sig_attrs)
+{
+ struct nvme_command *cmd = req->cmd;
+ u16 control = le16_to_cpu(cmd->rw.control);
+ u8 pi_type = req->ns->pi_type;
+ struct blk_integrity *bi;
+
+ bi = bdev_get_integrity(req->ns->bdev);
+
+ memset(sig_attrs, 0, sizeof(*sig_attrs));
+
+ if (control & NVME_RW_PRINFO_PRACT) {
+ /* for WRITE_INSERT/READ_STRIP no wire domain */
+ sig_attrs->wire.sig_type = IB_SIG_TYPE_NONE;
+ nvmet_rdma_set_sig_domain(bi, cmd, &sig_attrs->mem, control,
+ pi_type);
+ /* Clear the PRACT bit since HCA will generate/verify the PI */
+ control &= ~NVME_RW_PRINFO_PRACT;
+ cmd->rw.control = cpu_to_le16(control);
+ /* PI is added by the HW */
+ req->transfer_len += req->metadata_len;
+ } else {
+ /* for WRITE_PASS/READ_PASS both wire/memory domains exist */
+ nvmet_rdma_set_sig_domain(bi, cmd, &sig_attrs->wire, control,
+ pi_type);
+ nvmet_rdma_set_sig_domain(bi, cmd, &sig_attrs->mem, control,
+ pi_type);
+ }
+
+ if (control & NVME_RW_PRINFO_PRCHK_REF)
+ sig_attrs->check_mask |= IB_SIG_CHECK_REFTAG;
+ if (control & NVME_RW_PRINFO_PRCHK_GUARD)
+ sig_attrs->check_mask |= IB_SIG_CHECK_GUARD;
+ if (control & NVME_RW_PRINFO_PRCHK_APP)
+ sig_attrs->check_mask |= IB_SIG_CHECK_APPTAG;
+}
+
+static int nvmet_rdma_rw_ctx_init(struct nvmet_rdma_rsp *rsp, u64 addr, u32 key,
+ struct ib_sig_attrs *sig_attrs)
+{
+ struct rdma_cm_id *cm_id = rsp->queue->cm_id;
+ struct nvmet_req *req = &rsp->req;
+ int ret;
+
+ if (req->metadata_len)
+ ret = rdma_rw_ctx_signature_init(&rsp->rw, cm_id->qp,
+ cm_id->port_num, req->sg, req->sg_cnt,
+ req->metadata_sg, req->metadata_sg_cnt, sig_attrs,
+ addr, key, nvmet_data_dir(req));
+ else
+ ret = rdma_rw_ctx_init(&rsp->rw, cm_id->qp, cm_id->port_num,
+ req->sg, req->sg_cnt, 0, addr, key,
+ nvmet_data_dir(req));
+
+ return ret;
+}
+
+static void nvmet_rdma_rw_ctx_destroy(struct nvmet_rdma_rsp *rsp)
+{
+ struct rdma_cm_id *cm_id = rsp->queue->cm_id;
+ struct nvmet_req *req = &rsp->req;
+
+ if (req->metadata_len)
+ rdma_rw_ctx_destroy_signature(&rsp->rw, cm_id->qp,
+ cm_id->port_num, req->sg, req->sg_cnt,
+ req->metadata_sg, req->metadata_sg_cnt,
+ nvmet_data_dir(req));
+ else
+ rdma_rw_ctx_destroy(&rsp->rw, cm_id->qp, cm_id->port_num,
+ req->sg, req->sg_cnt, nvmet_data_dir(req));
+}
static void nvmet_rdma_release_rsp(struct nvmet_rdma_rsp *rsp)
{
@@ -510,14 +670,11 @@
atomic_add(1 + rsp->n_rdma, &queue->sq_wr_avail);
- if (rsp->n_rdma) {
- rdma_rw_ctx_destroy(&rsp->rw, queue->qp,
- queue->cm_id->port_num, rsp->req.sg,
- rsp->req.sg_cnt, nvmet_data_dir(&rsp->req));
- }
+ if (rsp->n_rdma)
+ nvmet_rdma_rw_ctx_destroy(rsp);
if (rsp->req.sg != rsp->cmd->inline_sg)
- sgl_free(rsp->req.sg);
+ nvmet_req_free_sgls(&rsp->req);
if (unlikely(!list_empty_careful(&queue->rsp_wr_wait_list)))
nvmet_rdma_process_wr_wait_list(queue);
@@ -543,7 +700,7 @@
{
struct nvmet_rdma_rsp *rsp =
container_of(wc->wr_cqe, struct nvmet_rdma_rsp, send_cqe);
- struct nvmet_rdma_queue *queue = cq->cq_context;
+ struct nvmet_rdma_queue *queue = wc->qp->qp_context;
nvmet_rdma_release_rsp(rsp);
@@ -569,11 +726,16 @@
rsp->send_wr.opcode = IB_WR_SEND;
}
- if (nvmet_rdma_need_data_out(rsp))
- first_wr = rdma_rw_ctx_wrs(&rsp->rw, cm_id->qp,
