From patchwork Fri May 20 08:37:09 2011 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Sasha Levin X-Patchwork-Id: 802762 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by demeter2.kernel.org (8.14.4/8.14.3) with ESMTP id p4K8bsAv024026 for ; Fri, 20 May 2011 08:37:54 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934889Ab1ETIhu (ORCPT ); Fri, 20 May 2011 04:37:50 -0400 Received: from mail-wy0-f174.google.com ([74.125.82.174]:47718 "EHLO mail-wy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S934846Ab1ETIhp (ORCPT ); Fri, 20 May 2011 04:37:45 -0400 Received: by wya21 with SMTP id 21so2545989wya.19 for ; Fri, 20 May 2011 01:37:44 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:from:to:cc:subject:date:message-id:x-mailer :in-reply-to:references; bh=Kc+d6zH4JuNSRuMtVv2DEkF9ive/LM0j7k4mwkR0VWs=; b=cHXwSJJ31qCrUvokreyqPbgINFhWU+9V6lKGPjNPyZjyBCt9+qUWtv8T/4opu/fqfb J+oDFPUkl1yGdfGIefo8sczqqF6B0DeGLvaX2MZd2Lz5rXuXuEL3GfOvSc62r/eEnwDO bGrU0GpCZb87vOzdKDWjGdhAUpnCUw+grYCYw= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=from:to:cc:subject:date:message-id:x-mailer:in-reply-to:references; b=CzstcOxvDj8uz87FQ0BKasWgxAJdGjzNX54FpWqjOKk4ekdHQcvsum3UXRfWIu8M3M 7tP6wEtPSl9l9ebopoo67a6tPr051ZhRaGw74MWsQfEyvYgEsWRaP/tNhQOLwe3hBRDM Uj5x3xbAecYOBlBMeWZEJRnzS8GmhsSfjwzFA= Received: by 10.227.195.4 with SMTP id ea4mr3530198wbb.76.1305880663574; Fri, 20 May 2011 01:37:43 -0700 (PDT) Received: from localhost.localdomain (bzq-79-179-206-38.red.bezeqint.net [79.179.206.38]) by mx.google.com with ESMTPS id o6sm2122519wbo.20.2011.05.20.01.37.40 (version=TLSv1/SSLv3 cipher=OTHER); Fri, 20 May 2011 01:37:43 -0700 (PDT) From: Sasha Levin To: penberg@kernel.org Cc: mingo@elte.hu, asias.hejun@gmail.com, gorcunov@gmail.com, prasadjoshi124@gmail.com, kvm@vger.kernel.org, Sasha Levin Subject: [PATCH 2/2 V3] kvm tools: Add virtio-9p Date: Fri, 20 May 2011 11:37:09 +0300 Message-Id: <1305880629-10571-2-git-send-email-levinsasha928@gmail.com> X-Mailer: git-send-email 1.7.5.rc3 In-Reply-To: <1305880629-10571-1-git-send-email-levinsasha928@gmail.com> References: <1305880629-10571-1-git-send-email-levinsasha928@gmail.com> Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org X-Greylist: IP, sender and recipient auto-whitelisted, not delayed by milter-greylist-4.2.6 (demeter2.kernel.org [140.211.167.43]); Fri, 20 May 2011 08:37:54 +0000 (UTC) Overview: 9p allows for simple RPC based resource sharing over different transports (in our case, virtio). This is the implementation of (most of) the original 9p2000 protocol, without the .u or the .l extensions. How to use: 1. Make sure kernel is compiled with: CONFIG_NET_9P=y CONFIG_NET_9P_VIRTIO=y CONFIG_NET_9P_DEBUG=y (At least until code is stable) CONFIG_9P_FS=y 2. Start KVM with '--virtio-9p '. What happens now is that a virtio transport with the name 'kvm_9p' is created. The server side of the transport maps dirname to the root of the file system. 