cxgbit.h - This file contains data structure definitions for cxgbit.ko. cxgbit_lro.h - This file contains data structure definitions for LRO support. cxgbit_main.c - This file contains code for registering with iscsi target transport and cxgb4 driver. cxgbit_cm.c - This file contains code for connection management. cxgbit_target.c - This file contains code for processing iSCSI PDU. cxgbit_ddp.c - This file contains code for Direct Data Placement. v2: added check for NULL sg in cxgbit_set_one_ppod() Reported-by: Dan Carpenter <dan.carpenter@xxxxxxxxxx> cxgbit: add Kconfig and Makefile v2: added dependency on INET Reported-by: Arnd Bergmann <arnd@xxxxxxxx> iscsi-target: update Kconfig and Makefile for compiling cxgbit.ko. Signed-off-by: Varun Prakash <varun@xxxxxxxxxxx> --- drivers/target/iscsi/Kconfig | 2 + drivers/target/iscsi/Makefile | 1 + drivers/target/iscsi/cxgbit/Kconfig | 7 + drivers/target/iscsi/cxgbit/Makefile | 6 + drivers/target/iscsi/cxgbit/cxgbit.h | 358 +++++ drivers/target/iscsi/cxgbit/cxgbit_cm.c | 2086 +++++++++++++++++++++++++++ drivers/target/iscsi/cxgbit/cxgbit_ddp.c | 325 +++++ drivers/target/iscsi/cxgbit/cxgbit_lro.h | 72 + drivers/target/iscsi/cxgbit/cxgbit_main.c | 703 +++++++++ drivers/target/iscsi/cxgbit/cxgbit_target.c | 1601 ++++++++++++++++++++ 10 files changed, 5161 insertions(+) create mode 100644 drivers/target/iscsi/cxgbit/Kconfig create mode 100644 drivers/target/iscsi/cxgbit/Makefile create mode 100644 drivers/target/iscsi/cxgbit/cxgbit.h create mode 100644 drivers/target/iscsi/cxgbit/cxgbit_cm.c create mode 100644 drivers/target/iscsi/cxgbit/cxgbit_ddp.c create mode 100644 drivers/target/iscsi/cxgbit/cxgbit_lro.h create mode 100644 drivers/target/iscsi/cxgbit/cxgbit_main.c create mode 100644 drivers/target/iscsi/cxgbit/cxgbit_target.c diff --git a/drivers/target/iscsi/Kconfig b/drivers/target/iscsi/Kconfig index 8345fb4..bbdbf9c 100644 --- a/drivers/target/iscsi/Kconfig +++ b/drivers/target/iscsi/Kconfig @@ -7,3 +7,5 @@ config ISCSI_TARGET help Say M here to enable the ConfigFS enabled Linux-iSCSI.org iSCSI Target Mode Stack. + +source "drivers/target/iscsi/cxgbit/Kconfig" diff --git a/drivers/target/iscsi/Makefile b/drivers/target/iscsi/Makefile index 0f43be9..0f18295 100644 --- a/drivers/target/iscsi/Makefile +++ b/drivers/target/iscsi/Makefile @@ -18,3 +18,4 @@ iscsi_target_mod-y += iscsi_target_parameters.o \ iscsi_target_transport.o obj-$(CONFIG_ISCSI_TARGET) += iscsi_target_mod.o +obj-$(CONFIG_ISCSI_TARGET_CXGB4) += cxgbit/ diff --git a/drivers/target/iscsi/cxgbit/Kconfig b/drivers/target/iscsi/cxgbit/Kconfig new file mode 100644 index 0000000..c9b6a3c --- /dev/null +++ b/drivers/target/iscsi/cxgbit/Kconfig @@ -0,0 +1,7 @@ +config ISCSI_TARGET_CXGB4 + tristate "Chelsio iSCSI target offload driver" + depends on ISCSI_TARGET && CHELSIO_T4 && INET + select CHELSIO_T4_UWIRE + ---help--- + To compile this driver as module, choose M here: the module + will be called cxgbit. diff --git a/drivers/target/iscsi/cxgbit/Makefile b/drivers/target/iscsi/cxgbit/Makefile new file mode 100644 index 0000000..bd56c07 --- /dev/null +++ b/drivers/target/iscsi/cxgbit/Makefile @@ -0,0 +1,6 @@ +ccflags-y := -Idrivers/net/ethernet/chelsio/cxgb4 +ccflags-y += -Idrivers/target/iscsi + +obj-$(CONFIG_ISCSI_TARGET_CXGB4) += cxgbit.o + +cxgbit-y := cxgbit_main.o cxgbit_cm.o cxgbit_target.o cxgbit_ddp.o diff --git a/drivers/target/iscsi/cxgbit/cxgbit.h b/drivers/target/iscsi/cxgbit/cxgbit.h new file mode 100644 index 0000000..3aa9a3c --- /dev/null +++ b/drivers/target/iscsi/cxgbit/cxgbit.h @@ -0,0 +1,358 @@ +/* + * Copyright (c) 2016 Chelsio Communications, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __CXGBIT_H__ +#define __CXGBIT_H__ + +#include <linux/mutex.h> +#include <linux/list.h> +#include <linux/spinlock.h> +#include <linux/idr.h> +#include <linux/completion.h> +#include <linux/netdevice.h> +#include <linux/sched.h> +#include <linux/pci.h> +#include <linux/dma-mapping.h> +#include <linux/inet.h> +#include <linux/wait.h> +#include <linux/kref.h> +#include <linux/timer.h> +#include <linux/io.h> + +#include <asm/byteorder.h> + +#include <net/net_namespace.h> + +#include <target/iscsi/iscsi_transport.h> +#include <iscsi_target_parameters.h> +#include <iscsi_target_login.h> + +#include "t4_regs.h" +#include "t4_msg.h" +#include "cxgb4.h" +#include "cxgb4_uld.h" +#include "l2t.h" +#include "cxgb4_ppm.h" +#include "cxgbit_lro.h" + +extern struct mutex cdev_list_lock; +extern struct list_head cdev_list_head; +struct cxgbit_np; + +struct cxgbit_sock; + +struct cxgbit_cmd { + struct sk_buff *skb; + struct scatterlist sg; + struct cxgbi_task_tag_info ttinfo; + bool setup_ddp; + bool release; +}; + +#define CXGBIT_MAX_ISO_PAYLOAD \ + min_t(u32, MAX_SKB_FRAGS * PAGE_SIZE, 65535) + +struct cxgbit_iso_info { + u8 flags; + u32 mpdu; + u32 len; + u32 burst_len; +}; + +enum cxgbit_skcb_flags { + SKCBF_TX_NEED_HDR = (1 << 0), /* packet needs a header */ + SKCBF_TX_FLAG_COMPL = (1 << 1), /* wr completion flag */ + SKCBF_TX_ISO = (1 << 2), /* iso cpl in tx skb */ + SKCBF_RX_LRO = (1 << 3), /* lro skb */ +}; + +struct cxgbit_skb_rx_cb { + u8 opcode; + void *pdu_cb; + void (*backlog_fn)(struct cxgbit_sock *, struct sk_buff *); +}; + +struct cxgbit_skb_tx_cb { + u8 submode; + u32 extra_len; +}; + +union cxgbit_skb_cb { + struct { + u8 flags; + union { + struct cxgbit_skb_tx_cb tx; + struct cxgbit_skb_rx_cb rx; + }; + }; + + struct { + /* This member must be first. */ + struct l2t_skb_cb l2t; + struct sk_buff *wr_next; + }; +}; + +#define CXGBIT_SKB_CB(skb) ((union cxgbit_skb_cb *)&((skb)->cb[0])) +#define cxgbit_skcb_flags(skb) (CXGBIT_SKB_CB(skb)->flags) +#define cxgbit_skcb_submode(skb) (CXGBIT_SKB_CB(skb)->tx.submode) +#define cxgbit_skcb_tx_wr_next(skb) (CXGBIT_SKB_CB(skb)->wr_next) +#define cxgbit_skcb_tx_extralen(skb) (CXGBIT_SKB_CB(skb)->tx.extra_len) +#define cxgbit_skcb_rx_opcode(skb) (CXGBIT_SKB_CB(skb)->rx.opcode) +#define cxgbit_skcb_rx_backlog_fn(skb) (CXGBIT_SKB_CB(skb)->rx.backlog_fn) +#define cxgbit_rx_pdu_cb(skb) (CXGBIT_SKB_CB(skb)->rx.pdu_cb) + +static inline void *cplhdr(struct sk_buff *skb) +{ + return skb->data; +} + +enum cxgbit_cdev_flags { + CDEV_STATE_UP = 0, + CDEV_ISO_ENABLE, + CDEV_DDP_ENABLE, +}; + +#define NP_INFO_HASH_SIZE 32 + +struct np_info { + struct np_info *next; + struct cxgbit_np *cnp; + unsigned int stid; +}; + +struct cxgbit_list_head { + struct list_head list; + /* device lock */ + spinlock_t lock; +}; + +struct cxgbit_device { + struct list_head list; + struct cxgb4_lld_info lldi; + struct np_info *np_hash_tab[NP_INFO_HASH_SIZE]; + /* np lock */ + spinlock_t np_lock; + u8 selectq[MAX_NPORTS][2]; + struct cxgbit_list_head cskq; + u32 mdsl; + struct kref kref; + unsigned long flags; +}; + +struct cxgbit_wr_wait { + struct completion completion; + int ret; +}; + +enum cxgbit_csk_state { + CSK_STATE_IDLE = 0, + CSK_STATE_LISTEN, + CSK_STATE_CONNECTING, + CSK_STATE_ESTABLISHED, + CSK_STATE_ABORTING, + CSK_STATE_CLOSING, + CSK_STATE_MORIBUND, + CSK_STATE_DEAD, +}; + +enum cxgbit_csk_flags { + CSK_TX_DATA_SENT = 0, + CSK_LOGIN_PDU_DONE, + CSK_LOGIN_DONE, + CSK_DDP_ENABLE, +}; + +struct cxgbit_sock_common { + struct cxgbit_device *cdev; + struct sockaddr_storage local_addr; + struct sockaddr_storage remote_addr; + struct cxgbit_wr_wait wr_wait; + enum cxgbit_csk_state state; + unsigned long flags; +}; + +struct cxgbit_np { + struct cxgbit_sock_common com; + wait_queue_head_t accept_wait; + struct iscsi_np *np; + struct completion accept_comp; + struct list_head np_accept_list; + /* np accept lock */ + spinlock_t np_accept_lock; + struct kref kref; + unsigned int stid; +}; + +struct cxgbit_sock { + struct cxgbit_sock_common com; + struct cxgbit_np *cnp; + struct iscsi_conn *conn; + struct l2t_entry *l2t; + struct dst_entry *dst; + struct list_head list; + struct sk_buff_head rxq; + struct sk_buff_head txq; + struct sk_buff_head ppodq; + struct sk_buff_head backlogq; + struct sk_buff_head skbq; + struct sk_buff *wr_pending_head; + struct sk_buff *wr_pending_tail; + struct sk_buff *skb; + struct sk_buff *lro_skb; + struct sk_buff *lro_hskb; + struct list_head accept_node; + /* socket lock */ + spinlock_t lock; + wait_queue_head_t waitq; + wait_queue_head_t ack_waitq; + bool lock_owner; + struct kref kref; + u32 max_iso_npdu; + u32 wr_cred; + u32 wr_una_cred; + u32 wr_max_cred; + u32 snd_una; + u32 tid; + u32 snd_nxt; + u32 rcv_nxt; + u32 smac_idx; + u32 tx_chan; + u32 mtu; + u32 write_seq; + u32 rx_credits; + u32 snd_win; + u32 rcv_win; + u16 mss; + u16 emss; + u16 plen; + u16 rss_qid; + u16 txq_idx; + u16 ctrlq_idx; + u8 tos; + u8 port_id; +#define CXGBIT_SUBMODE_HCRC 0x1 +#define CXGBIT_SUBMODE_DCRC 0x2 + u8 submode; +#ifdef CONFIG_CHELSIO_T4_DCB + u8 dcb_priority; +#endif + u8 snd_wscale; +}; + +void _cxgbit_free_cdev(struct kref *kref); +void _cxgbit_free_csk(struct kref *kref); +void _cxgbit_free_cnp(struct kref *kref); + +static inline void cxgbit_get_cdev(struct cxgbit_device *cdev) +{ + kref_get(&cdev->kref); +} + +static inline void cxgbit_put_cdev(struct cxgbit_device *cdev) +{ + kref_put(&cdev->kref, _cxgbit_free_cdev); +} + +static inline void cxgbit_get_csk(struct cxgbit_sock *csk) +{ + kref_get(&csk->kref); +} + +static inline void cxgbit_put_csk(struct cxgbit_sock *csk) +{ + kref_put(&csk->kref, _cxgbit_free_csk); +} + +static inline void cxgbit_get_cnp(struct cxgbit_np *cnp) +{ + kref_get(&cnp->kref); +} + +static inline void cxgbit_put_cnp(struct cxgbit_np *cnp) +{ + kref_put(&cnp->kref, _cxgbit_free_cnp); +} + +static inline void cxgbit_sock_reset_wr_list(struct cxgbit_sock *csk) +{ + csk->wr_pending_tail = NULL; + csk->wr_pending_head = NULL; +} + +static inline struct sk_buff *cxgbit_sock_peek_wr(const struct cxgbit_sock *csk) +{ + return csk->wr_pending_head; +} + +static inline void +cxgbit_sock_enqueue_wr(struct cxgbit_sock *csk, struct sk_buff *skb) +{ + cxgbit_skcb_tx_wr_next(skb) = NULL; + + skb_get(skb); + + if (!csk->wr_pending_head) + csk->wr_pending_head = skb; + else + cxgbit_skcb_tx_wr_next(csk->wr_pending_tail) = skb; + csk->wr_pending_tail = skb; +} + +static inline struct sk_buff *cxgbit_sock_dequeue_wr(struct cxgbit_sock *csk) +{ + struct sk_buff *skb = csk->wr_pending_head; + + if (likely(skb)) { + csk->wr_pending_head = cxgbit_skcb_tx_wr_next(skb); + cxgbit_skcb_tx_wr_next(skb) = NULL; + } + return skb; +} + +typedef void (*cxgbit_cplhandler_func)(struct cxgbit_device *, + struct sk_buff *); + +int cxgbit_setup_np(struct iscsi_np *, struct sockaddr_storage *); +int cxgbit_setup_conn_digest(struct cxgbit_sock *); +int cxgbit_accept_np(struct iscsi_np *, struct iscsi_conn *); +void cxgbit_free_np(struct iscsi_np *); +void cxgbit_free_conn(struct iscsi_conn *); +extern cxgbit_cplhandler_func cxgbit_cplhandlers[NUM_CPL_CMDS]; +int cxgbit_get_login_rx(struct iscsi_conn *, struct iscsi_login *); +int cxgbit_rx_data_ack(struct cxgbit_sock *); +int cxgbit_l2t_send(struct cxgbit_device *, struct sk_buff *, + struct l2t_entry *); +void cxgbit_push_tx_frames(struct cxgbit_sock *); +int cxgbit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32); +void *cxgbit_alloc_pdu(struct iscsi_conn *, struct iscsi_cmd *); +int cxgbit_xmit_pdu(struct iscsi_conn *, struct iscsi_cmd *, + const void *, u32); +int cxgbit_xmit_datain_pdu(struct iscsi_conn *, struct iscsi_cmd *, + struct iscsi_datain_req *, + struct iscsi_datain *); +void cxgbit_get_r2t_ttt(struct iscsi_conn *, struct iscsi_cmd *, + struct iscsi_r2t *); +u32 cxgbit_send_tx_flowc_wr(struct cxgbit_sock *); +int cxgbit_ofld_send(struct cxgbit_device *, struct sk_buff *); +void cxgbit_get_rx_pdu(struct iscsi_conn *); +int cxgbit_validate_params(struct iscsi_conn *); +struct cxgbit_device *cxgbit_find_device(struct net_device *, u8 *); + +/* DDP */ +int cxgbit_ddp_init(struct cxgbit_device *); +int cxgbit_setup_conn_pgidx(struct cxgbit_sock *, u32); +int cxgbit_reserve_ttt(struct cxgbit_sock *, struct iscsi_cmd *); +void cxgbit_release_cmd(struct iscsi_conn *, struct iscsi_cmd *); + +static inline +struct cxgbi_ppm *cdev2ppm(struct cxgbit_device *cdev) +{ + return (struct cxgbi_ppm *)(*cdev->lldi.iscsi_ppm); +} +#endif /* __CXGBIT_H__ */ diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c new file mode 100644 index 0000000..0ae0b13 --- /dev/null +++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c @@ -0,0 +1,2086 @@ +/* + * Copyright (c) 2016 Chelsio Communications, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/list.h> +#include <linux/workqueue.h> +#include <linux/skbuff.h> +#include <linux/timer.h> +#include <linux/notifier.h> +#include <linux/inetdevice.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <linux/if_vlan.h> + +#include <net/neighbour.h> +#include <net/netevent.h> +#include <net/route.h> +#include <net/tcp.h> +#include <net/ip6_route.h> +#include <net/addrconf.h> + +#include "cxgbit.h" +#include "clip_tbl.h" + +static void cxgbit_init_wr_wait(struct cxgbit_wr_wait *wr_waitp) +{ + wr_waitp->ret = 0; + reinit_completion(&wr_waitp->completion); +} + +static void +cxgbit_wake_up(struct cxgbit_wr_wait *wr_waitp, const char *func, u8 ret) +{ + if (ret == CPL_ERR_NONE) + wr_waitp->ret = 0; + else + wr_waitp->ret = -EIO; + + if (wr_waitp->ret) + pr_err("%s: err:%u", func, ret); + + complete(&wr_waitp->completion); +} + +static int +cxgbit_wait_for_reply(struct cxgbit_device *cdev, + struct cxgbit_wr_wait *wr_waitp, u32 tid, u32 timeout, + const char *func) +{ + int ret; + + if (!test_bit(CDEV_STATE_UP, &cdev->flags)) { + wr_waitp->ret = -EIO; + goto out; + } + + ret = wait_for_completion_timeout(&wr_waitp->completion, timeout * HZ); + if (!ret) { + pr_info("%s - Device %s not responding tid %u\n", + func, pci_name(cdev->lldi.pdev), tid); + wr_waitp->ret = -ETIMEDOUT; + } +out: + if (wr_waitp->ret) + pr_info("%s: FW reply %d tid %u\n", + pci_name(cdev->lldi.pdev), wr_waitp->ret, tid); + return wr_waitp->ret; +} + +/* Returns whether a CPL status conveys negative advice. + */ +static int cxgbit_is_neg_adv(unsigned int status) +{ + return status == CPL_ERR_RTX_NEG_ADVICE || + status == CPL_ERR_PERSIST_NEG_ADVICE || + status == CPL_ERR_KEEPALV_NEG_ADVICE; +} + +static int cxgbit_np_hashfn(const struct cxgbit_np *cnp) +{ + return ((unsigned long)cnp >> 10) & (NP_INFO_HASH_SIZE - 1); +} + +static struct np_info * +cxgbit_np_hash_add(struct cxgbit_device *cdev, struct cxgbit_np *cnp, + unsigned int stid) +{ + struct np_info *p = kzalloc(sizeof(*p), GFP_KERNEL); + + if (p) { + int bucket = cxgbit_np_hashfn(cnp); + + p->cnp = cnp; + p->stid = stid; + spin_lock(&cdev->np_lock); + p->next = cdev->np_hash_tab[bucket]; + cdev->np_hash_tab[bucket] = p; + spin_unlock(&cdev->np_lock); + } + + return p; +} + +static int +cxgbit_np_hash_find(struct cxgbit_device *cdev, struct cxgbit_np *cnp) +{ + int stid = -1, bucket = cxgbit_np_hashfn(cnp); + struct np_info *p; + + spin_lock(&cdev->np_lock); + for (p = cdev->np_hash_tab[bucket]; p; p = p->next) { + if (p->cnp == cnp) { + stid = p->stid; + break; + } + } + spin_unlock(&cdev->np_lock); + + return stid; +} + +static int cxgbit_np_hash_del(struct cxgbit_device *cdev, struct cxgbit_np *cnp) +{ + int stid = -1, bucket = cxgbit_np_hashfn(cnp); + struct np_info *p, **prev = &cdev->np_hash_tab[bucket]; + + spin_lock(&cdev->np_lock); + for (p = *prev; p; prev = &p->next, p = p->next) { + if (p->cnp == cnp) { + stid = p->stid; + *prev = p->next; + kfree(p); + break; + } + } + spin_unlock(&cdev->np_lock); + + return stid; +} + +void _cxgbit_free_cnp(struct kref *kref) +{ + struct cxgbit_np *cnp; + + cnp = container_of(kref, struct cxgbit_np, kref); + kfree(cnp); +} + +static int +cxgbit_create_server6(struct cxgbit_device *cdev, unsigned int stid, + struct cxgbit_np *cnp) +{ + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) + &cnp->com.local_addr; + int addr_type; + int ret; + + pr_debug("%s: dev = %s; stid = %u; sin6_port = %u\n", + __func__, cdev->lldi.ports[0]->name, stid, sin6->sin6_port); + + addr_type = ipv6_addr_type((const struct in6_addr *) + &sin6->sin6_addr); + if (addr_type != IPV6_ADDR_ANY) { + ret = cxgb4_clip_get(cdev->lldi.ports[0], + (const u32 *)&sin6->sin6_addr.s6_addr, 1); + if (ret) { + pr_err("Unable to find clip table entry. laddr %pI6. Error:%d.