X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=drivers%2Fscsi%2Fiscsi_tcp.c;h=2a2f0094570fb0d1dfb78eeb34bcf89b47d9aa75;hb=4ad7a018cf4ac3cbad661c28c0f783ee0a6e3bf6;hp=8edcfddc0bafc99269d971daf3b7dae7fa1a414c;hpb=77a23c21aaa723f6b0ffc4a701be8c8e5a32346d;p=safe%2Fjmp%2Flinux-2.6 diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index 8edcfdd..2a2f009 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -36,6 +37,7 @@ #include #include #include +#include #include #include #include @@ -46,7 +48,7 @@ MODULE_AUTHOR("Dmitry Yusupov , " "Alex Aizman "); MODULE_DESCRIPTION("iSCSI/TCP data-path"); MODULE_LICENSE("GPL"); -/* #define DEBUG_TCP */ +#undef DEBUG_TCP #define DEBUG_ASSERT #ifdef DEBUG_TCP @@ -62,203 +64,515 @@ MODULE_LICENSE("GPL"); #define BUG_ON(expr) #endif +static struct scsi_transport_template *iscsi_tcp_scsi_transport; +static struct scsi_host_template iscsi_sht; +static struct iscsi_transport iscsi_tcp_transport; + static unsigned int iscsi_max_lun = 512; module_param_named(max_lun, iscsi_max_lun, uint, S_IRUGO); +static int iscsi_tcp_hdr_recv_done(struct iscsi_tcp_conn *tcp_conn, + struct iscsi_segment *segment); + +/* + * Scatterlist handling: inside the iscsi_segment, we + * remember an index into the scatterlist, and set data/size + * to the current scatterlist entry. For highmem pages, we + * kmap as needed. + * + * Note that the page is unmapped when we return from + * TCP's data_ready handler, so we may end up mapping and + * unmapping the same page repeatedly. The whole reason + * for this is that we shouldn't keep the page mapped + * outside the softirq. + */ + +/** + * iscsi_tcp_segment_init_sg - init indicated scatterlist entry + * @segment: the buffer object + * @sg: scatterlist + * @offset: byte offset into that sg entry + * + * This function sets up the segment so that subsequent + * data is copied to the indicated sg entry, at the given + * offset. + */ static inline void -iscsi_buf_init_iov(struct iscsi_buf *ibuf, char *vbuf, int size) +iscsi_tcp_segment_init_sg(struct iscsi_segment *segment, + struct scatterlist *sg, unsigned int offset) { - ibuf->sg.page = virt_to_page(vbuf); - ibuf->sg.offset = offset_in_page(vbuf); - ibuf->sg.length = size; - ibuf->sent = 0; - ibuf->use_sendmsg = 1; + segment->sg = sg; + segment->sg_offset = offset; + segment->size = min(sg->length - offset, + segment->total_size - segment->total_copied); + segment->data = NULL; } +/** + * iscsi_tcp_segment_map - map the current S/G page + * @segment: iscsi_segment + * @recv: 1 if called from recv path + * + * We only need to possibly kmap data if scatter lists are being used, + * because the iscsi passthrough and internal IO paths will never use high + * mem pages. + */ static inline void -iscsi_buf_init_sg(struct iscsi_buf *ibuf, struct scatterlist *sg) +iscsi_tcp_segment_map(struct iscsi_segment *segment, int recv) { - ibuf->sg.page = sg->page; - ibuf->sg.offset = sg->offset; - ibuf->sg.length = sg->length; + struct scatterlist *sg; + + if (segment->data != NULL || !segment->sg) + return; + + sg = segment->sg; + BUG_ON(segment->sg_mapped); + BUG_ON(sg->length == 0); + /* - * Fastpath: sg element fits into single page + * If the page count is greater than one it is ok to send + * to the network layer's zero copy send path. If not we + * have to go the slow sendmsg path. We always map for the + * recv path. */ - if (sg->length + sg->offset <= PAGE_SIZE && !PageSlab(sg->page)) - ibuf->use_sendmsg = 0; - else - ibuf->use_sendmsg = 1; - ibuf->sent = 0; + if (page_count(sg_page(sg)) >= 1 && !recv) + return; + + debug_tcp("iscsi_tcp_segment_map %s %p\n", recv ? "recv" : "xmit", + segment); + segment->sg_mapped = kmap_atomic(sg_page(sg), KM_SOFTIRQ0); + segment->data = segment->sg_mapped + sg->offset + segment->sg_offset; } -static inline int -iscsi_buf_left(struct iscsi_buf *ibuf) +static inline void +iscsi_tcp_segment_unmap(struct iscsi_segment *segment) { - int rc; + debug_tcp("iscsi_tcp_segment_unmap %p\n", segment); - rc = ibuf->sg.length - ibuf->sent; - BUG_ON(rc < 0); - return rc; + if (segment->sg_mapped) { + debug_tcp("iscsi_tcp_segment_unmap valid\n"); + kunmap_atomic(segment->sg_mapped, KM_SOFTIRQ0); + segment->sg_mapped = NULL; + segment->data = NULL; + } } +/* + * Splice the digest buffer into the buffer + */ static inline void -iscsi_hdr_digest(struct iscsi_conn *conn, struct iscsi_buf *buf, - u8* crc) +iscsi_tcp_segment_splice_digest(struct iscsi_segment *segment, void *digest) { - struct iscsi_tcp_conn *tcp_conn = conn->dd_data; - - crypto_hash_digest(&tcp_conn->tx_hash, &buf->sg, buf->sg.length, crc); - buf->sg.length += sizeof(u32); + segment->data = digest; + segment->digest_len = ISCSI_DIGEST_SIZE; + segment->total_size += ISCSI_DIGEST_SIZE; + segment->size = ISCSI_DIGEST_SIZE; + segment->copied = 0; + segment->sg = NULL; + segment->hash = NULL; } +/** + * iscsi_tcp_segment_done - check whether the segment is complete + * @segment: iscsi segment to check + * @recv: set to one of this is called from the recv path + * @copied: number of bytes copied + * + * Check if we're done receiving this segment. If the receive + * buffer is full but we expect more data, move on to the + * next entry in the scatterlist. + * + * If the amount of data we received isn't a multiple of 4, + * we will transparently receive the pad bytes, too. + * + * This function must be re-entrant. + */ static inline int -iscsi_hdr_extract(struct iscsi_tcp_conn *tcp_conn) +iscsi_tcp_segment_done(struct iscsi_segment *segment, int recv, unsigned copied) { - struct sk_buff *skb = tcp_conn->in.skb; - - tcp_conn->in.zero_copy_hdr = 0; + static unsigned char padbuf[ISCSI_PAD_LEN]; + struct scatterlist sg; + unsigned int pad; - if (tcp_conn->in.copy >= tcp_conn->hdr_size && - tcp_conn->in_progress == IN_PROGRESS_WAIT_HEADER) { + debug_tcp("copied %u %u size %u %s\n", segment->copied, copied, + segment->size, recv ? "recv" : "xmit"); + if (segment->hash && copied) { /* - * Zero-copy PDU Header: using connection context - * to store header pointer. + * If a segment is kmapd we must unmap it before sending + * to the crypto layer since that will try to kmap it again. */ - if (skb_shinfo(skb)->frag_list == NULL && - !skb_shinfo(skb)->nr_frags) { - tcp_conn->in.hdr = (struct iscsi_hdr *) - ((char*)skb->data + tcp_conn->in.offset); - tcp_conn->in.zero_copy_hdr = 1; + iscsi_tcp_segment_unmap(segment); + + if (!segment->data) { + sg_init_table(&sg, 1); + sg_set_page(&sg, sg_page(segment->sg), copied, + segment->copied + segment->sg_offset + + segment->sg->offset); + } else + sg_init_one(&sg, segment->data + segment->copied, + copied); + crypto_hash_update(segment->hash, &sg, copied); + } + + segment->copied += copied; + if (segment->copied < segment->size) { + iscsi_tcp_segment_map(segment, recv); + return 0; + } + + segment->total_copied += segment->copied; + segment->copied = 0; + segment->size = 0; + + /* Unmap the current scatterlist page, if there is one. */ + iscsi_tcp_segment_unmap(segment); + + /* Do we have more scatterlist entries? */ + debug_tcp("total copied %u total size %u\n", segment->total_copied, + segment->total_size); + if (segment->total_copied < segment->total_size) { + /* Proceed to the next entry in the scatterlist. */ + iscsi_tcp_segment_init_sg(segment, sg_next(segment->sg), + 0); + iscsi_tcp_segment_map(segment, recv); + BUG_ON(segment->size == 0); + return 0; + } + + /* Do we need to handle padding? */ + pad = iscsi_padding(segment->total_copied); + if (pad != 0) { + debug_tcp("consume %d pad bytes\n", pad); + segment->total_size += pad; + segment->size = pad; + segment->data = padbuf; + return 0; + } + + /* + * Set us up for transferring the data digest. hdr digest + * is completely handled in hdr done function. + */ + if (segment->hash) { + crypto_hash_final(segment->hash, segment->digest); + iscsi_tcp_segment_splice_digest(segment, + recv ? segment->recv_digest : segment->digest); + return 0; + } + + return 1; +} + +/** + * iscsi_tcp_xmit_segment - transmit segment + * @tcp_conn: the iSCSI TCP connection + * @segment: the buffer to transmnit + * + * This function transmits as much of the buffer as + * the network layer will accept, and returns the number of + * bytes transmitted. + * + * If CRC hashing is enabled, the function will compute the + * hash as it goes. When the entire segment has been transmitted, + * it will retrieve the hash value and send it as well. + */ +static int +iscsi_tcp_xmit_segment(struct iscsi_tcp_conn *tcp_conn, + struct iscsi_segment *segment) +{ + struct socket *sk = tcp_conn->sock; + unsigned int copied = 0; + int r = 0; + + while (!iscsi_tcp_segment_done(segment, 0, r)) { + struct scatterlist *sg; + unsigned int offset, copy; + int flags = 0; + + r = 0; + offset = segment->copied; + copy = segment->size - offset; + + if (segment->total_copied + segment->size < segment->total_size) + flags |= MSG_MORE; + + /* Use sendpage if we can; else fall back to sendmsg */ + if (!segment->data) { + sg = segment->sg; + offset += segment->sg_offset + sg->offset; + r = tcp_conn->sendpage(sk, sg_page(sg), offset, copy, + flags); } else { - /* ignoring return code since we checked - * in.copy before */ - skb_copy_bits(skb, tcp_conn->in.offset, - &tcp_conn->hdr, tcp_conn->hdr_size); - tcp_conn->in.hdr = &tcp_conn->hdr; + struct msghdr msg = { .msg_flags = flags }; + struct kvec iov = { + .iov_base = segment->data + offset, + .iov_len = copy + }; + + r = kernel_sendmsg(sk, &msg, &iov, 1, copy); } - tcp_conn->in.offset += tcp_conn->hdr_size; - tcp_conn->in.copy -= tcp_conn->hdr_size; - } else { - int hdr_remains; - int copylen; - /* - * PDU header scattered across SKB's, - * copying it... This'll happen quite rarely. - */ + if (r < 0) { + iscsi_tcp_segment_unmap(segment); + if (copied || r == -EAGAIN) + break; + return r; + } + copied += r; + } + return copied; +} - if (tcp_conn->in_progress == IN_PROGRESS_WAIT_HEADER) - tcp_conn->in.hdr_offset = 0; +/** + * iscsi_tcp_segment_recv - copy data to segment + * @tcp_conn: the iSCSI TCP connection + * @segment: the buffer to copy to + * @ptr: data pointer + * @len: amount of data available + * + * This function copies up to @len bytes to the + * given buffer, and returns the number of bytes + * consumed, which can actually be less than @len. + * + * If hash digest is enabled, the function will update the + * hash while copying. + * Combining these two operations doesn't buy us a lot (yet), + * but in the future we could implement combined copy+crc, + * just way we do for network layer checksums. + */ +static int +iscsi_tcp_segment_recv(struct iscsi_tcp_conn *tcp_conn, + struct iscsi_segment *segment, const void *ptr, + unsigned int len) +{ + unsigned int copy = 0, copied = 0; - hdr_remains = tcp_conn->hdr_size - tcp_conn->in.hdr_offset; - BUG_ON(hdr_remains <= 0); + while (!iscsi_tcp_segment_done(segment, 1, copy)) { + if (copied == len) { + debug_tcp("iscsi_tcp_segment_recv copied %d bytes\n", + len); + break; + } - copylen = min(tcp_conn->in.copy, hdr_remains); - skb_copy_bits(skb, tcp_conn->in.offset, - (char*)&tcp_conn->hdr + tcp_conn->in.hdr_offset, - copylen); + copy = min(len - copied, segment->size - segment->copied); + debug_tcp("iscsi_tcp_segment_recv