3. Within the guest, mount the fs: mount -t 9p -otrans=virtio kvm_9p -oversion=9p2000 This will mount the 9p server to local_dir. Signed-off-by: Sasha Levin --- tools/kvm/Makefile | 1 + tools/kvm/include/kvm/ioport.h | 2 + tools/kvm/include/kvm/virtio-9p.h | 8 + tools/kvm/include/kvm/virtio-pci-dev.h | 1 + tools/kvm/kvm-run.c | 13 + tools/kvm/virtio/9p.c | 667 ++++++++++++++++++++++++++++++++ 6 files changed, 692 insertions(+), 0 deletions(-) create mode 100644 tools/kvm/include/kvm/virtio-9p.h create mode 100644 tools/kvm/virtio/9p.c diff --git a/tools/kvm/Makefile b/tools/kvm/Makefile index 30f0f61..8a10647 100644 --- a/tools/kvm/Makefile +++ b/tools/kvm/Makefile @@ -47,6 +47,7 @@ OBJS += threadpool.o OBJS += irq.o OBJS += ../../lib/rbtree.o OBJS += util/rbtree-interval.o +OBJS += virtio/9p.o FLAGS_BFD=$(CFLAGS) -lbfd has_bfd := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD)) diff --git a/tools/kvm/include/kvm/ioport.h b/tools/kvm/include/kvm/ioport.h index b9bbc3d..218530c 100644 --- a/tools/kvm/include/kvm/ioport.h +++ b/tools/kvm/include/kvm/ioport.h @@ -7,6 +7,8 @@ /* some ports we reserve for own use */ #define IOPORT_DBG 0xe0 +#define IOPORT_VIRTIO_P9 0xb200 /* Virtio 9P device */ +#define IOPORT_VIRTIO_P9_SIZE 256 #define IOPORT_VIRTIO_BLK 0xc200 /* Virtio block device */ #define IOPORT_VIRTIO_BLK_SIZE 0x200 #define IOPORT_VIRTIO_CONSOLE 0xd200 /* Virtio console device */ diff --git a/tools/kvm/include/kvm/virtio-9p.h b/tools/kvm/include/kvm/virtio-9p.h new file mode 100644 index 0000000..9052830 --- /dev/null +++ b/tools/kvm/include/kvm/virtio-9p.h @@ -0,0 +1,8 @@ +#ifndef KVM__VIRTIO_9P_H +#define KVM__VIRTIO_9P_H + +struct kvm; + +void virtio_9p__init(struct kvm *kvm, const char *root); + +#endif diff --git a/tools/kvm/include/kvm/virtio-pci-dev.h b/tools/kvm/include/kvm/virtio-pci-dev.h index fa8328d..1b7862e 100644 --- a/tools/kvm/include/kvm/virtio-pci-dev.h +++ b/tools/kvm/include/kvm/virtio-pci-dev.h @@ -12,6 +12,7 @@ #define PCI_DEVICE_ID_VIRTIO_BLK 0x1001 #define PCI_DEVICE_ID_VIRTIO_CONSOLE 0x1003 #define PCI_DEVICE_ID_VIRTIO_RNG 0x1004 +#define PCI_DEVICE_ID_VIRTIO_P9 0x1009 #define PCI_VENDOR_ID_REDHAT_QUMRANET 0x1af4 #define PCI_SUBSYSTEM_VENDOR_ID_REDHAT_QUMRANET 0x1af4 diff --git a/tools/kvm/kvm-run.c b/tools/kvm/kvm-run.c index 63181bf..aa7ee0a 100644 --- a/tools/kvm/kvm-run.c +++ b/tools/kvm/kvm-run.c @@ -27,6 +27,7 @@ #include #include #include +#include /* header files for gitish interface */ #include @@ -62,6 +63,7 @@ static const char *network; static const char *host_ip_addr; static const char *guest_mac; static const char *script; +static const char *virtio_9p_dir; static bool single_step; static bool readonly_image[MAX_DISK_IMAGES]; static bool virtio_rng; @@ -107,6 +109,8 @@ static const struct option options[] = { OPT_BOOLEAN('\0', "rng", &virtio_rng, "Enable virtio Random Number Generator"), OPT_STRING('\0', "kvm-dev", &kvm_dev, "kvm-dev", "KVM device file"), + OPT_STRING('\0', "virtio-9p", &virtio_9p_dir, "root