\n", + sin6->sin6_addr.s6_addr, ret); + return -ENOMEM; + } + } + + cxgbit_get_cnp(cnp); + cxgbit_init_wr_wait(&cnp->com.wr_wait); + + ret = cxgb4_create_server6(cdev->lldi.ports[0], + stid, &sin6->sin6_addr, + sin6->sin6_port, + cdev->lldi.rxq_ids[0]); + if (!ret) + ret = cxgbit_wait_for_reply(cdev, &cnp->com.wr_wait, + 0, 10, __func__); + else if (ret > 0) + ret = net_xmit_errno(ret); + else + cxgbit_put_cnp(cnp); + + if (ret) { + if (ret != -ETIMEDOUT) + cxgb4_clip_release(cdev->lldi.ports[0], + (const u32 *)&sin6->sin6_addr.s6_addr, 1); + + pr_err("create server6 err %d stid %d laddr %pI6 lport %d\n", + ret, stid, sin6->sin6_addr.s6_addr, + ntohs(sin6->sin6_port)); + } + + return ret; +} + +static int +cxgbit_create_server4(struct cxgbit_device *cdev, unsigned int stid, + struct cxgbit_np *cnp) +{ + struct sockaddr_in *sin = (struct sockaddr_in *) + &cnp->com.local_addr; + int ret; + + pr_debug("%s: dev = %s; stid = %u; sin_port = %u\n", + __func__, cdev->lldi.ports[0]->name, stid, sin->sin_port); + + cxgbit_get_cnp(cnp); + cxgbit_init_wr_wait(&cnp->com.wr_wait); + + ret = cxgb4_create_server(cdev->lldi.ports[0], + stid, sin->sin_addr.s_addr, + sin->sin_port, 0, + cdev->lldi.rxq_ids[0]); + if (!ret) + ret = cxgbit_wait_for_reply(cdev, + &cnp->com.wr_wait, + 0, 10, __func__); + else if (ret > 0) + ret = net_xmit_errno(ret); + else + cxgbit_put_cnp(cnp); + + if (ret) + pr_err("create server failed err %d stid %d laddr %pI4 lport %d\n", + ret, stid, &sin->sin_addr, ntohs(sin->sin_port)); + return ret; +} + +struct cxgbit_device *cxgbit_find_device(struct net_device *ndev, u8 *port_id) +{ + struct cxgbit_device *cdev; + u8 i; + + list_for_each_entry(cdev, &cdev_list_head, list) { + struct cxgb4_lld_info *lldi = &cdev->lldi; + + for (i = 0; i < lldi->nports; i++) { + if (lldi->ports[i] == ndev) { + if (port_id) + *port_id = i; + return cdev; + } + } + } + + return NULL; +} + +static struct net_device *cxgbit_get_real_dev(struct net_device *ndev) +{ + if (ndev->priv_flags & IFF_BONDING) { + pr_err("Bond devices are not supported. Interface:%s\n", + ndev->name); + return NULL; + } + + if (is_vlan_dev(ndev)) + return vlan_dev_real_dev(ndev); + + return ndev; +} + +static struct net_device *cxgbit_ipv4_netdev(__be32 saddr) +{ + struct net_device *ndev; + + ndev = __ip_dev_find(&init_net, saddr, false); + if (!ndev) + return NULL; + + return cxgbit_get_real_dev(ndev); +} + +static struct net_device *cxgbit_ipv6_netdev(struct in6_addr *addr6) +{ + struct net_device *ndev = NULL; + bool found = false; + + if (IS_ENABLED(CONFIG_IPV6)) { + for_each_netdev_rcu(&init_net, ndev) + if (ipv6_chk_addr(&init_net, addr6, ndev, 1)) { + found = true; + break; + } + } + if (!found) + return NULL; + return cxgbit_get_real_dev(ndev); +} + +static struct cxgbit_device *cxgbit_find_np_cdev(struct cxgbit_np *cnp) +{ + struct sockaddr_storage *sockaddr = &cnp->com.local_addr; + int ss_family = sockaddr->ss_family; + struct net_device *ndev = NULL; + struct cxgbit_device *cdev = NULL; + + rcu_read_lock(); + if (ss_family == AF_INET) { + struct sockaddr_in *sin; + + sin = (struct sockaddr_in *)sockaddr; + ndev = cxgbit_ipv4_netdev(sin->sin_addr.s_addr); + } else if (ss_family == AF_INET6) { + struct sockaddr_in6 *sin6; + + sin6 = (struct sockaddr_in6 *)sockaddr; + ndev = cxgbit_ipv6_netdev(&sin6->sin6_addr); + } + if (!ndev) + goto out; + + cdev = cxgbit_find_device(ndev, NULL); +out: + rcu_read_unlock(); + return cdev; +} + +static bool cxgbit_inaddr_any(struct cxgbit_np *cnp) +{ + struct sockaddr_storage *sockaddr = &cnp->com.local_addr; + int ss_family = sockaddr->ss_family; + int addr_type; + + if (ss_family == AF_INET) { + struct sockaddr_in *sin; + + sin = (struct sockaddr_in *)sockaddr; + if (sin->sin_addr.s_addr == htonl(INADDR_ANY)) + return true; + } else if (ss_family == AF_INET6) { + struct sockaddr_in6 *sin6; + + sin6 = (struct sockaddr_in6 *)sockaddr; + addr_type = ipv6_addr_type((const struct in6_addr *) + &sin6->sin6_addr); + if (addr_type == IPV6_ADDR_ANY) + return true; + } + return false; +} + +static int +__cxgbit_setup_cdev_np(struct cxgbit_device *cdev, struct cxgbit_np *cnp) +{ + int stid, ret; + int ss_family = cnp->com.local_addr.ss_family; + + if (!test_bit(CDEV_STATE_UP, &cdev->flags)) + return -EINVAL; + + stid = cxgb4_alloc_stid(cdev->lldi.tids, ss_family, cnp); + if (stid < 0) + return -EINVAL; + + if (!cxgbit_np_hash_add(cdev, cnp, stid)) { + cxgb4_free_stid(cdev->lldi.tids, stid, ss_family); + return -EINVAL; + } + + if (ss_family == AF_INET) + ret = cxgbit_create_server4(cdev, stid, cnp); + else + ret = cxgbit_create_server6(cdev, stid, cnp); + + if (ret) { + if (ret != -ETIMEDOUT) + cxgb4_free_stid(cdev->lldi.tids, stid, + ss_family); + cxgbit_np_hash_del(cdev, cnp); + return ret; + } + return ret; +} + +static int cxgbit_setup_cdev_np(struct cxgbit_np *cnp) +{ + struct cxgbit_device *cdev; + int ret = -1; + + mutex_lock(&cdev_list_lock); + cdev = cxgbit_find_np_cdev(cnp); + if (!cdev) + goto out; + + if (cxgbit_np_hash_find(cdev, cnp) >= 0) + goto out; + + if (__cxgbit_setup_cdev_np(cdev, cnp)) + goto out; + + cnp->com.cdev = cdev; + ret = 0; +out: + mutex_unlock(&cdev_list_lock); + return ret; +} + +static int cxgbit_setup_all_np(struct cxgbit_np *cnp) +{ + struct cxgbit_device *cdev; + int ret; + u32 count = 0; + + mutex_lock(&cdev_list_lock); + list_for_each_entry(cdev, &cdev_list_head, list) { + if (cxgbit_np_hash_find(cdev, cnp) >= 0) { + mutex_unlock(&cdev_list_lock); + return -1; + } + } + + list_for_each_entry(cdev, &cdev_list_head, list) { + ret = __cxgbit_setup_cdev_np(cdev, cnp); + if (ret == -ETIMEDOUT) + break; + if (ret != 0) + continue; + count++; + } + mutex_unlock(&cdev_list_lock); + + return count ? 0 : -1; +} + +int cxgbit_setup_np(struct iscsi_np *np, struct sockaddr_storage *ksockaddr) +{ + struct cxgbit_np *cnp; + int ret; + + if ((ksockaddr->ss_family != AF_INET) && + (ksockaddr->ss_family != AF_INET6)) + return -EINVAL; + + cnp = kzalloc(sizeof(*cnp), GFP_KERNEL); + if (!cnp) + return -ENOMEM; + + init_waitqueue_head(&cnp->accept_wait); + init_completion(&cnp->com.wr_wait.completion); + init_completion(&cnp->accept_comp); + INIT_LIST_HEAD(&cnp->np_accept_list); + spin_lock_init(&cnp->np_accept_lock); + kref_init(&cnp->kref); + memcpy(&np->np_sockaddr, ksockaddr, + sizeof(struct sockaddr_storage)); + memcpy(&cnp->com.local_addr, &np->np_sockaddr, + sizeof(cnp->com.local_addr)); + + cnp->np = np; + cnp->com.cdev = NULL; + + if (cxgbit_inaddr_any(cnp)) + ret = cxgbit_setup_all_np(cnp); + else + ret = cxgbit_setup_cdev_np(cnp); + + if (ret) { + cxgbit_put_cnp(cnp); + return -EINVAL; + } + + np->np_context = cnp; + cnp->com.state = CSK_STATE_LISTEN; + return 0; +} + +static void +cxgbit_set_conn_info(struct iscsi_np *np, struct iscsi_conn *conn, + struct cxgbit_sock *csk) +{ + conn->login_family = np->np_sockaddr.ss_family; + conn->login_sockaddr = csk->com.remote_addr; + conn->local_sockaddr = csk->com.local_addr; +} + +int cxgbit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) +{ + struct cxgbit_np *cnp = np->np_context; + struct cxgbit_sock *csk; + int ret = 0; + +accept_wait: + ret = wait_for_completion_interruptible(&cnp->accept_comp); + if (ret) + return -ENODEV; + + spin_lock_bh(&np->np_thread_lock); + if (np->np_thread_state >= ISCSI_NP_THREAD_RESET) { + spin_unlock_bh(&np->np_thread_lock); + /** + * No point in stalling here when np_thread + * is in state RESET/SHUTDOWN/EXIT - bail + **/ + return -ENODEV; + } + spin_unlock_bh(&np->np_thread_lock); + + spin_lock_bh(&cnp->np_accept_lock); + if (list_empty(&cnp->np_accept_list)) { + spin_unlock_bh(&cnp->np_accept_lock); + goto accept_wait; + } + + csk = list_first_entry(&cnp->np_accept_list, + struct cxgbit_sock, + accept_node); + + list_del_init(&csk->accept_node); + spin_unlock_bh(&cnp->np_accept_lock); + conn->context = csk; + csk->conn = conn; + + cxgbit_set_conn_info(np, conn, csk); + return 0; +} + +static int +__cxgbit_free_cdev_np(struct cxgbit_device *cdev, struct cxgbit_np *cnp) +{ + int stid, ret; + bool ipv6 = false; + + stid = cxgbit_np_hash_del(cdev, cnp); + if (stid < 0) + return -EINVAL; + if (!test_bit(CDEV_STATE_UP, &cdev->flags)) + return -EINVAL; + + if (cnp->np->np_sockaddr.ss_family == AF_INET6) + ipv6 = true; + + cxgbit_get_cnp(cnp); + cxgbit_init_wr_wait(&cnp->com.wr_wait); + ret = cxgb4_remove_server(cdev->lldi.ports[0], stid, + cdev->lldi.rxq_ids[0], ipv6); + + if (ret > 0) + ret = net_xmit_errno(ret); + + if (ret) { + cxgbit_put_cnp(cnp); + return ret; + } + + ret = cxgbit_wait_for_reply(cdev, &cnp->com.wr_wait, + 0, 10, __func__); + if (ret == -ETIMEDOUT) + return ret; + + if (ipv6 && cnp->com.cdev) { + struct sockaddr_in6 *sin6; + + sin6 = (struct sockaddr_in6 *)&cnp->com.local_addr; + cxgb4_clip_release(cdev->lldi.ports[0], + (const u32 *)&sin6->sin6_addr.s6_addr, + 1); + } + + cxgb4_free_stid(cdev->lldi.tids, stid, + cnp->com.local_addr.ss_family); + return 0; +} + +static void cxgbit_free_all_np(struct cxgbit_np *cnp) +{ + struct cxgbit_device *cdev; + int ret; + + mutex_lock(&cdev_list_lock); + list_for_each_entry(cdev, &cdev_list_head, list) { + ret = __cxgbit_free_cdev_np(cdev, cnp); + if (ret == -ETIMEDOUT) + break; + } + mutex_unlock(&cdev_list_lock); +} + +static void cxgbit_free_cdev_np(struct cxgbit_np *cnp) +{ + struct cxgbit_device *cdev; + bool found = false; + + mutex_lock(&cdev_list_lock); + list_for_each_entry(cdev, &cdev_list_head, list) { + if (cdev == cnp->com.cdev) { + found = true; + break; + } + } + if (!found) + goto out; + + __cxgbit_free_cdev_np(cdev, cnp); +out: + mutex_unlock(&cdev_list_lock); +} + +void cxgbit_free_np(struct iscsi_np *np) +{ + struct cxgbit_np *cnp = np->np_context; + + cnp->com.state = CSK_STATE_DEAD; + if (cnp->com.cdev) + cxgbit_free_cdev_np(cnp); + else + cxgbit_free_all_np(cnp); + + np->np_context = NULL; + cxgbit_put_cnp(cnp); +} + +static void cxgbit_send_halfclose(struct cxgbit_sock *csk) +{ + struct sk_buff *skb; + struct cpl_close_con_req *req; + unsigned int len = roundup(sizeof(struct cpl_close_con_req), 16); + + skb = alloc_skb(len, GFP_ATOMIC); + if (!skb) + return; + + req = (struct cpl_close_con_req *)__skb_put(skb, len); + memset(req, 0, len); + + set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx); + INIT_TP_WR(req, csk->tid); + OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_CLOSE_CON_REQ, + csk->tid)); + req->rsvd = 0; + + cxgbit_skcb_flags(skb) |= SKCBF_TX_FLAG_COMPL; + __skb_queue_tail(&csk->txq, skb); + cxgbit_push_tx_frames(csk); +} + +static void cxgbit_arp_failure_discard(void *handle, struct sk_buff *skb) +{ + pr_debug("%s cxgbit_device %p\n", __func__, handle); + kfree_skb(skb); +} + +static void cxgbit_abort_arp_failure(void *handle, struct sk_buff *skb) +{ + struct cxgbit_device *cdev = handle; + struct cpl_abort_req *req = cplhdr(skb); + + pr_debug("%s cdev %p\n", __func__, cdev); + req->cmd = CPL_ABORT_NO_RST; + cxgbit_ofld_send(cdev, skb); +} + +static int cxgbit_send_abort_req(struct cxgbit_sock *csk) +{ + struct cpl_abort_req *req; + unsigned int len = roundup(sizeof(*req), 16); + struct sk_buff *skb; + + pr_debug("%s: csk %p tid %u; state %d\n", + __func__, csk, csk->tid, csk->com.state); + + __skb_queue_purge(&csk->txq); + + if (!test_and_set_bit(CSK_TX_DATA_SENT, &csk->com.flags)) + cxgbit_send_tx_flowc_wr(csk); + + skb = __skb_dequeue(&csk->skbq); + req = (struct cpl_abort_req *)__skb_put(skb, len); + memset(req, 0, len); + + set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx); + t4_set_arp_err_handler(skb, csk->com.cdev, cxgbit_abort_arp_failure); + INIT_TP_WR(req, csk->tid); + OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_REQ, + csk->tid)); + req->cmd = CPL_ABORT_SEND_RST; + return cxgbit_l2t_send(csk->com.cdev, skb, csk->l2t); +} + +void cxgbit_free_conn(struct iscsi_conn *conn) +{ + struct cxgbit_sock *csk = conn->context; + bool release = false; + + pr_debug("%s: state %d\n", + __func__, csk->com.state); + + spin_lock_bh(&csk->lock); + switch (csk->com.state) { + case CSK_STATE_ESTABLISHED: + if (conn->conn_state == TARG_CONN_STATE_IN_LOGOUT) { + csk->com.state = CSK_STATE_CLOSING; + cxgbit_send_halfclose(csk); + } else { + csk->com.state = CSK_STATE_ABORTING; + cxgbit_send_abort_req(csk); + } + break; + case CSK_STATE_CLOSING: + csk->com.state = CSK_STATE_MORIBUND; + cxgbit_send_halfclose(csk); + break; + case CSK_STATE_DEAD: + release = true; + break; + default: + pr_err("%s: csk %p; state %d\n", + __func__, csk, csk->com.state); + } + spin_unlock_bh(&csk->lock); + + if (release) + cxgbit_put_csk(csk); +} + +static void cxgbit_set_emss(struct cxgbit_sock *csk, u16 opt) +{ + csk->emss = csk->com.cdev->lldi.mtus[TCPOPT_MSS_G(opt)] - + ((csk->com.remote_addr.ss_family == AF_INET) ? + sizeof(struct iphdr) : sizeof(struct ipv6hdr)) - + sizeof(struct tcphdr); + csk->mss = csk->emss; + if (TCPOPT_TSTAMP_G(opt)) + csk->emss -= round_up(TCPOLEN_TIMESTAMP, 4); + if (csk->emss < 128) + csk->emss = 128; + if (csk->emss & 7) + pr_info("Warning: misaligned mtu idx %u mss %u emss=%u\n", + TCPOPT_MSS_G(opt), csk->mss, csk->emss); + pr_debug("%s mss_idx %u mss %u emss=%u\n", __func__, TCPOPT_MSS_G(opt), + csk->mss, csk->emss); +} + +static void cxgbit_free_skb(struct cxgbit_sock *csk) +{ + struct sk_buff *skb; + + __skb_queue_purge(&csk->txq); + __skb_queue_purge(&csk->rxq); + __skb_queue_purge(&csk->backlogq); + __skb_queue_purge(&csk->ppodq); + __skb_queue_purge(&csk->skbq); + + while ((skb = cxgbit_sock_dequeue_wr(csk))) + kfree_skb(skb); + + __kfree_skb(csk->lro_hskb); +} + +void _cxgbit_free_csk(struct kref *kref) +{ + struct cxgbit_sock *csk; + struct cxgbit_device *cdev; + + csk = container_of(kref, struct cxgbit_sock, kref); + + pr_debug("%s csk %p state %d\n", __func__, csk, csk->com.state); + + if (csk->com.local_addr.ss_family == AF_INET6) { + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) + &csk->com.local_addr; + cxgb4_clip_release(csk->com.cdev->lldi.ports[0], + (const u32 *) + &sin6->sin6_addr.s6_addr, 1); + } + + cxgb4_remove_tid(csk->com.cdev->lldi.tids, 0, csk->tid); + dst_release(csk->dst); + cxgb4_l2t_release(csk->l2t); + + cdev = csk->com.cdev; + spin_lock_bh(&cdev->cskq.lock); + list_del(&csk->list); + spin_unlock_bh(&cdev->cskq.lock); + + cxgbit_free_skb(csk); + cxgbit_put_cdev(cdev); + + kfree(csk); +} + +static void +cxgbit_get_tuple_info(struct cpl_pass_accept_req *req, int *iptype, + __u8 *local_ip, __u8 *peer_ip, __be16 *local_port, + __be16 *peer_port) +{ + u32 eth_len = ETH_HDR_LEN_G(be32_to_cpu(req->hdr_len)); + u32 ip_len = IP_HDR_LEN_G(be32_to_cpu(req->hdr_len)); + struct iphdr *ip = (struct iphdr *)((u8 *)(req + 1) + eth_len); + struct ipv6hdr *ip6 = (struct ipv6hdr *)((u8 *)(req + 1) + eth_len); + struct tcphdr *tcp = (struct tcphdr *) + ((u8 *)(req + 1) + eth_len + ip_len); + + if (ip->version == 4) { + pr_debug("%s saddr 0x%x daddr 0x%x sport %u dport %u\n", + __func__, + ntohl(ip->saddr), ntohl(ip->daddr), + ntohs(tcp->source), + ntohs(tcp->dest)); + *iptype = 4; + memcpy(peer_ip, &ip->saddr, 4); + memcpy(local_ip, &ip->daddr, 4); + } else { + pr_debug("%s saddr %pI6 daddr %pI6 sport %u dport %u\n", + __func__, + ip6->saddr.s6_addr, ip6->daddr.s6_addr, + ntohs(tcp->source), + ntohs(tcp->dest)); + *iptype = 6; + memcpy(peer_ip, ip6->saddr.s6_addr, 16); + memcpy(local_ip, ip6->daddr.s6_addr, 16); + } + + *peer_port = tcp->source; + *local_port = tcp->dest; +} + +static int +cxgbit_our_interface(struct cxgbit_device *cdev, struct net_device *egress_dev) +{ + u8 i; + + egress_dev = cxgbit_get_real_dev(egress_dev); + for (i = 0; i < cdev->lldi.nports; i++) + if (cdev->lldi.ports[i] == egress_dev) + return 1; + return 0; +} + +static struct dst_entry * +cxgbit_find_route6(struct cxgbit_device *cdev, __u8 *local_ip, __u8 *peer_ip, + __be16 local_port, __be16 peer_port, u8 tos, + __u32 sin6_scope_id) +{ + struct dst_entry *dst = NULL; + + if (IS_ENABLED(CONFIG_IPV6)) { + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + memcpy(&fl6.daddr, peer_ip, 16); + memcpy(&fl6.saddr, local_ip, 16); + if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL) + fl6.flowi6_oif = sin6_scope_id; + dst = ip6_route_output(&init_net, NULL, &fl6); + if (!dst) + goto out; + if (!cxgbit_our_interface(cdev, ip6_dst_idev(dst)->dev) && + !(ip6_dst_idev(dst)->dev->flags & IFF_LOOPBACK)) { + dst_release(dst); + dst = NULL; + } + } +out: + return dst; +} + +static struct dst_entry * +cxgbit_find_route(struct cxgbit_device *cdev, __be32 local_ip, __be32 peer_ip, + __be16 local_port, __be16 peer_port, u8 tos) +{ + struct rtable *rt; + struct flowi4 fl4; + struct neighbour *n; + + rt = ip_route_output_ports(&init_net, &fl4, NULL, peer_ip, + local_ip, + peer_port, local_port, IPPROTO_TCP, + tos, 0); + if (IS_ERR(rt)) + return NULL; + n = dst_neigh_lookup(&rt->dst, &peer_ip); + if (!n) + return NULL; + if (!cxgbit_our_interface(cdev, n->dev) && + !