OpenCloudOS-Kernel/drivers/scsi/bnx2fc/bnx2fc_io.c

2103 lines
57 KiB
C
Raw Normal View History

/* bnx2fc_io.c: QLogic Linux FCoE offload driver.
* IO manager and SCSI IO processing.
*
* Copyright (c) 2008-2013 Broadcom Corporation
* Copyright (c) 2014-2016 QLogic Corporation
* Copyright (c) 2016-2017 Cavium Inc.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation.
*
* Written by: Bhanu Prakash Gollapudi (bprakash@broadcom.com)
*/
#include "bnx2fc.h"
#define RESERVE_FREE_LIST_INDEX num_possible_cpus()
static int bnx2fc_split_bd(struct bnx2fc_cmd *io_req, u64 addr, int sg_len,
int bd_index);
static int bnx2fc_map_sg(struct bnx2fc_cmd *io_req);
static int bnx2fc_build_bd_list_from_sg(struct bnx2fc_cmd *io_req);
static void bnx2fc_unmap_sg_list(struct bnx2fc_cmd *io_req);
static void bnx2fc_free_mp_resc(struct bnx2fc_cmd *io_req);
static void bnx2fc_parse_fcp_rsp(struct bnx2fc_cmd *io_req,
struct fcoe_fcp_rsp_payload *fcp_rsp,
u8 num_rq, unsigned char *rq_data);
void bnx2fc_cmd_timer_set(struct bnx2fc_cmd *io_req,
unsigned int timer_msec)
{
struct bnx2fc_interface *interface = io_req->port->priv;
if (queue_delayed_work(interface->timer_work_queue,
&io_req->timeout_work,
msecs_to_jiffies(timer_msec)))
kref_get(&io_req->refcount);
}
static void bnx2fc_cmd_timeout(struct work_struct *work)
{
struct bnx2fc_cmd *io_req = container_of(work, struct bnx2fc_cmd,
timeout_work.work);
u8 cmd_type = io_req->cmd_type;
struct bnx2fc_rport *tgt = io_req->tgt;
int rc;
BNX2FC_IO_DBG(io_req, "cmd_timeout, cmd_type = %d,"
"req_flags = %lx\n", cmd_type, io_req->req_flags);
spin_lock_bh(&tgt->tgt_lock);
if (test_and_clear_bit(BNX2FC_FLAG_ISSUE_RRQ, &io_req->req_flags)) {
clear_bit(BNX2FC_FLAG_RETIRE_OXID, &io_req->req_flags);
/*
* ideally we should hold the io_req until RRQ complets,
* and release io_req from timeout hold.
*/
spin_unlock_bh(&tgt->tgt_lock);
bnx2fc_send_rrq(io_req);
return;
}
if (test_and_clear_bit(BNX2FC_FLAG_RETIRE_OXID, &io_req->req_flags)) {
BNX2FC_IO_DBG(io_req, "IO ready for reuse now\n");
goto done;
}
switch (cmd_type) {
case BNX2FC_SCSI_CMD:
if (test_and_clear_bit(BNX2FC_FLAG_EH_ABORT,
&io_req->req_flags)) {
/* Handle eh_abort timeout */
BNX2FC_IO_DBG(io_req, "eh_abort timed out\n");
complete(&io_req->abts_done);
} else if (test_bit(BNX2FC_FLAG_ISSUE_ABTS,
&io_req->req_flags)) {
/* Handle internally generated ABTS timeout */
BNX2FC_IO_DBG(io_req, "ABTS timed out refcnt = %d\n",
kref_read(&io_req->refcount));
if (!(test_and_set_bit(BNX2FC_FLAG_ABTS_DONE,
&io_req->req_flags))) {
/*
* Cleanup and return original command to
* mid-layer.
*/
bnx2fc_initiate_cleanup(io_req);
kref_put(&io_req->refcount, bnx2fc_cmd_release);
spin_unlock_bh(&tgt->tgt_lock);
return;
}
} else {
/* Hanlde IO timeout */
BNX2FC_IO_DBG(io_req, "IO timed out. issue ABTS\n");
if (test_and_set_bit(BNX2FC_FLAG_IO_COMPL,
&io_req->req_flags)) {
BNX2FC_IO_DBG(io_req, "IO completed before "
" timer expiry\n");
goto done;
}
if (!test_and_set_bit(BNX2FC_FLAG_ISSUE_ABTS,
&io_req->req_flags)) {
rc = bnx2fc_initiate_abts(io_req);
if (rc == SUCCESS)
goto done;
kref_put(&io_req->refcount, bnx2fc_cmd_release);
spin_unlock_bh(&tgt->tgt_lock);
return;
} else {
BNX2FC_IO_DBG(io_req, "IO already in "
"ABTS processing\n");
}
}
break;
case BNX2FC_ELS:
if (test_bit(BNX2FC_FLAG_ISSUE_ABTS, &io_req->req_flags)) {
BNX2FC_IO_DBG(io_req, "ABTS for ELS timed out\n");
if (!test_and_set_bit(BNX2FC_FLAG_ABTS_DONE,
&io_req->req_flags)) {
kref_put(&io_req->refcount, bnx2fc_cmd_release);
spin_unlock_bh(&tgt->tgt_lock);
return;
}
} else {
/*
* Handle ELS timeout.
* tgt_lock is used to sync compl path and timeout
* path. If els compl path is processing this IO, we
* have nothing to do here, just release the timer hold
*/
BNX2FC_IO_DBG(io_req, "ELS timed out\n");
if (test_and_set_bit(BNX2FC_FLAG_ELS_DONE,
&io_req->req_flags))
goto done;
/* Indicate the cb_func that this ELS is timed out */
set_bit(BNX2FC_FLAG_ELS_TIMEOUT, &io_req->req_flags);
if ((io_req->cb_func) && (io_req->cb_arg)) {
io_req->cb_func(io_req->cb_arg);
io_req->cb_arg = NULL;
}
}
break;
default:
printk(KERN_ERR PFX "cmd_timeout: invalid cmd_type %d\n",
cmd_type);
break;
}
done:
/* release the cmd that was held when timer was set */
kref_put(&io_req->refcount, bnx2fc_cmd_release);
spin_unlock_bh(&tgt->tgt_lock);
}
static void bnx2fc_scsi_done(struct bnx2fc_cmd *io_req, int err_code)
{
/* Called with host lock held */
struct scsi_cmnd *sc_cmd = io_req->sc_cmd;
/*
* active_cmd_queue may have other command types as well,
* and during flush operation, we want to error back only
* scsi commands.
*/
if (io_req->cmd_type != BNX2FC_SCSI_CMD)
return;
BNX2FC_IO_DBG(io_req, "scsi_done. err_code = 0x%x\n", err_code);
if (test_bit(BNX2FC_FLAG_CMD_LOST, &io_req->req_flags)) {
/* Do not call scsi done for this IO */
return;
}
bnx2fc_unmap_sg_list(io_req);
io_req->sc_cmd = NULL;
/* Sanity checks before returning command to mid-layer */
if (!sc_cmd) {
printk(KERN_ERR PFX "scsi_done - sc_cmd NULL. "
"IO(0x%x) already cleaned up\n",
io_req->xid);
return;
}
if (!sc_cmd->device) {
pr_err(PFX "0x%x: sc_cmd->device is NULL.\n", io_req->xid);
return;
}
if (!sc_cmd->device->host) {
pr_err(PFX "0x%x: sc_cmd->device->host is NULL.\n",
io_req->xid);
return;
}
sc_cmd->result = err_code << 16;
BNX2FC_IO_DBG(io_req, "sc=%p, result=0x%x, retries=%d, allowed=%d\n",
sc_cmd, host_byte(sc_cmd->result), sc_cmd->retries,
sc_cmd->allowed);
scsi_set_resid(sc_cmd, scsi_bufflen(sc_cmd));
bnx2fc_priv(sc_cmd)->io_req = NULL;
scsi_done(sc_cmd);
}
struct bnx2fc_cmd_mgr *bnx2fc_cmd_mgr_alloc(struct bnx2fc_hba *hba)
{
struct bnx2fc_cmd_mgr *cmgr;
struct io_bdt *bdt_info;
struct bnx2fc_cmd *io_req;
size_t len;
u32 mem_size;
u16 xid;
int i;
int num_ios, num_pri_ios;
size_t bd_tbl_sz;
int arr_sz = num_possible_cpus() + 1;
u16 min_xid = BNX2FC_MIN_XID;
u16 max_xid = hba->max_xid;
if (max_xid <= min_xid || max_xid == FC_XID_UNKNOWN) {
printk(KERN_ERR PFX "cmd_mgr_alloc: Invalid min_xid 0x%x \
and max_xid 0x%x\n", min_xid, max_xid);
return NULL;
}
BNX2FC_MISC_DBG("min xid 0x%x, max xid 0x%x\n", min_xid, max_xid);
num_ios = max_xid - min_xid + 1;
len = (num_ios * (sizeof(struct bnx2fc_cmd *)));
len += sizeof(struct bnx2fc_cmd_mgr);
cmgr = kzalloc(len, GFP_KERNEL);
if (!cmgr) {
printk(KERN_ERR PFX "failed to alloc cmgr\n");
return NULL;
}
cmgr->hba = hba;
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:03:40 +08:00
cmgr->free_list = kcalloc(arr_sz, sizeof(*cmgr->free_list),
GFP_KERNEL);
if (!cmgr->free_list) {
printk(KERN_ERR PFX "failed to alloc free_list\n");
goto mem_err;
}
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:03:40 +08:00
cmgr->free_list_lock = kcalloc(arr_sz, sizeof(*cmgr->free_list_lock),
GFP_KERNEL);
if (!cmgr->free_list_lock) {
printk(KERN_ERR PFX "failed to alloc free_list_lock\n");
kfree(cmgr->free_list);
cmgr->free_list = NULL;
goto mem_err;
}
cmgr->cmds = (struct bnx2fc_cmd **)(cmgr + 1);
for (i = 0; i < arr_sz; i++) {
INIT_LIST_HEAD(&cmgr->free_list[i]);
spin_lock_init(&cmgr->free_list_lock[i]);
}
/*
* Pre-allocated pool of bnx2fc_cmds.
* Last entry in the free list array is the free list
* of slow path requests.
*/
xid = BNX2FC_MIN_XID;
num_pri_ios = num_ios - hba->elstm_xids;
for (i = 0; i < num_ios; i++) {
io_req = kzalloc(sizeof(*io_req), GFP_KERNEL);
if (!io_req) {
printk(KERN_ERR PFX "failed to alloc io_req\n");
goto mem_err;
}
INIT_LIST_HEAD(&io_req->link);
INIT_DELAYED_WORK(&io_req->timeout_work, bnx2fc_cmd_timeout);
io_req->xid = xid++;
if (i < num_pri_ios)
list_add_tail(&io_req->link,
&cmgr->free_list[io_req->xid %
num_possible_cpus()]);
else
list_add_tail(&io_req->link,
&cmgr->free_list[num_possible_cpus()]);
io_req++;
}
/* Allocate pool of io_bdts - one for each bnx2fc_cmd */
mem_size = num_ios * sizeof(struct io_bdt *);
cmgr->io_bdt_pool = kzalloc(mem_size, GFP_KERNEL);
if (!cmgr->io_bdt_pool) {
printk(KERN_ERR PFX "failed to alloc io_bdt_pool\n");
goto mem_err;
}
mem_size = sizeof(struct io_bdt);
for (i = 0; i < num_ios; i++) {
cmgr->io_bdt_pool[i] = kmalloc(mem_size, GFP_KERNEL);
if (!cmgr->io_bdt_pool[i]) {
printk(KERN_ERR PFX "failed to alloc "
"io_bdt_pool[%d]\n", i);
goto mem_err;
}
}
/* Allocate an map fcoe_bdt_ctx structures */
bd_tbl_sz = BNX2FC_MAX_BDS_PER_CMD * sizeof(struct fcoe_bd_ctx);
for (i = 0; i < num_ios; i++) {
bdt_info = cmgr->io_bdt_pool[i];
bdt_info->bd_tbl = dma_alloc_coherent(&hba->pcidev->dev,
bd_tbl_sz,
&bdt_info->bd_tbl_dma,
GFP_KERNEL);
if (!bdt_info->bd_tbl) {
printk(KERN_ERR PFX "failed to alloc "
"bdt_tbl[%d]\n", i);
goto mem_err;
}
}
return cmgr;
mem_err:
bnx2fc_cmd_mgr_free(cmgr);
return NULL;
}
void bnx2fc_cmd_mgr_free(struct bnx2fc_cmd_mgr *cmgr)
{
struct io_bdt *bdt_info;
struct bnx2fc_hba *hba = cmgr->hba;
size_t bd_tbl_sz;
u16 min_xid = BNX2FC_MIN_XID;
u16 max_xid = hba->max_xid;
int num_ios;
int i;
num_ios = max_xid - min_xid + 1;
/* Free fcoe_bdt_ctx structures */
if (!cmgr->io_bdt_pool)
goto free_cmd_pool;
bd_tbl_sz = BNX2FC_MAX_BDS_PER_CMD * sizeof(struct fcoe_bd_ctx);
for (i = 0; i < num_ios; i++) {
bdt_info = cmgr->io_bdt_pool[i];
if (bdt_info->bd_tbl) {
dma_free_coherent(&hba->pcidev->dev, bd_tbl_sz,
bdt_info->bd_tbl,
bdt_info->bd_tbl_dma);
bdt_info->bd_tbl = NULL;
}
}
/* Destroy io_bdt pool */
for (i = 0; i < num_ios; i++) {
kfree(cmgr->io_bdt_pool[i]);
cmgr->io_bdt_pool[i] = NULL;
}
kfree(cmgr->io_bdt_pool);
cmgr->io_bdt_pool = NULL;
free_cmd_pool:
kfree(cmgr->free_list_lock);
/* Destroy cmd pool */
if (!cmgr->free_list)
goto free_cmgr;
for (i = 0; i < num_possible_cpus() + 1; i++) {
struct bnx2fc_cmd *tmp, *io_req;
list_for_each_entry_safe(io_req, tmp,
&cmgr->free_list[i], link) {
list_del(&io_req->link);
kfree(io_req);
}
}
kfree(cmgr->free_list);
free_cmgr:
/* Free command manager itself */
kfree(cmgr);
}
struct bnx2fc_cmd *bnx2fc_elstm_alloc(struct bnx2fc_rport *tgt, int type)
{
struct fcoe_port *port = tgt->port;
struct bnx2fc_interface *interface = port->priv;
struct bnx2fc_cmd_mgr *cmd_mgr = interface->hba->cmd_mgr;
struct bnx2fc_cmd *io_req;
struct list_head *listp;
struct io_bdt *bd_tbl;
int index = RESERVE_FREE_LIST_INDEX;
u32 free_sqes;
u32 max_sqes;
u16 xid;
max_sqes = tgt->max_sqes;
switch (type) {
case BNX2FC_TASK_MGMT_CMD:
max_sqes = BNX2FC_TM_MAX_SQES;
break;
case BNX2FC_ELS:
max_sqes = BNX2FC_ELS_MAX_SQES;
break;
default:
break;
}
/*
* NOTE: Free list insertions and deletions are protected with
* cmgr lock
*/
spin_lock_bh(&cmd_mgr->free_list_lock[index]);
free_sqes = atomic_read(&tgt->free_sqes);
if ((list_empty(&(cmd_mgr->free_list[index]))) ||
(tgt->num_active_ios.counter >= max_sqes) ||
(free_sqes + max_sqes <= BNX2FC_SQ_WQES_MAX)) {
BNX2FC_TGT_DBG(tgt, "No free els_tm cmds available "
"ios(%d):sqes(%d)\n",
tgt->num_active_ios.counter, tgt->max_sqes);
if (list_empty(&(cmd_mgr->free_list[index])))
printk(KERN_ERR PFX "elstm_alloc: list_empty\n");
spin_unlock_bh(&cmd_mgr->free_list_lock[index]);
return NULL;
}
listp = (struct list_head *)
cmd_mgr->free_list[index].next;
list_del_init(listp);
io_req = (struct bnx2fc_cmd *) listp;
xid = io_req->xid;
cmd_mgr->cmds[xid] = io_req;
atomic_inc(&tgt->num_active_ios);
atomic_dec(&tgt->free_sqes);
spin_unlock_bh(&cmd_mgr->free_list_lock[index]);
INIT_LIST_HEAD(&io_req->link);
io_req->port = port;
io_req->cmd_mgr = cmd_mgr;
io_req->req_flags = 0;
io_req->cmd_type = type;
/* Bind io_bdt for this io_req */
/* Have a static link between io_req and io_bdt_pool */
bd_tbl = io_req->bd_tbl = cmd_mgr->io_bdt_pool[xid];
bd_tbl->io_req = io_req;
/* Hold the io_req against deletion */
kref_init(&io_req->refcount);
return io_req;
}
struct bnx2fc_cmd *bnx2fc_cmd_alloc(struct bnx2fc_rport *tgt)
{
struct fcoe_port *port = tgt->port;
struct bnx2fc_interface *interface = port->priv;
