From 244b2c5ca8b14627e4a17755e5922221e121c771 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 09 Oct 2024 06:15:07 +0000
Subject: [PATCH] change system file
---
kernel/drivers/scsi/qedf/qedf_io.c | 943 ++++++++++++++++++++++++++++++++++++++++++++--------------
1 files changed, 704 insertions(+), 239 deletions(-)
diff --git a/kernel/drivers/scsi/qedf/qedf_io.c b/kernel/drivers/scsi/qedf/qedf_io.c
index a17c138..1f8e812 100644
--- a/kernel/drivers/scsi/qedf/qedf_io.c
+++ b/kernel/drivers/scsi/qedf/qedf_io.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* QLogic FCoE Offload Driver
* Copyright (c) 2016-2018 Cavium Inc.
- *
- * This software is available under the terms of the GNU General Public License
- * (GPL) Version 2, available from the file COPYING in the main directory of
- * this source tree.
*/
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
@@ -25,7 +22,6 @@
container_of(work, struct qedf_ioreq, timeout_work.work);
struct qedf_ctx *qedf;
struct qedf_rport *fcport;
- u8 op = 0;
if (io_req == NULL) {
QEDF_INFO(NULL, QEDF_LOG_IO, "io_req is NULL.\n");
@@ -43,8 +39,9 @@
switch (io_req->cmd_type) {
case QEDF_ABTS:
if (qedf == NULL) {
- QEDF_INFO(NULL, QEDF_LOG_IO, "qedf is NULL for xid=0x%x.\n",
- io_req->xid);
+ QEDF_INFO(NULL, QEDF_LOG_IO,
+ "qedf is NULL for ABTS xid=0x%x.\n",
+ io_req->xid);
return;
}
@@ -61,6 +58,9 @@
*/
kref_put(&io_req->refcount, qedf_release_cmd);
+ /* Clear in abort bit now that we're done with the command */
+ clear_bit(QEDF_CMD_IN_ABORT, &io_req->flags);
+
/*
* Now that the original I/O and the ABTS are complete see
* if we need to reconnect to the target.
@@ -68,6 +68,15 @@
qedf_restart_rport(fcport);
break;
case QEDF_ELS:
+ if (!qedf) {
+ QEDF_INFO(NULL, QEDF_LOG_IO,
+ "qedf is NULL for ELS xid=0x%x.\n",
+ io_req->xid);
+ return;
+ }
+ /* ELS request no longer outstanding since it timed out */
+ clear_bit(QEDF_CMD_OUTSTANDING, &io_req->flags);
+
kref_get(&io_req->refcount);
/*
* Don't attempt to clean an ELS timeout as any subseqeunt
@@ -76,14 +85,13 @@
*/
QEDF_ERR(&(qedf->dbg_ctx), "ELS timeout, xid=0x%x.\n",
io_req->xid);
+ qedf_initiate_cleanup(io_req, true);
io_req->event = QEDF_IOREQ_EV_ELS_TMO;
/* Call callback function to complete command */
if (io_req->cb_func && io_req->cb_arg) {
- op = io_req->cb_arg->op;
io_req->cb_func(io_req->cb_arg);
io_req->cb_arg = NULL;
}
- qedf_initiate_cleanup(io_req, true);
kref_put(&io_req->refcount, qedf_release_cmd);
break;
case QEDF_SEQ_CLEANUP:
@@ -94,6 +102,8 @@
qedf_process_seq_cleanup_compl(qedf, NULL, io_req);
break;
default:
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Hit default case, xid=0x%x.\n", io_req->xid);
break;
}
}
@@ -103,7 +113,7 @@
struct io_bdt *bdt_info;
struct qedf_ctx *qedf = cmgr->qedf;
size_t bd_tbl_sz;
- u16 min_xid = QEDF_MIN_XID;
+ u16 min_xid = 0;
u16 max_xid = (FCOE_PARAMS_NUM_TASKS - 1);
int num_ios;
int i;
@@ -112,8 +122,10 @@
num_ios = max_xid - min_xid + 1;
/* Free fcoe_bdt_ctx structures */
- if (!cmgr->io_bdt_pool)
+ if (!cmgr->io_bdt_pool) {
+ QEDF_ERR(&qedf->dbg_ctx, "io_bdt_pool is NULL.\n");
goto free_cmd_pool;
+ }
bd_tbl_sz = QEDF_MAX_BDS_PER_CMD * sizeof(struct scsi_sge);
for (i = 0; i < num_ios; i++) {
@@ -157,6 +169,7 @@
struct qedf_ioreq *io_req =
container_of(work, struct qedf_ioreq, rrq_work.work);
+ atomic_set(&io_req->state, QEDFC_CMD_ST_RRQ_ACTIVE);
qedf_send_rrq(io_req);
}
@@ -169,7 +182,7 @@
u16 xid;
int i;
int num_ios;
- u16 min_xid = QEDF_MIN_XID;
+ u16 min_xid = 0;
u16 max_xid = (FCOE_PARAMS_NUM_TASKS - 1);
/* Make sure num_queues is already set before calling this function */
@@ -201,7 +214,7 @@
/*
* Initialize I/O request fields.
*/
- xid = QEDF_MIN_XID;
+ xid = 0;
for (i = 0; i < num_ios; i++) {
io_req = &cmgr->cmds[i];
@@ -215,8 +228,11 @@
io_req->sense_buffer = dma_alloc_coherent(&qedf->pdev->dev,
QEDF_SCSI_SENSE_BUFFERSIZE, &io_req->sense_buffer_dma,
GFP_KERNEL);
- if (!io_req->sense_buffer)
+ if (!io_req->sense_buffer) {
+ QEDF_ERR(&qedf->dbg_ctx,
+ "Failed to alloc sense buffer.\n");
goto mem_err;
+ }
/* Allocate task parameters to pass to f/w init funcions */
io_req->task_params = kzalloc(sizeof(*io_req->task_params),
@@ -329,7 +345,7 @@
cmd_mgr->idx = 0;
/* Check to make sure command was previously freed */
- if (!test_bit(QEDF_CMD_OUTSTANDING, &io_req->flags))
+ if (!io_req->alloc)
break;
}
@@ -338,7 +354,14 @@
goto out_failed;
}
- set_bit(QEDF_CMD_OUTSTANDING, &io_req->flags);
+ if (test_bit(QEDF_CMD_DIRTY, &io_req->flags))
+ QEDF_ERR(&qedf->dbg_ctx,
+ "io_req found to be dirty ox_id = 0x%x.\n",
+ io_req->xid);
+
+ /* Clear any flags now that we've reallocated the xid */
+ io_req->flags = 0;
+ io_req->alloc = 1;
spin_unlock_irqrestore(&cmd_mgr->lock, flags);
atomic_inc(&fcport->num_active_ios);
@@ -349,8 +372,13 @@
io_req->cmd_mgr = cmd_mgr;
io_req->fcport = fcport;
+ /* Clear any stale sc_cmd back pointer */
+ io_req->sc_cmd = NULL;
+ io_req->lun = -1;
+
/* Hold the io_req against deletion */
- kref_init(&io_req->refcount);
+ kref_init(&io_req->refcount); /* ID: 001 */
+ atomic_set(&io_req->state, QEDFC_CMD_ST_IO_ACTIVE);
/* Bind io_bdt for this io_req */
/* Have a static link between io_req and io_bdt_pool */
@@ -412,6 +440,14 @@
container_of(ref, struct qedf_ioreq, refcount);
struct qedf_cmd_mgr *cmd_mgr = io_req->cmd_mgr;
struct qedf_rport *fcport = io_req->fcport;
+ unsigned long flags;
+
+ if (io_req->cmd_type == QEDF_SCSI_CMD) {
+ QEDF_WARN(&fcport->qedf->dbg_ctx,
+ "Cmd released called without scsi_done called, io_req %p xid=0x%x.\n",
+ io_req, io_req->xid);
+ WARN_ON(io_req->sc_cmd);
+ }
if (io_req->cmd_type == QEDF_ELS ||
io_req->cmd_type == QEDF_TASK_MGMT_CMD)
@@ -419,36 +455,22 @@
atomic_inc(&cmd_mgr->free_list_cnt);
atomic_dec(&fcport->num_active_ios);
- if (atomic_read(&fcport->num_active_ios) < 0)
+ atomic_set(&io_req->state, QEDF_CMD_ST_INACTIVE);
+ if (atomic_read(&fcport->num_active_ios) < 0) {
QEDF_WARN(&(fcport->qedf->dbg_ctx), "active_ios < 0.\n");
+ WARN_ON(1);
+ }
/* Increment task retry identifier now that the request is released */
io_req->task_retry_identifier++;
+ io_req->fcport = NULL;
- clear_bit(QEDF_CMD_OUTSTANDING, &io_req->flags);
-}
-
-static int qedf_split_bd(struct qedf_ioreq *io_req, u64 addr, int sg_len,
- int bd_index)
-{
- struct scsi_sge *bd = io_req->bd_tbl->bd_tbl;
- int frag_size, sg_frags;
-
- sg_frags = 0;
- while (sg_len) {
- if (sg_len > QEDF_BD_SPLIT_SZ)
- frag_size = QEDF_BD_SPLIT_SZ;
- else
- frag_size = sg_len;
- bd[bd_index + sg_frags].sge_addr.lo = U64_LO(addr);
- bd[bd_index + sg_frags].sge_addr.hi = U64_HI(addr);
- bd[bd_index + sg_frags].sge_len = (uint16_t)frag_size;
-
- addr += (u64)frag_size;
- sg_frags++;
- sg_len -= frag_size;
- }
- return sg_frags;
+ clear_bit(QEDF_CMD_DIRTY, &io_req->flags);
+ io_req->cpu = 0;
+ spin_lock_irqsave(&cmd_mgr->lock, flags);
+ io_req->fcport = NULL;
+ io_req->alloc = 0;
+ spin_unlock_irqrestore(&cmd_mgr->lock, flags);
}
static int qedf_map_sg(struct qedf_ioreq *io_req)
@@ -462,74 +484,43 @@
int byte_count = 0;
int sg_count = 0;
int bd_count = 0;
- int sg_frags;
- unsigned int sg_len;
- u64 addr, end_addr;
- int i;
+ u32 sg_len;
+ u64 addr;
+ int i = 0;
sg_count = dma_map_sg(&qedf->pdev->dev, scsi_sglist(sc),
scsi_sg_count(sc), sc->sc_data_direction);
-
sg = scsi_sglist(sc);
- /*
- * New condition to send single SGE as cached-SGL with length less
- * than 64k.
