diff options
| -rw-r--r-- | Documentation/scsi/cxgb3i.txt | 85 | ||||
| -rw-r--r-- | drivers/scsi/Kconfig | 2 | ||||
| -rw-r--r-- | drivers/scsi/Makefile | 1 | ||||
| -rw-r--r-- | drivers/scsi/cxgb3i/Kbuild | 4 | ||||
| -rw-r--r-- | drivers/scsi/cxgb3i/Kconfig | 6 | ||||
| -rw-r--r-- | drivers/scsi/cxgb3i/cxgb3i.h | 139 | ||||
| -rw-r--r-- | drivers/scsi/cxgb3i/cxgb3i_ddp.c | 770 | ||||
| -rw-r--r-- | drivers/scsi/cxgb3i/cxgb3i_ddp.h | 306 | ||||
| -rw-r--r-- | drivers/scsi/cxgb3i/cxgb3i_init.c | 107 | ||||
| -rw-r--r-- | drivers/scsi/cxgb3i/cxgb3i_iscsi.c | 951 | ||||
| -rw-r--r-- | drivers/scsi/cxgb3i/cxgb3i_offload.c | 1810 | ||||
| -rw-r--r-- | drivers/scsi/cxgb3i/cxgb3i_offload.h | 231 | ||||
| -rw-r--r-- | drivers/scsi/cxgb3i/cxgb3i_pdu.c | 402 | ||||
| -rw-r--r-- | drivers/scsi/cxgb3i/cxgb3i_pdu.h | 59 |
14 files changed, 4873 insertions, 0 deletions
diff --git a/Documentation/scsi/cxgb3i.txt b/Documentation/scsi/cxgb3i.txt new file mode 100644 index 00000000000..8141fa01978 --- /dev/null +++ b/Documentation/scsi/cxgb3i.txt @@ -0,0 +1,85 @@ +Chelsio S3 iSCSI Driver for Linux + +Introduction +============ + +The Chelsio T3 ASIC based Adapters (S310, S320, S302, S304, Mezz cards, etc. +series of products) supports iSCSI acceleration and iSCSI Direct Data Placement +(DDP) where the hardware handles the expensive byte touching operations, such +as CRC computation and verification, and direct DMA to the final host memory +destination: + + - iSCSI PDU digest generation and verification + + On transmitting, Chelsio S3 h/w computes and inserts the Header and + Data digest into the PDUs. + On receiving, Chelsio S3 h/w computes and verifies the Header and + Data digest of the PDUs. + + - Direct Data Placement (DDP) + + S3 h/w can directly place the iSCSI Data-In or Data-Out PDU's + payload into pre-posted final destination host-memory buffers based + on the Initiator Task Tag (ITT) in Data-In or Target Task Tag (TTT) + in Data-Out PDUs. + + - PDU Transmit and Recovery + + On transmitting, S3 h/w accepts the complete PDU (header + data) + from the host driver, computes and inserts the digests, decomposes + the PDU into multiple TCP segments if necessary, and transmit all + the TCP segments onto the wire. It handles TCP retransmission if + needed. + + On receving, S3 h/w recovers the iSCSI PDU by reassembling TCP + segments, separating the header and data, calculating and verifying + the digests, then forwards the header to the host. The payload data, + if possible, will be directly placed into the pre-posted host DDP + buffer. Otherwise, the payload data will be sent to the host too. + +The cxgb3i driver interfaces with open-iscsi initiator and provides the iSCSI +acceleration through Chelsio hardware wherever applicable. + +Using the cxgb3i Driver +======================= + +The following steps need to be taken to accelerates the open-iscsi initiator: + +1. Load the cxgb3i driver: "modprobe cxgb3i" + + The cxgb3i module registers a new transport class "cxgb3i" with open-iscsi. + + * in the case of recompiling the kernel, the cxgb3i selection is located at + Device Drivers + SCSI device support ---> + [*] SCSI low-level drivers ---> + <M> Chelsio S3xx iSCSI support + +2. Create an interface file located under /etc/iscsi/ifaces/ for the new + transport class "cxgb3i". + + The content of the file should be in the following format: + iface.transport_name = cxgb3i + iface.net_ifacename = <ethX> + iface.ipaddress = <iscsi ip address> + + * if iface.ipaddress is specified, <iscsi ip address> needs to be either the + same as the ethX's ip address or an address on the same subnet. Make + sure the ip address is unique in the network. + +3. edit /etc/iscsi/iscsid.conf + The default setting for MaxRecvDataSegmentLength (131072) is too big, + replace "node.conn[0].iscsi.MaxRecvDataSegmentLength" to be a value no + bigger than 15360 (for example 8192): + + node.conn[0].iscsi.MaxRecvDataSegmentLength = 8192 + + * The login would fail for a normal session if MaxRecvDataSegmentLength is + too big. A error message in the format of + "cxgb3i: ERR! MaxRecvSegmentLength <X> too big. Need to be <= <Y>." + would be logged to dmesg. + +4. To direct open-iscsi traffic to go through cxgb3i's accelerated path, + "-I <iface file name>" option needs to be specified with most of the + iscsiadm command. <iface file name> is the transport interface file created + in step 2. diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 673463e4bbf..0e5e084dfb4 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -352,6 +352,8 @@ config ISCSI_TCP http://open-iscsi.org +source "drivers/scsi/cxgb3i/Kconfig" + config SGIWD93_SCSI tristate "SGI WD93C93 SCSI Driver" depends on SGI_HAS_WD93 && SCSI diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile index 07d0f58de9b..1410697257c 100644 --- a/drivers/scsi/Makefile +++ b/drivers/scsi/Makefile @@ -126,6 +126,7 @@ obj-$(CONFIG_SCSI_HPTIOP) += hptiop.o obj-$(CONFIG_SCSI_STEX) += stex.o obj-$(CONFIG_SCSI_MVSAS) += mvsas.o obj-$(CONFIG_PS3_ROM) += ps3rom.o +obj-$(CONFIG_SCSI_CXGB3_ISCSI) += libiscsi.o libiscsi_tcp.o cxgb3i/ obj-$(CONFIG_ARM) += arm/ diff --git a/drivers/scsi/cxgb3i/Kbuild b/drivers/scsi/cxgb3i/Kbuild new file mode 100644 index 00000000000..ee7d6d2f9c3 --- /dev/null +++ b/drivers/scsi/cxgb3i/Kbuild @@ -0,0 +1,4 @@ +EXTRA_CFLAGS += -I$(TOPDIR)/drivers/net/cxgb3 + +cxgb3i-y := cxgb3i_init.o cxgb3i_iscsi.o cxgb3i_pdu.o cxgb3i_offload.o +obj-$(CONFIG_SCSI_CXGB3_ISCSI) += cxgb3i_ddp.o cxgb3i.o diff --git a/drivers/scsi/cxgb3i/Kconfig b/drivers/scsi/cxgb3i/Kconfig new file mode 100644 index 00000000000..276281460ec --- /dev/null +++ b/drivers/scsi/cxgb3i/Kconfig @@ -0,0 +1,6 @@ +config SCSI_CXGB3_ISCSI + tristate "Chelsio S3xx iSCSI support" + select CHELSIO_T3 + select SCSI_ISCSI_ATTRS + ---help--- + This driver supports iSCSI offload for the Chelsio S3 series devices. diff --git a/drivers/scsi/cxgb3i/cxgb3i.h b/drivers/scsi/cxgb3i/cxgb3i.h new file mode 100644 index 00000000000..fde6e4c634e --- /dev/null +++ b/drivers/scsi/cxgb3i/cxgb3i.h @@ -0,0 +1,139 @@ +/* + * cxgb3i.h: Chelsio S3xx iSCSI driver. + * + * Copyright (c) 2008 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. + * + * Written by: Karen Xie (kxie@chelsio.com) + */ + +#ifndef __CXGB3I_H__ +#define __CXGB3I_H__ + +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/list.h> +#include <linux/netdevice.h> +#include <linux/scatterlist.h> +#include <scsi/libiscsi_tcp.h> + +/* from cxgb3 LLD */ +#include "common.h" +#include "t3_cpl.h" +#include "t3cdev.h" +#include "cxgb3_ctl_defs.h" +#include "cxgb3_offload.h" +#include "firmware_exports.h" + +#include "cxgb3i_offload.h" +#include "cxgb3i_ddp.h" + +#define CXGB3I_SCSI_QDEPTH_DFLT 128 +#define CXGB3I_MAX_TARGET CXGB3I_MAX_CONN +#define CXGB3I_MAX_LUN 512 +#define ISCSI_PDU_NONPAYLOAD_MAX \ + (sizeof(struct iscsi_hdr) + ISCSI_MAX_AHS_SIZE + 2*ISCSI_DIGEST_SIZE) + +struct cxgb3i_adapter; +struct cxgb3i_hba; +struct cxgb3i_endpoint; + +/** + * struct cxgb3i_hba - cxgb3i iscsi structure (per port) + * + * @snic: cxgb3i adapter containing this port + * @ndev: pointer to netdev structure + * @shost: pointer to scsi host structure + */ +struct cxgb3i_hba { + struct cxgb3i_adapter *snic; + struct net_device *ndev; + struct Scsi_Host *shost; +}; + +/** + * struct cxgb3i_adapter - cxgb3i adapter structure (per pci) + * + * @listhead: list head to link elements + * @lock: lock for this structure + * @tdev: pointer to t3cdev used by cxgb3 driver + * @pdev: pointer to pci dev + * @hba_cnt: # of hbas (the same as # of ports) + * @hba: all the hbas on this adapter + * @tx_max_size: max. tx packet size supported + * @rx_max_size: max. rx packet size supported + * @tag_format: ddp tag format settings + */ +struct cxgb3i_adapter { + struct list_head list_head; + spinlock_t lock; + struct t3cdev *tdev; + struct pci_dev *pdev; + unsigned char hba_cnt; + struct cxgb3i_hba *hba[MAX_NPORTS]; + + unsigned int tx_max_size; + unsigned int rx_max_size; + + struct cxgb3i_tag_format tag_format; +}; + +/** + * struct cxgb3i_conn - cxgb3i iscsi connection + * + * @listhead: list head to link elements + * @cep: pointer to iscsi_endpoint structure + * @conn: pointer to iscsi_conn structure + * @hba: pointer to the hba this conn. is going through + * @task_idx_bits: # of bits needed for session->cmds_max + */ +struct cxgb3i_conn { + struct list_head list_head; + struct cxgb3i_endpoint *cep; + struct iscsi_conn *conn; + struct cxgb3i_hba *hba; + unsigned int task_idx_bits; +}; + +/** + * struct cxgb3i_endpoint - iscsi tcp endpoint + * + * @c3cn: the h/w tcp connection representation + * @hba: pointer to the hba this conn. is going through + * @cconn: pointer to the associated cxgb3i iscsi connection + */ +struct cxgb3i_endpoint { + struct s3_conn *c3cn; + struct cxgb3i_hba *hba; + struct cxgb3i_conn *cconn; +}; + +int cxgb3i_iscsi_init(void); +void cxgb3i_iscsi_cleanup(void); + +struct cxgb3i_adapter *cxgb3i_adapter_add(struct t3cdev *); +void cxgb3i_adapter_remove(struct t3cdev *); +int cxgb3i_adapter_ulp_init(struct cxgb3i_adapter *); +void cxgb3i_adapter_ulp_cleanup(struct cxgb3i_adapter *); + +struct cxgb3i_hba *cxgb3i_hba_find_by_netdev(struct net_device *); +struct cxgb3i_hba *cxgb3i_hba_host_add(struct cxgb3i_adapter *, + struct net_device *); +void cxgb3i_hba_host_remove(struct cxgb3i_hba *); + +int cxgb3i_pdu_init(void); +void cxgb3i_pdu_cleanup(void); +void cxgb3i_conn_cleanup_task(struct iscsi_task *); +int cxgb3i_conn_alloc_pdu(struct iscsi_task *, u8); +int cxgb3i_conn_init_pdu(struct iscsi_task *, unsigned int, unsigned int); +int cxgb3i_conn_xmit_pdu(struct iscsi_task *); + +void cxgb3i_release_itt(struct iscsi_task *task, itt_t hdr_itt); +int cxgb3i_reserve_itt(struct iscsi_task *task, itt_t *hdr_itt); + +#endif diff --git a/drivers/scsi/cxgb3i/cxgb3i_ddp.c b/drivers/scsi/cxgb3i/cxgb3i_ddp.c new file mode 100644 index 00000000000..1a41f04264f --- /dev/null +++ b/drivers/scsi/cxgb3i/cxgb3i_ddp.c @@ -0,0 +1,770 @@ +/* + * cxgb3i_ddp.c: Chelsio S3xx iSCSI DDP Manager. + * + * Copyright (c) 2008 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. + * + * Written by: Karen Xie (kxie@chelsio.com) + */ + +#include <linux/skbuff.h> + +/* from cxgb3 LLD */ +#include "common.h" +#include "t3_cpl.h" +#include "t3cdev.h" +#include "cxgb3_ctl_defs.h" +#include "cxgb3_offload.h" +#include "firmware_exports.h" + +#include "cxgb3i_ddp.h" + +#define DRV_MODULE_NAME "cxgb3i_ddp" +#define DRV_MODULE_VERSION "1.0.0" +#define DRV_MODULE_RELDATE "Dec. 1, 2008" + +static char version[] = + "Chelsio S3xx iSCSI DDP " DRV_MODULE_NAME + " v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n"; + +MODULE_AUTHOR("Karen Xie <kxie@chelsio.com>"); +MODULE_DESCRIPTION("cxgb3i ddp pagepod manager"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(DRV_MODULE_VERSION); + +#define ddp_log_error(fmt...) printk(KERN_ERR "cxgb3i_ddp: ERR! " fmt) +#define ddp_log_warn(fmt...) printk(KERN_WARNING "cxgb3i_ddp: WARN! " fmt) +#define ddp_log_info(fmt...) printk(KERN_INFO "cxgb3i_ddp: " fmt) + +#ifdef __DEBUG_CXGB3I_DDP__ +#define ddp_log_debug(fmt, args...) \ + printk(KERN_INFO "cxgb3i_ddp: %s - " fmt, __func__ , ## args) +#else +#define ddp_log_debug(fmt...) +#endif + +/* + * iSCSI Direct Data Placement + * + * T3 h/w can directly place the iSCSI Data-In or Data-Out PDU's payload into + * pre-posted final destination host-memory buffers based on the Initiator + * Task Tag (ITT) in Data-In or Target Task Tag (TTT) in Data-Out PDUs. + * + * The host memory address is programmed into h/w in the format of pagepod + * entries. + * The location of the pagepod entry is encoded into ddp tag which is used or + * is the base for ITT/TTT. + */ + +#define DDP_PGIDX_MAX 4 +#define DDP_THRESHOLD 2048 +static unsigned char ddp_page_order[DDP_PGIDX_MAX] = {0, 1, 2, 4}; +static unsigned char ddp_page_shift[DDP_PGIDX_MAX] = {12, 13, 14, 16}; +static unsigned char page_idx = DDP_PGIDX_MAX; + +static LIST_HEAD(cxgb3i_ddp_list); +static DEFINE_RWLOCK(cxgb3i_ddp_rwlock); + +/* + * functions to program the pagepod in h/w + */ +static inline void ulp_mem_io_set_hdr(struct sk_buff *skb, unsigned int addr) +{ + struct ulp_mem_io *req = (struct ulp_mem_io *)skb->head; + + req->wr.wr_lo = 0; + req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_BYPASS)); + req->cmd_lock_addr = htonl(V_ULP_MEMIO_ADDR(addr >> 5) | + V_ULPTX_CMD(ULP_MEM_WRITE)); + req->len = htonl(V_ULP_MEMIO_DATA_LEN(PPOD_SIZE >> 5) | + V_ULPTX_NFLITS((PPOD_SIZE >> 3) + 1)); +} + +static int set_ddp_map(struct cxgb3i_ddp_info *ddp, struct pagepod_hdr *hdr, + unsigned int idx, unsigned int npods, + struct cxgb3i_gather_list *gl) +{ + unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ddp->llimit; + int i; + + for (i = 0; i < npods; i++, idx++, pm_addr += PPOD_SIZE) { + struct sk_buff *skb = ddp->gl_skb[idx]; + struct pagepod *ppod; + int j, pidx; + + /* hold on to the skb until we clear the ddp mapping */ + skb_get(skb); + + ulp_mem_io_set_hdr(skb, pm_addr); + ppod = (struct pagepod *) + (skb->head + sizeof(struct ulp_mem_io)); + memcpy(&(ppod->hdr), hdr, sizeof(struct pagepod)); + for (pidx = 4 * i, j = 0; j < 5; ++j, ++pidx) + ppod->addr[j] = pidx < gl->nelem ? + cpu_to_be64(gl->phys_addr[pidx]) : 0UL; + + skb->priority = CPL_PRIORITY_CONTROL; + cxgb3_ofld_send(ddp->tdev, skb); + } + return 0; +} + +static int clear_ddp_map(struct cxgb3i_ddp_info *ddp, unsigned int idx, + unsigned int npods) +{ + unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ddp->llimit; + int i; + + for (i = 0; i < npods; i++, idx++, pm_addr += PPOD_SIZE) { + struct sk_buff *skb = ddp->gl_skb[idx]; + + ddp->gl_skb[idx] = NULL; + memset((skb->head + sizeof(struct ulp_mem_io)), 0, PPOD_SIZE); + ulp_mem_io_set_hdr(skb, pm_addr); + skb->priority = CPL_PRIORITY_CONTROL; + cxgb3_ofld_send(ddp->tdev, skb); + } + return 0; +} + +static inline int ddp_find_unused_entries(struct cxgb3i_ddp_info *ddp, + int start, int max, int count, + struct cxgb3i_gather_list *gl) +{ + unsigned int i, j; + + spin_lock(&ddp->map_lock); + for (i = start; i <= max;) { + for (j = 0; j < count; j++) { + if (ddp->gl_map[i + j]) + break; + } + if (j == count) { + for (j = 0; j < count; j++) + ddp->gl_map[i + j] = gl; + spin_unlock(&ddp->map_lock); + return i; + } + i += j + 1; + } + spin_unlock(&ddp->map_lock); + return -EBUSY; +} + +static inline void ddp_unmark_entries(struct cxgb3i_ddp_info *ddp, + int start, int count) +{ + spin_lock(&ddp->map_lock); + memset(&ddp->gl_map[start], 0, + count * sizeof(struct cxgb3i_gather_list *)); + spin_unlock(&ddp->map_lock); +} + +static inline void ddp_free_gl_skb(struct cxgb3i_ddp_info *ddp, + int idx, int count) +{ + int i; + + for (i = 0; i < count; i++, idx++) + if (ddp->gl_skb[idx]) { + kfree_skb(ddp->gl_skb[idx]); + ddp->gl_skb[idx] = NULL; + } +} + +static inline int ddp_alloc_gl_skb(struct cxgb3i_ddp_info *ddp, int idx, + int count, gfp_t gfp) +{ + int i; + + for (i = 0; i < count; i++) { + struct sk_buff *skb = alloc_skb(sizeof(struct ulp_mem_io) + + PPOD_SIZE, gfp); + if (skb) { + ddp->gl_skb[idx + i] = skb; + skb_put(skb, sizeof(struct ulp_mem_io) + PPOD_SIZE); + } else { + ddp_free_gl_skb(ddp, idx, i); + return -ENOMEM; + } + } + return 0; +} + +/** + * cxgb3i_ddp_find_page_index - return ddp page index for a given page size. + * @pgsz: page size + * return the ddp page index, if no match is found return DDP_PGIDX_MAX. + */ +int cxgb3i_ddp_find_page_index(unsigned long pgsz) +{ + int i; + + for (i = 0; i < DDP_PGIDX_MAX; i++) { + if (pgsz == (1UL << ddp_page_shift[i])) + return i; + } + ddp_log_debug("ddp page size 0x%lx not supported.\n", pgsz); + return DDP_PGIDX_MAX; +} +EXPORT_SYMBOL_GPL(cxgb3i_ddp_find_page_index); + +static inline void ddp_gl_unmap(struct pci_dev *pdev, + struct cxgb3i_gather_list *gl) +{ + int i; + + for (i = 0; i < gl->nelem; i++) + pci_unmap_page(pdev, gl->phys_addr[i], PAGE_SIZE, + PCI_DMA_FROMDEVICE); +} + +static inline int ddp_gl_map(struct pci_dev *pdev, + struct cxgb3i_gather_list *gl) +{ + int i; + + for (i = 0; i < gl->nelem; i++) { + gl->phys_addr[i] = pci_map_page(pdev, gl->pages[i], 0, + PAGE_SIZE, + PCI_DMA_FROMDEVICE); + if (unlikely(pci_dma_mapping_error(pdev, gl->phys_addr[i]))) + goto unmap; + } + + return i; + +unmap: + if (i) { + unsigned int nelem = gl->nelem; + + gl->nelem = i; + ddp_gl_unmap(pdev, gl); + gl->nelem = nelem; + } + return -ENOMEM; +} + +/** + * cxgb3i_ddp_make_gl - build ddp page buffer list + * @xferlen: total buffer length + * @sgl: page buffer scatter-gather list + * @sgcnt: # of page buffers + * @pdev: pci_dev, used for pci map + * @gfp: allocation mode + * + * construct a ddp page buffer list from the scsi scattergather list. + * coalesce buffers as much as possible, and obtain dma addresses for + * each page. + * + * Return the cxgb3i_gather_list constructed from the page buffers if the + * memory can be used for ddp. Return NULL otherwise. + */ +struct cxgb3i_gather_list *cxgb3i_ddp_make_gl(unsigned int xferlen, + struct scatterlist *sgl, + unsigned int sgcnt, + struct pci_dev *pdev, + gfp_t gfp) +{ + struct cxgb3i_gather_list *gl; + struct scatterlist *sg = sgl; + struct page *sgpage = sg_page(sg); + unsigned int sglen = sg->length; + unsigned int sgoffset = sg->offset; + unsigned int npages = (xferlen + sgoffset + PAGE_SIZE - 1) >> + PAGE_SHIFT; + int i = 1, j = 0; + + if (xferlen < DDP_THRESHOLD) { + ddp_log_debug("xfer %u < threshold %u, no ddp.