struct bnx2fc_cmd_mgr *cmd_mgr = interface->hba->cmd_mgr;
struct bnx2fc_cmd *io_req;
struct list_head *listp;
struct io_bdt *bd_tbl;
u32 free_sqes;
u32 max_sqes;
u16 xid;
int index = raw_smp_processor_id();
max_sqes = BNX2FC_SCSI_MAX_SQES;
/*
* NOTE: Free list insertions and deletions are protected with
* cmgr lock
*/
spin_lock_bh(&cmd_mgr->free_list_lock[index]);
free_sqes = atomic_read(&tgt->free_sqes);
if ((list_empty(&cmd_mgr->free_list[index])) ||
(tgt->num_active_ios.counter >= max_sqes) ||
(free_sqes + max_sqes <= BNX2FC_SQ_WQES_MAX)) {
spin_unlock_bh(&cmd_mgr->free_list_lock[index]);
return NULL;
}
listp = (struct list_head *)
cmd_mgr->free_list[index].next;
list_del_init(listp);
io_req = (struct bnx2fc_cmd *) listp;
xid = io_req->xid;
cmd_mgr->cmds[xid] = io_req;
atomic_inc(&tgt->num_active_ios);
atomic_dec(&tgt->free_sqes);
spin_unlock_bh(&cmd_mgr->free_list_lock[index]);
INIT_LIST_HEAD(&io_req->link);
io_req->port = port;
io_req->cmd_mgr = cmd_mgr;
io_req->req_flags = 0;
/* Bind io_bdt for this io_req */
/* Have a static link between io_req and io_bdt_pool */
bd_tbl = io_req->bd_tbl = cmd_mgr->io_bdt_pool[xid];
bd_tbl->io_req = io_req;
/* Hold the io_req against deletion */
kref_init(&io_req->refcount);
return io_req;
}
void bnx2fc_cmd_release(struct kref *ref)
{
struct bnx2fc_cmd *io_req = container_of(ref,
struct bnx2fc_cmd, refcount);
struct bnx2fc_cmd_mgr *cmd_mgr = io_req->cmd_mgr;
int index;
if (io_req->cmd_type == BNX2FC_SCSI_CMD)
index = io_req->xid % num_possible_cpus();
else
index = RESERVE_FREE_LIST_INDEX;
spin_lock_bh(&cmd_mgr->free_list_lock[index]);
if (io_req->cmd_type != BNX2FC_SCSI_CMD)
bnx2fc_free_mp_resc(io_req);
cmd_mgr->cmds[io_req->xid] = NULL;
/* Delete IO from retire queue */
list_del_init(&io_req->link);
/* Add it to the free list */
list_add(&io_req->link,
&cmd_mgr->free_list[index]);
atomic_dec(&io_req->tgt->num_active_ios);
spin_unlock_bh(&cmd_mgr->free_list_lock[index]);
}
static void bnx2fc_free_mp_resc(struct bnx2fc_cmd *io_req)
{
struct bnx2fc_mp_req *mp_req = &(io_req->mp_req);
struct bnx2fc_interface *interface = io_req->port->priv;
struct bnx2fc_hba *hba = interface->hba;
size_t sz = sizeof(struct fcoe_bd_ctx);
/* clear tm flags */
mp_req->tm_flags = 0;
if (mp_req->mp_req_bd) {
dma_free_coherent(&hba->pcidev->dev, sz,
mp_req->mp_req_bd,
mp_req->mp_req_bd_dma);
mp_req->mp_req_bd = NULL;
}
if (mp_req->mp_resp_bd) {
dma_free_coherent(&hba->pcidev->dev, sz,
mp_req->mp_resp_bd,
mp_req->mp_resp_bd_dma);
mp_req->mp_resp_bd = NULL;
}
if (mp_req->req_buf) {
dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
mp_req->req_buf,
mp_req->req_buf_dma);
mp_req->req_buf = NULL;
}
if (mp_req->resp_buf) {
dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
mp_req->resp_buf,
mp_req->resp_buf_dma);
mp_req->resp_buf = NULL;
}
}
int bnx2fc_init_mp_req(struct bnx2fc_cmd *io_req)
{
struct bnx2fc_mp_req *mp_req;
struct fcoe_bd_ctx *mp_req_bd;
struct fcoe_bd_ctx *mp_resp_bd;
struct bnx2fc_interface *interface = io_req->port->priv;
struct bnx2fc_hba *hba = interface->hba;
dma_addr_t addr;
size_t sz;
mp_req = (struct bnx2fc_mp_req *)&(io_req->mp_req);
memset(mp_req, 0, sizeof(struct bnx2fc_mp_req));
if (io_req->cmd_type != BNX2FC_ELS) {
mp_req->req_len = sizeof(struct fcp_cmnd);
io_req->data_xfer_len = mp_req->req_len;
} else
mp_req->req_len = io_req->data_xfer_len;
mp_req->req_buf = dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
&mp_req->req_buf_dma,
GFP_ATOMIC);
if (!mp_req->req_buf) {
printk(KERN_ERR PFX "unable to alloc MP req buffer\n");
bnx2fc_free_mp_resc(io_req);
return FAILED;
}
mp_req->resp_buf = dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
&mp_req->resp_buf_dma,
GFP_ATOMIC);
if (!mp_req->resp_buf) {
printk(KERN_ERR PFX "unable to alloc TM resp buffer\n");
bnx2fc_free_mp_resc(io_req);
return FAILED;
}
memset(mp_req->req_buf, 0, CNIC_PAGE_SIZE);
memset(mp_req->resp_buf, 0, CNIC_PAGE_SIZE);
/* Allocate and map mp_req_bd and mp_resp_bd */
sz = sizeof(struct fcoe_bd_ctx);
mp_req->mp_req_bd = dma_alloc_coherent(&hba->pcidev->dev, sz,
&mp_req->mp_req_bd_dma,
GFP_ATOMIC);
if (!mp_req->mp_req_bd) {
printk(KERN_ERR PFX "unable to alloc MP req bd\n");
bnx2fc_free_mp_resc(io_req);
return FAILED;
}
mp_req->mp_resp_bd = dma_alloc_coherent(&hba->pcidev->dev, sz,
&mp_req->mp_resp_bd_dma,
GFP_ATOMIC);
if (!mp_req->mp_resp_bd) {
printk(KERN_ERR PFX "unable to alloc MP resp bd\n");
bnx2fc_free_mp_resc(io_req);
return FAILED;
}
/* Fill bd table */
addr = mp_req->req_buf_dma;
mp_req_bd = mp_req->mp_req_bd;
mp_req_bd->buf_addr_lo = (u32)addr & 0xffffffff;
mp_req_bd->buf_addr_hi = (u32)((u64)addr >> 32);
mp_req_bd->buf_len = CNIC_PAGE_SIZE;
mp_req_bd->flags = 0;
/*
* MP buffer is either a task mgmt command or an ELS.
* So the assumption is that it consumes a single bd
* entry in the bd table
*/
mp_resp_bd = mp_req->mp_resp_bd;
addr = mp_req->resp_buf_dma;
mp_resp_bd->buf_addr_lo = (u32)addr & 0xffffffff;
mp_resp_bd->buf_addr_hi = (u32)((u64)addr >> 32);
mp_resp_bd->buf_len = CNIC_PAGE_SIZE;
mp_resp_bd->flags = 0;
return SUCCESS;
}
static int bnx2fc_initiate_tmf(struct scsi_cmnd *sc_cmd, u8 tm_flags)
{
struct fc_lport *lport;
struct fc_rport *rport;
struct fc_rport_libfc_priv *rp;
struct fcoe_port *port;
struct bnx2fc_interface *interface;
struct bnx2fc_rport *tgt;
struct bnx2fc_cmd *io_req;
struct bnx2fc_mp_req *tm_req;
struct fcoe_task_ctx_entry *task;
struct fcoe_task_ctx_entry *task_page;
struct Scsi_Host *host = sc_cmd->device->host;
struct fc_frame_header *fc_hdr;
struct fcp_cmnd *fcp_cmnd;
int task_idx, index;
int rc = SUCCESS;
u16 xid;
u32 sid, did;
unsigned long start = jiffies;
lport = shost_priv(host);
rport = starget_to_rport(scsi_target(sc_cmd->device));
port = lport_priv(lport);
interface = port->priv;
if (rport == NULL) {
printk(KERN_ERR PFX "device_reset: rport is NULL\n");
rc = FAILED;
goto tmf_err;
}
rp = rport->dd_data;
rc = fc_block_scsi_eh(sc_cmd);
if (rc)
return rc;
if (lport->state != LPORT_ST_READY || !(lport->link_up)) {
printk(KERN_ERR PFX "device_reset: link is not ready\n");
rc = FAILED;
goto tmf_err;
}
/* rport and tgt are allocated together, so tgt should be non-NULL */
tgt = (struct bnx2fc_rport *)&rp[1];
if (!(test_bit(BNX2FC_FLAG_SESSION_READY, &tgt->flags))) {
printk(KERN_ERR PFX "device_reset: tgt not offloaded\n");
rc = FAILED;
goto tmf_err;
}
retry_tmf:
io_req = bnx2fc_elstm_alloc(tgt, BNX2FC_TASK_MGMT_CMD);
if (!io_req) {
if (time_after(jiffies, start + HZ)) {
printk(KERN_ERR PFX "tmf: Failed TMF");
rc = FAILED;
goto tmf_err;
}
msleep(20);
goto retry_tmf;
}
/* Initialize rest of io_req fields */
io_req->sc_cmd = sc_cmd;
io_req->port = port;
io_req->tgt = tgt;
tm_req = (struct bnx2fc_mp_req *)&(io_req->mp_req);
rc = bnx2fc_init_mp_req(io_req);
if (rc == FAILED) {
printk(KERN_ERR PFX "Task mgmt MP request init failed\n");
spin_lock_bh(&tgt->tgt_lock);
kref_put(&io_req->refcount, bnx2fc_cmd_release);
spin_unlock_bh(&tgt->tgt_lock);
goto tmf_err;
}
/* Set TM flags */
io_req->io_req_flags = 0;
tm_req->tm_flags = tm_flags;
/* Fill FCP_CMND */
bnx2fc_build_fcp_cmnd(io_req, (struct fcp_cmnd *)tm_req->req_buf);
fcp_cmnd = (struct fcp_cmnd *)tm_req->req_buf;
memset(fcp_cmnd->fc_cdb, 0, sc_cmd->cmd_len);
fcp_cmnd->fc_dl = 0;
/* Fill FC header */
fc_hdr = &(tm_req->req_fc_hdr);
sid = tgt->sid;
did = rport->port_id;
__fc_fill_fc_hdr(fc_hdr, FC_RCTL_DD_UNSOL_CMD, did, sid,
FC_TYPE_FCP, FC_FC_FIRST_SEQ | FC_FC_END_SEQ |
FC_FC_SEQ_INIT, 0);
/* Obtain exchange id */
xid = io_req->xid;
BNX2FC_TGT_DBG(tgt, "Initiate TMF - xid = 0x%x\n", xid);
task_idx = xid/BNX2FC_TASKS_PER_PAGE;
index = xid % BNX2FC_TASKS_PER_PAGE;
/* Initialize task context for this IO request */
task_page = (struct fcoe_task_ctx_entry *)
interface->hba->task_ctx[task_idx];
task = &(task_page[index]);
bnx2fc_init_mp_task(io_req, task);
bnx2fc_priv(sc_cmd)->io_req = io_req;
/* Obtain free SQ entry */
spin_lock_bh(&tgt->tgt_lock);
bnx2fc_add_2_sq(tgt, xid);
/* Enqueue the io_req to active_tm_queue */
io_req->on_tmf_queue = 1;
list_add_tail(&io_req->link, &tgt->active_tm_queue);
init_completion(&io_req->abts_done);
io_req->wait_for_abts_comp = 1;
/* Ring doorbell */
bnx2fc_ring_doorbell(tgt);
spin_unlock_bh(&tgt->tgt_lock);
rc = wait_for_completion_timeout(&io_req->abts_done,
interface->tm_timeout * HZ);
spin_lock_bh(&tgt->tgt_lock);
io_req->wait_for_abts_comp = 0;
if (!(test_bit(BNX2FC_FLAG_TM_COMPL, &io_req->req_flags))) {
set_bit(BNX2FC_FLAG_TM_TIMEOUT, &io_req->req_flags);
if (io_req->on_tmf_queue) {
list_del_init(&io_req->link);
io_req->on_tmf_queue = 0;
}
io_req->wait_for_cleanup_comp = 1;
init_completion(&io_req->cleanup_done);
bnx2fc_initiate_cleanup(io_req);
spin_unlock_bh(&tgt->tgt_lock);
rc = wait_for_completion_timeout(&io_req->cleanup_done,
BNX2FC_FW_TIMEOUT);
spin_lock_bh(&tgt->tgt_lock);
io_req->wait_for_cleanup_comp = 0;
if (!rc)
kref_put(&io_req->refcount, bnx2fc_cmd_release);
}
spin_unlock_bh(&tgt->tgt_lock);
if (!rc) {
BNX2FC_TGT_DBG(tgt, "task mgmt command failed...\n");
rc = FAILED;
} else {
BNX2FC_TGT_DBG(tgt, "task mgmt command success...\n");
rc = SUCCESS;
}
tmf_err:
return rc;
}
int bnx2fc_initiate_abts(struct bnx2fc_cmd *io_req)
{
struct fc_lport *lport;
struct bnx2fc_rport *tgt = io_req->tgt;
struct fc_rport *rport = tgt->rport;
struct fc_rport_priv *rdata = tgt->rdata;
struct bnx2fc_interface *interface;
struct fcoe_port *port;
struct bnx2fc_cmd *abts_io_req;
struct fcoe_task_ctx_entry *task;
struct fcoe_task_ctx_entry *task_page;
struct fc_frame_header *fc_hdr;
struct bnx2fc_mp_req *abts_req;
int task_idx, index;
u32 sid, did;
u16 xid;
int rc = SUCCESS;
u32 r_a_tov = rdata->r_a_tov;
/* called with tgt_lock held */
BNX2FC_IO_DBG(io_req, "Entered bnx2fc_initiate_abts\n");
port = io_req->port;
interface = port->priv;
lport = port->lport;
if (!test_bit(BNX2FC_FLAG_SESSION_READY, &tgt->flags)) {
printk(KERN_ERR PFX "initiate_abts: tgt not offloaded\n");
rc = FAILED;
goto abts_err;
}
if (rport == NULL) {
printk(KERN_ERR PFX "initiate_abts: rport is NULL\n");
rc = FAILED;
goto abts_err;
}
if (lport->state != LPORT_ST_READY || !(lport->link_up)) {
printk(KERN_ERR PFX "initiate_abts: link is not ready\n");
rc = FAILED;
goto abts_err;
}
abts_io_req = bnx2fc_elstm_alloc(tgt, BNX2FC_ABTS);
if (!abts_io_req) {
printk(KERN_ERR PFX "abts: couldn't allocate cmd\n");
rc = FAILED;
goto abts_err;
}
/* Initialize rest of io_req fields */
abts_io_req->sc_cmd = NULL;
abts_io_req->port = port;
abts_io_req->tgt = tgt;
abts_io_req->data_xfer_len = 0; /* No data transfer for ABTS */
abts_req = (struct bnx2fc_mp_req *)&(abts_io_req->mp_req);
memset(abts_req, 0, sizeof(struct bnx2fc_mp_req));
/* Fill FC header */
fc_hdr = &(abts_req->req_fc_hdr);
/* Obtain oxid and rxid for the original exchange to be aborted */
fc_hdr->fh_ox_id = htons(io_req->xid);
fc_hdr->fh_rx_id = htons(io_req->task->rxwr_txrd.var_ctx.rx_id);
sid = tgt->sid;
did = rport->port_id;
__fc_fill_fc_hdr(fc_hdr, FC_RCTL_BA_ABTS, did, sid,
FC_TYPE_BLS, FC_FC_FIRST_SEQ | FC_FC_END_SEQ |
FC_FC_SEQ_INIT, 0);
xid = abts_io_req->xid;
BNX2FC_IO_DBG(abts_io_req, "ABTS io_req\n");
task_idx = xid/BNX2FC_TASKS_PER_PAGE;
index = xid % BNX2FC_TASKS_PER_PAGE;
/* Initialize task context for this IO request */
task_page = (struct fcoe_task_ctx_entry *)
interface->hba->task_ctx[task_idx];
task = &(task_page[index]);
bnx2fc_init_mp_task(abts_io_req, task);
/*
* ABTS task is a temporary task that will be cleaned up
* irrespective of ABTS response. We need to start the timer
* for the original exchange, as the CQE is posted for the original
* IO request.
*
* Timer for ABTS is started only when it is originated by a
* TM request. For the ABTS issued as part of ULP timeout,
* scsi-ml maintains the timers.