- */
- if ((sg_count == 1) && (sg_dma_len(sg) <=
- QEDF_MAX_SGLEN_FOR_CACHESGL)) {
- sg_len = sg_dma_len(sg);
- addr = (u64)sg_dma_address(sg);
+ io_req->sge_type = QEDF_IOREQ_UNKNOWN_SGE;
- bd[bd_count].sge_addr.lo = (addr & 0xffffffff);
- bd[bd_count].sge_addr.hi = (addr >> 32);
- bd[bd_count].sge_len = (u16)sg_len;
-
- return ++bd_count;
- }
+ if (sg_count <= 8 || io_req->io_req_flags == QEDF_READ)
+ io_req->sge_type = QEDF_IOREQ_FAST_SGE;
scsi_for_each_sg(sc, sg, sg_count, i) {
- sg_len = sg_dma_len(sg);
+ sg_len = (u32)sg_dma_len(sg);
addr = (u64)sg_dma_address(sg);
- end_addr = (u64)(addr + sg_len);
/*
- * First s/g element in the list so check if the end_addr
- * is paged aligned. Also check to make sure the length is
- * at least page size.
+ * Intermediate s/g element so check if start address
+ * is page aligned. Only required for writes and only if the
+ * number of scatter/gather elements is 8 or more.
*/
- if ((i == 0) && (sg_count > 1) &&
- ((end_addr % QEDF_PAGE_SIZE) ||
- sg_len < QEDF_PAGE_SIZE))
- io_req->use_slowpath = true;
- /*
- * Last s/g element so check if the start address is paged
- * aligned.
- */
- else if ((i == (sg_count - 1)) && (sg_count > 1) &&
- (addr % QEDF_PAGE_SIZE))
- io_req->use_slowpath = true;
- /*
- * Intermediate s/g element so check if start and end address
- * is page aligned.
- */
- else if ((i != 0) && (i != (sg_count - 1)) &&
- ((addr % QEDF_PAGE_SIZE) || (end_addr % QEDF_PAGE_SIZE)))
- io_req->use_slowpath = true;
+ if (io_req->sge_type == QEDF_IOREQ_UNKNOWN_SGE && (i) &&
+ (i != (sg_count - 1)) && sg_len < QEDF_PAGE_SIZE)
+ io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
- if (sg_len > QEDF_MAX_BD_LEN) {
- sg_frags = qedf_split_bd(io_req, addr, sg_len,
- bd_count);
- } else {
- sg_frags = 1;
- bd[bd_count].sge_addr.lo = U64_LO(addr);
- bd[bd_count].sge_addr.hi = U64_HI(addr);
- bd[bd_count].sge_len = (uint16_t)sg_len;
- }
+ bd[bd_count].sge_addr.lo = cpu_to_le32(U64_LO(addr));
+ bd[bd_count].sge_addr.hi = cpu_to_le32(U64_HI(addr));
+ bd[bd_count].sge_len = cpu_to_le32(sg_len);
- bd_count += sg_frags;
+ bd_count++;
byte_count += sg_len;
}
+
+ /* To catch a case where FAST and SLOW nothing is set, set FAST */
+ if (io_req->sge_type == QEDF_IOREQ_UNKNOWN_SGE)
+ io_req->sge_type = QEDF_IOREQ_FAST_SGE;
if (byte_count != scsi_bufflen(sc))
QEDF_ERR(&(qedf->dbg_ctx), "byte_count = %d != "
@@ -655,8 +646,10 @@
io_req->sgl_task_params->num_sges = bd_count;
io_req->sgl_task_params->total_buffer_size =
scsi_bufflen(io_req->sc_cmd);
- io_req->sgl_task_params->small_mid_sge =
- io_req->use_slowpath;
+ if (io_req->sge_type == QEDF_IOREQ_SLOW_SGE)
+ io_req->sgl_task_params->small_mid_sge = 1;
+ else
+ io_req->sgl_task_params->small_mid_sge = 0;
}
/* Fill in physical address of sense buffer */
@@ -679,16 +672,10 @@
io_req->task_retry_identifier, fcp_cmnd);
/* Increment SGL type counters */
- if (bd_count == 1) {
- qedf->single_sge_ios++;
- io_req->sge_type = QEDF_IOREQ_SINGLE_SGE;
- } else if (io_req->use_slowpath) {
+ if (io_req->sge_type == QEDF_IOREQ_SLOW_SGE)
qedf->slow_sge_ios++;
- io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
- } else {
+ else
qedf->fast_sge_ios++;
- io_req->sge_type = QEDF_IOREQ_FAST_SGE;
- }
}
void qedf_init_mp_task(struct qedf_ioreq *io_req,
@@ -770,9 +757,6 @@
&task_fc_hdr,
&tx_sgl_task_params,
&rx_sgl_task_params, 0);
-
- /* Midpath requests always consume 1 SGE */
- qedf->single_sge_ios++;
}
/* Presumed that fcport->rport_lock is held */
@@ -804,10 +788,18 @@
FCOE_DB_DATA_AGG_VAL_SEL_SHIFT;
dbell.sq_prod = fcport->fw_sq_prod_idx;
- writel(*(u32 *)&dbell, fcport->p_doorbell);
- /* Make sure SQ index is updated so f/w prcesses requests in order */
+ /* wmb makes sure that the BDs data is updated before updating the
+ * producer, otherwise FW may read old data from the BDs.
+ */
wmb();
- mmiowb();
+ barrier();
+ writel(*(u32 *)&dbell, fcport->p_doorbell);
+ /*
+ * Fence required to flush the write combined buffer, since another
+ * CPU may write to the same doorbell address and data may be lost
+ * due to relaxed order nature of write combined bar.
