From 146c8a77d27bcbd7722120f70f51e3b287205d0a Mon Sep 17 00:00:00 2001 From: Paul Durrant Date: Wed, 16 Oct 2013 17:50:28 +0100 Subject: xen-netback: add support for IPv6 checksum offload to guest Check xenstore flag feature-ipv6-csum-offload to determine if a guest is happy to accept IPv6 packets with only partial checksum. Signed-off-by: Paul Durrant Cc: Wei Liu Cc: David Vrabel Cc: Ian Campbell Signed-off-by: David S. Miller --- include/xen/interface/io/netif.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/xen/interface') diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h index eb262e3324d2..c9e81849fcd7 100644 --- a/include/xen/interface/io/netif.h +++ b/include/xen/interface/io/netif.h @@ -50,6 +50,13 @@ * node as before. */ +/* + * "feature-no-csum-offload" should be used to turn IPv4 TCP/UDP checksum + * offload off or on. If it is missing then the feature is assumed to be on. + * "feature-ipv6-csum-offload" should be used to turn IPv6 TCP/UDP checksum + * offload on or off. If it is missing then the feature is assumed to be off. + */ + /* * This is the 'wire' format for packets: * Request 1: xen_netif_tx_request -- XEN_NETTXF_* (any flags) -- cgit v1.2.3 From a94685876859be30446357db6d6c4a9c951305b4 Mon Sep 17 00:00:00 2001 From: Paul Durrant Date: Wed, 16 Oct 2013 17:50:31 +0100 Subject: xen-netback: handle IPv6 TCP GSO packets from the guest This patch adds a xenstore feature flag, festure-gso-tcpv6, to advertise that netback can handle IPv6 TCP GSO packets. It creates SKB_GSO_TCPV6 skbs if the frontend passes an extra segment with the new type XEN_NETIF_GSO_TYPE_TCPV6 added to netif.h. Signed-off-by: Paul Durrant Cc: Wei Liu Cc: David Vrabel Acked-by: Ian Campbell Signed-off-by: David S. Miller --- drivers/net/xen-netback/netback.c | 11 ++++++++--- drivers/net/xen-netback/xenbus.c | 7 +++++++ include/xen/interface/io/netif.h | 10 +++++++++- 3 files changed, 24 insertions(+), 4 deletions(-) (limited to 'include/xen/interface') diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 4271f8d1da7a..0e327d46a139 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1098,15 +1098,20 @@ static int xenvif_set_skb_gso(struct xenvif *vif, return -EINVAL; } - /* Currently only TCPv4 S.O. is supported. */ - if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) { + switch (gso->u.gso.type) { + case XEN_NETIF_GSO_TYPE_TCPV4: + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + break; + case XEN_NETIF_GSO_TYPE_TCPV6: + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + break; + default: netdev_err(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type); xenvif_fatal_tx_err(vif); return -EINVAL; } skb_shinfo(skb)->gso_size = gso->u.gso.size; - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; /* Header must be checked, and gso_segs computed. */ skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 108e7523017a..02cb00bebdc9 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -105,6 +105,13 @@ static int netback_probe(struct xenbus_device *dev, goto abort_transaction; } + err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv6", + "%d", sg); + if (err) { + message = "writing feature-gso-tcpv6"; + goto abort_transaction; + } + /* We support partial checksum setup for IPv6 packets */ err = xenbus_printf(xbt, dev->nodename, "feature-ipv6-csum-offload", diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h index c9e81849fcd7..5e766ebe77f6 100644 --- a/include/xen/interface/io/netif.h +++ b/include/xen/interface/io/netif.h @@ -57,6 +57,13 @@ * offload on or off. If it is missing then the feature is assumed to be off. */ +/* + * "feature-gso-tcpv4" and "feature-gso-tcpv6" advertise the capability to + * handle large TCP packets (in IPv4 or IPv6 form respectively). Neither + * frontends