*/
/* if (test_bit(BNX2FC_FLAG_ISSUE_ABTS, &io_req->req_flags))*/
bnx2fc_cmd_timer_set(io_req, 2 * r_a_tov);
/* Obtain free SQ entry */
bnx2fc_add_2_sq(tgt, xid);
/* Ring doorbell */
bnx2fc_ring_doorbell(tgt);
abts_err:
return rc;
}
int bnx2fc_initiate_seq_cleanup(struct bnx2fc_cmd *orig_io_req, u32 offset,
enum fc_rctl r_ctl)
{
struct bnx2fc_rport *tgt = orig_io_req->tgt;
struct bnx2fc_interface *interface;
struct fcoe_port *port;
struct bnx2fc_cmd *seq_clnp_req;
struct fcoe_task_ctx_entry *task;
struct fcoe_task_ctx_entry *task_page;
struct bnx2fc_els_cb_arg *cb_arg = NULL;
int task_idx, index;
u16 xid;
int rc = 0;
BNX2FC_IO_DBG(orig_io_req, "bnx2fc_initiate_seq_cleanup xid = 0x%x\n",
orig_io_req->xid);
kref_get(&orig_io_req->refcount);
port = orig_io_req->port;
interface = port->priv;
cb_arg = kzalloc(sizeof(struct bnx2fc_els_cb_arg), GFP_ATOMIC);
if (!cb_arg) {
printk(KERN_ERR PFX "Unable to alloc cb_arg for seq clnup\n");
rc = -ENOMEM;
goto cleanup_err;
}
seq_clnp_req = bnx2fc_elstm_alloc(tgt, BNX2FC_SEQ_CLEANUP);
if (!seq_clnp_req) {
printk(KERN_ERR PFX "cleanup: couldn't allocate cmd\n");
rc = -ENOMEM;
kfree(cb_arg);
goto cleanup_err;
}
/* Initialize rest of io_req fields */
seq_clnp_req->sc_cmd = NULL;
seq_clnp_req->port = port;
seq_clnp_req->tgt = tgt;
seq_clnp_req->data_xfer_len = 0; /* No data transfer for cleanup */
xid = seq_clnp_req->xid;
task_idx = xid/BNX2FC_TASKS_PER_PAGE;
index = xid % BNX2FC_TASKS_PER_PAGE;
/* Initialize task context for this IO request */
task_page = (struct fcoe_task_ctx_entry *)
interface->hba->task_ctx[task_idx];
task = &(task_page[index]);
cb_arg->aborted_io_req = orig_io_req;
cb_arg->io_req = seq_clnp_req;
cb_arg->r_ctl = r_ctl;
cb_arg->offset = offset;
seq_clnp_req->cb_arg = cb_arg;
printk(KERN_ERR PFX "call init_seq_cleanup_task\n");
bnx2fc_init_seq_cleanup_task(seq_clnp_req, task, orig_io_req, offset);
/* Obtain free SQ entry */
bnx2fc_add_2_sq(tgt, xid);
/* Ring doorbell */
bnx2fc_ring_doorbell(tgt);
cleanup_err:
return rc;
}
int bnx2fc_initiate_cleanup(struct bnx2fc_cmd *io_req)
{
struct bnx2fc_rport *tgt = io_req->tgt;
struct bnx2fc_interface *interface;
struct fcoe_port *port;
struct bnx2fc_cmd *cleanup_io_req;
struct fcoe_task_ctx_entry *task;
struct fcoe_task_ctx_entry *task_page;
int task_idx, index;
u16 xid, orig_xid;
int rc = 0;
/* ASSUMPTION: called with tgt_lock held */
BNX2FC_IO_DBG(io_req, "Entered bnx2fc_initiate_cleanup\n");
port = io_req->port;
interface = port->priv;
cleanup_io_req = bnx2fc_elstm_alloc(tgt, BNX2FC_CLEANUP);
if (!cleanup_io_req) {
printk(KERN_ERR PFX "cleanup: couldn't allocate cmd\n");
rc = -1;
goto cleanup_err;
}
/* Initialize rest of io_req fields */
cleanup_io_req->sc_cmd = NULL;
cleanup_io_req->port = port;
cleanup_io_req->tgt = tgt;
cleanup_io_req->data_xfer_len = 0; /* No data transfer for cleanup */
xid = cleanup_io_req->xid;
task_idx = xid/BNX2FC_TASKS_PER_PAGE;
index = xid % BNX2FC_TASKS_PER_PAGE;
/* Initialize task context for this IO request */
task_page = (struct fcoe_task_ctx_entry *)
interface->hba->task_ctx[task_idx];
task = &(task_page[index]);
orig_xid = io_req->xid;
BNX2FC_IO_DBG(io_req, "CLEANUP io_req xid = 0x%x\n", xid);
bnx2fc_init_cleanup_task(cleanup_io_req, task, orig_xid);
/* Obtain free SQ entry */
bnx2fc_add_2_sq(tgt, xid);
/* Set flag that cleanup request is pending with the firmware */
set_bit(BNX2FC_FLAG_ISSUE_CLEANUP_REQ, &io_req->req_flags);
/* Ring doorbell */
bnx2fc_ring_doorbell(tgt);
cleanup_err:
return rc;
}
/**
* bnx2fc_eh_target_reset: Reset a target
*
* @sc_cmd: SCSI command
*
* Set from SCSI host template to send task mgmt command to the target
* and wait for the response
*/
int bnx2fc_eh_target_reset(struct scsi_cmnd *sc_cmd)
{
return bnx2fc_initiate_tmf(sc_cmd, FCP_TMF_TGT_RESET);
}
/**
* bnx2fc_eh_device_reset - Reset a single LUN
*
* @sc_cmd: SCSI command
*
* Set from SCSI host template to send task mgmt command to the target
* and wait for the response
*/
int bnx2fc_eh_device_reset(struct scsi_cmnd *sc_cmd)
{
return bnx2fc_initiate_tmf(sc_cmd, FCP_TMF_LUN_RESET);
}
static int bnx2fc_abts_cleanup(struct bnx2fc_cmd *io_req)
__must_hold(&tgt->tgt_lock)
{
struct bnx2fc_rport *tgt = io_req->tgt;
scsi: bnx2fc: Fix hung task messages when a cleanup response is not received during abort If a cleanup task is not responded to while we are in bnx2fc_abts_cleanup, it will hang the SCSI error handler since we use wait_for_completion instead of wait_for_completion_timeout. So, use wait_for_completion_timeout so that we don't hang the SCSI error handler thread forever. Fixes the call trace: [183373.131468] INFO: task scsi_eh_16:110146 blocked for more than 120 seconds. [183373.131469] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [183373.131470] scsi_eh_16 D ffff88103f2fca14 0 110146 2 0x00000080 [183373.131472] ffff880855e77cb0 0000000000000046 ffff881050654e70 ffff880855e77fd8 [183373.131474] ffff880855e77fd8 ffff880855e77fd8 ffff881050654e70 ffff88103f2fcb48 [183373.131475] ffff88103f2fcb50 7fffffffffffffff ffff881050654e70 ffff88103f2fca14 [183373.131477] Call Trace: [183373.131479] [<ffffffff8168b579>] schedule+0x29/0x70 [183373.131481] [<ffffffff81688fc9>] schedule_timeout+0x239/0x2d0 [183373.131486] [<ffffffff8142821e>] ? __dev_printk+0x3e/0x90 [183373.131487] [<ffffffff814282cd>] ? dev_printk+0x5d/0x80 [183373.131490] [<ffffffff8168b956>] wait_for_completion+0x116/0x170 [183373.131492] [<ffffffff810c4ec0>] ? wake_up_state+0x20/0x20 [183373.131494] [<ffffffffa048c234>] bnx2fc_abts_cleanup+0x3d/0x62 [bnx2fc] [183373.131497] [<ffffffffa0483a80>] bnx2fc_eh_abort+0x470/0x580 [bnx2fc] [183373.131500] [<ffffffff814570af>] scsi_error_handler+0x59f/0x8b0 [183373.131501] [<ffffffff81456b10>] ? scsi_eh_get_sense+0x250/0x250 [183373.131503] [<ffffffff810b052f>] kthread+0xcf/0xe0 [183373.131505] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [183373.131507] [<ffffffff81696418>] ret_from_fork+0x58/0x90 [183373.131509] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Signed-off-by: Chad Dupuis <chad.dupuis@cavium.com> Reviewed-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-11-15 23:06:06 +08:00
unsigned int time_left;
init_completion(&io_req->cleanup_done);
io_req->wait_for_cleanup_comp = 1;
bnx2fc_initiate_cleanup(io_req);
spin_unlock_bh(&tgt->tgt_lock);
scsi: bnx2fc: Fix hung task messages when a cleanup response is not received during abort If a cleanup task is not responded to while we are in bnx2fc_abts_cleanup, it will hang the SCSI error handler since we use wait_for_completion instead of wait_for_completion_timeout. So, use wait_for_completion_timeout so that we don't hang the SCSI error handler thread forever. Fixes the call trace: [183373.131468] INFO: task scsi_eh_16:110146 blocked for more than 120 seconds. [183373.131469] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [183373.131470] scsi_eh_16 D ffff88103f2fca14 0 110146 2 0x00000080 [183373.131472] ffff880855e77cb0 0000000000000046 ffff881050654e70 ffff880855e77fd8 [183373.131474] ffff880855e77fd8 ffff880855e77fd8 ffff881050654e70 ffff88103f2fcb48 [183373.131475] ffff88103f2fcb50 7fffffffffffffff ffff881050654e70 ffff88103f2fca14 [183373.131477] Call Trace: [183373.131479] [<ffffffff8168b579>] schedule+0x29/0x70 [183373.131481] [<ffffffff81688fc9>] schedule_timeout+0x239/0x2d0 [183373.131486] [<ffffffff8142821e>] ? __dev_printk+0x3e/0x90 [183373.131487] [<ffffffff814282cd>] ? dev_printk+0x5d/0x80 [183373.131490] [<ffffffff8168b956>] wait_for_completion+0x116/0x170 [183373.131492] [<ffffffff810c4ec0>] ? wake_up_state+0x20/0x20 [183373.131494] [<ffffffffa048c234>] bnx2fc_abts_cleanup+0x3d/0x62 [bnx2fc] [183373.131497] [<ffffffffa0483a80>] bnx2fc_eh_abort+0x470/0x580 [bnx2fc] [183373.131500] [<ffffffff814570af>] scsi_error_handler+0x59f/0x8b0 [183373.131501] [<ffffffff81456b10>] ? scsi_eh_get_sense+0x250/0x250 [183373.131503] [<ffffffff810b052f>] kthread+0xcf/0xe0 [183373.131505] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [183373.131507] [<ffffffff81696418>] ret_from_fork+0x58/0x90 [183373.131509] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Signed-off-by: Chad Dupuis <chad.dupuis@cavium.com> Reviewed-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-11-15 23:06:06 +08:00
/*
* Can't wait forever on cleanup response lest we let the SCSI error
* handler wait forever
*/
time_left = wait_for_completion_timeout(&io_req->cleanup_done,
scsi: bnx2fc: Fix hung task messages when a cleanup response is not received during abort If a cleanup task is not responded to while we are in bnx2fc_abts_cleanup, it will hang the SCSI error handler since we use wait_for_completion instead of wait_for_completion_timeout. So, use wait_for_completion_timeout so that we don't hang the SCSI error handler thread forever. Fixes the call trace: [183373.131468] INFO: task scsi_eh_16:110146 blocked for more than 120 seconds. [183373.131469] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [183373.131470] scsi_eh_16 D ffff88103f2fca14 0 110146 2 0x00000080 [183373.131472] ffff880855e77cb0 0000000000000046 ffff881050654e70 ffff880855e77fd8 [183373.131474] ffff880855e77fd8 ffff880855e77fd8 ffff881050654e70 ffff88103f2fcb48 [183373.131475] ffff88103f2fcb50 7fffffffffffffff ffff881050654e70 ffff88103f2fca14 [183373.131477] Call Trace: [183373.131479] [<ffffffff8168b579>] schedule+0x29/0x70 [183373.131481] [<ffffffff81688fc9>] schedule_timeout+0x239/0x2d0 [183373.131486] [<ffffffff8142821e>] ? __dev_printk+0x3e/0x90 [183373.131487] [<ffffffff814282cd>] ? dev_printk+0x5d/0x80 [183373.131490] [<ffffffff8168b956>] wait_for_completion+0x116/0x170 [183373.131492] [<ffffffff810c4ec0>] ? wake_up_state+0x20/0x20 [183373.131494] [<ffffffffa048c234>] bnx2fc_abts_cleanup+0x3d/0x62 [bnx2fc] [183373.131497] [<ffffffffa0483a80>] bnx2fc_eh_abort+0x470/0x580 [bnx2fc] [183373.131500] [<ffffffff814570af>] scsi_error_handler+0x59f/0x8b0 [183373.131501] [<ffffffff81456b10>] ? scsi_eh_get_sense+0x250/0x250 [183373.131503] [<ffffffff810b052f>] kthread+0xcf/0xe0 [183373.131505] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [183373.131507] [<ffffffff81696418>] ret_from_fork+0x58/0x90 [183373.131509] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Signed-off-by: Chad Dupuis <chad.dupuis@cavium.com> Reviewed-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-11-15 23:06:06 +08:00
BNX2FC_FW_TIMEOUT);
scsi: bnx2fc: Only put reference to io_req in bnx2fc_abts_cleanup if cleanup times out In certain tests where the SCSI error handler issues an abort that is already outstanding, we will cleanup the command so that the SCSI error handler can proceed. In some of these cases we were seeing a command mismatch: kernel: scsi host2: bnx2fc: xid:0x42b eh_abort - refcnt = 2 kernel: bnx2fc: eh_abort: io_req (xid = 0x42b) already in abts processing kernel: scsi host2: bnx2fc: xid:0x42b Entered bnx2fc_initiate_cleanup kernel: scsi host2: bnx2fc: xid:0x42b CLEANUP io_req xid = 0x80b kernel: scsi host2: bnx2fc: xid:0x80b cq_compl- cleanup resp rcvd kernel: scsi host2: bnx2fc: xid:0x42b complete - rx_state = 9 kernel: scsi host2: bnx2fc: xid:0x42b Entered process_cleanup_compl refcnt = 2, cmd_type = 1 kernel: scsi host2: bnx2fc: xid:0x42b scsi_done. err_code = 0x7 kernel: scsi host2: bnx2fc: xid:0x42b sc=ffff8807f93dfb80, result=0x7, retries=0, allowed=5 kernel: ------------[ cut here ]------------ kernel: WARNING: at /root/rpmbuild/BUILD/netxtreme2-7.14.43/obj/default/bnx2fc-2.12.1/driver/bnx2fc_io.c:1347 bnx2fc_eh_abort+0x56f/0x680 [bnx2fc]() kernel: xid=0x42b refcount=-1 kernel: Modules linked in: kernel: nls_utf8 isofs sr_mod cdrom tcp_lp dm_round_robin xt_CHECKSUM iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 tun bridge ebtable_filter ebtables fuse ip6table_filter ip6_tables iptable_filter bnx2fc(OE) cnic(OE) uio fcoe libfcoe 8021q libfc garp mrp scsi_transport_fc stp llc scsi_tgt vfat fat dm_service_time intel_powerclamp coretemp intel_rapl iosf_mbi kvm_intel kvm irqbypass crc32_pclmul ghash_clmulni_intel aesni_intel lrw gf128mul glue_helper ablk_helper cryptd ses enclosure ipmi_ssif i2c_core hpilo hpwdt wmi sg ipmi_devintf pcspkr ipmi_si ipmi_msghandler shpchp acpi_power_meter dm_multipath nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs sd_mod crc_t10dif kernel: crct10dif_generic bnx2x(OE) crct10dif_pclmul crct10dif_common crc32c_intel mdio ptp pps_core libcrc32c smartpqi scsi_transport_sas fjes uas usb_storage dm_mirror dm_region_hash dm_log dm_mod kernel: CPU: 9 PID: 2012 Comm: scsi_eh_2 Tainted: G W OE ------------ 3.10.0-514.el7.x86_64 #1 kernel: Hardware name: HPE Synergy 480 Gen10/Synergy 480 Gen10 Compute Module, BIOS I42 03/21/2018 kernel: ffff8807f25a3d98 0000000015e7fa0c ffff8807f25a3d50 ffffffff81685eac kernel: ffff8807f25a3d88 ffffffff81085820 ffff8807f8e39000 ffff880801ff7468 kernel: ffff880801ff7610 0000000000002002 ffff8807f8e39014 ffff8807f25a3df0 kernel: Call Trace: kernel: [<ffffffff81685eac>] dump_stack+0x19/0x1b kernel: [<ffffffff81085820>] warn_slowpath_common+0x70/0xb0 kernel: [<ffffffff810858bc>] warn_slowpath_fmt+0x5c/0x80 kernel: [<ffffffff8168d842>] ? _raw_spin_lock_bh+0x12/0x50 kernel: [<ffffffffa0549e6f>] bnx2fc_eh_abort+0x56f/0x680 [bnx2fc] kernel: [<ffffffff814570af>] scsi_error_handler+0x59f/0x8b0 kernel: [<ffffffff81456b10>] ? scsi_eh_get_sense+0x250/0x250 kernel: [<ffffffff810b052f>] kthread+0xcf/0xe0 kernel: [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 kernel: [<ffffffff81696418>] ret_from_fork+0x58/0x90 kernel: [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 kernel: ---[ end trace 42deb88f2032b111 ]--- The reason that there was a mismatch is that the SCSI command is actual returned from the cleanup handler. In previous testing, the type of cleanup notification we'd get from the CQE did not trigger the code that returned the SCSI command. To overcome the previous behavior we would put a reference in bnx2fc_abts_cleanup() to account for the SCSI command. However, in cases where the SCSI command is actually off, we end up with an extra put. The fix for this is to only take the extra put in bnx2fc_abts_cleanup if the completion for the cleanup times out. Signed-off-by: Chad Dupuis <cdupuis@marvell.com> Signed-off-by: Saurav Kashyap <skashyap@marvell.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-06-24 16:29:56 +08:00
if (!time_left) {
