From patchwork Thu Mar 2 16:43:03 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Felipe Franciosi X-Patchwork-Id: 9600917 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id E645260429 for ; Thu, 2 Mar 2017 16:43:46 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id D2A56237A5 for ; Thu, 2 Mar 2017 16:43:46 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id C2FBB27CAF; Thu, 2 Mar 2017 16:43:46 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.9 required=2.0 tests=BAYES_00,RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (No client certificate requested) by mail.wl.linuxfoundation.org (Postfix) with ESMTPS id 2F336237A5 for ; Thu, 2 Mar 2017 16:43:45 +0000 (UTC) Received: from localhost ([::1]:53274 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1cjTpQ-00036D-47 for patchwork-qemu-devel@patchwork.kernel.org; Thu, 02 Mar 2017 11:43:44 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:59222) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1cjTp0-00031X-E0 for qemu-devel@nongnu.org; Thu, 02 Mar 2017 11:43:21 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1cjTox-0000u5-2p for qemu-devel@nongnu.org; Thu, 02 Mar 2017 11:43:18 -0500 Received: from 206-15-90-246.static.twtelecom.net ([206.15.90.246]:12749 helo=felipe-franciosi.localdomain) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1cjTow-0000t6-8D for qemu-devel@nongnu.org; Thu, 02 Mar 2017 11:43:14 -0500 Received: by felipe-franciosi.localdomain (Postfix, from userid 500) id CAE5910688F; Thu, 2 Mar 2017 08:43:13 -0800 (PST) From: Felipe Franciosi To: Paolo Bonzini , Stefan Hajnoczi , Marc-Andre Lureau , "Michael S. Tsirkin" Date: Thu, 2 Mar 2017 08:43:03 -0800 Message-Id: <1488472983-9108-4-git-send-email-felipe@nutanix.com> X-Mailer: git-send-email 1.9.4 In-Reply-To: <1488472983-9108-1-git-send-email-felipe@nutanix.com> References: <1488472983-9108-1-git-send-email-felipe@nutanix.com> X-detected-operating-system: by eggs.gnu.org: GNU/Linux 3.x [fuzzy] X-Received-From: 206.15.90.246 Subject: [Qemu-devel] [PATCH v4 3/3] vus: Introduce a vhost-user-scsi sample application X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: "qemu-devel@nongnu.org" , Felipe Franciosi Errors-To: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Sender: "Qemu-devel" X-Virus-Scanned: ClamAV using ClamSMTP This commit introduces a vhost-user-scsi backend sample application. It must be linked with libiscsi and libvhost-user. To use it, compile with: make vhost-user-scsi And run as follows: ./vhost-user-scsi -u /tmp/vus.sock -i iscsi://uri_to_target/ The application is currently limited at one LUN only and it processes requests synchronously (therefore only achieving QD1). The purpose of the code is to show how a backend can be implemented and to test the vhost-user-scsi Qemu implementation. If a different instance of this vhost-user-scsi application is executed at a remote host, a VM can be live migrated to such a host. Signed-off-by: Felipe Franciosi --- Makefile | 3 + Makefile.objs | 4 + configure | 1 + contrib/vhost-user-scsi/Makefile.objs | 1 + contrib/vhost-user-scsi/vhost-user-scsi.c | 886 ++++++++++++++++++++++++++++++ 5 files changed, 895 insertions(+) create mode 100644 contrib/vhost-user-scsi/Makefile.objs create mode 100644 contrib/vhost-user-scsi/vhost-user-scsi.c diff --git a/Makefile b/Makefile index 1c4c04f..2189394 100644 --- a/Makefile +++ b/Makefile @@ -264,6 +264,7 @@ dummy := $(call unnest-vars,, \ ivshmem-client-obj-y \ ivshmem-server-obj-y \ libvhost-user-obj-y \ + vhost-user-scsi-obj-y \ qga-vss-dll-obj-y \ block-obj-y \ block-obj-m \ @@ -469,6 +470,8 @@ ivshmem-client$(EXESUF): $(ivshmem-client-obj-y) $(COMMON_LDADDS) $(call LINK, $^) ivshmem-server$(EXESUF): $(ivshmem-server-obj-y) $(COMMON_LDADDS) $(call LINK, $^) +vhost-user-scsi$(EXESUF): $(vhost-user-scsi-obj-y) + $(call LINK, $^) module_block.h: $(SRC_PATH)/scripts/modules/module_block.py config-host.mak $(call quiet-command,$(PYTHON) $< $@ \ diff --git a/Makefile.objs b/Makefile.objs index e740500..49543c2 100644 --- a/Makefile.objs +++ b/Makefile.objs @@ -113,6 +113,10 @@ qga-vss-dll-obj-y = qga/ ivshmem-client-obj-y = contrib/ivshmem-client/ ivshmem-server-obj-y = contrib/ivshmem-server/ libvhost-user-obj-y = contrib/libvhost-user/ +vhost-user-scsi.o-cflags := $(LIBISCSI_CFLAGS) +vhost-user-scsi.o-libs := $(LIBISCSI_LIBS) +vhost-user-scsi-obj-y = contrib/vhost-user-scsi/ +vhost-user-scsi-obj-y += contrib/libvhost-user/libvhost-user.o ###################################################################### trace-events-subdirs = diff --git a/configure b/configure index 6c21975..cc3fa7b 100755 --- a/configure +++ b/configure @@ -4812,6 +4812,7 @@ if test "$want_tools" = "yes" ; then if [ "$linux" = "yes" -o "$bsd" = "yes" -o "$solaris" = "yes" ] ; then tools="qemu-nbd\$(EXESUF) $tools" tools="ivshmem-client\$(EXESUF) ivshmem-server\$(EXESUF) $tools" + tools="vhost-user-scsi\$(EXESUF) $tools" fi fi if test "$softmmu" = yes ; then diff --git a/contrib/vhost-user-scsi/Makefile.objs b/contrib/vhost-user-scsi/Makefile.objs new file mode 100644 index 0000000..e83a38a --- /dev/null +++ b/contrib/vhost-user-scsi/Makefile.objs @@ -0,0 +1 @@ +vhost-user-scsi-obj-y = vhost-user-scsi.o diff --git a/contrib/vhost-user-scsi/vhost-user-scsi.c b/contrib/vhost-user-scsi/vhost-user-scsi.c new file mode 100644 index 0000000..e41bad0 --- /dev/null +++ b/contrib/vhost-user-scsi/vhost-user-scsi.c @@ -0,0 +1,886 @@ +/* + * vhost-user-scsi sample application + * + * Copyright (c) 2016 Nutanix Inc. All rights reserved. + * + * Author: + * Felipe Franciosi + * + * This work is licensed under the terms of the GNU GPL, version 2 only. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "contrib/libvhost-user/libvhost-user.h" +#include "hw/virtio/virtio-scsi.h" +#include "iscsi/iscsi.h" + +#include + +/* Small compat shim from glib 2.32 */ +#ifndef G_SOURCE_CONTINUE +#define G_SOURCE_CONTINUE TRUE +#endif +#ifndef G_SOURCE_REMOVE +#define G_SOURCE_REMOVE FALSE +#endif + +//#define VUS_DEBUG 1 + +/** Log helpers **/ + +#define PPRE \ + struct timespec ts; \ + char timebuf[64]; \ + struct tm tm; \ + (void)clock_gettime(CLOCK_REALTIME, &ts); \ + (void)strftime(timebuf, 64, "%Y%m%d %T", gmtime_r(&ts.tv_sec, &tm)) + +#define PEXT(lvl, msg, ...) do { \ + PPRE; \ + fprintf(stderr, "%s.