+ */
+ wmb();
}
static void qedf_trace_io(struct qedf_rport *fcport, struct qedf_ioreq *io_req,
@@ -865,24 +857,21 @@
struct qedf_ctx *qedf = lport_priv(lport);
struct e4_fcoe_task_context *task_ctx;
u16 xid;
- enum fcoe_task_type req_type = 0;
struct fcoe_wqe *sqe;
u16 sqe_idx;
/* Initialize rest of io_req fileds */
io_req->data_xfer_len = scsi_bufflen(sc_cmd);
sc_cmd->SCp.ptr = (char *)io_req;
- io_req->use_slowpath = false; /* Assume fast SGL by default */
+ io_req->sge_type = QEDF_IOREQ_FAST_SGE; /* Assume fast SGL by default */
/* Record which cpu this request is associated with */
io_req->cpu = smp_processor_id();
if (sc_cmd->sc_data_direction == DMA_FROM_DEVICE) {
- req_type = FCOE_TASK_TYPE_READ_INITIATOR;
io_req->io_req_flags = QEDF_READ;
qedf->input_requests++;
} else if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) {
- req_type = FCOE_TASK_TYPE_WRITE_INITIATOR;
io_req->io_req_flags = QEDF_WRITE;
qedf->output_requests++;
} else {
@@ -895,15 +884,23 @@
/* Build buffer descriptor list for firmware from sg list */
if (qedf_build_bd_list_from_sg(io_req)) {
QEDF_ERR(&(qedf->dbg_ctx), "BD list creation failed.\n");
+ /* Release cmd will release io_req, but sc_cmd is assigned */
+ io_req->sc_cmd = NULL;
kref_put(&io_req->refcount, qedf_release_cmd);
return -EAGAIN;
}
- if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
+ if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags) ||
+ test_bit(QEDF_RPORT_UPLOADING_CONNECTION, &fcport->flags)) {
QEDF_ERR(&(qedf->dbg_ctx), "Session not offloaded yet.\n");
+ /* Release cmd will release io_req, but sc_cmd is assigned */
+ io_req->sc_cmd = NULL;
kref_put(&io_req->refcount, qedf_release_cmd);
return -EINVAL;
}
+
+ /* Record LUN number for later use if we neeed them */
+ io_req->lun = (int)sc_cmd->device->lun;
/* Obtain free SQE */
sqe_idx = qedf_get_sqe_idx(fcport);
@@ -915,6 +912,8 @@
if (!task_ctx) {
QEDF_WARN(&(qedf->dbg_ctx), "task_ctx is NULL, xid=%d.\n",
xid);
+ /* Release cmd will release io_req, but sc_cmd is assigned */
+ io_req->sc_cmd = NULL;
kref_put(&io_req->refcount, qedf_release_cmd);
return -EINVAL;
}
@@ -923,6 +922,9 @@
/* Ring doorbell */
qedf_ring_doorbell(fcport);
+
+ /* Set that command is with the firmware now */
+ set_bit(QEDF_CMD_OUTSTANDING, &io_req->flags);
if (qedf_io_tracing && io_req->sc_cmd)
qedf_trace_io(fcport, io_req, QEDF_IO_TRACE_REQ);
@@ -942,10 +944,23 @@
int rc = 0;
int rval;
unsigned long flags = 0;
+ int num_sgs = 0;
+ num_sgs = scsi_sg_count(sc_cmd);
+ if (scsi_sg_count(sc_cmd) > QEDF_MAX_BDS_PER_CMD) {
+ QEDF_ERR(&qedf->dbg_ctx,
+ "Number of SG elements %d exceeds what hardware limitation of %d.\n",
+ num_sgs, QEDF_MAX_BDS_PER_CMD);
+ sc_cmd->result = DID_ERROR;
+ sc_cmd->scsi_done(sc_cmd);
+ return 0;
+ }
if (test_bit(QEDF_UNLOADING, &qedf->flags) ||
test_bit(QEDF_DBG_STOP_IO, &qedf->flags)) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Returning DNC as unloading or stop io, flags 0x%lx.\n",
+ qedf->flags);
sc_cmd->result = DID_NO_CONNECT << 16;
sc_cmd->scsi_done(sc_cmd);
return 0;
@@ -962,6 +977,9 @@
rval = fc_remote_port_chkready(rport);
if (rval) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "fc_remote_port_chkready failed=0x%x for port_id=0x%06x.\n",
+ rval, rport->port_id);
sc_cmd->result = rval;
sc_cmd->scsi_done(sc_cmd);
return 0;
@@ -969,12 +987,14 @@
/* Retry command if we are doing a qed drain operation */
if (test_bit(QEDF_DRAIN_ACTIVE, &qedf->flags)) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO, "Drain active.\n");
rc = SCSI_MLQUEUE_HOST_BUSY;
goto exit_qcmd;
}
if (lport->state != LPORT_ST_READY ||
atomic_read(&qedf->link_state) != QEDF_LINK_UP) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO, "Link down.\n");
rc = SCSI_MLQUEUE_HOST_BUSY;
goto exit_qcmd;
}
@@ -982,7 +1002,8 @@
/* rport and tgt are allocated together, so tgt should be non-NULL */
fcport = (struct qedf_rport *)&rp[1];
- if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
+ if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags) ||
+ test_bit(QEDF_RPORT_UPLOADING_CONNECTION, &fcport->flags)) {
/*
* Session is not offloaded yet. Let SCSI-ml retry
* the command.
@@ -990,19 +1011,28 @@
rc = SCSI_MLQUEUE_TARGET_BUSY;
goto exit_qcmd;
}
+
+ atomic_inc(&fcport->ios_to_queue);
+
if (fcport->retry_delay_timestamp) {
+ /* Take fcport->rport_lock for resetting the delay_timestamp */
+ spin_lock_irqsave(&fcport->rport_lock, flags);
if (time_after(jiffies, fcport->retry_delay_timestamp)) {
fcport->retry_delay_timestamp = 0;
} else {
+ spin_unlock_irqrestore(&fcport->rport_lock, flags);
/* If retry_delay timer is active, flow off the ML */
rc = SCSI_MLQUEUE_TARGET_BUSY;
+ atomic_dec(&fcport->ios_to_queue);
goto exit_qcmd;
}
+ spin_unlock_irqrestore(&fcport->rport_lock, flags);
}
io_req = qedf_alloc_cmd(fcport, QEDF_SCSI_CMD);
if (!io_req) {
rc = SCSI_MLQUEUE_HOST_BUSY;
+ atomic_dec(&fcport->ios_to_queue);
goto exit_qcmd;
}
@@ -1017,6 +1047,7 @@
rc = SCSI_MLQUEUE_HOST_BUSY;
}
spin_unlock_irqrestore(&fcport->rport_lock, flags);
+ atomic_dec(&fcport->ios_to_queue);
exit_qcmd:
return rc;
@@ -1093,22 +1124,29 @@
void qedf_scsi_completion(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
struct qedf_ioreq *io_req)
{
- u16 xid, rval;
- struct e4_fcoe_task_context *task_ctx;
struct scsi_cmnd *sc_cmd;
struct fcoe_cqe_rsp_info *fcp_rsp;
struct qedf_rport *fcport;
int refcount;
u16 scope, qualifier = 0;
u8 fw_residual_flag = 0;
+ unsigned long flags = 0;
+ u16 chk_scope = 0;
if (!io_req)
return;
if (!cqe)
return;
- xid = io_req->xid;
- task_ctx = qedf_get_task_mem(&qedf->tasks, xid);
+ if (!test_bit(QEDF_CMD_OUTSTANDING, &io_req->flags) ||
+ test_bit(QEDF_CMD_IN_CLEANUP, &io_req->flags) ||
