From bedbef8ad3e75a304af6361af235302bcc61d06b Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 14 May 2024 06:39:01 +0000
Subject: [PATCH] 修改内核路径
---
kernel/drivers/infiniband/ulp/iser/iser_memory.c | 340 ++++++++++++-------------------------------------------
1 files changed, 77 insertions(+), 263 deletions(-)
diff --git a/kernel/drivers/infiniband/ulp/iser/iser_memory.c b/kernel/drivers/infiniband/ulp/iser/iser_memory.c
index 379bc0d..d4e057f 100644
--- a/kernel/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/kernel/drivers/infiniband/ulp/iser/iser_memory.c
@@ -38,62 +38,13 @@
#include <linux/scatterlist.h>
#include "iscsi_iser.h"
-static
-int iser_fast_reg_fmr(struct iscsi_iser_task *iser_task,
- struct iser_data_buf *mem,
- struct iser_reg_resources *rsc,
- struct iser_mem_reg *mem_reg);
-static
-int iser_fast_reg_mr(struct iscsi_iser_task *iser_task,
- struct iser_data_buf *mem,
- struct iser_reg_resources *rsc,
- struct iser_mem_reg *mem_reg);
-
-static const struct iser_reg_ops fastreg_ops = {
- .alloc_reg_res = iser_alloc_fastreg_pool,
- .free_reg_res = iser_free_fastreg_pool,
- .reg_mem = iser_fast_reg_mr,
- .unreg_mem = iser_unreg_mem_fastreg,
- .reg_desc_get = iser_reg_desc_get_fr,
- .reg_desc_put = iser_reg_desc_put_fr,
-};
-
-static const struct iser_reg_ops fmr_ops = {
- .alloc_reg_res = iser_alloc_fmr_pool,
- .free_reg_res = iser_free_fmr_pool,
- .reg_mem = iser_fast_reg_fmr,
- .unreg_mem = iser_unreg_mem_fmr,
- .reg_desc_get = iser_reg_desc_get_fmr,
- .reg_desc_put = iser_reg_desc_put_fmr,
-};
void iser_reg_comp(struct ib_cq *cq, struct ib_wc *wc)
{
iser_err_comp(wc, "memreg");
}
-int iser_assign_reg_ops(struct iser_device *device)
-{
- struct ib_device *ib_dev = device->ib_device;
-
- /* Assign function handles - based on FMR support */
- if (ib_dev->alloc_fmr && ib_dev->dealloc_fmr &&
- ib_dev->map_phys_fmr && ib_dev->unmap_fmr) {
- iser_info("FMR supported, using FMR for registration\n");
- device->reg_ops = &fmr_ops;
- } else if (ib_dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) {
- iser_info("FastReg supported, using FastReg for registration\n");
- device->reg_ops = &fastreg_ops;
- device->remote_inv_sup = iser_always_reg;
- } else {
- iser_err("IB device does not support FMRs nor FastRegs, can't register memory\n");
- return -1;
- }
-
- return 0;
-}
-
-struct iser_fr_desc *
+static struct iser_fr_desc *
iser_reg_desc_get_fr(struct ib_conn *ib_conn)
{
struct iser_fr_pool *fr_pool = &ib_conn->fr_pool;
@@ -109,7 +60,7 @@
return desc;
}
-void
+static void
iser_reg_desc_put_fr(struct ib_conn *ib_conn,
struct iser_fr_desc *desc)
{
@@ -119,45 +70,6 @@
spin_lock_irqsave(&fr_pool->lock, flags);
list_add(&desc->list, &fr_pool->list);
spin_unlock_irqrestore(&fr_pool->lock, flags);
-}
-
-struct iser_fr_desc *
-iser_reg_desc_get_fmr(struct ib_conn *ib_conn)
-{
- struct iser_fr_pool *fr_pool = &ib_conn->fr_pool;
-
- return list_first_entry(&fr_pool->list,
- struct iser_fr_desc, list);
-}
-
-void
-iser_reg_desc_put_fmr(struct ib_conn *ib_conn,
- struct iser_fr_desc *desc)