\n", + xferlen, DDP_THRESHOLD); + return NULL; + } + + gl = kzalloc(sizeof(struct cxgb3i_gather_list) + + npages * (sizeof(dma_addr_t) + sizeof(struct page *)), + gfp); + if (!gl) + return NULL; + + gl->pages = (struct page **)&gl->phys_addr[npages]; + gl->length = xferlen; + gl->offset = sgoffset; + gl->pages[0] = sgpage; + + sg = sg_next(sg); + while (sg) { + struct page *page = sg_page(sg); + + if (sgpage == page && sg->offset == sgoffset + sglen) + sglen += sg->length; + else { + /* make sure the sgl is fit for ddp: + * each has the same page size, and + * all of the middle pages are used completely + */ + if ((j && sgoffset) || + ((i != sgcnt - 1) && + ((sglen + sgoffset) & ~PAGE_MASK))) + goto error_out; + + j++; + if (j == gl->nelem || sg->offset) + goto error_out; + gl->pages[j] = page; + sglen = sg->length; + sgoffset = sg->offset; + sgpage = page; + } + i++; + sg = sg_next(sg); + } + gl->nelem = ++j; + + if (ddp_gl_map(pdev, gl) < 0) + goto error_out; + + return gl; + +error_out: + kfree(gl); + return NULL; +} +EXPORT_SYMBOL_GPL(cxgb3i_ddp_make_gl); + +/** + * cxgb3i_ddp_release_gl - release a page buffer list + * @gl: a ddp page buffer list + * @pdev: pci_dev used for pci_unmap + * free a ddp page buffer list resulted from cxgb3i_ddp_make_gl(). + */ +void cxgb3i_ddp_release_gl(struct cxgb3i_gather_list *gl, + struct pci_dev *pdev) +{ + ddp_gl_unmap(pdev, gl); + kfree(gl); +} +EXPORT_SYMBOL_GPL(cxgb3i_ddp_release_gl); + +/** + * cxgb3i_ddp_tag_reserve - set up ddp for a data transfer + * @tdev: t3cdev adapter + * @tid: connection id + * @tformat: tag format + * @tagp: the s/w tag, if ddp setup is successful, it will be updated with + * ddp/hw tag + * @gl: the page momory list + * @gfp: allocation mode + * + * ddp setup for a given page buffer list and construct the ddp tag. + * return 0 if success, < 0 otherwise. + */ +int cxgb3i_ddp_tag_reserve(struct t3cdev *tdev, unsigned int tid, + struct cxgb3i_tag_format *tformat, u32 *tagp, + struct cxgb3i_gather_list *gl, gfp_t gfp) +{ + struct cxgb3i_ddp_info *ddp = tdev->ulp_iscsi; + struct pagepod_hdr hdr; + unsigned int npods; + int idx = -1, idx_max; + int err = -ENOMEM; + u32 sw_tag = *tagp; + u32 tag; + + if (page_idx >= DDP_PGIDX_MAX || !ddp || !gl || !gl->nelem || + gl->length < DDP_THRESHOLD) { + ddp_log_debug("pgidx %u, xfer %u/%u, NO ddp.\n", + page_idx, gl->length, DDP_THRESHOLD); + return -EINVAL; + } + + npods = (gl->nelem + PPOD_PAGES_MAX - 1) >> PPOD_PAGES_SHIFT; + idx_max = ddp->nppods - npods + 1; + + if (ddp->idx_last == ddp->nppods) + idx = ddp_find_unused_entries(ddp, 0, idx_max, npods, gl); + else { + idx = ddp_find_unused_entries(ddp, ddp->idx_last + 1, + idx_max, npods, gl); + if (idx < 0 && ddp->idx_last >= npods) + idx = ddp_find_unused_entries(ddp, 0, + ddp->idx_last - npods + 1, + npods, gl); + } + if (idx < 0) { + ddp_log_debug("xferlen %u, gl %u, npods %u NO DDP.\n", + gl->length, gl->nelem, npods); + return idx; + } + + err = ddp_alloc_gl_skb(ddp, idx, npods, gfp); + if (err < 0) + goto unmark_entries; + + tag = cxgb3i_ddp_tag_base(tformat, sw_tag); + tag |= idx << PPOD_IDX_SHIFT; + + hdr.rsvd = 0; + hdr.vld_tid = htonl(F_PPOD_VALID | V_PPOD_TID(tid)); + hdr.pgsz_tag_clr = htonl(tag & ddp->rsvd_tag_mask); + hdr.maxoffset = htonl(gl->length); + hdr.pgoffset = htonl(gl->offset); + + err = set_ddp_map(ddp, &hdr, idx, npods, gl); + if (err < 0) + goto free_gl_skb; + + ddp->idx_last = idx; + ddp_log_debug("xfer %u, gl %u,%u, tid 0x%x, 0x%x -> 0x%x(%u,%u).\n", + gl->length, gl->nelem, gl->offset, tid, sw_tag, tag, + idx, npods); + *tagp = tag; + return 0; + +free_gl_skb: + ddp_free_gl_skb(ddp, idx, npods); +unmark_entries: + ddp_unmark_entries(ddp, idx, npods); + return err; +} +EXPORT_SYMBOL_GPL(cxgb3i_ddp_tag_reserve); + +/** + * cxgb3i_ddp_tag_release - release a ddp tag + * @tdev: t3cdev adapter + * @tag: ddp tag + * ddp cleanup for a given ddp tag and release all the resources held + */ +void cxgb3i_ddp_tag_release(struct t3cdev *tdev, u32 tag) +{ + struct cxgb3i_ddp_info *ddp = tdev->ulp_iscsi; + u32 idx; + + if (!ddp) { + ddp_log_error("release ddp tag 0x%x, ddp NULL.\n", tag); + return; + } + + idx = (tag >> PPOD_IDX_SHIFT) & ddp->idx_mask; + if (idx < ddp->nppods) { + struct cxgb3i_gather_list *gl = ddp->gl_map[idx]; + unsigned int npods; + + if (!gl) { + ddp_log_error("release ddp 0x%x, idx 0x%x, gl NULL.\n", + tag, idx); + return; + } + npods = (gl->nelem + PPOD_PAGES_MAX - 1) >> PPOD_PAGES_SHIFT; + ddp_log_debug("ddp tag 0x%x, release idx 0x%x, npods %u.\n", + tag, idx, npods); + clear_ddp_map(ddp, idx, npods); + ddp_unmark_entries(ddp, idx, npods); + cxgb3i_ddp_release_gl(gl, ddp->pdev); + } else + ddp_log_error("ddp tag 0x%x, idx 0x%x > max 0x%x.\n", + tag, idx, ddp->nppods); +} +EXPORT_SYMBOL_GPL(cxgb3i_ddp_tag_release); + +static int setup_conn_pgidx(struct t3cdev *tdev, unsigned int tid, int pg_idx, + int reply) +{ + struct sk_buff *skb = alloc_skb(sizeof(struct cpl_set_tcb_field), + GFP_KERNEL); + struct cpl_set_tcb_field *req; + u64 val = pg_idx < DDP_PGIDX_MAX ? pg_idx : 0; + + if (!skb) + return -ENOMEM; + + /* set up ulp submode and page size */ + req = (struct cpl_set_tcb_field *)skb_put(skb, sizeof(*req)); + req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD)); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, tid)); + req->reply = V_NO_REPLY(reply ? 0 : 1); + req->cpu_idx = 0; + req->word = htons(31); + req->mask = cpu_to_be64(0xF0000000); + req->val = cpu_to_be64(val << 28); + skb->priority = CPL_PRIORITY_CONTROL; + + cxgb3_ofld_send(tdev, skb); + return 0; +} + +/** + * cxgb3i_setup_conn_host_pagesize - setup the conn.'s ddp page size + * @tdev: t3cdev adapter + * @tid: connection id + * @reply: request reply from h/w + * set up the ddp page size based on the host PAGE_SIZE for a connection + * identified by tid + */ +int cxgb3i_setup_conn_host_pagesize(struct t3cdev *tdev, unsigned int tid, + int reply) +{ + return setup_conn_pgidx(tdev, tid, page_idx, reply); +} +EXPORT_SYMBOL_GPL(cxgb3i_setup_conn_host_pagesize); + +/** + * cxgb3i_setup_conn_pagesize - setup the conn.'s ddp page size + * @tdev: t3cdev adapter + * @tid: connection id + * @reply: request reply from h/w + * @pgsz: ddp page size + * set up the ddp page size for a connection identified by tid + */ +int cxgb3i_setup_conn_pagesize(struct t3cdev *tdev, unsigned int tid, + int reply, unsigned long pgsz) +{ + int pgidx = cxgb3i_ddp_find_page_index(pgsz); + + return setup_conn_pgidx(tdev, tid, pgidx, reply); +} +EXPORT_SYMBOL_GPL(cxgb3i_setup_conn_pagesize); + +/** + * cxgb3i_setup_conn_digest - setup conn. digest setting + * @tdev: t3cdev adapter + * @tid: connection id + * @hcrc: header digest enabled + * @dcrc: data digest enabled + * @reply: request reply from h/w + * set up the iscsi digest settings for a connection identified by tid + */ +int cxgb3i_setup_conn_digest(struct t3cdev *tdev, unsigned int tid, + int hcrc, int dcrc, int reply) +{ + struct sk_buff *skb = alloc_skb(sizeof(struct cpl_set_tcb_field), + GFP_KERNEL); + struct cpl_set_tcb_field *req; + u64 val = (hcrc ? 1 : 0) | (dcrc ? 2 : 0); + + if (!skb) + return -ENOMEM; + + /* set up ulp submode and page size */ + req = (struct cpl_set_tcb_field *)skb_put(skb, sizeof(*req)); + req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD)); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, tid)); + req->reply = V_NO_REPLY(reply ? 0 : 1); + req->cpu_idx = 0; + req->word = htons(31); + req->mask = cpu_to_be64(0x0F000000); + req->val = cpu_to_be64(val << 24); + skb->priority = CPL_PRIORITY_CONTROL; + + cxgb3_ofld_send(tdev, skb); + return 0; +} +EXPORT_SYMBOL_GPL(cxgb3i_setup_conn_digest); + +static int ddp_init(struct t3cdev *tdev) +{ + struct cxgb3i_ddp_info *ddp; + struct ulp_iscsi_info uinfo; + unsigned int ppmax, bits; + int i, err; + static int vers_printed; + + if (!vers_printed) { + printk(KERN_INFO "%s", version); + vers_printed = 1; + } + + err = tdev->ctl(tdev, ULP_ISCSI_GET_PARAMS, &uinfo); + if (err < 0) { + ddp_log_error("%s, failed to get iscsi param err=%d.\n", + tdev->name, err); + return err; + } + + ppmax = (uinfo.ulimit - uinfo.llimit + 1) >> PPOD_SIZE_SHIFT; + bits = __ilog2_u32(ppmax) + 1; + if (bits > PPOD_IDX_MAX_SIZE) + bits = PPOD_IDX_MAX_SIZE; + ppmax = (1 << (bits - 1)) - 1; + + ddp = cxgb3i_alloc_big_mem(sizeof(struct cxgb3i_ddp_info) + + ppmax * + (sizeof(struct cxgb3i_gather_list *) + + sizeof(struct sk_buff *)), + GFP_KERNEL); + if (!ddp) { + ddp_log_warn("%s unable to alloc ddp 0x%d, ddp disabled.\n", + tdev->name, ppmax); + return 0; + } + ddp->gl_map = (struct cxgb3i_gather_list **)(ddp + 1); + ddp->gl_skb = (struct sk_buff **)(((char *)ddp->gl_map) + + ppmax * + sizeof(struct cxgb3i_gather_list *)); + spin_lock_init(&ddp->map_lock); + + ddp->tdev = tdev; + ddp->pdev = uinfo.pdev; + ddp->max_txsz = min_t(unsigned int, uinfo.max_txsz, ULP2_MAX_PKT_SIZE); + ddp->max_rxsz = min_t(unsigned int, uinfo.max_rxsz, ULP2_MAX_PKT_SIZE); + ddp->llimit = uinfo.llimit; + ddp->ulimit = uinfo.ulimit; + ddp->nppods = ppmax; + ddp->idx_last = ppmax; + ddp->idx_bits = bits; + ddp->idx_mask = (1 << bits) - 1; + ddp->rsvd_tag_mask = (1 << (bits + PPOD_IDX_SHIFT)) - 1; + + uinfo.tagmask = ddp->idx_mask << PPOD_IDX_SHIFT; + for (i = 0; i < DDP_PGIDX_MAX; i++) + uinfo.pgsz_factor[i] = ddp_page_order[i]; + uinfo.ulimit = uinfo.llimit + (ppmax << PPOD_SIZE_SHIFT); + + err = tdev->ctl(tdev, ULP_ISCSI_SET_PARAMS, &uinfo); + if (err < 0) { + ddp_log_warn("%s unable to set iscsi param err=%d, " + "ddp disabled.\n", tdev->name, err); + goto free_ddp_map; + } + + tdev->ulp_iscsi = ddp; + + /* add to the list */ + write_lock(&cxgb3i_ddp_rwlock); + list_add_tail(&ddp->list, &cxgb3i_ddp_list); + write_unlock(&cxgb3i_ddp_rwlock); + + ddp_log_info("nppods %u (0x%x ~ 0x%x), bits %u, mask 0x%x,0x%x " + "pkt %u,%u.\n", + ppmax, ddp->llimit, ddp->ulimit, ddp->idx_bits, + ddp->idx_mask, ddp->rsvd_tag_mask, + ddp->max_txsz, ddp->max_rxsz); + return 0; + +free_ddp_map: + cxgb3i_free_big_mem(ddp); + return err; +} + +/** + * cxgb3i_adapter_ddp_init - initialize the adapter's ddp resource + * @tdev: t3cdev adapter + * @tformat: tag format + * @txsz: max tx pkt size, filled in by this func. + * @rxsz: max rx pkt size, filled in by this func. + * initialize the ddp pagepod manager for a given adapter if needed and + * setup the tag format for a given iscsi entity + */ +int cxgb3i_adapter_ddp_init(struct t3cdev *tdev, + struct cxgb3i_tag_format *tformat, + unsigned int *txsz, unsigned int *rxsz) +{ + struct cxgb3i_ddp_info *ddp; + unsigned char idx_bits; + + if (!tformat) + return -EINVAL; + + if (!tdev->ulp_iscsi) { + int err = ddp_init(tdev); + if (err < 0) + return err; + } + ddp = (struct cxgb3i_ddp_info *)tdev->ulp_iscsi; + + idx_bits = 32 - tformat->sw_bits; + tformat->rsvd_bits = ddp->idx_bits; + tformat->rsvd_shift = PPOD_IDX_SHIFT; + tformat->rsvd_mask = (1 << tformat->rsvd_bits) - 1; + + ddp_log_info("tag format: sw %u, rsvd %u,%u, mask 0x%x.\n", + tformat->sw_bits, tformat->rsvd_bits, + tformat->rsvd_shift, tformat->rsvd_mask); + + *txsz = ddp->max_txsz; + *rxsz = ddp->max_rxsz; + ddp_log_info("ddp max pkt size: %u, %u.\n", + ddp->max_txsz, ddp->max_rxsz); + return 0; +} +EXPORT_SYMBOL_GPL(cxgb3i_adapter_ddp_init); + +static void ddp_release(struct cxgb3i_ddp_info *ddp) +{ + int i = 0; + struct t3cdev *tdev = ddp->tdev; + + tdev->ulp_iscsi = NULL; + while (i < ddp->nppods) { + struct cxgb3i_gather_list *gl = ddp->gl_map[i]; + if (gl) { + int npods = (gl->nelem + PPOD_PAGES_MAX - 1) + >> PPOD_PAGES_SHIFT; + + kfree(gl); + ddp_free_gl_skb(ddp, i, npods); + } else + i++; + } + cxgb3i_free_big_mem(ddp); +} + +/** + * cxgb3i_adapter_ddp_cleanup - release the adapter's ddp resource + * @tdev: t3cdev adapter + * release all the resource held by the ddp pagepod manager for a given + * adapter if needed + */ +void cxgb3i_adapter_ddp_cleanup(struct t3cdev *tdev) +{ + struct cxgb3i_ddp_info *ddp; + + /* remove from the list */ + write_lock(&cxgb3i_ddp_rwlock); + list_for_each_entry(ddp, &cxgb3i_ddp_list, list) { + if (ddp->tdev == tdev) { + list_del(&ddp->list); + break; + } + } + write_unlock(&cxgb3i_ddp_rwlock); + + if (ddp) + ddp_release(ddp); +} +EXPORT_SYMBOL_GPL(cxgb3i_adapter_ddp_cleanup); + +/** + * cxgb3i_ddp_init_module - module init entry point + * initialize any driver wide global data structures + */ +static int __init cxgb3i_ddp_init_module(void) +{ + page_idx = cxgb3i_ddp_find_page_index(PAGE_SIZE); + ddp_log_info("system PAGE_SIZE %lu, ddp idx %u.\n", + PAGE_SIZE, page_idx); + return 0; +} + +/** + * cxgb3i_ddp_exit_module - module cleanup/exit entry point + * go through the ddp list and release any resource held. + */ +static void __exit cxgb3i_ddp_exit_module(void) +{ + struct cxgb3i_ddp_info *ddp; + + /* release all ddp manager if there is any */ + write_lock(&cxgb3i_ddp_rwlock); + list_for_each_entry(ddp, &cxgb3i_ddp_list, list) { + list_del(&ddp->list); + ddp_release(ddp); + } + write_unlock(&cxgb3i_ddp_rwlock); +} + +module_init(cxgb3i_ddp_init_module); +module_exit(cxgb3i_ddp_exit_module); diff --git a/drivers/scsi/cxgb3i/cxgb3i_ddp.h b/drivers/scsi/cxgb3i/cxgb3i_ddp.h new file mode 100644 index 00000000000..5c7c4d95c49 --- /dev/null +++ b/drivers/scsi/cxgb3i/cxgb3i_ddp.h @@ -0,0 +1,306 @@ +/* + * cxgb3i_ddp.h: Chelsio S3xx iSCSI DDP Manager. + * + * Copyright (c) 2008 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. + * + * Written by: Karen Xie (kxie@chelsio.com) + */ + +#ifndef __CXGB3I_ULP2_DDP_H__ +#define __CXGB3I_ULP2_DDP_H__ + +/** + * struct cxgb3i_tag_format - cxgb3i ulp tag format for an iscsi entity + * + * @sw_bits: # of bits used by iscsi software layer + * @rsvd_bits: # of bits used by h/w + * @rsvd_shift: h/w bits shift left + * @rsvd_mask: reserved bit mask + */ +struct cxgb3i_tag_format { + unsigned char sw_bits; + unsigned char rsvd_bits; + unsigned char rsvd_shift; + unsigned char filler[1]; + u32 rsvd_mask; +}; + +/** + * struct cxgb3i_gather_list - cxgb3i direct data placement memory + * + * @tag: ddp tag + * @length: total data buffer length + * @offset: initial offset to the 1st page + * @nelem: # of pages + * @pages: page pointers + * @phys_addr: physical address + */ +struct cxgb3i_gather_list { + u32 tag; + unsigned int length; + unsigned int offset; + unsigned int nelem; + struct page **pages; + dma_addr_t phys_addr[0]; +}; + +/** + * struct cxgb3i_ddp_info - cxgb3i direct data placement for pdu payload + * + * @list: list head to link elements + * @tdev: pointer to t3cdev used by cxgb3 driver + * @max_txsz: max tx packet size for ddp + * @max_rxsz: max rx packet size for ddp + * @llimit: lower bound of the page pod memory + * @ulimit: upper bound of the page pod memory + * @nppods: # of page pod entries + * @idx_last: page pod entry last used + * @idx_bits: # of bits the pagepod index would take + * @idx_mask: pagepod index mask + * @rsvd_tag_mask: tag mask + * @map_lock: lock to synchonize access to the page pod map + * @gl_map: ddp memory gather list + * @gl_skb: skb used to program the pagepod + */ +struct cxgb3i_ddp_info { + struct list_head list; + struct t3cdev *tdev; + struct pci_dev *pdev; + unsigned int max_txsz; + unsigned int max_rxsz; + unsigned int llimit; + unsigned int ulimit; + unsigned int nppods; + unsigned int idx_last; + unsigned char idx_bits; + unsigned char filler[3]; + u32 idx_mask; + u32 rsvd_tag_mask; + spinlock_t map_lock; + struct cxgb3i_gather_list **gl_map; + struct sk_buff **gl_skb; +}; + +#define ULP2_MAX_PKT_SIZE 16224 +#define ULP2_MAX_PDU_PAYLOAD (ULP2_MAX_PKT_SIZE - ISCSI_PDU_NONPAYLOAD_MAX) +#define PPOD_PAGES_MAX 4 +#define PPOD_PAGES_SHIFT 2 /* 4 pages per pod */ + +/* + * struct pagepod_hdr, pagepod - pagepod format + */ +struct pagepod_hdr { + u32 vld_tid; + u32 pgsz_tag_clr; + u32 maxoffset; + u32 pgoffset; + u64 rsvd; +}; + +struct pagepod { + struct pagepod_hdr hdr; + u64 addr[PPOD_PAGES_MAX + 1]; +}; + +#define PPOD_SIZE sizeof(struct pagepod) /* 64 */ +#define PPOD_SIZE_SHIFT 6 + +#define PPOD_COLOR_SHIFT 0 +#define PPOD_COLOR_SIZE 6 +#define PPOD_COLOR_MASK ((1 << PPOD_COLOR_SIZE) - 1) + +#define PPOD_IDX_SHIFT PPOD_COLOR_SIZE +#define PPOD_IDX_MAX_SIZE 24 + +#define S_PPOD_TID 0 +#define M_PPOD_TID 0xFFFFFF +#define V_PPOD_TID(x) ((x) << S_PPOD_TID) + +#define S_PPOD_VALID 24 +#define V_PPOD_VALID(x) ((x) << S_PPOD_VALID) +#define F_PPOD_VALID V_PPOD_VALID(1U) + +#define S_PPOD_COLOR 0 +#define M_PPOD_COLOR 0x3F +#define V_PPOD_COLOR(x) ((x) << S_PPOD_COLOR) + +#define S_PPOD_TAG 6 +#define M_PPOD_TAG 0xFFFFFF +#define V_PPOD_TAG(x) ((x) << S_PPOD_TAG) + +#define S_PPOD_PGSZ 30 +#define M_PPOD_PGSZ 0x3 +#define V_PPOD_PGSZ(x) ((x) << S_PPOD_PGSZ) + +/* + * large memory chunk allocation/release + * use vmalloc() if kmalloc() fails + */ +static inline void *cxgb3i_alloc_big_mem(unsigned int size, + gfp_t gfp) +{ + void *p = kmalloc(size, gfp); + if (!p) + p = vmalloc(size); + if (p) + memset(p, 0, size); + return p; +} + +static inline void cxgb3i_free_big_mem(void *addr) +{ + if (is_vmalloc_addr(addr)) + vfree(addr); + else + kfree(addr); +} + +/* + * cxgb3i ddp tag are 32 bits, it consists of reserved bits used by h/w and + * non-reserved bits that can be used by the iscsi s/w. + * The reserved bits are identified by the rsvd_bits and rsvd_shift fields + * in struct cxgb3i_tag_format. + * + * The upper most reserved bit can be used to check if a tag is ddp tag or not: + * if the bit is 0, the tag is a valid ddp tag + */ + +/** + * cxgb3i_is_ddp_tag - check if a given tag is a hw/ddp tag + * @tformat: tag format information + * @tag: tag to be checked + * + * return true if the tag is a ddp tag, false otherwise. + */ +static inline int cxgb3i_is_ddp_tag(struct cxgb3i_tag_format *tformat, u32 tag) +{ + return !