scsi: bnx2fc: Fix hung task messages when a cleanup response is not received during abort If a cleanup task is not responded to while we are in bnx2fc_abts_cleanup, it will hang the SCSI error handler since we use wait_for_completion instead of wait_for_completion_timeout. So, use wait_for_completion_timeout so that we don't hang the SCSI error handler thread forever. Fixes the call trace: [183373.131468] INFO: task scsi_eh_16:110146 blocked for more than 120 seconds. [183373.131469] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [183373.131470] scsi_eh_16 D ffff88103f2fca14 0 110146 2 0x00000080 [183373.131472] ffff880855e77cb0 0000000000000046 ffff881050654e70 ffff880855e77fd8 [183373.131474] ffff880855e77fd8 ffff880855e77fd8 ffff881050654e70 ffff88103f2fcb48 [183373.131475] ffff88103f2fcb50 7fffffffffffffff ffff881050654e70 ffff88103f2fca14 [183373.131477] Call Trace: [183373.131479] [<ffffffff8168b579>] schedule+0x29/0x70 [183373.131481] [<ffffffff81688fc9>] schedule_timeout+0x239/0x2d0 [183373.131486] [<ffffffff8142821e>] ? __dev_printk+0x3e/0x90 [183373.131487] [<ffffffff814282cd>] ? dev_printk+0x5d/0x80 [183373.131490] [<ffffffff8168b956>] wait_for_completion+0x116/0x170 [183373.131492] [<ffffffff810c4ec0>] ? wake_up_state+0x20/0x20 [183373.131494] [<ffffffffa048c234>] bnx2fc_abts_cleanup+0x3d/0x62 [bnx2fc] [183373.131497] [<ffffffffa0483a80>] bnx2fc_eh_abort+0x470/0x580 [bnx2fc] [183373.131500] [<ffffffff814570af>] scsi_error_handler+0x59f/0x8b0 [183373.131501] [<ffffffff81456b10>] ? scsi_eh_get_sense+0x250/0x250 [183373.131503] [<ffffffff810b052f>] kthread+0xcf/0xe0 [183373.131505] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [183373.131507] [<ffffffff81696418>] ret_from_fork+0x58/0x90 [183373.131509] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Signed-off-by: Chad Dupuis <chad.dupuis@cavium.com> Reviewed-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-11-15 23:06:06 +08:00
BNX2FC_IO_DBG(io_req, "%s(): Wait for cleanup timed out.\n",
__func__);
scsi: bnx2fc: Only put reference to io_req in bnx2fc_abts_cleanup if cleanup times out In certain tests where the SCSI error handler issues an abort that is already outstanding, we will cleanup the command so that the SCSI error handler can proceed. In some of these cases we were seeing a command mismatch: kernel: scsi host2: bnx2fc: xid:0x42b eh_abort - refcnt = 2 kernel: bnx2fc: eh_abort: io_req (xid = 0x42b) already in abts processing kernel: scsi host2: bnx2fc: xid:0x42b Entered bnx2fc_initiate_cleanup kernel: scsi host2: bnx2fc: xid:0x42b CLEANUP io_req xid = 0x80b kernel: scsi host2: bnx2fc: xid:0x80b cq_compl- cleanup resp rcvd kernel: scsi host2: bnx2fc: xid:0x42b complete - rx_state = 9 kernel: scsi host2: bnx2fc: xid:0x42b Entered process_cleanup_compl refcnt = 2, cmd_type = 1 kernel: scsi host2: bnx2fc: xid:0x42b scsi_done. err_code = 0x7 kernel: scsi host2: bnx2fc: xid:0x42b sc=ffff8807f93dfb80, result=0x7, retries=0, allowed=5 kernel: ------------[ cut here ]------------ kernel: WARNING: at /root/rpmbuild/BUILD/netxtreme2-7.14.43/obj/default/bnx2fc-2.12.1/driver/bnx2fc_io.c:1347 bnx2fc_eh_abort+0x56f/0x680 [bnx2fc]() kernel: xid=0x42b refcount=-1 kernel: Modules linked in: kernel: nls_utf8 isofs sr_mod cdrom tcp_lp dm_round_robin xt_CHECKSUM iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 tun bridge ebtable_filter ebtables fuse ip6table_filter ip6_tables iptable_filter bnx2fc(OE) cnic(OE) uio fcoe libfcoe 8021q libfc garp mrp scsi_transport_fc stp llc scsi_tgt vfat fat dm_service_time intel_powerclamp coretemp intel_rapl iosf_mbi kvm_intel kvm irqbypass crc32_pclmul ghash_clmulni_intel aesni_intel lrw gf128mul glue_helper ablk_helper cryptd ses enclosure ipmi_ssif i2c_core hpilo hpwdt wmi sg ipmi_devintf pcspkr ipmi_si ipmi_msghandler shpchp acpi_power_meter dm_multipath nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs sd_mod crc_t10dif kernel: crct10dif_generic bnx2x(OE) crct10dif_pclmul crct10dif_common crc32c_intel mdio ptp pps_core libcrc32c smartpqi scsi_transport_sas fjes uas usb_storage dm_mirror dm_region_hash dm_log dm_mod kernel: CPU: 9 PID: 2012 Comm: scsi_eh_2 Tainted: G W OE ------------ 3.10.0-514.el7.x86_64 #1 kernel: Hardware name: HPE Synergy 480 Gen10/Synergy 480 Gen10 Compute Module, BIOS I42 03/21/2018 kernel: ffff8807f25a3d98 0000000015e7fa0c ffff8807f25a3d50 ffffffff81685eac kernel: ffff8807f25a3d88 ffffffff81085820 ffff8807f8e39000 ffff880801ff7468 kernel: ffff880801ff7610 0000000000002002 ffff8807f8e39014 ffff8807f25a3df0 kernel: Call Trace: kernel: [<ffffffff81685eac>] dump_stack+0x19/0x1b kernel: [<ffffffff81085820>] warn_slowpath_common+0x70/0xb0 kernel: [<ffffffff810858bc>] warn_slowpath_fmt+0x5c/0x80 kernel: [<ffffffff8168d842>] ? _raw_spin_lock_bh+0x12/0x50 kernel: [<ffffffffa0549e6f>] bnx2fc_eh_abort+0x56f/0x680 [bnx2fc] kernel: [<ffffffff814570af>] scsi_error_handler+0x59f/0x8b0 kernel: [<ffffffff81456b10>] ? scsi_eh_get_sense+0x250/0x250 kernel: [<ffffffff810b052f>] kthread+0xcf/0xe0 kernel: [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 kernel: [<ffffffff81696418>] ret_from_fork+0x58/0x90 kernel: [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 kernel: ---[ end trace 42deb88f2032b111 ]--- The reason that there was a mismatch is that the SCSI command is actual returned from the cleanup handler. In previous testing, the type of cleanup notification we'd get from the CQE did not trigger the code that returned the SCSI command. To overcome the previous behavior we would put a reference in bnx2fc_abts_cleanup() to account for the SCSI command. However, in cases where the SCSI command is actually off, we end up with an extra put. The fix for this is to only take the extra put in bnx2fc_abts_cleanup if the completion for the cleanup times out. Signed-off-by: Chad Dupuis <cdupuis@marvell.com> Signed-off-by: Saurav Kashyap <skashyap@marvell.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-06-24 16:29:56 +08:00
/*
* Put the extra reference to the SCSI command since it would
* not have been returned in this case.
*/
kref_put(&io_req->refcount, bnx2fc_cmd_release);
}
spin_lock_bh(&tgt->tgt_lock);
io_req->wait_for_cleanup_comp = 0;
return SUCCESS;
}
scsi: bnx2fc: Fix hung task messages when a cleanup response is not received during abort If a cleanup task is not responded to while we are in bnx2fc_abts_cleanup, it will hang the SCSI error handler since we use wait_for_completion instead of wait_for_completion_timeout. So, use wait_for_completion_timeout so that we don't hang the SCSI error handler thread forever. Fixes the call trace: [183373.131468] INFO: task scsi_eh_16:110146 blocked for more than 120 seconds. [183373.131469] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [183373.131470] scsi_eh_16 D ffff88103f2fca14 0 110146 2 0x00000080 [183373.131472] ffff880855e77cb0 0000000000000046 ffff881050654e70 ffff880855e77fd8 [183373.131474] ffff880855e77fd8 ffff880855e77fd8 ffff881050654e70 ffff88103f2fcb48 [183373.131475] ffff88103f2fcb50 7fffffffffffffff ffff881050654e70 ffff88103f2fca14 [183373.131477] Call Trace: [183373.131479] [<ffffffff8168b579>] schedule+0x29/0x70 [183373.131481] [<ffffffff81688fc9>] schedule_timeout+0x239/0x2d0 [183373.131486] [<ffffffff8142821e>] ? __dev_printk+0x3e/0x90 [183373.131487] [<ffffffff814282cd>] ? dev_printk+0x5d/0x80 [183373.131490] [<ffffffff8168b956>] wait_for_completion+0x116/0x170 [183373.131492] [<ffffffff810c4ec0>] ? wake_up_state+0x20/0x20 [183373.131494] [<ffffffffa048c234>] bnx2fc_abts_cleanup+0x3d/0x62 [bnx2fc] [183373.131497] [<ffffffffa0483a80>] bnx2fc_eh_abort+0x470/0x580 [bnx2fc] [183373.131500] [<ffffffff814570af>] scsi_error_handler+0x59f/0x8b0 [183373.131501] [<ffffffff81456b10>] ? scsi_eh_get_sense+0x250/0x250 [183373.131503] [<ffffffff810b052f>] kthread+0xcf/0xe0 [183373.131505] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [183373.131507] [<ffffffff81696418>] ret_from_fork+0x58/0x90 [183373.131509] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Signed-off-by: Chad Dupuis <chad.dupuis@cavium.com> Reviewed-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-11-15 23:06:06 +08:00
/**
* bnx2fc_eh_abort - eh_abort_handler api to abort an outstanding
* SCSI command
*
* @sc_cmd: SCSI_ML command pointer
*
* SCSI abort request handler
*/
int bnx2fc_eh_abort(struct scsi_cmnd *sc_cmd)
{
struct fc_rport *rport = starget_to_rport(scsi_target(sc_cmd->device));
struct fc_rport_libfc_priv *rp = rport->dd_data;
struct bnx2fc_cmd *io_req;
struct fc_lport *lport;
struct bnx2fc_rport *tgt;
int rc;
scsi: bnx2fc: Fix hung task messages when a cleanup response is not received during abort If a cleanup task is not responded to while we are in bnx2fc_abts_cleanup, it will hang the SCSI error handler since we use wait_for_completion instead of wait_for_completion_timeout. So, use wait_for_completion_timeout so that we don't hang the SCSI error handler thread forever. Fixes the call trace: [183373.131468] INFO: task scsi_eh_16:110146 blocked for more than 120 seconds. [183373.131469] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [183373.131470] scsi_eh_16 D ffff88103f2fca14 0 110146 2 0x00000080 [183373.131472] ffff880855e77cb0 0000000000000046 ffff881050654e70 ffff880855e77fd8 [183373.131474] ffff880855e77fd8 ffff880855e77fd8 ffff881050654e70 ffff88103f2fcb48 [183373.131475] ffff88103f2fcb50 7fffffffffffffff ffff881050654e70 ffff88103f2fca14 [183373.131477] Call Trace: [183373.131479] [<ffffffff8168b579>] schedule+0x29/0x70 [183373.131481] [<ffffffff81688fc9>] schedule_timeout+0x239/0x2d0 [183373.131486] [<ffffffff8142821e>] ? __dev_printk+0x3e/0x90 [183373.131487] [<ffffffff814282cd>] ? dev_printk+0x5d/0x80 [183373.131490] [<ffffffff8168b956>] wait_for_completion+0x116/0x170 [183373.131492] [<ffffffff810c4ec0>] ? wake_up_state+0x20/0x20 [183373.131494] [<ffffffffa048c234>] bnx2fc_abts_cleanup+0x3d/0x62 [bnx2fc] [183373.131497] [<ffffffffa0483a80>] bnx2fc_eh_abort+0x470/0x580 [bnx2fc] [183373.131500] [<ffffffff814570af>] scsi_error_handler+0x59f/0x8b0 [183373.131501] [<ffffffff81456b10>] ? scsi_eh_get_sense+0x250/0x250 [183373.131503] [<ffffffff810b052f>] kthread+0xcf/0xe0 [183373.131505] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [183373.131507] [<ffffffff81696418>] ret_from_fork+0x58/0x90 [183373.131509] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Signed-off-by: Chad Dupuis <chad.dupuis@cavium.com> Reviewed-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-11-15 23:06:06 +08:00
unsigned int time_left;
rc = fc_block_scsi_eh(sc_cmd);
if (rc)
return rc;
lport = shost_priv(sc_cmd->device->host);
if ((lport->state != LPORT_ST_READY) || !(lport->link_up)) {
printk(KERN_ERR PFX "eh_abort: link not ready\n");
return FAILED;
}
tgt = (struct bnx2fc_rport *)&rp[1];
BNX2FC_TGT_DBG(tgt, "Entered bnx2fc_eh_abort\n");
spin_lock_bh(&tgt->tgt_lock);
io_req = bnx2fc_priv(sc_cmd)->io_req;
if (!io_req) {
/* Command might have just completed */
printk(KERN_ERR PFX "eh_abort: io_req is NULL\n");
spin_unlock_bh(&tgt->tgt_lock);
return SUCCESS;
}
BNX2FC_IO_DBG(io_req, "eh_abort - refcnt = %d\n",
kref_read(&io_req->refcount));
/* Hold IO request across abort processing */
kref_get(&io_req->refcount);
BUG_ON(tgt != io_req->tgt);
/* Remove the io_req from the active_q. */
/*
* Task Mgmt functions (LUN RESET & TGT RESET) will not
* issue an ABTS on this particular IO req, as the
* io_req is no longer in the active_q.
*/
if (tgt->flush_in_prog) {
printk(KERN_ERR PFX "eh_abort: io_req (xid = 0x%x) "
"flush in progress\n", io_req->xid);
kref_put(&io_req->refcount, bnx2fc_cmd_release);
spin_unlock_bh(&tgt->tgt_lock);
return SUCCESS;
}
if (io_req->on_active_queue == 0) {
printk(KERN_ERR PFX "eh_abort: io_req (xid = 0x%x) "
"not on active_q\n", io_req->xid);
/*
* The IO is still with the FW.
* Return failure and let SCSI-ml retry eh_abort.
*/
spin_unlock_bh(&tgt->tgt_lock);
return FAILED;
}
/*
* Only eh_abort processing will remove the IO from
* active_cmd_q before processing the request. this is
* done to avoid race conditions between IOs aborted
* as part of task management completion and eh_abort
* processing
*/
list_del_init(&io_req->link);
io_req->on_active_queue = 0;
/* Move IO req to retire queue */
list_add_tail(&io_req->link, &tgt->io_retire_queue);
init_completion(&io_req->abts_done);
init_completion(&io_req->cleanup_done);
if (test_and_set_bit(BNX2FC_FLAG_ISSUE_ABTS, &io_req->req_flags)) {
printk(KERN_ERR PFX "eh_abort: io_req (xid = 0x%x) "
"already in abts processing\n", io_req->xid);
if (cancel_delayed_work(&io_req->timeout_work))
kref_put(&io_req->refcount,
bnx2fc_cmd_release); /* drop timer hold */
scsi: bnx2fc: Fix hung task messages when a cleanup response is not received during abort If a cleanup task is not responded to while we are in bnx2fc_abts_cleanup, it will hang the SCSI error handler since we use wait_for_completion instead of wait_for_completion_timeout. So, use wait_for_completion_timeout so that we don't hang the SCSI error handler thread forever. Fixes the call trace: [183373.131468] INFO: task scsi_eh_16:110146 blocked for more than 120 seconds. [183373.131469] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [183373.131470] scsi_eh_16 D ffff88103f2fca14 0 110146 2 0x00000080 [183373.131472] ffff880855e77cb0 0000000000000046 ffff881050654e70 ffff880855e77fd8 [183373.131474] ffff880855e77fd8 ffff880855e77fd8 ffff881050654e70 ffff88103f2fcb48 [183373.131475] ffff88103f2fcb50 7fffffffffffffff ffff881050654e70 ffff88103f2fca14 [183373.131477] Call Trace: [183373.131479] [<ffffffff8168b579>] schedule+0x29/0x70 [183373.131481] [<ffffffff81688fc9>] schedule_timeout+0x239/0x2d0 [183373.131486] [<ffffffff8142821e>] ? __dev_printk+0x3e/0x90 [183373.131487] [<ffffffff814282cd>] ? dev_printk+0x5d/0x80 [183373.131490] [<ffffffff8168b956>] wait_for_completion+0x116/0x170 [183373.131492] [<ffffffff810c4ec0>] ? wake_up_state+0x20/0x20 [183373.131494] [<ffffffffa048c234>] bnx2fc_abts_cleanup+0x3d/0x62 [bnx2fc] [183373.131497] [<ffffffffa0483a80>] bnx2fc_eh_abort+0x470/0x580 [bnx2fc] [183373.131500] [<ffffffff814570af>] scsi_error_handler+0x59f/0x8b0 [183373.131501] [<ffffffff81456b10>] ? scsi_eh_get_sense+0x250/0x250 [183373.131503] [<ffffffff810b052f>] kthread+0xcf/0xe0 [183373.131505] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [183373.131507] [<ffffffff81696418>] ret_from_fork+0x58/0x90 [183373.131509] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Signed-off-by: Chad Dupuis <chad.dupuis@cavium.com> Reviewed-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-11-15 23:06:06 +08:00
/*
* We don't want to hold off the upper layer timer so simply
* cleanup the command and return that I/O was successfully
* aborted.
