diff options
-rw-r--r-- | include/iscsi_if.h | 3 | ||||
-rw-r--r-- | include/iscsi_proto.h | 12 | ||||
-rw-r--r-- | kernel/Makefile | 4 | ||||
-rw-r--r-- | kernel/iscsi_tcp.c | 2087 | ||||
-rw-r--r-- | kernel/iscsi_tcp.h | 131 | ||||
-rw-r--r-- | kernel/libiscsi.c | 188 | ||||
-rw-r--r-- | kernel/libiscsi.h | 47 | ||||
-rw-r--r-- | kernel/scsi_transport_iscsi.c | 8 | ||||
-rw-r--r-- | kernel/scsi_transport_iscsi.h | 2 |
9 files changed, 1104 insertions, 1378 deletions
diff --git a/include/iscsi_if.h b/include/iscsi_if.h index dff4f29..7ad582e 100644 --- a/include/iscsi_if.h +++ b/include/iscsi_if.h @@ -21,7 +21,7 @@ #ifndef ISCSI_IF_H #define ISCSI_IF_H -#include <iscsi_proto.h> +#include "iscsi_proto.h" #define UEVENT_BASE 10 #define KEVENT_BASE 100 @@ -331,6 +331,7 @@ enum iscsi_host_param { * These flags describes reason of stop_conn() call */ #define STOP_CONN_TERM 0x1 +#define STOP_CONN_SUSPEND 0x2 #define STOP_CONN_RECOVER 0x3 #define ISCSI_STATS_CUSTOM_MAX 32 diff --git a/include/iscsi_proto.h b/include/iscsi_proto.h index e821932..6256e37 100644 --- a/include/iscsi_proto.h +++ b/include/iscsi_proto.h @@ -21,13 +21,15 @@ #ifndef ISCSI_PROTO_H #define ISCSI_PROTO_H +#include <linux/types.h> + #define ISCSI_DRAFT20_VERSION 0x00 /* default iSCSI listen port for incoming connections */ #define ISCSI_LISTEN_PORT 3260 /* Padding word length */ -#define PAD_WORD_LEN 4 +#define ISCSI_PAD_LEN 4 /* * useful common(control and data pathes) macro @@ -162,6 +164,14 @@ struct iscsi_rlength_ahdr { __be32 read_length; }; +/* Extended CDB AHS */ +struct iscsi_ecdb_ahdr { + __be16 ahslength; /* CDB length - 15, including reserved byte */ + uint8_t ahstype; + uint8_t reserved; + uint8_t ecdb[260 - 16]; /* 4-byte aligned extended CDB spillover */ +}; + /* SCSI Response Header */ struct iscsi_cmd_rsp { uint8_t opcode; diff --git a/kernel/Makefile b/kernel/Makefile index 6b768f0..5c22de5 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -80,9 +80,9 @@ linux_2_6_20: has_20to21_patch linux_2_6_21: has_20to21_patch -linux_2_6_22: $(unpatch_code) +linux_2_6_22: has_20to21_patch -linux_2_6_23: $(unpatch_code) +linux_2_6_23: has_20to21_patch do_unpatch_code: echo "Un-patching source code for use with linux-2.6.14 and up ..." diff --git a/kernel/iscsi_tcp.c b/kernel/iscsi_tcp.c index a51c564..bfd8ffe 100644 --- a/kernel/iscsi_tcp.c +++ b/kernel/iscsi_tcp.c @@ -48,7 +48,7 @@ MODULE_AUTHOR("Dmitry Yusupov <dmitry_yus@yahoo.com>, " "Alex Aizman <itn780@yahoo.com>"); MODULE_DESCRIPTION("iSCSI/TCP data-path"); MODULE_LICENSE("GPL"); -/* #define DEBUG_TCP */ +#undef DEBUG_TCP #define DEBUG_ASSERT #ifdef DEBUG_TCP @@ -67,118 +67,431 @@ MODULE_LICENSE("GPL"); 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); + +/* + * This code is converted to use sg chaining, but scsi misc does + * not yet have it or jen's tree may not have the currrent iscsi + * driver and linus may have one or the other. When everyone is in + * sync then remove this function, rename callers to sg_next and just + * use scatterlist.h's definition. + */ +static inline struct scatterlist *iscsi_sg_next(struct scatterlist *sg) +{ + if (!sg) { + BUG(); + return NULL; + } + return sg + 1; +} + +/* + * 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) >= 1 && !recv) + return; + + segment->sg_mapped = kmap_atomic(sg->page, 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; - - rc = ibuf->sg.length - ibuf->sent; - BUG_ON(rc < 0); - return rc; + if (segment->sg_mapped) { + 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; + static unsigned char padbuf[ISCSI_PAD_LEN]; + struct scatterlist sg; + unsigned int pad; + + debug_tcp("copied %u %u size %u %s\n", segment->copied, copied, + segment->size, recv ? "recv" : "xmit"); + if (segment->hash && copied) { + if (!segment->data) { + sg = *(segment->sg); + sg.length = copied; + sg.offset = 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; + } - tcp_conn->in.zero_copy_hdr = 0; + segment->total_copied += segment->copied; + segment->copied = 0; + segment->size = 0; - if (tcp_conn->in.copy >= tcp_conn->hdr_size && - tcp_conn->in_progress == IN_PROGRESS_WAIT_HEADER) { - /* - * Zero-copy PDU Header: using connection context - * to store header pointer. - */ - 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; + /* 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, iscsi_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, 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; +} + +/** + * 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; + + while (!iscsi_tcp_segment_done(segment, 1, copy)) { + if (copied == len) + goto out; + + copy = min(len - copied, segment->size - segment->copied); + memcpy(segment->data + segment->copied, ptr + copied, copy); + copied += copy; + } + +out: + 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; + } - if (tcp_conn->in_progress == IN_PROGRESS_WAIT_HEADER) - tcp_conn->in.hdr_offset = 0; + return 1; +} - hdr_remains = tcp_conn->hdr_size - tcp_conn->in.hdr_offset; - BUG_ON(hdr_remains <= 0); +/* + * 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; - 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); + if (hash) { + segment->hash = hash; + crypto_hash_init(hash); + } +} - 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); +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, unsigned int sg_count, + unsigned int offset, size_t size, + iscsi_segment_done_fn_t *done, struct hash_desc *hash) +{ + unsigned int i; + + debug_scsi("iscsi_segment_seek_sg offset %u size %llu\n", + offset, size); + __iscsi_segment_init(segment, size, done, hash); + for (i = 0; i < sg_count; i++, sg = iscsi_sg_next(sg)) { + 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 */ @@ -187,7 +500,6 @@ iscsi_tcp_cleanup_ctask(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) { struct iscsi_tcp_cmd_task *tcp_ctask = ctask->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*))) { @@ -196,12 +508,12 @@ iscsi_tcp_cleanup_ctask(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) debug_scsi("iscsi_tcp_cleanup_ctask pending r2t dropped\n"); } - sc = ctask->sc; - if (unlikely(!sc)) - return; - - tcp_ctask->xmstate = XMSTATE_IDLE; - tcp_ctask->r2t = NULL; + r2t = tcp_ctask->r2t; + if (r2t != NULL) { + __kfifo_put(tcp_ctask->r2tpool.queue, (void*)&r2t, + sizeof(void*)); + tcp_ctask->r2t = NULL; + } } /** @@ -220,11 +532,6 @@ iscsi_data_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) int datasn = be32_to_cpu(rhdr->datasn); 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; @@ -237,30 +544,28 @@ iscsi_data_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) tcp_ctask->exp_datasn++; tcp_ctask->data_offset = be32_to_cpu(rhdr->offset); - if (tcp_ctask->data_offset + tcp_conn->in.datalen > sc->request_bufflen) { + if (tcp_ctask->data_offset + tcp_conn->in.datalen > scsi_bufflen(sc)) { 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); + tcp_conn->in.datalen, scsi_bufflen(sc)); 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 <= scsi_bufflen(sc))) + scsi_set_resid(sc, 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++; @@ -284,7 +589,6 @@ iscsi_solicit_data_init(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask, 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)); @@ -308,43 +612,6 @@ 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; - } } /** @@ -403,11 +670,11 @@ 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) { + if (r2t->data_offset + r2t->data_length > scsi_bufflen(ctask->sc)) { 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); + r2t->data_offset, scsi_bufflen(ctask->sc)); return ISCSI_ERR_DATALEN; } @@ -418,7 +685,6 @@ iscsi_r2t_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) tcp_ctask->exp_datasn = r2tsn + 1; __kfifo_put(tcp_ctask->r2tqueue, (void*)&r2t, sizeof(void*)); - tcp_ctask->xmstate |= XMSTATE_SOL_HDR_INIT; conn->r2t_pdus_cnt++; iscsi_requeue_ctask(ctask); @@ -427,16 +693,49 @@ iscsi_r2t_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) return 0; } +/* + * Handle incoming reply to DataIn command + */ +static int +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_recv(struct iscsi_conn *conn) +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_cmd_task *ctask; + uint32_t itt; /* verify PDU length */ tcp_conn->in.datalen = ntoh24(hdr->dlength); @@ -445,77 +744,72 @@ iscsi_tcp_hdr_recv(struct iscsi_conn *conn) 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) { + /* XXX: what does this do? */ tcp_conn->in.datalen = 0; /* force drop */ return 0; } else 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); + ctask = session->cmds[itt]; + rc = iscsi_data_rsp(conn, ctask); if (rc) return rc; + if (tcp_conn->in.datalen) { + struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; + struct hash_desc *rx_hash = NULL; + + /* + * 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_ctask->data_offset, + tcp_conn->in.datalen); + return iscsi_segment_seek_sg(&tcp_conn->in.segment, + scsi_sglist(ctask->sc), + scsi_sg_count(ctask->sc), + tcp_ctask->data_offset, + tcp_conn->in.datalen, + iscsi_tcp_process_data_in, + rx_hash); + } /* 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(&session->lock); - rc = __iscsi_complete_pdu(conn, hdr, NULL, 0); - spin_unlock(&session->lock); + 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]; + ctask = session->cmds[itt]; 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 (ctask->sc->sc_data_direction == DMA_TO_DEVICE) + rc = iscsi_r2t_rsp(conn, ctask); else rc = ISCSI_ERR_PROTO; break; @@ -528,8 +822,7 @@ 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) { + 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, @@ -538,8 +831,13 @@ iscsi_tcp_hdr_recv(struct iscsi_conn *conn) 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: @@ -551,480 +849,157 @@ 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; - } - } + skb_prepare_seq_read(skb, offset, skb->len, &seq); + while (1) { + unsigned int avail; + const u8 *ptr; - /* - * 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 && - tcp_conn->in.copy) { - uint32_t recv_digest; - - debug_tcp("extra data_recv offset %d copy %d\n", - tcp_conn->in.offset, tcp_conn->in.copy); - - if (!tcp_conn->data_copied) { - 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); + avail = skb_seq_read(consumed, &ptr, &seq); + if (avail == 0) + break; + 