(tag & (1 << (tformat->rsvd_bits + tformat->rsvd_shift - 1))); +} + +/** + * cxgb3i_sw_tag_usable - check if a given s/w tag has enough bits left for + * the reserved/hw bits + * @tformat: tag format information + * @sw_tag: s/w tag to be checked + * + * return true if the tag is a ddp tag, false otherwise. + */ +static inline int cxgb3i_sw_tag_usable(struct cxgb3i_tag_format *tformat, + u32 sw_tag) +{ + sw_tag >>= (32 - tformat->rsvd_bits); + return !sw_tag; +} + +/** + * cxgb3i_set_non_ddp_tag - mark a given s/w tag as an invalid ddp tag + * @tformat: tag format information + * @sw_tag: s/w tag to be checked + * + * insert 1 at the upper most reserved bit to mark it as an invalid ddp tag. + */ +static inline u32 cxgb3i_set_non_ddp_tag(struct cxgb3i_tag_format *tformat, + u32 sw_tag) +{ + unsigned char shift = tformat->rsvd_bits + tformat->rsvd_shift - 1; + u32 mask = (1 << shift) - 1; + + if (sw_tag && (sw_tag & ~mask)) { + u32 v1 = sw_tag & ((1 << shift) - 1); + u32 v2 = (sw_tag >> (shift - 1)) << shift; + + return v2 | v1 | 1 << shift; + } + return sw_tag | 1 << shift; +} + +/** + * cxgb3i_ddp_tag_base - shift the s/w tag bits so that reserved bits are not + * used. + * @tformat: tag format information + * @sw_tag: s/w tag to be checked + */ +static inline u32 cxgb3i_ddp_tag_base(struct cxgb3i_tag_format *tformat, + u32 sw_tag) +{ + u32 mask = (1 << tformat->rsvd_shift) - 1; + + if (sw_tag && (sw_tag & ~mask)) { + u32 v1 = sw_tag & mask; + u32 v2 = sw_tag >> tformat->rsvd_shift; + + v2 <<= tformat->rsvd_shift + tformat->rsvd_bits; + return v2 | v1; + } + return sw_tag; +} + +/** + * cxgb3i_tag_rsvd_bits - get the reserved bits used by the h/w + * @tformat: tag format information + * @tag: tag to be checked + * + * return the reserved bits in the tag + */ +static inline u32 cxgb3i_tag_rsvd_bits(struct cxgb3i_tag_format *tformat, + u32 tag) +{ + if (cxgb3i_is_ddp_tag(tformat, tag)) + return (tag >> tformat->rsvd_shift) & tformat->rsvd_mask; + return 0; +} + +/** + * cxgb3i_tag_nonrsvd_bits - get the non-reserved bits used by the s/w + * @tformat: tag format information + * @tag: tag to be checked + * + * return the non-reserved bits in the tag. + */ +static inline u32 cxgb3i_tag_nonrsvd_bits(struct cxgb3i_tag_format *tformat, + u32 tag) +{ + unsigned char shift = tformat->rsvd_bits + tformat->rsvd_shift - 1; + u32 v1, v2; + + if (cxgb3i_is_ddp_tag(tformat, tag)) { + v1 = tag & ((1 << tformat->rsvd_shift) - 1); + v2 = (tag >> (shift + 1)) << tformat->rsvd_shift; + } else { + u32 mask = (1 << shift) - 1; + + tag &= ~(1 << shift); + v1 = tag & mask; + v2 = (tag >> 1) & ~mask; + } + return v1 | v2; +} + +int cxgb3i_ddp_tag_reserve(struct t3cdev *, unsigned int tid, + struct cxgb3i_tag_format *, u32 *tag, + struct cxgb3i_gather_list *, gfp_t gfp); +void cxgb3i_ddp_tag_release(struct t3cdev *, u32 tag); + +struct cxgb3i_gather_list *cxgb3i_ddp_make_gl(unsigned int xferlen, + struct scatterlist *sgl, + unsigned int sgcnt, + struct pci_dev *pdev, + gfp_t gfp); +void cxgb3i_ddp_release_gl(struct cxgb3i_gather_list *gl, + struct pci_dev *pdev); + +int cxgb3i_setup_conn_host_pagesize(struct t3cdev *, unsigned int tid, + int reply); +int cxgb3i_setup_conn_pagesize(struct t3cdev *, unsigned int tid, int reply, + unsigned long pgsz); +int cxgb3i_setup_conn_digest(struct t3cdev *, unsigned int tid, + int hcrc, int dcrc, int reply); +int cxgb3i_ddp_find_page_index(unsigned long pgsz); +int cxgb3i_adapter_ddp_init(struct t3cdev *, struct cxgb3i_tag_format *, + unsigned int *txsz, unsigned int *rxsz); +void cxgb3i_adapter_ddp_cleanup(struct t3cdev *); +#endif diff --git a/drivers/scsi/cxgb3i/cxgb3i_init.c b/drivers/scsi/cxgb3i/cxgb3i_init.c new file mode 100644 index 00000000000..091ecb4d9f3 --- /dev/null +++ b/drivers/scsi/cxgb3i/cxgb3i_init.c @@ -0,0 +1,107 @@ +/* cxgb3i_init.c: Chelsio S3xx iSCSI driver. + * + * Copyright (c) 2008 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. + * + * Written by: Karen Xie (kxie@chelsio.com) + */ + +#include "cxgb3i.h" + +#define DRV_MODULE_NAME "cxgb3i" +#define DRV_MODULE_VERSION "1.0.0" +#define DRV_MODULE_RELDATE "Jun. 1, 2008" + +static char version[] = + "Chelsio S3xx iSCSI Driver " DRV_MODULE_NAME + " v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n"; + +MODULE_AUTHOR("Karen Xie <kxie@chelsio.com>"); +MODULE_DESCRIPTION("Chelsio S3xx iSCSI Driver"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(DRV_MODULE_VERSION); + +static void open_s3_dev(struct t3cdev *); +static void close_s3_dev(struct t3cdev *); + +static cxgb3_cpl_handler_func cxgb3i_cpl_handlers[NUM_CPL_CMDS]; +static struct cxgb3_client t3c_client = { + .name = "iscsi_cxgb3", + .handlers = cxgb3i_cpl_handlers, + .add = open_s3_dev, + .remove = close_s3_dev, +}; + +/** + * open_s3_dev - register with cxgb3 LLD + * @t3dev: cxgb3 adapter instance + */ +static void open_s3_dev(struct t3cdev *t3dev) +{ + static int vers_printed; + + if (!vers_printed) { + printk(KERN_INFO "%s", version); + vers_printed = 1; + } + + cxgb3i_sdev_add(t3dev, &t3c_client); + cxgb3i_adapter_add(t3dev); +} + +/** + * close_s3_dev - de-register with cxgb3 LLD + * @t3dev: cxgb3 adapter instance + */ +static void close_s3_dev(struct t3cdev *t3dev) +{ + cxgb3i_adapter_remove(t3dev); + cxgb3i_sdev_remove(t3dev); +} + +/** + * cxgb3i_init_module - module init entry point + * + * initialize any driver wide global data structures and register itself + * with the cxgb3 module + */ +static int __init cxgb3i_init_module(void) +{ + int err; + + err = cxgb3i_sdev_init(cxgb3i_cpl_handlers); + if (err < 0) + return err; + + err = cxgb3i_iscsi_init(); + if (err < 0) + return err; + + err = cxgb3i_pdu_init(); + if (err < 0) + return err; + + cxgb3_register_client(&t3c_client); + + return 0; +} + +/** + * cxgb3i_exit_module - module cleanup/exit entry point + * + * go through the driver hba list and for each hba, release any resource held. + * and unregisters iscsi transport and the cxgb3 module + */ +static void __exit cxgb3i_exit_module(void) +{ + cxgb3_unregister_client(&t3c_client); + cxgb3i_pdu_cleanup(); + cxgb3i_iscsi_cleanup(); + cxgb3i_sdev_cleanup(); +} + +module_init(cxgb3i_init_module); +module_exit(cxgb3i_exit_module); diff --git a/drivers/scsi/cxgb3i/cxgb3i_iscsi.c b/drivers/scsi/cxgb3i/cxgb3i_iscsi.c new file mode 100644 index 00000000000..d83464b9b3f --- /dev/null +++ b/drivers/scsi/cxgb3i/cxgb3i_iscsi.c @@ -0,0 +1,951 @@ +/* cxgb3i_iscsi.c: Chelsio S3xx iSCSI driver. + * + * Copyright (c) 2008 Chelsio Communications, Inc. + * Copyright (c) 2008 Mike Christie + * Copyright (c) 2008 Red Hat, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + * + * Written by: Karen Xie (kxie@chelsio.com) + */ + +#include <linux/inet.h> +#include <linux/crypto.h> +#include <net/tcp.h> +#include <scsi/scsi_cmnd.h> +#include <scsi/scsi_device.h> +#include <scsi/scsi_eh.h> +#include <scsi/scsi_host.h> +#include <scsi/scsi.h> +#include <scsi/iscsi_proto.h> +#include <scsi/libiscsi.h> +#include <scsi/scsi_transport_iscsi.h> + +#include "cxgb3i.h" +#include "cxgb3i_pdu.h" + +#ifdef __DEBUG_CXGB3I_TAG__ +#define cxgb3i_tag_debug cxgb3i_log_debug +#else +#define cxgb3i_tag_debug(fmt...) +#endif + +#ifdef __DEBUG_CXGB3I_API__ +#define cxgb3i_api_debug cxgb3i_log_debug +#else +#define cxgb3i_api_debug(fmt...) +#endif + +/* + * align pdu size to multiple of 512 for better performance + */ +#define align_pdu_size(n) do { n = (n) & (~511); } while (0) + +static struct scsi_transport_template *cxgb3i_scsi_transport; +static struct scsi_host_template cxgb3i_host_template; +static struct iscsi_transport cxgb3i_iscsi_transport; +static unsigned char sw_tag_idx_bits; +static unsigned char sw_tag_age_bits; + +static LIST_HEAD(cxgb3i_snic_list); +static DEFINE_RWLOCK(cxgb3i_snic_rwlock); + +/** + * cxgb3i_adapter_add - init a s3 adapter structure and any h/w settings + * @t3dev: t3cdev adapter + * return the resulting cxgb3i_adapter struct + */ +struct cxgb3i_adapter *cxgb3i_adapter_add(struct t3cdev *t3dev) +{ + struct cxgb3i_adapter *snic; + struct adapter *adapter = tdev2adap(t3dev); + int i; + + snic = kzalloc(sizeof(*snic), GFP_KERNEL); + if (!snic) { + cxgb3i_api_debug("cxgb3 %s, OOM.\n", t3dev->name); + return NULL; + } + spin_lock_init(&snic->lock); + + snic->tdev = t3dev; + snic->pdev = adapter->pdev; + snic->tag_format.sw_bits = sw_tag_idx_bits + sw_tag_age_bits; + + if (cxgb3i_adapter_ddp_init(t3dev, &snic->tag_format, + &snic->tx_max_size, + &snic->rx_max_size) < 0) + goto free_snic; + + for_each_port(adapter, i) { + snic->hba[i] = cxgb3i_hba_host_add(snic, adapter->port[i]); + if (!snic->hba[i]) + goto ulp_cleanup; + } + snic->hba_cnt = adapter->params.nports; + + /* add to the list */ + write_lock(&cxgb3i_snic_rwlock); + list_add_tail(&snic->list_head, &cxgb3i_snic_list); + write_unlock(&cxgb3i_snic_rwlock); + + return snic; + +ulp_cleanup: + cxgb3i_adapter_ddp_cleanup(t3dev); +free_snic: + kfree(snic); + return NULL; +} + +/** + * cxgb3i_adapter_remove - release all the resources held and cleanup any + * h/w settings + * @t3dev: t3cdev adapter + */ +void cxgb3i_adapter_remove(struct t3cdev *t3dev) +{ + int i; + struct cxgb3i_adapter *snic; + + /* remove from the list */ + write_lock(&cxgb3i_snic_rwlock); + list_for_each_entry(snic, &cxgb3i_snic_list, list_head) { + if (snic->tdev == t3dev) { + list_del(&snic->list_head); + break; + } + } + write_unlock(&cxgb3i_snic_rwlock); + + if (snic) { + for (i = 0; i < snic->hba_cnt; i++) { + if (snic->hba[i]) { + cxgb3i_hba_host_remove(snic->hba[i]); + snic->hba[i] = NULL; + } + } + + /* release ddp resources */ + cxgb3i_adapter_ddp_cleanup(snic->tdev); + kfree(snic); + } +} + +/** + * cxgb3i_hba_find_by_netdev - find the cxgb3i_hba structure with a given + * net_device + * @t3dev: t3cdev adapter + */ +struct cxgb3i_hba *cxgb3i_hba_find_by_netdev(struct net_device *ndev) +{ + struct cxgb3i_adapter *snic; + int i; + + read_lock(&cxgb3i_snic_rwlock); + list_for_each_entry(snic, &cxgb3i_snic_list, list_head) { + for (i = 0; i < snic->hba_cnt; i++) { + if (snic->hba[i]->ndev == ndev) { + read_unlock(&cxgb3i_snic_rwlock); + return snic->hba[i]; + } + } + } + read_unlock(&cxgb3i_snic_rwlock); + return NULL; +} + +/** + * cxgb3i_hba_host_add - register a new host with scsi/iscsi + * @snic: the cxgb3i adapter + * @ndev: associated net_device + */ +struct cxgb3i_hba *cxgb3i_hba_host_add(struct cxgb3i_adapter *snic, + struct net_device *ndev) +{ + struct cxgb3i_hba *hba; + struct Scsi_Host *shost; + int err; + + shost = iscsi_host_alloc(&cxgb3i_host_template, + sizeof(struct cxgb3i_hba), + CXGB3I_SCSI_QDEPTH_DFLT); + if (!shost) { + cxgb3i_log_info("iscsi_host_alloc failed.\n"); + return NULL; + } + + shost->transportt = cxgb3i_scsi_transport; + shost->max_lun = CXGB3I_MAX_LUN; + shost->max_id = CXGB3I_MAX_TARGET; + shost->max_channel = 0; + shost->max_cmd_len = 16; + + hba = iscsi_host_priv(shost); + hba->snic = snic; + hba->ndev = ndev; + hba->shost = shost; + + pci_dev_get(snic->pdev); + err = iscsi_host_add(shost, &snic->pdev->dev); + if (err) { + cxgb3i_log_info("iscsi_host_add failed.\n"); + goto pci_dev_put; + } + + cxgb3i_api_debug("shost 0x%p, hba 0x%p, no %u.\n", + shost, hba, shost->host_no); + + return hba; + +pci_dev_put: + pci_dev_put(snic->pdev); + scsi_host_put(shost); + return NULL; +} + +/** + * cxgb3i_hba_host_remove - de-register the host with scsi/iscsi + * @hba: the cxgb3i hba + */ +void cxgb3i_hba_host_remove(struct cxgb3i_hba *hba) +{ + cxgb3i_api_debug("shost 0x%p, hba 0x%p, no %u.\n", + hba->shost, hba, hba->shost->host_no); + iscsi_host_remove(hba->shost); + pci_dev_put(hba->snic->pdev); + iscsi_host_free(hba->shost); +} + +/** + * cxgb3i_ep_connect - establish TCP connection to target portal + * @dst_addr: target IP address + * @non_blocking: blocking or non-blocking call + * + * Initiates a TCP/IP connection to the dst_addr + */ +static struct iscsi_endpoint *cxgb3i_ep_connect(struct sockaddr *dst_addr, + int non_blocking) +{ + struct iscsi_endpoint *ep; + struct cxgb3i_endpoint *cep; + struct cxgb3i_hba *hba; + struct s3_conn *c3cn = NULL; + int err = 0; + + c3cn = cxgb3i_c3cn_create(); + if (!c3cn) { + cxgb3i_log_info("ep connect OOM.\n"); + err = -ENOMEM; + goto release_conn; + } + + err = cxgb3i_c3cn_connect(c3cn, (struct sockaddr_in *)dst_addr); + if (err < 0) { + cxgb3i_log_info("ep connect failed.\n"); + goto release_conn; + } + hba = cxgb3i_hba_find_by_netdev(c3cn->dst_cache->dev); + if (!hba) { + err = -ENOSPC; + cxgb3i_log_info("NOT going through cxgbi device.\n"); + goto release_conn; + } + if (c3cn_is_closing(c3cn)) { + err = -ENOSPC; + cxgb3i_log_info("ep connect unable to connect.\n"); + goto release_conn; + } + + ep = iscsi_create_endpoint(sizeof(*cep)); + if (!ep) { + err = -ENOMEM; + cxgb3i_log_info("iscsi alloc ep, OOM.\n"); + goto release_conn; + } + cep = ep->dd_data; + cep->c3cn = c3cn; + cep->hba = hba; + + cxgb3i_api_debug("ep 0x%p, 0x%p, c3cn 0x%p, hba 0x%p.\n", + ep, cep, c3cn, hba); + return ep; + +release_conn: + cxgb3i_api_debug("conn 0x%p failed, release.\n", c3cn); + if (c3cn) + cxgb3i_c3cn_release(c3cn); + return ERR_PTR(err); +} + +/** + * cxgb3i_ep_poll - polls for TCP connection establishement + * @ep: TCP connection (endpoint) handle + * @timeout_ms: timeout value in milli secs + * + * polls for TCP connect request to complete + */ +static int cxgb3i_ep_poll(struct iscsi_endpoint *ep, int timeout_ms) +{ + struct cxgb3i_endpoint *cep = ep->dd_data; + struct s3_conn *c3cn = cep->c3cn; + + if (!c3cn_is_established(c3cn)) + return 0; + cxgb3i_api_debug("ep 0x%p, c3cn 0x%p established.\n", ep, c3cn); + return 1; +} + +/** + * cxgb3i_ep_disconnect - teardown TCP connection + * @ep: TCP connection (endpoint) handle + * + * teardown TCP connection + */ +static void cxgb3i_ep_disconnect(struct iscsi_endpoint *ep) +{ + struct cxgb3i_endpoint *cep = ep->dd_data; + struct cxgb3i_conn *cconn = cep->cconn; + + cxgb3i_api_debug("ep 0x%p, cep 0x%p.\n", ep, cep); + + if (cconn && cconn->conn) { + /* + * stop the xmit path so the xmit_pdu function is + * not being called + */ + iscsi_suspend_tx(cconn->conn); + + write_lock_bh(&cep->c3cn->callback_lock); + cep->c3cn->user_data = NULL; + cconn->cep = NULL; + write_unlock_bh(&cep->c3cn->callback_lock); + } + + cxgb3i_api_debug("ep 0x%p, cep 0x%p, release c3cn 0x%p.\n", + ep, cep, cep->c3cn); + cxgb3i_c3cn_release(cep->c3cn); + iscsi_destroy_endpoint(ep); +} + +/** + * cxgb3i_session_create - create a new iscsi session + * @cmds_max: max # of commands + * @qdepth: scsi queue depth + * @initial_cmdsn: initial iscsi CMDSN for this session + * @host_no: pointer to return host no + * + * Creates a new iSCSI session + */ +static struct iscsi_cls_session * +cxgb3i_session_create(struct iscsi_endpoint *ep, u16 cmds_max, u16 qdepth, + u32 initial_cmdsn, u32 *host_no) +{ + struct cxgb3i_endpoint *cep; + struct cxgb3i_hba *hba; + struct Scsi_Host *shost; + struct iscsi_cls_session *cls_session; + struct iscsi_session *session; + + if (!ep) { + cxgb3i_log_error("%s, missing endpoint.\n", __func__); + return NULL; + } + + cep = ep->dd_data; + hba = cep->hba; + shost = hba->shost; + cxgb3i_api_debug("ep 0x%p, cep 0x%p, hba 0x%p.\n", ep, cep, hba); + BUG_ON(hba != iscsi_host_priv(shost)); + + *host_no = shost->host_no; + + cls_session = iscsi_session_setup(&cxgb3i_iscsi_transport, shost, + cmds_max, + sizeof(struct iscsi_tcp_task), + initial_cmdsn, ISCSI_MAX_TARGET); + if (!cls_session) + return NULL; + session = cls_session->dd_data; + if (iscsi_tcp_r2tpool_alloc(session)) + goto remove_session; + + return cls_session; + +remove_session: + iscsi_session_teardown(cls_session); + return NULL; +} + +/** + * cxgb3i_session_destroy - destroys iscsi session + * @cls_session: pointer to iscsi cls session + * + * Destroys an iSCSI session instance and releases its all resources held + */ +static void cxgb3i_session_destroy(struct iscsi_cls_session *cls_session) +{ + cxgb3i_api_debug("sess 0x%p.