*/
bnx2fc_abts_cleanup(io_req);
/* This only occurs when an task abort was requested while ABTS
is in progress. Setting the IO_CLEANUP flag will skip the
RRQ process in the case when the fw generated SCSI_CMD cmpl
was a result from the ABTS request rather than the CLEANUP
request */
set_bit(BNX2FC_FLAG_IO_CLEANUP, &io_req->req_flags);
rc = FAILED;
scsi: bnx2fc: Fix hung task messages when a cleanup response is not received during abort If a cleanup task is not responded to while we are in bnx2fc_abts_cleanup, it will hang the SCSI error handler since we use wait_for_completion instead of wait_for_completion_timeout. So, use wait_for_completion_timeout so that we don't hang the SCSI error handler thread forever. Fixes the call trace: [183373.131468] INFO: task scsi_eh_16:110146 blocked for more than 120 seconds. [183373.131469] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [183373.131470] scsi_eh_16 D ffff88103f2fca14 0 110146 2 0x00000080 [183373.131472] ffff880855e77cb0 0000000000000046 ffff881050654e70 ffff880855e77fd8 [183373.131474] ffff880855e77fd8 ffff880855e77fd8 ffff881050654e70 ffff88103f2fcb48 [183373.131475] ffff88103f2fcb50 7fffffffffffffff ffff881050654e70 ffff88103f2fca14 [183373.131477] Call Trace: [183373.131479] [<ffffffff8168b579>] schedule+0x29/0x70 [183373.131481] [<ffffffff81688fc9>] schedule_timeout+0x239/0x2d0 [183373.131486] [<ffffffff8142821e>] ? __dev_printk+0x3e/0x90 [183373.131487] [<ffffffff814282cd>] ? dev_printk+0x5d/0x80 [183373.131490] [<ffffffff8168b956>] wait_for_completion+0x116/0x170 [183373.131492] [<ffffffff810c4ec0>] ? wake_up_state+0x20/0x20 [183373.131494] [<ffffffffa048c234>] bnx2fc_abts_cleanup+0x3d/0x62 [bnx2fc] [183373.131497] [<ffffffffa0483a80>] bnx2fc_eh_abort+0x470/0x580 [bnx2fc] [183373.131500] [<ffffffff814570af>] scsi_error_handler+0x59f/0x8b0 [183373.131501] [<ffffffff81456b10>] ? scsi_eh_get_sense+0x250/0x250 [183373.131503] [<ffffffff810b052f>] kthread+0xcf/0xe0 [183373.131505] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [183373.131507] [<ffffffff81696418>] ret_from_fork+0x58/0x90 [183373.131509] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Signed-off-by: Chad Dupuis <chad.dupuis@cavium.com> Reviewed-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-11-15 23:06:06 +08:00
goto done;
}
/* Cancel the current timer running on this io_req */
if (cancel_delayed_work(&io_req->timeout_work))
kref_put(&io_req->refcount,
bnx2fc_cmd_release); /* drop timer hold */
set_bit(BNX2FC_FLAG_EH_ABORT, &io_req->req_flags);
io_req->wait_for_abts_comp = 1;
rc = bnx2fc_initiate_abts(io_req);
if (rc == FAILED) {
io_req->wait_for_cleanup_comp = 1;
bnx2fc_initiate_cleanup(io_req);
spin_unlock_bh(&tgt->tgt_lock);
wait_for_completion(&io_req->cleanup_done);
spin_lock_bh(&tgt->tgt_lock);
io_req->wait_for_cleanup_comp = 0;
goto done;
}
spin_unlock_bh(&tgt->tgt_lock);
scsi: bnx2fc: Fix hung task messages when a cleanup response is not received during abort If a cleanup task is not responded to while we are in bnx2fc_abts_cleanup, it will hang the SCSI error handler since we use wait_for_completion instead of wait_for_completion_timeout. So, use wait_for_completion_timeout so that we don't hang the SCSI error handler thread forever. Fixes the call trace: [183373.131468] INFO: task scsi_eh_16:110146 blocked for more than 120 seconds. [183373.131469] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [183373.131470] scsi_eh_16 D ffff88103f2fca14 0 110146 2 0x00000080 [183373.131472] ffff880855e77cb0 0000000000000046 ffff881050654e70 ffff880855e77fd8 [183373.131474] ffff880855e77fd8 ffff880855e77fd8 ffff881050654e70 ffff88103f2fcb48 [183373.131475] ffff88103f2fcb50 7fffffffffffffff ffff881050654e70 ffff88103f2fca14 [183373.131477] Call Trace: [183373.131479] [<ffffffff8168b579>] schedule+0x29/0x70 [183373.131481] [<ffffffff81688fc9>] schedule_timeout+0x239/0x2d0 [183373.131486] [<ffffffff8142821e>] ? __dev_printk+0x3e/0x90 [183373.131487] [<ffffffff814282cd>] ? dev_printk+0x5d/0x80 [183373.131490] [<ffffffff8168b956>] wait_for_completion+0x116/0x170 [183373.131492] [<ffffffff810c4ec0>] ? wake_up_state+0x20/0x20 [183373.131494] [<ffffffffa048c234>] bnx2fc_abts_cleanup+0x3d/0x62 [bnx2fc] [183373.131497] [<ffffffffa0483a80>] bnx2fc_eh_abort+0x470/0x580 [bnx2fc] [183373.131500] [<ffffffff814570af>] scsi_error_handler+0x59f/0x8b0 [183373.131501] [<ffffffff81456b10>] ? scsi_eh_get_sense+0x250/0x250 [183373.131503] [<ffffffff810b052f>] kthread+0xcf/0xe0 [183373.131505] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [183373.131507] [<ffffffff81696418>] ret_from_fork+0x58/0x90 [183373.131509] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Signed-off-by: Chad Dupuis <chad.dupuis@cavium.com> Reviewed-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-11-15 23:06:06 +08:00
/* Wait 2 * RA_TOV + 1 to be sure timeout function hasn't fired */
time_left = wait_for_completion_timeout(&io_req->abts_done,
msecs_to_jiffies(2 * rp->r_a_tov + 1));
scsi: bnx2fc: Fix hung task messages when a cleanup response is not received during abort If a cleanup task is not responded to while we are in bnx2fc_abts_cleanup, it will hang the SCSI error handler since we use wait_for_completion instead of wait_for_completion_timeout. So, use wait_for_completion_timeout so that we don't hang the SCSI error handler thread forever. Fixes the call trace: [183373.131468] INFO: task scsi_eh_16:110146 blocked for more than 120 seconds. [183373.131469] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [183373.131470] scsi_eh_16 D ffff88103f2fca14 0 110146 2 0x00000080 [183373.131472] ffff880855e77cb0 0000000000000046 ffff881050654e70 ffff880855e77fd8 [183373.131474] ffff880855e77fd8 ffff880855e77fd8 ffff881050654e70 ffff88103f2fcb48 [183373.131475] ffff88103f2fcb50 7fffffffffffffff ffff881050654e70 ffff88103f2fca14 [183373.131477] Call Trace: [183373.131479] [<ffffffff8168b579>] schedule+0x29/0x70 [183373.131481] [<ffffffff81688fc9>] schedule_timeout+0x239/0x2d0 [183373.131486] [<ffffffff8142821e>] ? __dev_printk+0x3e/0x90 [183373.131487] [<ffffffff814282cd>] ? dev_printk+0x5d/0x80 [183373.131490] [<ffffffff8168b956>] wait_for_completion+0x116/0x170 [183373.131492] [<ffffffff810c4ec0>] ? wake_up_state+0x20/0x20 [183373.131494] [<ffffffffa048c234>] bnx2fc_abts_cleanup+0x3d/0x62 [bnx2fc] [183373.131497] [<ffffffffa0483a80>] bnx2fc_eh_abort+0x470/0x580 [bnx2fc] [183373.131500] [<ffffffff814570af>] scsi_error_handler+0x59f/0x8b0 [183373.131501] [<ffffffff81456b10>] ? scsi_eh_get_sense+0x250/0x250 [183373.131503] [<ffffffff810b052f>] kthread+0xcf/0xe0 [183373.131505] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [183373.131507] [<ffffffff81696418>] ret_from_fork+0x58/0x90 [183373.131509] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Signed-off-by: Chad Dupuis <chad.dupuis@cavium.com> Reviewed-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-11-15 23:06:06 +08:00
if (time_left)
BNX2FC_IO_DBG(io_req,
"Timed out in eh_abort waiting for abts_done");
spin_lock_bh(&tgt->tgt_lock);
io_req->wait_for_abts_comp = 0;
if (test_bit(BNX2FC_FLAG_IO_COMPL, &io_req->req_flags)) {
BNX2FC_IO_DBG(io_req, "IO completed in a different context\n");
rc = SUCCESS;
} else if (!(test_and_set_bit(BNX2FC_FLAG_ABTS_DONE,
&io_req->req_flags))) {
/* Let the scsi-ml try to recover this command */
printk(KERN_ERR PFX "abort failed, xid = 0x%x\n",
io_req->xid);
scsi: bnx2fc: Fix hung task messages when a cleanup response is not received during abort If a cleanup task is not responded to while we are in bnx2fc_abts_cleanup, it will hang the SCSI error handler since we use wait_for_completion instead of wait_for_completion_timeout. So, use wait_for_completion_timeout so that we don't hang the SCSI error handler thread forever. Fixes the call trace: [183373.131468] INFO: task scsi_eh_16:110146 blocked for more than 120 seconds. [183373.131469] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [183373.131470] scsi_eh_16 D ffff88103f2fca14 0 110146 2 0x00000080 [183373.131472] ffff880855e77cb0 0000000000000046 ffff881050654e70 ffff880855e77fd8 [183373.131474] ffff880855e77fd8 ffff880855e77fd8 ffff881050654e70 ffff88103f2fcb48 [183373.131475] ffff88103f2fcb50 7fffffffffffffff ffff881050654e70 ffff88103f2fca14 [183373.131477] Call Trace: [183373.131479] [<ffffffff8168b579>] schedule+0x29/0x70 [183373.131481] [<ffffffff81688fc9>] schedule_timeout+0x239/0x2d0 [183373.131486] [<ffffffff8142821e>] ? __dev_printk+0x3e/0x90 [183373.131487] [<ffffffff814282cd>] ? dev_printk+0x5d/0x80 [183373.131490] [<ffffffff8168b956>] wait_for_completion+0x116/0x170 [183373.131492] [<ffffffff810c4ec0>] ? wake_up_state+0x20/0x20 [183373.131494] [<ffffffffa048c234>] bnx2fc_abts_cleanup+0x3d/0x62 [bnx2fc] [183373.131497] [<ffffffffa0483a80>] bnx2fc_eh_abort+0x470/0x580 [bnx2fc] [183373.131500] [<ffffffff814570af>] scsi_error_handler+0x59f/0x8b0 [183373.131501] [<ffffffff81456b10>] ? scsi_eh_get_sense+0x250/0x250 [183373.131503] [<ffffffff810b052f>] kthread+0xcf/0xe0 [183373.131505] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [183373.131507] [<ffffffff81696418>] ret_from_fork+0x58/0x90 [183373.131509] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Signed-off-by: Chad Dupuis <chad.dupuis@cavium.com> Reviewed-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-11-15 23:06:06 +08:00
/*
* Cleanup firmware residuals before returning control back
* to SCSI ML.
*/
rc = bnx2fc_abts_cleanup(io_req);
scsi: bnx2fc: Fix hung task messages when a cleanup response is not received during abort If a cleanup task is not responded to while we are in bnx2fc_abts_cleanup, it will hang the SCSI error handler since we use wait_for_completion instead of wait_for_completion_timeout. So, use wait_for_completion_timeout so that we don't hang the SCSI error handler thread forever. Fixes the call trace: [183373.131468] INFO: task scsi_eh_16:110146 blocked for more than 120 seconds. [183373.131469] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [183373.131470] scsi_eh_16 D ffff88103f2fca14 0 110146 2 0x00000080 [183373.131472] ffff880855e77cb0 0000000000000046 ffff881050654e70 ffff880855e77fd8 [183373.131474] ffff880855e77fd8 ffff880855e77fd8 ffff881050654e70 ffff88103f2fcb48 [183373.131475] ffff88103f2fcb50 7fffffffffffffff ffff881050654e70 ffff88103f2fca14 [183373.131477] Call Trace: [183373.131479] [<ffffffff8168b579>] schedule+0x29/0x70 [183373.131481] [<ffffffff81688fc9>] schedule_timeout+0x239/0x2d0 [183373.131486] [<ffffffff8142821e>] ? __dev_printk+0x3e/0x90 [183373.131487] [<ffffffff814282cd>] ? dev_printk+0x5d/0x80 [183373.131490] [<ffffffff8168b956>] wait_for_completion+0x116/0x170 [183373.131492] [<ffffffff810c4ec0>] ? wake_up_state+0x20/0x20 [183373.131494] [<ffffffffa048c234>] bnx2fc_abts_cleanup+0x3d/0x62 [bnx2fc] [183373.131497] [<ffffffffa0483a80>] bnx2fc_eh_abort+0x470/0x580 [bnx2fc] [183373.131500] [<ffffffff814570af>] scsi_error_handler+0x59f/0x8b0 [183373.131501] [<ffffffff81456b10>] ? scsi_eh_get_sense+0x250/0x250 [183373.131503] [<ffffffff810b052f>] kthread+0xcf/0xe0 [183373.131505] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [183373.131507] [<ffffffff81696418>] ret_from_fork+0x58/0x90 [183373.131509] [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Signed-off-by: Chad Dupuis <chad.dupuis@cavium.com> Reviewed-by: Laurence Oberman <loberman@redhat.com> Tested-by: Laurence Oberman <loberman@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2017-11-15 23:06:06 +08:00
goto done;
} else {
/*
* We come here even when there was a race condition
* between timeout and abts completion, and abts
* completion happens just in time.
*/
BNX2FC_IO_DBG(io_req, "abort succeeded\n");
rc = SUCCESS;
bnx2fc_scsi_done(io_req, DID_ABORT);
kref_put(&io_req->refcount, bnx2fc_cmd_release);
}
done:
/* release the reference taken in eh_abort */
kref_put(&io_req->refcount, bnx2fc_cmd_release);
spin_unlock_bh(&tgt->tgt_lock);
return rc;
}
void bnx2fc_process_seq_cleanup_compl(struct bnx2fc_cmd *seq_clnp_req,
struct fcoe_task_ctx_entry *task,
u8 rx_state)
{
struct bnx2fc_els_cb_arg *cb_arg = seq_clnp_req->cb_arg;
struct bnx2fc_cmd *orig_io_req = cb_arg->aborted_io_req;
u32 offset = cb_arg->offset;
enum fc_rctl r_ctl = cb_arg->r_ctl;
int rc = 0;
struct bnx2fc_rport *tgt = orig_io_req->tgt;
BNX2FC_IO_DBG(orig_io_req, "Entered process_cleanup_compl xid = 0x%x"
"cmd_type = %d\n",
seq_clnp_req->xid, seq_clnp_req->cmd_type);
if (rx_state == FCOE_TASK_RX_STATE_IGNORED_SEQUENCE_CLEANUP) {
printk(KERN_ERR PFX "seq cleanup ignored - xid = 0x%x\n",
seq_clnp_req->xid);
goto free_cb_arg;
}
spin_unlock_bh(&tgt->tgt_lock);
rc = bnx2fc_send_srr(orig_io_req, offset, r_ctl);
spin_lock_bh(&tgt->tgt_lock);
if (rc)
printk(KERN_ERR PFX "clnup_compl: Unable to send SRR"
" IO will abort\n");
seq_clnp_req->cb_arg = NULL;
kref_put(&orig_io_req->refcount, bnx2fc_cmd_release);
free_cb_arg:
kfree(cb_arg);
return;
}
void bnx2fc_process_cleanup_compl(struct bnx2fc_cmd *io_req,
struct fcoe_task_ctx_entry *task,
u8 num_rq)
{
BNX2FC_IO_DBG(io_req, "Entered process_cleanup_compl "
"refcnt = %d, cmd_type = %d\n",
kref_read(&io_req->refcount), io_req->cmd_type);
/*
* Test whether there is a cleanup request pending. If not just
* exit.
*/
if (!test_and_clear_bit(BNX2FC_FLAG_ISSUE_CLEANUP_REQ,
&io_req->req_flags))
return;
/*
* If we receive a cleanup completion for this request then the
* firmware will not give us an abort completion for this request
* so clear any ABTS pending flags.
*/
if (test_bit(BNX2FC_FLAG_ISSUE_ABTS, &io_req->req_flags) &&
!test_bit(BNX2FC_FLAG_ABTS_DONE, &io_req->req_flags)) {
set_bit(BNX2FC_FLAG_ABTS_DONE, &io_req->req_flags);
if (io_req->wait_for_abts_comp)
complete(&io_req->abts_done);
}
bnx2fc_scsi_done(io_req, DID_ERROR);
kref_put(&io_req->refcount, bnx2fc_cmd_release);
if (io_req->wait_for_cleanup_comp)
complete(&io_req->cleanup_done);
}
void bnx2fc_process_abts_compl(struct bnx2fc_cmd *io_req,
struct fcoe_task_ctx_entry *task,
u8 num_rq)
{
u32 r_ctl;
u32 r_a_tov = FC_DEF_R_A_TOV;
u8 issue_rrq = 0;
struct bnx2fc_rport *tgt = io_req->tgt;
BNX2FC_IO_DBG(io_req, "Entered process_abts_compl xid = 0x%x"
"refcnt = %d, cmd_type = %d\n",
io_req->xid,
kref_read(&io_req->refcount), io_req->cmd_type);
if (test_and_set_bit(BNX2FC_FLAG_ABTS_DONE,
&io_req->req_flags)) {
BNX2FC_IO_DBG(io_req, "Timer context finished processing"
" this io\n");
return;
}
/*
* If we receive an ABTS completion here then we will not receive
* a cleanup completion so clear any cleanup pending flags.
*/
if (test_bit(BNX2FC_FLAG_ISSUE_CLEANUP_REQ, &io_req->req_flags)) {
clear_bit(BNX2FC_FLAG_ISSUE_CLEANUP_REQ, &io_req->req_flags);
if (io_req->wait_for_cleanup_comp)
complete(&io_req->cleanup_done);
}
/* Do not issue RRQ as this IO is already cleanedup */
if (test_and_set_bit(BNX2FC_FLAG_IO_CLEANUP,
&io_req->req_flags))
goto io_compl;
/*
* For ABTS issued due to SCSI eh_abort_handler, timeout
* values are maintained by scsi-ml itself. Cancel timeout
* in case ABTS issued as part of task management function
* or due to FW error.
*/
if (test_bit(BNX2FC_FLAG_ISSUE_ABTS, &io_req->req_flags))
if (cancel_delayed_work(&io_req->timeout_work))
kref_put(&io_req->refcount,
bnx2fc_cmd_release); /* drop timer hold */
r_ctl = (u8)task->rxwr_only.union_ctx.comp_info.abts_rsp.r_ctl;
switch (r_ctl) {
case FC_RCTL_BA_ACC:
/*
* Dont release this cmd yet. It will be relesed
* after we get RRQ response
*/
BNX2FC_IO_DBG(io_req, "ABTS response - ACC Send RRQ\n");
issue_rrq = 1;
break;
case FC_RCTL_BA_RJT:
BNX2FC_IO_DBG(io_req, "ABTS response - RJT\n");
break;
default:
printk(KERN_ERR PFX "Unknown ABTS response\n");
break;
}
if (issue_rrq) {
BNX2FC_IO_DBG(io_req, "Issue RRQ after R_A_TOV\n");
set_bit(BNX2FC_FLAG_ISSUE_RRQ, &io_req->req_flags);
}
set_bit(BNX2FC_FLAG_RETIRE_OXID, &io_req->req_flags);
bnx2fc_cmd_timer_set(io_req, r_a_tov);
io_compl:
if (io_req->wait_for_abts_comp) {
if (test_and_clear_bit(BNX2FC_FLAG_EH_ABORT,
&io_req->req_flags))
complete(&io_req->abts_done);
} else {
/*
* We end up here when ABTS is issued as
* in asynchronous context, i.e., as part
* of task management completion, or
* when FW error is received or when the
* ABTS is issued when the IO is timed
* out.