(n->dev->flags & IFF_LOOPBACK)) { + neigh_release(n); + dst_release(&rt->dst); + return NULL; + } + neigh_release(n); + return &rt->dst; +} + +static void cxgbit_set_tcp_window(struct cxgbit_sock *csk, struct port_info *pi) +{ + unsigned int linkspeed; + u8 scale; + + linkspeed = pi->link_cfg.speed; + scale = linkspeed / SPEED_10000; + +#define CXGBIT_10G_RCV_WIN (256 * 1024) + csk->rcv_win = CXGBIT_10G_RCV_WIN; + if (scale) + csk->rcv_win *= scale; + +#define CXGBIT_10G_SND_WIN (256 * 1024) + csk->snd_win = CXGBIT_10G_SND_WIN; + if (scale) + csk->snd_win *= scale; + + pr_debug("%s snd_win %d rcv_win %d\n", + __func__, csk->snd_win, csk->rcv_win); +} + +#ifdef CONFIG_CHELSIO_T4_DCB +static u8 cxgbit_get_iscsi_dcb_state(struct net_device *ndev) +{ + return ndev->dcbnl_ops->getstate(ndev); +} + +static int cxgbit_select_priority(int pri_mask) +{ + if (!pri_mask) + return 0; + + return (ffs(pri_mask) - 1); +} + +static u8 cxgbit_get_iscsi_dcb_priority(struct net_device *ndev, u16 local_port) +{ + int ret; + u8 caps; + + struct dcb_app iscsi_dcb_app = { + .protocol = local_port + }; + + ret = (int)ndev->dcbnl_ops->getcap(ndev, DCB_CAP_ATTR_DCBX, &caps); + + if (ret) + return 0; + + if (caps & DCB_CAP_DCBX_VER_IEEE) { + iscsi_dcb_app.selector = IEEE_8021QAZ_APP_SEL_ANY; + + ret = dcb_ieee_getapp_mask(ndev, &iscsi_dcb_app); + + } else if (caps & DCB_CAP_DCBX_VER_CEE) { + iscsi_dcb_app.selector = DCB_APP_IDTYPE_PORTNUM; + + ret = dcb_getapp(ndev, &iscsi_dcb_app); + } + + pr_info("iSCSI priority is set to %u\n", cxgbit_select_priority(ret)); + + return cxgbit_select_priority(ret); +} +#endif + +static int +cxgbit_offload_init(struct cxgbit_sock *csk, int iptype, __u8 *peer_ip, + u16 local_port, struct dst_entry *dst, + struct cxgbit_device *cdev) +{ + struct neighbour *n; + int ret, step; + struct net_device *ndev; + u16 rxq_idx, port_id; +#ifdef CONFIG_CHELSIO_T4_DCB + u8 priority = 0; +#endif + + n = dst_neigh_lookup(dst, peer_ip); + if (!n) + return -ENODEV; + + rcu_read_lock(); + ret = -ENOMEM; + if (n->dev->flags & IFF_LOOPBACK) { + if (iptype == 4) + ndev = cxgbit_ipv4_netdev(*(__be32 *)peer_ip); + else if (IS_ENABLED(CONFIG_IPV6)) + ndev = cxgbit_ipv6_netdev((struct in6_addr *)peer_ip); + else + ndev = NULL; + + if (!ndev) { + ret = -ENODEV; + goto out; + } + + csk->l2t = cxgb4_l2t_get(cdev->lldi.l2t, + n, ndev, 0); + if (!csk->l2t) + goto out; + csk->mtu = ndev->mtu; + csk->tx_chan = cxgb4_port_chan(ndev); + csk->smac_idx = (cxgb4_port_viid(ndev) & 0x7F) << 1; + step = cdev->lldi.ntxq / + cdev->lldi.nchan; + csk->txq_idx = cxgb4_port_idx(ndev) * step; + step = cdev->lldi.nrxq / + cdev->lldi.nchan; + csk->ctrlq_idx = cxgb4_port_idx(ndev); + csk->rss_qid = cdev->lldi.rxq_ids[ + cxgb4_port_idx(ndev) * step]; + csk->port_id = cxgb4_port_idx(ndev); + cxgbit_set_tcp_window(csk, + (struct port_info *)netdev_priv(ndev)); + } else { + ndev = cxgbit_get_real_dev(n->dev); + if (!ndev) { + ret = -ENODEV; + goto out; + } + +#ifdef CONFIG_CHELSIO_T4_DCB + if (cxgbit_get_iscsi_dcb_state(ndev)) + priority = cxgbit_get_iscsi_dcb_priority(ndev, + local_port); + + csk->dcb_priority = priority; + + csk->l2t = cxgb4_l2t_get(cdev->lldi.l2t, n, ndev, priority); +#else + csk->l2t = cxgb4_l2t_get(cdev->lldi.l2t, n, ndev, 0); +#endif + if (!csk->l2t) + goto out; + port_id = cxgb4_port_idx(ndev); + csk->mtu = dst_mtu(dst); + csk->tx_chan = cxgb4_port_chan(ndev); + csk->smac_idx = (cxgb4_port_viid(ndev) & 0x7F) << 1; + step = cdev->lldi.ntxq / + cdev->lldi.nports; + csk->txq_idx = (port_id * step) + + (cdev->selectq[port_id][0]++ % step); + csk->ctrlq_idx = cxgb4_port_idx(ndev); + step = cdev->lldi.nrxq / + cdev->lldi.nports; + rxq_idx = (port_id * step) + + (cdev->selectq[port_id][1]++ % step); + csk->rss_qid = cdev->lldi.rxq_ids[rxq_idx]; + csk->port_id = port_id; + cxgbit_set_tcp_window(csk, + (struct port_info *)netdev_priv(ndev)); + } + ret = 0; +out: + rcu_read_unlock(); + neigh_release(n); + return ret; +} + +int cxgbit_ofld_send(struct cxgbit_device *cdev, struct sk_buff *skb) +{ + int ret = 0; + + if (!test_bit(CDEV_STATE_UP, &cdev->flags)) { + kfree_skb(skb); + pr_err("%s - device not up - dropping\n", __func__); + return -EIO; + } + + ret = cxgb4_ofld_send(cdev->lldi.ports[0], skb); + if (ret < 0) + kfree_skb(skb); + return ret < 0 ? ret : 0; +} + +static void cxgbit_release_tid(struct cxgbit_device *cdev, u32 tid) +{ + struct cpl_tid_release *req; + unsigned int len = roundup(sizeof(*req), 16); + struct sk_buff *skb; + + skb = alloc_skb(len, GFP_ATOMIC); + if (!skb) + return; + + req = (struct cpl_tid_release *)__skb_put(skb, len); + memset(req, 0, len); + + INIT_TP_WR(req, tid); + OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID( + CPL_TID_RELEASE, tid)); + set_wr_txq(skb, CPL_PRIORITY_SETUP, 0); + cxgbit_ofld_send(cdev, skb); +} + +int +cxgbit_l2t_send(struct cxgbit_device *cdev, struct sk_buff *skb, + struct l2t_entry *l2e) +{ + int ret = 0; + + if (!test_bit(CDEV_STATE_UP, &cdev->flags)) { + kfree_skb(skb); + pr_err("%s - device not up - dropping\n", __func__); + return -EIO; + } + + ret = cxgb4_l2t_send(cdev->lldi.ports[0], skb, l2e); + if (ret < 0) + kfree_skb(skb); + return ret < 0 ? ret : 0; +} + +static void +cxgbit_best_mtu(const unsigned short *mtus, unsigned short mtu, + unsigned int *idx, int use_ts, int ipv6) +{ + unsigned short hdr_size = (ipv6 ? sizeof(struct ipv6hdr) : + sizeof(struct iphdr)) + + sizeof(struct tcphdr) + + (use_ts ? round_up(TCPOLEN_TIMESTAMP, + 4) : 0); + unsigned short data_size = mtu - hdr_size; + + cxgb4_best_aligned_mtu(mtus, hdr_size, data_size, 8, idx); +} + +static void cxgbit_send_rx_credits(struct cxgbit_sock *csk, struct sk_buff *skb) +{ + if (csk->com.state != CSK_STATE_ESTABLISHED) { + __kfree_skb(skb); + return; + } + + cxgbit_ofld_send(csk->com.cdev, skb); +} + +/* + * CPL connection rx data ack: host -> + * Send RX credits through an RX_DATA_ACK CPL message. + * Returns the number of credits sent. + */ +int cxgbit_rx_data_ack(struct cxgbit_sock *csk) +{ + struct sk_buff *skb; + struct cpl_rx_data_ack *req; + unsigned int len = roundup(sizeof(*req), 16); + + skb = alloc_skb(len, GFP_KERNEL); + if (!skb) + return -1; + + req = (struct cpl_rx_data_ack *)__skb_put(skb, len); + memset(req, 0, len); + + set_wr_txq(skb, CPL_PRIORITY_ACK, csk->ctrlq_idx); + INIT_TP_WR(req, csk->tid); + OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_RX_DATA_ACK, + csk->tid)); + req->credit_dack = cpu_to_be32(RX_DACK_CHANGE_F | RX_DACK_MODE_V(1) | + RX_CREDITS_V(csk->rx_credits)); + + csk->rx_credits = 0; + + spin_lock_bh(&csk->lock); + if (csk->lock_owner) { + cxgbit_skcb_rx_backlog_fn(skb) = cxgbit_send_rx_credits; + __skb_queue_tail(&csk->backlogq, skb); + spin_unlock_bh(&csk->lock); + return 0; + } + + cxgbit_send_rx_credits(csk, skb); + spin_unlock_bh(&csk->lock); + + return 0; +} + +#define FLOWC_WR_NPARAMS_MIN 9 +#define FLOWC_WR_NPARAMS_MAX 11 +static int cxgbit_alloc_csk_skb(struct cxgbit_sock *csk) +{ + struct sk_buff *skb; + u32 len, flowclen; + u8 i; + + flowclen = offsetof(struct fw_flowc_wr, + mnemval[FLOWC_WR_NPARAMS_MAX]); + + len = max_t(u32, sizeof(struct cpl_abort_req), + sizeof(struct cpl_abort_rpl)); + + len = max(len, flowclen); + len = roundup(len, 16); + + for (i = 0; i < 3; i++) { + skb = alloc_skb(len, GFP_ATOMIC); + if (!skb) + goto out; + __skb_queue_tail(&csk->skbq, skb); + } + + skb = alloc_skb(LRO_SKB_MIN_HEADROOM, GFP_ATOMIC); + if (!skb) + goto out; + + memset(skb->data, 0, LRO_SKB_MIN_HEADROOM); + csk->lro_hskb = skb; + + return 0; +out: + __skb_queue_purge(&csk->skbq); + return -ENOMEM; +} + +static u32 cxgbit_compute_wscale(u32 win) +{ + u32 wscale = 0; + + while (wscale < 14 && (65535 << wscale) < win) + wscale++; + return wscale; +} + +static void +cxgbit_pass_accept_rpl(struct cxgbit_sock *csk, struct cpl_pass_accept_req *req) +{ + struct sk_buff *skb; + const struct tcphdr *tcph; + struct cpl_t5_pass_accept_rpl *rpl5; + unsigned int len = roundup(sizeof(*rpl5), 16); + unsigned int mtu_idx; + u64 opt0; + u32 opt2, hlen; + u32 wscale; + u32 win; + + pr_debug("%s csk %p tid %u\n", __func__, csk, csk->tid); + + skb = alloc_skb(len, GFP_ATOMIC); + if (!skb) { + cxgbit_put_csk(csk); + return; + } + + rpl5 = (struct cpl_t5_pass_accept_rpl *)__skb_put(skb, len); + memset(rpl5, 0, len); + + INIT_TP_WR(rpl5, csk->tid); + OPCODE_TID(rpl5) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL, + csk->tid)); + cxgbit_best_mtu(csk->com.cdev->lldi.mtus, csk->mtu, &mtu_idx, + req->tcpopt.tstamp, + (csk->com.remote_addr.ss_family == AF_INET) ? 0 : 1); + wscale = cxgbit_compute_wscale(csk->rcv_win); + /* + * Specify the largest window that will fit in opt0. The + * remainder will be specified in the rx_data_ack. + */ + win = csk->rcv_win >> 10; + if (win > RCV_BUFSIZ_M) + win = RCV_BUFSIZ_M; + opt0 = TCAM_BYPASS_F | + WND_SCALE_V(wscale) | + MSS_IDX_V(mtu_idx) | + L2T_IDX_V(csk->l2t->idx) | + TX_CHAN_V(csk->tx_chan) | + SMAC_SEL_V(csk->smac_idx) | + DSCP_V(csk->tos >> 2) | + ULP_MODE_V(ULP_MODE_ISCSI) | + RCV_BUFSIZ_V(win); + + opt2 = RX_CHANNEL_V(0) | + RSS_QUEUE_VALID_F | RSS_QUEUE_V(csk->rss_qid); + + if (req->tcpopt.tstamp) + opt2 |= TSTAMPS_EN_F; + if (req->tcpopt.sack) + opt2 |= SACK_EN_F; + if (wscale) + opt2 |= WND_SCALE_EN_F; + + hlen = ntohl(req->hdr_len); + tcph = (const void *)(req + 1) + ETH_HDR_LEN_G(hlen) + + IP_HDR_LEN_G(hlen); + + if (tcph->ece && tcph->cwr) + opt2 |= CCTRL_ECN_V(1); + + opt2 |= RX_COALESCE_V(3); + opt2 |= CONG_CNTRL_V(CONG_ALG_NEWRENO); + + opt2 |= T5_ISS_F; + rpl5->iss = cpu_to_be32((prandom_u32() & ~7UL) - 1); + + opt2 |= T5_OPT_2_VALID_F; + + rpl5->opt0 = cpu_to_be64(opt0); + rpl5->opt2 = cpu_to_be32(opt2); + set_wr_txq(skb, CPL_PRIORITY_SETUP, csk->ctrlq_idx); + t4_set_arp_err_handler(skb, NULL, cxgbit_arp_failure_discard); + cxgbit_l2t_send(csk->com.cdev, skb, csk->l2t); +} + +static void +cxgbit_pass_accept_req(struct cxgbit_device *cdev, struct sk_buff *skb) +{ + struct cxgbit_sock *csk = NULL; + struct cxgbit_np *cnp; + struct cpl_pass_accept_req *req = cplhdr(skb); + unsigned int stid = PASS_OPEN_TID_G(ntohl(req->tos_stid)); + struct tid_info *t = cdev->lldi.tids; + unsigned int tid = GET_TID(req); + u16 peer_mss = ntohs(req->tcpopt.mss); + unsigned short hdrs; + + struct dst_entry *dst; + __u8 local_ip[16], peer_ip[16]; + __be16 local_port, peer_port; + int ret; + int iptype; + + pr_debug("%s: cdev = %p; stid = %u; tid = %u\n", + __func__, cdev, stid, tid); + + cnp = lookup_stid(t, stid); + if (!cnp) { + pr_err("%s connect request on invalid stid %d\n", + __func__, stid); + goto rel_skb; + } + + if (cnp->com.state != CSK_STATE_LISTEN) { + pr_err("%s - listening parent not in CSK_STATE_LISTEN\n", + __func__); + goto reject; + } + + csk = lookup_tid(t, tid); + if (csk) { + pr_err("%s csk not null tid %u\n", + __func__, tid); + goto rel_skb; + } + + cxgbit_get_tuple_info(req, &iptype, local_ip, peer_ip, + &local_port, &peer_port); + + /* Find output route */ + if (iptype == 4) { + pr_debug("%s parent sock %p tid %u laddr %pI4 raddr %pI4 " + "lport %d rport %d peer_mss %d\n" + , __func__, cnp, tid, + local_ip, peer_ip, ntohs(local_port), + ntohs(peer_port), peer_mss); + dst = cxgbit_find_route(cdev, *(__be32 *)local_ip, + *(__be32 *)peer_ip, + local_port, peer_port, + PASS_OPEN_TOS_G(ntohl(req->tos_stid))); + } else { + pr_debug("%s parent sock %p tid %u laddr %pI6 raddr %pI6 " + "lport %d rport %d peer_mss %d\n" + , __func__, cnp, tid, + local_ip, peer_ip, ntohs(local_port), + ntohs(peer_port), peer_mss); + dst = cxgbit_find_route6(cdev, local_ip, peer_ip, + local_port, peer_port, + PASS_OPEN_TOS_G(ntohl(req->tos_stid)), + ((struct sockaddr_in6 *) + &cnp->com.local_addr)->sin6_scope_id); + } + if (!dst) { + pr_err("%s - failed to find dst entry!\n", + __func__); + goto reject; + } + + csk = kzalloc(sizeof(*csk), GFP_ATOMIC); + if (!csk) { + dst_release(dst); + goto rel_skb; + } + + ret = cxgbit_offload_init(csk, iptype, peer_ip, ntohs(local_port), + dst, cdev); + if (ret) { + pr_err("%s - failed to allocate l2t entry!\n", + __func__); + dst_release(dst); + kfree(csk); + goto reject; + } + + kref_init(&csk->kref); + init_completion(&csk->com.wr_wait.completion); + + INIT_LIST_HEAD(&csk->accept_node); + + hdrs = (iptype == 4 ? sizeof(struct iphdr) : sizeof(struct ipv6hdr)) + + sizeof(struct tcphdr) + (req->tcpopt.tstamp ? 12 : 0); + if (peer_mss && csk->mtu > (peer_mss + hdrs)) + csk->mtu = peer_mss + hdrs; + + csk->com.state = CSK_STATE_CONNECTING; + csk->com.cdev = cdev; + csk->cnp = cnp; + csk->tos = PASS_OPEN_TOS_G(ntohl(req->tos_stid)); + csk->dst = dst; + csk->tid = tid; + csk->wr_cred = cdev->lldi.wr_cred - + DIV_ROUND_UP(sizeof(struct cpl_abort_req), 16); + csk->wr_max_cred = csk->wr_cred; + csk->wr_una_cred = 0; + + if (iptype == 4) { + struct sockaddr_in *sin = (struct sockaddr_in *) + &csk->com.local_addr; + sin->sin_family = AF_INET; + sin->sin_port = local_port; + sin->sin_addr.s_addr = *(__be32 *)local_ip; + + sin = (struct sockaddr_in *)&csk->com.remote_addr; + sin->sin_family = AF_INET; + sin->sin_port = peer_port; + sin->sin_addr.s_addr = *(__be32 *)peer_ip; + } else { + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) + &csk->com.local_addr; + + sin6->sin6_family = PF_INET6; + sin6->sin6_port = local_port; + memcpy(sin6->sin6_addr.s6_addr, local_ip, 16); + cxgb4_clip_get(cdev->lldi.ports[0], + (const u32 *)&sin6->sin6_addr.s6_addr, + 1); + + sin6 = (struct sockaddr_in6 *)&csk->com.remote_addr; + sin6->sin6_family = PF_INET6; + sin6->sin6_port = peer_port; + memcpy(sin6->sin6_addr.s6_addr, peer_ip, 16); + } + + skb_queue_head_init(&csk->rxq); + skb_queue_head_init(&csk->txq); + skb_queue_head_init(&csk->ppodq); + skb_queue_head_init(&csk->backlogq); + skb_queue_head_init(&csk->skbq); + cxgbit_sock_reset_wr_list(csk); + spin_lock_init(&csk->lock); + init_waitqueue_head(&csk->waitq); + init_waitqueue_head(&csk->ack_waitq); + csk->lock_owner = false; + + if (cxgbit_alloc_csk_skb(csk)) { + dst_release(dst); + kfree(csk); + goto rel_skb; + } + + cxgbit_get_cdev(cdev); + + spin_lock(&cdev->cskq.lock); + list_add_tail(&csk->list, &cdev->cskq.list); + spin_unlock(&cdev->cskq.lock); + + cxgb4_insert_tid(t, csk, tid); + cxgbit_pass_accept_rpl(csk, req); + goto rel_skb; + +reject: + cxgbit_release_tid(cdev, tid); +rel_skb: + __kfree_skb(skb); +} + +static u32 +cxgbit_tx_flowc_wr_credits(struct cxgbit_sock *csk, u32 *nparamsp, + u32 *flowclenp) +{ + u32 nparams, flowclen16, flowclen; + + nparams = FLOWC_WR_NPARAMS_MIN; + + if (csk->snd_wscale) + nparams++; + +#ifdef CONFIG_CHELSIO_T4_DCB + nparams++; +#endif + flowclen = offsetof(struct fw_flowc_wr, mnemval[nparams]); + flowclen16 = DIV_ROUND_UP(flowclen, 16); + flowclen = flowclen16 * 16; + /* + * Return the number of 16-byte credits used by the flowc request. + * Pass back the nparams and actual flowc length if requested. + */ + if (nparamsp) + *nparamsp = nparams; + if (flowclenp) + *flowclenp = flowclen; + return flowclen16; +} + +u32 cxgbit_send_tx_flowc_wr(struct cxgbit_sock *csk) +{ + struct cxgbit_device *cdev = csk->com.cdev; + struct fw_flowc_wr *flowc; + u32 nparams, flowclen16, flowclen; + struct sk_buff *skb; + u8 index; + +#ifdef CONFIG_CHELSIO_T4_DCB + u16 vlan = ((struct l2t_entry *)csk->l2t)->vlan; +#endif + + flowclen16 = cxgbit_tx_flowc_wr_credits(csk, &nparams, &flowclen); + + skb = __skb_dequeue(&csk->skbq); + flowc = (struct fw_flowc_wr *)__skb_put(skb, flowclen); + memset(flowc, 0, flowclen); + + flowc->op_to_nparams = cpu_to_be32(FW_WR_OP_V(FW_FLOWC_WR) | + FW_FLOWC_WR_NPARAMS_V(nparams)); + flowc->flowid_len16 = cpu_to_be32(FW_WR_LEN16_V(flowclen16) | + FW_WR_FLOWID_V(csk->tid)); + flowc->mnemval[0].mnemonic = FW_FLOWC_MNEM_PFNVFN; + flowc->mnemval[0].val = cpu_to_be32(FW_PFVF_CMD_PFN_V + (csk->com.cdev->lldi.pf)); + flowc->mnemval[1].mnemonic = FW_FLOWC_MNEM_CH; + flowc->mnemval[1].val = cpu_to_be32(csk->tx_chan); + flowc->mnemval[2].mnemonic = FW_FLOWC_MNEM_PORT; + flowc->mnemval[2].val = cpu_to_be32(csk->tx_chan); + flowc->mnemval[3].mnemonic = FW_FLOWC_MNEM_IQID; + flowc->mnemval[3].val = cpu_to_be32(csk->rss_qid); + flowc->mnemval[4].mnemonic = FW_FLOWC_MNEM_SNDNXT; + flowc->mnemval[4].val = cpu_to_be32(csk->snd_nxt); + flowc->mnemval[5].mnemonic = FW_FLOWC_MNEM_RCVNXT; + flowc->mnemval[5].val = cpu_to_be32(csk->rcv_nxt); + flowc->mnemval[6].mnemonic = FW_FLOWC_MNEM_SNDBUF; + flowc->mnemval[6].val = cpu_to_be32(csk->snd_win); + flowc->mnemval[7].mnemonic = FW_FLOWC_MNEM_MSS; + flowc->mnemval[7].val = cpu_to_be32(csk->emss); + + flowc->mnemval[8].mnemonic = FW_FLOWC_MNEM_TXDATAPLEN_MAX; + if (test_bit(CDEV_ISO_ENABLE, &cdev->flags)) + flowc->mnemval[8].val = cpu_to_be32(CXGBIT_MAX_ISO_PAYLOAD); + else + flowc->mnemval[8].val = cpu_to_be32(16384); + + index = 9; + + if (csk->snd_wscale) { + flowc->mnemval[index].mnemonic = FW_FLOWC_MNEM_RCV_SCALE; + flowc->mnemval[index].val = cpu_to_be32(csk->snd_wscale); + index++; + } + +#ifdef CONFIG_CHELSIO_T4_DCB + flowc->mnemval[index].mnemonic = FW_FLOWC_MNEM_DCBPRIO; + if (vlan == VLAN_NONE) { + pr_warn("csk %u without VLAN Tag on DCB Link\n", csk->tid); + flowc->mnemval[index].val = cpu_to_be32(0); + } else + flowc->mnemval[index].val = cpu_to_be32( + (vlan & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT); +#endif + + pr_debug("%s: csk %p; tx_chan = %u; rss_qid = %u; snd_seq = %u;" + " rcv_seq = %u; snd_win = %u; emss = %u\n", + __func__, csk, csk->tx_chan, csk->rss_qid, csk->snd_nxt, + csk->rcv_nxt, csk->snd_win, csk->emss); + set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx); + cxgbit_ofld_send(csk->com.cdev, skb); + return flowclen16; +} + +int cxgbit_setup_conn_digest(struct cxgbit_sock *csk) +{ + struct sk_buff *skb; + struct cpl_set_tcb_field *req; + u8 hcrc = csk->submode & CXGBIT_SUBMODE_HCRC; + u8 dcrc = csk->submode & CXGBIT_SUBMODE_DCRC; + unsigned int len = roundup(sizeof(*req), 16); + int ret; + + skb = alloc_skb(len, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + /* set up ulp submode */ + req = (struct cpl_set_tcb_field *)__skb_put(skb, len); + memset(req, 0, len); + + INIT_TP_WR(req, csk->tid); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, csk->tid)); + req->reply_ctrl = htons(NO_REPLY_V(0) | QUEUENO_V(csk->rss_qid)); + req->word_cookie = htons(0); + req->mask = cpu_to_be64(0x3 << 4); + req->val = cpu_to_be64(((hcrc ? ULP_CRC_HEADER : 0) | + (dcrc ? ULP_CRC_DATA : 0)) << 4); + set_wr_txq(skb, CPL_PRIORITY_CONTROL, csk->ctrlq_idx); + + cxgbit_get_csk(csk); + cxgbit_init_wr_wait(&csk->com.wr_wait); + + cxgbit_ofld_send(csk->com.cdev, skb); + + ret = cxgbit_wait_for_reply(csk->com.cdev, + &csk->com.wr_wait, + csk->tid, 5, __func__); + if (ret) + return -1; + + return 0; +} + +int cxgbit_setup_conn_pgidx(struct cxgbit_sock *csk, u32 pg_idx) +{ + struct sk_buff *skb; + struct cpl_set_tcb_field *req; + unsigned int len = roundup(sizeof(*req), 16); + int ret; + + skb = alloc_skb(len, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + req = (struct cpl_set_tcb_field *)__skb_put(skb, len); + memset(req, 0, len); + + INIT_TP_WR(req, csk->tid); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, csk->tid)); + req->reply_ctrl = htons(NO_REPLY_V(0) | QUEUENO_V(csk->rss_qid)); + req->word_cookie = htons(0); + req->mask = cpu_to_be64(0x3 << 8); + req->val = cpu_to_be64(pg_idx << 8); + set_wr_txq(skb, CPL_PRIORITY_CONTROL, csk->ctrlq_idx); + + cxgbit_get_csk(csk); + cxgbit_init_wr_wait(&csk->com.wr_wait); + + cxgbit_ofld_send(csk->com.cdev, skb); + + ret = cxgbit_wait_for_reply(csk->com.cdev, + &csk->com.wr_wait, + csk->tid, 5, __func__); + if (ret) + return -1; + + return 0; +} + +static void +cxgbit_pass_open_rpl(struct cxgbit_device *cdev, struct sk_buff *skb) +{ + struct cpl_pass_open_rpl *rpl = cplhdr(skb); + struct tid_info *t = cdev->lldi.tids; + unsigned int stid = GET_TID(rpl); + struct cxgbit_np *cnp = lookup_stid(t, stid); + + pr_debug("%s: cnp = %p; stid = %u; status = %d\n", + __func__, cnp, stid, rpl->status); + + if (!cnp) { + pr_info("%s stid %d lookup failure\n", __func__, stid); + return; + } + + cxgbit_wake_up(&cnp->com.wr_wait, __func__, rpl->status); + cxgbit_put_cnp(cnp); +} + +static void +cxgbit_close_listsrv_rpl(struct cxgbit_device *cdev, struct sk_buff *skb) +{ + struct cpl_close_listsvr_rpl *rpl = cplhdr(skb); + struct tid_info *t = cdev->lldi.tids; + unsigned int stid = GET_TID(rpl); + struct cxgbit_np *cnp = lookup_stid(t, stid); + + pr_debug("%s: cnp = %p; stid = %u; status = %d\n", + __func__, cnp, stid, rpl->status); + + if (!cnp) { + pr_info("%s stid %d lookup failure\n", __func__, stid); + return; + } + + cxgbit_wake_up(&cnp->com.wr_wait, __func__, rpl->status); + cxgbit_put_cnp(cnp); +} + +static void +cxgbit_pass_establish(struct cxgbit_device *cdev, struct sk_buff *skb) +{ + struct cpl_pass_establish *req = cplhdr(skb); + struct tid_info *t = cdev->lldi.tids; + unsigned int tid = GET_TID(req); + struct cxgbit_sock *csk; + struct cxgbit_np *cnp; + u16 tcp_opt = be16_to_cpu(req->tcp_opt); + u32 snd_isn = be32_to_cpu(req->snd_isn); + u32 rcv_isn = be32_to_cpu(req->rcv_isn); + + csk = lookup_tid(t, tid); + if (unlikely(!csk)) { + pr_err("can't find connection for tid %u.\n", tid); + goto rel_skb; + } + cnp = csk->cnp; + + pr_debug("%s: csk %p; tid %u; cnp %p\n", + __func__, csk, tid, cnp); + + csk->write_seq = snd_isn; + csk->snd_una = snd_isn; + csk->snd_nxt = snd_isn; + + csk->rcv_nxt = rcv_isn; + + if (csk->rcv_win > (RCV_BUFSIZ_M << 10)) + csk->rx_credits = (csk->rcv_win - (RCV_BUFSIZ_M << 10)); + + csk->snd_wscale = TCPOPT_SND_WSCALE_G(tcp_opt); + cxgbit_set_emss(csk, tcp_opt); + dst_confirm(csk->dst); + csk->com.state = CSK_STATE_ESTABLISHED; + spin_lock_bh(&cnp->np_accept_lock); + list_add_tail(&csk->accept_node, &cnp->np_accept_list); + spin_unlock_bh(&cnp->np_accept_lock); + complete(&cnp->accept_comp); +rel_skb: + __kfree_skb(skb); +} + +static void cxgbit_queue_rx_skb(struct cxgbit_sock *csk, struct sk_buff *skb) +{ + cxgbit_skcb_flags(skb) = 0; + spin_lock_bh(&csk->rxq.lock); + __skb_queue_tail(&csk->rxq, skb); + spin_unlock_bh(&csk->rxq.lock); + wake_up(&csk->waitq); +} + +static void cxgbit_peer_close(struct cxgbit_sock *csk, struct sk_buff *skb) +{ + pr_debug("%s: csk %p; tid %u; state %d\n", + __func__, csk, csk->tid, csk->com.state); + + switch (csk->com.state) { + case CSK_STATE_ESTABLISHED: + csk->com.state = CSK_STATE_CLOSING; + cxgbit_queue_rx_skb(csk, skb); + return; + case CSK_STATE_CLOSING: + /* simultaneous close */ + csk->com.state = CSK_STATE_MORIBUND; + break; + case CSK_STATE_MORIBUND: + csk->com.state = CSK_STATE_DEAD; + cxgbit_put_csk(csk); + break; + case CSK_STATE_ABORTING: + break; + default: + pr_info("%s: cpl_peer_close in bad state %d\n", + __func__, csk->com.state); + } + + __kfree_skb(skb); +} + +static void cxgbit_close_con_rpl(struct cxgbit_sock *csk, struct sk_buff *skb) +{ + pr_debug("%s: csk %p; tid %u; state %d\n", + __func__, csk, csk->tid, csk->com.state); + + switch (csk->com.state) { + case CSK_STATE_CLOSING: + csk->com.state = CSK_STATE_MORIBUND; + break; + case CSK_STATE_MORIBUND: + csk->com.state = CSK_STATE_DEAD; + cxgbit_put_csk(csk); + break; + case CSK_STATE_ABORTING: + case CSK_STATE_DEAD: + break; + default: + pr_info("%s: cpl_close_con_rpl in bad state %d\n", + __func__, csk->com.state); + } + + __kfree_skb(skb); +} + +static void cxgbit_abort_req_rss(struct cxgbit_sock *csk, struct sk_buff *skb) +{ + struct cpl_abort_req_rss *hdr = cplhdr(skb); + unsigned int tid = GET_TID(hdr); + struct cpl_abort_rpl *rpl; + struct sk_buff *rpl_skb; + bool release = false; + bool wakeup_thread = false; + unsigned int len = roundup(sizeof(*rpl), 16); + + pr_debug("%s: csk %p; tid %u; state %d\n", + __func__, csk, tid, csk->com.state); + + if (cxgbit_is_neg_adv(hdr->status)) { + pr_err("%s: got neg advise %d on tid %u\n", + __func__, hdr->status, tid); + goto rel_skb; + } + + switch (csk->com.state) { + case CSK_STATE_CONNECTING: + case CSK_STATE_MORIBUND: + csk->com.state = CSK_STATE_DEAD; + release = true; + break; + case CSK_STATE_ESTABLISHED: + csk->com.state = CSK_STATE_DEAD; + wakeup_thread = true; + break; + case CSK_STATE_CLOSING: + csk->com.state = CSK_STATE_DEAD; + if (!csk->conn) + release = true; + break; + case CSK_STATE_ABORTING: + break; + default: + pr_info("%s: cpl_abort_req_rss in bad state %d\n", + __func__, csk->com.state); + csk->com.state = CSK_STATE_DEAD; + } + + __skb_queue_purge(&csk->txq); + + if (!test_and_set_bit(CSK_TX_DATA_SENT, &csk->com.flags)) + cxgbit_send_tx_flowc_wr(csk); + + rpl_skb = __skb_dequeue(&csk->skbq); + set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx); + + rpl = (struct cpl_abort_rpl *)__skb_put(rpl_skb, len); + memset(rpl, 0, len); + + INIT_TP_WR(rpl, csk->tid); + OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_RPL, tid)); + rpl->cmd = CPL_ABORT_NO_RST; + cxgbit_ofld_send(csk->com.cdev, rpl_skb); + + if (wakeup_thread) { + cxgbit_queue_rx_skb(csk, skb); + return; + } + + if (release) + cxgbit_put_csk(csk); +rel_skb: + __kfree_skb(skb); +} + +static void cxgbit_abort_rpl_rss(struct cxgbit_sock *csk, struct sk_buff *skb) +{ + pr_debug("%s: csk %p; tid %u; state %d\n", + __func__, csk, csk->tid, csk->com.state); + + switch (csk->com.state) { + case CSK_STATE_ABORTING: + csk->com.state = CSK_STATE_DEAD; + cxgbit_put_csk(csk); + break; + default: + pr_info("%s: cpl_abort_rpl_rss in state %d\n", + __func__, csk->com.state); + } + + __kfree_skb(skb); +} + +static bool cxgbit_credit_err(const struct cxgbit_sock *csk) +{ + const struct sk_buff *skb = csk->wr_pending_head; + u32 credit = 0; + + if (unlikely(csk->wr_cred > csk->wr_max_cred)) { + pr_err("csk 0x%p, tid %u, credit %u > %u\n", + csk, csk->tid, csk->wr_cred, csk->wr_max_cred); + return true; + } + + while (skb) { + credit += skb->csum; + skb = cxgbit_skcb_tx_wr_next(skb); + } + + if (unlikely((csk->wr_cred + credit) != csk->wr_max_cred)) { + pr_err("csk 0x%p, tid %u, credit %u + %u != %u.\n", + csk, csk->tid, csk->wr_cred, + credit, csk->wr_max_cred); + + return true; + } + + return false; +} + +static void cxgbit_fw4_ack(struct cxgbit_sock *csk, struct sk_buff *skb) +{ + struct cpl_fw4_ack *rpl = (struct cpl_fw4_ack *)cplhdr(skb); + u32 credits = rpl->credits; + u32 snd_una = ntohl(rpl->snd_una); + + csk->wr_cred += credits; + if (csk->wr_una_cred > (csk->wr_max_cred - csk->wr_cred)) + csk->wr_una_cred = csk->wr_max_cred - csk->wr_cred; + + while (credits) { + struct sk_buff *p = cxgbit_sock_peek_wr(csk); + + if (unlikely(!p)) { + pr_err("csk 0x%p,%u, cr %u,%u+%u, empty.\n", + csk, csk->tid, credits, + csk->wr_cred, csk->wr_una_cred); + break; + } + + if (unlikely(credits < p->csum)) { + pr_warn("csk 0x%p,%u, cr %u,%u+%u, < %u.\n", + csk, csk->tid, + credits, csk->wr_cred, csk->wr_una_cred, + p->csum); + p->csum -= credits; + break; + } + + cxgbit_sock_dequeue_wr(csk); + credits -= p->csum; + kfree_skb(p); + } + + if (unlikely(cxgbit_credit_err(csk))) { + cxgbit_queue_rx_skb(csk, skb); + return; + } + + if (rpl->seq_vld & CPL_FW4_ACK_FLAGS_SEQVAL) { + if (unlikely(before(snd_una, csk->snd_una))) { + pr_warn("csk 0x%p,%u, snd_una %u/%u.", + csk, csk->tid, snd_una, + csk->snd_una); + goto rel_skb; + } + + if (csk->snd_una != snd_una) { + csk->snd_una = snd_una; + dst_confirm(csk->dst); + wake_up(&csk->ack_waitq); + } + } + + if (skb_queue_len(&csk->txq)) + cxgbit_push_tx_frames(csk); + +rel_skb: + __kfree_skb(skb); +} + +static void cxgbit_set_tcb_rpl(struct cxgbit_device *cdev, struct sk_buff *skb) +{ + struct cxgbit_sock *csk; + struct cpl_set_tcb_rpl *rpl = (struct cpl_set_tcb_rpl *)skb->data; + unsigned int tid = GET_TID(rpl); + struct cxgb4_lld_info *lldi = &cdev->lldi; + struct tid_info *t = lldi->tids; + + csk = lookup_tid(t, tid); + if (unlikely(!csk)) + pr_err("can't find connection for tid %u.\n", tid); + else + cxgbit_wake_up(&csk->com.wr_wait, __func__, rpl->status); + + cxgbit_put_csk(csk); +} + +static void cxgbit_rx_data(struct cxgbit_device *cdev, struct sk_buff *skb) +{ + struct cxgbit_sock *csk; + struct cpl_rx_data *cpl = cplhdr(skb); + unsigned int tid = GET_TID(cpl); + struct cxgb4_lld_info *lldi = &cdev->lldi; + struct tid_info *t = lldi->tids; + + csk = lookup_tid(t, tid); + if (unlikely(!csk)) { + pr_err("can't find conn. for tid %u.\n", tid); + goto rel_skb; + } + + cxgbit_queue_rx_skb(csk, skb); + return; +rel_skb: + __kfree_skb(skb); +} + +static void +__cxgbit_process_rx_cpl(struct cxgbit_sock *csk, struct sk_buff *skb) +{ + spin_lock(&csk->lock); + if (csk->lock_owner) { + __skb_queue_tail(&csk->backlogq, skb); + spin_unlock(&csk->lock); + return; + } + + cxgbit_skcb_rx_backlog_fn(skb)(csk, skb); + spin_unlock(&csk->lock); +} + +static void cxgbit_process_rx_cpl(struct cxgbit_sock *csk, struct sk_buff *skb) +{ + cxgbit_get_csk(csk); + __cxgbit_process_rx_cpl(csk, skb); + cxgbit_put_csk(csk); +} + +static void cxgbit_rx_cpl(struct cxgbit_device *cdev, struct sk_buff *skb) +{ + struct cxgbit_sock *csk; + struct cpl_tx_data *cpl = cplhdr(skb); + struct cxgb4_lld_info *lldi = &cdev->lldi; + struct tid_info *t = lldi->tids; + unsigned int tid = GET_TID(cpl); + u8 opcode = cxgbit_skcb_rx_opcode(skb); + bool ref = true; + + switch (opcode) { + case CPL_FW4_ACK: + cxgbit_skcb_rx_backlog_fn(skb) = cxgbit_fw4_ack; + ref = false; + break; + case CPL_PEER_CLOSE: + cxgbit_skcb_rx_backlog_fn(skb) = cxgbit_peer_close; + break; + case CPL_CLOSE_CON_RPL: + cxgbit_skcb_rx_backlog_fn(skb) = cxgbit_close_con_rpl; + break; + case CPL_ABORT_REQ_RSS: + cxgbit_skcb_rx_backlog_fn(skb) = cxgbit_abort_req_rss; + break; + case CPL_ABORT_RPL_RSS: + cxgbit_skcb_rx_backlog_fn(skb) = cxgbit_abort_rpl_rss; + break; + default: + goto rel_skb; + } + + csk = lookup_tid(t, tid); + if (unlikely(!csk)) { + pr_err("can't find conn. for tid %u.\n", tid); + goto rel_skb; + } + + if (ref) + cxgbit_process_rx_cpl(csk, skb); + else + __cxgbit_process_rx_cpl(csk, skb); + + return; +rel_skb: + __kfree_skb(skb); +} + +cxgbit_cplhandler_func cxgbit_cplhandlers[NUM_CPL_CMDS] = { + [CPL_PASS_OPEN_RPL] = cxgbit_pass_open_rpl, + [CPL_CLOSE_LISTSRV_RPL] = cxgbit_close_listsrv_rpl, + [CPL_PASS_ACCEPT_REQ] = cxgbit_pass_accept_req, + [CPL_PASS_ESTABLISH] = cxgbit_pass_establish, + [CPL_SET_TCB_RPL] = cxgbit_set_tcb_rpl, + [CPL_RX_DATA] = cxgbit_rx_data, + [CPL_FW4_ACK] = cxgbit_rx_cpl, + [CPL_PEER_CLOSE] = cxgbit_rx_cpl, + [CPL_CLOSE_CON_RPL] = cxgbit_rx_cpl, + [CPL_ABORT_REQ_RSS] = cxgbit_rx_cpl, + [CPL_ABORT_RPL_RSS] = cxgbit_rx_cpl, +}; diff --git a/drivers/target/iscsi/cxgbit/cxgbit_ddp.c b/drivers/target/iscsi/cxgbit/cxgbit_ddp.c new file mode 100644 index 0000000..5d78bdb --- /dev/null +++ b/drivers/target/iscsi/cxgbit/cxgbit_ddp.c @@ -0,0 +1,325 @@ +/* + * Copyright (c) 2016 Chelsio Communications, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "cxgbit.h" + +static void +cxgbit_set_one_ppod(struct cxgbi_pagepod *ppod, + struct cxgbi_task_tag_info *ttinfo, + struct scatterlist **sg_pp, unsigned int *sg_off) +{ + struct scatterlist *sg = sg_pp ? *sg_pp : NULL; + unsigned int offset = sg_off ? *sg_off : 0; + dma_addr_t addr = 0UL; + unsigned int len = 0; + int i; + + memcpy(ppod, &ttinfo->hdr, sizeof(struct cxgbi_pagepod_hdr)); + + if (sg) { + addr = sg_dma_address(sg); + len = sg_dma_len(sg); + } + + for (i = 0; i < PPOD_PAGES_MAX; i++) { + if (sg) { + ppod->addr[i] = cpu_to_be64(addr + offset); + offset += PAGE_SIZE; + if (offset == (len + sg->offset)) { + offset = 0; + sg = sg_next(sg); + if (sg) { + addr = sg_dma_address(sg); + len = sg_dma_len(sg); + } + } + } else { + ppod->addr[i] = 0ULL; + } + } + + /* + * the fifth address needs to be repeated in the next ppod, so do + * not move sg + */ + if (sg_pp) { + *sg_pp = sg; + *sg_off = offset; + } + + if (offset == len) { + offset = 0; + if (sg) { + sg = sg_next(sg); + if (sg) + addr = sg_dma_address(sg); + } + } + ppod->addr[i] = sg ? cpu_to_be64(addr + offset) : 0ULL; +} + +static struct sk_buff * +cxgbit_ppod_init_idata(struct cxgbit_device *cdev, struct cxgbi_ppm *ppm, + unsigned int idx, unsigned int npods, unsigned int tid) +{ + struct ulp_mem_io *req; + struct ulptx_idata *idata; + unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ppm->llimit; + unsigned int dlen = npods << PPOD_SIZE_SHIFT; + unsigned int wr_len = roundup(sizeof(struct ulp_mem_io) + + sizeof(struct ulptx_idata) + dlen, 16); + struct sk_buff *skb; + + skb = alloc_skb(wr_len, GFP_KERNEL); + if (!skb) + return NULL; + + req = (struct ulp_mem_io *)__skb_put(skb, wr_len); + INIT_ULPTX_WR(req, wr_len, 0, tid); + req->wr.wr_hi = htonl(FW_WR_OP_V(FW_ULPTX_WR) | + FW_WR_ATOMIC_V(0)); + req->cmd = htonl(ULPTX_CMD_V(ULP_TX_MEM_WRITE) | + ULP_MEMIO_ORDER_V(0) | + T5_ULP_MEMIO_IMM_V(1)); + req->dlen = htonl(ULP_MEMIO_DATA_LEN_V(dlen >> 5)); + req->lock_addr = htonl(ULP_MEMIO_ADDR_V(pm_addr >> 5)); + req->len16 = htonl(DIV_ROUND_UP(wr_len - sizeof(req->wr), 16)); + + idata = (struct ulptx_idata *)(req + 1); + idata->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_IMM)); + idata->len = htonl(dlen); + + return skb; +} + +static int +cxgbit_ppod_write_idata(struct cxgbi_ppm *ppm, struct cxgbit_sock *csk, + struct cxgbi_task_tag_info *ttinfo, unsigned int idx, + unsigned int npods, struct scatterlist **sg_pp, + unsigned int *sg_off) +{ + struct cxgbit_device *cdev = csk->com.cdev; + struct sk_buff *skb; + struct ulp_mem_io *req; + struct ulptx_idata *idata; + struct cxgbi_pagepod *ppod; + unsigned int i; + + skb = cxgbit_ppod_init_idata(cdev, ppm, idx, npods, csk->tid); + if (!skb) + return -ENOMEM; + + req = (struct ulp_mem_io *)skb->data; + idata = (struct ulptx_idata *)(req + 1); + ppod = (struct cxgbi_pagepod *)(idata + 1); + + for (i = 0; i < npods; i++, ppod++) + cxgbit_set_one_ppod(ppod, ttinfo, sg_pp, sg_off); + + __skb_queue_tail(&csk->ppodq, skb); + + return 0; +} + +static int +cxgbit_ddp_set_map(struct cxgbi_ppm *ppm, struct cxgbit_sock *csk, + struct cxgbi_task_tag_info *ttinfo) +{ + unsigned int pidx = ttinfo->idx; + unsigned int npods = ttinfo->npods; + unsigned int i, cnt; + struct scatterlist *sg = ttinfo->sgl; + unsigned int offset = 0; + int ret = 0; + + for (i = 0; i < npods; i += cnt, pidx += cnt) { + cnt = npods - i; + + if (cnt > ULPMEM_IDATA_MAX_NPPODS) + cnt = ULPMEM_IDATA_MAX_NPPODS; + + ret = cxgbit_ppod_write_idata(ppm, csk, ttinfo, pidx, cnt, + &sg, &offset); + if (ret < 0) + break; + } + + return ret; +} + +static int cxgbit_ddp_sgl_check(struct scatterlist *sg, + unsigned int nents) +{ + unsigned int last_sgidx = nents - 1; + unsigned int i; + + for (i = 0; i < nents; i++, sg = sg_next(sg)) { + unsigned int len = sg->length + sg->offset; + + if ((sg->offset & 0x3) || (i && sg->offset) || + ((i != last_sgidx) && (len != PAGE_SIZE))) { + return -EINVAL; + } + } + + return 0; +} + +static int +cxgbit_ddp_reserve(struct cxgbit_sock *csk, struct cxgbi_task_tag_info *ttinfo, + unsigned int xferlen) +{ + struct cxgbit_device *cdev = csk->com.cdev; + struct cxgbi_ppm *ppm = cdev2ppm(cdev); + struct scatterlist *sgl = ttinfo->sgl; + unsigned int sgcnt = ttinfo->nents; + unsigned int sg_offset = sgl->offset; + int ret; + + if ((xferlen < DDP_THRESHOLD) || (!sgcnt)) { + pr_debug("ppm 0x%p, pgidx %u, xfer %u, sgcnt %u, NO ddp.