-{
-}
-
-static void iser_data_buf_dump(struct iser_data_buf *data,
- struct ib_device *ibdev)
-{
- struct scatterlist *sg;
- int i;
-
- for_each_sg(data->sg, sg, data->dma_nents, i)
- iser_dbg("sg[%d] dma_addr:0x%lX page:0x%p "
- "off:0x%x sz:0x%x dma_len:0x%x\n",
- i, (unsigned long)ib_sg_dma_address(ibdev, sg),
- sg_page(sg), sg->offset,
- sg->length, ib_sg_dma_len(ibdev, sg));
-}
-
-static void iser_dump_page_vec(struct iser_page_vec *page_vec)
-{
- int i;
-
- iser_err("page vec npages %d data length %lld\n",
- page_vec->npages, page_vec->fake_mr.length);
- for (i = 0; i < page_vec->npages; i++)
- iser_err("vec[%d]: %llx\n", i, page_vec->pages[i]);
}
int iser_dma_map_task_data(struct iscsi_iser_task *iser_task,
@@ -171,7 +83,7 @@
dev = iser_task->iser_conn->ib_conn.device->ib_device;
data->dma_nents = ib_dma_map_sg(dev, data->sg, data->size, dma_dir);
- if (data->dma_nents == 0) {
+ if (unlikely(data->dma_nents == 0)) {
iser_err("dma_map_sg failed!!!\n");
return -EINVAL;
}
@@ -204,8 +116,8 @@
reg->rkey = device->pd->unsafe_global_rkey;
else
reg->rkey = 0;
- reg->sge.addr = ib_sg_dma_address(device->ib_device, &sg[0]);
- reg->sge.length = ib_sg_dma_len(device->ib_device, &sg[0]);
+ reg->sge.addr = sg_dma_address(&sg[0]);
+ reg->sge.length = sg_dma_len(&sg[0]);
iser_dbg("Single DMA entry: lkey=0x%x, rkey=0x%x, addr=0x%llx,"
" length=0x%x\n", reg->sge.lkey, reg->rkey,
@@ -214,100 +126,36 @@
return 0;
}
-static int iser_set_page(struct ib_mr *mr, u64 addr)
-{
- struct iser_page_vec *page_vec =
- container_of(mr, struct iser_page_vec, fake_mr);
-
- page_vec->pages[page_vec->npages++] = addr;
-
- return 0;
-}
-
-static
-int iser_fast_reg_fmr(struct iscsi_iser_task *iser_task,
- struct iser_data_buf *mem,
- struct iser_reg_resources *rsc,
- struct iser_mem_reg *reg)
-{
- struct ib_conn *ib_conn = &iser_task->iser_conn->ib_conn;
- struct iser_device *device = ib_conn->device;
- struct iser_page_vec *page_vec = rsc->page_vec;
- struct ib_fmr_pool *fmr_pool = rsc->fmr_pool;
- struct ib_pool_fmr *fmr;
- int ret, plen;
-
- page_vec->npages = 0;
- page_vec->fake_mr.page_size = SIZE_4K;
- plen = ib_sg_to_pages(&page_vec->fake_mr, mem->sg,
- mem->dma_nents, NULL, iser_set_page);
- if (unlikely(plen < mem->dma_nents)) {
- iser_err("page vec too short to hold this SG\n");
- iser_data_buf_dump(mem, device->ib_device);
- iser_dump_page_vec(page_vec);
- return -EINVAL;
- }
-
- fmr = ib_fmr_pool_map_phys(fmr_pool, page_vec->pages,
- page_vec->npages, page_vec->pages[0]);
- if (IS_ERR(fmr)) {
- ret = PTR_ERR(fmr);
- iser_err("ib_fmr_pool_map_phys failed: %d\n", ret);
- return ret;
- }
-
- reg->sge.lkey = fmr->fmr->lkey;
- reg->rkey = fmr->fmr->rkey;
- reg->sge.addr = page_vec->fake_mr.iova;
- reg->sge.length = page_vec->fake_mr.length;
- reg->mem_h = fmr;
-
- iser_dbg("fmr reg: lkey=0x%x, rkey=0x%x, addr=0x%llx,"
- " length=0x%x\n", reg->sge.lkey, reg->rkey,
- reg->sge.addr, reg->sge.length);
-
- return 0;
-}
-
-/**
- * Unregister (previosuly registered using FMR) memory.
- * If memory is non-FMR does nothing.