- cm_id->port_num, NULL, &rsp->send_wr);
- else
+ if (nvmet_rdma_need_data_out(rsp)) {
+ if (rsp->req.metadata_len)
+ first_wr = rdma_rw_ctx_wrs(&rsp->rw, cm_id->qp,
+ cm_id->port_num, &rsp->write_cqe, NULL);
+ else
+ first_wr = rdma_rw_ctx_wrs(&rsp->rw, cm_id->qp,
+ cm_id->port_num, NULL, &rsp->send_wr);
+ } else {
first_wr = &rsp->send_wr;
+ }
nvmet_rdma_post_recv(rsp->queue->dev, rsp->cmd);
@@ -591,16 +753,15 @@
{
struct nvmet_rdma_rsp *rsp =
container_of(wc->wr_cqe, struct nvmet_rdma_rsp, read_cqe);
- struct nvmet_rdma_queue *queue = cq->cq_context;
+ struct nvmet_rdma_queue *queue = wc->qp->qp_context;
+ u16 status = 0;
WARN_ON(rsp->n_rdma <= 0);
atomic_add(rsp->n_rdma, &queue->sq_wr_avail);
- rdma_rw_ctx_destroy(&rsp->rw, queue->qp,
- queue->cm_id->port_num, rsp->req.sg,
- rsp->req.sg_cnt, nvmet_data_dir(&rsp->req));
rsp->n_rdma = 0;
if (unlikely(wc->status != IB_WC_SUCCESS)) {
+ nvmet_rdma_rw_ctx_destroy(rsp);
nvmet_req_uninit(&rsp->req);
nvmet_rdma_release_rsp(rsp);
if (wc->status != IB_WC_WR_FLUSH_ERR) {
@@ -611,7 +772,57 @@
return;
}
- nvmet_req_execute(&rsp->req);
+ if (rsp->req.metadata_len)
+ status = nvmet_rdma_check_pi_status(rsp->rw.reg->mr);
+ nvmet_rdma_rw_ctx_destroy(rsp);
+
+ if (unlikely(status))
+ nvmet_req_complete(&rsp->req, status);
+ else
+ rsp->req.execute(&rsp->req);
+}
+
+static void nvmet_rdma_write_data_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+ struct nvmet_rdma_rsp *rsp =
+ container_of(wc->wr_cqe, struct nvmet_rdma_rsp, write_cqe);
+ struct nvmet_rdma_queue *queue = wc->qp->qp_context;
+ struct rdma_cm_id *cm_id = rsp->queue->cm_id;
+ u16 status;
+
+ if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY))
+ return;
+
+ WARN_ON(rsp->n_rdma <= 0);
+ atomic_add(rsp->n_rdma, &queue->sq_wr_avail);
+ rsp->n_rdma = 0;
+
+ if (unlikely(wc->status != IB_WC_SUCCESS)) {
+ nvmet_rdma_rw_ctx_destroy(rsp);
+ nvmet_req_uninit(&rsp->req);
+ nvmet_rdma_release_rsp(rsp);
+ if (wc->status != IB_WC_WR_FLUSH_ERR) {
+ pr_info("RDMA WRITE for CQE failed with status %s (%d).\n",
+ ib_wc_status_msg(wc->status), wc->status);
+ nvmet_rdma_error_comp(queue);
+ }
+ return;
+ }
+
+ /*
+ * Upon RDMA completion check the signature status
+ * - if succeeded send good NVMe response
+ * - if failed send bad NVMe response with appropriate error
+ */
+ status = nvmet_rdma_check_pi_status(rsp->rw.reg->mr);
+ if (unlikely(status))
+ rsp->req.cqe->status = cpu_to_le16(status << 1);
+ nvmet_rdma_rw_ctx_destroy(rsp);
+
+ if (unlikely(ib_post_send(cm_id->qp, &rsp->send_wr, NULL))) {
+ pr_err("sending cmd response failed\n");
+ nvmet_rdma_release_rsp(rsp);
+ }
}
static void nvmet_rdma_use_inline_sg(struct nvmet_rdma_rsp *rsp, u32 len,
@@ -644,8 +855,11 @@
u64 off = le64_to_cpu(sgl->addr);
u32 len = le32_to_cpu(sgl->length);
- if (!nvme_is_write(rsp->req.cmd))
+ if (!nvme_is_write(rsp->req.cmd)) {
+ rsp->req.error_loc =
+ offsetof(struct nvme_common_command, opcode);
return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ }
if (off + len > rsp->queue->dev->inline_data_size) {
pr_err("invalid inline data offset!\n");
@@ -665,26 +879,27 @@
static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp,