\n", + ppm, ppm->tformat.pgsz_idx_dflt, + xferlen, ttinfo->nents); + return -EINVAL; + } + + if (cxgbit_ddp_sgl_check(sgl, sgcnt) < 0) + return -EINVAL; + + ttinfo->nr_pages = (xferlen + sgl->offset + + (1 << PAGE_SHIFT) - 1) >> PAGE_SHIFT; + + /* + * the ddp tag will be used for the ttt in the outgoing r2t pdu + */ + ret = cxgbi_ppm_ppods_reserve(ppm, ttinfo->nr_pages, 0, &ttinfo->idx, + &ttinfo->tag, 0); + if (ret < 0) + return ret; + ttinfo->npods = ret; + + sgl->offset = 0; + ret = dma_map_sg(&ppm->pdev->dev, sgl, sgcnt, DMA_FROM_DEVICE); + sgl->offset = sg_offset; + if (!ret) { + pr_info("%s: 0x%x, xfer %u, sgl %u dma mapping err.\n", + __func__, 0, xferlen, sgcnt); + goto rel_ppods; + } + + cxgbi_ppm_make_ppod_hdr(ppm, ttinfo->tag, csk->tid, sgl->offset, + xferlen, &ttinfo->hdr); + + ret = cxgbit_ddp_set_map(ppm, csk, ttinfo); + if (ret < 0) { + __skb_queue_purge(&csk->ppodq); + dma_unmap_sg(&ppm->pdev->dev, sgl, sgcnt, DMA_FROM_DEVICE); + goto rel_ppods; + } + + return 0; + +rel_ppods: + cxgbi_ppm_ppod_release(ppm, ttinfo->idx); + return -EINVAL; +} + +void +cxgbit_get_r2t_ttt(struct iscsi_conn *conn, struct iscsi_cmd *cmd, + struct iscsi_r2t *r2t) +{ + struct cxgbit_sock *csk = conn->context; + struct cxgbit_device *cdev = csk->com.cdev; + struct cxgbit_cmd *ccmd = iscsit_priv_cmd(cmd); + struct cxgbi_task_tag_info *ttinfo = &ccmd->ttinfo; + int ret = -EINVAL; + + if ((!ccmd->setup_ddp) || + (!test_bit(CSK_DDP_ENABLE, &csk->com.flags))) + goto out; + + ccmd->setup_ddp = false; + + ttinfo->sgl = cmd->se_cmd.t_data_sg; + ttinfo->nents = cmd->se_cmd.t_data_nents; + + ret = cxgbit_ddp_reserve(csk, ttinfo, cmd->se_cmd.data_length); + if (ret < 0) { + pr_info("csk 0x%p, cmd 0x%p, xfer len %u, sgcnt %u no ddp.\n", + csk, cmd, cmd->se_cmd.data_length, ttinfo->nents); + + ttinfo->sgl = NULL; + ttinfo->nents = 0; + } else { + ccmd->release = true; + } +out: + pr_debug("cdev 0x%p, cmd 0x%p, tag 0x%x\n", cdev, cmd, ttinfo->tag); + r2t->targ_xfer_tag = ttinfo->tag; +} + +void cxgbit_release_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd) +{ + struct cxgbit_cmd *ccmd = iscsit_priv_cmd(cmd); + + if (ccmd->release) { + struct cxgbi_task_tag_info *ttinfo = &ccmd->ttinfo; + + if (ttinfo->sgl) { + struct cxgbit_sock *csk = conn->context; + struct cxgbit_device *cdev = csk->com.cdev; + struct cxgbi_ppm *ppm = cdev2ppm(cdev); + + cxgbi_ppm_ppod_release(ppm, ttinfo->idx); + + dma_unmap_sg(&ppm->pdev->dev, ttinfo->sgl, + ttinfo->nents, DMA_FROM_DEVICE); + } else { + put_page(sg_page(&ccmd->sg)); + } + + ccmd->release = false; + } +} + +int cxgbit_ddp_init(struct cxgbit_device *cdev) +{ + struct cxgb4_lld_info *lldi = &cdev->lldi; + struct net_device *ndev = cdev->lldi.ports[0]; + struct cxgbi_tag_format tformat; + unsigned int ppmax; + int ret, i; + + if (!lldi->vr->iscsi.size) { + pr_warn("%s, iscsi NOT enabled, check config!\n", ndev->name); + return -EACCES; + } + + ppmax = lldi->vr->iscsi.size >> PPOD_SIZE_SHIFT; + + memset(&tformat, 0, sizeof(struct cxgbi_tag_format)); + for (i = 0; i < 4; i++) + tformat.pgsz_order[i] = (lldi->iscsi_pgsz_order >> (i << 3)) + & 0xF; + cxgbi_tagmask_check(lldi->iscsi_tagmask, &tformat); + + ret = cxgbi_ppm_init(lldi->iscsi_ppm, cdev->lldi.ports[0], + cdev->lldi.pdev, &cdev->lldi, &tformat, + ppmax, lldi->iscsi_llimit, + lldi->vr->iscsi.start, 2); + if (ret >= 0) { + struct cxgbi_ppm *ppm = (struct cxgbi_ppm *)(*lldi->iscsi_ppm); + + if ((ppm->tformat.pgsz_idx_dflt < DDP_PGIDX_MAX) && + (ppm->ppmax >= 1024)) + set_bit(CDEV_DDP_ENABLE, &cdev->flags); + ret = 0; + } + + return ret; +} diff --git a/drivers/target/iscsi/cxgbit/cxgbit_lro.h b/drivers/target/iscsi/cxgbit/cxgbit_lro.h new file mode 100644 index 0000000..28c11bd --- /dev/null +++ b/drivers/target/iscsi/cxgbit/cxgbit_lro.h @@ -0,0 +1,72 @@ +/* + * Copyright (c) 2016 Chelsio Communications, 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. + * + */ + +#ifndef __CXGBIT_LRO_H__ +#define __CXGBIT_LRO_H__ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/skbuff.h> + +#define LRO_FLUSH_LEN_MAX 65535 + +struct cxgbit_lro_cb { + struct cxgbit_sock *csk; + u32 pdu_totallen; + u32 offset; + u8 pdu_idx; + bool complete; +}; + +enum cxgbit_pducb_flags { + PDUCBF_RX_HDR = (1 << 0), /* received pdu header */ + PDUCBF_RX_DATA = (1 << 1), /* received pdu payload */ + PDUCBF_RX_STATUS = (1 << 2), /* received ddp status */ + PDUCBF_RX_DATA_DDPD = (1 << 3), /* pdu payload ddp'd */ + PDUCBF_RX_HCRC_ERR = (1 << 4), /* header digest error */ + PDUCBF_RX_DCRC_ERR = (1 << 5), /* data digest error */ +}; + +struct cxgbit_lro_pdu_cb { + u8 flags; + u8 frags; + u8 hfrag_idx; + u8 nr_dfrags; + u8 dfrag_idx; + bool complete; + u32 seq; + u32 pdulen; + u32 hlen; + u32 dlen; + u32 doffset; + u32 ddigest; + void *hdr; +}; + +#define LRO_SKB_MAX_HEADROOM \ + (sizeof(struct cxgbit_lro_cb) + \ + (MAX_SKB_FRAGS * sizeof(struct cxgbit_lro_pdu_cb))) + +#define LRO_SKB_MIN_HEADROOM \ + (sizeof(struct cxgbit_lro_cb) + \ + sizeof(struct cxgbit_lro_pdu_cb)) + +#define cxgbit_skb_lro_cb(skb) ((struct cxgbit_lro_cb *)skb->data) +#define cxgbit_skb_lro_pdu_cb(skb, i) \ + ((struct cxgbit_lro_pdu_cb *)(skb->data + sizeof(struct cxgbit_lro_cb) \ + + (i * sizeof(struct cxgbit_lro_pdu_cb)))) + +#define CPL_RX_ISCSI_DDP_STATUS_DDP_SHIFT 16 /* ddp'able */ +#define CPL_RX_ISCSI_DDP_STATUS_PAD_SHIFT 19 /* pad error */ +#define CPL_RX_ISCSI_DDP_STATUS_HCRC_SHIFT 20 /* hcrc error */ +#define CPL_RX_ISCSI_DDP_STATUS_DCRC_SHIFT 21 /* dcrc error */ + +#endif /*__CXGBIT_LRO_H_*/ diff --git a/drivers/target/iscsi/cxgbit/cxgbit_main.c b/drivers/target/iscsi/cxgbit/cxgbit_main.c new file mode 100644 index 0000000..9cf8430 --- /dev/null +++ b/drivers/target/iscsi/cxgbit/cxgbit_main.c @@ -0,0 +1,703 @@ +/* + * Copyright (c) 2016 Chelsio Communications, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#define DRV_NAME "cxgbit" +#define DRV_VERSION "1.0.0-ko" +#define pr_fmt(fmt) DRV_NAME ": " fmt + +#include "cxgbit.h" + +#ifdef CONFIG_CHELSIO_T4_DCB +#include <net/dcbevent.h> +#include "cxgb4_dcb.h" +#endif + +LIST_HEAD(cdev_list_head); +/* cdev list lock */ +DEFINE_MUTEX(cdev_list_lock); + +void _cxgbit_free_cdev(struct kref *kref) +{ + struct cxgbit_device *cdev; + + cdev = container_of(kref, struct cxgbit_device, kref); + kfree(cdev); +} + +static void cxgbit_set_mdsl(struct cxgbit_device *cdev) +{ + struct cxgb4_lld_info *lldi = &cdev->lldi; + u32 mdsl; + +#define ULP2_MAX_PKT_LEN 16224 +#define ISCSI_PDU_NONPAYLOAD_LEN 312 + mdsl = min_t(u32, lldi->iscsi_iolen - ISCSI_PDU_NONPAYLOAD_LEN, + ULP2_MAX_PKT_LEN - ISCSI_PDU_NONPAYLOAD_LEN); + mdsl = min_t(u32, mdsl, 8192); + mdsl = min_t(u32, mdsl, (MAX_SKB_FRAGS - 1) * PAGE_SIZE); + + cdev->mdsl = mdsl; +} + +static void *cxgbit_uld_add(const struct cxgb4_lld_info *lldi) +{ + struct cxgbit_device *cdev; + + if (is_t4(lldi->adapter_type)) + return ERR_PTR(-ENODEV); + + cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); + if (!cdev) + return ERR_PTR(-ENOMEM); + + kref_init(&cdev->kref); + + cdev->lldi = *lldi; + + cxgbit_set_mdsl(cdev); + + if (cxgbit_ddp_init(cdev) < 0) { + kfree(cdev); + return ERR_PTR(-EINVAL); + } + + if (!test_bit(CDEV_DDP_ENABLE, &cdev->flags)) + pr_info("cdev %s ddp init failed\n", + pci_name(lldi->pdev)); + + if (lldi->fw_vers >= 0x10d2b00) + set_bit(CDEV_ISO_ENABLE, &cdev->flags); + + spin_lock_init(&cdev->cskq.lock); + INIT_LIST_HEAD(&cdev->cskq.list); + + mutex_lock(&cdev_list_lock); + list_add_tail(&cdev->list, &cdev_list_head); + mutex_unlock(&cdev_list_lock); + + pr_info("cdev %s added for iSCSI target transport\n", + pci_name(lldi->pdev)); + + return cdev; +} + +static void cxgbit_close_conn(struct cxgbit_device *cdev) +{ + struct cxgbit_sock *csk; + struct sk_buff *skb; + bool wakeup_thread = false; + + spin_lock_bh(&cdev->cskq.lock); + list_for_each_entry(csk, &cdev->cskq.list, list) { + skb = alloc_skb(0, GFP_ATOMIC); + if (!skb) + continue; + + spin_lock_bh(&csk->rxq.lock); + __skb_queue_tail(&csk->rxq, skb); + if (skb_queue_len(&csk->rxq) == 1) + wakeup_thread = true; + spin_unlock_bh(&csk->rxq.lock); + + if (wakeup_thread) { + wake_up(&csk->waitq); + wakeup_thread = false; + } + } + spin_unlock_bh(&cdev->cskq.lock); +} + +static void cxgbit_detach_cdev(struct cxgbit_device *cdev) +{ + bool free_cdev = false; + + spin_lock_bh(&cdev->cskq.lock); + if (list_empty(&cdev->cskq.list)) + free_cdev = true; + spin_unlock_bh(&cdev->cskq.lock); + + if (free_cdev) { + mutex_lock(&cdev_list_lock); + list_del(&cdev->list); + mutex_unlock(&cdev_list_lock); + + cxgbit_put_cdev(cdev); + } else { + cxgbit_close_conn(cdev); + } +} + +static int cxgbit_uld_state_change(void *handle, enum cxgb4_state state) +{ + struct cxgbit_device *cdev = handle; + + switch (state) { + case CXGB4_STATE_UP: + set_bit(CDEV_STATE_UP, &cdev->flags); + pr_info("cdev %s state UP.\n", pci_name(cdev->lldi.pdev)); + break; + case CXGB4_STATE_START_RECOVERY: + clear_bit(CDEV_STATE_UP, &cdev->flags); + cxgbit_close_conn(cdev); + pr_info("cdev %s state RECOVERY.\n", pci_name(cdev->lldi.pdev)); + break; + case CXGB4_STATE_DOWN: + pr_info("cdev %s state DOWN.\n", pci_name(cdev->lldi.pdev)); + break; + case CXGB4_STATE_DETACH: + clear_bit(CDEV_STATE_UP, &cdev->flags); + cxgbit_detach_cdev(cdev); + pr_info("cdev %s state DETACH.\n", pci_name(cdev->lldi.pdev)); + break; + default: + pr_info("cdev %s unknown state %d.\n", + pci_name(cdev->lldi.pdev), state); + break; + } + return 0; +} + +static void +cxgbit_proc_ddp_status(unsigned int tid, struct cpl_rx_data_ddp *cpl, + struct cxgbit_lro_pdu_cb *pdu_cb) +{ + unsigned int status = ntohl(cpl->ddpvld); + + pdu_cb->flags |= PDUCBF_RX_STATUS; + pdu_cb->ddigest = ntohl(cpl->ulp_crc); + pdu_cb->pdulen = ntohs(cpl->len); + + if (status & (1 << CPL_RX_ISCSI_DDP_STATUS_HCRC_SHIFT)) { + pr_info("tid 0x%x, status 0x%x, hcrc bad.\n", tid, status); + pdu_cb->flags |= PDUCBF_RX_HCRC_ERR; + } + + if (status & (1 << CPL_RX_ISCSI_DDP_STATUS_DCRC_SHIFT)) { + pr_info("tid 0x%x, status 0x%x, dcrc bad.\n", tid, status); + pdu_cb->flags |= PDUCBF_RX_DCRC_ERR; + } + + if (status & (1 << CPL_RX_ISCSI_DDP_STATUS_PAD_SHIFT)) + pr_info("tid 0x%x, status 0x%x, pad bad.\n", tid, status); + + if ((status & (1 << CPL_RX_ISCSI_DDP_STATUS_DDP_SHIFT)) && + (!(pdu_cb->flags & PDUCBF_RX_DATA))) { + pdu_cb->flags |= PDUCBF_RX_DATA_DDPD; + } +} + +static void +cxgbit_lro_add_packet_rsp(struct sk_buff *skb, u8 op, const __be64 *rsp) +{ + struct cxgbit_lro_cb *lro_cb = cxgbit_skb_lro_cb(skb); + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb, + lro_cb->pdu_idx); + struct cpl_rx_iscsi_ddp *cpl = (struct cpl_rx_iscsi_ddp *)(rsp + 1); + + cxgbit_proc_ddp_status(lro_cb->csk->tid, cpl, pdu_cb); + + if (pdu_cb->flags & PDUCBF_RX_HDR) + pdu_cb->complete = true; + + lro_cb->complete = true; + lro_cb->pdu_totallen += pdu_cb->pdulen; + lro_cb->pdu_idx++; +} + +static void +cxgbit_copy_frags(struct sk_buff *skb, const struct pkt_gl *gl, + unsigned int offset) +{ + u8 skb_frag_idx = skb_shinfo(skb)->nr_frags; + u8 i; + + /* usually there's just one frag */ + __skb_fill_page_desc(skb, skb_frag_idx, gl->frags[0].page, + gl->frags[0].offset + offset, + gl->frags[0].size - offset); + for (i = 1; i < gl->nfrags; i++) + __skb_fill_page_desc(skb, skb_frag_idx + i, + gl->frags[i].page, + gl->frags[i].offset, + gl->frags[i].size); + + skb_shinfo(skb)->nr_frags += gl->nfrags; + + /* get a reference to the last page, we don't own it */ + get_page(gl->frags[gl->nfrags - 1].page); +} + +static void +cxgbit_lro_add_packet_gl(struct sk_buff *skb, u8 op, const struct pkt_gl *gl) +{ + struct cxgbit_lro_cb *lro_cb = cxgbit_skb_lro_cb(skb); + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb, + lro_cb->pdu_idx); + u32 len, offset; + + if (op == CPL_ISCSI_HDR) { + struct cpl_iscsi_hdr *cpl = (struct cpl_iscsi_hdr *)gl->va; + + offset = sizeof(struct cpl_iscsi_hdr); + pdu_cb->flags |= PDUCBF_RX_HDR; + pdu_cb->seq = ntohl(cpl->seq); + len = ntohs(cpl->len); + pdu_cb->hdr = gl->va + offset; + pdu_cb->hlen = len; + pdu_cb->hfrag_idx = skb_shinfo(skb)->nr_frags; + + if (unlikely(gl->nfrags > 1)) + cxgbit_skcb_flags(skb) = 0; + + lro_cb->complete = false; + } else { + struct cpl_iscsi_data *cpl = (struct cpl_iscsi_data *)gl->va; + + offset = sizeof(struct cpl_iscsi_data); + pdu_cb->flags |= PDUCBF_RX_DATA; + len = ntohs(cpl->len); + pdu_cb->dlen = len; + pdu_cb->doffset = lro_cb->offset; + pdu_cb->nr_dfrags = gl->nfrags; + pdu_cb->dfrag_idx = skb_shinfo(skb)->nr_frags; + } + + cxgbit_copy_frags(skb, gl, offset); + + pdu_cb->frags += gl->nfrags; + lro_cb->offset += len; + skb->len += len; + skb->data_len += len; + skb->truesize += len; +} + +static struct sk_buff * +cxgbit_lro_init_skb(struct cxgbit_sock *csk, u8 op, const struct pkt_gl *gl, + const __be64 *rsp, struct napi_struct *napi) +{ + struct sk_buff *skb; + struct cxgbit_lro_cb *lro_cb; + + skb = napi_alloc_skb(napi, LRO_SKB_MAX_HEADROOM); + + if (unlikely(!skb)) + return NULL; + + memset(skb->data, 0, LRO_SKB_MAX_HEADROOM); + + cxgbit_skcb_flags(skb) |= SKCBF_RX_LRO; + + lro_cb = cxgbit_skb_lro_cb(skb); + + cxgbit_get_csk(csk); + + lro_cb->csk = csk; + + return skb; +} + +static void cxgbit_queue_lro_skb(struct cxgbit_sock *csk, struct sk_buff *skb) +{ + bool wakeup_thread = false; + + spin_lock(&csk->rxq.lock); + __skb_queue_tail(&csk->rxq, skb); + if (skb_queue_len(&csk->rxq) == 1) + wakeup_thread = true; + spin_unlock(&csk->rxq.lock); + + if (wakeup_thread) + wake_up(&csk->waitq); +} + +static void cxgbit_lro_flush(struct t4_lro_mgr *lro_mgr, struct sk_buff *skb) +{ + struct cxgbit_lro_cb *lro_cb = cxgbit_skb_lro_cb(skb); + struct cxgbit_sock *csk = lro_cb->csk; + + csk->lro_skb = NULL; + + __skb_unlink(skb, &lro_mgr->lroq); + cxgbit_queue_lro_skb(csk, skb); + + cxgbit_put_csk(csk); + + lro_mgr->lro_pkts++; + lro_mgr->lro_session_cnt--; +} + +static void cxgbit_uld_lro_flush(struct t4_lro_mgr *lro_mgr) +{ + struct sk_buff *skb; + + while ((skb = skb_peek(&lro_mgr->lroq))) + cxgbit_lro_flush(lro_mgr, skb); +} + +static int +cxgbit_lro_receive(struct cxgbit_sock *csk, u8 op, const __be64 *rsp, + const struct pkt_gl *gl, struct t4_lro_mgr *lro_mgr, + struct napi_struct *napi) +{ + struct sk_buff *skb; + struct cxgbit_lro_cb *lro_cb; + + if (!csk) { + pr_err("%s: csk NULL, op 0x%x.