Merge remote-tracking branch 'remotes/gkurz/tags/9p-next-2020-05-26' into staging
- fix build with musl libc
- fix potential deadlock of QEMU main event loop (cannot be hit with linux
client)
- revert 9pfs reply truncation (LP 1877688)
- xen backend waits for client to free space on the reply ring instead of
truncating or disconnecting
# gpg: Signature made Tue 26 May 2020 10:36:23 BST
# gpg: using RSA key B4828BAF943140CEF2A3491071D4D5E5822F73D6
# gpg: Good signature from "Greg Kurz <groug@kaod.org>" [full]
# gpg: aka "Gregory Kurz <gregory.kurz@free.fr>" [full]
# gpg: aka "[jpeg image of size 3330]" [full]
# Primary key fingerprint: B482 8BAF 9431 40CE F2A3 4910 71D4 D5E5 822F 73D6
* remotes/gkurz/tags/9p-next-2020-05-26:
xen/9pfs: increase max ring order to 9
xen/9pfs: yield when there isn't enough room on the ring
Revert "9p: init_in_iov_from_pdu can truncate the size"
9p: Lock directory streams with a CoMutex
9pfs: include linux/limits.h for XATTR_SIZE_MAX
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
diff --git a/hw/9pfs/9p.c b/hw/9pfs/9p.c
index a2a14b5..45a788f 100644
--- a/hw/9pfs/9p.c
+++ b/hw/9pfs/9p.c
@@ -28,6 +28,7 @@
#include "sysemu/qtest.h"
#include "qemu/xxhash.h"
#include <math.h>
+#include <linux/limits.h>
int open_fd_hw;
int total_open_fd;
@@ -2102,29 +2103,22 @@
* with qemu_iovec_destroy().
*/
static void v9fs_init_qiov_from_pdu(QEMUIOVector *qiov, V9fsPDU *pdu,
- size_t skip, size_t *size,
+ size_t skip, size_t size,
bool is_write)
{
QEMUIOVector elem;
struct iovec *iov;
unsigned int niov;
- size_t alloc_size = *size + skip;
if (is_write) {
- pdu->s->transport->init_out_iov_from_pdu(pdu, &iov, &niov, alloc_size);
+ pdu->s->transport->init_out_iov_from_pdu(pdu, &iov, &niov, size + skip);
} else {
- pdu->s->transport->init_in_iov_from_pdu(pdu, &iov, &niov, &alloc_size);
- }
-
- if (alloc_size < skip) {
- *size = 0;
- } else {
- *size = alloc_size - skip;
+ pdu->s->transport->init_in_iov_from_pdu(pdu, &iov, &niov, size + skip);
}
qemu_iovec_init_external(&elem, iov, niov);
qemu_iovec_init(qiov, niov);
- qemu_iovec_concat(qiov, &elem, skip, *size);
+ qemu_iovec_concat(qiov, &elem, skip, size);
}
static int v9fs_xattr_read(V9fsState *s, V9fsPDU *pdu, V9fsFidState *fidp,
@@ -2132,14 +2126,15 @@
{
ssize_t err;
size_t offset = 7;
- size_t read_count;
+ uint64_t read_count;
QEMUIOVector qiov_full;
if (fidp->fs.xattr.len < off) {
read_count = 0;
- } else if (fidp->fs.xattr.len - off < max_count) {
- read_count = fidp->fs.xattr.len - off;
} else {
+ read_count = fidp->fs.xattr.len - off;
+ }
+ if (read_count > max_count) {
read_count = max_count;
}
err = pdu_marshal(pdu, offset, "d", read_count);
@@ -2148,7 +2143,7 @@
}
offset += err;
- v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset, &read_count, false);
+ v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset, read_count, false);
err = v9fs_pack(qiov_full.iov, qiov_full.niov, 0,
((char *)fidp->fs.xattr.value) + off,
read_count);
@@ -2277,11 +2272,9 @@
QEMUIOVector qiov_full;
QEMUIOVector qiov;
int32_t len;
- size_t size = max_count;
- v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset + 4, &size, false);
+ v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset + 4, max_count, false);
qemu_iovec_init(&qiov, qiov_full.niov);
- max_count = size;
do {
qemu_iovec_reset(&qiov);
qemu_iovec_concat(&qiov, &qiov_full, count, qiov_full.size - count);
@@ -2532,7 +2525,6 @@
int32_t len = 0;
int32_t total = 0;
size_t offset = 7;
- size_t size;
V9fsFidState *fidp;
V9fsPDU *pdu = opaque;
V9fsState *s = pdu->s;
@@ -2545,9 +2537,7 @@
return;
}
offset += err;
- size = count;
- v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset, &size, true);
- count = size;
+ v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset, count, true);
trace_v9fs_write(pdu->tag, pdu->id, fid, off, count, qiov_full.niov);
fidp = get_fid(pdu, fid);
diff --git a/hw/9pfs/9p.h b/hw/9pfs/9p.h
index dd1c6cb..ee22716 100644