*/
if (io_req->on_active_queue) {
list_del_init(&io_req->link);
io_req->on_active_queue = 0;
/* Move IO req to retire queue */
list_add_tail(&io_req->link, &tgt->io_retire_queue);
}
bnx2fc_scsi_done(io_req, DID_ERROR);
kref_put(&io_req->refcount, bnx2fc_cmd_release);
}
}
static void bnx2fc_lun_reset_cmpl(struct bnx2fc_cmd *io_req)
{
struct scsi_cmnd *sc_cmd = io_req->sc_cmd;
struct bnx2fc_rport *tgt = io_req->tgt;
struct bnx2fc_cmd *cmd, *tmp;
u64 tm_lun = sc_cmd->device->lun;
u64 lun;
int rc = 0;
/* called with tgt_lock held */
BNX2FC_IO_DBG(io_req, "Entered bnx2fc_lun_reset_cmpl\n");
/*
* Walk thru the active_ios queue and ABORT the IO
* that matches with the LUN that was reset
*/
list_for_each_entry_safe(cmd, tmp, &tgt->active_cmd_queue, link) {
BNX2FC_TGT_DBG(tgt, "LUN RST cmpl: scan for pending IOs\n");
lun = cmd->sc_cmd->device->lun;
if (lun == tm_lun) {
/* Initiate ABTS on this cmd */
if (!test_and_set_bit(BNX2FC_FLAG_ISSUE_ABTS,
&cmd->req_flags)) {
/* cancel the IO timeout */
if (cancel_delayed_work(&io_req->timeout_work))
kref_put(&io_req->refcount,
bnx2fc_cmd_release);
/* timer hold */
rc = bnx2fc_initiate_abts(cmd);
/* abts shouldn't fail in this context */
WARN_ON(rc != SUCCESS);
} else
printk(KERN_ERR PFX "lun_rst: abts already in"
" progress for this IO 0x%x\n",
cmd->xid);
}
}
}
static void bnx2fc_tgt_reset_cmpl(struct bnx2fc_cmd *io_req)
{
struct bnx2fc_rport *tgt = io_req->tgt;
struct bnx2fc_cmd *cmd, *tmp;
int rc = 0;
/* called with tgt_lock held */
BNX2FC_IO_DBG(io_req, "Entered bnx2fc_tgt_reset_cmpl\n");
/*
* Walk thru the active_ios queue and ABORT the IO
* that matches with the LUN that was reset
*/
list_for_each_entry_safe(cmd, tmp, &tgt->active_cmd_queue, link) {
BNX2FC_TGT_DBG(tgt, "TGT RST cmpl: scan for pending IOs\n");
/* Initiate ABTS */
if (!test_and_set_bit(BNX2FC_FLAG_ISSUE_ABTS,
&cmd->req_flags)) {
/* cancel the IO timeout */
if (cancel_delayed_work(&io_req->timeout_work))
kref_put(&io_req->refcount,
bnx2fc_cmd_release); /* timer hold */
rc = bnx2fc_initiate_abts(cmd);
/* abts shouldn't fail in this context */
WARN_ON(rc != SUCCESS);
} else
printk(KERN_ERR PFX "tgt_rst: abts already in progress"
" for this IO 0x%x\n", cmd->xid);
}
}
void bnx2fc_process_tm_compl(struct bnx2fc_cmd *io_req,
struct fcoe_task_ctx_entry *task, u8 num_rq,
unsigned char *rq_data)
{
struct bnx2fc_mp_req *tm_req;
struct fc_frame_header *fc_hdr;
struct scsi_cmnd *sc_cmd = io_req->sc_cmd;
u64 *hdr;
u64 *temp_hdr;
void *rsp_buf;
/* Called with tgt_lock held */
BNX2FC_IO_DBG(io_req, "Entered process_tm_compl\n");
if (!(test_bit(BNX2FC_FLAG_TM_TIMEOUT, &io_req->req_flags)))
set_bit(BNX2FC_FLAG_TM_COMPL, &io_req->req_flags);
else {
/* TM has already timed out and we got
* delayed completion. Ignore completion
* processing.
*/
return;
}
tm_req = &(io_req->mp_req);
fc_hdr = &(tm_req->resp_fc_hdr);
hdr = (u64 *)fc_hdr;
temp_hdr = (u64 *)
&task->rxwr_only.union_ctx.comp_info.mp_rsp.fc_hdr;
hdr[0] = cpu_to_be64(temp_hdr[0]);
hdr[1] = cpu_to_be64(temp_hdr[1]);
hdr[2] = cpu_to_be64(temp_hdr[2]);
tm_req->resp_len =
task->rxwr_only.union_ctx.comp_info.mp_rsp.mp_payload_len;
rsp_buf = tm_req->resp_buf;
if (fc_hdr->fh_r_ctl == FC_RCTL_DD_CMD_STATUS) {
bnx2fc_parse_fcp_rsp(io_req,
(struct fcoe_fcp_rsp_payload *)
rsp_buf, num_rq, rq_data);
if (io_req->fcp_rsp_code == 0) {
/* TM successful */
if (tm_req->tm_flags & FCP_TMF_LUN_RESET)
bnx2fc_lun_reset_cmpl(io_req);
else if (tm_req->tm_flags & FCP_TMF_TGT_RESET)
bnx2fc_tgt_reset_cmpl(io_req);
}
} else {
printk(KERN_ERR PFX "tmf's fc_hdr r_ctl = 0x%x\n",
fc_hdr->fh_r_ctl);
}
if (!bnx2fc_priv(sc_cmd)->io_req) {
printk(KERN_ERR PFX "tm_compl: io_req is NULL\n");
return;
}
switch (io_req->fcp_status) {
case FC_GOOD:
if (io_req->cdb_status == 0) {
/* Good IO completion */
sc_cmd->result = DID_OK << 16;
} else {
/* Transport status is good, SCSI status not good */
sc_cmd->result = (DID_OK << 16) | io_req->cdb_status;
}
if (io_req->fcp_resid)
scsi_set_resid(sc_cmd, io_req->fcp_resid);
break;
default:
BNX2FC_IO_DBG(io_req, "process_tm_compl: fcp_status = %d\n",
io_req->fcp_status);
break;
}
sc_cmd = io_req->sc_cmd;
io_req->sc_cmd = NULL;
/* check if the io_req exists in tgt's tmf_q */
if (io_req->on_tmf_queue) {
list_del_init(&io_req->link);
io_req->on_tmf_queue = 0;
} else {
printk(KERN_ERR PFX "Command not on active_cmd_queue!\n");
return;
}
bnx2fc_priv(sc_cmd)->io_req = NULL;
scsi_done(sc_cmd);
kref_put(&io_req->refcount, bnx2fc_cmd_release);
if (io_req->wait_for_abts_comp) {
BNX2FC_IO_DBG(io_req, "tm_compl - wake up the waiter\n");
complete(&io_req->abts_done);
}
}
static int bnx2fc_split_bd(struct bnx2fc_cmd *io_req, u64 addr, int sg_len,
int bd_index)
{
struct fcoe_bd_ctx *bd = io_req->bd_tbl->bd_tbl;
int frag_size, sg_frags;
sg_frags = 0;
while (sg_len) {
if (sg_len >= BNX2FC_BD_SPLIT_SZ)
frag_size = BNX2FC_BD_SPLIT_SZ;
else
frag_size = sg_len;
bd[bd_index + sg_frags].buf_addr_lo = addr & 0xffffffff;
bd[bd_index + sg_frags].buf_addr_hi = addr >> 32;
bd[bd_index + sg_frags].buf_len = (u16)frag_size;
bd[bd_index + sg_frags].flags = 0;
addr += (u64) frag_size;
sg_frags++;
sg_len -= frag_size;
}
return sg_frags;
}
static int bnx2fc_map_sg(struct bnx2fc_cmd *io_req)
{
struct bnx2fc_interface *interface = io_req->port->priv;
struct bnx2fc_hba *hba = interface->hba;
struct scsi_cmnd *sc = io_req->sc_cmd;
struct fcoe_bd_ctx *bd = io_req->bd_tbl->bd_tbl;
struct scatterlist *sg;
int byte_count = 0;
int sg_count = 0;
int bd_count = 0;
int sg_frags;
unsigned int sg_len;
u64 addr;
int i;
WARN_ON(scsi_sg_count(sc) > BNX2FC_MAX_BDS_PER_CMD);
/*
* Use dma_map_sg directly to ensure we're using the correct
* dev struct off of pcidev.
*/
sg_count = dma_map_sg(&hba->pcidev->dev, scsi_sglist(sc),
scsi_sg_count(sc), sc->sc_data_direction);
scsi_for_each_sg(sc, sg, sg_count, i) {
sg_len = sg_dma_len(sg);
addr = sg_dma_address(sg);
if (sg_len > BNX2FC_MAX_BD_LEN) {
sg_frags = bnx2fc_split_bd(io_req, addr, sg_len,
bd_count);
} else {
sg_frags = 1;
bd[bd_count].buf_addr_lo = addr & 0xffffffff;
bd[bd_count].buf_addr_hi = addr >> 32;
bd[bd_count].buf_len = (u16)sg_len;
bd[bd_count].flags = 0;
}
bd_count += sg_frags;
byte_count += sg_len;
}
if (byte_count != scsi_bufflen(sc))
printk(KERN_ERR PFX "byte_count = %d != scsi_bufflen = %d, "
"task_id = 0x%x\n", byte_count, scsi_bufflen(sc),
io_req->xid);
return bd_count;
}
static int bnx2fc_build_bd_list_from_sg(struct bnx2fc_cmd *io_req)
{
struct scsi_cmnd *sc = io_req->sc_cmd;
struct fcoe_bd_ctx *bd = io_req->bd_tbl->bd_tbl;
int bd_count;
if (scsi_sg_count(sc)) {
bd_count = bnx2fc_map_sg(io_req);
if (bd_count == 0)
return -ENOMEM;
} else {
bd_count = 0;
bd[0].buf_addr_lo = bd[0].buf_addr_hi = 0;
bd[0].buf_len = bd[0].flags = 0;
}
io_req->bd_tbl->bd_valid = bd_count;
/*
* Return the command to ML if BD count exceeds the max number
* that can be handled by FW.
*/
if (bd_count > BNX2FC_FW_MAX_BDS_PER_CMD) {
pr_err("bd_count = %d exceeded FW supported max BD(255), task_id = 0x%x\n",
bd_count, io_req->xid);
return -ENOMEM;
}
return 0;
}
static void bnx2fc_unmap_sg_list(struct bnx2fc_cmd *io_req)
{
struct scsi_cmnd *sc = io_req->sc_cmd;
struct bnx2fc_interface *interface = io_req->port->priv;
struct bnx2fc_hba *hba = interface->hba;
/*
* Use dma_unmap_sg directly to ensure we're using the correct
* dev struct off of pcidev.
*/
if (io_req->bd_tbl->bd_valid && sc && scsi_sg_count(sc)) {
dma_unmap_sg(&hba->pcidev->dev, scsi_sglist(sc),
scsi_sg_count(sc), sc->sc_data_direction);
io_req->bd_tbl->bd_valid = 0;
}
}
void bnx2fc_build_fcp_cmnd(struct bnx2fc_cmd *io_req,
struct fcp_cmnd *fcp_cmnd)
{
struct scsi_cmnd *sc_cmd = io_req->sc_cmd;
memset(fcp_cmnd, 0, sizeof(struct fcp_cmnd));
int_to_scsilun(sc_cmd->device->lun, &fcp_cmnd->fc_lun);
fcp_cmnd->fc_dl = htonl(io_req->data_xfer_len);
memcpy(fcp_cmnd->fc_cdb, sc_cmd->cmnd, sc_cmd->cmd_len);
fcp_cmnd->fc_cmdref = 0;
fcp_cmnd->fc_pri_ta = 0;
fcp_cmnd->fc_tm_flags = io_req->mp_req.tm_flags;
fcp_cmnd->fc_flags = io_req->io_req_flags;
fcp_cmnd->fc_pri_ta = FCP_PTA_SIMPLE;
}
static void bnx2fc_parse_fcp_rsp(struct bnx2fc_cmd *io_req,
struct fcoe_fcp_rsp_payload *fcp_rsp,
u8 num_rq, unsigned char *rq_data)
{
struct scsi_cmnd *sc_cmd = io_req->sc_cmd;
u8 rsp_flags = fcp_rsp->fcp_flags.flags;
u32 rq_buff_len = 0;
int fcp_sns_len = 0;
int fcp_rsp_len = 0;
io_req->fcp_status = FC_GOOD;
io_req->fcp_resid = 0;
if (rsp_flags & (FCOE_FCP_RSP_FLAGS_FCP_RESID_OVER |
FCOE_FCP_RSP_FLAGS_FCP_RESID_UNDER))
io_req->fcp_resid = fcp_rsp->fcp_resid;
io_req->scsi_comp_flags = rsp_flags;
io_req->cdb_status = fcp_rsp->scsi_status_code;
/* Fetch fcp_rsp_info and fcp_sns_info if available */
if (num_rq) {
/*
* We do not anticipate num_rq >1, as the linux defined
* SCSI_SENSE_BUFFERSIZE is 96 bytes + 8 bytes of FCP_RSP_INFO
* 256 bytes of single rq buffer is good enough to hold this.
*/
if (rsp_flags &
FCOE_FCP_RSP_FLAGS_FCP_RSP_LEN_VALID) {
fcp_rsp_len = rq_buff_len
= fcp_rsp->fcp_rsp_len;
}
if (rsp_flags &
FCOE_FCP_RSP_FLAGS_FCP_SNS_LEN_VALID) {
fcp_sns_len = fcp_rsp->fcp_sns_len;
rq_buff_len += fcp_rsp->fcp_sns_len;
}
io_req->fcp_rsp_len = fcp_rsp_len;
io_req->fcp_sns_len = fcp_sns_len;
if (rq_buff_len > num_rq * BNX2FC_RQ_BUF_SZ) {
/* Invalid sense sense length. */
printk(KERN_ERR PFX "invalid sns length %d\n",
rq_buff_len);
/* reset rq_buff_len */
rq_buff_len = num_rq * BNX2FC_RQ_BUF_SZ;
}
/* fetch fcp_rsp_code */
if ((fcp_rsp_len == 4) || (fcp_rsp_len == 8)) {
/* Only for task management function */
io_req->fcp_rsp_code = rq_data[3];
BNX2FC_IO_DBG(io_req, "fcp_rsp_code = %d\n",
io_req->fcp_rsp_code);
}
/* fetch sense data */
rq_data += fcp_rsp_len;
if (fcp_sns_len > SCSI_SENSE_BUFFERSIZE) {
printk(KERN_ERR PFX "Truncating sense buffer\n");
fcp_sns_len = SCSI_SENSE_BUFFERSIZE;
}
memset(sc_cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE);
if (fcp_sns_len)
memcpy(sc_cmd->sense_buffer, rq_data, fcp_sns_len);
}
}
/**
* bnx2fc_queuecommand - Queuecommand function of the scsi template
*
* @host: The Scsi_Host the command was issued to
* @sc_cmd: struct scsi_cmnd to be executed
*
* This is the IO strategy routine, called by SCSI-ML
**/
int bnx2fc_queuecommand(struct Scsi_Host *host,
struct scsi_cmnd *sc_cmd)
{
struct fc_lport *lport = shost_priv(host);
struct fc_rport *rport = starget_to_rport(scsi_target(sc_cmd->device));
struct fc_rport_libfc_priv *rp = rport->dd_data;
struct bnx2fc_rport *tgt;
struct bnx2fc_cmd *io_req;
int rc = 0;
int rval;
rval = fc_remote_port_chkready(rport);
if (rval) {
sc_cmd->result = rval;
scsi_done(sc_cmd);
return 0;
}
if ((lport->state != LPORT_ST_READY) || !(lport->link_up)) {
rc = SCSI_MLQUEUE_HOST_BUSY;
goto exit_qcmd;
}
/* rport and tgt are allocated together, so tgt should be non-NULL */
tgt = (struct bnx2fc_rport *)&rp[1];
if (!test_bit(BNX2FC_FLAG_SESSION_READY, &tgt->flags)) {
/*
* Session is not offloaded yet. Let SCSI-ml retry
* the command.