struct nvme_keyed_sgl_desc *sgl, bool invalidate)
{
- struct rdma_cm_id *cm_id = rsp->queue->cm_id;
u64 addr = le64_to_cpu(sgl->addr);
- u32 len = get_unaligned_le24(sgl->length);
u32 key = get_unaligned_le32(sgl->key);
+ struct ib_sig_attrs sig_attrs;
int ret;
+ rsp->req.transfer_len = get_unaligned_le24(sgl->length);
+
/* no data command? */
- if (!len)
+ if (!rsp->req.transfer_len)
return 0;
- rsp->req.sg = sgl_alloc(len, GFP_KERNEL, &rsp->req.sg_cnt);
- if (!rsp->req.sg)
- return NVME_SC_INTERNAL;
+ if (rsp->req.metadata_len)
+ nvmet_rdma_set_sig_attrs(&rsp->req, &sig_attrs);
- ret = rdma_rw_ctx_init(&rsp->rw, cm_id->qp, cm_id->port_num,
- rsp->req.sg, rsp->req.sg_cnt, 0, addr, key,
- nvmet_data_dir(&rsp->req));
- if (ret < 0)
- return NVME_SC_INTERNAL;
- rsp->req.transfer_len += len;
+ ret = nvmet_req_alloc_sgls(&rsp->req);
+ if (unlikely(ret < 0))
+ goto error_out;
+
+ ret = nvmet_rdma_rw_ctx_init(rsp, addr, key, &sig_attrs);
+ if (unlikely(ret < 0))
+ goto error_out;
rsp->n_rdma += ret;
if (invalidate) {
@@ -693,6 +908,10 @@
}
return 0;
+
+error_out:
+ rsp->req.transfer_len = 0;
+ return NVME_SC_INTERNAL;
}
static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp)
@@ -706,6 +925,8 @@
return nvmet_rdma_map_sgl_inline(rsp);
default:
pr_err("invalid SGL subtype: %#x\n", sgl->type);
+ rsp->req.error_loc =
+ offsetof(struct nvme_common_command, dptr);
return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
}
case NVME_KEY_SGL_FMT_DATA_DESC:
@@ -716,10 +937,13 @@
return nvmet_rdma_map_sgl_keyed(rsp, sgl, false);
default:
pr_err("invalid SGL subtype: %#x\n", sgl->type);
+ rsp->req.error_loc =
+ offsetof(struct nvme_common_command, dptr);
return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
}
default:
pr_err("invalid SGL type: %#x\n", sgl->type);
+ rsp->req.error_loc = offsetof(struct nvme_common_command, dptr);
return NVME_SC_SGL_INVALID_TYPE | NVME_SC_DNR;
}
}
@@ -742,7 +966,7 @@
queue->cm_id->port_num, &rsp->read_cqe, NULL))
nvmet_req_complete(&rsp->req, NVME_SC_DATA_XFER_ERROR);
} else {
- nvmet_req_execute(&rsp->req);
+ rsp->req.execute(&rsp->req);
}
return true;
@@ -784,7 +1008,7 @@
{
struct nvmet_rdma_cmd *cmd =
container_of(wc->wr_cqe, struct nvmet_rdma_cmd, cqe);
- struct nvmet_rdma_queue *queue = cq->cq_context;
+ struct nvmet_rdma_queue *queue = wc->qp->qp_context;
struct nvmet_rdma_rsp *rsp;
if (unlikely(wc->status != IB_WC_SUCCESS)) {
@@ -836,23 +1060,40 @@
nvmet_rdma_handle_command(queue, rsp);
}
-static void nvmet_rdma_destroy_srq(struct nvmet_rdma_device *ndev)
+static void nvmet_rdma_destroy_srq(struct nvmet_rdma_srq *nsrq)
{
- if (!ndev->srq)
- return;
+ nvmet_rdma_free_cmds(nsrq->ndev, nsrq->cmds, nsrq->ndev->srq_size,
+ false);
+ ib_destroy_srq(nsrq->srq);
- nvmet_rdma_free_cmds(ndev, ndev->srq_cmds, ndev->srq_size, false);
- ib_destroy_srq(ndev->srq);
+ kfree(nsrq);
}
-static int nvmet_rdma_init_srq(struct nvmet_rdma_device *ndev)
+static void nvmet_rdma_destroy_srqs(struct nvmet_rdma_device *ndev)
+{
+ int i;
+
+ if (!ndev->srqs)
+ return;
+
+ for (i = 0; i < ndev->srq_count; i++)
+ nvmet_rdma_destroy_srq(ndev->srqs[i]);
+
+ kfree(ndev->srqs);