copying %d\n", copy); + memcpy(segment->data + segment->copied, ptr + copied, copy); + copied += copy; + } + return copied; +} + +static inline void +iscsi_tcp_dgst_header(struct hash_desc *hash, const void *hdr, size_t hdrlen, + unsigned char digest[ISCSI_DIGEST_SIZE]) +{ + struct scatterlist sg; + + sg_init_one(&sg, hdr, hdrlen); + crypto_hash_digest(hash, &sg, hdrlen, digest); +} + +static inline int +iscsi_tcp_dgst_verify(struct iscsi_tcp_conn *tcp_conn, + struct iscsi_segment *segment) +{ + if (!segment->digest_len) + return 1; + + if (memcmp(segment->recv_digest, segment->digest, + segment->digest_len)) { + debug_scsi("digest mismatch\n"); + return 0; + } - debug_tcp("PDU gather offset %d bytes %d in.offset %d " - "in.copy %d\n", tcp_conn->in.hdr_offset, copylen, - tcp_conn->in.offset, tcp_conn->in.copy); + return 1; +} + +/* + * Helper function to set up segment buffer + */ +static inline void +__iscsi_segment_init(struct iscsi_segment *segment, size_t size, + iscsi_segment_done_fn_t *done, struct hash_desc *hash) +{ + memset(segment, 0, sizeof(*segment)); + segment->total_size = size; + segment->done = done; + + if (hash) { + segment->hash = hash; + crypto_hash_init(hash); + } +} + +static inline void +iscsi_segment_init_linear(struct iscsi_segment *segment, void *data, + size_t size, iscsi_segment_done_fn_t *done, + struct hash_desc *hash) +{ + __iscsi_segment_init(segment, size, done, hash); + segment->data = data; + segment->size = size; +} - tcp_conn->in.offset += copylen; - tcp_conn->in.copy -= copylen; - if (copylen < hdr_remains) { - tcp_conn->in_progress = IN_PROGRESS_HEADER_GATHER; - tcp_conn->in.hdr_offset += copylen; - return -EAGAIN; +static inline int +iscsi_segment_seek_sg(struct iscsi_segment *segment, + struct scatterlist *sg_list, unsigned int sg_count, + unsigned int offset, size_t size, + iscsi_segment_done_fn_t *done, struct hash_desc *hash) +{ + struct scatterlist *sg; + unsigned int i; + + debug_scsi("iscsi_segment_seek_sg offset %u size %llu\n", + offset, size); + __iscsi_segment_init(segment, size, done, hash); + for_each_sg(sg_list, sg, sg_count, i) { + debug_scsi("sg %d, len %u offset %u\n", i, sg->length, + sg->offset); + if (offset < sg->length) { + iscsi_tcp_segment_init_sg(segment, sg, offset); + return 0; } - tcp_conn->in.hdr = &tcp_conn->hdr; - tcp_conn->discontiguous_hdr_cnt++; - tcp_conn->in_progress = IN_PROGRESS_WAIT_HEADER; + offset -= sg->length; } + return ISCSI_ERR_DATA_OFFSET; +} + +/** + * iscsi_tcp_hdr_recv_prep - prep segment for hdr reception + * @tcp_conn: iscsi connection to prep for + * + * This function always passes NULL for the hash argument, because when this + * function is called we do not yet know the final size of the header and want + * to delay the digest processing until we know that. + */ +static void +iscsi_tcp_hdr_recv_prep(struct iscsi_tcp_conn *tcp_conn) +{ + debug_tcp("iscsi_tcp_hdr_recv_prep(%p%s)\n", tcp_conn, + tcp_conn->iscsi_conn->hdrdgst_en ? ", digest enabled" : ""); + iscsi_segment_init_linear(&tcp_conn->in.segment, + tcp_conn->in.hdr_buf, sizeof(struct iscsi_hdr), + iscsi_tcp_hdr_recv_done, NULL); +} + +/* + * Handle incoming reply to any other type of command + */ +static int +iscsi_tcp_data_recv_done(struct iscsi_tcp_conn *tcp_conn, + struct iscsi_segment *segment) +{ + struct iscsi_conn *conn = tcp_conn->iscsi_conn; + int rc = 0; + + if (!iscsi_tcp_dgst_verify(tcp_conn, segment)) + return ISCSI_ERR_DATA_DGST; + + rc = iscsi_complete_pdu(conn, tcp_conn->in.hdr, + conn->data, tcp_conn->in.datalen); + if (rc) + return rc; + + iscsi_tcp_hdr_recv_prep(tcp_conn); return 0; } +static void +iscsi_tcp_data_recv_prep(struct iscsi_tcp_conn *tcp_conn) +{ + struct iscsi_conn *conn = tcp_conn->iscsi_conn; + struct hash_desc *rx_hash = NULL; + + if (conn->datadgst_en) + rx_hash = &tcp_conn->rx_hash; + + iscsi_segment_init_linear(&tcp_conn->in.segment, + conn->data, tcp_conn->in.datalen, + iscsi_tcp_data_recv_done, rx_hash); +} + /* * must be called with session lock */ static void -iscsi_tcp_cleanup_ctask(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) +iscsi_tcp_cleanup_task(struct iscsi_conn *conn, struct iscsi_task *task) { - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; + struct iscsi_tcp_task *tcp_task = task->dd_data; struct iscsi_r2t_info *r2t; - struct scsi_cmnd *sc; - /* flush ctask's r2t queues */ - while (__kfifo_get(tcp_ctask->r2tqueue, (void*)&r2t, sizeof(void*))) { - __kfifo_put(tcp_ctask->r2tpool.queue, (void*)&r2t, + /* nothing to do for mgmt tasks */ + if (!task->sc) + return; + + /* flush task's r2t queues */ + while (__kfifo_get(tcp_task->r2tqueue, (void*)&r2t, sizeof(void*))) { + __kfifo_put(tcp_task->r2tpool.queue, (void*)&r2t, sizeof(void*)); - debug_scsi("iscsi_tcp_cleanup_ctask pending r2t dropped\n"); + debug_scsi("iscsi_tcp_cleanup_task pending r2t dropped\n"); } - sc = ctask->sc; - if (unlikely(!sc)) - return; - - tcp_ctask->xmstate = XMSTATE_IDLE; - tcp_ctask->r2t = NULL; + r2t = tcp_task->r2t; + if (r2t != NULL) { + __kfifo_put(tcp_task->r2tpool.queue, (void*)&r2t, + sizeof(void*)); + tcp_task->r2t = NULL; + } } /** * iscsi_data_rsp - SCSI Data-In Response processing * @conn: iscsi connection - * @ctask: scsi command task + * @task: scsi command task **/ static int -iscsi_data_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) +iscsi_data_rsp(struct iscsi_conn *conn, struct iscsi_task *task) { struct iscsi_tcp_conn *tcp_conn = conn->dd_data; - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; + struct iscsi_tcp_task *tcp_task = task->dd_data; struct iscsi_data_rsp *rhdr = (struct iscsi_data_rsp *)tcp_conn->in.hdr; struct iscsi_session *session = conn->session; - struct scsi_cmnd *sc = ctask->sc; + struct scsi_cmnd *sc = task->sc; int datasn = be32_to_cpu(rhdr->datasn); + unsigned total_in_length = scsi_in(sc)->length; iscsi_update_cmdsn(session, (struct iscsi_nopin*)rhdr); - /* - * setup Data-In byte counter (gets decremented..) - */ - ctask->data_count = tcp_conn->in.datalen; - if (tcp_conn->in.datalen == 0) return 0; - if (tcp_ctask->exp_datasn != datasn) { - debug_tcp("%s: ctask->exp_datasn(%d) != rhdr->datasn(%d)\n", - __FUNCTION__, tcp_ctask->exp_datasn, datasn); + if (tcp_task->exp_datasn != datasn) { + debug_tcp("%s: task->exp_datasn(%d) != rhdr->datasn(%d)\n", + __func__, tcp_task->exp_datasn, datasn); return ISCSI_ERR_DATASN; } - tcp_ctask->exp_datasn++; + tcp_task->exp_datasn++; - tcp_ctask->data_offset = be32_to_cpu(rhdr->offset); - if (tcp_ctask->data_offset + tcp_conn->in.datalen > sc->request_bufflen) { + tcp_task->data_offset = be32_to_cpu(rhdr->offset); + if (tcp_task->data_offset + tcp_conn->in.datalen > total_in_length) { debug_tcp("%s: data_offset(%d) + data_len(%d) > total_length_in(%d)\n", - __FUNCTION__, tcp_ctask->data_offset, - tcp_conn->in.datalen, sc->request_bufflen); + __func__, tcp_task->data_offset, + tcp_conn->in.datalen, total_in_length); return ISCSI_ERR_DATA_OFFSET; } if (rhdr->flags & ISCSI_FLAG_DATA_STATUS) { + sc->result = (DID_OK << 16) | rhdr->cmd_status; conn->exp_statsn = be32_to_cpu(rhdr->statsn) + 1; - if (rhdr->flags & ISCSI_FLAG_DATA_UNDERFLOW) { + if (rhdr->flags & (ISCSI_FLAG_DATA_UNDERFLOW | + ISCSI_FLAG_DATA_OVERFLOW)) { int res_count = be32_to_cpu(rhdr->residual_count); if (res_count > 0 && - res_count <= sc->request_bufflen) { - sc->resid = res_count; - sc->result = (DID_OK << 16) | rhdr->cmd_status; - } else + (rhdr->flags & ISCSI_FLAG_CMD_OVERFLOW || + res_count <= total_in_length)) + scsi_in(sc)->resid = res_count; + else sc->result = (DID_BAD_TARGET << 16) | rhdr->cmd_status; - } else if (rhdr->flags & ISCSI_FLAG_DATA_OVERFLOW) { - sc->resid = be32_to_cpu(rhdr->residual_count); - sc->result = (DID_OK << 16) | rhdr->cmd_status; - } else - sc->result = (DID_OK << 16) | rhdr->cmd_status; + } } conn->datain_pdus_cnt++; @@ -268,7 +582,7 @@ iscsi_data_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) /** * iscsi_solicit_data_init - initialize first Data-Out * @conn: iscsi connection - * @ctask: scsi command task + * @task: scsi command task * @r2t: R2T info * * Notes: @@ -278,11 +592,10 @@ iscsi_data_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) * This function is called with connection lock taken. **/ static void -iscsi_solicit_data_init(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask, +iscsi_solicit_data_init(struct iscsi_conn *conn, struct iscsi_task *task, struct iscsi_r2t_info *r2t) { struct iscsi_data *hdr; - struct scsi_cmnd *sc = ctask->sc; hdr = &r2t->dtask.hdr; memset(hdr, 0, sizeof(struct iscsi_data)); @@ -290,8 +603,8 @@ iscsi_solicit_data_init(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask, hdr->datasn = cpu_to_be32(r2t->solicit_datasn); r2t->solicit_datasn++; hdr->opcode = ISCSI_OP_SCSI_DATA_OUT; - memcpy(hdr->lun, ctask->hdr->lun, sizeof(hdr->lun)); - hdr->itt = ctask->hdr->itt; + memcpy(hdr->lun, task->hdr->lun, sizeof(hdr->lun)); + hdr->itt = task->hdr->itt; hdr->exp_statsn = r2t->exp_statsn; hdr->offset = cpu_to_be32(r2t->data_offset); if (r2t->data_length > conn->max_xmit_dlength) { @@ -306,93 +619,57 @@ iscsi_solicit_data_init(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask, conn->dataout_pdus_cnt++; r2t->sent = 0; - - iscsi_buf_init_iov(&r2t->headbuf, (char*)hdr, - sizeof(struct iscsi_hdr)); - - if (sc->use_sg) { - int i, sg_count = 0; - struct scatterlist *sg = sc->request_buffer; - - r2t->sg = NULL; - for (i = 0; i < sc->use_sg; i++, sg += 1) { - /* FIXME: prefetch ? */ - if (sg_count + sg->length > r2t->data_offset) { - int page_offset; - - /* sg page found! */ - - /* offset within this page */ - page_offset = r2t->data_offset - sg_count; - - /* fill in this buffer */ - iscsi_buf_init_sg(&r2t->sendbuf, sg); - r2t->sendbuf.sg.offset += page_offset; - r2t->sendbuf.sg.length -= page_offset; - - /* xmit logic will continue with next one */ - r2t->sg = sg + 1; - break; - } - sg_count += sg->length; - } - BUG_ON(r2t->sg == NULL); - } else { - iscsi_buf_init_iov(&r2t->sendbuf, - (char*)sc->request_buffer + r2t->data_offset, - r2t->data_count); - r2t->sg = NULL; - } } /** * iscsi_r2t_rsp - iSCSI R2T Response processing * @conn: iscsi connection - * @ctask: scsi command task + * @task: scsi command task **/ static int -iscsi_r2t_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) +iscsi_r2t_rsp(struct iscsi_conn *conn, struct iscsi_task *task) { struct iscsi_r2t_info *r2t; struct iscsi_session *session = conn->session; - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; + struct iscsi_tcp_task *tcp_task = task->dd_data; struct iscsi_tcp_conn *tcp_conn = conn->dd_data; struct iscsi_r2t_rsp *rhdr = (struct iscsi_r2t_rsp *)tcp_conn->in.hdr; int r2tsn = be32_to_cpu(rhdr->r2tsn); int rc; if (tcp_conn->in.datalen) { - printk(KERN_ERR "iscsi_tcp: invalid R2t with datalen %d\n", - tcp_conn->in.datalen); + iscsi_conn_printk(KERN_ERR, conn, + "invalid R2t with datalen %d\n", + tcp_conn->in.datalen); return ISCSI_ERR_DATALEN; } - if (tcp_ctask->exp_datasn != r2tsn){ - debug_tcp("%s: ctask->exp_datasn(%d) != rhdr->r2tsn(%d)\n", - __FUNCTION__, tcp_ctask->exp_datasn, r2tsn); + if (tcp_task->exp_datasn != r2tsn){ + debug_tcp("%s: task->exp_datasn(%d) != rhdr->r2tsn(%d)\n", + __func__, tcp_task->exp_datasn, r2tsn); return ISCSI_ERR_R2TSN; } /* fill-in new R2T associated with the task */ - spin_lock(&session->lock); iscsi_update_cmdsn(session, (struct iscsi_nopin*)rhdr); - if (!ctask->sc || ctask->mtask || - session->state != ISCSI_STATE_LOGGED_IN) { - printk(KERN_INFO "iscsi_tcp: dropping R2T itt %d in " - "recovery...