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) { + 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); - } - 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; - } - - 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; + /* The done() functions sets up the + * next segment. */ } - - if (tcp_conn->in.padding) - tcp_conn->in_progress = IN_PROGRESS_PAD_RECV; - else if (conn->datadgst_en) - tcp_conn->in_progress = IN_PROGRESS_DDIGEST_RECV; - else - tcp_conn->in_progress = IN_PROGRESS_WAIT_HEADER; - tcp_conn->data_copied = 0; - } - - if (tcp_conn->in_progress == IN_PROGRESS_PAD_RECV && - tcp_conn->in.copy) { - int copylen = min(tcp_conn->in.padding - tcp_conn->data_copied, - tcp_conn->in.copy); - - tcp_conn->in.copy -= copylen; - tcp_conn->in.offset += copylen; - tcp_conn->data_copied += copylen; - - if (tcp_conn->data_copied != tcp_conn->in.padding) - tcp_conn->in_progress = IN_PROGRESS_PAD_RECV; - else if (conn->datadgst_en) - tcp_conn->in_progress = IN_PROGRESS_DDIGEST_RECV; - else - tcp_conn->in_progress = IN_PROGRESS_WAIT_HEADER; - tcp_conn->data_copied = 0; - } - - 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; } -nomore: - processed = tcp_conn->in.offset - offset; - BUG_ON(processed == 0); - return processed; + conn->rxdata_octets += consumed; + return consumed; -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 @@ -1104,121 +1079,173 @@ 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 inline void -iscsi_data_digest_init(struct iscsi_tcp_conn *tcp_conn, - struct iscsi_tcp_cmd_task *tcp_ctask) +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", __FUNCTION__, 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_ctask 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", __FUNCTION__, + 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) { - crypto_hash_init(&tcp_conn->tx_hash); - tcp_ctask->digest_count = 4; + 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", __FUNCTION__, tcp_conn, 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; + + iscsi_segment_init_linear(&tcp_conn->out.data_segment, + data, len, NULL, tx_hash); } /** @@ -1234,13 +1261,17 @@ iscsi_data_digest_init(struct iscsi_tcp_conn *tcp_conn, * * Called under connection lock. **/ -static void +static int iscsi_solicit_data_cont(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask, - struct iscsi_r2t_info *r2t, int left) + 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)); @@ -1261,50 +1292,46 @@ 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_ctask - Initialize iSCSI SCSI_READ or SCSI_WRITE commands * @conn: iscsi connection * @ctask: scsi command task * @sc: scsi command **/ -static void -iscsi_tcp_cmd_init(struct iscsi_cmd_task *ctask) +static int +iscsi_tcp_ctask_init(struct iscsi_cmd_task *ctask) { struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; + struct iscsi_conn *conn = ctask->conn; + struct scsi_cmnd *sc = ctask->sc; + int err; BUG_ON(__kfifo_len(tcp_ctask->r2tqueue)); - tcp_ctask->xmstate = XMSTATE_CMD_HDR_INIT; + tcp_ctask->sent = 0; + tcp_ctask->exp_datasn = 0; + + /* Prepare PDU, optionally w/ immediate data */ + debug_scsi("ctask deq [cid %d itt 0x%x imm %d unsol %d]\n", + conn->id, ctask->itt, ctask->imm_count, + ctask->unsol_count); + iscsi_tcp_send_hdr_prep(conn, ctask->hdr, ctask->hdr_len); + + if (!ctask->imm_count) + return 0; + + /* If we have immediate data, attach a payload */ + err = iscsi_tcp_send_data_prep(conn, scsi_sglist(sc), scsi_sg_count(sc), + 0, ctask->imm_count); + if (err) + return err; + tcp_ctask->sent += ctask->imm_count; + ctask->imm_count = 0; + return 0; } /** @@ -1316,71 +1343,17 @@ iscsi_tcp_cmd_init(struct iscsi_cmd_task *ctask) * 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) { - 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)); - - if (mtask->data_count) { - tcp_mtask->xmstate |= XMSTATE_IMM_DATA; - iscsi_buf_init_iov(&tcp_mtask->sendbuf, - (char*)mtask->data, - mtask->data_count); - } - - 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); - - tcp_mtask->sent = 0; - tcp_mtask->xmstate &= ~XMSTATE_IMM_HDR_INIT; - tcp_mtask->xmstate |= XMSTATE_IMM_HDR; - } - - 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; - } - - 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); - } + /* Flush any pending data first. */ + rc = iscsi_tcp_flush(conn); + if (rc < 0) + return rc; - BUG_ON(tcp_mtask->xmstate != XMSTATE_IDLE); if (mtask->hdr->itt == RESERVED_ITT) { struct iscsi_session *session = conn->session; @@ -1388,419 +1361,115 @@ iscsi_tcp_mtask_xmit(struct iscsi_conn *conn, struct iscsi_mgmt_task *mtask) iscsi_free_mgmt_task(conn, mtask); spin_unlock_bh(&session->lock); } + return 0; } +/* + * iscsi_tcp_ctask_xmit - xmit normal PDU task + * @conn: iscsi connection + * @ctask: 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_ctask_xmit(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask) { - struct scsi_cmnd *sc = ctask->sc; struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; + struct scsi_cmnd *sc = ctask->sc; 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; -} - -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)) - 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) - 