dir", + "Enable 9p over virtio"), OPT_GROUP("Kernel options:"), OPT_STRING('k', "kernel", &kernel_filename, "kernel", @@ -473,6 +477,15 @@ int kvm_cmd_run(int argc, const char **argv, const char *prefix) if (!script) script = DEFAULT_SCRIPT; + if (virtio_9p_dir) { + char tmp[PATH_MAX]; + + if (realpath(virtio_9p_dir, tmp)) + virtio_9p__init(kvm, tmp); + else + die("Failed resolving 9p path"); + } + symbol__init(vmlinux_filename); term_init(); diff --git a/tools/kvm/virtio/9p.c b/tools/kvm/virtio/9p.c new file mode 100644 index 0000000..56ecd8e --- /dev/null +++ b/tools/kvm/virtio/9p.c @@ -0,0 +1,667 @@ +#include "kvm/virtio-9p.h" +#include "kvm/virtio-pci-dev.h" +#include "kvm/virtio.h" +#include "kvm/ioport.h" +#include "kvm/mutex.h" +#include "kvm/util.h" +#include "kvm/kvm.h" +#include "kvm/pci.h" +#include "kvm/threadpool.h" +#include "kvm/irq.h" + +#include +#include +#include + +#include +#include +#include +#include +#include + +#define NUM_VIRT_QUEUES 1 +#define VIRTIO_P9_QUEUE_SIZE 128 +#define VIRTIO_P9_TAG "kvm_9p" +#define VIRTIO_P9_HDR_LEN (sizeof(u32)+sizeof(u8)+sizeof(u16)) +#define VIRTIO_P9_MAX_FID 128 +#define VIRTIO_P9_VERSION "9P2000" + +struct p9_msg { + u32 size; + u8 cmd; + u16 tag; + u8 msg[0]; +} __attribute__((packed)); + +struct p9_fid { + u32 fid; + u8 is_dir; + char abs_path[PATH_MAX]; + char *path; + DIR *dir; + int fd; +}; + +static struct pci_device_header virtio_p9_pci_device = { + .vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET, + .device_id = PCI_DEVICE_ID_VIRTIO_P9, + .header_type = PCI_HEADER_TYPE_NORMAL, + .revision_id = 0, + .class = 0x010000, + .subsys_vendor_id = PCI_SUBSYSTEM_VENDOR_ID_REDHAT_QUMRANET, + .subsys_id = VIRTIO_ID_9P, + .bar[0] = IOPORT_VIRTIO_P9 | PCI_BASE_ADDRESS_SPACE_IO, +}; + +struct p9_dev { + u8 status; + u8 isr; + u16 config_vector; + u32 features; + struct virtio_9p_config *config; + + /* virtio queue */ + u16 queue_selector; + struct virt_queue vqs[NUM_VIRT_QUEUES]; + void *jobs[NUM_VIRT_QUEUES]; + + struct p9_fid fids[VIRTIO_P9_MAX_FID]; + char root_dir[PATH_MAX]; +}; + +static struct p9_dev p9dev; + +/* Warning: Immediately use value returned from this function */ +static const char *rel_to_abs(const char *path, char *abs_path) +{ + sprintf(abs_path, "%s/%s", p9dev.root_dir, path); + + return abs_path; +} + +static bool virtio_p9_dev_in(void *data, unsigned long offset, int size, u32 count) +{ + u8 *config_space = (u8 *) p9dev.config; + + if (size != 1 || count != 1) + return false; + + ioport__write8(data, config_space[offset - VIRTIO_MSI_CONFIG_VECTOR]); + + return true; +} + +static bool virtio_p9_pci_io_in(struct kvm *kvm, u16 port, void *data, int size, u32 count) +{ + unsigned long offset; + bool ret = true; + + offset = port - IOPORT_VIRTIO_P9; + + switch (offset) { + case VIRTIO_PCI_HOST_FEATURES: + ioport__write32(data, p9dev.features); + ret = true; + break; + case VIRTIO_PCI_GUEST_FEATURES: + case VIRTIO_PCI_QUEUE_SEL: + case VIRTIO_PCI_QUEUE_NOTIFY: + ret = false; + break; + case VIRTIO_PCI_QUEUE_PFN: + ioport__write32(data, p9dev.vqs[p9dev.queue_selector].pfn); + break; + case VIRTIO_PCI_QUEUE_NUM: + ioport__write16(data, VIRTIO_P9_QUEUE_SIZE); + break; + case VIRTIO_PCI_STATUS: + ioport__write8(data, p9dev.status); + break; + case VIRTIO_PCI_ISR: + ioport__write8(data, p9dev.isr); + kvm__irq_line(kvm, virtio_p9_pci_device.irq_line, VIRTIO_IRQ_LOW); + p9dev.isr = VIRTIO_IRQ_LOW; + break; + default: + ret = virtio_p9_dev_in(data, offset, size, count); + break; + }; + + return ret; +} + +static int omode2uflags(u8 mode) +{ + int ret = 0; + + /* Basic open modes are same as uflags */ + ret = mode & 3; + + /* Everything else is different */ + if (mode & P9_OTRUNC) + ret |= O_TRUNC; + + if (mode & P9_OAPPEND) + ret |= O_APPEND; + + if (mode & P9_OEXCL) + ret |= O_EXCL; + + return ret; +} + +static void st2qid(struct stat *st, struct p9_qid *qid) +{ + *qid = (struct p9_qid) { + .path = st->st_ino, + .version = st->st_mtime, + }; + + if (S_ISDIR(st->st_mode)) + qid->type |= P9_QTDIR; +} + +static void close_fid(u32 fid) +{ + if (p9dev.fids[fid].fd > 0) { + close(p9dev.fids[fid].fd); + p9dev.fids[fid].fd = -1; + } + if (p9dev.fids[fid].dir) { + closedir(p9dev.fids[fid].dir); + p9dev.fids[fid].dir = NULL; + } +} + +static void set_p9msg_hdr(struct p9_msg *msg, u32 size, u8 cmd, u16 tag) +{ + *msg = (struct p9_msg) { + .size = size, + .tag = tag, + .cmd = cmd, + }; +} + +static bool virtio_p9_version(struct p9_msg *msg, u32 len, struct iovec *iov, u32 *outlen) +{ + struct p9_msg *outmsg = iov[0].iov_base; + struct p9_rversion *rversion = (struct p9_rversion *)outmsg->msg; + + rversion->msize = 4096; + rversion->version.len = strlen(VIRTIO_P9_VERSION); + memcpy(&rversion->version.str, VIRTIO_P9_VERSION, rversion->version.len); + + *outlen = VIRTIO_P9_HDR_LEN + rversion->version.len + sizeof(u16) + sizeof(u32); + set_p9msg_hdr(outmsg, *outlen, P9_RVERSION, msg->tag); + + return true; +} + +static bool virtio_p9_clunk(struct p9_msg *msg, u32 len, struct iovec *iov, u32 *outlen) +{ + struct p9_msg *outmsg = iov[0].iov_base; + struct p9_tclunk *tclunk = (struct p9_tclunk *)msg->msg; + + close_fid(tclunk->fid); + + *outlen = VIRTIO_P9_HDR_LEN; + set_p9msg_hdr(outmsg, *outlen, P9_RCLUNK, msg->tag); + + return true; +} + +static bool virtio_p9_open(struct p9_msg *msg, u32 len, struct iovec *iov, u32 *outlen) +{ + struct p9_msg *outmsg = iov[0].iov_base; + struct p9_topen *topen = (struct p9_topen *)msg->msg; + struct p9_ropen *ropen = (struct p9_ropen *)outmsg->msg; + struct p9_fid *new_fid = &p9dev.fids[topen->fid]; + struct stat st; + + if (stat(new_fid->abs_path, &st) < 0) + return false; + + st2qid(&st, &ropen->qid); + ropen->iounit = 0; + + if (new_fid->is_dir) + new_fid->dir = opendir(new_fid->abs_path); + else + new_fid->fd = open(new_fid->abs_path, omode2uflags(topen->mode)); + + *outlen = VIRTIO_P9_HDR_LEN + sizeof(*ropen); + set_p9msg_hdr(outmsg, *outlen, P9_ROPEN, msg->tag); + + return