\n", ctask->itt); - spin_unlock(&session->lock); + if (!task->sc || session->state != ISCSI_STATE_LOGGED_IN) { + iscsi_conn_printk(KERN_INFO, conn, + "dropping R2T itt %d in recovery.\n", + task->itt); return 0; } - rc = __kfifo_get(tcp_ctask->r2tpool.queue, (void*)&r2t, sizeof(void*)); + rc = __kfifo_get(tcp_task->r2tpool.queue, (void*)&r2t, sizeof(void*)); BUG_ON(!rc); r2t->exp_statsn = rhdr->statsn; r2t->data_length = be32_to_cpu(rhdr->data_length); if (r2t->data_length == 0) { - printk(KERN_ERR "iscsi_tcp: invalid R2T with zero data len\n"); - spin_unlock(&session->lock); + iscsi_conn_printk(KERN_ERR, conn, + "invalid R2T with zero data len\n"); + __kfifo_put(tcp_task->r2tpool.queue, (void*)&r2t, + sizeof(void*)); return ISCSI_ERR_DATALEN; } @@ -402,122 +679,159 @@ iscsi_r2t_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) r2t->data_length, session->max_burst); r2t->data_offset = be32_to_cpu(rhdr->data_offset); - if (r2t->data_offset + r2t->data_length > ctask->sc->request_bufflen) { - spin_unlock(&session->lock); - printk(KERN_ERR "iscsi_tcp: invalid R2T with data len %u at " - "offset %u and total length %d\n", r2t->data_length, - r2t->data_offset, ctask->sc->request_bufflen); + if (r2t->data_offset + r2t->data_length > scsi_out(task->sc)->length) { + iscsi_conn_printk(KERN_ERR, conn, + "invalid R2T with data len %u at offset %u " + "and total length %d\n", r2t->data_length, + r2t->data_offset, scsi_out(task->sc)->length); + __kfifo_put(tcp_task->r2tpool.queue, (void*)&r2t, + sizeof(void*)); return ISCSI_ERR_DATALEN; } r2t->ttt = rhdr->ttt; /* no flip */ r2t->solicit_datasn = 0; - iscsi_solicit_data_init(conn, ctask, r2t); + iscsi_solicit_data_init(conn, task, r2t); - tcp_ctask->exp_datasn = r2tsn + 1; - __kfifo_put(tcp_ctask->r2tqueue, (void*)&r2t, sizeof(void*)); - tcp_ctask->xmstate |= XMSTATE_SOL_HDR_INIT; - list_move_tail(&ctask->running, &conn->xmitqueue); - - scsi_queue_work(session->host, &conn->xmitwork); + tcp_task->exp_datasn = r2tsn + 1; + __kfifo_put(tcp_task->r2tqueue, (void*)&r2t, sizeof(void*)); conn->r2t_pdus_cnt++; - spin_unlock(&session->lock); + iscsi_requeue_task(task); return 0; } +/* + * Handle incoming reply to DataIn command + */ static int -iscsi_tcp_hdr_recv(struct iscsi_conn *conn) +iscsi_tcp_process_data_in(struct iscsi_tcp_conn *tcp_conn, + struct iscsi_segment *segment) +{ + struct iscsi_conn *conn = tcp_conn->iscsi_conn; + struct iscsi_hdr *hdr = tcp_conn->in.hdr; + int rc; + + if (!iscsi_tcp_dgst_verify(tcp_conn, segment)) + return ISCSI_ERR_DATA_DGST; + + /* check for non-exceptional status */ + if (hdr->flags & ISCSI_FLAG_DATA_STATUS) { + rc = iscsi_complete_pdu(conn, tcp_conn->in.hdr, NULL, 0); + if (rc) + return rc; + } + + iscsi_tcp_hdr_recv_prep(tcp_conn); + return 0; +} + +/** + * iscsi_tcp_hdr_dissect - process PDU header + * @conn: iSCSI connection + * @hdr: PDU header + * + * This function analyzes the header of the PDU received, + * and performs several sanity checks. If the PDU is accompanied + * by data, the receive buffer is set up to copy the incoming data + * to the correct location. + */ +static int +iscsi_tcp_hdr_dissect(struct iscsi_conn *conn, struct iscsi_hdr *hdr) { int rc = 0, opcode, ahslen; - struct iscsi_hdr *hdr; - struct iscsi_session *session = conn->session; struct iscsi_tcp_conn *tcp_conn = conn->dd_data; - uint32_t cdgst, rdgst = 0, itt; - - hdr = tcp_conn->in.hdr; + struct iscsi_task *task; /* verify PDU length */ tcp_conn->in.datalen = ntoh24(hdr->dlength); if (tcp_conn->in.datalen > conn->max_recv_dlength) { - printk(KERN_ERR "iscsi_tcp: datalen %d > %d\n", - tcp_conn->in.datalen, conn->max_recv_dlength); + iscsi_conn_printk(KERN_ERR, conn, + "iscsi_tcp: datalen %d > %d\n", + tcp_conn->in.datalen, conn->max_recv_dlength); return ISCSI_ERR_DATALEN; } - tcp_conn->data_copied = 0; - /* read AHS */ + /* Additional header segments. So far, we don't + * process additional headers. + */ ahslen = hdr->hlength << 2; - tcp_conn->in.offset += ahslen; - tcp_conn->in.copy -= ahslen; - if (tcp_conn->in.copy < 0) { - printk(KERN_ERR "iscsi_tcp: can't handle AHS with length " - "%d bytes\n", ahslen); - return ISCSI_ERR_AHSLEN; - } - - /* calculate read padding */ - tcp_conn->in.padding = tcp_conn->in.datalen & (ISCSI_PAD_LEN-1); - if (tcp_conn->in.padding) { - tcp_conn->in.padding = ISCSI_PAD_LEN - tcp_conn->in.padding; - debug_scsi("read padding %d bytes\n", tcp_conn->in.padding); - } - - if (conn->hdrdgst_en) { - struct scatterlist sg; - - sg_init_one(&sg, (u8 *)hdr, - sizeof(struct iscsi_hdr) + ahslen); - crypto_hash_digest(&tcp_conn->rx_hash, &sg, sg.length, - (u8 *)&cdgst); - rdgst = *(uint32_t*)((char*)hdr + sizeof(struct iscsi_hdr) + - ahslen); - if (cdgst != rdgst) { - printk(KERN_ERR "iscsi_tcp: hdrdgst error " - "recv 0x%x calc 0x%x\n", rdgst, cdgst); - return ISCSI_ERR_HDR_DGST; - } - } opcode = hdr->opcode & ISCSI_OPCODE_MASK; /* verify itt (itt encoding: age+cid+itt) */ - rc = iscsi_verify_itt(conn, hdr, &itt); - if (rc == ISCSI_ERR_NO_SCSI_CMD) { - tcp_conn->in.datalen = 0; /* force drop */ - return 0; - } else if (rc) + rc = iscsi_verify_itt(conn, hdr->itt); + if (rc) return rc; - debug_tcp("opcode 0x%x offset %d copy %d ahslen %d datalen %d\n", - opcode, tcp_conn->in.offset, tcp_conn->in.copy, - ahslen, tcp_conn->in.datalen); + debug_tcp("opcode 0x%x ahslen %d datalen %d\n", + opcode, ahslen, tcp_conn->in.datalen); switch(opcode) { case ISCSI_OP_SCSI_DATA_IN: - tcp_conn->in.ctask = session->cmds[itt]; - rc = iscsi_data_rsp(conn, tcp_conn->in.ctask); - if (rc) - return rc; - /* fall through */ - case ISCSI_OP_SCSI_CMD_RSP: - tcp_conn->in.ctask = session->cmds[itt]; - if (tcp_conn->in.datalen) - goto copy_hdr; + spin_lock(&conn->session->lock); + task = iscsi_itt_to_ctask(conn, hdr->itt); + if (!task) + rc = ISCSI_ERR_BAD_ITT; + else + rc = iscsi_data_rsp(conn, task); + if (rc) { + spin_unlock(&conn->session->lock); + break; + } - spin_lock(&session->lock); + if (tcp_conn->in.datalen) { + struct iscsi_tcp_task *tcp_task = task->dd_data; + struct hash_desc *rx_hash = NULL; + struct scsi_data_buffer *sdb = scsi_in(task->sc); + + /* + * Setup copy of Data-In into the Scsi_Cmnd + * Scatterlist case: + * We set up the iscsi_segment to point to the next + * scatterlist entry to copy to. As we go along, + * we move on to the next scatterlist entry and + * update the digest per-entry. + */ + if (conn->datadgst_en) + rx_hash = &tcp_conn->rx_hash; + + debug_tcp("iscsi_tcp_begin_data_in(%p, offset=%d, " + "datalen=%d)\n", tcp_conn, + tcp_task->data_offset, + tcp_conn->in.datalen); + rc = iscsi_segment_seek_sg(&tcp_conn->in.segment, + sdb->table.sgl, + sdb->table.nents, + tcp_task->data_offset, + tcp_conn->in.datalen, + iscsi_tcp_process_data_in, + rx_hash); + spin_unlock(&conn->session->lock); + return rc; + } rc = __iscsi_complete_pdu(conn, hdr, NULL, 0); - spin_unlock(&session->lock); + spin_unlock(&conn->session->lock); + break; + case ISCSI_OP_SCSI_CMD_RSP: + if (tcp_conn->in.datalen) { + iscsi_tcp_data_recv_prep(tcp_conn); + return 0; + } + rc = iscsi_complete_pdu(conn, hdr, NULL, 0); break; case ISCSI_OP_R2T: - tcp_conn->in.ctask = session->cmds[itt]; - if (ahslen) + spin_lock(&conn->session->lock); + task = iscsi_itt_to_ctask(conn, hdr->itt); + if (!task) + rc = ISCSI_ERR_BAD_ITT; + else if (ahslen) rc = ISCSI_ERR_AHSLEN; - else if (tcp_conn->in.ctask->sc->sc_data_direction == - DMA_TO_DEVICE) - rc = iscsi_r2t_rsp(conn, tcp_conn->in.ctask); + else if (task->sc->sc_data_direction == DMA_TO_DEVICE) + rc = iscsi_r2t_rsp(conn, task); else rc = ISCSI_ERR_PROTO; + spin_unlock(&conn->session->lock); break; case ISCSI_OP_LOGIN_RSP: case ISCSI_OP_TEXT_RSP: @@ -528,18 +842,24 @@ iscsi_tcp_hdr_recv(struct iscsi_conn *conn) * than 8K, but there are no targets that currently do this. * For now we fail until we find a vendor that needs it */ - if (ISCSI_DEF_MAX_RECV_SEG_LEN < - tcp_conn->in.datalen) { - printk(KERN_ERR "iscsi_tcp: received buffer of len %u " - "but conn buffer is only %u (opcode %0x)\n", - tcp_conn->in.datalen, - ISCSI_DEF_MAX_RECV_SEG_LEN, opcode); + if (ISCSI_DEF_MAX_RECV_SEG_LEN < tcp_conn->in.datalen) { + iscsi_conn_printk(KERN_ERR, conn, + "iscsi_tcp: received buffer of " + "len %u but conn buffer is only %u " + "(opcode %0x)\n", + tcp_conn->in.datalen, + ISCSI_DEF_MAX_RECV_SEG_LEN, opcode); rc = ISCSI_ERR_PROTO; break; } - if (tcp_conn->in.datalen) - goto copy_hdr; + /* If there's data coming in with the response, + * receive it to the connection's buffer. + */ + if (tcp_conn->in.datalen) { + iscsi_tcp_data_recv_prep(tcp_conn); + return 0; + } /* fall through */ case ISCSI_OP_LOGOUT_RSP: case ISCSI_OP_NOOP_IN: @@ -551,457 +871,161 @@ iscsi_tcp_hdr_recv(struct iscsi_conn *conn) break; } - return rc; - -copy_hdr: - /* - * if we did zero copy for the header but we will need multiple - * skbs to complete the command then we have to copy the header - * for later use - */ - if (tcp_conn->in.zero_copy_hdr && tcp_conn->in.copy <= - (tcp_conn->in.datalen + tcp_conn->in.padding + - (conn->datadgst_en ? 4 : 0))) { - debug_tcp("Copying header for later use. in.copy %d in.datalen" - " %d\n", tcp_conn->in.copy, tcp_conn->in.datalen); - memcpy(&tcp_conn->hdr, tcp_conn->in.hdr, - sizeof(struct iscsi_hdr)); - tcp_conn->in.hdr = &tcp_conn->hdr; - tcp_conn->in.zero_copy_hdr = 0; - } - return 0; -} - -/** - * iscsi_ctask_copy - copy skb bits to the destanation cmd task - * @conn: iscsi tcp connection - * @ctask: scsi command task - * @buf: buffer to copy to - * @buf_size: size of buffer - * @offset: offset within the buffer - * - * Notes: - * The function calls skb_copy_bits() and updates per-connection and - * per-cmd byte counters. - * - * Read counters (in bytes): - * - * conn->in.offset offset within in progress SKB - * conn->in.copy left to copy from in progress SKB - * including padding - * conn->in.copied copied already from in progress SKB - * conn->data_copied copied already from in progress buffer - * ctask->sent total bytes sent up to the MidLayer - * ctask->data_count left to copy from in progress Data-In - * buf_left left to copy from in progress buffer - **/ -static inline int -iscsi_ctask_copy(struct iscsi_tcp_conn *tcp_conn, struct iscsi_cmd_task *ctask, - void *buf, int buf_size, int offset) -{ - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; - int buf_left = buf_size - (tcp_conn->data_copied + offset); - unsigned size = min(tcp_conn->in.copy, buf_left); - int rc; - - size = min(size, ctask->data_count); - - debug_tcp("ctask_copy %d bytes at offset %d copied %d\n", - size, tcp_conn->in.offset, tcp_conn->in.copied); - - BUG_ON(size <= 0); - BUG_ON(tcp_ctask->sent + size > ctask->sc->request_bufflen); - - rc = skb_copy_bits(tcp_conn->in.skb, tcp_conn->in.offset, - (char*)buf + (offset + tcp_conn->data_copied), size); - /* must fit into skb->len */ - BUG_ON(rc); - - tcp_conn->in.offset += size; - tcp_conn->in.copy -= size; - tcp_conn->in.copied += size; - tcp_conn->data_copied += size; - tcp_ctask->sent += size; - ctask->data_count -= size; - - BUG_ON(tcp_conn->in.copy < 0); - BUG_ON(ctask->data_count < 0); - - if (buf_size != (tcp_conn->data_copied + offset)) { - if (!ctask->data_count) { - BUG_ON(buf_size - tcp_conn->data_copied < 0); - /* done with this PDU */ - return buf_size - tcp_conn->data_copied; - } - return -EAGAIN; + if (rc == 0) { + /* Anything that comes with data should have + * been handled above. */ + if (tcp_conn->in.datalen) + return ISCSI_ERR_PROTO; + iscsi_tcp_hdr_recv_prep(tcp_conn); } - /* done with this buffer or with both - PDU and buffer */ - tcp_conn->data_copied = 0; - return 0; + return rc; } /** - * iscsi_tcp_copy - copy skb bits to the destanation buffer - * @conn: iscsi tcp connection + * iscsi_tcp_hdr_recv_done - process PDU header * - * Notes: - * The function calls skb_copy_bits() and updates per-connection - * byte counters. - **/ -static inline int -iscsi_tcp_copy(struct iscsi_conn *conn, int buf_size) -{ - struct iscsi_tcp_conn *tcp_conn = conn->dd_data; - int buf_left = buf_size - tcp_conn->data_copied; - int size = min(tcp_conn->in.copy, buf_left); - int rc; - - debug_tcp("tcp_copy %d bytes at offset %d copied %d\n", - size, tcp_conn->in.offset, tcp_conn->data_copied); - BUG_ON(size <= 0); - - rc = skb_copy_bits(tcp_conn->in.skb, tcp_conn->in.offset, - (char*)conn->data + tcp_conn->data_copied, size); - BUG_ON(rc); - - tcp_conn->in.offset += size; - tcp_conn->in.copy -= size; - tcp_conn->in.copied += size; - tcp_conn->data_copied += size; - - if (buf_size != tcp_conn->data_copied) - return -EAGAIN; - - return 0; -} - -static inline void -partial_sg_digest_update(struct hash_desc *desc, struct scatterlist *sg, - int offset, int length) -{ - struct scatterlist temp; - - memcpy(&temp, sg, sizeof(struct scatterlist)); - temp.offset = offset; - temp.length = length; - crypto_hash_update(desc, &temp, length); -} - -static void -iscsi_recv_digest_update(struct iscsi_tcp_conn *tcp_conn, char* buf, int len) -{ - struct scatterlist tmp; - - sg_init_one(&tmp, buf, len); - crypto_hash_update(&tcp_conn->rx_hash, &tmp, len); -} - -static int iscsi_scsi_data_in(struct iscsi_conn *conn) + * This is the callback invoked when the PDU header has + * been received. If the header is followed by additional + * header segments, we go back for more data. + */ +static int +iscsi_tcp_hdr_recv_done(struct iscsi_tcp_conn *tcp_conn, + struct iscsi_segment *segment) { - struct iscsi_tcp_conn *tcp_conn = conn->dd_data; - struct iscsi_cmd_task *ctask = tcp_conn->in.ctask; - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; - struct scsi_cmnd *sc = ctask->sc; - struct scatterlist *sg; - int i, offset, rc = 0; - - BUG_ON((void*)ctask != sc->SCp.ptr); + struct iscsi_conn *conn = tcp_conn->iscsi_conn; + struct iscsi_hdr *hdr; - /* - * copying Data-In into the Scsi_Cmnd + /* Check if there are additional header segments + * *prior* to computing the digest, because we + * may need to go back to the caller for more. */ - if (!sc->use_sg) { - i = ctask->data_count; - rc = iscsi_ctask_copy(tcp_conn, ctask, sc->request_buffer, - sc->request_bufflen, - tcp_ctask->data_offset); - if (rc == -EAGAIN) - return rc; - if (conn->datadgst_en) - iscsi_recv_digest_update(tcp_conn, sc->request_buffer, - i); - rc = 0; - goto done; + hdr = (struct iscsi_hdr *) tcp_conn->in.hdr_buf; + if (segment->copied == sizeof(struct iscsi_hdr) && hdr->hlength) { + /* Bump the header length - the caller will + * just loop around and get the AHS for us, and + * call again. */ + unsigned int ahslen = hdr->hlength << 2; + + /* Make sure we don't overflow */ + if (sizeof(*hdr) + ahslen > sizeof(tcp_conn->in.hdr_buf)) + return ISCSI_ERR_AHSLEN; + + segment->total_size += ahslen; + segment->size += ahslen; + return 0; } - offset = tcp_ctask->data_offset; - sg = sc->request_buffer; - - if (tcp_ctask->data_offset) - for (i = 0; i < tcp_ctask->sg_count; i++) - offset -= sg[i].length; - /* we've passed through partial sg*/ - if (offset < 0) - offset = 0; - - for (i = tcp_ctask->sg_count; i < sc->use_sg; i++) { - char *dest; - - dest = kmap_atomic(sg[i].page, KM_SOFTIRQ0); - rc = iscsi_ctask_copy(tcp_conn, ctask, dest + sg[i].offset, - sg[i].length, offset); - kunmap_atomic(dest, KM_SOFTIRQ0); - if (rc == -EAGAIN) - /* continue with the next SKB/PDU */ - return rc; - if (!rc) { - if (conn->datadgst_en) { - if (!offset) - crypto_hash_update( - &tcp_conn->rx_hash, - &sg[i], sg[i].length); - else - partial_sg_digest_update( - &tcp_conn->rx_hash, - &sg[i], - sg[i].offset + offset, - sg[i].length - offset); - } - offset = 0; - tcp_ctask->sg_count++; - } - - if (!ctask->data_count) { - if (rc && conn->datadgst_en) - /* - * data-in is complete, but buffer not... - */ - partial_sg_digest_update(&tcp_conn->rx_hash, - &sg[i], - sg[i].offset, - sg[i].length-rc); - rc = 0; - break; + /* We're done processing the header. See if we're doing + * header digests; if so, set up the recv_digest buffer + * and go back for more. */ + if (conn->hdrdgst_en) { + if (segment->digest_len == 0) { + iscsi_tcp_segment_splice_digest(segment, + segment->recv_digest); + return 0; } + iscsi_tcp_dgst_header(&tcp_conn->rx_hash, hdr, + segment->total_copied - ISCSI_DIGEST_SIZE, + segment->digest); - if (!tcp_conn->in.copy) - return -EAGAIN; - } - BUG_ON(ctask->data_count); - -done: - /* check for non-exceptional status */ - if (tcp_conn->in.hdr->flags & ISCSI_FLAG_DATA_STATUS) { - debug_scsi("done [sc %lx res %d itt 0x%x flags 0x%x]\n", - (long)sc, sc->result, ctask->itt, - tcp_conn->in.hdr->flags); - spin_lock(&conn->session->lock); - __iscsi_complete_pdu(conn, tcp_conn->in.hdr, NULL, 0); - spin_unlock(&conn->session->lock); + if (!iscsi_tcp_dgst_verify(tcp_conn, segment)) + return ISCSI_ERR_HDR_DGST; } - return rc; -} - -static int -iscsi_data_recv(struct iscsi_conn *conn) -{ - struct iscsi_tcp_conn *tcp_conn = conn->dd_data; - int rc = 0, opcode; - - opcode = tcp_conn->in.hdr->opcode & ISCSI_OPCODE_MASK; - switch (opcode) { - case ISCSI_OP_SCSI_DATA_IN: - rc = iscsi_scsi_data_in(conn); - break; - case ISCSI_OP_SCSI_CMD_RSP: - case ISCSI_OP_TEXT_RSP: - case ISCSI_OP_LOGIN_RSP: - case ISCSI_OP_ASYNC_EVENT: - case ISCSI_OP_REJECT: - /* - * Collect data segment to the connection's data - * placeholder - */ - if (iscsi_tcp_copy(conn, tcp_conn->in.datalen)) { - rc = -EAGAIN; - goto exit; - } - - rc = iscsi_complete_pdu(conn, tcp_conn->in.hdr, conn->data, - tcp_conn->in.datalen); - if (!rc && conn->datadgst_en && opcode != ISCSI_OP_LOGIN_RSP) - iscsi_recv_digest_update(tcp_conn, conn->data, - tcp_conn->in.datalen); - break; - default: - BUG_ON(1); - } -exit: - return rc; + tcp_conn->in.hdr = hdr; + return iscsi_tcp_hdr_dissect(conn, hdr); } /** - * iscsi_tcp_data_recv - TCP receive in sendfile fashion + * iscsi_tcp_recv - TCP receive in sendfile fashion * @rd_desc: read descriptor * @skb: socket buffer * @offset: offset in skb * @len: skb->len - offset **/ static int -iscsi_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, - unsigned int offset, size_t len) +iscsi_tcp_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, + unsigned int offset, size_t len) { - int rc; struct iscsi_conn *conn = rd_desc->arg.data; struct iscsi_tcp_conn *tcp_conn = conn->dd_data; - int processed; - char pad[ISCSI_PAD_LEN]; - struct scatterlist sg; - - /* - * Save current SKB and its offset in the corresponding - * connection context. - */ - tcp_conn->in.copy = skb->len - offset; - tcp_conn->in.offset = offset; - tcp_conn->in.skb = skb; - tcp_conn->in.len = tcp_conn->in.copy; - BUG_ON(tcp_conn->in.copy <= 0); - debug_tcp("in %d bytes\n", tcp_conn->in.copy); + struct iscsi_segment *segment = &tcp_conn->in.segment; + struct skb_seq_state seq; + unsigned int consumed = 0; + int rc = 0; -more: - tcp_conn->in.copied = 0; - rc = 0; + debug_tcp("in %d bytes\n", skb->len - offset); if (unlikely(conn->suspend_rx)) { debug_tcp("conn %d Rx suspended!\n", conn->id); return 0; } - if (tcp_conn->in_progress == IN_PROGRESS_WAIT_HEADER || - tcp_conn->in_progress == IN_PROGRESS_HEADER_GATHER) { - rc = iscsi_hdr_extract(tcp_conn); - if (rc) { - if (rc == -EAGAIN) - goto nomore; - else { - iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED); - return 0; - } - } - - /* - * Verify and process incoming PDU header. - */ - rc = iscsi_tcp_hdr_recv(conn); - if (!rc && tcp_conn->in.datalen) { - if (conn->datadgst_en) - crypto_hash_init(&tcp_conn->rx_hash); - tcp_conn->in_progress = IN_PROGRESS_DATA_RECV; - } else if (rc) { - iscsi_conn_failure(conn, rc); - return 0; - } - } - - if (tcp_conn->in_progress == IN_PROGRESS_DDIGEST_RECV) { - uint32_t recv_digest; - - debug_tcp("extra data_recv offset %d copy %d\n", - tcp_conn->in.offset, tcp_conn->in.copy); - rc = iscsi_tcp_copy(conn, sizeof(uint32_t)); - if (rc) { - if (rc == -EAGAIN) - goto again; - iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED); - return 0; - } + skb_prepare_seq_read(skb, offset, skb->len, &seq); + while (1) { + unsigned int avail; + const u8 *ptr; - memcpy(&recv_digest, conn->data, sizeof(uint32_t)); - if (recv_digest != tcp_conn->in.datadgst) { - debug_tcp("iscsi_tcp: data digest error!" - "0x%x != 0x%x\n", recv_digest, - tcp_conn->in.datadgst); - iscsi_conn_failure(conn, ISCSI_ERR_DATA_DGST); - return 0; - } else { - debug_tcp("iscsi_tcp: data digest match!" - "0x%x == 0x%x\n", recv_digest, - tcp_conn->in.datadgst); - tcp_conn->in_progress = IN_PROGRESS_WAIT_HEADER; - } - } - - if (tcp_conn->in_progress == IN_PROGRESS_DATA_RECV && - tcp_conn->in.copy) { - - debug_tcp("data_recv offset %d copy %d\n", - tcp_conn->in.offset, tcp_conn->in.copy); - - rc = iscsi_data_recv(conn); - if (rc) { - if (rc == -EAGAIN) - goto again; - iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED); - return 0; + avail = skb_seq_read(consumed, &ptr, &seq); + if (avail == 0) { + debug_tcp("no more data avail. Consumed %d\n", + consumed); + break; } - tcp_conn->in.copy -= tcp_conn->in.padding; - tcp_conn->in.offset += tcp_conn->in.padding; - if (conn->datadgst_en) { - if (tcp_conn->in.padding) { - debug_tcp("padding -> %d\n", - tcp_conn->in.padding); - memset(pad, 0, tcp_conn->in.padding); - sg_init_one(&sg, pad, tcp_conn->in.padding); - crypto_hash_update(&tcp_conn->rx_hash, - &sg, sg.length); + BUG_ON(segment->copied >= segment->size); + + debug_tcp("skb %p ptr=%p avail=%u\n", skb, ptr, avail); + rc = iscsi_tcp_segment_recv(tcp_conn, segment, ptr, avail); + BUG_ON(rc == 0); + consumed += rc; + + if (segment->total_copied >= segment->total_size) { + debug_tcp("segment done\n"); + rc = segment->done(tcp_conn, segment); + if (rc != 0) { + skb_abort_seq_read(&seq); + goto error; } - crypto_hash_final(&tcp_conn->rx_hash, - (u8 *) &tcp_conn->in.datadgst); - debug_tcp("rx digest 0x%x\n", tcp_conn->in.datadgst); - tcp_conn->in_progress = IN_PROGRESS_DDIGEST_RECV; - tcp_conn->data_copied = 0; - } else - tcp_conn->in_progress = IN_PROGRESS_WAIT_HEADER; - } - - debug_tcp("f, processed %d from out of %d padding %d\n", - tcp_conn->in.offset - offset, (int)len, tcp_conn->in.padding); - BUG_ON(tcp_conn->in.offset - offset > len); - if (tcp_conn->in.offset - offset != len) { - debug_tcp("continue to process %d bytes\n", - (int)len - (tcp_conn->in.offset - offset)); - goto more; + /* The done() functions sets up the + * next segment. */ + } } + skb_abort_seq_read(&seq); + conn->rxdata_octets += consumed; + return consumed; -nomore: - processed = tcp_conn->in.offset - offset; - BUG_ON(processed == 0); - return processed; - -again: - processed = tcp_conn->in.offset - offset; - debug_tcp("c, processed %d from out of %d rd_desc_cnt %d\n", - processed, (int)len, (int)rd_desc->count); - BUG_ON(processed == 0); - BUG_ON(processed > len); - - conn->rxdata_octets += processed; - return processed; +error: + debug_tcp("Error receiving PDU, errno=%d\n", rc); + iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED); + return 0; } static void iscsi_tcp_data_ready(struct sock *sk, int flag) { struct iscsi_conn *conn = sk->sk_user_data; + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; read_descriptor_t rd_desc; read_lock(&sk->sk_callback_lock); /* - * Use rd_desc to pass 'conn' to iscsi_tcp_data_recv. + * Use rd_desc to pass 'conn' to iscsi_tcp_recv. * We set count to 1 because we want the network layer to - * hand us all the skbs that are available. iscsi_tcp_data_recv + * hand us all the skbs that are available. iscsi_tcp_recv * handled pdus that cross buffers or pdus that still need data. */ rd_desc.arg.data = conn; rd_desc.count = 1; - tcp_read_sock(sk, &rd_desc, iscsi_tcp_data_recv); + tcp_read_sock(sk, &rd_desc, iscsi_tcp_recv); read_unlock(&sk->sk_callback_lock); + + /* If we had to (atomically) map a highmem page, + * unmap it now. */ + iscsi_tcp_segment_unmap(&tcp_conn->in.segment); } static void @@ -1081,127 +1105,179 @@ iscsi_conn_restore_callbacks(struct iscsi_tcp_conn *tcp_conn) } /** - * iscsi_send - generic send routine - * @sk: kernel's socket - * @buf: buffer to write from - * @size: actual size to write - * @flags: socket's flags - */ -static inline int -iscsi_send(struct iscsi_conn *conn, struct iscsi_buf *buf, int size, int flags) + * iscsi_xmit - TCP transmit + **/ +static int +iscsi_xmit(struct iscsi_conn *conn) { struct iscsi_tcp_conn *tcp_conn = conn->dd_data; - struct socket *sk = tcp_conn->sock; - int offset = buf->sg.offset + buf->sent, res; + struct iscsi_segment *segment = &tcp_conn->out.segment; + unsigned int consumed = 0; + int rc = 0; - /* - * if we got use_sg=0 or are sending something we kmallocd - * then we did not have to do kmap (kmap returns page_address) - * - * if we got use_sg > 0, but had to drop down, we do not - * set clustering so this should only happen for that - * slab case. - */ - if (buf->use_sendmsg) - res = sock_no_sendpage(sk, buf->sg.page, offset, size, flags); - else - res = tcp_conn->sendpage(sk, buf->sg.page, offset, size, flags); - - if (res >= 0) { - conn->txdata_octets += res; - buf->sent += res; - return res; + while (1) { + rc = iscsi_tcp_xmit_segment(tcp_conn, segment); + if (rc < 0) + goto error; + if (rc == 0) + break; + + consumed += rc; + + if (segment->total_copied >= segment->total_size) { + if (segment->done != NULL) { + rc = segment->done(tcp_conn, segment); + if (rc < 0) + goto error; + } + } } - tcp_conn->sendpage_failures_cnt++; - if (res == -EAGAIN) - res = -ENOBUFS; - else - iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED); - return res; + debug_tcp("xmit %d bytes\n", consumed); + + conn->txdata_octets += consumed; + return consumed; + +error: + /* Transmit error. We could initiate error recovery + * here. */ + debug_tcp("Error sending PDU, errno=%d\n", rc); + iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED); + return rc; } /** - * iscsi_sendhdr - send PDU Header via tcp_sendpage() - * @conn: iscsi connection - * @buf: buffer to write from - * @datalen: lenght of data to be sent after the header - * - * Notes: - * (Tx, Fast Path) - **/ + * iscsi_tcp_xmit_qlen - return the number of bytes queued for xmit + */ static inline int -iscsi_sendhdr(struct iscsi_conn *conn, struct iscsi_buf *buf, int datalen) +iscsi_tcp_xmit_qlen(struct iscsi_conn *conn) { - int flags = 0; /* MSG_DONTWAIT; */ - int res, size; - - size = buf->sg.length - buf->sent; - BUG_ON(buf->sent + size > buf->sg.length); - if (buf->sent + size != buf->sg.length || datalen) - flags |= MSG_MORE; - - res = iscsi_send(conn, buf, size, flags); - debug_tcp("sendhdr %d bytes, sent %d res %d\n", size, buf->sent, res); - if (res >= 0) { - if (size != res) - return -EAGAIN; - return 0; - } + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct iscsi_segment *segment = &tcp_conn->out.segment; - return res; + return segment->total_copied - segment->total_size; } -/** - * iscsi_sendpage - send one page of iSCSI Data-Out. - * @conn: iscsi connection - * @buf: buffer to write from - * @count: remaining data - * @sent: number of bytes sent - * - * Notes: - * (Tx, Fast Path) - **/ static inline int -iscsi_sendpage(struct iscsi_conn *conn, struct iscsi_buf *buf, - int *count, int *sent) +iscsi_tcp_flush(struct iscsi_conn *conn) { - int flags = 0; /* MSG_DONTWAIT; */ - int res, size; - - size = buf->sg.length - buf->sent; - BUG_ON(buf->sent + size > buf->sg.length); - if (size > *count) - size = *count; - if (buf->sent + size != buf->sg.length || *count != size) - flags |= MSG_MORE; - - res = iscsi_send(conn, buf, size, flags); - debug_tcp("sendpage: %d bytes, sent %d left %d sent %d res %d\n", - size, buf->sent, *count, *sent, res); - if (res >= 0) { - *count -= res; - *sent += res; - if (size != res) + int rc; + + while (iscsi_tcp_xmit_qlen(conn)) { + rc = iscsi_xmit(conn); + if (rc == 0) return -EAGAIN; - return 0; + if (rc < 0) + return rc; } - return res; -} + return 0; +} + +/* + * This is called when we're done sending the header. + * Simply copy the data_segment to the send segment, and return. + */ +static int +iscsi_tcp_send_hdr_done(struct iscsi_tcp_conn *tcp_conn, + struct iscsi_segment *segment) +{ + tcp_conn->out.segment = tcp_conn->out.data_segment; + debug_tcp("Header done. Next segment size %u total_size %u\n", + tcp_conn->out.segment.size, tcp_conn->out.segment.total_size); + return 0; +} + +static void +iscsi_tcp_send_hdr_prep(struct iscsi_conn *conn, void *hdr, size_t hdrlen) +{ + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + + debug_tcp("%s(%p%s)\n", __func__, tcp_conn, + conn->hdrdgst_en? ", digest enabled" : ""); + + /* Clear the data segment - needs to be filled in by the + * caller using iscsi_tcp_send_data_prep() */ + memset(&tcp_conn->out.data_segment, 0, sizeof(struct iscsi_segment)); + + /* If header digest is enabled, compute the CRC and + * place the digest into the same buffer. We make + * sure that both iscsi_tcp_task and mtask have + * sufficient room. + */ + if (conn->hdrdgst_en) { + iscsi_tcp_dgst_header(&tcp_conn->tx_hash, hdr, hdrlen, + hdr + hdrlen); + hdrlen += ISCSI_DIGEST_SIZE; + } + + /* Remember header pointer for later, when we need + * to decide whether there's a payload to go along + * with the header. */ + tcp_conn->out.hdr = hdr; + + iscsi_segment_init_linear(&tcp_conn->out.segment, hdr, hdrlen, + iscsi_tcp_send_hdr_done, NULL); +} + +/* + * Prepare the send buffer for the payload data. + * Padding and checksumming will all be taken care + * of by the iscsi_segment routines. + */ +static int +iscsi_tcp_send_data_prep(struct iscsi_conn *conn, struct scatterlist *sg, + unsigned int count, unsigned int offset, + unsigned int len) +{ + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct hash_desc *tx_hash = NULL; + unsigned int hdr_spec_len; + + debug_tcp("%s(%p, offset=%d, datalen=%d%s)\n", __func__, + tcp_conn, offset, len, + conn->datadgst_en? ", digest enabled" : ""); + + /* Make sure the datalen matches what the caller + said he would send. */ + hdr_spec_len = ntoh24(tcp_conn->out.hdr->dlength); + WARN_ON(iscsi_padded(len) != iscsi_padded(hdr_spec_len)); + + if (conn->datadgst_en) + tx_hash = &tcp_conn->tx_hash; + + return iscsi_segment_seek_sg(&tcp_conn->out.data_segment, + sg, count, offset, len, + NULL, tx_hash); +} + +static void +iscsi_tcp_send_linear_data_prepare(struct iscsi_conn *conn, void *data, + size_t len) +{ + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct hash_desc *tx_hash = NULL; + unsigned int hdr_spec_len; + + debug_tcp("%s(%p, datalen=%d%s)\n", __func__, tcp_conn, len, + conn->datadgst_en? ", digest enabled" : ""); -static inline void -iscsi_data_digest_init(struct iscsi_tcp_conn *tcp_conn, - struct iscsi_tcp_cmd_task *tcp_ctask) -{ - crypto_hash_init(&tcp_conn->tx_hash); - tcp_ctask->digest_count = 4; + /* Make sure the datalen matches what the caller + said he would send. */ + hdr_spec_len = ntoh24(tcp_conn->out.hdr->dlength); + WARN_ON(iscsi_padded(len) != iscsi_padded(hdr_spec_len)); + + if (conn->datadgst_en) + tx_hash = &tcp_conn->tx_hash; + + iscsi_segment_init_linear(&tcp_conn->out.data_segment, + data, len, NULL, tx_hash); } /** * iscsi_solicit_data_cont - initialize next Data-Out * @conn: iscsi connection - * @ctask: scsi command task + * @task: scsi command task * @r2t: R2T info * @left: bytes left to transfer * @@ -1211,13 +1287,17 @@ iscsi_data_digest_init(struct iscsi_tcp_conn *tcp_conn, * * Called under connection lock. **/ -static void -iscsi_solicit_data_cont(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask, - struct iscsi_r2t_info *r2t, int left) +static int +iscsi_solicit_data_cont(struct iscsi_conn *conn, struct iscsi_task *task, + struct iscsi_r2t_info *r2t) { struct iscsi_data *hdr; - struct scsi_cmnd *sc = ctask->sc; - int new_offset; + int new_offset, left; + + BUG_ON(r2t->data_length - r2t->sent < 0); + left = r2t->data_length - r2t->sent; + if (left == 0) + return 0; hdr = &r2t->dtask.hdr; memset(hdr, 0, sizeof(struct iscsi_data)); @@ -1225,8 +1305,8 @@ iscsi_solicit_data_cont(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask, hdr->datasn = cpu_to_be32(r2t->solicit_datasn); r2t->solicit_datasn++; hdr->opcode = ISCSI_OP_SCSI_DATA_OUT; - memcpy(hdr->lun, ctask->hdr->lun, sizeof(hdr->lun)); - hdr->itt = ctask->hdr->itt; + memcpy(hdr->lun, task->hdr->lun, sizeof(hdr->lun)); + hdr->itt = task->hdr->itt; hdr->exp_statsn = r2t->exp_statsn; new_offset = r2t->data_offset + r2t->sent; hdr->offset = cpu_to_be32(new_offset); @@ -1238,548 +1318,177 @@ iscsi_solicit_data_cont(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask, r2t->data_count = left; hdr->flags = ISCSI_FLAG_CMD_FINAL; } - conn->dataout_pdus_cnt++; - - iscsi_buf_init_iov(&r2t->headbuf, (char*)hdr, - sizeof(struct iscsi_hdr)); - - if (iscsi_buf_left(&r2t->sendbuf)) - return; - - if (sc->use_sg) { - iscsi_buf_init_sg(&r2t->sendbuf, r2t->sg); - r2t->sg += 1; - } else { - iscsi_buf_init_iov(&r2t->sendbuf, - (char*)sc->request_buffer + new_offset, - r2t->data_count); - r2t->sg = NULL; - } -} - -static void iscsi_set_padding(struct iscsi_tcp_cmd_task *tcp_ctask, - unsigned long len) -{ - tcp_ctask->pad_count = len & (ISCSI_PAD_LEN - 1); - if (!tcp_ctask->pad_count) - return; - tcp_ctask->pad_count = ISCSI_PAD_LEN - tcp_ctask->pad_count; - debug_scsi("write padding %d bytes\n", tcp_ctask->pad_count); - tcp_ctask->xmstate |= XMSTATE_W_PAD; + conn->dataout_pdus_cnt++; + return 1; } /** - * iscsi_tcp_cmd_init - Initialize iSCSI SCSI_READ or SCSI_WRITE commands + * iscsi_tcp_task - Initialize iSCSI SCSI_READ or SCSI_WRITE commands * @conn: iscsi connection - * @ctask: scsi command task + * @task: scsi command task * @sc: scsi command **/ -static void -iscsi_tcp_cmd_init(struct iscsi_cmd_task *ctask) -{ - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; - - BUG_ON(__kfifo_len(tcp_ctask->r2tqueue)); - tcp_ctask->xmstate = XMSTATE_CMD_HDR_INIT; -} - -/** - * iscsi_tcp_mtask_xmit - xmit management(immediate) task - * @conn: iscsi connection - * @mtask: task management task - * - * Notes: - * The function can return -EAGAIN in which case caller must - * call it again later, or recover. '0' return code means successful - * xmit. - * - * Management xmit state machine consists of these states: - * XMSTATE_IMM_HDR_INIT - calculate digest of PDU Header - * XMSTATE_IMM_HDR - PDU Header xmit in progress - * XMSTATE_IMM_DATA - PDU Data xmit in progress - * XMSTATE_IDLE - management PDU is done - **/ static int -iscsi_tcp_mtask_xmit(struct iscsi_conn *conn, struct iscsi_mgmt_task *mtask) +iscsi_tcp_task_init(struct iscsi_task *task) { - struct iscsi_tcp_mgmt_task *tcp_mtask = mtask->dd_data; - int rc; - - debug_scsi("mtask deq [cid %d state %x itt 0x%x]\n", - conn->id, tcp_mtask->xmstate, mtask->itt); - - if (tcp_mtask->xmstate & XMSTATE_IMM_HDR_INIT) { - iscsi_buf_init_iov(&tcp_mtask->headbuf, (char*)mtask->hdr, - sizeof(struct iscsi_hdr)); + struct iscsi_tcp_task *tcp_task = task->dd_data; + struct iscsi_conn *conn = task->conn; + struct scsi_cmnd *sc = task->sc; + int err; - if (mtask->data_count) { - tcp_mtask->xmstate |= XMSTATE_IMM_DATA; - iscsi_buf_init_iov(&tcp_mtask->sendbuf, - (char*)mtask->data, - mtask->data_count); - } + if (!sc) { + /* + * mgmt tasks do not have a scatterlist since they come + * in from the iscsi interface. + */ + debug_scsi("mtask deq [cid %d itt 0x%x]\n", conn->id, + task->itt); - if (conn->c_stage != ISCSI_CONN_INITIAL_STAGE && - conn->stop_stage != STOP_CONN_RECOVER && - conn->hdrdgst_en) - iscsi_hdr_digest(conn, &tcp_mtask->headbuf, - (u8*)tcp_mtask->hdrext); + /* Prepare PDU, optionally w/ immediate data */ + iscsi_tcp_send_hdr_prep(conn, task->hdr, sizeof(*task->hdr)); - tcp_mtask->sent = 0; - tcp_mtask->xmstate &= ~XMSTATE_IMM_HDR_INIT; - tcp_mtask->xmstate |= XMSTATE_IMM_HDR; + /* If we have immediate data, attach a payload */ + if (task->data_count) + iscsi_tcp_send_linear_data_prepare(conn, task->data, + task->data_count); + return 0; } - if (tcp_mtask->xmstate & XMSTATE_IMM_HDR) { - rc = iscsi_sendhdr(conn, &tcp_mtask->headbuf, - mtask->data_count); - if (rc) - return rc; - tcp_mtask->xmstate &= ~XMSTATE_IMM_HDR; - } + BUG_ON(__kfifo_len(tcp_task->r2tqueue)); + tcp_task->sent = 0; + tcp_task->exp_datasn = 0; - if (tcp_mtask->xmstate & XMSTATE_IMM_DATA) { - BUG_ON(!mtask->data_count); - tcp_mtask->xmstate &= ~XMSTATE_IMM_DATA; - /* FIXME: implement. - * Virtual buffer could be spreaded across multiple pages... - */ - do { - int rc; - - rc = iscsi_sendpage(conn, &tcp_mtask->sendbuf, - &mtask->data_count, &tcp_mtask->sent); - if (rc) { - tcp_mtask->xmstate |= XMSTATE_IMM_DATA; - return rc; - } - } while (mtask->data_count); - } + /* Prepare PDU, optionally w/ immediate data */ + debug_scsi("task deq [cid %d itt 0x%x imm %d unsol %d]\n", + conn->id, task->itt, task->imm_count, + task->unsol_count); + iscsi_tcp_send_hdr_prep(conn, task->hdr, task->hdr_len); - BUG_ON(tcp_mtask->xmstate != XMSTATE_IDLE); - if (mtask->hdr->itt == RESERVED_ITT) { - struct iscsi_session *session = conn->session; + if (!task->imm_count) + return 0; - spin_lock_bh(&session->lock); - list_del(&conn->mtask->running); - __kfifo_put(session->mgmtpool.queue, (void*)&conn->mtask, - sizeof(void*)); - spin_unlock_bh(&session->lock); - } + /* If we have immediate data, attach a payload */ + err = iscsi_tcp_send_data_prep(conn, scsi_out(sc)->table.sgl, + scsi_out(sc)->table.nents, + 0, task->imm_count); + if (err) + return err; + tcp_task->sent += task->imm_count; + task->imm_count = 0; return 0; } +/* + * iscsi_tcp_task_xmit - xmit normal PDU task + * @task: iscsi command task + * + * We're expected to return 0 when everything was transmitted succesfully, + * -EAGAIN if there's still data in the queue, or != 0 for any other kind + * of error. + */ static int -iscsi_send_cmd_hdr(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) +iscsi_tcp_task_xmit(struct iscsi_task *task) { - struct scsi_cmnd *sc = ctask->sc; - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; + struct iscsi_conn *conn = task->conn; + struct iscsi_tcp_task *tcp_task = task->dd_data; + struct scsi_cmnd *sc = task->sc; + struct scsi_data_buffer *sdb; int rc = 0; - if (tcp_ctask->xmstate & XMSTATE_CMD_HDR_INIT) { - tcp_ctask->sent = 0; - tcp_ctask->sg_count = 0; - tcp_ctask->exp_datasn = 0; - - if (sc->sc_data_direction == DMA_TO_DEVICE) { - if (sc->use_sg) { - struct scatterlist *sg = sc->request_buffer; - - iscsi_buf_init_sg(&tcp_ctask->sendbuf, sg); - tcp_ctask->sg = sg + 1; - tcp_ctask->bad_sg = sg + sc->use_sg; - } else { - iscsi_buf_init_iov(&tcp_ctask->sendbuf, - sc->request_buffer, - sc->request_bufflen); - tcp_ctask->sg = NULL; - tcp_ctask->bad_sg = NULL; - } - - debug_scsi("cmd [itt 0x%x total %d imm_data %d " - "unsol count %d, unsol offset %d]\n", - ctask->itt, sc->request_bufflen, - ctask->imm_count, ctask->unsol_count, - ctask->unsol_offset); - } - - iscsi_buf_init_iov(&tcp_ctask->headbuf, (char*)ctask->hdr, - sizeof(struct iscsi_hdr)); - - if (conn->hdrdgst_en) - iscsi_hdr_digest(conn, &tcp_ctask->headbuf, - (u8*)tcp_ctask->hdrext); - tcp_ctask->xmstate &= ~XMSTATE_CMD_HDR_INIT; - tcp_ctask->xmstate |= XMSTATE_CMD_HDR_XMIT; - } - - if (tcp_ctask->xmstate & XMSTATE_CMD_HDR_XMIT) { - rc = iscsi_sendhdr(conn, &tcp_ctask->headbuf, ctask->imm_count); - if (rc) - return rc; - tcp_ctask->xmstate &= ~XMSTATE_CMD_HDR_XMIT; - - if (sc->sc_data_direction != DMA_TO_DEVICE) - return 0; - - if (ctask->imm_count) { - tcp_ctask->xmstate |= XMSTATE_IMM_DATA; - iscsi_set_padding(tcp_ctask, ctask->imm_count); - - if (ctask->conn->datadgst_en) { - iscsi_data_digest_init(ctask->conn->dd_data, - tcp_ctask); - tcp_ctask->immdigest = 0; - } - } - - if (ctask->unsol_count) - tcp_ctask->xmstate |= - XMSTATE_UNS_HDR | XMSTATE_UNS_INIT; - } - return rc; -} +flush: + /* Flush any pending data first. */ + rc = iscsi_tcp_flush(conn); + if (rc < 0) + return rc; -static int -iscsi_send_padding(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) -{ - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; - struct iscsi_tcp_conn *tcp_conn = conn->dd_data; - int sent = 0, rc; - - if (tcp_ctask->xmstate & XMSTATE_W_PAD) { - iscsi_buf_init_iov(&tcp_ctask->sendbuf, (char*)&tcp_ctask->pad, - tcp_ctask->pad_count); - if (conn->datadgst_en) - crypto_hash_update(&tcp_conn->tx_hash, - &tcp_ctask->sendbuf.sg, - tcp_ctask->sendbuf.sg.length); - } else if (!(tcp_ctask->xmstate & XMSTATE_W_RESEND_PAD)) + /* mgmt command */ + if (!sc) { + if (task->hdr->itt == RESERVED_ITT) + iscsi_put_task(task); return 0; - - tcp_ctask->xmstate &= ~XMSTATE_W_PAD; - tcp_ctask->xmstate &= ~XMSTATE_W_RESEND_PAD; - debug_scsi("sending %d pad bytes for itt 0x%x\n", - tcp_ctask->pad_count, ctask->itt); - rc = iscsi_sendpage(conn, &tcp_ctask->sendbuf, &tcp_ctask->pad_count, - &sent); - if (rc) { - debug_scsi("padding send failed %d\n", rc); - tcp_ctask->xmstate |= XMSTATE_W_RESEND_PAD; } - return rc; -} - -static int -iscsi_send_digest(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask, - struct iscsi_buf *buf, uint32_t *digest) -{ - struct iscsi_tcp_cmd_task *tcp_ctask; - struct iscsi_tcp_conn *tcp_conn; - int rc, sent = 0; - if (!conn->datadgst_en) + /* Are we done already? */ + if (sc->sc_data_direction != DMA_TO_DEVICE) return 0; - tcp_ctask = ctask->dd_data; - tcp_conn = conn->dd_data; - - if (!(tcp_ctask->xmstate & XMSTATE_W_RESEND_DATA_DIGEST)) { - crypto_hash_final(&tcp_conn->tx_hash, (u8*)digest); - iscsi_buf_init_iov(buf, (char*)digest, 4); - } - tcp_ctask->xmstate &= ~XMSTATE_W_RESEND_DATA_DIGEST; - - rc = iscsi_sendpage(conn, buf, &tcp_ctask->digest_count, &sent); - if (!rc) - debug_scsi("sent digest 0x%x for itt 0x%x\n", *digest, - ctask->itt); - else { - debug_scsi("sending digest 0x%x failed for itt 0x%x!\n", - *digest, ctask->itt); - tcp_ctask->xmstate |= XMSTATE_W_RESEND_DATA_DIGEST; - } - return rc; -} - -static int -iscsi_send_data(struct iscsi_cmd_task *ctask, struct iscsi_buf *sendbuf, - struct scatterlist **sg, int *sent, int *count, - struct iscsi_buf *digestbuf, uint32_t *digest) -{ - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; - struct iscsi_conn *conn = ctask->conn; - struct iscsi_tcp_conn *tcp_conn = conn->dd_data; - int rc, buf_sent, offset; - - while (*count) { - buf_sent = 0; - offset = sendbuf->sent; - - rc = iscsi_sendpage(conn, sendbuf, count, &buf_sent); - *sent = *sent + buf_sent; - if (buf_sent && conn->datadgst_en) - partial_sg_digest_update(&tcp_conn->tx_hash, - &sendbuf->sg, sendbuf->sg.offset + offset, - buf_sent); - if (!iscsi_buf_left(sendbuf) && *sg != tcp_ctask->bad_sg) { - iscsi_buf_init_sg(sendbuf, *sg); - *sg = *sg + 1; - } - - if (rc) - return rc; - } - - rc = iscsi_send_padding(conn, ctask); - if (rc) - return rc; - - return iscsi_send_digest(conn, ctask, digestbuf, digest); -} - -static int -iscsi_send_unsol_hdr(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) -{ - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; - struct iscsi_data_task *dtask; - int rc; - - tcp_ctask->xmstate |= XMSTATE_UNS_DATA; - if (tcp_ctask->xmstate & XMSTATE_UNS_INIT) { - dtask = &tcp_ctask->unsol_dtask; - - iscsi_prep_unsolicit_data_pdu(ctask, &dtask->hdr); - iscsi_buf_init_iov(&tcp_ctask->headbuf, (char*)&dtask->hdr, - sizeof(struct iscsi_hdr)); - if (conn->hdrdgst_en) - iscsi_hdr_digest(conn, &tcp_ctask->headbuf, - (u8*)dtask->hdrext); - - tcp_ctask->xmstate &= ~XMSTATE_UNS_INIT; - iscsi_set_padding(tcp_ctask, ctask->data_count); - } - - rc = iscsi_sendhdr(conn, &tcp_ctask->headbuf, ctask->data_count); - if (rc) { - tcp_ctask->xmstate &= ~XMSTATE_UNS_DATA; - tcp_ctask->xmstate |= XMSTATE_UNS_HDR; - return rc; - } - - if (conn->datadgst_en) { - dtask = &tcp_ctask->unsol_dtask; - iscsi_data_digest_init(ctask->conn->dd_data, tcp_ctask); - dtask->digest = 0; - } + sdb = scsi_out(sc); + if (task->unsol_count != 0) { + struct iscsi_data *hdr = &tcp_task->unsol_dtask.hdr; - debug_scsi("uns dout [itt 0x%x dlen %d sent %d]\n", - ctask->itt, ctask->unsol_count, tcp_ctask->sent); - return 0; -} + /* Prepare a header for the unsolicited PDU. + * The amount of data we want to send will be + * in task->data_count. + * FIXME: return the data count instead. + */ + iscsi_prep_unsolicit_data_pdu(task, hdr); -static int -iscsi_send_unsol_pdu(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) -{ - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; - int rc; + debug_tcp("unsol dout [itt 0x%x doff %d dlen %d]\n", + task->itt, tcp_task->sent, task->data_count); - if (tcp_ctask->xmstate & XMSTATE_UNS_HDR) { - BUG_ON(!ctask->unsol_count); - tcp_ctask->xmstate &= ~XMSTATE_UNS_HDR; -send_hdr: - rc = iscsi_send_unsol_hdr(conn, ctask); + iscsi_tcp_send_hdr_prep(conn, hdr, sizeof(*hdr)); + rc = iscsi_tcp_send_data_prep(conn, sdb->table.sgl, + sdb->table.nents, tcp_task->sent, + task->data_count); if (rc) - return rc; - } - - if (tcp_ctask->xmstate & XMSTATE_UNS_DATA) { - struct iscsi_data_task *dtask = &tcp_ctask->unsol_dtask; - int start = tcp_ctask->sent; + goto fail; + tcp_task->sent += task->data_count; + task->unsol_count -= task->data_count; + goto flush; + } else { + struct iscsi_session *session = conn->session; + struct iscsi_r2t_info *r2t; - rc = iscsi_send_data(ctask, &tcp_ctask->sendbuf, &tcp_ctask->sg, - &tcp_ctask->sent, &ctask->data_count, - &dtask->digestbuf, &dtask->digest); - ctask->unsol_count -= tcp_ctask->sent - start; - if (rc) - return rc; - tcp_ctask->xmstate &= ~XMSTATE_UNS_DATA; - /* - * Done with the Data-Out. Next, check if we need - * to send another unsolicited Data-Out. + /* All unsolicited PDUs sent. Check for solicited PDUs. */ - if (ctask->unsol_count) { - debug_scsi("sending more uns\n"); - tcp_ctask->xmstate |= XMSTATE_UNS_INIT; - goto send_hdr; + spin_lock_bh(&session->lock); + r2t = tcp_task->r2t; + if (r2t != NULL) { + /* Continue with this R2T? */ + if (!iscsi_solicit_data_cont(conn, task, r2t)) { + debug_scsi(" done with r2t %p\n", r2t); + + __kfifo_put(tcp_task->r2tpool.queue, + (void*)&r2t, sizeof(void*)); + tcp_task->r2t = r2t = NULL; + } } - } - return 0; -} - -static int iscsi_send_sol_pdu(struct iscsi_conn *conn, - struct iscsi_cmd_task *ctask) -{ - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; - struct iscsi_session *session = conn->session; - struct iscsi_r2t_info *r2t; - struct iscsi_data_task *dtask; - int left, rc; - if (tcp_ctask->xmstate & XMSTATE_SOL_HDR_INIT) { - if (!tcp_ctask->r2t) { - spin_lock_bh(&session->lock); - __kfifo_get(tcp_ctask->r2tqueue, (void*)&tcp_ctask->r2t, + if (r2t == NULL) { + __kfifo_get(tcp_task->r2tqueue, (void*)&tcp_task->r2t, sizeof(void*)); - spin_unlock_bh(&session->lock); + r2t = tcp_task->r2t; } -send_hdr: - r2t = tcp_ctask->r2t; - dtask = &r2t->dtask; - - if (conn->hdrdgst_en) - iscsi_hdr_digest(conn, &r2t->headbuf, - (u8*)dtask->hdrext); - tcp_ctask->xmstate &= ~XMSTATE_SOL_HDR_INIT; - tcp_ctask->xmstate |= XMSTATE_SOL_HDR; - } - - if (tcp_ctask->xmstate & XMSTATE_SOL_HDR) { - r2t = tcp_ctask->r2t; - dtask = &r2t->dtask; - - rc = iscsi_sendhdr(conn, &r2t->headbuf, r2t->data_count); - if (rc) - return rc; - tcp_ctask->xmstate &= ~XMSTATE_SOL_HDR; - tcp_ctask->xmstate |= XMSTATE_SOL_DATA; + spin_unlock_bh(&session->lock); - if (conn->datadgst_en) { - iscsi_data_digest_init(conn->dd_data, tcp_ctask); - dtask->digest = 0; + /* Waiting for more R2Ts to arrive. */ + if (r2t == NULL) { + debug_tcp("no R2Ts yet\n"); + return 0; } - iscsi_set_padding(tcp_ctask, r2t->data_count); - debug_scsi("sol dout [dsn %d itt 0x%x dlen %d sent %d]\n", - r2t->solicit_datasn - 1, ctask->itt, r2t->data_count, - r2t->sent); - } + debug_scsi("sol dout %p [dsn %d itt 0x%x doff %d dlen %d]\n", + r2t, r2t->solicit_datasn - 1, task->itt, + r2t->data_offset + r2t->sent, r2t->data_count); - if (tcp_ctask->xmstate & XMSTATE_SOL_DATA) { - r2t = tcp_ctask->r2t; - dtask = &r2t->dtask; + iscsi_tcp_send_hdr_prep(conn, &r2t->dtask.hdr, + sizeof(struct iscsi_hdr)); - rc = iscsi_send_data(ctask, &r2t->sendbuf, &r2t->sg, - &r2t->sent, &r2t->data_count, - &dtask->digestbuf, &dtask->digest); + rc = iscsi_tcp_send_data_prep(conn, sdb->table.sgl, + sdb->table.nents, + r2t->data_offset + r2t->sent, + r2t->data_count); if (rc) - return rc; - tcp_ctask->xmstate &= ~XMSTATE_SOL_DATA; - - /* - * Done with this Data-Out. Next, check if we have - * to send another Data-Out for this R2T. - */ - BUG_ON(r2t->data_length - r2t->sent < 0); - left = r2t->data_length - r2t->sent; - if (left) { - iscsi_solicit_data_cont(conn, ctask, r2t, left); - goto send_hdr; - } - - /* - * Done with this R2T. Check if there are more - * outstanding R2Ts ready to be processed. - */ - spin_lock_bh(&session->lock); - tcp_ctask->r2t = NULL; - __kfifo_put(tcp_ctask->r2tpool.queue, (void*)&r2t, - sizeof(void*)); - if (__kfifo_get(tcp_ctask->r2tqueue, (void*)&r2t, - sizeof(void*))) { - tcp_ctask->r2t = r2t; - spin_unlock_bh(&session->lock); - goto send_hdr; - } - spin_unlock_bh(&session->lock); + goto fail; + tcp_task->sent += r2t->data_count; + r2t->sent += r2t->data_count; + goto flush; } return 0; -} - -/** - * iscsi_tcp_ctask_xmit - xmit normal PDU task - * @conn: iscsi connection - * @ctask: iscsi command task - * - * Notes: - * The function can return -EAGAIN in which case caller must - * call it again later, or recover. '0' return code means successful - * xmit. - * The function is devided to logical helpers (above) for the different - * xmit stages. - * - *iscsi_send_cmd_hdr() - * XMSTATE_CMD_HDR_INIT - prepare Header and Data buffers Calculate - * Header Digest - * XMSTATE_CMD_HDR_XMIT - Transmit header in progress - * - *iscsi_send_padding - * XMSTATE_W_PAD - Prepare and send pading - * XMSTATE_W_RESEND_PAD - retry send pading - * - *iscsi_send_digest - * XMSTATE_W_RESEND_DATA_DIGEST - Finalize and send Data Digest - * XMSTATE_W_RESEND_DATA_DIGEST - retry sending digest - * - *iscsi_send_unsol_hdr - * XMSTATE_UNS_INIT - prepare un-solicit data header and digest - * XMSTATE_UNS_HDR - send un-solicit header - * - *iscsi_send_unsol_pdu - * XMSTATE_UNS_DATA - send un-solicit data in progress - * - *iscsi_send_sol_pdu - * XMSTATE_SOL_HDR_INIT - solicit data header and digest initialize - * XMSTATE_SOL_HDR - send solicit header - * XMSTATE_SOL_DATA - send solicit data - * - *iscsi_tcp_ctask_xmit - * XMSTATE_IMM_DATA - xmit managment data (??) - **/ -static int -iscsi_tcp_ctask_xmit(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) -{ - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; - int rc = 0; - - debug_scsi("ctask deq [cid %d xmstate %x itt 0x%x]\n", - conn->id, tcp_ctask->xmstate, ctask->itt); - - rc = iscsi_send_cmd_hdr(conn, ctask); - if (rc) - return rc; - if (ctask->sc->sc_data_direction != DMA_TO_DEVICE) - return 0; - - if (tcp_ctask->xmstate & XMSTATE_IMM_DATA) { - rc = iscsi_send_data(ctask, &tcp_ctask->sendbuf, &tcp_ctask->sg, - &tcp_ctask->sent, &ctask->imm_count, - &tcp_ctask->immbuf, &tcp_ctask->immdigest); - if (rc) - return rc; - tcp_ctask->xmstate &= ~XMSTATE_IMM_DATA; - } - - rc = iscsi_send_unsol_pdu(conn, ctask); - if (rc) - return rc; - - rc = iscsi_send_sol_pdu(conn, ctask); - if (rc) - return rc; - - return rc; +fail: + iscsi_conn_failure(conn, rc); + return -EIO; } static struct iscsi_cls_conn * @@ -1789,7 +1498,7 @@ iscsi_tcp_conn_create(struct iscsi_cls_session *cls_session, uint32_t conn_idx) struct iscsi_cls_conn *cls_conn; struct iscsi_tcp_conn *tcp_conn; - cls_conn = iscsi_conn_setup(cls_session, conn_idx); + cls_conn = iscsi_conn_setup(cls_session, sizeof(*tcp_conn), conn_idx); if (!cls_conn) return NULL; conn = cls_conn->dd_data; @@ -1799,45 +1508,31 @@ iscsi_tcp_conn_create(struct iscsi_cls_session *cls_session, uint32_t conn_idx) */ conn->max_recv_dlength = ISCSI_DEF_MAX_RECV_SEG_LEN; - tcp_conn = kzalloc(sizeof(*tcp_conn), GFP_KERNEL); - if (!tcp_conn) - goto tcp_conn_alloc_fail; - - conn->dd_data = tcp_conn; + tcp_conn = conn->dd_data; tcp_conn->iscsi_conn = conn; - tcp_conn->in_progress = IN_PROGRESS_WAIT_HEADER; - /* initial operational parameters */ - tcp_conn->hdr_size = sizeof(struct iscsi_hdr); tcp_conn->tx_hash.tfm = crypto_alloc_hash("crc32c", 0, CRYPTO_ALG_ASYNC); tcp_conn->tx_hash.flags = 0; - if (IS_ERR(tcp_conn->tx_hash.tfm)) { - printk(KERN_ERR "Could not create connection due to crc32c " - "loading error %ld. Make sure the crc32c module is " - "built as a module or into the kernel\n", - PTR_ERR(tcp_conn->tx_hash.tfm)); - goto free_tcp_conn; - } + if (IS_ERR(tcp_conn->tx_hash.tfm)) + goto free_conn; tcp_conn->rx_hash.tfm = crypto_alloc_hash("crc32c", 0, CRYPTO_ALG_ASYNC); tcp_conn->rx_hash.flags = 0; - if (IS_ERR(tcp_conn->rx_hash.tfm)) { - printk(KERN_ERR "Could not create connection due to crc32c " - "loading error %ld. Make sure the crc32c module is " - "built as a module or into the kernel\n", - PTR_ERR(tcp_conn->rx_hash.tfm)); + if (IS_ERR(tcp_conn->rx_hash.tfm)) goto free_tx_tfm; - } return cls_conn; free_tx_tfm: crypto_free_hash(tcp_conn->tx_hash.tfm); -free_tcp_conn: - kfree(tcp_conn); -tcp_conn_alloc_fail: +free_conn: + iscsi_conn_printk(KERN_ERR, conn, + "Could not create connection due to crc32c " + "loading error. Make sure the crc32c " + "module is built as a module or into the " + "kernel\n"); iscsi_conn_teardown(cls_conn); return NULL; } @@ -1845,18 +1540,21 @@ tcp_conn_alloc_fail: static void iscsi_tcp_release_conn(struct iscsi_conn *conn) { + struct iscsi_session *session = conn->session; struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct socket *sock = tcp_conn->sock; - if (!tcp_conn->sock) + if (!sock) return; - sock_hold(tcp_conn->sock->sk); + sock_hold(sock->sk); iscsi_conn_restore_callbacks(tcp_conn); - sock_put(tcp_conn->sock->sk); + sock_put(sock->sk); - sock_release(tcp_conn->sock); + spin_lock_bh(&session->lock); tcp_conn->sock = NULL; - conn->recv_lock = NULL; + spin_unlock_bh(&session->lock); + sockfd_put(sock); } static void @@ -1866,14 +1564,13 @@ iscsi_tcp_conn_destroy(struct iscsi_cls_conn *cls_conn) struct iscsi_tcp_conn *tcp_conn = conn->dd_data; iscsi_tcp_release_conn(conn); - iscsi_conn_teardown(cls_conn); if (tcp_conn->tx_hash.tfm) crypto_free_hash(tcp_conn->tx_hash.tfm); if (tcp_conn->rx_hash.tfm) crypto_free_hash(tcp_conn->rx_hash.tfm); - kfree(tcp_conn); + iscsi_conn_teardown(cls_conn); } static void @@ -1882,9 +1579,60 @@ iscsi_tcp_conn_stop(struct iscsi_cls_conn *cls_conn, int flag) struct iscsi_conn *conn = cls_conn->dd_data; struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + /* userspace may have goofed up and not bound us */ + if (!tcp_conn->sock) + return; + /* + * Make sure our recv side is stopped. + * Older tools called conn stop before ep_disconnect + * so IO could still be coming in. + */ + write_lock_bh(&tcp_conn->sock->sk->sk_callback_lock); + set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); + write_unlock_bh(&tcp_conn->sock->sk->sk_callback_lock); + iscsi_conn_stop(cls_conn, flag); iscsi_tcp_release_conn(conn); - tcp_conn->hdr_size = sizeof(struct iscsi_hdr); +} + +static int iscsi_tcp_get_addr(struct iscsi_conn *conn, struct socket *sock, + char *buf, int *port, + int (*getname)(struct socket *, struct sockaddr *, + int *addrlen)) +{ + struct sockaddr_storage *addr; + struct sockaddr_in6 *sin6; + struct sockaddr_in *sin; + int rc = 0, len; + + addr = kmalloc(sizeof(*addr), GFP_KERNEL); + if (!addr) + return -ENOMEM; + + if (getname(sock, (struct sockaddr *) addr, &len)) { + rc = -ENODEV; + goto free_addr; + } + + switch (addr->ss_family) { + case AF_INET: + sin = (struct sockaddr_in *)addr; + spin_lock_bh(&conn->session->lock); + sprintf(buf, NIPQUAD_FMT, NIPQUAD(sin->sin_addr.s_addr)); + *port = be16_to_cpu(sin->sin_port); + spin_unlock_bh(&conn->session->lock); + break; + case AF_INET6: + sin6 = (struct sockaddr_in6 *)addr; + spin_lock_bh(&conn->session->lock); + sprintf(buf, NIP6_FMT, NIP6(sin6->sin6_addr)); + *port = be16_to_cpu(sin6->sin6_port); + spin_unlock_bh(&conn->session->lock); + break; + } +free_addr: + kfree(addr); + return rc; } static int @@ -1892,6 +1640,8 @@ iscsi_tcp_conn_bind(struct iscsi_cls_session *cls_session, struct iscsi_cls_conn *cls_conn, uint64_t transport_eph, int is_leading) { + struct Scsi_Host *shost = iscsi_session_to_shost(cls_session); + struct iscsi_host *ihost = shost_priv(shost); struct iscsi_conn *conn = cls_conn->dd_data; struct iscsi_tcp_conn *tcp_conn = conn->dd_data; struct sock *sk; @@ -1901,13 +1651,28 @@ iscsi_tcp_conn_bind(struct iscsi_cls_session *cls_session, /* lookup for existing socket */ sock = sockfd_lookup((int)transport_eph, &err); if (!sock) { - printk(KERN_ERR "iscsi_tcp: sockfd_lookup failed %d\n", err); + iscsi_conn_printk(KERN_ERR, conn, + "sockfd_lookup failed %d\n", err); return -EEXIST; } + /* + * copy these values now because if we drop the session + * userspace may still want to query the values since we will + * be using them for the reconnect + */ + err = iscsi_tcp_get_addr(conn, sock, conn->portal_address, + &conn->portal_port, kernel_getpeername); + if (err) + goto free_socket; + + err = iscsi_tcp_get_addr(conn, sock, ihost->local_address, + &ihost->local_port, kernel_getsockname); + if (err) + goto free_socket; err = iscsi_conn_bind(cls_session, cls_conn, is_leading); if (err) - return err; + goto free_socket; /* bind iSCSI connection and socket */ tcp_conn->sock = sock; @@ -1918,29 +1683,17 @@ iscsi_tcp_conn_bind(struct iscsi_cls_session *cls_session, sk->sk_sndtimeo = 15 * HZ; /* FIXME: make it configurable */ sk->sk_allocation = GFP_ATOMIC; - /* FIXME: disable Nagle's algorithm */ - - /* - * Intercept TCP callbacks for sendfile like receive - * processing. - */ - conn->recv_lock = &sk->sk_callback_lock; iscsi_conn_set_callbacks(conn); tcp_conn->sendpage = tcp_conn->sock->ops->sendpage; /* * set receive state machine into initial state */ - tcp_conn->in_progress = IN_PROGRESS_WAIT_HEADER; - + iscsi_tcp_hdr_recv_prep(tcp_conn); return 0; -} -/* called with host lock */ -static void -iscsi_tcp_mgmt_init(struct iscsi_conn *conn, struct iscsi_mgmt_task *mtask) -{ - struct iscsi_tcp_mgmt_task *tcp_mtask = mtask->dd_data; - tcp_mtask->xmstate = XMSTATE_IMM_HDR_INIT; +free_socket: + sockfd_put(sock); + return err; } static int @@ -1953,8 +1706,8 @@ iscsi_r2tpool_alloc(struct iscsi_session *session) * initialize per-task: R2T pool and xmit queue */ for (cmd_i = 0; cmd_i < session->cmds_max; cmd_i++) { - struct iscsi_cmd_task *ctask = session->cmds[cmd_i]; - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; + struct iscsi_task *task = session->cmds[cmd_i]; + struct iscsi_tcp_task *tcp_task = task->dd_data; /* * pre-allocated x4 as much r2ts to handle race when @@ -1963,18 +1716,16 @@ iscsi_r2tpool_alloc(struct iscsi_session *session) */ /* R2T pool */ - if (iscsi_pool_init(&tcp_ctask->r2tpool, session->max_r2t * 4, - (void***)&tcp_ctask->r2ts, + if (iscsi_pool_init(&tcp_task->r2tpool, session->max_r2t * 4, NULL, sizeof(struct iscsi_r2t_info))) { goto r2t_alloc_fail; } /* R2T xmit queue */ - tcp_ctask->r2tqueue = kfifo_alloc( + tcp_task->r2tqueue = kfifo_alloc( session->max_r2t * 4 * sizeof(void*), GFP_KERNEL, NULL); - if (tcp_ctask->r2tqueue == ERR_PTR(-ENOMEM)) { - iscsi_pool_free(&tcp_ctask->r2tpool, - (void**)tcp_ctask->r2ts); + if (tcp_task->r2tqueue == ERR_PTR(-ENOMEM)) { + iscsi_pool_free(&tcp_task->r2tpool); goto r2t_alloc_fail; } } @@ -1983,12 +1734,11 @@ iscsi_r2tpool_alloc(struct iscsi_session *session) r2t_alloc_fail: for (i = 0; i < cmd_i; i++) { - struct iscsi_cmd_task *ctask = session->cmds[i]; - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; + struct iscsi_task *task = session->cmds[i]; + struct iscsi_tcp_task *tcp_task = task->dd_data; - kfifo_free(tcp_ctask->r2tqueue); - iscsi_pool_free(&tcp_ctask->r2tpool, - (void**)tcp_ctask->r2ts); + kfifo_free(tcp_task->r2tqueue); + iscsi_pool_free(&tcp_task->r2tpool); } return -ENOMEM; } @@ -1999,12 +1749,11 @@ iscsi_r2tpool_free(struct iscsi_session *session) int i; for (i = 0; i < session->cmds_max; i++) { - struct iscsi_cmd_task *ctask = session->cmds[i]; - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; + struct iscsi_task *task = session->cmds[i]; + struct iscsi_tcp_task *tcp_task = task->dd_data; - kfifo_free(tcp_ctask->r2tqueue); - iscsi_pool_free(&tcp_ctask->r2tpool, - (void**)tcp_ctask->r2ts); + kfifo_free(tcp_task->r2tqueue); + iscsi_pool_free(&tcp_task->r2tpool); } } @@ -2020,9 +1769,6 @@ iscsi_conn_set_param(struct iscsi_cls_conn *cls_conn, enum iscsi_param param, switch(param) { case ISCSI_PARAM_HDRDGST_EN: iscsi_set_param(cls_conn, param, buf, buflen); - tcp_conn->hdr_size = sizeof(struct iscsi_hdr); - if (conn->hdrdgst_en) - tcp_conn->hdr_size += sizeof(__u32); break; case ISCSI_PARAM_DATADGST_EN: iscsi_set_param(cls_conn, param, buf, buflen); @@ -2031,12 +1777,12 @@ iscsi_conn_set_param(struct iscsi_cls_conn *cls_conn, enum iscsi_param param, break; case ISCSI_PARAM_MAX_R2T: sscanf(buf, "%d", &value); - if (session->max_r2t == roundup_pow_of_two(value)) + if (value <= 0 || !is_power_of_2(value)) + return -EINVAL; + if (session->max_r2t == value) break; iscsi_r2tpool_free(session); iscsi_set_param(cls_conn, param, buf, buflen); - if (session->max_r2t & (session->max_r2t - 1)) - session->max_r2t = roundup_pow_of_two(session->max_r2t); if (iscsi_r2tpool_alloc(session)) return -ENOMEM; break; @@ -2052,33 +1798,18 @@ iscsi_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn, enum iscsi_param param, char *buf) { struct iscsi_conn *conn = cls_conn->dd_data; - struct iscsi_tcp_conn *tcp_conn = conn->dd_data; - struct inet_sock *inet; - struct ipv6_pinfo *np; - struct sock *sk; int len; switch(param) { case ISCSI_PARAM_CONN_PORT: - if (!tcp_conn->sock) - return -EINVAL; - - inet = inet_sk(tcp_conn->sock->sk); - len = sprintf(buf, "%hu\n", be16_to_cpu(inet->dport)); + 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: - if (!tcp_conn->sock) - return -EINVAL; - - sk = tcp_conn->sock->sk; - if (sk->sk_family == PF_INET) { - inet = inet_sk(sk); - len = sprintf(buf, NIPQUAD_FMT "\n", - NIPQUAD(inet->daddr)); - } else { - np = inet6_sk(sk); - len = sprintf(buf, NIP6_FMT "\n", NIP6(np->daddr)); - } + 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); @@ -2112,65 +1843,93 @@ iscsi_conn_get_stats(struct iscsi_cls_conn *cls_conn, struct iscsi_stats *stats) } static struct iscsi_cls_session * -iscsi_tcp_session_create(struct iscsi_transport *iscsit, - struct scsi_transport_template *scsit, - uint32_t initial_cmdsn, uint32_t *hostno) +iscsi_tcp_session_create(struct iscsi_endpoint *ep, uint16_t cmds_max, + uint16_t qdepth, uint32_t initial_cmdsn, + uint32_t *hostno) { struct iscsi_cls_session *cls_session; struct iscsi_session *session; - uint32_t hn; + struct Scsi_Host *shost; int cmd_i; - cls_session = iscsi_session_setup(iscsit, scsit, - sizeof(struct iscsi_tcp_cmd_task), - sizeof(struct iscsi_tcp_mgmt_task), - initial_cmdsn, &hn); - if (!cls_session) + if (ep) { + printk(KERN_ERR "iscsi_tcp: invalid ep %p.\n", ep); return NULL; - *hostno = hn; - - session = class_to_transport_session(cls_session); - for (cmd_i = 0; cmd_i < session->cmds_max; cmd_i++) { - struct iscsi_cmd_task *ctask = session->cmds[cmd_i]; - struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; - - ctask->hdr = &tcp_ctask->hdr; } - for (cmd_i = 0; cmd_i < session->mgmtpool_max; cmd_i++) { - struct iscsi_mgmt_task *mtask = session->mgmt_cmds[cmd_i]; - struct iscsi_tcp_mgmt_task *tcp_mtask = mtask->dd_data; + shost = iscsi_host_alloc(&iscsi_sht, 0, qdepth); + if (!shost) + return NULL; + shost->transportt = iscsi_tcp_scsi_transport; + shost->max_lun = iscsi_max_lun; + shost->max_id = 0; + shost->max_channel = 0; + shost->max_cmd_len = SCSI_MAX_VARLEN_CDB_SIZE; + + if (iscsi_host_add(shost, NULL)) + goto free_host; + *hostno = shost->host_no; + + cls_session = iscsi_session_setup(&iscsi_tcp_transport, shost, cmds_max, + sizeof(struct iscsi_tcp_task), + initial_cmdsn, 0); + if (!cls_session) + goto remove_host; + session = cls_session->dd_data; - mtask->hdr = &tcp_mtask->hdr; - } + shost->can_queue = session->scsi_cmds_max; + for (cmd_i = 0; cmd_i < session->cmds_max; cmd_i++) { + struct iscsi_task *task = session->cmds[cmd_i]; + struct iscsi_tcp_task *tcp_task = task->dd_data; - if (iscsi_r2tpool_alloc(class_to_transport_session(cls_session))) - goto r2tpool_alloc_fail; + task->hdr = &tcp_task->hdr.cmd_hdr; + task->hdr_max = sizeof(tcp_task->hdr) - ISCSI_DIGEST_SIZE; + } + if (iscsi_r2tpool_alloc(session)) + goto remove_session; return cls_session; -r2tpool_alloc_fail: +remove_session: iscsi_session_teardown(cls_session); +remove_host: + iscsi_host_remove(shost); +free_host: + iscsi_host_free(shost); return NULL; } static void iscsi_tcp_session_destroy(struct iscsi_cls_session *cls_session) { - iscsi_r2tpool_free(class_to_transport_session(cls_session)); - iscsi_session_teardown(cls_session); + struct Scsi_Host *shost = iscsi_session_to_shost(cls_session); + + iscsi_r2tpool_free(cls_session->dd_data); + + iscsi_host_remove(shost); + iscsi_host_free(shost); +} + +static int iscsi_tcp_slave_configure(struct scsi_device *sdev) +{ + blk_queue_bounce_limit(sdev->request_queue, BLK_BOUNCE_ANY); + blk_queue_dma_alignment(sdev->request_queue, 0); + return 0; } static struct scsi_host_template iscsi_sht = { + .module = THIS_MODULE, .name = "iSCSI Initiator over TCP/IP", .queuecommand = iscsi_queuecommand, .change_queue_depth = iscsi_change_queue_depth, - .can_queue = ISCSI_XMIT_CMDS_MAX - 1, - .sg_tablesize = ISCSI_SG_TABLESIZE, + .can_queue = ISCSI_DEF_XMIT_CMDS_MAX - 1, + .sg_tablesize = 4096, .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_host_reset_handler = iscsi_eh_host_reset, .use_clustering = DISABLE_CLUSTERING, + .slave_configure = iscsi_tcp_slave_configure, .proc_name = "iscsi_tcp", .this_id = -1, }; @@ -2199,13 +1958,14 @@ static struct iscsi_transport iscsi_tcp_transport = { ISCSI_PERSISTENT_ADDRESS | ISCSI_TARGET_NAME | ISCSI_TPGT | ISCSI_USERNAME | ISCSI_PASSWORD | - ISCSI_USERNAME_IN | ISCSI_PASSWORD_IN, - .host_param_mask = ISCSI_HOST_HWADDRESS | - ISCSI_HOST_INITIATOR_NAME, - .host_template = &iscsi_sht, - .conndata_size = sizeof(struct iscsi_conn), - .max_conn = 1, - .max_cmd_len = ISCSI_TCP_MAX_CMD_LEN, + 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, /* session management */ .create_session = iscsi_tcp_session_create, .destroy_session = iscsi_tcp_session_destroy, @@ -2224,11 +1984,9 @@ static struct iscsi_transport iscsi_tcp_transport = { /* IO */ .send_pdu = iscsi_conn_send_pdu, .get_stats = iscsi_conn_get_stats, - .init_cmd_task = iscsi_tcp_cmd_init, - .init_mgmt_task = iscsi_tcp_mgmt_init, - .xmit_cmd_task = iscsi_tcp_ctask_xmit, - .xmit_mgmt_task = iscsi_tcp_mtask_xmit, - .cleanup_cmd_task = iscsi_tcp_cleanup_ctask, + .init_task = iscsi_tcp_task_init, + .xmit_task = iscsi_tcp_task_xmit, + .cleanup_task = iscsi_tcp_cleanup_task, /* recovery */ .session_recovery_timedout = iscsi_session_recovery_timedout, }; @@ -2241,9 +1999,10 @@ iscsi_tcp_init(void) iscsi_max_lun); return -EINVAL; } - iscsi_tcp_transport.max_lun = iscsi_max_lun; - if (!iscsi_register_transport(&iscsi_tcp_transport)) + iscsi_tcp_scsi_transport = iscsi_register_transport( + &iscsi_tcp_transport); + if (!iscsi_tcp_scsi_transport) return -ENODEV; return 0;