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) +flush: + /* Flush any pending data first. */ + rc = iscsi_tcp_flush(conn); + if (rc < 0) 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; - } + /* Are we done already? */ + if (sc->sc_data_direction != DMA_TO_DEVICE) + return 0; - if (conn->datadgst_en) { - dtask = &tcp_ctask->unsol_dtask; - iscsi_data_digest_init(ctask->conn->dd_data, tcp_ctask); - dtask->digest = 0; - } + if (ctask->unsol_count != 0) { + struct iscsi_data *hdr = &tcp_ctask->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 ctask->data_count. + * FIXME: return the data count instead. + */ + iscsi_prep_unsolicit_data_pdu(ctask, 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", + ctask->itt, tcp_ctask->sent, ctask->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, scsi_sglist(sc), + scsi_sg_count(sc), + tcp_ctask->sent, + ctask->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_ctask->sent += ctask->data_count; + ctask->unsol_count -= ctask->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_ctask->r2t; + if (r2t != NULL) { + /* Continue with this R2T? */ +setup_data_out_pdu: + if (!iscsi_solicit_data_cont(conn, ctask, r2t)) { + debug_scsi(" done with r2t %p\n", r2t); + + __kfifo_put(tcp_ctask->r2tpool.queue, + (void*)&r2t, sizeof(void*)); + tcp_ctask->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); + if (r2t == NULL) { __kfifo_get(tcp_ctask->r2tqueue, (void*)&tcp_ctask->r2t, sizeof(void*)); - spin_unlock_bh(&session->lock); + r2t = tcp_ctask->r2t; + if (r2t) + goto setup_data_out_pdu; } -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 [dsn %d itt 0x%x doff %d dlen %d]\n", + r2t->solicit_datasn - 1, ctask->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, scsi_sglist(sc), + scsi_sg_count(sc), + 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_ctask->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 * @@ -1826,9 +1495,6 @@ iscsi_tcp_conn_create(struct iscsi_cls_session *cls_session, uint32_t conn_idx) conn->dd_data = tcp_conn; 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); @@ -1905,11 +1571,9 @@ static void 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; 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, @@ -1922,7 +1586,7 @@ static int iscsi_tcp_get_addr(struct iscsi_conn *conn, struct socket *sock, struct sockaddr_in *sin; int rc = 0, len; - addr = kmalloc(GFP_KERNEL, sizeof(*addr)); + addr = kmalloc(sizeof(*addr), GFP_KERNEL); if (!addr) return -ENOMEM; @@ -2009,7 +1673,7 @@ iscsi_tcp_conn_bind(struct iscsi_cls_session *cls_session, /* * set receive state machine into initial state */ - tcp_conn->in_progress = IN_PROGRESS_WAIT_HEADER; + iscsi_tcp_hdr_recv_prep(tcp_conn); return 0; free_socket: @@ -2019,10 +1683,17 @@ free_socket: /* called with host lock */ static void -iscsi_tcp_mgmt_init(struct iscsi_conn *conn, struct iscsi_mgmt_task *mtask) +iscsi_tcp_mtask_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; + debug_scsi("mtask deq [cid %d itt 0x%x]\n", conn->id, mtask->itt); + + /* Prepare PDU, optionally w/ immediate data */ + iscsi_tcp_send_hdr_prep(conn, mtask->hdr, sizeof(*mtask->hdr)); + + /* If we have immediate data, attach a payload */ + if (mtask->data_count) + iscsi_tcp_send_linear_data_prepare(conn, mtask->data, + mtask->data_count); } static int @@ -2045,8 +1716,7 @@ 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_ctask->r2tpool, session->max_r2t * 4, NULL, sizeof(struct iscsi_r2t_info))) { goto r2t_alloc_fail; } @@ -2055,8 +1725,7 @@ iscsi_r2tpool_alloc(struct iscsi_session *session) tcp_ctask->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); + iscsi_pool_free(&tcp_ctask->r2tpool); goto r2t_alloc_fail; } } @@ -2069,8 +1738,7 @@ r2t_alloc_fail: struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; kfifo_free(tcp_ctask->r2tqueue); - iscsi_pool_free(&tcp_ctask->r2tpool, - (void**)tcp_ctask->r2ts); + iscsi_pool_free(&tcp_ctask->r2tpool); } return -ENOMEM; } @@ -2085,8 +1753,7 @@ iscsi_r2tpool_free(struct iscsi_session *session) struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; kfifo_free(tcp_ctask->r2tqueue); - iscsi_pool_free(&tcp_ctask->r2tpool, - (void**)tcp_ctask->r2ts); + iscsi_pool_free(&tcp_ctask->r2tpool); } } @@ -2102,9 +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); @@ -2225,14 +1889,15 @@ iscsi_tcp_session_create(struct iscsi_transport *iscsit, struct iscsi_cmd_task *ctask = session->cmds[cmd_i]; struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data; - ctask->hdr = &tcp_ctask->hdr; + ctask->hdr = &tcp_ctask->hdr.cmd_hdr; + ctask->hdr_max = sizeof(tcp_ctask->hdr) - ISCSI_DIGEST_SIZE; } 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; - mtask->hdr = &tcp_mtask->hdr; + mtask->hdr = (struct iscsi_hdr *) &tcp_mtask->hdr; } if (iscsi_r2tpool_alloc(class_to_transport_session(cls_session))) @@ -2329,8 +1994,8 @@ 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, + .init_cmd_task = iscsi_tcp_ctask_init, + .init_mgmt_task = iscsi_tcp_mtask_init, .xmit_cmd_task = iscsi_tcp_ctask_xmit, .xmit_mgmt_task = iscsi_tcp_mtask_xmit, .cleanup_cmd_task = iscsi_tcp_cleanup_ctask, diff --git a/kernel/iscsi_tcp.h b/kernel/iscsi_tcp.h