+}
+
+static struct nvmet_rdma_srq *
+nvmet_rdma_init_srq(struct nvmet_rdma_device *ndev)
{
struct ib_srq_init_attr srq_attr = { NULL, };
+ size_t srq_size = ndev->srq_size;
+ struct nvmet_rdma_srq *nsrq;
struct ib_srq *srq;
- size_t srq_size;
int ret, i;
- srq_size = 4095; /* XXX: tune */
+ nsrq = kzalloc(sizeof(*nsrq), GFP_KERNEL);
+ if (!nsrq)
+ return ERR_PTR(-ENOMEM);
srq_attr.attr.max_wr = srq_size;
srq_attr.attr.max_sge = 1 + ndev->inline_page_count;
@@ -860,6 +1101,42 @@
srq_attr.srq_type = IB_SRQT_BASIC;
srq = ib_create_srq(ndev->pd, &srq_attr);
if (IS_ERR(srq)) {
+ ret = PTR_ERR(srq);
+ goto out_free;
+ }
+
+ nsrq->cmds = nvmet_rdma_alloc_cmds(ndev, srq_size, false);
+ if (IS_ERR(nsrq->cmds)) {
+ ret = PTR_ERR(nsrq->cmds);
+ goto out_destroy_srq;
+ }
+
+ nsrq->srq = srq;
+ nsrq->ndev = ndev;
+
+ for (i = 0; i < srq_size; i++) {
+ nsrq->cmds[i].nsrq = nsrq;
+ ret = nvmet_rdma_post_recv(ndev, &nsrq->cmds[i]);
+ if (ret)
+ goto out_free_cmds;
+ }
+
+ return nsrq;
+
+out_free_cmds:
+ nvmet_rdma_free_cmds(ndev, nsrq->cmds, srq_size, false);
+out_destroy_srq:
+ ib_destroy_srq(srq);
+out_free:
+ kfree(nsrq);
+ return ERR_PTR(ret);
+}
+
+static int nvmet_rdma_init_srqs(struct nvmet_rdma_device *ndev)
+{
+ int i, ret;
+
+ if (!ndev->device->attrs.max_srq_wr || !ndev->device->attrs.max_srq) {
/*
* If SRQs aren't supported we just go ahead and use normal
* non-shared receive queues.
@@ -868,27 +1145,29 @@
return 0;
}
- ndev->srq_cmds = nvmet_rdma_alloc_cmds(ndev, srq_size, false);
- if (IS_ERR(ndev->srq_cmds)) {
- ret = PTR_ERR(ndev->srq_cmds);
- goto out_destroy_srq;
- }
+ ndev->srq_size = min(ndev->device->attrs.max_srq_wr,
+ nvmet_rdma_srq_size);
+ ndev->srq_count = min(ndev->device->num_comp_vectors,
+ ndev->device->attrs.max_srq);
- ndev->srq = srq;
- ndev->srq_size = srq_size;
+ ndev->srqs = kcalloc(ndev->srq_count, sizeof(*ndev->srqs), GFP_KERNEL);
+ if (!ndev->srqs)
+ return -ENOMEM;
- for (i = 0; i < srq_size; i++) {
- ret = nvmet_rdma_post_recv(ndev, &ndev->srq_cmds[i]);
- if (ret)
- goto out_free_cmds;
+ for (i = 0; i < ndev->srq_count; i++) {
+ ndev->srqs[i] = nvmet_rdma_init_srq(ndev);
+ if (IS_ERR(ndev->srqs[i])) {
+ ret = PTR_ERR(ndev->srqs[i]);
+ goto err_srq;
+ }
}
return 0;
-out_free_cmds:
- nvmet_rdma_free_cmds(ndev, ndev->srq_cmds, ndev->srq_size, false);
-out_destroy_srq:
- ib_destroy_srq(srq);
+err_srq:
+ while (--i >= 0)
+ nvmet_rdma_destroy_srq(ndev->srqs[i]);
+ kfree(ndev->srqs);
return ret;
}
@@ -901,7 +1180,7 @@
list_del(&ndev->entry);
mutex_unlock(&device_list_mutex);
- nvmet_rdma_destroy_srq(ndev);
+ nvmet_rdma_destroy_srqs(ndev);
ib_dealloc_pd(ndev->pd);
kfree(ndev);
@@ -910,7 +1189,8 @@
static struct nvmet_rdma_device *
nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
{
- struct nvmet_port *port = cm_id->context;
+ struct nvmet_rdma_port *port = cm_id->context;
+ struct nvmet_port *nport = port->nport;
struct nvmet_rdma_device *ndev;
int inline_page_count;
int inline_sge_count;
@@ -927,18 +1207,26 @@
if (!ndev)
goto out_err;
- inline_page_count = num_pages(port->inline_data_size);
+ inline_page_count = num_pages(nport->inline_data_size);