\n", cls_session); + iscsi_tcp_r2tpool_free(cls_session->dd_data); + iscsi_session_teardown(cls_session); +} + +/** + * cxgb3i_conn_max_xmit_dlength -- check the max. xmit pdu segment size, + * reduce it to be within the hardware limit if needed + * @conn: iscsi connection + */ +static inline int cxgb3i_conn_max_xmit_dlength(struct iscsi_conn *conn) + +{ + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct cxgb3i_conn *cconn = tcp_conn->dd_data; + unsigned int max = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD, + cconn->hba->snic->tx_max_size - + ISCSI_PDU_NONPAYLOAD_MAX); + + if (conn->max_xmit_dlength) + conn->max_xmit_dlength = min_t(unsigned int, + conn->max_xmit_dlength, max); + else + conn->max_xmit_dlength = max; + align_pdu_size(conn->max_xmit_dlength); + cxgb3i_log_info("conn 0x%p, max xmit %u.\n", + conn, conn->max_xmit_dlength); + return 0; +} + +/** + * cxgb3i_conn_max_recv_dlength -- check the max. recv pdu segment size against + * the hardware limit + * @conn: iscsi connection + * return 0 if the value is valid, < 0 otherwise. + */ +static inline int cxgb3i_conn_max_recv_dlength(struct iscsi_conn *conn) +{ + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct cxgb3i_conn *cconn = tcp_conn->dd_data; + unsigned int max = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD, + cconn->hba->snic->rx_max_size - + ISCSI_PDU_NONPAYLOAD_MAX); + + align_pdu_size(max); + if (conn->max_recv_dlength) { + if (conn->max_recv_dlength > max) { + cxgb3i_log_error("MaxRecvDataSegmentLength %u too big." + " Need to be <= %u.\n", + conn->max_recv_dlength, max); + return -EINVAL; + } + conn->max_recv_dlength = min_t(unsigned int, + conn->max_recv_dlength, max); + align_pdu_size(conn->max_recv_dlength); + } else + conn->max_recv_dlength = max; + cxgb3i_api_debug("conn 0x%p, max recv %u.\n", + conn, conn->max_recv_dlength); + return 0; +} + +/** + * cxgb3i_conn_create - create iscsi connection instance + * @cls_session: pointer to iscsi cls session + * @cid: iscsi cid + * + * Creates a new iSCSI connection instance for a given session + */ +static struct iscsi_cls_conn *cxgb3i_conn_create(struct iscsi_cls_session + *cls_session, u32 cid) +{ + struct iscsi_cls_conn *cls_conn; + struct iscsi_conn *conn; + struct iscsi_tcp_conn *tcp_conn; + struct cxgb3i_conn *cconn; + + cxgb3i_api_debug("sess 0x%p, cid %u.\n", cls_session, cid); + + cls_conn = iscsi_tcp_conn_setup(cls_session, sizeof(*cconn), cid); + if (!cls_conn) + return NULL; + conn = cls_conn->dd_data; + tcp_conn = conn->dd_data; + cconn = tcp_conn->dd_data; + + cconn->conn = conn; + return cls_conn; +} + +/** + * cxgb3i_conn_bind - binds iscsi sess, conn and endpoint together + * @cls_session: pointer to iscsi cls session + * @cls_conn: pointer to iscsi cls conn + * @transport_eph: 64-bit EP handle + * @is_leading: leading connection on this session? + * + * Binds together an iSCSI session, an iSCSI connection and a + * TCP connection. This routine returns error code if the TCP + * connection does not belong on the device iSCSI sess/conn is bound + */ + +static int cxgb3i_conn_bind(struct iscsi_cls_session *cls_session, + struct iscsi_cls_conn *cls_conn, + u64 transport_eph, int is_leading) +{ + struct iscsi_conn *conn = cls_conn->dd_data; + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct cxgb3i_conn *cconn = tcp_conn->dd_data; + struct cxgb3i_adapter *snic; + struct iscsi_endpoint *ep; + struct cxgb3i_endpoint *cep; + struct s3_conn *c3cn; + int err; + + ep = iscsi_lookup_endpoint(transport_eph); + if (!ep) + return -EINVAL; + + /* setup ddp pagesize */ + cep = ep->dd_data; + c3cn = cep->c3cn; + snic = cep->hba->snic; + err = cxgb3i_setup_conn_host_pagesize(snic->tdev, c3cn->tid, 0); + if (err < 0) + return err; + + cxgb3i_api_debug("ep 0x%p, cls sess 0x%p, cls conn 0x%p.\n", + ep, cls_session, cls_conn); + + err = iscsi_conn_bind(cls_session, cls_conn, is_leading); + if (err) + return -EINVAL; + + /* calculate the tag idx bits needed for this conn based on cmds_max */ + cconn->task_idx_bits = (__ilog2_u32(conn->session->cmds_max - 1)) + 1; + cxgb3i_api_debug("session cmds_max 0x%x, bits %u.\n", + conn->session->cmds_max, cconn->task_idx_bits); + + read_lock(&c3cn->callback_lock); + c3cn->user_data = conn; + cconn->hba = cep->hba; + cconn->cep = cep; + cep->cconn = cconn; + read_unlock(&c3cn->callback_lock); + + cxgb3i_conn_max_xmit_dlength(conn); + cxgb3i_conn_max_recv_dlength(conn); + + spin_lock_bh(&conn->session->lock); + sprintf(conn->portal_address, NIPQUAD_FMT, + NIPQUAD(c3cn->daddr.sin_addr.s_addr)); + conn->portal_port = ntohs(c3cn->daddr.sin_port); + spin_unlock_bh(&conn->session->lock); + + /* init recv engine */ + iscsi_tcp_hdr_recv_prep(tcp_conn); + + return 0; +} + +/** + * cxgb3i_conn_get_param - return iscsi connection parameter to caller + * @cls_conn: pointer to iscsi cls conn + * @param: parameter type identifier + * @buf: buffer pointer + * + * returns iSCSI connection parameters + */ +static int cxgb3i_conn_get_param(struct iscsi_cls_conn *cls_conn, + enum iscsi_param param, char *buf) +{ + struct iscsi_conn *conn = cls_conn->dd_data; + int len; + + cxgb3i_api_debug("cls_conn 0x%p, param %d.\n", cls_conn, param); + + switch (param) { + case ISCSI_PARAM_CONN_PORT: + spin_lock_bh(&conn->session->lock); + len = sprintf(buf, "%hu\n", conn->portal_port); + spin_unlock_bh(&conn->session->lock); + break; + case ISCSI_PARAM_CONN_ADDRESS: + spin_lock_bh(&conn->session->lock); + len = sprintf(buf, "%s\n", conn->portal_address); + spin_unlock_bh(&conn->session->lock); + break; + default: + return iscsi_conn_get_param(cls_conn, param, buf); + } + + return len; +} + +/** + * cxgb3i_conn_set_param - set iscsi connection parameter + * @cls_conn: pointer to iscsi cls conn + * @param: parameter type identifier + * @buf: buffer pointer + * @buflen: buffer length + * + * set iSCSI connection parameters + */ +static int cxgb3i_conn_set_param(struct iscsi_cls_conn *cls_conn, + enum iscsi_param param, char *buf, int buflen) +{ + struct iscsi_conn *conn = cls_conn->dd_data; + struct iscsi_session *session = conn->session; + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct cxgb3i_conn *cconn = tcp_conn->dd_data; + struct cxgb3i_adapter *snic = cconn->hba->snic; + struct s3_conn *c3cn = cconn->cep->c3cn; + int value, err = 0; + + switch (param) { + case ISCSI_PARAM_HDRDGST_EN: + err = iscsi_set_param(cls_conn, param, buf, buflen); + if (!err && conn->hdrdgst_en) + err = cxgb3i_setup_conn_digest(snic->tdev, c3cn->tid, + conn->hdrdgst_en, + conn->datadgst_en, 0); + break; + case ISCSI_PARAM_DATADGST_EN: + err = iscsi_set_param(cls_conn, param, buf, buflen); + if (!err && conn->datadgst_en) + err = cxgb3i_setup_conn_digest(snic->tdev, c3cn->tid, + conn->hdrdgst_en, + conn->datadgst_en, 0); + break; + case ISCSI_PARAM_MAX_R2T: + sscanf(buf, "%d", &value); + if (value <= 0 || !is_power_of_2(value)) + return -EINVAL; + if (session->max_r2t == value) + break; + iscsi_tcp_r2tpool_free(session); + err = iscsi_set_param(cls_conn, param, buf, buflen); + if (!err && iscsi_tcp_r2tpool_alloc(session)) + return -ENOMEM; + case ISCSI_PARAM_MAX_RECV_DLENGTH: + err = iscsi_set_param(cls_conn, param, buf, buflen); + if (!err) + err = cxgb3i_conn_max_recv_dlength(conn); + break; + case ISCSI_PARAM_MAX_XMIT_DLENGTH: + err = iscsi_set_param(cls_conn, param, buf, buflen); + if (!err) + err = cxgb3i_conn_max_xmit_dlength(conn); + break; + default: + return iscsi_set_param(cls_conn, param, buf, buflen); + } + return err; +} + +/** + * cxgb3i_host_set_param - configure host (adapter) related parameters + * @shost: scsi host pointer + * @param: parameter type identifier + * @buf: buffer pointer + */ +static int cxgb3i_host_set_param(struct Scsi_Host *shost, + enum iscsi_host_param param, + char *buf, int buflen) +{ + struct cxgb3i_hba *hba = iscsi_host_priv(shost); + + cxgb3i_api_debug("param %d, buf %s.\n", param, buf); + + switch (param) { + case ISCSI_HOST_PARAM_IPADDRESS: + { + __be32 addr = in_aton(buf); + cxgb3i_set_private_ipv4addr(hba->ndev, addr); + return 0; + } + case ISCSI_HOST_PARAM_HWADDRESS: + case ISCSI_HOST_PARAM_NETDEV_NAME: + /* ignore */ + return 0; + default: + return iscsi_host_set_param(shost, param, buf, buflen); + } +} + +/** + * cxgb3i_host_get_param - returns host (adapter) related parameters + * @shost: scsi host pointer + * @param: parameter type identifier + * @buf: buffer pointer + */ +static int cxgb3i_host_get_param(struct Scsi_Host *shost, + enum iscsi_host_param param, char *buf) +{ + struct cxgb3i_hba *hba = iscsi_host_priv(shost); + int len = 0; + + cxgb3i_api_debug("hba %s, param %d.\n", hba->ndev->name, param); + + switch (param) { + case ISCSI_HOST_PARAM_HWADDRESS: + len = sysfs_format_mac(buf, hba->ndev->dev_addr, 6); + break; + case ISCSI_HOST_PARAM_NETDEV_NAME: + len = sprintf(buf, "%s\n", hba->ndev->name); + break; + case ISCSI_HOST_PARAM_IPADDRESS: + { + __be32 addr; + + addr = cxgb3i_get_private_ipv4addr(hba->ndev); + len = sprintf(buf, NIPQUAD_FMT, NIPQUAD(addr)); + break; + } + default: + return iscsi_host_get_param(shost, param, buf); + } + return len; +} + +/** + * cxgb3i_conn_get_stats - returns iSCSI stats + * @cls_conn: pointer to iscsi cls conn + * @stats: pointer to iscsi statistic struct + */ +static void cxgb3i_conn_get_stats(struct iscsi_cls_conn *cls_conn, + struct iscsi_stats *stats) +{ + struct iscsi_conn *conn = cls_conn->dd_data; + + stats->txdata_octets = conn->txdata_octets; + stats->rxdata_octets = conn->rxdata_octets; + stats->scsicmd_pdus = conn->scsicmd_pdus_cnt; + stats->dataout_pdus = conn->dataout_pdus_cnt; + stats->scsirsp_pdus = conn->scsirsp_pdus_cnt; + stats->datain_pdus = conn->datain_pdus_cnt; + stats->r2t_pdus = conn->r2t_pdus_cnt; + stats->tmfcmd_pdus = conn->tmfcmd_pdus_cnt; + stats->tmfrsp_pdus = conn->tmfrsp_pdus_cnt; + stats->digest_err = 0; + stats->timeout_err = 0; + stats->custom_length = 1; + strcpy(stats->custom[0].desc, "eh_abort_cnt"); + stats->custom[0].value = conn->eh_abort_cnt; +} + +/** + * cxgb3i_parse_itt - get the idx and age bits from a given tag + * @conn: iscsi connection + * @itt: itt tag + * @idx: task index, filled in by this function + * @age: session age, filled in by this function + */ +static void cxgb3i_parse_itt(struct iscsi_conn *conn, itt_t itt, + int *idx, int *age) +{ + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct cxgb3i_conn *cconn = tcp_conn->dd_data; + struct cxgb3i_adapter *snic = cconn->hba->snic; + u32 tag = ntohl((__force u32) itt); + u32 sw_bits; + + sw_bits = cxgb3i_tag_nonrsvd_bits(&snic->tag_format, tag); + if (idx) + *idx = sw_bits & ((1 << cconn->task_idx_bits) - 1); + if (age) + *age = (sw_bits >> cconn->task_idx_bits) & ISCSI_AGE_MASK; + + cxgb3i_tag_debug("parse tag 0x%x/0x%x, sw 0x%x, itt 0x%x, age 0x%x.\n", + tag, itt, sw_bits, idx ? *idx : 0xFFFFF, + age ? *age : 0xFF); +} + +/** + * cxgb3i_reserve_itt - generate tag for a give task + * Try to set up ddp for a scsi read task. + * @task: iscsi task + * @hdr_itt: tag, filled in by this function + */ +int cxgb3i_reserve_itt(struct iscsi_task *task, itt_t *hdr_itt) +{ + struct scsi_cmnd *sc = task->sc; + struct iscsi_conn *conn = task->conn; + struct iscsi_session *sess = conn->session; + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct cxgb3i_conn *cconn = tcp_conn->dd_data; + struct cxgb3i_adapter *snic = cconn->hba->snic; + struct cxgb3i_tag_format *tformat = &snic->tag_format; + u32 sw_tag = (sess->age << cconn->task_idx_bits) | task->itt; + u32 tag; + int err = -EINVAL; + + if (sc && + (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_FROM_DEVICE) && + cxgb3i_sw_tag_usable(tformat, sw_tag)) { + struct s3_conn *c3cn = cconn->cep->c3cn; + struct cxgb3i_gather_list *gl; + + gl = cxgb3i_ddp_make_gl(scsi_in(sc)->length, + scsi_in(sc)->table.sgl, + scsi_in(sc)->table.nents, + snic->pdev, + GFP_ATOMIC); + if (gl) { + tag = sw_tag; + err = cxgb3i_ddp_tag_reserve(snic->tdev, c3cn->tid, + tformat, &tag, + gl, GFP_ATOMIC); + if (err < 0) + cxgb3i_ddp_release_gl(gl, snic->pdev); + } + } + + if (err < 0) + tag = cxgb3i_set_non_ddp_tag(tformat, sw_tag); + /* the itt need to sent in big-endian order */ + *hdr_itt = (__force itt_t)htonl(tag); + + cxgb3i_tag_debug("new tag 0x%x/0x%x (itt 0x%x, age 0x%x).\n", + tag, *hdr_itt, task->itt, sess->age); + return 0; +} + +/** + * cxgb3i_release_itt - release the tag for a given task + * if the tag is a ddp tag, release the ddp setup + * @task: iscsi task + * @hdr_itt: tag + */ +void cxgb3i_release_itt(struct iscsi_task *task, itt_t hdr_itt) +{ + struct scsi_cmnd *sc = task->sc; + struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data; + struct cxgb3i_conn *cconn = tcp_conn->dd_data; + struct cxgb3i_adapter *snic = cconn->hba->snic; + struct cxgb3i_tag_format *tformat = &snic->tag_format; + u32 tag = ntohl((__force u32)hdr_itt); + + cxgb3i_tag_debug("release tag 0x%x.\n", tag); + + if (sc && + (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_FROM_DEVICE) && + cxgb3i_is_ddp_tag(tformat, tag)) + cxgb3i_ddp_tag_release(snic->tdev, tag); +} + +/** + * cxgb3i_host_template -- Scsi_Host_Template structure + * used when registering with the scsi mid layer + */ +static struct scsi_host_template cxgb3i_host_template = { + .module = THIS_MODULE, + .name = "Chelsio S3xx iSCSI Initiator", + .proc_name = "cxgb3i", + .queuecommand = iscsi_queuecommand, + .change_queue_depth = iscsi_change_queue_depth, + .can_queue = 128 * (ISCSI_DEF_XMIT_CMDS_MAX - 1), + .sg_tablesize = SG_ALL, + .max_sectors = 0xFFFF, + .cmd_per_lun = ISCSI_DEF_CMD_PER_LUN, + .eh_abort_handler = iscsi_eh_abort, + .eh_device_reset_handler = iscsi_eh_device_reset, + .eh_target_reset_handler = iscsi_eh_target_reset, + .use_clustering = DISABLE_CLUSTERING, + .this_id = -1, +}; + +static struct iscsi_transport cxgb3i_iscsi_transport = { + .owner = THIS_MODULE, + .name = "cxgb3i", + .caps = CAP_RECOVERY_L0 | CAP_MULTI_R2T | CAP_HDRDGST + | CAP_DATADGST | CAP_DIGEST_OFFLOAD | + CAP_PADDING_OFFLOAD, + .param_mask = ISCSI_MAX_RECV_DLENGTH | + ISCSI_MAX_XMIT_DLENGTH | + ISCSI_HDRDGST_EN | + ISCSI_DATADGST_EN | + ISCSI_INITIAL_R2T_EN | + ISCSI_MAX_R2T | + ISCSI_IMM_DATA_EN | + ISCSI_FIRST_BURST | + ISCSI_MAX_BURST | + ISCSI_PDU_INORDER_EN | + ISCSI_DATASEQ_INORDER_EN | + ISCSI_ERL | + ISCSI_CONN_PORT | + ISCSI_CONN_ADDRESS | + ISCSI_EXP_STATSN | + ISCSI_PERSISTENT_PORT | + ISCSI_PERSISTENT_ADDRESS | + ISCSI_TARGET_NAME | ISCSI_TPGT | + ISCSI_USERNAME | ISCSI_PASSWORD | + ISCSI_USERNAME_IN | ISCSI_PASSWORD_IN | + ISCSI_FAST_ABORT | ISCSI_ABORT_TMO | + ISCSI_LU_RESET_TMO | + ISCSI_PING_TMO | ISCSI_RECV_TMO | + ISCSI_IFACE_NAME | ISCSI_INITIATOR_NAME, + .host_param_mask = ISCSI_HOST_HWADDRESS | ISCSI_HOST_IPADDRESS | + ISCSI_HOST_INITIATOR_NAME | ISCSI_HOST_NETDEV_NAME, + .get_host_param = cxgb3i_host_get_param, + .set_host_param = cxgb3i_host_set_param, + /* session management */ + .create_session = cxgb3i_session_create, + .destroy_session = cxgb3i_session_destroy, + .get_session_param = iscsi_session_get_param, + /* connection management */ + .create_conn = cxgb3i_conn_create, + .bind_conn = cxgb3i_conn_bind, + .destroy_conn = iscsi_tcp_conn_teardown, + .start_conn = iscsi_conn_start, + .stop_conn = iscsi_conn_stop, + .get_conn_param = cxgb3i_conn_get_param, + .set_param = cxgb3i_conn_set_param, + .get_stats = cxgb3i_conn_get_stats, + /* pdu xmit req. from user space */ + .send_pdu = iscsi_conn_send_pdu, + /* task */ + .init_task = iscsi_tcp_task_init, + .xmit_task = iscsi_tcp_task_xmit, + .cleanup_task = cxgb3i_conn_cleanup_task, + + /* pdu */ + .alloc_pdu = cxgb3i_conn_alloc_pdu, + .init_pdu = cxgb3i_conn_init_pdu, + .xmit_pdu = cxgb3i_conn_xmit_pdu, + .parse_pdu_itt = cxgb3i_parse_itt, + + /* TCP connect/disconnect */ + .ep_connect = cxgb3i_ep_connect, + .ep_poll = cxgb3i_ep_poll, + .ep_disconnect = cxgb3i_ep_disconnect, + /* Error recovery timeout call */ + .session_recovery_timedout = iscsi_session_recovery_timedout, +}; + +int cxgb3i_iscsi_init(void) +{ + sw_tag_idx_bits = (__ilog2_u32(ISCSI_ITT_MASK)) + 1; + sw_tag_age_bits = (__ilog2_u32(ISCSI_AGE_MASK)) + 1; + cxgb3i_log_info("tag itt 0x%x, %u bits, age 0x%x, %u bits.\n", + ISCSI_ITT_MASK, sw_tag_idx_bits, + ISCSI_AGE_MASK, sw_tag_age_bits); + + cxgb3i_scsi_transport = + iscsi_register_transport(&cxgb3i_iscsi_transport); + if (!cxgb3i_scsi_transport) { + cxgb3i_log_error("Could not register cxgb3i transport.\n"); + return -ENODEV; + } + cxgb3i_api_debug("cxgb3i transport 0x%p.\n", cxgb3i_scsi_transport); + return 0; +} + +void cxgb3i_iscsi_cleanup(void) +{ + if (cxgb3i_scsi_transport) { + cxgb3i_api_debug("cxgb3i transport 0x%p.