%06ld " lvl ": %s:%s():%d: " msg "\n", \ + timebuf, ts.tv_nsec/1000, \ + __FILE__, __FUNCTION__, __LINE__, ## __VA_ARGS__); \ +} while(0) + +#define PNOR(lvl, msg, ...) do { \ + PPRE; \ + fprintf(stderr, "%s.%06ld " lvl ": " msg "\n", \ + timebuf, ts.tv_nsec/1000, ## __VA_ARGS__); \ +} while(0); + +#ifdef VUS_DEBUG +#define PDBG(msg, ...) PEXT("DBG", msg, ## __VA_ARGS__) +#define PERR(msg, ...) PEXT("ERR", msg, ## __VA_ARGS__) +#define PLOG(msg, ...) PEXT("LOG", msg, ## __VA_ARGS__) +#else +#define PDBG(msg, ...) { } +#define PERR(msg, ...) PNOR("ERR", msg, ## __VA_ARGS__) +#define PLOG(msg, ...) PNOR("LOG", msg, ## __VA_ARGS__) +#endif + +/** vhost-user-scsi specific definitions **/ + +#define VUS_MAX_LUNS 1 // Only 1 lun supported today +#define VUS_MAX_DEVS 1 // Only 1 devices supported today + +#define VUS_ISCSI_INITIATOR "iqn.2016-11.com.nutanix:vhost-user-scsi" + +typedef struct iscsi_lun { + struct iscsi_context *iscsi_ctx; + int iscsi_lun; +} iscsi_lun_t; + +typedef struct vhost_scsi_dev { + VuDev vu_dev; + int server_sock; + GMainLoop *loop; + GTree *fdmap; // maps fd to gsource context id + iscsi_lun_t luns[VUS_MAX_LUNS]; +} vhost_scsi_dev_t; + +static vhost_scsi_dev_t *vhost_scsi_devs[VUS_MAX_DEVS]; + +/** glib event loop integration for libvhost-user and misc callbacks **/ + +typedef struct vus_gsrc { + GSource parent; + vhost_scsi_dev_t *vdev_scsi; + GPollFD gfd; + vu_watch_cb vu_cb; +} vus_gsrc_t; + +static gint vus_fdmap_compare(gconstpointer a, gconstpointer b) +{ + if (b > a) return 1; + if (b < a) return -1; + return 0; +} + +static gboolean vus_gsrc_prepare(GSource *src, gint *timeout) +{ + assert(timeout); + + *timeout = -1; + return FALSE; +} + +static gboolean vus_gsrc_check(GSource *src) +{ + vus_gsrc_t *vus_src = (vus_gsrc_t *)src; + + assert(vus_src); + + return vus_src->gfd.revents & vus_src->gfd.events; +} + +static gboolean vus_gsrc_dispatch(GSource *src, GSourceFunc cb, gpointer data) +{ + vhost_scsi_dev_t *vdev_scsi; + vus_gsrc_t *vus_src = (vus_gsrc_t *)src; + + assert(vus_src); + assert(!(vus_src->vu_cb && cb)); + + vdev_scsi = vus_src->vdev_scsi; + + assert(vdev_scsi); + + if (vus_src->vu_cb) { + int vu_evt = 0; + + if (vus_src->gfd.events & G_IO_IN) vu_evt |= VU_WATCH_IN; + if (vus_src->gfd.events & G_IO_OUT) vu_evt |= VU_WATCH_OUT; + if (vus_src->gfd.events & G_IO_PRI) vu_evt |= VU_WATCH_PRI; + if (vus_src->gfd.events & G_IO_ERR) vu_evt |= VU_WATCH_ERR; + if (vus_src->gfd.events & G_IO_HUP) vu_evt |= VU_WATCH_HUP; + + vus_src->vu_cb(&vdev_scsi->vu_dev, vu_evt, data); + + return G_SOURCE_CONTINUE; + } + + if (cb) { + return cb(data); + } + + return G_SOURCE_CONTINUE; +} + +static GSourceFuncs vus_gsrc_funcs = { + vus_gsrc_prepare, + vus_gsrc_check, + vus_gsrc_dispatch, + NULL +}; + +static int vus_gsrc_new(vhost_scsi_dev_t *vdev_scsi, int fd, GIOCondition cond, + vu_watch_cb vu_cb, GSourceFunc gsrc_cb, gpointer data) +{ + GSource *vus_gsrc; + vus_gsrc_t *vus_src; + guint id; + + assert(vdev_scsi); + assert(fd >= 0); + assert(vu_cb || gsrc_cb); + assert(!