index 4b86fe4..57c2317 100644 --- a/kernel/iscsi_tcp.h +++ b/kernel/iscsi_tcp.h @@ -24,71 +24,64 @@ #include "libiscsi.h" -/* Socket's Receive state machine */ -#define IN_PROGRESS_WAIT_HEADER 0x0 -#define IN_PROGRESS_HEADER_GATHER 0x1 -#define IN_PROGRESS_DATA_RECV 0x2 -#define IN_PROGRESS_DDIGEST_RECV 0x3 -#define IN_PROGRESS_PAD_RECV 0x4 - -/* xmit state machine */ -#define XMSTATE_IDLE 0x0 -#define XMSTATE_CMD_HDR_INIT 0x1 -#define XMSTATE_CMD_HDR_XMIT 0x2 -#define XMSTATE_IMM_HDR 0x4 -#define XMSTATE_IMM_DATA 0x8 -#define XMSTATE_UNS_INIT 0x10 -#define XMSTATE_UNS_HDR 0x20 -#define XMSTATE_UNS_DATA 0x40 -#define XMSTATE_SOL_HDR 0x80 -#define XMSTATE_SOL_DATA 0x100 -#define XMSTATE_W_PAD 0x200 -#define XMSTATE_W_RESEND_PAD 0x400 -#define XMSTATE_W_RESEND_DATA_DIGEST 0x800 -#define XMSTATE_IMM_HDR_INIT 0x1000 -#define XMSTATE_SOL_HDR_INIT 0x2000 - -#define ISCSI_PAD_LEN 4 #define ISCSI_SG_TABLESIZE SG_ALL #define ISCSI_TCP_MAX_CMD_LEN 16 struct crypto_hash; struct socket; +struct iscsi_tcp_conn; +struct iscsi_segment; + +typedef int iscsi_segment_done_fn_t(struct iscsi_tcp_conn *, + struct iscsi_segment *); + +struct iscsi_segment { + unsigned char *data; + unsigned int size; + unsigned int copied; + unsigned int total_size; + unsigned int total_copied; + + struct hash_desc *hash; + unsigned char recv_digest[ISCSI_DIGEST_SIZE]; + unsigned char digest[ISCSI_DIGEST_SIZE]; + unsigned int digest_len; + + struct scatterlist *sg; + void *sg_mapped; + unsigned int sg_offset; + + iscsi_segment_done_fn_t *done; +}; /* Socket connection recieve helper */ struct iscsi_tcp_recv { struct iscsi_hdr *hdr; - struct sk_buff *skb; - int offset; - int len; - int hdr_offset; - int copy; - int copied; - int padding; - struct iscsi_cmd_task *ctask; /* current cmd in progress */ + struct iscsi_segment segment; + + /* Allocate buffer for BHS + AHS */ + uint32_t hdr_buf[64]; /* copied and flipped values */ int datalen; - int datadgst; - char zero_copy_hdr; +}; + +/* Socket connection send helper */ +struct iscsi_tcp_send { + struct iscsi_hdr *hdr; + struct iscsi_segment segment; + struct iscsi_segment data_segment; }; struct iscsi_tcp_conn { struct iscsi_conn *iscsi_conn; struct socket *sock; - struct iscsi_hdr hdr; /* header placeholder */ - char hdrext[4*sizeof(__u16) + - sizeof(__u32)]; - int data_copied; int stop_stage; /* conn_stop() flag: * * stop to recover, * * stop to terminate */ - /* iSCSI connection-wide sequencing */ - int hdr_size; /* PDU header size */ - /* control data */ struct iscsi_tcp_recv in; /* TCP receive context */ - int in_progress; /* connection state machine */ + struct iscsi_tcp_send out; /* TCP send context */ /* old values for socket callbacks */ void (*old_data_ready)(struct sock *, int); @@ -103,29 +96,19 @@ struct iscsi_tcp_conn { uint32_t sendpage_failures_cnt; uint32_t discontiguous_hdr_cnt; - ssize_t (*sendpage)(struct socket *, struct page *, int, size_t, int); -}; + int error; -struct iscsi_buf { - struct scatterlist sg; - unsigned int sent; - char use_sendmsg; + ssize_t (*sendpage)(struct socket *, struct page *, int, size_t, int); }; struct iscsi_data_task { struct iscsi_data hdr; /* PDU */ - char hdrext[sizeof(__u32)]; /* Header-Digest */ - struct iscsi_buf digestbuf; /* digest buffer */ - uint32_t digest; /* data digest */ + char hdrext[ISCSI_DIGEST_SIZE];/* Header-Digest */ }; struct iscsi_tcp_mgmt_task { struct iscsi_hdr hdr; - char hdrext[sizeof(__u32)]; /* Header-Digest */ - int xmstate; /* mgmt xmit progress */ - struct iscsi_buf headbuf; /* header buffer */ - struct iscsi_buf sendbuf; /* in progress buffer */ - int sent; + char hdrext[ISCSI_DIGEST_SIZE]; /* Header-Digest */ }; struct iscsi_r2t_info { @@ -133,38 +116,26 @@ struct iscsi_r2t_info { __be32 exp_statsn; /* copied from R2T */ uint32_t data_length; /* copied from R2T */ uint32_t data_offset; /* copied from R2T */ - struct iscsi_buf headbuf; /* Data-Out Header Buffer */ - struct iscsi_buf sendbuf; /* Data-Out in progress buffer*/ int sent; /* R2T sequence progress */ int data_count; /* DATA-Out payload progress */ - struct scatterlist *sg; /* per-R2T SG list */ int solicit_datasn; - struct iscsi_data_task dtask; /* which data task */ + struct iscsi_data_task dtask; /* Data-Out header buf */ }; struct iscsi_tcp_cmd_task { - struct iscsi_cmd hdr; - char hdrext[4*sizeof(__u16)+ /* AHS */ - sizeof(__u32)]; /* HeaderDigest */ - char pad[ISCSI_PAD_LEN]; - int pad_count; /* padded bytes */ - struct iscsi_buf headbuf; /* header buf (xmit) */ - struct iscsi_buf sendbuf; /* in progress buffer*/ - int xmstate; /* xmit xtate machine */ + struct iscsi_hdr_buff { + struct iscsi_cmd cmd_hdr; + char hdrextbuf[ISCSI_MAX_AHS_SIZE + + ISCSI_DIGEST_SIZE]; + } hdr; + int sent; - struct scatterlist *sg; /* per-cmd SG list */ - struct scatterlist *bad_sg; /* assert statement */ - int sg_count; /* SG's to process */ - uint32_t exp_datasn; /* expected target's R2TSN/DataSN */ + uint32_t exp_datasn; /* expected target's R2TSN/DataSN */ int data_offset; - struct iscsi_r2t_info *r2t; /* in progress R2T */ - struct iscsi_queue r2tpool; + struct iscsi_r2t_info *r2t; /* in progress R2T */ + struct iscsi_pool r2tpool; struct