inline_sge_count = max(cm_id->device->attrs.max_sge_rd,
cm_id->device->attrs.max_recv_sge) - 1;
if (inline_page_count > inline_sge_count) {
pr_warn("inline_data_size %d cannot be supported by device %s. Reducing to %lu.\n",
- port->inline_data_size, cm_id->device->name,
+ nport->inline_data_size, cm_id->device->name,
inline_sge_count * PAGE_SIZE);
- port->inline_data_size = inline_sge_count * PAGE_SIZE;
+ nport->inline_data_size = inline_sge_count * PAGE_SIZE;
inline_page_count = inline_sge_count;
}
- ndev->inline_data_size = port->inline_data_size;
+ ndev->inline_data_size = nport->inline_data_size;
ndev->inline_page_count = inline_page_count;
+
+ if (nport->pi_enable && !(cm_id->device->attrs.device_cap_flags &
+ IB_DEVICE_INTEGRITY_HANDOVER)) {
+ pr_warn("T10-PI is not supported by device %s. Disabling it\n",
+ cm_id->device->name);
+ nport->pi_enable = false;
+ }
+
ndev->device = cm_id->device;
kref_init(&ndev->ref);
@@ -947,7 +1235,7 @@
goto out_free_dev;
if (nvmet_rdma_use_srq) {
- ret = nvmet_rdma_init_srq(ndev);
+ ret = nvmet_rdma_init_srqs(ndev);
if (ret)
goto out_free_pd;
}
@@ -971,23 +1259,15 @@
{
struct ib_qp_init_attr qp_attr;
struct nvmet_rdma_device *ndev = queue->dev;
- int comp_vector, nr_cqe, ret, i;
-
- /*
- * Spread the io queues across completion vectors,
- * but still keep all admin queues on vector 0.
- */
- comp_vector = !queue->host_qid ? 0 :
- queue->idx % ndev->device->num_comp_vectors;
+ int nr_cqe, ret, i, factor;
/*
* Reserve CQ slots for RECV + RDMA_READ/RDMA_WRITE + RDMA_SEND.
*/
nr_cqe = queue->recv_queue_size + 2 * queue->send_queue_size;
- queue->cq = ib_alloc_cq(ndev->device, queue,
- nr_cqe + 1, comp_vector,
- IB_POLL_WORKQUEUE);
+ queue->cq = ib_cq_pool_get(ndev->device, nr_cqe + 1,
+ queue->comp_vector, IB_POLL_WORKQUEUE);
if (IS_ERR(queue->cq)) {
ret = PTR_ERR(queue->cq);
pr_err("failed to create CQ cqe= %d ret= %d\n",
@@ -1004,17 +1284,22 @@
qp_attr.qp_type = IB_QPT_RC;
/* +1 for drain */
qp_attr.cap.max_send_wr = queue->send_queue_size + 1;
- qp_attr.cap.max_rdma_ctxs = queue->send_queue_size;
+ factor = rdma_rw_mr_factor(ndev->device, queue->cm_id->port_num,
+ 1 << NVMET_RDMA_MAX_MDTS);
+ qp_attr.cap.max_rdma_ctxs = queue->send_queue_size * factor;
qp_attr.cap.max_send_sge = max(ndev->device->attrs.max_sge_rd,
ndev->device->attrs.max_send_sge);
- if (ndev->srq) {
- qp_attr.srq = ndev->srq;
+ if (queue->nsrq) {
+ qp_attr.srq = queue->nsrq->srq;
} else {
/* +1 for drain */
qp_attr.cap.max_recv_wr = 1 + queue->recv_queue_size;
qp_attr.cap.max_recv_sge = 1 + ndev->inline_page_count;
}
+
+ if (queue->port->pi_enable && queue->host_qid)
+ qp_attr.create_flags |= IB_QP_CREATE_INTEGRITY_EN;
ret = rdma_create_qp(queue->cm_id, ndev->pd, &qp_attr);
if (ret) {
@@ -1029,7 +1314,7 @@
__func__, queue->cq->cqe, qp_attr.cap.max_send_sge,
qp_attr.cap.max_send_wr, queue->cm_id);
- if (!ndev->srq) {
+ if (!queue->nsrq) {
for (i = 0; i < queue->recv_queue_size; i++) {
queue->cmds[i].queue = queue;
ret = nvmet_rdma_post_recv(ndev, &queue->cmds[i]);
@@ -1044,7 +1329,7 @@
err_destroy_qp:
rdma_destroy_qp(queue->cm_id);
err_destroy_cq:
- ib_free_cq(queue->cq);
+ ib_cq_pool_put(queue->cq, nr_cqe + 1);