(vu_cb && gsrc_cb)); + + vus_gsrc = g_source_new(&vus_gsrc_funcs, sizeof(vus_gsrc_t)); + if (!vus_gsrc) { + PERR("Error creating GSource for new watch"); + return -1; + } + vus_src = (vus_gsrc_t *)vus_gsrc; + + vus_src->vdev_scsi = vdev_scsi; + vus_src->gfd.fd = fd; + vus_src->gfd.events = cond; + vus_src->vu_cb = vu_cb; + + g_source_add_poll(vus_gsrc, &vus_src->gfd); + g_source_set_callback(vus_gsrc, gsrc_cb, data, NULL); + id = g_source_attach(vus_gsrc, NULL); + assert(id); + g_source_unref(vus_gsrc); + + g_tree_insert(vdev_scsi->fdmap, (gpointer)(uintptr_t)fd, + (gpointer)(uintptr_t)id); + + return 0; +} + +/* from libiscsi's scsi-lowlevel.h ** + * + * nb. We can't directly include scsi-lowlevel.h due to a namespace conflict: + * Qemu's scsi.h also defines "SCSI_XFER_NONE". + */ + +#define SCSI_CDB_MAX_SIZE 16 + +struct scsi_iovector { + struct scsi_iovec *iov; + int niov; + int nalloc; + size_t offset; + int consumed; +}; + +struct scsi_allocated_memory { + struct scsi_allocated_memory *next; + char buf[0]; +}; + +struct scsi_data { + int size; + unsigned char *data; +}; + +enum scsi_sense_key { + SCSI_SENSE_NO_SENSE = 0x00, + SCSI_SENSE_RECOVERED_ERROR = 0x01, + SCSI_SENSE_NOT_READY = 0x02, + SCSI_SENSE_MEDIUM_ERROR = 0x03, + SCSI_SENSE_HARDWARE_ERROR = 0x04, + SCSI_SENSE_ILLEGAL_REQUEST = 0x05, + SCSI_SENSE_UNIT_ATTENTION = 0x06, + SCSI_SENSE_DATA_PROTECTION = 0x07, + SCSI_SENSE_BLANK_CHECK = 0x08, + SCSI_SENSE_VENDOR_SPECIFIC = 0x09, + SCSI_SENSE_COPY_ABORTED = 0x0a, + SCSI_SENSE_COMMAND_ABORTED = 0x0b, + SCSI_SENSE_OBSOLETE_ERROR_CODE = 0x0c, + SCSI_SENSE_OVERFLOW_COMMAND = 0x0d, + SCSI_SENSE_MISCOMPARE = 0x0e +}; + +struct scsi_sense { + unsigned char error_type; + enum scsi_sense_key key; + int ascq; + unsigned sense_specific:1; + unsigned ill_param_in_cdb:1; + unsigned bit_pointer_valid:1; + unsigned char bit_pointer; + uint16_t field_pointer; +}; + +enum scsi_residual { + SCSI_RESIDUAL_NO_RESIDUAL = 0, + SCSI_RESIDUAL_UNDERFLOW, + SCSI_RESIDUAL_OVERFLOW +}; + +struct scsi_task { + int status; + int cdb_size; + int xfer_dir; + int expxferlen; + unsigned char cdb[SCSI_CDB_MAX_SIZE]; + enum scsi_residual residual_status; + size_t residual; + struct scsi_sense sense; + struct scsi_data datain; + struct scsi_allocated_memory *mem; + void *ptr; + + uint32_t itt; + uint32_t cmdsn; + uint32_t lun; + + struct scsi_iovector iovector_in; + struct scsi_iovector iovector_out; +}; + +/** libiscsi integration **/ + +static int iscsi_add_lun(iscsi_lun_t *lun, char *iscsi_uri) { + struct iscsi_url *iscsi_url; + struct iscsi_context *iscsi_ctx; + int ret = 0; + + assert(lun); + assert(iscsi_uri); + + iscsi_ctx = iscsi_create_context(VUS_ISCSI_INITIATOR); + if (!iscsi_ctx) { + PERR("Unable to create iSCSI context"); + return -1; + } + + iscsi_url = iscsi_parse_full_url(iscsi_ctx, iscsi_uri); + if (!iscsi_url) { + PERR("Unable to parse iSCSI URL: %s", iscsi_get_error(iscsi_ctx)); + goto