--- a/hw/9pfs/9p.h
+++ b/hw/9pfs/9p.h
@@ -197,22 +197,22 @@
typedef struct V9fsDir {
DIR *stream;
- QemuMutex readdir_mutex;
+ CoMutex readdir_mutex;
} V9fsDir;
static inline void v9fs_readdir_lock(V9fsDir *dir)
{
- qemu_mutex_lock(&dir->readdir_mutex);
+ qemu_co_mutex_lock(&dir->readdir_mutex);
}
static inline void v9fs_readdir_unlock(V9fsDir *dir)
{
- qemu_mutex_unlock(&dir->readdir_mutex);
+ qemu_co_mutex_unlock(&dir->readdir_mutex);
}
static inline void v9fs_readdir_init(V9fsDir *dir)
{
- qemu_mutex_init(&dir->readdir_mutex);
+ qemu_co_mutex_init(&dir->readdir_mutex);
}
/*
@@ -436,7 +436,7 @@
ssize_t (*pdu_vunmarshal)(V9fsPDU *pdu, size_t offset, const char *fmt,
va_list ap);
void (*init_in_iov_from_pdu)(V9fsPDU *pdu, struct iovec **piov,
- unsigned int *pniov, size_t *size);
+ unsigned int *pniov, size_t size);
void (*init_out_iov_from_pdu)(V9fsPDU *pdu, struct iovec **piov,
unsigned int *pniov, size_t size);
void (*push_and_notify)(V9fsPDU *pdu);
diff --git a/hw/9pfs/virtio-9p-device.c b/hw/9pfs/virtio-9p-device.c
index e5b4497..36f3aa9 100644
--- a/hw/9pfs/virtio-9p-device.c
+++ b/hw/9pfs/virtio-9p-device.c
@@ -147,22 +147,19 @@
}
static void virtio_init_in_iov_from_pdu(V9fsPDU *pdu, struct iovec **piov,
- unsigned int *pniov, size_t *size)
+ unsigned int *pniov, size_t size)
{
V9fsState *s = pdu->s;
V9fsVirtioState *v = container_of(s, V9fsVirtioState, state);
VirtQueueElement *elem = v->elems[pdu->idx];
size_t buf_size = iov_size(elem->in_sg, elem->in_num);
- if (buf_size < P9_IOHDRSZ) {
+ if (buf_size < size) {
VirtIODevice *vdev = VIRTIO_DEVICE(v);
virtio_error(vdev,
- "VirtFS reply type %d needs %zu bytes, buffer has %zu, less than minimum",
- pdu->id + 1, *size, buf_size);
- }
- if (buf_size < *size) {
- *size = buf_size;
+ "VirtFS reply type %d needs %zu bytes, buffer has %zu",
+ pdu->id + 1, size, buf_size);
}
*piov = elem->in_sg;
diff --git a/hw/9pfs/xen-9p-backend.c b/hw/9pfs/xen-9p-backend.c
index f04caab..a969fcc 100644
--- a/hw/9pfs/xen-9p-backend.c
+++ b/hw/9pfs/xen-9p-backend.c
@@ -21,7 +21,7 @@
#define VERSIONS "1"
#define MAX_RINGS 8
-#define MAX_RING_ORDER 8
+#define MAX_RING_ORDER 9
typedef struct Xen9pfsRing {
struct Xen9pfsDev *priv;
@@ -37,6 +37,7 @@
struct iovec *sg;
QEMUBH *bh;
+ Coroutine *co;
/* local copies, so that we can read/write PDU data directly from
* the ring */
@@ -188,7 +189,7 @@
static void xen_9pfs_init_in_iov_from_pdu(V9fsPDU *pdu,
struct iovec **piov,
unsigned int *pniov,
- size_t *size)
+ size_t size)
{
Xen9pfsDev *xen_9pfs = container_of(pdu->s, Xen9pfsDev, state);
Xen9pfsRing *ring = &xen_9pfs->rings[pdu->tag % xen_9pfs->num_rings];
@@ -198,19 +199,20 @@
g_free(ring->sg);
ring->sg = g_new0(struct iovec, 2);
- xen_9pfs_in_sg(ring, ring->sg, &num, pdu->idx, *size);
+ ring->co = qemu_coroutine_self();
+ /* make sure other threads see ring->co changes before continuing */
+ smp_wmb();
+again:
+ xen_9pfs_in_sg(ring, ring->sg, &num, pdu->idx, size);
buf_size = iov_size(ring->sg, num);
- if (buf_size < P9_IOHDRSZ) {
- xen_pv_printf(&xen_9pfs->xendev, 0, "Xen 9pfs reply type %d needs "
- "%zu bytes, buffer has %zu, less than minimum\n",
- pdu->id + 1, *size, buf_size);
- xen_be_set_state(&xen_9pfs->xendev, XenbusStateClosing);
- xen_9pfs_disconnect(&xen_9pfs->xendev);
+ if (buf_size < size) {
+ qemu_coroutine_yield();
+ goto again;
}
- if (buf_size < *size) {
- *size = buf_size;
- }
+ ring->co = NULL;
+ /* make sure other threads see ring->co changes before continuing */
+ smp_wmb();
*piov = ring->sg;
*pniov = num;
@@ -295,6 +297,20 @@
static void xen_9pfs_bh(void *opaque)
{
Xen9pfsRing *ring = opaque;
+ bool wait;
+
+again:
+ wait = ring->co != NULL && qemu_coroutine_entered(ring->co);
+ /* paired with the smb_wmb barriers in xen_9pfs_init_in_iov_from_pdu */
+ smp_rmb();
+ if (wait) {
+ cpu_relax();
+ goto again;
+ }
+
+ if (ring->co != NULL) {
+ qemu_coroutine_enter_if_inactive(ring->co);
+ }
xen_9pfs_receive(ring);
}