\n", + cxgb3i_scsi_transport); + iscsi_unregister_transport(&cxgb3i_iscsi_transport); + } +} diff --git a/drivers/scsi/cxgb3i/cxgb3i_offload.c b/drivers/scsi/cxgb3i/cxgb3i_offload.c new file mode 100644 index 00000000000..5f16081b68d --- /dev/null +++ b/drivers/scsi/cxgb3i/cxgb3i_offload.c @@ -0,0 +1,1810 @@ +/* + * cxgb3i_offload.c: Chelsio S3xx iscsi offloaded tcp connection management + * + * Copyright (C) 2003-2008 Chelsio Communications. All rights reserved. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the LICENSE file included in this + * release for licensing terms and conditions. + * + * Written by: Dimitris Michailidis (dm@chelsio.com) + * Karen Xie (kxie@chelsio.com) + */ + +#include <linux/if_vlan.h> +#include <linux/version.h> + +#include "cxgb3_defs.h" +#include "cxgb3_ctl_defs.h" +#include "firmware_exports.h" +#include "cxgb3i_offload.h" +#include "cxgb3i_pdu.h" +#include "cxgb3i_ddp.h" + +#ifdef __DEBUG_C3CN_CONN__ +#define c3cn_conn_debug cxgb3i_log_info +#else +#define c3cn_conn_debug(fmt...) +#endif + +#ifdef __DEBUG_C3CN_TX__ +#define c3cn_tx_debug cxgb3i_log_debug +#else +#define c3cn_tx_debug(fmt...) +#endif + +#ifdef __DEBUG_C3CN_RX__ +#define c3cn_rx_debug cxgb3i_log_debug +#else +#define c3cn_rx_debug(fmt...) +#endif + +/* + * module parameters releated to offloaded iscsi connection + */ +static int cxgb3_rcv_win = 256 * 1024; +module_param(cxgb3_rcv_win, int, 0644); +MODULE_PARM_DESC(cxgb3_rcv_win, "TCP receive window in bytes (default=256KB)"); + +static int cxgb3_snd_win = 64 * 1024; +module_param(cxgb3_snd_win, int, 0644); +MODULE_PARM_DESC(cxgb3_snd_win, "TCP send window in bytes (default=64KB)"); + +static int cxgb3_rx_credit_thres = 10 * 1024; +module_param(cxgb3_rx_credit_thres, int, 0644); +MODULE_PARM_DESC(rx_credit_thres, + "RX credits return threshold in bytes (default=10KB)"); + +static unsigned int cxgb3_max_connect = 8 * 1024; +module_param(cxgb3_max_connect, uint, 0644); +MODULE_PARM_DESC(cxgb3_max_connect, "Max. # of connections (default=8092)"); + +static unsigned int cxgb3_sport_base = 20000; +module_param(cxgb3_sport_base, uint, 0644); +MODULE_PARM_DESC(cxgb3_sport_base, "starting port number (default=20000)"); + +/* + * cxgb3i tcp connection data(per adapter) list + */ +static LIST_HEAD(cdata_list); +static DEFINE_RWLOCK(cdata_rwlock); + +static int c3cn_push_tx_frames(struct s3_conn *c3cn, int req_completion); +static void c3cn_release_offload_resources(struct s3_conn *c3cn); + +/* + * iscsi source port management + * + * Find a free source port in the port allocation map. We use a very simple + * rotor scheme to look for the next free port. + * + * If a source port has been specified make sure that it doesn't collide with + * our normal source port allocation map. If it's outside the range of our + * allocation/deallocation scheme just let them use it. + * + * If the source port is outside our allocation range, the caller is + * responsible for keeping track of their port usage. + */ +static int c3cn_get_port(struct s3_conn *c3cn, struct cxgb3i_sdev_data *cdata) +{ + unsigned int start; + int idx; + + if (!cdata) + goto error_out; + + if (c3cn->saddr.sin_port != 0) { + idx = ntohs(c3cn->saddr.sin_port) - cxgb3_sport_base; + if (idx < 0 || idx >= cxgb3_max_connect) + return 0; + if (!test_and_set_bit(idx, cdata->sport_map)) + return -EADDRINUSE; + } + + /* the sport_map_next may not be accurate but that is okay, sport_map + should be */ + start = idx = cdata->sport_map_next; + do { + if (++idx >= cxgb3_max_connect) + idx = 0; + if (!(test_and_set_bit(idx, cdata->sport_map))) { + c3cn->saddr.sin_port = htons(cxgb3_sport_base + idx); + cdata->sport_map_next = idx; + c3cn_conn_debug("%s reserve port %u.\n", + cdata->cdev->name, + cxgb3_sport_base + idx); + return 0; + } + } while (idx != start); + +error_out: + return -EADDRNOTAVAIL; +} + +static void c3cn_put_port(struct s3_conn *c3cn) +{ + struct cxgb3i_sdev_data *cdata = CXGB3_SDEV_DATA(c3cn->cdev); + + if (c3cn->saddr.sin_port) { + int idx = ntohs(c3cn->saddr.sin_port) - cxgb3_sport_base; + + c3cn->saddr.sin_port = 0; + if (idx < 0 || idx >= cxgb3_max_connect) + return; + clear_bit(idx, cdata->sport_map); + c3cn_conn_debug("%s, release port %u.\n", + cdata->cdev->name, cxgb3_sport_base + idx); + } +} + +static inline void c3cn_set_flag(struct s3_conn *c3cn, enum c3cn_flags flag) +{ + __set_bit(flag, &c3cn->flags); + c3cn_conn_debug("c3cn 0x%p, set %d, s %u, f 0x%lx.\n", + c3cn, flag, c3cn->state, c3cn->flags); +} + +static inline void c3cn_clear_flag(struct s3_conn *c3cn, enum c3cn_flags flag) +{ + __clear_bit(flag, &c3cn->flags); + c3cn_conn_debug("c3cn 0x%p, clear %d, s %u, f 0x%lx.\n", + c3cn, flag, c3cn->state, c3cn->flags); +} + +static inline int c3cn_flag(struct s3_conn *c3cn, enum c3cn_flags flag) +{ + if (c3cn == NULL) + return 0; + return test_bit(flag, &c3cn->flags); +} + +static void c3cn_set_state(struct s3_conn *c3cn, int state) +{ + c3cn_conn_debug("c3cn 0x%p state -> %u.\n", c3cn, state); + c3cn->state = state; +} + +static inline void c3cn_hold(struct s3_conn *c3cn) +{ + atomic_inc(&c3cn->refcnt); +} + +static inline void c3cn_put(struct s3_conn *c3cn) +{ + if (atomic_dec_and_test(&c3cn->refcnt)) { + c3cn_conn_debug("free c3cn 0x%p, s %u, f 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + kfree(c3cn); + } +} + +static void c3cn_closed(struct s3_conn *c3cn) +{ + c3cn_conn_debug("c3cn 0x%p, state %u, flag 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + + c3cn_put_port(c3cn); + c3cn_release_offload_resources(c3cn); + c3cn_set_state(c3cn, C3CN_STATE_CLOSED); + cxgb3i_conn_closing(c3cn); +} + +/* + * CPL (Chelsio Protocol Language) defines a message passing interface between + * the host driver and T3 asic. + * The section below implments CPLs that related to iscsi tcp connection + * open/close/abort and data send/receive. + */ + +/* + * CPL connection active open request: host -> + */ +static unsigned int find_best_mtu(const struct t3c_data *d, unsigned short mtu) +{ + int i = 0; + + while (i < d->nmtus - 1 && d->mtus[i + 1] <= mtu) + ++i; + return i; +} + +static unsigned int select_mss(struct s3_conn *c3cn, unsigned int pmtu) +{ + unsigned int idx; + struct dst_entry *dst = c3cn->dst_cache; + struct t3cdev *cdev = c3cn->cdev; + const struct t3c_data *td = T3C_DATA(cdev); + u16 advmss = dst_metric(dst, RTAX_ADVMSS); + + if (advmss > pmtu - 40) + advmss = pmtu - 40; + if (advmss < td->mtus[0] - 40) + advmss = td->mtus[0] - 40; + idx = find_best_mtu(td, advmss + 40); + return idx; +} + +static inline int compute_wscale(int win) +{ + int wscale = 0; + while (wscale < 14 && (65535<<wscale) < win) + wscale++; + return wscale; +} + +static inline unsigned int calc_opt0h(struct s3_conn *c3cn) +{ + int wscale = compute_wscale(cxgb3_rcv_win); + return V_KEEP_ALIVE(1) | + F_TCAM_BYPASS | + V_WND_SCALE(wscale) | + V_MSS_IDX(c3cn->mss_idx); +} + +static inline unsigned int calc_opt0l(struct s3_conn *c3cn) +{ + return V_ULP_MODE(ULP_MODE_ISCSI) | + V_RCV_BUFSIZ(cxgb3_rcv_win>>10); +} + +static void make_act_open_req(struct s3_conn *c3cn, struct sk_buff *skb, + unsigned int atid, const struct l2t_entry *e) +{ + struct cpl_act_open_req *req; + + c3cn_conn_debug("c3cn 0x%p, atid 0x%x.\n", c3cn, atid); + + skb->priority = CPL_PRIORITY_SETUP; + req = (struct cpl_act_open_req *)__skb_put(skb, sizeof(*req)); + req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD)); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_ACT_OPEN_REQ, atid)); + req->local_port = c3cn->saddr.sin_port; + req->peer_port = c3cn->daddr.sin_port; + req->local_ip = c3cn->saddr.sin_addr.s_addr; + req->peer_ip = c3cn->daddr.sin_addr.s_addr; + req->opt0h = htonl(calc_opt0h(c3cn) | V_L2T_IDX(e->idx) | + V_TX_CHANNEL(e->smt_idx)); + req->opt0l = htonl(calc_opt0l(c3cn)); + req->params = 0; +} + +static void fail_act_open(struct s3_conn *c3cn, int errno) +{ + c3cn_conn_debug("c3cn 0x%p, state %u, flag 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + c3cn->err = errno; + c3cn_closed(c3cn); +} + +static void act_open_req_arp_failure(struct t3cdev *dev, struct sk_buff *skb) +{ + struct s3_conn *c3cn = (struct s3_conn *)skb->sk; + + c3cn_conn_debug("c3cn 0x%p, state %u.\n", c3cn, c3cn->state); + + c3cn_hold(c3cn); + spin_lock_bh(&c3cn->lock); + if (c3cn->state == C3CN_STATE_CONNECTING) + fail_act_open(c3cn, EHOSTUNREACH); + spin_unlock_bh(&c3cn->lock); + c3cn_put(c3cn); + __kfree_skb(skb); +} + +/* + * CPL connection close request: host -> + * + * Close a connection by sending a CPL_CLOSE_CON_REQ message and queue it to + * the write queue (i.e., after any unsent txt data). + */ +static void skb_entail(struct s3_conn *c3cn, struct sk_buff *skb, + int flags) +{ + CXGB3_SKB_CB(skb)->seq = c3cn->write_seq; + CXGB3_SKB_CB(skb)->flags = flags; + __skb_queue_tail(&c3cn->write_queue, skb); +} + +static void send_close_req(struct s3_conn *c3cn) +{ + struct sk_buff *skb = c3cn->cpl_close; + struct cpl_close_con_req *req = (struct cpl_close_con_req *)skb->head; + unsigned int tid = c3cn->tid; + + c3cn_conn_debug("c3cn 0x%p, state 0x%x, flag 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + + c3cn->cpl_close = NULL; + + req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_OFLD_CLOSE_CON)); + req->wr.wr_lo = htonl(V_WR_TID(tid)); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_CLOSE_CON_REQ, tid)); + req->rsvd = htonl(c3cn->write_seq); + + skb_entail(c3cn, skb, C3CB_FLAG_NO_APPEND); + if (c3cn->state != C3CN_STATE_CONNECTING) + c3cn_push_tx_frames(c3cn, 1); +} + +/* + * CPL connection abort request: host -> + * + * Send an ABORT_REQ message. Makes sure we do not send multiple ABORT_REQs + * for the same connection and also that we do not try to send a message + * after the connection has closed. + */ +static void abort_arp_failure(struct t3cdev *cdev, struct sk_buff *skb) +{ + struct cpl_abort_req *req = cplhdr(skb); + + c3cn_conn_debug("tdev 0x%p.\n", cdev); + + req->cmd = CPL_ABORT_NO_RST; + cxgb3_ofld_send(cdev, skb); +} + +static inline void c3cn_purge_write_queue(struct s3_conn *c3cn) +{ + struct sk_buff *skb; + + while ((skb = __skb_dequeue(&c3cn->write_queue))) + __kfree_skb(skb); +} + +static void send_abort_req(struct s3_conn *c3cn) +{ + struct sk_buff *skb = c3cn->cpl_abort_req; + struct cpl_abort_req *req; + unsigned int tid = c3cn->tid; + + if (unlikely(c3cn->state == C3CN_STATE_ABORTING) || !skb || + !c3cn->cdev) + return; + + c3cn_set_state(c3cn, C3CN_STATE_ABORTING); + + c3cn_conn_debug("c3cn 0x%p, flag ABORT_RPL + ABORT_SHUT.\n", c3cn); + + c3cn_set_flag(c3cn, C3CN_ABORT_RPL_PENDING); + + /* Purge the send queue so we don't send anything after an abort. */ + c3cn_purge_write_queue(c3cn); + + c3cn->cpl_abort_req = NULL; + req = (struct cpl_abort_req *)skb->head; + + skb->priority = CPL_PRIORITY_DATA; + set_arp_failure_handler(skb, abort_arp_failure); + + req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_OFLD_HOST_ABORT_CON_REQ)); + req->wr.wr_lo = htonl(V_WR_TID(tid)); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_ABORT_REQ, tid)); + req->rsvd0 = htonl(c3cn->snd_nxt); + req->rsvd1 = !c3cn_flag(c3cn, C3CN_TX_DATA_SENT); + req->cmd = CPL_ABORT_SEND_RST; + + l2t_send(c3cn->cdev, skb, c3cn->l2t); +} + +/* + * CPL connection abort reply: host -> + * + * Send an ABORT_RPL message in response of the ABORT_REQ received. + */ +static void send_abort_rpl(struct s3_conn *c3cn, int rst_status) +{ + struct sk_buff *skb = c3cn->cpl_abort_rpl; + struct cpl_abort_rpl *rpl = (struct cpl_abort_rpl *)skb->head; + + c3cn->cpl_abort_rpl = NULL; + + skb->priority = CPL_PRIORITY_DATA; + rpl->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_OFLD_HOST_ABORT_CON_RPL)); + rpl->wr.wr_lo = htonl(V_WR_TID(c3cn->tid)); + OPCODE_TID(rpl) = htonl(MK_OPCODE_TID(CPL_ABORT_RPL, c3cn->tid)); + rpl->cmd = rst_status; + + cxgb3_ofld_send(c3cn->cdev, skb); +} + +/* + * CPL connection rx data ack: host -> + * Send RX credits through an RX_DATA_ACK CPL message. Returns the number of + * credits sent. + */ +static u32 send_rx_credits(struct s3_conn *c3cn, u32 credits, u32 dack) +{ + struct sk_buff *skb; + struct cpl_rx_data_ack *req; + + skb = alloc_skb(sizeof(*req), GFP_ATOMIC); + if (!skb) + return 0; + + req = (struct cpl_rx_data_ack *)__skb_put(skb, sizeof(*req)); + req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD)); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_RX_DATA_ACK, c3cn->tid)); + req->credit_dack = htonl(dack | V_RX_CREDITS(credits)); + skb->priority = CPL_PRIORITY_ACK; + cxgb3_ofld_send(c3cn->cdev, skb); + return credits; +} + +/* + * CPL connection tx data: host -> + * + * Send iscsi PDU via TX_DATA CPL message. Returns the number of + * credits sent. + * Each TX_DATA consumes work request credit (wrs), so we need to keep track of + * how many we've used so far and how many are pending (i.e., yet ack'ed by T3). + */ + +/* + * For ULP connections HW may inserts digest bytes into the pdu. Those digest + * bytes are not sent by the host but are part of the TCP payload and therefore + * consume TCP sequence space. + */ +static const unsigned int cxgb3_ulp_extra_len[] = { 0, 4, 4, 8 }; +static inline unsigned int ulp_extra_len(const struct sk_buff *skb) +{ + return cxgb3_ulp_extra_len[skb_ulp_mode(skb) & 3]; +} + +static unsigned int wrlen __read_mostly; + +/* + * The number of WRs needed for an skb depends on the number of fragments + * in the skb and whether it has any payload in its main body. This maps the + * length of the gather list represented by an skb into the # of necessary WRs. + * + * The max. length of an skb is controlled by the max pdu size which is ~16K. + * Also, assume the min. fragment length is the sector size (512), then add + * extra fragment counts for iscsi bhs and payload padding. + */ +#define SKB_WR_LIST_SIZE (16384/512 + 3) +static unsigned int skb_wrs[SKB_WR_LIST_SIZE] __read_mostly; + +static void s3_init_wr_tab(unsigned int wr_len) +{ + int i; + + if (skb_wrs[1]) /* already initialized */ + return; + + for (i = 1; i < SKB_WR_LIST_SIZE; i++) { + int sgl_len = (3 * i) / 2 + (i & 1); + + sgl_len += 3; + skb_wrs[i] = (sgl_len <= wr_len + ? 1 : 1 + (sgl_len - 2) / (wr_len - 1)); + } + + wrlen = wr_len * 8; +} + +static inline void reset_wr_list(struct s3_conn *c3cn) +{ + c3cn->wr_pending_head = NULL; +} + +/* + * Add a WR to a connections's list of pending WRs. This is a singly-linked + * list of sk_buffs operating as a FIFO. The head is kept in wr_pending_head + * and the tail in wr_pending_tail. + */ +static inline void enqueue_wr(struct s3_conn *c3cn, + struct sk_buff *skb) +{ + skb->sp = NULL; + + /* + * We want to take an extra reference since both us and the driver + * need to free the packet before it's really freed. We know there's + * just one user currently so we use atomic_set rather than skb_get + * to avoid the atomic op. + */ + atomic_set(&skb->users, 2); + + if (!c3cn->wr_pending_head) + c3cn->wr_pending_head = skb; + else + c3cn->wr_pending_tail->sp = (void *)skb; + c3cn->wr_pending_tail = skb; +} + +static inline struct sk_buff *peek_wr(const struct s3_conn *c3cn) +{ + return c3cn->wr_pending_head; +} + +static inline void free_wr_skb(struct sk_buff *skb) +{ + kfree_skb(skb); +} + +static inline struct sk_buff *dequeue_wr(struct s3_conn *c3cn) +{ + struct sk_buff *skb = c3cn->wr_pending_head; + + if (likely(skb)) { + /* Don't bother clearing the tail */ + c3cn->wr_pending_head = (struct sk_buff *)skb->sp; + skb->sp = NULL; + } + return skb; +} + +static void purge_wr_queue(struct s3_conn *c3cn) +{ + struct sk_buff *skb; + while ((skb = dequeue_wr(c3cn)) != NULL) + free_wr_skb(skb); +} + +static inline void make_tx_data_wr(struct s3_conn *c3cn, struct sk_buff *skb, + int len) +{ + struct tx_data_wr *req; + + skb_reset_transport_header(skb); + req = (struct tx_data_wr *)__skb_push(skb, sizeof(*req)); + req->wr_hi = htonl(V_WR_OP(FW_WROPCODE_OFLD_TX_DATA)); + req->wr_lo = htonl(V_WR_TID(c3cn->tid)); + req->sndseq = htonl(c3cn->snd_nxt); + /* len includes the length of any HW ULP additions */ + req->len = htonl(len); + req->param = htonl(V_TX_PORT(c3cn->l2t->smt_idx)); + /* V_TX_ULP_SUBMODE sets both the mode and submode */ + req->flags = htonl(V_TX_ULP_SUBMODE(skb_ulp_mode(skb)) | + V_TX_SHOVE((skb_peek(&c3cn->write_queue) ? 0 : 1))); + + if (!c3cn_flag(c3cn, C3CN_TX_DATA_SENT)) { + req->flags |= htonl(V_TX_ACK_PAGES(2) | F_TX_INIT | + V_TX_CPU_IDX(c3cn->qset)); + /* Sendbuffer is in units of 32KB. */ + req->param |= htonl(V_TX_SNDBUF(cxgb3_snd_win >> 15)); + c3cn_set_flag(c3cn, C3CN_TX_DATA_SENT); + } +} + +/** + * c3cn_push_tx_frames -- start transmit + * @c3cn: the offloaded connection + * @req_completion: request wr_ack or not + * + * Prepends TX_DATA_WR or CPL_CLOSE_CON_REQ headers to buffers waiting in a + * connection's send queue and sends them on to T3. Must be called with the + * connection's lock held. Returns the amount of send buffer space that was + * freed as a result of sending queued data to T3. + */ +static void arp_failure_discard(struct t3cdev *cdev, struct sk_buff *skb) +{ + kfree_skb(skb); +} + +static int c3cn_push_tx_frames(struct s3_conn *c3cn, int req_completion) +{ + int total_size = 0; + struct sk_buff *skb; + struct t3cdev *cdev; + struct cxgb3i_sdev_data *cdata; + + if (unlikely(c3cn->state == C3CN_STATE_CONNECTING || + c3cn->state == C3CN_STATE_CLOSE_WAIT_1 || + c3cn->state == C3CN_STATE_ABORTING)) { + c3cn_tx_debug("c3cn 0x%p, in closing state %u.