fail; + } + + iscsi_set_session_type(iscsi_ctx, ISCSI_SESSION_NORMAL); + iscsi_set_header_digest(iscsi_ctx, ISCSI_HEADER_DIGEST_NONE_CRC32C); + if (iscsi_full_connect_sync(iscsi_ctx, iscsi_url->portal, iscsi_url->lun)) { + PERR("Unable to login to iSCSI portal: %s", iscsi_get_error(iscsi_ctx)); + goto fail; + } + + lun->iscsi_ctx = iscsi_ctx; + lun->iscsi_lun = iscsi_url->lun; + + PDBG("Context %p created for lun 0: %s", iscsi_ctx, iscsi_uri); + +out: + if (iscsi_url) { + iscsi_destroy_url(iscsi_url); + } + return ret; + +fail: + (void)iscsi_destroy_context(iscsi_ctx); + ret = -1; + goto out; +} + +static struct scsi_task *scsi_task_new(int cdb_len, uint8_t *cdb, int dir, + int xfer_len) { + struct scsi_task *task; + + assert(cdb_len > 0); + assert(cdb); + + task = calloc(1, sizeof(struct scsi_task)); + if (!task) { + PERR("Error allocating task: %s", strerror(errno)); + return NULL; + } + + memcpy(task->cdb, cdb, cdb_len); + task->cdb_size = cdb_len; + task->xfer_dir = dir; + task->expxferlen = xfer_len; + + return task; +} + +static int get_cdb_len(uint8_t *cdb) { + assert(cdb); + + switch (cdb[0] >> 5) { + case 0: return 6; + case 1: /* fall through */ + case 2: return 10; + case 4: return 16; + case 5: return 12; + } + PERR("Unable to determine cdb len (0x%02hhX)", cdb[0]>>5); + return -1; +} + +static int handle_cmd_sync(struct iscsi_context *ctx, + VirtIOSCSICmdReq *req, + struct iovec *out, unsigned int out_len, + VirtIOSCSICmdResp *rsp, + struct iovec *in, unsigned int in_len) { + struct scsi_task *task; + uint32_t dir; + uint32_t len; + int cdb_len; + int i; + + assert(ctx); + assert(req); + assert(rsp); + + if (!((!req->lun[1]) && (req->lun[2] == 0x40) && (!req->lun[3]))) { + // Ignore anything different than target=0, lun=0 + PDBG("Ignoring unconnected lun (0x%hhX, 0x%hhX)", + req->lun[1], req->lun[3]); + rsp->status = SCSI_STATUS_CHECK_CONDITION; + memset(rsp->sense, 0, sizeof(rsp->sense)); + rsp->sense_len = 18; + rsp->sense[0] = 0x70; + rsp->sense[2] = SCSI_SENSE_ILLEGAL_REQUEST; + rsp->sense[7] = 10; + rsp->sense[12] = 0x24; + + return 0; + } + + cdb_len = get_cdb_len(req->cdb); + if (cdb_len == -1) { + return -1; + } + + len = 0; + if (!out_len && !in_len) { + dir = SCSI_XFER_NONE; + } else if (out_len) { + dir = SCSI_XFER_TO_DEV; + for (i=0; icdb, dir, len); + if (!task) { + PERR("Unable to create iscsi task"); + return -1; + } + + if (dir == SCSI_XFER_TO_DEV) { + task->iovector_out.iov = (struct scsi_iovec *)out; + task->iovector_out.niov = out_len; + } else if (dir == SCSI_XFER_FROM_DEV) { + task->iovector_in.iov = (struct scsi_iovec *)in; + task->iovector_in.niov = in_len; + } + + PDBG("Sending iscsi cmd (cdb_len=%d, dir=%d, task=%p)", + cdb_len, dir, task); + if (!iscsi_scsi_command_sync(ctx, 0, task, NULL)) { + PERR("Error serving SCSI command"); + free(task); + return -1; + } + + memset(rsp, 0, sizeof(*rsp)); + + rsp->status = task->status; + rsp->resid = task->residual; + + if (task->status == SCSI_STATUS_CHECK_CONDITION) { + rsp->response = VIRTIO_SCSI_S_FAILURE; + rsp->sense_len = task->datain.size - 2; + memcpy(rsp->sense, &task->datain.data[2], rsp->sense_len); + } + + free(task); + + PDBG("Filled in rsp: status=%hhX, resid=%u, response=%hhX, sense_len=%u", + rsp->status, rsp->resid, rsp->response, rsp->sense_len); + + return 0; +} + +/** libvhost-user callbacks **/ + +static vhost_scsi_dev_t *vdev_scsi_find_by_vu(VuDev *vu_dev); + +static void vus_panic_cb(VuDev *vu_dev, const char *buf) { + vhost_scsi_dev_t *vdev_scsi; + + assert(vu_dev); + + vdev_scsi = vdev_scsi_find_by_vu(vu_dev); + + if (buf) { + PERR("vu_panic: %s", buf); + } + + if (vdev_scsi) { + assert(vdev_scsi->loop); + g_main_loop_quit(vdev_scsi->loop); + } +} + +static void vus_add_watch_cb(VuDev *vu_dev, int fd, int vu_evt, vu_watch_cb cb, + void *pvt) { + vhost_scsi_dev_t *vdev_scsi; + gushort conds = 0; + guint id; + + assert(vu_dev); + assert(fd >= 0); + assert(cb); + + vdev_scsi = vdev_scsi_find_by_vu(vu_dev); + if (!vdev_scsi) { + vus_panic_cb(vu_dev, NULL); + return; + } + + id = (guint)(uintptr_t)g_tree_lookup(vdev_scsi->fdmap, + (gpointer)(uintptr_t)fd); + if (id) { + GSource *vus_src = g_main_context_find_source_by_id(NULL, id); + assert(vus_src); + g_source_destroy(vus_src); + (void)g_tree_remove(vdev_scsi->fdmap, (gpointer)(uintptr_t)fd); + } + + if (vu_evt & VU_WATCH_IN) conds |= G_IO_IN; + if (vu_evt & VU_WATCH_OUT) conds |= G_IO_OUT; + if (vu_evt & VU_WATCH_PRI) conds |= G_IO_PRI; + if (vu_evt & VU_WATCH_ERR) conds |= G_IO_ERR; + if (vu_evt & VU_WATCH_HUP) conds |= G_IO_HUP; + + if (vus_gsrc_new(vdev_scsi, fd, conds, cb, NULL, pvt)) { + vus_panic_cb(vu_dev, NULL); + } +} + +static void vus_del_watch_cb(VuDev *vu_dev, int fd) { + vhost_scsi_dev_t *vdev_scsi; + guint id; + + assert(vu_dev); + assert(fd >= 0); + + vdev_scsi = vdev_scsi_find_by_vu(vu_dev); + if (!vdev_scsi) { + vus_panic_cb(vu_dev, NULL); + return; + } + + id = (guint)(uintptr_t)g_tree_lookup(vdev_scsi->fdmap, + (gpointer)(uintptr_t)fd); + if (id) { + GSource *vus_src = g_main_context_find_source_by_id(NULL, id); + assert(vus_src); + g_source_destroy(vus_src); + (void)g_tree_remove(vdev_scsi->fdmap, (gpointer)(uintptr_t)fd); + } +} + +static void vus_proc_ctl(VuDev *vu_dev, int idx) { + /* Control VQ not implemented */ +} + +static void vus_proc_evt(VuDev *vu_dev, int idx) { + /* Event VQ not implemented */ +} + +static void vus_proc_req(VuDev *vu_dev, int idx) { + vhost_scsi_dev_t *vdev_scsi; + VuVirtq *vq; + + assert(vu_dev); + + vdev_scsi = vdev_scsi_find_by_vu(vu_dev); + if (!vdev_scsi) { + vus_panic_cb(vu_dev, NULL); + return; + } + + if ((idx < 0) || (idx >= VHOST_MAX_NR_VIRTQUEUE)) { + PERR("VQ Index out of range: %d", idx); + vus_panic_cb(vu_dev, NULL); + return; + } + + vq = vu_get_queue(vu_dev, idx); + if (!vq) { + PERR("Error fetching VQ (dev=%p, idx=%d)", vu_dev, idx); + vus_panic_cb(vu_dev, NULL); + return; + } + + PDBG("Got kicked on vq[%d]@%p", idx, vq); + + while(1) { + VuVirtqElement *elem; + VirtIOSCSICmdReq *req; + VirtIOSCSICmdResp *rsp; + + elem = vu_queue_pop(vu_dev, vq, sizeof(VuVirtqElement)); + if (!elem) { + PDBG("No more elements pending on vq[%d]@%p", idx, vq); + break; + } + PDBG("Popped elem@%p", elem); + + assert(!