goto out;
}
@@ -1054,7 +1339,8 @@
if (queue->cm_id)
rdma_destroy_id(queue->cm_id);
ib_destroy_qp(queue->qp);
- ib_free_cq(queue->cq);
+ ib_cq_pool_put(queue->cq, queue->recv_queue_size + 2 *
+ queue->send_queue_size + 1);
}
static void nvmet_rdma_free_queue(struct nvmet_rdma_queue *queue)
@@ -1064,7 +1350,7 @@
nvmet_sq_destroy(&queue->nvme_sq);
nvmet_rdma_destroy_queue_ib(queue);
- if (!queue->dev->srq) {
+ if (!queue->nsrq) {
nvmet_rdma_free_cmds(queue->dev, queue->cmds,
queue->recv_queue_size,
!queue->host_qid);
@@ -1126,7 +1412,8 @@
rej.recfmt = cpu_to_le16(NVME_RDMA_CM_FMT_1_0);
rej.sts = cpu_to_le16(status);
- return rdma_reject(cm_id, (void *)&rej, sizeof(rej));
+ return rdma_reject(cm_id, (void *)&rej, sizeof(rej),
+ IB_CM_REJ_CONSUMER_DEFINED);
}
static struct nvmet_rdma_queue *
@@ -1134,6 +1421,7 @@
struct rdma_cm_id *cm_id,
struct rdma_cm_event *event)
{
+ struct nvmet_rdma_port *port = cm_id->context;
struct nvmet_rdma_queue *queue;
int ret;
@@ -1160,6 +1448,7 @@
INIT_WORK(&queue->release_work, nvmet_rdma_release_queue_work);
queue->dev = ndev;
queue->cm_id = cm_id;
+ queue->port = port->nport;
spin_lock_init(&queue->state_lock);
queue->state = NVMET_RDMA_Q_CONNECTING;
@@ -1176,13 +1465,23 @@
goto out_destroy_sq;
}
+ /*
+ * Spread the io queues across completion vectors,
+ * but still keep all admin queues on vector 0.
+ */
+ queue->comp_vector = !queue->host_qid ? 0 :
+ queue->idx % ndev->device->num_comp_vectors;
+
+
ret = nvmet_rdma_alloc_rsps(queue);
if (ret) {
ret = NVME_RDMA_CM_NO_RSC;
goto out_ida_remove;
}
- if (!ndev->srq) {
+ if (ndev->srqs) {
+ queue->nsrq = ndev->srqs[queue->comp_vector % ndev->srq_count];
+ } else {
queue->cmds = nvmet_rdma_alloc_cmds(ndev,
queue->recv_queue_size,
!queue->host_qid);
@@ -1203,7 +1502,7 @@
return queue;
out_free_cmds:
- if (!ndev->srq) {
+ if (!queue->nsrq) {
nvmet_rdma_free_cmds(queue->dev, queue->cmds,
queue->recv_queue_size,
!queue->host_qid);
@@ -1228,6 +1527,10 @@
switch (event->event) {
case IB_EVENT_COMM_EST:
rdma_notify(queue->cm_id, event->event);
+ break;
+ case IB_EVENT_QP_LAST_WQE_REACHED:
+ pr_debug("received last WQE reached event for queue=0x%p\n",
+ queue);
break;
default:
pr_err("received IB QP event: %s (%d)\n",
@@ -1278,7 +1581,6 @@
ret = -ENOMEM;
goto put_device;
}
- queue->port = cm_id->context;
if (queue->host_qid == 0) {
/* Let inflight controller teardown complete */
@@ -1346,6 +1648,16 @@
spin_lock_irqsave(&queue->state_lock, flags);
switch (queue->state) {
case NVMET_RDMA_Q_CONNECTING:
+ while (!list_empty(&queue->rsp_wait_list)) {
+ struct nvmet_rdma_rsp *rsp;
+
+ rsp = list_first_entry(&queue->rsp_wait_list,
+ struct nvmet_rdma_rsp,
+ wait_list);
+ list_del(&rsp->wait_list);
+ nvmet_rdma_put_rsp(rsp);
+ }
+ fallthrough;
case NVMET_RDMA_Q_LIVE:
queue->state = NVMET_RDMA_Q_DISCONNECTING;
disconnect = true;
@@ -1408,7 +1720,7 @@
static int nvmet_rdma_device_removal(struct rdma_cm_id *cm_id,
struct nvmet_rdma_queue *queue)
{
- struct nvmet_port *port;
+ struct nvmet_rdma_port *port;
if (queue) {
/*
@@ -1427,7 +1739,7 @@
* cm_id destroy. use atomic xchg to make sure
* we don't compete with remove_port.