+ test_bit(QEDF_CMD_IN_ABORT, &io_req->flags)) {
+ QEDF_ERR(&qedf->dbg_ctx,
+ "io_req xid=0x%x already in cleanup or abort processing or already completed.\n",
+ io_req->xid);
+ return;
+ }
+
sc_cmd = io_req->sc_cmd;
fcp_rsp = &cqe->cqe_info.rsp_info;
@@ -1123,15 +1161,15 @@
return;
}
- if (!sc_cmd->request) {
- QEDF_WARN(&(qedf->dbg_ctx), "sc_cmd->request is NULL, "
- "sc_cmd=%p.\n", sc_cmd);
+ if (!sc_cmd->device) {
+ QEDF_ERR(&qedf->dbg_ctx,
+ "Device for sc_cmd %p is NULL.\n", sc_cmd);
return;
}
- if (!sc_cmd->request->special) {
- QEDF_WARN(&(qedf->dbg_ctx), "request->special is NULL so "
- "request not valid, sc_cmd=%p.\n", sc_cmd);
+ if (!sc_cmd->request) {
+ QEDF_WARN(&(qedf->dbg_ctx), "sc_cmd->request is NULL, "
+ "sc_cmd=%p.\n", sc_cmd);
return;
}
@@ -1142,6 +1180,19 @@
}
fcport = io_req->fcport;
+
+ /*
+ * When flush is active, let the cmds be completed from the cleanup
+ * context
+ */
+ if (test_bit(QEDF_RPORT_IN_TARGET_RESET, &fcport->flags) ||
+ (test_bit(QEDF_RPORT_IN_LUN_RESET, &fcport->flags) &&
+ sc_cmd->device->lun == (u64)fcport->lun_reset_lun)) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Dropping good completion xid=0x%x as fcport is flushing",
+ io_req->xid);
+ return;
+ }
qedf_parse_fcp_rsp(io_req, fcp_rsp);
@@ -1160,24 +1211,17 @@
fw_residual_flag = GET_FIELD(cqe->cqe_info.rsp_info.fw_error_flags,
FCOE_CQE_RSP_INFO_FW_UNDERRUN);
if (fw_residual_flag) {
- QEDF_ERR(&(qedf->dbg_ctx),
- "Firmware detected underrun: xid=0x%x fcp_rsp.flags=0x%02x "
- "fcp_resid=%d fw_residual=0x%x.\n", io_req->xid,
- fcp_rsp->rsp_flags.flags, io_req->fcp_resid,
- cqe->cqe_info.rsp_info.fw_residual);
+ QEDF_ERR(&qedf->dbg_ctx,
+ "Firmware detected underrun: xid=0x%x fcp_rsp.flags=0x%02x fcp_resid=%d fw_residual=0x%x lba=%02x%02x%02x%02x.\n",
+ io_req->xid, fcp_rsp->rsp_flags.flags,
+ io_req->fcp_resid,
+ cqe->cqe_info.rsp_info.fw_residual, sc_cmd->cmnd[2],
+ sc_cmd->cmnd[3], sc_cmd->cmnd[4], sc_cmd->cmnd[5]);
if (io_req->cdb_status == 0)
sc_cmd->result = (DID_ERROR << 16) | io_req->cdb_status;
else
sc_cmd->result = (DID_OK << 16) | io_req->cdb_status;
-
- /* Abort the command since we did not get all the data */
- init_completion(&io_req->abts_done);
- rval = qedf_initiate_abts(io_req, true);
- if (rval) {
- QEDF_ERR(&(qedf->dbg_ctx), "Failed to queue ABTS.\n");
- sc_cmd->result = (DID_ERROR << 16) | io_req->cdb_status;
- }
/*
* Set resid to the whole buffer length so we won't try to resue
@@ -1219,16 +1263,8 @@
/* Lower 14 bits */
qualifier = fcp_rsp->retry_delay_timer & 0x3FFF;
- if (qedf_retry_delay &&
- scope > 0 && qualifier > 0 &&
- qualifier <= 0x3FEF) {
- /* Check we don't go over the max */
- if (qualifier > QEDF_RETRY_DELAY_MAX)
- qualifier =
- QEDF_RETRY_DELAY_MAX;
- fcport->retry_delay_timestamp =
- jiffies + (qualifier * HZ / 10);
- }
+ if (qedf_retry_delay)
+ chk_scope = 1;
/* Record stats */
if (io_req->cdb_status ==
SAM_STAT_TASK_SET_FULL)
@@ -1239,6 +1275,36 @@
}
if (io_req->fcp_resid)
scsi_set_resid(sc_cmd, io_req->fcp_resid);
+
+ if (chk_scope == 1) {
+ if ((scope == 1 || scope == 2) &&
+ (qualifier > 0 && qualifier <= 0x3FEF)) {
+ /* Check we don't go over the max */
+ if (qualifier > QEDF_RETRY_DELAY_MAX) {
+ qualifier = QEDF_RETRY_DELAY_MAX;
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "qualifier = %d\n",
+ (fcp_rsp->retry_delay_timer &
+ 0x3FFF));
+ }
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Scope = %d and qualifier = %d",
+ scope, qualifier);
+ /* Take fcport->rport_lock to
+ * update the retry_delay_timestamp
+ */
+ spin_lock_irqsave(&fcport->rport_lock, flags);
+ fcport->retry_delay_timestamp =
+ jiffies + (qualifier * HZ / 10);
+ spin_unlock_irqrestore(&fcport->rport_lock,
+ flags);
+
+ } else {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "combination of scope = %d and qualifier = %d is not handled in qedf.\n",
+ scope, qualifier);
+ }
+ }
break;
default:
QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "fcp_status=%d.\n",
@@ -1250,6 +1316,12 @@
if (qedf_io_tracing)
qedf_trace_io(fcport, io_req, QEDF_IO_TRACE_RSP);
+ /*
+ * We wait till the end of the function to clear the
+ * outstanding bit in case we need to send an abort
+ */
+ clear_bit(QEDF_CMD_OUTSTANDING, &io_req->flags);
+
io_req->sc_cmd = NULL;
sc_cmd->SCp.ptr = NULL;
sc_cmd->scsi_done(sc_cmd);
@@ -1260,14 +1332,27 @@
void qedf_scsi_done(struct qedf_ctx *qedf, struct qedf_ioreq *io_req,
int result)
{
- u16 xid;
struct scsi_cmnd *sc_cmd;
int refcount;
- if (!io_req)
+ if (!io_req) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO, "io_req is NULL\n");
return;
+ }
- xid = io_req->xid;
+ if (test_and_set_bit(QEDF_CMD_ERR_SCSI_DONE, &io_req->flags)) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "io_req:%p scsi_done handling already done\n",
+ io_req);
+ return;
+ }
+
+ /*
+ * We will be done with this command after this call so clear the
+ * outstanding bit.
+ */
+ clear_bit(QEDF_CMD_OUTSTANDING, &io_req->flags);
+
sc_cmd = io_req->sc_cmd;
if (!sc_cmd) {
@@ -1275,10 +1360,48 @@
return;
}
+ if (!virt_addr_valid(sc_cmd)) {
+ QEDF_ERR(&qedf->dbg_ctx, "sc_cmd=%p is not valid.", sc_cmd);
+ goto bad_scsi_ptr;
+ }
+
if (!sc_cmd->SCp.ptr) {
QEDF_WARN(&(qedf->dbg_ctx), "SCp.ptr is NULL, returned in "
"another context.\n");
return;
+ }
+
+ if (!sc_cmd->device) {
+ QEDF_ERR(&qedf->dbg_ctx, "Device for sc_cmd %p is NULL.\n",
+ sc_cmd);
+ goto bad_scsi_ptr;
+ }
+
+ if (!virt_addr_valid(sc_cmd->device)) {
+ QEDF_ERR(&qedf->dbg_ctx,
+ "Device pointer for sc_cmd %p is bad.\n", sc_cmd);
+ goto bad_scsi_ptr;
+ }
+
+ if (!sc_cmd->sense_buffer) {
+ QEDF_ERR(&qedf->dbg_ctx,
+ "sc_cmd->sense_buffer for sc_cmd %p is NULL.\n",
+ sc_cmd);
+ goto bad_scsi_ptr;
+ }
+