\n", __func__, op); + goto out; + } + + if (csk->lro_skb) + goto add_packet; + +start_lro: + if (lro_mgr->lro_session_cnt >= MAX_LRO_SESSIONS) { + cxgbit_uld_lro_flush(lro_mgr); + goto start_lro; + } + + skb = cxgbit_lro_init_skb(csk, op, gl, rsp, napi); + if (unlikely(!skb)) + goto out; + + csk->lro_skb = skb; + + __skb_queue_tail(&lro_mgr->lroq, skb); + lro_mgr->lro_session_cnt++; + +add_packet: + skb = csk->lro_skb; + lro_cb = cxgbit_skb_lro_cb(skb); + + if ((gl && (((skb_shinfo(skb)->nr_frags + gl->nfrags) > + MAX_SKB_FRAGS) || (lro_cb->pdu_totallen >= LRO_FLUSH_LEN_MAX))) || + (lro_cb->pdu_idx >= MAX_SKB_FRAGS)) { + cxgbit_lro_flush(lro_mgr, skb); + goto start_lro; + } + + if (gl) + cxgbit_lro_add_packet_gl(skb, op, gl); + else + cxgbit_lro_add_packet_rsp(skb, op, rsp); + + lro_mgr->lro_merged++; + + return 0; + +out: + return -1; +} + +static int +cxgbit_uld_lro_rx_handler(void *hndl, const __be64 *rsp, + const struct pkt_gl *gl, struct t4_lro_mgr *lro_mgr, + struct napi_struct *napi) +{ + struct cxgbit_device *cdev = hndl; + struct cxgb4_lld_info *lldi = &cdev->lldi; + struct cpl_tx_data *rpl = NULL; + struct cxgbit_sock *csk = NULL; + unsigned int tid = 0; + struct sk_buff *skb; + unsigned int op = *(u8 *)rsp; + bool lro_flush = true; + + switch (op) { + case CPL_ISCSI_HDR: + case CPL_ISCSI_DATA: + case CPL_RX_ISCSI_DDP: + case CPL_FW4_ACK: + lro_flush = false; + case CPL_ABORT_RPL_RSS: + case CPL_PASS_ESTABLISH: + case CPL_PEER_CLOSE: + case CPL_CLOSE_CON_RPL: + case CPL_ABORT_REQ_RSS: + case CPL_SET_TCB_RPL: + case CPL_RX_DATA: + rpl = gl ? (struct cpl_tx_data *)gl->va : + (struct cpl_tx_data *)(rsp + 1); + tid = GET_TID(rpl); + csk = lookup_tid(lldi->tids, tid); + break; + default: + break; + } + + if (csk && csk->lro_skb && lro_flush) + cxgbit_lro_flush(lro_mgr, csk->lro_skb); + + if (!gl) { + unsigned int len; + + if (op == CPL_RX_ISCSI_DDP) { + if (!cxgbit_lro_receive(csk, op, rsp, NULL, lro_mgr, + napi)) + return 0; + } + + len = 64 - sizeof(struct rsp_ctrl) - 8; + skb = napi_alloc_skb(napi, len); + if (!skb) + goto nomem; + __skb_put(skb, len); + skb_copy_to_linear_data(skb, &rsp[1], len); + } else { + if (unlikely(op != *(u8 *)gl->va)) { + pr_info("? FL 0x%p,RSS%#llx,FL %#llx,len %u.\n", + gl->va, be64_to_cpu(*rsp), + be64_to_cpu(*(u64 *)gl->va), + gl->tot_len); + return 0; + } + + if (op == CPL_ISCSI_HDR || op == CPL_ISCSI_DATA) { + if (!cxgbit_lro_receive(csk, op, rsp, gl, lro_mgr, + napi)) + return 0; + } + +#define RX_PULL_LEN 128 + skb = cxgb4_pktgl_to_skb(gl, RX_PULL_LEN, RX_PULL_LEN); + if (unlikely(!skb)) + goto nomem; + } + + rpl = (struct cpl_tx_data *)skb->data; + op = rpl->ot.opcode; + cxgbit_skcb_rx_opcode(skb) = op; + + pr_debug("cdev %p, opcode 0x%x(0x%x,0x%x), skb %p.\n", + cdev, op, rpl->ot.opcode_tid, + ntohl(rpl->ot.opcode_tid), skb); + + if (op < NUM_CPL_CMDS && cxgbit_cplhandlers[op]) { + cxgbit_cplhandlers[op](cdev, skb); + } else { + pr_err("No handler for opcode 0x%x.\n", op); + __kfree_skb(skb); + } + return 0; +nomem: + pr_err("%s OOM bailing out.\n", __func__); + return 1; +} + +#ifdef CONFIG_CHELSIO_T4_DCB +struct cxgbit_dcb_work { + struct dcb_app_type dcb_app; + struct work_struct work; +}; + +static void +cxgbit_update_dcb_priority(struct cxgbit_device *cdev, u8 port_id, + u8 dcb_priority, u16 port_num) +{ + struct cxgbit_sock *csk; + struct sk_buff *skb; + u16 local_port; + bool wakeup_thread = false; + + spin_lock_bh(&cdev->cskq.lock); + list_for_each_entry(csk, &cdev->cskq.list, list) { + if (csk->port_id != port_id) + continue; + + if (csk->com.local_addr.ss_family == AF_INET6) { + struct sockaddr_in6 *sock_in6; + + sock_in6 = (struct sockaddr_in6 *)&csk->com.local_addr; + local_port = ntohs(sock_in6->sin6_port); + } else { + struct sockaddr_in *sock_in; + + sock_in = (struct sockaddr_in *)&csk->com.local_addr; + local_port = ntohs(sock_in->sin_port); + } + + if (local_port != port_num) + continue; + + if (csk->dcb_priority == dcb_priority) + continue; + + skb = alloc_skb(0, GFP_ATOMIC); + if (!skb) + continue; + + spin_lock(&csk->rxq.lock); + __skb_queue_tail(&csk->rxq, skb); + if (skb_queue_len(&csk->rxq) == 1) + wakeup_thread = true; + spin_unlock(&csk->rxq.lock); + + if (wakeup_thread) { + wake_up(&csk->waitq); + wakeup_thread = false; + } + } + spin_unlock_bh(&cdev->cskq.lock); +} + +static void cxgbit_dcb_workfn(struct work_struct *work) +{ + struct cxgbit_dcb_work *dcb_work; + struct net_device *ndev; + struct cxgbit_device *cdev = NULL; + struct dcb_app_type *iscsi_app; + u8 priority, port_id = 0xff; + + dcb_work = container_of(work, struct cxgbit_dcb_work, work); + iscsi_app = &dcb_work->dcb_app; + + if (iscsi_app->dcbx & DCB_CAP_DCBX_VER_IEEE) { + if (iscsi_app->app.selector != IEEE_8021QAZ_APP_SEL_ANY) + goto out; + + priority = iscsi_app->app.priority; + + } else if (iscsi_app->dcbx & DCB_CAP_DCBX_VER_CEE) { + if (iscsi_app->app.selector != DCB_APP_IDTYPE_PORTNUM) + goto out; + + if (!iscsi_app->app.priority) + goto out; + + priority = ffs(iscsi_app->app.priority) - 1; + } else { + goto out; + } + + pr_debug("priority for ifid %d is %u\n", + iscsi_app->ifindex, priority); + + ndev = dev_get_by_index(&init_net, iscsi_app->ifindex); + + if (!ndev) + goto out; + + mutex_lock(&cdev_list_lock); + cdev = cxgbit_find_device(ndev, &port_id); + + dev_put(ndev); + + if (!cdev) { + mutex_unlock(&cdev_list_lock); + goto out; + } + + cxgbit_update_dcb_priority(cdev, port_id, priority, + iscsi_app->app.protocol); + mutex_unlock(&cdev_list_lock); +out: + kfree(dcb_work); +} + +static int +cxgbit_dcbevent_notify(struct notifier_block *nb, unsigned long action, + void *data) +{ + struct cxgbit_dcb_work *dcb_work; + struct dcb_app_type *dcb_app = data; + + dcb_work = kzalloc(sizeof(*dcb_work), GFP_ATOMIC); + if (!dcb_work) + return NOTIFY_DONE; + + dcb_work->dcb_app = *dcb_app; + INIT_WORK(&dcb_work->work, cxgbit_dcb_workfn); + schedule_work(&dcb_work->work); + return NOTIFY_OK; +} +#endif + +static enum target_prot_op cxgbit_get_sup_prot_ops(struct iscsi_conn *conn) +{ + return TARGET_PROT_NORMAL; +} + +static struct iscsit_transport cxgbit_transport = { + .name = DRV_NAME, + .transport_type = ISCSI_HW_OFFLOAD, + .priv_size = sizeof(struct cxgbit_cmd), + .owner = THIS_MODULE, + .iscsit_setup_np = cxgbit_setup_np, + .iscsit_accept_np = cxgbit_accept_np, + .iscsit_free_np = cxgbit_free_np, + .iscsit_free_conn = cxgbit_free_conn, + .iscsit_get_login_rx = cxgbit_get_login_rx, + .iscsit_put_login_tx = cxgbit_put_login_tx, + .iscsit_immediate_queue = iscsit_immediate_queue, + .iscsit_response_queue = iscsit_response_queue, + .iscsit_get_dataout = iscsit_build_r2ts_for_cmd, + .iscsit_queue_data_in = iscsit_queue_rsp, + .iscsit_queue_status = iscsit_queue_rsp, + .iscsit_alloc_pdu = cxgbit_alloc_pdu, + .iscsit_xmit_pdu = cxgbit_xmit_pdu, + .iscsit_xmit_datain_pdu = cxgbit_xmit_datain_pdu, + .iscsit_get_r2t_ttt = cxgbit_get_r2t_ttt, + .iscsit_get_rx_pdu = cxgbit_get_rx_pdu, + .iscsit_validate_params = cxgbit_validate_params, + .iscsit_release_cmd = cxgbit_release_cmd, + .iscsit_aborted_task = iscsit_aborted_task, + .iscsit_get_sup_prot_ops = cxgbit_get_sup_prot_ops, +}; + +static struct cxgb4_uld_info cxgbit_uld_info = { + .name = DRV_NAME, + .add = cxgbit_uld_add, + .state_change = cxgbit_uld_state_change, + .lro_rx_handler = cxgbit_uld_lro_rx_handler, + .lro_flush = cxgbit_uld_lro_flush, +}; + +#ifdef CONFIG_CHELSIO_T4_DCB +static struct notifier_block cxgbit_dcbevent_nb = { + .notifier_call = cxgbit_dcbevent_notify, +}; +#endif + +static int __init cxgbit_init(void) +{ + cxgb4_register_uld(CXGB4_ULD_ISCSIT, &cxgbit_uld_info); + iscsit_register_transport(&cxgbit_transport); + +#ifdef CONFIG_CHELSIO_T4_DCB + pr_info("%s dcb enabled.\n", DRV_NAME); + register_dcbevent_notifier(&cxgbit_dcbevent_nb); +#endif + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, cb) < + sizeof(union cxgbit_skb_cb)); + return 0; +} + +static void __exit cxgbit_exit(void) +{ + struct cxgbit_device *cdev, *tmp; + +#ifdef CONFIG_CHELSIO_T4_DCB + unregister_dcbevent_notifier(&cxgbit_dcbevent_nb); +#endif + mutex_lock(&cdev_list_lock); + list_for_each_entry_safe(cdev, tmp, &cdev_list_head, list) { + list_del(&cdev->list); + cxgbit_put_cdev(cdev); + } + mutex_unlock(&cdev_list_lock); + iscsit_unregister_transport(&cxgbit_transport); + cxgb4_unregister_uld(CXGB4_ULD_ISCSIT); +} + +module_init(cxgbit_init); +module_exit(cxgbit_exit); + +MODULE_DESCRIPTION("Chelsio iSCSI target offload driver"); +MODULE_AUTHOR("Chelsio Communications"); +MODULE_VERSION(DRV_VERSION); +MODULE_LICENSE("GPL"); diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c new file mode 100644 index 0000000..96355b0a --- /dev/null +++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c @@ -0,0 +1,1601 @@ +/* + * Copyright (c) 2016 Chelsio Communications, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/workqueue.h> +#include <linux/kthread.h> +#include <asm/unaligned.h> +#include <target/target_core_base.h> +#include <target/target_core_fabric.h> +#include "cxgbit.h" + +struct sge_opaque_hdr { + void *dev; + dma_addr_t addr[MAX_SKB_FRAGS + 1]; +}; + +static const u8 cxgbit_digest_len[] = {0, 4, 4, 8}; + +#define TX_HDR_LEN (sizeof(struct sge_opaque_hdr) + \ + sizeof(struct fw_ofld_tx_data_wr)) + +static struct sk_buff * +__cxgbit_alloc_skb(struct cxgbit_sock *csk, u32 len, bool iso) +{ + struct sk_buff *skb = NULL; + u8 submode = 0; + int errcode; + static const u32 hdr_len = TX_HDR_LEN + ISCSI_HDR_LEN; + + if (len) { + skb = alloc_skb_with_frags(hdr_len, len, + 0, &errcode, + GFP_KERNEL); + if (!skb) + return NULL; + + skb_reserve(skb, TX_HDR_LEN); + skb_reset_transport_header(skb); + __skb_put(skb, ISCSI_HDR_LEN); + memset(skb->data, 0, ISCSI_HDR_LEN); + skb->data_len = len; + skb->len += len; + submode |= (csk->submode & CXGBIT_SUBMODE_DCRC); + + } else { + u32 iso_len = iso ? sizeof(struct cpl_tx_data_iso) : 0; + + skb = alloc_skb(hdr_len + iso_len, GFP_KERNEL); + if (!skb) + return NULL; + + skb_reserve(skb, TX_HDR_LEN + iso_len); + skb_reset_transport_header(skb); + __skb_put(skb, ISCSI_HDR_LEN); + memset(skb->data, 0, ISCSI_HDR_LEN); + } + + submode |= (csk->submode & CXGBIT_SUBMODE_HCRC); + cxgbit_skcb_submode(skb) = submode; + cxgbit_skcb_tx_extralen(skb) = cxgbit_digest_len[submode]; + cxgbit_skcb_flags(skb) |= SKCBF_TX_NEED_HDR; + return skb; +} + +static struct sk_buff *cxgbit_alloc_skb(struct cxgbit_sock *csk, u32 len) +{ + return __cxgbit_alloc_skb(csk, len, false); +} + +/* + * cxgbit_is_ofld_imm - check whether a packet can be sent as immediate data + * @skb: the packet + * + * Returns true if a packet can be sent as an offload WR with immediate + * data. We currently use the same limit as for Ethernet packets. + */ +static int cxgbit_is_ofld_imm(const struct sk_buff *skb) +{ + int length = skb->len; + + if (likely(cxgbit_skcb_flags(skb) & SKCBF_TX_NEED_HDR)) + length += sizeof(struct fw_ofld_tx_data_wr); + + if (likely(cxgbit_skcb_flags(skb) & SKCBF_TX_ISO)) + length += sizeof(struct cpl_tx_data_iso); + +#define MAX_IMM_TX_PKT_LEN 256 + return length <= MAX_IMM_TX_PKT_LEN; +} + +/* + * cxgbit_sgl_len - calculates the size of an SGL of the given capacity + * @n: the number of SGL entries + * Calculates the number of flits needed for a scatter/gather list that + * can hold the given number of entries. + */ +static inline unsigned int cxgbit_sgl_len(unsigned int n) +{ + n--; + return (3 * n) / 2 + (n & 1) + 2; +} + +/* + * cxgbit_calc_tx_flits_ofld - calculate # of flits for an offload packet + * @skb: the packet + * + * Returns the number of flits needed for the given offload packet. + * These packets are already fully constructed and no additional headers + * will be added. + */ +static unsigned int cxgbit_calc_tx_flits_ofld(const struct sk_buff *skb) +{ + unsigned int flits, cnt; + + if (cxgbit_is_ofld_imm(skb)) + return DIV_ROUND_UP(skb->len, 8); + flits = skb_transport_offset(skb) / 8; + cnt = skb_shinfo(skb)->nr_frags; + if (skb_tail_pointer(skb) != skb_transport_header(skb)) + cnt++; + return flits + cxgbit_sgl_len(cnt); +} + +#define CXGBIT_ISO_FSLICE 0x1 +#define CXGBIT_ISO_LSLICE 0x2 +static void +cxgbit_cpl_tx_data_iso(struct sk_buff *skb, struct cxgbit_iso_info *iso_info) +{ + struct cpl_tx_data_iso *cpl; + unsigned int submode = cxgbit_skcb_submode(skb); + unsigned int fslice = !!(iso_info->flags & CXGBIT_ISO_FSLICE); + unsigned int lslice = !!(iso_info->flags & CXGBIT_ISO_LSLICE); + + cpl = (struct cpl_tx_data_iso *)__skb_push(skb, sizeof(*cpl)); + + cpl->op_to_scsi = htonl(CPL_TX_DATA_ISO_OP_V(CPL_TX_DATA_ISO) | + CPL_TX_DATA_ISO_FIRST_V(fslice) | + CPL_TX_DATA_ISO_LAST_V(lslice) | + CPL_TX_DATA_ISO_CPLHDRLEN_V(0) | + CPL_TX_DATA_ISO_HDRCRC_V(submode & 1) | + CPL_TX_DATA_ISO_PLDCRC_V(((submode >> 1) & 1)) | + CPL_TX_DATA_ISO_IMMEDIATE_V(0) | + CPL_TX_DATA_ISO_SCSI_V(2)); + + cpl->ahs_len = 0; + cpl->mpdu = htons(DIV_ROUND_UP(iso_info->mpdu, 4)); + cpl->burst_size = htonl(DIV_ROUND_UP(iso_info->burst_len, 4)); + cpl->len = htonl(iso_info->len); + cpl->reserved2_seglen_offset = htonl(0); + cpl->datasn_offset = htonl(0); + cpl->buffer_offset = htonl(0); + cpl->reserved3 = 0; + + __skb_pull(skb, sizeof(*cpl)); +} + +static void +cxgbit_tx_data_wr(struct cxgbit_sock *csk, struct sk_buff *skb, u32 dlen, + u32 len, u32 credits, u32 compl) +{ + struct fw_ofld_tx_data_wr *req; + u32 submode = cxgbit_skcb_submode(skb); + u32 wr_ulp_mode = 0; + u32 hdr_size = sizeof(*req); + u32 opcode = FW_OFLD_TX_DATA_WR; + u32 immlen = 0; + u32 force = TX_FORCE_V(!submode); + + if (cxgbit_skcb_flags(skb) & SKCBF_TX_ISO) { + opcode = FW_ISCSI_TX_DATA_WR; + immlen += sizeof(struct cpl_tx_data_iso); + hdr_size += sizeof(struct cpl_tx_data_iso); + submode |= 8; + } + + if (cxgbit_is_ofld_imm(skb)) + immlen += dlen; + + req = (struct fw_ofld_tx_data_wr *)__skb_push(skb, + hdr_size); + req->op_to_immdlen = cpu_to_be32(FW_WR_OP_V(opcode) | + FW_WR_COMPL_V(compl) | + FW_WR_IMMDLEN_V(immlen)); + req->flowid_len16 = cpu_to_be32(FW_WR_FLOWID_V(csk->tid) | + FW_WR_LEN16_V(credits)); + req->plen = htonl(len); + wr_ulp_mode = FW_OFLD_TX_DATA_WR_ULPMODE_V(ULP_MODE_ISCSI) | + FW_OFLD_TX_DATA_WR_ULPSUBMODE_V(submode); + + req->tunnel_to_proxy = htonl((wr_ulp_mode) | force | + FW_OFLD_TX_DATA_WR_SHOVE_V(skb_peek(&csk->txq) ? 0 : 1)); +} + +static void cxgbit_arp_failure_skb_discard(void *handle, struct sk_buff *skb) +{ + kfree_skb(skb); +} + +void cxgbit_push_tx_frames(struct cxgbit_sock *csk) +{ + struct sk_buff *skb; + + while (csk->wr_cred && ((skb = skb_peek(&csk->txq)) != NULL)) { + u32 dlen = skb->len; + u32 len = skb->len; + u32 credits_needed; + u32 compl = 0; + u32 flowclen16 = 0; + u32 iso_cpl_len = 0; + + if (cxgbit_skcb_flags(skb) & SKCBF_TX_ISO) + iso_cpl_len = sizeof(struct cpl_tx_data_iso); + + if (cxgbit_is_ofld_imm(skb)) + credits_needed = DIV_ROUND_UP(dlen + iso_cpl_len, 16); + else + credits_needed = DIV_ROUND_UP((8 * + cxgbit_calc_tx_flits_ofld(skb)) + + iso_cpl_len, 16); + + if (likely(cxgbit_skcb_flags(skb) & SKCBF_TX_NEED_HDR)) + credits_needed += DIV_ROUND_UP( + sizeof(struct fw_ofld_tx_data_wr), 16); + /* + * Assumes the initial credits is large enough to support + * fw_flowc_wr plus largest possible first payload + */ + + if (!test_and_set_bit(CSK_TX_DATA_SENT, &csk->com.flags)) { + flowclen16 = cxgbit_send_tx_flowc_wr(csk); + csk->wr_cred -= flowclen16; + csk->wr_una_cred += flowclen16; + } + + if (csk->wr_cred < credits_needed) { + pr_debug("csk 0x%p, skb %u/%u, wr %d < %u.\n", + csk, skb->len, skb->data_len, + credits_needed, csk->wr_cred); + break; + } + __skb_unlink(skb, &csk->txq); + set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx); + skb->csum = credits_needed + flowclen16; + csk->wr_cred -= credits_needed; + csk->wr_una_cred += credits_needed; + + pr_debug("csk 0x%p, skb %u/%u, wr %d, left %u, unack %u.