- */
-void iser_unreg_mem_fmr(struct iscsi_iser_task *iser_task,
- enum iser_data_dir cmd_dir)
-{
- struct iser_mem_reg *reg = &iser_task->rdma_reg[cmd_dir];
- int ret;
-
- if (!reg->mem_h)
- return;
-
- iser_dbg("PHYSICAL Mem.Unregister mem_h %p\n", reg->mem_h);
-
- ret = ib_fmr_pool_unmap((struct ib_pool_fmr *)reg->mem_h);
- if (ret)
- iser_err("ib_fmr_pool_unmap failed %d\n", ret);
-
- reg->mem_h = NULL;
-}
-
void iser_unreg_mem_fastreg(struct iscsi_iser_task *iser_task,
enum iser_data_dir cmd_dir)
{
- struct iser_device *device = iser_task->iser_conn->ib_conn.device;
struct iser_mem_reg *reg = &iser_task->rdma_reg[cmd_dir];
+ struct iser_fr_desc *desc;
+ struct ib_mr_status mr_status;
- if (!reg->mem_h)
+ desc = reg->mem_h;
+ if (!desc)
return;
- device->reg_ops->reg_desc_put(&iser_task->iser_conn->ib_conn,
- reg->mem_h);
+ /*
+ * The signature MR cannot be invalidated and reused without checking.
+ * libiscsi calls the check_protection transport handler only if
+ * SCSI-Response is received. And the signature MR is not checked if
+ * the task is completed for some other reason like a timeout or error
+ * handling. That's why we must check the signature MR here before
+ * putting it to the free pool.
+ */
+ if (unlikely(desc->sig_protected)) {
+ desc->sig_protected = false;
+ ib_check_mr_status(desc->rsc.sig_mr, IB_MR_CHECK_SIG_STATUS,
+ &mr_status);
+ }
+ iser_reg_desc_put_fr(&iser_task->iser_conn->ib_conn, reg->mem_h);
reg->mem_h = NULL;
}
static void
-iser_set_dif_domain(struct scsi_cmnd *sc, struct ib_sig_attrs *sig_attrs,
- struct ib_sig_domain *domain)
+iser_set_dif_domain(struct scsi_cmnd *sc, struct ib_sig_domain *domain)
{
domain->sig_type = IB_SIG_TYPE_T10_DIF;
domain->sig.dif.pi_interval = scsi_prot_interval(sc);
@@ -330,21 +178,21 @@
case SCSI_PROT_WRITE_INSERT:
case SCSI_PROT_READ_STRIP:
sig_attrs->mem.sig_type = IB_SIG_TYPE_NONE;
- iser_set_dif_domain(sc, sig_attrs, &sig_attrs->wire);
+ iser_set_dif_domain(sc, &sig_attrs->wire);
sig_attrs->wire.sig.dif.bg_type = IB_T10DIF_CRC;
break;
case SCSI_PROT_READ_INSERT:
case SCSI_PROT_WRITE_STRIP:
sig_attrs->wire.sig_type = IB_SIG_TYPE_NONE;
- iser_set_dif_domain(sc, sig_attrs, &sig_attrs->mem);
+ iser_set_dif_domain(sc, &sig_attrs->mem);
sig_attrs->mem.sig.dif.bg_type = sc->prot_flags & SCSI_PROT_IP_CHECKSUM ?
IB_T10DIF_CSUM : IB_T10DIF_CRC;
break;
case SCSI_PROT_READ_PASS:
case SCSI_PROT_WRITE_PASS:
- iser_set_dif_domain(sc, sig_attrs, &sig_attrs->wire);
+ iser_set_dif_domain(sc, &sig_attrs->wire);
sig_attrs->wire.sig.dif.bg_type = IB_T10DIF_CRC;
- iser_set_dif_domain(sc, sig_attrs, &sig_attrs->mem);
+ iser_set_dif_domain(sc, &sig_attrs->mem);
sig_attrs->mem.sig.dif.bg_type = sc->prot_flags & SCSI_PROT_IP_CHECKSUM ?