\n", + c3cn, c3cn->state); + return 0; + } + + cdev = c3cn->cdev; + cdata = CXGB3_SDEV_DATA(cdev); + + while (c3cn->wr_avail + && (skb = skb_peek(&c3cn->write_queue)) != NULL) { + int len = skb->len; /* length before skb_push */ + int frags = skb_shinfo(skb)->nr_frags + (len != skb->data_len); + int wrs_needed = skb_wrs[frags]; + + if (wrs_needed > 1 && len + sizeof(struct tx_data_wr) <= wrlen) + wrs_needed = 1; + + WARN_ON(frags >= SKB_WR_LIST_SIZE || wrs_needed < 1); + + if (c3cn->wr_avail < wrs_needed) { + c3cn_tx_debug("c3cn 0x%p, skb len %u/%u, frag %u, " + "wr %d < %u.\n", + c3cn, skb->len, skb->datalen, frags, + wrs_needed, c3cn->wr_avail); + break; + } + + __skb_unlink(skb, &c3cn->write_queue); + skb->priority = CPL_PRIORITY_DATA; + skb->csum = wrs_needed; /* remember this until the WR_ACK */ + c3cn->wr_avail -= wrs_needed; + c3cn->wr_unacked += wrs_needed; + enqueue_wr(c3cn, skb); + + if (likely(CXGB3_SKB_CB(skb)->flags & C3CB_FLAG_NEED_HDR)) { + len += ulp_extra_len(skb); + make_tx_data_wr(c3cn, skb, len); + c3cn->snd_nxt += len; + if ((req_completion + && c3cn->wr_unacked == wrs_needed) + || (CXGB3_SKB_CB(skb)->flags & C3CB_FLAG_COMPL) + || c3cn->wr_unacked >= c3cn->wr_max / 2) { + struct work_request_hdr *wr = cplhdr(skb); + + wr->wr_hi |= htonl(F_WR_COMPL); + c3cn->wr_unacked = 0; + } + CXGB3_SKB_CB(skb)->flags &= ~C3CB_FLAG_NEED_HDR; + } + + total_size += skb->truesize; + set_arp_failure_handler(skb, arp_failure_discard); + l2t_send(cdev, skb, c3cn->l2t); + } + return total_size; +} + +/* + * process_cpl_msg: -> host + * Top-level CPL message processing used by most CPL messages that + * pertain to connections. + */ +static inline void process_cpl_msg(void (*fn)(struct s3_conn *, + struct sk_buff *), + struct s3_conn *c3cn, + struct sk_buff *skb) +{ + spin_lock_bh(&c3cn->lock); + fn(c3cn, skb); + spin_unlock_bh(&c3cn->lock); +} + +/* + * process_cpl_msg_ref: -> host + * Similar to process_cpl_msg() but takes an extra connection reference around + * the call to the handler. Should be used if the handler may drop a + * connection reference. + */ +static inline void process_cpl_msg_ref(void (*fn) (struct s3_conn *, + struct sk_buff *), + struct s3_conn *c3cn, + struct sk_buff *skb) +{ + c3cn_hold(c3cn); + process_cpl_msg(fn, c3cn, skb); + c3cn_put(c3cn); +} + +/* + * Process a CPL_ACT_ESTABLISH message: -> host + * Updates connection state from an active establish CPL message. Runs with + * the connection lock held. + */ + +static inline void s3_free_atid(struct t3cdev *cdev, unsigned int tid) +{ + struct s3_conn *c3cn = cxgb3_free_atid(cdev, tid); + if (c3cn) + c3cn_put(c3cn); +} + +static void c3cn_established(struct s3_conn *c3cn, u32 snd_isn, + unsigned int opt) +{ + c3cn_conn_debug("c3cn 0x%p, state %u.\n", c3cn, c3cn->state); + + c3cn->write_seq = c3cn->snd_nxt = c3cn->snd_una = snd_isn; + + /* + * Causes the first RX_DATA_ACK to supply any Rx credits we couldn't + * pass through opt0. + */ + if (cxgb3_rcv_win > (M_RCV_BUFSIZ << 10)) + c3cn->rcv_wup -= cxgb3_rcv_win - (M_RCV_BUFSIZ << 10); + + dst_confirm(c3cn->dst_cache); + + smp_mb(); + + c3cn_set_state(c3cn, C3CN_STATE_ESTABLISHED); +} + +static void process_act_establish(struct s3_conn *c3cn, struct sk_buff *skb) +{ + struct cpl_act_establish *req = cplhdr(skb); + u32 rcv_isn = ntohl(req->rcv_isn); /* real RCV_ISN + 1 */ + + c3cn_conn_debug("c3cn 0x%p, state %u, flag 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + + if (unlikely(c3cn->state != C3CN_STATE_CONNECTING)) + cxgb3i_log_error("TID %u expected SYN_SENT, got EST., s %u\n", + c3cn->tid, c3cn->state); + + c3cn->copied_seq = c3cn->rcv_wup = c3cn->rcv_nxt = rcv_isn; + c3cn_established(c3cn, ntohl(req->snd_isn), ntohs(req->tcp_opt)); + + __kfree_skb(skb); + + if (unlikely(c3cn_flag(c3cn, C3CN_ACTIVE_CLOSE_NEEDED))) + /* upper layer has requested closing */ + send_abort_req(c3cn); + else if (c3cn_push_tx_frames(c3cn, 1)) + cxgb3i_conn_tx_open(c3cn); +} + +static int do_act_establish(struct t3cdev *cdev, struct sk_buff *skb, + void *ctx) +{ + struct cpl_act_establish *req = cplhdr(skb); + unsigned int tid = GET_TID(req); + unsigned int atid = G_PASS_OPEN_TID(ntohl(req->tos_tid)); + struct s3_conn *c3cn = ctx; + struct cxgb3i_sdev_data *cdata = CXGB3_SDEV_DATA(cdev); + + c3cn_conn_debug("rcv, tid 0x%x, c3cn 0x%p, s %u, f 0x%lx.\n", + tid, c3cn, c3cn->state, c3cn->flags); + + c3cn->tid = tid; + c3cn_hold(c3cn); + cxgb3_insert_tid(cdata->cdev, cdata->client, c3cn, tid); + s3_free_atid(cdev, atid); + + c3cn->qset = G_QNUM(ntohl(skb->csum)); + + process_cpl_msg(process_act_establish, c3cn, skb); + return 0; +} + +/* + * Process a CPL_ACT_OPEN_RPL message: -> host + * Handle active open failures. + */ +static int act_open_rpl_status_to_errno(int status) +{ + switch (status) { + case CPL_ERR_CONN_RESET: + return ECONNREFUSED; + case CPL_ERR_ARP_MISS: + return EHOSTUNREACH; + case CPL_ERR_CONN_TIMEDOUT: + return ETIMEDOUT; + case CPL_ERR_TCAM_FULL: + return ENOMEM; + case CPL_ERR_CONN_EXIST: + cxgb3i_log_error("ACTIVE_OPEN_RPL: 4-tuple in use\n"); + return EADDRINUSE; + default: + return EIO; + } +} + +static void act_open_retry_timer(unsigned long data) +{ + struct sk_buff *skb; + struct s3_conn *c3cn = (struct s3_conn *)data; + + c3cn_conn_debug("c3cn 0x%p, state %u.\n", c3cn, c3cn->state); + + spin_lock_bh(&c3cn->lock); + skb = alloc_skb(sizeof(struct cpl_act_open_req), GFP_ATOMIC); + if (!skb) + fail_act_open(c3cn, ENOMEM); + else { + skb->sk = (struct sock *)c3cn; + set_arp_failure_handler(skb, act_open_req_arp_failure); + make_act_open_req(c3cn, skb, c3cn->tid, c3cn->l2t); + l2t_send(c3cn->cdev, skb, c3cn->l2t); + } + spin_unlock_bh(&c3cn->lock); + c3cn_put(c3cn); +} + +static void process_act_open_rpl(struct s3_conn *c3cn, struct sk_buff *skb) +{ + struct cpl_act_open_rpl *rpl = cplhdr(skb); + + c3cn_conn_debug("c3cn 0x%p, state %u, flag 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + + if (rpl->status == CPL_ERR_CONN_EXIST && + c3cn->retry_timer.function != act_open_retry_timer) { + c3cn->retry_timer.function = act_open_retry_timer; + if (!mod_timer(&c3cn->retry_timer, jiffies + HZ / 2)) + c3cn_hold(c3cn); + } else + fail_act_open(c3cn, act_open_rpl_status_to_errno(rpl->status)); + __kfree_skb(skb); +} + +static int do_act_open_rpl(struct t3cdev *cdev, struct sk_buff *skb, void *ctx) +{ + struct s3_conn *c3cn = ctx; + struct cpl_act_open_rpl *rpl = cplhdr(skb); + + c3cn_conn_debug("rcv, status 0x%x, c3cn 0x%p, s %u, f 0x%lx.\n", + rpl->status, c3cn, c3cn->state, c3cn->flags); + + if (rpl->status != CPL_ERR_TCAM_FULL && + rpl->status != CPL_ERR_CONN_EXIST && + rpl->status != CPL_ERR_ARP_MISS) + cxgb3_queue_tid_release(cdev, GET_TID(rpl)); + + process_cpl_msg_ref(process_act_open_rpl, c3cn, skb); + return 0; +} + +/* + * Process PEER_CLOSE CPL messages: -> host + * Handle peer FIN. + */ +static void process_peer_close(struct s3_conn *c3cn, struct sk_buff *skb) +{ + c3cn_conn_debug("c3cn 0x%p, state %u, flag 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + + if (c3cn_flag(c3cn, C3CN_ABORT_RPL_PENDING)) + goto out; + + switch (c3cn->state) { + case C3CN_STATE_ESTABLISHED: + c3cn_set_state(c3cn, C3CN_STATE_PASSIVE_CLOSE); + break; + case C3CN_STATE_ACTIVE_CLOSE: + c3cn_set_state(c3cn, C3CN_STATE_CLOSE_WAIT_2); + break; + case C3CN_STATE_CLOSE_WAIT_1: + c3cn_closed(c3cn); + break; + case C3CN_STATE_ABORTING: + break; + default: + cxgb3i_log_error("%s: peer close, TID %u in bad state %u\n", + c3cn->cdev->name, c3cn->tid, c3cn->state); + } + + cxgb3i_conn_closing(c3cn); +out: + __kfree_skb(skb); +} + +static int do_peer_close(struct t3cdev *cdev, struct sk_buff *skb, void *ctx) +{ + struct s3_conn *c3cn = ctx; + + c3cn_conn_debug("rcv, c3cn 0x%p, s %u, f 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + process_cpl_msg_ref(process_peer_close, c3cn, skb); + return 0; +} + +/* + * Process CLOSE_CONN_RPL CPL message: -> host + * Process a peer ACK to our FIN. + */ +static void process_close_con_rpl(struct s3_conn *c3cn, struct sk_buff *skb) +{ + struct cpl_close_con_rpl *rpl = cplhdr(skb); + + c3cn_conn_debug("c3cn 0x%p, state %u, flag 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + + c3cn->snd_una = ntohl(rpl->snd_nxt) - 1; /* exclude FIN */ + + if (c3cn_flag(c3cn, C3CN_ABORT_RPL_PENDING)) + goto out; + + switch (c3cn->state) { + case C3CN_STATE_ACTIVE_CLOSE: + c3cn_set_state(c3cn, C3CN_STATE_CLOSE_WAIT_1); + break; + case C3CN_STATE_CLOSE_WAIT_1: + case C3CN_STATE_CLOSE_WAIT_2: + c3cn_closed(c3cn); + break; + case C3CN_STATE_ABORTING: + break; + default: + cxgb3i_log_error("%s: close_rpl, TID %u in bad state %u\n", + c3cn->cdev->name, c3cn->tid, c3cn->state); + } + +out: + kfree_skb(skb); +} + +static int do_close_con_rpl(struct t3cdev *cdev, struct sk_buff *skb, + void *ctx) +{ + struct s3_conn *c3cn = ctx; + + c3cn_conn_debug("rcv, c3cn 0x%p, s %u, f 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + + process_cpl_msg_ref(process_close_con_rpl, c3cn, skb); + return 0; +} + +/* + * Process ABORT_REQ_RSS CPL message: -> host + * Process abort requests. If we are waiting for an ABORT_RPL we ignore this + * request except that we need to reply to it. + */ + +static int abort_status_to_errno(struct s3_conn *c3cn, int abort_reason, + int *need_rst) +{ + switch (abort_reason) { + case CPL_ERR_BAD_SYN: /* fall through */ + case CPL_ERR_CONN_RESET: + return c3cn->state > C3CN_STATE_ESTABLISHED ? + EPIPE : ECONNRESET; + case CPL_ERR_XMIT_TIMEDOUT: + case CPL_ERR_PERSIST_TIMEDOUT: + case CPL_ERR_FINWAIT2_TIMEDOUT: + case CPL_ERR_KEEPALIVE_TIMEDOUT: + return ETIMEDOUT; + default: + return EIO; + } +} + +static void process_abort_req(struct s3_conn *c3cn, struct sk_buff *skb) +{ + int rst_status = CPL_ABORT_NO_RST; + const struct cpl_abort_req_rss *req = cplhdr(skb); + + c3cn_conn_debug("c3cn 0x%p, state %u, flag 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + + if (!c3cn_flag(c3cn, C3CN_ABORT_REQ_RCVD)) { + c3cn_set_flag(c3cn, C3CN_ABORT_REQ_RCVD); + c3cn_set_state(c3cn, C3CN_STATE_ABORTING); + __kfree_skb(skb); + return; + } + + c3cn_clear_flag(c3cn, C3CN_ABORT_REQ_RCVD); + send_abort_rpl(c3cn, rst_status); + + if (!c3cn_flag(c3cn, C3CN_ABORT_RPL_PENDING)) { + c3cn->err = + abort_status_to_errno(c3cn, req->status, &rst_status); + c3cn_closed(c3cn); + } +} + +static int do_abort_req(struct t3cdev *cdev, struct sk_buff *skb, void *ctx) +{ + const struct cpl_abort_req_rss *req = cplhdr(skb); + struct s3_conn *c3cn = ctx; + + c3cn_conn_debug("rcv, c3cn 0x%p, s 0x%x, f 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + + if (req->status == CPL_ERR_RTX_NEG_ADVICE || + req->status == CPL_ERR_PERSIST_NEG_ADVICE) { + __kfree_skb(skb); + return 0; + } + + process_cpl_msg_ref(process_abort_req, c3cn, skb); + return 0; +} + +/* + * Process ABORT_RPL_RSS CPL message: -> host + * Process abort replies. We only process these messages if we anticipate + * them as the coordination between SW and HW in this area is somewhat lacking + * and sometimes we get ABORT_RPLs after we are done with the connection that + * originated the ABORT_REQ. + */ +static void process_abort_rpl(struct s3_conn *c3cn, struct sk_buff *skb) +{ + c3cn_conn_debug("c3cn 0x%p, state %u, flag 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + + if (c3cn_flag(c3cn, C3CN_ABORT_RPL_PENDING)) { + if (!c3cn_flag(c3cn, C3CN_ABORT_RPL_RCVD)) + c3cn_set_flag(c3cn, C3CN_ABORT_RPL_RCVD); + else { + c3cn_clear_flag(c3cn, C3CN_ABORT_RPL_RCVD); + c3cn_clear_flag(c3cn, C3CN_ABORT_RPL_PENDING); + if (c3cn_flag(c3cn, C3CN_ABORT_REQ_RCVD)) + cxgb3i_log_error("%s tid %u, ABORT_RPL_RSS\n", + c3cn->cdev->name, c3cn->tid); + c3cn_closed(c3cn); + } + } + __kfree_skb(skb); +} + +static int do_abort_rpl(struct t3cdev *cdev, struct sk_buff *skb, void *ctx) +{ + struct cpl_abort_rpl_rss *rpl = cplhdr(skb); + struct s3_conn *c3cn = ctx; + + c3cn_conn_debug("rcv, status 0x%x, c3cn 0x%p, s %u, 0x%lx.\n", + rpl->status, c3cn, c3cn ? c3cn->state : 0, + c3cn ? c3cn->flags : 0UL); + + /* + * Ignore replies to post-close aborts indicating that the abort was + * requested too late. These connections are terminated when we get + * PEER_CLOSE or CLOSE_CON_RPL and by the time the abort_rpl_rss + * arrives the TID is either no longer used or it has been recycled. + */ + if (rpl->status == CPL_ERR_ABORT_FAILED) + goto discard; + + /* + * Sometimes we've already closed the connection, e.g., a post-close + * abort races with ABORT_REQ_RSS, the latter frees the connection + * expecting the ABORT_REQ will fail with CPL_ERR_ABORT_FAILED, + * but FW turns the ABORT_REQ into a regular one and so we get + * ABORT_RPL_RSS with status 0 and no connection. + */ + if (!c3cn) + goto discard; + + process_cpl_msg_ref(process_abort_rpl, c3cn, skb); + return 0; + +discard: + __kfree_skb(skb); + return 0; +} + +/* + * Process RX_ISCSI_HDR CPL message: -> host + * Handle received PDUs, the payload could be DDP'ed. If not, the payload + * follow after the bhs. + */ +static void process_rx_iscsi_hdr(struct s3_conn *c3cn, struct sk_buff *skb) +{ + struct cpl_iscsi_hdr *hdr_cpl = cplhdr(skb); + struct cpl_iscsi_hdr_norss data_cpl; + struct cpl_rx_data_ddp_norss ddp_cpl; + unsigned int hdr_len, data_len, status; + unsigned int len; + int err; + + if (unlikely(c3cn->state >= C3CN_STATE_PASSIVE_CLOSE)) { + if (c3cn->state != C3CN_STATE_ABORTING) + send_abort_req(c3cn); + __kfree_skb(skb); + return; + } + + CXGB3_SKB_CB(skb)->seq = ntohl(hdr_cpl->seq); + CXGB3_SKB_CB(skb)->flags = 0; + + skb_reset_transport_header(skb); + __skb_pull(skb, sizeof(struct cpl_iscsi_hdr)); + + len = hdr_len = ntohs(hdr_cpl->len); + /* msg coalesce is off or not enough data received */ + if (skb->len <= hdr_len) { + cxgb3i_log_error("%s: TID %u, ISCSI_HDR, skb len %u < %u.\n", + c3cn->cdev->name, c3cn->tid, + skb->len, hdr_len); + goto abort_conn; + } + + err = skb_copy_bits(skb, skb->len - sizeof(ddp_cpl), &ddp_cpl, + sizeof(ddp_cpl)); + if (err < 0) + goto abort_conn; + + skb_ulp_mode(skb) = ULP2_FLAG_DATA_READY; + skb_ulp_pdulen(skb) = ntohs(ddp_cpl.len); + skb_ulp_ddigest(skb) = ntohl(ddp_cpl.ulp_crc); + status = ntohl(ddp_cpl.ddp_status); + + c3cn_rx_debug("rx skb 0x%p, len %u, pdulen %u, ddp status 0x%x.\n", + skb, skb->len, skb_ulp_pdulen(skb), status); + + if (status & (1 << RX_DDP_STATUS_HCRC_SHIFT)) + skb_ulp_mode(skb) |= ULP2_FLAG_HCRC_ERROR; + if (status & (1 << RX_DDP_STATUS_DCRC_SHIFT)) + skb_ulp_mode(skb) |= ULP2_FLAG_DCRC_ERROR; + if (status & (1 << RX_DDP_STATUS_PAD_SHIFT)) + skb_ulp_mode(skb) |= ULP2_FLAG_PAD_ERROR; + + if (skb->len > (hdr_len + sizeof(ddp_cpl))) { + err = skb_copy_bits(skb, hdr_len, &data_cpl, sizeof(data_cpl)); + if (err < 0) + goto abort_conn; + data_len = ntohs(data_cpl.len); + len += sizeof(data_cpl) + data_len; + } else if (status & (1 << RX_DDP_STATUS_DDP_SHIFT)) + skb_ulp_mode(skb) |= ULP2_FLAG_DATA_DDPED; + + c3cn->rcv_nxt = ntohl(ddp_cpl.seq) + skb_ulp_pdulen(skb); + __pskb_trim(skb, len); + __skb_queue_tail(&c3cn->receive_queue, skb); + cxgb3i_conn_pdu_ready(c3cn); + + return; + +abort_conn: + send_abort_req(c3cn); + __kfree_skb(skb); +} + +static int do_iscsi_hdr(struct t3cdev *t3dev, struct sk_buff *skb, void *ctx) +{ + struct s3_conn *c3cn = ctx; + + process_cpl_msg(process_rx_iscsi_hdr, c3cn, skb); + return 0; +} + +/* + * Process TX_DATA_ACK CPL messages: -> host + * Process an acknowledgment of WR completion. Advance snd_una and send the + * next batch of work requests from the write queue. + */ +static void process_wr_ack(struct s3_conn *c3cn, struct sk_buff *skb) +{ + struct cpl_wr_ack *hdr = cplhdr(skb); + unsigned int credits = ntohs(hdr->credits); + u32 snd_una = ntohl(hdr->snd_una); + + c3cn->wr_avail += credits; + if (c3cn->wr_unacked > c3cn->wr_max - c3cn->wr_avail) + c3cn->wr_unacked = c3cn->wr_max - c3cn->wr_avail; + + while (credits) { + struct sk_buff *p = peek_wr(c3cn); + + if (unlikely(!p)) { + cxgb3i_log_error("%u WR_ACK credits for TID %u with " + "nothing pending, state %u\n", + credits, c3cn->tid, c3cn->state); + break; + } + if (unlikely(credits < p->csum)) { + p->csum -= credits; + break; + } else { + dequeue_wr(c3cn); + credits -= p->csum; + free_wr_skb(p); + } + } + + if (unlikely(before(snd_una, c3cn->snd_una))) + goto out_free; + + if (c3cn->snd_una != snd_una) { + c3cn->snd_una = snd_una; + dst_confirm(c3cn->dst_cache); + } + + if (skb_queue_len(&c3cn->write_queue) && c3cn_push_tx_frames(c3cn, 0)) + cxgb3i_conn_tx_open(c3cn); +out_free: + __kfree_skb(skb); +} + +static int do_wr_ack(struct t3cdev *cdev, struct sk_buff *skb, void *ctx) +{ + struct s3_conn *c3cn = ctx; + + process_cpl_msg(process_wr_ack, c3cn, skb); + return 0; +} + +/* + * for each connection, pre-allocate skbs needed for close/abort requests. So + * that we can service the request right away. + */ +static void c3cn_free_cpl_skbs(struct s3_conn *c3cn) +{ + if (c3cn->cpl_close) + kfree_skb(c3cn->cpl_close); + if (c3cn->cpl_abort_req) + kfree_skb(c3cn->cpl_abort_req); + if (c3cn->cpl_abort_rpl) + kfree_skb(c3cn->cpl_abort_rpl); +} + +static int c3cn_alloc_cpl_skbs(struct s3_conn *c3cn) +{ + c3cn->cpl_close = alloc_skb(sizeof(struct cpl_close_con_req), + GFP_KERNEL); + if (!c3cn->cpl_close) + return -ENOMEM; + skb_put(c3cn->cpl_close, sizeof(struct cpl_close_con_req)); + + c3cn->cpl_abort_req = alloc_skb(sizeof(struct cpl_abort_req), + GFP_KERNEL); + if (!c3cn->cpl_abort_req) + goto free_cpl_skbs; + skb_put(c3cn->cpl_abort_req, sizeof(struct cpl_abort_req)); + + c3cn->cpl_abort_rpl = alloc_skb(sizeof(struct cpl_abort_rpl), + GFP_KERNEL); + if (!c3cn->cpl_abort_rpl) + goto free_cpl_skbs; + skb_put(c3cn->cpl_abort_rpl, sizeof(struct cpl_abort_rpl)); + + return 0; + +free_cpl_skbs: + c3cn_free_cpl_skbs(c3cn); + return -ENOMEM; +} + +/** + * c3cn_release_offload_resources - release offload resource + * @c3cn: the offloaded iscsi tcp connection. + * Release resources held by an offload connection (TID, L2T entry, etc.) + */ +static void c3cn_release_offload_resources(struct s3_conn *c3cn) +{ + struct t3cdev *cdev = c3cn->cdev; + unsigned int tid = c3cn->tid; + + if (!cdev) + return; + + c3cn->qset = 0; + + c3cn_free_cpl_skbs(c3cn); + + if (c3cn->wr_avail != c3cn->wr_max) { + purge_wr_queue(c3cn); + reset_wr_list(c3cn); + } + + if (c3cn->l2t) { + l2t_release(L2DATA(cdev), c3cn->l2t); + c3cn->l2t = NULL; + } + + if (c3cn->state == C3CN_STATE_CONNECTING) /* we have ATID */ + s3_free_atid(cdev, tid); + else { /* we have TID */ + cxgb3_remove_tid(cdev, (void *)c3cn, tid); + c3cn_put(c3cn); + } + + c3cn->cdev = NULL; +} + +/** + * cxgb3i_c3cn_create - allocate and initialize an s3_conn structure + * returns the s3_conn structure allocated. + */ +struct s3_conn *cxgb3i_c3cn_create(void) +{ + struct s3_conn *c3cn; + + c3cn = kzalloc(sizeof(*c3cn), GFP_KERNEL); + if (!c3cn) + return NULL; + + /* pre-allocate close/abort cpl, so we don't need to wait for memory + when close/abort is requested. */ + if (c3cn_alloc_cpl_skbs(c3cn) < 0) + goto free_c3cn; + + c3cn_conn_debug("alloc c3cn 0x%p.