\n", + csk, skb->len, skb->data_len, credits_needed, + csk->wr_cred, csk->wr_una_cred); + + if (likely(cxgbit_skcb_flags(skb) & SKCBF_TX_NEED_HDR)) { + len += cxgbit_skcb_tx_extralen(skb); + + if ((csk->wr_una_cred >= (csk->wr_max_cred / 2)) || + (!before(csk->write_seq, + csk->snd_una + csk->snd_win))) { + compl = 1; + csk->wr_una_cred = 0; + } + + cxgbit_tx_data_wr(csk, skb, dlen, len, credits_needed, + compl); + csk->snd_nxt += len; + + } else if ((cxgbit_skcb_flags(skb) & SKCBF_TX_FLAG_COMPL) || + (csk->wr_una_cred >= (csk->wr_max_cred / 2))) { + struct cpl_close_con_req *req = + (struct cpl_close_con_req *)skb->data; + req->wr.wr_hi |= htonl(FW_WR_COMPL_F); + csk->wr_una_cred = 0; + } + + cxgbit_sock_enqueue_wr(csk, skb); + t4_set_arp_err_handler(skb, csk, + cxgbit_arp_failure_skb_discard); + + pr_debug("csk 0x%p,%u, skb 0x%p, %u.\n", + csk, csk->tid, skb, len); + + cxgbit_l2t_send(csk->com.cdev, skb, csk->l2t); + } +} + +static bool cxgbit_lock_sock(struct cxgbit_sock *csk) +{ + spin_lock_bh(&csk->lock); + + if (before(csk->write_seq, csk->snd_una + csk->snd_win)) + csk->lock_owner = true; + + spin_unlock_bh(&csk->lock); + + return csk->lock_owner; +} + +static void cxgbit_unlock_sock(struct cxgbit_sock *csk) +{ + struct sk_buff_head backlogq; + struct sk_buff *skb; + void (*fn)(struct cxgbit_sock *, struct sk_buff *); + + skb_queue_head_init(&backlogq); + + spin_lock_bh(&csk->lock); + while (skb_queue_len(&csk->backlogq)) { + skb_queue_splice_init(&csk->backlogq, &backlogq); + spin_unlock_bh(&csk->lock); + + while ((skb = __skb_dequeue(&backlogq))) { + fn = cxgbit_skcb_rx_backlog_fn(skb); + fn(csk, skb); + } + + spin_lock_bh(&csk->lock); + } + + csk->lock_owner = false; + spin_unlock_bh(&csk->lock); +} + +static int cxgbit_queue_skb(struct cxgbit_sock *csk, struct sk_buff *skb) +{ + int ret = 0; + + wait_event_interruptible(csk->ack_waitq, cxgbit_lock_sock(csk)); + + if (unlikely((csk->com.state != CSK_STATE_ESTABLISHED) || + signal_pending(current))) { + __kfree_skb(skb); + __skb_queue_purge(&csk->ppodq); + ret = -1; + spin_lock_bh(&csk->lock); + if (csk->lock_owner) { + spin_unlock_bh(&csk->lock); + goto unlock; + } + spin_unlock_bh(&csk->lock); + return ret; + } + + csk->write_seq += skb->len + + cxgbit_skcb_tx_extralen(skb); + + skb_queue_splice_tail_init(&csk->ppodq, &csk->txq); + __skb_queue_tail(&csk->txq, skb); + cxgbit_push_tx_frames(csk); + +unlock: + cxgbit_unlock_sock(csk); + return ret; +} + +void *cxgbit_alloc_pdu(struct iscsi_conn *conn, struct iscsi_cmd *cmd) +{ + struct cxgbit_sock *csk = conn->context; + struct cxgbit_cmd *ccmd = iscsit_priv_cmd(cmd); + struct sk_buff *skb; + static const u32 max_hdr_len = TX_HDR_LEN + ISCSI_HDR_LEN + + sizeof(struct cpl_tx_data_iso); + + skb = alloc_skb(max_hdr_len, GFP_KERNEL); + if (!skb) + return NULL; + + skb_reserve(skb, max_hdr_len); + skb_reset_transport_header(skb); + __skb_put(skb, ISCSI_HDR_LEN); + memset(skb->data, 0, ISCSI_HDR_LEN); + + cxgbit_skcb_submode(skb) = csk->submode & + CXGBIT_SUBMODE_HCRC; + cxgbit_skcb_flags(skb) |= SKCBF_TX_NEED_HDR; + + ccmd->skb = skb; + + return skb->data; +} + +static int +cxgbit_map_skb(struct iscsi_cmd *cmd, struct sk_buff *skb, u32 data_offset, + u32 data_length) +{ + u32 i = 0, nr_frags = MAX_SKB_FRAGS; + u32 padding = ((-data_length) & 3); + struct scatterlist *sg; + struct page *page; + unsigned int page_off; + + if (padding) + nr_frags--; + + /* + * We know each entry in t_data_sg contains a page. + */ + sg = &cmd->se_cmd.t_data_sg[data_offset / PAGE_SIZE]; + page_off = (data_offset % PAGE_SIZE); + + while (data_length && (i < nr_frags)) { + u32 cur_len = min_t(u32, data_length, sg->length - page_off); + + page = sg_page(sg); + + get_page(page); + skb_fill_page_desc(skb, i, page, sg->offset + page_off, + cur_len); + skb->data_len += cur_len; + skb->len += cur_len; + skb->truesize += cur_len; + + data_length -= cur_len; + page_off = 0; + sg = sg_next(sg); + i++; + } + + if (data_length) + return -1; + + if (padding) { + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!page) + return -1; + skb_fill_page_desc(skb, i, page, 0, padding); + skb->data_len += padding; + skb->len += padding; + skb->truesize += padding; + } + + return 0; +} + +static int +cxgbit_tx_datain_iso(struct cxgbit_sock *csk, struct iscsi_cmd *cmd, + struct iscsi_datain_req *dr) +{ + struct iscsi_conn *conn = csk->conn; + struct cxgbit_cmd *ccmd = iscsit_priv_cmd(cmd); + struct sk_buff *skb; + struct iscsi_datain datain; + struct cxgbit_iso_info iso_info; + u32 data_length = cmd->se_cmd.data_length; + u32 mrdsl = conn->conn_ops->MaxRecvDataSegmentLength; + u32 num_pdu, plen, tx_data = 0; + bool task_sense = !!(cmd->se_cmd.se_cmd_flags & + SCF_TRANSPORT_TASK_SENSE); + bool set_statsn = false; + int ret = -1; + + while (data_length) { + num_pdu = (data_length + mrdsl - 1) / mrdsl; + if (num_pdu > csk->max_iso_npdu) + num_pdu = csk->max_iso_npdu; + + plen = num_pdu * mrdsl; + if (plen > data_length) + plen = data_length; + + if (ccmd->skb) { + skb = ccmd->skb; + memset(skb->data, 0, ISCSI_HDR_LEN); + ccmd->skb = NULL; + } else { + skb = __cxgbit_alloc_skb(csk, 0, true); + if (!skb) + return -ENOMEM; + } + + cxgbit_skcb_flags(skb) |= SKCBF_TX_ISO; + cxgbit_skcb_submode(skb) |= (csk->submode & + CXGBIT_SUBMODE_DCRC); + cxgbit_skcb_tx_extralen(skb) = (num_pdu * + cxgbit_digest_len[cxgbit_skcb_submode(skb)]) + + ((num_pdu - 1) * ISCSI_HDR_LEN); + + memset(&datain, 0, sizeof(struct iscsi_datain)); + memset(&iso_info, 0, sizeof(iso_info)); + + if (!tx_data) + iso_info.flags |= CXGBIT_ISO_FSLICE; + + if (!(data_length - plen)) { + iso_info.flags |= CXGBIT_ISO_LSLICE; + if (!task_sense) { + datain.flags = ISCSI_FLAG_DATA_STATUS; + iscsit_increment_maxcmdsn(cmd, conn->sess); + cmd->stat_sn = conn->stat_sn++; + set_statsn = true; + } + } + + iso_info.burst_len = num_pdu * mrdsl; + iso_info.mpdu = mrdsl; + iso_info.len = ISCSI_HDR_LEN + plen; + + cxgbit_cpl_tx_data_iso(skb, &iso_info); + + datain.offset = tx_data; + datain.data_sn = cmd->data_sn - 1; + + iscsit_build_datain_pdu(cmd, conn, &datain, + (struct iscsi_data_rsp *)skb->data, + set_statsn); + + ret = cxgbit_map_skb(cmd, skb, tx_data, plen); + if (unlikely(ret)) { + __kfree_skb(skb); + goto out; + } + + ret = cxgbit_queue_skb(csk, skb); + if (unlikely(ret)) + goto out; + + tx_data += plen; + data_length -= plen; + + cmd->read_data_done += plen; + cmd->data_sn += num_pdu; + } + + dr->dr_complete = DATAIN_COMPLETE_NORMAL; + + return 0; + +out: + return ret; +} + +static int +cxgbit_tx_datain(struct cxgbit_sock *csk, struct iscsi_cmd *cmd, + struct iscsi_datain *datain) +{ + struct cxgbit_cmd *ccmd = iscsit_priv_cmd(cmd); + struct sk_buff *skb = ccmd->skb; + int ret = 0; + + ccmd->skb = NULL; + + if (datain->length) { + cxgbit_skcb_submode(skb) |= (csk->submode & + CXGBIT_SUBMODE_DCRC); + cxgbit_skcb_tx_extralen(skb) = + cxgbit_digest_len[cxgbit_skcb_submode(skb)]; + } + + ret = cxgbit_map_skb(cmd, skb, datain->offset, datain->length); + if (ret < 0) { + __kfree_skb(skb); + return ret; + } + + return cxgbit_queue_skb(csk, skb); +} + +int +cxgbit_xmit_datain_pdu(struct iscsi_conn *conn, struct iscsi_cmd *cmd, + struct iscsi_datain_req *dr, struct iscsi_datain *datain) +{ + struct cxgbit_sock *csk = conn->context; + u32 data_length = cmd->se_cmd.data_length; + u32 padding = ((-data_length) & 3); + u32 mrdsl = conn->conn_ops->MaxRecvDataSegmentLength; + + if ((data_length > mrdsl) && (!dr->recovery) && + (!padding) && (!datain->offset) && csk->max_iso_npdu) { + atomic_long_add(data_length - datain->length, + &conn->sess->tx_data_octets); + return cxgbit_tx_datain_iso(csk, cmd, dr); + } + + return cxgbit_tx_datain(csk, cmd, datain); +} + +int +cxgbit_xmit_pdu(struct iscsi_conn *conn, struct iscsi_cmd *cmd, + const void *data_buf, u32 data_buf_len) +{ + struct cxgbit_sock *csk = conn->context; + struct cxgbit_cmd *ccmd = iscsit_priv_cmd(cmd); + struct sk_buff *skb = ccmd->skb; + + ccmd->skb = NULL; + + if (data_buf_len) { + u32 padding = ((-data_buf_len) & 3); + u32 nr_frags = DIV_ROUND_UP(data_buf_len + + padding, PAGE_SIZE); + u32 pad_bytes = 0; + u8 i; + + for (i = 0; i < nr_frags; i++) { + struct page *page; + + page = alloc_page(GFP_KERNEL); + if (!page) { + __kfree_skb(skb); + return -ENOMEM; + } + + skb_fill_page_desc(skb, i, page, 0, PAGE_SIZE); + skb->truesize += PAGE_SIZE; + } + + skb->data_len = data_buf_len + padding; + skb->len += skb->data_len; + + skb_store_bits(skb, ISCSI_HDR_LEN, data_buf, data_buf_len); + + if (padding) + skb_store_bits(skb, ISCSI_HDR_LEN + data_buf_len, + &pad_bytes, padding); + + cxgbit_skcb_submode(skb) |= (csk->submode & + CXGBIT_SUBMODE_DCRC); + } + + cxgbit_skcb_tx_extralen(skb) = cxgbit_digest_len[ + cxgbit_skcb_submode(skb)]; + + return cxgbit_queue_skb(csk, skb); +} + +int cxgbit_validate_params(struct iscsi_conn *conn) +{ + struct cxgbit_sock *csk = conn->context; + struct cxgbit_device *cdev = csk->com.cdev; + struct iscsi_param *param; + u32 max_xmitdsl; + + param = iscsi_find_param_from_key(MAXXMITDATASEGMENTLENGTH, + conn->param_list); + if (!param) + return -1; + + if (kstrtou32(param->value, 0, &max_xmitdsl) < 0) + return -1; + + if (max_xmitdsl > cdev->mdsl) { + if (iscsi_change_param_sprintf + (conn, "MaxXmitDataSegmentLength=%u", + cdev->mdsl)) + return -1; + } + + return 0; +} + +static int cxgbit_set_digest(struct cxgbit_sock *csk) +{ + struct iscsi_conn *conn = csk->conn; + struct iscsi_param *param; + + param = iscsi_find_param_from_key(HEADERDIGEST, conn->param_list); + if (!param) { + pr_err("param not found key %s\n", HEADERDIGEST); + return -1; + } + + if (!strcmp(param->value, CRC32C)) + csk->submode |= CXGBIT_SUBMODE_HCRC; + + param = iscsi_find_param_from_key(DATADIGEST, conn->param_list); + if (!param) { + csk->submode = 0; + pr_err("param not found key %s\n", DATADIGEST); + return -1; + } + + if (!strcmp(param->value, CRC32C)) + csk->submode |= CXGBIT_SUBMODE_DCRC; + + if (cxgbit_setup_conn_digest(csk)) { + csk->submode = 0; + return -1; + } + + return 0; +} + +static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk) +{ + struct iscsi_conn *conn = csk->conn; + struct iscsi_conn_ops *conn_ops = conn->conn_ops; + struct iscsi_param *param; + u32 mrdsl, mbl; + u32 max_npdu, max_iso_npdu; + + if (conn->login->leading_connection) { + param = iscsi_find_param_from_key(DATASEQUENCEINORDER, + conn->param_list); + if (!param) { + pr_err("param not found key %s\n", DATASEQUENCEINORDER); + return -1; + } + + if (strcmp(param->value, YES)) + return 0; + + param = iscsi_find_param_from_key(DATAPDUINORDER, + conn->param_list); + if (!param) { + pr_err("param not found key %s\n", DATAPDUINORDER); + return -1; + } + + if (strcmp(param->value, YES)) + return 0; + + param = iscsi_find_param_from_key(MAXBURSTLENGTH, + conn->param_list); + if (!param) { + pr_err("param not found key %s\n", MAXBURSTLENGTH); + return -1; + } + + if (kstrtou32(param->value, 0, &mbl) < 0) + return -1; + } else { + if (!conn->sess->sess_ops->DataSequenceInOrder) + return 0; + if (!conn->sess->sess_ops->DataPDUInOrder) + return 0; + + mbl = conn->sess->sess_ops->MaxBurstLength; + } + + mrdsl = conn_ops->MaxRecvDataSegmentLength; + max_npdu = mbl / mrdsl; + + max_iso_npdu = CXGBIT_MAX_ISO_PAYLOAD / + (ISCSI_HDR_LEN + mrdsl + + cxgbit_digest_len[csk->submode]); + + csk->max_iso_npdu = min(max_npdu, max_iso_npdu); + + if (csk->max_iso_npdu <= 1) + csk->max_iso_npdu = 0; + + return 0; +} + +static int cxgbit_set_params(struct iscsi_conn *conn) +{ + struct cxgbit_sock *csk = conn->context; + struct cxgbit_device *cdev = csk->com.cdev; + struct cxgbi_ppm *ppm = *csk->com.cdev->lldi.iscsi_ppm; + struct iscsi_conn_ops *conn_ops = conn->conn_ops; + struct iscsi_param *param; + u8 erl; + + if (conn_ops->MaxRecvDataSegmentLength > cdev->mdsl) + conn_ops->MaxRecvDataSegmentLength = cdev->mdsl; + + if (conn->login->leading_connection) { + param = iscsi_find_param_from_key(ERRORRECOVERYLEVEL, + conn->param_list); + if (!param) { + pr_err("param not found key %s\n", ERRORRECOVERYLEVEL); + return -1; + } + if (kstrtou8(param->value, 0, &erl) < 0) + return -1; + } else { + erl = conn->sess->sess_ops->ErrorRecoveryLevel; + } + + if (!erl) { + if (test_bit(CDEV_ISO_ENABLE, &cdev->flags)) { + if (cxgbit_set_iso_npdu(csk)) + return -1; + } + + if (test_bit(CDEV_DDP_ENABLE, &cdev->flags)) { + if (cxgbit_setup_conn_pgidx(csk, + ppm->tformat.pgsz_idx_dflt)) + return -1; + set_bit(CSK_DDP_ENABLE, &csk->com.flags); + } + } + + if (cxgbit_set_digest(csk)) + return -1; + + return 0; +} + +int +cxgbit_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login, + u32 length) +{ + struct cxgbit_sock *csk = conn->context; + struct sk_buff *skb; + u32 padding_buf = 0; + u8 padding = ((-length) & 3); + + skb = cxgbit_alloc_skb(csk, length + padding); + if (!skb) + return -ENOMEM; + skb_store_bits(skb, 0, login->rsp, ISCSI_HDR_LEN); + skb_store_bits(skb, ISCSI_HDR_LEN, login->rsp_buf, length); + + if (padding) + skb_store_bits(skb, ISCSI_HDR_LEN + length, + &padding_buf, padding); + + if (login->login_complete) { + if (cxgbit_set_params(conn)) { + kfree_skb(skb); + return -1; + } + + set_bit(CSK_LOGIN_DONE, &csk->com.flags); + } + + if (cxgbit_queue_skb(csk, skb)) + return -1; + + if ((!login->login_complete) && (!login->login_failed)) + schedule_delayed_work(&conn->login_work, 0); + + return 0; +} + +static void +cxgbit_skb_copy_to_sg(struct sk_buff *skb, struct scatterlist *sg, + unsigned int nents) +{ + struct skb_seq_state st; + const u8 *buf; + unsigned int consumed = 0, buf_len; + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(skb); + + skb_prepare_seq_read(skb, pdu_cb->doffset, + pdu_cb->doffset + pdu_cb->dlen, + &st); + + while (true) { + buf_len = skb_seq_read(consumed, &buf, &st); + if (!buf_len) { + skb_abort_seq_read(&st); + break; + } + + consumed += sg_pcopy_from_buffer(sg, nents, (void *)buf, + buf_len, consumed); + } +} + +static struct iscsi_cmd *cxgbit_allocate_cmd(struct cxgbit_sock *csk) +{ + struct iscsi_conn *conn = csk->conn; + struct cxgbi_ppm *ppm = cdev2ppm(csk->com.cdev); + struct cxgbit_cmd *ccmd; + struct iscsi_cmd *cmd; + + cmd = iscsit_allocate_cmd(conn, TASK_INTERRUPTIBLE); + if (!cmd) { + pr_err("Unable to allocate iscsi_cmd + cxgbit_cmd\n"); + return NULL; + } + + ccmd = iscsit_priv_cmd(cmd); + ccmd->ttinfo.tag = ppm->tformat.no_ddp_mask; + ccmd->setup_ddp = true; + + return cmd; +} + +static int +cxgbit_handle_immediate_data(struct iscsi_cmd *cmd, struct iscsi_scsi_req *hdr, + u32 length) +{ + struct iscsi_conn *conn = cmd->conn; + struct cxgbit_sock *csk = conn->context; + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb); + + if (pdu_cb->flags & PDUCBF_RX_DCRC_ERR) { + pr_err("ImmediateData CRC32C DataDigest error\n"); + if (!conn->sess->sess_ops->ErrorRecoveryLevel) { + pr_err("Unable to recover from" + " Immediate Data digest failure while" + " in ERL=0.