((elem->out_num > 1) && (elem->in_num > 1))); + assert((elem->out_num > 0) && (elem->in_num > 0)); + + if (elem->out_sg[0].iov_len < sizeof(VirtIOSCSICmdReq)) { + PERR("Invalid virtio-scsi req header"); + vus_panic_cb(vu_dev, NULL); + break; + } + req = (VirtIOSCSICmdReq *)elem->out_sg[0].iov_base; + + if (elem->in_sg[0].iov_len < sizeof(VirtIOSCSICmdResp)) { + PERR("Invalid virtio-scsi rsp header"); + vus_panic_cb(vu_dev, NULL); + break; + } + rsp = (VirtIOSCSICmdResp *)elem->in_sg[0].iov_base; + + if (handle_cmd_sync(vdev_scsi->luns[0].iscsi_ctx, + req, &elem->out_sg[1], elem->out_num-1, + rsp, &elem->in_sg[1], elem->in_num-1) != 0) { + vus_panic_cb(vu_dev, NULL); + break; + } + + vu_queue_push(vu_dev, vq, elem, 0); + vu_queue_notify(vu_dev, vq); + + free(elem); + } +} + +static void vus_queue_set_started(VuDev *vu_dev, int idx, bool started) { + VuVirtq *vq; + + assert(vu_dev); + + if ((idx < 0) || (idx >= VHOST_MAX_NR_VIRTQUEUE)) { + PERR("VQ Index out of range: %d", idx); + vus_panic_cb(vu_dev, NULL); + return; + } + + vq = vu_get_queue(vu_dev, idx); + + switch(idx) { + case 0: + vu_set_queue_handler(vu_dev, vq, started?vus_proc_ctl:NULL); + break; + case 1: + vu_set_queue_handler(vu_dev, vq, started?vus_proc_evt:NULL); + break; + default: + vu_set_queue_handler(vu_dev, vq, started?vus_proc_req:NULL); + } +} + +static const VuDevIface vus_iface = { + .queue_set_started = vus_queue_set_started, +}; + +static gboolean vus_vhost_cb(gpointer data) { + VuDev *vu_dev = (VuDev *)data; + + assert(vu_dev); + + if (!vu_dispatch(vu_dev) != 0) { + PERR("Error processing vhost message"); + vus_panic_cb(vu_dev, NULL); + return G_SOURCE_REMOVE; + } + + return G_SOURCE_CONTINUE; +} + +/** misc helpers **/ + +static int unix_sock_new(char *unix_fn) { + int sock; + struct sockaddr_un un; + size_t len; + + assert(unix_fn); + + sock = socket(AF_UNIX, SOCK_STREAM, 0); + if (sock <= 0) { + perror("socket"); + return -1; + } + + un.sun_family = AF_UNIX; + (void)snprintf(un.sun_path, sizeof(un.sun_path), "%s", unix_fn); + len = sizeof(un.sun_family) + strlen(un.sun_path); + + (void)unlink(unix_fn); + if (bind(sock, (struct sockaddr *)&un, len) < 0) { + perror("bind"); + goto fail; + } + + if (listen(sock, 1) < 0) { + perror("listen"); + goto fail; + } + + return sock; + +fail: + (void)close(sock); + + return -1; +} + +/** vhost-user-scsi **/ + +static vhost_scsi_dev_t *vdev_scsi_find_by_vu(VuDev *vu_dev) { + int i; + + assert(vu_dev); + + for (i=0; ivu_dev == vu_dev) { + return vhost_scsi_devs[i]; + } + } + + PERR("Unknown VuDev %p", vu_dev); + return NULL; +} + +static void vdev_scsi_deinit(vhost_scsi_dev_t *vdev_scsi) { + if (!vdev_scsi) { + return; + } + + if (vdev_scsi->server_sock >= 0) { + struct sockaddr_storage ss; + socklen_t sslen = sizeof(ss); + + if (getsockname(vdev_scsi->server_sock, (struct sockaddr *)&ss, + &sslen) == 0) { + struct sockaddr_un *su = (struct sockaddr_un *)&ss; + (void)unlink(su->sun_path); + } + + (void)close(vdev_scsi->server_sock); + vdev_scsi->server_sock = -1; + } + + if (vdev_scsi->loop) { + g_main_loop_unref(vdev_scsi->loop); + vdev_scsi->loop = NULL; + } +} + +static vhost_scsi_dev_t *vdev_scsi_new(char *unix_fn) { + vhost_scsi_dev_t *vdev_scsi = NULL; + + assert(unix_fn); + + vdev_scsi = calloc(1, sizeof(vhost_scsi_dev_t)); + if (!vdev_scsi) { + PERR("calloc: %s", strerror(errno)); + return NULL; + } + + vdev_scsi->server_sock = unix_sock_new(unix_fn); + if (vdev_scsi->server_sock < 0) { + goto err; + } + + vdev_scsi->loop = g_main_loop_new(NULL, FALSE); + if (!vdev_scsi->loop) { + PERR("Error creating glib event loop"); + goto err; + } + + vdev_scsi->fdmap = g_tree_new(vus_fdmap_compare); + if (!vdev_scsi->fdmap) { + PERR("Error creating glib tree for fdmap"); + goto err; + } + + return vdev_scsi; + +err: + vdev_scsi_deinit(vdev_scsi); + free(vdev_scsi); + + return NULL; +} + +static int vdev_scsi_add_iscsi_lun(vhost_scsi_dev_t *vdev_scsi, + char *iscsi_uri, uint32_t lun) { + assert(vdev_scsi); + assert(iscsi_uri); + assert(lun < VUS_MAX_LUNS); + + if (vdev_scsi->luns[lun].iscsi_ctx) { + PERR("Lun %d already configured", lun); + return -1; + } + + if (iscsi_add_lun(&vdev_scsi->luns[lun], iscsi_uri) != 0) { + return -1; + } + + return 0; +} + +static int vdev_scsi_run(vhost_scsi_dev_t *vdev_scsi) { + int cli_sock; + int ret = 0; + + assert(vdev_scsi); + assert(vdev_scsi->server_sock >= 0); + assert(vdev_scsi->loop); + + cli_sock = accept(vdev_scsi->server_sock, (void *)0, (void *)0); + if (cli_sock < 0) { + perror("accept"); + return -1; + } + + vu_init(&vdev_scsi->vu_dev, + cli_sock, + vus_panic_cb, + vus_add_watch_cb, + vus_del_watch_cb, + &vus_iface); + + if (vus_gsrc_new(vdev_scsi, cli_sock, G_IO_IN, NULL, vus_vhost_cb, + &vdev_scsi->vu_dev)) { + goto fail; + } + + g_main_loop_run(vdev_scsi->loop); + +out: + vu_deinit(&vdev_scsi->vu_dev); + + return ret; + +fail: + ret = -1; + goto out; +} + +int main(int argc, char **argv) +{ + vhost_scsi_dev_t *vdev_scsi = NULL; + char *unix_fn = NULL; + char *iscsi_uri = NULL; + int opt, err = EXIT_SUCCESS; + + while ((opt = getopt(argc, argv, "u:i:")) != -1) { + switch (opt) { + case 'h': + goto help; + case 'u': + unix_fn = strdup(optarg); + break; + case 'i': + iscsi_uri = strdup(optarg); + break; + default: + goto help; + } + } + if (!unix_fn || !iscsi_uri) { + goto help; + } + + vdev_scsi = vdev_scsi_new(unix_fn); + if (!vdev_scsi) { + goto err; + } + vhost_scsi_devs[0] = vdev_scsi; + + if (vdev_scsi_add_iscsi_lun(vdev_scsi, iscsi_uri, 0) != 0) { + goto err; + } + + if (vdev_scsi_run(vdev_scsi) != 0) { + goto err; + } + +out: + if (vdev_scsi) { + vdev_scsi_deinit(vdev_scsi); + free(vdev_scsi); + } + if (unix_fn) { + free(unix_fn); + } + if (iscsi_uri) { + free(iscsi_uri); + } + + return err; + +err: + err = EXIT_FAILURE; + goto out; + +help: + fprintf(stderr, "Usage: %s [ -u unix_sock_path -i iscsi_uri ] | [ -h ]\n", + argv[0]); + fprintf(stderr, " -u path to unix socket\n"); + fprintf(stderr, " -i iscsi uri for lun 0\n"); + fprintf(stderr, " -h print help and quit\n"); + + goto err; +}