*/
rc = SCSI_MLQUEUE_TARGET_BUSY;
goto exit_qcmd;
}
if (tgt->retry_delay_timestamp) {
if (time_after(jiffies, tgt->retry_delay_timestamp)) {
tgt->retry_delay_timestamp = 0;
} else {
/* If retry_delay timer is active, flow off the ML */
rc = SCSI_MLQUEUE_TARGET_BUSY;
goto exit_qcmd;
}
}
bnx2fc: fix tgt spinlock locking bnx2fc_queuecommand(): when allocating a new io_req, the tgt_lock spinlock must be locked before calling bnx2fc_cmd_alloc(). The spinlock should also be kept locked until bnx2fc_post_io_req() has been completed. If not, a kernel thread may call bnx2fc_process_cq_compl() that extracts the newly allocated io_req from hba->cmd_mgr->cmds and destroys it while it is still being used by bnx2fc_post_io_req(). BUG: unable to handle kernel NULL pointer dereference at 000000000000004c IP: [<ffffffffa03130da>] bnx2fc_init_task+0x6a/0x230 [bnx2fc] PGD 0 Oops: 0000 [#1] SMP last sysfs file: /sys/devices/pci0000:00/0000:00:02.0/0000:04:00.3/net/eth3/type CPU 33 Modules linked in: autofs4 target_core_iblock target_core_file target_core_pscsi target_core_mod configfs bnx2fc cnic uio fcoe libfcoe libfc scsi_transport_fc 8021q garp scsi_tgt stp llc cpufreq_ondemand freq_table pcc_cpufreq ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables ipv6 power_meter microcode iTCO_wdt iTCO_vendor_support hpilo hpwdt sg bnx2x libcrc32c mdio serio_raw lpc_ich mfd_core shpchp ext4 jbd2 mbcache sd_mod crc_t10dif hpsa video output dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_wait_scan] Pid: 7355, comm: bnx2fc_thread/3 Not tainted 2.6.32-431.el6.x86_64 #1 HP ProLiant BL460c Gen8 RIP: 0010:[<ffffffffa03130da>] [<ffffffffa03130da>] bnx2fc_init_task+0x6a/0x230 [bnx2fc] RSP: 0018:ffff8820b0da3b68 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff882003801080 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff882003801100 RBP: ffff8820b0da3bc8 R08: ffffffff8160d4e8 R09: 0000000000000040 R10: 0000000000000000 R11: 0000000000000000 R12: ffff88400e600e00 R13: ffff8840108fbe40 R14: ffff88200ffe5400 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8820b0da0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 000000000000004c CR3: 0000002010b67000 CR4: 00000000001407e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process bnx2fc_thread/3 (pid: 7355, threadinfo ffff88401f940000, task ffff884012f5f540) Stack: ffff8820b0da3bc8 ffffffff81527303 ffff884000000020 ffff8820b0da3bd8 <d> ffff8820b0da3b98 000000028138931a ffff88400f506078 ffff88400e600e00 <d> ffff88200ffe5400 ffff88200ffe5590 0000000000000021 0000000000000002 Call Trace: <IRQ> [<ffffffff81527303>] ? printk+0x41/0x46 [<ffffffffa03169bc>] bnx2fc_post_io_req+0x11c/0x440 [bnx2fc] [<ffffffff812825b9>] ? cpumask_next_and+0x29/0x50 [<ffffffff8137ffd0>] ? scsi_done+0x0/0x60 [<ffffffffa0316df7>] bnx2fc_queuecommand+0x117/0x140 [bnx2fc] [<ffffffff81380245>] scsi_dispatch_cmd+0xe5/0x310 [<ffffffff81388b9e>] scsi_request_fn+0x5ee/0x7a0 [<ffffffff812658f1>] __blk_run_queue+0x31/0x40 [<ffffffff81265a40>] blk_run_queue+0x30/0x50 [<ffffffff81387da6>] scsi_run_queue+0xc6/0x270 [<ffffffff81260f92>] ? elv_requeue_request+0x52/0xa0 [<ffffffff813897a0>] scsi_requeue_command+0x90/0xb0 [<ffffffff81389b84>] scsi_io_completion+0x154/0x6c0 [<ffffffff8137ff62>] scsi_finish_command+0xc2/0x130 [<ffffffff8138a255>] scsi_softirq_done+0x145/0x170 [<ffffffff8126e865>] blk_done_softirq+0x85/0xa0 [<ffffffff8107a8e1>] __do_softirq+0xc1/0x1e0 [<ffffffff8100c30c>] ? call_softirq+0x1c/0x30 [<ffffffff8100c30c>] call_softirq+0x1c/0x30 <EOI> [<ffffffff8100fa75>] ? do_softirq+0x65/0xa0 [<ffffffff8107a40a>] local_bh_enable_ip+0x9a/0xb0 [<ffffffff8152a4eb>] _spin_unlock_bh+0x1b/0x20 [<ffffffffa0313937>] bnx2fc_process_cq_compl+0x257/0x2b0 [bnx2fc] [<ffffffffa03114ea>] bnx2fc_percpu_io_thread+0xea/0x160 [bnx2fc] [<ffffffffa0311400>] ? bnx2fc_percpu_io_thread+0x0/0x160 [bnx2fc] [<ffffffff8109aef6>] kthread+0x96/0xa0 [<ffffffff8100c20a>] child_rip+0xa/0x20 [<ffffffff8109ae60>] ? kthread+0x0/0xa0 [<ffffffff8100c200>] ? child_rip+0x0/0x20 Code: 89 df 45 8b 7e 30 0f 85 75 01 00 00 89 d1 31 c0 c1 e9 03 83 e2 04 89 c9 f3 48 ab 74 06 c7 07 00 00 00 00 49 89 9c 24 88 01 00 00 <83> 7e 4c 01 b8 01 00 00 00 0f 84 e7 00 00 00 89 c2 0a 53 38 41 RIP [<ffffffffa03130da>] bnx2fc_init_task+0x6a/0x230 [bnx2fc] RSP <ffff8820b0da3b68> CR2: 000000000000004c Signed-off-by: Maurizio Lombardi <mlombard@redhat.com> Acked-by: Chad Dupuis <chad.dupuis@qlogic.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2014-11-07 19:55:39 +08:00
spin_lock_bh(&tgt->tgt_lock);
io_req = bnx2fc_cmd_alloc(tgt);
if (!io_req) {
rc = SCSI_MLQUEUE_HOST_BUSY;
bnx2fc: fix tgt spinlock locking bnx2fc_queuecommand(): when allocating a new io_req, the tgt_lock spinlock must be locked before calling bnx2fc_cmd_alloc(). The spinlock should also be kept locked until bnx2fc_post_io_req() has been completed. If not, a kernel thread may call bnx2fc_process_cq_compl() that extracts the newly allocated io_req from hba->cmd_mgr->cmds and destroys it while it is still being used by bnx2fc_post_io_req(). BUG: unable to handle kernel NULL pointer dereference at 000000000000004c IP: [<ffffffffa03130da>] bnx2fc_init_task+0x6a/0x230 [bnx2fc] PGD 0 Oops: 0000 [#1] SMP last sysfs file: /sys/devices/pci0000:00/0000:00:02.0/0000:04:00.3/net/eth3/type CPU 33 Modules linked in: autofs4 target_core_iblock target_core_file target_core_pscsi target_core_mod configfs bnx2fc cnic uio fcoe libfcoe libfc scsi_transport_fc 8021q garp scsi_tgt stp llc cpufreq_ondemand freq_table pcc_cpufreq ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables ipv6 power_meter microcode iTCO_wdt iTCO_vendor_support hpilo hpwdt sg bnx2x libcrc32c mdio serio_raw lpc_ich mfd_core shpchp ext4 jbd2 mbcache sd_mod crc_t10dif hpsa video output dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_wait_scan] Pid: 7355, comm: bnx2fc_thread/3 Not tainted 2.6.32-431.el6.x86_64 #1 HP ProLiant BL460c Gen8 RIP: 0010:[<ffffffffa03130da>] [<ffffffffa03130da>] bnx2fc_init_task+0x6a/0x230 [bnx2fc] RSP: 0018:ffff8820b0da3b68 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff882003801080 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff882003801100 RBP: ffff8820b0da3bc8 R08: ffffffff8160d4e8 R09: 0000000000000040 R10: 0000000000000000 R11: 0000000000000000 R12: ffff88400e600e00 R13: ffff8840108fbe40 R14: ffff88200ffe5400 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8820b0da0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 000000000000004c CR3: 0000002010b67000 CR4: 00000000001407e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process bnx2fc_thread/3 (pid: 7355, threadinfo ffff88401f940000, task ffff884012f5f540) Stack: ffff8820b0da3bc8 ffffffff81527303 ffff884000000020 ffff8820b0da3bd8 <d> ffff8820b0da3b98 000000028138931a ffff88400f506078 ffff88400e600e00 <d> ffff88200ffe5400 ffff88200ffe5590 0000000000000021 0000000000000002 Call Trace: <IRQ> [<ffffffff81527303>] ? printk+0x41/0x46 [<ffffffffa03169bc>] bnx2fc_post_io_req+0x11c/0x440 [bnx2fc] [<ffffffff812825b9>] ? cpumask_next_and+0x29/0x50 [<ffffffff8137ffd0>] ? scsi_done+0x0/0x60 [<ffffffffa0316df7>] bnx2fc_queuecommand+0x117/0x140 [bnx2fc] [<ffffffff81380245>] scsi_dispatch_cmd+0xe5/0x310 [<ffffffff81388b9e>] scsi_request_fn+0x5ee/0x7a0 [<ffffffff812658f1>] __blk_run_queue+0x31/0x40 [<ffffffff81265a40>] blk_run_queue+0x30/0x50 [<ffffffff81387da6>] scsi_run_queue+0xc6/0x270 [<ffffffff81260f92>] ? elv_requeue_request+0x52/0xa0 [<ffffffff813897a0>] scsi_requeue_command+0x90/0xb0 [<ffffffff81389b84>] scsi_io_completion+0x154/0x6c0 [<ffffffff8137ff62>] scsi_finish_command+0xc2/0x130 [<ffffffff8138a255>] scsi_softirq_done+0x145/0x170 [<ffffffff8126e865>] blk_done_softirq+0x85/0xa0 [<ffffffff8107a8e1>] __do_softirq+0xc1/0x1e0 [<ffffffff8100c30c>] ? call_softirq+0x1c/0x30 [<ffffffff8100c30c>] call_softirq+0x1c/0x30 <EOI> [<ffffffff8100fa75>] ? do_softirq+0x65/0xa0 [<ffffffff8107a40a>] local_bh_enable_ip+0x9a/0xb0 [<ffffffff8152a4eb>] _spin_unlock_bh+0x1b/0x20 [<ffffffffa0313937>] bnx2fc_process_cq_compl+0x257/0x2b0 [bnx2fc] [<ffffffffa03114ea>] bnx2fc_percpu_io_thread+0xea/0x160 [bnx2fc] [<ffffffffa0311400>] ? bnx2fc_percpu_io_thread+0x0/0x160 [bnx2fc] [<ffffffff8109aef6>] kthread+0x96/0xa0 [<ffffffff8100c20a>] child_rip+0xa/0x20 [<ffffffff8109ae60>] ? kthread+0x0/0xa0 [<ffffffff8100c200>] ? child_rip+0x0/0x20 Code: 89 df 45 8b 7e 30 0f 85 75 01 00 00 89 d1 31 c0 c1 e9 03 83 e2 04 89 c9 f3 48 ab 74 06 c7 07 00 00 00 00 49 89 9c 24 88 01 00 00 <83> 7e 4c 01 b8 01 00 00 00 0f 84 e7 00 00 00 89 c2 0a 53 38 41 RIP [<ffffffffa03130da>] bnx2fc_init_task+0x6a/0x230 [bnx2fc] RSP <ffff8820b0da3b68> CR2: 000000000000004c Signed-off-by: Maurizio Lombardi <mlombard@redhat.com> Acked-by: Chad Dupuis <chad.dupuis@qlogic.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2014-11-07 19:55:39 +08:00
goto exit_qcmd_tgtlock;
}
io_req->sc_cmd = sc_cmd;
if (bnx2fc_post_io_req(tgt, io_req)) {
printk(KERN_ERR PFX "Unable to post io_req\n");
rc = SCSI_MLQUEUE_HOST_BUSY;
bnx2fc: fix tgt spinlock locking bnx2fc_queuecommand(): when allocating a new io_req, the tgt_lock spinlock must be locked before calling bnx2fc_cmd_alloc(). The spinlock should also be kept locked until bnx2fc_post_io_req() has been completed. If not, a kernel thread may call bnx2fc_process_cq_compl() that extracts the newly allocated io_req from hba->cmd_mgr->cmds and destroys it while it is still being used by bnx2fc_post_io_req(). BUG: unable to handle kernel NULL pointer dereference at 000000000000004c IP: [<ffffffffa03130da>] bnx2fc_init_task+0x6a/0x230 [bnx2fc] PGD 0 Oops: 0000 [#1] SMP last sysfs file: /sys/devices/pci0000:00/0000:00:02.0/0000:04:00.3/net/eth3/type CPU 33 Modules linked in: autofs4 target_core_iblock target_core_file target_core_pscsi target_core_mod configfs bnx2fc cnic uio fcoe libfcoe libfc scsi_transport_fc 8021q garp scsi_tgt stp llc cpufreq_ondemand freq_table pcc_cpufreq ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables ipv6 power_meter microcode iTCO_wdt iTCO_vendor_support hpilo hpwdt sg bnx2x libcrc32c mdio serio_raw lpc_ich mfd_core shpchp ext4 jbd2 mbcache sd_mod crc_t10dif hpsa video output dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_wait_scan] Pid: 7355, comm: bnx2fc_thread/3 Not tainted 2.6.32-431.el6.x86_64 #1 HP ProLiant BL460c Gen8 RIP: 0010:[<ffffffffa03130da>] [<ffffffffa03130da>] bnx2fc_init_task+0x6a/0x230 [bnx2fc] RSP: 0018:ffff8820b0da3b68 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff882003801080 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff882003801100 RBP: ffff8820b0da3bc8 R08: ffffffff8160d4e8 R09: 0000000000000040 R10: 0000000000000000 R11: 0000000000000000 R12: ffff88400e600e00 R13: ffff8840108fbe40 R14: ffff88200ffe5400 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8820b0da0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 000000000000004c CR3: 0000002010b67000 CR4: 00000000001407e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process bnx2fc_thread/3 (pid: 7355, threadinfo ffff88401f940000, task ffff884012f5f540) Stack: ffff8820b0da3bc8 ffffffff81527303 ffff884000000020 ffff8820b0da3bd8 <d> ffff8820b0da3b98 000000028138931a ffff88400f506078 ffff88400e600e00 <d> ffff88200ffe5400 ffff88200ffe5590 0000000000000021 0000000000000002 Call Trace: <IRQ> [<ffffffff81527303>] ? printk+0x41/0x46 [<ffffffffa03169bc>] bnx2fc_post_io_req+0x11c/0x440 [bnx2fc] [<ffffffff812825b9>] ? cpumask_next_and+0x29/0x50 [<ffffffff8137ffd0>] ? scsi_done+0x0/0x60 [<ffffffffa0316df7>] bnx2fc_queuecommand+0x117/0x140 [bnx2fc] [<ffffffff81380245>] scsi_dispatch_cmd+0xe5/0x310 [<ffffffff81388b9e>] scsi_request_fn+0x5ee/0x7a0 [<ffffffff812658f1>] __blk_run_queue+0x31/0x40 [<ffffffff81265a40>] blk_run_queue+0x30/0x50 [<ffffffff81387da6>] scsi_run_queue+0xc6/0x270 [<ffffffff81260f92>] ? elv_requeue_request+0x52/0xa0 [<ffffffff813897a0>] scsi_requeue_command+0x90/0xb0 [<ffffffff81389b84>] scsi_io_completion+0x154/0x6c0 [<ffffffff8137ff62>] scsi_finish_command+0xc2/0x130 [<ffffffff8138a255>] scsi_softirq_done+0x145/0x170 [<ffffffff8126e865>] blk_done_softirq+0x85/0xa0 [<ffffffff8107a8e1>] __do_softirq+0xc1/0x1e0 [<ffffffff8100c30c>] ? call_softirq+0x1c/0x30 [<ffffffff8100c30c>] call_softirq+0x1c/0x30 <EOI> [<ffffffff8100fa75>] ? do_softirq+0x65/0xa0 [<ffffffff8107a40a>] local_bh_enable_ip+0x9a/0xb0 [<ffffffff8152a4eb>] _spin_unlock_bh+0x1b/0x20 [<ffffffffa0313937>] bnx2fc_process_cq_compl+0x257/0x2b0 [bnx2fc] [<ffffffffa03114ea>] bnx2fc_percpu_io_thread+0xea/0x160 [bnx2fc] [<ffffffffa0311400>] ? bnx2fc_percpu_io_thread+0x0/0x160 [bnx2fc] [<ffffffff8109aef6>] kthread+0x96/0xa0 [<ffffffff8100c20a>] child_rip+0xa/0x20 [<ffffffff8109ae60>] ? kthread+0x0/0xa0 [<ffffffff8100c200>] ? child_rip+0x0/0x20 Code: 89 df 45 8b 7e 30 0f 85 75 01 00 00 89 d1 31 c0 c1 e9 03 83 e2 04 89 c9 f3 48 ab 74 06 c7 07 00 00 00 00 49 89 9c 24 88 01 00 00 <83> 7e 4c 01 b8 01 00 00 00 0f 84 e7 00 00 00 89 c2 0a 53 38 41 RIP [<ffffffffa03130da>] bnx2fc_init_task+0x6a/0x230 [bnx2fc] RSP <ffff8820b0da3b68> CR2: 000000000000004c Signed-off-by: Maurizio Lombardi <mlombard@redhat.com> Acked-by: Chad Dupuis <chad.dupuis@qlogic.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2014-11-07 19:55:39 +08:00
goto exit_qcmd_tgtlock;
}
