From d5986c804f05070a07dfe702f7c66357daaa1ab6 Mon Sep 17 00:00:00 2001

From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>

Date: Mon, 27 Jan 2020 19:01:20 +0100

Subject: [PATCH 049/116] virtiofsd: Pass write iov's all the way through

MIME-Version: 1.0

Content-Type: text/plain; charset=UTF-8

Content-Transfer-Encoding: 8bit

RH-Author: Dr. David Alan Gilbert <dgilbert@redhat.com>

Message-id: <20200127190227.40942-46-dgilbert@redhat.com>

Patchwork-id: 93497

O-Subject: [RHEL-AV-8.2 qemu-kvm PATCH 045/112] virtiofsd: Pass write iov's all the way through

Bugzilla: 1694164

RH-Acked-by: Philippe Mathieu-Daudé <philmd@redhat.com>

RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>

RH-Acked-by: Sergio Lopez Pascual <slp@redhat.com>

From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>

Pass the write iov pointing to guest RAM all the way through rather

than copying the data.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

Reviewed-by: Xiao Yang <yangx.jy@cn.fujitsu.com>

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

(cherry picked from commit e17f7a580e2c599330ad3a6946be615ca2fe97d9)

Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>

---

 tools/virtiofsd/fuse_virtio.c | 79 +++++++++++++++++++++++++++++++++++++++----

 1 file changed, 73 insertions(+), 6 deletions(-)

diff --git a/tools/virtiofsd/fuse_virtio.c b/tools/virtiofsd/fuse_virtio.c

index fd588a4..872968f 100644

--- a/tools/virtiofsd/fuse_virtio.c

+++ b/tools/virtiofsd/fuse_virtio.c

@@ -454,6 +454,10 @@ static void *fv_queue_thread(void *opaque)

                  __func__, qi->qidx, (size_t)evalue, in_bytes, out_bytes);

         while (1) {

+            bool allocated_bufv = false;

+            struct fuse_bufvec bufv;

+            struct fuse_bufvec *pbufv;

+

             /*

              * An element contains one request and the space to send our

              * response They're spread over multiple descriptors in a

@@ -495,14 +499,76 @@ static void *fv_queue_thread(void *opaque)

                          __func__, elem->index);

                 assert(0); /* TODO */

             }

-            copy_from_iov(&fbuf, out_num, out_sg);

-            fbuf.size = out_len;

+            /* Copy just the first element and look at it */

+            copy_from_iov(&fbuf, 1, out_sg);

+

+            if (out_num > 2 &&

+                out_sg[0].iov_len == sizeof(struct fuse_in_header) &&

+                ((struct fuse_in_header *)fbuf.mem)->opcode == FUSE_WRITE &&

+                out_sg[1].iov_len == sizeof(struct fuse_write_in)) {

+                /*

+                 * For a write we don't actually need to copy the

+                 * data, we can just do it straight out of guest memory

+                 * but we must still copy the headers in case the guest

+                 * was nasty and changed them while we were using them.

+                 */

+                fuse_log(FUSE_LOG_DEBUG, "%s: Write special case\n", __func__);

+

+                /* copy the fuse_write_in header after the fuse_in_header */

+                fbuf.mem += out_sg->iov_len;

+                copy_from_iov(&fbuf, 1, out_sg + 1);

+                fbuf.mem -= out_sg->iov_len;

+                fbuf.size = out_sg[0].iov_len + out_sg[1].iov_len;

+

+                /* Allocate the bufv, with space for the rest of the iov */

+                allocated_bufv = true;

+                pbufv = malloc(sizeof(struct fuse_bufvec) +

+                               sizeof(struct fuse_buf) * (out_num - 2));

+                if (!pbufv) {

+                    vu_queue_unpop(dev, q, elem, 0);

+                    free(elem);

+                    fuse_log(FUSE_LOG_ERR, "%s: pbufv malloc failed\n",

+                             __func__);

+                    goto out;

+                }

+

+                pbufv->count = 1;

+                pbufv->buf[0] = fbuf;

+

+                size_t iovindex, pbufvindex;

+                iovindex = 2; /* 2 headers, separate iovs */

+                pbufvindex = 1; /* 2 headers, 1 fusebuf */

+

+                for (; iovindex < out_num; iovindex++, pbufvindex++) {

+                    pbufv->count++;

+                    pbufv->buf[pbufvindex].pos = ~0; /* Dummy */

+                    pbufv->buf[pbufvindex].flags = 0;

+                    pbufv->buf[pbufvindex].mem = out_sg[iovindex].iov_base;

+                    pbufv->buf[pbufvindex].size = out_sg[iovindex].iov_len;

+                }

+            } else {

+                /* Normal (non fast write) path */

+

+                /* Copy the rest of the buffer */

+                fbuf.mem += out_sg->iov_len;

+                copy_from_iov(&fbuf, out_num - 1, out_sg + 1);

+                fbuf.mem -= out_sg->iov_len;

+                fbuf.size = out_len;

-            /* TODO! Endianness of header */

+                /* TODO! Endianness of header */

-            /* TODO: Add checks for fuse_session_exited */

-            struct fuse_bufvec bufv = { .buf[0] = fbuf, .count = 1 };

-            fuse_session_process_buf_int(se, &bufv, &ch);

+                /* TODO: Add checks for fuse_session_exited */

+                bufv.buf[0] = fbuf;

+                bufv.count = 1;

+                pbufv = &buf;;

+            }

+            pbufv->idx = 0;

+            pbufv->off = 0;

+            fuse_session_process_buf_int(se, pbufv, &ch);

+

+            if (allocated_bufv) {

+                free(pbufv);

+            }

             if (!qi->reply_sent) {

                 fuse_log(FUSE_LOG_DEBUG, "%s: elem %d no reply sent\n",

@@ -516,6 +582,7 @@ static void *fv_queue_thread(void *opaque)

             elem = NULL;

         }

     }

+out:

     pthread_mutex_destroy(&ch.lock);

     free(fbuf.mem);

-- 

1.8.3.1