IB_T10DIF_CSUM : IB_T10DIF_CRC;
break;
@@ -370,27 +218,29 @@
static inline void
iser_inv_rkey(struct ib_send_wr *inv_wr,
struct ib_mr *mr,
- struct ib_cqe *cqe)
+ struct ib_cqe *cqe,
+ struct ib_send_wr *next_wr)
{
inv_wr->opcode = IB_WR_LOCAL_INV;
inv_wr->wr_cqe = cqe;
inv_wr->ex.invalidate_rkey = mr->rkey;
inv_wr->send_flags = 0;
inv_wr->num_sge = 0;
+ inv_wr->next = next_wr;
}
static int
iser_reg_sig_mr(struct iscsi_iser_task *iser_task,
- struct iser_pi_context *pi_ctx,
- struct iser_mem_reg *data_reg,
- struct iser_mem_reg *prot_reg,
+ struct iser_data_buf *mem,
+ struct iser_data_buf *sig_mem,
+ struct iser_reg_resources *rsc,
struct iser_mem_reg *sig_reg)
{
struct iser_tx_desc *tx_desc = &iser_task->desc;
- struct ib_sig_attrs *sig_attrs = &tx_desc->sig_attrs;
struct ib_cqe *cqe = &iser_task->iser_conn->ib_conn.reg_cqe;
- struct ib_sig_handover_wr *wr;
- struct ib_mr *mr = pi_ctx->sig_mr;
+ struct ib_mr *mr = rsc->sig_mr;
+ struct ib_sig_attrs *sig_attrs = mr->sig_attrs;
+ struct ib_reg_wr *wr = &tx_desc->reg_wr;
int ret;
memset(sig_attrs, 0, sizeof(*sig_attrs));
@@ -400,33 +250,36 @@
iser_set_prot_checks(iser_task->sc, &sig_attrs->check_mask);
- if (pi_ctx->sig_mr_valid)
- iser_inv_rkey(iser_tx_next_wr(tx_desc), mr, cqe);
+ if (rsc->mr_valid)
+ iser_inv_rkey(&tx_desc->inv_wr, mr, cqe, &wr->wr);
ib_update_fast_reg_key(mr, ib_inc_rkey(mr->rkey));
- wr = container_of(iser_tx_next_wr(tx_desc), struct ib_sig_handover_wr,
- wr);
- wr->wr.opcode = IB_WR_REG_SIG_MR;
+ ret = ib_map_mr_sg_pi(mr, mem->sg, mem->dma_nents, NULL,
+ sig_mem->sg, sig_mem->dma_nents, NULL, SZ_4K);
+ if (unlikely(ret)) {
+ iser_err("failed to map PI sg (%d)\n",
+ mem->dma_nents + sig_mem->dma_nents);
+ goto err;
+ }
+
+ memset(wr, 0, sizeof(*wr));
+ wr->wr.next = &tx_desc->send_wr;
+ wr->wr.opcode = IB_WR_REG_MR_INTEGRITY;
wr->wr.wr_cqe = cqe;
- wr->wr.sg_list = &data_reg->sge;
- wr->wr.num_sge = 1;
+ wr->wr.num_sge = 0;
wr->wr.send_flags = 0;
- wr->sig_attrs = sig_attrs;
- wr->sig_mr = mr;
- if (scsi_prot_sg_count(iser_task->sc))
- wr->prot = &prot_reg->sge;
- else
- wr->prot = NULL;
- wr->access_flags = IB_ACCESS_LOCAL_WRITE |
- IB_ACCESS_REMOTE_READ |
- IB_ACCESS_REMOTE_WRITE;
- pi_ctx->sig_mr_valid = 1;
+ wr->mr = mr;
+ wr->key = mr->rkey;
+ wr->access = IB_ACCESS_LOCAL_WRITE |
+ IB_ACCESS_REMOTE_READ |
+ IB_ACCESS_REMOTE_WRITE;
+ rsc->mr_valid = 1;
sig_reg->sge.lkey = mr->lkey;
sig_reg->rkey = mr->rkey;
- sig_reg->sge.addr = 0;
- sig_reg->sge.length = scsi_transfer_length(iser_task->sc);
+ sig_reg->sge.addr = mr->iova;
+ sig_reg->sge.length = mr->length;
iser_dbg("lkey=0x%x rkey=0x%x addr=0x%llx length=%u\n",
sig_reg->sge.lkey, sig_reg->rkey, sig_reg->sge.addr,
@@ -443,22 +296,22 @@
struct iser_tx_desc *tx_desc = &iser_task->desc;
struct ib_cqe *cqe = &iser_task->iser_conn->ib_conn.reg_cqe;
struct ib_mr *mr = rsc->mr;
- struct ib_reg_wr *wr;
+ struct ib_reg_wr *wr = &tx_desc->reg_wr;
int n;
if (rsc->mr_valid)
- iser_inv_rkey(iser_tx_next_wr(tx_desc), mr, cqe);
+ iser_inv_rkey(&tx_desc->inv_wr, mr, cqe, &wr->wr);
ib_update_fast_reg_key(mr, ib_inc_rkey(mr->rkey));