*/
- if (xchg(&port->priv, NULL) != cm_id)
+ if (xchg(&port->cm_id, NULL) != cm_id)
return 0;
/*
@@ -1458,6 +1770,13 @@
nvmet_rdma_queue_established(queue);
break;
case RDMA_CM_EVENT_ADDR_CHANGE:
+ if (!queue) {
+ struct nvmet_rdma_port *port = cm_id->context;
+
+ schedule_delayed_work(&port->repair_work, 0);
+ break;
+ }
+ fallthrough;
case RDMA_CM_EVENT_DISCONNECTED:
case RDMA_CM_EVENT_TIMEWAIT_EXIT:
nvmet_rdma_queue_disconnect(queue);
@@ -1468,7 +1787,7 @@
case RDMA_CM_EVENT_REJECTED:
pr_debug("Connection rejected: %s\n",
rdma_reject_msg(cm_id, event->status));
- /* FALLTHROUGH */
+ fallthrough;
case RDMA_CM_EVENT_UNREACHABLE:
case RDMA_CM_EVENT_CONNECT_ERROR:
nvmet_rdma_queue_connect_fail(cm_id, queue);
@@ -1500,42 +1819,43 @@
mutex_unlock(&nvmet_rdma_queue_mutex);
}
-static int nvmet_rdma_add_port(struct nvmet_port *port)
+static void nvmet_rdma_destroy_port_queues(struct nvmet_rdma_port *port)
{
+ struct nvmet_rdma_queue *queue, *tmp;
+ struct nvmet_port *nport = port->nport;
+
+ mutex_lock(&nvmet_rdma_queue_mutex);
+ list_for_each_entry_safe(queue, tmp, &nvmet_rdma_queue_list,
+ queue_list) {
+ if (queue->port != nport)
+ continue;
+
+ list_del_init(&queue->queue_list);
+ __nvmet_rdma_queue_disconnect(queue);
+ }
+ mutex_unlock(&nvmet_rdma_queue_mutex);
+}
+
+static void nvmet_rdma_disable_port(struct nvmet_rdma_port *port)
+{
+ struct rdma_cm_id *cm_id = xchg(&port->cm_id, NULL);
+
+ if (cm_id)
+ rdma_destroy_id(cm_id);
+
+ /*
+ * Destroy the remaining queues, which are not belong to any
+ * controller yet. Do it here after the RDMA-CM was destroyed
+ * guarantees that no new queue will be created.
+ */
+ nvmet_rdma_destroy_port_queues(port);
+}
+
+static int nvmet_rdma_enable_port(struct nvmet_rdma_port *port)
+{
+ struct sockaddr *addr = (struct sockaddr *)&port->addr;
struct rdma_cm_id *cm_id;
- struct sockaddr_storage addr = { };
- __kernel_sa_family_t af;
int ret;
-
- switch (port->disc_addr.adrfam) {
- case NVMF_ADDR_FAMILY_IP4:
- af = AF_INET;
- break;
- case NVMF_ADDR_FAMILY_IP6:
- af = AF_INET6;
- break;
- default:
- pr_err("address family %d not supported\n",
- port->disc_addr.adrfam);
- return -EINVAL;
- }
-
- if (port->inline_data_size < 0) {
- port->inline_data_size = NVMET_RDMA_DEFAULT_INLINE_DATA_SIZE;
- } else if (port->inline_data_size > NVMET_RDMA_MAX_INLINE_DATA_SIZE) {
- pr_warn("inline_data_size %u is too large, reducing to %u\n",
- port->inline_data_size,
- NVMET_RDMA_MAX_INLINE_DATA_SIZE);
- port->inline_data_size = NVMET_RDMA_MAX_INLINE_DATA_SIZE;
- }
-
- ret = inet_pton_with_scope(&init_net, af, port->disc_addr.traddr,
- port->disc_addr.trsvcid, &addr);
- if (ret) {
- pr_err("malformed ip/port passed: %s:%s\n",
- port->disc_addr.traddr, port->disc_addr.trsvcid);
- return ret;
- }
cm_id = rdma_create_id(&init_net, nvmet_rdma_cm_handler, port,
RDMA_PS_TCP, IB_QPT_RC);
@@ -1554,23 +1874,19 @@
goto out_destroy_id;
}
- ret = rdma_bind_addr(cm_id, (struct sockaddr *)&addr);
+ ret = rdma_bind_addr(cm_id, addr);
if (ret) {
- pr_err("binding CM ID to %pISpcs failed (%d)\n",
- (struct sockaddr *)&addr, ret);
+ pr_err("binding CM ID to %pISpcs failed (%d)\n", addr, ret);
goto out_destroy_id;
}
ret = rdma_listen(cm_id, 128);
if (ret) {
- pr_err("listening to %pISpcs failed (%d)\n",
- (struct sockaddr *)&addr, ret);
+ pr_err("listening to %pISpcs failed (%d)\n", addr, ret);
goto out_destroy_id;
}
- pr_info("enabling port %d (%pISpcs)\n",
- le16_to_cpu(port->disc_addr.portid), (struct sockaddr *)&addr);
- port->priv = cm_id;