true; +} + +static bool virtio_p9_create(struct p9_msg *msg, u32 len, struct iovec *iov, u32 *outlen) +{ + struct p9_msg *outmsg = iov[0].iov_base; + struct p9_tcreate *tcreate = (struct p9_tcreate *)msg->msg; + struct p9_rcreate *rcreate = (struct p9_rcreate *)outmsg->msg; + struct p9_fid *fid = &p9dev.fids[tcreate->fid]; + struct stat st; + u8 mode; + u32 perm; + + rcreate->iounit = 0; + + /* Get last byte of the variable length struct */ + mode = *((u8 *)msg + msg->size - 1); + perm = *(u32 *)((u8 *)msg + msg->size - 5); + + sprintf(fid->path, "%s/%.*s", fid->path, tcreate->name.len, (char *)&tcreate->name.str); + + close_fid(tcreate->fid); + + if (perm & P9_DMDIR) { + mkdir(fid->abs_path, perm & 0xFFFF); + fid->dir = opendir(fid->abs_path); + fid->is_dir = 1; + } else { + fid->fd = open(fid->abs_path, omode2uflags(mode) | O_CREAT, 0777); + } + + if (stat(fid->abs_path, &st) < 0) + return false; + + st2qid(&st, &rcreate->qid); + + *outlen = VIRTIO_P9_HDR_LEN + sizeof(*rcreate); + set_p9msg_hdr(outmsg, *outlen, P9_RCREATE, msg->tag); + + return true; +} + +static bool virtio_p9_walk(struct p9_msg *msg, u32 len, struct iovec *iov, u32 *outlen) +{ + struct p9_msg *outmsg = iov[0].iov_base; + struct p9_twalk *twalk = (struct p9_twalk *)msg->msg; + struct p9_rwalk *rwalk = (struct p9_rwalk *)outmsg->msg; + struct p9_str *str = twalk->wnames; + struct p9_fid *new_fid = &p9dev.fids[twalk->newfid]; + u8 i; + + rwalk->nwqid = 0; + if (twalk->nwname) { + struct p9_fid *fid = &p9dev.fids[twalk->fid]; + + for (i = 0; i < twalk->nwname; i++) { + char tmp[PATH_MAX] = {0}; + char full_path[PATH_MAX]; + struct stat st; + + /* Format the new path we're 'walk'ing into */ + sprintf(tmp, "%s/%.*s", fid->path, str->len, (char *)&str->str); + + if (stat(rel_to_abs(tmp, full_path), &st) < 0) + break; + + st2qid(&st, &rwalk->wqids[i]); + new_fid->is_dir = S_ISDIR(st.st_mode); + strcpy(new_fid->path, tmp); + new_fid->fid = twalk->newfid; + rwalk->nwqid++; + } + } else { + new_fid->is_dir = p9dev.fids[twalk->fid].is_dir; + strcpy(new_fid->path, p9dev.fids[twalk->fid].path); + new_fid->fid = twalk->newfid; + } + + *outlen = VIRTIO_P9_HDR_LEN + sizeof(u16) + sizeof(struct p9_qid) * rwalk->nwqid; + set_p9msg_hdr(outmsg, *outlen, P9_RWALK, msg->tag); + + return true; +} + +static bool virtio_p9_attach(struct p9_msg *msg, u32 len, struct iovec *iov, u32 *outlen) +{ + struct p9_msg *outmsg = iov[0].iov_base; + struct p9_rattach *rattach = (struct p9_rattach *)outmsg->msg; + struct p9_tattach *tattach = (struct p9_tattach *)msg->msg; + struct stat st; + struct p9_fid *fid; + u32 i; + + /* Reset everything */ + for (i = 0; i < VIRTIO_P9_MAX_FID; i++) + p9dev.fids[i].fid = P9_NOFID; + + if (stat(p9dev.root_dir, &st) < 0) + return false; + + st2qid(&st, &rattach->qid); + + fid = &p9dev.fids[tattach->fid]; + fid->fid = tattach->fid; + fid->is_dir = 1; + strcpy(fid->path, "/"); + + *outlen = VIRTIO_P9_HDR_LEN + sizeof(*rattach); + set_p9msg_hdr(outmsg, *outlen, P9_RATTACH, msg->tag); + + return true; +} + +static u32 virtio_p9_fill_stat(const char *name, struct stat *st, struct p9_rstat *rstat) +{ + struct p9_str *str; + + rstat->stat.type = 0; + rstat->stat.dev = 0; + st2qid(st, &rstat->stat.qid); + rstat->stat.mode = st->st_mode; + rstat->stat.length = st->st_size; + if (S_ISDIR(st->st_mode)) { + rstat->stat.length = 0; + rstat->stat.mode |= P9_DMDIR; + } + + rstat->stat.atime = st->st_atime; + rstat->stat.mtime = st->st_mtime; + + str = (struct p9_str *)&rstat->stat.name; + str->len = strlen(name); + memcpy(&str->str, name, str->len); + str = (void *)str + str->len + sizeof(u16); + + /* TODO: Pass usernames to the client */ + str->len = 0; + str = (void *)str + sizeof(u16); + str->len = 0; + str = (void *)str + sizeof(u16); + str->len = 0; + str = (void *)str + sizeof(u16); + + /* We subtract a u16 here because rstat->size doesn't include rstat->size itself */ + rstat->stat.size = (void *)str - (void *)&rstat->stat - sizeof(u16); + + return rstat->stat.size + sizeof(u16); +} + +static bool virtio_p9_read(struct p9_msg *msg, u32 len, struct iovec *iov, int iovcnt, u32 *outlen) +{ + struct p9_msg *outmsg = iov[0].iov_base; + struct p9_tread *tread = (struct p9_tread *)msg->msg; + struct p9_rread *rread = (struct p9_rread *)outmsg->msg; + struct p9_rstat *rstat = (struct p9_rstat *)iov[1].iov_base; + struct p9_fid *fid = &p9dev.fids[tread->fid]; + struct stat st; + + rread->count = 0; + + if (fid->is_dir) { + /* If reading a dir, fill the buffer with p9_stat entries */ + struct dirent *cur = readdir(fid->dir); + char full_path[PATH_MAX]; + + while (cur) { + u32 read; + + stat(rel_to_abs(cur->d_name, full_path), &st); + read = virtio_p9_fill_stat(cur->d_name, &st, rstat); + rread->count += read; + rstat = (void *)rstat + read; + cur = readdir(fid->dir); + } + } else { + iov[0].iov_base += VIRTIO_P9_HDR_LEN + sizeof(u32); + iov[0].iov_len -= VIRTIO_P9_HDR_LEN + sizeof(u32); + rread->count = preadv(fid->fd, iov, iovcnt, tread->offset); + if (rread->count > tread->count) + rread->count = tread->count; + } + + *outlen = VIRTIO_P9_HDR_LEN + sizeof(u32) + rread->count; + set_p9msg_hdr(outmsg, *outlen, P9_RREAD, msg->tag); + + return true; +} + +static bool virtio_p9_stat(struct p9_msg *msg, u32 len, struct iovec *iov, u32 *outlen) +{ + struct p9_msg *outmsg = iov[0].iov_base; + struct p9_tstat *tstat = (struct p9_tstat *)msg->msg; + struct p9_rstat *rstat = (struct p9_rstat *)(outmsg->msg + sizeof(u16)); + struct stat st; + struct p9_fid *fid = &p9dev.fids[tstat->fid]; + u32 ret; + + if (stat(fid->abs_path, &st) < 0) + return false; + + ret = virtio_p9_fill_stat(fid->path, &st, rstat); + + *outlen = VIRTIO_P9_HDR_LEN + ret + sizeof(u16) * 2; + set_p9msg_hdr(outmsg, *outlen, P9_RSTAT, msg->tag); + return true; +} + +static bool virtio_p9_wstat(struct p9_msg *msg, u32 len, struct iovec *iov, u32 *outlen) +{ + struct p9_msg *outmsg = iov[0].iov_base; + struct p9_twstat *twstat = (struct p9_twstat *)msg->msg; + struct p9_str *str; + struct p9_fid *fid = &p9dev.fids[twstat->fid]; + int res; + + if (twstat->stat.length != -1UL) + res = ftruncate(fid->fd, twstat->stat.length); + + if (twstat->stat.mode != -1U) + chmod(fid->abs_path, twstat->stat.mode & 0xFFFF); + + str = (void *)&twstat->stat.name + sizeof(u16); + if (str->len > 0) { + char new_name[PATH_MAX] = {0}; + char full_path[PATH_MAX]; + char *last_dir = strrchr(fid->path, '/'); + + /* We need to get the full file name out of twstat->name */ + if (last_dir) + strncpy(new_name, fid->path, last_dir - fid->path + 1); + + memcpy(new_name + strlen(new_name), &str->str, str->len); + + /* fid is reused for the new file */ + rename(fid->abs_path, rel_to_abs(new_name, full_path)); + sprintf(fid->path, "%s", new_name); + } + + *outlen = VIRTIO_P9_HDR_LEN; + set_p9msg_hdr(outmsg, *outlen, P9_RWSTAT, msg->tag); + return true; +} + +static bool virtio_p9_remove(struct p9_msg *msg, u32 len, struct iovec *iov, u32 *outlen) +{ + struct p9_msg *outmsg = iov[0].iov_base; + struct p9_tremove *tremove = (struct p9_tremove *)msg->msg; + struct p9_fid *fid = &p9dev.fids[tremove->fid]; + + close_fid(tremove->fid); + if (fid->is_dir) + rmdir(fid->abs_path); + else + unlink(fid->abs_path); + + *outlen = VIRTIO_P9_HDR_LEN; + set_p9msg_hdr(outmsg, *outlen, P9_RREMOVE, msg->tag); + return true; +} + +static bool virtio_p9_write(struct p9_msg *msg, u32 len, struct iovec *iov, int iovcnt, u32 *outlen) +{ + struct p9_msg *outmsg; + struct p9_rwrite *rwrite; + struct p9_twrite *twrite = (struct p9_twrite *)msg->msg; + struct p9_fid *fid = &p9dev.fids[twrite->fid]; + + if (iovcnt == 1) { + outmsg = iov[0].iov_base; + rwrite = (struct p9_rwrite *)outmsg->msg; + rwrite->count = pwrite(fid->fd, &twrite->data, twrite->count, twrite->offset); + } else { + outmsg = iov[2].iov_base; + rwrite = (struct p9_rwrite *)outmsg->msg; + rwrite->count = pwrite(fid->fd, iov[1].iov_base, twrite->count, twrite->offset); + } + + *outlen = VIRTIO_P9_HDR_LEN + sizeof(u32); + set_p9msg_hdr(outmsg, *outlen, P9_RWRITE, msg->tag); + + return true; +} + +static bool virtio_p9_do_io_request(struct kvm *kvm, struct virt_queue *queue) +{ + struct iovec iov[VIRTIO_P9_QUEUE_SIZE]; + u16 out, in, head; + struct p9_msg *msg; + u32 len = 0; + + head = virt_queue__get_iov(queue, iov, &out, &in, kvm); + msg = iov[0].iov_base; + + switch (msg->cmd) { + case P9_TVERSION: + virtio_p9_version(msg, iov[0].iov_len, iov+1, &len); + break; + case P9_TATTACH: + virtio_p9_attach(msg, iov[0].iov_len, iov+1, &len); + break; + case P9_TSTAT: + virtio_p9_stat(msg, iov[0].iov_len, iov+1, &len); + break; + case P9_TCLUNK: + virtio_p9_clunk(msg, iov[0].iov_len, iov+1, &len); + break; + case P9_TWALK: + virtio_p9_walk(msg, iov[0].iov_len, iov+1, &len); + break; + case P9_TOPEN: + virtio_p9_open(msg, iov[0].iov_len, iov+1, &len); + break; + case P9_TREAD: + virtio_p9_read(msg, iov[0].iov_len, iov+1, in, &len); + break; + case