- n = ib_map_mr_sg(mr, mem->sg, mem->dma_nents, NULL, SIZE_4K);
+ n = ib_map_mr_sg(mr, mem->sg, mem->dma_nents, NULL, SZ_4K);
if (unlikely(n != mem->dma_nents)) {
iser_err("failed to map sg (%d/%d)\n",
n, mem->dma_nents);
return n < 0 ? n : -EINVAL;
}
- wr = container_of(iser_tx_next_wr(tx_desc), struct ib_reg_wr, wr);
+ wr->wr.next = &tx_desc->send_wr;
wr->wr.opcode = IB_WR_REG_MR;
wr->wr.wr_cqe = cqe;
wr->wr.send_flags = 0;
@@ -483,21 +336,6 @@
}
static int
-iser_reg_prot_sg(struct iscsi_iser_task *task,
- struct iser_data_buf *mem,
- struct iser_fr_desc *desc,
- bool use_dma_key,
- struct iser_mem_reg *reg)
-{
- struct iser_device *device = task->iser_conn->ib_conn.device;
-
- if (use_dma_key)
- return iser_reg_dma(device, mem, reg);
-
- return device->reg_ops->reg_mem(task, mem, &desc->pi_ctx->rsc, reg);
-}
-
-static int
iser_reg_data_sg(struct iscsi_iser_task *task,
struct iser_data_buf *mem,
struct iser_fr_desc *desc,
@@ -509,18 +347,16 @@
if (use_dma_key)
return iser_reg_dma(device, mem, reg);
- return device->reg_ops->reg_mem(task, mem, &desc->rsc, reg);
+ return iser_fast_reg_mr(task, mem, &desc->rsc, reg);
}
-int iser_reg_rdma_mem(struct iscsi_iser_task *task,
- enum iser_data_dir dir,
- bool all_imm)
+int iser_reg_mem_fastreg(struct iscsi_iser_task *task,
+ enum iser_data_dir dir,
+ bool all_imm)
{
struct ib_conn *ib_conn = &task->iser_conn->ib_conn;
- struct iser_device *device = ib_conn->device;
struct iser_data_buf *mem = &task->data[dir];
struct iser_mem_reg *reg = &task->rdma_reg[dir];
- struct iser_mem_reg *data_reg;
struct iser_fr_desc *desc = NULL;
bool use_dma_key;
int err;
@@ -529,51 +365,29 @@
scsi_get_prot_op(task->sc) == SCSI_PROT_NORMAL;
if (!use_dma_key) {
- desc = device->reg_ops->reg_desc_get(ib_conn);
+ desc = iser_reg_desc_get_fr(ib_conn);
reg->mem_h = desc;
}
- if (scsi_get_prot_op(task->sc) == SCSI_PROT_NORMAL)
- data_reg = reg;
- else
- data_reg = &task->desc.data_reg;
-
- err = iser_reg_data_sg(task, mem, desc, use_dma_key, data_reg);
- if (unlikely(err))
- goto err_reg;
-
- if (scsi_get_prot_op(task->sc) != SCSI_PROT_NORMAL) {
- struct iser_mem_reg *prot_reg = &task->desc.prot_reg;
-
- if (scsi_prot_sg_count(task->sc)) {
- mem = &task->prot[dir];
- err = iser_reg_prot_sg(task, mem, desc,
- use_dma_key, prot_reg);
- if (unlikely(err))
- goto err_reg;
- }
-
- err = iser_reg_sig_mr(task, desc->pi_ctx, data_reg,
- prot_reg, reg);
+ if (scsi_get_prot_op(task->sc) == SCSI_PROT_NORMAL) {
+ err = iser_reg_data_sg(task, mem, desc, use_dma_key, reg);
+ if (unlikely(err))
+ goto err_reg;
+ } else {
+ err = iser_reg_sig_mr(task, mem, &task->prot[dir],
+ &desc->rsc, reg);
if (unlikely(err))
goto err_reg;
- desc->pi_ctx->sig_protected = 1;
+ desc->sig_protected = true;
}
return 0;
err_reg:
if (desc)
- device->reg_ops->reg_desc_put(ib_conn, desc);
+ iser_reg_desc_put_fr(ib_conn, desc);
return err;
}
-void iser_unreg_rdma_mem(struct iscsi_iser_task *task,
- enum iser_data_dir dir)
-{
- struct iser_device *device = task->iser_conn->ib_conn.device;
-
- device->reg_ops->unreg_mem(task, dir);
-}
--
Gitblit v1.6.2