\n", c3cn); + + c3cn->flags = 0; + spin_lock_init(&c3cn->lock); + atomic_set(&c3cn->refcnt, 1); + skb_queue_head_init(&c3cn->receive_queue); + skb_queue_head_init(&c3cn->write_queue); + setup_timer(&c3cn->retry_timer, NULL, (unsigned long)c3cn); + rwlock_init(&c3cn->callback_lock); + + return c3cn; + +free_c3cn: + kfree(c3cn); + return NULL; +} + +static void c3cn_active_close(struct s3_conn *c3cn) +{ + int data_lost; + int close_req = 0; + + c3cn_conn_debug("c3cn 0x%p, state %u, flag 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + + dst_confirm(c3cn->dst_cache); + + c3cn_hold(c3cn); + spin_lock_bh(&c3cn->lock); + + data_lost = skb_queue_len(&c3cn->receive_queue); + __skb_queue_purge(&c3cn->receive_queue); + + switch (c3cn->state) { + case C3CN_STATE_CLOSED: + case C3CN_STATE_ACTIVE_CLOSE: + case C3CN_STATE_CLOSE_WAIT_1: + case C3CN_STATE_CLOSE_WAIT_2: + case C3CN_STATE_ABORTING: + /* nothing need to be done */ + break; + case C3CN_STATE_CONNECTING: + /* defer until cpl_act_open_rpl or cpl_act_establish */ + c3cn_set_flag(c3cn, C3CN_ACTIVE_CLOSE_NEEDED); + break; + case C3CN_STATE_ESTABLISHED: + close_req = 1; + c3cn_set_state(c3cn, C3CN_STATE_ACTIVE_CLOSE); + break; + case C3CN_STATE_PASSIVE_CLOSE: + close_req = 1; + c3cn_set_state(c3cn, C3CN_STATE_CLOSE_WAIT_2); + break; + } + + if (close_req) { + if (data_lost) + /* Unread data was tossed, zap the connection. */ + send_abort_req(c3cn); + else + send_close_req(c3cn); + } + + spin_unlock_bh(&c3cn->lock); + c3cn_put(c3cn); +} + +/** + * cxgb3i_c3cn_release - close and release an iscsi tcp connection and any + * resource held + * @c3cn: the iscsi tcp connection + */ +void cxgb3i_c3cn_release(struct s3_conn *c3cn) +{ + c3cn_conn_debug("c3cn 0x%p, s %u, f 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + if (likely(c3cn->state != C3CN_STATE_CONNECTING)) + c3cn_active_close(c3cn); + else + c3cn_set_flag(c3cn, C3CN_ACTIVE_CLOSE_NEEDED); + c3cn_put(c3cn); +} + +static int is_cxgb3_dev(struct net_device *dev) +{ + struct cxgb3i_sdev_data *cdata; + + write_lock(&cdata_rwlock); + list_for_each_entry(cdata, &cdata_list, list) { + struct adap_ports *ports = &cdata->ports; + int i; + + for (i = 0; i < ports->nports; i++) + if (dev == ports->lldevs[i]) { + write_unlock(&cdata_rwlock); + return 1; + } + } + write_unlock(&cdata_rwlock); + return 0; +} + +/** + * cxgb3_egress_dev - return the cxgb3 egress device + * @root_dev: the root device anchoring the search + * @c3cn: the connection used to determine egress port in bonding mode + * @context: in bonding mode, indicates a connection set up or failover + * + * Return egress device or NULL if the egress device isn't one of our ports. + */ +static struct net_device *cxgb3_egress_dev(struct net_device *root_dev, + struct s3_conn *c3cn, + int context) +{ + while (root_dev) { + if (root_dev->priv_flags & IFF_802_1Q_VLAN) + root_dev = vlan_dev_real_dev(root_dev); + else if (is_cxgb3_dev(root_dev)) + return root_dev; + else + return NULL; + } + return NULL; +} + +static struct rtable *find_route(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +{ + struct rtable *rt; + struct flowi fl = { + .oif = 0, + .nl_u = { + .ip4_u = { + .daddr = daddr, + .saddr = saddr, + .tos = 0 } }, + .proto = IPPROTO_TCP, + .uli_u = { + .ports = { + .sport = sport, + .dport = dport } } }; + + if (ip_route_output_flow(&init_net, &rt, &fl, NULL, 0)) + return NULL; + return rt; +} + +/* + * Assign offload parameters to some connection fields. + */ +static void init_offload_conn(struct s3_conn *c3cn, + struct t3cdev *cdev, + struct dst_entry *dst) +{ + BUG_ON(c3cn->cdev != cdev); + c3cn->wr_max = c3cn->wr_avail = T3C_DATA(cdev)->max_wrs; + c3cn->wr_unacked = 0; + c3cn->mss_idx = select_mss(c3cn, dst_mtu(dst)); + + reset_wr_list(c3cn); +} + +static int initiate_act_open(struct s3_conn *c3cn, struct net_device *dev) +{ + struct cxgb3i_sdev_data *cdata = NDEV2CDATA(dev); + struct t3cdev *cdev = cdata->cdev; + struct dst_entry *dst = c3cn->dst_cache; + struct sk_buff *skb; + + c3cn_conn_debug("c3cn 0x%p, state %u, flag 0x%lx.\n", + c3cn, c3cn->state, c3cn->flags); + /* + * Initialize connection data. Note that the flags and ULP mode are + * initialized higher up ... + */ + c3cn->dev = dev; + c3cn->cdev = cdev; + c3cn->tid = cxgb3_alloc_atid(cdev, cdata->client, c3cn); + if (c3cn->tid < 0) + goto out_err; + + c3cn->qset = 0; + c3cn->l2t = t3_l2t_get(cdev, dst->neighbour, dev); + if (!c3cn->l2t) + goto free_tid; + + skb = alloc_skb(sizeof(struct cpl_act_open_req), GFP_KERNEL); + if (!skb) + goto free_l2t; + + skb->sk = (struct sock *)c3cn; + set_arp_failure_handler(skb, act_open_req_arp_failure); + + c3cn_hold(c3cn); + + init_offload_conn(c3cn, cdev, dst); + c3cn->err = 0; + + make_act_open_req(c3cn, skb, c3cn->tid, c3cn->l2t); + l2t_send(cdev, skb, c3cn->l2t); + return 0; + +free_l2t: + l2t_release(L2DATA(cdev), c3cn->l2t); +free_tid: + s3_free_atid(cdev, c3cn->tid); + c3cn->tid = 0; +out_err: + return -1; +} + + +/** + * cxgb3i_c3cn_connect - initiates an iscsi tcp connection to a given address + * @c3cn: the iscsi tcp connection + * @usin: destination address + * + * return 0 if active open request is sent, < 0 otherwise. + */ +int cxgb3i_c3cn_connect(struct s3_conn *c3cn, struct sockaddr_in *usin) +{ + struct rtable *rt; + struct net_device *dev; + struct cxgb3i_sdev_data *cdata; + struct t3cdev *cdev; + __be32 sipv4; + int err; + + if (usin->sin_family != AF_INET) + return -EAFNOSUPPORT; + + c3cn->daddr.sin_port = usin->sin_port; + c3cn->daddr.sin_addr.s_addr = usin->sin_addr.s_addr; + + rt = find_route(c3cn->saddr.sin_addr.s_addr, + c3cn->daddr.sin_addr.s_addr, + c3cn->saddr.sin_port, + c3cn->daddr.sin_port); + if (rt == NULL) { + c3cn_conn_debug("NO route to 0x%x, port %u.\n", + c3cn->daddr.sin_addr.s_addr, + ntohs(c3cn->daddr.sin_port)); + return -ENETUNREACH; + } + + if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) { + c3cn_conn_debug("multi-cast route to 0x%x, port %u.\n", + c3cn->daddr.sin_addr.s_addr, + ntohs(c3cn->daddr.sin_port)); + ip_rt_put(rt); + return -ENETUNREACH; + } + + if (!c3cn->saddr.sin_addr.s_addr) + c3cn->saddr.sin_addr.s_addr = rt->rt_src; + + /* now commit destination to connection */ + c3cn->dst_cache = &rt->u.dst; + + /* try to establish an offloaded connection */ + dev = cxgb3_egress_dev(c3cn->dst_cache->dev, c3cn, 0); + if (dev == NULL) { + c3cn_conn_debug("c3cn 0x%p, egress dev NULL.\n", c3cn); + return -ENETUNREACH; + } + cdata = NDEV2CDATA(dev); + cdev = cdata->cdev; + + /* get a source port if one hasn't been provided */ + err = c3cn_get_port(c3cn, cdata); + if (err) + return err; + + c3cn_conn_debug("c3cn 0x%p get port %u.\n", + c3cn, ntohs(c3cn->saddr.sin_port)); + + sipv4 = cxgb3i_get_private_ipv4addr(dev); + if (!sipv4) { + c3cn_conn_debug("c3cn 0x%p, iscsi ip not configured.\n", c3cn); + sipv4 = c3cn->saddr.sin_addr.s_addr; + cxgb3i_set_private_ipv4addr(dev, sipv4); + } else + c3cn->saddr.sin_addr.s_addr = sipv4; + + c3cn_conn_debug("c3cn 0x%p, %u.%u.%u.%u,%u-%u.%u.%u.%u,%u SYN_SENT.\n", + c3cn, NIPQUAD(c3cn->saddr.sin_addr.s_addr), + ntohs(c3cn->saddr.sin_port), + NIPQUAD(c3cn->daddr.sin_addr.s_addr), + ntohs(c3cn->daddr.sin_port)); + + c3cn_set_state(c3cn, C3CN_STATE_CONNECTING); + if (!initiate_act_open(c3cn, dev)) + return 0; + + /* + * If we get here, we don't have an offload connection so simply + * return a failure. + */ + err = -ENOTSUPP; + + /* + * This trashes the connection and releases the local port, + * if necessary. + */ + c3cn_conn_debug("c3cn 0x%p -> CLOSED.\n", c3cn); + c3cn_set_state(c3cn, C3CN_STATE_CLOSED); + ip_rt_put(rt); + c3cn_put_port(c3cn); + c3cn->daddr.sin_port = 0; + return err; +} + +/** + * cxgb3i_c3cn_rx_credits - ack received tcp data. + * @c3cn: iscsi tcp connection + * @copied: # of bytes processed + * + * Called after some received data has been read. It returns RX credits + * to the HW for the amount of data processed. + */ +void cxgb3i_c3cn_rx_credits(struct s3_conn *c3cn, int copied) +{ + struct t3cdev *cdev; + int must_send; + u32 credits, dack = 0; + + if (c3cn->state != C3CN_STATE_ESTABLISHED) + return; + + credits = c3cn->copied_seq - c3cn->rcv_wup; + if (unlikely(!credits)) + return; + + cdev = c3cn->cdev; + + if (unlikely(cxgb3_rx_credit_thres == 0)) + return; + + dack = F_RX_DACK_CHANGE | V_RX_DACK_MODE(1); + + /* + * For coalescing to work effectively ensure the receive window has + * at least 16KB left. + */ + must_send = credits + 16384 >= cxgb3_rcv_win; + + if (must_send || credits >= cxgb3_rx_credit_thres) + c3cn->rcv_wup += send_rx_credits(c3cn, credits, dack); +} + +/** + * cxgb3i_c3cn_send_pdus - send the skbs containing iscsi pdus + * @c3cn: iscsi tcp connection + * @skb: skb contains the iscsi pdu + * + * Add a list of skbs to a connection send queue. The skbs must comply with + * the max size limit of the device and have a headroom of at least + * TX_HEADER_LEN bytes. + * Return # of bytes queued. + */ +int cxgb3i_c3cn_send_pdus(struct s3_conn *c3cn, struct sk_buff *skb) +{ + struct sk_buff *next; + int err, copied = 0; + + spin_lock_bh(&c3cn->lock); + + if (c3cn->state != C3CN_STATE_ESTABLISHED) { + c3cn_tx_debug("c3cn 0x%p, not in est. state %u.\n", + c3cn, c3cn->state); + err = -EAGAIN; + goto out_err; + } + + err = -EPIPE; + if (c3cn->err) { + c3cn_tx_debug("c3cn 0x%p, err %d.\n", c3cn, c3cn->err); + goto out_err; + } + + while (skb) { + int frags = skb_shinfo(skb)->nr_frags + + (skb->len != skb->data_len); + + if (unlikely(skb_headroom(skb) < TX_HEADER_LEN)) { + c3cn_tx_debug("c3cn 0x%p, skb head.\n", c3cn); + err = -EINVAL; + goto out_err; + } + + if (frags >= SKB_WR_LIST_SIZE) { + cxgb3i_log_error("c3cn 0x%p, tx frags %d, len %u,%u.\n", + c3cn, skb_shinfo(skb)->nr_frags, + skb->len, skb->data_len); + err = -EINVAL; + goto out_err; + } + + next = skb->next; + skb->next = NULL; + skb_entail(c3cn, skb, C3CB_FLAG_NO_APPEND | C3CB_FLAG_NEED_HDR); + copied += skb->len; + c3cn->write_seq += skb->len + ulp_extra_len(skb); + skb = next; + } +done: + if (likely(skb_queue_len(&c3cn->write_queue))) + c3cn_push_tx_frames(c3cn, 1); + spin_unlock_bh(&c3cn->lock); + return copied; + +out_err: + if (copied == 0 && err == -EPIPE) + copied = c3cn->err ? c3cn->err : -EPIPE; + goto done; +} + +static void sdev_data_cleanup(struct cxgb3i_sdev_data *cdata) +{ + struct adap_ports *ports = &cdata->ports; + int i; + + for (i = 0; i < ports->nports; i++) + NDEV2CDATA(ports->lldevs[i]) = NULL; + cxgb3i_free_big_mem(cdata); +} + +void cxgb3i_sdev_cleanup(void) +{ + struct cxgb3i_sdev_data *cdata; + + write_lock(&cdata_rwlock); + list_for_each_entry(cdata, &cdata_list, list) { + list_del(&cdata->list); + sdev_data_cleanup(cdata); + } + write_unlock(&cdata_rwlock); +} + +int cxgb3i_sdev_init(cxgb3_cpl_handler_func *cpl_handlers) +{ + cpl_handlers[CPL_ACT_ESTABLISH] = do_act_establish; + cpl_handlers[CPL_ACT_OPEN_RPL] = do_act_open_rpl; + cpl_handlers[CPL_PEER_CLOSE] = do_peer_close; + cpl_handlers[CPL_ABORT_REQ_RSS] = do_abort_req; + cpl_handlers[CPL_ABORT_RPL_RSS] = do_abort_rpl; + cpl_handlers[CPL_CLOSE_CON_RPL] = do_close_con_rpl; + cpl_handlers[CPL_TX_DMA_ACK] = do_wr_ack; + cpl_handlers[CPL_ISCSI_HDR] = do_iscsi_hdr; + + if (cxgb3_max_connect > CXGB3I_MAX_CONN) + cxgb3_max_connect = CXGB3I_MAX_CONN; + return 0; +} + +/** + * cxgb3i_sdev_add - allocate and initialize resources for each adapter found + * @cdev: t3cdev adapter + * @client: cxgb3 driver client + */ +void cxgb3i_sdev_add(struct t3cdev *cdev, struct cxgb3_client *client) +{ + struct cxgb3i_sdev_data *cdata; + struct ofld_page_info rx_page_info; + unsigned int wr_len; + int mapsize = DIV_ROUND_UP(cxgb3_max_connect, + 8 * sizeof(unsigned long)); + int i; + + cdata = cxgb3i_alloc_big_mem(sizeof(*cdata) + mapsize, GFP_KERNEL); + if (!cdata) + return; + + if (cdev->ctl(cdev, GET_WR_LEN, &wr_len) < 0 || + cdev->ctl(cdev, GET_PORTS, &cdata->ports) < 0 || + cdev->ctl(cdev, GET_RX_PAGE_INFO, &rx_page_info) < 0) + goto free_cdata; + + s3_init_wr_tab(wr_len); + + INIT_LIST_HEAD(&cdata->list); + cdata->cdev = cdev; + cdata->client = client; + + for (i = 0; i < cdata->ports.nports; i++) + NDEV2CDATA(cdata->ports.lldevs[i]) = cdata; + + write_lock(&cdata_rwlock); + list_add_tail(&cdata->list, &cdata_list); + write_unlock(&cdata_rwlock); + + return; + +free_cdata: + cxgb3i_free_big_mem(cdata); +} + +/** + * cxgb3i_sdev_remove - free the allocated resources for the adapter + * @cdev: t3cdev adapter + */ +void cxgb3i_sdev_remove(struct t3cdev *cdev) +{ + struct cxgb3i_sdev_data *cdata = CXGB3_SDEV_DATA(cdev); + + write_lock(&cdata_rwlock); + list_del(&cdata->list); + write_unlock(&cdata_rwlock); + + sdev_data_cleanup(cdata); +} diff --git a/drivers/scsi/cxgb3i/cxgb3i_offload.h b/drivers/scsi/cxgb3i/cxgb3i_offload.h new file mode 100644 index 00000000000..5b93d629e5c --- /dev/null +++ b/drivers/scsi/cxgb3i/cxgb3i_offload.h @@ -0,0 +1,231 @@ +/* + * cxgb3i_offload.h: Chelsio S3xx iscsi offloaded tcp connection management + * + * Copyright (C) 2003-2008 Chelsio Communications. All rights reserved. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the LICENSE file included in this + * release for licensing terms and conditions. + * + * Written by: Dimitris Michailidis (dm@chelsio.com) + * Karen Xie (kxie@chelsio.com) + */ + +#ifndef _CXGB3I_OFFLOAD_H +#define _CXGB3I_OFFLOAD_H + +#include <linux/skbuff.h> +#include <net/tcp.h> + +#include "common.h" +#include "adapter.h" +#include "t3cdev.h" +#include "cxgb3_offload.h" + +#define cxgb3i_log_error(fmt...) printk(KERN_ERR "cxgb3i: ERR! " fmt) +#define cxgb3i_log_warn(fmt...) printk(KERN_WARNING "cxgb3i: WARN! " fmt) +#define cxgb3i_log_info(fmt...) printk(KERN_INFO "cxgb3i: " fmt) +#define cxgb3i_log_debug(fmt, args...) \ + printk(KERN_INFO "cxgb3i: %s - " fmt, __func__ , ## args) + +/** + * struct s3_conn - an iscsi tcp connection structure + * + * @dev: net device of with connection + * @cdev: adapter t3cdev for net device + * @flags: see c3cn_flags below + * @tid: connection id assigned by the h/w + * @qset: queue set used by connection + * @mss_idx: Maximum Segment Size table index + * @l2t: ARP resolution entry for offload packets + * @wr_max: maximum in-flight writes + * @wr_avail: number of writes available + * @wr_unacked: writes since last request for completion notification + * @wr_pending_head: head of pending write queue + * @wr_pending_tail: tail of pending write queue + * @cpl_close: skb for cpl_close_req + * @cpl_abort_req: skb for cpl_abort_req + * @cpl_abort_rpl: skb for cpl_abort_rpl + * @lock: connection status lock + * @refcnt: reference count on connection + * @state: connection state + * @saddr: source ip/port address + * @daddr: destination ip/port address + * @dst_cache: reference to destination route + * @receive_queue: received PDUs + * @write_queue: un-pushed pending writes + * @retry_timer: retry timer for various operations + * @err: connection error status + * @callback_lock: lock for opaque user context + * @user_data: opaque user context + * @rcv_nxt: next receive seq. # + * @copied_seq: head of yet unread data + * @rcv_wup: rcv_nxt on last window update sent + * @snd_nxt: next sequence we send + * @snd_una: first byte we want an ack for + * @write_seq: tail+1 of data held in send buffer + */ +struct s3_conn { + struct net_device *dev; + struct t3cdev *cdev; + unsigned long flags; + int tid; + int qset; + int mss_idx; + struct l2t_entry *l2t; + int wr_max; + int wr_avail; + int wr_unacked; + struct sk_buff *wr_pending_head; + struct sk_buff *wr_pending_tail; + struct sk_buff *cpl_close; + struct sk_buff *cpl_abort_req; + struct sk_buff *cpl_abort_rpl; + spinlock_t lock; + atomic_t refcnt; + volatile unsigned int state; + struct sockaddr_in saddr; + struct sockaddr_in daddr; + struct dst_entry *dst_cache; + struct sk_buff_head receive_queue; + struct sk_buff_head write_queue; + struct timer_list retry_timer; + int err; + rwlock_t callback_lock; + void *user_data; + + u32 rcv_nxt; + u32 copied_seq; + u32 rcv_wup; + u32 snd_nxt; + u32 snd_una; + u32 write_seq; +}; + +/* + * connection state + */ +enum conn_states { + C3CN_STATE_CONNECTING = 1, + C3CN_STATE_ESTABLISHED, + C3CN_STATE_ACTIVE_CLOSE, + C3CN_STATE_PASSIVE_CLOSE, + C3CN_STATE_CLOSE_WAIT_1, + C3CN_STATE_CLOSE_WAIT_2, + C3CN_STATE_ABORTING, + C3CN_STATE_CLOSED, +}; + +static inline unsigned int c3cn_is_closing(const struct s3_conn *c3cn) +{ + return c3cn->state >= C3CN_STATE_ACTIVE_CLOSE; +} +static inline unsigned int c3cn_is_established(const struct s3_conn *c3cn) +{ + return c3cn->state == C3CN_STATE_ESTABLISHED; +} + +/* + * Connection flags -- many to track some close related events. + */ +enum c3cn_flags { + C3CN_ABORT_RPL_RCVD, /* received one ABORT_RPL_RSS message */ + C3CN_ABORT_REQ_RCVD, /* received one ABORT_REQ_RSS message */ + C3CN_ABORT_RPL_PENDING, /* expecting an abort reply */ + C3CN_TX_DATA_SENT, /* already sent a TX_DATA WR */ + C3CN_ACTIVE_CLOSE_NEEDED, /* need to be closed */ +}; + +/** + * cxgb3i_sdev_data - Per adapter data. + * Linked off of each Ethernet device port on the adapter. + * Also available via the t3cdev structure since we have pointers to our port + * net_device's there ... + * + * @list: list head to link elements + * @cdev: t3cdev adapter + * @client: CPL client pointer + * @ports: array of adapter ports + * @sport_map_next: next index into the port map + * @sport_map: source port map + */ +struct cxgb3i_sdev_data { + struct list_head list; + struct t3cdev *cdev; + struct cxgb3_client *client; + struct adap_ports ports; + unsigned int sport_map_next; + unsigned long sport_map[0]; +}; +#define NDEV2CDATA(ndev) (*(struct cxgb3i_sdev_data **)&(ndev)->ec_ptr) +#define CXGB3_SDEV_DATA(cdev) NDEV2CDATA((cdev)->lldev) + +void cxgb3i_sdev_cleanup(void); +int cxgb3i_sdev_init(cxgb3_cpl_handler_func *); +void cxgb3i_sdev_add(struct t3cdev *, struct cxgb3_client *); +void cxgb3i_sdev_remove(struct t3cdev *); + +struct s3_conn *cxgb3i_c3cn_create(void); +int cxgb3i_c3cn_connect(struct s3_conn *, struct sockaddr_in *); +void cxgb3i_c3cn_rx_credits(struct s3_conn *, int); +int cxgb3i_c3cn_send_pdus(struct s3_conn *, struct sk_buff *); +void cxgb3i_c3cn_release(struct s3_conn *); + +/** + * cxgb3_skb_cb - control block for received pdu state and ULP mode management. + * + * @flag: see C3CB_FLAG_* below + * @ulp_mode: ULP mode/submode of sk_buff + * @seq: tcp sequence number + * @ddigest: pdu data digest + * @pdulen: recovered pdu length + * @ulp_data: scratch area for ULP + */ +struct cxgb3_skb_cb { + __u8 flags; + __u8 ulp_mode; + __u32 seq; + __u32 ddigest; + __u32 pdulen; + __u8 ulp_data[16]; +}; + +#define CXGB3_SKB_CB(skb) ((struct cxgb3_skb_cb *)&((skb)->cb[0])) + +#define skb_ulp_mode(skb) (CXGB3_SKB_CB(skb)->ulp_mode) +#define skb_ulp_ddigest(skb) (CXGB3_SKB_CB(skb)->ddigest) +#define skb_ulp_pdulen(skb) (CXGB3_SKB_CB(skb)->pdulen) +#define skb_ulp_data(skb) (CXGB3_SKB_CB(skb)->ulp_data) + +enum c3cb_flags { + C3CB_FLAG_NEED_HDR = 1 << 0, /* packet needs a TX_DATA_WR header */ + C3CB_FLAG_NO_APPEND = 1 << 1, /* don't grow this skb */ + C3CB_FLAG_COMPL = 1 << 2, /* request WR completion */ +}; + +/** + * sge_opaque_hdr - + * Opaque version of structure the SGE stores at skb->head of TX_DATA packets + * and for which we must reserve space. + */ +struct sge_opaque_hdr { + void *dev; + dma_addr_t addr[MAX_SKB_FRAGS + 1]; +}; + +/* for TX: a skb must have a headroom of at least TX_HEADER_LEN bytes */ +#define TX_HEADER_LEN \ + (sizeof(struct tx_data_wr) + sizeof(struct sge_opaque_hdr)) + +/* + * get and set private ip for iscsi traffic + */ +#define cxgb3i_get_private_ipv4addr(ndev) \ + (((struct port_info *)(netdev_priv(ndev)))->iscsi_ipv4addr) +#define cxgb3i_set_private_ipv4addr(ndev, addr) \ + (((struct port_info *)(netdev_priv(ndev)))->iscsi_ipv4addr) = addr + +/* max. connections per adapter */ +#define CXGB3I_MAX_CONN 16384 +#endif /* _CXGB3_OFFLOAD_H */ diff --git a/drivers/scsi/cxgb3i/cxgb3i_pdu.c b/drivers/scsi/cxgb3i/cxgb3i_pdu.c new file mode 100644 index 00000000000..ce7ce8c6094 --- /dev/null +++ b/drivers/scsi/cxgb3i/cxgb3i_pdu.c @@ -0,0 +1,402 @@ +/* + * cxgb3i_pdu.c: Chelsio S3xx iSCSI driver. + * + * Copyright (c) 2008 Chelsio Communications, Inc. + * Copyright (c) 2008 Mike Christie + * Copyright (c) 2008 Red Hat, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + * + * Written by: Karen Xie (kxie@chelsio.com) + */ + +#include <linux/skbuff.h> +#include <linux/crypto.h> +#include <scsi/scsi_cmnd.h> +#include <scsi/scsi_host.h> + +#include "cxgb3i.h" +#include "cxgb3i_pdu.h" + +#ifdef __DEBUG_CXGB3I_RX__ +#define cxgb3i_rx_debug cxgb3i_log_debug +#else +#define cxgb3i_rx_debug(fmt...) +#endif + +#ifdef __DEBUG_CXGB3I_TX__ +#define cxgb3i_tx_debug cxgb3i_log_debug +#else +#define cxgb3i_tx_debug(fmt...) +#endif + +static struct page *pad_page; + +/* + * pdu receive, interact with libiscsi_tcp + */ +static inline int read_pdu_skb(struct iscsi_conn *conn, struct sk_buff *skb, + unsigned int offset, int offloaded) +{ + int status = 0; + int bytes_read; + + bytes_read = iscsi_tcp_recv_skb(conn, skb, offset, offloaded, &status); + switch (status) { + case ISCSI_TCP_CONN_ERR: + return -EIO; + case ISCSI_TCP_SUSPENDED: + /* no transfer - just have caller flush queue */ + return bytes_read; + case ISCSI_TCP_SKB_DONE: + /* + * pdus should always fit in the skb and we should get + * segment done notifcation. + */ + iscsi_conn_printk(KERN_ERR, conn, "Invalid pdu or skb."); + return -EFAULT; + case ISCSI_TCP_SEGMENT_DONE: + return bytes_read; + default: + iscsi_conn_printk(KERN_ERR, conn, "Invalid iscsi_tcp_recv_skb " + "status %d\n", status); + return -EINVAL; + } +} + +static int cxgb3i_conn_read_pdu_skb(struct iscsi_conn *conn, + struct sk_buff *skb) +{ + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + bool offloaded = 0; + unsigned int offset; + int rc; + + cxgb3i_rx_debug("conn 0x%p, skb 0x%p, len %u, flag 0x%x.\n", + conn, skb, skb->len, skb_ulp_mode(skb)); + + if (!iscsi_tcp_recv_segment_is_hdr(tcp_conn)) { + iscsi_conn_failure(conn, ISCSI_ERR_PROTO); + return -EIO; + } + + if (conn->hdrdgst_en && (skb_ulp_mode(skb) & ULP2_FLAG_HCRC_ERROR)) { + iscsi_conn_failure(conn, ISCSI_ERR_HDR_DGST); + return -EIO; + } + + if (conn->datadgst_en && (skb_ulp_mode(skb) & ULP2_FLAG_DCRC_ERROR)) { + iscsi_conn_failure(conn, ISCSI_ERR_DATA_DGST); + return -EIO; + } + + /* iscsi hdr */ + rc = read_pdu_skb(conn, skb, 0, 0); + if (rc <= 0) + return rc; + + if (iscsi_tcp_recv_segment_is_hdr(tcp_conn)) + return 0; + + offset = rc; + if (conn->hdrdgst_en) + offset += ISCSI_DIGEST_SIZE; + + /* iscsi data */ + if (skb_ulp_mode(skb) & ULP2_FLAG_DATA_DDPED) { + cxgb3i_rx_debug("skb 0x%p, opcode 0x%x, data %u, ddp'ed, " + "itt 0x%x.\n", + skb, + tcp_conn->in.hdr->opcode & ISCSI_OPCODE_MASK, + tcp_conn->in.datalen, + ntohl(tcp_conn->in.hdr->itt)); + offloaded = 1; + } else { + cxgb3i_rx_debug("skb 0x%p, opcode 0x%x, data %u, NOT ddp'ed, " + "itt 0x%x.\n", + skb, + tcp_conn->in.hdr->opcode & ISCSI_OPCODE_MASK, + tcp_conn->in.datalen, + ntohl(tcp_conn->in.hdr->itt)); + offset += sizeof(struct cpl_iscsi_hdr_norss); + } + + rc = read_pdu_skb(conn, skb, offset, offloaded); + if (rc < 0) + return rc; + else + return 0; +} + +/* + * pdu transmit, interact with libiscsi_tcp + */ +static inline void tx_skb_setmode(struct sk_buff *skb, int hcrc, int dcrc) +{ + u8 submode = 0; + + if (hcrc) + submode |= 1; + if (dcrc) + submode |= 2; + skb_ulp_mode(skb) = (ULP_MODE_ISCSI << 4) | submode; +} + +void cxgb3i_conn_cleanup_task(struct iscsi_task *task) +{ + struct iscsi_tcp_task *tcp_task = task->dd_data; + + /* never reached the xmit task callout */ + if (tcp_task->dd_data) + kfree_skb(tcp_task->dd_data); + tcp_task->dd_data = NULL; + + /* MNC - Do we need a check in case this is called but + * cxgb3i_conn_alloc_pdu has never been called on the task */ + cxgb3i_release_itt(task, task->hdr_itt); + iscsi_tcp_cleanup_task(task); +} + +/* + * We do not support ahs yet + */ +int cxgb3i_conn_alloc_pdu(struct iscsi_task *task, u8 opcode) +{ + struct iscsi_tcp_task *tcp_task = task->dd_data; + struct sk_buff *skb; + + task->hdr = NULL; + /* always allocate rooms for AHS */ + skb = alloc_skb(sizeof(struct iscsi_hdr) + ISCSI_MAX_AHS_SIZE + + TX_HEADER_LEN, GFP_ATOMIC); + if (!skb) + return -ENOMEM; + + cxgb3i_tx_debug("task 0x%p, opcode 0x%x, skb 0x%p.\n", + task, opcode, skb); + + tcp_task->dd_data = skb; + skb_reserve(skb, TX_HEADER_LEN); + task->hdr = (struct iscsi_hdr *)skb->data; + task->hdr_max = sizeof(struct iscsi_hdr); + + /* data_out uses scsi_cmd's itt */ + if (opcode != ISCSI_OP_SCSI_DATA_OUT) + cxgb3i_reserve_itt(task, &task->hdr->itt); + + return 0; +} + +int cxgb3i_conn_init_pdu(struct iscsi_task *task, unsigned int offset, + unsigned int count) +{ + struct iscsi_tcp_task *tcp_task = task->dd_data; + struct sk_buff *skb = tcp_task->dd_data; + struct iscsi_conn *conn = task->conn; + struct page *pg; + unsigned int datalen = count; + int i, padlen = iscsi_padding(count); + skb_frag_t *frag; + + cxgb3i_tx_debug("task 0x%p,0x%p, offset %u, count %u, skb 0x%p.\n", + task, task->sc, offset, count, skb); + + skb_put(skb, task->hdr_len); + tx_skb_setmode(skb, conn->hdrdgst_en, datalen ? conn->datadgst_en : 0); + if (!count) + return 0; + + if (task->sc) { + struct scatterlist *sg; + struct scsi_data_buffer *sdb; + unsigned int sgoffset = offset; + struct page *sgpg; + unsigned int sglen; + + sdb = scsi_out(task->sc); + sg = sdb->table.sgl; + + for_each_sg(sdb->table.sgl, sg, sdb->table.nents, i) { + cxgb3i_tx_debug("sg %d, page 0x%p, len %u offset %u\n", + i, sg_page(sg), sg->length, sg->offset); + + if (sgoffset < sg->length) + break; + sgoffset -= sg->length; + } + sgpg = sg_page(sg); + sglen = sg->length - sgoffset; + + do { + int j = skb_shinfo(skb)->nr_frags; + unsigned int copy; + + if (!sglen) { + sg = sg_next(sg); + sgpg = sg_page(sg); + sgoffset = 0; + sglen = sg->length; + ++i; + } + copy = min(sglen, datalen); + if (j && skb_can_coalesce(skb, j, sgpg, + sg->offset + sgoffset)) { + skb_shinfo(skb)->frags[j - 1].size += copy; + } else { + get_page(sgpg); + skb_fill_page_desc(skb, j, sgpg, + sg->offset + sgoffset, copy); + } + sgoffset += copy; + sglen -= copy; + datalen -= copy; + } while (datalen); + } else { + pg = virt_to_page(task->data); + + while (datalen) { + i = skb_shinfo(skb)->nr_frags; + frag = &skb_shinfo(skb)->frags[i]; + + get_page(pg); + frag->page = pg; + frag->page_offset = 0; + frag->size = min((unsigned int)PAGE_SIZE, datalen); + + skb_shinfo(skb)->nr_frags++; + datalen -= frag->size; + pg++; + } + } + + if (padlen) { + i = skb_shinfo(skb)->nr_frags; + frag = &skb_shinfo(skb)->frags[i]; + frag->page = pad_page; + frag->page_offset = 0; + frag->size = padlen; + skb_shinfo(skb)->nr_frags++; + } + + datalen = count + padlen; + skb->data_len += datalen; + skb->truesize += datalen; + skb->len += datalen; + return 0; +} + +int cxgb3i_conn_xmit_pdu(struct iscsi_task *task) +{ + struct iscsi_tcp_task *tcp_task = task->dd_data; + struct sk_buff *skb = tcp_task->dd_data; + struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data; + struct cxgb3i_conn *cconn = tcp_conn->dd_data; + unsigned int datalen; + int err; + + if (!skb) + return 0; + + datalen = skb->data_len; + tcp_task->dd_data = NULL; + err = cxgb3i_c3cn_send_pdus(cconn->cep->c3cn, skb); + cxgb3i_tx_debug("task 0x%p, skb 0x%p, len %u/%u, rv %d.\n", + task, skb, skb->len, skb->data_len, err); + if (err > 0) { + int pdulen = err; + + if (task->conn->hdrdgst_en) + pdulen += ISCSI_DIGEST_SIZE; + if (datalen && task->conn->datadgst_en) + pdulen += ISCSI_DIGEST_SIZE; + + task->conn->txdata_octets += pdulen; + return 0; + } + + if (err < 0 && err != -EAGAIN) { + kfree_skb(skb); + cxgb3i_tx_debug("itt 0x%x, skb 0x%p, len %u/%u, xmit err %d.\n", + task->itt, skb, skb->len, skb->data_len, err); + iscsi_conn_printk(KERN_ERR, task->conn, "xmit err %d.\n", err); + iscsi_conn_failure(task->conn, ISCSI_ERR_XMIT_FAILED); + return err; + } + /* reset skb to send when we are called again */ + tcp_task->dd_data = skb; + return -EAGAIN; +} + +int cxgb3i_pdu_init(void) +{ + pad_page = alloc_page(GFP_KERNEL); + if (!pad_page) + return -ENOMEM; + memset(page_address(pad_page), 0, PAGE_SIZE); + return 0; +} + +void cxgb3i_pdu_cleanup(void) +{ + if (pad_page) { + __free_page(pad_page); + pad_page = NULL; + } +} + +void cxgb3i_conn_pdu_ready(struct s3_conn *c3cn) +{ + struct sk_buff *skb; + unsigned int read = 0; + struct iscsi_conn *conn = c3cn->user_data; + int err = 0; + + cxgb3i_rx_debug("cn 0x%p.\n", c3cn); + + read_lock(&c3cn->callback_lock); + if (unlikely(!conn || conn->suspend_rx)) { + cxgb3i_rx_debug("conn 0x%p, id %d, suspend_rx %lu!\n", + conn, conn ? conn->id : 0xFF, + conn ? conn->suspend_rx : 0xFF); + read_unlock(&c3cn->callback_lock); + return; + } + skb = skb_peek(&c3cn->receive_queue); + while (!err && skb) { + __skb_unlink(skb, &c3cn->receive_queue); + read += skb_ulp_pdulen(skb); + err = cxgb3i_conn_read_pdu_skb(conn, skb); + __kfree_skb(skb); + skb = skb_peek(&c3cn->receive_queue); + } + read_unlock(&c3cn->callback_lock); + if (c3cn) { + c3cn->copied_seq += read; + cxgb3i_c3cn_rx_credits(c3cn, read); + } + conn->rxdata_octets += read; +} + +void cxgb3i_conn_tx_open(struct s3_conn *c3cn) +{ + struct iscsi_conn *conn = c3cn->user_data; + + cxgb3i_tx_debug("cn 0x%p.\n", c3cn); + if (conn) { + cxgb3i_tx_debug("cn 0x%p, cid %d.\n", c3cn, conn->id); + scsi_queue_work(conn->session->host, &conn->xmitwork); + } +} + +void cxgb3i_conn_closing(struct s3_conn *c3cn) +{ + struct iscsi_conn *conn; + + read_lock(&c3cn->callback_lock); + conn = c3cn->user_data; + if (conn && c3cn->state != C3CN_STATE_ESTABLISHED) + iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED); + read_unlock(&c3cn->callback_lock); +} diff --git a/drivers/scsi/cxgb3i/cxgb3i_pdu.h b/drivers/scsi/cxgb3i/cxgb3i_pdu.h new file mode 100644 index 00000000000..a3f685cc236 --- /dev/null +++ b/drivers/scsi/cxgb3i/cxgb3i_pdu.h @@ -0,0 +1,59 @@ +/* + * cxgb3i_ulp2.h: Chelsio S3xx iSCSI driver. + * + * Copyright (c) 2008 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. + * + * Written by: Karen Xie (kxie@chelsio.com) + */ + +#ifndef __CXGB3I_ULP2_PDU_H__ +#define __CXGB3I_ULP2_PDU_H__ + +struct cpl_iscsi_hdr_norss { + union opcode_tid ot; + u16 pdu_len_ddp; + u16 len; + u32 seq; + u16 urg; + u8 rsvd; + u8 status; +}; + +struct cpl_rx_data_ddp_norss { + union opcode_tid ot; + u16 urg; + u16 len; + u32 seq; + u32 nxt_seq; + u32 ulp_crc; + u32 ddp_status; +}; + +#define RX_DDP_STATUS_IPP_SHIFT 27 /* invalid pagepod */ +#define RX_DDP_STATUS_TID_SHIFT 26 /* tid mismatch */ +#define RX_DDP_STATUS_COLOR_SHIFT 25 /* color mismatch */ +#define RX_DDP_STATUS_OFFSET_SHIFT 24 /* offset mismatch */ +#define RX_DDP_STATUS_ULIMIT_SHIFT 23 /* ulimit error */ +#define RX_DDP_STATUS_TAG_SHIFT 22 /* tag mismatch */ +#define RX_DDP_STATUS_DCRC_SHIFT 21 /* dcrc error */ +#define RX_DDP_STATUS_HCRC_SHIFT 20 /* hcrc error */ +#define RX_DDP_STATUS_PAD_SHIFT 19 /* pad error */ +#define RX_DDP_STATUS_PPP_SHIFT 18 /* pagepod parity error */ +#define RX_DDP_STATUS_LLIMIT_SHIFT 17 /* llimit error */ +#define RX_DDP_STATUS_DDP_SHIFT 16 /* ddp'able */ +#define RX_DDP_STATUS_PMM_SHIFT 15 /* pagepod mismatch */ + +#define ULP2_FLAG_DATA_READY 0x1 +#define ULP2_FLAG_DATA_DDPED 0x2 +#define ULP2_FLAG_HCRC_ERROR 0x10 +#define ULP2_FLAG_DCRC_ERROR 0x20 +#define ULP2_FLAG_PAD_ERROR 0x40 + +void cxgb3i_conn_closing(struct s3_conn *); +void cxgb3i_conn_pdu_ready(struct s3_conn *c3cn); +void cxgb3i_conn_tx_open(struct s3_conn *c3cn); +#endif |