+ if (!virt_addr_valid(sc_cmd->sense_buffer)) {
+ QEDF_ERR(&qedf->dbg_ctx,
+ "sc_cmd->sense_buffer for sc_cmd %p is bad.\n",
+ sc_cmd);
+ goto bad_scsi_ptr;
+ }
+
+ if (!sc_cmd->scsi_done) {
+ QEDF_ERR(&qedf->dbg_ctx,
+ "sc_cmd->scsi_done for sc_cmd %p is NULL.\n",
+ sc_cmd);
+ goto bad_scsi_ptr;
}
qedf_unmap_sg_list(qedf, io_req);
@@ -1307,6 +1430,15 @@
sc_cmd->SCp.ptr = NULL;
sc_cmd->scsi_done(sc_cmd);
kref_put(&io_req->refcount, qedf_release_cmd);
+ return;
+
+bad_scsi_ptr:
+ /*
+ * Clear the io_req->sc_cmd backpointer so we don't try to process
+ * this again
+ */
+ io_req->sc_cmd = NULL;
+ kref_put(&io_req->refcount, qedf_release_cmd); /* ID: 001 */
}
/*
@@ -1321,8 +1453,12 @@
u64 err_warn_bit_map;
u8 err_warn = 0xff;
- if (!cqe)
+ if (!cqe) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "cqe is NULL for io_req %p xid=0x%x\n",
+ io_req, io_req->xid);
return;
+ }
QEDF_ERR(&(io_req->fcport->qedf->dbg_ctx), "Warning CQE, "
"xid=0x%x\n", io_req->xid);
@@ -1384,8 +1520,21 @@
{
int rval;
- if (!cqe)
+ if (io_req == NULL) {
+ QEDF_INFO(NULL, QEDF_LOG_IO, "io_req is NULL.\n");
return;
+ }
+
+ if (io_req->fcport == NULL) {
+ QEDF_INFO(NULL, QEDF_LOG_IO, "fcport is NULL.\n");
+ return;
+ }
+
+ if (!cqe) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "cqe is NULL for io_req %p\n", io_req);
+ return;
+ }
QEDF_ERR(&(io_req->fcport->qedf->dbg_ctx), "Error detection CQE, "
"xid=0x%x\n", io_req->xid);
@@ -1398,6 +1547,16 @@
le32_to_cpu(cqe->cqe_info.err_info.tx_buf_off),
le32_to_cpu(cqe->cqe_info.err_info.rx_buf_off),
le32_to_cpu(cqe->cqe_info.err_info.rx_id));
+
+ /* When flush is active, let the cmds be flushed out from the cleanup context */
+ if (test_bit(QEDF_RPORT_IN_TARGET_RESET, &io_req->fcport->flags) ||
+ (test_bit(QEDF_RPORT_IN_LUN_RESET, &io_req->fcport->flags) &&
+ io_req->sc_cmd->device->lun == (u64)io_req->fcport->lun_reset_lun)) {
+ QEDF_ERR(&qedf->dbg_ctx,
+ "Dropping EQE for xid=0x%x as fcport is flushing",
+ io_req->xid);
+ return;
+ }
if (qedf->stop_io_on_error) {
qedf_stop_all_io(qedf);
@@ -1423,6 +1582,8 @@
*/
els_req->event = QEDF_IOREQ_EV_ELS_FLUSH;
+ clear_bit(QEDF_CMD_OUTSTANDING, &els_req->flags);
+
/* Cancel the timer */
cancel_delayed_work_sync(&els_req->timeout_work);
@@ -1445,9 +1606,15 @@
struct qedf_ctx *qedf;
struct qedf_cmd_mgr *cmd_mgr;
int i, rc;
+ unsigned long flags;
+ int flush_cnt = 0;
+ int wait_cnt = 100;
+ int refcount = 0;
- if (!fcport)
+ if (!fcport) {
+ QEDF_ERR(NULL, "fcport is NULL\n");
return;
+ }
/* Check that fcport is still offloaded */
if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
@@ -1456,18 +1623,102 @@
}
qedf = fcport->qedf;
+
+ if (!qedf) {
+ QEDF_ERR(NULL, "qedf is NULL.\n");
+ return;
+ }
+
+ /* Only wait for all commands to be queued in the Upload context */
+ if (test_bit(QEDF_RPORT_UPLOADING_CONNECTION, &fcport->flags) &&
+ (lun == -1)) {
+ while (atomic_read(&fcport->ios_to_queue)) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Waiting for %d I/Os to be queued\n",
+ atomic_read(&fcport->ios_to_queue));
+ if (wait_cnt == 0) {
+ QEDF_ERR(NULL,
+ "%d IOs request could not be queued\n",
+ atomic_read(&fcport->ios_to_queue));
+ }
+ msleep(20);
+ wait_cnt--;
+ }
+ }
+
cmd_mgr = qedf->cmd_mgr;
- QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "Flush active i/o's.\n");
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Flush active i/o's num=0x%x fcport=0x%p port_id=0x%06x scsi_id=%d.\n",
+ atomic_read(&fcport->num_active_ios), fcport,
+ fcport->rdata->ids.port_id, fcport->rport->scsi_target_id);
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO, "Locking flush mutex.\n");
+
+ mutex_lock(&qedf->flush_mutex);
+ if (lun == -1) {
+ set_bit(QEDF_RPORT_IN_TARGET_RESET, &fcport->flags);
+ } else {
+ set_bit(QEDF_RPORT_IN_LUN_RESET, &fcport->flags);
+ fcport->lun_reset_lun = lun;
+ }
for (i = 0; i < FCOE_PARAMS_NUM_TASKS; i++) {
io_req = &cmd_mgr->cmds[i];
if (!io_req)
continue;
+ if (!io_req->fcport)
+ continue;
+
+ spin_lock_irqsave(&cmd_mgr->lock, flags);
+
+ if (io_req->alloc) {
+ if (!test_bit(QEDF_CMD_OUTSTANDING, &io_req->flags)) {
+ if (io_req->cmd_type == QEDF_SCSI_CMD)
+ QEDF_ERR(&qedf->dbg_ctx,
+ "Allocated but not queued, xid=0x%x\n",
+ io_req->xid);
+ }
+ spin_unlock_irqrestore(&cmd_mgr->lock, flags);
+ } else {
+ spin_unlock_irqrestore(&cmd_mgr->lock, flags);
+ continue;
+ }
+
if (io_req->fcport != fcport)
continue;
- if (io_req->cmd_type == QEDF_ELS) {
+
+ /* In case of ABTS, CMD_OUTSTANDING is cleared on ABTS response,
+ * but RRQ is still pending.
+ * Workaround: Within qedf_send_rrq, we check if the fcport is
+ * NULL, and we drop the ref on the io_req to clean it up.
+ */
+ if (!test_bit(QEDF_CMD_OUTSTANDING, &io_req->flags)) {
+ refcount = kref_read(&io_req->refcount);
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Not outstanding, xid=0x%x, cmd_type=%d refcount=%d.\n",
+ io_req->xid, io_req->cmd_type, refcount);
+ /* If RRQ work has been queue, try to cancel it and
+ * free the io_req
+ */
+ if (atomic_read(&io_req->state) ==
+ QEDFC_CMD_ST_RRQ_WAIT) {
+ if (cancel_delayed_work_sync
+ (&io_req->rrq_work)) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Putting reference for pending RRQ work xid=0x%x.\n",
+ io_req->xid);
+ /* ID: 003 */
+ kref_put(&io_req->refcount,
+ qedf_release_cmd);
+ }
+ }
+ continue;
+ }
+
+ /* Only consider flushing ELS during target reset */
+ if (io_req->cmd_type == QEDF_ELS &&
+ lun == -1) {
rc = kref_get_unless_zero(&io_req->refcount);
if (!rc) {
QEDF_ERR(&(qedf->dbg_ctx),
@@ -1475,7 +1726,10 @@
io_req, io_req->xid);
continue;
}
+ qedf_initiate_cleanup(io_req, false);
+ flush_cnt++;
qedf_flush_els_req(qedf, io_req);
+
/*
* Release the kref and go back to the top of the
* loop.