kfifo *r2tqueue; - struct iscsi_r2t_info **r2ts; - int digest_count; - uint32_t immdigest; /* for imm data */ - struct iscsi_buf immbuf; /* for imm data digest */ - struct iscsi_data_task unsol_dtask; /* unsol data task */ + struct iscsi_data_task unsol_dtask; /* Data-Out header buf */ }; #endif /* ISCSI_H */ diff --git a/kernel/libiscsi.c b/kernel/libiscsi.c index 790a6af..dce6b4e 100644 --- a/kernel/libiscsi.c +++ b/kernel/libiscsi.c @@ -33,6 +33,7 @@ #include <scsi/scsi_host.h> #include <scsi/scsi.h> #include <scsi/scsi_transport.h> + #include "iscsi_proto.h" #include "scsi_transport_iscsi.h" #include "libiscsi.h" @@ -122,6 +123,20 @@ void iscsi_prep_unsolicit_data_pdu(struct iscsi_cmd_task *ctask, } EXPORT_SYMBOL_GPL(iscsi_prep_unsolicit_data_pdu); +static int iscsi_add_hdr(struct iscsi_cmd_task *ctask, unsigned len) +{ + unsigned exp_len = ctask->hdr_len + len; + + if (exp_len > ctask->hdr_max) { + WARN_ON(1); + return -EINVAL; + } + + WARN_ON(len & (ISCSI_PAD_LEN - 1)); /* caller must pad the AHS */ + ctask->hdr_len = exp_len; + return 0; +} + /** * iscsi_prep_scsi_cmd_pdu - prep iscsi scsi cmd pdu * @ctask: iscsi cmd task @@ -129,27 +144,32 @@ EXPORT_SYMBOL_GPL(iscsi_prep_unsolicit_data_pdu); * Prep basic iSCSI PDU fields for a scsi cmd pdu. The LLD should set * fields like dlength or final based on how much data it sends */ -static void iscsi_prep_scsi_cmd_pdu(struct iscsi_cmd_task *ctask) +static int iscsi_prep_scsi_cmd_pdu(struct iscsi_cmd_task *ctask) { struct iscsi_conn *conn = ctask->conn; struct iscsi_session *session = conn->session; struct iscsi_cmd *hdr = ctask->hdr; struct scsi_cmnd *sc = ctask->sc; + unsigned hdrlength; + int rc; - hdr->opcode = ISCSI_OP_SCSI_CMD; - hdr->flags = ISCSI_ATTR_SIMPLE; - int_to_scsilun(sc->device->lun, (struct scsi_lun *)hdr->lun); - hdr->itt = build_itt(ctask->itt, conn->id, session->age); - hdr->data_length = cpu_to_be32(sc->request_bufflen); - hdr->cmdsn = cpu_to_be32(session->cmdsn); - session->cmdsn++; - hdr->exp_statsn = cpu_to_be32(conn->exp_statsn); - memcpy(hdr->cdb, sc->cmnd, sc->cmd_len); + ctask->hdr_len = 0; + rc = iscsi_add_hdr(ctask, sizeof(*hdr)); + if (rc) + return rc; + hdr->opcode = ISCSI_OP_SCSI_CMD; + hdr->flags = ISCSI_ATTR_SIMPLE; + int_to_scsilun(sc->device->lun, (struct scsi_lun *)hdr->lun); + hdr->itt = build_itt(ctask->itt, conn->id, session->age); + hdr->data_length = cpu_to_be32(scsi_bufflen(sc)); + hdr->cmdsn = cpu_to_be32(session->cmdsn); + session->cmdsn++; + hdr->exp_statsn = cpu_to_be32(conn->exp_statsn); + memcpy(hdr->cdb, sc->cmnd, sc->cmd_len); if (sc->cmd_len < MAX_COMMAND_SIZE) memset(&hdr->cdb[sc->cmd_len], 0, MAX_COMMAND_SIZE - sc->cmd_len); - ctask->data_count = 0; ctask->imm_count = 0; if (sc->sc_data_direction == DMA_TO_DEVICE) { hdr->flags |= ISCSI_FLAG_CMD_WRITE; @@ -172,25 +192,25 @@ static void iscsi_prep_scsi_cmd_pdu(struct iscsi_cmd_task *ctask) ctask->unsol_datasn = 0; if (session->imm_data_en) { - if (sc->request_bufflen >= session->first_burst) + if (scsi_bufflen(sc) >= session->first_burst) ctask->imm_count = min(session->first_burst, conn->max_xmit_dlength); else - ctask->imm_count = min(sc->request_bufflen, + ctask->imm_count = min(scsi_bufflen(sc), conn->max_xmit_dlength); - hton24(ctask->hdr->dlength, ctask->imm_count); + hton24(hdr->dlength, ctask->imm_count); } else - zero_data(ctask->hdr->dlength); + zero_data(hdr->dlength); if (!session->initial_r2t_en) { ctask->unsol_count = min((session->first_burst), - (sc->request_bufflen)) - ctask->imm_count; + (scsi_bufflen(sc))) - ctask->imm_count; ctask->unsol_offset = ctask->imm_count; } if (!ctask->unsol_count) /* No unsolicit Data-Out's */ - ctask->hdr->flags |= ISCSI_FLAG_CMD_FINAL; + hdr->flags |= ISCSI_FLAG_CMD_FINAL; } else { hdr->flags |= ISCSI_FLAG_CMD_FINAL; zero_data(hdr->dlength); @@ -199,13 +219,25 @@ static void iscsi_prep_scsi_cmd_pdu(struct iscsi_cmd_task *ctask) hdr->flags |= ISCSI_FLAG_CMD_READ; } - conn->scsicmd_pdus_cnt++; + /* calculate size of additional header segments (AHSs) */ + hdrlength = ctask->hdr_len - sizeof(*hdr); - debug_scsi("iscsi prep [%s cid %d sc %p cdb 0x%x itt 0x%x len %d " + WARN_ON(hdrlength & (ISCSI_PAD_LEN-1)); + hdrlength /= ISCSI_PAD_LEN; + + WARN_ON(hdrlength >= 256); + hdr->hlength = hdrlength & 0xFF; + + if (conn->session->tt->init_cmd_task(conn->ctask)) + return EIO; + + conn->scsicmd_pdus_cnt++; + debug_scsi("iscsi prep [%s cid %d sc %p cdb 0x%x itt 0x%x len %d " "cmdsn %d win %d]\n", - sc->sc_data_direction == DMA_TO_DEVICE ? "write" : "read", - conn->id, sc, sc->cmnd[0], ctask->itt, sc->request_bufflen, - session->cmdsn, session->max_cmdsn - session->exp_cmdsn + 1); + sc->sc_data_direction == DMA_TO_DEVICE ? "write" : "read", + conn->id, sc, sc->cmnd[0], ctask->itt, scsi_bufflen(sc), + session->cmdsn, session->max_cmdsn - session->exp_cmdsn + 1); + return 0; } /** @@ -266,7 +298,7 @@ static void fail_command(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask, conn->session->tt->cleanup_cmd_task(conn, ctask); sc->result = err; - sc->resid = sc->request_bufflen; + scsi_set_resid(sc, scsi_bufflen(sc)); if (conn->ctask == ctask) conn->ctask = NULL; /* release ref from queuecommand */ @@ -281,7 +313,7 @@ static void fail_command(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask, * Must be called with session lock. */ void iscsi_free_mgmt_task(struct iscsi_conn *conn, - struct iscsi_mgmt_task *mtask) + struct iscsi_mgmt_task *mtask) { list_del_init(&mtask->running); if (conn->login_mtask == mtask) @@ -403,17 +435,19 @@ invalid_datalen: if (sc->sc_data_direction == DMA_TO_DEVICE) goto out; - if (rhdr->flags & ISCSI_FLAG_CMD_UNDERFLOW) { + if (rhdr->flags & (ISCSI_FLAG_CMD_UNDERFLOW | + ISCSI_FLAG_CMD_OVERFLOW)) { int res_count = be32_to_cpu(rhdr->residual_count); - if (res_count > 0 && res_count <= sc->request_bufflen) - sc->resid = res_count; + if (res_count > 0 && + (rhdr->flags & ISCSI_FLAG_CMD_OVERFLOW || + res_count <= scsi_bufflen(sc))) + scsi_set_resid(sc, res_count); else sc->result = (DID_BAD_TARGET << 16) | rhdr->cmd_status; - } else if (rhdr->flags & ISCSI_FLAG_CMD_BIDI_UNDERFLOW) + } else if (rhdr->flags & (ISCSI_FLAG_CMD_BIDI_UNDERFLOW | + ISCSI_FLAG_CMD_BIDI_OVERFLOW)) sc->result = (DID_BAD_TARGET << 16) | rhdr->cmd_status; - else if (rhdr->flags & ISCSI_FLAG_CMD_OVERFLOW) - sc->resid = be32_to_cpu(rhdr->residual_count); out: debug_scsi("done [sc %lx res %d itt 0x%x]\n", @@ -887,15 +921,18 @@ check_mgmt: while (!list_empty(&conn->xmitqueue)) { if (conn->tmf_state == TMF_QUEUED) break; + conn->ctask = list_entry(conn->xmitqueue.next, struct iscsi_cmd_task, running); if (conn->session->state == ISCSI_STATE_LOGGING_OUT) { - fail_command(conn, conn->ctask, DID_IMM_RETRY); + fail_command(conn, conn->ctask, DID_IMM_RETRY << 16); + continue; + } + if (iscsi_prep_scsi_cmd_pdu(conn->ctask)) { + fail_command(conn, conn->ctask, DID_ABORT << 16); continue; } - iscsi_prep_scsi_cmd_pdu(conn->ctask); - conn->session->tt->init_cmd_task(conn->ctask); conn->ctask->state = ISCSI_TASK_RUNNING; list_move_tail(conn->xmitqueue.next, &conn->run_list); rc = iscsi_xmit_ctask(conn); @@ -978,8 +1015,9 @@ int iscsi_queuecommand(struct scsi_cmnd *sc, void (*done)(struct scsi_cmnd *)) sc->SCp.ptr = NULL; host = sc->device->host; - session = iscsi_hostdata(host->hostdata); + spin_unlock(host->host_lock); + session = iscsi_hostdata(host->hostdata); spin_lock(&session->lock); /* @@ -1045,11 +1083,13 @@ int iscsi_queuecommand(struct scsi_cmnd *sc, void (*done)(struct scsi_cmnd *)) spin_unlock(&session->lock); scsi_queue_work(host, &conn->xmitwork); + spin_lock(host->host_lock); return 0; reject: spin_unlock(&session->lock); debug_scsi("cmd 0x%x rejected (%d)\n", sc->cmnd[0], reason); + spin_lock(host->host_lock); return SCSI_MLQUEUE_HOST_BUSY; fault: @@ -1057,8 +1097,9 @@ fault: printk(KERN_ERR "iscsi: cmd 0x%x is not queued (%d)\n", sc->cmnd[0], reason); sc->result = (DID_NO_CONNECT << 16); - sc->resid = sc->request_bufflen; + scsi_set_resid(sc, scsi_bufflen(sc)); sc->scsi_done(sc); + spin_lock(host->host_lock); return 0; } EXPORT_SYMBOL_GPL(iscsi_queuecommand); @@ -1553,59 +1594,64 @@ done: } EXPORT_SYMBOL_GPL(iscsi_eh_device_reset); +/* + * Pre-allocate a pool of @max items of @item_size. By default, the pool + * should be accessed via kfifo_{get,put} on q->queue. + * Optionally, the caller can obtain the array of object pointers + * by passing in a non-NULL @items pointer + */ int -iscsi_pool_init(struct iscsi_queue *q, int max, void ***items, int item_size) +iscsi_pool_init(struct iscsi_pool *q, int max, void ***items, int item_size) { - int i; + int i, num_arrays = 1; - *items = kmalloc(max * sizeof(void*), GFP_KERNEL); - if (*items == NULL) - return -ENOMEM; + memset(q, 0, sizeof(*q)); q->max = max; - q->pool = kmalloc(max * sizeof(void*), GFP_KERNEL); - if (q->pool == NULL) { - kfree(*items); - return -ENOMEM; - } + + /* If the user passed an items pointer, he wants a copy of + * the array. */ + if (items) + num_arrays++; + q->pool = kzalloc(num_arrays * max * sizeof(void*), GFP_KERNEL); + if (q->pool == NULL) + goto enomem; q->queue = kfifo_init((void*)q->pool, max * sizeof(void*), GFP_KERNEL, NULL); - if (q->queue == ERR_PTR(-ENOMEM)) { - kfree(q->pool); - kfree(*items); - return -ENOMEM; - } + if (q->queue == ERR_PTR(-ENOMEM)) + goto enomem; for (i = 0; i < max; i++) { - q->pool[i] = kmalloc(item_size, GFP_KERNEL); + q->pool[i] = kzalloc(item_size, GFP_KERNEL); if (q->pool[i] == NULL) { - int j; - - for (j = 0; j < i; j++) - kfree(q->pool[j]); - - kfifo_free(q->queue); - kfree(q->pool); - kfree(*items); - return -ENOMEM; + q->max = i; + goto enomem; } - memset(q->pool[i], 0, item_size); - (*items)[i] = q->pool[i]; __kfifo_put(q->queue, (void*)&q->pool[i], sizeof(void*)); } + + if (items) { + *items = q->pool + max; + memcpy(*items, q->pool, max * sizeof(void *)); + } + return 0; + +enomem: + iscsi_pool_free(q); + return -ENOMEM; } EXPORT_SYMBOL_GPL(iscsi_pool_init); -void iscsi_pool_free(struct iscsi_queue *q, void **items) +void iscsi_pool_free(struct iscsi_pool *q) { int i; for (i = 0; i < q->max; i++) - kfree(items[i]); - kfree(q->pool); - kfree(items); + kfree(q->pool[i]); + if (q->pool) + kfree(q->pool); } EXPORT_SYMBOL_GPL(iscsi_pool_free); @@ -1655,7 +1701,7 @@ iscsi_session_setup(struct iscsi_transport *iscsit, printk(KERN_ERR "iscsi: invalid queue depth of %d. " "Queue depth must be between 1 and %d.