+ port->cm_id = cm_id;
return 0;
out_destroy_id:
@@ -1578,18 +1894,92 @@
return ret;
}
-static void nvmet_rdma_remove_port(struct nvmet_port *port)
+static void nvmet_rdma_repair_port_work(struct work_struct *w)
{
- struct rdma_cm_id *cm_id = xchg(&port->priv, NULL);
+ struct nvmet_rdma_port *port = container_of(to_delayed_work(w),
+ struct nvmet_rdma_port, repair_work);
+ int ret;
- if (cm_id)
- rdma_destroy_id(cm_id);
+ nvmet_rdma_disable_port(port);
+ ret = nvmet_rdma_enable_port(port);
+ if (ret)
+ schedule_delayed_work(&port->repair_work, 5 * HZ);
+}
+
+static int nvmet_rdma_add_port(struct nvmet_port *nport)
+{
+ struct nvmet_rdma_port *port;
+ __kernel_sa_family_t af;
+ int ret;
+
+ port = kzalloc(sizeof(*port), GFP_KERNEL);
+ if (!port)
+ return -ENOMEM;
+
+ nport->priv = port;
+ port->nport = nport;
+ INIT_DELAYED_WORK(&port->repair_work, nvmet_rdma_repair_port_work);
+
+ switch (nport->disc_addr.adrfam) {
+ case NVMF_ADDR_FAMILY_IP4:
+ af = AF_INET;
+ break;
+ case NVMF_ADDR_FAMILY_IP6:
+ af = AF_INET6;
+ break;
+ default:
+ pr_err("address family %d not supported\n",
+ nport->disc_addr.adrfam);
+ ret = -EINVAL;
+ goto out_free_port;
+ }
+
+ if (nport->inline_data_size < 0) {
+ nport->inline_data_size = NVMET_RDMA_DEFAULT_INLINE_DATA_SIZE;
+ } else if (nport->inline_data_size > NVMET_RDMA_MAX_INLINE_DATA_SIZE) {
+ pr_warn("inline_data_size %u is too large, reducing to %u\n",
+ nport->inline_data_size,
+ NVMET_RDMA_MAX_INLINE_DATA_SIZE);
+ nport->inline_data_size = NVMET_RDMA_MAX_INLINE_DATA_SIZE;
+ }
+
+ ret = inet_pton_with_scope(&init_net, af, nport->disc_addr.traddr,
+ nport->disc_addr.trsvcid, &port->addr);
+ if (ret) {
+ pr_err("malformed ip/port passed: %s:%s\n",
+ nport->disc_addr.traddr, nport->disc_addr.trsvcid);
+ goto out_free_port;
+ }
+
+ ret = nvmet_rdma_enable_port(port);
+ if (ret)
+ goto out_free_port;
+
+ pr_info("enabling port %d (%pISpcs)\n",
+ le16_to_cpu(nport->disc_addr.portid),
+ (struct sockaddr *)&port->addr);
+
+ return 0;
+
+out_free_port:
+ kfree(port);
+ return ret;
+}
+
+static void nvmet_rdma_remove_port(struct nvmet_port *nport)
+{
+ struct nvmet_rdma_port *port = nport->priv;
+
+ cancel_delayed_work_sync(&port->repair_work);
+ nvmet_rdma_disable_port(port);
+ kfree(port);
}
static void nvmet_rdma_disc_port_addr(struct nvmet_req *req,
- struct nvmet_port *port, char *traddr)
+ struct nvmet_port *nport, char *traddr)
{
- struct rdma_cm_id *cm_id = port->priv;
+ struct nvmet_rdma_port *port = nport->priv;
+ struct rdma_cm_id *cm_id = port->cm_id;
if (inet_addr_is_any((struct sockaddr *)&cm_id->route.addr.src_addr)) {
struct nvmet_rdma_rsp *rsp =
@@ -1599,20 +1989,28 @@
sprintf(traddr, "%pISc", addr);
} else {
- memcpy(traddr, port->disc_addr.traddr, NVMF_TRADDR_SIZE);
+ memcpy(traddr, nport->disc_addr.traddr, NVMF_TRADDR_SIZE);
}
+}
+
+static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl)
+{
+ if (ctrl->pi_support)
+ return NVMET_RDMA_MAX_METADATA_MDTS;
+ return NVMET_RDMA_MAX_MDTS;
}
static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
.owner = THIS_MODULE,
.type = NVMF_TRTYPE_RDMA,
.msdbd = 1,
- .has_keyed_sgls = 1,
+ .flags = NVMF_KEYED_SGLS | NVMF_METADATA_SUPPORTED,
.add_port = nvmet_rdma_add_port,
.remove_port = nvmet_rdma_remove_port,
.queue_response = nvmet_rdma_queue_response,
.delete_ctrl = nvmet_rdma_delete_ctrl,
.disc_traddr = nvmet_rdma_disc_port_addr,
+ .get_mdts = nvmet_rdma_get_mdts,
};
static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data)
--
Gitblit v1.6.2