@@ -1484,6 +1738,7 @@
}
if (io_req->cmd_type == QEDF_ABTS) {
+ /* ID: 004 */
rc = kref_get_unless_zero(&io_req->refcount);
if (!rc) {
QEDF_ERR(&(qedf->dbg_ctx),
@@ -1491,28 +1746,50 @@
io_req, io_req->xid);
continue;
}
+ if (lun != -1 && io_req->lun != lun)
+ goto free_cmd;
+
QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
"Flushing abort xid=0x%x.\n", io_req->xid);
- clear_bit(QEDF_CMD_IN_ABORT, &io_req->flags);
-
- if (io_req->sc_cmd) {
- if (io_req->return_scsi_cmd_on_abts)
- qedf_scsi_done(qedf, io_req, DID_ERROR);
+ if (cancel_delayed_work_sync(&io_req->rrq_work)) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Putting ref for cancelled RRQ work xid=0x%x.\n",
+ io_req->xid);
+ kref_put(&io_req->refcount, qedf_release_cmd);
}
- /* Notify eh_abort handler that ABTS is complete */
- complete(&io_req->abts_done);
- kref_put(&io_req->refcount, qedf_release_cmd);
-
+ if (cancel_delayed_work_sync(&io_req->timeout_work)) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Putting ref for cancelled tmo work xid=0x%x.\n",
+ io_req->xid);
+ qedf_initiate_cleanup(io_req, true);
+ /* Notify eh_abort handler that ABTS is
+ * complete
+ */
+ complete(&io_req->abts_done);
+ clear_bit(QEDF_CMD_IN_ABORT, &io_req->flags);
+ /* ID: 002 */
+ kref_put(&io_req->refcount, qedf_release_cmd);
+ }
+ flush_cnt++;
goto free_cmd;
}
if (!io_req->sc_cmd)
continue;
- if (lun > 0) {
- if (io_req->sc_cmd->device->lun !=
- (u64)lun)
+ if (!io_req->sc_cmd->device) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Device backpointer NULL for sc_cmd=%p.\n",
+ io_req->sc_cmd);
+ /* Put reference for non-existent scsi_cmnd */
+ io_req->sc_cmd = NULL;
+ qedf_initiate_cleanup(io_req, false);
+ kref_put(&io_req->refcount, qedf_release_cmd);
+ continue;
+ }
+ if (lun > -1) {
+ if (io_req->lun != lun)
continue;
}
@@ -1526,15 +1803,65 @@
"io_req=0x%p xid=0x%x\n", io_req, io_req->xid);
continue;
}
+
QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
"Cleanup xid=0x%x.\n", io_req->xid);
+ flush_cnt++;
/* Cleanup task and return I/O mid-layer */
qedf_initiate_cleanup(io_req, true);
free_cmd:
- kref_put(&io_req->refcount, qedf_release_cmd);
+ kref_put(&io_req->refcount, qedf_release_cmd); /* ID: 004 */
}
+
+ wait_cnt = 60;
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Flushed 0x%x I/Os, active=0x%x.\n",
+ flush_cnt, atomic_read(&fcport->num_active_ios));
+ /* Only wait for all commands to complete in the Upload context */
+ if (test_bit(QEDF_RPORT_UPLOADING_CONNECTION, &fcport->flags) &&
+ (lun == -1)) {
+ while (atomic_read(&fcport->num_active_ios)) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Flushed 0x%x I/Os, active=0x%x cnt=%d.\n",
+ flush_cnt,
+ atomic_read(&fcport->num_active_ios),
+ wait_cnt);
+ if (wait_cnt == 0) {
+ QEDF_ERR(&qedf->dbg_ctx,
+ "Flushed %d I/Os, active=%d.\n",
+ flush_cnt,
+ atomic_read(&fcport->num_active_ios));
+ for (i = 0; i < FCOE_PARAMS_NUM_TASKS; i++) {
+ io_req = &cmd_mgr->cmds[i];
+ if (io_req->fcport &&
+ io_req->fcport == fcport) {
+ refcount =
+ kref_read(&io_req->refcount);
+ set_bit(QEDF_CMD_DIRTY,
+ &io_req->flags);
+ QEDF_ERR(&qedf->dbg_ctx,
+ "Outstanding io_req =%p xid=0x%x flags=0x%lx, sc_cmd=%p refcount=%d cmd_type=%d.\n",
+ io_req, io_req->xid,
+ io_req->flags,
+ io_req->sc_cmd,
+ refcount,
+ io_req->cmd_type);
+ }
+ }
+ WARN_ON(1);
+ break;
+ }
+ msleep(500);
+ wait_cnt--;
+ }
+ }
+
+ clear_bit(QEDF_RPORT_IN_LUN_RESET, &fcport->flags);
+ clear_bit(QEDF_RPORT_IN_TARGET_RESET, &fcport->flags);
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO, "Unlocking flush mutex.\n");
+ mutex_unlock(&qedf->flush_mutex);
}
/*
@@ -1548,58 +1875,70 @@
struct fc_rport_priv *rdata;
struct qedf_ctx *qedf;
u16 xid;
- u32 r_a_tov = 0;
int rc = 0;
unsigned long flags;
struct fcoe_wqe *sqe;
u16 sqe_idx;
+ int refcount = 0;
/* Sanity check qedf_rport before dereferencing any pointers */
if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
QEDF_ERR(NULL, "tgt not offloaded\n");
rc = 1;
- goto abts_err;
+ goto out;
}
- rdata = fcport->rdata;
- r_a_tov = rdata->r_a_tov;
qedf = fcport->qedf;
+ rdata = fcport->rdata;
+
+ if (!rdata || !kref_get_unless_zero(&rdata->kref)) {
+ QEDF_ERR(&qedf->dbg_ctx, "stale rport\n");
+ rc = 1;
+ goto out;
+ }
+
lport = qedf->lport;
if (lport->state != LPORT_ST_READY || !(lport->link_up)) {
QEDF_ERR(&(qedf->dbg_ctx), "link is not ready\n");
rc = 1;
- goto abts_err;
+ goto drop_rdata_kref;
}
if (atomic_read(&qedf->link_down_tmo_valid) > 0) {
QEDF_ERR(&(qedf->dbg_ctx), "link_down_tmo active.\n");
rc = 1;
- goto abts_err;
+ goto drop_rdata_kref;
}
/* Ensure room on SQ */
if (!atomic_read(&fcport->free_sqes)) {
QEDF_ERR(&(qedf->dbg_ctx), "No SQ entries available\n");
rc = 1;
- goto abts_err;
+ goto drop_rdata_kref;
}
if (test_bit(QEDF_RPORT_UPLOADING_CONNECTION, &fcport->flags)) {
QEDF_ERR(&qedf->dbg_ctx, "fcport is uploading.\n");
rc = 1;
- goto out;
+ goto drop_rdata_kref;
}
+ spin_lock_irqsave(&fcport->rport_lock, flags);
if (!test_bit(QEDF_CMD_OUTSTANDING, &io_req->flags) ||
test_bit(QEDF_CMD_IN_CLEANUP, &io_req->flags) ||
test_bit(QEDF_CMD_IN_ABORT, &io_req->flags)) {
- QEDF_ERR(&(qedf->dbg_ctx), "io_req xid=0x%x already in "
- "cleanup or abort processing or already "
- "completed.\n", io_req->xid);
+ QEDF_ERR(&qedf->dbg_ctx,
+ "io_req xid=0x%x sc_cmd=%p already in cleanup or abort processing or already completed.\n",
+ io_req->xid, io_req->sc_cmd);
rc = 1;
- goto out;
+ spin_unlock_irqrestore(&fcport->rport_lock, flags);
+ goto drop_rdata_kref;
}
+
+ /* Set the command type to abort */
+ io_req->cmd_type = QEDF_ABTS;
+ spin_unlock_irqrestore(&fcport->rport_lock, flags);
kref_get(&io_req->refcount);
@@ -1607,18 +1946,15 @@
qedf->control_requests++;
qedf->packet_aborts++;
- /* Set the return CPU to be the same as the request one */
- io_req->cpu = smp_processor_id();
-
- /* Set the command type to abort */
- io_req->cmd_type = QEDF_ABTS;
io_req->return_scsi_cmd_on_abts = return_scsi_cmd_on_abts;
set_bit(QEDF_CMD_IN_ABORT, &io_req->flags);
- QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM, "ABTS io_req xid = "
- "0x%x\n", xid);
+ refcount = kref_read(&io_req->refcount);
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_SCSI_TM,
+ "ABTS io_req xid = 0x%x refcount=%d\n",
+ xid, refcount);
- qedf_cmd_timer_set(qedf, io_req, QEDF_ABORT_TIMEOUT * HZ);
+ qedf_cmd_timer_set(qedf, io_req, QEDF_ABORT_TIMEOUT);
spin_lock_irqsave(&fcport->rport_lock, flags);
@@ -1632,13 +1968,8 @@
spin_unlock_irqrestore(&fcport->rport_lock, flags);
- return rc;
-abts_err:
- /*
- * If the ABTS task fails to queue then we need to cleanup the
- * task at the firmware.
- */
- qedf_initiate_cleanup(io_req, return_scsi_cmd_on_abts);
+drop_rdata_kref:
+ kref_put(&rdata->kref, fc_rport_destroy);
out:
return rc;
}
@@ -1647,28 +1978,61 @@
struct qedf_ioreq *io_req)
{
uint32_t r_ctl;
- uint16_t xid;
+ int rc;
+ struct qedf_rport *fcport = io_req->fcport;
QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM, "Entered with xid = "
"0x%x cmd_type = %d\n", io_req->xid, io_req->cmd_type);
- cancel_delayed_work(&io_req->timeout_work);
-
- xid = io_req->xid;
r_ctl = cqe->cqe_info.abts_info.r_ctl;
+
+ /* This was added at a point when we were scheduling abts_compl &
+ * cleanup_compl on different CPUs and there was a possibility of
+ * the io_req to be freed from the other context before we got here.