\n"); + iscsit_reject_cmd(cmd, ISCSI_REASON_DATA_DIGEST_ERROR, + (unsigned char *)hdr); + return IMMEDIATE_DATA_CANNOT_RECOVER; + } + + iscsit_reject_cmd(cmd, ISCSI_REASON_DATA_DIGEST_ERROR, + (unsigned char *)hdr); + return IMMEDIATE_DATA_ERL1_CRC_FAILURE; + } + + if (cmd->se_cmd.se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC) { + struct cxgbit_cmd *ccmd = iscsit_priv_cmd(cmd); + struct skb_shared_info *ssi = skb_shinfo(csk->skb); + skb_frag_t *dfrag = &ssi->frags[pdu_cb->dfrag_idx]; + + sg_init_table(&ccmd->sg, 1); + sg_set_page(&ccmd->sg, dfrag->page.p, skb_frag_size(dfrag), + dfrag->page_offset); + get_page(dfrag->page.p); + + cmd->se_cmd.t_data_sg = &ccmd->sg; + cmd->se_cmd.t_data_nents = 1; + + ccmd->release = true; + } else { + struct scatterlist *sg = &cmd->se_cmd.t_data_sg[0]; + u32 sg_nents = max(1UL, DIV_ROUND_UP(pdu_cb->dlen, PAGE_SIZE)); + + cxgbit_skb_copy_to_sg(csk->skb, sg, sg_nents); + } + + cmd->write_data_done += pdu_cb->dlen; + + if (cmd->write_data_done == cmd->se_cmd.data_length) { + spin_lock_bh(&cmd->istate_lock); + cmd->cmd_flags |= ICF_GOT_LAST_DATAOUT; + cmd->i_state = ISTATE_RECEIVED_LAST_DATAOUT; + spin_unlock_bh(&cmd->istate_lock); + } + + return IMMEDIATE_DATA_NORMAL_OPERATION; +} + +static int +cxgbit_get_immediate_data(struct iscsi_cmd *cmd, struct iscsi_scsi_req *hdr, + bool dump_payload) +{ + struct iscsi_conn *conn = cmd->conn; + int cmdsn_ret = 0, immed_ret = IMMEDIATE_DATA_NORMAL_OPERATION; + /* + * Special case for Unsupported SAM WRITE Opcodes and ImmediateData=Yes. + */ + if (dump_payload) + goto after_immediate_data; + + immed_ret = cxgbit_handle_immediate_data(cmd, hdr, + cmd->first_burst_len); +after_immediate_data: + if (immed_ret == IMMEDIATE_DATA_NORMAL_OPERATION) { + /* + * A PDU/CmdSN carrying Immediate Data passed + * DataCRC, check against ExpCmdSN/MaxCmdSN if + * Immediate Bit is not set. + */ + cmdsn_ret = iscsit_sequence_cmd(conn, cmd, + (unsigned char *)hdr, + hdr->cmdsn); + if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER) + return -1; + + if (cmd->sense_reason || cmdsn_ret == CMDSN_LOWER_THAN_EXP) { + target_put_sess_cmd(&cmd->se_cmd); + return 0; + } else if (cmd->unsolicited_data) { + iscsit_set_unsoliticed_dataout(cmd); + } + + } else if (immed_ret == IMMEDIATE_DATA_ERL1_CRC_FAILURE) { + /* + * Immediate Data failed DataCRC and ERL>=1, + * silently drop this PDU and let the initiator + * plug the CmdSN gap. + * + * FIXME: Send Unsolicited NOPIN with reserved + * TTT here to help the initiator figure out + * the missing CmdSN, although they should be + * intelligent enough to determine the missing + * CmdSN and issue a retry to plug the sequence. + */ + cmd->i_state = ISTATE_REMOVE; + iscsit_add_cmd_to_immediate_queue(cmd, conn, cmd->i_state); + } else /* immed_ret == IMMEDIATE_DATA_CANNOT_RECOVER */ + return -1; + + return 0; +} + +static int +cxgbit_handle_scsi_cmd(struct cxgbit_sock *csk, struct iscsi_cmd *cmd) +{ + struct iscsi_conn *conn = csk->conn; + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb); + struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)pdu_cb->hdr; + int rc; + bool dump_payload = false; + + rc = iscsit_setup_scsi_cmd(conn, cmd, (unsigned char *)hdr); + if (rc < 0) + return rc; + + if (pdu_cb->dlen && (pdu_cb->dlen == cmd->se_cmd.data_length) && + (pdu_cb->nr_dfrags == 1)) + cmd->se_cmd.se_cmd_flags |= SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC; + + rc = iscsit_process_scsi_cmd(conn, cmd, hdr); + if (rc < 0) + return 0; + else if (rc > 0) + dump_payload = true; + + if (!pdu_cb->dlen) + return 0; + + return cxgbit_get_immediate_data(cmd, hdr, dump_payload); +} + +static int cxgbit_handle_iscsi_dataout(struct cxgbit_sock *csk) +{ + struct scatterlist *sg_start; + struct iscsi_conn *conn = csk->conn; + struct iscsi_cmd *cmd = NULL; + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb); + struct iscsi_data *hdr = (struct iscsi_data *)pdu_cb->hdr; + u32 data_offset = be32_to_cpu(hdr->offset); + u32 data_len = pdu_cb->dlen; + int rc, sg_nents, sg_off; + bool dcrc_err = false; + + rc = iscsit_check_dataout_hdr(conn, (unsigned char *)hdr, &cmd); + if (rc < 0) + return rc; + else if (!cmd) + return 0; + + if (pdu_cb->flags & PDUCBF_RX_DCRC_ERR) { + pr_err("ITT: 0x%08x, Offset: %u, Length: %u," + " DataSN: 0x%08x\n", + hdr->itt, hdr->offset, data_len, + hdr->datasn); + + dcrc_err = true; + goto check_payload; + } + + pr_debug("DataOut data_len: %u, " + "write_data_done: %u, data_length: %u\n", + data_len, cmd->write_data_done, + cmd->se_cmd.data_length); + + if (!(pdu_cb->flags & PDUCBF_RX_DATA_DDPD)) { + sg_off = data_offset / PAGE_SIZE; + sg_start = &cmd->se_cmd.t_data_sg[sg_off]; + sg_nents = max(1UL, DIV_ROUND_UP(data_len, PAGE_SIZE)); + + cxgbit_skb_copy_to_sg(csk->skb, sg_start, sg_nents); + } + +check_payload: + + rc = iscsit_check_dataout_payload(cmd, hdr, dcrc_err); + if (rc < 0) + return rc; + + return 0; +} + +static int cxgbit_handle_nop_out(struct cxgbit_sock *csk, struct iscsi_cmd *cmd) +{ + struct iscsi_conn *conn = csk->conn; + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb); + struct iscsi_nopout *hdr = (struct iscsi_nopout *)pdu_cb->hdr; + unsigned char *ping_data = NULL; + u32 payload_length = pdu_cb->dlen; + int ret; + + ret = iscsit_setup_nop_out(conn, cmd, hdr); + if (ret < 0) + return 0; + + if (pdu_cb->flags & PDUCBF_RX_DCRC_ERR) { + if (!conn->sess->sess_ops->ErrorRecoveryLevel) { + pr_err("Unable to recover from" + " NOPOUT Ping DataCRC failure while in" + " ERL=0.\n"); + ret = -1; + goto out; + } else { + /* + * drop this PDU and let the + * initiator plug the CmdSN gap. + */ + pr_info("Dropping NOPOUT" + " Command CmdSN: 0x%08x due to" + " DataCRC error.\n", hdr->cmdsn); + ret = 0; + goto out; + } + } + + /* + * Handle NOP-OUT payload for traditional iSCSI sockets + */ + if (payload_length && hdr->ttt == cpu_to_be32(0xFFFFFFFF)) { + ping_data = kzalloc(payload_length + 1, GFP_KERNEL); + if (!ping_data) { + pr_err("Unable to allocate memory for" + " NOPOUT ping data.\n"); + ret = -1; + goto out; + } + + skb_copy_bits(csk->skb, pdu_cb->doffset, + ping_data, payload_length); + + ping_data[payload_length] = '\0'; + /* + * Attach ping data to struct iscsi_cmd->buf_ptr. + */ + cmd->buf_ptr = ping_data; + cmd->buf_ptr_size = payload_length; + + pr_debug("Got %u bytes of NOPOUT ping" + " data.\n", payload_length); + pr_debug("Ping Data: \"%s\"\n", ping_data); + } + + return iscsit_process_nop_out(conn, cmd, hdr); +out: + if (cmd) + iscsit_free_cmd(cmd, false); + return ret; +} + +static int +cxgbit_handle_text_cmd(struct cxgbit_sock *csk, struct iscsi_cmd *cmd) +{ + struct iscsi_conn *conn = csk->conn; + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb); + struct iscsi_text *hdr = (struct iscsi_text *)pdu_cb->hdr; + u32 payload_length = pdu_cb->dlen; + int rc; + unsigned char *text_in = NULL; + + rc = iscsit_setup_text_cmd(conn, cmd, hdr); + if (rc < 0) + return rc; + + if (pdu_cb->flags & PDUCBF_RX_DCRC_ERR) { + if (!conn->sess->sess_ops->ErrorRecoveryLevel) { + pr_err("Unable to recover from" + " Text Data digest failure while in" + " ERL=0.\n"); + goto reject; + } else { + /* + * drop this PDU and let the + * initiator plug the CmdSN gap. + */ + pr_info("Dropping Text" + " Command CmdSN: 0x%08x due to" + " DataCRC error.\n", hdr->cmdsn); + return 0; + } + } + + if (payload_length) { + text_in = kzalloc(payload_length, GFP_KERNEL); + if (!text_in) { + pr_err("Unable to allocate text_in of payload_length: %u\n", + payload_length); + return -ENOMEM; + } + skb_copy_bits(csk->skb, pdu_cb->doffset, + text_in, payload_length); + + text_in[payload_length - 1] = '\0'; + + cmd->text_in_ptr = text_in; + } + + return iscsit_process_text_cmd(conn, cmd, hdr); + +reject: + return iscsit_reject_cmd(cmd, ISCSI_REASON_PROTOCOL_ERROR, + pdu_cb->hdr); +} + +static int cxgbit_target_rx_opcode(struct cxgbit_sock *csk) +{ + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb); + struct iscsi_hdr *hdr = (struct iscsi_hdr *)pdu_cb->hdr; + struct iscsi_conn *conn = csk->conn; + struct iscsi_cmd *cmd = NULL; + u8 opcode = (hdr->opcode & ISCSI_OPCODE_MASK); + int ret = -EINVAL; + + switch (opcode) { + case ISCSI_OP_SCSI_CMD: + cmd = cxgbit_allocate_cmd(csk); + if (!cmd) + goto reject; + + ret = cxgbit_handle_scsi_cmd(csk, cmd); + break; + case ISCSI_OP_SCSI_DATA_OUT: + ret = cxgbit_handle_iscsi_dataout(csk); + break; + case ISCSI_OP_NOOP_OUT: + if (hdr->ttt == cpu_to_be32(0xFFFFFFFF)) { + cmd = cxgbit_allocate_cmd(csk); + if (!cmd) + goto reject; + } + + ret = cxgbit_handle_nop_out(csk, cmd); + break; + case ISCSI_OP_SCSI_TMFUNC: + cmd = cxgbit_allocate_cmd(csk); + if (!cmd) + goto reject; + + ret = iscsit_handle_task_mgt_cmd(conn, cmd, + (unsigned char *)hdr); + break; + case ISCSI_OP_TEXT: + if (hdr->ttt != cpu_to_be32(0xFFFFFFFF)) { + cmd = iscsit_find_cmd_from_itt(conn, hdr->itt); + if (!cmd) + goto reject; + } else { + cmd = cxgbit_allocate_cmd(csk); + if (!cmd) + goto reject; + } + + ret = cxgbit_handle_text_cmd(csk, cmd); + break; + case ISCSI_OP_LOGOUT: + cmd = cxgbit_allocate_cmd(csk); + if (!cmd) + goto reject; + + ret = iscsit_handle_logout_cmd(conn, cmd, (unsigned char *)hdr); + if (ret > 0) + wait_for_completion_timeout(&conn->conn_logout_comp, + SECONDS_FOR_LOGOUT_COMP + * HZ); + break; + case ISCSI_OP_SNACK: + ret = iscsit_handle_snack(conn, (unsigned char *)hdr); + break; + default: + pr_err("Got unknown iSCSI OpCode: 0x%02x\n", opcode); + dump_stack(); + break; + } + + return ret; + +reject: + return iscsit_add_reject(conn, ISCSI_REASON_BOOKMARK_NO_RESOURCES, + (unsigned char *)hdr); + return ret; +} + +static int cxgbit_rx_opcode(struct cxgbit_sock *csk) +{ + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb); + struct iscsi_conn *conn = csk->conn; + struct iscsi_hdr *hdr = pdu_cb->hdr; + u8 opcode; + + if (pdu_cb->flags & PDUCBF_RX_HCRC_ERR) { + atomic_long_inc(&conn->sess->conn_digest_errors); + goto transport_err; + } + + if (conn->conn_state == TARG_CONN_STATE_IN_LOGOUT) + goto transport_err; + + opcode = hdr->opcode & ISCSI_OPCODE_MASK; + + if (conn->sess->sess_ops->SessionType && + ((!(opcode & ISCSI_OP_TEXT)) || + (!(opcode & ISCSI_OP_LOGOUT)))) { + pr_err("Received illegal iSCSI Opcode: 0x%02x" + " while in Discovery Session, rejecting.\n", opcode); + iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR, + (unsigned char *)hdr); + goto transport_err; + } + + if (cxgbit_target_rx_opcode(csk) < 0) + goto transport_err; + + return 0; + +transport_err: + return -1; +} + +static int cxgbit_rx_login_pdu(struct cxgbit_sock *csk) +{ + struct iscsi_conn *conn = csk->conn; + struct iscsi_login *login = conn->login; + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_rx_pdu_cb(csk->skb); + struct iscsi_login_req *login_req; + + login_req = (struct iscsi_login_req *)login->req; + memcpy(login_req, pdu_cb->hdr, sizeof(*login_req)); + + pr_debug("Got Login Command, Flags 0x%02x, ITT: 0x%08x," + " CmdSN: 0x%08x, ExpStatSN: 0x%08x, CID: %hu, Length: %u\n", + login_req->flags, login_req->itt, login_req->cmdsn, + login_req->exp_statsn, login_req->cid, pdu_cb->dlen); + /* + * Setup the initial iscsi_login values from the leading + * login request PDU. + */ + if (login->first_request) { + login_req = (struct iscsi_login_req *)login->req; + login->leading_connection = (!login_req->tsih) ? 1 : 0; + login->current_stage = ISCSI_LOGIN_CURRENT_STAGE( + login_req->flags); + login->version_min = login_req->min_version; + login->version_max = login_req->max_version; + memcpy(login->isid, login_req->isid, 6); + login->cmd_sn = be32_to_cpu(login_req->cmdsn); + login->init_task_tag = login_req->itt; + login->initial_exp_statsn = be32_to_cpu(login_req->exp_statsn); + login->cid = be16_to_cpu(login_req->cid); + login->tsih = be16_to_cpu(login_req->tsih); + } + + if (iscsi_target_check_login_request(conn, login) < 0) + return -1; + + memset(login->req_buf, 0, MAX_KEY_VALUE_PAIRS); + skb_copy_bits(csk->skb, pdu_cb->doffset, login->req_buf, pdu_cb->dlen); + + return 0; +} + +static int +cxgbit_process_iscsi_pdu(struct cxgbit_sock *csk, struct sk_buff *skb, int idx) +{ + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb, idx); + int ret; + + cxgbit_rx_pdu_cb(skb) = pdu_cb; + + csk->skb = skb; + + if (!test_bit(CSK_LOGIN_DONE, &csk->com.flags)) { + ret = cxgbit_rx_login_pdu(csk); + set_bit(CSK_LOGIN_PDU_DONE, &csk->com.flags); + } else { + ret = cxgbit_rx_opcode(csk); + } + + return ret; +} + +static void cxgbit_lro_skb_dump(struct sk_buff *skb) +{ + struct skb_shared_info *ssi = skb_shinfo(skb); + struct cxgbit_lro_cb *lro_cb = cxgbit_skb_lro_cb(skb); + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb, 0); + u8 i; + + pr_info("skb 0x%p, head 0x%p, 0x%p, len %u,%u, frags %u.\n", + skb, skb->head, skb->data, skb->len, skb->data_len, + ssi->nr_frags); + pr_info("skb 0x%p, lro_cb, csk 0x%p, pdu %u, %u.\n", + skb, lro_cb->csk, lro_cb->pdu_idx, lro_cb->pdu_totallen); + + for (i = 0; i < lro_cb->pdu_idx; i++, pdu_cb++) + pr_info("skb 0x%p, pdu %d, %u, f 0x%x, seq 0x%x, dcrc 0x%x, " + "frags %u.\n", + skb, i, pdu_cb->pdulen, pdu_cb->flags, pdu_cb->seq, + pdu_cb->ddigest, pdu_cb->frags); + for (i = 0; i < ssi->nr_frags; i++) + pr_info("skb 0x%p, frag %d, off %u, sz %u.\n", + skb, i, ssi->frags[i].page_offset, ssi->frags[i].size); +} + +static void cxgbit_lro_hskb_reset(struct cxgbit_sock *csk) +{ + struct sk_buff *skb = csk->lro_hskb; + struct skb_shared_info *ssi = skb_shinfo(skb); + u8 i; + + memset(skb->data, 0, LRO_SKB_MIN_HEADROOM); + for (i = 0; i < ssi->nr_frags; i++) + put_page(skb_frag_page(&ssi->frags[i])); + ssi->nr_frags = 0; +} + +static void +cxgbit_lro_skb_merge(struct cxgbit_sock *csk, struct sk_buff *skb, u8 pdu_idx) +{ + struct sk_buff *hskb = csk->lro_hskb; + struct cxgbit_lro_pdu_cb *hpdu_cb = cxgbit_skb_lro_pdu_cb(hskb, 0); + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb, pdu_idx); + struct skb_shared_info *hssi = skb_shinfo(hskb); + struct skb_shared_info *ssi = skb_shinfo(skb); + unsigned int len = 0; + + if (pdu_cb->flags & PDUCBF_RX_HDR) { + hpdu_cb->flags = pdu_cb->flags; + hpdu_cb->seq = pdu_cb->seq; + hpdu_cb->hdr = pdu_cb->hdr; + hpdu_cb->hlen = pdu_cb->hlen; + + memcpy(&hssi->frags[0], &ssi->frags[pdu_cb->hfrag_idx], + sizeof(skb_frag_t)); + + get_page(skb_frag_page(&hssi->frags[0])); + hssi->nr_frags = 1; + hpdu_cb->frags = 1; + hpdu_cb->hfrag_idx = 0; + + len = hssi->frags[0].size; + hskb->len = len; + hskb->data_len = len; + hskb->truesize = len; + } + + if (pdu_cb->flags & PDUCBF_RX_DATA) { + u8 hfrag_idx = 1, i; + + hpdu_cb->flags |= pdu_cb->flags; + + len = 0; + for (i = 0; i < pdu_cb->nr_dfrags; hfrag_idx++, i++) { + memcpy(&hssi->frags[hfrag_idx], + &ssi->frags[pdu_cb->dfrag_idx + i], + sizeof(skb_frag_t)); + + get_page(skb_frag_page(&hssi->frags[hfrag_idx])); + + len += hssi->frags[hfrag_idx].size; + + hssi->nr_frags++; + hpdu_cb->frags++; + } + + hpdu_cb->dlen = pdu_cb->dlen; + hpdu_cb->doffset = hpdu_cb->hlen; + hpdu_cb->nr_dfrags = pdu_cb->nr_dfrags; + hpdu_cb->dfrag_idx = 1; + hskb->len += len; + hskb->data_len += len; + hskb->truesize += len; + } + + if (pdu_cb->flags & PDUCBF_RX_STATUS) { + hpdu_cb->flags |= pdu_cb->flags; + + if (hpdu_cb->flags & PDUCBF_RX_DATA) + hpdu_cb->flags &= ~PDUCBF_RX_DATA_DDPD; + + hpdu_cb->ddigest = pdu_cb->ddigest; + hpdu_cb->pdulen = pdu_cb->pdulen; + } +} + +static int cxgbit_process_lro_skb(struct cxgbit_sock *csk, struct sk_buff *skb) +{ + struct cxgbit_lro_cb *lro_cb = cxgbit_skb_lro_cb(skb); + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb, 0); + u8 pdu_idx = 0, last_idx = 0; + int ret = 0; + + if (!pdu_cb->complete) { + cxgbit_lro_skb_merge(csk, skb, 0); + + if (pdu_cb->flags & PDUCBF_RX_STATUS) { + struct sk_buff *hskb = csk->lro_hskb; + + ret = cxgbit_process_iscsi_pdu(csk, hskb, 0); + + cxgbit_lro_hskb_reset(csk); + + if (ret < 0) + goto out; + } + + pdu_idx = 1; + } + + if (lro_cb->pdu_idx) + last_idx = lro_cb->pdu_idx - 1; + + for (; pdu_idx <= last_idx; pdu_idx++) { + ret = cxgbit_process_iscsi_pdu(csk, skb, pdu_idx); + if (ret < 0) + goto out; + } + + if ((!lro_cb->complete) && lro_cb->pdu_idx) + cxgbit_lro_skb_merge(csk, skb, lro_cb->pdu_idx); + +out: + return ret; +} + +static int cxgbit_rx_lro_skb(struct cxgbit_sock *csk, struct sk_buff *skb) +{ + struct cxgbit_lro_cb *lro_cb = cxgbit_skb_lro_cb(skb); + struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb, 0); + int ret = -1; + + if ((pdu_cb->flags & PDUCBF_RX_HDR) && + (pdu_cb->seq != csk->rcv_nxt)) { + pr_info("csk 0x%p, tid 0x%x, seq 0x%x != 0x%x.\n", + csk, csk->tid, pdu_cb->seq, csk->rcv_nxt); + cxgbit_lro_skb_dump(skb); + return ret; + } + + csk->rcv_nxt += lro_cb->pdu_totallen; + + ret = cxgbit_process_lro_skb(csk, skb); + + csk->rx_credits += lro_cb->pdu_totallen; + + if (csk->rx_credits >= (csk->rcv_win / 4)) + cxgbit_rx_data_ack(csk); + + return ret; +} + +static int cxgbit_rx_skb(struct cxgbit_sock *csk, struct sk_buff *skb) +{ + int ret = -1; + + if (likely(cxgbit_skcb_flags(skb) & SKCBF_RX_LRO)) + ret = cxgbit_rx_lro_skb(csk, skb); + + __kfree_skb(skb); + return ret; +} + +static bool cxgbit_rxq_len(struct cxgbit_sock *csk, struct sk_buff_head *rxq) +{ + spin_lock_bh(&csk->rxq.lock); + if (skb_queue_len(&csk->rxq)) { + skb_queue_splice_init(&csk->rxq, rxq); + spin_unlock_bh(&csk->rxq.lock); + return true; + } + spin_unlock_bh(&csk->rxq.lock); + return false; +} + +static int cxgbit_wait_rxq(struct cxgbit_sock *csk) +{ + struct sk_buff *skb; + struct sk_buff_head rxq; + + skb_queue_head_init(&rxq); + + wait_event_interruptible(csk->waitq, cxgbit_rxq_len(csk, &rxq)); + + if (signal_pending(current)) + goto out; + + while ((skb = __skb_dequeue(&rxq))) { + if (cxgbit_rx_skb(csk, skb)) + goto out; + } + + return 0; +out: + __skb_queue_purge(&rxq); + return -1; +} + +int cxgbit_get_login_rx(struct iscsi_conn *conn, struct iscsi_login *login) +{ + struct cxgbit_sock *csk = conn->context; + int ret = -1; + + while (!test_and_clear_bit(CSK_LOGIN_PDU_DONE, &csk->com.flags)) { + ret = cxgbit_wait_rxq(csk); + if (ret) { + clear_bit(CSK_LOGIN_PDU_DONE, &csk->com.flags); + break; + } + } + + return ret; +} + +void cxgbit_get_rx_pdu(struct iscsi_conn *conn) +{ + struct cxgbit_sock *csk = conn->context; + + while (!kthread_should_stop()) { + iscsit_thread_check_cpumask(conn, current, 0); + if (cxgbit_wait_rxq(csk)) + return; + } +} -- 2.0.2 -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html