From f6c65bfb93fd90f69a11fd1db1e7b2cebb056b01 Mon Sep 17 00:00:00 2001 From: Vincenzo Maffione Date: Thu, 6 Feb 2014 17:02:20 +0100 Subject: net: add offloading support to netmap backend Whit this patch, the netmap backend supports TSO/UFO/CSUM offloadings, and accepts the virtio-net header, similarly to what happens with TAP. The offloading callbacks in the NetClientInfo interface have been implemented. Signed-off-by: Vincenzo Maffione Signed-off-by: Stefan Hajnoczi --- net/netmap.c | 68 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 67 insertions(+), 1 deletion(-) (limited to 'net/netmap.c') diff --git a/net/netmap.c b/net/netmap.c index 0ccc4976b5..73f6d7acf3 100644 --- a/net/netmap.c +++ b/net/netmap.c @@ -31,6 +31,7 @@ #include #include "net/net.h" +#include "net/tap.h" #include "clients.h" #include "sysemu/sysemu.h" #include "qemu/error-report.h" @@ -54,6 +55,7 @@ typedef struct NetmapState { bool read_poll; bool write_poll; struct iovec iov[IOV_MAX]; + int vnet_hdr_len; /* Current virtio-net header length. */ } NetmapState; #define D(format, ...) \ @@ -274,7 +276,7 @@ static ssize_t netmap_receive_iov(NetClientState *nc, return iov_size(iov, iovcnt); } - i = ring->cur; + last = i = ring->cur; avail = ring->avail; if (avail < iovcnt) { @@ -394,6 +396,63 @@ static void netmap_cleanup(NetClientState *nc) s->me.fd = -1; } +/* Offloading manipulation support callbacks. */ +static bool netmap_has_ufo(NetClientState *nc) +{ + return true; +} + +static bool netmap_has_vnet_hdr(NetClientState *nc) +{ + return true; +} + +static bool netmap_has_vnet_hdr_len(NetClientState *nc, int len) +{ + return len == 0 || len == sizeof(struct virtio_net_hdr) || + len == sizeof(struct virtio_net_hdr_mrg_rxbuf); +} + +static void netmap_using_vnet_hdr(NetClientState *nc, bool enable) +{ +} + +static void netmap_set_vnet_hdr_len(NetClientState *nc, int len) +{ + NetmapState *s = DO_UPCAST(NetmapState, nc, nc); + int err; + struct nmreq req; + + /* Issue a NETMAP_BDG_VNET_HDR command to change the virtio-net header + * length for the netmap adapter associated to 'me->ifname'. + */ + memset(&req, 0, sizeof(req)); + pstrcpy(req.nr_name, sizeof(req.nr_name), s->me.ifname); + req.nr_version = NETMAP_API; + req.nr_cmd = NETMAP_BDG_VNET_HDR; + req.nr_arg1 = len; + err = ioctl(s->me.fd, NIOCREGIF, &req); + if (err) { + error_report("Unable to execute NETMAP_BDG_VNET_HDR on %s: %s", + s->me.ifname, strerror(errno)); + } else { + /* Keep track of the current length. */ + s->vnet_hdr_len = len; + } +} + +static void netmap_set_offload(NetClientState *nc, int csum, int tso4, int tso6, + int ecn, int ufo) +{ + NetmapState *s = DO_UPCAST(NetmapState, nc, nc); + + /* Setting a virtio-net header length greater than zero automatically + * enables the offloadings. + */ + if (!s->vnet_hdr_len) { + netmap_set_vnet_hdr_len(nc, sizeof(struct virtio_net_hdr)); + } +} /* NetClientInfo methods */ static NetClientInfo net_netmap_info = { @@ -403,6 +462,12 @@ static NetClientInfo net_netmap_info = { .receive_iov = netmap_receive_iov, .poll = netmap_poll, .cleanup = netmap_cleanup, + .has_ufo = netmap_has_ufo, + .has_vnet_hdr = netmap_has_vnet_hdr, + .has_vnet_hdr_len = netmap_has_vnet_hdr_len, + .using_vnet_hdr = netmap_using_vnet_hdr, + .set_offload = netmap_set_offload, + .set_vnet_hdr_len = netmap_set_vnet_hdr_len, }; /* The exported init function @@ -428,6 +493,7 @@ int net_init_netmap(const NetClientOptions *opts, nc = qemu_new_net_client(&net_netmap_info, peer, "netmap", name); s = DO_UPCAST(NetmapState, nc, nc); s->me = me; + s->vnet_hdr_len = 0; netmap_read_poll(s, true); /* Initially only poll for reads. */ return 0; -- cgit 1.4.1 From 0a985b37272b563b1f8414431c6064eb1aa0c97b Mon Sep 17 00:00:00 2001 From: Vincenzo Maffione Date: Thu, 20 Feb 2014 15:40:43 +0100 Subject: net: Disable netmap backend when not supported This patch fixes configure so that the netmap backend is not compiled in if the host doesn't support an API version >= 11. A version upper bound (15) has been added so that the netmap API can be extended with some minor features without requiring QEMU code modifications. Moreover, some changes have been done to net/netmap.c in order to reflect the current netmap API/ABI (11). The NETMAP_WITH_LIBS macro makes possible to include some utilities (e.g. netmap ring macros, D(), RD() and other high level functions) through the netmap headers. In this way we get rid of the D and RD macro definitions in the QEMU code, and we open the way for further code simplifications that will be introduced by future patches. Signed-off-by: Vincenzo Maffione Signed-off-by: Stefan Hajnoczi --- configure | 10 +++++++++- net/netmap.c | 55 +++++++++++++------------------------------------------ 2 files changed, 22 insertions(+), 43 deletions(-) (limited to 'net/netmap.c') diff --git a/configure b/configure index 00f90702bc..9ad3ff3aeb 100755 --- a/configure +++ b/configure @@ -2215,13 +2215,21 @@ EOF fi ########################################## -# netmap headers probe +# netmap support probe +# Apart from looking for netmap headers, we make sure that the host API version +# supports the netmap backend (>=11). The upper bound (15) is meant to simulate +# a minor/major version number. Minor new features will be marked with values up +# to 15, and if something happens that requires a change to the backend we will +# move above 15, submit the backend fixes and modify this two bounds. if test "$netmap" != "no" ; then cat > $TMPC << EOF #include #include #include #include +#if (NETMAP_API < 11) || (NETMAP_API > 15) +#error +#endif int main(void) { return 0; } EOF if compile_prog "" "" ; then diff --git a/net/netmap.c b/net/netmap.c index 73f6d7acf3..8213304a5b 100644 --- a/net/netmap.c +++ b/net/netmap.c @@ -27,6 +27,8 @@ #include #include #include +#include +#define NETMAP_WITH_LIBS #include #include @@ -58,31 +60,6 @@ typedef struct NetmapState { int vnet_hdr_len; /* Current virtio-net header length. */ } NetmapState; -#define D(format, ...) \ - do { \ - struct timeval __xxts; \ - gettimeofday(&__xxts, NULL); \ - printf("%03d.%06d %s [%d] " format "\n", \ - (int)__xxts.tv_sec % 1000, (int)__xxts.tv_usec, \ - __func__, __LINE__, ##__VA_ARGS__); \ - } while (0) - -/* Rate limited version of "D", lps indicates how many per second */ -#define RD(lps, format, ...) \ - do { \ - static int t0, __cnt; \ - struct timeval __xxts; \ - gettimeofday(&__xxts, NULL); \ - if (t0 != __xxts.tv_sec) { \ - t0 = __xxts.tv_sec; \ - __cnt = 0; \ - } \ - if (__cnt++ < lps) { \ - D(format, ##__VA_ARGS__); \ - } \ - } while (0) - - #ifndef __FreeBSD__ #define pkt_copy bcopy #else @@ -239,7 +216,7 @@ static ssize_t netmap_receive(NetClientState *nc, return size; } - if (ring->avail == 0) { + if (nm_ring_empty(ring)) { /* No available slots in the netmap TX ring. */ netmap_write_poll(s, true); return 0; @@ -252,8 +229,7 @@ static ssize_t netmap_receive(NetClientState *nc, ring->slot[i].len = size; ring->slot[i].flags = 0; pkt_copy(buf, dst, size); - ring->cur = NETMAP_RING_NEXT(ring, i); - ring->avail--; + ring->cur = ring->head = nm_ring_next(ring, i); ioctl(s->me.fd, NIOCTXSYNC, NULL); return size; @@ -269,7 +245,6 @@ static ssize_t netmap_receive_iov(NetClientState *nc, uint8_t *dst; int j; uint32_t i; - uint32_t avail; if (unlikely(!ring)) { /* Drop the packet. */ @@ -277,9 +252,8 @@ static ssize_t netmap_receive_iov(NetClientState *nc, } last = i = ring->cur; - avail = ring->avail; - if (avail < iovcnt) { + if (nm_ring_space(ring) < iovcnt) { /* Not enough netmap slots. */ netmap_write_poll(s, true); return 0; @@ -295,7 +269,7 @@ static ssize_t netmap_receive_iov(NetClientState *nc, while (iov_frag_size) { nm_frag_size = MIN(iov_frag_size, ring->nr_buf_size); - if (unlikely(avail == 0)) { + if (unlikely(nm_ring_empty(ring))) { /* We run out of netmap slots while splitting the iovec fragments. */ netmap_write_poll(s, true); @@ -310,8 +284,7 @@ static ssize_t netmap_receive_iov(NetClientState *nc, pkt_copy(iov[j].iov_base + offset, dst, nm_frag_size); last = i; - i = NETMAP_RING_NEXT(ring, i); - avail--; + i = nm_ring_next(ring, i); offset += nm_frag_size; iov_frag_size -= nm_frag_size; @@ -320,9 +293,8 @@ static ssize_t netmap_receive_iov(NetClientState *nc, /* The last slot must not have NS_MOREFRAG set. */ ring->slot[last].flags &= ~NS_MOREFRAG; - /* Now update ring->cur and ring->avail. */ - ring->cur = i; - ring->avail = avail; + /* Now update ring->cur and ring->head. */ + ring->cur = ring->head = i; ioctl(s->me.fd, NIOCTXSYNC, NULL); @@ -345,7 +317,7 @@ static void netmap_send(void *opaque) /* Keep sending while there are available packets into the netmap RX ring and the forwarding path towards the peer is open. */ - while (ring->avail > 0 && qemu_can_send_packet(&s->nc)) { + while (!nm_ring_empty(ring) && qemu_can_send_packet(&s->nc)) { uint32_t i; uint32_t idx; bool morefrag; @@ -360,11 +332,10 @@ static void netmap_send(void *opaque) s->iov[iovcnt].iov_len = ring->slot[i].len; iovcnt++; - ring->cur = NETMAP_RING_NEXT(ring, i); - ring->avail--; - } while (ring->avail && morefrag); + ring->cur = ring->head = nm_ring_next(ring, i); + } while (!nm_ring_empty(ring) && morefrag); - if (unlikely(!ring->avail && morefrag)) { + if (unlikely(nm_ring_empty(ring) && morefrag)) { RD(5, "[netmap_send] ran out of slots, with a pending" "incomplete packet\n"); } -- cgit 1.4.1