+ */
+ if (!fcport) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Dropping ABTS completion xid=0x%x as fcport is NULL",
+ io_req->xid);
+ return;
+ }
+
+ /*
+ * When flush is active, let the cmds be completed from the cleanup
+ * context
+ */
+ if (test_bit(QEDF_RPORT_IN_TARGET_RESET, &fcport->flags) ||
+ test_bit(QEDF_RPORT_IN_LUN_RESET, &fcport->flags)) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Dropping ABTS completion xid=0x%x as fcport is flushing",
+ io_req->xid);
+ return;
+ }
+
+ if (!cancel_delayed_work(&io_req->timeout_work)) {
+ QEDF_ERR(&qedf->dbg_ctx,
+ "Wasn't able to cancel abts timeout work.\n");
+ }
switch (r_ctl) {
case FC_RCTL_BA_ACC:
QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM,
"ABTS response - ACC Send RRQ after R_A_TOV\n");
io_req->event = QEDF_IOREQ_EV_ABORT_SUCCESS;
+ rc = kref_get_unless_zero(&io_req->refcount); /* ID: 003 */
+ if (!rc) {
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_SCSI_TM,
+ "kref is already zero so ABTS was already completed or flushed xid=0x%x.\n",
+ io_req->xid);
+ return;
+ }
/*
* Dont release this cmd yet. It will be relesed
* after we get RRQ response
*/
- kref_get(&io_req->refcount);
queue_delayed_work(qedf->dpc_wq, &io_req->rrq_work,
msecs_to_jiffies(qedf->lport->r_a_tov));
+ atomic_set(&io_req->state, QEDFC_CMD_ST_RRQ_WAIT);
break;
/* For error cases let the cleanup return the command */
case FC_RCTL_BA_RJT:
@@ -1684,6 +2048,10 @@
clear_bit(QEDF_CMD_IN_ABORT, &io_req->flags);
if (io_req->sc_cmd) {
+ if (!io_req->return_scsi_cmd_on_abts)
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_SCSI_TM,
+ "Not call scsi_done for xid=0x%x.\n",
+ io_req->xid);
if (io_req->return_scsi_cmd_on_abts)
qedf_scsi_done(qedf, io_req, DID_ERROR);
}
@@ -1803,13 +2171,12 @@
{
struct qedf_rport *fcport;
struct qedf_ctx *qedf;
- uint16_t xid;
- struct e4_fcoe_task_context *task;
int tmo = 0;
int rc = SUCCESS;
unsigned long flags;
struct fcoe_wqe *sqe;
u16 sqe_idx;
+ int refcount = 0;
fcport = io_req->fcport;
if (!fcport) {
@@ -1820,7 +2187,6 @@
/* Sanity check qedf_rport before dereferencing any pointers */
if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
QEDF_ERR(NULL, "tgt not offloaded\n");
- rc = 1;
return SUCCESS;
}
@@ -1830,37 +2196,50 @@
return SUCCESS;
}
+ if (io_req->cmd_type == QEDF_ELS) {
+ goto process_els;
+ }
+
if (!test_bit(QEDF_CMD_OUTSTANDING, &io_req->flags) ||
- test_bit(QEDF_CMD_IN_CLEANUP, &io_req->flags)) {
+ test_and_set_bit(QEDF_CMD_IN_CLEANUP, &io_req->flags)) {
QEDF_ERR(&(qedf->dbg_ctx), "io_req xid=0x%x already in "
"cleanup processing or already completed.\n",
io_req->xid);
return SUCCESS;
}
+ set_bit(QEDF_CMD_IN_CLEANUP, &io_req->flags);
+process_els:
/* Ensure room on SQ */
if (!atomic_read(&fcport->free_sqes)) {
QEDF_ERR(&(qedf->dbg_ctx), "No SQ entries available\n");
+ /* Need to make sure we clear the flag since it was set */
+ clear_bit(QEDF_CMD_IN_CLEANUP, &io_req->flags);
return FAILED;
}
+ if (io_req->cmd_type == QEDF_CLEANUP) {
+ QEDF_ERR(&qedf->dbg_ctx,
+ "io_req=0x%x is already a cleanup command cmd_type=%d.\n",
+ io_req->xid, io_req->cmd_type);
+ clear_bit(QEDF_CMD_IN_CLEANUP, &io_req->flags);
+ return SUCCESS;
+ }
- QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "Entered xid=0x%x\n",
- io_req->xid);
+ refcount = kref_read(&io_req->refcount);
+
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_IO,
+ "Entered xid=0x%x sc_cmd=%p cmd_type=%d flags=0x%lx refcount=%d fcport=%p port_id=0x%06x\n",
+ io_req->xid, io_req->sc_cmd, io_req->cmd_type, io_req->flags,
+ refcount, fcport, fcport->rdata->ids.port_id);
/* Cleanup cmds re-use the same TID as the original I/O */
- xid = io_req->xid;
+ spin_lock_irqsave(&fcport->rport_lock, flags);
io_req->cmd_type = QEDF_CLEANUP;
+ spin_unlock_irqrestore(&fcport->rport_lock, flags);
io_req->return_scsi_cmd_on_abts = return_scsi_cmd_on_abts;
- /* Set the return CPU to be the same as the request one */
- io_req->cpu = smp_processor_id();
-
- set_bit(QEDF_CMD_IN_CLEANUP, &io_req->flags);
-
- task = qedf_get_task_mem(&qedf->tasks, xid);
-
- init_completion(&io_req->tm_done);
+ init_completion(&io_req->cleanup_done);
spin_lock_irqsave(&fcport->rport_lock, flags);
@@ -1874,8 +2253,8 @@
spin_unlock_irqrestore(&fcport->rport_lock, flags);
- tmo = wait_for_completion_timeout(&io_req->tm_done,
- QEDF_CLEANUP_TIMEOUT * HZ);
+ tmo = wait_for_completion_timeout(&io_req->cleanup_done,
+ QEDF_CLEANUP_TIMEOUT * HZ);
if (!tmo) {
rc = FAILED;
@@ -1888,7 +2267,22 @@
qedf_drain_request(qedf);
}
+ /* If it TASK MGMT handle it, reference will be decreased
+ * in qedf_execute_tmf
+ */
+ if (io_req->tm_flags == FCP_TMF_LUN_RESET ||
+ io_req->tm_flags == FCP_TMF_TGT_RESET) {
+ clear_bit(QEDF_CMD_OUTSTANDING, &io_req->flags);
+ io_req->sc_cmd = NULL;
+ kref_put(&io_req->refcount, qedf_release_cmd);
+ complete(&io_req->tm_done);
+ }
+
if (io_req->sc_cmd) {
+ if (!io_req->return_scsi_cmd_on_abts)
+ QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_SCSI_TM,
+ "Not call scsi_done for xid=0x%x.\n",
+ io_req->xid);
if (io_req->return_scsi_cmd_on_abts)
qedf_scsi_done(qedf, io_req, DID_ERROR);
}
@@ -1910,7 +2304,7 @@
clear_bit(QEDF_CMD_IN_CLEANUP, &io_req->flags);
/* Complete so we can finish cleaning up the I/O */
- complete(&io_req->tm_done);
+ complete(&io_req->cleanup_done);
}
static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd,
@@ -1923,29 +2317,28 @@
int rc = 0;
uint16_t xid;
int tmo = 0;
+ int lun = 0;
unsigned long flags;
struct fcoe_wqe *sqe;
u16 sqe_idx;
if (!sc_cmd) {
- QEDF_ERR(&(qedf->dbg_ctx), "invalid arg\n");
+ QEDF_ERR(&qedf->dbg_ctx, "sc_cmd is NULL\n");
return FAILED;
}
+ lun = (int)sc_cmd->device->lun;
if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
QEDF_ERR(&(qedf->dbg_ctx), "fcport not offloaded\n");
rc = FAILED;
- return FAILED;
+ goto no_flush;
}
-
- QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM, "portid = 0x%x "
- "tm_flags = %d\n", fcport->rdata->ids.port_id, tm_flags);
io_req = qedf_alloc_cmd(fcport, QEDF_TASK_MGMT_CMD);
if (!io_req) {
QEDF_ERR(&(qedf->dbg_ctx), "Failed TMF");
rc = -EAGAIN;
- goto reset_tmf_err;
+ goto no_flush;
}
if (tm_flags == FCP_TMF_LUN_RESET)
@@ -1958,7 +2351,7 @@
io_req->fcport = fcport;
io_req->cmd_type = QEDF_TASK_MGMT_CMD;
- /* Set the return CPU to be the same as the request one */
+ /* Record which cpu this request is associated with */
io_req->cpu = smp_processor_id();
/* Set TM flags */
@@ -1967,7 +2360,7 @@
io_req->tm_flags = tm_flags;
/* Default is to return a SCSI command when an error occurs */
- io_req->return_scsi_cmd_on_abts = true;
+ io_req->return_scsi_cmd_on_abts = false;
/* Obtain exchange id */
xid = io_req->xid;
@@ -1991,12 +2384,16 @@
spin_unlock_irqrestore(&fcport->rport_lock, flags);
+ set_bit(QEDF_CMD_OUTSTANDING, &io_req->flags);
tmo = wait_for_completion_timeout(&io_req->tm_done,
QEDF_TM_TIMEOUT * HZ);
if (!tmo) {
rc = FAILED;
QEDF_ERR(&(qedf->dbg_ctx), "wait for tm_cmpl timeout!\n");
+ /* Clear outstanding bit since command timed out */
+ clear_bit(QEDF_CMD_OUTSTANDING, &io_req->flags);
+ io_req->sc_cmd = NULL;
} else {
/* Check TMF response code */
if (io_req->fcp_rsp_code == 0)
@@ -2004,14 +2401,25 @@
else
rc = FAILED;
}
+ /*
+ * Double check that fcport has not gone into an uploading state before
+ * executing the command flush for the LUN/target.