P9_TCREATE: + virtio_p9_create(msg, iov[0].iov_len, iov+1, &len); + break; + case P9_TWSTAT: + virtio_p9_wstat(msg, iov[0].iov_len, iov+1, &len); + break; + case P9_TREMOVE: + virtio_p9_remove(msg, iov[0].iov_len, iov+1, &len); + break; + case P9_TWRITE: + virtio_p9_write(msg, iov[0].iov_len, iov+1, out, &len); + break; + default: + printf("Unsupported P9 message type: %u\n", msg->cmd); + break; + } + virt_queue__set_used_elem(queue, head, len); + + return true; +} + +static void virtio_p9_do_io(struct kvm *kvm, void *param) +{ + struct virt_queue *vq = param; + + while (virt_queue__available(vq)) { + virtio_p9_do_io_request(kvm, vq); + virt_queue__trigger_irq(vq, virtio_p9_pci_device.irq_line, &p9dev.isr, kvm); + } +} + +static bool virtio_p9_pci_io_out(struct kvm *kvm, u16 port, void *data, int size, u32 count) +{ + unsigned long offset; + bool ret = true; + + offset = port - IOPORT_VIRTIO_P9; + + switch (offset) { + case VIRTIO_MSI_QUEUE_VECTOR: + case VIRTIO_PCI_GUEST_FEATURES: + break; + case VIRTIO_PCI_QUEUE_PFN: { + struct virt_queue *queue; + void *p; + + queue = &p9dev.vqs[p9dev.queue_selector]; + queue->pfn = ioport__read32(data); + p = guest_pfn_to_host(kvm, queue->pfn); + + vring_init(&queue->vring, VIRTIO_P9_QUEUE_SIZE, p, VIRTIO_PCI_VRING_ALIGN); + + p9dev.jobs[p9dev.queue_selector] = thread_pool__add_job(kvm, virtio_p9_do_io, queue); + + break; + } + case VIRTIO_PCI_QUEUE_SEL: + p9dev.queue_selector = ioport__read16(data); + break; + case VIRTIO_PCI_QUEUE_NOTIFY: { + u16 queue_index; + queue_index = ioport__read16(data); + thread_pool__do_job(p9dev.jobs[queue_index]); + break; + } + case VIRTIO_PCI_STATUS: + p9dev.status = ioport__read8(data); + break; + case VIRTIO_MSI_CONFIG_VECTOR: + p9dev.config_vector = VIRTIO_MSI_NO_VECTOR; + break; + default: + ret = false; + break; + }; + + return ret; +} + +static struct ioport_operations virtio_p9_io_ops = { + .io_in = virtio_p9_pci_io_in, + .io_out = virtio_p9_pci_io_out, +}; + +void virtio_9p__init(struct kvm *kvm, const char *root) +{ + u8 pin, line, dev; + u32 i, root_len; + + p9dev.config = calloc(1, sizeof(*p9dev.config) + sizeof(VIRTIO_P9_TAG)); + if (p9dev.config == NULL) + return; + + strcpy(p9dev.root_dir, root); + root_len = strlen(root); + + /* + * We prefix the full path in all fids, This allows us to get the + * absolute path of an fid without playing with strings. + */ + for (i = 0; i < VIRTIO_P9_MAX_FID; i++) { + strcpy(p9dev.fids[i].abs_path, root); + p9dev.fids[i].path = p9dev.fids[i].abs_path + root_len; + } + + p9dev.config->tag_len = strlen(VIRTIO_P9_TAG); + memcpy(p9dev.config->tag, VIRTIO_P9_TAG, strlen(VIRTIO_P9_TAG)); + p9dev.features |= 1 << VIRTIO_9P_MOUNT_TAG; + + if (irq__register_device(VIRTIO_ID_9P, &dev, &pin, &line) < 0) + return; + + virtio_p9_pci_device.irq_pin = pin; + virtio_p9_pci_device.irq_line = line; + pci__register(&virtio_p9_pci_device, dev); + + ioport__register(IOPORT_VIRTIO_P9, &virtio_p9_io_ops, IOPORT_VIRTIO_P9_SIZE); +}