nor backends are assumed to be capable unless the flags are + * present. + */ + /* * This is the 'wire' format for packets: * Request 1: xen_netif_tx_request -- XEN_NETTXF_* (any flags) @@ -102,8 +109,9 @@ struct xen_netif_tx_request { #define _XEN_NETIF_EXTRA_FLAG_MORE (0) #define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE) -/* GSO types - only TCPv4 currently supported. */ +/* GSO types */ #define XEN_NETIF_GSO_TYPE_TCPV4 (1) +#define XEN_NETIF_GSO_TYPE_TCPV6 (2) /* * This structure needs to fit within both netif_tx_request and -- cgit v1.2.3 From 82cada22a0bbec6a7afb573ef5fb6c512aaa2739 Mon Sep 17 00:00:00 2001 From: Paul Durrant Date: Wed, 16 Oct 2013 17:50:32 +0100 Subject: xen-netback: enable IPv6 TCP GSO to the guest This patch adds code to handle SKB_GSO_TCPV6 skbs and construct appropriate extra or prefix segments to pass the large packet to the frontend. New xenstore flags, feature-gso-tcpv6 and feature-gso-tcpv6-prefix, are sampled to determine if the frontend is capable of handling such packets. Signed-off-by: Paul Durrant Cc: Wei Liu Cc: David Vrabel Cc: Ian Campbell Signed-off-by: David S. Miller --- drivers/net/xen-netback/common.h | 9 +++++-- drivers/net/xen-netback/interface.c | 6 +++-- drivers/net/xen-netback/netback.c | 48 +++++++++++++++++++++++++++++-------- drivers/net/xen-netback/xenbus.c | 29 ++++++++++++++++++++-- include/xen/interface/io/netif.h | 1 + 5 files changed, 77 insertions(+), 16 deletions(-) (limited to 'include/xen/interface') diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index b4a9a3c844b2..55b8dec86233 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -87,9 +87,13 @@ struct pending_tx_info { struct xenvif_rx_meta { int id; int size; + int gso_type; int gso_size; }; +#define GSO_BIT(type) \ + (1 << XEN_NETIF_GSO_TYPE_ ## type) + /* Discriminate from any valid pending_idx value. */ #define INVALID_PENDING_IDX 0xFFFF @@ -150,9 +154,10 @@ struct xenvif { u8 fe_dev_addr[6]; /* Frontend feature information. */ + int gso_mask; + int gso_prefix_mask; + u8 can_sg:1; - u8 gso:1; - u8 gso_prefix:1; u8 ip_csum:1; u8 ipv6_csum:1; diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index cb0d8ea3d9f2..e4aa26748f80 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -214,8 +214,10 @@ static netdev_features_t xenvif_fix_features(struct net_device *dev, if (!vif->can_sg) features &= ~NETIF_F_SG; - if (!vif->gso && !vif->gso_prefix) + if (~(vif->gso_mask | vif->gso_prefix_mask) & GSO_BIT(TCPV4)) features &= ~NETIF_F_TSO; + if (~(vif->gso_mask | vif->gso_prefix_mask) & GSO_BIT(TCPV6)) + features &= ~NETIF_F_TSO6; if (!vif->ip_csum) features &= ~NETIF_F_IP_CSUM; if (!vif->ipv6_csum) @@ -320,7 +322,7 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, dev->netdev_ops = &xenvif_netdev_ops; dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_TSO; + NETIF_F_TSO | NETIF_F_TSO6; dev->features = dev->hw_features | NETIF_F_RXCSUM; SET_ETHTOOL_OPS(dev, &xenvif_ethtool_ops); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 0e327d46a139..828fdab4f1a4 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -142,7 +142,7 @@ static int max_required_rx_slots(struct xenvif *vif) int max = DIV_ROUND_UP(vif->dev->mtu, PAGE_SIZE); /* XXX FIXME: RX path dependent on MAX_SKB_FRAGS */ - if (vif->can_sg || vif->gso || vif->gso_prefix) + if (vif->can_sg || vif->gso_mask || vif->gso_prefix_mask) max += MAX_SKB_FRAGS + 1; /* extra_info + frags */ return max; @@ -314,6 +314,7 @@ static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif *vif, req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++); meta = npo->meta + npo->meta_prod++; + meta->gso_type = XEN_NETIF_GSO_TYPE_NONE; meta->gso_size = 0; meta->size = 0; meta->id = req->id; @@ -336,6 +337,7 