bnx2fc: fix tgt spinlock locking bnx2fc_queuecommand(): when allocating a new io_req, the tgt_lock spinlock must be locked before calling bnx2fc_cmd_alloc(). The spinlock should also be kept locked until bnx2fc_post_io_req() has been completed. If not, a kernel thread may call bnx2fc_process_cq_compl() that extracts the newly allocated io_req from hba->cmd_mgr->cmds and destroys it while it is still being used by bnx2fc_post_io_req(). BUG: unable to handle kernel NULL pointer dereference at 000000000000004c IP: [<ffffffffa03130da>] bnx2fc_init_task+0x6a/0x230 [bnx2fc] PGD 0 Oops: 0000 [#1] SMP last sysfs file: /sys/devices/pci0000:00/0000:00:02.0/0000:04:00.3/net/eth3/type CPU 33 Modules linked in: autofs4 target_core_iblock target_core_file target_core_pscsi target_core_mod configfs bnx2fc cnic uio fcoe libfcoe libfc scsi_transport_fc 8021q garp scsi_tgt stp llc cpufreq_ondemand freq_table pcc_cpufreq ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables ipv6 power_meter microcode iTCO_wdt iTCO_vendor_support hpilo hpwdt sg bnx2x libcrc32c mdio serio_raw lpc_ich mfd_core shpchp ext4 jbd2 mbcache sd_mod crc_t10dif hpsa video output dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_wait_scan] Pid: 7355, comm: bnx2fc_thread/3 Not tainted 2.6.32-431.el6.x86_64 #1 HP ProLiant BL460c Gen8 RIP: 0010:[<ffffffffa03130da>] [<ffffffffa03130da>] bnx2fc_init_task+0x6a/0x230 [bnx2fc] RSP: 0018:ffff8820b0da3b68 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff882003801080 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff882003801100 RBP: ffff8820b0da3bc8 R08: ffffffff8160d4e8 R09: 0000000000000040 R10: 0000000000000000 R11: 0000000000000000 R12: ffff88400e600e00 R13: ffff8840108fbe40 R14: ffff88200ffe5400 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8820b0da0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 000000000000004c CR3: 0000002010b67000 CR4: 00000000001407e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process bnx2fc_thread/3 (pid: 7355, threadinfo ffff88401f940000, task ffff884012f5f540) Stack: ffff8820b0da3bc8 ffffffff81527303 ffff884000000020 ffff8820b0da3bd8 <d> ffff8820b0da3b98 000000028138931a ffff88400f506078 ffff88400e600e00 <d> ffff88200ffe5400 ffff88200ffe5590 0000000000000021 0000000000000002 Call Trace: <IRQ> [<ffffffff81527303>] ? printk+0x41/0x46 [<ffffffffa03169bc>] bnx2fc_post_io_req+0x11c/0x440 [bnx2fc] [<ffffffff812825b9>] ? cpumask_next_and+0x29/0x50 [<ffffffff8137ffd0>] ? scsi_done+0x0/0x60 [<ffffffffa0316df7>] bnx2fc_queuecommand+0x117/0x140 [bnx2fc] [<ffffffff81380245>] scsi_dispatch_cmd+0xe5/0x310 [<ffffffff81388b9e>] scsi_request_fn+0x5ee/0x7a0 [<ffffffff812658f1>] __blk_run_queue+0x31/0x40 [<ffffffff81265a40>] blk_run_queue+0x30/0x50 [<ffffffff81387da6>] scsi_run_queue+0xc6/0x270 [<ffffffff81260f92>] ? elv_requeue_request+0x52/0xa0 [<ffffffff813897a0>] scsi_requeue_command+0x90/0xb0 [<ffffffff81389b84>] scsi_io_completion+0x154/0x6c0 [<ffffffff8137ff62>] scsi_finish_command+0xc2/0x130 [<ffffffff8138a255>] scsi_softirq_done+0x145/0x170 [<ffffffff8126e865>] blk_done_softirq+0x85/0xa0 [<ffffffff8107a8e1>] __do_softirq+0xc1/0x1e0 [<ffffffff8100c30c>] ? call_softirq+0x1c/0x30 [<ffffffff8100c30c>] call_softirq+0x1c/0x30 <EOI> [<ffffffff8100fa75>] ? do_softirq+0x65/0xa0 [<ffffffff8107a40a>] local_bh_enable_ip+0x9a/0xb0 [<ffffffff8152a4eb>] _spin_unlock_bh+0x1b/0x20 [<ffffffffa0313937>] bnx2fc_process_cq_compl+0x257/0x2b0 [bnx2fc] [<ffffffffa03114ea>] bnx2fc_percpu_io_thread+0xea/0x160 [bnx2fc] [<ffffffffa0311400>] ? bnx2fc_percpu_io_thread+0x0/0x160 [bnx2fc] [<ffffffff8109aef6>] kthread+0x96/0xa0 [<ffffffff8100c20a>] child_rip+0xa/0x20 [<ffffffff8109ae60>] ? kthread+0x0/0xa0 [<ffffffff8100c200>] ? child_rip+0x0/0x20 Code: 89 df 45 8b 7e 30 0f 85 75 01 00 00 89 d1 31 c0 c1 e9 03 83 e2 04 89 c9 f3 48 ab 74 06 c7 07 00 00 00 00 49 89 9c 24 88 01 00 00 <83> 7e 4c 01 b8 01 00 00 00 0f 84 e7 00 00 00 89 c2 0a 53 38 41 RIP [<ffffffffa03130da>] bnx2fc_init_task+0x6a/0x230 [bnx2fc] RSP <ffff8820b0da3b68> CR2: 000000000000004c Signed-off-by: Maurizio Lombardi <mlombard@redhat.com> Acked-by: Chad Dupuis <chad.dupuis@qlogic.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2014-11-07 19:55:39 +08:00
exit_qcmd_tgtlock:
spin_unlock_bh(&tgt->tgt_lock);
exit_qcmd:
return rc;
}
void bnx2fc_process_scsi_cmd_compl(struct bnx2fc_cmd *io_req,
struct fcoe_task_ctx_entry *task,
u8 num_rq, unsigned char *rq_data)
{
struct fcoe_fcp_rsp_payload *fcp_rsp;
struct bnx2fc_rport *tgt = io_req->tgt;
struct scsi_cmnd *sc_cmd;
u16 scope = 0, qualifier = 0;
/* scsi_cmd_cmpl is called with tgt lock held */
if (test_and_set_bit(BNX2FC_FLAG_IO_COMPL, &io_req->req_flags)) {
/* we will not receive ABTS response for this IO */
BNX2FC_IO_DBG(io_req, "Timer context finished processing "
"this scsi cmd\n");
if (test_and_clear_bit(BNX2FC_FLAG_IO_CLEANUP,
&io_req->req_flags)) {
BNX2FC_IO_DBG(io_req,
"Actual completion after cleanup request cleaning up\n");
bnx2fc_process_cleanup_compl(io_req, task, num_rq);
}
return;
}
/* Cancel the timeout_work, as we received IO completion */
if (cancel_delayed_work(&io_req->timeout_work))
kref_put(&io_req->refcount,
bnx2fc_cmd_release); /* drop timer hold */
sc_cmd = io_req->sc_cmd;
if (sc_cmd == NULL) {
printk(KERN_ERR PFX "scsi_cmd_compl - sc_cmd is NULL\n");
return;
}
/* Fetch fcp_rsp from task context and perform cmd completion */
fcp_rsp = (struct fcoe_fcp_rsp_payload *)
&(task->rxwr_only.union_ctx.comp_info.fcp_rsp.payload);
/* parse fcp_rsp and obtain sense data from RQ if available */
bnx2fc_parse_fcp_rsp(io_req, fcp_rsp, num_rq, rq_data);
if (!bnx2fc_priv(sc_cmd)->io_req) {
printk(KERN_ERR PFX "io_req is NULL\n");
return;
}
if (io_req->on_active_queue) {
list_del_init(&io_req->link);
io_req->on_active_queue = 0;
/* Move IO req to retire queue */
list_add_tail(&io_req->link, &tgt->io_retire_queue);
} else {
/* This should not happen, but could have been pulled
* by bnx2fc_flush_active_ios(), or during a race
* between command abort and (late) completion.
*/
BNX2FC_IO_DBG(io_req, "xid not on active_cmd_queue\n");
if (io_req->wait_for_abts_comp)
if (test_and_clear_bit(BNX2FC_FLAG_EH_ABORT,
&io_req->req_flags))
complete(&io_req->abts_done);
}
bnx2fc_unmap_sg_list(io_req);
io_req->sc_cmd = NULL;
switch (io_req->fcp_status) {
case FC_GOOD:
if (io_req->cdb_status == 0) {
/* Good IO completion */
sc_cmd->result = DID_OK << 16;
} else {
/* Transport status is good, SCSI status not good */
BNX2FC_IO_DBG(io_req, "scsi_cmpl: cdb_status = %d"
" fcp_resid = 0x%x\n",
io_req->cdb_status, io_req->fcp_resid);
sc_cmd->result = (DID_OK << 16) | io_req->cdb_status;
if (io_req->cdb_status == SAM_STAT_TASK_SET_FULL ||
io_req->cdb_status == SAM_STAT_BUSY) {
/* Newer array firmware with BUSY or
* TASK_SET_FULL may return a status that needs
* the scope bits masked.
* Or a huge delay timestamp up to 27 minutes
* can result.
*/
if (fcp_rsp->retry_delay_timer) {
/* Upper 2 bits */
scope = fcp_rsp->retry_delay_timer
& 0xC000;
/* Lower 14 bits */
qualifier = fcp_rsp->retry_delay_timer
& 0x3FFF;
}
if (scope > 0 && qualifier > 0 &&
qualifier <= 0x3FEF) {
/* Set the jiffies +
* retry_delay_timer * 100ms
* for the rport/tgt
*/
tgt->retry_delay_timestamp = jiffies +
(qualifier * HZ / 10);
}
}
}
if (io_req->fcp_resid)
scsi_set_resid(sc_cmd, io_req->fcp_resid);
break;
default:
printk(KERN_ERR PFX "scsi_cmd_compl: fcp_status = %d\n",
io_req->fcp_status);
break;
}
bnx2fc_priv(sc_cmd)->io_req = NULL;
scsi_done(sc_cmd);
kref_put(&io_req->refcount, bnx2fc_cmd_release);
}
int bnx2fc_post_io_req(struct bnx2fc_rport *tgt,
struct bnx2fc_cmd *io_req)
{
struct fcoe_task_ctx_entry *task;
struct fcoe_task_ctx_entry *task_page;
struct scsi_cmnd *sc_cmd = io_req->sc_cmd;
struct fcoe_port *port = tgt->port;
struct bnx2fc_interface *interface = port->priv;
struct bnx2fc_hba *hba = interface->hba;
struct fc_lport *lport = port->lport;
int task_idx, index;
u16 xid;
bnx2fc: fix tgt spinlock locking bnx2fc_queuecommand(): when allocating a new io_req, the tgt_lock spinlock must be locked before calling bnx2fc_cmd_alloc(). The spinlock should also be kept locked until bnx2fc_post_io_req() has been completed. If not, a kernel thread may call bnx2fc_process_cq_compl() that extracts the newly allocated io_req from hba->cmd_mgr->cmds and destroys it while it is still being used by bnx2fc_post_io_req(). BUG: unable to handle kernel NULL pointer dereference at 000000000000004c IP: [<ffffffffa03130da>] bnx2fc_init_task+0x6a/0x230 [bnx2fc] PGD 0 Oops: 0000 [#1] SMP last sysfs file: /sys/devices/pci0000:00/0000:00:02.0/0000:04:00.3/net/eth3/type CPU 33 Modules linked in: autofs4 target_core_iblock target_core_file target_core_pscsi target_core_mod configfs bnx2fc cnic uio fcoe libfcoe libfc scsi_transport_fc 8021q garp scsi_tgt stp llc cpufreq_ondemand freq_table pcc_cpufreq ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables ipv6 power_meter microcode iTCO_wdt iTCO_vendor_support hpilo hpwdt sg bnx2x libcrc32c mdio serio_raw lpc_ich mfd_core shpchp ext4 jbd2 mbcache sd_mod crc_t10dif hpsa video output dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_wait_scan] Pid: 7355, comm: bnx2fc_thread/3 Not tainted 2.6.32-431.el6.x86_64 #1 HP ProLiant BL460c Gen8 RIP: 0010:[<ffffffffa03130da>] [<ffffffffa03130da>] bnx2fc_init_task+0x6a/0x230 [bnx2fc] RSP: 0018:ffff8820b0da3b68 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff882003801080 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff882003801100 RBP: ffff8820b0da3bc8 R08: ffffffff8160d4e8 R09: 0000000000000040 R10: 0000000000000000 R11: 0000000000000000 R12: ffff88400e600e00 R13: ffff8840108fbe40 R14: ffff88200ffe5400 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8820b0da0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 000000000000004c CR3: 0000002010b67000 CR4: 00000000001407e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process bnx2fc_thread/3 (pid: 7355, threadinfo ffff88401f940000, task ffff884012f5f540) Stack: ffff8820b0da3bc8 ffffffff81527303 ffff884000000020 ffff8820b0da3bd8 <d> ffff8820b0da3b98 000000028138931a ffff88400f506078 ffff88400e600e00 <d> ffff88200ffe5400 ffff88200ffe5590 0000000000000021 0000000000000002 Call Trace: <IRQ> [<ffffffff81527303>] ? printk+0x41/0x46 [<ffffffffa03169bc>] bnx2fc_post_io_req+0x11c/0x440 [bnx2fc] [<ffffffff812825b9>] ? cpumask_next_and+0x29/0x50 [<ffffffff8137ffd0>] ? scsi_done+0x0/0x60 [<ffffffffa0316df7>] bnx2fc_queuecommand+0x117/0x140 [bnx2fc] [<ffffffff81380245>] scsi_dispatch_cmd+0xe5/0x310 [<ffffffff81388b9e>] scsi_request_fn+0x5ee/0x7a0 [<ffffffff812658f1>] __blk_run_queue+0x31/0x40 [<ffffffff81265a40>] blk_run_queue+0x30/0x50 [<ffffffff81387da6>] scsi_run_queue+0xc6/0x270 [<ffffffff81260f92>] ? elv_requeue_request+0x52/0xa0 [<ffffffff813897a0>] scsi_requeue_command+0x90/0xb0 [<ffffffff81389b84>] scsi_io_completion+0x154/0x6c0 [<ffffffff8137ff62>] scsi_finish_command+0xc2/0x130 [<ffffffff8138a255>] scsi_softirq_done+0x145/0x170 [<ffffffff8126e865>] blk_done_softirq+0x85/0xa0 [<ffffffff8107a8e1>] __do_softirq+0xc1/0x1e0 [<ffffffff8100c30c>] ? call_softirq+0x1c/0x30 [<ffffffff8100c30c>] call_softirq+0x1c/0x30 <EOI> [<ffffffff8100fa75>] ? do_softirq+0x65/0xa0 [<ffffffff8107a40a>] local_bh_enable_ip+0x9a/0xb0 [<ffffffff8152a4eb>] _spin_unlock_bh+0x1b/0x20 [<ffffffffa0313937>] bnx2fc_process_cq_compl+0x257/0x2b0 [bnx2fc] [<ffffffffa03114ea>] bnx2fc_percpu_io_thread+0xea/0x160 [bnx2fc] [<ffffffffa0311400>] ? bnx2fc_percpu_io_thread+0x0/0x160 [bnx2fc] [<ffffffff8109aef6>] kthread+0x96/0xa0 [<ffffffff8100c20a>] child_rip+0xa/0x20 [<ffffffff8109ae60>] ? kthread+0x0/0xa0 [<ffffffff8100c200>] ? child_rip+0x0/0x20 Code: 89 df 45 8b 7e 30 0f 85 75 01 00 00 89 d1 31 c0 c1 e9 03 83 e2 04 89 c9 f3 48 ab 74 06 c7 07 00 00 00 00 49 89 9c 24 88 01 00 00 <83> 7e 4c 01 b8 01 00 00 00 0f 84 e7 00 00 00 89 c2 0a 53 38 41 RIP [<ffffffffa03130da>] bnx2fc_init_task+0x6a/0x230 [bnx2fc] RSP <ffff8820b0da3b68> CR2: 000000000000004c Signed-off-by: Maurizio Lombardi <mlombard@redhat.com> Acked-by: Chad Dupuis <chad.dupuis@qlogic.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2014-11-07 19:55:39 +08:00
/* bnx2fc_post_io_req() is called with the tgt_lock held */
/* Initialize rest of io_req fields */
io_req->cmd_type = BNX2FC_SCSI_CMD;
io_req->port = port;
io_req->tgt = tgt;
io_req->data_xfer_len = scsi_bufflen(sc_cmd);
bnx2fc_priv(sc_cmd)->io_req = io_req;
if (sc_cmd->sc_data_direction == DMA_FROM_DEVICE) {
io_req->io_req_flags = BNX2FC_READ;
this_cpu_inc(lport->stats->InputRequests);
this_cpu_add(lport->stats->InputBytes, io_req->data_xfer_len);
} else if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) {
io_req->io_req_flags = BNX2FC_WRITE;
this_cpu_inc(lport->stats->OutputRequests);
this_cpu_add(lport->stats->OutputBytes, io_req->data_xfer_len);
} else {
io_req->io_req_flags = 0;
this_cpu_inc(lport->stats->ControlRequests);
}
xid = io_req->xid;
/* Build buffer descriptor list for firmware from sg list */
if (bnx2fc_build_bd_list_from_sg(io_req)) {
printk(KERN_ERR PFX "BD list creation failed\n");
kref_put(&io_req->refcount, bnx2fc_cmd_release);
return -EAGAIN;
}
task_idx = xid / BNX2FC_TASKS_PER_PAGE;
index = xid % BNX2FC_TASKS_PER_PAGE;
/* Initialize task context for this IO request */
task_page = (struct fcoe_task_ctx_entry *) hba->task_ctx[task_idx];
task = &(task_page[index]);
bnx2fc_init_task(io_req, task);
if (tgt->flush_in_prog) {
printk(KERN_ERR PFX "Flush in progress..Host Busy\n");
kref_put(&io_req->refcount, bnx2fc_cmd_release);
return -EAGAIN;
}
if (!test_bit(BNX2FC_FLAG_SESSION_READY, &tgt->flags)) {
printk(KERN_ERR PFX "Session not ready...post_io\n");
kref_put(&io_req->refcount, bnx2fc_cmd_release);
return -EAGAIN;
}
/* Time IO req */
if (tgt->io_timeout)
bnx2fc_cmd_timer_set(io_req, BNX2FC_IO_TIMEOUT);
/* Obtain free SQ entry */
bnx2fc_add_2_sq(tgt, xid);
/* Enqueue the io_req to active_cmd_queue */
io_req->on_active_queue = 1;
/* move io_req from pending_queue to active_queue */
list_add_tail(&io_req->link, &tgt->active_cmd_queue);
/* Ring doorbell */
bnx2fc_ring_doorbell(tgt);
return 0;
}