\n", qdepth, ISCSI_MAX_CMD_PER_LUN); - qdepth = ISCSI_DEF_CMD_PER_LUN; + qdepth = ISCSI_DEF_CMD_PER_LUN; } if (cmds_max < 2 || (cmds_max & (cmds_max - 1)) || @@ -1752,9 +1798,9 @@ module_put: cls_session_fail: scsi_remove_host(shost); add_host_fail: - iscsi_pool_free(&session->mgmtpool, (void**)session->mgmt_cmds); + iscsi_pool_free(&session->mgmtpool); mgmtpool_alloc_fail: - iscsi_pool_free(&session->cmdpool, (void**)session->cmds); + iscsi_pool_free(&session->cmdpool); cmdpool_alloc_fail: scsi_host_put(shost); return NULL; @@ -1777,8 +1823,8 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session) iscsi_remove_session(cls_session); scsi_remove_host(shost); - iscsi_pool_free(&session->mgmtpool, (void**)session->mgmt_cmds); - iscsi_pool_free(&session->cmdpool, (void**)session->cmds); + iscsi_pool_free(&session->mgmtpool); + iscsi_pool_free(&session->cmdpool); kfree(session->password); kfree(session->password_in); diff --git a/kernel/libiscsi.h b/kernel/libiscsi.h index d02c55f..8328bc7 100644 --- a/kernel/libiscsi.h +++ b/kernel/libiscsi.h @@ -77,6 +77,13 @@ enum { #define ISCSI_ADDRESS_BUF_LEN 64 +enum { + /* this is the maximum possible storage for AHSs */ + ISCSI_MAX_AHS_SIZE = sizeof(struct iscsi_ecdb_ahdr) + + sizeof(struct iscsi_rlength_ahdr), + ISCSI_DIGEST_SIZE = sizeof(__u32), +}; + struct iscsi_mgmt_task { /* * Becuae LLDs allocate their hdr differently, this is a pointer to @@ -98,10 +105,13 @@ enum { struct iscsi_cmd_task { /* - * Becuae LLDs allocate their hdr differently, this is a pointer to - * that storage. It must be setup at session creation time. + * Because LLDs allocate their hdr differently, this is a pointer + * and length to that storage. It must be setup at session + * creation time. */ struct iscsi_cmd *hdr; + unsigned short hdr_max; + unsigned short hdr_len; /* accumulated size of hdr used */ int itt; /* this ITT */ uint32_t unsol_datasn; @@ -120,6 +130,11 @@ struct iscsi_cmd_task { void *dd_data; /* driver/transport data */ }; +static inline void* iscsi_next_hdr(struct iscsi_cmd_task *ctask) +{ + return (void*)ctask->hdr + ctask->hdr_len; +} + struct iscsi_conn { struct iscsi_cls_conn *cls_conn; /* ptr to class connection */ void *dd_data; /* iscsi_transport data */ @@ -206,7 +221,7 @@ struct iscsi_conn { uint32_t eh_abort_cnt; }; -struct iscsi_queue { +struct iscsi_pool { struct kfifo *queue; /* FIFO Queue */ void **pool; /* Pool of elements */ int max; /* Max number of elements */ @@ -267,10 +282,10 @@ struct iscsi_session { int cmds_max; /* size of cmds array */ struct iscsi_cmd_task **cmds; /* Original Cmds arr */ - struct iscsi_queue cmdpool; /* PDU's pool */ + struct iscsi_pool cmdpool; /* PDU's pool */ int mgmtpool_max; /* size of mgmt array */ struct iscsi_mgmt_task **mgmt_cmds; /* Original mgmt arr */ - struct iscsi_queue mgmtpool; /* Mgmt PDU's pool */ + struct iscsi_pool mgmtpool; /* Mgmt PDU's pool */ }; /* @@ -345,7 +360,25 @@ extern void iscsi_free_mgmt_task(struct iscsi_conn *conn, /* * generic helpers */ -extern void iscsi_pool_free(struct iscsi_queue *, void **); -extern int iscsi_pool_init(struct iscsi_queue *, int, void ***, int); +extern void iscsi_pool_free(struct iscsi_pool *); +extern int iscsi_pool_init(struct iscsi_pool *, int, void ***, int); + +/* + * inline functions to deal with padding. + */ +static inline unsigned int +iscsi_padded(unsigned int len) +{ + return (len + ISCSI_PAD_LEN - 1) & ~(ISCSI_PAD_LEN - 1); +} + +static inline unsigned int +iscsi_padding(unsigned int len) +{ + len &= (ISCSI_PAD_LEN - 1); + if (len) + len = ISCSI_PAD_LEN - len; + return len; +} #endif diff --git a/kernel/scsi_transport_iscsi.c b/kernel/scsi_transport_iscsi.c index d1b8abb..0dbcedd 100644 --- a/kernel/scsi_transport_iscsi.c +++ b/kernel/scsi_transport_iscsi.c @@ -33,7 +33,7 @@ #define ISCSI_SESSION_ATTRS 16 #define ISCSI_CONN_ATTRS 11 #define ISCSI_HOST_ATTRS 4 -#define ISCSI_TRANSPORT_VERSION "2.0-865" +#define ISCSI_TRANSPORT_VERSION "2.0-724" struct iscsi_internal { int daemon_pid; @@ -1141,7 +1141,7 @@ iscsi_if_rx(struct sock *sk, int len) struct nlmsghdr *nlh; struct iscsi_uevent *ev; - nlh = (struct nlmsghdr *)skb->data; + nlh = nlmsg_hdr(skb); if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len) { break; @@ -1551,8 +1551,8 @@ static __init int iscsi_transport_init(void) if (err) goto unregister_conn_class; - nls = netlink_kernel_create(NETLINK_ISCSI, 1, iscsi_if_rx, - NULL, THIS_MODULE); + nls = netlink_kernel_create(NETLINK_ISCSI, 1, iscsi_if_rx, NULL, + THIS_MODULE); if (!nls) { err = -ENOBUFS; goto unregister_session_class; diff --git a/kernel/scsi_transport_iscsi.h b/kernel/scsi_transport_iscsi.h index bc1ce21..26717c5 100644 --- a/kernel/scsi_transport_iscsi.h +++ b/kernel/scsi_transport_iscsi.h @@ -116,7 +116,7 @@ struct iscsi_transport { char *data, uint32_t data_size); void (*get_stats) (struct iscsi_cls_conn *conn, struct iscsi_stats *stats); - void (*init_cmd_task) (struct iscsi_cmd_task *ctask); + int (*init_cmd_task) (struct iscsi_cmd_task *ctask); void (*init_mgmt_task) (struct iscsi_conn *conn, struct iscsi_mgmt_task *mtask); int (*xmit_cmd_task) (struct iscsi_conn *conn, |