+ */
+ if (test_bit(QEDF_RPORT_UPLOADING_CONNECTION, &fcport->flags)) {
+ QEDF_ERR(&qedf->dbg_ctx,
+ "fcport is uploading, not executing flush.\n");
+ goto no_flush;
+ }
+ /* We do not need this io_req any more */
+ kref_put(&io_req->refcount, qedf_release_cmd);
+
if (tm_flags == FCP_TMF_LUN_RESET)
- qedf_flush_active_ios(fcport, (int)sc_cmd->device->lun);
+ qedf_flush_active_ios(fcport, lun);
else
qedf_flush_active_ios(fcport, -1);
- kref_put(&io_req->refcount, qedf_release_cmd);
-
+no_flush:
if (rc != SUCCESS) {
QEDF_ERR(&(qedf->dbg_ctx), "task mgmt command failed...\n");
rc = FAILED;
@@ -2019,7 +2427,6 @@
QEDF_ERR(&(qedf->dbg_ctx), "task mgmt command success...\n");
rc = SUCCESS;
}
-reset_tmf_err:
return rc;
}
@@ -2029,26 +2436,65 @@
struct fc_rport_libfc_priv *rp = rport->dd_data;
struct qedf_rport *fcport = (struct qedf_rport *)&rp[1];
struct qedf_ctx *qedf;
- struct fc_lport *lport;
+ struct fc_lport *lport = shost_priv(sc_cmd->device->host);
int rc = SUCCESS;
int rval;
+ struct qedf_ioreq *io_req = NULL;
+ int ref_cnt = 0;
+ struct fc_rport_priv *rdata = fcport->rdata;
+
+ QEDF_ERR(NULL,
+ "tm_flags 0x%x sc_cmd %p op = 0x%02x target_id = 0x%x lun=%d\n",
+ tm_flags, sc_cmd, sc_cmd->cmd_len ? sc_cmd->cmnd[0] : 0xff,
+ rport->scsi_target_id, (int)sc_cmd->device->lun);
+
+ if (!rdata || !kref_get_unless_zero(&rdata->kref)) {
+ QEDF_ERR(NULL, "stale rport\n");
+ return FAILED;
+ }
+
+ QEDF_ERR(NULL, "portid=%06x tm_flags =%s\n", rdata->ids.port_id,
+ (tm_flags == FCP_TMF_TGT_RESET) ? "TARGET RESET" :
+ "LUN RESET");
+
+ if (sc_cmd->SCp.ptr) {
+ io_req = (struct qedf_ioreq *)sc_cmd->SCp.ptr;
+ ref_cnt = kref_read(&io_req->refcount);
+ QEDF_ERR(NULL,
+ "orig io_req = %p xid = 0x%x ref_cnt = %d.\n",
+ io_req, io_req->xid, ref_cnt);
+ }
rval = fc_remote_port_chkready(rport);
-
if (rval) {
QEDF_ERR(NULL, "device_reset rport not ready\n");
rc = FAILED;
goto tmf_err;
}
- if (fcport == NULL) {
+ rc = fc_block_scsi_eh(sc_cmd);
+ if (rc)
+ goto tmf_err;
+
+ if (!fcport) {
QEDF_ERR(NULL, "device_reset: rport is NULL\n");
rc = FAILED;
goto tmf_err;
}
qedf = fcport->qedf;
- lport = qedf->lport;
+
+ if (!qedf) {
+ QEDF_ERR(NULL, "qedf is NULL.\n");
+ rc = FAILED;
+ goto tmf_err;
+ }
+
+ if (test_bit(QEDF_RPORT_UPLOADING_CONNECTION, &fcport->flags)) {
+ QEDF_ERR(&qedf->dbg_ctx, "Connection is getting uploaded.\n");
+ rc = SUCCESS;
+ goto tmf_err;
+ }
if (test_bit(QEDF_UNLOADING, &qedf->flags) ||
test_bit(QEDF_DBG_STOP_IO, &qedf->flags)) {
@@ -2062,9 +2508,22 @@
goto tmf_err;
}
+ if (test_bit(QEDF_RPORT_UPLOADING_CONNECTION, &fcport->flags)) {
+ if (!fcport->rdata)
+ QEDF_ERR(&qedf->dbg_ctx, "fcport %p is uploading.\n",
+ fcport);
+ else
+ QEDF_ERR(&qedf->dbg_ctx,
+ "fcport %p port_id=%06x is uploading.\n",
+ fcport, fcport->rdata->ids.port_id);
+ rc = FAILED;
+ goto tmf_err;
+ }
+
rc = qedf_execute_tmf(fcport, sc_cmd, tm_flags);
tmf_err:
+ kref_put(&rdata->kref, fc_rport_destroy);
return rc;
}
@@ -2072,6 +2531,8 @@
struct qedf_ioreq *io_req)
{
struct fcoe_cqe_rsp_info *fcp_rsp;
+
+ clear_bit(QEDF_CMD_OUTSTANDING, &io_req->flags);
fcp_rsp = &cqe->cqe_info.rsp_info;
qedf_parse_fcp_rsp(io_req, fcp_rsp);
@@ -2084,7 +2545,6 @@
struct fcoe_cqe *cqe)
{
unsigned long flags;
- uint16_t tmp;
uint16_t pktlen = cqe->cqe_info.unsolic_info.pkt_len;
u32 payload_len, crc;
struct fc_frame_header *fh;
@@ -2136,6 +2596,11 @@
fh = (struct fc_frame_header *)fc_frame_header_get(fp);
memcpy(fh, (void *)bdq_addr, pktlen);
+ QEDF_WARN(&qedf->dbg_ctx,
+ "Processing Unsolicated frame, src=%06x dest=%06x r_ctl=0x%x type=0x%x cmd=%02x\n",
+ ntoh24(fh->fh_s_id), ntoh24(fh->fh_d_id), fh->fh_r_ctl,
+ fh->fh_type, fc_frame_payload_op(fp));
+
/* Initialize the frame so libfc sees it as a valid frame */
crc = fcoe_fc_crc(fp);
fc_frame_init(fp);
@@ -2177,9 +2642,9 @@
qedf->bdq_prod_idx = 0;
writew(qedf->bdq_prod_idx, qedf->bdq_primary_prod);
- tmp = readw(qedf->bdq_primary_prod);
+ readw(qedf->bdq_primary_prod);
writew(qedf->bdq_prod_idx, qedf->bdq_secondary_prod);
- tmp = readw(qedf->bdq_secondary_prod);
+ readw(qedf->bdq_secondary_prod);
spin_unlock_irqrestore(&qedf->hba_lock, flags);
}
--
Gitblit v1.6.2