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, struct gnttab_copy *copy_gop; struct xenvif_rx_meta *meta; unsigned long bytes; + int gso_type; /* Data must not cross a page boundary. */ BUG_ON(size + offset > PAGE_SIZE<gso_size && !vif->gso_prefix) + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) + gso_type = XEN_NETIF_GSO_TYPE_TCPV4; + else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) + gso_type = XEN_NETIF_GSO_TYPE_TCPV6; + else + gso_type = XEN_NETIF_GSO_TYPE_NONE; + + if (*head && ((1 << gso_type) & vif->gso_mask)) vif->rx.req_cons++; *head = 0; /* There must be something in this buffer now. */ @@ -425,14 +434,28 @@ static int xenvif_gop_skb(struct sk_buff *skb, unsigned char *data; int head = 1; int old_meta_prod; + int gso_type; + int gso_size; old_meta_prod = npo->meta_prod; + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { + gso_type = XEN_NETIF_GSO_TYPE_TCPV4; + gso_size = skb_shinfo(skb)->gso_size; + } else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) { + gso_type = XEN_NETIF_GSO_TYPE_TCPV6; + gso_size = skb_shinfo(skb)->gso_size; + } else { + gso_type = XEN_NETIF_GSO_TYPE_NONE; + gso_size = 0; + } + /* Set up a GSO prefix descriptor, if necessary */ - if (skb_shinfo(skb)->gso_size && vif->gso_prefix) { + if ((1 << skb_shinfo(skb)->gso_type) & vif->gso_prefix_mask) { req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++); meta = npo->meta + npo->meta_prod++; - meta->gso_size = skb_shinfo(skb)->gso_size; + meta->gso_type = gso_type; + meta->gso_size = gso_size; meta->size = 0; meta->id = req->id; } @@ -440,10 +463,13 @@ static int xenvif_gop_skb(struct sk_buff *skb, req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++); meta = npo->meta + npo->meta_prod++; - if (!vif->gso_prefix) - meta->gso_size = skb_shinfo(skb)->gso_size; - else + if ((1 << gso_type) & vif->gso_mask) { + meta->gso_type = gso_type; + meta->gso_size = gso_size; + } else { + meta->gso_type = XEN_NETIF_GSO_TYPE_NONE; meta->gso_size = 0; + } meta->size = 0; meta->id = req->id; @@ -589,7 +615,8 @@ void xenvif_rx_action(struct xenvif *vif) vif = netdev_priv(skb->dev); - if (vif->meta[npo.meta_cons].gso_size && vif->gso_prefix) { + if ((1 << vif->meta[npo.meta_cons].gso_type) & + vif->gso_prefix_mask) { resp = RING_GET_RESPONSE(&vif->rx, vif->rx.rsp_prod_pvt++); @@ -626,7 +653,8 @@ void xenvif_rx_action(struct xenvif *vif) vif->meta[npo.meta_cons].size, flags); - if (vif->meta[npo.meta_cons].gso_size && !vif->gso_prefix) { + if ((1 << vif->meta[npo.meta_cons].gso_type) & + vif->gso_mask) { struct xen_netif_extra_info *gso = (struct xen_netif_extra_info *) RING_GET_RESPONSE(&vif->rx, @@ -634,8 +662,8 @@ void xenvif_rx_action(struct xenvif *vif) resp->flags |= XEN_NETRXF_extra_info; + gso->u.gso.type = vif->meta[npo.meta_cons].gso_type; gso->u.gso.size = vif->meta[npo.meta_cons].gso_size; - gso->u.gso.type = XEN_NETIF_GSO_TYPE_TCPV4; gso->u.gso.pad = 0; gso->u.gso.features = 0; diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 02cb00bebdc9..f0358992b04f 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -577,15 +577,40 @@ static int connect_rings(struct backend_info *be) val = 0; vif->can_sg = !!val; + vif->gso_mask = 0; + vif->gso_prefix_mask = 0; + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4", "%d", &val) < 0) val = 0; - vif->gso = !!val; + if (val) + vif->gso_mask |= GSO_BIT(TCPV4); if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4-prefix", "%d", &val) < 0) val = 0; - vif->gso_prefix = !!val; + if (val) + vif->gso_prefix_mask |= GSO_BIT(TCPV4); + + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6", + "%d", &val) < 0) + val = 0; + if (val) + vif->gso_mask |= GSO_BIT(TCPV6); + + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6-prefix", + "%d", &val) < 0) + val = 0; + if (val) + vif->gso_prefix_mask |= GSO_BIT(TCPV6); + + if (vif->gso_mask & vif->gso_prefix_mask) { + xenbus_dev_fatal(dev, err, + "%s: gso and gso prefix flags are not " + "mutually exclusive", + dev->otherend); + return -EOPNOTSUPP; + } if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-no-csum-offload", "%d", &val) < 0) diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h index 5e766ebe77f6..c50061db6098 100644 --- a/include/xen/interface/io/netif.h +++ b/include/xen/interface/io/netif.h @@ -110,6 +110,7 @@ struct xen_netif_tx_request { #define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE) /* GSO types */ +#define XEN_NETIF_GSO_TYPE_NONE (0) #define XEN_NETIF_GSO_TYPE_TCPV4 (1) #define XEN_NETIF_GSO_TYPE_TCPV6 (2) -- cgit v1.2.3 From 8deb3eb1461e4cb136c88d03ec5a6729ccf2f933 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Fri, 25 Oct 2013 16:26:02 -0400 Subject: xen/mcfg: Call PHYSDEVOP_pci_mmcfg_reserved for MCFG areas. The PCI MMCONFIG area is usually reserved via the E820 so the Xen hypervisor is aware of these regions. But they can also be enumerated in the ACPI DSDT which means the hypervisor won't know of them until the initial domain informs it of via PHYSDEVOP_pci_mmcfg_reserved. This is what this patch does for all of the MCFG regions that the initial domain is aware of (E820 enumerated and ACPI). Reported-by: Santosh Jodh CC: Jan Beulich Reviewed-by: Boris Ostrovsky CC: David Vrabel CC: Mukesh Rathor Signed-off-by: Konrad Rzeszutek Wilk [v1: Redid it a bit] [v2: Dropped the P2M 1-1 setting] [v3: Check for Xen in-case we are running under baremetal] [v4: Wrap with CONFIG_PCI_MMCONFIG] --- drivers/xen/pci.c | 47 +++++++++++++++++++++++++++++++++++++++++ include/xen/interface/physdev.h | 11 ++++++++++ 2 files changed, 58 insertions(+) (limited to 'include/xen/interface') diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c index 18fff88254eb..d15f6e80479f 100644 --- a/drivers/xen/pci.c +++ b/drivers/xen/pci.c @@ -26,6 +26,7 @@ #include #include #include "../pci/pci.h" +#include static bool __read_mostly pci_seg_supported = true; @@ -192,3 +193,49 @@ static int __init register_xen_pci_notifier(void) } arch_initcall(register_xen_pci_notifier); + +#ifdef CONFIG_PCI_MMCONFIG +static int __init xen_mcfg_late(void) +{ + struct pci_mmcfg_region *cfg; + int rc; + + if (!xen_initial_domain()) + return 0; + + if ((pci_probe & PCI_PROBE_MMCONF) == 0) + return 0; + + if (list_empty(&pci_mmcfg_list)) + return 0; + + /* Check whether they are in the right area. */ + list_for_each_entry(cfg, &pci_mmcfg_list, list) { + struct physdev_pci_mmcfg_reserved r; + + r.address = cfg->address; + r.segment = cfg->segment; + r.start_bus = cfg->start_bus; + r.end_bus = cfg->end_bus; + r.flags = XEN_PCI_MMCFG_RESERVED; + + rc = HYPERVISOR_physdev_op(PHYSDEVOP_pci_mmcfg_reserved, &r); + switch (rc) { + case 0: + case -ENOSYS: + continue; + + default: + pr_warn("Failed to report MMCONFIG reservation" + " state for %s to hypervisor" + " (%d)\n", + cfg->name, rc); + } + } + return 0; +} +/* + * Needs to be done after acpi_init which are subsys_initcall. + */ +subsys_initcall_sync(xen_mcfg_late); +#endif diff --git a/include/xen/interface/physdev.h b/include/xen/interface/physdev.h index 7000bb1f6e96..42721d13a106 100644 --- a/include/xen/interface/physdev.h +++ b/include/xen/interface/physdev.h @@ -231,6 +231,17 @@ struct physdev_get_free_pirq { #define XEN_PCI_DEV_VIRTFN 0x2 #define XEN_PCI_DEV_PXM 0x4 +#define XEN_PCI_MMCFG_RESERVED 0x1 + +#define PHYSDEVOP_pci_mmcfg_reserved 24 +struct physdev_pci_mmcfg_reserved { + uint64_t address; + uint16_t segment; + uint8_t start_bus; + uint8_t end_bus; + uint32_t flags; +}; + #define PHYSDEVOP_pci_device_add 25 struct physdev_pci_device_add { /* IN */ -- cgit v1.2.3